Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1ab613e..154e2e8 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Intel network device configuration
#
@@ -33,7 +34,7 @@
to identify the adapter.
More specific information on configuring the driver is in
- <file:Documentation/networking/e100.rst>.
+ <file:Documentation/networking/device_drivers/intel/e100.rst>.
To compile this driver as a module, choose M here. The module
will be called e100.
@@ -49,7 +50,7 @@
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.rst>.
+ <file:Documentation/networking/device_drivers/intel/e1000.rst>.
To compile this driver as a module, choose M here. The module
will be called e1000.
@@ -68,6 +69,9 @@
<http://support.intel.com>
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/e1000e.rst>.
+
To compile this driver as a module, choose M here. The module
will be called e1000e.
@@ -94,7 +98,7 @@
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.rst>.
+ <file:Documentation/networking/device_drivers/intel/igb.rst>.
To compile this driver as a module, choose M here. The module
will be called igb.
@@ -130,7 +134,7 @@
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/e1000.rst>.
+ <file:Documentation/networking/device_drivers/intel/igbvf.rst>.
To compile this driver as a module, choose M here. The module
will be called igbvf.
@@ -147,7 +151,7 @@
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/ixgb.txt>.
+ <file:Documentation/networking/device_drivers/intel/ixgb.rst>.
To compile this driver as a module, choose M here. The module
will be called ixgb.
@@ -156,6 +160,7 @@
tristate "Intel(R) 10GbE PCI Express adapters support"
depends on PCI
select MDIO
+ select PHYLIB
imply PTP_1588_CLOCK
---help---
This driver supports Intel(R) 10GbE PCI Express family of
@@ -164,6 +169,9 @@
<http://support.intel.com>
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/ixgbe.rst>.
+
To compile this driver as a module, choose M here. The module
will be called ixgbe.
@@ -194,6 +202,15 @@
If unsure, say N.
+config IXGBE_IPSEC
+ bool "IPSec XFRM cryptography-offload acceleration"
+ depends on IXGBE
+ depends on XFRM_OFFLOAD
+ default y
+ select XFRM_ALGO
+ ---help---
+ Enable support for IPSec offload in ixgbe.ko
+
config IXGBEVF
tristate "Intel(R) 10GbE PCI Express Virtual Function Ethernet support"
depends on PCI_MSI
@@ -205,12 +222,21 @@
<http://support.intel.com>
More specific information on configuring the driver is in
- <file:Documentation/networking/ixgbevf.txt>.
+ <file:Documentation/networking/device_drivers/intel/ixgbevf.rst>.
To compile this driver as a module, choose M here. The module
will be called ixgbevf. MSI-X interrupt support is required
for this driver to work correctly.
+config IXGBEVF_IPSEC
+ bool "IPSec XFRM cryptography-offload acceleration"
+ depends on IXGBEVF
+ depends on XFRM_OFFLOAD
+ default y
+ select XFRM_ALGO
+ ---help---
+ Enable support for IPSec offload in ixgbevf.ko
+
config I40E
tristate "Intel(R) Ethernet Controller XL710 Family support"
imply PTP_1588_CLOCK
@@ -222,6 +248,9 @@
<http://support.intel.com>
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/i40e.rst>.
+
To compile this driver as a module, choose M here. The module
will be called i40e.
@@ -235,20 +264,30 @@
If unsure, say N.
+# this is here to allow seamless migration from I40EVF --> IAVF name
+# so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF
+config IAVF
+ tristate
config I40EVF
tristate "Intel(R) Ethernet Adaptive Virtual Function support"
+ select IAVF
depends on PCI_MSI
---help---
This driver supports virtual functions for Intel XL710,
- X710, X722, and all devices advertising support for Intel
- Ethernet Adaptive Virtual Function devices. For more
+ X710, X722, XXV710, and all devices advertising support for
+ Intel Ethernet Adaptive Virtual Function devices. For more
information on how to identify your adapter, go to the Adapter
& Driver ID Guide that can be located at:
- <http://support.intel.com>
+ <https://support.intel.com>
+
+ This driver was formerly named i40evf.
+
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/iavf.rst>.
To compile this driver as a module, choose M here. The module
- will be called i40evf. MSI-X interrupt support is required
+ will be called iavf. MSI-X interrupt support is required
for this driver to work correctly.
config ICE
@@ -262,6 +301,9 @@
<http://support.intel.com>
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/ice.rst>.
+
To compile this driver as a module, choose M here. The module
will be called ice.
@@ -277,7 +319,26 @@
<http://support.intel.com>
+ More specific information on configuring the driver is in
+ <file:Documentation/networking/device_drivers/intel/fm10k.rst>.
+
To compile this driver as a module, choose M here. The module
will be called fm10k. MSI-X interrupt support is required
+config IGC
+ tristate "Intel(R) Ethernet Controller I225-LM/I225-V support"
+ default n
+ depends on PCI
+ ---help---
+ This driver supports Intel(R) Ethernet Controller I225-LM/I225-V
+ family of adapters.
+
+ For more information on how to identify your adapter, go
+ to the Adapter & Driver ID Guide that can be located at:
+
+ <http://support.intel.com>
+
+ To compile this driver as a module, choose M here. The module
+ will be called igc.
+
endif # NET_VENDOR_INTEL
diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile
index 807a4f8..3075290 100644
--- a/drivers/net/ethernet/intel/Makefile
+++ b/drivers/net/ethernet/intel/Makefile
@@ -7,11 +7,12 @@
obj-$(CONFIG_E1000) += e1000/
obj-$(CONFIG_E1000E) += e1000e/
obj-$(CONFIG_IGB) += igb/
+obj-$(CONFIG_IGC) += igc/
obj-$(CONFIG_IGBVF) += igbvf/
obj-$(CONFIG_IXGBE) += ixgbe/
obj-$(CONFIG_IXGBEVF) += ixgbevf/
obj-$(CONFIG_I40E) += i40e/
obj-$(CONFIG_IXGB) += ixgb/
-obj-$(CONFIG_I40EVF) += i40evf/
+obj-$(CONFIG_IAVF) += iavf/
obj-$(CONFIG_FM10K) += fm10k/
obj-$(CONFIG_ICE) += ice/
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 27d5f27..a65d5a9 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -164,7 +164,7 @@
MODULE_DESCRIPTION(DRV_DESCRIPTION);
MODULE_AUTHOR(DRV_COPYRIGHT);
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
MODULE_FIRMWARE(FIRMWARE_D101M);
MODULE_FIRMWARE(FIRMWARE_D101S);
@@ -1345,8 +1345,8 @@
fw = e100_request_firmware(nic);
/* If it's NULL, then no ucode is required */
- if (!fw || IS_ERR(fw))
- return PTR_ERR(fw);
+ if (IS_ERR_OR_NULL(fw))
+ return PTR_ERR_OR_ZERO(fw);
if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode)))
netif_err(nic, probe, nic->netdev,
@@ -2225,11 +2225,13 @@
e100_rx_clean(nic, &work_done, budget);
e100_tx_clean(nic);
- /* If budget not fully consumed, exit the polling mode */
- if (work_done < budget) {
- napi_complete_done(napi, work_done);
+ /* If budget fully consumed, continue polling */
+ if (work_done == budget)
+ return budget;
+
+ /* only re-enable interrupt if stack agrees polling is really done */
+ if (likely(napi_complete_done(napi, work_done)))
e100_enable_irq(nic);
- }
return work_done;
}
@@ -2795,7 +2797,7 @@
netdev->features = features;
e100_exec_cb(nic, NULL, e100_configure);
- return 0;
+ return 1;
}
static const struct net_device_ops e100_netdev_ops = {
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 2569a16..be56e63 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -607,6 +607,7 @@
for (i = 0; i < adapter->num_rx_queues; i++)
rxdr[i].count = rxdr->count;
+ err = 0;
if (netif_running(adapter->netdev)) {
/* Try to get new resources before deleting old */
err = e1000_setup_all_rx_resources(adapter);
@@ -627,14 +628,13 @@
adapter->rx_ring = rxdr;
adapter->tx_ring = txdr;
err = e1000_up(adapter);
- if (err)
- goto err_setup;
}
kfree(tx_old);
kfree(rx_old);
clear_bit(__E1000_RESETTING, &adapter->flags);
- return 0;
+ return err;
+
err_setup_tx:
e1000_free_all_rx_resources(adapter);
err_setup_rx:
@@ -646,7 +646,6 @@
err_alloc_tx:
if (netif_running(adapter->netdev))
e1000_up(adapter);
-err_setup:
clear_bit(__E1000_RESETTING, &adapter->flags);
return err;
}
@@ -937,8 +936,7 @@
txdr->buffer_info[i].dma,
txdr->buffer_info[i].length,
DMA_TO_DEVICE);
- if (txdr->buffer_info[i].skb)
- dev_kfree_skb(txdr->buffer_info[i].skb);
+ dev_kfree_skb(txdr->buffer_info[i].skb);
}
}
@@ -993,8 +991,8 @@
txdr->size = txdr->count * sizeof(struct e1000_tx_desc);
txdr->size = ALIGN(txdr->size, 4096);
- txdr->desc = dma_zalloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
- GFP_KERNEL);
+ txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
+ GFP_KERNEL);
if (!txdr->desc) {
ret_val = 2;
goto err_nomem;
@@ -1051,8 +1049,8 @@
}
rxdr->size = rxdr->count * sizeof(struct e1000_rx_desc);
- rxdr->desc = dma_zalloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
- GFP_KERNEL);
+ rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
+ GFP_KERNEL);
if (!rxdr->desc) {
ret_val = 6;
goto err_nomem;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 2110d5f..86493fe 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -195,7 +195,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
@@ -820,7 +820,7 @@
else
e1000_reset(adapter);
- return 0;
+ return 1;
}
static const struct net_device_ops e1000_netdev_ops = {
@@ -2433,7 +2433,6 @@
if (link) {
if (!netif_carrier_ok(netdev)) {
u32 ctrl;
- bool txb2b = true;
/* update snapshot of PHY registers on LSC */
e1000_get_speed_and_duplex(hw,
&adapter->link_speed,
@@ -2455,11 +2454,9 @@
adapter->tx_timeout_factor = 1;
switch (adapter->link_speed) {
case SPEED_10:
- txb2b = false;
adapter->tx_timeout_factor = 16;
break;
case SPEED_100:
- txb2b = false;
/* maybe add some timeout factor ? */
break;
}
@@ -2892,9 +2889,8 @@
}
for (f = 0; f < nr_frags; f++) {
- const struct skb_frag_struct *frag;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
- frag = &skb_shinfo(skb)->frags[f];
len = skb_frag_size(frag);
offset = 0;
@@ -3022,7 +3018,7 @@
* applicable for weak-ordered memory model archs,
* such as IA-64).
*/
- wmb();
+ dma_wmb();
tx_ring->next_to_use = i;
}
@@ -3270,14 +3266,9 @@
/* Make sure there is space in the ring for the next send. */
e1000_maybe_stop_tx(netdev, tx_ring, desc_needed);
- if (!skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
- /* we need this if more than one processor can write to
- * our tail at a time, it synchronizes IO on IA64/Altix
- * systems
- */
- mmiowb();
}
} else {
dev_kfree_skb_any(skb);
@@ -3806,14 +3797,15 @@
adapter->clean_rx(adapter, &adapter->rx_ring[0], &work_done, budget);
- if (!tx_clean_complete)
- work_done = budget;
+ if (!tx_clean_complete || work_done == budget)
+ return budget;
- /* If budget not fully consumed, exit the polling mode */
- if (work_done < budget) {
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done))) {
if (likely(adapter->itr_setting & 3))
e1000_set_itr(adapter);
- napi_complete_done(napi, work_done);
if (!test_bit(__E1000_DOWN, &adapter->flags))
e1000_irq_enable(adapter);
}
@@ -4183,8 +4175,7 @@
/* an error means any chain goes out the window
* too
*/
- if (rx_ring->rx_skb_top)
- dev_kfree_skb(rx_ring->rx_skb_top);
+ dev_kfree_skb(rx_ring->rx_skb_top);
rx_ring->rx_skb_top = NULL;
goto next_desc;
}
@@ -4547,7 +4538,7 @@
* applicable for weak-ordered memory model archs,
* such as IA-64).
*/
- wmb();
+ dma_wmb();
writel(i, adapter->hw.hw_addr + rx_ring->rdt);
}
}
@@ -4662,7 +4653,7 @@
* applicable for weak-ordered memory model archs,
* such as IA-64).
*/
- wmb();
+ dma_wmb();
writel(i, hw->hw_addr + rx_ring->rdt);
}
}
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 257bd59..4b103cc 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -680,7 +680,7 @@
ew32(TCTL, E1000_TCTL_PSP);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
ctrl = er32(CTRL);
@@ -696,11 +696,16 @@
ret_val =
e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
&kum_reg_data);
- if (ret_val)
- return ret_val;
- kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
- e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
- kum_reg_data);
+ if (!ret_val) {
+ kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+ ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+ E1000_KMRNCTRLSTA_INBAND_PARAM,
+ kum_reg_data);
+ if (ret_val)
+ e_dbg("Error disabling far-end loopback\n");
+ } else {
+ e_dbg("Error disabling far-end loopback\n");
+ }
ret_val = e1000e_get_auto_rd_done(hw);
if (ret_val)
@@ -754,11 +759,19 @@
return ret_val;
/* Disable IBIST slave mode (far-end loopback) */
- e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
- &kum_reg_data);
- kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
- e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
- kum_reg_data);
+ ret_val =
+ e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
+ &kum_reg_data);
+ if (!ret_val) {
+ kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+ ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+ E1000_KMRNCTRLSTA_INBAND_PARAM,
+ kum_reg_data);
+ if (ret_val)
+ e_dbg("Error disabling far-end loopback\n");
+ } else {
+ e_dbg("Error disabling far-end loopback\n");
+ }
/* Set the transmit descriptor write-back policy */
reg_data = er32(TXDCTL(0));
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index b930930..2c1bab3 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -959,7 +959,7 @@
ew32(TCTL, tctl);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
/* Must acquire the MDIO ownership before MAC reset.
* Ownership defaults to firmware after a reset.
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index fd550de..63c3c79 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -222,6 +222,9 @@
#define E1000_STATUS_PHYRA 0x00000400 /* PHY Reset Asserted */
#define E1000_STATUS_GIO_MASTER_ENABLE 0x00080000 /* Master Req status */
+/* PCIm function state */
+#define E1000_STATUS_PCIM_STATE 0x40000000
+
#define HALF_DUPLEX 1
#define FULL_DUPLEX 2
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index c760dc7..6c51b1b 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -13,7 +13,6 @@
#include <linux/io.h>
#include <linux/netdevice.h>
#include <linux/pci.h>
-#include <linux/pci-aspm.h>
#include <linux/crc32.h>
#include <linux/if_vlan.h>
#include <linux/timecounter.h>
@@ -186,12 +185,13 @@
/* board specific private data structure */
struct e1000_adapter {
- struct timer_list watchdog_timer;
struct timer_list phy_info_timer;
struct timer_list blink_timer;
struct work_struct reset_task;
- struct work_struct watchdog_task;
+ struct delayed_work watchdog_task;
+
+ struct workqueue_struct *e1000_workqueue;
const struct e1000_info *ei;
@@ -505,6 +505,9 @@
void e1000e_ptp_init(struct e1000_adapter *adapter);
void e1000e_ptp_remove(struct e1000_adapter *adapter);
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+ struct ptp_system_timestamp *sts);
+
static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw)
{
return hw->phy.ops.reset(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 02ebf20..de8c581 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -1014,7 +1014,7 @@
/* Disable all the interrupts */
ew32(IMC, 0xFFFFFFFF);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
/* Test each interrupt */
for (i = 0; i < 10; i++) {
@@ -1046,7 +1046,7 @@
ew32(IMC, mask);
ew32(ICS, mask);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
if (adapter->test_icr & mask) {
*data = 3;
@@ -1064,7 +1064,7 @@
ew32(IMS, mask);
ew32(ICS, mask);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
if (!(adapter->test_icr & mask)) {
*data = 4;
@@ -1082,7 +1082,7 @@
ew32(IMC, ~mask & 0x00007FFF);
ew32(ICS, ~mask & 0x00007FFF);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
if (adapter->test_icr) {
*data = 5;
@@ -1094,7 +1094,7 @@
/* Disable all the interrupts */
ew32(IMC, 0xFFFFFFFF);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
/* Unhook test interrupt handler */
free_irq(irq, netdev);
@@ -1126,8 +1126,7 @@
buffer_info->dma,
buffer_info->length,
DMA_TO_DEVICE);
- if (buffer_info->skb)
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb(buffer_info->skb);
}
}
@@ -1139,8 +1138,7 @@
dma_unmap_single(&pdev->dev,
buffer_info->dma,
2048, DMA_FROM_DEVICE);
- if (buffer_info->skb)
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb(buffer_info->skb);
}
}
@@ -1470,7 +1468,7 @@
*/
ew32(SCTL, E1000_SCTL_ENABLE_SERDES_LOOPBACK);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
return 0;
}
@@ -1584,7 +1582,7 @@
hw->phy.media_type == e1000_media_type_internal_serdes) {
ew32(SCTL, E1000_SCTL_DISABLE_SERDES_LOOPBACK);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
break;
}
/* Fall Through */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index cdae0ef..a1fab77 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -271,7 +271,7 @@
u16 count = 20;
do {
- usleep_range(5000, 10000);
+ usleep_range(5000, 6000);
} while (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LPCD) && count--);
msleep(30);
@@ -405,7 +405,7 @@
/* Ungate automatic PHY configuration on non-managed 82579 */
if ((hw->mac.type == e1000_pch2lan) &&
!(fwsm & E1000_ICH_FWSM_FW_VALID)) {
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
e1000_gate_hw_phy_config_ich8lan(hw, false);
}
@@ -531,7 +531,7 @@
phy->id = 0;
while ((e1000_phy_unknown == e1000e_get_phy_type_from_id(phy->id)) &&
(i++ < 100)) {
- usleep_range(1000, 2000);
+ usleep_range(1000, 1100);
ret_val = e1000e_get_phy_id(hw);
if (ret_val)
return ret_val;
@@ -1244,7 +1244,7 @@
goto out;
}
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
}
e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
@@ -1429,6 +1429,16 @@
else
phy_reg |= 0xFA;
e1e_wphy_locked(hw, I217_PLL_CLOCK_GATE_REG, phy_reg);
+
+ if (speed == SPEED_1000) {
+ hw->phy.ops.read_reg_locked(hw, HV_PM_CTRL,
+ &phy_reg);
+
+ phy_reg |= HV_PM_CTRL_K1_CLK_REQ;
+
+ hw->phy.ops.write_reg_locked(hw, HV_PM_CTRL,
+ phy_reg);
+ }
}
hw->phy.ops.release(hw);
@@ -1999,7 +2009,7 @@
while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) &&
(i++ < 30))
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
return blocked ? E1000_BLK_PHY_RESET : 0;
}
@@ -2818,7 +2828,7 @@
return 0;
/* Allow time for h/w to get to quiescent state after reset */
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
/* Perform any necessary post-reset workarounds */
switch (hw->mac.type) {
@@ -2854,7 +2864,7 @@
if (hw->mac.type == e1000_pch2lan) {
/* Ungate automatic PHY configuration on non-managed 82579 */
if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
e1000_gate_hw_phy_config_ich8lan(hw, false);
}
@@ -3875,7 +3885,7 @@
*/
if (!ret_val) {
nvm->ops.reload(hw);
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
}
out:
@@ -4026,7 +4036,7 @@
*/
if (!ret_val) {
nvm->ops.reload(hw);
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
}
out:
@@ -4650,7 +4660,7 @@
ew32(TCTL, E1000_TCTL_PSP);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
/* Workaround for ICH8 bit corruption issue in FIFO memory */
if (hw->mac.type == e1000_ich8lan) {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index eb09c75..1502895 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -210,7 +210,7 @@
/* PHY Power Management Control */
#define HV_PM_CTRL PHY_REG(770, 17)
-#define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA 0x100
+#define HV_PM_CTRL_K1_CLK_REQ 0x200
#define HV_PM_CTRL_K1_ENABLE 0x4000
#define I217_PLL_CLOCK_GATE_REG PHY_REG(772, 28)
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index 4abd55d..e531976 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -797,7 +797,7 @@
* milliseconds even if the other end is doing it in SW).
*/
for (i = 0; i < FIBER_LINK_UP_LIMIT; i++) {
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
status = er32(STATUS);
if (status & E1000_STATUS_LU)
break;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 3ba0c90..d7d56e4 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1780,7 +1780,8 @@
}
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ mod_delayed_work(adapter->e1000_workqueue,
+ &adapter->watchdog_task, HZ);
}
/* Reset on uncorrectable ECC error */
@@ -1860,7 +1861,8 @@
}
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ mod_delayed_work(adapter->e1000_workqueue,
+ &adapter->watchdog_task, HZ);
}
/* Reset on uncorrectable ECC error */
@@ -1905,7 +1907,8 @@
hw->mac.get_link_status = true;
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ mod_delayed_work(adapter->e1000_workqueue,
+ &adapter->watchdog_task, HZ);
}
if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -2106,7 +2109,7 @@
if (strlen(netdev->name) < (IFNAMSIZ - 5))
snprintf(adapter->rx_ring->name,
sizeof(adapter->rx_ring->name) - 1,
- "%s-rx-0", netdev->name);
+ "%.14s-rx-0", netdev->name);
else
memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
err = request_irq(adapter->msix_entries[vector].vector,
@@ -2122,7 +2125,7 @@
if (strlen(netdev->name) < (IFNAMSIZ - 5))
snprintf(adapter->tx_ring->name,
sizeof(adapter->tx_ring->name) - 1,
- "%s-tx-0", netdev->name);
+ "%.14s-tx-0", netdev->name);
else
memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
err = request_irq(adapter->msix_entries[vector].vector,
@@ -2305,8 +2308,8 @@
{
struct pci_dev *pdev = adapter->pdev;
- ring->desc = dma_zalloc_coherent(&pdev->dev, ring->size, &ring->dma,
- GFP_KERNEL);
+ ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma,
+ GFP_KERNEL);
if (!ring->desc)
return -ENOMEM;
@@ -2651,9 +2654,9 @@
/**
* e1000e_poll - NAPI Rx polling callback
* @napi: struct associated with this polling callback
- * @weight: number of packets driver is allowed to process this poll
+ * @budget: number of packets driver is allowed to process this poll
**/
-static int e1000e_poll(struct napi_struct *napi, int weight)
+static int e1000e_poll(struct napi_struct *napi, int budget)
{
struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter,
napi);
@@ -2667,16 +2670,17 @@
(adapter->rx_ring->ims_val & adapter->tx_ring->ims_val))
tx_cleaned = e1000_clean_tx_irq(adapter->tx_ring);
- adapter->clean_rx(adapter->rx_ring, &work_done, weight);
+ adapter->clean_rx(adapter->rx_ring, &work_done, budget);
- if (!tx_cleaned)
- work_done = weight;
+ if (!tx_cleaned || work_done == budget)
+ return budget;
- /* If weight not fully consumed, exit the polling mode */
- if (work_done < weight) {
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done))) {
if (adapter->itr_setting & 3)
e1000_set_itr(adapter);
- napi_complete_done(napi, work_done);
if (!test_bit(__E1000_DOWN, &adapter->state)) {
if (adapter->msix_entries)
ew32(IMS, adapter->rx_ring->ims_val);
@@ -3207,7 +3211,7 @@
if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
ew32(RCTL, rctl & ~E1000_RCTL_EN);
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
if (adapter->flags2 & FLAG2_DMA_BURST) {
/* set the writeback threshold (only takes effect if the RDTR
@@ -3815,7 +3819,6 @@
if (tx_ring->next_to_use == tx_ring->count)
tx_ring->next_to_use = 0;
ew32(TDT(0), tx_ring->next_to_use);
- mmiowb();
usleep_range(200, 250);
}
@@ -4046,12 +4049,12 @@
case e1000_pch_lpt:
case e1000_pch_spt:
case e1000_pch_cnp:
- fc->refresh_time = 0x0400;
+ fc->refresh_time = 0xFFFF;
+ fc->pause_time = 0xFFFF;
if (adapter->netdev->mtu <= ETH_DATA_LEN) {
fc->high_water = 0x05C20;
fc->low_water = 0x05048;
- fc->pause_time = 0x0650;
break;
}
@@ -4208,7 +4211,7 @@
e1000_configure_msix(adapter);
e1000_irq_enable(adapter);
- netif_start_queue(adapter->netdev);
+ /* Tx queue started by watchdog timer when link is up */
e1000e_trigger_lsc(adapter);
}
@@ -4272,13 +4275,12 @@
/* flush both disables and wait for them to finish */
e1e_flush();
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
e1000_irq_disable(adapter);
napi_synchronize(&adapter->napi);
- del_timer_sync(&adapter->watchdog_timer);
del_timer_sync(&adapter->phy_info_timer);
spin_lock(&adapter->stats64_lock);
@@ -4310,7 +4312,7 @@
{
might_sleep();
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
- usleep_range(1000, 2000);
+ usleep_range(1000, 1100);
e1000e_down(adapter, true);
e1000e_up(adapter);
clear_bit(__E1000_RESETTING, &adapter->state);
@@ -4319,13 +4321,16 @@
/**
* e1000e_sanitize_systim - sanitize raw cycle counter reads
* @hw: pointer to the HW structure
- * @systim: time value read, sanitized and returned
+ * @systim: PHC time value read, sanitized and returned
+ * @sts: structure to hold system time before and after reading SYSTIML,
+ * may be NULL
*
* Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
* check to see that the time is incrementing at a reasonable
* rate and is a multiple of incvalue.
**/
-static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
+static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim,
+ struct ptp_system_timestamp *sts)
{
u64 time_delta, rem, temp;
u64 systim_next;
@@ -4335,7 +4340,9 @@
incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
/* latch SYSTIMH on read of SYSTIML */
+ ptp_read_system_prets(sts);
systim_next = (u64)er32(SYSTIML);
+ ptp_read_system_postts(sts);
systim_next |= (u64)er32(SYSTIMH) << 32;
time_delta = systim_next - systim;
@@ -4353,15 +4360,16 @@
}
/**
- * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
- * @cc: cyclecounter structure
+ * e1000e_read_systim - read SYSTIM register
+ * @adapter: board private structure
+ * @sts: structure which will contain system time before and after reading
+ * SYSTIML, may be NULL
**/
-static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+ struct ptp_system_timestamp *sts)
{
- struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
- cc);
struct e1000_hw *hw = &adapter->hw;
- u32 systimel, systimeh;
+ u32 systimel, systimel_2, systimeh;
u64 systim;
/* SYSTIMH latching upon SYSTIML read does not work well.
* This means that if SYSTIML overflows after we read it but before
@@ -4369,11 +4377,15 @@
* will experience a huge non linear increment in the systime value
* to fix that we test for overflow and if true, we re-read systime.
*/
+ ptp_read_system_prets(sts);
systimel = er32(SYSTIML);
+ ptp_read_system_postts(sts);
systimeh = er32(SYSTIMH);
/* Is systimel is so large that overflow is possible? */
if (systimel >= (u32)0xffffffff - E1000_TIMINCA_INCVALUE_MASK) {
- u32 systimel_2 = er32(SYSTIML);
+ ptp_read_system_prets(sts);
+ systimel_2 = er32(SYSTIML);
+ ptp_read_system_postts(sts);
if (systimel > systimel_2) {
/* There was an overflow, read again SYSTIMH, and use
* systimel_2
@@ -4386,12 +4398,24 @@
systim |= (u64)systimeh << 32;
if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
- systim = e1000e_sanitize_systim(hw, systim);
+ systim = e1000e_sanitize_systim(hw, systim, sts);
return systim;
}
/**
+ * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
+ * @cc: cyclecounter structure
+ **/
+static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+{
+ struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
+ cc);
+
+ return e1000e_read_systim(adapter, NULL);
+}
+
+/**
* e1000_sw_init - Initialize general software structures (struct e1000_adapter)
* @adapter: board private structure to initialize
*
@@ -4584,6 +4608,7 @@
pm_runtime_get_sync(&pdev->dev);
netif_carrier_off(netdev);
+ netif_stop_queue(netdev);
/* allocate transmit descriptors */
err = e1000e_setup_tx_resources(adapter->tx_ring);
@@ -4644,7 +4669,6 @@
e1000_irq_enable(adapter);
adapter->tx_hang_recheck = false;
- netif_start_queue(netdev);
hw->mac.get_link_status = true;
pm_runtime_put(&pdev->dev);
@@ -4685,7 +4709,7 @@
int count = E1000_CHECK_RESET_COUNT;
while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
@@ -5128,31 +5152,18 @@
}
}
-/**
- * e1000_watchdog - Timer Call-back
- * @data: pointer to adapter cast into an unsigned long
- **/
-static void e1000_watchdog(struct timer_list *t)
-{
- struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
-
- /* Do the rest outside of interrupt context */
- schedule_work(&adapter->watchdog_task);
-
- /* TODO: make this use queue_delayed_work() */
-}
-
static void e1000_watchdog_task(struct work_struct *work)
{
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter,
- watchdog_task);
+ watchdog_task.work);
struct net_device *netdev = adapter->netdev;
struct e1000_mac_info *mac = &adapter->hw.mac;
struct e1000_phy_info *phy = &adapter->hw.phy;
struct e1000_ring *tx_ring = adapter->tx_ring;
+ u32 dmoff_exit_timeout = 100, tries = 0;
struct e1000_hw *hw = &adapter->hw;
- u32 link, tctl;
+ u32 link, tctl, pcim_state;
if (test_bit(__E1000_DOWN, &adapter->state))
return;
@@ -5177,6 +5188,21 @@
/* Cancel scheduled suspend requests. */
pm_runtime_resume(netdev->dev.parent);
+ /* Checking if MAC is in DMoff state*/
+ pcim_state = er32(STATUS);
+ while (pcim_state & E1000_STATUS_PCIM_STATE) {
+ if (tries++ == dmoff_exit_timeout) {
+ e_dbg("Error in exiting dmoff\n");
+ break;
+ }
+ usleep_range(10000, 20000);
+ pcim_state = er32(STATUS);
+
+ /* Checking if MAC exited DMoff state */
+ if (!(pcim_state & E1000_STATUS_PCIM_STATE))
+ e1000_phy_hw_reset(&adapter->hw);
+ }
+
/* update snapshot of PHY registers on LSC */
e1000_phy_read_status(adapter);
mac->ops.get_link_up_info(&adapter->hw,
@@ -5266,6 +5292,7 @@
if (phy->ops.cfg_on_link_up)
phy->ops.cfg_on_link_up(hw);
+ netif_wake_queue(netdev);
netif_carrier_on(netdev);
if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -5279,6 +5306,7 @@
/* Link status message must follow this format */
pr_info("%s NIC Link is Down\n", adapter->netdev->name);
netif_carrier_off(netdev);
+ netif_stop_queue(netdev);
if (!test_bit(__E1000_DOWN, &adapter->state))
mod_timer(&adapter->phy_info_timer,
round_jiffies(jiffies + 2 * HZ));
@@ -5376,8 +5404,9 @@
/* Reset the timer */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_timer(&adapter->watchdog_timer,
- round_jiffies(jiffies + 2 * HZ));
+ queue_delayed_work(adapter->e1000_workqueue,
+ &adapter->watchdog_task,
+ round_jiffies(2 * HZ));
}
#define E1000_TX_FLAGS_CSUM 0x00000001
@@ -5550,9 +5579,8 @@
}
for (f = 0; f < nr_frags; f++) {
- const struct skb_frag_struct *frag;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
- frag = &skb_shinfo(skb)->frags[f];
len = skb_frag_size(frag);
offset = 0;
@@ -5877,19 +5905,13 @@
DIV_ROUND_UP(PAGE_SIZE,
adapter->tx_fifo_limit) + 2));
- if (!skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
e1000e_update_tdt_wa(tx_ring,
tx_ring->next_to_use);
else
writel(tx_ring->next_to_use, tx_ring->tail);
-
- /* we need this if more than one processor can write
- * to our tail at a time, it synchronizes IO on
- *IA64/Altix systems
- */
- mmiowb();
}
} else {
dev_kfree_skb_any(skb);
@@ -6003,7 +6025,7 @@
}
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
- usleep_range(1000, 2000);
+ usleep_range(1000, 1100);
/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
adapter->max_frame_size = max_frame;
e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
@@ -6274,7 +6296,7 @@
static int e1000e_pm_freeze(struct device *dev)
{
- struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
+ struct net_device *netdev = dev_get_drvdata(dev);
struct e1000_adapter *adapter = netdev_priv(netdev);
netif_device_detach(netdev);
@@ -6283,7 +6305,7 @@
int count = E1000_CHECK_RESET_COUNT;
while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
@@ -6607,7 +6629,7 @@
#ifdef CONFIG_PM_SLEEP
static int e1000e_pm_thaw(struct device *dev)
{
- struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
+ struct net_device *netdev = dev_get_drvdata(dev);
struct e1000_adapter *adapter = netdev_priv(netdev);
e1000e_set_interrupt_capability(adapter);
@@ -6656,8 +6678,7 @@
static int e1000e_pm_runtime_idle(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct net_device *netdev = pci_get_drvdata(pdev);
+ struct net_device *netdev = dev_get_drvdata(dev);
struct e1000_adapter *adapter = netdev_priv(netdev);
u16 eee_lp;
@@ -6698,7 +6719,7 @@
int count = E1000_CHECK_RESET_COUNT;
while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
@@ -6854,8 +6875,6 @@
result = PCI_ERS_RESULT_RECOVERED;
}
- pci_cleanup_aer_uncorrect_error_status(pdev);
-
return result;
}
@@ -6985,7 +7004,7 @@
else
e1000e_reset(adapter);
- return 0;
+ return 1;
}
static const struct net_device_ops e1000e_netdev_ops = {
@@ -7240,11 +7259,21 @@
goto err_eeprom;
}
- timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
+ adapter->e1000_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+ e1000e_driver_name);
+
+ if (!adapter->e1000_workqueue) {
+ err = -ENOMEM;
+ goto err_workqueue;
+ }
+
+ INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog_task);
+ queue_delayed_work(adapter->e1000_workqueue, &adapter->watchdog_task,
+ 0);
+
timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
INIT_WORK(&adapter->reset_task, e1000_reset_task);
- INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
@@ -7330,12 +7359,17 @@
e1000_print_device_info(adapter);
- if (pci_dev_run_wake(pdev))
+ dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP);
+
+ if (pci_dev_run_wake(pdev) && hw->mac.type < e1000_pch_cnp)
pm_runtime_put_noidle(&pdev->dev);
return 0;
err_register:
+ flush_workqueue(adapter->e1000_workqueue);
+ destroy_workqueue(adapter->e1000_workqueue);
+err_workqueue:
if (!(adapter->flags & FLAG_HAS_AMT))
e1000e_release_hw_control(adapter);
err_eeprom:
@@ -7382,15 +7416,17 @@
*/
if (!down)
set_bit(__E1000_DOWN, &adapter->state);
- del_timer_sync(&adapter->watchdog_timer);
del_timer_sync(&adapter->phy_info_timer);
cancel_work_sync(&adapter->reset_task);
- cancel_work_sync(&adapter->watchdog_task);
cancel_work_sync(&adapter->downshift_task);
cancel_work_sync(&adapter->update_phy_task);
cancel_work_sync(&adapter->print_hang_task);
+ cancel_delayed_work(&adapter->watchdog_task);
+ flush_workqueue(adapter->e1000_workqueue);
+ destroy_workqueue(adapter->e1000_workqueue);
+
if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
cancel_work_sync(&adapter->tx_hwtstamp_work);
if (adapter->tx_hwtstamp_skb) {
@@ -7592,7 +7628,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
/* netdev.c */
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index 937f9af..e609f4d 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -392,7 +392,7 @@
break;
}
}
- usleep_range(10000, 20000);
+ usleep_range(10000, 11000);
nvm->ops.release(hw);
}
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 37c7694..1a4c65d 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -161,22 +161,30 @@
#endif/*CONFIG_E1000E_HWTS*/
/**
- * e1000e_phc_gettime - Reads the current time from the hardware clock
+ * e1000e_phc_gettimex - Reads the current time from the hardware clock and
+ * system clock
* @ptp: ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec structure to hold the current PHC time
+ * @sts: structure to hold the current system time
*
* Read the timecounter and return the correct value in ns after converting
* it into a struct timespec.
**/
-static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int e1000e_phc_gettimex(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
ptp_clock_info);
unsigned long flags;
- u64 ns;
+ u64 cycles, ns;
spin_lock_irqsave(&adapter->systim_lock, flags);
- ns = timecounter_read(&adapter->tc);
+
+ /* NOTE: Non-monotonic SYSTIM readings may be returned */
+ cycles = e1000e_read_systim(adapter, sts);
+ ns = timecounter_cyc2time(&adapter->tc, cycles);
+
spin_unlock_irqrestore(&adapter->systim_lock, flags);
*ts = ns_to_timespec64(ns);
@@ -232,9 +240,12 @@
systim_overflow_work.work);
struct e1000_hw *hw = &adapter->hw;
struct timespec64 ts;
+ u64 ns;
- adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts);
+ /* Update the timecounter */
+ ns = timecounter_read(&adapter->tc);
+ ts = ns_to_timespec64(ns);
e_dbg("SYSTIM overflow check at %lld.%09lu\n",
(long long) ts.tv_sec, ts.tv_nsec);
@@ -251,7 +262,7 @@
.pps = 0,
.adjfreq = e1000e_phc_adjfreq,
.adjtime = e1000e_phc_adjtime,
- .gettime64 = e1000e_phc_gettime,
+ .gettimex64 = e1000e_phc_gettimex,
.settime64 = e1000e_phc_settime,
.enable = e1000e_phc_enable,
};
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 7d42582..b144419 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#ifndef _FM10K_H_
#define _FM10K_H_
@@ -177,14 +177,10 @@
#define MIN_Q_VECTORS 1
enum fm10k_non_q_vectors {
FM10K_MBX_VECTOR,
-#define NON_Q_VECTORS_VF NON_Q_VECTORS_PF
- NON_Q_VECTORS_PF
+ NON_Q_VECTORS
};
-#define NON_Q_VECTORS(hw) (((hw)->mac.type == fm10k_mac_pf) ? \
- NON_Q_VECTORS_PF : \
- NON_Q_VECTORS_VF)
-#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS(hw))
+#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS)
struct fm10k_q_vector {
struct fm10k_intfc *interface;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
index 20768ac..c453154 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k.h"
@@ -36,7 +36,7 @@
static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
{
u8 num_tc = 0;
- int i, err;
+ int i;
/* verify type and determine num_tcs needed */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
@@ -57,7 +57,7 @@
/* update TC hardware mapping if necessary */
if (num_tc != netdev_get_num_tc(dev)) {
- err = fm10k_setup_tc(dev, num_tc);
+ int err = fm10k_setup_tc(dev, num_tc);
if (err)
return err;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
index dca1041..1d27b2f 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
@@ -160,8 +160,6 @@
snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx);
q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc);
- if (!q_vector->dbg_q_vector)
- return;
/* Generate a file for each rx ring in the q_vector */
for (i = 0; i < q_vector->tx.count; i++) {
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 4895dd8..c681d2d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include <linux/vmalloc.h>
@@ -222,7 +222,6 @@
const unsigned int size)
{
unsigned int i;
- char *p;
if (!pointer) {
/* memory is not zero allocated so we have to clear it */
@@ -232,7 +231,7 @@
}
for (i = 0; i < size; i++) {
- p = (char *)pointer + stats[i].stat_offset;
+ char *p = (char *)pointer + stats[i].stat_offset;
switch (stats[i].sizeof_stat) {
case sizeof(u64):
@@ -651,7 +650,6 @@
struct ethtool_coalesce *ec)
{
struct fm10k_intfc *interface = netdev_priv(dev);
- struct fm10k_q_vector *qv;
u16 tx_itr, rx_itr;
int i;
@@ -677,7 +675,8 @@
/* update q_vectors */
for (i = 0; i < interface->num_q_vectors; i++) {
- qv = interface->q_vector[i];
+ struct fm10k_q_vector *qv = interface->q_vector[i];
+
qv->tx.itr = tx_itr;
qv->rx.itr = rx_itr;
}
@@ -1115,13 +1114,12 @@
struct ethtool_channels *ch)
{
struct fm10k_intfc *interface = netdev_priv(dev);
- struct fm10k_hw *hw = &interface->hw;
/* report maximum channels */
ch->max_combined = fm10k_max_channels(dev);
/* report info for other vector */
- ch->max_other = NON_Q_VECTORS(hw);
+ ch->max_other = NON_Q_VECTORS;
ch->other_count = ch->max_other;
/* record RSS queues */
@@ -1133,14 +1131,13 @@
{
struct fm10k_intfc *interface = netdev_priv(dev);
unsigned int count = ch->combined_count;
- struct fm10k_hw *hw = &interface->hw;
/* verify they are not requesting separate vectors */
if (!count || ch->rx_count || ch->tx_count)
return -EINVAL;
/* verify other_count has not changed */
- if (ch->other_count != NON_Q_VECTORS(hw))
+ if (ch->other_count != NON_Q_VECTORS)
return -EINVAL;
/* verify the number of channels does not exceed hardware limits */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index e707d71..afe1faf 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k.h"
#include "fm10k_vf.h"
@@ -244,7 +244,8 @@
}
/* guarantee we have free space in the SM mailbox */
- if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) {
+ if (hw->mbx.state == FM10K_STATE_OPEN &&
+ !hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) {
/* keep track of how many times this occurs */
interface->hw_sm_mbx_full++;
@@ -302,6 +303,26 @@
}
}
+static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev)
+{
+ u32 err_mask;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+ if (!pos)
+ return;
+
+ /* Mask the completion abort bit in the ERR_UNCOR_MASK register,
+ * preventing the device from reporting these errors to the upstream
+ * PCIe root device. This avoids bringing down platforms which upgrade
+ * non-fatal completer aborts into machine check exceptions. Completer
+ * aborts can occur whenever a VF reads a queue it doesn't own.
+ */
+ pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask);
+ err_mask |= PCI_ERR_UNC_COMP_ABORT;
+ pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask);
+}
+
int fm10k_iov_resume(struct pci_dev *pdev)
{
struct fm10k_intfc *interface = pci_get_drvdata(pdev);
@@ -317,6 +338,12 @@
if (!iov_data)
return -ENOMEM;
+ /* Lower severity of completer abort error reporting as
+ * the VFs can trigger this any time they read a queue
+ * that they don't own.
+ */
+ fm10k_mask_aer_comp_abort(pdev);
+
/* allocate hardware resources for the VFs */
hw->iov.ops.assign_resources(hw, num_vfs, num_vfs);
@@ -399,7 +426,7 @@
struct fm10k_iov_data *iov_data = interface->iov_data;
struct fm10k_hw *hw = &interface->hw;
size_t size;
- int i, err;
+ int i;
/* return error if iov_data is already populated */
if (iov_data)
@@ -425,6 +452,7 @@
/* loop through vf_info structures initializing each entry */
for (i = 0; i < num_vfs; i++) {
struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+ int err;
/* Record VF VSI value */
vf_info->vsi = i + 1;
@@ -460,20 +488,6 @@
fm10k_iov_free_data(pdev);
}
-static void fm10k_disable_aer_comp_abort(struct pci_dev *pdev)
-{
- u32 err_sev;
- int pos;
-
- pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
- if (!pos)
- return;
-
- pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &err_sev);
- err_sev &= ~PCI_ERR_UNC_COMP_ABORT;
- pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, err_sev);
-}
-
int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs)
{
int current_vfs = pci_num_vf(pdev);
@@ -495,12 +509,6 @@
/* allocate VFs if not already allocated */
if (num_vfs && num_vfs != current_vfs) {
- /* Disable completer abort error reporting as
- * the VFs can trigger this any time they read a queue
- * that they don't own.
- */
- fm10k_disable_aer_comp_abort(pdev);
-
err = pci_enable_sriov(pdev, num_vfs);
if (err) {
dev_err(&pdev->dev,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 3f53654..2be9222 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include <linux/types.h>
#include <linux/module.h>
@@ -11,17 +11,17 @@
#include "fm10k.h"
-#define DRV_VERSION "0.23.4-k"
+#define DRV_VERSION "0.26.1-k"
#define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver"
const char fm10k_driver_version[] = DRV_VERSION;
char fm10k_driver_name[] = "fm10k";
static const char fm10k_driver_string[] = DRV_SUMMARY;
static const char fm10k_copyright[] =
- "Copyright(c) 2013 - 2018 Intel Corporation.";
+ "Copyright(c) 2013 - 2019 Intel Corporation.";
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION(DRV_SUMMARY);
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
/* single workqueue for entire fm10k driver */
@@ -41,6 +41,8 @@
/* create driver workqueue */
fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
fm10k_driver_name);
+ if (!fm10k_workqueue)
+ return -ENOMEM;
fm10k_dbg_init();
@@ -278,7 +280,7 @@
/* we need the header to contain the greater of either ETH_HLEN or
* 60 bytes if the skb->len is less than 60 for skb_pad.
*/
- pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
+ pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);
/* align pull length to size of long to optimize memcpy performance */
memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
@@ -313,7 +315,7 @@
/* prefetch first cache line of first page */
prefetch(page_addr);
#if L1_CACHE_BYTES < 128
- prefetch(page_addr + L1_CACHE_BYTES);
+ prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES));
#endif
/* allocate a skb to store the frags */
@@ -944,7 +946,7 @@
struct sk_buff *skb = first->skb;
struct fm10k_tx_buffer *tx_buffer;
struct fm10k_tx_desc *tx_desc;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
unsigned char *data;
dma_addr_t dma;
unsigned int data_len, size;
@@ -1035,13 +1037,8 @@
fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return;
@@ -1076,8 +1073,11 @@
* + 2 desc gap to keep tail from touching head
* otherwise try next time
*/
- for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
- count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+
+ count += TXD_USE_COUNT(skb_frag_size(frag));
+ }
if (fm10k_maybe_stop_tx(tx_ring, count + 3)) {
tx_ring->tx_stats.tx_busy++;
@@ -1465,11 +1465,11 @@
if (!clean_complete)
return budget;
- /* all work done, exit the polling mode */
- napi_complete_done(napi, work_done);
-
- /* re-enable the q_vector */
- fm10k_qv_enable(q_vector);
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ fm10k_qv_enable(q_vector);
return min(work_done, budget - 1);
}
@@ -1603,14 +1603,12 @@
{
struct fm10k_q_vector *q_vector;
struct fm10k_ring *ring;
- int ring_count, size;
+ int ring_count;
ring_count = txr_count + rxr_count;
- size = sizeof(struct fm10k_q_vector) +
- (sizeof(struct fm10k_ring) * ring_count);
/* allocate q_vector and rings */
- q_vector = kzalloc(size, GFP_KERNEL);
+ q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL);
if (!q_vector)
return -ENOMEM;
@@ -1828,7 +1826,7 @@
v_budget = min_t(u16, v_budget, num_online_cpus());
/* account for vectors not related to queues */
- v_budget += NON_Q_VECTORS(hw);
+ v_budget += NON_Q_VECTORS;
/* At the same time, hardware can only support a maximum of
* hw.mac->max_msix_vectors vectors. With features
@@ -1860,7 +1858,7 @@
}
/* record the number of queues available for q_vectors */
- interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw);
+ interface->num_q_vectors = v_budget - NON_Q_VECTORS;
return 0;
}
@@ -1874,7 +1872,7 @@
static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface)
{
struct net_device *dev = interface->netdev;
- int pc, offset, rss_i, i, q_idx;
+ int pc, offset, rss_i, i;
u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1;
u8 num_pcs = netdev_get_num_tc(dev);
@@ -1884,7 +1882,8 @@
rss_i = interface->ring_feature[RING_F_RSS].indices;
for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) {
- q_idx = pc;
+ int q_idx = pc;
+
for (i = 0; i < rss_i; i++) {
interface->tx_ring[offset + i]->reg_idx = q_idx;
interface->tx_ring[offset + i]->qos_pc = pc;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
index 21021fe..75e51f9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k_common.h"
@@ -297,13 +297,14 @@
{
struct fm10k_mbx_fifo *fifo = &mbx->rx;
u16 total_len = 0, msg_len;
- u32 *msg;
/* length should include previous amounts pushed */
len += mbx->pushed;
/* offset in message is based off of current message size */
do {
+ u32 *msg;
+
msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len);
msg_len = FM10K_TLV_DWORD_LEN(*msg);
total_len += msg_len;
@@ -1920,7 +1921,6 @@
/* reduce length by 1 to convert to a mask */
u16 mbmem_len = mbx->mbmem_len - 1;
u16 tail_len, len = 0;
- u32 *msg;
/* push head behind tail */
if (mbx->tail < head)
@@ -1930,6 +1930,8 @@
/* determine msg aligned offset for end of buffer */
do {
+ u32 *msg;
+
msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len);
tail_len = len;
len += FM10K_TLV_DWORD_LEN(*msg);
@@ -2132,7 +2134,8 @@
* DWORDs, not bytes. Any invalid values will cause the mailbox to return
* error.
**/
-s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx,
+s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw,
+ struct fm10k_mbx_info *mbx,
const struct fm10k_msg_data *msg_data)
{
mbx->mbx_reg = FM10K_GMBX;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 538a846..09f7a24 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k.h"
#include <linux/vmalloc.h>
@@ -54,7 +54,7 @@
**/
static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface)
{
- int i, err = 0;
+ int i, err;
for (i = 0; i < interface->num_tx_queues; i++) {
err = fm10k_setup_tx_resources(interface->tx_ring[i]);
@@ -121,7 +121,7 @@
**/
static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface)
{
- int i, err = 0;
+ int i, err;
for (i = 0; i < interface->num_rx_queues; i++) {
err = fm10k_setup_rx_resources(interface->rx_ring[i]);
@@ -169,7 +169,6 @@
**/
static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring)
{
- struct fm10k_tx_buffer *tx_buffer;
unsigned long size;
u16 i;
@@ -179,7 +178,8 @@
/* Free all the Tx ring sk_buffs */
for (i = 0; i < tx_ring->count; i++) {
- tx_buffer = &tx_ring->tx_buffer[i];
+ struct fm10k_tx_buffer *tx_buffer = &tx_ring->tx_buffer[i];
+
fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer);
}
@@ -253,8 +253,7 @@
if (!rx_ring->rx_buffer)
return;
- if (rx_ring->skb)
- dev_kfree_skb(rx_ring->skb);
+ dev_kfree_skb(rx_ring->skb);
rx_ring->skb = NULL;
/* Free all the Rx ring sk_buffs */
@@ -871,7 +870,7 @@
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
- int err = -EHOSTDOWN;
+ int err;
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
@@ -891,7 +890,7 @@
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
- int err = -EHOSTDOWN;
+ int err;
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
@@ -1444,11 +1443,11 @@
static void fm10k_assign_l2_accel(struct fm10k_intfc *interface,
struct fm10k_l2_accel *l2_accel)
{
- struct fm10k_ring *ring;
int i;
for (i = 0; i < interface->num_rx_queues; i++) {
- ring = interface->rx_ring[i];
+ struct fm10k_ring *ring = interface->rx_ring[i];
+
rcu_assign_pointer(ring->l2_accel, l2_accel);
}
@@ -1463,7 +1462,7 @@
struct fm10k_l2_accel *old_l2_accel = NULL;
struct fm10k_dglort_cfg dglort = { 0 };
struct fm10k_hw *hw = &interface->hw;
- int size = 0, i;
+ int size, i;
u16 vid, glort;
/* The hardware supported by fm10k only filters on the destination MAC
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index c859aba..bb236fa 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include <linux/module.h>
#include <linux/interrupt.h>
@@ -23,6 +23,8 @@
*/
static const struct pci_device_id fm10k_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_PF), fm10k_device_pf },
+ { PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_QDA2), fm10k_device_pf },
+ { PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_DA2), fm10k_device_pf },
{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_VF), fm10k_device_vf },
/* required last entry */
{ 0, }
@@ -342,7 +344,6 @@
struct net_device *netdev = interface->netdev;
u32 __iomem *hw_addr;
u32 value;
- int err;
/* do nothing if netdev is still present or hw_addr is set */
if (netif_device_present(netdev) || interface->hw.hw_addr)
@@ -360,6 +361,8 @@
hw_addr = READ_ONCE(interface->uc_addr);
value = readl(hw_addr);
if (~value) {
+ int err;
+
/* Make sure the reset was initiated because we detached,
* otherwise we might race with a different reset flow.
*/
@@ -695,8 +698,6 @@
*/
static void fm10k_check_hang_subtask(struct fm10k_intfc *interface)
{
- int i;
-
/* If we're down or resetting, just bail */
if (test_bit(__FM10K_DOWN, interface->state) ||
test_bit(__FM10K_RESETTING, interface->state))
@@ -708,6 +709,8 @@
interface->next_tx_hang_check = jiffies + (2 * HZ);
if (netif_carrier_ok(interface->netdev)) {
+ int i;
+
/* Force detection of hung controller */
for (i = 0; i < interface->num_tx_queues; i++)
set_check_for_tx_hang(interface->tx_ring[i]);
@@ -895,7 +898,7 @@
/* Map interrupt */
if (ring->q_vector) {
- txint = ring->q_vector->v_idx + NON_Q_VECTORS(hw);
+ txint = ring->q_vector->v_idx + NON_Q_VECTORS;
txint |= FM10K_INT_MAP_TIMER0;
}
@@ -1034,7 +1037,7 @@
/* Map interrupt */
if (ring->q_vector) {
- rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw);
+ rxint = ring->q_vector->v_idx + NON_Q_VECTORS;
rxint |= FM10K_INT_MAP_TIMER1;
}
@@ -1717,10 +1720,9 @@
void fm10k_qv_free_irq(struct fm10k_intfc *interface)
{
int vector = interface->num_q_vectors;
- struct fm10k_hw *hw = &interface->hw;
struct msix_entry *entry;
- entry = &interface->msix_entries[NON_Q_VECTORS(hw) + vector];
+ entry = &interface->msix_entries[NON_Q_VECTORS + vector];
while (vector) {
struct fm10k_q_vector *q_vector;
@@ -1757,7 +1759,7 @@
unsigned int ri = 0, ti = 0;
int vector, err;
- entry = &interface->msix_entries[NON_Q_VECTORS(hw)];
+ entry = &interface->msix_entries[NON_Q_VECTORS];
for (vector = 0; vector < interface->num_q_vectors; vector++) {
struct fm10k_q_vector *q_vector = interface->q_vector[vector];
@@ -2337,7 +2339,7 @@
/* Restart the MAC/VLAN request queue in-case of outstanding events */
fm10k_macvlan_schedule(interface);
- return err;
+ return 0;
}
/**
@@ -2350,7 +2352,7 @@
**/
static int __maybe_unused fm10k_resume(struct device *dev)
{
- struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
+ struct fm10k_intfc *interface = dev_get_drvdata(dev);
struct net_device *netdev = interface->netdev;
struct fm10k_hw *hw = &interface->hw;
int err;
@@ -2377,7 +2379,7 @@
**/
static int __maybe_unused fm10k_suspend(struct device *dev)
{
- struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
+ struct fm10k_intfc *interface = dev_get_drvdata(dev);
struct net_device *netdev = interface->netdev;
netif_device_detach(netdev);
@@ -2440,8 +2442,6 @@
result = PCI_ERS_RESULT_RECOVERED;
}
- pci_cleanup_aer_uncorrect_error_status(pdev);
-
return result;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 8f0a99b..be07bfd 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k_pf.h"
#include "fm10k_vf.h"
@@ -1148,11 +1148,11 @@
* @results: Pointer array to message, results[0] is pointer to message
* @mbx: Pointer to mailbox information structure
*
- * This function is a default handler for MSI-X requests from the VF. The
+ * This function is a default handler for MSI-X requests from the VF. The
* assumption is that in this case it is acceptable to just directly
* hand off the message from the VF to the underlying shared code.
**/
-s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results,
+s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results,
struct fm10k_mbx_info *mbx)
{
struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
@@ -1352,7 +1352,6 @@
struct fm10k_mbx_info *mbx)
{
struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
- u32 *result;
s32 err = 0;
u32 msg[2];
u8 mode = 0;
@@ -1362,7 +1361,7 @@
return FM10K_ERR_PARAM;
if (!!results[FM10K_LPORT_STATE_MSG_XCAST_MODE]) {
- result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE];
+ u32 *result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE];
/* XCAST mode update requested */
err = fm10k_tlv_attr_get_u8(result, &mode);
@@ -1566,7 +1565,7 @@
/* read remaining fields */
fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI);
fault->address <<= 32;
- fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO);
+ fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO);
fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO);
/* clear valid bit to allow for next error */
@@ -1642,7 +1641,7 @@
* switch API.
**/
s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+ struct fm10k_mbx_info __always_unused *mbx)
{
u16 glort, mask;
u32 dglort_map;
@@ -1685,7 +1684,7 @@
* This handler configures the default VLAN for the PF
**/
static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+ struct fm10k_mbx_info __always_unused *mbx)
{
u16 glort, pvid;
u32 pvid_update;
@@ -1746,7 +1745,7 @@
* messages that the PF has sent.
**/
s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+ struct fm10k_mbx_info __always_unused *mbx)
{
struct fm10k_swapi_error err_msg;
s32 err;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
index 2a7a40b..21eff08 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k_tlv.h"
@@ -472,7 +472,7 @@
const struct fm10k_tlv_attr *tlv_attr)
{
u32 i, attr_id, offset = 0;
- s32 err = 0;
+ s32 err;
u16 len;
/* verify pointers are not NULL */
@@ -587,8 +587,9 @@
* a minimum it just indicates that the message requested was
* unimplemented.
**/
-s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw,
+ u32 __always_unused **results,
+ struct fm10k_mbx_info __always_unused *mbx)
{
return FM10K_NOT_IMPLEMENTED;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 3e608e4..15ac1c7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#ifndef _FM10K_TYPE_H_
#define _FM10K_TYPE_H_
@@ -15,6 +15,8 @@
#define FM10K_DEV_ID_PF 0x15A4
#define FM10K_DEV_ID_VF 0x15A5
+#define FM10K_DEV_ID_SDI_FM10420_QDA2 0x15D0
+#define FM10K_DEV_ID_SDI_FM10420_DA2 0x15D5
#define FM10K_MAX_QUEUES 256
#define FM10K_MAX_QUEUES_PF 128
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index a8519c1..dc8ccd3 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
#include "fm10k_vf.h"
@@ -198,7 +198,7 @@
* This function should determine the MAC address for the VF
**/
s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+ struct fm10k_mbx_info __always_unused *mbx)
{
u8 perm_addr[ETH_ALEN];
u16 vid;
@@ -267,8 +267,10 @@
* This function is used to add or remove unicast MAC addresses for
* the VF.
**/
-static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort,
- const u8 *mac, u16 vid, bool add, u8 flags)
+static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw,
+ u16 __always_unused glort,
+ const u8 *mac, u16 vid, bool add,
+ u8 __always_unused flags)
{
struct fm10k_mbx_info *mbx = &hw->mbx;
u32 msg[7];
@@ -309,7 +311,8 @@
* This function is used to add or remove multicast MAC addresses for
* the VF.
**/
-static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, u16 glort,
+static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw,
+ u16 __always_unused glort,
const u8 *mac, u16 vid, bool add)
{
struct fm10k_mbx_info *mbx = &hw->mbx;
@@ -373,7 +376,7 @@
* are ready to bring up the interface.
**/
s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results,
- struct fm10k_mbx_info *mbx)
+ struct fm10k_mbx_info __always_unused *mbx)
{
hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ?
FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO;
@@ -392,8 +395,9 @@
* enabled we can add filters, if it is disabled all filters for this
* logical port are flushed.
**/
-static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort,
- u16 count, bool enable)
+static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw,
+ u16 __always_unused glort,
+ u16 __always_unused count, bool enable)
{
struct fm10k_mbx_info *mbx = &hw->mbx;
u32 msg[2];
@@ -420,7 +424,8 @@
* so that it can enable either multicast, multicast promiscuous, or
* promiscuous mode of operation.
**/
-static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode)
+static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw,
+ u16 __always_unused glort, u8 mode)
{
struct fm10k_mbx_info *mbx = &hw->mbx;
u32 msg[3];
@@ -475,7 +480,7 @@
* that information to then populate a DGLORTMAP/DEC entry and the queues
* to which it has been assigned.
**/
-static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw *hw,
+static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw,
struct fm10k_dglort_cfg *dglort)
{
/* verify the dglort pointer */
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 14397e7..2f21b3e 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -21,7 +21,9 @@
i40e_diag.o \
i40e_txrx.o \
i40e_ptp.o \
+ i40e_ddp.o \
i40e_client.o \
- i40e_virtchnl_pf.o
+ i40e_virtchnl_pf.o \
+ i40e_xsk.o
i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 7a80652..2af9f63 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -27,6 +27,7 @@
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
+#include <linux/if_macvlan.h>
#include <linux/if_bridge.h>
#include <linux/clocksource.h>
#include <linux/net_tstamp.h>
@@ -34,6 +35,7 @@
#include <net/pkt_cls.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/xdp_sock.h>
#include "i40e_type.h"
#include "i40e_prototype.h"
#include "i40e_client.h"
@@ -122,13 +124,13 @@
__I40E_MDD_EVENT_PENDING,
__I40E_VFLR_EVENT_PENDING,
__I40E_RESET_RECOVERY_PENDING,
+ __I40E_TIMEOUT_RECOVERY_PENDING,
__I40E_MISC_IRQ_REQUESTED,
__I40E_RESET_INTR_RECEIVED,
__I40E_REINIT_REQUESTED,
__I40E_PF_RESET_REQUESTED,
__I40E_CORE_RESET_REQUESTED,
__I40E_GLOBAL_RESET_REQUESTED,
- __I40E_EMP_RESET_REQUESTED,
__I40E_EMP_RESET_INTR_RECEIVED,
__I40E_SUSPENDED,
__I40E_PTP_TX_IN_PROGRESS,
@@ -146,6 +148,8 @@
__I40E_CLIENT_SERVICE_REQUESTED,
__I40E_CLIENT_L2_CHANGE,
__I40E_CLIENT_RESET,
+ __I40E_VIRTCHNL_OP_PENDING,
+ __I40E_RECOVERY_MODE,
/* This must be last as it determines the size of the BITMAP */
__I40E_STATE_SIZE__,
};
@@ -239,11 +243,11 @@
u32 fd_id;
};
-#define I40E_CLOUD_FIELD_OMAC 0x01
-#define I40E_CLOUD_FIELD_IMAC 0x02
-#define I40E_CLOUD_FIELD_IVLAN 0x04
-#define I40E_CLOUD_FIELD_TEN_ID 0x08
-#define I40E_CLOUD_FIELD_IIP 0x10
+#define I40E_CLOUD_FIELD_OMAC BIT(0)
+#define I40E_CLOUD_FIELD_IMAC BIT(1)
+#define I40E_CLOUD_FIELD_IVLAN BIT(2)
+#define I40E_CLOUD_FIELD_TEN_ID BIT(3)
+#define I40E_CLOUD_FIELD_IIP BIT(4)
#define I40E_CLOUD_FILTER_FLAGS_OMAC I40E_CLOUD_FIELD_OMAC
#define I40E_CLOUD_FILTER_FLAGS_IMAC I40E_CLOUD_FIELD_IMAC
@@ -291,8 +295,6 @@
u8 tunnel_type;
};
-#define I40E_ETH_P_LLDP 0x88cc
-
#define I40E_DCB_PRIO_TYPE_STRICT 0
#define I40E_DCB_PRIO_TYPE_ETS 1
#define I40E_DCB_STRICT_PRIO_CREDITS 127
@@ -318,6 +320,29 @@
u8 filter_index;
};
+#define I40_DDP_FLASH_REGION 100
+#define I40E_PROFILE_INFO_SIZE 48
+#define I40E_MAX_PROFILE_NUM 16
+#define I40E_PROFILE_LIST_SIZE \
+ (I40E_PROFILE_INFO_SIZE * I40E_MAX_PROFILE_NUM + 4)
+#define I40E_DDP_PROFILE_PATH "intel/i40e/ddp/"
+#define I40E_DDP_PROFILE_NAME_MAX 64
+
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+ bool is_add);
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
+
+struct i40e_ddp_profile_list {
+ u32 p_count;
+ struct i40e_profile_info p_info[0];
+};
+
+struct i40e_ddp_old_profile_list {
+ struct list_head list;
+ size_t old_ddp_size;
+ u8 old_ddp_buf[0];
+};
+
/* macros related to FLX_PIT */
#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
@@ -387,6 +412,11 @@
u8 pit_index;
};
+struct i40e_fwd_adapter {
+ struct net_device *netdev;
+ int bit_no;
+};
+
struct i40e_channel {
struct list_head list;
bool initialized;
@@ -401,11 +431,25 @@
struct i40e_aqc_vsi_properties_data info;
u64 max_tx_rate;
+ struct i40e_fwd_adapter *fwd;
/* track this channel belongs to which VSI */
struct i40e_vsi *parent_vsi;
};
+static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch)
+{
+ return !!ch->fwd;
+}
+
+static inline u8 *i40e_channel_mac(struct i40e_channel *ch)
+{
+ if (i40e_is_channel_macvlan(ch))
+ return ch->fwd->netdev->dev_addr;
+ else
+ return NULL;
+}
+
/* struct that defines the Ethernet device */
struct i40e_pf {
struct pci_dev *pdev;
@@ -494,7 +538,6 @@
#define I40E_HW_STOP_FW_LLDP BIT(16)
#define I40E_HW_PORT_ID_VALID BIT(17)
#define I40E_HW_RESTART_AUTONEG BIT(18)
-#define I40E_HW_STOPPABLE_FW_LLDP BIT(19)
u32 flags;
#define I40E_FLAG_RX_CSUM_ENABLED BIT(0)
@@ -522,6 +565,8 @@
#define I40E_FLAG_FD_SB_INACTIVE BIT(22)
#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER BIT(23)
#define I40E_FLAG_DISABLE_FW_LLDP BIT(24)
+#define I40E_FLAG_RS_FEC BIT(25)
+#define I40E_FLAG_BASE_R_FEC BIT(26)
struct i40e_client_instance *cinst;
bool stat_offsets_loaded;
@@ -585,6 +630,8 @@
struct sk_buff *ptp_tx_skb;
unsigned long ptp_tx_start;
struct hwtstamp_config tstamp_config;
+ struct timespec64 ptp_prev_hw_time;
+ ktime_t ptp_reset_start;
struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
u32 ptp_adj_mult;
u32 tx_hwtstamp_timeouts;
@@ -606,6 +653,8 @@
u16 override_q_count;
u16 last_sw_conf_flags;
u16 last_sw_conf_valid_flags;
+ /* List to keep previous DDP profiles to be rolled back in the future */
+ struct list_head ddp_old_prof;
};
/**
@@ -745,7 +794,8 @@
u16 alloc_queue_pairs; /* Allocated Tx/Rx queues */
u16 req_queue_pairs; /* User requested queue pairs */
u16 num_queue_pairs; /* Used tx and rx pairs */
- u16 num_desc;
+ u16 num_tx_desc;
+ u16 num_rx_desc;
enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */
s16 vf_id; /* Virtual function ID for SRIOV VSIs */
@@ -782,10 +832,19 @@
struct list_head ch_list;
u16 tc_seid_map[I40E_MAX_TRAFFIC_CLASS];
+ /* macvlan fields */
+#define I40E_MAX_MACVLANS 128 /* Max HW vectors - 1 on FVL */
+#define I40E_MIN_MACVLAN_VECTORS 2 /* Min vectors to enable macvlans */
+ DECLARE_BITMAP(fwd_bitmask, I40E_MAX_MACVLANS);
+ struct list_head macvlan_list;
+ int macvlan_cnt;
+
void *priv; /* client driver data reference. */
/* VSI specific handlers */
irqreturn_t (*irq_handler)(int irq, void *data);
+
+ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
} ____cacheline_internodealigned_in_smp;
struct i40e_netdev_priv {
@@ -961,6 +1020,7 @@
return NULL;
}
void i40e_update_stats(struct i40e_vsi *vsi);
+void i40e_update_veb_stats(struct i40e_veb *veb);
void i40e_update_eth_stats(struct i40e_vsi *vsi);
struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi);
int i40e_fetch_switch_configuration(struct i40e_pf *pf,
@@ -1077,6 +1137,8 @@
void i40e_ptp_set_increment(struct i40e_pf *pf);
int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
+void i40e_ptp_save_hw_time(struct i40e_pf *pf);
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
void i40e_ptp_init(struct i40e_pf *pf);
void i40e_ptp_stop(struct i40e_pf *pf);
int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
@@ -1085,6 +1147,8 @@
i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf);
void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags);
+
static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
{
return !!vsi->xdp_prog;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 501ee71..72c0488 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -588,6 +588,12 @@
hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+ hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+ }
+ if (hw->mac.type == I40E_MAC_X722 &&
+ hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+ hw->aq.api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722) {
+ hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
}
/* Newer versions of firmware require lock when reading the NVM */
@@ -602,6 +608,13 @@
hw->aq.api_min_ver >= 7))
hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
+ if (hw->aq.api_maj_ver > 1 ||
+ (hw->aq.api_maj_ver == 1 &&
+ hw->aq.api_min_ver >= 8)) {
+ hw->flags |= I40E_HW_FLAG_FW_LLDP_PERSISTENT;
+ hw->flags |= I40E_HW_FLAG_DROP_MODE;
+ }
+
if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
ret_code = I40E_ERR_FIRMWARE_API_VERSION;
goto init_adminq_free_arq;
@@ -664,7 +677,7 @@
desc = I40E_ADMINQ_DESC(*asq, ntc);
details = I40E_ADMINQ_DETAILS(*asq, ntc);
while (rd32(hw, hw->aq.asq.head) != ntc) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
"ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
if (details->callback) {
@@ -743,7 +756,7 @@
if (val >= hw->aq.num_asq_entries) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
"AQTX: head overrun at %d\n", val);
- status = I40E_ERR_QUEUE_EMPTY;
+ status = I40E_ERR_ADMIN_QUEUE_FULL;
goto asq_send_command_error;
}
@@ -824,7 +837,7 @@
}
/* bump the tail */
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n");
+ i40e_debug(hw, I40E_DEBUG_AQ_COMMAND, "AQTX: desc and buffer:\n");
i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring,
buff, buff_size);
(hw->aq.asq.next_to_use)++;
@@ -875,7 +888,7 @@
hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
}
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
"AQTX: desc and buffer writeback:\n");
i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size);
@@ -984,7 +997,7 @@
memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
e->msg_len);
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
+ i40e_debug(hw, I40E_DEBUG_AQ_COMMAND, "AQRX: desc and buffer:\n");
i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf,
hw->aq.arq_buf_size);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 80e3eec..69a2daa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -11,8 +11,8 @@
*/
#define I40E_FW_API_VERSION_MAJOR 0x0001
-#define I40E_FW_API_VERSION_MINOR_X722 0x0005
-#define I40E_FW_API_VERSION_MINOR_X710 0x0007
+#define I40E_FW_API_VERSION_MINOR_X722 0x0009
+#define I40E_FW_API_VERSION_MINOR_X710 0x0009
#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
I40E_FW_API_VERSION_MINOR_X710 : \
@@ -20,6 +20,10 @@
/* API version 1.7 implements additional link and PHY-specific APIs */
#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+/* API version 1.9 for X722 implements additional link and PHY-specific APIs */
+#define I40E_MINOR_VER_GET_LINK_INFO_X722 0x0009
+/* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */
+#define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006
struct i40e_aq_desc {
__le16 flags;
@@ -259,6 +263,7 @@
i40e_aqc_opc_get_cee_dcb_cfg = 0x0A07,
i40e_aqc_opc_lldp_set_local_mib = 0x0A08,
i40e_aqc_opc_lldp_stop_start_spec_agent = 0x0A09,
+ i40e_aqc_opc_lldp_restore = 0x0A0A,
/* Tunnel commands */
i40e_aqc_opc_add_udp_tunnel = 0x0B00,
@@ -1379,7 +1384,7 @@
#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \
I40E_AQC_ADD_CLOUD_FILTER_SHIFT)
/* 0x0000 reserved */
-#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001
+/* 0x0001 reserved */
/* 0x0002 reserved */
#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003
#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID 0x0004
@@ -1391,6 +1396,9 @@
#define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A
#define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B
#define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C
+/* 0x000D reserved */
+/* 0x000E reserved */
+/* 0x000F reserved */
/* 0x0010 to 0x0017 is for custom filters */
#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */
#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */
@@ -1885,6 +1893,8 @@
I40E_PHY_TYPE_25GBASE_LR = 0x22,
I40E_PHY_TYPE_25GBASE_AOC = 0x23,
I40E_PHY_TYPE_25GBASE_ACC = 0x24,
+ I40E_PHY_TYPE_2_5GBASE_T = 0x30,
+ I40E_PHY_TYPE_5GBASE_T = 0x31,
I40E_PHY_TYPE_MAX,
I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
I40E_PHY_TYPE_EMPTY = 0xFE,
@@ -1926,19 +1936,25 @@
BIT_ULL(I40E_PHY_TYPE_25GBASE_SR) | \
BIT_ULL(I40E_PHY_TYPE_25GBASE_LR) | \
BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC) | \
- BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC))
+ BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC) | \
+ BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T) | \
+ BIT_ULL(I40E_PHY_TYPE_5GBASE_T))
+#define I40E_LINK_SPEED_2_5GB_SHIFT 0x0
#define I40E_LINK_SPEED_100MB_SHIFT 0x1
#define I40E_LINK_SPEED_1000MB_SHIFT 0x2
#define I40E_LINK_SPEED_10GB_SHIFT 0x3
#define I40E_LINK_SPEED_40GB_SHIFT 0x4
#define I40E_LINK_SPEED_20GB_SHIFT 0x5
#define I40E_LINK_SPEED_25GB_SHIFT 0x6
+#define I40E_LINK_SPEED_5GB_SHIFT 0x7
enum i40e_aq_link_speed {
I40E_LINK_SPEED_UNKNOWN = 0,
I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT),
I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT),
+ I40E_LINK_SPEED_2_5GB = (1 << I40E_LINK_SPEED_2_5GB_SHIFT),
+ I40E_LINK_SPEED_5GB = (1 << I40E_LINK_SPEED_5GB_SHIFT),
I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT),
I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT),
I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT),
@@ -1984,6 +2000,8 @@
#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08
#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10
#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20
+#define I40E_AQ_PHY_TYPE_EXT_2_5GBASE_T 0x40
+#define I40E_AQ_PHY_TYPE_EXT_5GBASE_T 0x80
u8 fec_cfg_curr_mod_ext_info;
#define I40E_AQ_ENABLE_FEC_KR 0x01
#define I40E_AQ_ENABLE_FEC_RS 0x02
@@ -2038,20 +2056,21 @@
struct i40e_aq_set_mac_config {
__le16 max_frame_size;
u8 params;
-#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04
-#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78
-#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7
-#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4
-#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2
-#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1
+#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04
+#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78
+#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3
+#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8
+#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7
+#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6
+#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5
+#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4
+#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3
+#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2
+#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1
+#define I40E_AQ_SET_MAC_CONFIG_DROP_BLOCKING_PACKET_EN 0x80
u8 tx_timer_priority; /* bitmap */
__le16 tx_timer_value;
__le16 fc_refresh_threshold;
@@ -2496,18 +2515,19 @@
/* Stop LLDP (direct 0x0A05) */
struct i40e_aqc_lldp_stop {
u8 command;
-#define I40E_AQ_LLDP_AGENT_STOP 0x0
-#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1
+#define I40E_AQ_LLDP_AGENT_STOP 0x0
+#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1
+#define I40E_AQ_LLDP_AGENT_STOP_PERSIST 0x2
u8 reserved[15];
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop);
/* Start LLDP (direct 0x0A06) */
-
struct i40e_aqc_lldp_start {
u8 command;
-#define I40E_AQ_LLDP_AGENT_START 0x1
+#define I40E_AQ_LLDP_AGENT_START 0x1
+#define I40E_AQ_LLDP_AGENT_START_PERSIST 0x2
u8 reserved[15];
};
@@ -2631,6 +2651,16 @@
I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop_start_specific_agent);
+/* Restore LLDP Agent factory settings (direct 0x0A0A) */
+struct i40e_aqc_lldp_restore {
+ u8 command;
+#define I40E_AQ_LLDP_AGENT_RESTORE_NOT 0x0
+#define I40E_AQ_LLDP_AGENT_RESTORE 0x1
+ u8 reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_restore);
+
/* Add Udp Tunnel command and completion (direct 0x0B00) */
struct i40e_aqc_add_udp_tunnel {
__le16 udp_port;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 5f3b8b9..e81530c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -578,11 +578,9 @@
struct i40e_hw *hw = &pf->hw;
struct i40e_qv_info *qv_info;
u32 v_idx, i, reg_idx, reg;
- u32 size;
- size = sizeof(struct i40e_qvlist_info) +
- (sizeof(struct i40e_qv_info) * (qvlist_info->num_vectors - 1));
- ldev->qvlist_info = kzalloc(size, GFP_KERNEL);
+ ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info,
+ qvlist_info->num_vectors - 1), GFP_KERNEL);
if (!ldev->qvlist_info)
return -ENOMEM;
ldev->qvlist_info->num_vectors = qvlist_info->num_vectors;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 85f75b5..7560f06 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_type.h"
#include "i40e_adminq.h"
#include "i40e_prototype.h"
@@ -13,7 +14,7 @@
* This function sets the mac type of the adapter based on the
* vendor ID and device ID stored in the hw structure.
**/
-static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
+i40e_status i40e_set_mac_type(struct i40e_hw *hw)
{
i40e_status status = 0;
@@ -28,10 +29,14 @@
case I40E_DEV_ID_QSFP_C:
case I40E_DEV_ID_10G_BASE_T:
case I40E_DEV_ID_10G_BASE_T4:
+ case I40E_DEV_ID_10G_B:
+ case I40E_DEV_ID_10G_SFP:
case I40E_DEV_ID_20G_KR2:
case I40E_DEV_ID_20G_KR2_A:
case I40E_DEV_ID_25G_B:
case I40E_DEV_ID_25G_SFP28:
+ case I40E_DEV_ID_X710_N3000:
+ case I40E_DEV_ID_XXV710_N3000:
hw->mac.type = I40E_MAC_XL710;
break;
case I40E_DEV_ID_KX_X722:
@@ -277,47 +282,49 @@
void *buffer, u16 buf_len)
{
struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+ u32 effective_mask = hw->debug_mask & mask;
+ char prefix[27];
u16 len;
u8 *buf = (u8 *)buffer;
- if ((!(mask & hw->debug_mask)) || (desc == NULL))
+ if (!effective_mask || !desc)
return;
len = le16_to_cpu(aq_desc->datalen);
- i40e_debug(hw, mask,
+ i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
"AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
le16_to_cpu(aq_desc->opcode),
le16_to_cpu(aq_desc->flags),
le16_to_cpu(aq_desc->datalen),
le16_to_cpu(aq_desc->retval));
- i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n",
+ i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+ "\tcookie (h,l) 0x%08X 0x%08X\n",
le32_to_cpu(aq_desc->cookie_high),
le32_to_cpu(aq_desc->cookie_low));
- i40e_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n",
+ i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+ "\tparam (0,1) 0x%08X 0x%08X\n",
le32_to_cpu(aq_desc->params.internal.param0),
le32_to_cpu(aq_desc->params.internal.param1));
- i40e_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n",
+ i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+ "\taddr (h,l) 0x%08X 0x%08X\n",
le32_to_cpu(aq_desc->params.external.addr_high),
le32_to_cpu(aq_desc->params.external.addr_low));
- if ((buffer != NULL) && (aq_desc->datalen != 0)) {
+ if (buffer && buf_len != 0 && len != 0 &&
+ (effective_mask & I40E_DEBUG_AQ_DESC_BUFFER)) {
i40e_debug(hw, mask, "AQ CMD Buffer:\n");
if (buf_len < len)
len = buf_len;
- /* write the full 16-byte chunks */
- if (hw->debug_mask & mask) {
- char prefix[27];
- snprintf(prefix, sizeof(prefix),
- "i40e %02x:%02x.%x: \t0x",
- hw->bus.bus_id,
- hw->bus.device,
- hw->bus.func);
+ snprintf(prefix, sizeof(prefix),
+ "i40e %02x:%02x.%x: \t0x",
+ hw->bus.bus_id,
+ hw->bus.device,
+ hw->bus.func);
- print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
- 16, 1, buf, len, false);
- }
+ print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
+ 16, 1, buf, len, false);
}
}
@@ -1149,6 +1156,8 @@
break;
case I40E_PHY_TYPE_100BASE_TX:
case I40E_PHY_TYPE_1000BASE_T:
+ case I40E_PHY_TYPE_2_5GBASE_T:
+ case I40E_PHY_TYPE_5GBASE_T:
case I40E_PHY_TYPE_10GBASE_T:
media = I40E_MEDIA_TYPE_BASET;
break;
@@ -1466,7 +1475,6 @@
**/
u32 i40e_led_get(struct i40e_hw *hw)
{
- u32 current_mode = 0;
u32 mode = 0;
int i;
@@ -1479,21 +1487,6 @@
if (!gpio_val)
continue;
- /* ignore gpio LED src mode entries related to the activity
- * LEDs
- */
- current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
- >> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
- switch (current_mode) {
- case I40E_COMBINED_ACTIVITY:
- case I40E_FILTER_ACTIVITY:
- case I40E_MAC_ACTIVITY:
- case I40E_LINK_ACTIVITY:
- continue;
- default:
- break;
- }
-
mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK) >>
I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT;
break;
@@ -1513,7 +1506,6 @@
**/
void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
{
- u32 current_mode = 0;
int i;
if (mode & 0xfffffff0)
@@ -1527,22 +1519,6 @@
if (!gpio_val)
continue;
-
- /* ignore gpio LED src mode entries related to the activity
- * LEDs
- */
- current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
- >> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
- switch (current_mode) {
- case I40E_COMBINED_ACTIVITY:
- case I40E_FILTER_ACTIVITY:
- case I40E_MAC_ACTIVITY:
- case I40E_LINK_ACTIVITY:
- continue;
- default:
- break;
- }
-
gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
/* this & is a bit of paranoia, but serves as a range check */
gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) &
@@ -1602,19 +1578,22 @@
status = i40e_asq_send_command(hw, &desc, abilities,
abilities_size, cmd_details);
- if (status)
- break;
-
- if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) {
+ switch (hw->aq.asq_last_status) {
+ case I40E_AQ_RC_EIO:
status = I40E_ERR_UNKNOWN_PHY;
break;
- } else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) {
+ case I40E_AQ_RC_EAGAIN:
usleep_range(1000, 2000);
total_delay++;
status = I40E_ERR_TIMEOUT;
+ break;
+ /* also covers I40E_AQ_RC_OK */
+ default:
+ break;
}
- } while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) &&
- (total_delay < max_delay));
+
+ } while ((hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) &&
+ (total_delay < max_delay));
if (status)
return status;
@@ -1668,25 +1647,15 @@
return status;
}
-/**
- * i40e_set_fc
- * @hw: pointer to the hw struct
- * @aq_failures: buffer to return AdminQ failure information
- * @atomic_restart: whether to enable atomic link restart
- *
- * Set the requested flow control mode using set_phy_config.
- **/
-enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
- bool atomic_restart)
+static noinline_for_stack enum i40e_status_code
+i40e_set_fc_status(struct i40e_hw *hw,
+ struct i40e_aq_get_phy_abilities_resp *abilities,
+ bool atomic_restart)
{
- enum i40e_fc_mode fc_mode = hw->fc.requested_mode;
- struct i40e_aq_get_phy_abilities_resp abilities;
struct i40e_aq_set_phy_config config;
- enum i40e_status_code status;
+ enum i40e_fc_mode fc_mode = hw->fc.requested_mode;
u8 pause_mask = 0x0;
- *aq_failures = 0x0;
-
switch (fc_mode) {
case I40E_FC_FULL:
pause_mask |= I40E_AQ_PHY_FLAG_PAUSE_TX;
@@ -1702,6 +1671,48 @@
break;
}
+ memset(&config, 0, sizeof(struct i40e_aq_set_phy_config));
+ /* clear the old pause settings */
+ config.abilities = abilities->abilities & ~(I40E_AQ_PHY_FLAG_PAUSE_TX) &
+ ~(I40E_AQ_PHY_FLAG_PAUSE_RX);
+ /* set the new abilities */
+ config.abilities |= pause_mask;
+ /* If the abilities have changed, then set the new config */
+ if (config.abilities == abilities->abilities)
+ return 0;
+
+ /* Auto restart link so settings take effect */
+ if (atomic_restart)
+ config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK;
+ /* Copy over all the old settings */
+ config.phy_type = abilities->phy_type;
+ config.phy_type_ext = abilities->phy_type_ext;
+ config.link_speed = abilities->link_speed;
+ config.eee_capability = abilities->eee_capability;
+ config.eeer = abilities->eeer_val;
+ config.low_power_ctrl = abilities->d3_lpan;
+ config.fec_config = abilities->fec_cfg_curr_mod_ext_info &
+ I40E_AQ_PHY_FEC_CONFIG_MASK;
+
+ return i40e_aq_set_phy_config(hw, &config, NULL);
+}
+
+/**
+ * i40e_set_fc
+ * @hw: pointer to the hw struct
+ * @aq_failures: buffer to return AdminQ failure information
+ * @atomic_restart: whether to enable atomic link restart
+ *
+ * Set the requested flow control mode using set_phy_config.
+ **/
+enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
+ bool atomic_restart)
+{
+ struct i40e_aq_get_phy_abilities_resp abilities;
+ enum i40e_status_code status;
+
+ *aq_failures = 0x0;
+
/* Get the current phy config */
status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
NULL);
@@ -1710,31 +1721,10 @@
return status;
}
- memset(&config, 0, sizeof(struct i40e_aq_set_phy_config));
- /* clear the old pause settings */
- config.abilities = abilities.abilities & ~(I40E_AQ_PHY_FLAG_PAUSE_TX) &
- ~(I40E_AQ_PHY_FLAG_PAUSE_RX);
- /* set the new abilities */
- config.abilities |= pause_mask;
- /* If the abilities have changed, then set the new config */
- if (config.abilities != abilities.abilities) {
- /* Auto restart link so settings take effect */
- if (atomic_restart)
- config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK;
- /* Copy over all the old settings */
- config.phy_type = abilities.phy_type;
- config.phy_type_ext = abilities.phy_type_ext;
- config.link_speed = abilities.link_speed;
- config.eee_capability = abilities.eee_capability;
- config.eeer = abilities.eeer_val;
- config.low_power_ctrl = abilities.d3_lpan;
- config.fec_config = abilities.fec_cfg_curr_mod_ext_info &
- I40E_AQ_PHY_FEC_CONFIG_MASK;
- status = i40e_aq_set_phy_config(hw, &config, NULL);
+ status = i40e_set_fc_status(hw, &abilities, atomic_restart);
+ if (status)
+ *aq_failures |= I40E_SET_FC_AQ_FAIL_SET;
- if (status)
- *aq_failures |= I40E_SET_FC_AQ_FAIL_SET;
- }
/* Update the link info */
status = i40e_update_link_info(hw);
if (status) {
@@ -1886,8 +1876,8 @@
hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
- if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
- hw->aq.api_min_ver >= 7) {
+ if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE &&
+ hw->mac.type != I40E_MAC_X722) {
__le32 tmp;
memcpy(&tmp, resp->link_type, sizeof(tmp));
@@ -2563,7 +2553,7 @@
* i40e_updatelink_status - update status of the HW network link
* @hw: pointer to the hw struct
**/
-i40e_status i40e_update_link_info(struct i40e_hw *hw)
+noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw)
{
struct i40e_aq_get_phy_abilities_resp abilities;
i40e_status status = 0;
@@ -3657,14 +3647,54 @@
}
/**
+ * i40e_aq_restore_lldp
+ * @hw: pointer to the hw struct
+ * @setting: pointer to factory setting variable or NULL
+ * @restore: True if factory settings should be restored
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Restore LLDP Agent factory settings if @restore set to True. In other case
+ * only returns factory setting in AQ response.
+ **/
+enum i40e_status_code
+i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_lldp_restore *cmd =
+ (struct i40e_aqc_lldp_restore *)&desc.params.raw;
+ i40e_status status;
+
+ if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) {
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Restore LLDP not supported by current FW version.\n");
+ return I40E_ERR_DEVICE_NOT_SUPPORTED;
+ }
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore);
+
+ if (restore)
+ cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE;
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ if (setting)
+ *setting = cmd->command & 1;
+
+ return status;
+}
+
+/**
* i40e_aq_stop_lldp
* @hw: pointer to the hw struct
* @shutdown_agent: True if LLDP Agent needs to be Shutdown
+ * @persist: True if stop of LLDP should be persistent across power cycles
* @cmd_details: pointer to command details structure or NULL
*
* Stop or Shutdown the embedded LLDP Agent
**/
i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+ bool persist,
struct i40e_asq_cmd_details *cmd_details)
{
struct i40e_aq_desc desc;
@@ -3677,6 +3707,14 @@
if (shutdown_agent)
cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
+ if (persist) {
+ if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+ cmd->command |= I40E_AQ_LLDP_AGENT_STOP_PERSIST;
+ else
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Persistent Stop LLDP not supported by current FW version.\n");
+ }
+
status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
return status;
@@ -3686,13 +3724,14 @@
* i40e_aq_start_lldp
* @hw: pointer to the hw struct
* @buff: buffer for result
+ * @persist: True if start of LLDP should be persistent across power cycles
* @buff_size: buffer size
* @cmd_details: pointer to command details structure or NULL
*
* Start the embedded LLDP Agent on all ports.
**/
-i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
- struct i40e_asq_cmd_details *cmd_details)
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
+ struct i40e_asq_cmd_details *cmd_details)
{
struct i40e_aq_desc desc;
struct i40e_aqc_lldp_start *cmd =
@@ -3702,6 +3741,15 @@
i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start);
cmd->command = I40E_AQ_LLDP_AGENT_START;
+
+ if (persist) {
+ if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+ cmd->command |= I40E_AQ_LLDP_AGENT_START_PERSIST;
+ else
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Persistent Start LLDP not supported by current FW version.\n");
+ }
+
status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
return status;
@@ -3723,6 +3771,9 @@
(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
i40e_status status;
+ if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+ return I40E_ERR_DEVICE_NOT_SUPPORTED;
+
i40e_fill_default_direct_cmd_desc(&desc,
i40e_aqc_opc_set_dcb_parameters);
@@ -4870,6 +4921,7 @@
break;
case I40E_DEV_ID_10G_BASE_T:
case I40E_DEV_ID_10G_BASE_T4:
+ case I40E_DEV_ID_10G_BASE_T_BC:
case I40E_DEV_ID_10G_BASE_T_X722:
case I40E_DEV_ID_25G_B:
case I40E_DEV_ID_25G_SFP28:
@@ -5445,6 +5497,163 @@
return NULL;
}
+/* Get section table in profile */
+#define I40E_SECTION_TABLE(profile, sec_tbl) \
+ do { \
+ struct i40e_profile_segment *p = (profile); \
+ u32 count; \
+ u32 *nvm; \
+ count = p->device_table_count; \
+ nvm = (u32 *)&p->device_table[count]; \
+ sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; \
+ } while (0)
+
+/* Get section header in profile */
+#define I40E_SECTION_HEADER(profile, offset) \
+ (struct i40e_profile_section_header *)((u8 *)(profile) + (offset))
+
+/**
+ * i40e_find_section_in_profile
+ * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE)
+ * @profile: pointer to the i40e segment header to be searched
+ *
+ * This function searches i40e segment for a particular section type. On
+ * success it returns a pointer to the section header, otherwise it will
+ * return NULL.
+ **/
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+ struct i40e_profile_segment *profile)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_section_table *sec_tbl;
+ u32 sec_off;
+ u32 i;
+
+ if (profile->header.type != SEGMENT_TYPE_I40E)
+ return NULL;
+
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ for (i = 0; i < sec_tbl->section_count; i++) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ if (sec->section.type == section_type)
+ return sec;
+ }
+
+ return NULL;
+}
+
+/**
+ * i40e_ddp_exec_aq_section - Execute generic AQ for DDP
+ * @hw: pointer to the hw struct
+ * @aq: command buffer containing all data to execute AQ
+ **/
+static enum
+i40e_status_code i40e_ddp_exec_aq_section(struct i40e_hw *hw,
+ struct i40e_profile_aq_section *aq)
+{
+ i40e_status status;
+ struct i40e_aq_desc desc;
+ u8 *msg = NULL;
+ u16 msglen;
+
+ i40e_fill_default_direct_cmd_desc(&desc, aq->opcode);
+ desc.flags |= cpu_to_le16(aq->flags);
+ memcpy(desc.params.raw, aq->param, sizeof(desc.params.raw));
+
+ msglen = aq->datalen;
+ if (msglen) {
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
+ I40E_AQ_FLAG_RD));
+ if (msglen > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+ desc.datalen = cpu_to_le16(msglen);
+ msg = &aq->data[0];
+ }
+
+ status = i40e_asq_send_command(hw, &desc, msg, msglen, NULL);
+
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "unable to exec DDP AQ opcode %u, error %d\n",
+ aq->opcode, status);
+ return status;
+ }
+
+ /* copy returned desc to aq_buf */
+ memcpy(aq->param, desc.params.raw, sizeof(desc.params.raw));
+
+ return 0;
+}
+
+/**
+ * i40e_validate_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be validated
+ * @track_id: package tracking id
+ * @rollback: flag if the profile is for rollback.
+ *
+ * Validates supported devices and profile's sections.
+ */
+static enum i40e_status_code
+i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u32 track_id, bool rollback)
+{
+ struct i40e_profile_section_header *sec = NULL;
+ i40e_status status = 0;
+ struct i40e_section_table *sec_tbl;
+ u32 vendor_dev_id;
+ u32 dev_cnt;
+ u32 sec_off;
+ u32 i;
+
+ if (track_id == I40E_DDP_TRACKID_INVALID) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE, "Invalid track_id\n");
+ return I40E_NOT_SUPPORTED;
+ }
+
+ dev_cnt = profile->device_table_count;
+ for (i = 0; i < dev_cnt; i++) {
+ vendor_dev_id = profile->device_table[i].vendor_dev_id;
+ if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL &&
+ hw->device_id == (vendor_dev_id & 0xFFFF))
+ break;
+ }
+ if (dev_cnt && i == dev_cnt) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Device doesn't support DDP\n");
+ return I40E_ERR_DEVICE_NOT_SUPPORTED;
+ }
+
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ /* Validate sections types */
+ for (i = 0; i < sec_tbl->section_count; i++) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ if (rollback) {
+ if (sec->section.type == SECTION_TYPE_MMIO ||
+ sec->section.type == SECTION_TYPE_AQ ||
+ sec->section.type == SECTION_TYPE_RB_AQ) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Not a roll-back package\n");
+ return I40E_NOT_SUPPORTED;
+ }
+ } else {
+ if (sec->section.type == SECTION_TYPE_RB_AQ ||
+ sec->section.type == SECTION_TYPE_RB_MMIO) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Not an original package\n");
+ return I40E_NOT_SUPPORTED;
+ }
+ }
+ }
+
+ return status;
+}
+
/**
* i40e_write_profile
* @hw: pointer to the hardware structure
@@ -5460,47 +5669,99 @@
i40e_status status = 0;
struct i40e_section_table *sec_tbl;
struct i40e_profile_section_header *sec = NULL;
- u32 dev_cnt;
- u32 vendor_dev_id;
- u32 *nvm;
+ struct i40e_profile_aq_section *ddp_aq;
u32 section_size = 0;
u32 offset = 0, info = 0;
+ u32 sec_off;
u32 i;
- dev_cnt = profile->device_table_count;
+ status = i40e_validate_profile(hw, profile, track_id, false);
+ if (status)
+ return status;
- for (i = 0; i < dev_cnt; i++) {
- vendor_dev_id = profile->device_table[i].vendor_dev_id;
- if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
- if (hw->device_id == (vendor_dev_id & 0xFFFF))
- break;
- }
- if (i == dev_cnt) {
- i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP");
- return I40E_ERR_DEVICE_NOT_SUPPORTED;
- }
-
- nvm = (u32 *)&profile->device_table[dev_cnt];
- sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
+ I40E_SECTION_TABLE(profile, sec_tbl);
for (i = 0; i < sec_tbl->section_count; i++) {
- sec = (struct i40e_profile_section_header *)((u8 *)profile +
- sec_tbl->section_offset[i]);
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ /* Process generic admin command */
+ if (sec->section.type == SECTION_TYPE_AQ) {
+ ddp_aq = (struct i40e_profile_aq_section *)&sec[1];
+ status = i40e_ddp_exec_aq_section(hw, ddp_aq);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Failed to execute aq: section %d, opcode %u\n",
+ i, ddp_aq->opcode);
+ break;
+ }
+ sec->section.type = SECTION_TYPE_RB_AQ;
+ }
- /* Skip 'AQ', 'note' and 'name' sections */
+ /* Skip any non-mmio sections */
if (sec->section.type != SECTION_TYPE_MMIO)
continue;
section_size = sec->section.size +
sizeof(struct i40e_profile_section_header);
- /* Write profile */
+ /* Write MMIO section */
status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
track_id, &offset, &info, NULL);
if (status) {
i40e_debug(hw, I40E_DEBUG_PACKAGE,
- "Failed to write profile: offset %d, info %d",
- offset, info);
+ "Failed to write profile: section %d, offset %d, info %d\n",
+ i, offset, info);
+ break;
+ }
+ }
+ return status;
+}
+
+/**
+ * i40e_rollback_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be removed
+ * @track_id: package tracking id
+ *
+ * Rolls back previously loaded package.
+ */
+enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u32 track_id)
+{
+ struct i40e_profile_section_header *sec = NULL;
+ i40e_status status = 0;
+ struct i40e_section_table *sec_tbl;
+ u32 offset = 0, info = 0;
+ u32 section_size = 0;
+ u32 sec_off;
+ int i;
+
+ status = i40e_validate_profile(hw, profile, track_id, true);
+ if (status)
+ return status;
+
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ /* For rollback write sections in reverse */
+ for (i = sec_tbl->section_count - 1; i >= 0; i--) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+
+ /* Skip any non-rollback sections */
+ if (sec->section.type != SECTION_TYPE_RB_MMIO)
+ continue;
+
+ section_size = sec->section.size +
+ sizeof(struct i40e_profile_section_header);
+
+ /* Write roll-back MMIO section */
+ status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
+ track_id, &offset, &info, NULL);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Failed to write profile: section %d, offset %d, info %d\n",
+ i, offset, info);
break;
}
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 56bff8f..200a1cb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -863,22 +863,39 @@
/**
* i40e_init_dcb
* @hw: pointer to the hw struct
+ * @enable_mib_change: enable mib change event
*
* Update DCB configuration from the Firmware
**/
-i40e_status i40e_init_dcb(struct i40e_hw *hw)
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
{
i40e_status ret = 0;
struct i40e_lldp_variables lldp_cfg;
u8 adminstatus = 0;
if (!hw->func_caps.dcb)
- return ret;
+ return I40E_NOT_SUPPORTED;
/* Read LLDP NVM area */
- ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
+ if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT) {
+ u8 offset = 0;
+
+ if (hw->mac.type == I40E_MAC_XL710)
+ offset = I40E_LLDP_CURRENT_STATUS_XL710_OFFSET;
+ else if (hw->mac.type == I40E_MAC_X722)
+ offset = I40E_LLDP_CURRENT_STATUS_X722_OFFSET;
+ else
+ return I40E_NOT_SUPPORTED;
+
+ ret = i40e_read_nvm_module_data(hw,
+ I40E_SR_EMP_SR_SETTINGS_PTR,
+ offset, 1,
+ &lldp_cfg.adminstatus);
+ } else {
+ ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
+ }
if (ret)
- return ret;
+ return I40E_ERR_NOT_READY;
/* Get the LLDP AdminStatus for the current port */
adminstatus = lldp_cfg.adminstatus >> (hw->port * 4);
@@ -887,7 +904,7 @@
/* LLDP agent disabled */
if (!adminstatus) {
hw->dcbx_status = I40E_DCBX_STATUS_DISABLED;
- return ret;
+ return I40E_ERR_NOT_READY;
}
/* Get DCBX status */
@@ -896,26 +913,19 @@
return ret;
/* Check the DCBX Status */
- switch (hw->dcbx_status) {
- case I40E_DCBX_STATUS_DONE:
- case I40E_DCBX_STATUS_IN_PROGRESS:
+ if (hw->dcbx_status == I40E_DCBX_STATUS_DONE ||
+ hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) {
/* Get current DCBX configuration */
ret = i40e_get_dcb_config(hw);
if (ret)
return ret;
- break;
- case I40E_DCBX_STATUS_DISABLED:
- return ret;
- case I40E_DCBX_STATUS_NOT_STARTED:
- case I40E_DCBX_STATUS_MULTIPLE_PEERS:
- default:
- break;
+ } else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
+ return I40E_ERR_NOT_READY;
}
/* Configure the LLDP MIB change event */
- ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
- if (ret)
- return ret;
+ if (enable_mib_change)
+ ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
return ret;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 2b748a6..2a80c5d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -30,6 +30,8 @@
#define I40E_CEE_SUBTYPE_APP_PRI 4
#define I40E_CEE_MAX_FEAT_TYPE 3
+#define I40E_LLDP_CURRENT_STATUS_XL710_OFFSET 0x2B
+#define I40E_LLDP_CURRENT_STATUS_X722_OFFSET 0x31
/* Defines for LLDP TLV header */
#define I40E_LLDP_TLV_LEN_SHIFT 0
#define I40E_LLDP_TLV_LEN_MASK (0x01FF << I40E_LLDP_TLV_LEN_SHIFT)
@@ -124,5 +126,5 @@
u8 bridgetype,
struct i40e_dcbx_config *dcbcfg);
i40e_status i40e_get_dcb_config(struct i40e_hw *hw);
-i40e_status i40e_init_dcb(struct i40e_hw *hw);
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change);
#endif /* _I40E_DCB_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
new file mode 100644
index 0000000..5e08f10
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "i40e.h"
+
+#include <linux/firmware.h>
+
+/**
+ * i40e_ddp_profiles_eq - checks if DDP profiles are the equivalent
+ * @a: new profile info
+ * @b: old profile info
+ *
+ * checks if DDP profiles are the equivalent.
+ * Returns true if profiles are the same.
+ **/
+static bool i40e_ddp_profiles_eq(struct i40e_profile_info *a,
+ struct i40e_profile_info *b)
+{
+ return a->track_id == b->track_id &&
+ !memcmp(&a->version, &b->version, sizeof(a->version)) &&
+ !memcmp(&a->name, &b->name, I40E_DDP_NAME_SIZE);
+}
+
+/**
+ * i40e_ddp_does_profile_exist - checks if DDP profile loaded already
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile loaded already.
+ * Returns >0 if the profile exists.
+ * Returns 0 if the profile is absent.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_exist(struct i40e_hw *hw,
+ struct i40e_profile_info *pinfo)
+{
+ struct i40e_ddp_profile_list *profile_list;
+ u8 buff[I40E_PROFILE_LIST_SIZE];
+ i40e_status status;
+ int i;
+
+ status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+ NULL);
+ if (status)
+ return -1;
+
+ profile_list = (struct i40e_ddp_profile_list *)buff;
+ for (i = 0; i < profile_list->p_count; i++) {
+ if (i40e_ddp_profiles_eq(pinfo, &profile_list->p_info[i]))
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * i40e_ddp_profiles_overlap - checks if DDP profiles overlap.
+ * @new: new profile info
+ * @old: old profile info
+ *
+ * checks if DDP profiles overlap.
+ * Returns true if profiles are overlap.
+ **/
+static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new,
+ struct i40e_profile_info *old)
+{
+ unsigned int group_id_old = (u8)((old->track_id & 0x00FF0000) >> 16);
+ unsigned int group_id_new = (u8)((new->track_id & 0x00FF0000) >> 16);
+
+ /* 0x00 group must be only the first */
+ if (group_id_new == 0)
+ return true;
+ /* 0xFF group is compatible with anything else */
+ if (group_id_new == 0xFF || group_id_old == 0xFF)
+ return false;
+ /* otherwise only profiles from the same group are compatible*/
+ return group_id_old != group_id_new;
+}
+
+/**
+ * i40e_ddp_does_profiles_ - checks if DDP overlaps with existing one.
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile overlaps with existing one.
+ * Returns >0 if the profile overlaps.
+ * Returns 0 if the profile is ok.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_overlap(struct i40e_hw *hw,
+ struct i40e_profile_info *pinfo)
+{
+ struct i40e_ddp_profile_list *profile_list;
+ u8 buff[I40E_PROFILE_LIST_SIZE];
+ i40e_status status;
+ int i;
+
+ status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+ NULL);
+ if (status)
+ return -EIO;
+
+ profile_list = (struct i40e_ddp_profile_list *)buff;
+ for (i = 0; i < profile_list->p_count; i++) {
+ if (i40e_ddp_profiles_overlap(pinfo,
+ &profile_list->p_info[i]))
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * i40e_add_pinfo
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package
+ * @profile_info_sec: buffer for information section
+ * @track_id: package tracking id
+ *
+ * Register a profile to the list of loaded profiles.
+ */
+static enum i40e_status_code
+i40e_add_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u8 *profile_info_sec, u32 track_id)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_profile_info *pinfo;
+ i40e_status status;
+ u32 offset = 0, info = 0;
+
+ sec = (struct i40e_profile_section_header *)profile_info_sec;
+ sec->tbl_size = 1;
+ sec->data_end = sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info);
+ sec->section.type = SECTION_TYPE_INFO;
+ sec->section.offset = sizeof(struct i40e_profile_section_header);
+ sec->section.size = sizeof(struct i40e_profile_info);
+ pinfo = (struct i40e_profile_info *)(profile_info_sec +
+ sec->section.offset);
+ pinfo->track_id = track_id;
+ pinfo->version = profile->version;
+ pinfo->op = I40E_DDP_ADD_TRACKID;
+
+ /* Clear reserved field */
+ memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+ memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+ status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+ track_id, &offset, &info, NULL);
+ return status;
+}
+
+/**
+ * i40e_del_pinfo - delete DDP profile info from NIC
+ * @hw: HW data structure
+ * @profile: DDP profile segment to be deleted
+ * @profile_info_sec: DDP profile section header
+ * @track_id: track ID of the profile for deletion
+ *
+ * Removes DDP profile from the NIC.
+ **/
+static enum i40e_status_code
+i40e_del_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u8 *profile_info_sec, u32 track_id)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_profile_info *pinfo;
+ i40e_status status;
+ u32 offset = 0, info = 0;
+
+ sec = (struct i40e_profile_section_header *)profile_info_sec;
+ sec->tbl_size = 1;
+ sec->data_end = sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info);
+ sec->section.type = SECTION_TYPE_INFO;
+ sec->section.offset = sizeof(struct i40e_profile_section_header);
+ sec->section.size = sizeof(struct i40e_profile_info);
+ pinfo = (struct i40e_profile_info *)(profile_info_sec +
+ sec->section.offset);
+ pinfo->track_id = track_id;
+ pinfo->version = profile->version;
+ pinfo->op = I40E_DDP_REMOVE_TRACKID;
+
+ /* Clear reserved field */
+ memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+ memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+ status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+ track_id, &offset, &info, NULL);
+ return status;
+}
+
+/**
+ * i40e_ddp_is_pkg_hdr_valid - performs basic pkg header integrity checks
+ * @netdev: net device structure (for logging purposes)
+ * @pkg_hdr: pointer to package header
+ * @size_huge: size of the whole DDP profile package in size_t
+ *
+ * Checks correctness of pkg header: Version, size too big/small, and
+ * all segment offsets alignment and boundaries. This function lets
+ * reject non DDP profile file to be loaded by administrator mistake.
+ **/
+static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev,
+ struct i40e_package_header *pkg_hdr,
+ size_t size_huge)
+{
+ u32 size = 0xFFFFFFFFU & size_huge;
+ u32 pkg_hdr_size;
+ u32 segment;
+
+ if (!pkg_hdr)
+ return false;
+
+ if (pkg_hdr->version.major > 0) {
+ struct i40e_ddp_version ver = pkg_hdr->version;
+
+ netdev_err(netdev, "Unsupported DDP profile version %u.%u.%u.%u",
+ ver.major, ver.minor, ver.update, ver.draft);
+ return false;
+ }
+ if (size_huge > size) {
+ netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G");
+ return false;
+ }
+ if (size < (sizeof(struct i40e_package_header) +
+ sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+ netdev_err(netdev, "Invalid DDP profile - size is too small.");
+ return false;
+ }
+
+ pkg_hdr_size = sizeof(u32) * (pkg_hdr->segment_count + 2U);
+ if (size < pkg_hdr_size) {
+ netdev_err(netdev, "Invalid DDP profile - too many segments");
+ return false;
+ }
+ for (segment = 0; segment < pkg_hdr->segment_count; ++segment) {
+ u32 offset = pkg_hdr->segment_offset[segment];
+
+ if (0xFU & offset) {
+ netdev_err(netdev,
+ "Invalid DDP profile %u segment alignment",
+ segment);
+ return false;
+ }
+ if (pkg_hdr_size > offset || offset >= size) {
+ netdev_err(netdev,
+ "Invalid DDP profile %u segment offset",
+ segment);
+ return false;
+ }
+ }
+
+ return true;
+}
+
+/**
+ * i40e_ddp_load - performs DDP loading
+ * @netdev: net device structure
+ * @data: buffer containing recipe file
+ * @size: size of the buffer
+ * @is_add: true when loading profile, false when rolling back the previous one
+ *
+ * Checks correctness and loads DDP profile to the NIC. The function is
+ * also used for rolling back previously loaded profile.
+ **/
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+ bool is_add)
+{
+ u8 profile_info_sec[sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info)];
+ struct i40e_metadata_segment *metadata_hdr;
+ struct i40e_profile_segment *profile_hdr;
+ struct i40e_profile_info pinfo;
+ struct i40e_package_header *pkg_hdr;
+ i40e_status status;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ u32 track_id;
+ int istatus;
+
+ pkg_hdr = (struct i40e_package_header *)data;
+ if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size))
+ return -EINVAL;
+
+ if (size < (sizeof(struct i40e_package_header) +
+ sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+ netdev_err(netdev, "Invalid DDP recipe size.");
+ return -EINVAL;
+ }
+
+ /* Find beginning of segment data in buffer */
+ metadata_hdr = (struct i40e_metadata_segment *)
+ i40e_find_segment_in_package(SEGMENT_TYPE_METADATA, pkg_hdr);
+ if (!metadata_hdr) {
+ netdev_err(netdev, "Failed to find metadata segment in DDP recipe.");
+ return -EINVAL;
+ }
+
+ track_id = metadata_hdr->track_id;
+ profile_hdr = (struct i40e_profile_segment *)
+ i40e_find_segment_in_package(SEGMENT_TYPE_I40E, pkg_hdr);
+ if (!profile_hdr) {
+ netdev_err(netdev, "Failed to find profile segment in DDP recipe.");
+ return -EINVAL;
+ }
+
+ pinfo.track_id = track_id;
+ pinfo.version = profile_hdr->version;
+ if (is_add)
+ pinfo.op = I40E_DDP_ADD_TRACKID;
+ else
+ pinfo.op = I40E_DDP_REMOVE_TRACKID;
+
+ memcpy(pinfo.name, profile_hdr->name, I40E_DDP_NAME_SIZE);
+
+ /* Check if profile data already exists*/
+ istatus = i40e_ddp_does_profile_exist(&pf->hw, &pinfo);
+ if (istatus < 0) {
+ netdev_err(netdev, "Failed to fetch loaded profiles.");
+ return istatus;
+ }
+ if (is_add) {
+ if (istatus > 0) {
+ netdev_err(netdev, "DDP profile already loaded.");
+ return -EINVAL;
+ }
+ istatus = i40e_ddp_does_profile_overlap(&pf->hw, &pinfo);
+ if (istatus < 0) {
+ netdev_err(netdev, "Failed to fetch loaded profiles.");
+ return istatus;
+ }
+ if (istatus > 0) {
+ netdev_err(netdev, "DDP profile overlaps with existing one.");
+ return -EINVAL;
+ }
+ } else {
+ if (istatus == 0) {
+ netdev_err(netdev,
+ "DDP profile for deletion does not exist.");
+ return -EINVAL;
+ }
+ }
+
+ /* Load profile data */
+ if (is_add) {
+ status = i40e_write_profile(&pf->hw, profile_hdr, track_id);
+ if (status) {
+ if (status == I40E_ERR_DEVICE_NOT_SUPPORTED) {
+ netdev_err(netdev,
+ "Profile is not supported by the device.");
+ return -EPERM;
+ }
+ netdev_err(netdev, "Failed to write DDP profile.");
+ return -EIO;
+ }
+ } else {
+ status = i40e_rollback_profile(&pf->hw, profile_hdr, track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to remove DDP profile.");
+ return -EIO;
+ }
+ }
+
+ /* Add/remove profile to/from profile list in FW */
+ if (is_add) {
+ status = i40e_add_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+ track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to add DDP profile info.");
+ return -EIO;
+ }
+ } else {
+ status = i40e_del_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+ track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to restore DDP profile info.");
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_ddp_restore - restore previously loaded profile and remove from list
+ * @pf: PF data struct
+ *
+ * Restores previously loaded profile stored on the list in driver memory.
+ * After rolling back removes entry from the list.
+ **/
+static int i40e_ddp_restore(struct i40e_pf *pf)
+{
+ struct i40e_ddp_old_profile_list *entry;
+ struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev;
+ int status = 0;
+
+ if (!list_empty(&pf->ddp_old_prof)) {
+ entry = list_first_entry(&pf->ddp_old_prof,
+ struct i40e_ddp_old_profile_list,
+ list);
+ status = i40e_ddp_load(netdev, entry->old_ddp_buf,
+ entry->old_ddp_size, false);
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ return status;
+}
+
+/**
+ * i40e_ddp_flash - callback function for ethtool flash feature
+ * @netdev: net device structure
+ * @flash: kernel flash structure
+ *
+ * Ethtool callback function used for loading and unloading DDP profiles.
+ **/
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash)
+{
+ const struct firmware *ddp_config;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int status = 0;
+
+ /* Check for valid region first */
+ if (flash->region != I40_DDP_FLASH_REGION) {
+ netdev_err(netdev, "Requested firmware region is not recognized by this driver.");
+ return -EINVAL;
+ }
+ if (pf->hw.bus.func != 0) {
+ netdev_err(netdev, "Any DDP operation is allowed only on Phy0 NIC interface");
+ return -EINVAL;
+ }
+
+ /* If the user supplied "-" instead of file name rollback previously
+ * stored profile.
+ */
+ if (strncmp(flash->data, "-", 2) != 0) {
+ struct i40e_ddp_old_profile_list *list_entry;
+ char profile_name[sizeof(I40E_DDP_PROFILE_PATH)
+ + I40E_DDP_PROFILE_NAME_MAX];
+
+ profile_name[sizeof(profile_name) - 1] = 0;
+ strncpy(profile_name, I40E_DDP_PROFILE_PATH,
+ sizeof(profile_name) - 1);
+ strncat(profile_name, flash->data, I40E_DDP_PROFILE_NAME_MAX);
+ /* Load DDP recipe. */
+ status = request_firmware(&ddp_config, profile_name,
+ &netdev->dev);
+ if (status) {
+ netdev_err(netdev, "DDP recipe file request failed.");
+ return status;
+ }
+
+ status = i40e_ddp_load(netdev, ddp_config->data,
+ ddp_config->size, true);
+
+ if (!status) {
+ list_entry =
+ kzalloc(sizeof(struct i40e_ddp_old_profile_list) +
+ ddp_config->size, GFP_KERNEL);
+ if (!list_entry) {
+ netdev_info(netdev, "Failed to allocate memory for previous DDP profile data.");
+ netdev_info(netdev, "New profile loaded but roll-back will be impossible.");
+ } else {
+ memcpy(list_entry->old_ddp_buf,
+ ddp_config->data, ddp_config->size);
+ list_entry->old_ddp_size = ddp_config->size;
+ list_add(&list_entry->list, &pf->ddp_old_prof);
+ }
+ }
+
+ release_firmware(ddp_config);
+ } else {
+ if (!list_empty(&pf->ddp_old_prof)) {
+ status = i40e_ddp_restore(pf);
+ } else {
+ netdev_warn(netdev, "There is no DDP profile to restore.");
+ status = -ENOENT;
+ }
+ }
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 56b911a..99ea543 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -132,8 +132,6 @@
dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n",
(unsigned long int)nd->vlan_features);
}
- dev_info(&pf->pdev->dev, " active_vlans is %s\n",
- vsi->active_vlans ? "<valid>" : "<null>");
dev_info(&pf->pdev->dev,
" flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n",
vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags);
@@ -335,8 +333,9 @@
" seid = %d, id = %d, uplink_seid = %d\n",
vsi->seid, vsi->id, vsi->uplink_seid);
dev_info(&pf->pdev->dev,
- " base_queue = %d, num_queue_pairs = %d, num_desc = %d\n",
- vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc);
+ " base_queue = %d, num_queue_pairs = %d, num_tx_desc = %d, num_rx_desc = %d\n",
+ vsi->base_queue, vsi->num_queue_pairs, vsi->num_tx_desc,
+ vsi->num_rx_desc);
dev_info(&pf->pdev->dev, " type = %i\n", vsi->type);
if (vsi->type == I40E_VSI_SRIOV)
dev_info(&pf->pdev->dev, " VF ID = %i\n", vsi->vf_id);
@@ -1126,10 +1125,6 @@
dev_info(&pf->pdev->dev, "debugfs: forcing GlobR\n");
i40e_do_reset_safe(pf, BIT(__I40E_GLOBAL_RESET_REQUESTED));
- } else if (strncmp(cmd_buf, "empr", 4) == 0) {
- dev_info(&pf->pdev->dev, "debugfs: forcing EMPR\n");
- i40e_do_reset_safe(pf, BIT(__I40E_EMP_RESET_REQUESTED));
-
} else if (strncmp(cmd_buf, "read", 4) == 0) {
u32 address;
u32 value;
@@ -1323,7 +1318,7 @@
if (strncmp(&cmd_buf[5], "stop", 4) == 0) {
int ret;
- ret = i40e_aq_stop_lldp(&pf->hw, false, NULL);
+ ret = i40e_aq_stop_lldp(&pf->hw, false, false, NULL);
if (ret) {
dev_info(&pf->pdev->dev,
"Stop LLDP AQ command failed =0x%x\n",
@@ -1332,7 +1327,7 @@
}
ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
pf->hw.mac.addr,
- I40E_ETH_P_LLDP, 0,
+ ETH_P_LLDP, 0,
pf->vsi[pf->lan_vsi]->seid,
0, true, NULL, NULL);
if (ret) {
@@ -1350,7 +1345,7 @@
ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
pf->hw.mac.addr,
- I40E_ETH_P_LLDP, 0,
+ ETH_P_LLDP, 0,
pf->vsi[pf->lan_vsi]->seid,
0, false, NULL, NULL);
if (ret) {
@@ -1360,7 +1355,7 @@
/* Continue and start FW LLDP anyways */
}
- ret = i40e_aq_start_lldp(&pf->hw, NULL);
+ ret = i40e_aq_start_lldp(&pf->hw, false, NULL);
if (ret) {
dev_info(&pf->pdev->dev,
"Start LLDP AQ command failed =0x%x\n",
@@ -1644,30 +1639,7 @@
count = buf_tmp - i40e_dbg_netdev_ops_buf + 1;
}
- if (strncmp(i40e_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) {
- cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
- if (cnt != 1) {
- dev_info(&pf->pdev->dev, "tx_timeout <vsi_seid>\n");
- goto netdev_ops_write_done;
- }
- vsi = i40e_dbg_find_vsi(pf, vsi_seid);
- if (!vsi) {
- dev_info(&pf->pdev->dev,
- "tx_timeout: VSI %d not found\n", vsi_seid);
- } else if (!vsi->netdev) {
- dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n",
- vsi_seid);
- } else if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
- dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n",
- vsi_seid);
- } else if (rtnl_trylock()) {
- vsi->netdev->netdev_ops->ndo_tx_timeout(vsi->netdev);
- rtnl_unlock();
- dev_info(&pf->pdev->dev, "tx_timeout called\n");
- } else {
- dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
- }
- } else if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+ if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
int mtu;
cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
@@ -1735,7 +1707,6 @@
dev_info(&pf->pdev->dev, "unknown command '%s'\n",
i40e_dbg_netdev_ops_buf);
dev_info(&pf->pdev->dev, "available commands\n");
- dev_info(&pf->pdev->dev, " tx_timeout <vsi_seid>\n");
dev_info(&pf->pdev->dev, " change_mtu <vsi_seid> <mtu>\n");
dev_info(&pf->pdev->dev, " set_rx_mode <vsi_seid>\n");
dev_info(&pf->pdev->dev, " napi <vsi_seid>\n");
@@ -1757,29 +1728,15 @@
**/
void i40e_dbg_pf_init(struct i40e_pf *pf)
{
- struct dentry *pfile;
const char *name = pci_name(pf->pdev);
- const struct device *dev = &pf->pdev->dev;
pf->i40e_dbg_pf = debugfs_create_dir(name, i40e_dbg_root);
- if (!pf->i40e_dbg_pf)
- return;
- pfile = debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf,
- &i40e_dbg_command_fops);
- if (!pfile)
- goto create_failed;
+ debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf,
+ &i40e_dbg_command_fops);
- pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf,
- &i40e_dbg_netdev_ops_fops);
- if (!pfile)
- goto create_failed;
-
- return;
-
-create_failed:
- dev_info(dev, "debugfs dir/file for %s failed\n", name);
- debugfs_remove_recursive(pf->i40e_dbg_pf);
+ debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf,
+ &i40e_dbg_netdev_ops_fops);
}
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h
index 334b05f..bac4da0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h
@@ -5,6 +5,8 @@
#define _I40E_DEVIDS_H_
/* Device IDs */
+#define I40E_DEV_ID_X710_N3000 0x0CF8
+#define I40E_DEV_ID_XXV710_N3000 0x0D58
#define I40E_DEV_ID_SFP_XL710 0x1572
#define I40E_DEV_ID_QEMU 0x1574
#define I40E_DEV_ID_KX_B 0x1580
@@ -18,6 +20,9 @@
#define I40E_DEV_ID_10G_BASE_T4 0x1589
#define I40E_DEV_ID_25G_B 0x158A
#define I40E_DEV_ID_25G_SFP28 0x158B
+#define I40E_DEV_ID_10G_BASE_T_BC 0x15FF
+#define I40E_DEV_ID_10G_B 0x104F
+#define I40E_DEV_ID_10G_SFP 0x104E
#define I40E_DEV_ID_KX_X722 0x37CE
#define I40E_DEV_ID_QSFP_X722 0x37CF
#define I40E_DEV_ID_SFP_X722 0x37D0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 5ff6caa..41e1240 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -5,26 +5,227 @@
#include "i40e.h"
#include "i40e_diag.h"
+#include "i40e_txrx_common.h"
+/* ethtool statistics helpers */
+
+/**
+ * struct i40e_stats - definition for an ethtool statistic
+ * @stat_string: statistic name to display in ethtool -S output
+ * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64)
+ * @stat_offset: offsetof() the stat from a base pointer
+ *
+ * This structure defines a statistic to be added to the ethtool stats buffer.
+ * It defines a statistic as offset from a common base pointer. Stats should
+ * be defined in constant arrays using the I40E_STAT macro, with every element
+ * of the array using the same _type for calculating the sizeof_stat and
+ * stat_offset.
+ *
+ * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or
+ * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from
+ * the i40e_add_ethtool_stat() helper function.
+ *
+ * The @stat_string is interpreted as a format string, allowing formatted
+ * values to be inserted while looping over multiple structures for a given
+ * statistics array. Thus, every statistic string in an array should have the
+ * same type and number of format specifiers, to be formatted by variadic
+ * arguments to the i40e_add_stat_string() helper function.
+ **/
struct i40e_stats {
- /* The stat_string is expected to be a format string formatted using
- * vsnprintf by i40e_add_stat_strings. Every member of a stats array
- * should use the same format specifiers as they will be formatted
- * using the same variadic arguments.
- */
char stat_string[ETH_GSTRING_LEN];
int sizeof_stat;
int stat_offset;
};
+/* Helper macro to define an i40e_stat structure with proper size and type.
+ * Use this when defining constant statistics arrays. Note that @_type expects
+ * only a type name and is used multiple times.
+ */
#define I40E_STAT(_type, _name, _stat) { \
.stat_string = _name, \
.sizeof_stat = FIELD_SIZEOF(_type, _stat), \
.stat_offset = offsetof(_type, _stat) \
}
+/* Helper macro for defining some statistics directly copied from the netdev
+ * stats structure.
+ */
#define I40E_NETDEV_STAT(_net_stat) \
I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat)
+
+/* Helper macro for defining some statistics related to queues */
+#define I40E_QUEUE_STAT(_name, _stat) \
+ I40E_STAT(struct i40e_ring, _name, _stat)
+
+/* Stats associated with a Tx or Rx ring */
+static const struct i40e_stats i40e_gstrings_queue_stats[] = {
+ I40E_QUEUE_STAT("%s-%u.packets", stats.packets),
+ I40E_QUEUE_STAT("%s-%u.bytes", stats.bytes),
+};
+
+/**
+ * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer
+ * @data: location to store the stat value
+ * @pointer: basis for where to copy from
+ * @stat: the stat definition
+ *
+ * Copies the stat data defined by the pointer and stat structure pair into
+ * the memory supplied as data. Used to implement i40e_add_ethtool_stats and
+ * i40e_add_queue_stats. If the pointer is null, data will be zero'd.
+ */
+static void
+i40e_add_one_ethtool_stat(u64 *data, void *pointer,
+ const struct i40e_stats *stat)
+{
+ char *p;
+
+ if (!pointer) {
+ /* ensure that the ethtool data buffer is zero'd for any stats
+ * which don't have a valid pointer.
+ */
+ *data = 0;
+ return;
+ }
+
+ p = (char *)pointer + stat->stat_offset;
+ switch (stat->sizeof_stat) {
+ case sizeof(u64):
+ *data = *((u64 *)p);
+ break;
+ case sizeof(u32):
+ *data = *((u32 *)p);
+ break;
+ case sizeof(u16):
+ *data = *((u16 *)p);
+ break;
+ case sizeof(u8):
+ *data = *((u8 *)p);
+ break;
+ default:
+ WARN_ONCE(1, "unexpected stat size for %s",
+ stat->stat_string);
+ *data = 0;
+ }
+}
+
+/**
+ * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location to copy stats from
+ * @stats: array of stats to copy
+ * @size: the size of the stats definition
+ *
+ * Copy the stats defined by the stats array using the pointer as a base into
+ * the data buffer supplied by ethtool. Updates the data pointer to point to
+ * the next empty location for successive calls to __i40e_add_ethtool_stats.
+ * If pointer is null, set the data values to zero and update the pointer to
+ * skip these stats.
+ **/
+static void
+__i40e_add_ethtool_stats(u64 **data, void *pointer,
+ const struct i40e_stats stats[],
+ const unsigned int size)
+{
+ unsigned int i;
+
+ for (i = 0; i < size; i++)
+ i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]);
+}
+
+/**
+ * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location where stats are stored
+ * @stats: static const array of stat definitions
+ *
+ * Macro to ease the use of __i40e_add_ethtool_stats by taking a static
+ * constant stats array and passing the ARRAY_SIZE(). This avoids typos by
+ * ensuring that we pass the size associated with the given stats array.
+ *
+ * The parameter @stats is evaluated twice, so parameters with side effects
+ * should be avoided.
+ **/
+#define i40e_add_ethtool_stats(data, pointer, stats) \
+ __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
+/**
+ * i40e_add_queue_stats - copy queue statistics into supplied buffer
+ * @data: ethtool stats buffer
+ * @ring: the ring to copy
+ *
+ * Queue statistics must be copied while protected by
+ * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats.
+ * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the
+ * ring pointer is null, zero out the queue stat values and update the data
+ * pointer. Otherwise safely copy the stats from the ring into the supplied
+ * buffer and update the data pointer when finished.
+ *
+ * This function expects to be called while under rcu_read_lock().
+ **/
+static void
+i40e_add_queue_stats(u64 **data, struct i40e_ring *ring)
+{
+ const unsigned int size = ARRAY_SIZE(i40e_gstrings_queue_stats);
+ const struct i40e_stats *stats = i40e_gstrings_queue_stats;
+ unsigned int start;
+ unsigned int i;
+
+ /* To avoid invalid statistics values, ensure that we keep retrying
+ * the copy until we get a consistent value according to
+ * u64_stats_fetch_retry_irq. But first, make sure our ring is
+ * non-null before attempting to access its syncp.
+ */
+ do {
+ start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp);
+ for (i = 0; i < size; i++) {
+ i40e_add_one_ethtool_stat(&(*data)[i], ring,
+ &stats[i]);
+ }
+ } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start));
+
+ /* Once we successfully copy the stats in, update the data pointer */
+ *data += size;
+}
+
+/**
+ * __i40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ * @size: size of the stats array
+ *
+ * Format and copy the strings described by stats into the buffer pointed at
+ * by p.
+ **/
+static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
+ const unsigned int size, ...)
+{
+ unsigned int i;
+
+ for (i = 0; i < size; i++) {
+ va_list args;
+
+ va_start(args, size);
+ vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
+ *p += ETH_GSTRING_LEN;
+ va_end(args);
+ }
+}
+
+/**
+ * 40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ *
+ * Format and copy the strings described by the const static stats value into
+ * the buffer pointed at by p.
+ *
+ * The parameter @stats is evaluated twice, so parameters with side effects
+ * should be avoided. Additionally, stats must be an array such that
+ * ARRAY_SIZE can be called on it.
+ **/
+#define i40e_add_stat_strings(p, stats, ...) \
+ __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
+
#define I40E_PF_STAT(_name, _stat) \
I40E_STAT(struct i40e_pf, _name, _stat)
#define I40E_VSI_STAT(_name, _stat) \
@@ -33,6 +234,8 @@
I40E_STAT(struct i40e_veb, _name, _stat)
#define I40E_PFC_STAT(_name, _stat) \
I40E_STAT(struct i40e_pfc_stats, _name, _stat)
+#define I40E_QUEUE_STAT(_name, _stat) \
+ I40E_STAT(struct i40e_ring, _name, _stat)
static const struct i40e_stats i40e_gstrings_net_stats[] = {
I40E_NETDEV_STAT(rx_packets),
@@ -171,20 +374,11 @@
I40E_PFC_STAT("port.rx_priority_%u_xon_2_xoff", priority_xon_2_xoff),
};
-/* We use num_tx_queues here as a proxy for the maximum number of queues
- * available because we always allocate queues symmetrically.
- */
-#define I40E_MAX_NUM_QUEUES(n) ((n)->num_tx_queues)
-#define I40E_QUEUE_STATS_LEN(n) \
- (I40E_MAX_NUM_QUEUES(n) \
- * 2 /* Tx and Rx together */ \
- * (sizeof(struct i40e_queue_stats) / sizeof(u64)))
-#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats)
#define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats)
+
#define I40E_MISC_STATS_LEN ARRAY_SIZE(i40e_gstrings_misc_stats)
-#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
- I40E_MISC_STATS_LEN + \
- I40E_QUEUE_STATS_LEN((n)))
+
+#define I40E_VSI_STATS_LEN (I40E_NETDEV_STATS_LEN + I40E_MISC_STATS_LEN)
#define I40E_PFC_STATS_LEN (ARRAY_SIZE(i40e_gstrings_pfc_stats) * \
I40E_MAX_USER_PRIORITY)
@@ -193,10 +387,15 @@
(ARRAY_SIZE(i40e_gstrings_veb_tc_stats) * \
I40E_MAX_TRAFFIC_CLASS))
-#define I40E_PF_STATS_LEN(n) (I40E_GLOBAL_STATS_LEN + \
+#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats)
+
+#define I40E_PF_STATS_LEN (I40E_GLOBAL_STATS_LEN + \
I40E_PFC_STATS_LEN + \
I40E_VEB_STATS_LEN + \
- I40E_VSI_STATS_LEN((n)))
+ I40E_VSI_STATS_LEN)
+
+/* Length of stats for a single queue */
+#define I40E_QUEUE_STATS_LEN ARRAY_SIZE(i40e_gstrings_queue_stats)
enum i40e_ethtool_test_id {
I40E_ETH_TEST_REG = 0,
@@ -239,6 +438,8 @@
I40E_PRIV_FLAG("disable-source-pruning",
I40E_FLAG_SOURCE_PRUNING_DISABLED, 0),
I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0),
+ I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0),
+ I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
};
#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -307,6 +508,20 @@
ethtool_link_ksettings_add_link_mode(ks, advertising,
10000baseT_Full);
}
+ if (phy_types & I40E_CAP_PHY_TYPE_2_5GBASE_T) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_2_5GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseT_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_5GBASE_T) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 5000baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_5GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 5000baseT_Full);
+ }
if (phy_types & I40E_CAP_PHY_TYPE_XLAUI ||
phy_types & I40E_CAP_PHY_TYPE_XLPPI ||
phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC)
@@ -334,18 +549,24 @@
ethtool_link_ksettings_add_link_mode(ks, advertising,
1000baseT_Full);
}
- if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4)
+ if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) {
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseSR4_Full);
- if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
- ethtool_link_ksettings_add_link_mode(ks, supported,
- 40000baseLR4_Full);
- if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseSR4_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4) {
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseLR4_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
40000baseLR4_Full);
}
+ if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseKR4_Full);
+ }
if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) {
ethtool_link_ksettings_add_link_mode(ks, supported,
20000baseKR2_Full);
@@ -407,6 +628,24 @@
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseCR_Full);
}
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) {
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_NONE);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ }
+ }
/* need to add new 10G PHY types */
if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) {
@@ -449,13 +688,15 @@
phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
+ phy_types & I40E_CAP_PHY_TYPE_5GBASE_T ||
+ phy_types & I40E_CAP_PHY_TYPE_2_5GBASE_T ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
@@ -470,6 +711,35 @@
}
/**
+ * i40e_get_settings_link_up_fec - Get the FEC mode encoding from mask
+ * @req_fec_info: mask request FEC info
+ * @ks: ethtool ksettings to fill in
+ **/
+static void i40e_get_settings_link_up_fec(u8 req_fec_info,
+ struct ethtool_link_ksettings *ks)
+{
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+
+ if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+ } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ } else {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_NONE);
+ if (I40E_AQ_SET_FEC_AUTO & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ }
+ }
+}
+
+/**
* i40e_get_settings_link_up - Get the Link settings for when link is up
* @hw: hw structure
* @ks: ethtool ksettings to fill in
@@ -501,14 +771,20 @@
case I40E_PHY_TYPE_40GBASE_AOC:
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseCR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseCR4_Full);
break;
case I40E_PHY_TYPE_40GBASE_SR4:
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseSR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseSR4_Full);
break;
case I40E_PHY_TYPE_40GBASE_LR4:
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseLR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseLR4_Full);
break;
case I40E_PHY_TYPE_25GBASE_SR:
case I40E_PHY_TYPE_25GBASE_LR:
@@ -522,6 +798,7 @@
25000baseSR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseSR_Full);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
ethtool_link_ksettings_add_link_mode(ks, supported,
10000baseSR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -552,12 +829,18 @@
10000baseT_Full);
break;
case I40E_PHY_TYPE_10GBASE_T:
+ case I40E_PHY_TYPE_5GBASE_T:
+ case I40E_PHY_TYPE_2_5GBASE_T:
case I40E_PHY_TYPE_1000BASE_T:
case I40E_PHY_TYPE_100BASE_TX:
ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
ethtool_link_ksettings_add_link_mode(ks, supported,
10000baseT_Full);
ethtool_link_ksettings_add_link_mode(ks, supported,
+ 5000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
1000baseT_Full);
ethtool_link_ksettings_add_link_mode(ks, supported,
100baseT_Full);
@@ -565,6 +848,12 @@
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
ethtool_link_ksettings_add_link_mode(ks, advertising,
10000baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_5GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 5000baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_2_5GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
ethtool_link_ksettings_add_link_mode(ks, advertising,
1000baseT_Full);
@@ -639,6 +928,7 @@
40000baseKR4_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseKR_Full);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
ethtool_link_ksettings_add_link_mode(ks, advertising,
20000baseKR2_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -656,6 +946,8 @@
25000baseCR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseCR_Full);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
+
break;
case I40E_PHY_TYPE_25GBASE_AOC:
case I40E_PHY_TYPE_25GBASE_ACC:
@@ -663,9 +955,10 @@
ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
ethtool_link_ksettings_add_link_mode(ks, supported,
25000baseCR_Full);
-
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseCR_Full);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
+
ethtool_link_ksettings_add_link_mode(ks, supported,
10000baseCR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -700,6 +993,12 @@
case I40E_LINK_SPEED_10GB:
ks->base.speed = SPEED_10000;
break;
+ case I40E_LINK_SPEED_5GB:
+ ks->base.speed = SPEED_5000;
+ break;
+ case I40E_LINK_SPEED_2_5GB:
+ ks->base.speed = SPEED_2500;
+ break;
case I40E_LINK_SPEED_1GB:
ks->base.speed = SPEED_1000;
break;
@@ -707,6 +1006,7 @@
ks->base.speed = SPEED_100;
break;
default:
+ ks->base.speed = SPEED_UNKNOWN;
break;
}
ks->base.duplex = DUPLEX_FULL;
@@ -786,6 +1086,7 @@
break;
case I40E_MEDIA_TYPE_FIBER:
ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE);
ks->base.port = PORT_FIBRE;
break;
case I40E_MEDIA_TYPE_UNKNOWN:
@@ -984,6 +1285,12 @@
10000baseLR_Full))
config.link_speed |= I40E_LINK_SPEED_10GB;
if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 2500baseT_Full))
+ config.link_speed |= I40E_LINK_SPEED_2_5GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 5000baseT_Full))
+ config.link_speed |= I40E_LINK_SPEED_5GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
20000baseKR2_Full))
config.link_speed |= I40E_LINK_SPEED_20GB;
if (ethtool_link_ksettings_test_link_mode(ks, advertising,
@@ -1061,6 +1368,154 @@
return err;
}
+static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_aq_get_phy_abilities_resp abilities;
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status status = 0;
+ u32 flags = 0;
+ int err = 0;
+
+ flags = READ_ONCE(pf->flags);
+ i40e_set_fec_in_flags(fec_cfg, &flags);
+
+ /* Get the current phy config */
+ memset(&abilities, 0, sizeof(abilities));
+ status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+ NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ if (abilities.fec_cfg_curr_mod_ext_info != fec_cfg) {
+ struct i40e_aq_set_phy_config config;
+
+ memset(&config, 0, sizeof(config));
+ config.phy_type = abilities.phy_type;
+ config.abilities = abilities.abilities;
+ config.phy_type_ext = abilities.phy_type_ext;
+ config.link_speed = abilities.link_speed;
+ config.eee_capability = abilities.eee_capability;
+ config.eeer = abilities.eeer_val;
+ config.low_power_ctrl = abilities.d3_lpan;
+ config.fec_config = fec_cfg & I40E_AQ_PHY_FEC_CONFIG_MASK;
+ status = i40e_aq_set_phy_config(hw, &config, NULL);
+ if (status) {
+ netdev_info(netdev,
+ "Set phy config failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, status),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ err = -EAGAIN;
+ goto done;
+ }
+ pf->flags = flags;
+ status = i40e_update_link_info(hw);
+ if (status)
+ /* debug level message only due to relation to the link
+ * itself rather than to the FEC settings
+ * (e.g. no physical connection etc.)
+ */
+ netdev_dbg(netdev,
+ "Updating link info failed with err %s aq_err %s\n",
+ i40e_stat_str(hw, status),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ }
+
+done:
+ return err;
+}
+
+static int i40e_get_fec_param(struct net_device *netdev,
+ struct ethtool_fecparam *fecparam)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_aq_get_phy_abilities_resp abilities;
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status status = 0;
+ int err = 0;
+
+ /* Get the current phy config */
+ memset(&abilities, 0, sizeof(abilities));
+ status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+ NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ fecparam->fec = 0;
+ if (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_AUTO)
+ fecparam->fec |= ETHTOOL_FEC_AUTO;
+ if ((abilities.fec_cfg_curr_mod_ext_info &
+ I40E_AQ_SET_FEC_REQUEST_RS) ||
+ (abilities.fec_cfg_curr_mod_ext_info &
+ I40E_AQ_SET_FEC_ABILITY_RS))
+ fecparam->fec |= ETHTOOL_FEC_RS;
+ if ((abilities.fec_cfg_curr_mod_ext_info &
+ I40E_AQ_SET_FEC_REQUEST_KR) ||
+ (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_ABILITY_KR))
+ fecparam->fec |= ETHTOOL_FEC_BASER;
+ if (abilities.fec_cfg_curr_mod_ext_info == 0)
+ fecparam->fec |= ETHTOOL_FEC_OFF;
+
+ if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA)
+ fecparam->active_fec = ETHTOOL_FEC_BASER;
+ else if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA)
+ fecparam->active_fec = ETHTOOL_FEC_RS;
+ else
+ fecparam->active_fec = ETHTOOL_FEC_OFF;
+done:
+ return err;
+}
+
+static int i40e_set_fec_param(struct net_device *netdev,
+ struct ethtool_fecparam *fecparam)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u8 fec_cfg = 0;
+ int err = 0;
+
+ if (hw->device_id != I40E_DEV_ID_25G_SFP28 &&
+ hw->device_id != I40E_DEV_ID_25G_B) {
+ err = -EPERM;
+ goto done;
+ }
+
+ switch (fecparam->fec) {
+ case ETHTOOL_FEC_AUTO:
+ fec_cfg = I40E_AQ_SET_FEC_AUTO;
+ break;
+ case ETHTOOL_FEC_RS:
+ fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+ I40E_AQ_SET_FEC_ABILITY_RS);
+ break;
+ case ETHTOOL_FEC_BASER:
+ fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+ I40E_AQ_SET_FEC_ABILITY_KR);
+ break;
+ case ETHTOOL_FEC_OFF:
+ case ETHTOOL_FEC_NONE:
+ fec_cfg = 0;
+ break;
+ default:
+ dev_warn(&pf->pdev->dev, "Unsupported FEC mode: %d",
+ fecparam->fec);
+ err = -EINVAL;
+ goto done;
+ }
+
+ err = i40e_set_fec_cfg(netdev, fec_cfg);
+
+done:
+ return err;
+}
+
static int i40e_nway_reset(struct net_device *netdev)
{
/* restart autonegotiation */
@@ -1136,6 +1591,7 @@
i40e_status status;
u8 aq_failures;
int err = 0;
+ u32 is_an;
/* Changing the port's flow control is not supported if this isn't the
* port's controlling PF
@@ -1148,15 +1604,14 @@
if (vsi != pf->vsi[pf->lan_vsi])
return -EOPNOTSUPP;
- if (pause->autoneg != ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
- AUTONEG_ENABLE : AUTONEG_DISABLE)) {
+ is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED;
+ if (pause->autoneg != is_an) {
netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
return -EOPNOTSUPP;
}
/* If we have link and don't have autoneg */
- if (!test_bit(__I40E_DOWN, pf->state) &&
- !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) {
+ if (!test_bit(__I40E_DOWN, pf->state) && !is_an) {
/* Send message that it might not necessarily work*/
netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
}
@@ -1176,7 +1631,7 @@
else if (!pause->rx_pause && !pause->tx_pause)
hw->fc.requested_mode = I40E_FC_NONE;
else
- return -EINVAL;
+ return -EINVAL;
/* Tell the OS link is going down, the link will go back up when fw
* says it is ready asynchronously
@@ -1207,7 +1662,7 @@
err = -EAGAIN;
}
- if (!test_bit(__I40E_DOWN, pf->state)) {
+ if (!test_bit(__I40E_DOWN, pf->state) && is_an) {
/* Give it a little more time to try to come back */
msleep(75);
if (!test_bit(__I40E_DOWN, pf->state))
@@ -1512,6 +1967,13 @@
(new_rx_count == vsi->rx_rings[0]->count))
return 0;
+ /* If there is a AF_XDP UMEM attached to any of Rx rings,
+ * disallow changing the number of descriptors -- regardless
+ * if the netdev is running or not.
+ */
+ if (i40e_xsk_any_rx_ring_enabled(vsi))
+ return -EBUSY;
+
while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
timeout--;
if (!timeout)
@@ -1527,6 +1989,8 @@
if (i40e_enabled_xdp_vsi(vsi))
vsi->xdp_rings[i]->count = new_tx_count;
}
+ vsi->num_tx_desc = new_tx_count;
+ vsi->num_rx_desc = new_rx_count;
goto done;
}
@@ -1663,6 +2127,8 @@
rx_rings = NULL;
}
+ vsi->num_tx_desc = new_tx_count;
+ vsi->num_rx_desc = new_rx_count;
i40e_up(vsi);
free_tx:
@@ -1701,11 +2167,30 @@
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
+ int stats_len;
if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1)
- return I40E_PF_STATS_LEN(netdev);
+ stats_len = I40E_PF_STATS_LEN;
else
- return I40E_VSI_STATS_LEN(netdev);
+ stats_len = I40E_VSI_STATS_LEN;
+
+ /* The number of stats reported for a given net_device must remain
+ * constant throughout the life of that device.
+ *
+ * This is because the API for obtaining the size, strings, and stats
+ * is spread out over three separate ethtool ioctls. There is no safe
+ * way to lock the number of stats across these calls, so we must
+ * assume that they will never change.
+ *
+ * Due to this, we report the maximum number of queues, even if not
+ * every queue is currently configured. Since we always allocate
+ * queues in pairs, we'll just use netdev->num_tx_queues * 2. This
+ * works because the num_tx_queues is set at device creation and never
+ * changes.
+ */
+ stats_len += I40E_QUEUE_STATS_LEN * 2 * netdev->num_tx_queues;
+
+ return stats_len;
}
static int i40e_get_sset_count(struct net_device *netdev, int sset)
@@ -1728,89 +2213,6 @@
}
/**
- * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer
- * @data: location to store the stat value
- * @pointer: basis for where to copy from
- * @stat: the stat definition
- *
- * Copies the stat data defined by the pointer and stat structure pair into
- * the memory supplied as data. Used to implement i40e_add_ethtool_stats.
- * If the pointer is null, data will be zero'd.
- */
-static inline void
-i40e_add_one_ethtool_stat(u64 *data, void *pointer,
- const struct i40e_stats *stat)
-{
- char *p;
-
- if (!pointer) {
- /* ensure that the ethtool data buffer is zero'd for any stats
- * which don't have a valid pointer.
- */
- *data = 0;
- return;
- }
-
- p = (char *)pointer + stat->stat_offset;
- switch (stat->sizeof_stat) {
- case sizeof(u64):
- *data = *((u64 *)p);
- break;
- case sizeof(u32):
- *data = *((u32 *)p);
- break;
- case sizeof(u16):
- *data = *((u16 *)p);
- break;
- case sizeof(u8):
- *data = *((u8 *)p);
- break;
- default:
- WARN_ONCE(1, "unexpected stat size for %s",
- stat->stat_string);
- *data = 0;
- }
-}
-
-/**
- * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer
- * @data: ethtool stats buffer
- * @pointer: location to copy stats from
- * @stats: array of stats to copy
- * @size: the size of the stats definition
- *
- * Copy the stats defined by the stats array using the pointer as a base into
- * the data buffer supplied by ethtool. Updates the data pointer to point to
- * the next empty location for successive calls to __i40e_add_ethtool_stats.
- * If pointer is null, set the data values to zero and update the pointer to
- * skip these stats.
- **/
-static inline void
-__i40e_add_ethtool_stats(u64 **data, void *pointer,
- const struct i40e_stats stats[],
- const unsigned int size)
-{
- unsigned int i;
-
- for (i = 0; i < size; i++)
- i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]);
-}
-
-/**
- * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer
- * @data: ethtool stats buffer
- * @pointer: location where stats are stored
- * @stats: static const array of stat definitions
- *
- * Macro to ease the use of __i40e_add_ethtool_stats by taking a static
- * constant stats array and passing the ARRAY_SIZE(). This avoids typos by
- * ensuring that we pass the size associated with the given stats array.
- * Assumes that stats is an array.
- **/
-#define i40e_add_ethtool_stats(data, pointer, stats) \
- __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
-
-/**
* i40e_get_pfc_stats - copy HW PFC statistics to formatted structure
* @pf: the PF device structure
* @i: the priority value to copy
@@ -1853,12 +2255,10 @@
struct ethtool_stats *stats, u64 *data)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_ring *tx_ring, *rx_ring;
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- struct i40e_veb *veb = pf->veb[pf->lan_veb];
+ struct i40e_veb *veb = NULL;
unsigned int i;
- unsigned int start;
bool veb_stats;
u64 *p = data;
@@ -1870,44 +2270,24 @@
i40e_add_ethtool_stats(&data, vsi, i40e_gstrings_misc_stats);
rcu_read_lock();
- for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev) ; i++) {
- tx_ring = READ_ONCE(vsi->tx_rings[i]);
-
- if (!tx_ring) {
- /* Bump the stat counter to skip these stats, and make
- * sure the memory is zero'd
- */
- *(data++) = 0;
- *(data++) = 0;
- *(data++) = 0;
- *(data++) = 0;
- continue;
- }
-
- /* process Tx ring statistics */
- do {
- start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
- data[0] = tx_ring->stats.packets;
- data[1] = tx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
- data += 2;
-
- /* Rx ring is the 2nd half of the queue pair */
- rx_ring = &tx_ring[1];
- do {
- start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
- data[0] = rx_ring->stats.packets;
- data[1] = rx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
- data += 2;
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ i40e_add_queue_stats(&data, READ_ONCE(vsi->tx_rings[i]));
+ i40e_add_queue_stats(&data, READ_ONCE(vsi->rx_rings[i]));
}
rcu_read_unlock();
+
if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
goto check_data_pointer;
veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
+ (pf->lan_veb < I40E_MAX_VEB) &&
(pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
+ if (veb_stats) {
+ veb = pf->veb[pf->lan_veb];
+ i40e_update_veb_stats(veb);
+ }
+
/* If veb stats aren't enabled, pass NULL instead of the veb so that
* we initialize stats to zero and update the data pointer
* intelligently
@@ -1933,42 +2313,6 @@
}
/**
- * __i40e_add_stat_strings - copy stat strings into ethtool buffer
- * @p: ethtool supplied buffer
- * @stats: stat definitions array
- * @size: size of the stats array
- *
- * Format and copy the strings described by stats into the buffer pointed at
- * by p.
- **/
-static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
- const unsigned int size, ...)
-{
- unsigned int i;
-
- for (i = 0; i < size; i++) {
- va_list args;
-
- va_start(args, size);
- vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
- *p += ETH_GSTRING_LEN;
- va_end(args);
- }
-}
-
-/**
- * 40e_add_stat_strings - copy stat strings into ethtool buffer
- * @p: ethtool supplied buffer
- * @stats: stat definitions array
- *
- * Format and copy the strings described by the const static stats value into
- * the buffer pointed at by p. Assumes that stats can have ARRAY_SIZE called
- * for it.
- **/
-#define i40e_add_stat_strings(p, stats, ...) \
- __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
-
-/**
* i40e_get_stat_strings - copy stat strings into supplied buffer
* @netdev: the netdev to collect strings for
* @data: supplied buffer to copy strings into
@@ -1990,18 +2334,15 @@
i40e_add_stat_strings(&data, i40e_gstrings_misc_stats);
- for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev); i++) {
- snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_packets", i);
- data += ETH_GSTRING_LEN;
- snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_bytes", i);
- data += ETH_GSTRING_LEN;
- snprintf(data, ETH_GSTRING_LEN, "rx-%u.rx_packets", i);
- data += ETH_GSTRING_LEN;
- snprintf(data, ETH_GSTRING_LEN, "rx-%u.rx_bytes", i);
- data += ETH_GSTRING_LEN;
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ i40e_add_stat_strings(&data, i40e_gstrings_queue_stats,
+ "tx", i);
+ i40e_add_stat_strings(&data, i40e_gstrings_queue_stats,
+ "rx", i);
}
+
if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
- return;
+ goto check_data_pointer;
i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
@@ -2013,6 +2354,7 @@
for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i);
+check_data_pointer:
WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN,
"stat strings count mismatch!");
}
@@ -2099,7 +2441,7 @@
return 0;
}
-static int i40e_link_test(struct net_device *netdev, u64 *data)
+static u64 i40e_link_test(struct net_device *netdev, u64 *data)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
@@ -2122,7 +2464,7 @@
return *data;
}
-static int i40e_reg_test(struct net_device *netdev, u64 *data)
+static u64 i40e_reg_test(struct net_device *netdev, u64 *data)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
@@ -2133,7 +2475,7 @@
return *data;
}
-static int i40e_eeprom_test(struct net_device *netdev, u64 *data)
+static u64 i40e_eeprom_test(struct net_device *netdev, u64 *data)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
@@ -2147,7 +2489,7 @@
return *data;
}
-static int i40e_intr_test(struct net_device *netdev, u64 *data)
+static u64 i40e_intr_test(struct net_device *netdev, u64 *data)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
@@ -2302,7 +2644,7 @@
return -EOPNOTSUPP;
/* only magic packet is supported */
- if (wol->wolopts && (wol->wolopts != WAKE_MAGIC))
+ if (wol->wolopts & ~WAKE_MAGIC)
return -EOPNOTSUPP;
/* is this a new value? */
@@ -2363,10 +2705,10 @@
default:
break;
}
- if (ret)
- return -ENOENT;
- else
- return 0;
+ if (ret)
+ return -ENOENT;
+ else
+ return 0;
}
/* NOTE: i40e hardware uses a conversion factor of 2 for Interrupt
@@ -4528,9 +4870,12 @@
static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
+ u64 orig_flags, new_flags, changed_flags;
+ enum i40e_admin_queue_err adq_err;
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- u64 orig_flags, new_flags, changed_flags;
+ bool is_reset_needed;
+ i40e_status status;
u32 i, j;
orig_flags = READ_ONCE(pf->flags);
@@ -4574,6 +4919,10 @@
flags_complete:
changed_flags = orig_flags ^ new_flags;
+ is_reset_needed = !!(changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
+ I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED |
+ I40E_FLAG_DISABLE_FW_LLDP));
+
/* Before we finalize any flag changes, we need to perform some
* checks to ensure that the changes are supported and safe.
*/
@@ -4584,26 +4933,29 @@
return -EOPNOTSUPP;
/* If the driver detected FW LLDP was disabled on init, this flag could
- * be set, however we do not support _changing_ the flag if NPAR is
- * enabled or FW API version < 1.7. There are situations where older
- * FW versions/NPAR enabled PFs could disable LLDP, however we _must_
- * not allow the user to enable/disable LLDP with this flag on
- * unsupported FW versions.
+ * be set, however we do not support _changing_ the flag:
+ * - on XL710 if NPAR is enabled or FW API version < 1.7
+ * - on X722 with FW API version < 1.6
+ * There are situations where older FW versions/NPAR enabled PFs could
+ * disable LLDP, however we _must_ not allow the user to enable/disable
+ * LLDP with this flag on unsupported FW versions.
*/
if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
- if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) {
+ if (!(pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) {
dev_warn(&pf->pdev->dev,
"Device does not support changing FW LLDP\n");
return -EOPNOTSUPP;
}
}
- /* Now that we've checked to ensure that the new flags are valid, load
- * them into place. Since we only modify flags either (a) during
- * initialization or (b) while holding the RTNL lock, we don't need
- * anything fancy here.
- */
- pf->flags = new_flags;
+ if (((changed_flags & I40E_FLAG_RS_FEC) ||
+ (changed_flags & I40E_FLAG_BASE_R_FEC)) &&
+ pf->hw.device_id != I40E_DEV_ID_25G_SFP28 &&
+ pf->hw.device_id != I40E_DEV_ID_25G_B) {
+ dev_warn(&pf->pdev->dev,
+ "Device does not support changing FEC configuration\n");
+ return -EOPNOTSUPP;
+ }
/* Process any additional changes needed as a result of flag changes.
* The changed_flags value reflects the list of bits that were
@@ -4612,7 +4964,7 @@
/* Flush current ATR settings if ATR was disabled */
if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
- !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) {
+ !(new_flags & I40E_FLAG_FD_ATR_ENABLED)) {
set_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state);
set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
}
@@ -4621,7 +4973,7 @@
u16 sw_flags = 0, valid_flags = 0;
int ret;
- if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
+ if (!(new_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
@@ -4636,17 +4988,35 @@
}
}
- if ((changed_flags & pf->flags &
+ if ((changed_flags & I40E_FLAG_RS_FEC) ||
+ (changed_flags & I40E_FLAG_BASE_R_FEC)) {
+ u8 fec_cfg = 0;
+
+ if (new_flags & I40E_FLAG_RS_FEC &&
+ new_flags & I40E_FLAG_BASE_R_FEC) {
+ fec_cfg = I40E_AQ_SET_FEC_AUTO;
+ } else if (new_flags & I40E_FLAG_RS_FEC) {
+ fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+ I40E_AQ_SET_FEC_ABILITY_RS);
+ } else if (new_flags & I40E_FLAG_BASE_R_FEC) {
+ fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+ I40E_AQ_SET_FEC_ABILITY_KR);
+ }
+ if (i40e_set_fec_cfg(dev, fec_cfg))
+ dev_warn(&pf->pdev->dev, "Cannot change FEC config\n");
+ }
+
+ if ((changed_flags & new_flags &
I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) &&
- (pf->flags & I40E_FLAG_MFP_ENABLED))
+ (new_flags & I40E_FLAG_MFP_ENABLED))
dev_warn(&pf->pdev->dev,
"Turning on link-down-on-close flag may affect other partitions\n");
if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
- if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
+ if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) {
struct i40e_dcbx_config *dcbcfg;
- i40e_aq_stop_lldp(&pf->hw, true, NULL);
+ i40e_aq_stop_lldp(&pf->hw, true, false, NULL);
i40e_aq_set_dcb_parameters(&pf->hw, true, NULL);
/* reset local_dcbx_config to default */
dcbcfg = &pf->hw.local_dcbx_config;
@@ -4661,17 +5031,43 @@
dcbcfg->pfc.willing = 1;
dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS;
} else {
- i40e_aq_start_lldp(&pf->hw, NULL);
+ status = i40e_aq_start_lldp(&pf->hw, false, NULL);
+ if (status) {
+ adq_err = pf->hw.aq.asq_last_status;
+ switch (adq_err) {
+ case I40E_AQ_RC_EEXIST:
+ dev_warn(&pf->pdev->dev,
+ "FW LLDP agent is already running\n");
+ is_reset_needed = false;
+ break;
+ case I40E_AQ_RC_EPERM:
+ dev_warn(&pf->pdev->dev,
+ "Device configuration forbids SW from starting the LLDP agent.\n");
+ return -EINVAL;
+ default:
+ dev_warn(&pf->pdev->dev,
+ "Starting FW LLDP agent failed: error: %s, %s\n",
+ i40e_stat_str(&pf->hw,
+ status),
+ i40e_aq_str(&pf->hw,
+ adq_err));
+ return -EINVAL;
+ }
+ }
}
}
+ /* Now that we've checked to ensure that the new flags are valid, load
+ * them into place. Since we only modify flags either (a) during
+ * initialization or (b) while holding the RTNL lock, we don't need
+ * anything fancy here.
+ */
+ pf->flags = new_flags;
+
/* Issue reset to cause things to take effect, as additional bits
* are added we will need to create a mask of bits requiring reset
*/
- if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
- I40E_FLAG_LEGACY_RX |
- I40E_FLAG_SOURCE_PRUNING_DISABLED |
- I40E_FLAG_DISABLE_FW_LLDP))
+ if (is_reset_needed)
i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
return 0;
@@ -4741,6 +5137,12 @@
/* Module is not SFF-8472 compliant */
modinfo->type = ETH_MODULE_SFF_8079;
modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ } else if (!(sff8472_swap & I40E_MODULE_SFF_DDM_IMPLEMENTED)) {
+ /* Module is SFF-8472 compliant but doesn't implement
+ * Digital Diagnostic Monitoring (DDM).
+ */
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
} else {
modinfo->type = ETH_MODULE_SFF_8472;
modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
@@ -4829,6 +5231,22 @@
return 0;
}
+static int i40e_get_eee(struct net_device *netdev, struct ethtool_eee *edata)
+{
+ return -EOPNOTSUPP;
+}
+
+static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata)
+{
+ return -EOPNOTSUPP;
+}
+
+static const struct ethtool_ops i40e_ethtool_recovery_mode_ops = {
+ .set_eeprom = i40e_set_eeprom,
+ .get_eeprom_len = i40e_get_eeprom_len,
+ .get_eeprom = i40e_get_eeprom,
+};
+
static const struct ethtool_ops i40e_ethtool_ops = {
.get_drvinfo = i40e_get_drvinfo,
.get_regs_len = i40e_get_regs_len,
@@ -4850,6 +5268,8 @@
.set_rxnfc = i40e_set_rxnfc,
.self_test = i40e_diag_test,
.get_strings = i40e_get_strings,
+ .get_eee = i40e_get_eee,
+ .set_eee = i40e_set_eee,
.set_phys_id = i40e_set_phys_id,
.get_sset_count = i40e_get_sset_count,
.get_ethtool_stats = i40e_get_ethtool_stats,
@@ -4870,9 +5290,18 @@
.set_per_queue_coalesce = i40e_set_per_queue_coalesce,
.get_link_ksettings = i40e_get_link_ksettings,
.set_link_ksettings = i40e_set_link_ksettings,
+ .get_fecparam = i40e_get_fec_param,
+ .set_fecparam = i40e_set_fec_param,
+ .flash_device = i40e_ddp_flash,
};
void i40e_set_ethtool_ops(struct net_device *netdev)
{
- netdev->ethtool_ops = &i40e_ethtool_ops;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+
+ if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+ netdev->ethtool_ops = &i40e_ethtool_ops;
+ else
+ netdev->ethtool_ops = &i40e_ethtool_recovery_mode_ops;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
index 19ce93d..163ee8c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_osdep.h"
#include "i40e_register.h"
#include "i40e_status.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
index 994011c..be24d42 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_osdep.h"
#include "i40e_register.h"
#include "i40e_type.h"
@@ -963,7 +964,7 @@
/**
* i40e_hmc_get_object_va - retrieves an object's virtual address
- * @hmc_info: pointer to i40e_hmc_info struct
+ * @hw: the hardware struct, from which we obtain the i40e_hmc_info pointer
* @object_base: pointer to u64 to get the va
* @rsrc_type: the hmc resource type
* @obj_idx: hmc object index
@@ -972,16 +973,16 @@
* base pointer. This function is used for LAN Queue contexts.
**/
static
-i40e_status i40e_hmc_get_object_va(struct i40e_hmc_info *hmc_info,
- u8 **object_base,
- enum i40e_hmc_lan_rsrc_type rsrc_type,
- u32 obj_idx)
+i40e_status i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base,
+ enum i40e_hmc_lan_rsrc_type rsrc_type,
+ u32 obj_idx)
{
+ struct i40e_hmc_info *hmc_info = &hw->hmc;
u32 obj_offset_in_sd, obj_offset_in_pd;
- i40e_status ret_code = 0;
struct i40e_hmc_sd_entry *sd_entry;
struct i40e_hmc_pd_entry *pd_entry;
u32 pd_idx, pd_lmt, rel_pd_idx;
+ i40e_status ret_code = 0;
u64 obj_offset_in_fpm;
u32 sd_idx, sd_lmt;
@@ -1047,7 +1048,7 @@
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_TX, queue);
if (err < 0)
return err;
@@ -1068,7 +1069,7 @@
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_TX, queue);
if (err < 0)
return err;
@@ -1088,7 +1089,7 @@
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_RX, queue);
if (err < 0)
return err;
@@ -1109,7 +1110,7 @@
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_RX, queue);
if (err < 0)
return err;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3c34270..6031223 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9,7 +9,9 @@
/* Local includes */
#include "i40e.h"
#include "i40e_diag.h"
+#include "i40e_xsk.h"
#include <net/udp_tunnel.h>
+#include <net/xdp_sock.h>
/* All i40e tracepoints are defined by the include below, which
* must be included exactly once across the whole kernel with
* CREATE_TRACE_POINTS defined
@@ -24,13 +26,13 @@
#define DRV_KERN "-k"
#define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_MINOR 8
+#define DRV_VERSION_BUILD 20
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
const char i40e_driver_version_str[] = DRV_VERSION;
-static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporation.";
+static const char i40e_copyright[] = "Copyright (c) 2013 - 2019 Intel Corporation.";
/* a bit of forward declarations */
static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
@@ -44,6 +46,10 @@
static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
static int i40e_reset(struct i40e_pf *pf);
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf);
+static bool i40e_check_recovery_mode(struct i40e_pf *pf);
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw);
static void i40e_fdir_sb_setup(struct i40e_pf *pf);
static int i40e_veb_get_bw_info(struct i40e_veb *veb);
static int i40e_get_capabilities(struct i40e_pf *pf,
@@ -67,6 +73,9 @@
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
@@ -75,6 +84,8 @@
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_X710_N3000), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_XXV710_N3000), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0},
/* required last entry */
@@ -89,7 +100,7 @@
MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
static struct workqueue_struct *i40e_wq;
@@ -107,8 +118,8 @@
struct i40e_pf *pf = (struct i40e_pf *)hw->back;
mem->size = ALIGN(size, alignment);
- mem->va = dma_zalloc_coherent(&pf->pdev->dev, mem->size,
- &mem->pa, GFP_KERNEL);
+ mem->va = dma_alloc_coherent(&pf->pdev->dev, mem->size, &mem->pa,
+ GFP_KERNEL);
if (!mem->va)
return -ENOMEM;
@@ -276,8 +287,9 @@
**/
void i40e_service_event_schedule(struct i40e_pf *pf)
{
- if (!test_bit(__I40E_DOWN, pf->state) &&
- !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+ if ((!test_bit(__I40E_DOWN, pf->state) &&
+ !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) ||
+ test_bit(__I40E_RECOVERY_MODE, pf->state))
queue_work(i40e_wq, &pf->service_task);
}
@@ -336,6 +348,10 @@
(pf->tx_timeout_last_recovery + netdev->watchdog_timeo)))
return; /* don't do any new action before the next timeout */
+ /* don't kick off another recovery if one is already pending */
+ if (test_and_set_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state))
+ return;
+
if (tx_ring) {
head = i40e_get_head(tx_ring);
/* Read interrupt register */
@@ -420,9 +436,9 @@
struct rtnl_link_stats64 *stats)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_ring *tx_ring, *rx_ring;
struct i40e_vsi *vsi = np->vsi;
struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi);
+ struct i40e_ring *ring;
int i;
if (test_bit(__I40E_VSI_DOWN, vsi->state))
@@ -436,24 +452,26 @@
u64 bytes, packets;
unsigned int start;
- tx_ring = READ_ONCE(vsi->tx_rings[i]);
- if (!tx_ring)
+ ring = READ_ONCE(vsi->tx_rings[i]);
+ if (!ring)
continue;
- i40e_get_netdev_stats_struct_tx(tx_ring, stats);
+ i40e_get_netdev_stats_struct_tx(ring, stats);
- rx_ring = &tx_ring[1];
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ ring++;
+ i40e_get_netdev_stats_struct_tx(ring, stats);
+ }
+ ring++;
do {
- start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
- packets = rx_ring->stats.packets;
- bytes = rx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
+ packets = ring->stats.packets;
+ bytes = ring->stats.bytes;
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
stats->rx_packets += packets;
stats->rx_bytes += bytes;
- if (i40e_enabled_xdp_vsi(vsi))
- i40e_get_netdev_stats_struct_tx(&rx_ring[1], stats);
}
rcu_read_unlock();
@@ -517,6 +535,10 @@
sizeof(pf->veb[i]->stats));
memset(&pf->veb[i]->stats_offsets, 0,
sizeof(pf->veb[i]->stats_offsets));
+ memset(&pf->veb[i]->tc_stats, 0,
+ sizeof(pf->veb[i]->tc_stats));
+ memset(&pf->veb[i]->tc_stats_offsets, 0,
+ sizeof(pf->veb[i]->tc_stats_offsets));
pf->veb[i]->stat_offsets_loaded = false;
}
}
@@ -619,9 +641,6 @@
i40e_stat_update32(hw, I40E_GLV_RUPP(stat_idx),
vsi->stat_offsets_loaded,
&oes->rx_unknown_protocol, &es->rx_unknown_protocol);
- i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx),
- vsi->stat_offsets_loaded,
- &oes->tx_errors, &es->tx_errors);
i40e_stat_update48(hw, I40E_GLV_GORCH(stat_idx),
I40E_GLV_GORCL(stat_idx),
@@ -663,7 +682,7 @@
* i40e_update_veb_stats - Update Switch component statistics
* @veb: the VEB being updated
**/
-static void i40e_update_veb_stats(struct i40e_veb *veb)
+void i40e_update_veb_stats(struct i40e_veb *veb)
{
struct i40e_pf *pf = veb->pf;
struct i40e_hw *hw = &pf->hw;
@@ -1489,8 +1508,7 @@
bool found = false;
int bkt;
- WARN(!spin_is_locked(&vsi->mac_filter_hash_lock),
- "Missing mac_filter_hash_lock\n");
+ lockdep_assert_held(&vsi->mac_filter_hash_lock);
hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (ether_addr_equal(macaddr, f->macaddr)) {
__i40e_del_filter(vsi, f);
@@ -1528,8 +1546,8 @@
return 0;
}
- if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
- test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
+ if (test_bit(__I40E_DOWN, pf->state) ||
+ test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
return -EADDRNOTAVAIL;
if (ether_addr_equal(hw->mac.addr, addr->sa_data))
@@ -1539,22 +1557,21 @@
netdev_info(netdev, "set new mac address %pM\n", addr->sa_data);
/* Copy the address first, so that we avoid a possible race with
- * .set_rx_mode(). If we copy after changing the address in the filter
- * list, we might open ourselves to a narrow race window where
- * .set_rx_mode could delete our dev_addr filter and prevent traffic
- * from passing.
+ * .set_rx_mode().
+ * - Remove old address from MAC filter
+ * - Copy new address
+ * - Add new address to MAC filter
*/
- ether_addr_copy(netdev->dev_addr, addr->sa_data);
-
spin_lock_bh(&vsi->mac_filter_hash_lock);
i40e_del_mac_filter(vsi, netdev->dev_addr);
- i40e_add_mac_filter(vsi, addr->sa_data);
+ ether_addr_copy(netdev->dev_addr, addr->sa_data);
+ i40e_add_mac_filter(vsi, netdev->dev_addr);
spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
if (vsi->type == I40E_VSI_MAIN) {
i40e_status ret;
- ret = i40e_aq_mac_address_write(&vsi->back->hw,
- I40E_AQC_WRITE_TYPE_LAA_WOL,
+ ret = i40e_aq_mac_address_write(hw, I40E_AQC_WRITE_TYPE_LAA_WOL,
addr->sa_data, NULL);
if (ret)
netdev_info(netdev, "Ignoring error from firmware on LAA update, status %s, AQ ret %s\n",
@@ -1565,7 +1582,7 @@
/* schedule our worker thread which will take care of
* applying the new filter changes
*/
- i40e_service_event_schedule(vsi->back);
+ i40e_service_event_schedule(pf);
return 0;
}
@@ -2101,11 +2118,22 @@
fcnt = i40e_update_filter_state(num_add, list, add_head);
if (fcnt != num_add) {
- set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
- dev_warn(&vsi->back->pdev->dev,
- "Error %s adding RX filters on %s, promiscuous mode forced on\n",
- i40e_aq_str(hw, aq_err),
- vsi_name);
+ if (vsi->type == I40E_VSI_MAIN) {
+ set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+ i40e_aq_str(hw, aq_err), vsi_name);
+ } else if (vsi->type == I40E_VSI_SRIOV ||
+ vsi->type == I40E_VSI_VMDQ1 ||
+ vsi->type == I40E_VSI_VMDQ2) {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi_name);
+ } else {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi->type);
+ }
}
}
@@ -2507,6 +2535,10 @@
vsi_name,
i40e_stat_str(hw, aq_ret),
i40e_aq_str(hw, hw->aq.asq_last_status));
+ } else {
+ dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n",
+ vsi->netdev->name,
+ cur_multipromisc ? "entering" : "leaving");
}
}
@@ -2560,6 +2592,10 @@
return;
if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state))
return;
+ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) {
+ set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state);
+ return;
+ }
for (v = 0; v < pf->num_alloc_vsi; v++) {
if (pf->vsi[v] &&
@@ -2574,6 +2610,7 @@
}
}
}
+ clear_bit(__I40E_VF_DISABLE, pf->state);
}
/**
@@ -2648,6 +2685,10 @@
struct i40e_vsi_context ctxt;
i40e_status ret;
+ /* Don't modify stripping options if a port VLAN is active */
+ if (vsi->info.pvid)
+ return;
+
if ((vsi->info.valid_sections &
cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_MODE_MASK) == 0))
@@ -2678,6 +2719,10 @@
struct i40e_vsi_context ctxt;
i40e_status ret;
+ /* Don't modify stripping options if a port VLAN is active */
+ if (vsi->info.pvid)
+ return;
+
if ((vsi->info.valid_sections &
cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_EMOD_MASK) ==
@@ -2943,9 +2988,9 @@
**/
void i40e_vsi_remove_pvid(struct i40e_vsi *vsi)
{
- i40e_vlan_stripping_disable(vsi);
-
vsi->info.pvid = 0;
+
+ i40e_vlan_stripping_disable(vsi);
}
/**
@@ -3058,6 +3103,26 @@
}
/**
+ * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the UMEM or NULL.
+ **/
+static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+ bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+ int qid = ring->queue_index;
+
+ if (ring_is_xdp(ring))
+ qid -= ring->vsi->alloc_queue_pairs;
+
+ if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+ return NULL;
+
+ return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+}
+
+/**
* i40e_configure_tx_ring - Configure a transmit ring context and rest
* @ring: The Tx ring to configure
*
@@ -3072,6 +3137,9 @@
i40e_status err = 0;
u32 qtx_ctl = 0;
+ if (ring_is_xdp(ring))
+ ring->xsk_umem = i40e_xsk_umem(ring);
+
/* some ATR related tx ring init */
if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) {
ring->atr_sample_rate = vsi->back->atr_sample_rate;
@@ -3181,13 +3249,46 @@
struct i40e_hw *hw = &vsi->back->hw;
struct i40e_hmc_obj_rxq rx_ctx;
i40e_status err = 0;
+ bool ok;
+ int ret;
bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
/* clear the context structure first */
memset(&rx_ctx, 0, sizeof(rx_ctx));
- ring->rx_buf_len = vsi->rx_buf_len;
+ if (ring->vsi->type == I40E_VSI_MAIN)
+ xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+ ring->xsk_umem = i40e_xsk_umem(ring);
+ if (ring->xsk_umem) {
+ ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
+ XDP_PACKET_HEADROOM;
+ /* For AF_XDP ZC, we disallow packets to span on
+ * multiple buffers, thus letting us skip that
+ * handling in the fast-path.
+ */
+ chain_len = 1;
+ ring->zca.free = i40e_zca_free;
+ ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_ZERO_COPY,
+ &ring->zca);
+ if (ret)
+ return ret;
+ dev_info(&vsi->back->pdev->dev,
+ "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+ ring->queue_index);
+
+ } else {
+ ring->rx_buf_len = vsi->rx_buf_len;
+ if (ring->vsi->type == I40E_VSI_MAIN) {
+ ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED,
+ NULL);
+ if (ret)
+ return ret;
+ }
+ }
rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
@@ -3243,7 +3344,18 @@
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
writel(0, ring->tail);
- i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ ok = ring->xsk_umem ?
+ i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
+ !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ if (!ok) {
+ /* Log this in case the user has forgotten to give the kernel
+ * any buffers, even later in the application.
+ */
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
+ ring->xsk_umem ? "UMEM enabled " : "",
+ ring->queue_index, pf_q);
+ }
return 0;
}
@@ -3262,7 +3374,7 @@
for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
err = i40e_configure_tx_ring(vsi->tx_rings[i]);
- if (!i40e_enabled_xdp_vsi(vsi))
+ if (err || !i40e_enabled_xdp_vsi(vsi))
return err;
for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
@@ -3560,7 +3672,7 @@
(I40E_QUEUE_TYPE_TX
<< I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
- wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+ wr32(hw, I40E_QINT_TQCTL(nextqp), val);
}
val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
@@ -3927,7 +4039,8 @@
enable_intr:
/* re-enable interrupt causes */
wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
- if (!test_bit(__I40E_DOWN, pf->state)) {
+ if (!test_bit(__I40E_DOWN, pf->state) ||
+ test_bit(__I40E_RECOVERY_MODE, pf->state)) {
i40e_service_event_schedule(pf);
i40e_irq_dynamic_enable_icr0(pf);
}
@@ -5762,8 +5875,10 @@
return -ENOENT;
}
- /* Success, update channel */
- ch->enabled_tc = enabled_tc;
+ /* Success, update channel, set enabled_tc only if the channel
+ * is not a macvlan
+ */
+ ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc;
ch->seid = ctxt.seid;
ch->vsi_number = ctxt.vsi_number;
ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx);
@@ -6326,11 +6441,13 @@
* Also do not enable DCBx if FW LLDP agent is disabled
*/
if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) ||
- (pf->flags & I40E_FLAG_DISABLE_FW_LLDP))
+ (pf->flags & I40E_FLAG_DISABLE_FW_LLDP)) {
+ dev_info(&pf->pdev->dev, "DCB is not supported or FW LLDP is disabled\n");
+ err = I40E_NOT_SUPPORTED;
goto out;
+ }
- /* Get the initial DCB configuration */
- err = i40e_init_dcb(hw);
+ err = i40e_init_dcb(hw, true);
if (!err) {
/* Device/Function is not DCBX capable */
if ((!hw->func_caps.dcb) ||
@@ -6384,7 +6501,10 @@
char *req_fec = "";
char *an = "";
- new_speed = pf->hw.phy.link_info.link_speed;
+ if (isup)
+ new_speed = pf->hw.phy.link_info.link_speed;
+ else
+ new_speed = I40E_LINK_SPEED_UNKNOWN;
if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed))
return;
@@ -6417,6 +6537,12 @@
case I40E_LINK_SPEED_10GB:
speed = "10 G";
break;
+ case I40E_LINK_SPEED_5GB:
+ speed = "5 G";
+ break;
+ case I40E_LINK_SPEED_2_5GB:
+ speed = "2.5 G";
+ break;
case I40E_LINK_SPEED_1GB:
speed = "1000 M";
break;
@@ -6443,19 +6569,19 @@
}
if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
- req_fec = ", Requested FEC: None";
- fec = ", FEC: None";
- an = ", Autoneg: False";
+ req_fec = "None";
+ fec = "None";
+ an = "False";
if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
- an = ", Autoneg: True";
+ an = "True";
if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_KR_ENA)
- fec = ", FEC: CL74 FC-FEC/BASE-R";
+ fec = "CL74 FC-FEC/BASE-R";
else if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_RS_ENA)
- fec = ", FEC: CL108 RS-FEC";
+ fec = "CL108 RS-FEC";
/* 'CL108 RS-FEC' should be displayed when RS is requested, or
* both RS and FC are requested
@@ -6464,14 +6590,19 @@
(I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS)) {
if (vsi->back->hw.phy.link_info.req_fec_info &
I40E_AQ_REQUEST_FEC_RS)
- req_fec = ", Requested FEC: CL108 RS-FEC";
+ req_fec = "CL108 RS-FEC";
else
- req_fec = ", Requested FEC: CL74 FC-FEC/BASE-R";
+ req_fec = "CL74 FC-FEC/BASE-R";
}
+ netdev_info(vsi->netdev,
+ "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
+ speed, req_fec, fec, an, fc);
+ } else {
+ netdev_info(vsi->netdev,
+ "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n",
+ speed, fc);
}
- netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s%s, Flow Control: %s\n",
- speed, req_fec, fec, an, fc);
}
/**
@@ -6568,6 +6699,24 @@
struct i40e_hw *hw = &pf->hw;
i40e_status err;
u64 mask;
+ u8 speed;
+
+ /* Card might've been put in an unstable state by other drivers
+ * and applications, which causes incorrect speed values being
+ * set on startup. In order to clear speed registers, we call
+ * get_phy_capabilities twice, once to get initial state of
+ * available speeds, and once to get current PHY config.
+ */
+ err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities,
+ NULL);
+ if (err) {
+ dev_err(&pf->pdev->dev,
+ "failed to get phy cap., ret = %s last_status = %s\n",
+ i40e_stat_str(hw, err),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return err;
+ }
+ speed = abilities.link_speed;
/* Get the current phy config */
err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
@@ -6581,9 +6730,9 @@
}
/* If link needs to go up, but was not forced to go down,
- * no need for a flap
+ * and its speed values are OK, no need for a flap
*/
- if (is_up && abilities.phy_type != 0)
+ if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0)
return I40E_SUCCESS;
/* To force link we need to set bits for all supported PHY types,
@@ -6595,7 +6744,10 @@
config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0;
/* Copy the old settings, except of phy_type */
config.abilities = abilities.abilities;
- config.link_speed = abilities.link_speed;
+ if (abilities.link_speed != 0)
+ config.link_speed = abilities.link_speed;
+ else
+ config.link_speed = speed;
config.eee_capability = abilities.eee_capability;
config.eeer = abilities.eeer_val;
config.low_power_ctrl = abilities.d3_lpan;
@@ -6651,8 +6803,13 @@
for (i = 0; i < vsi->num_queue_pairs; i++) {
i40e_clean_tx_ring(vsi->tx_rings[i]);
- if (i40e_enabled_xdp_vsi(vsi))
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ /* Make sure that in-progress ndo_xdp_xmit
+ * calls are completed.
+ */
+ synchronize_rcu();
i40e_clean_tx_ring(vsi->xdp_rings[i]);
+ }
i40e_clean_rx_ring(vsi->rx_rings[i]);
}
@@ -6732,6 +6889,489 @@
}
/**
+ * i40e_del_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function deletes a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid,
+ const u8 *macaddr, int *aq_err)
+{
+ struct i40e_aqc_remove_macvlan_element_data element;
+ i40e_status status;
+
+ memset(&element, 0, sizeof(element));
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+ status = i40e_aq_remove_macvlan(hw, seid, &element, 1, NULL);
+ *aq_err = hw->aq.asq_last_status;
+
+ return status;
+}
+
+/**
+ * i40e_add_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function adds a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_add_macvlan_filter(struct i40e_hw *hw, u16 seid,
+ const u8 *macaddr, int *aq_err)
+{
+ struct i40e_aqc_add_macvlan_element_data element;
+ i40e_status status;
+ u16 cmd_flags = 0;
+
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ element.queue_number = 0;
+ element.match_method = I40E_AQC_MM_ERR_NO_RES;
+ cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH;
+ element.flags = cpu_to_le16(cmd_flags);
+ status = i40e_aq_add_macvlan(hw, seid, &element, 1, NULL);
+ *aq_err = hw->aq.asq_last_status;
+
+ return status;
+}
+
+/**
+ * i40e_reset_ch_rings - Reset the queue contexts in a channel
+ * @vsi: the VSI we want to access
+ * @ch: the channel we want to access
+ */
+static void i40e_reset_ch_rings(struct i40e_vsi *vsi, struct i40e_channel *ch)
+{
+ struct i40e_ring *tx_ring, *rx_ring;
+ u16 pf_q;
+ int i;
+
+ for (i = 0; i < ch->num_queue_pairs; i++) {
+ pf_q = ch->base_queue + i;
+ tx_ring = vsi->tx_rings[pf_q];
+ tx_ring->ch = NULL;
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->ch = NULL;
+ }
+}
+
+/**
+ * i40e_free_macvlan_channels
+ * @vsi: the VSI we want to access
+ *
+ * This function frees the Qs of the channel VSI from
+ * the stack and also deletes the channel VSIs which
+ * serve as macvlans.
+ */
+static void i40e_free_macvlan_channels(struct i40e_vsi *vsi)
+{
+ struct i40e_channel *ch, *ch_tmp;
+ int ret;
+
+ if (list_empty(&vsi->macvlan_list))
+ return;
+
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ struct i40e_vsi *parent_vsi;
+
+ if (i40e_is_channel_macvlan(ch)) {
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(vsi->netdev, ch->fwd->netdev);
+ netdev_set_sb_channel(ch->fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ }
+
+ list_del(&ch->list);
+ parent_vsi = ch->parent_vsi;
+ if (!parent_vsi || !ch->initialized) {
+ kfree(ch);
+ continue;
+ }
+
+ /* remove the VSI */
+ ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid,
+ NULL);
+ if (ret)
+ dev_err(&vsi->back->pdev->dev,
+ "unable to remove channel (%d) for parent VSI(%d)\n",
+ ch->seid, parent_vsi->seid);
+ kfree(ch);
+ }
+ vsi->macvlan_cnt = 0;
+}
+
+/**
+ * i40e_fwd_ring_up - bring the macvlan device up
+ * @vsi: the VSI we want to access
+ * @vdev: macvlan netdevice
+ * @fwd: the private fwd structure
+ */
+static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev,
+ struct i40e_fwd_adapter *fwd)
+{
+ int ret = 0, num_tc = 1, i, aq_err;
+ struct i40e_channel *ch, *ch_tmp;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ if (list_empty(&vsi->macvlan_list))
+ return -EINVAL;
+
+ /* Go through the list and find an available channel */
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ if (!i40e_is_channel_macvlan(ch)) {
+ ch->fwd = fwd;
+ /* record configuration for macvlan interface in vdev */
+ for (i = 0; i < num_tc; i++)
+ netdev_bind_sb_channel_queue(vsi->netdev, vdev,
+ i,
+ ch->num_queue_pairs,
+ ch->base_queue);
+ for (i = 0; i < ch->num_queue_pairs; i++) {
+ struct i40e_ring *tx_ring, *rx_ring;
+ u16 pf_q;
+
+ pf_q = ch->base_queue + i;
+
+ /* Get to TX ring ptr */
+ tx_ring = vsi->tx_rings[pf_q];
+ tx_ring->ch = ch;
+
+ /* Get the RX ring ptr */
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->ch = ch;
+ }
+ break;
+ }
+ }
+
+ /* Guarantee all rings are updated before we update the
+ * MAC address filter.
+ */
+ wmb();
+
+ /* Add a mac filter */
+ ret = i40e_add_macvlan_filter(hw, ch->seid, vdev->dev_addr, &aq_err);
+ if (ret) {
+ /* if we cannot add the MAC rule then disable the offload */
+ macvlan_release_l2fw_offload(vdev);
+ for (i = 0; i < ch->num_queue_pairs; i++) {
+ struct i40e_ring *rx_ring;
+ u16 pf_q;
+
+ pf_q = ch->base_queue + i;
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->netdev = NULL;
+ }
+ dev_info(&pf->pdev->dev,
+ "Error adding mac filter on macvlan err %s, aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, aq_err));
+ netdev_err(vdev, "L2fwd offload disabled to L2 filter error\n");
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_setup_macvlans - create the channels which will be macvlans
+ * @vsi: the VSI we want to access
+ * @macvlan_cnt: no. of macvlans to be setup
+ * @qcnt: no. of Qs per macvlan
+ * @vdev: macvlan netdevice
+ */
+static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt,
+ struct net_device *vdev)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vsi_context ctxt;
+ u16 sections, qmap, num_qps;
+ struct i40e_channel *ch;
+ int i, pow, ret = 0;
+ u8 offset = 0;
+
+ if (vsi->type != I40E_VSI_MAIN || !macvlan_cnt)
+ return -EINVAL;
+
+ num_qps = vsi->num_queue_pairs - (macvlan_cnt * qcnt);
+
+ /* find the next higher power-of-2 of num queue pairs */
+ pow = fls(roundup_pow_of_two(num_qps) - 1);
+
+ qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+ (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+ /* Setup context bits for the main VSI */
+ sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+ sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+ memset(&ctxt, 0, sizeof(ctxt));
+ ctxt.seid = vsi->seid;
+ ctxt.pf_num = vsi->back->hw.pf_id;
+ ctxt.vf_num = 0;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.info = vsi->info;
+ ctxt.info.tc_mapping[0] = cpu_to_le16(qmap);
+ ctxt.info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+ ctxt.info.queue_mapping[0] = cpu_to_le16(vsi->base_queue);
+ ctxt.info.valid_sections |= cpu_to_le16(sections);
+
+ /* Reconfigure RSS for main VSI with new max queue count */
+ vsi->rss_size = max_t(u16, num_qps, qcnt);
+ ret = i40e_vsi_config_rss(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Failed to reconfig RSS for num_queues (%u)\n",
+ vsi->rss_size);
+ return ret;
+ }
+ vsi->reconfig_rss = true;
+ dev_dbg(&vsi->back->pdev->dev,
+ "Reconfigured RSS with num_queues (%u)\n", vsi->rss_size);
+ vsi->next_base_queue = num_qps;
+ vsi->cnt_q_avail = vsi->num_queue_pairs - num_qps;
+
+ /* Update the VSI after updating the VSI queue-mapping
+ * information
+ */
+ ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Update vsi tc config failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return ret;
+ }
+ /* update the local VSI info with updated queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+
+ /* Create channels for macvlans */
+ INIT_LIST_HEAD(&vsi->macvlan_list);
+ for (i = 0; i < macvlan_cnt; i++) {
+ ch = kzalloc(sizeof(*ch), GFP_KERNEL);
+ if (!ch) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+ INIT_LIST_HEAD(&ch->list);
+ ch->num_queue_pairs = qcnt;
+ if (!i40e_setup_channel(pf, vsi, ch)) {
+ ret = -EINVAL;
+ goto err_free;
+ }
+ ch->parent_vsi = vsi;
+ vsi->cnt_q_avail -= ch->num_queue_pairs;
+ vsi->macvlan_cnt++;
+ list_add_tail(&ch->list, &vsi->macvlan_list);
+ }
+
+ return ret;
+
+err_free:
+ dev_info(&pf->pdev->dev, "Failed to setup macvlans\n");
+ i40e_free_macvlan_channels(vsi);
+
+ return ret;
+}
+
+/**
+ * i40e_fwd_add - configure macvlans
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ **/
+static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ u16 q_per_macvlan = 0, macvlan_cnt = 0, vectors;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_fwd_adapter *fwd;
+ int avail_macvlan, ret;
+
+ if ((pf->flags & I40E_FLAG_DCB_ENABLED)) {
+ netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if ((pf->flags & I40E_FLAG_TC_MQPRIO)) {
+ netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (pf->num_lan_msix < I40E_MIN_MACVLAN_VECTORS) {
+ netdev_info(netdev, "Not enough vectors available to support macvlans\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* The macvlan device has to be a single Q device so that the
+ * tc_to_txq field can be reused to pick the tx queue.
+ */
+ if (netif_is_multiqueue(vdev))
+ return ERR_PTR(-ERANGE);
+
+ if (!vsi->macvlan_cnt) {
+ /* reserve bit 0 for the pf device */
+ set_bit(0, vsi->fwd_bitmask);
+
+ /* Try to reserve as many queues as possible for macvlans. First
+ * reserve 3/4th of max vectors, then half, then quarter and
+ * calculate Qs per macvlan as you go
+ */
+ vectors = pf->num_lan_msix;
+ if (vectors <= I40E_MAX_MACVLANS && vectors > 64) {
+ /* allocate 4 Qs per macvlan and 32 Qs to the PF*/
+ q_per_macvlan = 4;
+ macvlan_cnt = (vectors - 32) / 4;
+ } else if (vectors <= 64 && vectors > 32) {
+ /* allocate 2 Qs per macvlan and 16 Qs to the PF*/
+ q_per_macvlan = 2;
+ macvlan_cnt = (vectors - 16) / 2;
+ } else if (vectors <= 32 && vectors > 16) {
+ /* allocate 1 Q per macvlan and 16 Qs to the PF*/
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 16;
+ } else if (vectors <= 16 && vectors > 8) {
+ /* allocate 1 Q per macvlan and 8 Qs to the PF */
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 8;
+ } else {
+ /* allocate 1 Q per macvlan and 1 Q to the PF */
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 1;
+ }
+
+ if (macvlan_cnt == 0)
+ return ERR_PTR(-EBUSY);
+
+ /* Quiesce VSI queues */
+ i40e_quiesce_vsi(vsi);
+
+ /* sets up the macvlans but does not "enable" them */
+ ret = i40e_setup_macvlans(vsi, macvlan_cnt, q_per_macvlan,
+ vdev);
+ if (ret)
+ return ERR_PTR(ret);
+
+ /* Unquiesce VSI */
+ i40e_unquiesce_vsi(vsi);
+ }
+ avail_macvlan = find_first_zero_bit(vsi->fwd_bitmask,
+ vsi->macvlan_cnt);
+ if (avail_macvlan >= I40E_MAX_MACVLANS)
+ return ERR_PTR(-EBUSY);
+
+ /* create the fwd struct */
+ fwd = kzalloc(sizeof(*fwd), GFP_KERNEL);
+ if (!fwd)
+ return ERR_PTR(-ENOMEM);
+
+ set_bit(avail_macvlan, vsi->fwd_bitmask);
+ fwd->bit_no = avail_macvlan;
+ netdev_set_sb_channel(vdev, avail_macvlan);
+ fwd->netdev = vdev;
+
+ if (!netif_running(netdev))
+ return fwd;
+
+ /* Set fwd ring up */
+ ret = i40e_fwd_ring_up(vsi, vdev, fwd);
+ if (ret) {
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
+ kfree(fwd);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return fwd;
+}
+
+/**
+ * i40e_del_all_macvlans - Delete all the mac filters on the channels
+ * @vsi: the VSI we want to access
+ */
+static void i40e_del_all_macvlans(struct i40e_vsi *vsi)
+{
+ struct i40e_channel *ch, *ch_tmp;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int aq_err, ret = 0;
+
+ if (list_empty(&vsi->macvlan_list))
+ return;
+
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ if (i40e_is_channel_macvlan(ch)) {
+ ret = i40e_del_macvlan_filter(hw, ch->seid,
+ i40e_channel_mac(ch),
+ &aq_err);
+ if (!ret) {
+ /* Reset queue contexts */
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(vsi->netdev,
+ ch->fwd->netdev);
+ netdev_set_sb_channel(ch->fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ }
+ }
+ }
+}
+
+/**
+ * i40e_fwd_del - delete macvlan interfaces
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ */
+static void i40e_fwd_del(struct net_device *netdev, void *vdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_fwd_adapter *fwd = vdev;
+ struct i40e_channel *ch, *ch_tmp;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int aq_err, ret = 0;
+
+ /* Find the channel associated with the macvlan and del mac filter */
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ if (i40e_is_channel_macvlan(ch) &&
+ ether_addr_equal(i40e_channel_mac(ch),
+ fwd->netdev->dev_addr)) {
+ ret = i40e_del_macvlan_filter(hw, ch->seid,
+ i40e_channel_mac(ch),
+ &aq_err);
+ if (!ret) {
+ /* Reset queue contexts */
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(netdev, fwd->netdev);
+ netdev_set_sb_channel(fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Error deleting mac filter on macvlan err %s, aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, aq_err));
+ }
+ break;
+ }
+ }
+}
+
+/**
* i40e_setup_tc - configure multiple traffic classes
* @netdev: net device to configure
* @type_data: tc offload data
@@ -6744,10 +7384,12 @@
struct i40e_pf *pf = vsi->back;
u8 enabled_tc = 0, num_tc, hw;
bool need_reset = false;
+ int old_queue_pairs;
int ret = -EINVAL;
u16 mode;
int i;
+ old_queue_pairs = vsi->num_queue_pairs;
num_tc = mqprio_qopt->qopt.num_tc;
hw = mqprio_qopt->qopt.hw;
mode = mqprio_qopt->mode;
@@ -6824,6 +7466,10 @@
vsi->seid);
need_reset = true;
goto exit;
+ } else {
+ dev_info(&vsi->back->pdev->dev,
+ "Setup channel (id:%u) utilizing num_queues %d\n",
+ vsi->seid, vsi->tc_config.tc_info[0].qcount);
}
if (pf->flags & I40E_FLAG_TC_MQPRIO) {
@@ -6848,6 +7494,7 @@
}
ret = i40e_configure_queue_channels(vsi);
if (ret) {
+ vsi->num_queue_pairs = old_queue_pairs;
netdev_info(netdev,
"Failed configuring queue channels\n");
need_reset = true;
@@ -7087,19 +7734,21 @@
/**
* i40e_parse_cls_flower - Parse tc flower filters provided by kernel
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
* @filter: Pointer to cloud filter structure
*
**/
static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *f,
+ struct flow_cls_offload *f,
struct i40e_cloud_filter *filter)
{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+ struct flow_dissector *dissector = rule->match.dissector;
u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
struct i40e_pf *pf = vsi->back;
u8 field_flags = 0;
- if (f->dissector->used_keys &
+ if (dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_BASIC) |
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -7109,143 +7758,109 @@
BIT(FLOW_DISSECTOR_KEY_PORTS) |
BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
- f->dissector->used_keys);
+ dissector->used_keys);
return -EOPNOTSUPP;
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
- struct flow_dissector_key_keyid *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ENC_KEYID,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_match_enc_keyid match;
- struct flow_dissector_key_keyid *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ENC_KEYID,
- f->mask);
-
- if (mask->keyid != 0)
+ flow_rule_match_enc_keyid(rule, &match);
+ if (match.mask->keyid != 0)
field_flags |= I40E_CLOUD_FIELD_TEN_ID;
- filter->tenant_id = be32_to_cpu(key->keyid);
+ filter->tenant_id = be32_to_cpu(match.key->keyid);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_match_basic match;
- struct flow_dissector_key_basic *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
-
- n_proto_key = ntohs(key->n_proto);
- n_proto_mask = ntohs(mask->n_proto);
+ flow_rule_match_basic(rule, &match);
+ n_proto_key = ntohs(match.key->n_proto);
+ n_proto_mask = ntohs(match.mask->n_proto);
if (n_proto_key == ETH_P_ALL) {
n_proto_key = 0;
n_proto_mask = 0;
}
filter->n_proto = n_proto_key & n_proto_mask;
- filter->ip_proto = key->ip_proto;
+ filter->ip_proto = match.key->ip_proto;
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
- struct flow_dissector_key_eth_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_match_eth_addrs match;
- struct flow_dissector_key_eth_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->mask);
+ flow_rule_match_eth_addrs(rule, &match);
/* use is_broadcast and is_zero to check for all 0xf or 0 */
- if (!is_zero_ether_addr(mask->dst)) {
- if (is_broadcast_ether_addr(mask->dst)) {
+ if (!is_zero_ether_addr(match.mask->dst)) {
+ if (is_broadcast_ether_addr(match.mask->dst)) {
field_flags |= I40E_CLOUD_FIELD_OMAC;
} else {
dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
- mask->dst);
+ match.mask->dst);
return I40E_ERR_CONFIG;
}
}
- if (!is_zero_ether_addr(mask->src)) {
- if (is_broadcast_ether_addr(mask->src)) {
+ if (!is_zero_ether_addr(match.mask->src)) {
+ if (is_broadcast_ether_addr(match.mask->src)) {
field_flags |= I40E_CLOUD_FIELD_IMAC;
} else {
dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
- mask->src);
+ match.mask->src);
return I40E_ERR_CONFIG;
}
}
- ether_addr_copy(filter->dst_mac, key->dst);
- ether_addr_copy(filter->src_mac, key->src);
+ ether_addr_copy(filter->dst_mac, match.key->dst);
+ ether_addr_copy(filter->src_mac, match.key->src);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
- struct flow_dissector_key_vlan *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->key);
- struct flow_dissector_key_vlan *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->mask);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_match_vlan match;
- if (mask->vlan_id) {
- if (mask->vlan_id == VLAN_VID_MASK) {
+ flow_rule_match_vlan(rule, &match);
+ if (match.mask->vlan_id) {
+ if (match.mask->vlan_id == VLAN_VID_MASK) {
field_flags |= I40E_CLOUD_FIELD_IVLAN;
} else {
dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
- mask->vlan_id);
+ match.mask->vlan_id);
return I40E_ERR_CONFIG;
}
}
- filter->vlan_id = cpu_to_be16(key->vlan_id);
+ filter->vlan_id = cpu_to_be16(match.key->vlan_id);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
- struct flow_dissector_key_control *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_match_control match;
- addr_type = key->addr_type;
+ flow_rule_match_control(rule, &match);
+ addr_type = match.key->addr_type;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
- struct flow_dissector_key_ipv4_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->key);
- struct flow_dissector_key_ipv4_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->mask);
+ struct flow_match_ipv4_addrs match;
- if (mask->dst) {
- if (mask->dst == cpu_to_be32(0xffffffff)) {
+ flow_rule_match_ipv4_addrs(rule, &match);
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
- &mask->dst);
+ &match.mask->dst);
return I40E_ERR_CONFIG;
}
}
- if (mask->src) {
- if (mask->src == cpu_to_be32(0xffffffff)) {
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
- &mask->src);
+ &match.mask->src);
return I40E_ERR_CONFIG;
}
}
@@ -7254,70 +7869,60 @@
dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
return I40E_ERR_CONFIG;
}
- filter->dst_ipv4 = key->dst;
- filter->src_ipv4 = key->src;
+ filter->dst_ipv4 = match.key->dst;
+ filter->src_ipv4 = match.key->src;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
- struct flow_dissector_key_ipv6_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->key);
- struct flow_dissector_key_ipv6_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->mask);
+ struct flow_match_ipv6_addrs match;
+
+ flow_rule_match_ipv6_addrs(rule, &match);
/* src and dest IPV6 address should not be LOOPBACK
* (0:0:0:0:0:0:0:1), which can be represented as ::1
*/
- if (ipv6_addr_loopback(&key->dst) ||
- ipv6_addr_loopback(&key->src)) {
+ if (ipv6_addr_loopback(&match.key->dst) ||
+ ipv6_addr_loopback(&match.key->src)) {
dev_err(&pf->pdev->dev,
"Bad ipv6, addr is LOOPBACK\n");
return I40E_ERR_CONFIG;
}
- if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+ if (!ipv6_addr_any(&match.mask->dst) ||
+ !ipv6_addr_any(&match.mask->src))
field_flags |= I40E_CLOUD_FIELD_IIP;
- memcpy(&filter->src_ipv6, &key->src.s6_addr32,
+ memcpy(&filter->src_ipv6, &match.key->src.s6_addr32,
sizeof(filter->src_ipv6));
- memcpy(&filter->dst_ipv6, &key->dst.s6_addr32,
+ memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32,
sizeof(filter->dst_ipv6));
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
- struct flow_dissector_key_ports *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->key);
- struct flow_dissector_key_ports *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->mask);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+ struct flow_match_ports match;
- if (mask->src) {
- if (mask->src == cpu_to_be16(0xffff)) {
+ flow_rule_match_ports(rule, &match);
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be16(0xffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
- be16_to_cpu(mask->src));
+ be16_to_cpu(match.mask->src));
return I40E_ERR_CONFIG;
}
}
- if (mask->dst) {
- if (mask->dst == cpu_to_be16(0xffff)) {
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be16(0xffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
- be16_to_cpu(mask->dst));
+ be16_to_cpu(match.mask->dst));
return I40E_ERR_CONFIG;
}
}
- filter->dst_port = key->dst;
- filter->src_port = key->src;
+ filter->dst_port = match.key->dst;
+ filter->src_port = match.key->src;
switch (filter->ip_proto) {
case IPPROTO_TCP:
@@ -7371,11 +7976,11 @@
/**
* i40e_configure_clsflower - Configure tc flower filters
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
*
**/
static int i40e_configure_clsflower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid);
struct i40e_cloud_filter *filter = NULL;
@@ -7467,11 +8072,11 @@
/**
* i40e_delete_clsflower - Remove tc flower filters
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
*
**/
static int i40e_delete_clsflower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct i40e_cloud_filter *filter = NULL;
struct i40e_pf *pf = vsi->back;
@@ -7514,16 +8119,16 @@
* @type_data: offload data
**/
static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct i40e_vsi *vsi = np->vsi;
switch (cls_flower->command) {
- case TC_CLSFLOWER_REPLACE:
+ case FLOW_CLS_REPLACE:
return i40e_configure_clsflower(vsi, cls_flower);
- case TC_CLSFLOWER_DESTROY:
+ case FLOW_CLS_DESTROY:
return i40e_delete_clsflower(vsi, cls_flower);
- case TC_CLSFLOWER_STATS:
+ case FLOW_CLS_STATS:
return -EOPNOTSUPP;
default:
return -EOPNOTSUPP;
@@ -7547,34 +8152,21 @@
}
}
-static int i40e_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct i40e_netdev_priv *np = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
- np, np, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
+static LIST_HEAD(i40e_block_cb_list);
static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+
switch (type) {
case TC_SETUP_QDISC_MQPRIO:
return i40e_setup_tc(netdev, type_data);
case TC_SETUP_BLOCK:
- return i40e_setup_tc_block(netdev, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &i40e_block_cb_list,
+ i40e_setup_tc_block_cb,
+ np, np, true);
default:
return -EOPNOTSUPP;
}
@@ -7869,6 +8461,11 @@
dev_dbg(&pf->pdev->dev, "PFR requested\n");
i40e_handle_reset_warning(pf, lock_acquired);
+ dev_info(&pf->pdev->dev,
+ pf->flags & I40E_FLAG_DISABLE_FW_LLDP ?
+ "FW LLDP is disabled\n" :
+ "FW LLDP is enabled\n");
+
} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
int v;
@@ -8057,8 +8654,8 @@
i40e_service_event_schedule(pf);
} else {
i40e_pf_unquiesce_all_vsi(pf);
- set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
- set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
+ set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
+ set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
}
exit:
@@ -8440,14 +9037,9 @@
i40e_status status;
bool new_link, old_link;
- /* save off old link status information */
- pf->hw.phy.link_info_old = pf->hw.phy.link_info;
-
/* set this to force the get_link_status call to refresh state */
pf->hw.phy.get_link_info = true;
-
old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP);
-
status = i40e_get_link_status(&pf->hw, &new_link);
/* On success, disable temp link polling */
@@ -8477,7 +9069,7 @@
/* Notify the base of the switch tree connected to
* the link. Floating VEBs are not notified.
*/
- if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
i40e_veb_link_event(pf->veb[pf->lan_veb], new_link);
else
i40e_vsi_link_event(vsi, new_link);
@@ -9235,6 +9827,11 @@
dev_warn(&pf->pdev->dev,
"shutdown_lan_hmc failed: %d\n", ret);
}
+
+ /* Save the current PTP time so that we can restore the time after the
+ * reset completes.
+ */
+ i40e_ptp_save_hw_time(pf);
}
/**
@@ -9327,6 +9924,7 @@
**/
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
{
+ int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state);
struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
struct i40e_hw *hw = &pf->hw;
u8 set_fc_aq_fail = 0;
@@ -9334,7 +9932,14 @@
u32 val;
int v;
- if (test_bit(__I40E_DOWN, pf->state))
+ if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
+ i40e_check_recovery_mode(pf)) {
+ i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
+ }
+
+ if (test_bit(__I40E_DOWN, pf->state) &&
+ !test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+ !old_recovery_mode_bit)
goto clear_recovery;
dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
@@ -9363,6 +9968,44 @@
if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
i40e_verify_eeprom(pf);
+ /* if we are going out of or into recovery mode we have to act
+ * accordingly with regard to resources initialization
+ * and deinitialization
+ */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state) ||
+ old_recovery_mode_bit) {
+ if (i40e_get_capabilities(pf,
+ i40e_aqc_opc_list_func_capabilities))
+ goto end_unlock;
+
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ /* we're staying in recovery mode so we'll reinitialize
+ * misc vector here
+ */
+ if (i40e_setup_misc_vector_for_recovery_mode(pf))
+ goto end_unlock;
+ } else {
+ if (!lock_acquired)
+ rtnl_lock();
+ /* we're going out of recovery mode so we'll free
+ * the IRQ allocated specifically for recovery mode
+ * and restore the interrupt scheme
+ */
+ free_irq(pf->pdev->irq, pf);
+ i40e_clear_interrupt_scheme(pf);
+ if (i40e_restore_interrupt_scheme(pf))
+ goto end_unlock;
+ }
+
+ /* tell the firmware that we're starting */
+ i40e_send_version(pf);
+
+ /* bail out in case recovery mode was detected, as there is
+ * no need for further configuration.
+ */
+ goto end_unlock;
+ }
+
i40e_clear_pxe_mode(hw);
ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
if (ret)
@@ -9566,6 +10209,7 @@
clear_bit(__I40E_RESET_FAILED, pf->state);
clear_recovery:
clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+ clear_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state);
}
/**
@@ -9613,7 +10257,6 @@
{
struct i40e_hw *hw = &pf->hw;
bool mdd_detected = false;
- bool pf_mdd_detected = false;
struct i40e_vf *vf;
u32 reg;
int i;
@@ -9659,19 +10302,12 @@
reg = rd32(hw, I40E_PF_MDET_TX);
if (reg & I40E_PF_MDET_TX_VALID_MASK) {
wr32(hw, I40E_PF_MDET_TX, 0xFFFF);
- dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
- pf_mdd_detected = true;
+ dev_dbg(&pf->pdev->dev, "TX driver issue detected on PF\n");
}
reg = rd32(hw, I40E_PF_MDET_RX);
if (reg & I40E_PF_MDET_RX_VALID_MASK) {
wr32(hw, I40E_PF_MDET_RX, 0xFFFF);
- dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
- pf_mdd_detected = true;
- }
- /* Queue belongs to the PF, initiate a reset */
- if (pf_mdd_detected) {
- set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
- i40e_service_event_schedule(pf);
+ dev_dbg(&pf->pdev->dev, "RX driver issue detected on PF\n");
}
}
@@ -9684,6 +10320,9 @@
vf->num_mdd_events++;
dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
i);
+ dev_info(&pf->pdev->dev,
+ "Use PF Control I/F to re-enable the VF\n");
+ set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
}
reg = rd32(hw, I40E_VP_MDET_RX(i));
@@ -9692,11 +10331,6 @@
vf->num_mdd_events++;
dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
i);
- }
-
- if (vf->num_mdd_events > I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED) {
- dev_info(&pf->pdev->dev,
- "Too many MDD events on VF %d, disabled\n", i);
dev_info(&pf->pdev->dev,
"Use PF Control I/F to re-enable the VF\n");
set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
@@ -9823,31 +10457,38 @@
unsigned long start_time = jiffies;
/* don't bother with service tasks if a reset is in progress */
- if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+ if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+ test_bit(__I40E_SUSPENDED, pf->state))
return;
if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
return;
- i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
- i40e_sync_filters_subtask(pf);
- i40e_reset_subtask(pf);
- i40e_handle_mdd_event(pf);
- i40e_vc_process_vflr_event(pf);
- i40e_watchdog_subtask(pf);
- i40e_fdir_reinit_subtask(pf);
- if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
- /* Client subtask will reopen next time through. */
- i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+ if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
+ i40e_sync_filters_subtask(pf);
+ i40e_reset_subtask(pf);
+ i40e_handle_mdd_event(pf);
+ i40e_vc_process_vflr_event(pf);
+ i40e_watchdog_subtask(pf);
+ i40e_fdir_reinit_subtask(pf);
+ if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
+ /* Client subtask will reopen next time through. */
+ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi],
+ true);
+ } else {
+ i40e_client_subtask(pf);
+ if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
+ pf->state))
+ i40e_notify_client_of_l2_param_changes(
+ pf->vsi[pf->lan_vsi]);
+ }
+ i40e_sync_filters_subtask(pf);
+ i40e_sync_udp_filters_subtask(pf);
} else {
- i40e_client_subtask(pf);
- if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
- pf->state))
- i40e_notify_client_of_l2_param_changes(
- pf->vsi[pf->lan_vsi]);
+ i40e_reset_subtask(pf);
}
- i40e_sync_filters_subtask(pf);
- i40e_sync_udp_filters_subtask(pf);
+
i40e_clean_adminq_subtask(pf);
/* flush memory to make sure state is correct before next watchdog */
@@ -9889,8 +10530,12 @@
switch (vsi->type) {
case I40E_VSI_MAIN:
vsi->alloc_queue_pairs = pf->num_lan_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
if (pf->flags & I40E_FLAG_MSIX_ENABLED)
vsi->num_q_vectors = pf->num_lan_msix;
else
@@ -9900,22 +10545,32 @@
case I40E_VSI_FDIR:
vsi->alloc_queue_pairs = 1;
- vsi->num_desc = ALIGN(I40E_FDIR_RING_COUNT,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_tx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_rx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
vsi->num_q_vectors = pf->num_fdsb_msix;
break;
case I40E_VSI_VMDQ2:
vsi->alloc_queue_pairs = pf->num_vmdq_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
vsi->num_q_vectors = pf->num_vmdq_msix;
break;
case I40E_VSI_SRIOV:
vsi->alloc_queue_pairs = pf->num_vf_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
break;
default:
@@ -10028,6 +10683,12 @@
hash_init(vsi->mac_filter_hash);
vsi->irqs_ready = false;
+ if (type == I40E_VSI_MAIN) {
+ vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+ if (!vsi->af_xdp_zc_qps)
+ goto err_rings;
+ }
+
ret = i40e_set_num_rings_in_vsi(vsi);
if (ret)
goto err_rings;
@@ -10046,6 +10707,7 @@
goto unlock_pf;
err_rings:
+ bitmap_free(vsi->af_xdp_zc_qps);
pf->next_vsi = i - 1;
kfree(vsi);
unlock_pf:
@@ -10126,6 +10788,7 @@
i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
+ bitmap_free(vsi->af_xdp_zc_qps);
i40e_vsi_free_arrays(vsi, true);
i40e_clear_rss_config_user(vsi);
@@ -10183,7 +10846,7 @@
ring->vsi = vsi;
ring->netdev = vsi->netdev;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_tx_desc;
ring->size = 0;
ring->dcb_tc = 0;
if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10200,7 +10863,7 @@
ring->vsi = vsi;
ring->netdev = NULL;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_tx_desc;
ring->size = 0;
ring->dcb_tc = 0;
if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10216,7 +10879,7 @@
ring->vsi = vsi;
ring->netdev = vsi->netdev;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_rx_desc;
ring->size = 0;
ring->dcb_tc = 0;
ring->itr_setting = pf->rx_itr_default;
@@ -10662,6 +11325,48 @@
}
/**
+ * i40e_setup_misc_vector_for_recovery_mode - Setup the misc vector to handle
+ * non queue events in recovery mode
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0 or MSI/legacy, which is used to manage
+ * the non-queue interrupts, e.g. AdminQ and errors in recovery mode.
+ * This is handled differently than in recovery mode since no Tx/Rx resources
+ * are being allocated.
+ **/
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
+{
+ int err;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ err = i40e_setup_misc_vector(pf);
+
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "MSI-X misc vector request failed, error %d\n",
+ err);
+ return err;
+ }
+ } else {
+ u32 flags = pf->flags & I40E_FLAG_MSI_ENABLED ? 0 : IRQF_SHARED;
+
+ err = request_irq(pf->pdev->irq, i40e_intr, flags,
+ pf->int_name, pf);
+
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "MSI/legacy misc vector request failed, error %d\n",
+ err);
+ return err;
+ }
+ i40e_enable_misc_int_causes(pf);
+ i40e_irq_dynamic_enable_icr0(pf);
+ }
+
+ return 0;
+}
+
+/**
* i40e_setup_misc_vector - Setup the misc vector to handle non queue events
* @pf: board private structure
*
@@ -10972,6 +11677,7 @@
if (!(pf->flags & I40E_FLAG_RSS_ENABLED))
return 0;
+ queue_count = min_t(int, queue_count, num_online_cpus());
new_rss_size = min_t(int, queue_count, pf->rss_size_max);
if (queue_count != vsi->num_queue_pairs) {
@@ -11266,16 +11972,15 @@
/* IWARP needs one extra vector for CQP just like MISC.*/
pf->num_iwarp_msix = (int)num_online_cpus() + 1;
}
- /* Stopping the FW LLDP engine is only supported on the
- * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP
- * engine is not supported if NPAR is functioning on this
- * part
+ /* Stopping FW LLDP engine is supported on XL710 and X722
+ * starting from FW versions determined in i40e_init_adminq.
+ * Stopping the FW LLDP engine is not supported on XL710
+ * if NPAR is functioning so unset this hw flag in this case.
*/
if (pf->hw.mac.type == I40E_MAC_XL710 &&
- !pf->hw.func_caps.npar_enable &&
- (pf->hw.aq.api_maj_ver > 1 ||
- (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6)))
- pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP;
+ pf->hw.func_caps.npar_enable &&
+ (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+ pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE;
#ifdef CONFIG_PCI_IOV
if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
@@ -11412,6 +12117,9 @@
return -EINVAL;
}
+ if (!(features & NETIF_F_HW_L2FW_DOFFLOAD) && vsi->macvlan_cnt)
+ i40e_del_all_macvlans(vsi);
+
need_reset = i40e_set_ntuple(pf, features);
if (need_reset)
@@ -11575,7 +12283,8 @@
static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_pf *pf = np->vsi->back;
@@ -11616,6 +12325,7 @@
* @dev: the netdev being configured
* @nlh: RTNL message
* @flags: bridge flags
+ * @extack: netlink extended ack
*
* Inserts a new hardware bridge if not already created and
* enables the bridging mode requested (VEB or VEPA). If the
@@ -11628,7 +12338,8 @@
**/
static int i40e_ndo_bridge_setlink(struct net_device *dev,
struct nlmsghdr *nlh,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
@@ -11824,10 +12535,274 @@
if (old_prog)
bpf_prog_put(old_prog);
+ /* Kick start the NAPI context if there is an AF_XDP socket open
+ * on that queue id. This so that receiving will start.
+ */
+ if (need_reset && prog)
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ if (vsi->xdp_rings[i]->xsk_umem)
+ (void)i40e_xsk_wakeup(vsi->netdev, i,
+ XDP_WAKEUP_RX);
+
return 0;
}
/**
+ * i40e_enter_busy_conf - Enters busy config state
+ * @vsi: vsi
+ *
+ * Returns 0 on success, <0 for failure.
+ **/
+static int i40e_enter_busy_conf(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int timeout = 50;
+
+ while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
+ timeout--;
+ if (!timeout)
+ return -EBUSY;
+ usleep_range(1000, 2000);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_exit_busy_conf - Exits busy config state
+ * @vsi: vsi
+ **/
+static void i40e_exit_busy_conf(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+
+ clear_bit(__I40E_CONFIG_BUSY, pf->state);
+}
+
+/**
+ * i40e_queue_pair_reset_stats - Resets all statistics for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
+{
+ memset(&vsi->rx_rings[queue_pair]->rx_stats, 0,
+ sizeof(vsi->rx_rings[queue_pair]->rx_stats));
+ memset(&vsi->tx_rings[queue_pair]->stats, 0,
+ sizeof(vsi->tx_rings[queue_pair]->stats));
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ memset(&vsi->xdp_rings[queue_pair]->stats, 0,
+ sizeof(vsi->xdp_rings[queue_pair]->stats));
+ }
+}
+
+/**
+ * i40e_queue_pair_clean_rings - Cleans all the rings of a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
+{
+ i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ /* Make sure that in-progress ndo_xdp_xmit calls are
+ * completed.
+ */
+ synchronize_rcu();
+ i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+ }
+ i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
+}
+
+/**
+ * i40e_queue_pair_toggle_napi - Enables/disables NAPI for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ **/
+static void i40e_queue_pair_toggle_napi(struct i40e_vsi *vsi, int queue_pair,
+ bool enable)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_q_vector *q_vector = rxr->q_vector;
+
+ if (!vsi->netdev)
+ return;
+
+ /* All rings in a qp belong to the same qvector. */
+ if (q_vector->rx.ring || q_vector->tx.ring) {
+ if (enable)
+ napi_enable(&q_vector->napi);
+ else
+ napi_disable(&q_vector->napi);
+ }
+}
+
+/**
+ * i40e_queue_pair_toggle_rings - Enables/disables all rings for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+static int i40e_queue_pair_toggle_rings(struct i40e_vsi *vsi, int queue_pair,
+ bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ int pf_q, ret = 0;
+
+ pf_q = vsi->base_queue + queue_pair;
+ ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q,
+ false /*is xdp*/, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Tx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ return ret;
+ }
+
+ i40e_control_rx_q(pf, pf_q, enable);
+ ret = i40e_pf_rxq_wait(pf, pf_q, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Rx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ return ret;
+ }
+
+ /* Due to HW errata, on Rx disable only, the register can
+ * indicate done before it really is. Needs 50ms to be sure
+ */
+ if (!enable)
+ mdelay(50);
+
+ if (!i40e_enabled_xdp_vsi(vsi))
+ return ret;
+
+ ret = i40e_control_wait_tx_q(vsi->seid, pf,
+ pf_q + vsi->alloc_queue_pairs,
+ true /*is xdp*/, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d XDP Tx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_queue_pair_enable_irq - Enables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ /* All rings in a qp belong to the same qvector. */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx);
+ else
+ i40e_irq_dynamic_enable_icr0(pf);
+
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_queue_pair_disable_irq - Disables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ /* For simplicity, instead of removing the qp interrupt causes
+ * from the interrupt linked list, we simply disable the interrupt, and
+ * leave the list intact.
+ *
+ * All rings in a qp belong to the same qvector.
+ */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ u32 intpf = vsi->base_vector + rxr->q_vector->v_idx;
+
+ wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0);
+ i40e_flush(hw);
+ synchronize_irq(pf->msix_entries[intpf].vector);
+ } else {
+ /* Legacy and MSI mode - this stops all interrupt handling */
+ wr32(hw, I40E_PFINT_ICR0_ENA, 0);
+ wr32(hw, I40E_PFINT_DYN_CTL0, 0);
+ i40e_flush(hw);
+ synchronize_irq(pf->pdev->irq);
+ }
+}
+
+/**
+ * i40e_queue_pair_disable - Disables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair)
+{
+ int err;
+
+ err = i40e_enter_busy_conf(vsi);
+ if (err)
+ return err;
+
+ i40e_queue_pair_disable_irq(vsi, queue_pair);
+ err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */);
+ i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
+ i40e_queue_pair_clean_rings(vsi, queue_pair);
+ i40e_queue_pair_reset_stats(vsi, queue_pair);
+
+ return err;
+}
+
+/**
+ * i40e_queue_pair_enable - Enables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair)
+{
+ int err;
+
+ err = i40e_configure_tx_ring(vsi->tx_rings[queue_pair]);
+ if (err)
+ return err;
+
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ err = i40e_configure_tx_ring(vsi->xdp_rings[queue_pair]);
+ if (err)
+ return err;
+ }
+
+ err = i40e_configure_rx_ring(vsi->rx_rings[queue_pair]);
+ if (err)
+ return err;
+
+ err = i40e_queue_pair_toggle_rings(vsi, queue_pair, true /* on */);
+ i40e_queue_pair_toggle_napi(vsi, queue_pair, true /* on */);
+ i40e_queue_pair_enable_irq(vsi, queue_pair);
+
+ i40e_exit_busy_conf(vsi);
+
+ return err;
+}
+
+/**
* i40e_xdp - implements ndo_bpf for i40e
* @dev: netdevice
* @xdp: XDP command
@@ -11847,6 +12822,9 @@
case XDP_QUERY_PROG:
xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
return 0;
+ case XDP_SETUP_XSK_UMEM:
+ return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
+ xdp->xsk.queue_id);
default:
return -EINVAL;
}
@@ -11886,6 +12864,9 @@
.ndo_bridge_setlink = i40e_ndo_bridge_setlink,
.ndo_bpf = i40e_xdp,
.ndo_xdp_xmit = i40e_xdp_xmit,
+ .ndo_xsk_wakeup = i40e_xsk_wakeup,
+ .ndo_dfwd_add_station = i40e_fwd_add,
+ .ndo_dfwd_del_station = i40e_fwd_del,
};
/**
@@ -11945,13 +12926,16 @@
/* record features VLANs can make use of */
netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
- if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
- netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
+ /* enable macvlan offloads */
+ netdev->hw_features |= NETIF_F_HW_L2FW_DOFFLOAD;
hw_features = hw_enc_features |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
+ if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+ hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
+
netdev->hw_features |= hw_features;
netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
@@ -12011,6 +12995,9 @@
ether_addr_copy(netdev->dev_addr, mac_addr);
ether_addr_copy(netdev->perm_addr, mac_addr);
+ /* i40iw_net_event() reads 16 bytes from neigh->primary_key */
+ netdev->neigh_priv_len = sizeof(u32) * 4;
+
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->priv_flags |= IFF_SUPP_NOFCS;
/* Setup netdev TC information */
@@ -12054,7 +13041,7 @@
struct i40e_pf *pf = vsi->back;
/* Uplink is not a bridge so default to VEB */
- if (vsi->veb_idx == I40E_NO_VEB)
+ if (vsi->veb_idx >= I40E_MAX_VEB)
return 1;
veb = pf->veb[vsi->veb_idx];
@@ -13035,7 +14022,7 @@
for (vsi_idx = 0; vsi_idx < pf->num_alloc_vsi; vsi_idx++)
if (pf->vsi[vsi_idx] && pf->vsi[vsi_idx]->seid == vsi_seid)
break;
- if (vsi_idx >= pf->num_alloc_vsi && vsi_seid != 0) {
+ if (vsi_idx == pf->num_alloc_vsi && vsi_seid != 0) {
dev_info(&pf->pdev->dev, "vsi seid %d not found\n",
vsi_seid);
return NULL;
@@ -13112,7 +14099,7 @@
/* Main VEB? */
if (uplink_seid != pf->mac_seid)
break;
- if (pf->lan_veb == I40E_NO_VEB) {
+ if (pf->lan_veb >= I40E_MAX_VEB) {
int v;
/* find existing or else empty VEB */
@@ -13122,13 +14109,15 @@
break;
}
}
- if (pf->lan_veb == I40E_NO_VEB) {
+ if (pf->lan_veb >= I40E_MAX_VEB) {
v = i40e_veb_mem_alloc(pf);
if (v < 0)
break;
pf->lan_veb = v;
}
}
+ if (pf->lan_veb >= I40E_MAX_VEB)
+ break;
pf->veb[pf->lan_veb]->seid = seid;
pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid;
@@ -13282,7 +14271,7 @@
/* Set up the PF VSI associated with the PF's main VSI
* that is already in the HW switch
*/
- if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
uplink_seid = pf->veb[pf->lan_veb]->seid;
else
uplink_seid = pf->mac_seid;
@@ -13528,6 +14517,204 @@
}
/**
+ * i40e_set_fec_in_flags - helper function for setting FEC options in flags
+ * @fec_cfg: FEC option to set in flags
+ * @flags: ptr to flags in which we set FEC option
+ **/
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
+{
+ if (fec_cfg & I40E_AQ_SET_FEC_AUTO)
+ *flags |= I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC;
+ if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_RS) ||
+ (fec_cfg & I40E_AQ_SET_FEC_ABILITY_RS)) {
+ *flags |= I40E_FLAG_RS_FEC;
+ *flags &= ~I40E_FLAG_BASE_R_FEC;
+ }
+ if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_KR) ||
+ (fec_cfg & I40E_AQ_SET_FEC_ABILITY_KR)) {
+ *flags |= I40E_FLAG_BASE_R_FEC;
+ *flags &= ~I40E_FLAG_RS_FEC;
+ }
+ if (fec_cfg == 0)
+ *flags &= ~(I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC);
+}
+
+/**
+ * i40e_check_recovery_mode - check if we are running transition firmware
+ * @pf: board private structure
+ *
+ * Check registers indicating the firmware runs in recovery mode. Sets the
+ * appropriate driver state.
+ *
+ * Returns true if the recovery mode was detected, false otherwise
+ **/
+static bool i40e_check_recovery_mode(struct i40e_pf *pf)
+{
+ u32 val = rd32(&pf->hw, I40E_GL_FWSTS) & I40E_GL_FWSTS_FWS1B_MASK;
+ bool is_recovery_mode = false;
+
+ if (pf->hw.mac.type == I40E_MAC_XL710)
+ is_recovery_mode =
+ val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK ||
+ val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK ||
+ val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK ||
+ val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK;
+ if (pf->hw.mac.type == I40E_MAC_X722)
+ is_recovery_mode =
+ val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK ||
+ val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK;
+ if (is_recovery_mode) {
+ dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n");
+ dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+ set_bit(__I40E_RECOVERY_MODE, pf->state);
+
+ return true;
+ }
+ if (test_and_clear_bit(__I40E_RECOVERY_MODE, pf->state))
+ dev_info(&pf->pdev->dev, "Reinitializing in normal mode with full functionality.\n");
+
+ return false;
+}
+
+/**
+ * i40e_pf_loop_reset - perform reset in a loop.
+ * @pf: board private structure
+ *
+ * This function is useful when a NIC is about to enter recovery mode.
+ * When a NIC's internal data structures are corrupted the NIC's
+ * firmware is going to enter recovery mode.
+ * Right after a POR it takes about 7 minutes for firmware to enter
+ * recovery mode. Until that time a NIC is in some kind of intermediate
+ * state. After that time period the NIC almost surely enters
+ * recovery mode. The only way for a driver to detect intermediate
+ * state is to issue a series of pf-resets and check a return value.
+ * If a PF reset returns success then the firmware could be in recovery
+ * mode so the caller of this code needs to check for recovery mode
+ * if this function returns success. There is a little chance that
+ * firmware will hang in intermediate state forever.
+ * Since waiting 7 minutes is quite a lot of time this function waits
+ * 10 seconds and then gives up by returning an error.
+ *
+ * Return 0 on success, negative on failure.
+ **/
+static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf)
+{
+ const unsigned short MAX_CNT = 1000;
+ const unsigned short MSECS = 10;
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status ret;
+ int cnt;
+
+ for (cnt = 0; cnt < MAX_CNT; ++cnt) {
+ ret = i40e_pf_reset(hw);
+ if (!ret)
+ break;
+ msleep(MSECS);
+ }
+
+ if (cnt == MAX_CNT) {
+ dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret);
+ return ret;
+ }
+
+ pf->pfr_count++;
+ return ret;
+}
+
+/**
+ * i40e_init_recovery_mode - initialize subsystems needed in recovery mode
+ * @pf: board private structure
+ * @hw: ptr to the hardware info
+ *
+ * This function does a minimal setup of all subsystems needed for running
+ * recovery mode.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw)
+{
+ struct i40e_vsi *vsi;
+ int err;
+ int v_idx;
+
+ pci_save_state(pf->pdev);
+
+ /* set up periodic task facility */
+ timer_setup(&pf->service_timer, i40e_service_timer, 0);
+ pf->service_timer_period = HZ;
+
+ INIT_WORK(&pf->service_task, i40e_service_task);
+ clear_bit(__I40E_SERVICE_SCHED, pf->state);
+
+ err = i40e_init_interrupt_scheme(pf);
+ if (err)
+ goto err_switch_setup;
+
+ /* The number of VSIs reported by the FW is the minimum guaranteed
+ * to us; HW supports far more and we share the remaining pool with
+ * the other PFs. We allocate space for more than the guarantee with
+ * the understanding that we might not get them all later.
+ */
+ if (pf->hw.func_caps.num_vsis < I40E_MIN_VSI_ALLOC)
+ pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
+ else
+ pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+
+ /* Set up the vsi struct and our local tracking of the MAIN PF vsi. */
+ pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
+ GFP_KERNEL);
+ if (!pf->vsi) {
+ err = -ENOMEM;
+ goto err_switch_setup;
+ }
+
+ /* We allocate one VSI which is needed as absolute minimum
+ * in order to register the netdev
+ */
+ v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
+ if (v_idx < 0)
+ goto err_switch_setup;
+ pf->lan_vsi = v_idx;
+ vsi = pf->vsi[v_idx];
+ if (!vsi)
+ goto err_switch_setup;
+ vsi->alloc_queue_pairs = 1;
+ err = i40e_config_netdev(vsi);
+ if (err)
+ goto err_switch_setup;
+ err = register_netdev(vsi->netdev);
+ if (err)
+ goto err_switch_setup;
+ vsi->netdev_registered = true;
+ i40e_dbg_pf_init(pf);
+
+ err = i40e_setup_misc_vector_for_recovery_mode(pf);
+ if (err)
+ goto err_switch_setup;
+
+ /* tell the firmware that we're starting */
+ i40e_send_version(pf);
+
+ /* since everything's happy, start the service_task timer */
+ mod_timer(&pf->service_timer,
+ round_jiffies(jiffies + pf->service_timer_period));
+
+ return 0;
+
+err_switch_setup:
+ i40e_reset_interrupt_capability(pf);
+ del_timer_sync(&pf->service_timer);
+ i40e_shutdown_adminq(hw);
+ iounmap(hw->hw_addr);
+ pci_disable_pcie_error_reporting(pf->pdev);
+ pci_release_mem_regions(pf->pdev);
+ pci_disable_device(pf->pdev);
+ kfree(pf);
+
+ return err;
+}
+
+/**
* i40e_probe - Device initialization routine
* @pdev: PCI device information struct
* @ent: entry in i40e_pci_tbl
@@ -13596,7 +14783,17 @@
pf->ioremap_len = min_t(int, pci_resource_len(pdev, 0),
I40E_MAX_CSR_SPACE);
-
+ /* We believe that the highest register to read is
+ * I40E_GLGEN_STAT_CLEAR, so we check if the BAR size
+ * is not less than that before mapping to prevent a
+ * kernel panic.
+ */
+ if (pf->ioremap_len < I40E_GLGEN_STAT_CLEAR) {
+ dev_err(&pdev->dev, "Cannot map registers, bar size 0x%X too small, aborting\n",
+ pf->ioremap_len);
+ err = -ENOMEM;
+ goto err_ioremap;
+ }
hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pf->ioremap_len);
if (!hw->hw_addr) {
err = -EIO;
@@ -13624,6 +14821,7 @@
INIT_LIST_HEAD(&pf->l3_flex_pit_list);
INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+ INIT_LIST_HEAD(&pf->ddp_old_prof);
/* set up the locks for the AQ, do this only once in probe
* and destroy them only once in remove
@@ -13651,12 +14849,21 @@
/* Reset here to make sure all is clean and to define PF 'n' */
i40e_clear_hw(hw);
- err = i40e_pf_reset(hw);
+
+ err = i40e_set_mac_type(hw);
+ if (err) {
+ dev_warn(&pdev->dev, "unidentified MAC or BLANK NVM: %d\n",
+ err);
+ goto err_pf_reset;
+ }
+
+ err = i40e_pf_loop_reset(pf);
if (err) {
dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
goto err_pf_reset;
}
- pf->pfr_count++;
+
+ i40e_check_recovery_mode(pf);
hw->aq.num_arq_entries = I40E_AQ_LEN;
hw->aq.num_asq_entries = I40E_AQ_LEN;
@@ -13682,7 +14889,11 @@
if (err) {
if (err == I40E_ERR_FIRMWARE_API_VERSION)
dev_info(&pdev->dev,
- "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+ "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else
dev_info(&pdev->dev,
"The driver for the device stopped because the device firmware failed to init. Try updating your NVM image.\n");
@@ -13691,19 +14902,28 @@
}
i40e_get_oem_version(hw);
- /* provide nvm, fw, api versions */
- dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+ /* provide nvm, fw, api versions, vendor:device id, subsys vendor:device id */
+ dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s [%04x:%04x] [%04x:%04x]\n",
hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
hw->aq.api_maj_ver, hw->aq.api_min_ver,
- i40e_nvm_version_str(hw));
+ i40e_nvm_version_str(hw), hw->vendor_id, hw->device_id,
+ hw->subsystem_vendor_id, hw->subsystem_device_id);
if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
dev_info(&pdev->dev,
- "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+ "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
dev_info(&pdev->dev,
- "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+ "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
i40e_verify_eeprom(pf);
@@ -13712,6 +14932,7 @@
dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
i40e_clear_pxe_mode(hw);
+
err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
if (err)
goto err_adminq_setup;
@@ -13722,6 +14943,9 @@
goto err_sw_init;
}
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state))
+ return i40e_init_recovery_mode(pf, hw);
+
err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
hw->func_caps.num_rx_qp, 0, 0);
if (err) {
@@ -13742,7 +14966,7 @@
*/
if (pf->hw_features & I40E_HW_STOP_FW_LLDP) {
dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
- i40e_aq_stop_lldp(hw, true, NULL);
+ i40e_aq_stop_lldp(hw, true, false, NULL);
}
/* allow a platform config to override the HW addr */
@@ -13762,6 +14986,11 @@
pci_set_drvdata(pdev, pf);
pci_save_state(pdev);
+ dev_info(&pdev->dev,
+ (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) ?
+ "FW LLDP is disabled\n" :
+ "FW LLDP is enabled\n");
+
/* Enable FW to write default DCB config on link-up */
i40e_aq_set_dcb_parameters(hw, true, NULL);
@@ -13979,23 +15208,23 @@
switch (hw->bus.speed) {
case i40e_bus_speed_8000:
- strncpy(speed, "8.0", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "8.0", PCI_SPEED_SIZE); break;
case i40e_bus_speed_5000:
- strncpy(speed, "5.0", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "5.0", PCI_SPEED_SIZE); break;
case i40e_bus_speed_2500:
- strncpy(speed, "2.5", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "2.5", PCI_SPEED_SIZE); break;
default:
break;
}
switch (hw->bus.width) {
case i40e_bus_width_pcie_x8:
- strncpy(width, "8", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "8", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x4:
- strncpy(width, "4", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "4", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x2:
- strncpy(width, "2", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "2", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x1:
- strncpy(width, "1", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "1", PCI_WIDTH_SIZE); break;
default:
break;
}
@@ -14018,6 +15247,9 @@
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
+ /* set the FEC config due to the board capabilities */
+ i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, &pf->flags);
+
/* get the supported phy types from the fw */
err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
if (err)
@@ -14104,6 +15336,19 @@
if (pf->service_task.func)
cancel_work_sync(&pf->service_task);
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ struct i40e_vsi *vsi = pf->vsi[0];
+
+ /* We know that we have allocated only one vsi for this PF,
+ * it was just for registering netdevice, so the interface
+ * could be visible in the 'ifconfig' output
+ */
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+
+ goto unmap;
+ }
+
/* Client close must be called explicitly here because the timer
* has been stopped.
*/
@@ -14153,6 +15398,12 @@
ret_code);
}
+unmap:
+ /* Free MSI/legacy interrupt 0 when in recovery mode. */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+ !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+ free_irq(pf->pdev->irq, pf);
+
/* shutdown the adminq */
i40e_shutdown_adminq(hw);
@@ -14161,14 +15412,17 @@
mutex_destroy(&hw->aq.asq_mutex);
/* Clear all dynamic memory lists of rings, q_vectors, and VSIs */
+ rtnl_lock();
i40e_clear_interrupt_scheme(pf);
for (i = 0; i < pf->num_alloc_vsi; i++) {
if (pf->vsi[i]) {
- i40e_vsi_clear_rings(pf->vsi[i]);
+ if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+ i40e_vsi_clear_rings(pf->vsi[i]);
i40e_vsi_clear(pf->vsi[i]);
pf->vsi[i] = NULL;
}
}
+ rtnl_unlock();
for (i = 0; i < I40E_MAX_VEB; i++) {
kfree(pf->veb[i]);
@@ -14229,7 +15483,6 @@
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
pci_ers_result_t result;
- int err;
u32 reg;
dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -14250,14 +15503,6 @@
result = PCI_ERS_RESULT_DISCONNECT;
}
- err = pci_cleanup_aer_uncorrect_error_status(pdev);
- if (err) {
- dev_info(&pdev->dev,
- "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n",
- err);
- /* non-fatal, continue */
- }
-
return result;
}
@@ -14380,7 +15625,18 @@
wr32(hw, I40E_PFPM_WUFC,
(pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
+ /* Free MSI/legacy interrupt 0 when in recovery mode. */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+ !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+ free_irq(pf->pdev->irq, pf);
+
+ /* Since we're going to destroy queues during the
+ * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
+ * whole section
+ */
+ rtnl_lock();
i40e_clear_interrupt_scheme(pf);
+ rtnl_unlock();
if (system_state == SYSTEM_POWER_OFF) {
pci_wake_from_d3(pdev, pf->wol_en);
@@ -14394,8 +15650,7 @@
**/
static int __maybe_unused i40e_suspend(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct i40e_pf *pf = pci_get_drvdata(pdev);
+ struct i40e_pf *pf = dev_get_drvdata(dev);
struct i40e_hw *hw = &pf->hw;
/* If we're already suspended, then there is nothing to do */
@@ -14445,8 +15700,7 @@
**/
static int __maybe_unused i40e_resume(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct i40e_pf *pf = pci_get_drvdata(pdev);
+ struct i40e_pf *pf = dev_get_drvdata(dev);
int err;
/* If we're not suspended, then there is nothing to do */
@@ -14463,7 +15717,7 @@
*/
err = i40e_restore_interrupt_scheme(pf);
if (err) {
- dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n",
+ dev_err(dev, "Cannot restore interrupt scheme: %d\n",
err);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 0299e5b..e4d8d20 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -322,6 +322,77 @@
}
/**
+ * i40e_read_nvm_module_data - Reads NVM Buffer to specified memory location
+ * @hw: pointer to the HW structure
+ * @module_ptr: Pointer to module in words with respect to NVM beginning
+ * @offset: offset in words from module start
+ * @words_data_size: Words to read from NVM
+ * @data_ptr: Pointer to memory location where resulting buffer will be stored
+ **/
+i40e_status i40e_read_nvm_module_data(struct i40e_hw *hw,
+ u8 module_ptr, u16 offset,
+ u16 words_data_size,
+ u16 *data_ptr)
+{
+ i40e_status status;
+ u16 ptr_value = 0;
+ u32 flat_offset;
+
+ if (module_ptr != 0) {
+ status = i40e_read_nvm_word(hw, module_ptr, &ptr_value);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Reading nvm word failed.Error code: %d.\n",
+ status);
+ return I40E_ERR_NVM;
+ }
+ }
+#define I40E_NVM_INVALID_PTR_VAL 0x7FFF
+#define I40E_NVM_INVALID_VAL 0xFFFF
+
+ /* Pointer not initialized */
+ if (ptr_value == I40E_NVM_INVALID_PTR_VAL ||
+ ptr_value == I40E_NVM_INVALID_VAL)
+ return I40E_ERR_BAD_PTR;
+
+ /* Check whether the module is in SR mapped area or outside */
+ if (ptr_value & I40E_PTR_TYPE) {
+ /* Pointer points outside of the Shared RAM mapped area */
+ ptr_value &= ~I40E_PTR_TYPE;
+
+ /* PtrValue in 4kB units, need to convert to words */
+ ptr_value /= 2;
+ flat_offset = ((u32)ptr_value * 0x1000) + (u32)offset;
+ status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (!status) {
+ status = i40e_aq_read_nvm(hw, 0, 2 * flat_offset,
+ 2 * words_data_size,
+ data_ptr, true, NULL);
+ i40e_release_nvm(hw);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Reading nvm aq failed.Error code: %d.\n",
+ status);
+ return I40E_ERR_NVM;
+ }
+ } else {
+ return I40E_ERR_NVM;
+ }
+ } else {
+ /* Read from the Shadow RAM */
+ status = i40e_read_nvm_buffer(hw, ptr_value + offset,
+ &words_data_size, data_ptr);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_ALL,
+ "Reading nvm buffer failed.Error code: %d.\n",
+ status);
+ }
+ }
+
+ return status;
+}
+
+/**
* i40e_read_nvm_buffer_srctl - Reads Shadow RAM buffer via SRCTL register
* @hw: pointer to the HW structure
* @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
@@ -430,6 +501,36 @@
}
/**
+ * i40e_read_nvm_buffer - Reads Shadow RAM buffer and acquire lock if necessary
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd()
+ * method. The buffer read is preceded by the NVM ownership take
+ * and followed by the release.
+ **/
+i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
+ u16 *words, u16 *data)
+{
+ i40e_status ret_code = 0;
+
+ if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
+ ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (!ret_code) {
+ ret_code = i40e_read_nvm_buffer_aq(hw, offset, words,
+ data);
+ i40e_release_nvm(hw);
+ }
+ } else {
+ ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data);
+ }
+
+ return ret_code;
+}
+
+/**
* i40e_write_nvm_aq - Writes Shadow RAM.
* @hw: pointer to the HW structure.
* @module_pointer: module pointer location in words from the NVM beginning
@@ -578,11 +679,10 @@
__le16 le_sum;
ret_code = i40e_calc_nvm_checksum(hw, &checksum);
- if (!ret_code) {
- le_sum = cpu_to_le16(checksum);
+ le_sum = cpu_to_le16(checksum);
+ if (!ret_code)
ret_code = i40e_write_nvm_aq(hw, 0x00, I40E_SR_SW_CHECKSUM_WORD,
1, &le_sum, true);
- }
return ret_code;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index a07574b..c302ef2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -18,7 +18,10 @@
* actual OS primitives
*/
-#define hw_dbg(hw, S, A...) do {} while (0)
+#define hw_dbg(hw, S, A...) \
+do { \
+ dev_dbg(&((struct i40e_pf *)hw->back)->pdev->dev, S, ##A); \
+} while (0)
#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
#define rd32(a, reg) readl((a)->hw_addr + (reg))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index e08d754..5250441 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -203,14 +203,18 @@
i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
bool enable_update,
struct i40e_asq_cmd_details *cmd_details);
+enum i40e_status_code
+i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
+ struct i40e_asq_cmd_details *cmd_details);
i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+ bool persist,
struct i40e_asq_cmd_details *cmd_details);
i40e_status i40e_aq_set_dcb_parameters(struct i40e_hw *hw,
bool dcb_enable,
struct i40e_asq_cmd_details
*cmd_details);
-i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
- struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
+ struct i40e_asq_cmd_details *cmd_details);
i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
void *buff, u16 buff_size,
struct i40e_asq_cmd_details *cmd_details);
@@ -311,6 +315,12 @@
void i40e_release_nvm(struct i40e_hw *hw);
i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
u16 *data);
+i40e_status i40e_read_nvm_module_data(struct i40e_hw *hw,
+ u8 module_ptr, u16 offset,
+ u16 words_data_size,
+ u16 *data_ptr);
+i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
+ u16 *words, u16 *data);
i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw);
i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw,
u16 *checksum);
@@ -322,6 +332,8 @@
void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw);
void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);
+i40e_status i40e_set_mac_type(struct i40e_hw *hw);
+
extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[];
static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
@@ -346,6 +358,10 @@
return VIRTCHNL_LINK_SPEED_100MB;
case I40E_LINK_SPEED_1GB:
return VIRTCHNL_LINK_SPEED_1GB;
+ case I40E_LINK_SPEED_2_5GB:
+ return VIRTCHNL_LINK_SPEED_2_5GB;
+ case I40E_LINK_SPEED_5GB:
+ return VIRTCHNL_LINK_SPEED_5GB;
case I40E_LINK_SPEED_10GB:
return VIRTCHNL_LINK_SPEED_10GB;
case I40E_LINK_SPEED_40GB:
@@ -429,10 +445,16 @@
struct i40e_generic_seg_header *
i40e_find_segment_in_package(u32 segment_type,
struct i40e_package_header *pkg_header);
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+ struct i40e_profile_segment *profile);
enum i40e_status_code
i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
u32 track_id);
enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
+ u32 track_id);
+enum i40e_status_code
i40e_add_pinfo_to_list(struct i40e_hw *hw,
struct i40e_profile_segment *profile,
u8 *profile_info_sec, u32 track_id);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 35f2866..9bf1ad4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -28,19 +28,23 @@
* i40e_ptp_read - Read the PHC time from the device
* @pf: Board private structure
* @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
*
* This function reads the PRTTSYN_TIME registers and stores them in a
* timespec. However, since the registers are 64 bits of nanoseconds, we must
* convert the result to a timespec before we can return.
**/
-static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts)
+static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct i40e_hw *hw = &pf->hw;
u32 hi, lo;
u64 ns;
/* The timer latches on the lowest register read. */
+ ptp_read_system_prets(sts);
lo = rd32(hw, I40E_PRTTSYN_TIME_L);
+ ptp_read_system_postts(sts);
hi = rd32(hw, I40E_PRTTSYN_TIME_H);
ns = (((u64)hi) << 32) | lo;
@@ -136,18 +140,18 @@
* @ptp: The PTP clock structure
* @delta: Offset in nanoseconds to adjust the PHC time by
*
- * Adjust the frequency of the PHC by the indicated parts per billion from the
- * base frequency.
+ * Adjust the current clock time by a delta specified in nanoseconds.
**/
static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
- struct timespec64 now;
+ struct timespec64 now, then;
+ then = ns_to_timespec64(delta);
mutex_lock(&pf->tmreg_lock);
- i40e_ptp_read(pf, &now);
- timespec64_add_ns(&now, delta);
+ i40e_ptp_read(pf, &now, NULL);
+ now = timespec64_add(now, then);
i40e_ptp_write(pf, (const struct timespec64 *)&now);
mutex_unlock(&pf->tmreg_lock);
@@ -156,19 +160,21 @@
}
/**
- * i40e_ptp_gettime - Get the time of the PHC
+ * i40e_ptp_gettimex - Get the time of the PHC
* @ptp: The PTP clock structure
* @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
*
* Read the device clock and return the correct value on ns, after converting it
* into a timespec struct.
**/
-static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int i40e_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
mutex_lock(&pf->tmreg_lock);
- i40e_ptp_read(pf, ts);
+ i40e_ptp_read(pf, ts, sts);
mutex_unlock(&pf->tmreg_lock);
return 0;
@@ -694,14 +700,15 @@
if (!IS_ERR_OR_NULL(pf->ptp_clock))
return 0;
- strncpy(pf->ptp_caps.name, i40e_driver_name, sizeof(pf->ptp_caps.name));
+ strlcpy(pf->ptp_caps.name, i40e_driver_name,
+ sizeof(pf->ptp_caps.name) - 1);
pf->ptp_caps.owner = THIS_MODULE;
pf->ptp_caps.max_adj = 999999999;
pf->ptp_caps.n_ext_ts = 0;
pf->ptp_caps.pps = 0;
pf->ptp_caps.adjfreq = i40e_ptp_adjfreq;
pf->ptp_caps.adjtime = i40e_ptp_adjtime;
- pf->ptp_caps.gettime64 = i40e_ptp_gettime;
+ pf->ptp_caps.gettimex64 = i40e_ptp_gettimex;
pf->ptp_caps.settime64 = i40e_ptp_settime;
pf->ptp_caps.enable = i40e_ptp_feature_enable;
@@ -717,16 +724,68 @@
pf->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
pf->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+ /* Set the previous "reset" time to the current Kernel clock time */
+ ktime_get_real_ts64(&pf->ptp_prev_hw_time);
+ pf->ptp_reset_start = ktime_get();
+
return 0;
}
/**
+ * i40e_ptp_save_hw_time - Save the current PTP time as ptp_prev_hw_time
+ * @pf: Board private structure
+ *
+ * Read the current PTP time and save it into pf->ptp_prev_hw_time. This should
+ * be called at the end of preparing to reset, just before hardware reset
+ * occurs, in order to preserve the PTP time as close as possible across
+ * resets.
+ */
+void i40e_ptp_save_hw_time(struct i40e_pf *pf)
+{
+ /* don't try to access the PTP clock if it's not enabled */
+ if (!(pf->flags & I40E_FLAG_PTP))
+ return;
+
+ i40e_ptp_gettimex(&pf->ptp_caps, &pf->ptp_prev_hw_time, NULL);
+ /* Get a monotonic starting time for this reset */
+ pf->ptp_reset_start = ktime_get();
+}
+
+/**
+ * i40e_ptp_restore_hw_time - Restore the ptp_prev_hw_time + delta to PTP regs
+ * @pf: Board private structure
+ *
+ * Restore the PTP hardware clock registers. We previously cached the PTP
+ * hardware time as pf->ptp_prev_hw_time. To be as accurate as possible,
+ * update this value based on the time delta since the time was saved, using
+ * CLOCK_MONOTONIC (via ktime_get()) to calculate the time difference.
+ *
+ * This ensures that the hardware clock is restored to nearly what it should
+ * have been if a reset had not occurred.
+ */
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf)
+{
+ ktime_t delta = ktime_sub(ktime_get(), pf->ptp_reset_start);
+
+ /* Update the previous HW time with the ktime delta */
+ timespec64_add_ns(&pf->ptp_prev_hw_time, ktime_to_ns(delta));
+
+ /* Restore the hardware clock registers */
+ i40e_ptp_settime(&pf->ptp_caps, &pf->ptp_prev_hw_time);
+}
+
+/**
* i40e_ptp_init - Initialize the 1588 support after device probe or reset
* @pf: Board private structure
*
* This function sets device up for 1588 support. The first time it is run, it
* will create a PHC clock device. It does not create a clock device if one
* already exists. It also reconfigures the device after a reset.
+ *
+ * The first time a clock is created, i40e_ptp_create_clock will set
+ * pf->ptp_prev_hw_time to the current system time. During resets, it is
+ * expected that this timespec will be set to the last known PTP clock time,
+ * in order to preserve the clock time as close as possible across a reset.
**/
void i40e_ptp_init(struct i40e_pf *pf)
{
@@ -758,7 +817,6 @@
dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n",
__func__);
} else if (pf->ptp_clock) {
- struct timespec64 ts;
u32 regval;
if (pf->hw.debug_mask & I40E_DEBUG_LAN)
@@ -779,9 +837,8 @@
/* reset timestamping mode */
i40e_ptp_set_timestamp_mode(pf, &pf->tstamp_config);
- /* Set the clock value. */
- ts = ktime_to_timespec64(ktime_get_real());
- i40e_ptp_settime(&pf->ptp_caps, &ts);
+ /* Restore the clock time based on last known value */
+ i40e_ptp_restore_hw_time(pf);
}
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 52e3680..d35d690 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -58,7 +58,7 @@
#define I40E_PF_ARQLEN_ARQCRIT_SHIFT 30
#define I40E_PF_ARQLEN_ARQCRIT_MASK I40E_MASK(0x1, I40E_PF_ARQLEN_ARQCRIT_SHIFT)
#define I40E_PF_ARQLEN_ARQENABLE_SHIFT 31
-#define I40E_PF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1, I40E_PF_ARQLEN_ARQENABLE_SHIFT)
+#define I40E_PF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ARQLEN_ARQENABLE_SHIFT)
#define I40E_PF_ARQT 0x00080480 /* Reset: EMPR */
#define I40E_PF_ARQT_ARQT_SHIFT 0
#define I40E_PF_ARQT_ARQT_MASK I40E_MASK(0x3FF, I40E_PF_ARQT_ARQT_SHIFT)
@@ -81,7 +81,7 @@
#define I40E_PF_ATQLEN_ATQCRIT_SHIFT 30
#define I40E_PF_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_PF_ATQLEN_ATQCRIT_SHIFT)
#define I40E_PF_ATQLEN_ATQENABLE_SHIFT 31
-#define I40E_PF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1, I40E_PF_ATQLEN_ATQENABLE_SHIFT)
+#define I40E_PF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ATQLEN_ATQENABLE_SHIFT)
#define I40E_PF_ATQT 0x00080400 /* Reset: EMPR */
#define I40E_PF_ATQT_ATQT_SHIFT 0
#define I40E_PF_ATQT_ATQT_MASK I40E_MASK(0x3FF, I40E_PF_ATQT_ATQT_SHIFT)
@@ -108,7 +108,7 @@
#define I40E_VF_ARQLEN_ARQCRIT_SHIFT 30
#define I40E_VF_ARQLEN_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQCRIT_SHIFT)
#define I40E_VF_ARQLEN_ARQENABLE_SHIFT 31
-#define I40E_VF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQENABLE_SHIFT)
+#define I40E_VF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN_ARQENABLE_SHIFT)
#define I40E_VF_ARQT(_VF) (0x00082C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
#define I40E_VF_ARQT_MAX_INDEX 127
#define I40E_VF_ARQT_ARQT_SHIFT 0
@@ -136,7 +136,7 @@
#define I40E_VF_ATQLEN_ATQCRIT_SHIFT 30
#define I40E_VF_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQCRIT_SHIFT)
#define I40E_VF_ATQLEN_ATQENABLE_SHIFT 31
-#define I40E_VF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQENABLE_SHIFT)
+#define I40E_VF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN_ATQENABLE_SHIFT)
#define I40E_VF_ATQT(_VF) (0x00082800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */
#define I40E_VF_ATQT_MAX_INDEX 127
#define I40E_VF_ATQT_ATQT_SHIFT 0
@@ -259,7 +259,7 @@
#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT 30
#define I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT)
#define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT 31
-#define I40E_PRTDCB_RETSTCC_ETSTC_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSTCC_ETSTC_SHIFT)
+#define I40E_PRTDCB_RETSTCC_ETSTC_MASK I40E_MASK(0x1u, I40E_PRTDCB_RETSTCC_ETSTC_SHIFT)
#define I40E_PRTDCB_RPPMC 0x001223A0 /* Reset: CORER */
#define I40E_PRTDCB_RPPMC_LANRPPM_SHIFT 0
#define I40E_PRTDCB_RPPMC_LANRPPM_MASK I40E_MASK(0xFF, I40E_PRTDCB_RPPMC_LANRPPM_SHIFT)
@@ -363,6 +363,12 @@
#define I40E_GL_FWSTS_FWRI_MASK I40E_MASK(0x1, I40E_GL_FWSTS_FWRI_SHIFT)
#define I40E_GL_FWSTS_FWS1B_SHIFT 16
#define I40E_GL_FWSTS_FWS1B_MASK I40E_MASK(0xFF, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0x30, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK I40E_MASK(0x31, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK I40E_MASK(0x32, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK I40E_MASK(0x33, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0xB, I40E_GL_FWSTS_FWS1B_SHIFT)
+#define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK I40E_MASK(0xC, I40E_GL_FWSTS_FWS1B_SHIFT)
#define I40E_GLGEN_CLKSTAT 0x000B8184 /* Reset: POR */
#define I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT 0
#define I40E_GLGEN_CLKSTAT_CLKMODE_MASK I40E_MASK(0x1, I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT)
@@ -503,7 +509,7 @@
#define I40E_GLGEN_MSCA_MDICMD_SHIFT 30
#define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT)
#define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31
-#define I40E_GLGEN_MSCA_MDIINPROGEN_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT)
+#define I40E_GLGEN_MSCA_MDIINPROGEN_MASK I40E_MASK(0x1u, I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT)
#define I40E_GLGEN_MSRWD(_i) (0x0008819C + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */
#define I40E_GLGEN_MSRWD_MAX_INDEX 3
#define I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT 0
@@ -1242,14 +1248,14 @@
#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT 30
#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT)
#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT 31
-#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK I40E_MASK(0x1u, I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT)
#define I40E_PFLAN_QALLOC 0x001C0400 /* Reset: CORER */
#define I40E_PFLAN_QALLOC_FIRSTQ_SHIFT 0
#define I40E_PFLAN_QALLOC_FIRSTQ_MASK I40E_MASK(0x7FF, I40E_PFLAN_QALLOC_FIRSTQ_SHIFT)
#define I40E_PFLAN_QALLOC_LASTQ_SHIFT 16
#define I40E_PFLAN_QALLOC_LASTQ_MASK I40E_MASK(0x7FF, I40E_PFLAN_QALLOC_LASTQ_SHIFT)
#define I40E_PFLAN_QALLOC_VALID_SHIFT 31
-#define I40E_PFLAN_QALLOC_VALID_MASK I40E_MASK(0x1, I40E_PFLAN_QALLOC_VALID_SHIFT)
+#define I40E_PFLAN_QALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PFLAN_QALLOC_VALID_SHIFT)
#define I40E_QRX_ENA(_Q) (0x00120000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: PFR */
#define I40E_QRX_ENA_MAX_INDEX 1535
#define I40E_QRX_ENA_QENA_REQ_SHIFT 0
@@ -1658,7 +1664,7 @@
#define I40E_GLNVM_SRCTL_START_SHIFT 30
#define I40E_GLNVM_SRCTL_START_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_START_SHIFT)
#define I40E_GLNVM_SRCTL_DONE_SHIFT 31
-#define I40E_GLNVM_SRCTL_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_DONE_SHIFT)
+#define I40E_GLNVM_SRCTL_DONE_MASK I40E_MASK(0x1u, I40E_GLNVM_SRCTL_DONE_SHIFT)
#define I40E_GLNVM_SRDATA 0x000B6114 /* Reset: POR */
#define I40E_GLNVM_SRDATA_WRDATA_SHIFT 0
#define I40E_GLNVM_SRDATA_WRDATA_MASK I40E_MASK(0xFFFF, I40E_GLNVM_SRDATA_WRDATA_SHIFT)
@@ -3025,7 +3031,7 @@
#define I40E_PF_VT_PFALLOC_LASTVF_SHIFT 8
#define I40E_PF_VT_PFALLOC_LASTVF_MASK I40E_MASK(0xFF, I40E_PF_VT_PFALLOC_LASTVF_SHIFT)
#define I40E_PF_VT_PFALLOC_VALID_SHIFT 31
-#define I40E_PF_VT_PFALLOC_VALID_MASK I40E_MASK(0x1, I40E_PF_VT_PFALLOC_VALID_SHIFT)
+#define I40E_PF_VT_PFALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PF_VT_PFALLOC_VALID_SHIFT)
#define I40E_VP_MDET_RX(_VF) (0x0012A000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */
#define I40E_VP_MDET_RX_MAX_INDEX 127
#define I40E_VP_MDET_RX_VALID_SHIFT 0
@@ -3161,7 +3167,7 @@
#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30
#define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT)
#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31
-#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQENABLE_SHIFT)
+#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN1_ARQENABLE_SHIFT)
#define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */
#define I40E_VF_ARQT1_ARQT_SHIFT 0
#define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT)
@@ -3184,7 +3190,7 @@
#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30
#define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT)
#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31
-#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQENABLE_SHIFT)
+#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN1_ATQENABLE_SHIFT)
#define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */
#define I40E_VF_ATQT1_ATQT_SHIFT 0
#define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b5042d1..e3f29dc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2,22 +2,13 @@
/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/prefetch.h>
-#include <net/busy_poll.h>
#include <linux/bpf_trace.h>
#include <net/xdp.h>
#include "i40e.h"
#include "i40e_trace.h"
#include "i40e_prototype.h"
-
-static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
- u32 td_tag)
-{
- return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
- ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) |
- ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
- ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
- ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT));
-}
+#include "i40e_txrx_common.h"
+#include "i40e_xsk.h"
#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
/**
@@ -536,8 +527,8 @@
* This is used to verify if the FD programming or invalidation
* requested by SW to the HW is successful or not and take actions accordingly.
**/
-static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, u8 prog_id)
+void i40e_fd_handle_status(struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc, u8 prog_id)
{
struct i40e_pf *pf = rx_ring->vsi->back;
struct pci_dev *pdev = pf->pdev;
@@ -644,13 +635,18 @@
unsigned long bi_size;
u16 i;
- /* ring already cleared, nothing to do */
- if (!tx_ring->tx_bi)
- return;
+ if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) {
+ i40e_xsk_clean_tx_ring(tx_ring);
+ } else {
+ /* ring already cleared, nothing to do */
+ if (!tx_ring->tx_bi)
+ return;
- /* Free all the Tx ring sk_buffs */
- for (i = 0; i < tx_ring->count; i++)
- i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]);
+ /* Free all the Tx ring sk_buffs */
+ for (i = 0; i < tx_ring->count; i++)
+ i40e_unmap_and_free_tx_resource(tx_ring,
+ &tx_ring->tx_bi[i]);
+ }
bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
memset(tx_ring->tx_bi, 0, bi_size);
@@ -767,8 +763,6 @@
}
}
-#define WB_STRIDE 4
-
/**
* i40e_clean_tx_irq - Reclaim resources after transmit completes
* @vsi: the VSI we care about
@@ -780,7 +774,7 @@
static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
struct i40e_ring *tx_ring, int napi_budget)
{
- u16 i = tx_ring->next_to_clean;
+ int i = tx_ring->next_to_clean;
struct i40e_tx_buffer *tx_buf;
struct i40e_tx_desc *tx_head;
struct i40e_tx_desc *tx_desc;
@@ -873,27 +867,8 @@
i += tx_ring->count;
tx_ring->next_to_clean = i;
- u64_stats_update_begin(&tx_ring->syncp);
- tx_ring->stats.bytes += total_bytes;
- tx_ring->stats.packets += total_packets;
- u64_stats_update_end(&tx_ring->syncp);
- tx_ring->q_vector->tx.total_bytes += total_bytes;
- tx_ring->q_vector->tx.total_packets += total_packets;
-
- if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
- /* check to see if there are < 4 descriptors
- * waiting to be written back, then kick the hardware to force
- * them to be written back in case we stay in NAPI.
- * In this mode on X722 we do not enable Interrupt.
- */
- unsigned int j = i40e_get_tx_pending(tx_ring, false);
-
- if (budget &&
- ((j / WB_STRIDE) == 0) && (j > 0) &&
- !test_bit(__I40E_VSI_DOWN, vsi->state) &&
- (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
- tx_ring->arm_wb = true;
- }
+ i40e_update_tx_stats(tx_ring, total_packets, total_bytes);
+ i40e_arm_wb(tx_ring, vsi, budget);
if (ring_is_xdp(tx_ring))
return !!budget;
@@ -1244,6 +1219,11 @@
new_buff->page = old_buff->page;
new_buff->page_offset = old_buff->page_offset;
new_buff->pagecnt_bias = old_buff->pagecnt_bias;
+
+ rx_ring->rx_stats.page_reuse_count++;
+
+ /* clear contents of buffer_info */
+ old_buff->page = NULL;
}
/**
@@ -1266,7 +1246,7 @@
}
/**
- * i40e_clean_programming_status - clean the programming status descriptor
+ * i40e_clean_programming_status - try clean the programming status descriptor
* @rx_ring: the rx ring that has this descriptor
* @rx_desc: the rx descriptor written back by HW
* @qw: qword representing status_error_len in CPU ordering
@@ -1275,15 +1255,22 @@
* status being successful or not and take actions accordingly. FCoE should
* handle its context/filter programming/invalidation status and take actions.
*
+ * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL.
**/
-static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- u64 qw)
+struct i40e_rx_buffer *i40e_clean_programming_status(
+ struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc,
+ u64 qw)
{
struct i40e_rx_buffer *rx_buffer;
- u32 ntc = rx_ring->next_to_clean;
+ u32 ntc;
u8 id;
+ if (!i40e_rx_is_programming_status(qw))
+ return NULL;
+
+ ntc = rx_ring->next_to_clean;
+
/* fetch, update, and store next to clean */
rx_buffer = &rx_ring->rx_bi[ntc++];
ntc = (ntc < rx_ring->count) ? ntc : 0;
@@ -1291,18 +1278,13 @@
prefetch(I40E_RX_DESC(rx_ring, ntc));
- /* place unused page back on the ring */
- i40e_reuse_rx_page(rx_ring, rx_buffer);
- rx_ring->rx_stats.page_reuse_count++;
-
- /* clear contents of buffer_info */
- rx_buffer->page = NULL;
-
id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
i40e_fd_handle_status(rx_ring, rx_desc, id);
+
+ return rx_buffer;
}
/**
@@ -1372,6 +1354,11 @@
rx_ring->skb = NULL;
}
+ if (rx_ring->xsk_umem) {
+ i40e_xsk_clean_rx_ring(rx_ring);
+ goto skip_free;
+ }
+
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
@@ -1400,6 +1387,7 @@
rx_bi->page_offset = 0;
}
+skip_free:
bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
memset(rx_ring->rx_bi, 0, bi_size);
@@ -1492,7 +1480,7 @@
* @rx_ring: ring to bump
* @val: new head index
**/
-static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
+void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
{
rx_ring->next_to_use = val;
@@ -1571,24 +1559,6 @@
}
/**
- * i40e_receive_skb - Send a completed packet up the stack
- * @rx_ring: rx ring in play
- * @skb: packet to send up
- * @vlan_tag: vlan tag for packet
- **/
-static void i40e_receive_skb(struct i40e_ring *rx_ring,
- struct sk_buff *skb, u16 vlan_tag)
-{
- struct i40e_q_vector *q_vector = rx_ring->q_vector;
-
- if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
- (vlan_tag & VLAN_VID_MASK))
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
-
- napi_gro_receive(&q_vector->napi, skb);
-}
-
-/**
* i40e_alloc_rx_buffers - Replace used receive buffers
* @rx_ring: ring to place buffers on
* @cleaned_count: number of buffers to replace
@@ -1804,10 +1774,8 @@
* order to populate the hash, checksum, VLAN, protocol, and
* other fields within the skb.
**/
-static inline
void i40e_process_skb_fields(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, struct sk_buff *skb,
- u8 rx_ptype)
+ union i40e_rx_desc *rx_desc, struct sk_buff *skb)
{
u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
@@ -1815,6 +1783,8 @@
u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK;
u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT;
+ u8 rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
+ I40E_RXD_QW1_PTYPE_SHIFT;
if (unlikely(tsynvalid))
i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn);
@@ -1825,6 +1795,13 @@
skb_record_rx_queue(skb, rx_ring->queue_index);
+ if (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) {
+ u16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1;
+
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ le16_to_cpu(vlan_tag));
+ }
+
/* modifies the skb - consumes the enet header */
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
}
@@ -2058,7 +2035,8 @@
/* Determine available headroom for copy */
headlen = size;
if (headlen > I40E_RX_HDR_SIZE)
- headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE);
+ headlen = eth_get_headlen(skb->dev, xdp->data,
+ I40E_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
memcpy(__skb_put(skb, headlen), xdp->data,
@@ -2152,7 +2130,6 @@
if (i40e_can_reuse_rx_page(rx_buffer)) {
/* hand second half of page back to the ring */
i40e_reuse_rx_page(rx_ring, rx_buffer);
- rx_ring->rx_stats.page_reuse_count++;
} else {
/* we are not reusing the buffer so unmap it */
dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
@@ -2160,10 +2137,9 @@
DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
__page_frag_cache_drain(rx_buffer->page,
rx_buffer->pagecnt_bias);
+ /* clear contents of buffer_info */
+ rx_buffer->page = NULL;
}
-
- /* clear contents of buffer_info */
- rx_buffer->page = NULL;
}
/**
@@ -2199,16 +2175,10 @@
return true;
}
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED BIT(0)
-#define I40E_XDP_TX BIT(1)
-#define I40E_XDP_REDIR BIT(2)
-
static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring);
-static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp,
- struct i40e_ring *xdp_ring)
+int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring)
{
struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
@@ -2287,7 +2257,13 @@
#endif
}
-static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
+/**
+ * i40e_xdp_ring_update_tail - Updates the XDP Tx ring tail register
+ * @xdp_ring: XDP Tx ring
+ *
+ * This function updates the XDP Tx ring tail register.
+ **/
+void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
{
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch.
@@ -2297,6 +2273,48 @@
}
/**
+ * i40e_update_rx_stats - Update Rx ring statistics
+ * @rx_ring: rx descriptor ring
+ * @total_rx_bytes: number of bytes received
+ * @total_rx_packets: number of packets received
+ *
+ * This function updates the Rx ring statistics.
+ **/
+void i40e_update_rx_stats(struct i40e_ring *rx_ring,
+ unsigned int total_rx_bytes,
+ unsigned int total_rx_packets)
+{
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->stats.packets += total_rx_packets;
+ rx_ring->stats.bytes += total_rx_bytes;
+ u64_stats_update_end(&rx_ring->syncp);
+ rx_ring->q_vector->rx.total_packets += total_rx_packets;
+ rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+}
+
+/**
+ * i40e_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map
+ * @rx_ring: Rx ring
+ * @xdp_res: Result of the receive batch
+ *
+ * This function bumps XDP Tx tail and/or flush redirect map, and
+ * should be called when a batch of packets has been processed in the
+ * napi loop.
+ **/
+void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res)
+{
+ if (xdp_res & I40E_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_res & I40E_XDP_TX) {
+ struct i40e_ring *xdp_ring =
+ rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+
+ i40e_xdp_ring_update_tail(xdp_ring);
+ }
+}
+
+/**
* i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
* @rx_ring: rx descriptor ring to transact packets on
* @budget: Total limit on number of packets to process
@@ -2323,8 +2341,6 @@
struct i40e_rx_buffer *rx_buffer;
union i40e_rx_desc *rx_desc;
unsigned int size;
- u16 vlan_tag;
- u8 rx_ptype;
u64 qword;
/* return some buffers to hardware, one at a time is too slow */
@@ -2349,11 +2365,14 @@
*/
dma_rmb();
- if (unlikely(i40e_rx_is_programming_status(qword))) {
- i40e_clean_programming_status(rx_ring, rx_desc, qword);
+ rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc,
+ qword);
+ if (unlikely(rx_buffer)) {
+ i40e_reuse_rx_page(rx_ring, rx_buffer);
cleaned_count++;
continue;
}
+
size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
if (!size)
@@ -2414,42 +2433,21 @@
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
- qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
- I40E_RXD_QW1_PTYPE_SHIFT;
-
/* populate checksum, VLAN, and protocol */
- i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
- vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
- le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
+ i40e_process_skb_fields(rx_ring, rx_desc, skb);
i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
- i40e_receive_skb(rx_ring, skb, vlan_tag);
+ napi_gro_receive(&rx_ring->q_vector->napi, skb);
skb = NULL;
/* update budget accounting */
total_rx_packets++;
}
- if (xdp_xmit & I40E_XDP_REDIR)
- xdp_do_flush_map();
-
- if (xdp_xmit & I40E_XDP_TX) {
- struct i40e_ring *xdp_ring =
- rx_ring->vsi->xdp_rings[rx_ring->queue_index];
-
- i40e_xdp_ring_update_tail(xdp_ring);
- }
-
+ i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
rx_ring->skb = skb;
- u64_stats_update_begin(&rx_ring->syncp);
- rx_ring->stats.packets += total_rx_packets;
- rx_ring->stats.bytes += total_rx_bytes;
- u64_stats_update_end(&rx_ring->syncp);
- rx_ring->q_vector->rx.total_packets += total_rx_packets;
- rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+ i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
/* guarantee a trip back through this routine if there was a failure */
return failure ? budget : (int)total_rx_packets;
@@ -2587,7 +2585,11 @@
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
i40e_for_each_ring(ring, q_vector->tx) {
- if (!i40e_clean_tx_irq(vsi, ring, budget)) {
+ bool wd = ring->xsk_umem ?
+ i40e_clean_xdp_tx_irq(vsi, ring, budget) :
+ i40e_clean_tx_irq(vsi, ring, budget);
+
+ if (!wd) {
clean_complete = false;
continue;
}
@@ -2605,7 +2607,9 @@
budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
i40e_for_each_ring(ring, q_vector->rx) {
- int cleaned = i40e_clean_rx_irq(ring, budget_per_ring);
+ int cleaned = ring->xsk_umem ?
+ i40e_clean_rx_irq_zc(ring, budget_per_ring) :
+ i40e_clean_rx_irq(ring, budget_per_ring);
work_done += cleaned;
/* if we clean as many as budgeted, we must not be done */
@@ -2645,10 +2649,11 @@
if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
q_vector->arm_wb_state = false;
- /* Work is done so exit the polling mode and re-enable the interrupt */
- napi_complete_done(napi, work_done);
-
- i40e_update_enable_itr(vsi, q_vector);
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ i40e_update_enable_itr(vsi, q_vector);
return min(work_done, budget - 1);
}
@@ -3257,7 +3262,7 @@
**/
bool __i40e_chk_linearize(struct sk_buff *skb)
{
- const struct skb_frag_struct *frag, *stale;
+ const skb_frag_t *frag, *stale;
int nr_frags, sum;
/* no need to check if number of frags is less than 7 */
@@ -3301,7 +3306,7 @@
* descriptor associated with the fragment.
*/
if (stale_size > I40E_MAX_DATA_PER_TXD) {
- int align_pad = -(stale->page_offset) &
+ int align_pad = -(skb_frag_off(stale)) &
(I40E_MAX_READ_REQ_SIZE - 1);
sum -= align_pad;
@@ -3344,7 +3349,7 @@
{
unsigned int data_len = skb->data_len;
unsigned int size = skb_headlen(skb);
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
struct i40e_tx_buffer *tx_bi;
struct i40e_tx_desc *tx_desc;
u16 i = tx_ring->next_to_use;
@@ -3451,6 +3456,8 @@
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, td_offset, size, td_tag);
+ skb_tx_timestamp(skb);
+
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch.
*
@@ -3463,13 +3470,8 @@
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return 0;
@@ -3504,6 +3506,7 @@
u16 i = xdp_ring->next_to_use;
struct i40e_tx_buffer *tx_bi;
struct i40e_tx_desc *tx_desc;
+ void *data = xdpf->data;
u32 size = xdpf->len;
dma_addr_t dma;
@@ -3511,8 +3514,7 @@
xdp_ring->tx_stats.tx_busy++;
return I40E_XDP_CONSUMED;
}
-
- dma = dma_map_single(xdp_ring->dev, xdpf->data, size, DMA_TO_DEVICE);
+ dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
if (dma_mapping_error(xdp_ring->dev, dma))
return I40E_XDP_CONSUMED;
@@ -3630,8 +3632,6 @@
if (tsyn)
tx_flags |= I40E_TX_FLAGS_TSYN;
- skb_tx_timestamp(skb);
-
/* always enable CRC insertion offload */
td_cmd |= I40E_TX_DESC_CMD_ICRC;
@@ -3705,6 +3705,7 @@
struct i40e_netdev_priv *np = netdev_priv(dev);
unsigned int queue_index = smp_processor_id();
struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
struct i40e_ring *xdp_ring;
int drops = 0;
int i;
@@ -3712,7 +3713,8 @@
if (test_bit(__I40E_VSI_DOWN, vsi->state))
return -ENETDOWN;
- if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+ if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs ||
+ test_bit(__I40E_CONFIG_BUSY, pf->state))
return -ENXIO;
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index bb04f6a..36d37f3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -296,13 +296,17 @@
struct i40e_rx_buffer {
dma_addr_t dma;
- struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
- __u32 page_offset;
-#else
- __u16 page_offset;
-#endif
- __u16 pagecnt_bias;
+ union {
+ struct {
+ struct page *page;
+ __u32 page_offset;
+ __u16 pagecnt_bias;
+ };
+ struct {
+ void *addr;
+ u64 handle;
+ };
+ };
};
struct i40e_queue_stats {
@@ -414,6 +418,8 @@
struct i40e_channel *ch;
struct xdp_rxq_info xdp_rxq;
+ struct xdp_umem *xsk_umem;
+ struct zero_copy_allocator zca; /* ZC allocator anchor */
} ____cacheline_internodealigned_in_smp;
static inline bool ring_uses_build_skb(struct i40e_ring *ring)
@@ -515,7 +521,7 @@
**/
static inline int i40e_xmit_descriptor_count(struct sk_buff *skb)
{
- const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
int count = 0, size = skb_headlen(skb);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
new file mode 100644
index 0000000..8af0e99
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Intel Corporation. */
+
+#ifndef I40E_TXRX_COMMON_
+#define I40E_TXRX_COMMON_
+
+void i40e_fd_handle_status(struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc, u8 prog_id);
+int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
+struct i40e_rx_buffer *i40e_clean_programming_status(
+ struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc,
+ u64 qw);
+void i40e_process_skb_fields(struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc, struct sk_buff *skb);
+void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
+void i40e_update_rx_stats(struct i40e_ring *rx_ring,
+ unsigned int total_rx_bytes,
+ unsigned int total_rx_packets);
+void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res);
+void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val);
+
+#define I40E_XDP_PASS 0
+#define I40E_XDP_CONSUMED BIT(0)
+#define I40E_XDP_TX BIT(1)
+#define I40E_XDP_REDIR BIT(2)
+
+/**
+ * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword
+ **/
+static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
+ u32 td_tag)
+{
+ return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
+ ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) |
+ ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
+ ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
+ ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT));
+}
+
+/**
+ * i40e_update_tx_stats - Update the egress statistics for the Tx ring
+ * @tx_ring: Tx ring to update
+ * @total_packet: total packets sent
+ * @total_bytes: total bytes sent
+ **/
+static inline void i40e_update_tx_stats(struct i40e_ring *tx_ring,
+ unsigned int total_packets,
+ unsigned int total_bytes)
+{
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->stats.bytes += total_bytes;
+ tx_ring->stats.packets += total_packets;
+ u64_stats_update_end(&tx_ring->syncp);
+ tx_ring->q_vector->tx.total_bytes += total_bytes;
+ tx_ring->q_vector->tx.total_packets += total_packets;
+}
+
+#define WB_STRIDE 4
+
+/**
+ * i40e_arm_wb - (Possibly) arms Tx write-back
+ * @tx_ring: Tx ring to update
+ * @vsi: the VSI
+ * @budget: the NAPI budget left
+ **/
+static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
+ struct i40e_vsi *vsi,
+ int budget)
+{
+ if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
+ /* check to see if there are < 4 descriptors
+ * waiting to be written back, then kick the hardware to force
+ * them to be written back in case we stay in NAPI.
+ * In this mode on X722 we do not enable Interrupt.
+ */
+ unsigned int j = i40e_get_tx_pending(tx_ring, false);
+
+ if (budget &&
+ ((j / WB_STRIDE) == 0) && j > 0 &&
+ !test_bit(__I40E_VSI_DOWN, vsi->state) &&
+ (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+ tx_ring->arm_wb = true;
+ }
+}
+
+void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
+void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
+bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi);
+
+#endif /* I40E_TXRX_COMMON_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 7df969c..b43ec94 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -252,6 +252,12 @@
I40E_PHY_TYPE_OFFSET)
#define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \
I40E_PHY_TYPE_OFFSET)
+/* Offset for 2.5G/5G PHY Types value to bit number conversion */
+#define I40E_PHY_TYPE_OFFSET2 (-10)
+#define I40E_CAP_PHY_TYPE_2_5GBASE_T BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T + \
+ I40E_PHY_TYPE_OFFSET2)
+#define I40E_CAP_PHY_TYPE_5GBASE_T BIT_ULL(I40E_PHY_TYPE_5GBASE_T + \
+ I40E_PHY_TYPE_OFFSET2)
#define I40E_HW_CAP_MAX_GPIO 30
/* Capabilities of a PF or a VF or the whole device */
struct i40e_hw_capabilities {
@@ -437,6 +443,7 @@
#define I40E_MODULE_SFF_8472_COMP 0x5E
#define I40E_MODULE_SFF_8472_SWAP 0x5C
#define I40E_MODULE_SFF_ADDR_MODE 0x04
+#define I40E_MODULE_SFF_DDM_IMPLEMENTED 0x40
#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D
#define I40E_MODULE_TYPE_QSFP28 0x11
#define I40E_MODULE_QSFP_MAX_LEN 640
@@ -615,6 +622,9 @@
#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1)
#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2)
#define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
+#define I40E_HW_FLAG_FW_LLDP_STOPPABLE BIT_ULL(4)
+#define I40E_HW_FLAG_FW_LLDP_PERSISTENT BIT_ULL(5)
+#define I40E_HW_FLAG_DROP_MODE BIT_ULL(7)
u64 flags;
/* Used in set switch config AQ command */
@@ -1308,6 +1318,7 @@
#define I40E_SR_VPD_PTR 0x2F
#define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E
#define I40E_SR_SW_CHECKSUM_WORD 0x3F
+#define I40E_SR_EMP_SR_SETTINGS_PTR 0x48
/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
#define I40E_SR_VPD_MODULE_MAX_SIZE 1024
@@ -1526,6 +1537,8 @@
struct i40e_metadata_segment {
struct i40e_generic_seg_header header;
struct i40e_ddp_version version;
+#define I40E_DDP_TRACKID_RDONLY 0
+#define I40E_DDP_TRACKID_INVALID 0xFFFFFFFF
u32 track_id;
char name[I40E_DDP_NAME_SIZE];
};
@@ -1554,15 +1567,36 @@
struct {
#define SECTION_TYPE_INFO 0x00000010
#define SECTION_TYPE_MMIO 0x00000800
+#define SECTION_TYPE_RB_MMIO 0x00001800
#define SECTION_TYPE_AQ 0x00000801
+#define SECTION_TYPE_RB_AQ 0x00001801
#define SECTION_TYPE_NOTE 0x80000000
#define SECTION_TYPE_NAME 0x80000001
+#define SECTION_TYPE_PROTO 0x80000002
+#define SECTION_TYPE_PCTYPE 0x80000003
+#define SECTION_TYPE_PTYPE 0x80000004
u32 type;
u32 offset;
u32 size;
} section;
};
+struct i40e_profile_tlv_section_record {
+ u8 rtype;
+ u8 type;
+ u16 len;
+ u8 data[12];
+};
+
+/* Generic AQ section in proflie */
+struct i40e_profile_aq_section {
+ u16 opcode;
+ u16 flags;
+ u8 param[16];
+ u16 datalen;
+ u8 data[1];
+};
+
struct i40e_profile_info {
u32 track_id;
struct i40e_ddp_version version;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index c6d24ea..3d24408 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -55,7 +55,12 @@
pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
pfe.severity = PF_EVENT_SEVERITY_INFO;
- if (vf->link_forced) {
+
+ /* Always report link is down if the VF queues aren't enabled */
+ if (!vf->queues_enabled) {
+ pfe.event_data.link_event.link_status = false;
+ pfe.event_data.link_event.link_speed = 0;
+ } else if (vf->link_forced) {
pfe.event_data.link_event.link_status = vf->link_up;
pfe.event_data.link_event.link_speed =
(vf->link_up ? VIRTCHNL_LINK_SPEED_40GB : 0);
@@ -65,6 +70,7 @@
pfe.event_data.link_event.link_speed =
i40e_virtchnl_link_speed(ls->link_speed);
}
+
i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT,
0, (u8 *)&pfe, sizeof(pfe), NULL);
}
@@ -181,7 +187,7 @@
* check for the valid queue id
**/
static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u16 vsi_id,
- u8 qid)
+ u16 qid)
{
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = i40e_find_vsi_from_id(pf, vsi_id);
@@ -196,7 +202,7 @@
*
* check for the valid vector id
**/
-static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u8 vector_id)
+static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u32 vector_id)
{
struct i40e_pf *pf = vf->pf;
@@ -440,15 +446,28 @@
struct virtchnl_iwarp_qv_info *qv_info;
u32 v_idx, i, reg_idx, reg;
u32 next_q_idx, next_q_type;
- u32 msix_vf, size;
+ u32 msix_vf;
+ int ret = 0;
- size = sizeof(struct virtchnl_iwarp_qvlist_info) +
- (sizeof(struct virtchnl_iwarp_qv_info) *
- (qvlist_info->num_vectors - 1));
- vf->qvlist_info = kzalloc(size, GFP_KERNEL);
- if (!vf->qvlist_info)
- return -ENOMEM;
+ msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
+ if (qvlist_info->num_vectors > msix_vf) {
+ dev_warn(&pf->pdev->dev,
+ "Incorrect number of iwarp vectors %u. Maximum %u allowed.\n",
+ qvlist_info->num_vectors,
+ msix_vf);
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ kfree(vf->qvlist_info);
+ vf->qvlist_info = kzalloc(struct_size(vf->qvlist_info, qv_info,
+ qvlist_info->num_vectors - 1),
+ GFP_KERNEL);
+ if (!vf->qvlist_info) {
+ ret = -ENOMEM;
+ goto err_out;
+ }
vf->qvlist_info->num_vectors = qvlist_info->num_vectors;
msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
@@ -456,11 +475,14 @@
qv_info = &qvlist_info->qv_info[i];
if (!qv_info)
continue;
- v_idx = qv_info->v_idx;
/* Validate vector id belongs to this vf */
- if (!i40e_vc_isvalid_vector_id(vf, v_idx))
- goto err;
+ if (!i40e_vc_isvalid_vector_id(vf, qv_info->v_idx)) {
+ ret = -EINVAL;
+ goto err_free;
+ }
+
+ v_idx = qv_info->v_idx;
vf->qvlist_info->qv_info[i] = *qv_info;
@@ -502,10 +524,11 @@
}
return 0;
-err:
+err_free:
kfree(vf->qvlist_info);
vf->qvlist_info = NULL;
- return -EINVAL;
+err_out:
+ return ret;
}
/**
@@ -1084,6 +1107,128 @@
return -EIO;
}
+static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi);
+
+/**
+ * i40e_config_vf_promiscuous_mode
+ * @vf: pointer to the VF info
+ * @vsi_id: VSI id
+ * @allmulti: set MAC L2 layer multicast promiscuous enable/disable
+ * @alluni: set MAC L2 layer unicast promiscuous enable/disable
+ *
+ * Called from the VF to configure the promiscuous mode of
+ * VF vsis and from the VF reset path to reset promiscuous mode.
+ **/
+static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
+ u16 vsi_id,
+ bool allmulti,
+ bool alluni)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_mac_filter *f;
+ i40e_status aq_ret = 0;
+ struct i40e_vsi *vsi;
+ int bkt;
+
+ vsi = i40e_find_vsi_from_id(pf, vsi_id);
+ if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi)
+ return I40E_ERR_PARAM;
+
+ if (vf->port_vlan_id) {
+ aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, vsi->seid,
+ allmulti,
+ vf->port_vlan_id,
+ NULL);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n",
+ vf->vf_id,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ return aq_ret;
+ }
+
+ aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, vsi->seid,
+ alluni,
+ vf->port_vlan_id,
+ NULL);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n",
+ vf->vf_id,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ }
+ return aq_ret;
+ } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) {
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
+ if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID)
+ continue;
+ aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw,
+ vsi->seid,
+ allmulti,
+ f->vlan,
+ NULL);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "Could not add VLAN %d to multicast promiscuous domain err %s aq_err %s\n",
+ f->vlan,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ }
+
+ aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw,
+ vsi->seid,
+ alluni,
+ f->vlan,
+ NULL);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "Could not add VLAN %d to Unicast promiscuous domain err %s aq_err %s\n",
+ f->vlan,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ }
+ }
+ return aq_ret;
+ }
+ aq_ret = i40e_aq_set_vsi_multicast_promiscuous(hw, vsi->seid, allmulti,
+ NULL);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n",
+ vf->vf_id,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ return aq_ret;
+ }
+
+ aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, vsi->seid, alluni,
+ NULL, true);
+ if (aq_ret) {
+ int aq_err = pf->hw.aq.asq_last_status;
+
+ dev_err(&pf->pdev->dev,
+ "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n",
+ vf->vf_id,
+ i40e_stat_str(&pf->hw, aq_ret),
+ i40e_aq_str(&pf->hw, aq_err));
+ }
+
+ return aq_ret;
+}
+
/**
* i40e_trigger_vf_reset
* @vf: pointer to the VF structure
@@ -1145,6 +1290,9 @@
struct i40e_hw *hw = &pf->hw;
u32 reg;
+ /* disable promisc modes in case they were enabled */
+ i40e_config_vf_promiscuous_mode(vf, vf->lan_vsi_id, false, false);
+
/* free VF resources to begin resetting the VSI state */
i40e_free_vf_res(vf);
@@ -1542,13 +1690,20 @@
int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
+ int ret = 0;
+
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
+ }
if (num_vfs) {
if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
}
- return i40e_pci_sriov_enable(pdev, num_vfs);
+ ret = i40e_pci_sriov_enable(pdev, num_vfs);
+ goto sriov_configure_out;
}
if (!pci_vfs_assigned(pf->pdev)) {
@@ -1557,9 +1712,12 @@
i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
} else {
dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto sriov_configure_out;
}
- return 0;
+sriov_configure_out:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
+ return ret;
}
/***********************virtual channel routines******************/
@@ -1693,7 +1851,7 @@
i40e_status aq_ret = 0;
struct i40e_vsi *vsi;
int num_vsis = 1;
- int len = 0;
+ size_t len = 0;
int ret;
if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
@@ -1701,9 +1859,7 @@
goto err;
}
- len = (sizeof(struct virtchnl_vf_resource) +
- sizeof(struct virtchnl_vsi_resource) * num_vsis);
-
+ len = struct_size(vfres, vsi_res, num_vsis);
vfres = kzalloc(len, GFP_KERNEL);
if (!vfres) {
aq_ret = I40E_ERR_NO_MEMORY;
@@ -1840,143 +1996,81 @@
* i40e_vc_config_promiscuous_mode_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the promiscuous mode of
* VF vsis
**/
-static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
- u8 *msg, u16 msglen)
+static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_promisc_info *info =
(struct virtchnl_promisc_info *)msg;
struct i40e_pf *pf = vf->pf;
- struct i40e_hw *hw = &pf->hw;
- struct i40e_mac_filter *f;
i40e_status aq_ret = 0;
bool allmulti = false;
- struct i40e_vsi *vsi;
bool alluni = false;
- int aq_err = 0;
- int bkt;
- vsi = i40e_find_vsi_from_id(pf, info->vsi_id);
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, info->vsi_id) ||
- !vsi) {
+ if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
- goto error_param;
+ goto err_out;
}
if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
dev_err(&pf->pdev->dev,
"Unprivileged VF %d is attempting to configure promiscuous mode\n",
vf->vf_id);
- /* Lie to the VF on purpose. */
+
+ /* Lie to the VF on purpose, because this is an error we can
+ * ignore. Unprivileged VF is not a virtual channel error.
+ */
aq_ret = 0;
- goto error_param;
+ goto err_out;
}
+
+ if (info->flags > I40E_MAX_VF_PROMISC_FLAGS) {
+ aq_ret = I40E_ERR_PARAM;
+ goto err_out;
+ }
+
+ if (!i40e_vc_isvalid_vsi_id(vf, info->vsi_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto err_out;
+ }
+
/* Multicast promiscuous handling*/
if (info->flags & FLAG_VF_MULTICAST_PROMISC)
allmulti = true;
- if (vf->port_vlan_id) {
- aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, vsi->seid,
- allmulti,
- vf->port_vlan_id,
- NULL);
- } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) {
- hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
- if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID)
- continue;
- aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw,
- vsi->seid,
- allmulti,
- f->vlan,
- NULL);
- aq_err = pf->hw.aq.asq_last_status;
- if (aq_ret) {
- dev_err(&pf->pdev->dev,
- "Could not add VLAN %d to multicast promiscuous domain err %s aq_err %s\n",
- f->vlan,
- i40e_stat_str(&pf->hw, aq_ret),
- i40e_aq_str(&pf->hw, aq_err));
- break;
- }
- }
- } else {
- aq_ret = i40e_aq_set_vsi_multicast_promiscuous(hw, vsi->seid,
- allmulti, NULL);
- aq_err = pf->hw.aq.asq_last_status;
- if (aq_ret) {
- dev_err(&pf->pdev->dev,
- "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n",
- vf->vf_id,
- i40e_stat_str(&pf->hw, aq_ret),
- i40e_aq_str(&pf->hw, aq_err));
- goto error_param;
- }
- }
-
- if (!aq_ret) {
- dev_info(&pf->pdev->dev,
- "VF %d successfully set multicast promiscuous mode\n",
- vf->vf_id);
- if (allmulti)
- set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
- else
- clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
- }
-
if (info->flags & FLAG_VF_UNICAST_PROMISC)
alluni = true;
- if (vf->port_vlan_id) {
- aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, vsi->seid,
- alluni,
- vf->port_vlan_id,
- NULL);
- } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) {
- hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
- if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID)
- continue;
- aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw,
- vsi->seid,
- alluni,
- f->vlan,
- NULL);
- aq_err = pf->hw.aq.asq_last_status;
- if (aq_ret)
- dev_err(&pf->pdev->dev,
- "Could not add VLAN %d to Unicast promiscuous domain err %s aq_err %s\n",
- f->vlan,
- i40e_stat_str(&pf->hw, aq_ret),
- i40e_aq_str(&pf->hw, aq_err));
- }
- } else {
- aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, vsi->seid,
- alluni, NULL,
- true);
- aq_err = pf->hw.aq.asq_last_status;
- if (aq_ret) {
- dev_err(&pf->pdev->dev,
- "VF %d failed to set unicast promiscuous mode %8.8x err %s aq_err %s\n",
- vf->vf_id, info->flags,
- i40e_stat_str(&pf->hw, aq_ret),
- i40e_aq_str(&pf->hw, aq_err));
- goto error_param;
- }
- }
+ aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti,
+ alluni);
+ if (aq_ret)
+ goto err_out;
- if (!aq_ret) {
+ if (allmulti) {
+ if (!test_and_set_bit(I40E_VF_STATE_MC_PROMISC,
+ &vf->vf_states))
+ dev_info(&pf->pdev->dev,
+ "VF %d successfully set multicast promiscuous mode\n",
+ vf->vf_id);
+ } else if (test_and_clear_bit(I40E_VF_STATE_MC_PROMISC,
+ &vf->vf_states))
dev_info(&pf->pdev->dev,
- "VF %d successfully set unicast promiscuous mode\n",
+ "VF %d successfully unset multicast promiscuous mode\n",
vf->vf_id);
- if (alluni)
- set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
- else
- clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
- }
-error_param:
+ if (alluni) {
+ if (!test_and_set_bit(I40E_VF_STATE_UC_PROMISC,
+ &vf->vf_states))
+ dev_info(&pf->pdev->dev,
+ "VF %d successfully set unicast promiscuous mode\n",
+ vf->vf_id);
+ } else if (test_and_clear_bit(I40E_VF_STATE_UC_PROMISC,
+ &vf->vf_states))
+ dev_info(&pf->pdev->dev,
+ "VF %d successfully unset unicast promiscuous mode\n",
+ vf->vf_id);
+
+err_out:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf,
VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
@@ -1987,37 +2081,57 @@
* i40e_vc_config_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the rx/tx
* queues
**/
-static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vsi_queue_config_info *qci =
(struct virtchnl_vsi_queue_config_info *)msg;
struct virtchnl_queue_pair_info *qpi;
struct i40e_pf *pf = vf->pf;
u16 vsi_id, vsi_queue_id = 0;
+ u16 num_qps_all = 0;
i40e_status aq_ret = 0;
int i, j = 0, idx = 0;
- vsi_id = qci->vsi_id;
-
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
- if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ if (!i40e_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
+ if (qci->num_queue_pairs > I40E_MAX_VF_QUEUES) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vf->adq_enabled) {
+ for (i = 0; i < I40E_MAX_VF_VSI; i++)
+ num_qps_all += vf->ch[i].num_qps;
+ if (num_qps_all != qci->num_queue_pairs) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+ }
+
+ vsi_id = qci->vsi_id;
+
for (i = 0; i < qci->num_queue_pairs; i++) {
qpi = &qci->qpair[i];
if (!vf->adq_enabled) {
+ if (!i40e_vc_isvalid_queue_id(vf, vsi_id,
+ qpi->txq.queue_id)) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
vsi_queue_id = qpi->txq.queue_id;
if (qpi->txq.vsi_id != qci->vsi_id ||
@@ -2028,9 +2142,12 @@
}
}
- if (!i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) {
- aq_ret = I40E_ERR_PARAM;
- goto error_param;
+ if (vf->adq_enabled) {
+ if (idx >= ARRAY_SIZE(vf->ch)) {
+ aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+ goto error_param;
+ }
+ vsi_id = vf->ch[idx].vsi_id;
}
if (i40e_config_vsi_rx_queue(vf, vsi_id, vsi_queue_id,
@@ -2045,8 +2162,12 @@
* VF does not know about these additional VSIs and all
* it cares is about its own queues. PF configures these queues
* to its appropriate VSIs based on TC mapping
- **/
+ */
if (vf->adq_enabled) {
+ if (idx >= ARRAY_SIZE(vf->ch)) {
+ aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+ goto error_param;
+ }
if (j == (vf->ch[idx].num_qps - 1)) {
idx++;
j = 0; /* resetting the queue count */
@@ -2055,7 +2176,6 @@
j++;
vsi_queue_id++;
}
- vsi_id = vf->ch[idx].vsi_id;
}
}
/* set vsi num_queue_pairs in use to num configured by VF */
@@ -2105,17 +2225,16 @@
* i40e_vc_config_irq_map_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to configure the irq to
* queue map
**/
-static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_irq_map_info *irqmap_info =
(struct virtchnl_irq_map_info *)msg;
struct virtchnl_vector_map *map;
- u16 vsi_id, vector_id;
+ u16 vsi_id;
i40e_status aq_ret = 0;
int i;
@@ -2124,16 +2243,21 @@
goto error_param;
}
+ if (irqmap_info->num_vectors >
+ vf->pf->hw.func_caps.num_msix_vectors_vf) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
for (i = 0; i < irqmap_info->num_vectors; i++) {
map = &irqmap_info->vecmap[i];
- vector_id = map->vector_id;
- vsi_id = map->vsi_id;
/* validate msg params */
- if (!i40e_vc_isvalid_vector_id(vf, vector_id) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ if (!i40e_vc_isvalid_vector_id(vf, map->vector_id) ||
+ !i40e_vc_isvalid_vsi_id(vf, map->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
+ vsi_id = map->vsi_id;
if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) {
aq_ret = I40E_ERR_PARAM;
@@ -2202,16 +2326,14 @@
* i40e_vc_enable_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to enable all or specific queue(s)
**/
-static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
struct i40e_pf *pf = vf->pf;
- u16 vsi_id = vqs->vsi_id;
i40e_status aq_ret = 0;
int i;
@@ -2220,7 +2342,7 @@
goto error_param;
}
- if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2251,6 +2373,8 @@
}
}
+ vf->queues_enabled = true;
+
error_param:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES,
@@ -2261,18 +2385,20 @@
* i40e_vc_disable_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to disable all or specific
* queue(s)
**/
-static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
struct i40e_pf *pf = vf->pf;
i40e_status aq_ret = 0;
+ /* Immediately mark queues as disabled */
+ vf->queues_enabled = false;
+
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
@@ -2283,7 +2409,9 @@
goto error_param;
}
- if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+ if ((vqs->rx_queues == 0 && vqs->tx_queues == 0) ||
+ vqs->rx_queues > I40E_MAX_VF_QUEUES ||
+ vqs->tx_queues > I40E_MAX_VF_QUEUES) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2309,29 +2437,24 @@
* i40e_vc_request_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* VFs get a default number of queues but can use this message to request a
* different number. If the request is successful, PF will reset the VF and
* return 0. If unsuccessful, PF will send message informing VF of number of
* available queues and return result of sending VF a message.
**/
-static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen)
+static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vf_res_request *vfres =
(struct virtchnl_vf_res_request *)msg;
- int req_pairs = vfres->num_queue_pairs;
- int cur_pairs = vf->num_queue_pairs;
+ u16 req_pairs = vfres->num_queue_pairs;
+ u8 cur_pairs = vf->num_queue_pairs;
struct i40e_pf *pf = vf->pf;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
return -EINVAL;
- if (req_pairs <= 0) {
- dev_err(&pf->pdev->dev,
- "VF %d tried to request %d queues. Ignoring.\n",
- vf->vf_id, req_pairs);
- } else if (req_pairs > I40E_MAX_VF_QUEUES) {
+ if (req_pairs > I40E_MAX_VF_QUEUES) {
dev_err(&pf->pdev->dev,
"VF %d tried to request more than %d queues.\n",
vf->vf_id,
@@ -2360,11 +2483,10 @@
* i40e_vc_get_stats_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to get vsi stats
**/
-static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_queue_select *vqs =
(struct virtchnl_queue_select *)msg;
@@ -2399,9 +2521,11 @@
(u8 *)&stats, sizeof(stats));
}
-/* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
-#define I40E_VC_MAX_VLAN_PER_VF 8
+/* If the VF is not trusted restrict the number of MAC/VLAN it can program
+ * MAC filters: 16 for multicast, 1 for MAC, 1 for broadcast
+ */
+#define I40E_VC_MAX_MAC_ADDR_PER_VF (16 + 1 + 1)
+#define I40E_VC_MAX_VLAN_PER_VF 16
/**
* i40e_check_vf_permission
@@ -2458,7 +2582,7 @@
!is_multicast_ether_addr(addr) && vf->pf_set_mac &&
!ether_addr_equal(addr, vf->default_lan_addr.addr)) {
dev_err(&pf->pdev->dev,
- "VF attempting to override administratively set MAC address, reload the VF driver to resume normal operation\n");
+ "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
return -EPERM;
}
}
@@ -2470,22 +2594,20 @@
* i40e_vc_add_mac_addr_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* add guest mac address filter
**/
-static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = al->vsi_id;
i40e_status ret = 0;
int i;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2541,22 +2663,20 @@
* i40e_vc_del_mac_addr_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* remove guest mac address filter
**/
-static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = al->vsi_id;
i40e_status ret = 0;
int i;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2569,6 +2689,16 @@
ret = I40E_ERR_INVALID_MAC_ADDR;
goto error_param;
}
+
+ if (vf->pf_set_mac &&
+ ether_addr_equal(al->list[i].addr,
+ vf->default_lan_addr.addr)) {
+ dev_err(&pf->pdev->dev,
+ "MAC addr %pM has been set by PF, cannot delete it for VF %d, reset VF to change MAC addr\n",
+ vf->default_lan_addr.addr, vf->vf_id);
+ ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
}
vsi = pf->vsi[vf->lan_vsi_idx];
@@ -2601,17 +2731,15 @@
* i40e_vc_add_vlan_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* program guest vlan id
**/
-static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vlan_filter_list *vfl =
(struct virtchnl_vlan_filter_list *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = vfl->vsi_id;
i40e_status aq_ret = 0;
int i;
@@ -2622,7 +2750,7 @@
goto error_param;
}
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2674,22 +2802,20 @@
* i40e_vc_remove_vlan_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* remove programmed guest vlan id
**/
-static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_vlan_filter_list *vfl =
(struct virtchnl_vlan_filter_list *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = vfl->vsi_id;
i40e_status aq_ret = 0;
int i;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+ !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2703,7 +2829,8 @@
vsi = pf->vsi[vf->lan_vsi_idx];
if (vsi->info.pvid) {
- aq_ret = I40E_ERR_PARAM;
+ if (vfl->num_elements > 1 || vfl->vlan_id[0])
+ aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2761,13 +2888,11 @@
* i40e_vc_iwarp_qvmap_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
* @config: config qvmap or release it
*
* called from the VF for the iwarp msgs
**/
-static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen,
- bool config)
+static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config)
{
struct virtchnl_iwarp_qvlist_info *qvlist_info =
(struct virtchnl_iwarp_qvlist_info *)msg;
@@ -2798,21 +2923,19 @@
* i40e_vc_config_rss_key
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Configure the VF's RSS key
**/
-static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_key *vrk =
(struct virtchnl_rss_key *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = vrk->vsi_id;
i40e_status aq_ret = 0;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
+ !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) ||
(vrk->key_len != I40E_HKEY_ARRAY_SIZE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
@@ -2830,26 +2953,31 @@
* i40e_vc_config_rss_lut
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Configure the VF's RSS LUT
**/
-static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_lut *vrl =
(struct virtchnl_rss_lut *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
- u16 vsi_id = vrl->vsi_id;
i40e_status aq_ret = 0;
+ u16 i;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
- !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
+ !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) ||
(vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
+ for (i = 0; i < vrl->lut_entries; i++)
+ if (vrl->lut[i] >= vf->num_queue_pairs) {
+ aq_ret = I40E_ERR_PARAM;
+ goto err;
+ }
+
vsi = pf->vsi[vf->lan_vsi_idx];
aq_ret = i40e_config_rss(vsi, NULL, vrl->lut, I40E_VF_HLUT_ARRAY_SIZE);
/* send the response to the VF */
@@ -2862,11 +2990,10 @@
* i40e_vc_get_rss_hena
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Return the RSS HENA bits allowed by the hardware
**/
-static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_hena *vrh = NULL;
struct i40e_pf *pf = vf->pf;
@@ -2898,11 +3025,10 @@
* i40e_vc_set_rss_hena
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Set the RSS HENA bits for the VF
**/
-static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen)
+static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
{
struct virtchnl_rss_hena *vrh =
(struct virtchnl_rss_hena *)msg;
@@ -2927,21 +3053,20 @@
* i40e_vc_enable_vlan_stripping
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Enable vlan header stripping for the VF
**/
-static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg,
- u16 msglen)
+static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
{
- struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_status aq_ret = 0;
+ struct i40e_vsi *vsi;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
+ vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_vlan_stripping_enable(vsi);
/* send the response to the VF */
@@ -2954,21 +3079,20 @@
* i40e_vc_disable_vlan_stripping
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* Disable vlan header stripping for the VF
**/
-static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg,
- u16 msglen)
+static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
{
- struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_status aq_ret = 0;
+ struct i40e_vsi *vsi;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
+ vsi = vf->pf->vsi[vf->lan_vsi_idx];
i40e_vlan_stripping_disable(vsi);
/* send the response to the VF */
@@ -3075,7 +3199,7 @@
}
if (mask.dst_port & data.dst_port) {
- if (!data.dst_port || be16_to_cpu(data.dst_port) > 0xFFFF) {
+ if (!data.dst_port) {
dev_info(&pf->pdev->dev, "VF %d: Invalid Dest port\n",
vf->vf_id);
goto err;
@@ -3083,7 +3207,7 @@
}
if (mask.src_port & data.src_port) {
- if (!data.src_port || be16_to_cpu(data.src_port) > 0xFFFF) {
+ if (!data.src_port) {
dev_info(&pf->pdev->dev, "VF %d: Invalid Source port\n",
vf->vf_id);
goto err;
@@ -3323,7 +3447,7 @@
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
- goto err;
+ goto err_out;
}
if (!vf->adq_enabled) {
@@ -3331,15 +3455,15 @@
"VF %d: ADq is not enabled, can't apply cloud filter\n",
vf->vf_id);
aq_ret = I40E_ERR_PARAM;
- goto err;
+ goto err_out;
}
if (i40e_validate_cloud_filter(vf, vcf)) {
dev_info(&pf->pdev->dev,
"VF %d: Invalid input/s, can't apply cloud filter\n",
vf->vf_id);
- aq_ret = I40E_ERR_PARAM;
- goto err;
+ aq_ret = I40E_ERR_PARAM;
+ goto err_out;
}
cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
@@ -3400,13 +3524,17 @@
"VF %d: Failed to add cloud filter, err %s aq_err %s\n",
vf->vf_id, i40e_stat_str(&pf->hw, ret),
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
- goto err;
+ goto err_free;
}
INIT_HLIST_NODE(&cfilter->cloud_node);
hlist_add_head(&cfilter->cloud_node, &vf->cloud_filter_list);
+ /* release the pointer passing it to the collection */
+ cfilter = NULL;
vf->num_cloud_filters++;
-err:
+err_free:
+ kfree(cfilter);
+err_out:
return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_CLOUD_FILTER,
aq_ret);
}
@@ -3422,8 +3550,9 @@
(struct virtchnl_tc_info *)msg;
struct i40e_pf *pf = vf->pf;
struct i40e_link_status *ls = &pf->hw.phy.link_info;
- int i, adq_request_qps = 0, speed = 0;
+ int i, adq_request_qps = 0;
i40e_status aq_ret = 0;
+ u64 speed = 0;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
@@ -3449,8 +3578,8 @@
/* max number of traffic classes for VF currently capped at 4 */
if (!tci->num_tc || tci->num_tc > I40E_MAX_VF_VSI) {
dev_err(&pf->pdev->dev,
- "VF %d trying to set %u TCs, valid range 1-4 TCs per VF\n",
- vf->vf_id, tci->num_tc);
+ "VF %d trying to set %u TCs, valid range 1-%u TCs per VF\n",
+ vf->vf_id, tci->num_tc, I40E_MAX_VF_VSI);
aq_ret = I40E_ERR_PARAM;
goto err;
}
@@ -3460,8 +3589,9 @@
if (!tci->list[i].count ||
tci->list[i].count > I40E_DEFAULT_QUEUES_PER_VF) {
dev_err(&pf->pdev->dev,
- "VF %d: TC %d trying to set %u queues, valid range 1-4 queues per TC\n",
- vf->vf_id, i, tci->list[i].count);
+ "VF %d: TC %d trying to set %u queues, valid range 1-%u queues per TC\n",
+ vf->vf_id, i, tci->list[i].count,
+ I40E_DEFAULT_QUEUES_PER_VF);
aq_ret = I40E_ERR_PARAM;
goto err;
}
@@ -3610,7 +3740,7 @@
int ret;
pf->vf_aq_requests++;
- if (local_vf_id >= pf->num_alloc_vfs)
+ if (local_vf_id < 0 || local_vf_id >= pf->num_alloc_vfs)
return -EINVAL;
vf = &(pf->vf[local_vf_id]);
@@ -3621,25 +3751,12 @@
/* perform basic checks on the msg */
ret = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen);
- /* perform additional checks specific to this driver */
- if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) {
- struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg;
-
- if (vrk->key_len != I40E_HKEY_ARRAY_SIZE)
- ret = -EINVAL;
- } else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) {
- struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
-
- if (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)
- ret = -EINVAL;
- }
-
if (ret) {
i40e_vc_send_resp_to_vf(vf, v_opcode, I40E_ERR_PARAM);
dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n",
local_vf_id, v_opcode, msglen);
switch (ret) {
- case VIRTCHNL_ERR_PARAM:
+ case VIRTCHNL_STATUS_ERR_PARAM:
return -EPERM;
default:
return -EINVAL;
@@ -3659,65 +3776,65 @@
ret = 0;
break;
case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
- ret = i40e_vc_config_promiscuous_mode_msg(vf, msg, msglen);
+ ret = i40e_vc_config_promiscuous_mode_msg(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_VSI_QUEUES:
- ret = i40e_vc_config_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_config_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_IRQ_MAP:
- ret = i40e_vc_config_irq_map_msg(vf, msg, msglen);
+ ret = i40e_vc_config_irq_map_msg(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_QUEUES:
- ret = i40e_vc_enable_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_enable_queues_msg(vf, msg);
i40e_vc_notify_vf_link_state(vf);
break;
case VIRTCHNL_OP_DISABLE_QUEUES:
- ret = i40e_vc_disable_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_disable_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_ADD_ETH_ADDR:
- ret = i40e_vc_add_mac_addr_msg(vf, msg, msglen);
+ ret = i40e_vc_add_mac_addr_msg(vf, msg);
break;
case VIRTCHNL_OP_DEL_ETH_ADDR:
- ret = i40e_vc_del_mac_addr_msg(vf, msg, msglen);
+ ret = i40e_vc_del_mac_addr_msg(vf, msg);
break;
case VIRTCHNL_OP_ADD_VLAN:
- ret = i40e_vc_add_vlan_msg(vf, msg, msglen);
+ ret = i40e_vc_add_vlan_msg(vf, msg);
break;
case VIRTCHNL_OP_DEL_VLAN:
- ret = i40e_vc_remove_vlan_msg(vf, msg, msglen);
+ ret = i40e_vc_remove_vlan_msg(vf, msg);
break;
case VIRTCHNL_OP_GET_STATS:
- ret = i40e_vc_get_stats_msg(vf, msg, msglen);
+ ret = i40e_vc_get_stats_msg(vf, msg);
break;
case VIRTCHNL_OP_IWARP:
ret = i40e_vc_iwarp_msg(vf, msg, msglen);
break;
case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
- ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, true);
+ ret = i40e_vc_iwarp_qvmap_msg(vf, msg, true);
break;
case VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP:
- ret = i40e_vc_iwarp_qvmap_msg(vf, msg, msglen, false);
+ ret = i40e_vc_iwarp_qvmap_msg(vf, msg, false);
break;
case VIRTCHNL_OP_CONFIG_RSS_KEY:
- ret = i40e_vc_config_rss_key(vf, msg, msglen);
+ ret = i40e_vc_config_rss_key(vf, msg);
break;
case VIRTCHNL_OP_CONFIG_RSS_LUT:
- ret = i40e_vc_config_rss_lut(vf, msg, msglen);
+ ret = i40e_vc_config_rss_lut(vf, msg);
break;
case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
- ret = i40e_vc_get_rss_hena(vf, msg, msglen);
+ ret = i40e_vc_get_rss_hena(vf, msg);
break;
case VIRTCHNL_OP_SET_RSS_HENA:
- ret = i40e_vc_set_rss_hena(vf, msg, msglen);
+ ret = i40e_vc_set_rss_hena(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
- ret = i40e_vc_enable_vlan_stripping(vf, msg, msglen);
+ ret = i40e_vc_enable_vlan_stripping(vf, msg);
break;
case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
- ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen);
+ ret = i40e_vc_disable_vlan_stripping(vf, msg);
break;
case VIRTCHNL_OP_REQUEST_QUEUES:
- ret = i40e_vc_request_queues_msg(vf, msg, msglen);
+ ret = i40e_vc_request_queues_msg(vf, msg);
break;
case VIRTCHNL_OP_ENABLE_CHANNELS:
ret = i40e_vc_add_qch_msg(vf, msg);
@@ -3786,6 +3903,35 @@
}
/**
+ * i40e_validate_vf
+ * @pf: the physical function
+ * @vf_id: VF identifier
+ *
+ * Check that the VF is enabled and the VSI exists.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_validate_vf(struct i40e_pf *pf, int vf_id)
+{
+ struct i40e_vsi *vsi;
+ struct i40e_vf *vf;
+ int ret = 0;
+
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev,
+ "Invalid VF Identifier %d\n", vf_id);
+ ret = -EINVAL;
+ goto err_out;
+ }
+ vf = &pf->vf[vf_id];
+ vsi = i40e_find_vsi_from_id(pf, vf->lan_vsi_id);
+ if (!vsi)
+ ret = -EINVAL;
+err_out:
+ return ret;
+}
+
+/**
* i40e_ndo_set_vf_mac
* @netdev: network interface device structure
* @vf_id: VF identifier
@@ -3805,24 +3951,31 @@
int bkt;
u8 i;
- /* validate the request */
- if (vf_id >= pf->num_alloc_vfs) {
- dev_err(&pf->pdev->dev,
- "Invalid VF Identifier %d\n", vf_id);
- ret = -EINVAL;
- goto error_param;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
}
- vf = &(pf->vf[vf_id]);
+ /* validate the request */
+ ret = i40e_validate_vf(pf, vf_id);
+ if (ret)
+ goto error_param;
+
+ vf = &pf->vf[vf_id];
vsi = pf->vsi[vf->lan_vsi_idx];
/* When the VF is resetting wait until it is done.
* It can take up to 200 milliseconds,
* but wait for up to 300 milliseconds to be safe.
+ * If the VF is indeed in reset, the vsi pointer has
+ * to show on the newly loaded vsi under pf->vsi[id].
*/
for (i = 0; i < 15; i++) {
- if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states))
+ if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
+ if (i > 0)
+ vsi = pf->vsi[vf->lan_vsi_idx];
break;
+ }
msleep(20);
}
if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
@@ -3873,11 +4026,14 @@
mac, vf_id);
}
- /* Force the VF driver stop so it has to reload with new MAC address */
+ /* Force the VF interface down so it has to bring up with new MAC
+ * address
+ */
i40e_vc_disable_vf(vf);
- dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n");
+ dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n");
error_param:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -3924,18 +4080,22 @@
{
u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT);
struct i40e_netdev_priv *np = netdev_priv(netdev);
+ bool allmulti = false, alluni = false;
struct i40e_pf *pf = np->vsi->back;
struct i40e_vsi *vsi;
struct i40e_vf *vf;
int ret = 0;
- /* validate the request */
- if (vf_id >= pf->num_alloc_vfs) {
- dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
- ret = -EINVAL;
- goto error_pvid;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
}
+ /* validate the request */
+ ret = i40e_validate_vf(pf, vf_id);
+ if (ret)
+ goto error_pvid;
+
if ((vlan_id > I40E_MAX_VLANID) || (qos > 7)) {
dev_err(&pf->pdev->dev, "Invalid VF Parameters\n");
ret = -EINVAL;
@@ -3948,7 +4108,7 @@
goto error_pvid;
}
- vf = &(pf->vf[vf_id]);
+ vf = &pf->vf[vf_id];
vsi = pf->vsi[vf->lan_vsi_idx];
if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
@@ -4005,6 +4165,15 @@
}
spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+ /* disable promisc modes in case they were enabled */
+ ret = i40e_config_vf_promiscuous_mode(vf, vf->lan_vsi_id,
+ allmulti, alluni);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Unable to config VF promiscuous mode\n");
+ goto error_pvid;
+ }
+
if (vlan_id || qos)
ret = i40e_vsi_add_pvid(vsi, vlanprio);
else
@@ -4031,6 +4200,12 @@
spin_unlock_bh(&vsi->mac_filter_hash_lock);
+ if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states))
+ alluni = true;
+
+ if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states))
+ allmulti = true;
+
/* Schedule the worker thread to take care of applying changes */
i40e_service_event_schedule(vsi->back);
@@ -4043,9 +4218,17 @@
* default LAN MAC address.
*/
vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
+
+ ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n");
+ goto error_pvid;
+ }
+
ret = 0;
error_pvid:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -4067,20 +4250,24 @@
struct i40e_vf *vf;
int ret = 0;
- /* validate the request */
- if (vf_id >= pf->num_alloc_vfs) {
- dev_err(&pf->pdev->dev, "Invalid VF Identifier %d.\n", vf_id);
- ret = -EINVAL;
- goto error;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
}
+ /* validate the request */
+ ret = i40e_validate_vf(pf, vf_id);
+ if (ret)
+ goto error;
+
if (min_tx_rate) {
dev_err(&pf->pdev->dev, "Invalid min tx rate (%d) (greater than 0) specified for VF %d.\n",
min_tx_rate, vf_id);
- return -EINVAL;
+ ret = -EINVAL;
+ goto error;
}
- vf = &(pf->vf[vf_id]);
+ vf = &pf->vf[vf_id];
vsi = pf->vsi[vf->lan_vsi_idx];
if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
@@ -4095,6 +4282,7 @@
vf->tx_rate = max_tx_rate;
error:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -4115,20 +4303,21 @@
struct i40e_vf *vf;
int ret = 0;
- /* validate the request */
- if (vf_id >= pf->num_alloc_vfs) {
- dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
- ret = -EINVAL;
- goto error_param;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
}
- vf = &(pf->vf[vf_id]);
+ /* validate the request */
+ ret = i40e_validate_vf(pf, vf_id);
+ if (ret)
+ goto error_param;
+
+ vf = &pf->vf[vf_id];
/* first vsi is always the LAN vsi */
vsi = pf->vsi[vf->lan_vsi_idx];
- if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
- dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
- vf_id);
- ret = -EAGAIN;
+ if (!vsi) {
+ ret = -ENOENT;
goto error_param;
}
@@ -4152,6 +4341,7 @@
ret = 0;
error_param:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -4173,6 +4363,11 @@
int abs_vf_id;
int ret = 0;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
+ }
+
/* validate the request */
if (vf_id >= pf->num_alloc_vfs) {
dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4199,7 +4394,7 @@
vf->link_forced = true;
vf->link_up = true;
pfe.event_data.link_event.link_status = true;
- pfe.event_data.link_event.link_speed = I40E_LINK_SPEED_40GB;
+ pfe.event_data.link_event.link_speed = VIRTCHNL_LINK_SPEED_40GB;
break;
case IFLA_VF_LINK_STATE_DISABLE:
vf->link_forced = true;
@@ -4216,6 +4411,7 @@
0, (u8 *)&pfe, sizeof(pfe), NULL);
error_out:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -4237,6 +4433,11 @@
struct i40e_vf *vf;
int ret = 0;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
+ }
+
/* validate the request */
if (vf_id >= pf->num_alloc_vfs) {
dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4270,6 +4471,7 @@
ret = -EIO;
}
out:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
@@ -4288,15 +4490,22 @@
struct i40e_vf *vf;
int ret = 0;
+ if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+ dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+ return -EAGAIN;
+ }
+
/* validate the request */
if (vf_id >= pf->num_alloc_vfs) {
dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
if (pf->flags & I40E_FLAG_MFP_ENABLED) {
dev_err(&pf->pdev->dev, "Trusted VF not supported in MFP mode.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
vf = &pf->vf[vf_id];
@@ -4319,5 +4528,6 @@
}
out:
+ clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
return ret;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index bf67d62..7164b9b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -13,9 +13,11 @@
#define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED 3
#define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED 10
-#define I40E_VLAN_PRIORITY_SHIFT 12
+#define I40E_VLAN_PRIORITY_SHIFT 13
#define I40E_VLAN_MASK 0xFFF
-#define I40E_PRIORITY_MASK 0x7000
+#define I40E_PRIORITY_MASK 0xE000
+
+#define I40E_MAX_VF_PROMISC_FLAGS 3
/* Various queue ctrls */
enum i40e_queue_ctrl {
@@ -97,6 +99,7 @@
unsigned int tx_rate; /* Tx bandwidth limit in Mbps */
bool link_forced;
bool link_up; /* only valid if VF link is forced */
+ bool queues_enabled; /* true if the VF queues are enabled */
bool spoofchk;
u16 num_mac;
u16 num_vlan;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
new file mode 100644
index 0000000..d07e1a8
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -0,0 +1,880 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
+#include <net/xdp.h>
+
+#include "i40e.h"
+#include "i40e_txrx_common.h"
+#include "i40e_xsk.h"
+
+/**
+ * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
+ * @vsi: Current VSI
+ * @umem: UMEM to DMA map
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct device *dev;
+ unsigned int i, j;
+ dma_addr_t dma;
+
+ dev = &pf->pdev->dev;
+ for (i = 0; i < umem->npgs; i++) {
+ dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
+ if (dma_mapping_error(dev, dma))
+ goto out_unmap;
+
+ umem->pages[i].dma = dma;
+ }
+
+ return 0;
+
+out_unmap:
+ for (j = 0; j < i; j++) {
+ dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
+ umem->pages[i].dma = 0;
+ }
+
+ return -1;
+}
+
+/**
+ * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev
+ * @vsi: Current VSI
+ * @umem: UMEM to DMA map
+ **/
+static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct device *dev;
+ unsigned int i;
+
+ dev = &pf->pdev->dev;
+
+ for (i = 0; i < umem->npgs; i++) {
+ dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
+
+ umem->pages[i].dma = 0;
+ }
+}
+
+/**
+ * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
+ * @vsi: Current VSI
+ * @umem: UMEM
+ * @qid: Rx ring to associate UMEM to
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
+ u16 qid)
+{
+ struct net_device *netdev = vsi->netdev;
+ struct xdp_umem_fq_reuse *reuseq;
+ bool if_running;
+ int err;
+
+ if (vsi->type != I40E_VSI_MAIN)
+ return -EINVAL;
+
+ if (qid >= vsi->num_queue_pairs)
+ return -EINVAL;
+
+ if (qid >= netdev->real_num_rx_queues ||
+ qid >= netdev->real_num_tx_queues)
+ return -EINVAL;
+
+ reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
+ if (!reuseq)
+ return -ENOMEM;
+
+ xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
+
+ err = i40e_xsk_umem_dma_map(vsi, umem);
+ if (err)
+ return err;
+
+ set_bit(qid, vsi->af_xdp_zc_qps);
+
+ if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
+
+ if (if_running) {
+ err = i40e_queue_pair_disable(vsi, qid);
+ if (err)
+ return err;
+
+ err = i40e_queue_pair_enable(vsi, qid);
+ if (err)
+ return err;
+
+ /* Kick start the NAPI context so that receiving will start */
+ err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid
+ * @vsi: Current VSI
+ * @qid: Rx ring to associate UMEM to
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
+{
+ struct net_device *netdev = vsi->netdev;
+ struct xdp_umem *umem;
+ bool if_running;
+ int err;
+
+ umem = xdp_get_umem_from_qid(netdev, qid);
+ if (!umem)
+ return -EINVAL;
+
+ if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
+
+ if (if_running) {
+ err = i40e_queue_pair_disable(vsi, qid);
+ if (err)
+ return err;
+ }
+
+ clear_bit(qid, vsi->af_xdp_zc_qps);
+ i40e_xsk_umem_dma_unmap(vsi, umem);
+
+ if (if_running) {
+ err = i40e_queue_pair_enable(vsi, qid);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
+ * @vsi: Current VSI
+ * @umem: UMEM to enable/associate to a ring, or NULL to disable
+ * @qid: Rx ring to (dis)associate UMEM (from)to
+ *
+ * This function enables or disables a UMEM to a certain ring.
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+ u16 qid)
+{
+ return umem ? i40e_xsk_umem_enable(vsi, umem, qid) :
+ i40e_xsk_umem_disable(vsi, qid);
+}
+
+/**
+ * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff
+ * @rx_ring: Rx ring
+ * @xdp: xdp_buff used as input to the XDP program
+ *
+ * This function enables or disables a UMEM to a certain ring.
+ *
+ * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
+ **/
+static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ int err, result = I40E_XDP_PASS;
+ struct i40e_ring *xdp_ring;
+ struct bpf_prog *xdp_prog;
+ u64 offset;
+ u32 act;
+
+ rcu_read_lock();
+ /* NB! xdp_prog will always be !NULL, due to the fact that
+ * this path is enabled by setting an XDP program.
+ */
+ xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
+ offset = xdp->data - xdp->data_hard_start;
+
+ xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
+
+ switch (act) {
+ case XDP_PASS:
+ break;
+ case XDP_TX:
+ xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+ result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+ break;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+ /* fallthrough -- handle aborts by dropping packet */
+ case XDP_DROP:
+ result = I40E_XDP_CONSUMED;
+ break;
+ }
+ rcu_read_unlock();
+ return result;
+}
+
+/**
+ * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer
+ * @rx_ring: Rx ring
+ * @bi: Rx buffer to populate
+ *
+ * This function allocates an Rx buffer. The buffer can come from fill
+ * queue, or via the recycle queue (next_to_alloc).
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ void *addr = bi->addr;
+ u64 handle, hr;
+
+ if (addr) {
+ rx_ring->rx_stats.page_reuse_count++;
+ return true;
+ }
+
+ if (!xsk_umem_peek_addr(umem, &handle)) {
+ rx_ring->rx_stats.alloc_page_failed++;
+ return false;
+ }
+
+ hr = umem->headroom + XDP_PACKET_HEADROOM;
+
+ bi->dma = xdp_umem_get_dma(umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
+
+ xsk_umem_discard_addr(umem);
+ return true;
+}
+
+/**
+ * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer
+ * @rx_ring: Rx ring
+ * @bi: Rx buffer to populate
+ *
+ * This function allocates an Rx buffer. The buffer can come from fill
+ * queue, or via the reuse queue.
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ u64 handle, hr;
+
+ if (!xsk_umem_peek_addr_rq(umem, &handle)) {
+ rx_ring->rx_stats.alloc_page_failed++;
+ return false;
+ }
+
+ handle &= rx_ring->xsk_umem->chunk_mask;
+
+ hr = umem->headroom + XDP_PACKET_HEADROOM;
+
+ bi->dma = xdp_umem_get_dma(umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
+
+ xsk_umem_discard_addr_rq(umem);
+ return true;
+}
+
+static __always_inline bool
+__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
+ bool alloc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi))
+{
+ u16 ntu = rx_ring->next_to_use;
+ union i40e_rx_desc *rx_desc;
+ struct i40e_rx_buffer *bi;
+ bool ok = true;
+
+ rx_desc = I40E_RX_DESC(rx_ring, ntu);
+ bi = &rx_ring->rx_bi[ntu];
+ do {
+ if (!alloc(rx_ring, bi)) {
+ ok = false;
+ goto no_buffers;
+ }
+
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
+ rx_ring->rx_buf_len,
+ DMA_BIDIRECTIONAL);
+
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+
+ rx_desc++;
+ bi++;
+ ntu++;
+
+ if (unlikely(ntu == rx_ring->count)) {
+ rx_desc = I40E_RX_DESC(rx_ring, 0);
+ bi = rx_ring->rx_bi;
+ ntu = 0;
+ }
+
+ rx_desc->wb.qword1.status_error_len = 0;
+ count--;
+ } while (count);
+
+no_buffers:
+ if (rx_ring->next_to_use != ntu)
+ i40e_release_rx_desc(rx_ring, ntu);
+
+ return ok;
+}
+
+/**
+ * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * This function allocates a number of Rx buffers from the reuse queue
+ * or fill ring and places them on the Rx ring.
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
+{
+ return __i40e_alloc_rx_buffers_zc(rx_ring, count,
+ i40e_alloc_buffer_slow_zc);
+}
+
+/**
+ * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * This function allocates a number of Rx buffers from the fill ring
+ * or the internal recycle mechanism and places them on the Rx ring.
+ *
+ * Returns true for a successful allocation, false otherwise
+ **/
+static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
+{
+ return __i40e_alloc_rx_buffers_zc(rx_ring, count,
+ i40e_alloc_buffer_zc);
+}
+
+/**
+ * i40e_get_rx_buffer_zc - Return the current Rx buffer
+ * @rx_ring: Rx ring
+ * @size: The size of the rx buffer (read from descriptor)
+ *
+ * This function returns the current, received Rx buffer, and also
+ * does DMA synchronization. the Rx ring.
+ *
+ * Returns the received Rx buffer
+ **/
+static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
+ const unsigned int size)
+{
+ struct i40e_rx_buffer *bi;
+
+ bi = &rx_ring->rx_bi[rx_ring->next_to_clean];
+
+ /* we are reusing so sync this buffer for CPU use */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ bi->dma, 0,
+ size,
+ DMA_BIDIRECTIONAL);
+
+ return bi;
+}
+
+/**
+ * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer
+ * @rx_ring: Rx ring
+ * @old_bi: The Rx buffer to recycle
+ *
+ * This function recycles a finished Rx buffer, and places it on the
+ * recycle queue (next_to_alloc).
+ **/
+static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *old_bi)
+{
+ struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc];
+ u16 nta = rx_ring->next_to_alloc;
+
+ /* update, and store next to alloc */
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ /* transfer page from old buffer to new buffer */
+ new_bi->dma = old_bi->dma;
+ new_bi->addr = old_bi->addr;
+ new_bi->handle = old_bi->handle;
+
+ old_bi->addr = NULL;
+}
+
+/**
+ * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations
+ * @alloc: Zero-copy allocator
+ * @handle: Buffer handle
+ **/
+void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
+{
+ struct i40e_rx_buffer *bi;
+ struct i40e_ring *rx_ring;
+ u64 hr, mask;
+ u16 nta;
+
+ rx_ring = container_of(alloc, struct i40e_ring, zca);
+ hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
+ mask = rx_ring->xsk_umem->chunk_mask;
+
+ nta = rx_ring->next_to_alloc;
+ bi = &rx_ring->rx_bi[nta];
+
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ handle &= mask;
+
+ bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
+ rx_ring->xsk_umem->headroom);
+}
+
+/**
+ * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
+ * @rx_ring: Rx ring
+ * @bi: Rx buffer
+ * @xdp: xdp_buff
+ *
+ * This functions allocates a new skb from a zero-copy Rx buffer.
+ *
+ * Returns the skb, or NULL on failure.
+ **/
+static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *bi,
+ struct xdp_buff *xdp)
+{
+ unsigned int metasize = xdp->data - xdp->data_meta;
+ unsigned int datasize = xdp->data_end - xdp->data;
+ struct sk_buff *skb;
+
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ xdp->data_end - xdp->data_hard_start,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ return NULL;
+
+ skb_reserve(skb, xdp->data - xdp->data_hard_start);
+ memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+ if (metasize)
+ skb_metadata_set(skb, metasize);
+
+ i40e_reuse_rx_buffer_zc(rx_ring, bi);
+ return skb;
+}
+
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+ u32 ntc = rx_ring->next_to_clean + 1;
+
+ ntc = (ntc < rx_ring->count) ? ntc : 0;
+ rx_ring->next_to_clean = ntc;
+ prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
+/**
+ * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
+ * @rx_ring: Rx ring
+ * @budget: NAPI budget
+ *
+ * Returns amount of work completed
+ **/
+int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
+{
+ unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+ u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+ unsigned int xdp_res, xdp_xmit = 0;
+ bool failure = false;
+ struct sk_buff *skb;
+ struct xdp_buff xdp;
+
+ xdp.rxq = &rx_ring->xdp_rxq;
+
+ while (likely(total_rx_packets < (unsigned int)budget)) {
+ struct i40e_rx_buffer *bi;
+ union i40e_rx_desc *rx_desc;
+ unsigned int size;
+ u64 qword;
+
+ if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
+ failure = failure ||
+ !i40e_alloc_rx_buffers_fast_zc(rx_ring,
+ cleaned_count);
+ cleaned_count = 0;
+ }
+
+ rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
+ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we have
+ * verified the descriptor has been written back.
+ */
+ dma_rmb();
+
+ bi = i40e_clean_programming_status(rx_ring, rx_desc,
+ qword);
+ if (unlikely(bi)) {
+ i40e_reuse_rx_buffer_zc(rx_ring, bi);
+ cleaned_count++;
+ continue;
+ }
+
+ size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+ I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+ if (!size)
+ break;
+
+ bi = i40e_get_rx_buffer_zc(rx_ring, size);
+ xdp.data = bi->addr;
+ xdp.data_meta = xdp.data;
+ xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
+ xdp.data_end = xdp.data + size;
+ xdp.handle = bi->handle;
+
+ xdp_res = i40e_run_xdp_zc(rx_ring, &xdp);
+ if (xdp_res) {
+ if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
+ bi->addr = NULL;
+ } else {
+ i40e_reuse_rx_buffer_zc(rx_ring, bi);
+ }
+
+ total_rx_bytes += size;
+ total_rx_packets++;
+
+ cleaned_count++;
+ i40e_inc_ntc(rx_ring);
+ continue;
+ }
+
+ /* XDP_PASS path */
+
+ /* NB! We are not checking for errors using
+ * i40e_test_staterr with
+ * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
+ * SBP is *not* set in PRT_SBPVSI (default not set).
+ */
+ skb = i40e_construct_skb_zc(rx_ring, bi, &xdp);
+ if (!skb) {
+ rx_ring->rx_stats.alloc_buff_failed++;
+ break;
+ }
+
+ cleaned_count++;
+ i40e_inc_ntc(rx_ring);
+
+ if (eth_skb_pad(skb))
+ continue;
+
+ total_rx_bytes += skb->len;
+ total_rx_packets++;
+
+ i40e_process_skb_fields(rx_ring, rx_desc, skb);
+ napi_gro_receive(&rx_ring->q_vector->napi, skb);
+ }
+
+ i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
+ i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
+
+ if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+ if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+ xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+ else
+ xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+
+ return (int)total_rx_packets;
+ }
+ return failure ? budget : (int)total_rx_packets;
+}
+
+/**
+ * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
+ * @xdp_ring: XDP Tx ring
+ * @budget: NAPI budget
+ *
+ * Returns true if the work is finished.
+ **/
+static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
+{
+ struct i40e_tx_desc *tx_desc = NULL;
+ struct i40e_tx_buffer *tx_bi;
+ bool work_done = true;
+ struct xdp_desc desc;
+ dma_addr_t dma;
+
+ while (budget-- > 0) {
+ if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
+ xdp_ring->tx_stats.tx_busy++;
+ work_done = false;
+ break;
+ }
+
+ if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
+ break;
+
+ dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
+
+ dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
+ DMA_BIDIRECTIONAL);
+
+ tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
+ tx_bi->bytecount = desc.len;
+
+ tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
+ tx_desc->buffer_addr = cpu_to_le64(dma);
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(I40E_TX_DESC_CMD_ICRC
+ | I40E_TX_DESC_CMD_EOP,
+ 0, desc.len, 0);
+
+ xdp_ring->next_to_use++;
+ if (xdp_ring->next_to_use == xdp_ring->count)
+ xdp_ring->next_to_use = 0;
+ }
+
+ if (tx_desc) {
+ /* Request an interrupt for the last frame and bump tail ptr. */
+ tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS <<
+ I40E_TXD_QW1_CMD_SHIFT);
+ i40e_xdp_ring_update_tail(xdp_ring);
+
+ xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+ }
+
+ return !!budget && work_done;
+}
+
+/**
+ * i40e_clean_xdp_tx_buffer - Frees and unmaps an XDP Tx entry
+ * @tx_ring: XDP Tx ring
+ * @tx_bi: Tx buffer info to clean
+ **/
+static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
+ struct i40e_tx_buffer *tx_bi)
+{
+ xdp_return_frame(tx_bi->xdpf);
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_bi, dma),
+ dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_bi, len, 0);
+}
+
+/**
+ * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries
+ * @tx_ring: XDP Tx ring
+ * @tx_bi: Tx buffer info to clean
+ *
+ * Returns true if cleanup/tranmission is done.
+ **/
+bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
+ struct i40e_ring *tx_ring, int napi_budget)
+{
+ unsigned int ntc, total_bytes = 0, budget = vsi->work_limit;
+ u32 i, completed_frames, frames_ready, xsk_frames = 0;
+ struct xdp_umem *umem = tx_ring->xsk_umem;
+ u32 head_idx = i40e_get_head(tx_ring);
+ bool work_done = true, xmit_done;
+ struct i40e_tx_buffer *tx_bi;
+
+ if (head_idx < tx_ring->next_to_clean)
+ head_idx += tx_ring->count;
+ frames_ready = head_idx - tx_ring->next_to_clean;
+
+ if (frames_ready == 0) {
+ goto out_xmit;
+ } else if (frames_ready > budget) {
+ completed_frames = budget;
+ work_done = false;
+ } else {
+ completed_frames = frames_ready;
+ }
+
+ ntc = tx_ring->next_to_clean;
+
+ for (i = 0; i < completed_frames; i++) {
+ tx_bi = &tx_ring->tx_bi[ntc];
+
+ if (tx_bi->xdpf)
+ i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
+ else
+ xsk_frames++;
+
+ tx_bi->xdpf = NULL;
+ total_bytes += tx_bi->bytecount;
+
+ if (++ntc >= tx_ring->count)
+ ntc = 0;
+ }
+
+ tx_ring->next_to_clean += completed_frames;
+ if (unlikely(tx_ring->next_to_clean >= tx_ring->count))
+ tx_ring->next_to_clean -= tx_ring->count;
+
+ if (xsk_frames)
+ xsk_umem_complete_tx(umem, xsk_frames);
+
+ i40e_arm_wb(tx_ring, vsi, budget);
+ i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
+
+out_xmit:
+ if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+ xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+
+ xmit_done = i40e_xmit_zc(tx_ring, budget);
+
+ return work_done && xmit_done;
+}
+
+/**
+ * i40e_xsk_wakeup - Implements the ndo_xsk_wakeup
+ * @dev: the netdevice
+ * @queue_id: queue id to wake up
+ * @flags: ignored in our case since we have Rx and Tx in the same NAPI.
+ *
+ * Returns <0 for errors, 0 otherwise.
+ **/
+int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
+{
+ struct i40e_netdev_priv *np = netdev_priv(dev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_ring *ring;
+
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return -ENETDOWN;
+
+ if (!i40e_enabled_xdp_vsi(vsi))
+ return -ENXIO;
+
+ if (queue_id >= vsi->num_queue_pairs)
+ return -ENXIO;
+
+ if (!vsi->xdp_rings[queue_id]->xsk_umem)
+ return -ENXIO;
+
+ ring = vsi->xdp_rings[queue_id];
+
+ /* The idea here is that if NAPI is running, mark a miss, so
+ * it will run again. If not, trigger an interrupt and
+ * schedule the NAPI from interrupt context. If NAPI would be
+ * scheduled here, the interrupt affinity would not be
+ * honored.
+ */
+ if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi))
+ i40e_force_wb(vsi, ring->q_vector);
+
+ return 0;
+}
+
+void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
+{
+ u16 i;
+
+ for (i = 0; i < rx_ring->count; i++) {
+ struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+
+ if (!rx_bi->addr)
+ continue;
+
+ xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
+ rx_bi->addr = NULL;
+ }
+}
+
+/**
+ * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown
+ * @xdp_ring: XDP Tx ring
+ **/
+void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
+{
+ u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
+ struct xdp_umem *umem = tx_ring->xsk_umem;
+ struct i40e_tx_buffer *tx_bi;
+ u32 xsk_frames = 0;
+
+ while (ntc != ntu) {
+ tx_bi = &tx_ring->tx_bi[ntc];
+
+ if (tx_bi->xdpf)
+ i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
+ else
+ xsk_frames++;
+
+ tx_bi->xdpf = NULL;
+
+ ntc++;
+ if (ntc >= tx_ring->count)
+ ntc = 0;
+ }
+
+ if (xsk_frames)
+ xsk_umem_complete_tx(umem, xsk_frames);
+}
+
+/**
+ * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached
+ * @vsi: vsi
+ *
+ * Returns true if any of the Rx rings has an AF_XDP UMEM attached
+ **/
+bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
+{
+ struct net_device *netdev = vsi->netdev;
+ int i;
+
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ if (xdp_get_umem_from_qid(netdev, i))
+ return true;
+ }
+
+ return false;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
new file mode 100644
index 0000000..9ed59c1
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Intel Corporation. */
+
+#ifndef _I40E_XSK_H_
+#define _I40E_XSK_H_
+
+struct i40e_vsi;
+struct xdp_umem;
+struct zero_copy_allocator;
+
+int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
+int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
+int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+ u16 qid);
+void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
+int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
+
+bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
+ struct i40e_ring *tx_ring, int napi_budget);
+int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+
+#endif /* _I40E_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile
deleted file mode 100644
index 3c5c6e9..0000000
--- a/drivers/net/ethernet/intel/i40evf/Makefile
+++ /dev/null
@@ -1,16 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Copyright(c) 2013 - 2018 Intel Corporation.
-
-#
-## Makefile for the Intel(R) 40GbE VF driver
-#
-#
-
-ccflags-y += -I$(src)
-subdir-ccflags-y += -I$(src)
-
-obj-$(CONFIG_I40EVF) += i40evf.o
-
-i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \
- i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o
-
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
deleted file mode 100644
index 1f264b9..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
+++ /dev/null
@@ -1,136 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_ADMINQ_H_
-#define _I40E_ADMINQ_H_
-
-#include "i40e_osdep.h"
-#include "i40e_status.h"
-#include "i40e_adminq_cmd.h"
-
-#define I40E_ADMINQ_DESC(R, i) \
- (&(((struct i40e_aq_desc *)((R).desc_buf.va))[i]))
-
-#define I40E_ADMINQ_DESC_ALIGNMENT 4096
-
-struct i40e_adminq_ring {
- struct i40e_virt_mem dma_head; /* space for dma structures */
- struct i40e_dma_mem desc_buf; /* descriptor ring memory */
- struct i40e_virt_mem cmd_buf; /* command buffer memory */
-
- union {
- struct i40e_dma_mem *asq_bi;
- struct i40e_dma_mem *arq_bi;
- } r;
-
- u16 count; /* Number of descriptors */
- u16 rx_buf_len; /* Admin Receive Queue buffer length */
-
- /* used for interrupt processing */
- u16 next_to_use;
- u16 next_to_clean;
-
- /* used for queue tracking */
- u32 head;
- u32 tail;
- u32 len;
- u32 bah;
- u32 bal;
-};
-
-/* ASQ transaction details */
-struct i40e_asq_cmd_details {
- void *callback; /* cast from type I40E_ADMINQ_CALLBACK */
- u64 cookie;
- u16 flags_ena;
- u16 flags_dis;
- bool async;
- bool postpone;
- struct i40e_aq_desc *wb_desc;
-};
-
-#define I40E_ADMINQ_DETAILS(R, i) \
- (&(((struct i40e_asq_cmd_details *)((R).cmd_buf.va))[i]))
-
-/* ARQ event information */
-struct i40e_arq_event_info {
- struct i40e_aq_desc desc;
- u16 msg_len;
- u16 buf_len;
- u8 *msg_buf;
-};
-
-/* Admin Queue information */
-struct i40e_adminq_info {
- struct i40e_adminq_ring arq; /* receive queue */
- struct i40e_adminq_ring asq; /* send queue */
- u32 asq_cmd_timeout; /* send queue cmd write back timeout*/
- u16 num_arq_entries; /* receive queue depth */
- u16 num_asq_entries; /* send queue depth */
- u16 arq_buf_size; /* receive queue buffer size */
- u16 asq_buf_size; /* send queue buffer size */
- u16 fw_maj_ver; /* firmware major version */
- u16 fw_min_ver; /* firmware minor version */
- u32 fw_build; /* firmware build number */
- u16 api_maj_ver; /* api major version */
- u16 api_min_ver; /* api minor version */
-
- struct mutex asq_mutex; /* Send queue lock */
- struct mutex arq_mutex; /* Receive queue lock */
-
- /* last status values on send and receive queues */
- enum i40e_admin_queue_err asq_last_status;
- enum i40e_admin_queue_err arq_last_status;
-};
-
-/**
- * i40e_aq_rc_to_posix - convert errors to user-land codes
- * aq_ret: AdminQ handler error code can override aq_rc
- * aq_rc: AdminQ firmware error code to convert
- **/
-static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
-{
- int aq_to_posix[] = {
- 0, /* I40E_AQ_RC_OK */
- -EPERM, /* I40E_AQ_RC_EPERM */
- -ENOENT, /* I40E_AQ_RC_ENOENT */
- -ESRCH, /* I40E_AQ_RC_ESRCH */
- -EINTR, /* I40E_AQ_RC_EINTR */
- -EIO, /* I40E_AQ_RC_EIO */
- -ENXIO, /* I40E_AQ_RC_ENXIO */
- -E2BIG, /* I40E_AQ_RC_E2BIG */
- -EAGAIN, /* I40E_AQ_RC_EAGAIN */
- -ENOMEM, /* I40E_AQ_RC_ENOMEM */
- -EACCES, /* I40E_AQ_RC_EACCES */
- -EFAULT, /* I40E_AQ_RC_EFAULT */
- -EBUSY, /* I40E_AQ_RC_EBUSY */
- -EEXIST, /* I40E_AQ_RC_EEXIST */
- -EINVAL, /* I40E_AQ_RC_EINVAL */
- -ENOTTY, /* I40E_AQ_RC_ENOTTY */
- -ENOSPC, /* I40E_AQ_RC_ENOSPC */
- -ENOSYS, /* I40E_AQ_RC_ENOSYS */
- -ERANGE, /* I40E_AQ_RC_ERANGE */
- -EPIPE, /* I40E_AQ_RC_EFLUSHED */
- -ESPIPE, /* I40E_AQ_RC_BAD_ADDR */
- -EROFS, /* I40E_AQ_RC_EMODE */
- -EFBIG, /* I40E_AQ_RC_EFBIG */
- };
-
- /* aq_rc is invalid if AQ timed out */
- if (aq_ret == I40E_ERR_ADMIN_QUEUE_TIMEOUT)
- return -EAGAIN;
-
- if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0]))))
- return -ERANGE;
-
- return aq_to_posix[aq_rc];
-}
-
-/* general information */
-#define I40E_AQ_LARGE_BUF 512
-#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */
-
-void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
- u16 opcode);
-
-#endif /* _I40E_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
deleted file mode 100644
index 5fd8529..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ /dev/null
@@ -1,2717 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_ADMINQ_CMD_H_
-#define _I40E_ADMINQ_CMD_H_
-
-/* This header file defines the i40e Admin Queue commands and is shared between
- * i40e Firmware and Software.
- *
- * This file needs to comply with the Linux Kernel coding style.
- */
-
-#define I40E_FW_API_VERSION_MAJOR 0x0001
-#define I40E_FW_API_VERSION_MINOR_X722 0x0005
-#define I40E_FW_API_VERSION_MINOR_X710 0x0007
-
-#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
- I40E_FW_API_VERSION_MINOR_X710 : \
- I40E_FW_API_VERSION_MINOR_X722)
-
-/* API version 1.7 implements additional link and PHY-specific APIs */
-#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
-
-struct i40e_aq_desc {
- __le16 flags;
- __le16 opcode;
- __le16 datalen;
- __le16 retval;
- __le32 cookie_high;
- __le32 cookie_low;
- union {
- struct {
- __le32 param0;
- __le32 param1;
- __le32 param2;
- __le32 param3;
- } internal;
- struct {
- __le32 param0;
- __le32 param1;
- __le32 addr_high;
- __le32 addr_low;
- } external;
- u8 raw[16];
- } params;
-};
-
-/* Flags sub-structure
- * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-/* command flags and offsets*/
-#define I40E_AQ_FLAG_DD_SHIFT 0
-#define I40E_AQ_FLAG_CMP_SHIFT 1
-#define I40E_AQ_FLAG_ERR_SHIFT 2
-#define I40E_AQ_FLAG_VFE_SHIFT 3
-#define I40E_AQ_FLAG_LB_SHIFT 9
-#define I40E_AQ_FLAG_RD_SHIFT 10
-#define I40E_AQ_FLAG_VFC_SHIFT 11
-#define I40E_AQ_FLAG_BUF_SHIFT 12
-#define I40E_AQ_FLAG_SI_SHIFT 13
-#define I40E_AQ_FLAG_EI_SHIFT 14
-#define I40E_AQ_FLAG_FE_SHIFT 15
-
-#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */
-#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */
-#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */
-#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */
-#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */
-#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */
-#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */
-#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
-#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */
-#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */
-#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */
-
-/* error codes */
-enum i40e_admin_queue_err {
- I40E_AQ_RC_OK = 0, /* success */
- I40E_AQ_RC_EPERM = 1, /* Operation not permitted */
- I40E_AQ_RC_ENOENT = 2, /* No such element */
- I40E_AQ_RC_ESRCH = 3, /* Bad opcode */
- I40E_AQ_RC_EINTR = 4, /* operation interrupted */
- I40E_AQ_RC_EIO = 5, /* I/O error */
- I40E_AQ_RC_ENXIO = 6, /* No such resource */
- I40E_AQ_RC_E2BIG = 7, /* Arg too long */
- I40E_AQ_RC_EAGAIN = 8, /* Try again */
- I40E_AQ_RC_ENOMEM = 9, /* Out of memory */
- I40E_AQ_RC_EACCES = 10, /* Permission denied */
- I40E_AQ_RC_EFAULT = 11, /* Bad address */
- I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */
- I40E_AQ_RC_EEXIST = 13, /* object already exists */
- I40E_AQ_RC_EINVAL = 14, /* Invalid argument */
- I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */
- I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */
- I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */
- I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */
- I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */
- I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */
- I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */
- I40E_AQ_RC_EFBIG = 22, /* File too large */
-};
-
-/* Admin Queue command opcodes */
-enum i40e_admin_queue_opc {
- /* aq commands */
- i40e_aqc_opc_get_version = 0x0001,
- i40e_aqc_opc_driver_version = 0x0002,
- i40e_aqc_opc_queue_shutdown = 0x0003,
- i40e_aqc_opc_set_pf_context = 0x0004,
-
- /* resource ownership */
- i40e_aqc_opc_request_resource = 0x0008,
- i40e_aqc_opc_release_resource = 0x0009,
-
- i40e_aqc_opc_list_func_capabilities = 0x000A,
- i40e_aqc_opc_list_dev_capabilities = 0x000B,
-
- /* Proxy commands */
- i40e_aqc_opc_set_proxy_config = 0x0104,
- i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105,
-
- /* LAA */
- i40e_aqc_opc_mac_address_read = 0x0107,
- i40e_aqc_opc_mac_address_write = 0x0108,
-
- /* PXE */
- i40e_aqc_opc_clear_pxe_mode = 0x0110,
-
- /* WoL commands */
- i40e_aqc_opc_set_wol_filter = 0x0120,
- i40e_aqc_opc_get_wake_reason = 0x0121,
-
- /* internal switch commands */
- i40e_aqc_opc_get_switch_config = 0x0200,
- i40e_aqc_opc_add_statistics = 0x0201,
- i40e_aqc_opc_remove_statistics = 0x0202,
- i40e_aqc_opc_set_port_parameters = 0x0203,
- i40e_aqc_opc_get_switch_resource_alloc = 0x0204,
- i40e_aqc_opc_set_switch_config = 0x0205,
- i40e_aqc_opc_rx_ctl_reg_read = 0x0206,
- i40e_aqc_opc_rx_ctl_reg_write = 0x0207,
-
- i40e_aqc_opc_add_vsi = 0x0210,
- i40e_aqc_opc_update_vsi_parameters = 0x0211,
- i40e_aqc_opc_get_vsi_parameters = 0x0212,
-
- i40e_aqc_opc_add_pv = 0x0220,
- i40e_aqc_opc_update_pv_parameters = 0x0221,
- i40e_aqc_opc_get_pv_parameters = 0x0222,
-
- i40e_aqc_opc_add_veb = 0x0230,
- i40e_aqc_opc_update_veb_parameters = 0x0231,
- i40e_aqc_opc_get_veb_parameters = 0x0232,
-
- i40e_aqc_opc_delete_element = 0x0243,
-
- i40e_aqc_opc_add_macvlan = 0x0250,
- i40e_aqc_opc_remove_macvlan = 0x0251,
- i40e_aqc_opc_add_vlan = 0x0252,
- i40e_aqc_opc_remove_vlan = 0x0253,
- i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254,
- i40e_aqc_opc_add_tag = 0x0255,
- i40e_aqc_opc_remove_tag = 0x0256,
- i40e_aqc_opc_add_multicast_etag = 0x0257,
- i40e_aqc_opc_remove_multicast_etag = 0x0258,
- i40e_aqc_opc_update_tag = 0x0259,
- i40e_aqc_opc_add_control_packet_filter = 0x025A,
- i40e_aqc_opc_remove_control_packet_filter = 0x025B,
- i40e_aqc_opc_add_cloud_filters = 0x025C,
- i40e_aqc_opc_remove_cloud_filters = 0x025D,
- i40e_aqc_opc_clear_wol_switch_filters = 0x025E,
-
- i40e_aqc_opc_add_mirror_rule = 0x0260,
- i40e_aqc_opc_delete_mirror_rule = 0x0261,
-
- /* Dynamic Device Personalization */
- i40e_aqc_opc_write_personalization_profile = 0x0270,
- i40e_aqc_opc_get_personalization_profile_list = 0x0271,
-
- /* DCB commands */
- i40e_aqc_opc_dcb_ignore_pfc = 0x0301,
- i40e_aqc_opc_dcb_updated = 0x0302,
- i40e_aqc_opc_set_dcb_parameters = 0x0303,
-
- /* TX scheduler */
- i40e_aqc_opc_configure_vsi_bw_limit = 0x0400,
- i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406,
- i40e_aqc_opc_configure_vsi_tc_bw = 0x0407,
- i40e_aqc_opc_query_vsi_bw_config = 0x0408,
- i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A,
- i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410,
-
- i40e_aqc_opc_enable_switching_comp_ets = 0x0413,
- i40e_aqc_opc_modify_switching_comp_ets = 0x0414,
- i40e_aqc_opc_disable_switching_comp_ets = 0x0415,
- i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416,
- i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417,
- i40e_aqc_opc_query_switching_comp_ets_config = 0x0418,
- i40e_aqc_opc_query_port_ets_config = 0x0419,
- i40e_aqc_opc_query_switching_comp_bw_config = 0x041A,
- i40e_aqc_opc_suspend_port_tx = 0x041B,
- i40e_aqc_opc_resume_port_tx = 0x041C,
- i40e_aqc_opc_configure_partition_bw = 0x041D,
- /* hmc */
- i40e_aqc_opc_query_hmc_resource_profile = 0x0500,
- i40e_aqc_opc_set_hmc_resource_profile = 0x0501,
-
- /* phy commands*/
- i40e_aqc_opc_get_phy_abilities = 0x0600,
- i40e_aqc_opc_set_phy_config = 0x0601,
- i40e_aqc_opc_set_mac_config = 0x0603,
- i40e_aqc_opc_set_link_restart_an = 0x0605,
- i40e_aqc_opc_get_link_status = 0x0607,
- i40e_aqc_opc_set_phy_int_mask = 0x0613,
- i40e_aqc_opc_get_local_advt_reg = 0x0614,
- i40e_aqc_opc_set_local_advt_reg = 0x0615,
- i40e_aqc_opc_get_partner_advt = 0x0616,
- i40e_aqc_opc_set_lb_modes = 0x0618,
- i40e_aqc_opc_get_phy_wol_caps = 0x0621,
- i40e_aqc_opc_set_phy_debug = 0x0622,
- i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
- i40e_aqc_opc_run_phy_activity = 0x0626,
- i40e_aqc_opc_set_phy_register = 0x0628,
- i40e_aqc_opc_get_phy_register = 0x0629,
-
- /* NVM commands */
- i40e_aqc_opc_nvm_read = 0x0701,
- i40e_aqc_opc_nvm_erase = 0x0702,
- i40e_aqc_opc_nvm_update = 0x0703,
- i40e_aqc_opc_nvm_config_read = 0x0704,
- i40e_aqc_opc_nvm_config_write = 0x0705,
- i40e_aqc_opc_oem_post_update = 0x0720,
- i40e_aqc_opc_thermal_sensor = 0x0721,
-
- /* virtualization commands */
- i40e_aqc_opc_send_msg_to_pf = 0x0801,
- i40e_aqc_opc_send_msg_to_vf = 0x0802,
- i40e_aqc_opc_send_msg_to_peer = 0x0803,
-
- /* alternate structure */
- i40e_aqc_opc_alternate_write = 0x0900,
- i40e_aqc_opc_alternate_write_indirect = 0x0901,
- i40e_aqc_opc_alternate_read = 0x0902,
- i40e_aqc_opc_alternate_read_indirect = 0x0903,
- i40e_aqc_opc_alternate_write_done = 0x0904,
- i40e_aqc_opc_alternate_set_mode = 0x0905,
- i40e_aqc_opc_alternate_clear_port = 0x0906,
-
- /* LLDP commands */
- i40e_aqc_opc_lldp_get_mib = 0x0A00,
- i40e_aqc_opc_lldp_update_mib = 0x0A01,
- i40e_aqc_opc_lldp_add_tlv = 0x0A02,
- i40e_aqc_opc_lldp_update_tlv = 0x0A03,
- i40e_aqc_opc_lldp_delete_tlv = 0x0A04,
- i40e_aqc_opc_lldp_stop = 0x0A05,
- i40e_aqc_opc_lldp_start = 0x0A06,
-
- /* Tunnel commands */
- i40e_aqc_opc_add_udp_tunnel = 0x0B00,
- i40e_aqc_opc_del_udp_tunnel = 0x0B01,
- i40e_aqc_opc_set_rss_key = 0x0B02,
- i40e_aqc_opc_set_rss_lut = 0x0B03,
- i40e_aqc_opc_get_rss_key = 0x0B04,
- i40e_aqc_opc_get_rss_lut = 0x0B05,
-
- /* Async Events */
- i40e_aqc_opc_event_lan_overflow = 0x1001,
-
- /* OEM commands */
- i40e_aqc_opc_oem_parameter_change = 0xFE00,
- i40e_aqc_opc_oem_device_status_change = 0xFE01,
- i40e_aqc_opc_oem_ocsd_initialize = 0xFE02,
- i40e_aqc_opc_oem_ocbb_initialize = 0xFE03,
-
- /* debug commands */
- i40e_aqc_opc_debug_read_reg = 0xFF03,
- i40e_aqc_opc_debug_write_reg = 0xFF04,
- i40e_aqc_opc_debug_modify_reg = 0xFF07,
- i40e_aqc_opc_debug_dump_internals = 0xFF08,
-};
-
-/* command structures and indirect data structures */
-
-/* Structure naming conventions:
- * - no suffix for direct command descriptor structures
- * - _data for indirect sent data
- * - _resp for indirect return data (data which is both will use _data)
- * - _completion for direct return data
- * - _element_ for repeated elements (may also be _data or _resp)
- *
- * Command structures are expected to overlay the params.raw member of the basic
- * descriptor, and as such cannot exceed 16 bytes in length.
- */
-
-/* This macro is used to generate a compilation error if a structure
- * is not exactly the correct length. It gives a divide by zero error if the
- * structure is not of the correct size, otherwise it creates an enum that is
- * never used.
- */
-#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \
- { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) }
-
-/* This macro is used extensively to ensure that command structures are 16
- * bytes in length as they have to map to the raw array of that size.
- */
-#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X)
-
-/* internal (0x00XX) commands */
-
-/* Get version (direct 0x0001) */
-struct i40e_aqc_get_version {
- __le32 rom_ver;
- __le32 fw_build;
- __le16 fw_major;
- __le16 fw_minor;
- __le16 api_major;
- __le16 api_minor;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version);
-
-/* Send driver version (indirect 0x0002) */
-struct i40e_aqc_driver_version {
- u8 driver_major_ver;
- u8 driver_minor_ver;
- u8 driver_build_ver;
- u8 driver_subbuild_ver;
- u8 reserved[4];
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version);
-
-/* Queue Shutdown (direct 0x0003) */
-struct i40e_aqc_queue_shutdown {
- __le32 driver_unloading;
-#define I40E_AQ_DRIVER_UNLOADING 0x1
- u8 reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown);
-
-/* Set PF context (0x0004, direct) */
-struct i40e_aqc_set_pf_context {
- u8 pf_id;
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
-
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-#define I40E_AQ_RESOURCE_NVM 1
-#define I40E_AQ_RESOURCE_SDP 2
-#define I40E_AQ_RESOURCE_ACCESS_READ 1
-#define I40E_AQ_RESOURCE_ACCESS_WRITE 2
-#define I40E_AQ_RESOURCE_NVM_READ_TIMEOUT 3000
-#define I40E_AQ_RESOURCE_NVM_WRITE_TIMEOUT 180000
-
-struct i40e_aqc_request_resource {
- __le16 resource_id;
- __le16 access_type;
- __le32 timeout;
- __le32 resource_number;
- u8 reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource);
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct i40e_aqc_list_capabilites {
- u8 command_flags;
-#define I40E_AQ_LIST_CAP_PF_INDEX_EN 1
- u8 pf_index;
- u8 reserved[2];
- __le32 count;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites);
-
-struct i40e_aqc_list_capabilities_element_resp {
- __le16 id;
- u8 major_rev;
- u8 minor_rev;
- __le32 number;
- __le32 logical_id;
- __le32 phys_id;
- u8 reserved[16];
-};
-
-/* list of caps */
-
-#define I40E_AQ_CAP_ID_SWITCH_MODE 0x0001
-#define I40E_AQ_CAP_ID_MNG_MODE 0x0002
-#define I40E_AQ_CAP_ID_NPAR_ACTIVE 0x0003
-#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004
-#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005
-#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006
-#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008
-#define I40E_AQ_CAP_ID_SRIOV 0x0012
-#define I40E_AQ_CAP_ID_VF 0x0013
-#define I40E_AQ_CAP_ID_VMDQ 0x0014
-#define I40E_AQ_CAP_ID_8021QBG 0x0015
-#define I40E_AQ_CAP_ID_8021QBR 0x0016
-#define I40E_AQ_CAP_ID_VSI 0x0017
-#define I40E_AQ_CAP_ID_DCB 0x0018
-#define I40E_AQ_CAP_ID_FCOE 0x0021
-#define I40E_AQ_CAP_ID_ISCSI 0x0022
-#define I40E_AQ_CAP_ID_RSS 0x0040
-#define I40E_AQ_CAP_ID_RXQ 0x0041
-#define I40E_AQ_CAP_ID_TXQ 0x0042
-#define I40E_AQ_CAP_ID_MSIX 0x0043
-#define I40E_AQ_CAP_ID_VF_MSIX 0x0044
-#define I40E_AQ_CAP_ID_FLOW_DIRECTOR 0x0045
-#define I40E_AQ_CAP_ID_1588 0x0046
-#define I40E_AQ_CAP_ID_IWARP 0x0051
-#define I40E_AQ_CAP_ID_LED 0x0061
-#define I40E_AQ_CAP_ID_SDP 0x0062
-#define I40E_AQ_CAP_ID_MDIO 0x0063
-#define I40E_AQ_CAP_ID_WSR_PROT 0x0064
-#define I40E_AQ_CAP_ID_NVM_MGMT 0x0080
-#define I40E_AQ_CAP_ID_FLEX10 0x00F1
-#define I40E_AQ_CAP_ID_CEM 0x00F2
-
-/* Set CPPM Configuration (direct 0x0103) */
-struct i40e_aqc_cppm_configuration {
- __le16 command_flags;
-#define I40E_AQ_CPPM_EN_LTRC 0x0800
-#define I40E_AQ_CPPM_EN_DMCTH 0x1000
-#define I40E_AQ_CPPM_EN_DMCTLX 0x2000
-#define I40E_AQ_CPPM_EN_HPTC 0x4000
-#define I40E_AQ_CPPM_EN_DMARC 0x8000
- __le16 ttlx;
- __le32 dmacr;
- __le16 dmcth;
- u8 hptc;
- u8 reserved;
- __le32 pfltrc;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_cppm_configuration);
-
-/* Set ARP Proxy command / response (indirect 0x0104) */
-struct i40e_aqc_arp_proxy_data {
- __le16 command_flags;
-#define I40E_AQ_ARP_INIT_IPV4 0x0800
-#define I40E_AQ_ARP_UNSUP_CTL 0x1000
-#define I40E_AQ_ARP_ENA 0x2000
-#define I40E_AQ_ARP_ADD_IPV4 0x4000
-#define I40E_AQ_ARP_DEL_IPV4 0x8000
- __le16 table_id;
- __le32 enabled_offloads;
-#define I40E_AQ_ARP_DIRECTED_OFFLOAD_ENABLE 0x00000020
-#define I40E_AQ_ARP_OFFLOAD_ENABLE 0x00000800
- __le32 ip_addr;
- u8 mac_addr[6];
- u8 reserved[2];
-};
-
-I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data);
-
-/* Set NS Proxy Table Entry Command (indirect 0x0105) */
-struct i40e_aqc_ns_proxy_data {
- __le16 table_idx_mac_addr_0;
- __le16 table_idx_mac_addr_1;
- __le16 table_idx_ipv6_0;
- __le16 table_idx_ipv6_1;
- __le16 control;
-#define I40E_AQ_NS_PROXY_ADD_0 0x0001
-#define I40E_AQ_NS_PROXY_DEL_0 0x0002
-#define I40E_AQ_NS_PROXY_ADD_1 0x0004
-#define I40E_AQ_NS_PROXY_DEL_1 0x0008
-#define I40E_AQ_NS_PROXY_ADD_IPV6_0 0x0010
-#define I40E_AQ_NS_PROXY_DEL_IPV6_0 0x0020
-#define I40E_AQ_NS_PROXY_ADD_IPV6_1 0x0040
-#define I40E_AQ_NS_PROXY_DEL_IPV6_1 0x0080
-#define I40E_AQ_NS_PROXY_COMMAND_SEQ 0x0100
-#define I40E_AQ_NS_PROXY_INIT_IPV6_TBL 0x0200
-#define I40E_AQ_NS_PROXY_INIT_MAC_TBL 0x0400
-#define I40E_AQ_NS_PROXY_OFFLOAD_ENABLE 0x0800
-#define I40E_AQ_NS_PROXY_DIRECTED_OFFLOAD_ENABLE 0x1000
- u8 mac_addr_0[6];
- u8 mac_addr_1[6];
- u8 local_mac_addr[6];
- u8 ipv6_addr_0[16]; /* Warning! spec specifies BE byte order */
- u8 ipv6_addr_1[16];
-};
-
-I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data);
-
-/* Manage LAA Command (0x0106) - obsolete */
-struct i40e_aqc_mng_laa {
- __le16 command_flags;
-#define I40E_AQ_LAA_FLAG_WR 0x8000
- u8 reserved[2];
- __le32 sal;
- __le16 sah;
- u8 reserved2[6];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa);
-
-/* Manage MAC Address Read Command (indirect 0x0107) */
-struct i40e_aqc_mac_address_read {
- __le16 command_flags;
-#define I40E_AQC_LAN_ADDR_VALID 0x10
-#define I40E_AQC_SAN_ADDR_VALID 0x20
-#define I40E_AQC_PORT_ADDR_VALID 0x40
-#define I40E_AQC_WOL_ADDR_VALID 0x80
-#define I40E_AQC_MC_MAG_EN_VALID 0x100
-#define I40E_AQC_ADDR_VALID_MASK 0x3F0
- u8 reserved[6];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_read);
-
-struct i40e_aqc_mac_address_read_data {
- u8 pf_lan_mac[6];
- u8 pf_san_mac[6];
- u8 port_mac[6];
- u8 pf_wol_mac[6];
-};
-
-I40E_CHECK_STRUCT_LEN(24, i40e_aqc_mac_address_read_data);
-
-/* Manage MAC Address Write Command (0x0108) */
-struct i40e_aqc_mac_address_write {
- __le16 command_flags;
-#define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000
-#define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000
-#define I40E_AQC_WRITE_TYPE_PORT 0x8000
-#define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG 0xC000
-#define I40E_AQC_WRITE_TYPE_MASK 0xC000
-
- __le16 mac_sah;
- __le32 mac_sal;
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_write);
-
-/* PXE commands (0x011x) */
-
-/* Clear PXE Command and response (direct 0x0110) */
-struct i40e_aqc_clear_pxe {
- u8 rx_cnt;
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
-
-/* Set WoL Filter (0x0120) */
-
-struct i40e_aqc_set_wol_filter {
- __le16 filter_index;
-#define I40E_AQC_MAX_NUM_WOL_FILTERS 8
-#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15
-#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \
- I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
-
-#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0
-#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \
- I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
- __le16 cmd_flags;
-#define I40E_AQC_SET_WOL_FILTER 0x8000
-#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000
-#define I40E_AQC_SET_WOL_FILTER_WOL_PRESERVE_ON_PFR 0x2000
-#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0
-#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1
- __le16 valid_flags;
-#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000
-#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000
- u8 reserved[2];
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
-
-struct i40e_aqc_set_wol_filter_data {
- u8 filter[128];
- u8 mask[16];
-};
-
-I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
-
-/* Get Wake Reason (0x0121) */
-
-struct i40e_aqc_get_wake_reason_completion {
- u8 reserved_1[2];
- __le16 wake_reason;
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
- I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8
-#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \
- I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
- u8 reserved_2[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
-
-/* Switch configuration commands (0x02xx) */
-
-/* Used by many indirect commands that only pass an seid and a buffer in the
- * command
- */
-struct i40e_aqc_switch_seid {
- __le16 seid;
- u8 reserved[6];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_switch_seid);
-
-/* Get Switch Configuration command (indirect 0x0200)
- * uses i40e_aqc_switch_seid for the descriptor
- */
-struct i40e_aqc_get_switch_config_header_resp {
- __le16 num_reported;
- __le16 num_total;
- u8 reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp);
-
-struct i40e_aqc_switch_config_element_resp {
- u8 element_type;
-#define I40E_AQ_SW_ELEM_TYPE_MAC 1
-#define I40E_AQ_SW_ELEM_TYPE_PF 2
-#define I40E_AQ_SW_ELEM_TYPE_VF 3
-#define I40E_AQ_SW_ELEM_TYPE_EMP 4
-#define I40E_AQ_SW_ELEM_TYPE_BMC 5
-#define I40E_AQ_SW_ELEM_TYPE_PV 16
-#define I40E_AQ_SW_ELEM_TYPE_VEB 17
-#define I40E_AQ_SW_ELEM_TYPE_PA 18
-#define I40E_AQ_SW_ELEM_TYPE_VSI 19
- u8 revision;
-#define I40E_AQ_SW_ELEM_REV_1 1
- __le16 seid;
- __le16 uplink_seid;
- __le16 downlink_seid;
- u8 reserved[3];
- u8 connection_type;
-#define I40E_AQ_CONN_TYPE_REGULAR 0x1
-#define I40E_AQ_CONN_TYPE_DEFAULT 0x2
-#define I40E_AQ_CONN_TYPE_CASCADED 0x3
- __le16 scheduler_id;
- __le16 element_info;
-};
-
-I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp);
-
-/* Get Switch Configuration (indirect 0x0200)
- * an array of elements are returned in the response buffer
- * the first in the array is the header, remainder are elements
- */
-struct i40e_aqc_get_switch_config_resp {
- struct i40e_aqc_get_switch_config_header_resp header;
- struct i40e_aqc_switch_config_element_resp element[1];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp);
-
-/* Add Statistics (direct 0x0201)
- * Remove Statistics (direct 0x0202)
- */
-struct i40e_aqc_add_remove_statistics {
- __le16 seid;
- __le16 vlan;
- __le16 stat_index;
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_statistics);
-
-/* Set Port Parameters command (direct 0x0203) */
-struct i40e_aqc_set_port_parameters {
- __le16 command_flags;
-#define I40E_AQ_SET_P_PARAMS_SAVE_BAD_PACKETS 1
-#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */
-#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4
- __le16 bad_frame_vsi;
-#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0
-#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF
- __le16 default_seid; /* reserved for command */
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_port_parameters);
-
-/* Get Switch Resource Allocation (indirect 0x0204) */
-struct i40e_aqc_get_switch_resource_alloc {
- u8 num_entries; /* reserved for command */
- u8 reserved[7];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_resource_alloc);
-
-/* expect an array of these structs in the response buffer */
-struct i40e_aqc_switch_resource_alloc_element_resp {
- u8 resource_type;
-#define I40E_AQ_RESOURCE_TYPE_VEB 0x0
-#define I40E_AQ_RESOURCE_TYPE_VSI 0x1
-#define I40E_AQ_RESOURCE_TYPE_MACADDR 0x2
-#define I40E_AQ_RESOURCE_TYPE_STAG 0x3
-#define I40E_AQ_RESOURCE_TYPE_ETAG 0x4
-#define I40E_AQ_RESOURCE_TYPE_MULTICAST_HASH 0x5
-#define I40E_AQ_RESOURCE_TYPE_UNICAST_HASH 0x6
-#define I40E_AQ_RESOURCE_TYPE_VLAN 0x7
-#define I40E_AQ_RESOURCE_TYPE_VSI_LIST_ENTRY 0x8
-#define I40E_AQ_RESOURCE_TYPE_ETAG_LIST_ENTRY 0x9
-#define I40E_AQ_RESOURCE_TYPE_VLAN_STAT_POOL 0xA
-#define I40E_AQ_RESOURCE_TYPE_MIRROR_RULE 0xB
-#define I40E_AQ_RESOURCE_TYPE_QUEUE_SETS 0xC
-#define I40E_AQ_RESOURCE_TYPE_VLAN_FILTERS 0xD
-#define I40E_AQ_RESOURCE_TYPE_INNER_MAC_FILTERS 0xF
-#define I40E_AQ_RESOURCE_TYPE_IP_FILTERS 0x10
-#define I40E_AQ_RESOURCE_TYPE_GRE_VN_KEYS 0x11
-#define I40E_AQ_RESOURCE_TYPE_VN2_KEYS 0x12
-#define I40E_AQ_RESOURCE_TYPE_TUNNEL_PORTS 0x13
- u8 reserved1;
- __le16 guaranteed;
- __le16 total;
- __le16 used;
- __le16 total_unalloced;
- u8 reserved2[6];
-};
-
-I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
-
-/* Set Switch Configuration (direct 0x0205) */
-struct i40e_aqc_set_switch_config {
- __le16 flags;
-/* flags used for both fields below */
-#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001
-#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002
- __le16 valid_flags;
- /* The ethertype in switch_tag is dropped on ingress and used
- * internally by the switch. Set this to zero for the default
- * of 0x88a8 (802.1ad). Should be zero for firmware API
- * versions lower than 1.7.
- */
- __le16 switch_tag;
- /* The ethertypes in first_tag and second_tag are used to
- * match the outer and inner VLAN tags (respectively) when HW
- * double VLAN tagging is enabled via the set port parameters
- * AQ command. Otherwise these are both ignored. Set them to
- * zero for their defaults of 0x8100 (802.1Q). Should be zero
- * for firmware API versions lower than 1.7.
- */
- __le16 first_tag;
- __le16 second_tag;
- u8 reserved[6];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
-
-/* Read Receive control registers (direct 0x0206)
- * Write Receive control registers (direct 0x0207)
- * used for accessing Rx control registers that can be
- * slow and need special handling when under high Rx load
- */
-struct i40e_aqc_rx_ctl_reg_read_write {
- __le32 reserved1;
- __le32 address;
- __le32 reserved2;
- __le32 value;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_rx_ctl_reg_read_write);
-
-/* Add VSI (indirect 0x0210)
- * this indirect command uses struct i40e_aqc_vsi_properties_data
- * as the indirect buffer (128 bytes)
- *
- * Update VSI (indirect 0x211)
- * uses the same data structure as Add VSI
- *
- * Get VSI (indirect 0x0212)
- * uses the same completion and data structure as Add VSI
- */
-struct i40e_aqc_add_get_update_vsi {
- __le16 uplink_seid;
- u8 connection_type;
-#define I40E_AQ_VSI_CONN_TYPE_NORMAL 0x1
-#define I40E_AQ_VSI_CONN_TYPE_DEFAULT 0x2
-#define I40E_AQ_VSI_CONN_TYPE_CASCADED 0x3
- u8 reserved1;
- u8 vf_id;
- u8 reserved2;
- __le16 vsi_flags;
-#define I40E_AQ_VSI_TYPE_SHIFT 0x0
-#define I40E_AQ_VSI_TYPE_MASK (0x3 << I40E_AQ_VSI_TYPE_SHIFT)
-#define I40E_AQ_VSI_TYPE_VF 0x0
-#define I40E_AQ_VSI_TYPE_VMDQ2 0x1
-#define I40E_AQ_VSI_TYPE_PF 0x2
-#define I40E_AQ_VSI_TYPE_EMP_MNG 0x3
-#define I40E_AQ_VSI_FLAG_CASCADED_PV 0x4
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi);
-
-struct i40e_aqc_add_get_update_vsi_completion {
- __le16 seid;
- __le16 vsi_number;
- __le16 vsi_used;
- __le16 vsi_free;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi_completion);
-
-struct i40e_aqc_vsi_properties_data {
- /* first 96 byte are written by SW */
- __le16 valid_sections;
-#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001
-#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002
-#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004
-#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008
-#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010
-#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020
-#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040
-#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080
-#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100
-#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200
- /* switch section */
- __le16 switch_id; /* 12bit id combined with flags below */
-#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000
-#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT)
-#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000
-#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000
-#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000
- u8 sw_reserved[2];
- /* security section */
- u8 sec_flags;
-#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01
-#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02
-#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04
- u8 sec_reserved;
- /* VLAN section */
- __le16 pvid; /* VLANS include priority bits */
- __le16 fcoe_pvid;
- u8 port_vlan_flags;
-#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00
-#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \
- I40E_AQ_VSI_PVLAN_MODE_SHIFT)
-#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01
-#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02
-#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03
-#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04
-#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03
-#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \
- I40E_AQ_VSI_PVLAN_EMOD_SHIFT)
-#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0
-#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08
-#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10
-#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18
- u8 pvlan_reserved[3];
- /* ingress egress up sections */
- __le32 ingress_table; /* bitmap, 3 bits per up */
-#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0
-#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP0_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3
-#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP1_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6
-#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP2_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9
-#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP3_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12
-#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP4_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15
-#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP5_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18
-#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP6_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21
-#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \
- I40E_AQ_VSI_UP_TABLE_UP7_SHIFT)
- __le32 egress_table; /* same defines as for ingress table */
- /* cascaded PV section */
- __le16 cas_pv_tag;
- u8 cas_pv_flags;
-#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \
- I40E_AQ_VSI_CAS_PV_TAGX_SHIFT)
-#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01
-#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02
-#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10
-#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20
-#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40
- u8 cas_pv_reserved;
- /* queue mapping section */
- __le16 mapping_flags;
-#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0
-#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1
- __le16 queue_mapping[16];
-#define I40E_AQ_VSI_QUEUE_SHIFT 0x0
-#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT)
- __le16 tc_mapping[8];
-#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0
-#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \
- I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT)
-#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9
-#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \
- I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT)
- /* queueing option section */
- u8 queueing_opt_flags;
-#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04
-#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08
-#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10
-#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20
-#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00
-#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40
- u8 queueing_opt_reserved[3];
- /* scheduler section */
- u8 up_enable_bits;
- u8 sched_reserved;
- /* outer up section */
- __le32 outer_up_table; /* same structure and defines as ingress tbl */
- u8 cmd_reserved[8];
- /* last 32 bytes are written by FW */
- __le16 qs_handle[8];
-#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF
- __le16 stat_counter_idx;
- __le16 sched_id;
- u8 resp_reserved[12];
-};
-
-I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data);
-
-/* Add Port Virtualizer (direct 0x0220)
- * also used for update PV (direct 0x0221) but only flags are used
- * (IS_CTRL_PORT only works on add PV)
- */
-struct i40e_aqc_add_update_pv {
- __le16 command_flags;
-#define I40E_AQC_PV_FLAG_PV_TYPE 0x1
-#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_STAG_EN 0x2
-#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_ETAG_EN 0x4
-#define I40E_AQC_PV_FLAG_IS_CTRL_PORT 0x8
- __le16 uplink_seid;
- __le16 connected_seid;
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv);
-
-struct i40e_aqc_add_update_pv_completion {
- /* reserved for update; for add also encodes error if rc == ENOSPC */
- __le16 pv_seid;
-#define I40E_AQC_PV_ERR_FLAG_NO_PV 0x1
-#define I40E_AQC_PV_ERR_FLAG_NO_SCHED 0x2
-#define I40E_AQC_PV_ERR_FLAG_NO_COUNTER 0x4
-#define I40E_AQC_PV_ERR_FLAG_NO_ENTRY 0x8
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv_completion);
-
-/* Get PV Params (direct 0x0222)
- * uses i40e_aqc_switch_seid for the descriptor
- */
-
-struct i40e_aqc_get_pv_params_completion {
- __le16 seid;
- __le16 default_stag;
- __le16 pv_flags; /* same flags as add_pv */
-#define I40E_AQC_GET_PV_PV_TYPE 0x1
-#define I40E_AQC_GET_PV_FRWD_UNKNOWN_STAG 0x2
-#define I40E_AQC_GET_PV_FRWD_UNKNOWN_ETAG 0x4
- u8 reserved[8];
- __le16 default_port_seid;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_pv_params_completion);
-
-/* Add VEB (direct 0x0230) */
-struct i40e_aqc_add_veb {
- __le16 uplink_seid;
- __le16 downlink_seid;
- __le16 veb_flags;
-#define I40E_AQC_ADD_VEB_FLOATING 0x1
-#define I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT 1
-#define I40E_AQC_ADD_VEB_PORT_TYPE_MASK (0x3 << \
- I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT)
-#define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT 0x2
-#define I40E_AQC_ADD_VEB_PORT_TYPE_DATA 0x4
-#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8 /* deprecated */
-#define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS 0x10
- u8 enable_tcs;
- u8 reserved[9];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb);
-
-struct i40e_aqc_add_veb_completion {
- u8 reserved[6];
- __le16 switch_seid;
- /* also encodes error if rc == ENOSPC; codes are the same as add_pv */
- __le16 veb_seid;
-#define I40E_AQC_VEB_ERR_FLAG_NO_VEB 0x1
-#define I40E_AQC_VEB_ERR_FLAG_NO_SCHED 0x2
-#define I40E_AQC_VEB_ERR_FLAG_NO_COUNTER 0x4
-#define I40E_AQC_VEB_ERR_FLAG_NO_ENTRY 0x8
- __le16 statistic_index;
- __le16 vebs_used;
- __le16 vebs_free;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb_completion);
-
-/* Get VEB Parameters (direct 0x0232)
- * uses i40e_aqc_switch_seid for the descriptor
- */
-struct i40e_aqc_get_veb_parameters_completion {
- __le16 seid;
- __le16 switch_id;
- __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */
- __le16 statistic_index;
- __le16 vebs_used;
- __le16 vebs_free;
- u8 reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion);
-
-/* Delete Element (direct 0x0243)
- * uses the generic i40e_aqc_switch_seid
- */
-
-/* Add MAC-VLAN (indirect 0x0250) */
-
-/* used for the command for most vlan commands */
-struct i40e_aqc_macvlan {
- __le16 num_addresses;
- __le16 seid[3];
-#define I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_MACVLAN_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
-#define I40E_AQC_MACVLAN_CMD_SEID_VALID 0x8000
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_macvlan);
-
-/* indirect data for command and response */
-struct i40e_aqc_add_macvlan_element_data {
- u8 mac_addr[6];
- __le16 vlan_tag;
- __le16 flags;
-#define I40E_AQC_MACVLAN_ADD_PERFECT_MATCH 0x0001
-#define I40E_AQC_MACVLAN_ADD_HASH_MATCH 0x0002
-#define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN 0x0004
-#define I40E_AQC_MACVLAN_ADD_TO_QUEUE 0x0008
-#define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC 0x0010
- __le16 queue_number;
-#define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT 0
-#define I40E_AQC_MACVLAN_CMD_QUEUE_MASK (0x7FF << \
- I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT)
- /* response section */
- u8 match_method;
-#define I40E_AQC_MM_PERFECT_MATCH 0x01
-#define I40E_AQC_MM_HASH_MATCH 0x02
-#define I40E_AQC_MM_ERR_NO_RES 0xFF
- u8 reserved1[3];
-};
-
-struct i40e_aqc_add_remove_macvlan_completion {
- __le16 perfect_mac_used;
- __le16 perfect_mac_free;
- __le16 unicast_hash_free;
- __le16 multicast_hash_free;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_macvlan_completion);
-
-/* Remove MAC-VLAN (indirect 0x0251)
- * uses i40e_aqc_macvlan for the descriptor
- * data points to an array of num_addresses of elements
- */
-
-struct i40e_aqc_remove_macvlan_element_data {
- u8 mac_addr[6];
- __le16 vlan_tag;
- u8 flags;
-#define I40E_AQC_MACVLAN_DEL_PERFECT_MATCH 0x01
-#define I40E_AQC_MACVLAN_DEL_HASH_MATCH 0x02
-#define I40E_AQC_MACVLAN_DEL_IGNORE_VLAN 0x08
-#define I40E_AQC_MACVLAN_DEL_ALL_VSIS 0x10
- u8 reserved[3];
- /* reply section */
- u8 error_code;
-#define I40E_AQC_REMOVE_MACVLAN_SUCCESS 0x0
-#define I40E_AQC_REMOVE_MACVLAN_FAIL 0xFF
- u8 reply_reserved[3];
-};
-
-/* Add VLAN (indirect 0x0252)
- * Remove VLAN (indirect 0x0253)
- * use the generic i40e_aqc_macvlan for the command
- */
-struct i40e_aqc_add_remove_vlan_element_data {
- __le16 vlan_tag;
- u8 vlan_flags;
-/* flags for add VLAN */
-#define I40E_AQC_ADD_VLAN_LOCAL 0x1
-#define I40E_AQC_ADD_PVLAN_TYPE_SHIFT 1
-#define I40E_AQC_ADD_PVLAN_TYPE_MASK (0x3 << I40E_AQC_ADD_PVLAN_TYPE_SHIFT)
-#define I40E_AQC_ADD_PVLAN_TYPE_REGULAR 0x0
-#define I40E_AQC_ADD_PVLAN_TYPE_PRIMARY 0x2
-#define I40E_AQC_ADD_PVLAN_TYPE_SECONDARY 0x4
-#define I40E_AQC_VLAN_PTYPE_SHIFT 3
-#define I40E_AQC_VLAN_PTYPE_MASK (0x3 << I40E_AQC_VLAN_PTYPE_SHIFT)
-#define I40E_AQC_VLAN_PTYPE_REGULAR_VSI 0x0
-#define I40E_AQC_VLAN_PTYPE_PROMISC_VSI 0x8
-#define I40E_AQC_VLAN_PTYPE_COMMUNITY_VSI 0x10
-#define I40E_AQC_VLAN_PTYPE_ISOLATED_VSI 0x18
-/* flags for remove VLAN */
-#define I40E_AQC_REMOVE_VLAN_ALL 0x1
- u8 reserved;
- u8 result;
-/* flags for add VLAN */
-#define I40E_AQC_ADD_VLAN_SUCCESS 0x0
-#define I40E_AQC_ADD_VLAN_FAIL_REQUEST 0xFE
-#define I40E_AQC_ADD_VLAN_FAIL_RESOURCE 0xFF
-/* flags for remove VLAN */
-#define I40E_AQC_REMOVE_VLAN_SUCCESS 0x0
-#define I40E_AQC_REMOVE_VLAN_FAIL 0xFF
- u8 reserved1[3];
-};
-
-struct i40e_aqc_add_remove_vlan_completion {
- u8 reserved[4];
- __le16 vlans_used;
- __le16 vlans_free;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-/* Set VSI Promiscuous Modes (direct 0x0254) */
-struct i40e_aqc_set_vsi_promiscuous_modes {
- __le16 promiscuous_flags;
- __le16 valid_flags;
-/* flags used for both fields above */
-#define I40E_AQC_SET_VSI_PROMISC_UNICAST 0x01
-#define I40E_AQC_SET_VSI_PROMISC_MULTICAST 0x02
-#define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04
-#define I40E_AQC_SET_VSI_DEFAULT 0x08
-#define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10
-#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000
- __le16 seid;
-#define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF
- __le16 vlan_tag;
-#define I40E_AQC_SET_VSI_VLAN_MASK 0x0FFF
-#define I40E_AQC_SET_VSI_VLAN_VALID 0x8000
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes);
-
-/* Add S/E-tag command (direct 0x0255)
- * Uses generic i40e_aqc_add_remove_tag_completion for completion
- */
-struct i40e_aqc_add_tag {
- __le16 flags;
-#define I40E_AQC_ADD_TAG_FLAG_TO_QUEUE 0x0001
- __le16 seid;
-#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT)
- __le16 tag;
- __le16 queue_number;
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_tag);
-
-struct i40e_aqc_add_remove_tag_completion {
- u8 reserved[12];
- __le16 tags_used;
- __le16 tags_free;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_tag_completion);
-
-/* Remove S/E-tag command (direct 0x0256)
- * Uses generic i40e_aqc_add_remove_tag_completion for completion
- */
-struct i40e_aqc_remove_tag {
- __le16 seid;
-#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT)
- __le16 tag;
- u8 reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag);
-
-/* Add multicast E-Tag (direct 0x0257)
- * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields
- * and no external data
- */
-struct i40e_aqc_add_remove_mcast_etag {
- __le16 pv_seid;
- __le16 etag;
- u8 num_unicast_etags;
- u8 reserved[3];
- __le32 addr_high; /* address of array of 2-byte s-tags */
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag);
-
-struct i40e_aqc_add_remove_mcast_etag_completion {
- u8 reserved[4];
- __le16 mcast_etags_used;
- __le16 mcast_etags_free;
- __le32 addr_high;
- __le32 addr_low;
-
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag_completion);
-
-/* Update S/E-Tag (direct 0x0259) */
-struct i40e_aqc_update_tag {
- __le16 seid;
-#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT)
- __le16 old_tag;
- __le16 new_tag;
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag);
-
-struct i40e_aqc_update_tag_completion {
- u8 reserved[12];
- __le16 tags_used;
- __le16 tags_free;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag_completion);
-
-/* Add Control Packet filter (direct 0x025A)
- * Remove Control Packet filter (direct 0x025B)
- * uses the i40e_aqc_add_oveb_cloud,
- * and the generic direct completion structure
- */
-struct i40e_aqc_add_remove_control_packet_filter {
- u8 mac[6];
- __le16 etype;
- __le16 flags;
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC 0x0001
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP 0x0002
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TO_QUEUE 0x0004
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX 0x0008
-#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_RX 0x0000
- __le16 seid;
-#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT)
- __le16 queue;
- u8 reserved[2];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter);
-
-struct i40e_aqc_add_remove_control_packet_filter_completion {
- __le16 mac_etype_used;
- __le16 etype_used;
- __le16 mac_etype_free;
- __le16 etype_free;
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter_completion);
-
-/* Add Cloud filters (indirect 0x025C)
- * Remove Cloud filters (indirect 0x025D)
- * uses the i40e_aqc_add_remove_cloud_filters,
- * and the generic indirect completion structure
- */
-struct i40e_aqc_add_remove_cloud_filters {
- u8 num_filters;
- u8 reserved;
- __le16 seid;
-#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0
-#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \
- I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT)
- u8 big_buffer_flag;
-#define I40E_AQC_ADD_CLOUD_CMD_BB 1
- u8 reserved2[3];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters);
-
-struct i40e_aqc_cloud_filters_element_data {
- u8 outer_mac[6];
- u8 inner_mac[6];
- __le16 inner_vlan;
- union {
- struct {
- u8 reserved[12];
- u8 data[4];
- } v4;
- struct {
- u8 data[16];
- } v6;
- struct {
- __le16 data[8];
- } raw_v6;
- } ipaddr;
- __le16 flags;
-#define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0
-#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \
- I40E_AQC_ADD_CLOUD_FILTER_SHIFT)
-/* 0x0000 reserved */
-#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001
-/* 0x0002 reserved */
-#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003
-#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID 0x0004
-/* 0x0005 reserved */
-#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID 0x0006
-/* 0x0007 reserved */
-/* 0x0008 reserved */
-#define I40E_AQC_ADD_CLOUD_FILTER_OMAC 0x0009
-#define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A
-#define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B
-#define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C
-/* 0x0010 to 0x0017 is for custom filters */
-#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */
-#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */
-#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT 0x0012 /* Dest MAC + VLAN + L4 Port */
-
-#define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080
-#define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6
-#define I40E_AQC_ADD_CLOUD_VNK_MASK 0x00C0
-#define I40E_AQC_ADD_CLOUD_FLAGS_IPV4 0
-#define I40E_AQC_ADD_CLOUD_FLAGS_IPV6 0x0100
-
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED 4
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE 5
-
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC 0x2000
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC 0x4000
-#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP 0x8000
-
- __le32 tenant_id;
- u8 reserved[4];
- __le16 queue_number;
-#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0
-#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x7FF << \
- I40E_AQC_ADD_CLOUD_QUEUE_SHIFT)
- u8 reserved2[14];
- /* response section */
- u8 allocation_result;
-#define I40E_AQC_ADD_CLOUD_FILTER_SUCCESS 0x0
-#define I40E_AQC_ADD_CLOUD_FILTER_FAIL 0xFF
- u8 response_reserved[7];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data);
-
-/* i40e_aqc_cloud_filters_element_bb is used when
- * I40E_AQC_ADD_CLOUD_CMD_BB flag is set.
- */
-struct i40e_aqc_cloud_filters_element_bb {
- struct i40e_aqc_cloud_filters_element_data element;
- u16 general_fields[32];
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0 0
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1 1
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2 2
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0 3
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1 4
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2 5
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0 6
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1 7
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2 8
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0 9
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1 10
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2 11
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0 12
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1 13
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2 14
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0 15
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1 16
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2 17
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3 18
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4 19
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5 20
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6 21
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7 22
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0 23
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1 24
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2 25
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3 26
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4 27
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5 28
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6 29
-#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7 30
-};
-
-I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb);
-
-struct i40e_aqc_remove_cloud_filters_completion {
- __le16 perfect_ovlan_used;
- __le16 perfect_ovlan_free;
- __le16 vlan_used;
- __le16 vlan_free;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion);
-
-/* Replace filter Command 0x025F
- * uses the i40e_aqc_replace_cloud_filters,
- * and the generic indirect completion structure
- */
-struct i40e_filter_data {
- u8 filter_type;
- u8 input[3];
-};
-
-I40E_CHECK_STRUCT_LEN(4, i40e_filter_data);
-
-struct i40e_aqc_replace_cloud_filters_cmd {
- u8 valid_flags;
-#define I40E_AQC_REPLACE_L1_FILTER 0x0
-#define I40E_AQC_REPLACE_CLOUD_FILTER 0x1
-#define I40E_AQC_GET_CLOUD_FILTERS 0x2
-#define I40E_AQC_MIRROR_CLOUD_FILTER 0x4
-#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER 0x8
- u8 old_filter_type;
- u8 new_filter_type;
- u8 tr_bit;
- u8 reserved[4];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd);
-
-struct i40e_aqc_replace_cloud_filters_cmd_buf {
- u8 data[32];
-/* Filter type INPUT codes*/
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX 3
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED BIT(7)
-
-/* Field Vector offsets */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA 0
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH 6
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG 7
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN 8
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN 9
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN 10
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY 11
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC 12
-/* big FLU */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA 14
-/* big FLU */
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA 15
-
-#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN 37
- struct i40e_filter_data filters[8];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf);
-
-/* Add Mirror Rule (indirect or direct 0x0260)
- * Delete Mirror Rule (indirect or direct 0x0261)
- * note: some rule types (4,5) do not use an external buffer.
- * take care to set the flags correctly.
- */
-struct i40e_aqc_add_delete_mirror_rule {
- __le16 seid;
- __le16 rule_type;
-#define I40E_AQC_MIRROR_RULE_TYPE_SHIFT 0
-#define I40E_AQC_MIRROR_RULE_TYPE_MASK (0x7 << \
- I40E_AQC_MIRROR_RULE_TYPE_SHIFT)
-#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_INGRESS 1
-#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_EGRESS 2
-#define I40E_AQC_MIRROR_RULE_TYPE_VLAN 3
-#define I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS 4
-#define I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS 5
- __le16 num_entries;
- __le16 destination; /* VSI for add, rule id for delete */
- __le32 addr_high; /* address of array of 2-byte VSI or VLAN ids */
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule);
-
-struct i40e_aqc_add_delete_mirror_rule_completion {
- u8 reserved[2];
- __le16 rule_id; /* only used on add */
- __le16 mirror_rules_used;
- __le16 mirror_rules_free;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
-
-/* Dynamic Device Personalization */
-struct i40e_aqc_write_personalization_profile {
- u8 flags;
- u8 reserved[3];
- __le32 profile_track_id;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile);
-
-struct i40e_aqc_write_ddp_resp {
- __le32 error_offset;
- __le32 error_info;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-struct i40e_aqc_get_applied_profiles {
- u8 flags;
-#define I40E_AQC_GET_DDP_GET_CONF 0x1
-#define I40E_AQC_GET_DDP_GET_RDPU_CONF 0x2
- u8 rsv[3];
- __le32 reserved;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles);
-
-/* DCB 0x03xx*/
-
-/* PFC Ignore (direct 0x0301)
- * the command and response use the same descriptor structure
- */
-struct i40e_aqc_pfc_ignore {
- u8 tc_bitmap;
- u8 command_flags; /* unused on response */
-#define I40E_AQC_PFC_IGNORE_SET 0x80
-#define I40E_AQC_PFC_IGNORE_CLEAR 0x0
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_pfc_ignore);
-
-/* DCB Update (direct 0x0302) uses the i40e_aq_desc structure
- * with no parameters
- */
-
-/* TX scheduler 0x04xx */
-
-/* Almost all the indirect commands use
- * this generic struct to pass the SEID in param0
- */
-struct i40e_aqc_tx_sched_ind {
- __le16 vsi_seid;
- u8 reserved[6];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_tx_sched_ind);
-
-/* Several commands respond with a set of queue set handles */
-struct i40e_aqc_qs_handles_resp {
- __le16 qs_handles[8];
-};
-
-/* Configure VSI BW limits (direct 0x0400) */
-struct i40e_aqc_configure_vsi_bw_limit {
- __le16 vsi_seid;
- u8 reserved[2];
- __le16 credit;
- u8 reserved1[2];
- u8 max_credit; /* 0-3, limit = 2^max */
- u8 reserved2[7];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_vsi_bw_limit);
-
-/* Configure VSI Bandwidth Limit per Traffic Type (indirect 0x0406)
- * responds with i40e_aqc_qs_handles_resp
- */
-struct i40e_aqc_configure_vsi_ets_sla_bw_data {
- u8 tc_valid_bits;
- u8 reserved[15];
- __le16 tc_bw_credits[8]; /* FW writesback QS handles here */
-
- /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
- __le16 tc_bw_max[2];
- u8 reserved1[28];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data);
-
-/* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407)
- * responds with i40e_aqc_qs_handles_resp
- */
-struct i40e_aqc_configure_vsi_tc_bw_data {
- u8 tc_valid_bits;
- u8 reserved[3];
- u8 tc_bw_credits[8];
- u8 reserved1[4];
- __le16 qs_handles[8];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data);
-
-/* Query vsi bw configuration (indirect 0x0408) */
-struct i40e_aqc_query_vsi_bw_config_resp {
- u8 tc_valid_bits;
- u8 tc_suspended_bits;
- u8 reserved[14];
- __le16 qs_handles[8];
- u8 reserved1[4];
- __le16 port_bw_limit;
- u8 reserved2[2];
- u8 max_bw; /* 0-3, limit = 2^max */
- u8 reserved3[23];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp);
-
-/* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */
-struct i40e_aqc_query_vsi_ets_sla_config_resp {
- u8 tc_valid_bits;
- u8 reserved[3];
- u8 share_credits[8];
- __le16 credits[8];
-
- /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
- __le16 tc_bw_max[2];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp);
-
-/* Configure Switching Component Bandwidth Limit (direct 0x0410) */
-struct i40e_aqc_configure_switching_comp_bw_limit {
- __le16 seid;
- u8 reserved[2];
- __le16 credit;
- u8 reserved1[2];
- u8 max_bw; /* 0-3, limit = 2^max */
- u8 reserved2[7];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit);
-
-/* Enable Physical Port ETS (indirect 0x0413)
- * Modify Physical Port ETS (indirect 0x0414)
- * Disable Physical Port ETS (indirect 0x0415)
- */
-struct i40e_aqc_configure_switching_comp_ets_data {
- u8 reserved[4];
- u8 tc_valid_bits;
- u8 seepage;
-#define I40E_AQ_ETS_SEEPAGE_EN_MASK 0x1
- u8 tc_strict_priority_flags;
- u8 reserved1[17];
- u8 tc_bw_share_credits[8];
- u8 reserved2[96];
-};
-
-I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data);
-
-/* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */
-struct i40e_aqc_configure_switching_comp_ets_bw_limit_data {
- u8 tc_valid_bits;
- u8 reserved[15];
- __le16 tc_bw_credit[8];
-
- /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
- __le16 tc_bw_max[2];
- u8 reserved1[28];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40,
- i40e_aqc_configure_switching_comp_ets_bw_limit_data);
-
-/* Configure Switching Component Bandwidth Allocation per Tc
- * (indirect 0x0417)
- */
-struct i40e_aqc_configure_switching_comp_bw_config_data {
- u8 tc_valid_bits;
- u8 reserved[2];
- u8 absolute_credits; /* bool */
- u8 tc_bw_share_credits[8];
- u8 reserved1[20];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data);
-
-/* Query Switching Component Configuration (indirect 0x0418) */
-struct i40e_aqc_query_switching_comp_ets_config_resp {
- u8 tc_valid_bits;
- u8 reserved[35];
- __le16 port_bw_limit;
- u8 reserved1[2];
- u8 tc_bw_max; /* 0-3, limit = 2^max */
- u8 reserved2[23];
-};
-
-I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp);
-
-/* Query PhysicalPort ETS Configuration (indirect 0x0419) */
-struct i40e_aqc_query_port_ets_config_resp {
- u8 reserved[4];
- u8 tc_valid_bits;
- u8 reserved1;
- u8 tc_strict_priority_bits;
- u8 reserved2;
- u8 tc_bw_share_credits[8];
- __le16 tc_bw_limits[8];
-
- /* 4 bits per tc 0-7, 4th bit reserved, limit = 2^max */
- __le16 tc_bw_max[2];
- u8 reserved3[32];
-};
-
-I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp);
-
-/* Query Switching Component Bandwidth Allocation per Traffic Type
- * (indirect 0x041A)
- */
-struct i40e_aqc_query_switching_comp_bw_config_resp {
- u8 tc_valid_bits;
- u8 reserved[2];
- u8 absolute_credits_enable; /* bool */
- u8 tc_bw_share_credits[8];
- __le16 tc_bw_limits[8];
-
- /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */
- __le16 tc_bw_max[2];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp);
-
-/* Suspend/resume port TX traffic
- * (direct 0x041B and 0x041C) uses the generic SEID struct
- */
-
-/* Configure partition BW
- * (indirect 0x041D)
- */
-struct i40e_aqc_configure_partition_bw_data {
- __le16 pf_valid_bits;
- u8 min_bw[16]; /* guaranteed bandwidth */
- u8 max_bw[16]; /* bandwidth limit */
-};
-
-I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data);
-
-/* Get and set the active HMC resource profile and status.
- * (direct 0x0500) and (direct 0x0501)
- */
-struct i40e_aq_get_set_hmc_resource_profile {
- u8 pm_profile;
- u8 pe_vf_enabled;
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aq_get_set_hmc_resource_profile);
-
-enum i40e_aq_hmc_profile {
- /* I40E_HMC_PROFILE_NO_CHANGE = 0, reserved */
- I40E_HMC_PROFILE_DEFAULT = 1,
- I40E_HMC_PROFILE_FAVOR_VF = 2,
- I40E_HMC_PROFILE_EQUAL = 3,
-};
-
-/* Get PHY Abilities (indirect 0x0600) uses the generic indirect struct */
-
-/* set in param0 for get phy abilities to report qualified modules */
-#define I40E_AQ_PHY_REPORT_QUALIFIED_MODULES 0x0001
-#define I40E_AQ_PHY_REPORT_INITIAL_VALUES 0x0002
-
-enum i40e_aq_phy_type {
- I40E_PHY_TYPE_SGMII = 0x0,
- I40E_PHY_TYPE_1000BASE_KX = 0x1,
- I40E_PHY_TYPE_10GBASE_KX4 = 0x2,
- I40E_PHY_TYPE_10GBASE_KR = 0x3,
- I40E_PHY_TYPE_40GBASE_KR4 = 0x4,
- I40E_PHY_TYPE_XAUI = 0x5,
- I40E_PHY_TYPE_XFI = 0x6,
- I40E_PHY_TYPE_SFI = 0x7,
- I40E_PHY_TYPE_XLAUI = 0x8,
- I40E_PHY_TYPE_XLPPI = 0x9,
- I40E_PHY_TYPE_40GBASE_CR4_CU = 0xA,
- I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB,
- I40E_PHY_TYPE_10GBASE_AOC = 0xC,
- I40E_PHY_TYPE_40GBASE_AOC = 0xD,
- I40E_PHY_TYPE_UNRECOGNIZED = 0xE,
- I40E_PHY_TYPE_UNSUPPORTED = 0xF,
- I40E_PHY_TYPE_100BASE_TX = 0x11,
- I40E_PHY_TYPE_1000BASE_T = 0x12,
- I40E_PHY_TYPE_10GBASE_T = 0x13,
- I40E_PHY_TYPE_10GBASE_SR = 0x14,
- I40E_PHY_TYPE_10GBASE_LR = 0x15,
- I40E_PHY_TYPE_10GBASE_SFPP_CU = 0x16,
- I40E_PHY_TYPE_10GBASE_CR1 = 0x17,
- I40E_PHY_TYPE_40GBASE_CR4 = 0x18,
- I40E_PHY_TYPE_40GBASE_SR4 = 0x19,
- I40E_PHY_TYPE_40GBASE_LR4 = 0x1A,
- I40E_PHY_TYPE_1000BASE_SX = 0x1B,
- I40E_PHY_TYPE_1000BASE_LX = 0x1C,
- I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D,
- I40E_PHY_TYPE_20GBASE_KR2 = 0x1E,
- I40E_PHY_TYPE_25GBASE_KR = 0x1F,
- I40E_PHY_TYPE_25GBASE_CR = 0x20,
- I40E_PHY_TYPE_25GBASE_SR = 0x21,
- I40E_PHY_TYPE_25GBASE_LR = 0x22,
- I40E_PHY_TYPE_25GBASE_AOC = 0x23,
- I40E_PHY_TYPE_25GBASE_ACC = 0x24,
- I40E_PHY_TYPE_MAX,
- I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
- I40E_PHY_TYPE_EMPTY = 0xFE,
- I40E_PHY_TYPE_DEFAULT = 0xFF,
-};
-
-#define I40E_LINK_SPEED_100MB_SHIFT 0x1
-#define I40E_LINK_SPEED_1000MB_SHIFT 0x2
-#define I40E_LINK_SPEED_10GB_SHIFT 0x3
-#define I40E_LINK_SPEED_40GB_SHIFT 0x4
-#define I40E_LINK_SPEED_20GB_SHIFT 0x5
-#define I40E_LINK_SPEED_25GB_SHIFT 0x6
-
-enum i40e_aq_link_speed {
- I40E_LINK_SPEED_UNKNOWN = 0,
- I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT),
- I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT),
- I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT),
- I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT),
- I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT),
- I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT),
-};
-
-struct i40e_aqc_module_desc {
- u8 oui[3];
- u8 reserved1;
- u8 part_number[16];
- u8 revision[4];
- u8 reserved2[8];
-};
-
-I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc);
-
-struct i40e_aq_get_phy_abilities_resp {
- __le32 phy_type; /* bitmap using the above enum for offsets */
- u8 link_speed; /* bitmap using the above enum bit patterns */
- u8 abilities;
-#define I40E_AQ_PHY_FLAG_PAUSE_TX 0x01
-#define I40E_AQ_PHY_FLAG_PAUSE_RX 0x02
-#define I40E_AQ_PHY_FLAG_LOW_POWER 0x04
-#define I40E_AQ_PHY_LINK_ENABLED 0x08
-#define I40E_AQ_PHY_AN_ENABLED 0x10
-#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20
-#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40
-#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80
- __le16 eee_capability;
-#define I40E_AQ_EEE_100BASE_TX 0x0002
-#define I40E_AQ_EEE_1000BASE_T 0x0004
-#define I40E_AQ_EEE_10GBASE_T 0x0008
-#define I40E_AQ_EEE_1000BASE_KX 0x0010
-#define I40E_AQ_EEE_10GBASE_KX4 0x0020
-#define I40E_AQ_EEE_10GBASE_KR 0x0040
- __le32 eeer_val;
- u8 d3_lpan;
-#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01
- u8 phy_type_ext;
-#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
-#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02
-#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04
-#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08
-#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10
-#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20
- u8 fec_cfg_curr_mod_ext_info;
-#define I40E_AQ_ENABLE_FEC_KR 0x01
-#define I40E_AQ_ENABLE_FEC_RS 0x02
-#define I40E_AQ_REQUEST_FEC_KR 0x04
-#define I40E_AQ_REQUEST_FEC_RS 0x08
-#define I40E_AQ_ENABLE_FEC_AUTO 0x10
-#define I40E_AQ_FEC
-#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0
-#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5
-
- u8 ext_comp_code;
- u8 phy_id[4];
- u8 module_type[3];
- u8 qualified_module_count;
-#define I40E_AQ_PHY_MAX_QMS 16
- struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS];
-};
-
-I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp);
-
-/* Set PHY Config (direct 0x0601) */
-struct i40e_aq_set_phy_config { /* same bits as above in all */
- __le32 phy_type;
- u8 link_speed;
- u8 abilities;
-/* bits 0-2 use the values from get_phy_abilities_resp */
-#define I40E_AQ_PHY_ENABLE_LINK 0x08
-#define I40E_AQ_PHY_ENABLE_AN 0x10
-#define I40E_AQ_PHY_ENABLE_ATOMIC_LINK 0x20
- __le16 eee_capability;
- __le32 eeer;
- u8 low_power_ctrl;
- u8 phy_type_ext;
-#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
-#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02
-#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04
-#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08
- u8 fec_config;
-#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0)
-#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1)
-#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2)
-#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3)
-#define I40E_AQ_SET_FEC_AUTO BIT(4)
-#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0
-#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT)
- u8 reserved;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
-
-/* Set MAC Config command data structure (direct 0x0603) */
-struct i40e_aq_set_mac_config {
- __le16 max_frame_size;
- u8 params;
-#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04
-#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78
-#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7
-#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6
-#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5
-#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4
-#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3
-#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2
-#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1
- u8 tx_timer_priority; /* bitmap */
- __le16 tx_timer_value;
- __le16 fc_refresh_threshold;
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aq_set_mac_config);
-
-/* Restart Auto-Negotiation (direct 0x605) */
-struct i40e_aqc_set_link_restart_an {
- u8 command;
-#define I40E_AQ_PHY_RESTART_AN 0x02
-#define I40E_AQ_PHY_LINK_ENABLE 0x04
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_link_restart_an);
-
-/* Get Link Status cmd & response data structure (direct 0x0607) */
-struct i40e_aqc_get_link_status {
- __le16 command_flags; /* only field set on command */
-#define I40E_AQ_LSE_MASK 0x3
-#define I40E_AQ_LSE_NOP 0x0
-#define I40E_AQ_LSE_DISABLE 0x2
-#define I40E_AQ_LSE_ENABLE 0x3
-/* only response uses this flag */
-#define I40E_AQ_LSE_IS_ENABLED 0x1
- u8 phy_type; /* i40e_aq_phy_type */
- u8 link_speed; /* i40e_aq_link_speed */
- u8 link_info;
-#define I40E_AQ_LINK_UP 0x01 /* obsolete */
-#define I40E_AQ_LINK_UP_FUNCTION 0x01
-#define I40E_AQ_LINK_FAULT 0x02
-#define I40E_AQ_LINK_FAULT_TX 0x04
-#define I40E_AQ_LINK_FAULT_RX 0x08
-#define I40E_AQ_LINK_FAULT_REMOTE 0x10
-#define I40E_AQ_LINK_UP_PORT 0x20
-#define I40E_AQ_MEDIA_AVAILABLE 0x40
-#define I40E_AQ_SIGNAL_DETECT 0x80
- u8 an_info;
-#define I40E_AQ_AN_COMPLETED 0x01
-#define I40E_AQ_LP_AN_ABILITY 0x02
-#define I40E_AQ_PD_FAULT 0x04
-#define I40E_AQ_FEC_EN 0x08
-#define I40E_AQ_PHY_LOW_POWER 0x10
-#define I40E_AQ_LINK_PAUSE_TX 0x20
-#define I40E_AQ_LINK_PAUSE_RX 0x40
-#define I40E_AQ_QUALIFIED_MODULE 0x80
- u8 ext_info;
-#define I40E_AQ_LINK_PHY_TEMP_ALARM 0x01
-#define I40E_AQ_LINK_XCESSIVE_ERRORS 0x02
-#define I40E_AQ_LINK_TX_SHIFT 0x02
-#define I40E_AQ_LINK_TX_MASK (0x03 << I40E_AQ_LINK_TX_SHIFT)
-#define I40E_AQ_LINK_TX_ACTIVE 0x00
-#define I40E_AQ_LINK_TX_DRAINED 0x01
-#define I40E_AQ_LINK_TX_FLUSHED 0x03
-#define I40E_AQ_LINK_FORCED_40G 0x10
-/* 25G Error Codes */
-#define I40E_AQ_25G_NO_ERR 0X00
-#define I40E_AQ_25G_NOT_PRESENT 0X01
-#define I40E_AQ_25G_NVM_CRC_ERR 0X02
-#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03
-#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04
-#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05
- u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
-/* Since firmware API 1.7 loopback field keeps power class info as well */
-#define I40E_AQ_LOOPBACK_MASK 0x07
-#define I40E_AQ_PWR_CLASS_SHIFT_LB 6
-#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
- __le16 max_frame_size;
- u8 config;
-#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01
-#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
-#define I40E_AQ_CONFIG_CRC_ENA 0x04
-#define I40E_AQ_CONFIG_PACING_MASK 0x78
- union {
- struct {
- u8 power_desc;
-#define I40E_AQ_LINK_POWER_CLASS_1 0x00
-#define I40E_AQ_LINK_POWER_CLASS_2 0x01
-#define I40E_AQ_LINK_POWER_CLASS_3 0x02
-#define I40E_AQ_LINK_POWER_CLASS_4 0x03
-#define I40E_AQ_PWR_CLASS_MASK 0x03
- u8 reserved[4];
- };
- struct {
- u8 link_type[4];
- u8 link_type_ext;
- };
- };
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
-
-/* Set event mask command (direct 0x613) */
-struct i40e_aqc_set_phy_int_mask {
- u8 reserved[8];
- __le16 event_mask;
-#define I40E_AQ_EVENT_LINK_UPDOWN 0x0002
-#define I40E_AQ_EVENT_MEDIA_NA 0x0004
-#define I40E_AQ_EVENT_LINK_FAULT 0x0008
-#define I40E_AQ_EVENT_PHY_TEMP_ALARM 0x0010
-#define I40E_AQ_EVENT_EXCESSIVE_ERRORS 0x0020
-#define I40E_AQ_EVENT_SIGNAL_DETECT 0x0040
-#define I40E_AQ_EVENT_AN_COMPLETED 0x0080
-#define I40E_AQ_EVENT_MODULE_QUAL_FAIL 0x0100
-#define I40E_AQ_EVENT_PORT_TX_SUSPENDED 0x0200
- u8 reserved1[6];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_int_mask);
-
-/* Get Local AN advt register (direct 0x0614)
- * Set Local AN advt register (direct 0x0615)
- * Get Link Partner AN advt register (direct 0x0616)
- */
-struct i40e_aqc_an_advt_reg {
- __le32 local_an_reg0;
- __le16 local_an_reg1;
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_an_advt_reg);
-
-/* Set Loopback mode (0x0618) */
-struct i40e_aqc_set_lb_mode {
- __le16 lb_mode;
-#define I40E_AQ_LB_PHY_LOCAL 0x01
-#define I40E_AQ_LB_PHY_REMOTE 0x02
-#define I40E_AQ_LB_MAC_LOCAL 0x04
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode);
-
-/* Set PHY Debug command (0x0622) */
-struct i40e_aqc_set_phy_debug {
- u8 command_flags;
-#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL 0x02
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT 2
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK (0x03 << \
- I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT)
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE 0x00
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD 0x01
-#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT 0x02
-#define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW 0x10
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_debug);
-
-enum i40e_aq_phy_reg_type {
- I40E_AQC_PHY_REG_INTERNAL = 0x1,
- I40E_AQC_PHY_REG_EXERNAL_BASET = 0x2,
- I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3
-};
-
-/* Run PHY Activity (0x0626) */
-struct i40e_aqc_run_phy_activity {
- __le16 activity_id;
- u8 flags;
- u8 reserved1;
- __le32 control;
- __le32 data;
- u8 reserved2[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
-
-/* Set PHY Register command (0x0628) */
-/* Get PHY Register command (0x0629) */
-struct i40e_aqc_phy_register_access {
- u8 phy_interface;
-#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0
-#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1
-#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2
- u8 dev_address;
- u8 reserved1[2];
- __le32 reg_address;
- __le32 reg_value;
- u8 reserved2[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
-
-/* NVM Read command (indirect 0x0701)
- * NVM Erase commands (direct 0x0702)
- * NVM Update commands (indirect 0x0703)
- */
-struct i40e_aqc_nvm_update {
- u8 command_flags;
-#define I40E_AQ_NVM_LAST_CMD 0x01
-#define I40E_AQ_NVM_REARRANGE_TO_FLAT 0x20
-#define I40E_AQ_NVM_REARRANGE_TO_STRUCT 0x40
-#define I40E_AQ_NVM_FLASH_ONLY 0x80
-#define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT 1
-#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK 0x03
-#define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED 0x03
-#define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL 0x01
- u8 module_pointer;
- __le16 length;
- __le32 offset;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
-
-/* NVM Config Read (indirect 0x0704) */
-struct i40e_aqc_nvm_config_read {
- __le16 cmd_flags;
-#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1
-#define I40E_AQ_ANVM_READ_SINGLE_FEATURE 0
-#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES 1
- __le16 element_count;
- __le16 element_id; /* Feature/field ID */
- __le16 element_id_msw; /* MSWord of field ID */
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_read);
-
-/* NVM Config Write (indirect 0x0705) */
-struct i40e_aqc_nvm_config_write {
- __le16 cmd_flags;
- __le16 element_count;
- u8 reserved[4];
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write);
-
-/* Used for 0x0704 as well as for 0x0705 commands */
-#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT 1
-#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \
- BIT(I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT)
-#define I40E_AQ_ANVM_FEATURE 0
-#define I40E_AQ_ANVM_IMMEDIATE_FIELD BIT(FEATURE_OR_IMMEDIATE_SHIFT)
-struct i40e_aqc_nvm_config_data_feature {
- __le16 feature_id;
-#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY 0x01
-#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP 0x08
-#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR 0x10
- __le16 feature_options;
- __le16 feature_selection;
-};
-
-I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature);
-
-struct i40e_aqc_nvm_config_data_immediate_field {
- __le32 field_id;
- __le32 field_value;
- __le16 field_options;
- __le16 reserved;
-};
-
-I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field);
-
-/* OEM Post Update (indirect 0x0720)
- * no command data struct used
- */
- struct i40e_aqc_nvm_oem_post_update {
-#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA 0x01
- u8 sel_data;
- u8 reserved[7];
-};
-
-I40E_CHECK_STRUCT_LEN(0x8, i40e_aqc_nvm_oem_post_update);
-
-struct i40e_aqc_nvm_oem_post_update_buffer {
- u8 str_len;
- u8 dev_addr;
- __le16 eeprom_addr;
- u8 data[36];
-};
-
-I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer);
-
-/* Thermal Sensor (indirect 0x0721)
- * read or set thermal sensor configs and values
- * takes a sensor and command specific data buffer, not detailed here
- */
-struct i40e_aqc_thermal_sensor {
- u8 sensor_action;
-#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG 0
-#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG 1
-#define I40E_AQ_THERMAL_SENSOR_READ_TEMP 2
- u8 reserved[7];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_thermal_sensor);
-
-/* Send to PF command (indirect 0x0801) id is only used by PF
- * Send to VF command (indirect 0x0802) id is only used by PF
- * Send to Peer PF command (indirect 0x0803)
- */
-struct i40e_aqc_pf_vf_message {
- __le32 id;
- u8 reserved[4];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message);
-
-/* Alternate structure */
-
-/* Direct write (direct 0x0900)
- * Direct read (direct 0x0902)
- */
-struct i40e_aqc_alternate_write {
- __le32 address0;
- __le32 data0;
- __le32 address1;
- __le32 data1;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write);
-
-/* Indirect write (indirect 0x0901)
- * Indirect read (indirect 0x0903)
- */
-
-struct i40e_aqc_alternate_ind_write {
- __le32 address;
- __le32 length;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_ind_write);
-
-/* Done alternate write (direct 0x0904)
- * uses i40e_aq_desc
- */
-struct i40e_aqc_alternate_write_done {
- __le16 cmd_flags;
-#define I40E_AQ_ALTERNATE_MODE_BIOS_MASK 1
-#define I40E_AQ_ALTERNATE_MODE_BIOS_LEGACY 0
-#define I40E_AQ_ALTERNATE_MODE_BIOS_UEFI 1
-#define I40E_AQ_ALTERNATE_RESET_NEEDED 2
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write_done);
-
-/* Set OEM mode (direct 0x0905) */
-struct i40e_aqc_alternate_set_mode {
- __le32 mode;
-#define I40E_AQ_ALTERNATE_MODE_NONE 0
-#define I40E_AQ_ALTERNATE_MODE_OEM 1
- u8 reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_set_mode);
-
-/* Clear port Alternate RAM (direct 0x0906) uses i40e_aq_desc */
-
-/* async events 0x10xx */
-
-/* Lan Queue Overflow Event (direct, 0x1001) */
-struct i40e_aqc_lan_overflow {
- __le32 prtdcb_rupto;
- __le32 otx_ctl;
- u8 reserved[8];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lan_overflow);
-
-/* Get LLDP MIB (indirect 0x0A00) */
-struct i40e_aqc_lldp_get_mib {
- u8 type;
- u8 reserved1;
-#define I40E_AQ_LLDP_MIB_TYPE_MASK 0x3
-#define I40E_AQ_LLDP_MIB_LOCAL 0x0
-#define I40E_AQ_LLDP_MIB_REMOTE 0x1
-#define I40E_AQ_LLDP_MIB_LOCAL_AND_REMOTE 0x2
-#define I40E_AQ_LLDP_BRIDGE_TYPE_MASK 0xC
-#define I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT 0x2
-#define I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE 0x0
-#define I40E_AQ_LLDP_BRIDGE_TYPE_NON_TPMR 0x1
-#define I40E_AQ_LLDP_TX_SHIFT 0x4
-#define I40E_AQ_LLDP_TX_MASK (0x03 << I40E_AQ_LLDP_TX_SHIFT)
-/* TX pause flags use I40E_AQ_LINK_TX_* above */
- __le16 local_len;
- __le16 remote_len;
- u8 reserved2[2];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_get_mib);
-
-/* Configure LLDP MIB Change Event (direct 0x0A01)
- * also used for the event (with type in the command field)
- */
-struct i40e_aqc_lldp_update_mib {
- u8 command;
-#define I40E_AQ_LLDP_MIB_UPDATE_ENABLE 0x0
-#define I40E_AQ_LLDP_MIB_UPDATE_DISABLE 0x1
- u8 reserved[7];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_mib);
-
-/* Add LLDP TLV (indirect 0x0A02)
- * Delete LLDP TLV (indirect 0x0A04)
- */
-struct i40e_aqc_lldp_add_tlv {
- u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */
- u8 reserved1[1];
- __le16 len;
- u8 reserved2[4];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_add_tlv);
-
-/* Update LLDP TLV (indirect 0x0A03) */
-struct i40e_aqc_lldp_update_tlv {
- u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */
- u8 reserved;
- __le16 old_len;
- __le16 new_offset;
- __le16 new_len;
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv);
-
-/* Stop LLDP (direct 0x0A05) */
-struct i40e_aqc_lldp_stop {
- u8 command;
-#define I40E_AQ_LLDP_AGENT_STOP 0x0
-#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop);
-
-/* Start LLDP (direct 0x0A06) */
-
-struct i40e_aqc_lldp_start {
- u8 command;
-#define I40E_AQ_LLDP_AGENT_START 0x1
- u8 reserved[15];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start);
-
-/* Set DCB (direct 0x0303) */
-struct i40e_aqc_set_dcb_parameters {
- u8 command;
-#define I40E_AQ_DCB_SET_AGENT 0x1
-#define I40E_DCB_VALID 0x1
- u8 valid_flags;
- u8 reserved[14];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_dcb_parameters);
-
-/* Apply MIB changes (0x0A07)
- * uses the generic struc as it contains no data
- */
-
-/* Add Udp Tunnel command and completion (direct 0x0B00) */
-struct i40e_aqc_add_udp_tunnel {
- __le16 udp_port;
- u8 reserved0[3];
- u8 protocol_type;
-#define I40E_AQC_TUNNEL_TYPE_VXLAN 0x00
-#define I40E_AQC_TUNNEL_TYPE_NGE 0x01
-#define I40E_AQC_TUNNEL_TYPE_TEREDO 0x10
-#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE 0x11
- u8 reserved1[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel);
-
-struct i40e_aqc_add_udp_tunnel_completion {
- __le16 udp_port;
- u8 filter_entry_index;
- u8 multiple_pfs;
-#define I40E_AQC_SINGLE_PF 0x0
-#define I40E_AQC_MULTIPLE_PFS 0x1
- u8 total_filters;
- u8 reserved[11];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel_completion);
-
-/* remove UDP Tunnel command (0x0B01) */
-struct i40e_aqc_remove_udp_tunnel {
- u8 reserved[2];
- u8 index; /* 0 to 15 */
- u8 reserved2[13];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_udp_tunnel);
-
-struct i40e_aqc_del_udp_tunnel_completion {
- __le16 udp_port;
- u8 index; /* 0 to 15 */
- u8 multiple_pfs;
- u8 total_filters_used;
- u8 reserved1[11];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_del_udp_tunnel_completion);
-
-struct i40e_aqc_get_set_rss_key {
-#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15)
-#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0
-#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \
- I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT)
- __le16 vsi_id;
- u8 reserved[6];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key);
-
-struct i40e_aqc_get_set_rss_key_data {
- u8 standard_rss_key[0x28];
- u8 extended_hash_key[0xc];
-};
-
-I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data);
-
-struct i40e_aqc_get_set_rss_lut {
-#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15)
-#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0
-#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \
- I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT)
- __le16 vsi_id;
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \
- BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT)
-
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1
- __le16 flags;
- u8 reserved[4];
- __le32 addr_high;
- __le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut);
-
-/* tunnel key structure 0x0B10 */
-
-struct i40e_aqc_tunnel_key_structure_A0 {
- __le16 key1_off;
- __le16 key1_len;
- __le16 key2_off;
- __le16 key2_len;
- __le16 flags;
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01
-/* response flags */
-#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01
-#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03
- u8 resreved[6];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure_A0);
-
-struct i40e_aqc_tunnel_key_structure {
- u8 key1_off;
- u8 key2_off;
- u8 key1_len; /* 0 to 15 */
- u8 key2_len; /* 0 to 15 */
- u8 flags;
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01
-/* response flags */
-#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01
-#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02
-#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03
- u8 network_key_index;
-#define I40E_AQC_NETWORK_KEY_INDEX_VXLAN 0x0
-#define I40E_AQC_NETWORK_KEY_INDEX_NGE 0x1
-#define I40E_AQC_NETWORK_KEY_INDEX_FLEX_MAC_IN_UDP 0x2
-#define I40E_AQC_NETWORK_KEY_INDEX_GRE 0x3
- u8 reserved[10];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure);
-
-/* OEM mode commands (direct 0xFE0x) */
-struct i40e_aqc_oem_param_change {
- __le32 param_type;
-#define I40E_AQ_OEM_PARAM_TYPE_PF_CTL 0
-#define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1
-#define I40E_AQ_OEM_PARAM_MAC 2
- __le32 param_value1;
- __le16 param_value2;
- u8 reserved[6];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change);
-
-struct i40e_aqc_oem_state_change {
- __le32 state;
-#define I40E_AQ_OEM_STATE_LINK_DOWN 0x0
-#define I40E_AQ_OEM_STATE_LINK_UP 0x1
- u8 reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change);
-
-/* Initialize OCSD (0xFE02, direct) */
-struct i40e_aqc_opc_oem_ocsd_initialize {
- u8 type_status;
- u8 reserved1[3];
- __le32 ocsd_memory_block_addr_high;
- __le32 ocsd_memory_block_addr_low;
- __le32 requested_update_interval;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize);
-
-/* Initialize OCBB (0xFE03, direct) */
-struct i40e_aqc_opc_oem_ocbb_initialize {
- u8 type_status;
- u8 reserved1[3];
- __le32 ocbb_memory_block_addr_high;
- __le32 ocbb_memory_block_addr_low;
- u8 reserved2[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize);
-
-/* debug commands */
-
-/* get device id (0xFF00) uses the generic structure */
-
-/* set test more (0xFF01, internal) */
-
-struct i40e_acq_set_test_mode {
- u8 mode;
-#define I40E_AQ_TEST_PARTIAL 0
-#define I40E_AQ_TEST_FULL 1
-#define I40E_AQ_TEST_NVM 2
- u8 reserved[3];
- u8 command;
-#define I40E_AQ_TEST_OPEN 0
-#define I40E_AQ_TEST_CLOSE 1
-#define I40E_AQ_TEST_INC 2
- u8 reserved2[3];
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_acq_set_test_mode);
-
-/* Debug Read Register command (0xFF03)
- * Debug Write Register command (0xFF04)
- */
-struct i40e_aqc_debug_reg_read_write {
- __le32 reserved;
- __le32 address;
- __le32 value_high;
- __le32 value_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_reg_read_write);
-
-/* Scatter/gather Reg Read (indirect 0xFF05)
- * Scatter/gather Reg Write (indirect 0xFF06)
- */
-
-/* i40e_aq_desc is used for the command */
-struct i40e_aqc_debug_reg_sg_element_data {
- __le32 address;
- __le32 value;
-};
-
-/* Debug Modify register (direct 0xFF07) */
-struct i40e_aqc_debug_modify_reg {
- __le32 address;
- __le32 value;
- __le32 clear_mask;
- __le32 set_mask;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_reg);
-
-/* dump internal data (0xFF08, indirect) */
-
-#define I40E_AQ_CLUSTER_ID_AUX 0
-#define I40E_AQ_CLUSTER_ID_SWITCH_FLU 1
-#define I40E_AQ_CLUSTER_ID_TXSCHED 2
-#define I40E_AQ_CLUSTER_ID_HMC 3
-#define I40E_AQ_CLUSTER_ID_MAC0 4
-#define I40E_AQ_CLUSTER_ID_MAC1 5
-#define I40E_AQ_CLUSTER_ID_MAC2 6
-#define I40E_AQ_CLUSTER_ID_MAC3 7
-#define I40E_AQ_CLUSTER_ID_DCB 8
-#define I40E_AQ_CLUSTER_ID_EMP_MEM 9
-#define I40E_AQ_CLUSTER_ID_PKT_BUF 10
-#define I40E_AQ_CLUSTER_ID_ALTRAM 11
-
-struct i40e_aqc_debug_dump_internals {
- u8 cluster_id;
- u8 table_id;
- __le16 data_size;
- __le32 idx;
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_dump_internals);
-
-struct i40e_aqc_debug_modify_internals {
- u8 cluster_id;
- u8 cluster_specific_params[7];
- __le32 address_high;
- __le32 address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_internals);
-
-#endif /* _I40E_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h
deleted file mode 100644
index cb86892..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_ALLOC_H_
-#define _I40E_ALLOC_H_
-
-struct i40e_hw;
-
-/* Memory allocation types */
-enum i40e_memory_type {
- i40e_mem_arq_buf = 0, /* ARQ indirect command buffer */
- i40e_mem_asq_buf = 1,
- i40e_mem_atq_buf = 2, /* ATQ indirect command buffer */
- i40e_mem_arq_ring = 3, /* ARQ descriptor ring */
- i40e_mem_atq_ring = 4, /* ATQ descriptor ring */
- i40e_mem_pd = 5, /* Page Descriptor */
- i40e_mem_bp = 6, /* Backing Page - 4KB */
- i40e_mem_bp_jumbo = 7, /* Backing Page - > 4KB */
- i40e_mem_reserved
-};
-
-/* prototype for functions used for dynamic memory allocation */
-i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw,
- struct i40e_dma_mem *mem,
- enum i40e_memory_type type,
- u64 size, u32 alignment);
-i40e_status i40e_free_dma_mem(struct i40e_hw *hw,
- struct i40e_dma_mem *mem);
-i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw,
- struct i40e_virt_mem *mem,
- u32 size);
-i40e_status i40e_free_virt_mem(struct i40e_hw *hw,
- struct i40e_virt_mem *mem);
-
-#endif /* _I40E_ALLOC_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
deleted file mode 100644
index eea280b..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ /dev/null
@@ -1,1320 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#include "i40e_type.h"
-#include "i40e_adminq.h"
-#include "i40e_prototype.h"
-#include <linux/avf/virtchnl.h>
-
-/**
- * i40e_set_mac_type - Sets MAC type
- * @hw: pointer to the HW structure
- *
- * This function sets the mac type of the adapter based on the
- * vendor ID and device ID stored in the hw structure.
- **/
-i40e_status i40e_set_mac_type(struct i40e_hw *hw)
-{
- i40e_status status = 0;
-
- if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
- switch (hw->device_id) {
- case I40E_DEV_ID_SFP_XL710:
- case I40E_DEV_ID_QEMU:
- case I40E_DEV_ID_KX_B:
- case I40E_DEV_ID_KX_C:
- case I40E_DEV_ID_QSFP_A:
- case I40E_DEV_ID_QSFP_B:
- case I40E_DEV_ID_QSFP_C:
- case I40E_DEV_ID_10G_BASE_T:
- case I40E_DEV_ID_10G_BASE_T4:
- case I40E_DEV_ID_20G_KR2:
- case I40E_DEV_ID_20G_KR2_A:
- case I40E_DEV_ID_25G_B:
- case I40E_DEV_ID_25G_SFP28:
- hw->mac.type = I40E_MAC_XL710;
- break;
- case I40E_DEV_ID_SFP_X722:
- case I40E_DEV_ID_1G_BASE_T_X722:
- case I40E_DEV_ID_10G_BASE_T_X722:
- case I40E_DEV_ID_SFP_I_X722:
- hw->mac.type = I40E_MAC_X722;
- break;
- case I40E_DEV_ID_X722_VF:
- hw->mac.type = I40E_MAC_X722_VF;
- break;
- case I40E_DEV_ID_VF:
- case I40E_DEV_ID_VF_HV:
- case I40E_DEV_ID_ADAPTIVE_VF:
- hw->mac.type = I40E_MAC_VF;
- break;
- default:
- hw->mac.type = I40E_MAC_GENERIC;
- break;
- }
- } else {
- status = I40E_ERR_DEVICE_NOT_SUPPORTED;
- }
-
- hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n",
- hw->mac.type, status);
- return status;
-}
-
-/**
- * i40evf_aq_str - convert AQ err code to a string
- * @hw: pointer to the HW structure
- * @aq_err: the AQ error code to convert
- **/
-const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
-{
- switch (aq_err) {
- case I40E_AQ_RC_OK:
- return "OK";
- case I40E_AQ_RC_EPERM:
- return "I40E_AQ_RC_EPERM";
- case I40E_AQ_RC_ENOENT:
- return "I40E_AQ_RC_ENOENT";
- case I40E_AQ_RC_ESRCH:
- return "I40E_AQ_RC_ESRCH";
- case I40E_AQ_RC_EINTR:
- return "I40E_AQ_RC_EINTR";
- case I40E_AQ_RC_EIO:
- return "I40E_AQ_RC_EIO";
- case I40E_AQ_RC_ENXIO:
- return "I40E_AQ_RC_ENXIO";
- case I40E_AQ_RC_E2BIG:
- return "I40E_AQ_RC_E2BIG";
- case I40E_AQ_RC_EAGAIN:
- return "I40E_AQ_RC_EAGAIN";
- case I40E_AQ_RC_ENOMEM:
- return "I40E_AQ_RC_ENOMEM";
- case I40E_AQ_RC_EACCES:
- return "I40E_AQ_RC_EACCES";
- case I40E_AQ_RC_EFAULT:
- return "I40E_AQ_RC_EFAULT";
- case I40E_AQ_RC_EBUSY:
- return "I40E_AQ_RC_EBUSY";
- case I40E_AQ_RC_EEXIST:
- return "I40E_AQ_RC_EEXIST";
- case I40E_AQ_RC_EINVAL:
- return "I40E_AQ_RC_EINVAL";
- case I40E_AQ_RC_ENOTTY:
- return "I40E_AQ_RC_ENOTTY";
- case I40E_AQ_RC_ENOSPC:
- return "I40E_AQ_RC_ENOSPC";
- case I40E_AQ_RC_ENOSYS:
- return "I40E_AQ_RC_ENOSYS";
- case I40E_AQ_RC_ERANGE:
- return "I40E_AQ_RC_ERANGE";
- case I40E_AQ_RC_EFLUSHED:
- return "I40E_AQ_RC_EFLUSHED";
- case I40E_AQ_RC_BAD_ADDR:
- return "I40E_AQ_RC_BAD_ADDR";
- case I40E_AQ_RC_EMODE:
- return "I40E_AQ_RC_EMODE";
- case I40E_AQ_RC_EFBIG:
- return "I40E_AQ_RC_EFBIG";
- }
-
- snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
- return hw->err_str;
-}
-
-/**
- * i40evf_stat_str - convert status err code to a string
- * @hw: pointer to the HW structure
- * @stat_err: the status error code to convert
- **/
-const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err)
-{
- switch (stat_err) {
- case 0:
- return "OK";
- case I40E_ERR_NVM:
- return "I40E_ERR_NVM";
- case I40E_ERR_NVM_CHECKSUM:
- return "I40E_ERR_NVM_CHECKSUM";
- case I40E_ERR_PHY:
- return "I40E_ERR_PHY";
- case I40E_ERR_CONFIG:
- return "I40E_ERR_CONFIG";
- case I40E_ERR_PARAM:
- return "I40E_ERR_PARAM";
- case I40E_ERR_MAC_TYPE:
- return "I40E_ERR_MAC_TYPE";
- case I40E_ERR_UNKNOWN_PHY:
- return "I40E_ERR_UNKNOWN_PHY";
- case I40E_ERR_LINK_SETUP:
- return "I40E_ERR_LINK_SETUP";
- case I40E_ERR_ADAPTER_STOPPED:
- return "I40E_ERR_ADAPTER_STOPPED";
- case I40E_ERR_INVALID_MAC_ADDR:
- return "I40E_ERR_INVALID_MAC_ADDR";
- case I40E_ERR_DEVICE_NOT_SUPPORTED:
- return "I40E_ERR_DEVICE_NOT_SUPPORTED";
- case I40E_ERR_MASTER_REQUESTS_PENDING:
- return "I40E_ERR_MASTER_REQUESTS_PENDING";
- case I40E_ERR_INVALID_LINK_SETTINGS:
- return "I40E_ERR_INVALID_LINK_SETTINGS";
- case I40E_ERR_AUTONEG_NOT_COMPLETE:
- return "I40E_ERR_AUTONEG_NOT_COMPLETE";
- case I40E_ERR_RESET_FAILED:
- return "I40E_ERR_RESET_FAILED";
- case I40E_ERR_SWFW_SYNC:
- return "I40E_ERR_SWFW_SYNC";
- case I40E_ERR_NO_AVAILABLE_VSI:
- return "I40E_ERR_NO_AVAILABLE_VSI";
- case I40E_ERR_NO_MEMORY:
- return "I40E_ERR_NO_MEMORY";
- case I40E_ERR_BAD_PTR:
- return "I40E_ERR_BAD_PTR";
- case I40E_ERR_RING_FULL:
- return "I40E_ERR_RING_FULL";
- case I40E_ERR_INVALID_PD_ID:
- return "I40E_ERR_INVALID_PD_ID";
- case I40E_ERR_INVALID_QP_ID:
- return "I40E_ERR_INVALID_QP_ID";
- case I40E_ERR_INVALID_CQ_ID:
- return "I40E_ERR_INVALID_CQ_ID";
- case I40E_ERR_INVALID_CEQ_ID:
- return "I40E_ERR_INVALID_CEQ_ID";
- case I40E_ERR_INVALID_AEQ_ID:
- return "I40E_ERR_INVALID_AEQ_ID";
- case I40E_ERR_INVALID_SIZE:
- return "I40E_ERR_INVALID_SIZE";
- case I40E_ERR_INVALID_ARP_INDEX:
- return "I40E_ERR_INVALID_ARP_INDEX";
- case I40E_ERR_INVALID_FPM_FUNC_ID:
- return "I40E_ERR_INVALID_FPM_FUNC_ID";
- case I40E_ERR_QP_INVALID_MSG_SIZE:
- return "I40E_ERR_QP_INVALID_MSG_SIZE";
- case I40E_ERR_QP_TOOMANY_WRS_POSTED:
- return "I40E_ERR_QP_TOOMANY_WRS_POSTED";
- case I40E_ERR_INVALID_FRAG_COUNT:
- return "I40E_ERR_INVALID_FRAG_COUNT";
- case I40E_ERR_QUEUE_EMPTY:
- return "I40E_ERR_QUEUE_EMPTY";
- case I40E_ERR_INVALID_ALIGNMENT:
- return "I40E_ERR_INVALID_ALIGNMENT";
- case I40E_ERR_FLUSHED_QUEUE:
- return "I40E_ERR_FLUSHED_QUEUE";
- case I40E_ERR_INVALID_PUSH_PAGE_INDEX:
- return "I40E_ERR_INVALID_PUSH_PAGE_INDEX";
- case I40E_ERR_INVALID_IMM_DATA_SIZE:
- return "I40E_ERR_INVALID_IMM_DATA_SIZE";
- case I40E_ERR_TIMEOUT:
- return "I40E_ERR_TIMEOUT";
- case I40E_ERR_OPCODE_MISMATCH:
- return "I40E_ERR_OPCODE_MISMATCH";
- case I40E_ERR_CQP_COMPL_ERROR:
- return "I40E_ERR_CQP_COMPL_ERROR";
- case I40E_ERR_INVALID_VF_ID:
- return "I40E_ERR_INVALID_VF_ID";
- case I40E_ERR_INVALID_HMCFN_ID:
- return "I40E_ERR_INVALID_HMCFN_ID";
- case I40E_ERR_BACKING_PAGE_ERROR:
- return "I40E_ERR_BACKING_PAGE_ERROR";
- case I40E_ERR_NO_PBLCHUNKS_AVAILABLE:
- return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE";
- case I40E_ERR_INVALID_PBLE_INDEX:
- return "I40E_ERR_INVALID_PBLE_INDEX";
- case I40E_ERR_INVALID_SD_INDEX:
- return "I40E_ERR_INVALID_SD_INDEX";
- case I40E_ERR_INVALID_PAGE_DESC_INDEX:
- return "I40E_ERR_INVALID_PAGE_DESC_INDEX";
- case I40E_ERR_INVALID_SD_TYPE:
- return "I40E_ERR_INVALID_SD_TYPE";
- case I40E_ERR_MEMCPY_FAILED:
- return "I40E_ERR_MEMCPY_FAILED";
- case I40E_ERR_INVALID_HMC_OBJ_INDEX:
- return "I40E_ERR_INVALID_HMC_OBJ_INDEX";
- case I40E_ERR_INVALID_HMC_OBJ_COUNT:
- return "I40E_ERR_INVALID_HMC_OBJ_COUNT";
- case I40E_ERR_INVALID_SRQ_ARM_LIMIT:
- return "I40E_ERR_INVALID_SRQ_ARM_LIMIT";
- case I40E_ERR_SRQ_ENABLED:
- return "I40E_ERR_SRQ_ENABLED";
- case I40E_ERR_ADMIN_QUEUE_ERROR:
- return "I40E_ERR_ADMIN_QUEUE_ERROR";
- case I40E_ERR_ADMIN_QUEUE_TIMEOUT:
- return "I40E_ERR_ADMIN_QUEUE_TIMEOUT";
- case I40E_ERR_BUF_TOO_SHORT:
- return "I40E_ERR_BUF_TOO_SHORT";
- case I40E_ERR_ADMIN_QUEUE_FULL:
- return "I40E_ERR_ADMIN_QUEUE_FULL";
- case I40E_ERR_ADMIN_QUEUE_NO_WORK:
- return "I40E_ERR_ADMIN_QUEUE_NO_WORK";
- case I40E_ERR_BAD_IWARP_CQE:
- return "I40E_ERR_BAD_IWARP_CQE";
- case I40E_ERR_NVM_BLANK_MODE:
- return "I40E_ERR_NVM_BLANK_MODE";
- case I40E_ERR_NOT_IMPLEMENTED:
- return "I40E_ERR_NOT_IMPLEMENTED";
- case I40E_ERR_PE_DOORBELL_NOT_ENABLED:
- return "I40E_ERR_PE_DOORBELL_NOT_ENABLED";
- case I40E_ERR_DIAG_TEST_FAILED:
- return "I40E_ERR_DIAG_TEST_FAILED";
- case I40E_ERR_NOT_READY:
- return "I40E_ERR_NOT_READY";
- case I40E_NOT_SUPPORTED:
- return "I40E_NOT_SUPPORTED";
- case I40E_ERR_FIRMWARE_API_VERSION:
- return "I40E_ERR_FIRMWARE_API_VERSION";
- case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR:
- return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR";
- }
-
- snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err);
- return hw->err_str;
-}
-
-/**
- * i40evf_debug_aq
- * @hw: debug mask related to admin queue
- * @mask: debug mask
- * @desc: pointer to admin queue descriptor
- * @buffer: pointer to command buffer
- * @buf_len: max length of buffer
- *
- * Dumps debug log about adminq command with descriptor contents.
- **/
-void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
- void *buffer, u16 buf_len)
-{
- struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
- u8 *buf = (u8 *)buffer;
-
- if ((!(mask & hw->debug_mask)) || (desc == NULL))
- return;
-
- i40e_debug(hw, mask,
- "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
- le16_to_cpu(aq_desc->opcode),
- le16_to_cpu(aq_desc->flags),
- le16_to_cpu(aq_desc->datalen),
- le16_to_cpu(aq_desc->retval));
- i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n",
- le32_to_cpu(aq_desc->cookie_high),
- le32_to_cpu(aq_desc->cookie_low));
- i40e_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n",
- le32_to_cpu(aq_desc->params.internal.param0),
- le32_to_cpu(aq_desc->params.internal.param1));
- i40e_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n",
- le32_to_cpu(aq_desc->params.external.addr_high),
- le32_to_cpu(aq_desc->params.external.addr_low));
-
- if ((buffer != NULL) && (aq_desc->datalen != 0)) {
- u16 len = le16_to_cpu(aq_desc->datalen);
-
- i40e_debug(hw, mask, "AQ CMD Buffer:\n");
- if (buf_len < len)
- len = buf_len;
- /* write the full 16-byte chunks */
- if (hw->debug_mask & mask) {
- char prefix[27];
-
- snprintf(prefix, sizeof(prefix),
- "i40evf %02x:%02x.%x: \t0x",
- hw->bus.bus_id,
- hw->bus.device,
- hw->bus.func);
-
- print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
- 16, 1, buf, len, false);
- }
- }
-}
-
-/**
- * i40evf_check_asq_alive
- * @hw: pointer to the hw struct
- *
- * Returns true if Queue is enabled else false.
- **/
-bool i40evf_check_asq_alive(struct i40e_hw *hw)
-{
- if (hw->aq.asq.len)
- return !!(rd32(hw, hw->aq.asq.len) &
- I40E_VF_ATQLEN1_ATQENABLE_MASK);
- else
- return false;
-}
-
-/**
- * i40evf_aq_queue_shutdown
- * @hw: pointer to the hw struct
- * @unloading: is the driver unloading itself
- *
- * Tell the Firmware that we're shutting down the AdminQ and whether
- * or not the driver is unloading as well.
- **/
-i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw,
- bool unloading)
-{
- struct i40e_aq_desc desc;
- struct i40e_aqc_queue_shutdown *cmd =
- (struct i40e_aqc_queue_shutdown *)&desc.params.raw;
- i40e_status status;
-
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_queue_shutdown);
-
- if (unloading)
- cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING);
- status = i40evf_asq_send_command(hw, &desc, NULL, 0, NULL);
-
- return status;
-}
-
-/**
- * i40e_aq_get_set_rss_lut
- * @hw: pointer to the hardware structure
- * @vsi_id: vsi fw index
- * @pf_lut: for PF table set true, for VSI table set false
- * @lut: pointer to the lut buffer provided by the caller
- * @lut_size: size of the lut buffer
- * @set: set true to set the table, false to get the table
- *
- * Internal function to get or set RSS look up table
- **/
-static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
- u16 vsi_id, bool pf_lut,
- u8 *lut, u16 lut_size,
- bool set)
-{
- i40e_status status;
- struct i40e_aq_desc desc;
- struct i40e_aqc_get_set_rss_lut *cmd_resp =
- (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw;
-
- if (set)
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_set_rss_lut);
- else
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_get_rss_lut);
-
- /* Indirect command */
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
-
- cmd_resp->vsi_id =
- cpu_to_le16((u16)((vsi_id <<
- I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
- I40E_AQC_SET_RSS_LUT_VSI_ID_MASK));
- cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID);
-
- if (pf_lut)
- cmd_resp->flags |= cpu_to_le16((u16)
- ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
- I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
- I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
- else
- cmd_resp->flags |= cpu_to_le16((u16)
- ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
- I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
- I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
-
- status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL);
-
- return status;
-}
-
-/**
- * i40evf_aq_get_rss_lut
- * @hw: pointer to the hardware structure
- * @vsi_id: vsi fw index
- * @pf_lut: for PF table set true, for VSI table set false
- * @lut: pointer to the lut buffer provided by the caller
- * @lut_size: size of the lut buffer
- *
- * get the RSS lookup table, PF or VSI type
- **/
-i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id,
- bool pf_lut, u8 *lut, u16 lut_size)
-{
- return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size,
- false);
-}
-
-/**
- * i40evf_aq_set_rss_lut
- * @hw: pointer to the hardware structure
- * @vsi_id: vsi fw index
- * @pf_lut: for PF table set true, for VSI table set false
- * @lut: pointer to the lut buffer provided by the caller
- * @lut_size: size of the lut buffer
- *
- * set the RSS lookup table, PF or VSI type
- **/
-i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id,
- bool pf_lut, u8 *lut, u16 lut_size)
-{
- return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true);
-}
-
-/**
- * i40e_aq_get_set_rss_key
- * @hw: pointer to the hw struct
- * @vsi_id: vsi fw index
- * @key: pointer to key info struct
- * @set: set true to set the key, false to get the key
- *
- * get the RSS key per VSI
- **/
-static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw,
- u16 vsi_id,
- struct i40e_aqc_get_set_rss_key_data *key,
- bool set)
-{
- i40e_status status;
- struct i40e_aq_desc desc;
- struct i40e_aqc_get_set_rss_key *cmd_resp =
- (struct i40e_aqc_get_set_rss_key *)&desc.params.raw;
- u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data);
-
- if (set)
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_set_rss_key);
- else
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_get_rss_key);
-
- /* Indirect command */
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
-
- cmd_resp->vsi_id =
- cpu_to_le16((u16)((vsi_id <<
- I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
- I40E_AQC_SET_RSS_KEY_VSI_ID_MASK));
- cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID);
-
- status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL);
-
- return status;
-}
-
-/**
- * i40evf_aq_get_rss_key
- * @hw: pointer to the hw struct
- * @vsi_id: vsi fw index
- * @key: pointer to key info struct
- *
- **/
-i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw,
- u16 vsi_id,
- struct i40e_aqc_get_set_rss_key_data *key)
-{
- return i40e_aq_get_set_rss_key(hw, vsi_id, key, false);
-}
-
-/**
- * i40evf_aq_set_rss_key
- * @hw: pointer to the hw struct
- * @vsi_id: vsi fw index
- * @key: pointer to key info struct
- *
- * set the RSS key per VSI
- **/
-i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw,
- u16 vsi_id,
- struct i40e_aqc_get_set_rss_key_data *key)
-{
- return i40e_aq_get_set_rss_key(hw, vsi_id, key, true);
-}
-
-
-/* The i40evf_ptype_lookup table is used to convert from the 8-bit ptype in the
- * hardware to a bit-field that can be used by SW to more easily determine the
- * packet type.
- *
- * Macros are used to shorten the table lines and make this table human
- * readable.
- *
- * We store the PTYPE in the top byte of the bit field - this is just so that
- * we can check that the table doesn't have a row missing, as the index into
- * the table should be the PTYPE.
- *
- * Typical work flow:
- *
- * IF NOT i40evf_ptype_lookup[ptype].known
- * THEN
- * Packet is unknown
- * ELSE IF i40evf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP
- * Use the rest of the fields to look at the tunnels, inner protocols, etc
- * ELSE
- * Use the enum i40e_rx_l2_ptype to decode the packet type
- * ENDIF
- */
-
-/* macro to make the table lines short */
-#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
- { PTYPE, \
- 1, \
- I40E_RX_PTYPE_OUTER_##OUTER_IP, \
- I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \
- I40E_RX_PTYPE_##OUTER_FRAG, \
- I40E_RX_PTYPE_TUNNEL_##T, \
- I40E_RX_PTYPE_TUNNEL_END_##TE, \
- I40E_RX_PTYPE_##TEF, \
- I40E_RX_PTYPE_INNER_PROT_##I, \
- I40E_RX_PTYPE_PAYLOAD_LAYER_##PL }
-
-#define I40E_PTT_UNUSED_ENTRY(PTYPE) \
- { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-
-/* shorter macros makes the table fit but are terse */
-#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG
-#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG
-#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC
-
-/* Lookup table mapping the HW PTYPE to the bit field for decoding */
-struct i40e_rx_ptype_decoded i40evf_ptype_lookup[] = {
- /* L2 Packet types */
- I40E_PTT_UNUSED_ENTRY(0),
- I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
- I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2),
- I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
- I40E_PTT_UNUSED_ENTRY(4),
- I40E_PTT_UNUSED_ENTRY(5),
- I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
- I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
- I40E_PTT_UNUSED_ENTRY(8),
- I40E_PTT_UNUSED_ENTRY(9),
- I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
- I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
- I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-
- /* Non Tunneled IPv4 */
- I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(25),
- I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4),
- I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
- I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
- /* IPv4 --> IPv4 */
- I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
- I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
- I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(32),
- I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
- I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
- /* IPv4 --> IPv6 */
- I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
- I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
- I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(39),
- I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
- I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
- /* IPv4 --> GRE/NAT */
- I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
- /* IPv4 --> GRE/NAT --> IPv4 */
- I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
- I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
- I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(47),
- I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
- I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
- /* IPv4 --> GRE/NAT --> IPv6 */
- I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
- I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
- I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(54),
- I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
- I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
- /* IPv4 --> GRE/NAT --> MAC */
- I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
- /* IPv4 --> GRE/NAT --> MAC --> IPv4 */
- I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
- I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
- I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(62),
- I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
- I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
- /* IPv4 --> GRE/NAT -> MAC --> IPv6 */
- I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
- I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
- I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(69),
- I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
- I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
- /* IPv4 --> GRE/NAT --> MAC/VLAN */
- I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
- /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
- I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
- I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
- I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(77),
- I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
- I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
- /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
- I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
- I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
- I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(84),
- I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
- I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
- /* Non Tunneled IPv6 */
- I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
- I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3),
- I40E_PTT_UNUSED_ENTRY(91),
- I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4),
- I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
- I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
- /* IPv6 --> IPv4 */
- I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
- I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
- I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(98),
- I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
- I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
- /* IPv6 --> IPv6 */
- I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
- I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
- I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(105),
- I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
- I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT */
- I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
- /* IPv6 --> GRE/NAT -> IPv4 */
- I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
- I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
- I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(113),
- I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
- I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT -> IPv6 */
- I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
- I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
- I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(120),
- I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
- I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT -> MAC */
- I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
- /* IPv6 --> GRE/NAT -> MAC -> IPv4 */
- I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
- I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
- I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(128),
- I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
- I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT -> MAC -> IPv6 */
- I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
- I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
- I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(135),
- I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
- I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT -> MAC/VLAN */
- I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
- /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
- I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
- I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
- I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(143),
- I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
- I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
- I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
- /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
- I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
- I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
- I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
- I40E_PTT_UNUSED_ENTRY(150),
- I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
- I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
- I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
- /* unused entries */
- I40E_PTT_UNUSED_ENTRY(154),
- I40E_PTT_UNUSED_ENTRY(155),
- I40E_PTT_UNUSED_ENTRY(156),
- I40E_PTT_UNUSED_ENTRY(157),
- I40E_PTT_UNUSED_ENTRY(158),
- I40E_PTT_UNUSED_ENTRY(159),
-
- I40E_PTT_UNUSED_ENTRY(160),
- I40E_PTT_UNUSED_ENTRY(161),
- I40E_PTT_UNUSED_ENTRY(162),
- I40E_PTT_UNUSED_ENTRY(163),
- I40E_PTT_UNUSED_ENTRY(164),
- I40E_PTT_UNUSED_ENTRY(165),
- I40E_PTT_UNUSED_ENTRY(166),
- I40E_PTT_UNUSED_ENTRY(167),
- I40E_PTT_UNUSED_ENTRY(168),
- I40E_PTT_UNUSED_ENTRY(169),
-
- I40E_PTT_UNUSED_ENTRY(170),
- I40E_PTT_UNUSED_ENTRY(171),
- I40E_PTT_UNUSED_ENTRY(172),
- I40E_PTT_UNUSED_ENTRY(173),
- I40E_PTT_UNUSED_ENTRY(174),
- I40E_PTT_UNUSED_ENTRY(175),
- I40E_PTT_UNUSED_ENTRY(176),
- I40E_PTT_UNUSED_ENTRY(177),
- I40E_PTT_UNUSED_ENTRY(178),
- I40E_PTT_UNUSED_ENTRY(179),
-
- I40E_PTT_UNUSED_ENTRY(180),
- I40E_PTT_UNUSED_ENTRY(181),
- I40E_PTT_UNUSED_ENTRY(182),
- I40E_PTT_UNUSED_ENTRY(183),
- I40E_PTT_UNUSED_ENTRY(184),
- I40E_PTT_UNUSED_ENTRY(185),
- I40E_PTT_UNUSED_ENTRY(186),
- I40E_PTT_UNUSED_ENTRY(187),
- I40E_PTT_UNUSED_ENTRY(188),
- I40E_PTT_UNUSED_ENTRY(189),
-
- I40E_PTT_UNUSED_ENTRY(190),
- I40E_PTT_UNUSED_ENTRY(191),
- I40E_PTT_UNUSED_ENTRY(192),
- I40E_PTT_UNUSED_ENTRY(193),
- I40E_PTT_UNUSED_ENTRY(194),
- I40E_PTT_UNUSED_ENTRY(195),
- I40E_PTT_UNUSED_ENTRY(196),
- I40E_PTT_UNUSED_ENTRY(197),
- I40E_PTT_UNUSED_ENTRY(198),
- I40E_PTT_UNUSED_ENTRY(199),
-
- I40E_PTT_UNUSED_ENTRY(200),
- I40E_PTT_UNUSED_ENTRY(201),
- I40E_PTT_UNUSED_ENTRY(202),
- I40E_PTT_UNUSED_ENTRY(203),
- I40E_PTT_UNUSED_ENTRY(204),
- I40E_PTT_UNUSED_ENTRY(205),
- I40E_PTT_UNUSED_ENTRY(206),
- I40E_PTT_UNUSED_ENTRY(207),
- I40E_PTT_UNUSED_ENTRY(208),
- I40E_PTT_UNUSED_ENTRY(209),
-
- I40E_PTT_UNUSED_ENTRY(210),
- I40E_PTT_UNUSED_ENTRY(211),
- I40E_PTT_UNUSED_ENTRY(212),
- I40E_PTT_UNUSED_ENTRY(213),
- I40E_PTT_UNUSED_ENTRY(214),
- I40E_PTT_UNUSED_ENTRY(215),
- I40E_PTT_UNUSED_ENTRY(216),
- I40E_PTT_UNUSED_ENTRY(217),
- I40E_PTT_UNUSED_ENTRY(218),
- I40E_PTT_UNUSED_ENTRY(219),
-
- I40E_PTT_UNUSED_ENTRY(220),
- I40E_PTT_UNUSED_ENTRY(221),
- I40E_PTT_UNUSED_ENTRY(222),
- I40E_PTT_UNUSED_ENTRY(223),
- I40E_PTT_UNUSED_ENTRY(224),
- I40E_PTT_UNUSED_ENTRY(225),
- I40E_PTT_UNUSED_ENTRY(226),
- I40E_PTT_UNUSED_ENTRY(227),
- I40E_PTT_UNUSED_ENTRY(228),
- I40E_PTT_UNUSED_ENTRY(229),
-
- I40E_PTT_UNUSED_ENTRY(230),
- I40E_PTT_UNUSED_ENTRY(231),
- I40E_PTT_UNUSED_ENTRY(232),
- I40E_PTT_UNUSED_ENTRY(233),
- I40E_PTT_UNUSED_ENTRY(234),
- I40E_PTT_UNUSED_ENTRY(235),
- I40E_PTT_UNUSED_ENTRY(236),
- I40E_PTT_UNUSED_ENTRY(237),
- I40E_PTT_UNUSED_ENTRY(238),
- I40E_PTT_UNUSED_ENTRY(239),
-
- I40E_PTT_UNUSED_ENTRY(240),
- I40E_PTT_UNUSED_ENTRY(241),
- I40E_PTT_UNUSED_ENTRY(242),
- I40E_PTT_UNUSED_ENTRY(243),
- I40E_PTT_UNUSED_ENTRY(244),
- I40E_PTT_UNUSED_ENTRY(245),
- I40E_PTT_UNUSED_ENTRY(246),
- I40E_PTT_UNUSED_ENTRY(247),
- I40E_PTT_UNUSED_ENTRY(248),
- I40E_PTT_UNUSED_ENTRY(249),
-
- I40E_PTT_UNUSED_ENTRY(250),
- I40E_PTT_UNUSED_ENTRY(251),
- I40E_PTT_UNUSED_ENTRY(252),
- I40E_PTT_UNUSED_ENTRY(253),
- I40E_PTT_UNUSED_ENTRY(254),
- I40E_PTT_UNUSED_ENTRY(255)
-};
-
-/**
- * i40evf_aq_rx_ctl_read_register - use FW to read from an Rx control register
- * @hw: pointer to the hw struct
- * @reg_addr: register address
- * @reg_val: ptr to register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Use the firmware to read the Rx control register,
- * especially useful if the Rx unit is under heavy pressure
- **/
-i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw,
- u32 reg_addr, u32 *reg_val,
- struct i40e_asq_cmd_details *cmd_details)
-{
- struct i40e_aq_desc desc;
- struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp =
- (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
- i40e_status status;
-
- if (!reg_val)
- return I40E_ERR_PARAM;
-
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_rx_ctl_reg_read);
-
- cmd_resp->address = cpu_to_le32(reg_addr);
-
- status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
- if (status == 0)
- *reg_val = le32_to_cpu(cmd_resp->value);
-
- return status;
-}
-
-/**
- * i40evf_read_rx_ctl - read from an Rx control register
- * @hw: pointer to the hw struct
- * @reg_addr: register address
- **/
-u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
-{
- i40e_status status = 0;
- bool use_register;
- int retry = 5;
- u32 val = 0;
-
- use_register = (((hw->aq.api_maj_ver == 1) &&
- (hw->aq.api_min_ver < 5)) ||
- (hw->mac.type == I40E_MAC_X722));
- if (!use_register) {
-do_retry:
- status = i40evf_aq_rx_ctl_read_register(hw, reg_addr,
- &val, NULL);
- if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
- usleep_range(1000, 2000);
- retry--;
- goto do_retry;
- }
- }
-
- /* if the AQ access failed, try the old-fashioned way */
- if (status || use_register)
- val = rd32(hw, reg_addr);
-
- return val;
-}
-
-/**
- * i40evf_aq_rx_ctl_write_register
- * @hw: pointer to the hw struct
- * @reg_addr: register address
- * @reg_val: register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Use the firmware to write to an Rx control register,
- * especially useful if the Rx unit is under heavy pressure
- **/
-i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw,
- u32 reg_addr, u32 reg_val,
- struct i40e_asq_cmd_details *cmd_details)
-{
- struct i40e_aq_desc desc;
- struct i40e_aqc_rx_ctl_reg_read_write *cmd =
- (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
- i40e_status status;
-
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_rx_ctl_reg_write);
-
- cmd->address = cpu_to_le32(reg_addr);
- cmd->value = cpu_to_le32(reg_val);
-
- status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
- return status;
-}
-
-/**
- * i40evf_write_rx_ctl - write to an Rx control register
- * @hw: pointer to the hw struct
- * @reg_addr: register address
- * @reg_val: register value
- **/
-void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
-{
- i40e_status status = 0;
- bool use_register;
- int retry = 5;
-
- use_register = (((hw->aq.api_maj_ver == 1) &&
- (hw->aq.api_min_ver < 5)) ||
- (hw->mac.type == I40E_MAC_X722));
- if (!use_register) {
-do_retry:
- status = i40evf_aq_rx_ctl_write_register(hw, reg_addr,
- reg_val, NULL);
- if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
- usleep_range(1000, 2000);
- retry--;
- goto do_retry;
- }
- }
-
- /* if the AQ access failed, try the old-fashioned way */
- if (status || use_register)
- wr32(hw, reg_addr, reg_val);
-}
-
-/**
- * i40e_aq_send_msg_to_pf
- * @hw: pointer to the hardware structure
- * @v_opcode: opcodes for VF-PF communication
- * @v_retval: return error code
- * @msg: pointer to the msg buffer
- * @msglen: msg length
- * @cmd_details: pointer to command details
- *
- * Send message to PF driver using admin queue. By default, this message
- * is sent asynchronously, i.e. i40evf_asq_send_command() does not wait for
- * completion before returning.
- **/
-i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw,
- enum virtchnl_ops v_opcode,
- i40e_status v_retval,
- u8 *msg, u16 msglen,
- struct i40e_asq_cmd_details *cmd_details)
-{
- struct i40e_aq_desc desc;
- struct i40e_asq_cmd_details details;
- i40e_status status;
-
- i40evf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf);
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI);
- desc.cookie_high = cpu_to_le32(v_opcode);
- desc.cookie_low = cpu_to_le32(v_retval);
- if (msglen) {
- desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF
- | I40E_AQ_FLAG_RD));
- if (msglen > I40E_AQ_LARGE_BUF)
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
- desc.datalen = cpu_to_le16(msglen);
- }
- if (!cmd_details) {
- memset(&details, 0, sizeof(details));
- details.async = true;
- cmd_details = &details;
- }
- status = i40evf_asq_send_command(hw, &desc, msg, msglen, cmd_details);
- return status;
-}
-
-/**
- * i40e_vf_parse_hw_config
- * @hw: pointer to the hardware structure
- * @msg: pointer to the virtual channel VF resource structure
- *
- * Given a VF resource message from the PF, populate the hw struct
- * with appropriate information.
- **/
-void i40e_vf_parse_hw_config(struct i40e_hw *hw,
- struct virtchnl_vf_resource *msg)
-{
- struct virtchnl_vsi_resource *vsi_res;
- int i;
-
- vsi_res = &msg->vsi_res[0];
-
- hw->dev_caps.num_vsis = msg->num_vsis;
- hw->dev_caps.num_rx_qp = msg->num_queue_pairs;
- hw->dev_caps.num_tx_qp = msg->num_queue_pairs;
- hw->dev_caps.num_msix_vectors_vf = msg->max_vectors;
- hw->dev_caps.dcb = msg->vf_cap_flags &
- VIRTCHNL_VF_OFFLOAD_L2;
- hw->dev_caps.fcoe = 0;
- for (i = 0; i < msg->num_vsis; i++) {
- if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) {
- ether_addr_copy(hw->mac.perm_addr,
- vsi_res->default_mac_addr);
- ether_addr_copy(hw->mac.addr,
- vsi_res->default_mac_addr);
- }
- vsi_res++;
- }
-}
-
-/**
- * i40e_vf_reset
- * @hw: pointer to the hardware structure
- *
- * Send a VF_RESET message to the PF. Does not wait for response from PF
- * as none will be forthcoming. Immediately after calling this function,
- * the admin queue should be shut down and (optionally) reinitialized.
- **/
-i40e_status i40e_vf_reset(struct i40e_hw *hw)
-{
- return i40e_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF,
- 0, NULL, 0, NULL);
-}
-
-/**
- * i40evf_aq_write_ddp - Write dynamic device personalization (ddp)
- * @hw: pointer to the hw struct
- * @buff: command buffer (size in bytes = buff_size)
- * @buff_size: buffer size in bytes
- * @track_id: package tracking id
- * @error_offset: returns error offset
- * @error_info: returns error information
- * @cmd_details: pointer to command details structure or NULL
- **/
-enum
-i40e_status_code i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff,
- u16 buff_size, u32 track_id,
- u32 *error_offset, u32 *error_info,
- struct i40e_asq_cmd_details *cmd_details)
-{
- struct i40e_aq_desc desc;
- struct i40e_aqc_write_personalization_profile *cmd =
- (struct i40e_aqc_write_personalization_profile *)
- &desc.params.raw;
- struct i40e_aqc_write_ddp_resp *resp;
- i40e_status status;
-
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_write_personalization_profile);
-
- desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
- if (buff_size > I40E_AQ_LARGE_BUF)
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
-
- desc.datalen = cpu_to_le16(buff_size);
-
- cmd->profile_track_id = cpu_to_le32(track_id);
-
- status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
- if (!status) {
- resp = (struct i40e_aqc_write_ddp_resp *)&desc.params.raw;
- if (error_offset)
- *error_offset = le32_to_cpu(resp->error_offset);
- if (error_info)
- *error_info = le32_to_cpu(resp->error_info);
- }
-
- return status;
-}
-
-/**
- * i40evf_aq_get_ddp_list - Read dynamic device personalization (ddp)
- * @hw: pointer to the hw struct
- * @buff: command buffer (size in bytes = buff_size)
- * @buff_size: buffer size in bytes
- * @flags: AdminQ command flags
- * @cmd_details: pointer to command details structure or NULL
- **/
-enum
-i40e_status_code i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
- u16 buff_size, u8 flags,
- struct i40e_asq_cmd_details *cmd_details)
-{
- struct i40e_aq_desc desc;
- struct i40e_aqc_get_applied_profiles *cmd =
- (struct i40e_aqc_get_applied_profiles *)&desc.params.raw;
- i40e_status status;
-
- i40evf_fill_default_direct_cmd_desc(&desc,
- i40e_aqc_opc_get_personalization_profile_list);
-
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
- if (buff_size > I40E_AQ_LARGE_BUF)
- desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
- desc.datalen = cpu_to_le16(buff_size);
-
- cmd->flags = flags;
-
- status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
-
- return status;
-}
-
-/**
- * i40evf_find_segment_in_package
- * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E)
- * @pkg_hdr: pointer to the package header to be searched
- *
- * This function searches a package file for a particular segment type. On
- * success it returns a pointer to the segment header, otherwise it will
- * return NULL.
- **/
-struct i40e_generic_seg_header *
-i40evf_find_segment_in_package(u32 segment_type,
- struct i40e_package_header *pkg_hdr)
-{
- struct i40e_generic_seg_header *segment;
- u32 i;
-
- /* Search all package segments for the requested segment type */
- for (i = 0; i < pkg_hdr->segment_count; i++) {
- segment =
- (struct i40e_generic_seg_header *)((u8 *)pkg_hdr +
- pkg_hdr->segment_offset[i]);
-
- if (segment->type == segment_type)
- return segment;
- }
-
- return NULL;
-}
-
-/**
- * i40evf_write_profile
- * @hw: pointer to the hardware structure
- * @profile: pointer to the profile segment of the package to be downloaded
- * @track_id: package tracking id
- *
- * Handles the download of a complete package.
- */
-enum i40e_status_code
-i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
- u32 track_id)
-{
- i40e_status status = 0;
- struct i40e_section_table *sec_tbl;
- struct i40e_profile_section_header *sec = NULL;
- u32 dev_cnt;
- u32 vendor_dev_id;
- u32 *nvm;
- u32 section_size = 0;
- u32 offset = 0, info = 0;
- u32 i;
-
- dev_cnt = profile->device_table_count;
-
- for (i = 0; i < dev_cnt; i++) {
- vendor_dev_id = profile->device_table[i].vendor_dev_id;
- if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
- if (hw->device_id == (vendor_dev_id & 0xFFFF))
- break;
- }
- if (i == dev_cnt) {
- i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP");
- return I40E_ERR_DEVICE_NOT_SUPPORTED;
- }
-
- nvm = (u32 *)&profile->device_table[dev_cnt];
- sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
-
- for (i = 0; i < sec_tbl->section_count; i++) {
- sec = (struct i40e_profile_section_header *)((u8 *)profile +
- sec_tbl->section_offset[i]);
-
- /* Skip 'AQ', 'note' and 'name' sections */
- if (sec->section.type != SECTION_TYPE_MMIO)
- continue;
-
- section_size = sec->section.size +
- sizeof(struct i40e_profile_section_header);
-
- /* Write profile */
- status = i40evf_aq_write_ddp(hw, (void *)sec, (u16)section_size,
- track_id, &offset, &info, NULL);
- if (status) {
- i40e_debug(hw, I40E_DEBUG_PACKAGE,
- "Failed to write profile: offset %d, info %d",
- offset, info);
- break;
- }
- }
- return status;
-}
-
-/**
- * i40evf_add_pinfo_to_list
- * @hw: pointer to the hardware structure
- * @profile: pointer to the profile segment of the package
- * @profile_info_sec: buffer for information section
- * @track_id: package tracking id
- *
- * Register a profile to the list of loaded profiles.
- */
-enum i40e_status_code
-i40evf_add_pinfo_to_list(struct i40e_hw *hw,
- struct i40e_profile_segment *profile,
- u8 *profile_info_sec, u32 track_id)
-{
- i40e_status status = 0;
- struct i40e_profile_section_header *sec = NULL;
- struct i40e_profile_info *pinfo;
- u32 offset = 0, info = 0;
-
- sec = (struct i40e_profile_section_header *)profile_info_sec;
- sec->tbl_size = 1;
- sec->data_end = sizeof(struct i40e_profile_section_header) +
- sizeof(struct i40e_profile_info);
- sec->section.type = SECTION_TYPE_INFO;
- sec->section.offset = sizeof(struct i40e_profile_section_header);
- sec->section.size = sizeof(struct i40e_profile_info);
- pinfo = (struct i40e_profile_info *)(profile_info_sec +
- sec->section.offset);
- pinfo->track_id = track_id;
- pinfo->version = profile->version;
- pinfo->op = I40E_DDP_ADD_TRACKID;
- memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
-
- status = i40evf_aq_write_ddp(hw, (void *)sec, sec->data_end,
- track_id, &offset, &info, NULL);
- return status;
-}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h
deleted file mode 100644
index f300bf2..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_DEVIDS_H_
-#define _I40E_DEVIDS_H_
-
-/* Device IDs */
-#define I40E_DEV_ID_SFP_XL710 0x1572
-#define I40E_DEV_ID_QEMU 0x1574
-#define I40E_DEV_ID_KX_B 0x1580
-#define I40E_DEV_ID_KX_C 0x1581
-#define I40E_DEV_ID_QSFP_A 0x1583
-#define I40E_DEV_ID_QSFP_B 0x1584
-#define I40E_DEV_ID_QSFP_C 0x1585
-#define I40E_DEV_ID_10G_BASE_T 0x1586
-#define I40E_DEV_ID_20G_KR2 0x1587
-#define I40E_DEV_ID_20G_KR2_A 0x1588
-#define I40E_DEV_ID_10G_BASE_T4 0x1589
-#define I40E_DEV_ID_25G_B 0x158A
-#define I40E_DEV_ID_25G_SFP28 0x158B
-#define I40E_DEV_ID_VF 0x154C
-#define I40E_DEV_ID_VF_HV 0x1571
-#define I40E_DEV_ID_ADAPTIVE_VF 0x1889
-#define I40E_DEV_ID_SFP_X722 0x37D0
-#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1
-#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2
-#define I40E_DEV_ID_SFP_I_X722 0x37D3
-#define I40E_DEV_ID_X722_VF 0x37CD
-
-#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \
- (d) == I40E_DEV_ID_QSFP_B || \
- (d) == I40E_DEV_ID_QSFP_C)
-
-#endif /* _I40E_DEVIDS_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h
deleted file mode 100644
index 1c78de8..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h
+++ /dev/null
@@ -1,215 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_HMC_H_
-#define _I40E_HMC_H_
-
-#define I40E_HMC_MAX_BP_COUNT 512
-
-/* forward-declare the HW struct for the compiler */
-struct i40e_hw;
-
-#define I40E_HMC_INFO_SIGNATURE 0x484D5347 /* HMSG */
-#define I40E_HMC_PD_CNT_IN_SD 512
-#define I40E_HMC_DIRECT_BP_SIZE 0x200000 /* 2M */
-#define I40E_HMC_PAGED_BP_SIZE 4096
-#define I40E_HMC_PD_BP_BUF_ALIGNMENT 4096
-#define I40E_FIRST_VF_FPM_ID 16
-
-struct i40e_hmc_obj_info {
- u64 base; /* base addr in FPM */
- u32 max_cnt; /* max count available for this hmc func */
- u32 cnt; /* count of objects driver actually wants to create */
- u64 size; /* size in bytes of one object */
-};
-
-enum i40e_sd_entry_type {
- I40E_SD_TYPE_INVALID = 0,
- I40E_SD_TYPE_PAGED = 1,
- I40E_SD_TYPE_DIRECT = 2
-};
-
-struct i40e_hmc_bp {
- enum i40e_sd_entry_type entry_type;
- struct i40e_dma_mem addr; /* populate to be used by hw */
- u32 sd_pd_index;
- u32 ref_cnt;
-};
-
-struct i40e_hmc_pd_entry {
- struct i40e_hmc_bp bp;
- u32 sd_index;
- bool rsrc_pg;
- bool valid;
-};
-
-struct i40e_hmc_pd_table {
- struct i40e_dma_mem pd_page_addr; /* populate to be used by hw */
- struct i40e_hmc_pd_entry *pd_entry; /* [512] for sw book keeping */
- struct i40e_virt_mem pd_entry_virt_mem; /* virt mem for pd_entry */
-
- u32 ref_cnt;
- u32 sd_index;
-};
-
-struct i40e_hmc_sd_entry {
- enum i40e_sd_entry_type entry_type;
- bool valid;
-
- union {
- struct i40e_hmc_pd_table pd_table;
- struct i40e_hmc_bp bp;
- } u;
-};
-
-struct i40e_hmc_sd_table {
- struct i40e_virt_mem addr; /* used to track sd_entry allocations */
- u32 sd_cnt;
- u32 ref_cnt;
- struct i40e_hmc_sd_entry *sd_entry; /* (sd_cnt*512) entries max */
-};
-
-struct i40e_hmc_info {
- u32 signature;
- /* equals to pci func num for PF and dynamically allocated for VFs */
- u8 hmc_fn_id;
- u16 first_sd_index; /* index of the first available SD */
-
- /* hmc objects */
- struct i40e_hmc_obj_info *hmc_obj;
- struct i40e_virt_mem hmc_obj_virt_mem;
- struct i40e_hmc_sd_table sd_table;
-};
-
-#define I40E_INC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt++)
-#define I40E_INC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt++)
-#define I40E_INC_BP_REFCNT(bp) ((bp)->ref_cnt++)
-
-#define I40E_DEC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt--)
-#define I40E_DEC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt--)
-#define I40E_DEC_BP_REFCNT(bp) ((bp)->ref_cnt--)
-
-/**
- * I40E_SET_PF_SD_ENTRY - marks the sd entry as valid in the hardware
- * @hw: pointer to our hw struct
- * @pa: pointer to physical address
- * @sd_index: segment descriptor index
- * @type: if sd entry is direct or paged
- **/
-#define I40E_SET_PF_SD_ENTRY(hw, pa, sd_index, type) \
-{ \
- u32 val1, val2, val3; \
- val1 = (u32)(upper_32_bits(pa)); \
- val2 = (u32)(pa) | (I40E_HMC_MAX_BP_COUNT << \
- I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \
- ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \
- I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT) | \
- BIT(I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT); \
- val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \
- wr32((hw), I40E_PFHMC_SDDATAHIGH, val1); \
- wr32((hw), I40E_PFHMC_SDDATALOW, val2); \
- wr32((hw), I40E_PFHMC_SDCMD, val3); \
-}
-
-/**
- * I40E_CLEAR_PF_SD_ENTRY - marks the sd entry as invalid in the hardware
- * @hw: pointer to our hw struct
- * @sd_index: segment descriptor index
- * @type: if sd entry is direct or paged
- **/
-#define I40E_CLEAR_PF_SD_ENTRY(hw, sd_index, type) \
-{ \
- u32 val2, val3; \
- val2 = (I40E_HMC_MAX_BP_COUNT << \
- I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \
- ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \
- I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT); \
- val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \
- wr32((hw), I40E_PFHMC_SDDATAHIGH, 0); \
- wr32((hw), I40E_PFHMC_SDDATALOW, val2); \
- wr32((hw), I40E_PFHMC_SDCMD, val3); \
-}
-
-/**
- * I40E_INVALIDATE_PF_HMC_PD - Invalidates the pd cache in the hardware
- * @hw: pointer to our hw struct
- * @sd_idx: segment descriptor index
- * @pd_idx: page descriptor index
- **/
-#define I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, pd_idx) \
- wr32((hw), I40E_PFHMC_PDINV, \
- (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) | \
- ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
-
-/**
- * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit
- * @hmc_info: pointer to the HMC configuration information structure
- * @type: type of HMC resources we're searching
- * @index: starting index for the object
- * @cnt: number of objects we're trying to create
- * @sd_idx: pointer to return index of the segment descriptor in question
- * @sd_limit: pointer to return the maximum number of segment descriptors
- *
- * This function calculates the segment descriptor index and index limit
- * for the resource defined by i40e_hmc_rsrc_type.
- **/
-#define I40E_FIND_SD_INDEX_LIMIT(hmc_info, type, index, cnt, sd_idx, sd_limit)\
-{ \
- u64 fpm_addr, fpm_limit; \
- fpm_addr = (hmc_info)->hmc_obj[(type)].base + \
- (hmc_info)->hmc_obj[(type)].size * (index); \
- fpm_limit = fpm_addr + (hmc_info)->hmc_obj[(type)].size * (cnt);\
- *(sd_idx) = (u32)(fpm_addr / I40E_HMC_DIRECT_BP_SIZE); \
- *(sd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_DIRECT_BP_SIZE); \
- /* add one more to the limit to correct our range */ \
- *(sd_limit) += 1; \
-}
-
-/**
- * I40E_FIND_PD_INDEX_LIMIT - finds page descriptor index limit
- * @hmc_info: pointer to the HMC configuration information struct
- * @type: HMC resource type we're examining
- * @idx: starting index for the object
- * @cnt: number of objects we're trying to create
- * @pd_index: pointer to return page descriptor index
- * @pd_limit: pointer to return page descriptor index limit
- *
- * Calculates the page descriptor index and index limit for the resource
- * defined by i40e_hmc_rsrc_type.
- **/
-#define I40E_FIND_PD_INDEX_LIMIT(hmc_info, type, idx, cnt, pd_index, pd_limit)\
-{ \
- u64 fpm_adr, fpm_limit; \
- fpm_adr = (hmc_info)->hmc_obj[(type)].base + \
- (hmc_info)->hmc_obj[(type)].size * (idx); \
- fpm_limit = fpm_adr + (hmc_info)->hmc_obj[(type)].size * (cnt); \
- *(pd_index) = (u32)(fpm_adr / I40E_HMC_PAGED_BP_SIZE); \
- *(pd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_PAGED_BP_SIZE); \
- /* add one more to the limit to correct our range */ \
- *(pd_limit) += 1; \
-}
-i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw,
- struct i40e_hmc_info *hmc_info,
- u32 sd_index,
- enum i40e_sd_entry_type type,
- u64 direct_mode_sz);
-
-i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw,
- struct i40e_hmc_info *hmc_info,
- u32 pd_index,
- struct i40e_dma_mem *rsrc_pg);
-i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
- struct i40e_hmc_info *hmc_info,
- u32 idx);
-i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
- u32 idx);
-i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw,
- struct i40e_hmc_info *hmc_info,
- u32 idx, bool is_pf);
-i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info,
- u32 idx);
-i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw,
- struct i40e_hmc_info *hmc_info,
- u32 idx, bool is_pf);
-
-#endif /* _I40E_HMC_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h
deleted file mode 100644
index 82b00f7..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h
+++ /dev/null
@@ -1,158 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_LAN_HMC_H_
-#define _I40E_LAN_HMC_H_
-
-/* forward-declare the HW struct for the compiler */
-struct i40e_hw;
-
-/* HMC element context information */
-
-/* Rx queue context data
- *
- * The sizes of the variables may be larger than needed due to crossing byte
- * boundaries. If we do not have the width of the variable set to the correct
- * size then we could end up shifting bits off the top of the variable when the
- * variable is at the top of a byte and crosses over into the next byte.
- */
-struct i40e_hmc_obj_rxq {
- u16 head;
- u16 cpuid; /* bigger than needed, see above for reason */
- u64 base;
- u16 qlen;
-#define I40E_RXQ_CTX_DBUFF_SHIFT 7
- u16 dbuff; /* bigger than needed, see above for reason */
-#define I40E_RXQ_CTX_HBUFF_SHIFT 6
- u16 hbuff; /* bigger than needed, see above for reason */
- u8 dtype;
- u8 dsize;
- u8 crcstrip;
- u8 fc_ena;
- u8 l2tsel;
- u8 hsplit_0;
- u8 hsplit_1;
- u8 showiv;
- u32 rxmax; /* bigger than needed, see above for reason */
- u8 tphrdesc_ena;
- u8 tphwdesc_ena;
- u8 tphdata_ena;
- u8 tphhead_ena;
- u16 lrxqthresh; /* bigger than needed, see above for reason */
- u8 prefena; /* NOTE: normally must be set to 1 at init */
-};
-
-/* Tx queue context data
-*
-* The sizes of the variables may be larger than needed due to crossing byte
-* boundaries. If we do not have the width of the variable set to the correct
-* size then we could end up shifting bits off the top of the variable when the
-* variable is at the top of a byte and crosses over into the next byte.
-*/
-struct i40e_hmc_obj_txq {
- u16 head;
- u8 new_context;
- u64 base;
- u8 fc_ena;
- u8 timesync_ena;
- u8 fd_ena;
- u8 alt_vlan_ena;
- u16 thead_wb;
- u8 cpuid;
- u8 head_wb_ena;
- u16 qlen;
- u8 tphrdesc_ena;
- u8 tphrpacket_ena;
- u8 tphwdesc_ena;
- u64 head_wb_addr;
- u32 crc;
- u16 rdylist;
- u8 rdylist_act;
-};
-
-/* for hsplit_0 field of Rx HMC context */
-enum i40e_hmc_obj_rx_hsplit_0 {
- I40E_HMC_OBJ_RX_HSPLIT_0_NO_SPLIT = 0,
- I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_L2 = 1,
- I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_IP = 2,
- I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_TCP_UDP = 4,
- I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_SCTP = 8,
-};
-
-/* fcoe_cntx and fcoe_filt are for debugging purpose only */
-struct i40e_hmc_obj_fcoe_cntx {
- u32 rsv[32];
-};
-
-struct i40e_hmc_obj_fcoe_filt {
- u32 rsv[8];
-};
-
-/* Context sizes for LAN objects */
-enum i40e_hmc_lan_object_size {
- I40E_HMC_LAN_OBJ_SZ_8 = 0x3,
- I40E_HMC_LAN_OBJ_SZ_16 = 0x4,
- I40E_HMC_LAN_OBJ_SZ_32 = 0x5,
- I40E_HMC_LAN_OBJ_SZ_64 = 0x6,
- I40E_HMC_LAN_OBJ_SZ_128 = 0x7,
- I40E_HMC_LAN_OBJ_SZ_256 = 0x8,
- I40E_HMC_LAN_OBJ_SZ_512 = 0x9,
-};
-
-#define I40E_HMC_L2OBJ_BASE_ALIGNMENT 512
-#define I40E_HMC_OBJ_SIZE_TXQ 128
-#define I40E_HMC_OBJ_SIZE_RXQ 32
-#define I40E_HMC_OBJ_SIZE_FCOE_CNTX 128
-#define I40E_HMC_OBJ_SIZE_FCOE_FILT 64
-
-enum i40e_hmc_lan_rsrc_type {
- I40E_HMC_LAN_FULL = 0,
- I40E_HMC_LAN_TX = 1,
- I40E_HMC_LAN_RX = 2,
- I40E_HMC_FCOE_CTX = 3,
- I40E_HMC_FCOE_FILT = 4,
- I40E_HMC_LAN_MAX = 5
-};
-
-enum i40e_hmc_model {
- I40E_HMC_MODEL_DIRECT_PREFERRED = 0,
- I40E_HMC_MODEL_DIRECT_ONLY = 1,
- I40E_HMC_MODEL_PAGED_ONLY = 2,
- I40E_HMC_MODEL_UNKNOWN,
-};
-
-struct i40e_hmc_lan_create_obj_info {
- struct i40e_hmc_info *hmc_info;
- u32 rsrc_type;
- u32 start_idx;
- u32 count;
- enum i40e_sd_entry_type entry_type;
- u64 direct_mode_sz;
-};
-
-struct i40e_hmc_lan_delete_obj_info {
- struct i40e_hmc_info *hmc_info;
- u32 rsrc_type;
- u32 start_idx;
- u32 count;
-};
-
-i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num,
- u32 rxq_num, u32 fcoe_cntx_num,
- u32 fcoe_filt_num);
-i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw,
- enum i40e_hmc_model model);
-i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw);
-
-i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw,
- u16 queue);
-i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw,
- u16 queue,
- struct i40e_hmc_obj_txq *s);
-i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw,
- u16 queue);
-i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw,
- u16 queue,
- struct i40e_hmc_obj_rxq *s);
-
-#endif /* _I40E_LAN_HMC_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
deleted file mode 100644
index 3ddddb4..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_OSDEP_H_
-#define _I40E_OSDEP_H_
-
-#include <linux/types.h>
-#include <linux/if_ether.h>
-#include <linux/if_vlan.h>
-#include <linux/tcp.h>
-#include <linux/pci.h>
-
-/* get readq/writeq support for 32 bit kernels, use the low-first version */
-#include <linux/io-64-nonatomic-lo-hi.h>
-
-/* File to be the magic between shared code and
- * actual OS primitives
- */
-
-#define hw_dbg(hw, S, A...) do {} while (0)
-
-#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
-#define rd32(a, reg) readl((a)->hw_addr + (reg))
-
-#define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg)))
-#define rd64(a, reg) readq((a)->hw_addr + (reg))
-#define i40e_flush(a) readl((a)->hw_addr + I40E_VFGEN_RSTAT)
-
-/* memory allocation tracking */
-struct i40e_dma_mem {
- void *va;
- dma_addr_t pa;
- u32 size;
-};
-
-#define i40e_allocate_dma_mem(h, m, unused, s, a) \
- i40evf_allocate_dma_mem_d(h, m, s, a)
-#define i40e_free_dma_mem(h, m) i40evf_free_dma_mem_d(h, m)
-
-struct i40e_virt_mem {
- void *va;
- u32 size;
-};
-#define i40e_allocate_virt_mem(h, m, s) i40evf_allocate_virt_mem_d(h, m, s)
-#define i40e_free_virt_mem(h, m) i40evf_free_virt_mem_d(h, m)
-
-#define i40e_debug(h, m, s, ...) i40evf_debug_d(h, m, s, ##__VA_ARGS__)
-extern void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...)
- __attribute__ ((format(gnu_printf, 3, 4)));
-
-typedef enum i40e_status_code i40e_status;
-#endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
deleted file mode 100644
index a358f4b..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ /dev/null
@@ -1,130 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_PROTOTYPE_H_
-#define _I40E_PROTOTYPE_H_
-
-#include "i40e_type.h"
-#include "i40e_alloc.h"
-#include <linux/avf/virtchnl.h>
-
-/* Prototypes for shared code functions that are not in
- * the standard function pointer structures. These are
- * mostly because they are needed even before the init
- * has happened and will assist in the early SW and FW
- * setup.
- */
-
-/* adminq functions */
-i40e_status i40evf_init_adminq(struct i40e_hw *hw);
-i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw);
-void i40e_adminq_init_ring_data(struct i40e_hw *hw);
-i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
- struct i40e_arq_event_info *e,
- u16 *events_pending);
-i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
- struct i40e_aq_desc *desc,
- void *buff, /* can be NULL */
- u16 buff_size,
- struct i40e_asq_cmd_details *cmd_details);
-bool i40evf_asq_done(struct i40e_hw *hw);
-
-/* debug function for adminq */
-void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
- void *desc, void *buffer, u16 buf_len);
-
-void i40e_idle_aq(struct i40e_hw *hw);
-void i40evf_resume_aq(struct i40e_hw *hw);
-bool i40evf_check_asq_alive(struct i40e_hw *hw);
-i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
-const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
-const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err);
-
-i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 seid,
- bool pf_lut, u8 *lut, u16 lut_size);
-i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 seid,
- bool pf_lut, u8 *lut, u16 lut_size);
-i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw,
- u16 seid,
- struct i40e_aqc_get_set_rss_key_data *key);
-i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw,
- u16 seid,
- struct i40e_aqc_get_set_rss_key_data *key);
-
-i40e_status i40e_set_mac_type(struct i40e_hw *hw);
-
-extern struct i40e_rx_ptype_decoded i40evf_ptype_lookup[];
-
-static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
-{
- return i40evf_ptype_lookup[ptype];
-}
-
-/* prototype for functions used for SW locks */
-
-/* i40e_common for VF drivers*/
-void i40e_vf_parse_hw_config(struct i40e_hw *hw,
- struct virtchnl_vf_resource *msg);
-i40e_status i40e_vf_reset(struct i40e_hw *hw);
-i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw,
- enum virtchnl_ops v_opcode,
- i40e_status v_retval,
- u8 *msg, u16 msglen,
- struct i40e_asq_cmd_details *cmd_details);
-i40e_status i40e_set_filter_control(struct i40e_hw *hw,
- struct i40e_filter_control_settings *settings);
-i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
- u8 *mac_addr, u16 ethtype, u16 flags,
- u16 vsi_seid, u16 queue, bool is_add,
- struct i40e_control_filter_stats *stats,
- struct i40e_asq_cmd_details *cmd_details);
-void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
- u16 vsi_seid);
-i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw,
- u32 reg_addr, u32 *reg_val,
- struct i40e_asq_cmd_details *cmd_details);
-u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr);
-i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw,
- u32 reg_addr, u32 reg_val,
- struct i40e_asq_cmd_details *cmd_details);
-void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
-i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
- u8 phy_select, u8 dev_addr,
- u32 reg_addr, u32 reg_val,
- struct i40e_asq_cmd_details *cmd_details);
-i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
- u8 phy_select, u8 dev_addr,
- u32 reg_addr, u32 *reg_val,
- struct i40e_asq_cmd_details *cmd_details);
-
-i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page,
- u16 reg, u8 phy_addr, u16 *value);
-i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page,
- u16 reg, u8 phy_addr, u16 value);
-i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
- u8 phy_addr, u16 *value);
-i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
- u8 phy_addr, u16 value);
-u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
-i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
- u32 time, u32 interval);
-i40e_status i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff,
- u16 buff_size, u32 track_id,
- u32 *error_offset, u32 *error_info,
- struct i40e_asq_cmd_details *
- cmd_details);
-i40e_status i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
- u16 buff_size, u8 flags,
- struct i40e_asq_cmd_details *
- cmd_details);
-struct i40e_generic_seg_header *
-i40evf_find_segment_in_package(u32 segment_type,
- struct i40e_package_header *pkg_header);
-enum i40e_status_code
-i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
- u32 track_id);
-enum i40e_status_code
-i40evf_add_pinfo_to_list(struct i40e_hw *hw,
- struct i40e_profile_segment *profile,
- u8 *profile_info_sec, u32 track_id);
-#endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h
deleted file mode 100644
index 49e1f57..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_register.h
+++ /dev/null
@@ -1,313 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_REGISTER_H_
-#define _I40E_REGISTER_H_
-
-#define I40E_VFMSIX_PBA1(_i) (0x00002000 + ((_i) * 4)) /* _i=0...19 */ /* Reset: VFLR */
-#define I40E_VFMSIX_PBA1_MAX_INDEX 19
-#define I40E_VFMSIX_PBA1_PENBIT_SHIFT 0
-#define I40E_VFMSIX_PBA1_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA1_PENBIT_SHIFT)
-#define I40E_VFMSIX_TADD1(_i) (0x00002100 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TADD1_MAX_INDEX 639
-#define I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT 0
-#define I40E_VFMSIX_TADD1_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT)
-#define I40E_VFMSIX_TADD1_MSIXTADD_SHIFT 2
-#define I40E_VFMSIX_TADD1_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD1_MSIXTADD_SHIFT)
-#define I40E_VFMSIX_TMSG1(_i) (0x00002108 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TMSG1_MAX_INDEX 639
-#define I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT 0
-#define I40E_VFMSIX_TMSG1_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT)
-#define I40E_VFMSIX_TUADD1(_i) (0x00002104 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TUADD1_MAX_INDEX 639
-#define I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT 0
-#define I40E_VFMSIX_TUADD1_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT)
-#define I40E_VFMSIX_TVCTRL1(_i) (0x0000210C + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TVCTRL1_MAX_INDEX 639
-#define I40E_VFMSIX_TVCTRL1_MASK_SHIFT 0
-#define I40E_VFMSIX_TVCTRL1_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL1_MASK_SHIFT)
-#define I40E_VF_ARQBAH1 0x00006000 /* Reset: EMPR */
-#define I40E_VF_ARQBAH1_ARQBAH_SHIFT 0
-#define I40E_VF_ARQBAH1_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAH1_ARQBAH_SHIFT)
-#define I40E_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */
-#define I40E_VF_ARQBAL1_ARQBAL_SHIFT 0
-#define I40E_VF_ARQBAL1_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAL1_ARQBAL_SHIFT)
-#define I40E_VF_ARQH1 0x00007400 /* Reset: EMPR */
-#define I40E_VF_ARQH1_ARQH_SHIFT 0
-#define I40E_VF_ARQH1_ARQH_MASK I40E_MASK(0x3FF, I40E_VF_ARQH1_ARQH_SHIFT)
-#define I40E_VF_ARQLEN1 0x00008000 /* Reset: EMPR */
-#define I40E_VF_ARQLEN1_ARQLEN_SHIFT 0
-#define I40E_VF_ARQLEN1_ARQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ARQLEN1_ARQLEN_SHIFT)
-#define I40E_VF_ARQLEN1_ARQVFE_SHIFT 28
-#define I40E_VF_ARQLEN1_ARQVFE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQVFE_SHIFT)
-#define I40E_VF_ARQLEN1_ARQOVFL_SHIFT 29
-#define I40E_VF_ARQLEN1_ARQOVFL_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQOVFL_SHIFT)
-#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30
-#define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT)
-#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31
-#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQENABLE_SHIFT)
-#define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */
-#define I40E_VF_ARQT1_ARQT_SHIFT 0
-#define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT)
-#define I40E_VF_ATQBAH1 0x00007800 /* Reset: EMPR */
-#define I40E_VF_ATQBAH1_ATQBAH_SHIFT 0
-#define I40E_VF_ATQBAH1_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAH1_ATQBAH_SHIFT)
-#define I40E_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */
-#define I40E_VF_ATQBAL1_ATQBAL_SHIFT 0
-#define I40E_VF_ATQBAL1_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAL1_ATQBAL_SHIFT)
-#define I40E_VF_ATQH1 0x00006400 /* Reset: EMPR */
-#define I40E_VF_ATQH1_ATQH_SHIFT 0
-#define I40E_VF_ATQH1_ATQH_MASK I40E_MASK(0x3FF, I40E_VF_ATQH1_ATQH_SHIFT)
-#define I40E_VF_ATQLEN1 0x00006800 /* Reset: EMPR */
-#define I40E_VF_ATQLEN1_ATQLEN_SHIFT 0
-#define I40E_VF_ATQLEN1_ATQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ATQLEN1_ATQLEN_SHIFT)
-#define I40E_VF_ATQLEN1_ATQVFE_SHIFT 28
-#define I40E_VF_ATQLEN1_ATQVFE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQVFE_SHIFT)
-#define I40E_VF_ATQLEN1_ATQOVFL_SHIFT 29
-#define I40E_VF_ATQLEN1_ATQOVFL_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQOVFL_SHIFT)
-#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30
-#define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT)
-#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31
-#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQENABLE_SHIFT)
-#define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */
-#define I40E_VF_ATQT1_ATQT_SHIFT 0
-#define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT)
-#define I40E_VFGEN_RSTAT 0x00008800 /* Reset: VFR */
-#define I40E_VFGEN_RSTAT_VFR_STATE_SHIFT 0
-#define I40E_VFGEN_RSTAT_VFR_STATE_MASK I40E_MASK(0x3, I40E_VFGEN_RSTAT_VFR_STATE_SHIFT)
-#define I40E_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */
-#define I40E_VFINT_DYN_CTL01_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTL01_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT 1
-#define I40E_VFINT_DYN_CTL01_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTL01_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTL01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTL01_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT)
-#define I40E_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */
-#define I40E_VFINT_DYN_CTLN1_MAX_INDEX 15
-#define I40E_VFINT_DYN_CTLN1_INTENA_SHIFT 0
-#define I40E_VFINT_DYN_CTLN1_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT 1
-#define I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2
-#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3
-#define I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5
-#define I40E_VFINT_DYN_CTLN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT 25
-#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT 31
-#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT)
-#define I40E_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */
-#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR0_ENA1_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR0_ENA1_RSVD_SHIFT 31
-#define I40E_VFINT_ICR0_ENA1_RSVD_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_RSVD_SHIFT)
-#define I40E_VFINT_ICR01 0x00004800 /* Reset: CORER */
-#define I40E_VFINT_ICR01_INTEVENT_SHIFT 0
-#define I40E_VFINT_ICR01_INTEVENT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_INTEVENT_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_0_SHIFT 1
-#define I40E_VFINT_ICR01_QUEUE_0_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_0_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_1_SHIFT 2
-#define I40E_VFINT_ICR01_QUEUE_1_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_1_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_2_SHIFT 3
-#define I40E_VFINT_ICR01_QUEUE_2_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_2_SHIFT)
-#define I40E_VFINT_ICR01_QUEUE_3_SHIFT 4
-#define I40E_VFINT_ICR01_QUEUE_3_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_3_SHIFT)
-#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT 25
-#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT)
-#define I40E_VFINT_ICR01_ADMINQ_SHIFT 30
-#define I40E_VFINT_ICR01_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_ADMINQ_SHIFT)
-#define I40E_VFINT_ICR01_SWINT_SHIFT 31
-#define I40E_VFINT_ICR01_SWINT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_SWINT_SHIFT)
-#define I40E_VFINT_ITR01(_i) (0x00004C00 + ((_i) * 4)) /* _i=0...2 */ /* Reset: VFR */
-#define I40E_VFINT_ITR01_MAX_INDEX 2
-#define I40E_VFINT_ITR01_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITR01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITR01_INTERVAL_SHIFT)
-#define I40E_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */
-#define I40E_VFINT_ITRN1_MAX_INDEX 2
-#define I40E_VFINT_ITRN1_INTERVAL_SHIFT 0
-#define I40E_VFINT_ITRN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITRN1_INTERVAL_SHIFT)
-#define I40E_VFINT_STAT_CTL01 0x00005400 /* Reset: CORER */
-#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT 2
-#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT)
-#define I40E_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_QRX_TAIL1_MAX_INDEX 15
-#define I40E_QRX_TAIL1_TAIL_SHIFT 0
-#define I40E_QRX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QRX_TAIL1_TAIL_SHIFT)
-#define I40E_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */
-#define I40E_QTX_TAIL1_MAX_INDEX 15
-#define I40E_QTX_TAIL1_TAIL_SHIFT 0
-#define I40E_QTX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QTX_TAIL1_TAIL_SHIFT)
-#define I40E_VFMSIX_PBA 0x00002000 /* Reset: VFLR */
-#define I40E_VFMSIX_PBA_PENBIT_SHIFT 0
-#define I40E_VFMSIX_PBA_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA_PENBIT_SHIFT)
-#define I40E_VFMSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TADD_MAX_INDEX 16
-#define I40E_VFMSIX_TADD_MSIXTADD10_SHIFT 0
-#define I40E_VFMSIX_TADD_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD_MSIXTADD10_SHIFT)
-#define I40E_VFMSIX_TADD_MSIXTADD_SHIFT 2
-#define I40E_VFMSIX_TADD_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD_MSIXTADD_SHIFT)
-#define I40E_VFMSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TMSG_MAX_INDEX 16
-#define I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT 0
-#define I40E_VFMSIX_TMSG_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT)
-#define I40E_VFMSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TUADD_MAX_INDEX 16
-#define I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT 0
-#define I40E_VFMSIX_TUADD_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT)
-#define I40E_VFMSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */
-#define I40E_VFMSIX_TVCTRL_MAX_INDEX 16
-#define I40E_VFMSIX_TVCTRL_MASK_SHIFT 0
-#define I40E_VFMSIX_TVCTRL_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL_MASK_SHIFT)
-#define I40E_VFCM_PE_ERRDATA 0x0000DC00 /* Reset: VFR */
-#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0
-#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT 4
-#define I40E_VFCM_PE_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT)
-#define I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT 8
-#define I40E_VFCM_PE_ERRDATA_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT)
-#define I40E_VFCM_PE_ERRINFO 0x0000D800 /* Reset: VFR */
-#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0
-#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT 4
-#define I40E_VFCM_PE_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8
-#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16
-#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT)
-#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24
-#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT)
-#define I40E_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
-#define I40E_VFQF_HENA_MAX_INDEX 1
-#define I40E_VFQF_HENA_PTYPE_ENA_SHIFT 0
-#define I40E_VFQF_HENA_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_VFQF_HENA_PTYPE_ENA_SHIFT)
-#define I40E_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */
-#define I40E_VFQF_HKEY_MAX_INDEX 12
-#define I40E_VFQF_HKEY_KEY_0_SHIFT 0
-#define I40E_VFQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_0_SHIFT)
-#define I40E_VFQF_HKEY_KEY_1_SHIFT 8
-#define I40E_VFQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_1_SHIFT)
-#define I40E_VFQF_HKEY_KEY_2_SHIFT 16
-#define I40E_VFQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_2_SHIFT)
-#define I40E_VFQF_HKEY_KEY_3_SHIFT 24
-#define I40E_VFQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_3_SHIFT)
-#define I40E_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
-#define I40E_VFQF_HLUT_MAX_INDEX 15
-#define I40E_VFQF_HLUT_LUT0_SHIFT 0
-#define I40E_VFQF_HLUT_LUT0_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT0_SHIFT)
-#define I40E_VFQF_HLUT_LUT1_SHIFT 8
-#define I40E_VFQF_HLUT_LUT1_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT1_SHIFT)
-#define I40E_VFQF_HLUT_LUT2_SHIFT 16
-#define I40E_VFQF_HLUT_LUT2_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT2_SHIFT)
-#define I40E_VFQF_HLUT_LUT3_SHIFT 24
-#define I40E_VFQF_HLUT_LUT3_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT3_SHIFT)
-#define I40E_VFQF_HREGION(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...7 */ /* Reset: CORER */
-#define I40E_VFQF_HREGION_MAX_INDEX 7
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT)
-#define I40E_VFQF_HREGION_REGION_0_SHIFT 1
-#define I40E_VFQF_HREGION_REGION_0_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_0_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT)
-#define I40E_VFQF_HREGION_REGION_1_SHIFT 5
-#define I40E_VFQF_HREGION_REGION_1_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_1_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT)
-#define I40E_VFQF_HREGION_REGION_2_SHIFT 9
-#define I40E_VFQF_HREGION_REGION_2_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_2_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT)
-#define I40E_VFQF_HREGION_REGION_3_SHIFT 13
-#define I40E_VFQF_HREGION_REGION_3_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_3_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT)
-#define I40E_VFQF_HREGION_REGION_4_SHIFT 17
-#define I40E_VFQF_HREGION_REGION_4_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_4_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT)
-#define I40E_VFQF_HREGION_REGION_5_SHIFT 21
-#define I40E_VFQF_HREGION_REGION_5_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_5_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT)
-#define I40E_VFQF_HREGION_REGION_6_SHIFT 25
-#define I40E_VFQF_HREGION_REGION_6_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_6_SHIFT)
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28
-#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT)
-#define I40E_VFQF_HREGION_REGION_7_SHIFT 29
-#define I40E_VFQF_HREGION_REGION_7_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_7_SHIFT)
-#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT)
-#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30
-#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT)
-#define I40E_VFPE_AEQALLOC1 0x0000A400 /* Reset: VFR */
-#define I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT 0
-#define I40E_VFPE_AEQALLOC1_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT)
-#define I40E_VFPE_CCQPHIGH1 0x00009800 /* Reset: VFR */
-#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT 0
-#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT)
-#define I40E_VFPE_CCQPLOW1 0x0000AC00 /* Reset: VFR */
-#define I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT 0
-#define I40E_VFPE_CCQPLOW1_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1 0x0000B800 /* Reset: VFR */
-#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT 0
-#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT 4
-#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT 16
-#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT)
-#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT 31
-#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT)
-#define I40E_VFPE_CQACK1 0x0000B000 /* Reset: VFR */
-#define I40E_VFPE_CQACK1_PECQID_SHIFT 0
-#define I40E_VFPE_CQACK1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQACK1_PECQID_SHIFT)
-#define I40E_VFPE_CQARM1 0x0000B400 /* Reset: VFR */
-#define I40E_VFPE_CQARM1_PECQID_SHIFT 0
-#define I40E_VFPE_CQARM1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQARM1_PECQID_SHIFT)
-#define I40E_VFPE_CQPDB1 0x0000BC00 /* Reset: VFR */
-#define I40E_VFPE_CQPDB1_WQHEAD_SHIFT 0
-#define I40E_VFPE_CQPDB1_WQHEAD_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPDB1_WQHEAD_SHIFT)
-#define I40E_VFPE_CQPERRCODES1 0x00009C00 /* Reset: VFR */
-#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT 0
-#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT)
-#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT 16
-#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT)
-#define I40E_VFPE_CQPTAIL1 0x0000A000 /* Reset: VFR */
-#define I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT 0
-#define I40E_VFPE_CQPTAIL1_WQTAIL_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT)
-#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT 31
-#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT)
-#define I40E_VFPE_IPCONFIG01 0x00008C00 /* Reset: VFR */
-#define I40E_VFPE_IPCONFIG01_PEIPID_SHIFT 0
-#define I40E_VFPE_IPCONFIG01_PEIPID_MASK I40E_MASK(0xFFFF, I40E_VFPE_IPCONFIG01_PEIPID_SHIFT)
-#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT 16
-#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT)
-#define I40E_VFPE_MRTEIDXMASK1 0x00009000 /* Reset: VFR */
-#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT 0
-#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT)
-#define I40E_VFPE_RCVUNEXPECTEDERROR1 0x00009400 /* Reset: VFR */
-#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT 0
-#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT)
-#define I40E_VFPE_TCPNOWTIMER1 0x0000A800 /* Reset: VFR */
-#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT 0
-#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT)
-#define I40E_VFPE_WQEALLOC1 0x0000C000 /* Reset: VFR */
-#define I40E_VFPE_WQEALLOC1_PEQPID_SHIFT 0
-#define I40E_VFPE_WQEALLOC1_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_VFPE_WQEALLOC1_PEQPID_SHIFT)
-#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT 20
-#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT)
-#endif /* _I40E_REGISTER_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/i40evf/i40e_status.h
deleted file mode 100644
index 77be070..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_status.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_STATUS_H_
-#define _I40E_STATUS_H_
-
-/* Error Codes */
-enum i40e_status_code {
- I40E_SUCCESS = 0,
- I40E_ERR_NVM = -1,
- I40E_ERR_NVM_CHECKSUM = -2,
- I40E_ERR_PHY = -3,
- I40E_ERR_CONFIG = -4,
- I40E_ERR_PARAM = -5,
- I40E_ERR_MAC_TYPE = -6,
- I40E_ERR_UNKNOWN_PHY = -7,
- I40E_ERR_LINK_SETUP = -8,
- I40E_ERR_ADAPTER_STOPPED = -9,
- I40E_ERR_INVALID_MAC_ADDR = -10,
- I40E_ERR_DEVICE_NOT_SUPPORTED = -11,
- I40E_ERR_MASTER_REQUESTS_PENDING = -12,
- I40E_ERR_INVALID_LINK_SETTINGS = -13,
- I40E_ERR_AUTONEG_NOT_COMPLETE = -14,
- I40E_ERR_RESET_FAILED = -15,
- I40E_ERR_SWFW_SYNC = -16,
- I40E_ERR_NO_AVAILABLE_VSI = -17,
- I40E_ERR_NO_MEMORY = -18,
- I40E_ERR_BAD_PTR = -19,
- I40E_ERR_RING_FULL = -20,
- I40E_ERR_INVALID_PD_ID = -21,
- I40E_ERR_INVALID_QP_ID = -22,
- I40E_ERR_INVALID_CQ_ID = -23,
- I40E_ERR_INVALID_CEQ_ID = -24,
- I40E_ERR_INVALID_AEQ_ID = -25,
- I40E_ERR_INVALID_SIZE = -26,
- I40E_ERR_INVALID_ARP_INDEX = -27,
- I40E_ERR_INVALID_FPM_FUNC_ID = -28,
- I40E_ERR_QP_INVALID_MSG_SIZE = -29,
- I40E_ERR_QP_TOOMANY_WRS_POSTED = -30,
- I40E_ERR_INVALID_FRAG_COUNT = -31,
- I40E_ERR_QUEUE_EMPTY = -32,
- I40E_ERR_INVALID_ALIGNMENT = -33,
- I40E_ERR_FLUSHED_QUEUE = -34,
- I40E_ERR_INVALID_PUSH_PAGE_INDEX = -35,
- I40E_ERR_INVALID_IMM_DATA_SIZE = -36,
- I40E_ERR_TIMEOUT = -37,
- I40E_ERR_OPCODE_MISMATCH = -38,
- I40E_ERR_CQP_COMPL_ERROR = -39,
- I40E_ERR_INVALID_VF_ID = -40,
- I40E_ERR_INVALID_HMCFN_ID = -41,
- I40E_ERR_BACKING_PAGE_ERROR = -42,
- I40E_ERR_NO_PBLCHUNKS_AVAILABLE = -43,
- I40E_ERR_INVALID_PBLE_INDEX = -44,
- I40E_ERR_INVALID_SD_INDEX = -45,
- I40E_ERR_INVALID_PAGE_DESC_INDEX = -46,
- I40E_ERR_INVALID_SD_TYPE = -47,
- I40E_ERR_MEMCPY_FAILED = -48,
- I40E_ERR_INVALID_HMC_OBJ_INDEX = -49,
- I40E_ERR_INVALID_HMC_OBJ_COUNT = -50,
- I40E_ERR_INVALID_SRQ_ARM_LIMIT = -51,
- I40E_ERR_SRQ_ENABLED = -52,
- I40E_ERR_ADMIN_QUEUE_ERROR = -53,
- I40E_ERR_ADMIN_QUEUE_TIMEOUT = -54,
- I40E_ERR_BUF_TOO_SHORT = -55,
- I40E_ERR_ADMIN_QUEUE_FULL = -56,
- I40E_ERR_ADMIN_QUEUE_NO_WORK = -57,
- I40E_ERR_BAD_IWARP_CQE = -58,
- I40E_ERR_NVM_BLANK_MODE = -59,
- I40E_ERR_NOT_IMPLEMENTED = -60,
- I40E_ERR_PE_DOORBELL_NOT_ENABLED = -61,
- I40E_ERR_DIAG_TEST_FAILED = -62,
- I40E_ERR_NOT_READY = -63,
- I40E_NOT_SUPPORTED = -64,
- I40E_ERR_FIRMWARE_API_VERSION = -65,
- I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66,
-};
-
-#endif /* _I40E_STATUS_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
deleted file mode 100644
index 3b5a63b..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ /dev/null
@@ -1,524 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_TXRX_H_
-#define _I40E_TXRX_H_
-
-/* Interrupt Throttling and Rate Limiting Goodies */
-#define I40E_DEFAULT_IRQ_WORK 256
-
-/* The datasheet for the X710 and XL710 indicate that the maximum value for
- * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec
- * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing
- * the register value which is divided by 2 lets use the actual values and
- * avoid an excessive amount of translation.
- */
-#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */
-#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */
-#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */
-#define I40E_ITR_100K 10 /* all values below must be even */
-#define I40E_ITR_50K 20
-#define I40E_ITR_20K 50
-#define I40E_ITR_18K 60
-#define I40E_ITR_8K 122
-#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */
-#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC)
-#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK)
-#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC))
-
-#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC)
-#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC)
-
-/* 0x40 is the enable bit for interrupt rate limiting, and must be set if
- * the value of the rate limit is non-zero
- */
-#define INTRL_ENA BIT(6)
-#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */
-#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2)
-#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0)
-#define I40E_INTRL_8K 125 /* 8000 ints/sec */
-#define I40E_INTRL_62K 16 /* 62500 ints/sec */
-#define I40E_INTRL_83K 12 /* 83333 ints/sec */
-
-#define I40E_QUEUE_END_OF_LIST 0x7FF
-
-/* this enum matches hardware bits and is meant to be used by DYN_CTLN
- * registers and QINT registers or more generally anywhere in the manual
- * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
- * register but instead is a special value meaning "don't update" ITR0/1/2.
- */
-enum i40e_dyn_idx_t {
- I40E_IDX_ITR0 = 0,
- I40E_IDX_ITR1 = 1,
- I40E_IDX_ITR2 = 2,
- I40E_ITR_NONE = 3 /* ITR_NONE must not be used as an index */
-};
-
-/* these are indexes into ITRN registers */
-#define I40E_RX_ITR I40E_IDX_ITR0
-#define I40E_TX_ITR I40E_IDX_ITR1
-#define I40E_PE_ITR I40E_IDX_ITR2
-
-/* Supported RSS offloads */
-#define I40E_DEFAULT_RSS_HENA ( \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \
- BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
-
-#define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
-
-/* Supported Rx Buffer Sizes (a multiple of 128) */
-#define I40E_RXBUFFER_256 256
-#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */
-#define I40E_RXBUFFER_2048 2048
-#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */
-#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */
-
-/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
- * reserve 2 more, and skb_shared_info adds an additional 384 bytes more,
- * this adds up to 512 bytes of extra data meaning the smallest allocation
- * we could have is 1K.
- * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab)
- * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
- */
-#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
-#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
-#define i40e_rx_desc i40e_32byte_rx_desc
-
-#define I40E_RX_DMA_ATTR \
- (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
-
-/* Attempt to maximize the headroom available for incoming frames. We
- * use a 2K buffer for receives and need 1536/1534 to store the data for
- * the frame. This leaves us with 512 bytes of room. From that we need
- * to deduct the space needed for the shared info and the padding needed
- * to IP align the frame.
- *
- * Note: For cache line sizes 256 or larger this value is going to end
- * up negative. In these cases we should fall back to the legacy
- * receive path.
- */
-#if (PAGE_SIZE < 8192)
-#define I40E_2K_TOO_SMALL_WITH_PADDING \
-((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
-
-static inline int i40e_compute_pad(int rx_buf_len)
-{
- int page_size, pad_size;
-
- page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
- pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
-
- return pad_size;
-}
-
-static inline int i40e_skb_pad(void)
-{
- int rx_buf_len;
-
- /* If a 2K buffer cannot handle a standard Ethernet frame then
- * optimize padding for a 3K buffer instead of a 1.5K buffer.
- *
- * For a 3K buffer we need to add enough padding to allow for
- * tailroom due to NET_IP_ALIGN possibly shifting us out of
- * cache-line alignment.
- */
- if (I40E_2K_TOO_SMALL_WITH_PADDING)
- rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
- else
- rx_buf_len = I40E_RXBUFFER_1536;
-
- /* if needed make room for NET_IP_ALIGN */
- rx_buf_len -= NET_IP_ALIGN;
-
- return i40e_compute_pad(rx_buf_len);
-}
-
-#define I40E_SKB_PAD i40e_skb_pad()
-#else
-#define I40E_2K_TOO_SMALL_WITH_PADDING false
-#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#endif
-
-/**
- * i40e_test_staterr - tests bits in Rx descriptor status and error fields
- * @rx_desc: pointer to receive descriptor (in le64 format)
- * @stat_err_bits: value to mask
- *
- * This function does some fast chicanery in order to return the
- * value of the mask which is really only used for boolean tests.
- * The status_error_len doesn't need to be shifted because it begins
- * at offset zero.
- */
-static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
- const u64 stat_err_bits)
-{
- return !!(rx_desc->wb.qword1.status_error_len &
- cpu_to_le64(stat_err_bits));
-}
-
-/* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */
-#define I40E_RX_INCREMENT(r, i) \
- do { \
- (i)++; \
- if ((i) == (r)->count) \
- i = 0; \
- r->next_to_clean = i; \
- } while (0)
-
-#define I40E_RX_NEXT_DESC(r, i, n) \
- do { \
- (i)++; \
- if ((i) == (r)->count) \
- i = 0; \
- (n) = I40E_RX_DESC((r), (i)); \
- } while (0)
-
-#define I40E_RX_NEXT_DESC_PREFETCH(r, i, n) \
- do { \
- I40E_RX_NEXT_DESC((r), (i), (n)); \
- prefetch((n)); \
- } while (0)
-
-#define I40E_MAX_BUFFER_TXD 8
-#define I40E_MIN_TX_LEN 17
-
-/* The size limit for a transmit buffer in a descriptor is (16K - 1).
- * In order to align with the read requests we will align the value to
- * the nearest 4K which represents our maximum read request size.
- */
-#define I40E_MAX_READ_REQ_SIZE 4096
-#define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1)
-#define I40E_MAX_DATA_PER_TXD_ALIGNED \
- (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1))
-
-/**
- * i40e_txd_use_count - estimate the number of descriptors needed for Tx
- * @size: transmit request size in bytes
- *
- * Due to hardware alignment restrictions (4K alignment), we need to
- * assume that we can have no more than 12K of data per descriptor, even
- * though each descriptor can take up to 16K - 1 bytes of aligned memory.
- * Thus, we need to divide by 12K. But division is slow! Instead,
- * we decompose the operation into shifts and one relatively cheap
- * multiply operation.
- *
- * To divide by 12K, we first divide by 4K, then divide by 3:
- * To divide by 4K, shift right by 12 bits
- * To divide by 3, multiply by 85, then divide by 256
- * (Divide by 256 is done by shifting right by 8 bits)
- * Finally, we add one to round up. Because 256 isn't an exact multiple of
- * 3, we'll underestimate near each multiple of 12K. This is actually more
- * accurate as we have 4K - 1 of wiggle room that we can fit into the last
- * segment. For our purposes this is accurate out to 1M which is orders of
- * magnitude greater than our largest possible GSO size.
- *
- * This would then be implemented as:
- * return (((size >> 12) * 85) >> 8) + 1;
- *
- * Since multiplication and division are commutative, we can reorder
- * operations into:
- * return ((size * 85) >> 20) + 1;
- */
-static inline unsigned int i40e_txd_use_count(unsigned int size)
-{
- return ((size * 85) >> 20) + 1;
-}
-
-/* Tx Descriptors needed, worst case */
-#define DESC_NEEDED (MAX_SKB_FRAGS + 6)
-#define I40E_MIN_DESC_PENDING 4
-
-#define I40E_TX_FLAGS_HW_VLAN BIT(1)
-#define I40E_TX_FLAGS_SW_VLAN BIT(2)
-#define I40E_TX_FLAGS_TSO BIT(3)
-#define I40E_TX_FLAGS_IPV4 BIT(4)
-#define I40E_TX_FLAGS_IPV6 BIT(5)
-#define I40E_TX_FLAGS_FCCRC BIT(6)
-#define I40E_TX_FLAGS_FSO BIT(7)
-#define I40E_TX_FLAGS_FD_SB BIT(9)
-#define I40E_TX_FLAGS_VXLAN_TUNNEL BIT(10)
-#define I40E_TX_FLAGS_VLAN_MASK 0xffff0000
-#define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000
-#define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29
-#define I40E_TX_FLAGS_VLAN_SHIFT 16
-
-struct i40e_tx_buffer {
- struct i40e_tx_desc *next_to_watch;
- union {
- struct sk_buff *skb;
- void *raw_buf;
- };
- unsigned int bytecount;
- unsigned short gso_segs;
-
- DEFINE_DMA_UNMAP_ADDR(dma);
- DEFINE_DMA_UNMAP_LEN(len);
- u32 tx_flags;
-};
-
-struct i40e_rx_buffer {
- dma_addr_t dma;
- struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
- __u32 page_offset;
-#else
- __u16 page_offset;
-#endif
- __u16 pagecnt_bias;
-};
-
-struct i40e_queue_stats {
- u64 packets;
- u64 bytes;
-};
-
-struct i40e_tx_queue_stats {
- u64 restart_queue;
- u64 tx_busy;
- u64 tx_done_old;
- u64 tx_linearize;
- u64 tx_force_wb;
- int prev_pkt_ctr;
- u64 tx_lost_interrupt;
-};
-
-struct i40e_rx_queue_stats {
- u64 non_eop_descs;
- u64 alloc_page_failed;
- u64 alloc_buff_failed;
- u64 page_reuse_count;
- u64 realloc_count;
-};
-
-enum i40e_ring_state_t {
- __I40E_TX_FDIR_INIT_DONE,
- __I40E_TX_XPS_INIT_DONE,
- __I40E_RING_STATE_NBITS /* must be last */
-};
-
-/* some useful defines for virtchannel interface, which
- * is the only remaining user of header split
- */
-#define I40E_RX_DTYPE_NO_SPLIT 0
-#define I40E_RX_DTYPE_HEADER_SPLIT 1
-#define I40E_RX_DTYPE_SPLIT_ALWAYS 2
-#define I40E_RX_SPLIT_L2 0x1
-#define I40E_RX_SPLIT_IP 0x2
-#define I40E_RX_SPLIT_TCP_UDP 0x4
-#define I40E_RX_SPLIT_SCTP 0x8
-
-/* struct that defines a descriptor ring, associated with a VSI */
-struct i40e_ring {
- struct i40e_ring *next; /* pointer to next ring in q_vector */
- void *desc; /* Descriptor ring memory */
- struct device *dev; /* Used for DMA mapping */
- struct net_device *netdev; /* netdev ring maps to */
- union {
- struct i40e_tx_buffer *tx_bi;
- struct i40e_rx_buffer *rx_bi;
- };
- DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
- u16 queue_index; /* Queue number of ring */
- u8 dcb_tc; /* Traffic class of ring */
- u8 __iomem *tail;
-
- /* high bit set means dynamic, use accessors routines to read/write.
- * hardware only supports 2us resolution for the ITR registers.
- * these values always store the USER setting, and must be converted
- * before programming to a register.
- */
- u16 itr_setting;
-
- u16 count; /* Number of descriptors */
- u16 reg_idx; /* HW register index of the ring */
- u16 rx_buf_len;
-
- /* used in interrupt processing */
- u16 next_to_use;
- u16 next_to_clean;
-
- u8 atr_sample_rate;
- u8 atr_count;
-
- bool ring_active; /* is ring online or not */
- bool arm_wb; /* do something to arm write back */
- u8 packet_stride;
-
- u16 flags;
-#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
-#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1)
-
- /* stats structs */
- struct i40e_queue_stats stats;
- struct u64_stats_sync syncp;
- union {
- struct i40e_tx_queue_stats tx_stats;
- struct i40e_rx_queue_stats rx_stats;
- };
-
- unsigned int size; /* length of descriptor ring in bytes */
- dma_addr_t dma; /* physical address of ring */
-
- struct i40e_vsi *vsi; /* Backreference to associated VSI */
- struct i40e_q_vector *q_vector; /* Backreference to associated vector */
-
- struct rcu_head rcu; /* to avoid race on free */
- u16 next_to_alloc;
- struct sk_buff *skb; /* When i40evf_clean_rx_ring_irq() must
- * return before it sees the EOP for
- * the current packet, we save that skb
- * here and resume receiving this
- * packet the next time
- * i40evf_clean_rx_ring_irq() is called
- * for this ring.
- */
-} ____cacheline_internodealigned_in_smp;
-
-static inline bool ring_uses_build_skb(struct i40e_ring *ring)
-{
- return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED);
-}
-
-static inline void set_ring_build_skb_enabled(struct i40e_ring *ring)
-{
- ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
-}
-
-static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
-{
- ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
-}
-
-#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002
-#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002
-#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e
-#define I40E_ITR_ADAPTIVE_LATENCY 0x8000
-#define I40E_ITR_ADAPTIVE_BULK 0x0000
-#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY))
-
-struct i40e_ring_container {
- struct i40e_ring *ring; /* pointer to linked list of ring(s) */
- unsigned long next_update; /* jiffies value of next update */
- unsigned int total_bytes; /* total bytes processed this int */
- unsigned int total_packets; /* total packets processed this int */
- u16 count;
- u16 target_itr; /* target ITR setting for ring(s) */
- u16 current_itr; /* current ITR setting for ring(s) */
-};
-
-/* iterator for handling rings in ring container */
-#define i40e_for_each_ring(pos, head) \
- for (pos = (head).ring; pos != NULL; pos = pos->next)
-
-static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
-{
-#if (PAGE_SIZE < 8192)
- if (ring->rx_buf_len > (PAGE_SIZE / 2))
- return 1;
-#endif
- return 0;
-}
-
-#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring))
-
-bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
-netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
-void i40evf_clean_tx_ring(struct i40e_ring *tx_ring);
-void i40evf_clean_rx_ring(struct i40e_ring *rx_ring);
-int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring);
-int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring);
-void i40evf_free_tx_resources(struct i40e_ring *tx_ring);
-void i40evf_free_rx_resources(struct i40e_ring *rx_ring);
-int i40evf_napi_poll(struct napi_struct *napi, int budget);
-void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
-u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw);
-void i40evf_detect_recover_hung(struct i40e_vsi *vsi);
-int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
-bool __i40evf_chk_linearize(struct sk_buff *skb);
-
-/**
- * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
- * @skb: send buffer
- * @tx_ring: ring to send buffer on
- *
- * Returns number of data descriptors needed for this skb. Returns 0 to indicate
- * there is not enough descriptors available in this ring since we need at least
- * one descriptor.
- **/
-static inline int i40e_xmit_descriptor_count(struct sk_buff *skb)
-{
- const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
- unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
- int count = 0, size = skb_headlen(skb);
-
- for (;;) {
- count += i40e_txd_use_count(size);
-
- if (!nr_frags--)
- break;
-
- size = skb_frag_size(frag++);
- }
-
- return count;
-}
-
-/**
- * i40e_maybe_stop_tx - 1st level check for Tx stop conditions
- * @tx_ring: the ring to be checked
- * @size: the size buffer we want to assure is available
- *
- * Returns 0 if stop is not needed
- **/
-static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
-{
- if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
- return 0;
- return __i40evf_maybe_stop_tx(tx_ring, size);
-}
-
-/**
- * i40e_chk_linearize - Check if there are more than 8 fragments per packet
- * @skb: send buffer
- * @count: number of buffers used
- *
- * Note: Our HW can't scatter-gather more than 8 fragments to build
- * a packet on the wire and so we need to figure out the cases where we
- * need to linearize the skb.
- **/
-static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
-{
- /* Both TSO and single send will work if count is less than 8 */
- if (likely(count < I40E_MAX_BUFFER_TXD))
- return false;
-
- if (skb_is_gso(skb))
- return __i40evf_chk_linearize(skb);
-
- /* we can support up to 8 data buffers for a single send */
- return count != I40E_MAX_BUFFER_TXD;
-}
-/**
- * @ring: Tx ring to find the netdev equivalent of
- **/
-static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring)
-{
- return netdev_get_tx_queue(ring->netdev, ring->queue_index);
-}
-#endif /* _I40E_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
deleted file mode 100644
index 094387d..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ /dev/null
@@ -1,1496 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_TYPE_H_
-#define _I40E_TYPE_H_
-
-#include "i40e_status.h"
-#include "i40e_osdep.h"
-#include "i40e_register.h"
-#include "i40e_adminq.h"
-#include "i40e_hmc.h"
-#include "i40e_lan_hmc.h"
-#include "i40e_devids.h"
-
-/* I40E_MASK is a macro used on 32 bit registers */
-#define I40E_MASK(mask, shift) ((u32)(mask) << (shift))
-
-#define I40E_MAX_VSI_QP 16
-#define I40E_MAX_VF_VSI 3
-#define I40E_MAX_CHAINED_RX_BUFFERS 5
-#define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16
-
-/* Max default timeout in ms, */
-#define I40E_MAX_NVM_TIMEOUT 18000
-
-/* Max timeout in ms for the phy to respond */
-#define I40E_MAX_PHY_TIMEOUT 500
-
-/* Switch from ms to the 1usec global time (this is the GTIME resolution) */
-#define I40E_MS_TO_GTIME(time) ((time) * 1000)
-
-/* forward declaration */
-struct i40e_hw;
-typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
-
-/* Data type manipulation macros. */
-
-#define I40E_DESC_UNUSED(R) \
- ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
- (R)->next_to_clean - (R)->next_to_use - 1)
-
-/* bitfields for Tx queue mapping in QTX_CTL */
-#define I40E_QTX_CTL_VF_QUEUE 0x0
-#define I40E_QTX_CTL_VM_QUEUE 0x1
-#define I40E_QTX_CTL_PF_QUEUE 0x2
-
-/* debug masks - set these bits in hw->debug_mask to control output */
-enum i40e_debug_mask {
- I40E_DEBUG_INIT = 0x00000001,
- I40E_DEBUG_RELEASE = 0x00000002,
-
- I40E_DEBUG_LINK = 0x00000010,
- I40E_DEBUG_PHY = 0x00000020,
- I40E_DEBUG_HMC = 0x00000040,
- I40E_DEBUG_NVM = 0x00000080,
- I40E_DEBUG_LAN = 0x00000100,
- I40E_DEBUG_FLOW = 0x00000200,
- I40E_DEBUG_DCB = 0x00000400,
- I40E_DEBUG_DIAG = 0x00000800,
- I40E_DEBUG_FD = 0x00001000,
- I40E_DEBUG_PACKAGE = 0x00002000,
-
- I40E_DEBUG_AQ_MESSAGE = 0x01000000,
- I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000,
- I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000,
- I40E_DEBUG_AQ_COMMAND = 0x06000000,
- I40E_DEBUG_AQ = 0x0F000000,
-
- I40E_DEBUG_USER = 0xF0000000,
-
- I40E_DEBUG_ALL = 0xFFFFFFFF
-};
-
-/* These are structs for managing the hardware information and the operations.
- * The structures of function pointers are filled out at init time when we
- * know for sure exactly which hardware we're working with. This gives us the
- * flexibility of using the same main driver code but adapting to slightly
- * different hardware needs as new parts are developed. For this architecture,
- * the Firmware and AdminQ are intended to insulate the driver from most of the
- * future changes, but these structures will also do part of the job.
- */
-enum i40e_mac_type {
- I40E_MAC_UNKNOWN = 0,
- I40E_MAC_XL710,
- I40E_MAC_VF,
- I40E_MAC_X722,
- I40E_MAC_X722_VF,
- I40E_MAC_GENERIC,
-};
-
-enum i40e_media_type {
- I40E_MEDIA_TYPE_UNKNOWN = 0,
- I40E_MEDIA_TYPE_FIBER,
- I40E_MEDIA_TYPE_BASET,
- I40E_MEDIA_TYPE_BACKPLANE,
- I40E_MEDIA_TYPE_CX4,
- I40E_MEDIA_TYPE_DA,
- I40E_MEDIA_TYPE_VIRTUAL
-};
-
-enum i40e_fc_mode {
- I40E_FC_NONE = 0,
- I40E_FC_RX_PAUSE,
- I40E_FC_TX_PAUSE,
- I40E_FC_FULL,
- I40E_FC_PFC,
- I40E_FC_DEFAULT
-};
-
-enum i40e_set_fc_aq_failures {
- I40E_SET_FC_AQ_FAIL_NONE = 0,
- I40E_SET_FC_AQ_FAIL_GET = 1,
- I40E_SET_FC_AQ_FAIL_SET = 2,
- I40E_SET_FC_AQ_FAIL_UPDATE = 4,
- I40E_SET_FC_AQ_FAIL_SET_UPDATE = 6
-};
-
-enum i40e_vsi_type {
- I40E_VSI_MAIN = 0,
- I40E_VSI_VMDQ1 = 1,
- I40E_VSI_VMDQ2 = 2,
- I40E_VSI_CTRL = 3,
- I40E_VSI_FCOE = 4,
- I40E_VSI_MIRROR = 5,
- I40E_VSI_SRIOV = 6,
- I40E_VSI_FDIR = 7,
- I40E_VSI_TYPE_UNKNOWN
-};
-
-enum i40e_queue_type {
- I40E_QUEUE_TYPE_RX = 0,
- I40E_QUEUE_TYPE_TX,
- I40E_QUEUE_TYPE_PE_CEQ,
- I40E_QUEUE_TYPE_UNKNOWN
-};
-
-struct i40e_link_status {
- enum i40e_aq_phy_type phy_type;
- enum i40e_aq_link_speed link_speed;
- u8 link_info;
- u8 an_info;
- u8 req_fec_info;
- u8 fec_info;
- u8 ext_info;
- u8 loopback;
- /* is Link Status Event notification to SW enabled */
- bool lse_enable;
- u16 max_frame_size;
- bool crc_enable;
- u8 pacing;
- u8 requested_speeds;
- u8 module_type[3];
- /* 1st byte: module identifier */
-#define I40E_MODULE_TYPE_SFP 0x03
-#define I40E_MODULE_TYPE_QSFP 0x0D
- /* 2nd byte: ethernet compliance codes for 10/40G */
-#define I40E_MODULE_TYPE_40G_ACTIVE 0x01
-#define I40E_MODULE_TYPE_40G_LR4 0x02
-#define I40E_MODULE_TYPE_40G_SR4 0x04
-#define I40E_MODULE_TYPE_40G_CR4 0x08
-#define I40E_MODULE_TYPE_10G_BASE_SR 0x10
-#define I40E_MODULE_TYPE_10G_BASE_LR 0x20
-#define I40E_MODULE_TYPE_10G_BASE_LRM 0x40
-#define I40E_MODULE_TYPE_10G_BASE_ER 0x80
- /* 3rd byte: ethernet compliance codes for 1G */
-#define I40E_MODULE_TYPE_1000BASE_SX 0x01
-#define I40E_MODULE_TYPE_1000BASE_LX 0x02
-#define I40E_MODULE_TYPE_1000BASE_CX 0x04
-#define I40E_MODULE_TYPE_1000BASE_T 0x08
-};
-
-struct i40e_phy_info {
- struct i40e_link_status link_info;
- struct i40e_link_status link_info_old;
- bool get_link_info;
- enum i40e_media_type media_type;
- /* all the phy types the NVM is capable of */
- u64 phy_types;
-};
-
-#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII)
-#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX)
-#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4)
-#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR)
-#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4)
-#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI)
-#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI)
-#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI)
-#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI)
-#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI)
-#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU)
-#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU)
-#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC)
-#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC)
-#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX)
-#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T)
-#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T)
-#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR)
-#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR)
-#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU)
-#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1)
-#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4)
-#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4)
-#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4)
-#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX)
-#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX)
-#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \
- BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL)
-#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2)
-/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some
- * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit
- * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So,
- * a shift is needed to adjust for this with values larger than 31. The
- * only affected values are I40E_PHY_TYPE_25GBASE_*.
- */
-#define I40E_PHY_TYPE_OFFSET 1
-#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \
- I40E_PHY_TYPE_OFFSET)
-#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \
- I40E_PHY_TYPE_OFFSET)
-#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \
- I40E_PHY_TYPE_OFFSET)
-#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \
- I40E_PHY_TYPE_OFFSET)
-#define I40E_HW_CAP_MAX_GPIO 30
-/* Capabilities of a PF or a VF or the whole device */
-struct i40e_hw_capabilities {
- u32 switch_mode;
-#define I40E_NVM_IMAGE_TYPE_EVB 0x0
-#define I40E_NVM_IMAGE_TYPE_CLOUD 0x2
-#define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3
-
- u32 management_mode;
- u32 mng_protocols_over_mctp;
-#define I40E_MNG_PROTOCOL_PLDM 0x2
-#define I40E_MNG_PROTOCOL_OEM_COMMANDS 0x4
-#define I40E_MNG_PROTOCOL_NCSI 0x8
- u32 npar_enable;
- u32 os2bmc;
- u32 valid_functions;
- bool sr_iov_1_1;
- bool vmdq;
- bool evb_802_1_qbg; /* Edge Virtual Bridging */
- bool evb_802_1_qbh; /* Bridge Port Extension */
- bool dcb;
- bool fcoe;
- bool iscsi; /* Indicates iSCSI enabled */
- bool flex10_enable;
- bool flex10_capable;
- u32 flex10_mode;
-#define I40E_FLEX10_MODE_UNKNOWN 0x0
-#define I40E_FLEX10_MODE_DCC 0x1
-#define I40E_FLEX10_MODE_DCI 0x2
-
- u32 flex10_status;
-#define I40E_FLEX10_STATUS_DCC_ERROR 0x1
-#define I40E_FLEX10_STATUS_VC_MODE 0x2
-
- bool sec_rev_disabled;
- bool update_disabled;
-#define I40E_NVM_MGMT_SEC_REV_DISABLED 0x1
-#define I40E_NVM_MGMT_UPDATE_DISABLED 0x2
-
- bool mgmt_cem;
- bool ieee_1588;
- bool iwarp;
- bool fd;
- u32 fd_filters_guaranteed;
- u32 fd_filters_best_effort;
- bool rss;
- u32 rss_table_size;
- u32 rss_table_entry_width;
- bool led[I40E_HW_CAP_MAX_GPIO];
- bool sdp[I40E_HW_CAP_MAX_GPIO];
- u32 nvm_image_type;
- u32 num_flow_director_filters;
- u32 num_vfs;
- u32 vf_base_id;
- u32 num_vsis;
- u32 num_rx_qp;
- u32 num_tx_qp;
- u32 base_queue;
- u32 num_msix_vectors;
- u32 num_msix_vectors_vf;
- u32 led_pin_num;
- u32 sdp_pin_num;
- u32 mdio_port_num;
- u32 mdio_port_mode;
- u8 rx_buf_chain_len;
- u32 enabled_tcmap;
- u32 maxtc;
- u64 wr_csr_prot;
-};
-
-struct i40e_mac_info {
- enum i40e_mac_type type;
- u8 addr[ETH_ALEN];
- u8 perm_addr[ETH_ALEN];
- u8 san_addr[ETH_ALEN];
- u16 max_fcoeq;
-};
-
-enum i40e_aq_resources_ids {
- I40E_NVM_RESOURCE_ID = 1
-};
-
-enum i40e_aq_resource_access_type {
- I40E_RESOURCE_READ = 1,
- I40E_RESOURCE_WRITE
-};
-
-struct i40e_nvm_info {
- u64 hw_semaphore_timeout; /* usec global time (GTIME resolution) */
- u32 timeout; /* [ms] */
- u16 sr_size; /* Shadow RAM size in words */
- bool blank_nvm_mode; /* is NVM empty (no FW present)*/
- u16 version; /* NVM package version */
- u32 eetrack; /* NVM data version */
- u32 oem_ver; /* OEM version info */
-};
-
-/* definitions used in NVM update support */
-
-enum i40e_nvmupd_cmd {
- I40E_NVMUPD_INVALID,
- I40E_NVMUPD_READ_CON,
- I40E_NVMUPD_READ_SNT,
- I40E_NVMUPD_READ_LCB,
- I40E_NVMUPD_READ_SA,
- I40E_NVMUPD_WRITE_ERA,
- I40E_NVMUPD_WRITE_CON,
- I40E_NVMUPD_WRITE_SNT,
- I40E_NVMUPD_WRITE_LCB,
- I40E_NVMUPD_WRITE_SA,
- I40E_NVMUPD_CSUM_CON,
- I40E_NVMUPD_CSUM_SA,
- I40E_NVMUPD_CSUM_LCB,
- I40E_NVMUPD_STATUS,
- I40E_NVMUPD_EXEC_AQ,
- I40E_NVMUPD_GET_AQ_RESULT,
- I40E_NVMUPD_GET_AQ_EVENT,
-};
-
-enum i40e_nvmupd_state {
- I40E_NVMUPD_STATE_INIT,
- I40E_NVMUPD_STATE_READING,
- I40E_NVMUPD_STATE_WRITING,
- I40E_NVMUPD_STATE_INIT_WAIT,
- I40E_NVMUPD_STATE_WRITE_WAIT,
- I40E_NVMUPD_STATE_ERROR
-};
-
-/* nvm_access definition and its masks/shifts need to be accessible to
- * application, core driver, and shared code. Where is the right file?
- */
-#define I40E_NVM_READ 0xB
-#define I40E_NVM_WRITE 0xC
-
-#define I40E_NVM_MOD_PNT_MASK 0xFF
-
-#define I40E_NVM_TRANS_SHIFT 8
-#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT)
-#define I40E_NVM_PRESERVATION_FLAGS_SHIFT 12
-#define I40E_NVM_PRESERVATION_FLAGS_MASK \
- (0x3 << I40E_NVM_PRESERVATION_FLAGS_SHIFT)
-#define I40E_NVM_PRESERVATION_FLAGS_SELECTED 0x01
-#define I40E_NVM_PRESERVATION_FLAGS_ALL 0x02
-#define I40E_NVM_CON 0x0
-#define I40E_NVM_SNT 0x1
-#define I40E_NVM_LCB 0x2
-#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB)
-#define I40E_NVM_ERA 0x4
-#define I40E_NVM_CSUM 0x8
-#define I40E_NVM_AQE 0xe
-#define I40E_NVM_EXEC 0xf
-
-#define I40E_NVM_ADAPT_SHIFT 16
-#define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT)
-
-#define I40E_NVMUPD_MAX_DATA 4096
-#define I40E_NVMUPD_IFACE_TIMEOUT 2 /* seconds */
-
-struct i40e_nvm_access {
- u32 command;
- u32 config;
- u32 offset; /* in bytes */
- u32 data_size; /* in bytes */
- u8 data[1];
-};
-
-/* (Q)SFP module access definitions */
-#define I40E_I2C_EEPROM_DEV_ADDR 0xA0
-#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2
-#define I40E_MODULE_TYPE_ADDR 0x00
-#define I40E_MODULE_REVISION_ADDR 0x01
-#define I40E_MODULE_SFF_8472_COMP 0x5E
-#define I40E_MODULE_SFF_8472_SWAP 0x5C
-#define I40E_MODULE_SFF_ADDR_MODE 0x04
-#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D
-#define I40E_MODULE_TYPE_QSFP28 0x11
-#define I40E_MODULE_QSFP_MAX_LEN 640
-
-/* PCI bus types */
-enum i40e_bus_type {
- i40e_bus_type_unknown = 0,
- i40e_bus_type_pci,
- i40e_bus_type_pcix,
- i40e_bus_type_pci_express,
- i40e_bus_type_reserved
-};
-
-/* PCI bus speeds */
-enum i40e_bus_speed {
- i40e_bus_speed_unknown = 0,
- i40e_bus_speed_33 = 33,
- i40e_bus_speed_66 = 66,
- i40e_bus_speed_100 = 100,
- i40e_bus_speed_120 = 120,
- i40e_bus_speed_133 = 133,
- i40e_bus_speed_2500 = 2500,
- i40e_bus_speed_5000 = 5000,
- i40e_bus_speed_8000 = 8000,
- i40e_bus_speed_reserved
-};
-
-/* PCI bus widths */
-enum i40e_bus_width {
- i40e_bus_width_unknown = 0,
- i40e_bus_width_pcie_x1 = 1,
- i40e_bus_width_pcie_x2 = 2,
- i40e_bus_width_pcie_x4 = 4,
- i40e_bus_width_pcie_x8 = 8,
- i40e_bus_width_32 = 32,
- i40e_bus_width_64 = 64,
- i40e_bus_width_reserved
-};
-
-/* Bus parameters */
-struct i40e_bus_info {
- enum i40e_bus_speed speed;
- enum i40e_bus_width width;
- enum i40e_bus_type type;
-
- u16 func;
- u16 device;
- u16 lan_id;
- u16 bus_id;
-};
-
-/* Flow control (FC) parameters */
-struct i40e_fc_info {
- enum i40e_fc_mode current_mode; /* FC mode in effect */
- enum i40e_fc_mode requested_mode; /* FC mode requested by caller */
-};
-
-#define I40E_MAX_TRAFFIC_CLASS 8
-#define I40E_MAX_USER_PRIORITY 8
-#define I40E_DCBX_MAX_APPS 32
-#define I40E_LLDPDU_SIZE 1500
-
-/* IEEE 802.1Qaz ETS Configuration data */
-struct i40e_ieee_ets_config {
- u8 willing;
- u8 cbs;
- u8 maxtcs;
- u8 prioritytable[I40E_MAX_TRAFFIC_CLASS];
- u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS];
- u8 tsatable[I40E_MAX_TRAFFIC_CLASS];
-};
-
-/* IEEE 802.1Qaz ETS Recommendation data */
-struct i40e_ieee_ets_recommend {
- u8 prioritytable[I40E_MAX_TRAFFIC_CLASS];
- u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS];
- u8 tsatable[I40E_MAX_TRAFFIC_CLASS];
-};
-
-/* IEEE 802.1Qaz PFC Configuration data */
-struct i40e_ieee_pfc_config {
- u8 willing;
- u8 mbc;
- u8 pfccap;
- u8 pfcenable;
-};
-
-/* IEEE 802.1Qaz Application Priority data */
-struct i40e_ieee_app_priority_table {
- u8 priority;
- u8 selector;
- u16 protocolid;
-};
-
-struct i40e_dcbx_config {
- u32 numapps;
- u32 tlv_status; /* CEE mode TLV status */
- struct i40e_ieee_ets_config etscfg;
- struct i40e_ieee_ets_recommend etsrec;
- struct i40e_ieee_pfc_config pfc;
- struct i40e_ieee_app_priority_table app[I40E_DCBX_MAX_APPS];
-};
-
-/* Port hardware description */
-struct i40e_hw {
- u8 __iomem *hw_addr;
- void *back;
-
- /* subsystem structs */
- struct i40e_phy_info phy;
- struct i40e_mac_info mac;
- struct i40e_bus_info bus;
- struct i40e_nvm_info nvm;
- struct i40e_fc_info fc;
-
- /* pci info */
- u16 device_id;
- u16 vendor_id;
- u16 subsystem_device_id;
- u16 subsystem_vendor_id;
- u8 revision_id;
- u8 port;
- bool adapter_stopped;
-
- /* capabilities for entire device and PCI func */
- struct i40e_hw_capabilities dev_caps;
- struct i40e_hw_capabilities func_caps;
-
- /* Flow Director shared filter space */
- u16 fdir_shared_filter_count;
-
- /* device profile info */
- u8 pf_id;
- u16 main_vsi_seid;
-
- /* for multi-function MACs */
- u16 partition_id;
- u16 num_partitions;
- u16 num_ports;
-
- /* Closest numa node to the device */
- u16 numa_node;
-
- /* Admin Queue info */
- struct i40e_adminq_info aq;
-
- /* state of nvm update process */
- enum i40e_nvmupd_state nvmupd_state;
- struct i40e_aq_desc nvm_wb_desc;
- struct i40e_aq_desc nvm_aq_event_desc;
- struct i40e_virt_mem nvm_buff;
- bool nvm_release_on_done;
- u16 nvm_wait_opcode;
-
- /* HMC info */
- struct i40e_hmc_info hmc; /* HMC info struct */
-
- /* LLDP/DCBX Status */
- u16 dcbx_status;
-
-#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1)
-#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2)
-
- /* DCBX info */
- struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */
- struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */
- struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
-
- /* Used in set switch config AQ command */
- u16 switch_tag;
- u16 first_tag;
- u16 second_tag;
-
- /* debug mask */
- u32 debug_mask;
- char err_str[16];
-};
-
-static inline bool i40e_is_vf(struct i40e_hw *hw)
-{
- return (hw->mac.type == I40E_MAC_VF ||
- hw->mac.type == I40E_MAC_X722_VF);
-}
-
-struct i40e_driver_version {
- u8 major_version;
- u8 minor_version;
- u8 build_version;
- u8 subbuild_version;
- u8 driver_string[32];
-};
-
-/* RX Descriptors */
-union i40e_16byte_rx_desc {
- struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
- } read;
- struct {
- struct {
- struct {
- union {
- __le16 mirroring_status;
- __le16 fcoe_ctx_id;
- } mirr_fcoe;
- __le16 l2tag1;
- } lo_dword;
- union {
- __le32 rss; /* RSS Hash */
- __le32 fd_id; /* Flow director filter id */
- __le32 fcoe_param; /* FCoE DDP Context id */
- } hi_dword;
- } qword0;
- struct {
- /* ext status/error/pktype/length */
- __le64 status_error_len;
- } qword1;
- } wb; /* writeback */
-};
-
-union i40e_32byte_rx_desc {
- struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
- /* bit 0 of hdr_buffer_addr is DD bit */
- __le64 rsvd1;
- __le64 rsvd2;
- } read;
- struct {
- struct {
- struct {
- union {
- __le16 mirroring_status;
- __le16 fcoe_ctx_id;
- } mirr_fcoe;
- __le16 l2tag1;
- } lo_dword;
- union {
- __le32 rss; /* RSS Hash */
- __le32 fcoe_param; /* FCoE DDP Context id */
- /* Flow director filter id in case of
- * Programming status desc WB
- */
- __le32 fd_id;
- } hi_dword;
- } qword0;
- struct {
- /* status/error/pktype/length */
- __le64 status_error_len;
- } qword1;
- struct {
- __le16 ext_status; /* extended status */
- __le16 rsvd;
- __le16 l2tag2_1;
- __le16 l2tag2_2;
- } qword2;
- struct {
- union {
- __le32 flex_bytes_lo;
- __le32 pe_status;
- } lo_dword;
- union {
- __le32 flex_bytes_hi;
- __le32 fd_id;
- } hi_dword;
- } qword3;
- } wb; /* writeback */
-};
-
-enum i40e_rx_desc_status_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_DESC_STATUS_DD_SHIFT = 0,
- I40E_RX_DESC_STATUS_EOF_SHIFT = 1,
- I40E_RX_DESC_STATUS_L2TAG1P_SHIFT = 2,
- I40E_RX_DESC_STATUS_L3L4P_SHIFT = 3,
- I40E_RX_DESC_STATUS_CRCP_SHIFT = 4,
- I40E_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */
- I40E_RX_DESC_STATUS_TSYNVALID_SHIFT = 7,
- /* Note: Bit 8 is reserved in X710 and XL710 */
- I40E_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8,
- I40E_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */
- I40E_RX_DESC_STATUS_FLM_SHIFT = 11,
- I40E_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */
- I40E_RX_DESC_STATUS_LPBK_SHIFT = 14,
- I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15,
- I40E_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */
- /* Note: For non-tunnel packets INT_UDP_0 is the right status for
- * UDP header
- */
- I40E_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18,
- I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
-
-#define I40E_RXD_QW1_STATUS_SHIFT 0
-#define I40E_RXD_QW1_STATUS_MASK ((BIT(I40E_RX_DESC_STATUS_LAST) - 1) \
- << I40E_RXD_QW1_STATUS_SHIFT)
-
-#define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT I40E_RX_DESC_STATUS_TSYNINDX_SHIFT
-#define I40E_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \
- I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT)
-
-#define I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT I40E_RX_DESC_STATUS_TSYNVALID_SHIFT
-#define I40E_RXD_QW1_STATUS_TSYNVALID_MASK \
- BIT_ULL(I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT)
-
-enum i40e_rx_desc_fltstat_values {
- I40E_RX_DESC_FLTSTAT_NO_DATA = 0,
- I40E_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */
- I40E_RX_DESC_FLTSTAT_RSV = 2,
- I40E_RX_DESC_FLTSTAT_RSS_HASH = 3,
-};
-
-#define I40E_RXD_QW1_ERROR_SHIFT 19
-#define I40E_RXD_QW1_ERROR_MASK (0xFFUL << I40E_RXD_QW1_ERROR_SHIFT)
-
-enum i40e_rx_desc_error_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_DESC_ERROR_RXE_SHIFT = 0,
- I40E_RX_DESC_ERROR_RECIPE_SHIFT = 1,
- I40E_RX_DESC_ERROR_HBO_SHIFT = 2,
- I40E_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */
- I40E_RX_DESC_ERROR_IPE_SHIFT = 3,
- I40E_RX_DESC_ERROR_L4E_SHIFT = 4,
- I40E_RX_DESC_ERROR_EIPE_SHIFT = 5,
- I40E_RX_DESC_ERROR_OVERSIZE_SHIFT = 6,
- I40E_RX_DESC_ERROR_PPRS_SHIFT = 7
-};
-
-enum i40e_rx_desc_error_l3l4e_fcoe_masks {
- I40E_RX_DESC_ERROR_L3L4E_NONE = 0,
- I40E_RX_DESC_ERROR_L3L4E_PROT = 1,
- I40E_RX_DESC_ERROR_L3L4E_FC = 2,
- I40E_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3,
- I40E_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4
-};
-
-#define I40E_RXD_QW1_PTYPE_SHIFT 30
-#define I40E_RXD_QW1_PTYPE_MASK (0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT)
-
-/* Packet type non-ip values */
-enum i40e_rx_l2_ptype {
- I40E_RX_PTYPE_L2_RESERVED = 0,
- I40E_RX_PTYPE_L2_MAC_PAY2 = 1,
- I40E_RX_PTYPE_L2_TIMESYNC_PAY2 = 2,
- I40E_RX_PTYPE_L2_FIP_PAY2 = 3,
- I40E_RX_PTYPE_L2_OUI_PAY2 = 4,
- I40E_RX_PTYPE_L2_MACCNTRL_PAY2 = 5,
- I40E_RX_PTYPE_L2_LLDP_PAY2 = 6,
- I40E_RX_PTYPE_L2_ECP_PAY2 = 7,
- I40E_RX_PTYPE_L2_EVB_PAY2 = 8,
- I40E_RX_PTYPE_L2_QCN_PAY2 = 9,
- I40E_RX_PTYPE_L2_EAPOL_PAY2 = 10,
- I40E_RX_PTYPE_L2_ARP = 11,
- I40E_RX_PTYPE_L2_FCOE_PAY3 = 12,
- I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13,
- I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14,
- I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15,
- I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16,
- I40E_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17,
- I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18,
- I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19,
- I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20,
- I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21,
- I40E_RX_PTYPE_GRENAT4_MAC_PAY3 = 58,
- I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87,
- I40E_RX_PTYPE_GRENAT6_MAC_PAY3 = 124,
- I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153
-};
-
-struct i40e_rx_ptype_decoded {
- u32 ptype:8;
- u32 known:1;
- u32 outer_ip:1;
- u32 outer_ip_ver:1;
- u32 outer_frag:1;
- u32 tunnel_type:3;
- u32 tunnel_end_prot:2;
- u32 tunnel_end_frag:1;
- u32 inner_prot:4;
- u32 payload_layer:3;
-};
-
-enum i40e_rx_ptype_outer_ip {
- I40E_RX_PTYPE_OUTER_L2 = 0,
- I40E_RX_PTYPE_OUTER_IP = 1
-};
-
-enum i40e_rx_ptype_outer_ip_ver {
- I40E_RX_PTYPE_OUTER_NONE = 0,
- I40E_RX_PTYPE_OUTER_IPV4 = 0,
- I40E_RX_PTYPE_OUTER_IPV6 = 1
-};
-
-enum i40e_rx_ptype_outer_fragmented {
- I40E_RX_PTYPE_NOT_FRAG = 0,
- I40E_RX_PTYPE_FRAG = 1
-};
-
-enum i40e_rx_ptype_tunnel_type {
- I40E_RX_PTYPE_TUNNEL_NONE = 0,
- I40E_RX_PTYPE_TUNNEL_IP_IP = 1,
- I40E_RX_PTYPE_TUNNEL_IP_GRENAT = 2,
- I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3,
- I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4,
-};
-
-enum i40e_rx_ptype_tunnel_end_prot {
- I40E_RX_PTYPE_TUNNEL_END_NONE = 0,
- I40E_RX_PTYPE_TUNNEL_END_IPV4 = 1,
- I40E_RX_PTYPE_TUNNEL_END_IPV6 = 2,
-};
-
-enum i40e_rx_ptype_inner_prot {
- I40E_RX_PTYPE_INNER_PROT_NONE = 0,
- I40E_RX_PTYPE_INNER_PROT_UDP = 1,
- I40E_RX_PTYPE_INNER_PROT_TCP = 2,
- I40E_RX_PTYPE_INNER_PROT_SCTP = 3,
- I40E_RX_PTYPE_INNER_PROT_ICMP = 4,
- I40E_RX_PTYPE_INNER_PROT_TIMESYNC = 5
-};
-
-enum i40e_rx_ptype_payload_layer {
- I40E_RX_PTYPE_PAYLOAD_LAYER_NONE = 0,
- I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1,
- I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2,
- I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3,
-};
-
-#define I40E_RXD_QW1_LENGTH_PBUF_SHIFT 38
-#define I40E_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \
- I40E_RXD_QW1_LENGTH_PBUF_SHIFT)
-
-#define I40E_RXD_QW1_LENGTH_HBUF_SHIFT 52
-#define I40E_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \
- I40E_RXD_QW1_LENGTH_HBUF_SHIFT)
-
-#define I40E_RXD_QW1_LENGTH_SPH_SHIFT 63
-#define I40E_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(I40E_RXD_QW1_LENGTH_SPH_SHIFT)
-
-enum i40e_rx_desc_ext_status_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0,
- I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1,
- I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */
- I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */
- I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9,
- I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10,
- I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11,
-};
-
-enum i40e_rx_desc_pe_status_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */
- I40E_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */
- I40E_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */
- I40E_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24,
- I40E_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25,
- I40E_RX_DESC_PE_STATUS_PORTV_SHIFT = 26,
- I40E_RX_DESC_PE_STATUS_URG_SHIFT = 27,
- I40E_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28,
- I40E_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29
-};
-
-#define I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38
-#define I40E_RX_PROG_STATUS_DESC_LENGTH 0x2000000
-
-#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2
-#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \
- I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT)
-
-#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19
-#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \
- I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT)
-
-enum i40e_rx_prog_status_desc_status_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_PROG_STATUS_DESC_DD_SHIFT = 0,
- I40E_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */
-};
-
-enum i40e_rx_prog_status_desc_prog_id_masks {
- I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1,
- I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2,
- I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4,
-};
-
-enum i40e_rx_prog_status_desc_error_bits {
- /* Note: These are predefined bit offsets */
- I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0,
- I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1,
- I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2,
- I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3
-};
-
-/* TX Descriptor */
-struct i40e_tx_desc {
- __le64 buffer_addr; /* Address of descriptor's data buf */
- __le64 cmd_type_offset_bsz;
-};
-
-#define I40E_TXD_QW1_DTYPE_SHIFT 0
-#define I40E_TXD_QW1_DTYPE_MASK (0xFUL << I40E_TXD_QW1_DTYPE_SHIFT)
-
-enum i40e_tx_desc_dtype_value {
- I40E_TX_DESC_DTYPE_DATA = 0x0,
- I40E_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */
- I40E_TX_DESC_DTYPE_CONTEXT = 0x1,
- I40E_TX_DESC_DTYPE_FCOE_CTX = 0x2,
- I40E_TX_DESC_DTYPE_FILTER_PROG = 0x8,
- I40E_TX_DESC_DTYPE_DDP_CTX = 0x9,
- I40E_TX_DESC_DTYPE_FLEX_DATA = 0xB,
- I40E_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC,
- I40E_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD,
- I40E_TX_DESC_DTYPE_DESC_DONE = 0xF
-};
-
-#define I40E_TXD_QW1_CMD_SHIFT 4
-#define I40E_TXD_QW1_CMD_MASK (0x3FFUL << I40E_TXD_QW1_CMD_SHIFT)
-
-enum i40e_tx_desc_cmd_bits {
- I40E_TX_DESC_CMD_EOP = 0x0001,
- I40E_TX_DESC_CMD_RS = 0x0002,
- I40E_TX_DESC_CMD_ICRC = 0x0004,
- I40E_TX_DESC_CMD_IL2TAG1 = 0x0008,
- I40E_TX_DESC_CMD_DUMMY = 0x0010,
- I40E_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */
- I40E_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */
- I40E_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */
- I40E_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */
- I40E_TX_DESC_CMD_FCOET = 0x0080,
- I40E_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */
- I40E_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */
-};
-
-#define I40E_TXD_QW1_OFFSET_SHIFT 16
-#define I40E_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \
- I40E_TXD_QW1_OFFSET_SHIFT)
-
-enum i40e_tx_desc_length_fields {
- /* Note: These are predefined bit offsets */
- I40E_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */
- I40E_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */
- I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */
-};
-
-#define I40E_TXD_QW1_TX_BUF_SZ_SHIFT 34
-#define I40E_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \
- I40E_TXD_QW1_TX_BUF_SZ_SHIFT)
-
-#define I40E_TXD_QW1_L2TAG1_SHIFT 48
-#define I40E_TXD_QW1_L2TAG1_MASK (0xFFFFULL << I40E_TXD_QW1_L2TAG1_SHIFT)
-
-/* Context descriptors */
-struct i40e_tx_context_desc {
- __le32 tunneling_params;
- __le16 l2tag2;
- __le16 rsvd;
- __le64 type_cmd_tso_mss;
-};
-
-#define I40E_TXD_CTX_QW1_DTYPE_SHIFT 0
-#define I40E_TXD_CTX_QW1_DTYPE_MASK (0xFUL << I40E_TXD_CTX_QW1_DTYPE_SHIFT)
-
-#define I40E_TXD_CTX_QW1_CMD_SHIFT 4
-#define I40E_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << I40E_TXD_CTX_QW1_CMD_SHIFT)
-
-enum i40e_tx_ctx_desc_cmd_bits {
- I40E_TX_CTX_DESC_TSO = 0x01,
- I40E_TX_CTX_DESC_TSYN = 0x02,
- I40E_TX_CTX_DESC_IL2TAG2 = 0x04,
- I40E_TX_CTX_DESC_IL2TAG2_IL2H = 0x08,
- I40E_TX_CTX_DESC_SWTCH_NOTAG = 0x00,
- I40E_TX_CTX_DESC_SWTCH_UPLINK = 0x10,
- I40E_TX_CTX_DESC_SWTCH_LOCAL = 0x20,
- I40E_TX_CTX_DESC_SWTCH_VSI = 0x30,
- I40E_TX_CTX_DESC_SWPE = 0x40
-};
-
-#define I40E_TXD_CTX_QW1_TSO_LEN_SHIFT 30
-#define I40E_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \
- I40E_TXD_CTX_QW1_TSO_LEN_SHIFT)
-
-#define I40E_TXD_CTX_QW1_MSS_SHIFT 50
-#define I40E_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \
- I40E_TXD_CTX_QW1_MSS_SHIFT)
-
-#define I40E_TXD_CTX_QW1_VSI_SHIFT 50
-#define I40E_TXD_CTX_QW1_VSI_MASK (0x1FFULL << I40E_TXD_CTX_QW1_VSI_SHIFT)
-
-#define I40E_TXD_CTX_QW0_EXT_IP_SHIFT 0
-#define I40E_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \
- I40E_TXD_CTX_QW0_EXT_IP_SHIFT)
-
-enum i40e_tx_ctx_desc_eipt_offload {
- I40E_TX_CTX_EXT_IP_NONE = 0x0,
- I40E_TX_CTX_EXT_IP_IPV6 = 0x1,
- I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2,
- I40E_TX_CTX_EXT_IP_IPV4 = 0x3
-};
-
-#define I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2
-#define I40E_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \
- I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT)
-
-#define I40E_TXD_CTX_QW0_NATT_SHIFT 9
-#define I40E_TXD_CTX_QW0_NATT_MASK (0x3ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
-
-#define I40E_TXD_CTX_UDP_TUNNELING BIT_ULL(I40E_TXD_CTX_QW0_NATT_SHIFT)
-#define I40E_TXD_CTX_GRE_TUNNELING (0x2ULL << I40E_TXD_CTX_QW0_NATT_SHIFT)
-
-#define I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT 11
-#define I40E_TXD_CTX_QW0_EIP_NOINC_MASK \
- BIT_ULL(I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT)
-
-#define I40E_TXD_CTX_EIP_NOINC_IPID_CONST I40E_TXD_CTX_QW0_EIP_NOINC_MASK
-
-#define I40E_TXD_CTX_QW0_NATLEN_SHIFT 12
-#define I40E_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \
- I40E_TXD_CTX_QW0_NATLEN_SHIFT)
-
-#define I40E_TXD_CTX_QW0_DECTTL_SHIFT 19
-#define I40E_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \
- I40E_TXD_CTX_QW0_DECTTL_SHIFT)
-
-#define I40E_TXD_CTX_QW0_L4T_CS_SHIFT 23
-#define I40E_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(I40E_TXD_CTX_QW0_L4T_CS_SHIFT)
-struct i40e_filter_program_desc {
- __le32 qindex_flex_ptype_vsi;
- __le32 rsvd;
- __le32 dtype_cmd_cntindex;
- __le32 fd_id;
-};
-#define I40E_TXD_FLTR_QW0_QINDEX_SHIFT 0
-#define I40E_TXD_FLTR_QW0_QINDEX_MASK (0x7FFUL << \
- I40E_TXD_FLTR_QW0_QINDEX_SHIFT)
-#define I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT 11
-#define I40E_TXD_FLTR_QW0_FLEXOFF_MASK (0x7UL << \
- I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT)
-#define I40E_TXD_FLTR_QW0_PCTYPE_SHIFT 17
-#define I40E_TXD_FLTR_QW0_PCTYPE_MASK (0x3FUL << \
- I40E_TXD_FLTR_QW0_PCTYPE_SHIFT)
-
-/* Packet Classifier Types for filters */
-enum i40e_filter_pctype {
- /* Note: Values 0-28 are reserved for future use.
- * Value 29, 30, 32 are not supported on XL710 and X710.
- */
- I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29,
- I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30,
- I40E_FILTER_PCTYPE_NONF_IPV4_UDP = 31,
- I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32,
- I40E_FILTER_PCTYPE_NONF_IPV4_TCP = 33,
- I40E_FILTER_PCTYPE_NONF_IPV4_SCTP = 34,
- I40E_FILTER_PCTYPE_NONF_IPV4_OTHER = 35,
- I40E_FILTER_PCTYPE_FRAG_IPV4 = 36,
- /* Note: Values 37-38 are reserved for future use.
- * Value 39, 40, 42 are not supported on XL710 and X710.
- */
- I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39,
- I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40,
- I40E_FILTER_PCTYPE_NONF_IPV6_UDP = 41,
- I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42,
- I40E_FILTER_PCTYPE_NONF_IPV6_TCP = 43,
- I40E_FILTER_PCTYPE_NONF_IPV6_SCTP = 44,
- I40E_FILTER_PCTYPE_NONF_IPV6_OTHER = 45,
- I40E_FILTER_PCTYPE_FRAG_IPV6 = 46,
- /* Note: Value 47 is reserved for future use */
- I40E_FILTER_PCTYPE_FCOE_OX = 48,
- I40E_FILTER_PCTYPE_FCOE_RX = 49,
- I40E_FILTER_PCTYPE_FCOE_OTHER = 50,
- /* Note: Values 51-62 are reserved for future use */
- I40E_FILTER_PCTYPE_L2_PAYLOAD = 63,
-};
-
-enum i40e_filter_program_desc_dest {
- I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET = 0x0,
- I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX = 0x1,
- I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_OTHER = 0x2,
-};
-
-enum i40e_filter_program_desc_fd_status {
- I40E_FILTER_PROGRAM_DESC_FD_STATUS_NONE = 0x0,
- I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID = 0x1,
- I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID_4FLEX_BYTES = 0x2,
- I40E_FILTER_PROGRAM_DESC_FD_STATUS_8FLEX_BYTES = 0x3,
-};
-
-#define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23
-#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \
- I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
-
-#define I40E_TXD_FLTR_QW1_CMD_SHIFT 4
-#define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \
- I40E_TXD_FLTR_QW1_CMD_SHIFT)
-
-#define I40E_TXD_FLTR_QW1_PCMD_SHIFT (0x0ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
-#define I40E_TXD_FLTR_QW1_PCMD_MASK (0x7ULL << I40E_TXD_FLTR_QW1_PCMD_SHIFT)
-
-enum i40e_filter_program_desc_pcmd {
- I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE = 0x1,
- I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE = 0x2,
-};
-
-#define I40E_TXD_FLTR_QW1_DEST_SHIFT (0x3ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
-#define I40E_TXD_FLTR_QW1_DEST_MASK (0x3ULL << I40E_TXD_FLTR_QW1_DEST_SHIFT)
-
-#define I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT (0x7ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT)
-#define I40E_TXD_FLTR_QW1_CNT_ENA_MASK BIT_ULL(I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT)
-
-#define I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT (0x9ULL + \
- I40E_TXD_FLTR_QW1_CMD_SHIFT)
-#define I40E_TXD_FLTR_QW1_FD_STATUS_MASK (0x3ULL << \
- I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT)
-
-#define I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT 20
-#define I40E_TXD_FLTR_QW1_CNTINDEX_MASK (0x1FFUL << \
- I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT)
-
-enum i40e_filter_type {
- I40E_FLOW_DIRECTOR_FLTR = 0,
- I40E_PE_QUAD_HASH_FLTR = 1,
- I40E_ETHERTYPE_FLTR,
- I40E_FCOE_CTX_FLTR,
- I40E_MAC_VLAN_FLTR,
- I40E_HASH_FLTR
-};
-
-struct i40e_vsi_context {
- u16 seid;
- u16 uplink_seid;
- u16 vsi_number;
- u16 vsis_allocated;
- u16 vsis_unallocated;
- u16 flags;
- u8 pf_num;
- u8 vf_num;
- u8 connection_type;
- struct i40e_aqc_vsi_properties_data info;
-};
-
-struct i40e_veb_context {
- u16 seid;
- u16 uplink_seid;
- u16 veb_number;
- u16 vebs_allocated;
- u16 vebs_unallocated;
- u16 flags;
- struct i40e_aqc_get_veb_parameters_completion info;
-};
-
-/* Statistics collected by each port, VSI, VEB, and S-channel */
-struct i40e_eth_stats {
- u64 rx_bytes; /* gorc */
- u64 rx_unicast; /* uprc */
- u64 rx_multicast; /* mprc */
- u64 rx_broadcast; /* bprc */
- u64 rx_discards; /* rdpc */
- u64 rx_unknown_protocol; /* rupp */
- u64 tx_bytes; /* gotc */
- u64 tx_unicast; /* uptc */
- u64 tx_multicast; /* mptc */
- u64 tx_broadcast; /* bptc */
- u64 tx_discards; /* tdpc */
- u64 tx_errors; /* tepc */
-};
-
-/* Statistics collected per VEB per TC */
-struct i40e_veb_tc_stats {
- u64 tc_rx_packets[I40E_MAX_TRAFFIC_CLASS];
- u64 tc_rx_bytes[I40E_MAX_TRAFFIC_CLASS];
- u64 tc_tx_packets[I40E_MAX_TRAFFIC_CLASS];
- u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS];
-};
-
-/* Statistics collected by the MAC */
-struct i40e_hw_port_stats {
- /* eth stats collected by the port */
- struct i40e_eth_stats eth;
-
- /* additional port specific stats */
- u64 tx_dropped_link_down; /* tdold */
- u64 crc_errors; /* crcerrs */
- u64 illegal_bytes; /* illerrc */
- u64 error_bytes; /* errbc */
- u64 mac_local_faults; /* mlfc */
- u64 mac_remote_faults; /* mrfc */
- u64 rx_length_errors; /* rlec */
- u64 link_xon_rx; /* lxonrxc */
- u64 link_xoff_rx; /* lxoffrxc */
- u64 priority_xon_rx[8]; /* pxonrxc[8] */
- u64 priority_xoff_rx[8]; /* pxoffrxc[8] */
- u64 link_xon_tx; /* lxontxc */
- u64 link_xoff_tx; /* lxofftxc */
- u64 priority_xon_tx[8]; /* pxontxc[8] */
- u64 priority_xoff_tx[8]; /* pxofftxc[8] */
- u64 priority_xon_2_xoff[8]; /* pxon2offc[8] */
- u64 rx_size_64; /* prc64 */
- u64 rx_size_127; /* prc127 */
- u64 rx_size_255; /* prc255 */
- u64 rx_size_511; /* prc511 */
- u64 rx_size_1023; /* prc1023 */
- u64 rx_size_1522; /* prc1522 */
- u64 rx_size_big; /* prc9522 */
- u64 rx_undersize; /* ruc */
- u64 rx_fragments; /* rfc */
- u64 rx_oversize; /* roc */
- u64 rx_jabber; /* rjc */
- u64 tx_size_64; /* ptc64 */
- u64 tx_size_127; /* ptc127 */
- u64 tx_size_255; /* ptc255 */
- u64 tx_size_511; /* ptc511 */
- u64 tx_size_1023; /* ptc1023 */
- u64 tx_size_1522; /* ptc1522 */
- u64 tx_size_big; /* ptc9522 */
- u64 mac_short_packet_dropped; /* mspdc */
- u64 checksum_error; /* xec */
- /* flow director stats */
- u64 fd_atr_match;
- u64 fd_sb_match;
- u64 fd_atr_tunnel_match;
- u32 fd_atr_status;
- u32 fd_sb_status;
- /* EEE LPI */
- u32 tx_lpi_status;
- u32 rx_lpi_status;
- u64 tx_lpi_count; /* etlpic */
- u64 rx_lpi_count; /* erlpic */
-};
-
-/* Checksum and Shadow RAM pointers */
-#define I40E_SR_NVM_CONTROL_WORD 0x00
-#define I40E_EMP_MODULE_PTR 0x0F
-#define I40E_SR_EMP_MODULE_PTR 0x48
-#define I40E_NVM_OEM_VER_OFF 0x83
-#define I40E_SR_NVM_DEV_STARTER_VERSION 0x18
-#define I40E_SR_NVM_WAKE_ON_LAN 0x19
-#define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27
-#define I40E_SR_NVM_EETRACK_LO 0x2D
-#define I40E_SR_NVM_EETRACK_HI 0x2E
-#define I40E_SR_VPD_PTR 0x2F
-#define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E
-#define I40E_SR_SW_CHECKSUM_WORD 0x3F
-
-/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
-#define I40E_SR_VPD_MODULE_MAX_SIZE 1024
-#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024
-#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06
-#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT)
-#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5)
-#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12)
-#define I40E_PTR_TYPE BIT(15)
-
-/* Shadow RAM related */
-#define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800
-#define I40E_SR_WORDS_IN_1KB 512
-/* Checksum should be calculated such that after adding all the words,
- * including the checksum word itself, the sum should be 0xBABA.
- */
-#define I40E_SR_SW_CHECKSUM_BASE 0xBABA
-
-#define I40E_SRRD_SRCTL_ATTEMPTS 100000
-
-enum i40e_switch_element_types {
- I40E_SWITCH_ELEMENT_TYPE_MAC = 1,
- I40E_SWITCH_ELEMENT_TYPE_PF = 2,
- I40E_SWITCH_ELEMENT_TYPE_VF = 3,
- I40E_SWITCH_ELEMENT_TYPE_EMP = 4,
- I40E_SWITCH_ELEMENT_TYPE_BMC = 6,
- I40E_SWITCH_ELEMENT_TYPE_PE = 16,
- I40E_SWITCH_ELEMENT_TYPE_VEB = 17,
- I40E_SWITCH_ELEMENT_TYPE_PA = 18,
- I40E_SWITCH_ELEMENT_TYPE_VSI = 19,
-};
-
-/* Supported EtherType filters */
-enum i40e_ether_type_index {
- I40E_ETHER_TYPE_1588 = 0,
- I40E_ETHER_TYPE_FIP = 1,
- I40E_ETHER_TYPE_OUI_EXTENDED = 2,
- I40E_ETHER_TYPE_MAC_CONTROL = 3,
- I40E_ETHER_TYPE_LLDP = 4,
- I40E_ETHER_TYPE_EVB_PROTOCOL1 = 5,
- I40E_ETHER_TYPE_EVB_PROTOCOL2 = 6,
- I40E_ETHER_TYPE_QCN_CNM = 7,
- I40E_ETHER_TYPE_8021X = 8,
- I40E_ETHER_TYPE_ARP = 9,
- I40E_ETHER_TYPE_RSV1 = 10,
- I40E_ETHER_TYPE_RSV2 = 11,
-};
-
-/* Filter context base size is 1K */
-#define I40E_HASH_FILTER_BASE_SIZE 1024
-/* Supported Hash filter values */
-enum i40e_hash_filter_size {
- I40E_HASH_FILTER_SIZE_1K = 0,
- I40E_HASH_FILTER_SIZE_2K = 1,
- I40E_HASH_FILTER_SIZE_4K = 2,
- I40E_HASH_FILTER_SIZE_8K = 3,
- I40E_HASH_FILTER_SIZE_16K = 4,
- I40E_HASH_FILTER_SIZE_32K = 5,
- I40E_HASH_FILTER_SIZE_64K = 6,
- I40E_HASH_FILTER_SIZE_128K = 7,
- I40E_HASH_FILTER_SIZE_256K = 8,
- I40E_HASH_FILTER_SIZE_512K = 9,
- I40E_HASH_FILTER_SIZE_1M = 10,
-};
-
-/* DMA context base size is 0.5K */
-#define I40E_DMA_CNTX_BASE_SIZE 512
-/* Supported DMA context values */
-enum i40e_dma_cntx_size {
- I40E_DMA_CNTX_SIZE_512 = 0,
- I40E_DMA_CNTX_SIZE_1K = 1,
- I40E_DMA_CNTX_SIZE_2K = 2,
- I40E_DMA_CNTX_SIZE_4K = 3,
- I40E_DMA_CNTX_SIZE_8K = 4,
- I40E_DMA_CNTX_SIZE_16K = 5,
- I40E_DMA_CNTX_SIZE_32K = 6,
- I40E_DMA_CNTX_SIZE_64K = 7,
- I40E_DMA_CNTX_SIZE_128K = 8,
- I40E_DMA_CNTX_SIZE_256K = 9,
-};
-
-/* Supported Hash look up table (LUT) sizes */
-enum i40e_hash_lut_size {
- I40E_HASH_LUT_SIZE_128 = 0,
- I40E_HASH_LUT_SIZE_512 = 1,
-};
-
-/* Structure to hold a per PF filter control settings */
-struct i40e_filter_control_settings {
- /* number of PE Quad Hash filter buckets */
- enum i40e_hash_filter_size pe_filt_num;
- /* number of PE Quad Hash contexts */
- enum i40e_dma_cntx_size pe_cntx_num;
- /* number of FCoE filter buckets */
- enum i40e_hash_filter_size fcoe_filt_num;
- /* number of FCoE DDP contexts */
- enum i40e_dma_cntx_size fcoe_cntx_num;
- /* size of the Hash LUT */
- enum i40e_hash_lut_size hash_lut_size;
- /* enable FDIR filters for PF and its VFs */
- bool enable_fdir;
- /* enable Ethertype filters for PF and its VFs */
- bool enable_ethtype;
- /* enable MAC/VLAN filters for PF and its VFs */
- bool enable_macvlan;
-};
-
-/* Structure to hold device level control filter counts */
-struct i40e_control_filter_stats {
- u16 mac_etype_used; /* Used perfect match MAC/EtherType filters */
- u16 etype_used; /* Used perfect EtherType filters */
- u16 mac_etype_free; /* Un-used perfect match MAC/EtherType filters */
- u16 etype_free; /* Un-used perfect EtherType filters */
-};
-
-enum i40e_reset_type {
- I40E_RESET_POR = 0,
- I40E_RESET_CORER = 1,
- I40E_RESET_GLOBR = 2,
- I40E_RESET_EMPR = 3,
-};
-
-/* IEEE 802.1AB LLDP Agent Variables from NVM */
-#define I40E_NVM_LLDP_CFG_PTR 0x06
-#define I40E_SR_LLDP_CFG_PTR 0x31
-
-/* RSS Hash Table Size */
-#define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000
-
-/* INPUT SET MASK for RSS, flow director and flexible payload */
-#define I40E_FD_INSET_L3_SRC_SHIFT 47
-#define I40E_FD_INSET_L3_SRC_WORD_MASK (0x3ULL << \
- I40E_FD_INSET_L3_SRC_SHIFT)
-#define I40E_FD_INSET_L3_DST_SHIFT 35
-#define I40E_FD_INSET_L3_DST_WORD_MASK (0x3ULL << \
- I40E_FD_INSET_L3_DST_SHIFT)
-#define I40E_FD_INSET_L4_SRC_SHIFT 34
-#define I40E_FD_INSET_L4_SRC_WORD_MASK (0x1ULL << \
- I40E_FD_INSET_L4_SRC_SHIFT)
-#define I40E_FD_INSET_L4_DST_SHIFT 33
-#define I40E_FD_INSET_L4_DST_WORD_MASK (0x1ULL << \
- I40E_FD_INSET_L4_DST_SHIFT)
-#define I40E_FD_INSET_VERIFY_TAG_SHIFT 31
-#define I40E_FD_INSET_VERIFY_TAG_WORD_MASK (0x3ULL << \
- I40E_FD_INSET_VERIFY_TAG_SHIFT)
-
-#define I40E_FD_INSET_FLEX_WORD50_SHIFT 17
-#define I40E_FD_INSET_FLEX_WORD50_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD50_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD51_SHIFT 16
-#define I40E_FD_INSET_FLEX_WORD51_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD51_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD52_SHIFT 15
-#define I40E_FD_INSET_FLEX_WORD52_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD52_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD53_SHIFT 14
-#define I40E_FD_INSET_FLEX_WORD53_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD53_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD54_SHIFT 13
-#define I40E_FD_INSET_FLEX_WORD54_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD54_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD55_SHIFT 12
-#define I40E_FD_INSET_FLEX_WORD55_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD55_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD56_SHIFT 11
-#define I40E_FD_INSET_FLEX_WORD56_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD56_SHIFT)
-#define I40E_FD_INSET_FLEX_WORD57_SHIFT 10
-#define I40E_FD_INSET_FLEX_WORD57_MASK (0x1ULL << \
- I40E_FD_INSET_FLEX_WORD57_SHIFT)
-
-/* Version format for Dynamic Device Personalization(DDP) */
-struct i40e_ddp_version {
- u8 major;
- u8 minor;
- u8 update;
- u8 draft;
-};
-
-#define I40E_DDP_NAME_SIZE 32
-
-/* Package header */
-struct i40e_package_header {
- struct i40e_ddp_version version;
- u32 segment_count;
- u32 segment_offset[1];
-};
-
-/* Generic segment header */
-struct i40e_generic_seg_header {
-#define SEGMENT_TYPE_METADATA 0x00000001
-#define SEGMENT_TYPE_NOTES 0x00000002
-#define SEGMENT_TYPE_I40E 0x00000011
-#define SEGMENT_TYPE_X722 0x00000012
- u32 type;
- struct i40e_ddp_version version;
- u32 size;
- char name[I40E_DDP_NAME_SIZE];
-};
-
-struct i40e_metadata_segment {
- struct i40e_generic_seg_header header;
- struct i40e_ddp_version version;
- u32 track_id;
- char name[I40E_DDP_NAME_SIZE];
-};
-
-struct i40e_device_id_entry {
- u32 vendor_dev_id;
- u32 sub_vendor_dev_id;
-};
-
-struct i40e_profile_segment {
- struct i40e_generic_seg_header header;
- struct i40e_ddp_version version;
- char name[I40E_DDP_NAME_SIZE];
- u32 device_table_count;
- struct i40e_device_id_entry device_table[1];
-};
-
-struct i40e_section_table {
- u32 section_count;
- u32 section_offset[1];
-};
-
-struct i40e_profile_section_header {
- u16 tbl_size;
- u16 data_end;
- struct {
-#define SECTION_TYPE_INFO 0x00000010
-#define SECTION_TYPE_MMIO 0x00000800
-#define SECTION_TYPE_AQ 0x00000801
-#define SECTION_TYPE_NOTE 0x80000000
-#define SECTION_TYPE_NAME 0x80000001
- u32 type;
- u32 offset;
- u32 size;
- } section;
-};
-
-struct i40e_profile_info {
- u32 track_id;
- struct i40e_ddp_version version;
- u8 op;
-#define I40E_DDP_ADD_TRACKID 0x01
-#define I40E_DDP_REMOVE_TRACKID 0x02
- u8 reserved[7];
- u8 name[I40E_DDP_NAME_SIZE];
-};
-#endif /* _I40E_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
deleted file mode 100644
index 96e537a..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ /dev/null
@@ -1,427 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40EVF_H_
-#define _I40EVF_H_
-
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/aer.h>
-#include <linux/netdevice.h>
-#include <linux/vmalloc.h>
-#include <linux/interrupt.h>
-#include <linux/ethtool.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/tcp.h>
-#include <linux/sctp.h>
-#include <linux/ipv6.h>
-#include <linux/kernel.h>
-#include <linux/bitops.h>
-#include <linux/timer.h>
-#include <linux/workqueue.h>
-#include <linux/wait.h>
-#include <linux/delay.h>
-#include <linux/gfp.h>
-#include <linux/skbuff.h>
-#include <linux/dma-mapping.h>
-#include <linux/etherdevice.h>
-#include <linux/socket.h>
-#include <linux/jiffies.h>
-#include <net/ip6_checksum.h>
-#include <net/pkt_cls.h>
-#include <net/udp.h>
-#include <net/tc_act/tc_gact.h>
-#include <net/tc_act/tc_mirred.h>
-
-#include "i40e_type.h"
-#include <linux/avf/virtchnl.h>
-#include "i40e_txrx.h"
-
-#define DEFAULT_DEBUG_LEVEL_SHIFT 3
-#define PFX "i40evf: "
-
-/* VSI state flags shared with common code */
-enum i40evf_vsi_state_t {
- __I40E_VSI_DOWN,
- /* This must be last as it determines the size of the BITMAP */
- __I40E_VSI_STATE_SIZE__,
-};
-
-/* dummy struct to make common code less painful */
-struct i40e_vsi {
- struct i40evf_adapter *back;
- struct net_device *netdev;
- unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
- u16 seid;
- u16 id;
- DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__);
- int base_vector;
- u16 work_limit;
- u16 qs_handle;
- void *priv; /* client driver data reference. */
-};
-
-/* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40EVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */
-#define I40EVF_DEFAULT_TXD 512
-#define I40EVF_DEFAULT_RXD 512
-#define I40EVF_MAX_TXD 4096
-#define I40EVF_MIN_TXD 64
-#define I40EVF_MAX_RXD 4096
-#define I40EVF_MIN_RXD 64
-#define I40EVF_REQ_DESCRIPTOR_MULTIPLE 32
-#define I40EVF_MAX_AQ_BUF_SIZE 4096
-#define I40EVF_AQ_LEN 32
-#define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */
-
-#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
-
-#define I40E_RX_DESC(R, i) (&(((union i40e_32byte_rx_desc *)((R)->desc))[i]))
-#define I40E_TX_DESC(R, i) (&(((struct i40e_tx_desc *)((R)->desc))[i]))
-#define I40E_TX_CTXTDESC(R, i) \
- (&(((struct i40e_tx_context_desc *)((R)->desc))[i]))
-#define I40EVF_MAX_REQ_QUEUES 4
-
-#define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4)
-#define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4)
-#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */
-
-/* MAX_MSIX_Q_VECTORS of these are allocated,
- * but we only use one per queue-specific vector.
- */
-struct i40e_q_vector {
- struct i40evf_adapter *adapter;
- struct i40e_vsi *vsi;
- struct napi_struct napi;
- struct i40e_ring_container rx;
- struct i40e_ring_container tx;
- u32 ring_mask;
- u8 itr_countdown; /* when 0 should adjust adaptive ITR */
- u8 num_ringpairs; /* total number of ring pairs in vector */
- u16 v_idx; /* index in the vsi->q_vector array. */
- u16 reg_idx; /* register index of the interrupt */
- char name[IFNAMSIZ + 15];
- bool arm_wb_state;
- cpumask_t affinity_mask;
- struct irq_affinity_notify affinity_notify;
-};
-
-/* Helper macros to switch between ints/sec and what the register uses.
- * And yes, it's the same math going both ways. The lowest value
- * supported by all of the i40e hardware is 8.
- */
-#define EITR_INTS_PER_SEC_TO_REG(_eitr) \
- ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8)
-#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG
-
-#define I40EVF_DESC_UNUSED(R) \
- ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
- (R)->next_to_clean - (R)->next_to_use - 1)
-
-#define I40EVF_RX_DESC_ADV(R, i) \
- (&(((union i40e_adv_rx_desc *)((R).desc))[i]))
-#define I40EVF_TX_DESC_ADV(R, i) \
- (&(((union i40e_adv_tx_desc *)((R).desc))[i]))
-#define I40EVF_TX_CTXTDESC_ADV(R, i) \
- (&(((struct i40e_adv_tx_context_desc *)((R).desc))[i]))
-
-#define OTHER_VECTOR 1
-#define NONQ_VECS (OTHER_VECTOR)
-
-#define MIN_MSIX_Q_VECTORS 1
-#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS)
-
-#define I40EVF_QUEUE_END_OF_LIST 0x7FF
-#define I40EVF_FREE_VECTOR 0x7FFF
-struct i40evf_mac_filter {
- struct list_head list;
- u8 macaddr[ETH_ALEN];
- bool remove; /* filter needs to be removed */
- bool add; /* filter needs to be added */
-};
-
-struct i40evf_vlan_filter {
- struct list_head list;
- u16 vlan;
- bool remove; /* filter needs to be removed */
- bool add; /* filter needs to be added */
-};
-
-#define I40EVF_MAX_TRAFFIC_CLASS 4
-/* State of traffic class creation */
-enum i40evf_tc_state_t {
- __I40EVF_TC_INVALID, /* no traffic class, default state */
- __I40EVF_TC_RUNNING, /* traffic classes have been created */
-};
-
-/* channel info */
-struct i40evf_channel_config {
- struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS];
- enum i40evf_tc_state_t state;
- u8 total_qps;
-};
-
-/* State of cloud filter */
-enum i40evf_cloud_filter_state_t {
- __I40EVF_CF_INVALID, /* cloud filter not added */
- __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */
- __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */
- __I40EVF_CF_ACTIVE, /* cloud filter is active */
-};
-
-/* Driver state. The order of these is important! */
-enum i40evf_state_t {
- __I40EVF_STARTUP, /* driver loaded, probe complete */
- __I40EVF_REMOVE, /* driver is being unloaded */
- __I40EVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */
- __I40EVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */
- __I40EVF_INIT_SW, /* got resources, setting up structs */
- __I40EVF_RESETTING, /* in reset */
- /* Below here, watchdog is running */
- __I40EVF_DOWN, /* ready, can be opened */
- __I40EVF_DOWN_PENDING, /* descending, waiting for watchdog */
- __I40EVF_TESTING, /* in ethtool self-test */
- __I40EVF_RUNNING, /* opened, working */
-};
-
-enum i40evf_critical_section_t {
- __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */
- __I40EVF_IN_CLIENT_TASK,
- __I40EVF_IN_REMOVE_TASK, /* device being removed */
-};
-
-#define I40EVF_CLOUD_FIELD_OMAC 0x01
-#define I40EVF_CLOUD_FIELD_IMAC 0x02
-#define I40EVF_CLOUD_FIELD_IVLAN 0x04
-#define I40EVF_CLOUD_FIELD_TEN_ID 0x08
-#define I40EVF_CLOUD_FIELD_IIP 0x10
-
-#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC
-#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC
-#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\
- I40EVF_CLOUD_FIELD_IVLAN)
-#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\
- I40EVF_CLOUD_FIELD_TEN_ID)
-#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\
- I40EVF_CLOUD_FIELD_IMAC |\
- I40EVF_CLOUD_FIELD_TEN_ID)
-#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\
- I40EVF_CLOUD_FIELD_IVLAN |\
- I40EVF_CLOUD_FIELD_TEN_ID)
-#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP
-
-/* bookkeeping of cloud filters */
-struct i40evf_cloud_filter {
- enum i40evf_cloud_filter_state_t state;
- struct list_head list;
- struct virtchnl_filter f;
- unsigned long cookie;
- bool del; /* filter needs to be deleted */
- bool add; /* filter needs to be added */
-};
-
-/* board specific private data structure */
-struct i40evf_adapter {
- struct timer_list watchdog_timer;
- struct work_struct reset_task;
- struct work_struct adminq_task;
- struct delayed_work client_task;
- struct delayed_work init_task;
- wait_queue_head_t down_waitqueue;
- struct i40e_q_vector *q_vectors;
- struct list_head vlan_filter_list;
- struct list_head mac_filter_list;
- /* Lock to protect accesses to MAC and VLAN lists */
- spinlock_t mac_vlan_list_lock;
- char misc_vector_name[IFNAMSIZ + 9];
- int num_active_queues;
- int num_req_queues;
-
- /* TX */
- struct i40e_ring *tx_rings;
- u32 tx_timeout_count;
- u32 tx_desc_count;
-
- /* RX */
- struct i40e_ring *rx_rings;
- u64 hw_csum_rx_error;
- u32 rx_desc_count;
- int num_msix_vectors;
- int num_iwarp_msix;
- int iwarp_base_vector;
- u32 client_pending;
- struct i40e_client_instance *cinst;
- struct msix_entry *msix_entries;
-
- u32 flags;
-#define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0)
-#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3)
-#define I40EVF_FLAG_RESET_PENDING BIT(4)
-#define I40EVF_FLAG_RESET_NEEDED BIT(5)
-#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6)
-#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8)
-#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9)
-#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10)
-#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11)
-#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12)
-#define I40EVF_FLAG_PROMISC_ON BIT(13)
-#define I40EVF_FLAG_ALLMULTI_ON BIT(14)
-#define I40EVF_FLAG_LEGACY_RX BIT(15)
-#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16)
-#define I40EVF_FLAG_QUEUES_DISABLED BIT(17)
-/* duplicates for common code */
-#define I40E_FLAG_DCB_ENABLED 0
-#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED
-#define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX
- /* flags for admin queue service task */
- u32 aq_required;
-#define I40EVF_FLAG_AQ_ENABLE_QUEUES BIT(0)
-#define I40EVF_FLAG_AQ_DISABLE_QUEUES BIT(1)
-#define I40EVF_FLAG_AQ_ADD_MAC_FILTER BIT(2)
-#define I40EVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3)
-#define I40EVF_FLAG_AQ_DEL_MAC_FILTER BIT(4)
-#define I40EVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5)
-#define I40EVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6)
-#define I40EVF_FLAG_AQ_MAP_VECTORS BIT(7)
-#define I40EVF_FLAG_AQ_HANDLE_RESET BIT(8)
-#define I40EVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */
-#define I40EVF_FLAG_AQ_GET_CONFIG BIT(10)
-/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */
-#define I40EVF_FLAG_AQ_GET_HENA BIT(11)
-#define I40EVF_FLAG_AQ_SET_HENA BIT(12)
-#define I40EVF_FLAG_AQ_SET_RSS_KEY BIT(13)
-#define I40EVF_FLAG_AQ_SET_RSS_LUT BIT(14)
-#define I40EVF_FLAG_AQ_REQUEST_PROMISC BIT(15)
-#define I40EVF_FLAG_AQ_RELEASE_PROMISC BIT(16)
-#define I40EVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17)
-#define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18)
-#define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19)
-#define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20)
-#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21)
-#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22)
-#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23)
-#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24)
-
- /* OS defined structs */
- struct net_device *netdev;
- struct pci_dev *pdev;
-
- struct i40e_hw hw; /* defined in i40e_type.h */
-
- enum i40evf_state_t state;
- unsigned long crit_section;
-
- struct work_struct watchdog_task;
- bool netdev_registered;
- bool link_up;
- enum virtchnl_link_speed link_speed;
- enum virtchnl_ops current_op;
-#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
- (_a)->vf_res->vf_cap_flags & \
- VIRTCHNL_VF_OFFLOAD_IWARP : \
- 0)
-#define CLIENT_ENABLED(_a) ((_a)->cinst)
-/* RSS by the PF should be preferred over RSS via other methods. */
-#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \
- VIRTCHNL_VF_OFFLOAD_RSS_PF)
-#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \
- VIRTCHNL_VF_OFFLOAD_RSS_AQ)
-#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \
- (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \
- VIRTCHNL_VF_OFFLOAD_RSS_PF)))
-#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
- VIRTCHNL_VF_OFFLOAD_VLAN)
- struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
- struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
- struct virtchnl_version_info pf_version;
-#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
- ((_a)->pf_version.minor == 1))
- u16 msg_enable;
- struct i40e_eth_stats current_stats;
- struct i40e_vsi vsi;
- u32 aq_wait_count;
- /* RSS stuff */
- u64 hena;
- u16 rss_key_size;
- u16 rss_lut_size;
- u8 *rss_key;
- u8 *rss_lut;
- /* ADQ related members */
- struct i40evf_channel_config ch_config;
- u8 num_tc;
- struct list_head cloud_filter_list;
- /* lock to protest access to the cloud filter list */
- spinlock_t cloud_filter_list_lock;
- u16 num_cloud_filters;
-};
-
-
-/* Ethtool Private Flags */
-
-/* lan device */
-struct i40e_device {
- struct list_head list;
- struct i40evf_adapter *vf;
-};
-
-/* needed by i40evf_ethtool.c */
-extern char i40evf_driver_name[];
-extern const char i40evf_driver_version[];
-
-int i40evf_up(struct i40evf_adapter *adapter);
-void i40evf_down(struct i40evf_adapter *adapter);
-int i40evf_process_config(struct i40evf_adapter *adapter);
-void i40evf_schedule_reset(struct i40evf_adapter *adapter);
-void i40evf_reset(struct i40evf_adapter *adapter);
-void i40evf_set_ethtool_ops(struct net_device *netdev);
-void i40evf_update_stats(struct i40evf_adapter *adapter);
-void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter);
-int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter);
-void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask);
-void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter);
-void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter);
-
-void i40e_napi_add_all(struct i40evf_adapter *adapter);
-void i40e_napi_del_all(struct i40evf_adapter *adapter);
-
-int i40evf_send_api_ver(struct i40evf_adapter *adapter);
-int i40evf_verify_api_ver(struct i40evf_adapter *adapter);
-int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter);
-int i40evf_get_vf_config(struct i40evf_adapter *adapter);
-void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush);
-void i40evf_configure_queues(struct i40evf_adapter *adapter);
-void i40evf_deconfigure_queues(struct i40evf_adapter *adapter);
-void i40evf_enable_queues(struct i40evf_adapter *adapter);
-void i40evf_disable_queues(struct i40evf_adapter *adapter);
-void i40evf_map_queues(struct i40evf_adapter *adapter);
-int i40evf_request_queues(struct i40evf_adapter *adapter, int num);
-void i40evf_add_ether_addrs(struct i40evf_adapter *adapter);
-void i40evf_del_ether_addrs(struct i40evf_adapter *adapter);
-void i40evf_add_vlans(struct i40evf_adapter *adapter);
-void i40evf_del_vlans(struct i40evf_adapter *adapter);
-void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags);
-void i40evf_request_stats(struct i40evf_adapter *adapter);
-void i40evf_request_reset(struct i40evf_adapter *adapter);
-void i40evf_get_hena(struct i40evf_adapter *adapter);
-void i40evf_set_hena(struct i40evf_adapter *adapter);
-void i40evf_set_rss_key(struct i40evf_adapter *adapter);
-void i40evf_set_rss_lut(struct i40evf_adapter *adapter);
-void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter);
-void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter);
-void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
- enum virtchnl_ops v_opcode,
- i40e_status v_retval, u8 *msg, u16 msglen);
-int i40evf_config_rss(struct i40evf_adapter *adapter);
-int i40evf_lan_add_device(struct i40evf_adapter *adapter);
-int i40evf_lan_del_device(struct i40evf_adapter *adapter);
-void i40evf_client_subtask(struct i40evf_adapter *adapter);
-void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len);
-void i40evf_notify_client_l2_params(struct i40e_vsi *vsi);
-void i40evf_notify_client_open(struct i40e_vsi *vsi);
-void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset);
-void i40evf_enable_channels(struct i40evf_adapter *adapter);
-void i40evf_disable_channels(struct i40evf_adapter *adapter);
-void i40evf_add_cloud_filter(struct i40evf_adapter *adapter);
-void i40evf_del_cloud_filter(struct i40evf_adapter *adapter);
-#endif /* _I40EVF_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
deleted file mode 100644
index 3cc9d60..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40evf_client.c
+++ /dev/null
@@ -1,579 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#include <linux/list.h>
-#include <linux/errno.h>
-
-#include "i40evf.h"
-#include "i40e_prototype.h"
-#include "i40evf_client.h"
-
-static
-const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR;
-static struct i40e_client *vf_registered_client;
-static LIST_HEAD(i40evf_devices);
-static DEFINE_MUTEX(i40evf_device_mutex);
-
-static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
- struct i40e_client *client,
- u8 *msg, u16 len);
-
-static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
- struct i40e_client *client,
- struct i40e_qvlist_info *qvlist_info);
-
-static struct i40e_ops i40evf_lan_ops = {
- .virtchnl_send = i40evf_client_virtchnl_send,
- .setup_qvlist = i40evf_client_setup_qvlist,
-};
-
-/**
- * i40evf_client_get_params - retrieve relevant client parameters
- * @vsi: VSI with parameters
- * @params: client param struct
- **/
-static
-void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params)
-{
- int i;
-
- memset(params, 0, sizeof(struct i40e_params));
- params->mtu = vsi->netdev->mtu;
- params->link_up = vsi->back->link_up;
-
- for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
- params->qos.prio_qos[i].tc = 0;
- params->qos.prio_qos[i].qs_handle = vsi->qs_handle;
- }
-}
-
-/**
- * i40evf_notify_client_message - call the client message receive callback
- * @vsi: the VSI associated with this client
- * @msg: message buffer
- * @len: length of message
- *
- * If there is a client to this VSI, call the client
- **/
-void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len)
-{
- struct i40e_client_instance *cinst;
-
- if (!vsi)
- return;
-
- cinst = vsi->back->cinst;
- if (!cinst || !cinst->client || !cinst->client->ops ||
- !cinst->client->ops->virtchnl_receive) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance virtchnl_receive function\n");
- return;
- }
- cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client,
- msg, len);
-}
-
-/**
- * i40evf_notify_client_l2_params - call the client notify callback
- * @vsi: the VSI with l2 param changes
- *
- * If there is a client to this VSI, call the client
- **/
-void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
-{
- struct i40e_client_instance *cinst;
- struct i40e_params params;
-
- if (!vsi)
- return;
-
- cinst = vsi->back->cinst;
-
- if (!cinst || !cinst->client || !cinst->client->ops ||
- !cinst->client->ops->l2_param_change) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance l2_param_change function\n");
- return;
- }
- i40evf_client_get_params(vsi, ¶ms);
- cinst->lan_info.params = params;
- cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
- ¶ms);
-}
-
-/**
- * i40evf_notify_client_open - call the client open callback
- * @vsi: the VSI with netdev opened
- *
- * If there is a client to this netdev, call the client with open
- **/
-void i40evf_notify_client_open(struct i40e_vsi *vsi)
-{
- struct i40evf_adapter *adapter = vsi->back;
- struct i40e_client_instance *cinst = adapter->cinst;
- int ret;
-
- if (!cinst || !cinst->client || !cinst->client->ops ||
- !cinst->client->ops->open) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance open function\n");
- return;
- }
- if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) {
- ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
- if (!ret)
- set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
- }
-}
-
-/**
- * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map
- * @ldev: pointer to L2 context.
- *
- * Return 0 on success or < 0 on error
- **/
-static int i40evf_client_release_qvlist(struct i40e_info *ldev)
-{
- struct i40evf_adapter *adapter = ldev->vf;
- i40e_status err;
-
- if (adapter->aq_required)
- return -EAGAIN;
-
- err = i40e_aq_send_msg_to_pf(&adapter->hw,
- VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
- I40E_SUCCESS, NULL, 0, NULL);
-
- if (err)
- dev_err(&adapter->pdev->dev,
- "Unable to send iWarp vector release message to PF, error %d, aq status %d\n",
- err, adapter->hw.aq.asq_last_status);
-
- return err;
-}
-
-/**
- * i40evf_notify_client_close - call the client close callback
- * @vsi: the VSI with netdev closed
- * @reset: true when close called due to reset pending
- *
- * If there is a client to this netdev, call the client with close
- **/
-void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset)
-{
- struct i40evf_adapter *adapter = vsi->back;
- struct i40e_client_instance *cinst = adapter->cinst;
-
- if (!cinst || !cinst->client || !cinst->client->ops ||
- !cinst->client->ops->close) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance close function\n");
- return;
- }
- cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
- i40evf_client_release_qvlist(&cinst->lan_info);
- clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
-}
-
-/**
- * i40evf_client_add_instance - add a client instance to the instance list
- * @adapter: pointer to the board struct
- *
- * Returns cinst ptr on success, NULL on failure
- **/
-static struct i40e_client_instance *
-i40evf_client_add_instance(struct i40evf_adapter *adapter)
-{
- struct i40e_client_instance *cinst = NULL;
- struct i40e_vsi *vsi = &adapter->vsi;
- struct netdev_hw_addr *mac = NULL;
- struct i40e_params params;
-
- if (!vf_registered_client)
- goto out;
-
- if (adapter->cinst) {
- cinst = adapter->cinst;
- goto out;
- }
-
- cinst = kzalloc(sizeof(*cinst), GFP_KERNEL);
- if (!cinst)
- goto out;
-
- cinst->lan_info.vf = (void *)adapter;
- cinst->lan_info.netdev = vsi->netdev;
- cinst->lan_info.pcidev = adapter->pdev;
- cinst->lan_info.fid = 0;
- cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF;
- cinst->lan_info.hw_addr = adapter->hw.hw_addr;
- cinst->lan_info.ops = &i40evf_lan_ops;
- cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR;
- cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR;
- cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD;
- i40evf_client_get_params(vsi, ¶ms);
- cinst->lan_info.params = params;
- set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
-
- cinst->lan_info.msix_count = adapter->num_iwarp_msix;
- cinst->lan_info.msix_entries =
- &adapter->msix_entries[adapter->iwarp_base_vector];
-
- mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
- struct netdev_hw_addr, list);
- if (mac)
- ether_addr_copy(cinst->lan_info.lanmac, mac->addr);
- else
- dev_err(&adapter->pdev->dev, "MAC address list is empty!\n");
-
- cinst->client = vf_registered_client;
- adapter->cinst = cinst;
-out:
- return cinst;
-}
-
-/**
- * i40evf_client_del_instance - removes a client instance from the list
- * @adapter: pointer to the board struct
- *
- **/
-static
-void i40evf_client_del_instance(struct i40evf_adapter *adapter)
-{
- kfree(adapter->cinst);
- adapter->cinst = NULL;
-}
-
-/**
- * i40evf_client_subtask - client maintenance work
- * @adapter: board private structure
- **/
-void i40evf_client_subtask(struct i40evf_adapter *adapter)
-{
- struct i40e_client *client = vf_registered_client;
- struct i40e_client_instance *cinst;
- int ret = 0;
-
- if (adapter->state < __I40EVF_DOWN)
- return;
-
- /* first check client is registered */
- if (!client)
- return;
-
- /* Add the client instance to the instance list */
- cinst = i40evf_client_add_instance(adapter);
- if (!cinst)
- return;
-
- dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
- client->name);
-
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
- /* Send an Open request to the client */
-
- if (client->ops && client->ops->open)
- ret = client->ops->open(&cinst->lan_info, client);
- if (!ret)
- set_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cinst->state);
- else
- /* remove client instance */
- i40evf_client_del_instance(adapter);
- }
-}
-
-/**
- * i40evf_lan_add_device - add a lan device struct to the list of lan devices
- * @adapter: pointer to the board struct
- *
- * Returns 0 on success or none 0 on error
- **/
-int i40evf_lan_add_device(struct i40evf_adapter *adapter)
-{
- struct i40e_device *ldev;
- int ret = 0;
-
- mutex_lock(&i40evf_device_mutex);
- list_for_each_entry(ldev, &i40evf_devices, list) {
- if (ldev->vf == adapter) {
- ret = -EEXIST;
- goto out;
- }
- }
- ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
- if (!ldev) {
- ret = -ENOMEM;
- goto out;
- }
- ldev->vf = adapter;
- INIT_LIST_HEAD(&ldev->list);
- list_add(&ldev->list, &i40evf_devices);
- dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
- adapter->hw.bus.bus_id, adapter->hw.bus.device,
- adapter->hw.bus.func);
-
- /* Since in some cases register may have happened before a device gets
- * added, we can schedule a subtask to go initiate the clients.
- */
- adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
-
-out:
- mutex_unlock(&i40evf_device_mutex);
- return ret;
-}
-
-/**
- * i40evf_lan_del_device - removes a lan device from the device list
- * @adapter: pointer to the board struct
- *
- * Returns 0 on success or non-0 on error
- **/
-int i40evf_lan_del_device(struct i40evf_adapter *adapter)
-{
- struct i40e_device *ldev, *tmp;
- int ret = -ENODEV;
-
- mutex_lock(&i40evf_device_mutex);
- list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) {
- if (ldev->vf == adapter) {
- dev_info(&adapter->pdev->dev,
- "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
- adapter->hw.bus.bus_id, adapter->hw.bus.device,
- adapter->hw.bus.func);
- list_del(&ldev->list);
- kfree(ldev);
- ret = 0;
- break;
- }
- }
-
- mutex_unlock(&i40evf_device_mutex);
- return ret;
-}
-
-/**
- * i40evf_client_release - release client specific resources
- * @client: pointer to the registered client
- *
- **/
-static void i40evf_client_release(struct i40e_client *client)
-{
- struct i40e_client_instance *cinst;
- struct i40e_device *ldev;
- struct i40evf_adapter *adapter;
-
- mutex_lock(&i40evf_device_mutex);
- list_for_each_entry(ldev, &i40evf_devices, list) {
- adapter = ldev->vf;
- cinst = adapter->cinst;
- if (!cinst)
- continue;
- if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
- if (client->ops && client->ops->close)
- client->ops->close(&cinst->lan_info, client,
- false);
- i40evf_client_release_qvlist(&cinst->lan_info);
- clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
-
- dev_warn(&adapter->pdev->dev,
- "Client %s instance closed\n", client->name);
- }
- /* delete the client instance */
- i40evf_client_del_instance(adapter);
- dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n",
- client->name);
- }
- mutex_unlock(&i40evf_device_mutex);
-}
-
-/**
- * i40evf_client_prepare - prepare client specific resources
- * @client: pointer to the registered client
- *
- **/
-static void i40evf_client_prepare(struct i40e_client *client)
-{
- struct i40e_device *ldev;
- struct i40evf_adapter *adapter;
-
- mutex_lock(&i40evf_device_mutex);
- list_for_each_entry(ldev, &i40evf_devices, list) {
- adapter = ldev->vf;
- /* Signal the watchdog to service the client */
- adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
- }
- mutex_unlock(&i40evf_device_mutex);
-}
-
-/**
- * i40evf_client_virtchnl_send - send a message to the PF instance
- * @ldev: pointer to L2 context.
- * @client: Client pointer.
- * @msg: pointer to message buffer
- * @len: message length
- *
- * Return 0 on success or < 0 on error
- **/
-static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
- struct i40e_client *client,
- u8 *msg, u16 len)
-{
- struct i40evf_adapter *adapter = ldev->vf;
- i40e_status err;
-
- if (adapter->aq_required)
- return -EAGAIN;
-
- err = i40e_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP,
- I40E_SUCCESS, msg, len, NULL);
- if (err)
- dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
- err, adapter->hw.aq.asq_last_status);
-
- return err;
-}
-
-/**
- * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
- * @ldev: pointer to L2 context.
- * @client: Client pointer.
- * @qvlist_info: queue and vector list
- *
- * Return 0 on success or < 0 on error
- **/
-static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
- struct i40e_client *client,
- struct i40e_qvlist_info *qvlist_info)
-{
- struct virtchnl_iwarp_qvlist_info *v_qvlist_info;
- struct i40evf_adapter *adapter = ldev->vf;
- struct i40e_qv_info *qv_info;
- i40e_status err;
- u32 v_idx, i;
- u32 msg_size;
-
- if (adapter->aq_required)
- return -EAGAIN;
-
- /* A quick check on whether the vectors belong to the client */
- for (i = 0; i < qvlist_info->num_vectors; i++) {
- qv_info = &qvlist_info->qv_info[i];
- if (!qv_info)
- continue;
- v_idx = qv_info->v_idx;
- if ((v_idx >=
- (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) ||
- (v_idx < adapter->iwarp_base_vector))
- return -EINVAL;
- }
-
- v_qvlist_info = (struct virtchnl_iwarp_qvlist_info *)qvlist_info;
- msg_size = sizeof(struct virtchnl_iwarp_qvlist_info) +
- (sizeof(struct virtchnl_iwarp_qv_info) *
- (v_qvlist_info->num_vectors - 1));
-
- adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
- err = i40e_aq_send_msg_to_pf(&adapter->hw,
- VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP,
- I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL);
-
- if (err) {
- dev_err(&adapter->pdev->dev,
- "Unable to send iWarp vector config message to PF, error %d, aq status %d\n",
- err, adapter->hw.aq.asq_last_status);
- goto out;
- }
-
- err = -EBUSY;
- for (i = 0; i < 5; i++) {
- msleep(100);
- if (!(adapter->client_pending &
- BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) {
- err = 0;
- break;
- }
- }
-out:
- return err;
-}
-
-/**
- * i40evf_register_client - Register a i40e client driver with the L2 driver
- * @client: pointer to the i40e_client struct
- *
- * Returns 0 on success or non-0 on error
- **/
-int i40evf_register_client(struct i40e_client *client)
-{
- int ret = 0;
-
- if (!client) {
- ret = -EIO;
- goto out;
- }
-
- if (strlen(client->name) == 0) {
- pr_info("i40evf: Failed to register client with no name\n");
- ret = -EIO;
- goto out;
- }
-
- if (vf_registered_client) {
- pr_info("i40evf: Client %s has already been registered!\n",
- client->name);
- ret = -EEXIST;
- goto out;
- }
-
- if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) ||
- (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) {
- pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n",
- client->name);
- pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n",
- client->version.major, client->version.minor,
- client->version.build,
- i40evf_client_interface_version_str);
- ret = -EIO;
- goto out;
- }
-
- vf_registered_client = client;
-
- i40evf_client_prepare(client);
-
- pr_info("i40evf: Registered client %s with return code %d\n",
- client->name, ret);
-out:
- return ret;
-}
-EXPORT_SYMBOL(i40evf_register_client);
-
-/**
- * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver
- * @client: pointer to the i40e_client struct
- *
- * Returns 0 on success or non-0 on error
- **/
-int i40evf_unregister_client(struct i40e_client *client)
-{
- int ret = 0;
-
- /* When a unregister request comes through we would have to send
- * a close for each of the client instances that were opened.
- * client_release function is called to handle this.
- */
- i40evf_client_release(client);
-
- if (vf_registered_client != client) {
- pr_info("i40evf: Client %s has not been registered\n",
- client->name);
- ret = -ENODEV;
- goto out;
- }
- vf_registered_client = NULL;
- pr_info("i40evf: Unregistered client %s\n", client->name);
-out:
- return ret;
-}
-EXPORT_SYMBOL(i40evf_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
deleted file mode 100644
index 5585f36..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40evf_client.h
+++ /dev/null
@@ -1,169 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40EVF_CLIENT_H_
-#define _I40EVF_CLIENT_H_
-
-#define I40EVF_CLIENT_STR_LENGTH 10
-
-/* Client interface version should be updated anytime there is a change in the
- * existing APIs or data structures.
- */
-#define I40EVF_CLIENT_VERSION_MAJOR 0
-#define I40EVF_CLIENT_VERSION_MINOR 01
-#define I40EVF_CLIENT_VERSION_BUILD 00
-#define I40EVF_CLIENT_VERSION_STR \
- __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \
- __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \
- __stringify(I40EVF_CLIENT_VERSION_BUILD)
-
-struct i40e_client_version {
- u8 major;
- u8 minor;
- u8 build;
- u8 rsvd;
-};
-
-enum i40e_client_state {
- __I40E_CLIENT_NULL,
- __I40E_CLIENT_REGISTERED
-};
-
-enum i40e_client_instance_state {
- __I40E_CLIENT_INSTANCE_NONE,
- __I40E_CLIENT_INSTANCE_OPENED,
-};
-
-struct i40e_ops;
-struct i40e_client;
-
-/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
- * In order for us to keep the interface simple, SW will define a
- * unique type value for AEQ.
- */
-#define I40E_QUEUE_TYPE_PE_AEQ 0x80
-#define I40E_QUEUE_INVALID_IDX 0xFFFF
-
-struct i40e_qv_info {
- u32 v_idx; /* msix_vector */
- u16 ceq_idx;
- u16 aeq_idx;
- u8 itr_idx;
-};
-
-struct i40e_qvlist_info {
- u32 num_vectors;
- struct i40e_qv_info qv_info[1];
-};
-
-#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
-
-/* set of LAN parameters useful for clients managed by LAN */
-
-/* Struct to hold per priority info */
-struct i40e_prio_qos_params {
- u16 qs_handle; /* qs handle for prio */
- u8 tc; /* TC mapped to prio */
- u8 reserved;
-};
-
-#define I40E_CLIENT_MAX_USER_PRIORITY 8
-/* Struct to hold Client QoS */
-struct i40e_qos_params {
- struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
-};
-
-struct i40e_params {
- struct i40e_qos_params qos;
- u16 mtu;
- u16 link_up; /* boolean */
-};
-
-/* Structure to hold LAN device info for a client device */
-struct i40e_info {
- struct i40e_client_version version;
- u8 lanmac[6];
- struct net_device *netdev;
- struct pci_dev *pcidev;
- u8 __iomem *hw_addr;
- u8 fid; /* function id, PF id or VF id */
-#define I40E_CLIENT_FTYPE_PF 0
-#define I40E_CLIENT_FTYPE_VF 1
- u8 ftype; /* function type, PF or VF */
- void *vf; /* cast to i40evf_adapter */
-
- /* All L2 params that could change during the life span of the device
- * and needs to be communicated to the client when they change
- */
- struct i40e_params params;
- struct i40e_ops *ops;
-
- u16 msix_count; /* number of msix vectors*/
- /* Array down below will be dynamically allocated based on msix_count */
- struct msix_entry *msix_entries;
- u16 itr_index; /* Which ITR index the PE driver is suppose to use */
-};
-
-struct i40e_ops {
- /* setup_q_vector_list enables queues with a particular vector */
- int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
- struct i40e_qvlist_info *qv_info);
-
- u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
- u8 *msg, u16 len);
-
- /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
- void (*request_reset)(struct i40e_info *ldev,
- struct i40e_client *client);
-};
-
-struct i40e_client_ops {
- /* Should be called from register_client() or whenever the driver is
- * ready to create a specific client instance.
- */
- int (*open)(struct i40e_info *ldev, struct i40e_client *client);
-
- /* Should be closed when netdev is unavailable or when unregister
- * call comes in. If the close happens due to a reset, set the reset
- * bit to true.
- */
- void (*close)(struct i40e_info *ldev, struct i40e_client *client,
- bool reset);
-
- /* called when some l2 managed parameters changes - mss */
- void (*l2_param_change)(struct i40e_info *ldev,
- struct i40e_client *client,
- struct i40e_params *params);
-
- /* called when a message is received from the PF */
- int (*virtchnl_receive)(struct i40e_info *ldev,
- struct i40e_client *client,
- u8 *msg, u16 len);
-};
-
-/* Client device */
-struct i40e_client_instance {
- struct list_head list;
- struct i40e_info lan_info;
- struct i40e_client *client;
- unsigned long state;
-};
-
-struct i40e_client {
- struct list_head list; /* list of registered clients */
- char name[I40EVF_CLIENT_STR_LENGTH];
- struct i40e_client_version version;
- unsigned long state; /* client state */
- atomic_t ref_cnt; /* Count of all the client devices of this kind */
- u32 flags;
-#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0)
-#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2)
- u8 type;
-#define I40E_CLIENT_IWARP 0
- struct i40e_client_ops *ops; /* client ops provided by the client */
-};
-
-/* used by clients */
-int i40evf_register_client(struct i40e_client *client);
-int i40evf_unregister_client(struct i40e_client *client);
-#endif /* _I40EVF_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
deleted file mode 100644
index 69efe0a..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ /dev/null
@@ -1,820 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-/* ethtool support for i40evf */
-#include "i40evf.h"
-
-#include <linux/uaccess.h>
-
-struct i40evf_stats {
- char stat_string[ETH_GSTRING_LEN];
- int stat_offset;
-};
-
-#define I40EVF_STAT(_name, _stat) { \
- .stat_string = _name, \
- .stat_offset = offsetof(struct i40evf_adapter, _stat) \
-}
-
-/* All stats are u64, so we don't need to track the size of the field. */
-static const struct i40evf_stats i40evf_gstrings_stats[] = {
- I40EVF_STAT("rx_bytes", current_stats.rx_bytes),
- I40EVF_STAT("rx_unicast", current_stats.rx_unicast),
- I40EVF_STAT("rx_multicast", current_stats.rx_multicast),
- I40EVF_STAT("rx_broadcast", current_stats.rx_broadcast),
- I40EVF_STAT("rx_discards", current_stats.rx_discards),
- I40EVF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol),
- I40EVF_STAT("tx_bytes", current_stats.tx_bytes),
- I40EVF_STAT("tx_unicast", current_stats.tx_unicast),
- I40EVF_STAT("tx_multicast", current_stats.tx_multicast),
- I40EVF_STAT("tx_broadcast", current_stats.tx_broadcast),
- I40EVF_STAT("tx_discards", current_stats.tx_discards),
- I40EVF_STAT("tx_errors", current_stats.tx_errors),
-};
-
-#define I40EVF_GLOBAL_STATS_LEN ARRAY_SIZE(i40evf_gstrings_stats)
-#define I40EVF_QUEUE_STATS_LEN(_dev) \
- (((struct i40evf_adapter *)\
- netdev_priv(_dev))->num_active_queues \
- * 2 * (sizeof(struct i40e_queue_stats) / sizeof(u64)))
-#define I40EVF_STATS_LEN(_dev) \
- (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev))
-
-/* For now we have one and only one private flag and it is only defined
- * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead
- * of leaving all this code sitting around empty we will strip it unless
- * our one private flag is actually available.
- */
-struct i40evf_priv_flags {
- char flag_string[ETH_GSTRING_LEN];
- u32 flag;
- bool read_only;
-};
-
-#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \
- .flag_string = _name, \
- .flag = _flag, \
- .read_only = _read_only, \
-}
-
-static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = {
- I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0),
-};
-
-#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags)
-
-/**
- * i40evf_get_link_ksettings - Get Link Speed and Duplex settings
- * @netdev: network interface device structure
- * @cmd: ethtool command
- *
- * Reports speed/duplex settings. Because this is a VF, we don't know what
- * kind of link we really have, so we fake it.
- **/
-static int i40evf_get_link_ksettings(struct net_device *netdev,
- struct ethtool_link_ksettings *cmd)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- ethtool_link_ksettings_zero_link_mode(cmd, supported);
- cmd->base.autoneg = AUTONEG_DISABLE;
- cmd->base.port = PORT_NONE;
- /* Set speed and duplex */
- switch (adapter->link_speed) {
- case I40E_LINK_SPEED_40GB:
- cmd->base.speed = SPEED_40000;
- break;
- case I40E_LINK_SPEED_25GB:
-#ifdef SPEED_25000
- cmd->base.speed = SPEED_25000;
-#else
- netdev_info(netdev,
- "Speed is 25G, display not supported by this version of ethtool.\n");
-#endif
- break;
- case I40E_LINK_SPEED_20GB:
- cmd->base.speed = SPEED_20000;
- break;
- case I40E_LINK_SPEED_10GB:
- cmd->base.speed = SPEED_10000;
- break;
- case I40E_LINK_SPEED_1GB:
- cmd->base.speed = SPEED_1000;
- break;
- case I40E_LINK_SPEED_100MB:
- cmd->base.speed = SPEED_100;
- break;
- default:
- break;
- }
- cmd->base.duplex = DUPLEX_FULL;
-
- return 0;
-}
-
-/**
- * i40evf_get_sset_count - Get length of string set
- * @netdev: network interface device structure
- * @sset: id of string set
- *
- * Reports size of string table. This driver only supports
- * strings for statistics.
- **/
-static int i40evf_get_sset_count(struct net_device *netdev, int sset)
-{
- if (sset == ETH_SS_STATS)
- return I40EVF_STATS_LEN(netdev);
- else if (sset == ETH_SS_PRIV_FLAGS)
- return I40EVF_PRIV_FLAGS_STR_LEN;
- else
- return -EINVAL;
-}
-
-/**
- * i40evf_get_ethtool_stats - report device statistics
- * @netdev: network interface device structure
- * @stats: ethtool statistics structure
- * @data: pointer to data buffer
- *
- * All statistics are added to the data buffer as an array of u64.
- **/
-static void i40evf_get_ethtool_stats(struct net_device *netdev,
- struct ethtool_stats *stats, u64 *data)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- unsigned int i, j;
- char *p;
-
- for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) {
- p = (char *)adapter + i40evf_gstrings_stats[i].stat_offset;
- data[i] = *(u64 *)p;
- }
- for (j = 0; j < adapter->num_active_queues; j++) {
- data[i++] = adapter->tx_rings[j].stats.packets;
- data[i++] = adapter->tx_rings[j].stats.bytes;
- }
- for (j = 0; j < adapter->num_active_queues; j++) {
- data[i++] = adapter->rx_rings[j].stats.packets;
- data[i++] = adapter->rx_rings[j].stats.bytes;
- }
-}
-
-/**
- * i40evf_get_strings - Get string set
- * @netdev: network interface device structure
- * @sset: id of string set
- * @data: buffer for string data
- *
- * Builds stats string table.
- **/
-static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u8 *p = data;
- int i;
-
- if (sset == ETH_SS_STATS) {
- for (i = 0; i < (int)I40EVF_GLOBAL_STATS_LEN; i++) {
- memcpy(p, i40evf_gstrings_stats[i].stat_string,
- ETH_GSTRING_LEN);
- p += ETH_GSTRING_LEN;
- }
- for (i = 0; i < adapter->num_active_queues; i++) {
- snprintf(p, ETH_GSTRING_LEN, "tx-%u.packets", i);
- p += ETH_GSTRING_LEN;
- snprintf(p, ETH_GSTRING_LEN, "tx-%u.bytes", i);
- p += ETH_GSTRING_LEN;
- }
- for (i = 0; i < adapter->num_active_queues; i++) {
- snprintf(p, ETH_GSTRING_LEN, "rx-%u.packets", i);
- p += ETH_GSTRING_LEN;
- snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i);
- p += ETH_GSTRING_LEN;
- }
- } else if (sset == ETH_SS_PRIV_FLAGS) {
- for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
- snprintf(p, ETH_GSTRING_LEN, "%s",
- i40evf_gstrings_priv_flags[i].flag_string);
- p += ETH_GSTRING_LEN;
- }
- }
-}
-
-/**
- * i40evf_get_priv_flags - report device private flags
- * @netdev: network interface device structure
- *
- * The get string set count and the string set should be matched for each
- * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags
- * array.
- *
- * Returns a u32 bitmap of flags.
- **/
-static u32 i40evf_get_priv_flags(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u32 i, ret_flags = 0;
-
- for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
- const struct i40evf_priv_flags *priv_flags;
-
- priv_flags = &i40evf_gstrings_priv_flags[i];
-
- if (priv_flags->flag & adapter->flags)
- ret_flags |= BIT(i);
- }
-
- return ret_flags;
-}
-
-/**
- * i40evf_set_priv_flags - set private flags
- * @netdev: network interface device structure
- * @flags: bit flags to be set
- **/
-static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u32 orig_flags, new_flags, changed_flags;
- u32 i;
-
- orig_flags = READ_ONCE(adapter->flags);
- new_flags = orig_flags;
-
- for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
- const struct i40evf_priv_flags *priv_flags;
-
- priv_flags = &i40evf_gstrings_priv_flags[i];
-
- if (flags & BIT(i))
- new_flags |= priv_flags->flag;
- else
- new_flags &= ~(priv_flags->flag);
-
- if (priv_flags->read_only &&
- ((orig_flags ^ new_flags) & ~BIT(i)))
- return -EOPNOTSUPP;
- }
-
- /* Before we finalize any flag changes, any checks which we need to
- * perform to determine if the new flags will be supported should go
- * here...
- */
-
- /* Compare and exchange the new flags into place. If we failed, that
- * is if cmpxchg returns anything but the old value, this means
- * something else must have modified the flags variable since we
- * copied it. We'll just punt with an error and log something in the
- * message buffer.
- */
- if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) {
- dev_warn(&adapter->pdev->dev,
- "Unable to update adapter->flags as it was modified by another thread...\n");
- return -EAGAIN;
- }
-
- changed_flags = orig_flags ^ new_flags;
-
- /* Process any additional changes needed as a result of flag changes.
- * The changed_flags value reflects the list of bits that were changed
- * in the code above.
- */
-
- /* issue a reset to force legacy-rx change to take effect */
- if (changed_flags & I40EVF_FLAG_LEGACY_RX) {
- if (netif_running(netdev)) {
- adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
- schedule_work(&adapter->reset_task);
- }
- }
-
- return 0;
-}
-
-/**
- * i40evf_get_msglevel - Get debug message level
- * @netdev: network interface device structure
- *
- * Returns current debug message level.
- **/
-static u32 i40evf_get_msglevel(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- return adapter->msg_enable;
-}
-
-/**
- * i40evf_set_msglevel - Set debug message level
- * @netdev: network interface device structure
- * @data: message level
- *
- * Set current debug message level. Higher values cause the driver to
- * be noisier.
- **/
-static void i40evf_set_msglevel(struct net_device *netdev, u32 data)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- if (I40E_DEBUG_USER & data)
- adapter->hw.debug_mask = data;
- adapter->msg_enable = data;
-}
-
-/**
- * i40evf_get_drvinfo - Get driver info
- * @netdev: network interface device structure
- * @drvinfo: ethool driver info structure
- *
- * Returns information about the driver and device for display to the user.
- **/
-static void i40evf_get_drvinfo(struct net_device *netdev,
- struct ethtool_drvinfo *drvinfo)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- strlcpy(drvinfo->driver, i40evf_driver_name, 32);
- strlcpy(drvinfo->version, i40evf_driver_version, 32);
- strlcpy(drvinfo->fw_version, "N/A", 4);
- strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
- drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN;
-}
-
-/**
- * i40evf_get_ringparam - Get ring parameters
- * @netdev: network interface device structure
- * @ring: ethtool ringparam structure
- *
- * Returns current ring parameters. TX and RX rings are reported separately,
- * but the number of rings is not reported.
- **/
-static void i40evf_get_ringparam(struct net_device *netdev,
- struct ethtool_ringparam *ring)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- ring->rx_max_pending = I40EVF_MAX_RXD;
- ring->tx_max_pending = I40EVF_MAX_TXD;
- ring->rx_pending = adapter->rx_desc_count;
- ring->tx_pending = adapter->tx_desc_count;
-}
-
-/**
- * i40evf_set_ringparam - Set ring parameters
- * @netdev: network interface device structure
- * @ring: ethtool ringparam structure
- *
- * Sets ring parameters. TX and RX rings are controlled separately, but the
- * number of rings is not specified, so all rings get the same settings.
- **/
-static int i40evf_set_ringparam(struct net_device *netdev,
- struct ethtool_ringparam *ring)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u32 new_rx_count, new_tx_count;
-
- if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
- return -EINVAL;
-
- new_tx_count = clamp_t(u32, ring->tx_pending,
- I40EVF_MIN_TXD,
- I40EVF_MAX_TXD);
- new_tx_count = ALIGN(new_tx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE);
-
- new_rx_count = clamp_t(u32, ring->rx_pending,
- I40EVF_MIN_RXD,
- I40EVF_MAX_RXD);
- new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE);
-
- /* if nothing to do return success */
- if ((new_tx_count == adapter->tx_desc_count) &&
- (new_rx_count == adapter->rx_desc_count))
- return 0;
-
- adapter->tx_desc_count = new_tx_count;
- adapter->rx_desc_count = new_rx_count;
-
- if (netif_running(netdev)) {
- adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
- schedule_work(&adapter->reset_task);
- }
-
- return 0;
-}
-
-/**
- * __i40evf_get_coalesce - get per-queue coalesce settings
- * @netdev: the netdev to check
- * @ec: ethtool coalesce data structure
- * @queue: which queue to pick
- *
- * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs
- * are per queue. If queue is <0 then we default to queue 0 as the
- * representative value.
- **/
-static int __i40evf_get_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *ec,
- int queue)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40e_vsi *vsi = &adapter->vsi;
- struct i40e_ring *rx_ring, *tx_ring;
-
- ec->tx_max_coalesced_frames = vsi->work_limit;
- ec->rx_max_coalesced_frames = vsi->work_limit;
-
- /* Rx and Tx usecs per queue value. If user doesn't specify the
- * queue, return queue 0's value to represent.
- */
- if (queue < 0)
- queue = 0;
- else if (queue >= adapter->num_active_queues)
- return -EINVAL;
-
- rx_ring = &adapter->rx_rings[queue];
- tx_ring = &adapter->tx_rings[queue];
-
- if (ITR_IS_DYNAMIC(rx_ring->itr_setting))
- ec->use_adaptive_rx_coalesce = 1;
-
- if (ITR_IS_DYNAMIC(tx_ring->itr_setting))
- ec->use_adaptive_tx_coalesce = 1;
-
- ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC;
- ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC;
-
- return 0;
-}
-
-/**
- * i40evf_get_coalesce - Get interrupt coalescing settings
- * @netdev: network interface device structure
- * @ec: ethtool coalesce structure
- *
- * Returns current coalescing settings. This is referred to elsewhere in the
- * driver as Interrupt Throttle Rate, as this is how the hardware describes
- * this functionality. Note that if per-queue settings have been modified this
- * only represents the settings of queue 0.
- **/
-static int i40evf_get_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *ec)
-{
- return __i40evf_get_coalesce(netdev, ec, -1);
-}
-
-/**
- * i40evf_get_per_queue_coalesce - get coalesce values for specific queue
- * @netdev: netdev to read
- * @ec: coalesce settings from ethtool
- * @queue: the queue to read
- *
- * Read specific queue's coalesce settings.
- **/
-static int i40evf_get_per_queue_coalesce(struct net_device *netdev,
- u32 queue,
- struct ethtool_coalesce *ec)
-{
- return __i40evf_get_coalesce(netdev, ec, queue);
-}
-
-/**
- * i40evf_set_itr_per_queue - set ITR values for specific queue
- * @adapter: the VF adapter struct to set values for
- * @ec: coalesce settings from ethtool
- * @queue: the queue to modify
- *
- * Change the ITR settings for a specific queue.
- **/
-static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter,
- struct ethtool_coalesce *ec,
- int queue)
-{
- struct i40e_ring *rx_ring = &adapter->rx_rings[queue];
- struct i40e_ring *tx_ring = &adapter->tx_rings[queue];
- struct i40e_q_vector *q_vector;
-
- rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
- tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
-
- rx_ring->itr_setting |= I40E_ITR_DYNAMIC;
- if (!ec->use_adaptive_rx_coalesce)
- rx_ring->itr_setting ^= I40E_ITR_DYNAMIC;
-
- tx_ring->itr_setting |= I40E_ITR_DYNAMIC;
- if (!ec->use_adaptive_tx_coalesce)
- tx_ring->itr_setting ^= I40E_ITR_DYNAMIC;
-
- q_vector = rx_ring->q_vector;
- q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
-
- q_vector = tx_ring->q_vector;
- q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
-
- /* The interrupt handler itself will take care of programming
- * the Tx and Rx ITR values based on the values we have entered
- * into the q_vector, no need to write the values now.
- */
-}
-
-/**
- * __i40evf_set_coalesce - set coalesce settings for particular queue
- * @netdev: the netdev to change
- * @ec: ethtool coalesce settings
- * @queue: the queue to change
- *
- * Sets the coalesce settings for a particular queue.
- **/
-static int __i40evf_set_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *ec,
- int queue)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40e_vsi *vsi = &adapter->vsi;
- int i;
-
- if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
- vsi->work_limit = ec->tx_max_coalesced_frames_irq;
-
- if (ec->rx_coalesce_usecs == 0) {
- if (ec->use_adaptive_rx_coalesce)
- netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n");
- } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) ||
- (ec->rx_coalesce_usecs > I40E_MAX_ITR)) {
- netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
- return -EINVAL;
- }
-
- else
- if (ec->tx_coalesce_usecs == 0) {
- if (ec->use_adaptive_tx_coalesce)
- netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n");
- } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) ||
- (ec->tx_coalesce_usecs > I40E_MAX_ITR)) {
- netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n");
- return -EINVAL;
- }
-
- /* Rx and Tx usecs has per queue value. If user doesn't specify the
- * queue, apply to all queues.
- */
- if (queue < 0) {
- for (i = 0; i < adapter->num_active_queues; i++)
- i40evf_set_itr_per_queue(adapter, ec, i);
- } else if (queue < adapter->num_active_queues) {
- i40evf_set_itr_per_queue(adapter, ec, queue);
- } else {
- netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n",
- adapter->num_active_queues - 1);
- return -EINVAL;
- }
-
- return 0;
-}
-
-/**
- * i40evf_set_coalesce - Set interrupt coalescing settings
- * @netdev: network interface device structure
- * @ec: ethtool coalesce structure
- *
- * Change current coalescing settings for every queue.
- **/
-static int i40evf_set_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *ec)
-{
- return __i40evf_set_coalesce(netdev, ec, -1);
-}
-
-/**
- * i40evf_set_per_queue_coalesce - set specific queue's coalesce settings
- * @netdev: the netdev to change
- * @ec: ethtool's coalesce settings
- * @queue: the queue to modify
- *
- * Modifies a specific queue's coalesce settings.
- */
-static int i40evf_set_per_queue_coalesce(struct net_device *netdev,
- u32 queue,
- struct ethtool_coalesce *ec)
-{
- return __i40evf_set_coalesce(netdev, ec, queue);
-}
-
-/**
- * i40evf_get_rxnfc - command to get RX flow classification rules
- * @netdev: network interface device structure
- * @cmd: ethtool rxnfc command
- * @rule_locs: pointer to store rule locations
- *
- * Returns Success if the command is supported.
- **/
-static int i40evf_get_rxnfc(struct net_device *netdev,
- struct ethtool_rxnfc *cmd,
- u32 *rule_locs)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- int ret = -EOPNOTSUPP;
-
- switch (cmd->cmd) {
- case ETHTOOL_GRXRINGS:
- cmd->data = adapter->num_active_queues;
- ret = 0;
- break;
- case ETHTOOL_GRXFH:
- netdev_info(netdev,
- "RSS hash info is not available to vf, use pf.\n");
- break;
- default:
- break;
- }
-
- return ret;
-}
-/**
- * i40evf_get_channels: get the number of channels supported by the device
- * @netdev: network interface device structure
- * @ch: channel information structure
- *
- * For the purposes of our device, we only use combined channels, i.e. a tx/rx
- * queue pair. Report one extra channel to match our "other" MSI-X vector.
- **/
-static void i40evf_get_channels(struct net_device *netdev,
- struct ethtool_channels *ch)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- /* Report maximum channels */
- ch->max_combined = I40EVF_MAX_REQ_QUEUES;
-
- ch->max_other = NONQ_VECS;
- ch->other_count = NONQ_VECS;
-
- ch->combined_count = adapter->num_active_queues;
-}
-
-/**
- * i40evf_set_channels: set the new channel count
- * @netdev: network interface device structure
- * @ch: channel information structure
- *
- * Negotiate a new number of channels with the PF then do a reset. During
- * reset we'll realloc queues and fix the RSS table. Returns 0 on success,
- * negative on failure.
- **/
-static int i40evf_set_channels(struct net_device *netdev,
- struct ethtool_channels *ch)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- int num_req = ch->combined_count;
-
- if (num_req != adapter->num_active_queues &&
- !(adapter->vf_res->vf_cap_flags &
- VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) {
- dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n");
- return -EINVAL;
- }
-
- if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
- adapter->num_tc) {
- dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n");
- return -EINVAL;
- }
-
- /* All of these should have already been checked by ethtool before this
- * even gets to us, but just to be sure.
- */
- if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES)
- return -EINVAL;
-
- if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS)
- return -EINVAL;
-
- adapter->num_req_queues = num_req;
- return i40evf_request_queues(adapter, num_req);
-}
-
-/**
- * i40evf_get_rxfh_key_size - get the RSS hash key size
- * @netdev: network interface device structure
- *
- * Returns the table size.
- **/
-static u32 i40evf_get_rxfh_key_size(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- return adapter->rss_key_size;
-}
-
-/**
- * i40evf_get_rxfh_indir_size - get the rx flow hash indirection table size
- * @netdev: network interface device structure
- *
- * Returns the table size.
- **/
-static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- return adapter->rss_lut_size;
-}
-
-/**
- * i40evf_get_rxfh - get the rx flow hash indirection table
- * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function in use
- *
- * Reads the indirection table directly from the hardware. Always returns 0.
- **/
-static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
- u8 *hfunc)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u16 i;
-
- if (hfunc)
- *hfunc = ETH_RSS_HASH_TOP;
- if (!indir)
- return 0;
-
- memcpy(key, adapter->rss_key, adapter->rss_key_size);
-
- /* Each 32 bits pointed by 'indir' is stored with a lut entry */
- for (i = 0; i < adapter->rss_lut_size; i++)
- indir[i] = (u32)adapter->rss_lut[i];
-
- return 0;
-}
-
-/**
- * i40evf_set_rxfh - set the rx flow hash indirection table
- * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
- *
- * Returns -EINVAL if the table specifies an inavlid queue id, otherwise
- * returns 0 after programming the table.
- **/
-static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
- const u8 *key, const u8 hfunc)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- u16 i;
-
- /* We do not allow change in unsupported parameters */
- if (key ||
- (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
- return -EOPNOTSUPP;
- if (!indir)
- return 0;
-
- if (key) {
- memcpy(adapter->rss_key, key, adapter->rss_key_size);
- }
-
- /* Each 32 bits pointed by 'indir' is stored with a lut entry */
- for (i = 0; i < adapter->rss_lut_size; i++)
- adapter->rss_lut[i] = (u8)(indir[i]);
-
- return i40evf_config_rss(adapter);
-}
-
-static const struct ethtool_ops i40evf_ethtool_ops = {
- .get_drvinfo = i40evf_get_drvinfo,
- .get_link = ethtool_op_get_link,
- .get_ringparam = i40evf_get_ringparam,
- .set_ringparam = i40evf_set_ringparam,
- .get_strings = i40evf_get_strings,
- .get_ethtool_stats = i40evf_get_ethtool_stats,
- .get_sset_count = i40evf_get_sset_count,
- .get_priv_flags = i40evf_get_priv_flags,
- .set_priv_flags = i40evf_set_priv_flags,
- .get_msglevel = i40evf_get_msglevel,
- .set_msglevel = i40evf_set_msglevel,
- .get_coalesce = i40evf_get_coalesce,
- .set_coalesce = i40evf_set_coalesce,
- .get_per_queue_coalesce = i40evf_get_per_queue_coalesce,
- .set_per_queue_coalesce = i40evf_set_per_queue_coalesce,
- .get_rxnfc = i40evf_get_rxnfc,
- .get_rxfh_indir_size = i40evf_get_rxfh_indir_size,
- .get_rxfh = i40evf_get_rxfh,
- .set_rxfh = i40evf_set_rxfh,
- .get_channels = i40evf_get_channels,
- .set_channels = i40evf_set_channels,
- .get_rxfh_key_size = i40evf_get_rxfh_key_size,
- .get_link_ksettings = i40evf_get_link_ksettings,
-};
-
-/**
- * i40evf_set_ethtool_ops - Initialize ethtool ops struct
- * @netdev: network interface device structure
- *
- * Sets ethtool ops struct in our netdev so that ethtool can call
- * our functions.
- **/
-void i40evf_set_ethtool_ops(struct net_device *netdev)
-{
- netdev->ethtool_ops = &i40evf_ethtool_ops;
-}
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
deleted file mode 100644
index fef6d89..0000000
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ /dev/null
@@ -1,3982 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#include "i40evf.h"
-#include "i40e_prototype.h"
-#include "i40evf_client.h"
-/* All i40evf tracepoints are defined by the include below, which must
- * be included exactly once across the whole kernel with
- * CREATE_TRACE_POINTS defined
- */
-#define CREATE_TRACE_POINTS
-#include "i40e_trace.h"
-
-static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
-static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
-static int i40evf_close(struct net_device *netdev);
-
-char i40evf_driver_name[] = "i40evf";
-static const char i40evf_driver_string[] =
- "Intel(R) 40-10 Gigabit Virtual Function Network Driver";
-
-#define DRV_KERN "-k"
-
-#define DRV_VERSION_MAJOR 3
-#define DRV_VERSION_MINOR 2
-#define DRV_VERSION_BUILD 2
-#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
- __stringify(DRV_VERSION_MINOR) "." \
- __stringify(DRV_VERSION_BUILD) \
- DRV_KERN
-const char i40evf_driver_version[] = DRV_VERSION;
-static const char i40evf_copyright[] =
- "Copyright (c) 2013 - 2015 Intel Corporation.";
-
-/* i40evf_pci_tbl - PCI Device ID Table
- *
- * Wildcard entries (PCI_ANY_ID) should come last
- * Last entry must be all 0s
- *
- * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
- * Class, Class Mask, private data (not used) }
- */
-static const struct pci_device_id i40evf_pci_tbl[] = {
- {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF), 0},
- {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF_HV), 0},
- {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF), 0},
- {PCI_VDEVICE(INTEL, I40E_DEV_ID_ADAPTIVE_VF), 0},
- /* required last entry */
- {0, }
-};
-
-MODULE_DEVICE_TABLE(pci, i40evf_pci_tbl);
-
-MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
-MODULE_DESCRIPTION("Intel(R) XL710 X710 Virtual Function Network Driver");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_VERSION);
-
-static struct workqueue_struct *i40evf_wq;
-
-/**
- * i40evf_allocate_dma_mem_d - OS specific memory alloc for shared code
- * @hw: pointer to the HW structure
- * @mem: ptr to mem struct to fill out
- * @size: size of memory requested
- * @alignment: what to align the allocation to
- **/
-i40e_status i40evf_allocate_dma_mem_d(struct i40e_hw *hw,
- struct i40e_dma_mem *mem,
- u64 size, u32 alignment)
-{
- struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back;
-
- if (!mem)
- return I40E_ERR_PARAM;
-
- mem->size = ALIGN(size, alignment);
- mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size,
- (dma_addr_t *)&mem->pa, GFP_KERNEL);
- if (mem->va)
- return 0;
- else
- return I40E_ERR_NO_MEMORY;
-}
-
-/**
- * i40evf_free_dma_mem_d - OS specific memory free for shared code
- * @hw: pointer to the HW structure
- * @mem: ptr to mem struct to free
- **/
-i40e_status i40evf_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem)
-{
- struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back;
-
- if (!mem || !mem->va)
- return I40E_ERR_PARAM;
- dma_free_coherent(&adapter->pdev->dev, mem->size,
- mem->va, (dma_addr_t)mem->pa);
- return 0;
-}
-
-/**
- * i40evf_allocate_virt_mem_d - OS specific memory alloc for shared code
- * @hw: pointer to the HW structure
- * @mem: ptr to mem struct to fill out
- * @size: size of memory requested
- **/
-i40e_status i40evf_allocate_virt_mem_d(struct i40e_hw *hw,
- struct i40e_virt_mem *mem, u32 size)
-{
- if (!mem)
- return I40E_ERR_PARAM;
-
- mem->size = size;
- mem->va = kzalloc(size, GFP_KERNEL);
-
- if (mem->va)
- return 0;
- else
- return I40E_ERR_NO_MEMORY;
-}
-
-/**
- * i40evf_free_virt_mem_d - OS specific memory free for shared code
- * @hw: pointer to the HW structure
- * @mem: ptr to mem struct to free
- **/
-i40e_status i40evf_free_virt_mem_d(struct i40e_hw *hw,
- struct i40e_virt_mem *mem)
-{
- if (!mem)
- return I40E_ERR_PARAM;
-
- /* it's ok to kfree a NULL pointer */
- kfree(mem->va);
-
- return 0;
-}
-
-/**
- * i40evf_debug_d - OS dependent version of debug printing
- * @hw: pointer to the HW structure
- * @mask: debug level mask
- * @fmt_str: printf-type format description
- **/
-void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...)
-{
- char buf[512];
- va_list argptr;
-
- if (!(mask & ((struct i40e_hw *)hw)->debug_mask))
- return;
-
- va_start(argptr, fmt_str);
- vsnprintf(buf, sizeof(buf), fmt_str, argptr);
- va_end(argptr);
-
- /* the debug string is already formatted with a newline */
- pr_info("%s", buf);
-}
-
-/**
- * i40evf_schedule_reset - Set the flags and schedule a reset event
- * @adapter: board private structure
- **/
-void i40evf_schedule_reset(struct i40evf_adapter *adapter)
-{
- if (!(adapter->flags &
- (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED))) {
- adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
- schedule_work(&adapter->reset_task);
- }
-}
-
-/**
- * i40evf_tx_timeout - Respond to a Tx Hang
- * @netdev: network interface device structure
- **/
-static void i40evf_tx_timeout(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- adapter->tx_timeout_count++;
- i40evf_schedule_reset(adapter);
-}
-
-/**
- * i40evf_misc_irq_disable - Mask off interrupt generation on the NIC
- * @adapter: board private structure
- **/
-static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter)
-{
- struct i40e_hw *hw = &adapter->hw;
-
- if (!adapter->msix_entries)
- return;
-
- wr32(hw, I40E_VFINT_DYN_CTL01, 0);
-
- /* read flush */
- rd32(hw, I40E_VFGEN_RSTAT);
-
- synchronize_irq(adapter->msix_entries[0].vector);
-}
-
-/**
- * i40evf_misc_irq_enable - Enable default interrupt generation settings
- * @adapter: board private structure
- **/
-static void i40evf_misc_irq_enable(struct i40evf_adapter *adapter)
-{
- struct i40e_hw *hw = &adapter->hw;
-
- wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK |
- I40E_VFINT_DYN_CTL01_ITR_INDX_MASK);
- wr32(hw, I40E_VFINT_ICR0_ENA1, I40E_VFINT_ICR0_ENA1_ADMINQ_MASK);
-
- /* read flush */
- rd32(hw, I40E_VFGEN_RSTAT);
-}
-
-/**
- * i40evf_irq_disable - Mask off interrupt generation on the NIC
- * @adapter: board private structure
- **/
-static void i40evf_irq_disable(struct i40evf_adapter *adapter)
-{
- int i;
- struct i40e_hw *hw = &adapter->hw;
-
- if (!adapter->msix_entries)
- return;
-
- for (i = 1; i < adapter->num_msix_vectors; i++) {
- wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), 0);
- synchronize_irq(adapter->msix_entries[i].vector);
- }
- /* read flush */
- rd32(hw, I40E_VFGEN_RSTAT);
-}
-
-/**
- * i40evf_irq_enable_queues - Enable interrupt for specified queues
- * @adapter: board private structure
- * @mask: bitmap of queues to enable
- **/
-void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask)
-{
- struct i40e_hw *hw = &adapter->hw;
- int i;
-
- for (i = 1; i < adapter->num_msix_vectors; i++) {
- if (mask & BIT(i - 1)) {
- wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1),
- I40E_VFINT_DYN_CTLN1_INTENA_MASK |
- I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK);
- }
- }
-}
-
-/**
- * i40evf_irq_enable - Enable default interrupt generation settings
- * @adapter: board private structure
- * @flush: boolean value whether to run rd32()
- **/
-void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush)
-{
- struct i40e_hw *hw = &adapter->hw;
-
- i40evf_misc_irq_enable(adapter);
- i40evf_irq_enable_queues(adapter, ~0);
-
- if (flush)
- rd32(hw, I40E_VFGEN_RSTAT);
-}
-
-/**
- * i40evf_msix_aq - Interrupt handler for vector 0
- * @irq: interrupt number
- * @data: pointer to netdev
- **/
-static irqreturn_t i40evf_msix_aq(int irq, void *data)
-{
- struct net_device *netdev = data;
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40e_hw *hw = &adapter->hw;
-
- /* handle non-queue interrupts, these reads clear the registers */
- rd32(hw, I40E_VFINT_ICR01);
- rd32(hw, I40E_VFINT_ICR0_ENA1);
-
- /* schedule work on the private workqueue */
- schedule_work(&adapter->adminq_task);
-
- return IRQ_HANDLED;
-}
-
-/**
- * i40evf_msix_clean_rings - MSIX mode Interrupt Handler
- * @irq: interrupt number
- * @data: pointer to a q_vector
- **/
-static irqreturn_t i40evf_msix_clean_rings(int irq, void *data)
-{
- struct i40e_q_vector *q_vector = data;
-
- if (!q_vector->tx.ring && !q_vector->rx.ring)
- return IRQ_HANDLED;
-
- napi_schedule_irqoff(&q_vector->napi);
-
- return IRQ_HANDLED;
-}
-
-/**
- * i40evf_map_vector_to_rxq - associate irqs with rx queues
- * @adapter: board private structure
- * @v_idx: interrupt number
- * @r_idx: queue number
- **/
-static void
-i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx)
-{
- struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx];
- struct i40e_ring *rx_ring = &adapter->rx_rings[r_idx];
- struct i40e_hw *hw = &adapter->hw;
-
- rx_ring->q_vector = q_vector;
- rx_ring->next = q_vector->rx.ring;
- rx_ring->vsi = &adapter->vsi;
- q_vector->rx.ring = rx_ring;
- q_vector->rx.count++;
- q_vector->rx.next_update = jiffies + 1;
- q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
- q_vector->ring_mask |= BIT(r_idx);
- wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx),
- q_vector->rx.current_itr);
- q_vector->rx.current_itr = q_vector->rx.target_itr;
-}
-
-/**
- * i40evf_map_vector_to_txq - associate irqs with tx queues
- * @adapter: board private structure
- * @v_idx: interrupt number
- * @t_idx: queue number
- **/
-static void
-i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
-{
- struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx];
- struct i40e_ring *tx_ring = &adapter->tx_rings[t_idx];
- struct i40e_hw *hw = &adapter->hw;
-
- tx_ring->q_vector = q_vector;
- tx_ring->next = q_vector->tx.ring;
- tx_ring->vsi = &adapter->vsi;
- q_vector->tx.ring = tx_ring;
- q_vector->tx.count++;
- q_vector->tx.next_update = jiffies + 1;
- q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
- q_vector->num_ringpairs++;
- wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx),
- q_vector->tx.target_itr);
- q_vector->tx.current_itr = q_vector->tx.target_itr;
-}
-
-/**
- * i40evf_map_rings_to_vectors - Maps descriptor rings to vectors
- * @adapter: board private structure to initialize
- *
- * This function maps descriptor rings to the queue-specific vectors
- * we were allotted through the MSI-X enabling code. Ideally, we'd have
- * one vector per ring/queue, but on a constrained vector budget, we
- * group the rings as "efficiently" as possible. You would add new
- * mapping configurations in here.
- **/
-static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
-{
- int rings_remaining = adapter->num_active_queues;
- int ridx = 0, vidx = 0;
- int q_vectors;
-
- q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-
- for (; ridx < rings_remaining; ridx++) {
- i40evf_map_vector_to_rxq(adapter, vidx, ridx);
- i40evf_map_vector_to_txq(adapter, vidx, ridx);
-
- /* In the case where we have more queues than vectors, continue
- * round-robin on vectors until all queues are mapped.
- */
- if (++vidx >= q_vectors)
- vidx = 0;
- }
-
- adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
-}
-
-/**
- * i40evf_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- **/
-static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
-{
- struct i40e_q_vector *q_vector =
- container_of(notify, struct i40e_q_vector, affinity_notify);
-
- cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * i40evf_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- **/
-static void i40evf_irq_affinity_release(struct kref *ref) {}
-
-/**
- * i40evf_request_traffic_irqs - Initialize MSI-X interrupts
- * @adapter: board private structure
- * @basename: device basename
- *
- * Allocates MSI-X vectors for tx and rx handling, and requests
- * interrupts from the kernel.
- **/
-static int
-i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
-{
- unsigned int vector, q_vectors;
- unsigned int rx_int_idx = 0, tx_int_idx = 0;
- int irq_num, err;
- int cpu;
-
- i40evf_irq_disable(adapter);
- /* Decrement for Other and TCP Timer vectors */
- q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-
- for (vector = 0; vector < q_vectors; vector++) {
- struct i40e_q_vector *q_vector = &adapter->q_vectors[vector];
- irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
-
- if (q_vector->tx.ring && q_vector->rx.ring) {
- snprintf(q_vector->name, sizeof(q_vector->name),
- "i40evf-%s-TxRx-%d", basename, rx_int_idx++);
- tx_int_idx++;
- } else if (q_vector->rx.ring) {
- snprintf(q_vector->name, sizeof(q_vector->name),
- "i40evf-%s-rx-%d", basename, rx_int_idx++);
- } else if (q_vector->tx.ring) {
- snprintf(q_vector->name, sizeof(q_vector->name),
- "i40evf-%s-tx-%d", basename, tx_int_idx++);
- } else {
- /* skip this unused q_vector */
- continue;
- }
- err = request_irq(irq_num,
- i40evf_msix_clean_rings,
- 0,
- q_vector->name,
- q_vector);
- if (err) {
- dev_info(&adapter->pdev->dev,
- "Request_irq failed, error: %d\n", err);
- goto free_queue_irqs;
- }
- /* register for affinity change notifications */
- q_vector->affinity_notify.notify = i40evf_irq_affinity_notify;
- q_vector->affinity_notify.release =
- i40evf_irq_affinity_release;
- irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
- /* Spread the IRQ affinity hints across online CPUs. Note that
- * get_cpu_mask returns a mask with a permanent lifetime so
- * it's safe to use as a hint for irq_set_affinity_hint.
- */
- cpu = cpumask_local_spread(q_vector->v_idx, -1);
- irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
- }
-
- return 0;
-
-free_queue_irqs:
- while (vector) {
- vector--;
- irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
- irq_set_affinity_notifier(irq_num, NULL);
- irq_set_affinity_hint(irq_num, NULL);
- free_irq(irq_num, &adapter->q_vectors[vector]);
- }
- return err;
-}
-
-/**
- * i40evf_request_misc_irq - Initialize MSI-X interrupts
- * @adapter: board private structure
- *
- * Allocates MSI-X vector 0 and requests interrupts from the kernel. This
- * vector is only for the admin queue, and stays active even when the netdev
- * is closed.
- **/
-static int i40evf_request_misc_irq(struct i40evf_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- int err;
-
- snprintf(adapter->misc_vector_name,
- sizeof(adapter->misc_vector_name) - 1, "i40evf-%s:mbx",
- dev_name(&adapter->pdev->dev));
- err = request_irq(adapter->msix_entries[0].vector,
- &i40evf_msix_aq, 0,
- adapter->misc_vector_name, netdev);
- if (err) {
- dev_err(&adapter->pdev->dev,
- "request_irq for %s failed: %d\n",
- adapter->misc_vector_name, err);
- free_irq(adapter->msix_entries[0].vector, netdev);
- }
- return err;
-}
-
-/**
- * i40evf_free_traffic_irqs - Free MSI-X interrupts
- * @adapter: board private structure
- *
- * Frees all MSI-X vectors other than 0.
- **/
-static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter)
-{
- int vector, irq_num, q_vectors;
-
- if (!adapter->msix_entries)
- return;
-
- q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-
- for (vector = 0; vector < q_vectors; vector++) {
- irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
- irq_set_affinity_notifier(irq_num, NULL);
- irq_set_affinity_hint(irq_num, NULL);
- free_irq(irq_num, &adapter->q_vectors[vector]);
- }
-}
-
-/**
- * i40evf_free_misc_irq - Free MSI-X miscellaneous vector
- * @adapter: board private structure
- *
- * Frees MSI-X vector 0.
- **/
-static void i40evf_free_misc_irq(struct i40evf_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
-
- if (!adapter->msix_entries)
- return;
-
- free_irq(adapter->msix_entries[0].vector, netdev);
-}
-
-/**
- * i40evf_configure_tx - Configure Transmit Unit after Reset
- * @adapter: board private structure
- *
- * Configure the Tx unit of the MAC after a reset.
- **/
-static void i40evf_configure_tx(struct i40evf_adapter *adapter)
-{
- struct i40e_hw *hw = &adapter->hw;
- int i;
-
- for (i = 0; i < adapter->num_active_queues; i++)
- adapter->tx_rings[i].tail = hw->hw_addr + I40E_QTX_TAIL1(i);
-}
-
-/**
- * i40evf_configure_rx - Configure Receive Unit after Reset
- * @adapter: board private structure
- *
- * Configure the Rx unit of the MAC after a reset.
- **/
-static void i40evf_configure_rx(struct i40evf_adapter *adapter)
-{
- unsigned int rx_buf_len = I40E_RXBUFFER_2048;
- struct i40e_hw *hw = &adapter->hw;
- int i;
-
- /* Legacy Rx will always default to a 2048 buffer size. */
-#if (PAGE_SIZE < 8192)
- if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) {
- struct net_device *netdev = adapter->netdev;
-
- /* For jumbo frames on systems with 4K pages we have to use
- * an order 1 page, so we might as well increase the size
- * of our Rx buffer to make better use of the available space
- */
- rx_buf_len = I40E_RXBUFFER_3072;
-
- /* We use a 1536 buffer size for configurations with
- * standard Ethernet mtu. On x86 this gives us enough room
- * for shared info and 192 bytes of padding.
- */
- if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
- (netdev->mtu <= ETH_DATA_LEN))
- rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
- }
-#endif
-
- for (i = 0; i < adapter->num_active_queues; i++) {
- adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i);
- adapter->rx_rings[i].rx_buf_len = rx_buf_len;
-
- if (adapter->flags & I40EVF_FLAG_LEGACY_RX)
- clear_ring_build_skb_enabled(&adapter->rx_rings[i]);
- else
- set_ring_build_skb_enabled(&adapter->rx_rings[i]);
- }
-}
-
-/**
- * i40evf_find_vlan - Search filter list for specific vlan filter
- * @adapter: board private structure
- * @vlan: vlan tag
- *
- * Returns ptr to the filter object or NULL. Must be called while holding the
- * mac_vlan_list_lock.
- **/
-static struct
-i40evf_vlan_filter *i40evf_find_vlan(struct i40evf_adapter *adapter, u16 vlan)
-{
- struct i40evf_vlan_filter *f;
-
- list_for_each_entry(f, &adapter->vlan_filter_list, list) {
- if (vlan == f->vlan)
- return f;
- }
- return NULL;
-}
-
-/**
- * i40evf_add_vlan - Add a vlan filter to the list
- * @adapter: board private structure
- * @vlan: VLAN tag
- *
- * Returns ptr to the filter object or NULL when no memory available.
- **/
-static struct
-i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan)
-{
- struct i40evf_vlan_filter *f = NULL;
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- f = i40evf_find_vlan(adapter, vlan);
- if (!f) {
- f = kzalloc(sizeof(*f), GFP_KERNEL);
- if (!f)
- goto clearout;
-
- f->vlan = vlan;
-
- INIT_LIST_HEAD(&f->list);
- list_add(&f->list, &adapter->vlan_filter_list);
- f->add = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
- }
-
-clearout:
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
- return f;
-}
-
-/**
- * i40evf_del_vlan - Remove a vlan filter from the list
- * @adapter: board private structure
- * @vlan: VLAN tag
- **/
-static void i40evf_del_vlan(struct i40evf_adapter *adapter, u16 vlan)
-{
- struct i40evf_vlan_filter *f;
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- f = i40evf_find_vlan(adapter, vlan);
- if (f) {
- f->remove = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
- }
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-}
-
-/**
- * i40evf_vlan_rx_add_vid - Add a VLAN filter to a device
- * @netdev: network device struct
- * @proto: unused protocol data
- * @vid: VLAN tag
- **/
-static int i40evf_vlan_rx_add_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- if (!VLAN_ALLOWED(adapter))
- return -EIO;
- if (i40evf_add_vlan(adapter, vid) == NULL)
- return -ENOMEM;
- return 0;
-}
-
-/**
- * i40evf_vlan_rx_kill_vid - Remove a VLAN filter from a device
- * @netdev: network device struct
- * @proto: unused protocol data
- * @vid: VLAN tag
- **/
-static int i40evf_vlan_rx_kill_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- if (VLAN_ALLOWED(adapter)) {
- i40evf_del_vlan(adapter, vid);
- return 0;
- }
- return -EIO;
-}
-
-/**
- * i40evf_find_filter - Search filter list for specific mac filter
- * @adapter: board private structure
- * @macaddr: the MAC address
- *
- * Returns ptr to the filter object or NULL. Must be called while holding the
- * mac_vlan_list_lock.
- **/
-static struct
-i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter,
- const u8 *macaddr)
-{
- struct i40evf_mac_filter *f;
-
- if (!macaddr)
- return NULL;
-
- list_for_each_entry(f, &adapter->mac_filter_list, list) {
- if (ether_addr_equal(macaddr, f->macaddr))
- return f;
- }
- return NULL;
-}
-
-/**
- * i40e_add_filter - Add a mac filter to the filter list
- * @adapter: board private structure
- * @macaddr: the MAC address
- *
- * Returns ptr to the filter object or NULL when no memory available.
- **/
-static struct
-i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
- const u8 *macaddr)
-{
- struct i40evf_mac_filter *f;
-
- if (!macaddr)
- return NULL;
-
- f = i40evf_find_filter(adapter, macaddr);
- if (!f) {
- f = kzalloc(sizeof(*f), GFP_ATOMIC);
- if (!f)
- return f;
-
- ether_addr_copy(f->macaddr, macaddr);
-
- list_add_tail(&f->list, &adapter->mac_filter_list);
- f->add = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
- } else {
- f->remove = false;
- }
-
- return f;
-}
-
-/**
- * i40evf_set_mac - NDO callback to set port mac address
- * @netdev: network interface device structure
- * @p: pointer to an address structure
- *
- * Returns 0 on success, negative on failure
- **/
-static int i40evf_set_mac(struct net_device *netdev, void *p)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40e_hw *hw = &adapter->hw;
- struct i40evf_mac_filter *f;
- struct sockaddr *addr = p;
-
- if (!is_valid_ether_addr(addr->sa_data))
- return -EADDRNOTAVAIL;
-
- if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
- return 0;
-
- if (adapter->flags & I40EVF_FLAG_ADDR_SET_BY_PF)
- return -EPERM;
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- f = i40evf_find_filter(adapter, hw->mac.addr);
- if (f) {
- f->remove = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER;
- }
-
- f = i40evf_add_filter(adapter, addr->sa_data);
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- if (f) {
- ether_addr_copy(hw->mac.addr, addr->sa_data);
- ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
- }
-
- return (f == NULL) ? -ENOMEM : 0;
-}
-
-/**
- * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address
- * @netdev: the netdevice
- * @addr: address to add
- *
- * Called by __dev_(mc|uc)_sync when an address needs to be added. We call
- * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
- */
-static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- if (i40evf_add_filter(adapter, addr))
- return 0;
- else
- return -ENOMEM;
-}
-
-/**
- * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address
- * @netdev: the netdevice
- * @addr: address to add
- *
- * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call
- * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
- */
-static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40evf_mac_filter *f;
-
- /* Under some circumstances, we might receive a request to delete
- * our own device address from our uc list. Because we store the
- * device address in the VSI's MAC/VLAN filter list, we need to ignore
- * such requests and not delete our device address from this list.
- */
- if (ether_addr_equal(addr, netdev->dev_addr))
- return 0;
-
- f = i40evf_find_filter(adapter, addr);
- if (f) {
- f->remove = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER;
- }
- return 0;
-}
-
-/**
- * i40evf_set_rx_mode - NDO callback to set the netdev filters
- * @netdev: network interface device structure
- **/
-static void i40evf_set_rx_mode(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
- __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync);
- __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync);
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- if (netdev->flags & IFF_PROMISC &&
- !(adapter->flags & I40EVF_FLAG_PROMISC_ON))
- adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_PROMISC;
- else if (!(netdev->flags & IFF_PROMISC) &&
- adapter->flags & I40EVF_FLAG_PROMISC_ON)
- adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_PROMISC;
-
- if (netdev->flags & IFF_ALLMULTI &&
- !(adapter->flags & I40EVF_FLAG_ALLMULTI_ON))
- adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_ALLMULTI;
- else if (!(netdev->flags & IFF_ALLMULTI) &&
- adapter->flags & I40EVF_FLAG_ALLMULTI_ON)
- adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI;
-}
-
-/**
- * i40evf_napi_enable_all - enable NAPI on all queue vectors
- * @adapter: board private structure
- **/
-static void i40evf_napi_enable_all(struct i40evf_adapter *adapter)
-{
- int q_idx;
- struct i40e_q_vector *q_vector;
- int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-
- for (q_idx = 0; q_idx < q_vectors; q_idx++) {
- struct napi_struct *napi;
-
- q_vector = &adapter->q_vectors[q_idx];
- napi = &q_vector->napi;
- napi_enable(napi);
- }
-}
-
-/**
- * i40evf_napi_disable_all - disable NAPI on all queue vectors
- * @adapter: board private structure
- **/
-static void i40evf_napi_disable_all(struct i40evf_adapter *adapter)
-{
- int q_idx;
- struct i40e_q_vector *q_vector;
- int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-
- for (q_idx = 0; q_idx < q_vectors; q_idx++) {
- q_vector = &adapter->q_vectors[q_idx];
- napi_disable(&q_vector->napi);
- }
-}
-
-/**
- * i40evf_configure - set up transmit and receive data structures
- * @adapter: board private structure
- **/
-static void i40evf_configure(struct i40evf_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- int i;
-
- i40evf_set_rx_mode(netdev);
-
- i40evf_configure_tx(adapter);
- i40evf_configure_rx(adapter);
- adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_QUEUES;
-
- for (i = 0; i < adapter->num_active_queues; i++) {
- struct i40e_ring *ring = &adapter->rx_rings[i];
-
- i40evf_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
- }
-}
-
-/**
- * i40evf_up_complete - Finish the last steps of bringing up a connection
- * @adapter: board private structure
- *
- * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock.
- **/
-static void i40evf_up_complete(struct i40evf_adapter *adapter)
-{
- adapter->state = __I40EVF_RUNNING;
- clear_bit(__I40E_VSI_DOWN, adapter->vsi.state);
-
- i40evf_napi_enable_all(adapter);
-
- adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES;
- if (CLIENT_ENABLED(adapter))
- adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN;
- mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
-}
-
-/**
- * i40e_down - Shutdown the connection processing
- * @adapter: board private structure
- *
- * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock.
- **/
-void i40evf_down(struct i40evf_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- struct i40evf_vlan_filter *vlf;
- struct i40evf_mac_filter *f;
- struct i40evf_cloud_filter *cf;
-
- if (adapter->state <= __I40EVF_DOWN_PENDING)
- return;
-
- netif_carrier_off(netdev);
- netif_tx_disable(netdev);
- adapter->link_up = false;
- i40evf_napi_disable_all(adapter);
- i40evf_irq_disable(adapter);
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- /* clear the sync flag on all filters */
- __dev_uc_unsync(adapter->netdev, NULL);
- __dev_mc_unsync(adapter->netdev, NULL);
-
- /* remove all MAC filters */
- list_for_each_entry(f, &adapter->mac_filter_list, list) {
- f->remove = true;
- }
-
- /* remove all VLAN filters */
- list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
- vlf->remove = true;
- }
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- /* remove all cloud filters */
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- list_for_each_entry(cf, &adapter->cloud_filter_list, list) {
- cf->del = true;
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-
- if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) &&
- adapter->state != __I40EVF_RESETTING) {
- /* cancel any current operation */
- adapter->current_op = VIRTCHNL_OP_UNKNOWN;
- /* Schedule operations to close down the HW. Don't wait
- * here for this to complete. The watchdog is still running
- * and it will take care of this.
- */
- adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER;
- adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES;
- }
-
- mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
-}
-
-/**
- * i40evf_acquire_msix_vectors - Setup the MSIX capability
- * @adapter: board private structure
- * @vectors: number of vectors to request
- *
- * Work with the OS to set up the MSIX vectors needed.
- *
- * Returns 0 on success, negative on failure
- **/
-static int
-i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors)
-{
- int err, vector_threshold;
-
- /* We'll want at least 3 (vector_threshold):
- * 0) Other (Admin Queue and link, mostly)
- * 1) TxQ[0] Cleanup
- * 2) RxQ[0] Cleanup
- */
- vector_threshold = MIN_MSIX_COUNT;
-
- /* The more we get, the more we will assign to Tx/Rx Cleanup
- * for the separate queues...where Rx Cleanup >= Tx Cleanup.
- * Right now, we simply care about how many we'll get; we'll
- * set them up later while requesting irq's.
- */
- err = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
- vector_threshold, vectors);
- if (err < 0) {
- dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n");
- kfree(adapter->msix_entries);
- adapter->msix_entries = NULL;
- return err;
- }
-
- /* Adjust for only the vectors we'll use, which is minimum
- * of max_msix_q_vectors + NONQ_VECS, or the number of
- * vectors we were allocated.
- */
- adapter->num_msix_vectors = err;
- return 0;
-}
-
-/**
- * i40evf_free_queues - Free memory for all rings
- * @adapter: board private structure to initialize
- *
- * Free all of the memory associated with queue pairs.
- **/
-static void i40evf_free_queues(struct i40evf_adapter *adapter)
-{
- if (!adapter->vsi_res)
- return;
- adapter->num_active_queues = 0;
- kfree(adapter->tx_rings);
- adapter->tx_rings = NULL;
- kfree(adapter->rx_rings);
- adapter->rx_rings = NULL;
-}
-
-/**
- * i40evf_alloc_queues - Allocate memory for all rings
- * @adapter: board private structure to initialize
- *
- * We allocate one ring per queue at run-time since we don't know the
- * number of queues at compile-time. The polling_netdev array is
- * intended for Multiqueue, but should work fine with a single queue.
- **/
-static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
-{
- int i, num_active_queues;
-
- /* If we're in reset reallocating queues we don't actually know yet for
- * certain the PF gave us the number of queues we asked for but we'll
- * assume it did. Once basic reset is finished we'll confirm once we
- * start negotiating config with PF.
- */
- if (adapter->num_req_queues)
- num_active_queues = adapter->num_req_queues;
- else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
- adapter->num_tc)
- num_active_queues = adapter->ch_config.total_qps;
- else
- num_active_queues = min_t(int,
- adapter->vsi_res->num_queue_pairs,
- (int)(num_online_cpus()));
-
-
- adapter->tx_rings = kcalloc(num_active_queues,
- sizeof(struct i40e_ring), GFP_KERNEL);
- if (!adapter->tx_rings)
- goto err_out;
- adapter->rx_rings = kcalloc(num_active_queues,
- sizeof(struct i40e_ring), GFP_KERNEL);
- if (!adapter->rx_rings)
- goto err_out;
-
- for (i = 0; i < num_active_queues; i++) {
- struct i40e_ring *tx_ring;
- struct i40e_ring *rx_ring;
-
- tx_ring = &adapter->tx_rings[i];
-
- tx_ring->queue_index = i;
- tx_ring->netdev = adapter->netdev;
- tx_ring->dev = &adapter->pdev->dev;
- tx_ring->count = adapter->tx_desc_count;
- tx_ring->itr_setting = I40E_ITR_TX_DEF;
- if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
- tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
-
- rx_ring = &adapter->rx_rings[i];
- rx_ring->queue_index = i;
- rx_ring->netdev = adapter->netdev;
- rx_ring->dev = &adapter->pdev->dev;
- rx_ring->count = adapter->rx_desc_count;
- rx_ring->itr_setting = I40E_ITR_RX_DEF;
- }
-
- adapter->num_active_queues = num_active_queues;
-
- return 0;
-
-err_out:
- i40evf_free_queues(adapter);
- return -ENOMEM;
-}
-
-/**
- * i40evf_set_interrupt_capability - set MSI-X or FAIL if not supported
- * @adapter: board private structure to initialize
- *
- * Attempt to configure the interrupts using the best available
- * capabilities of the hardware and the kernel.
- **/
-static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter)
-{
- int vector, v_budget;
- int pairs = 0;
- int err = 0;
-
- if (!adapter->vsi_res) {
- err = -EIO;
- goto out;
- }
- pairs = adapter->num_active_queues;
-
- /* It's easy to be greedy for MSI-X vectors, but it really doesn't do
- * us much good if we have more vectors than CPUs. However, we already
- * limit the total number of queues by the number of CPUs so we do not
- * need any further limiting here.
- */
- v_budget = min_t(int, pairs + NONQ_VECS,
- (int)adapter->vf_res->max_vectors);
-
- adapter->msix_entries = kcalloc(v_budget,
- sizeof(struct msix_entry), GFP_KERNEL);
- if (!adapter->msix_entries) {
- err = -ENOMEM;
- goto out;
- }
-
- for (vector = 0; vector < v_budget; vector++)
- adapter->msix_entries[vector].entry = vector;
-
- err = i40evf_acquire_msix_vectors(adapter, v_budget);
-
-out:
- netif_set_real_num_rx_queues(adapter->netdev, pairs);
- netif_set_real_num_tx_queues(adapter->netdev, pairs);
- return err;
-}
-
-/**
- * i40e_config_rss_aq - Configure RSS keys and lut by using AQ commands
- * @adapter: board private structure
- *
- * Return 0 on success, negative on failure
- **/
-static int i40evf_config_rss_aq(struct i40evf_adapter *adapter)
-{
- struct i40e_aqc_get_set_rss_key_data *rss_key =
- (struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key;
- struct i40e_hw *hw = &adapter->hw;
- int ret = 0;
-
- if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
- /* bail because we already have a command pending */
- dev_err(&adapter->pdev->dev, "Cannot configure RSS, command %d pending\n",
- adapter->current_op);
- return -EBUSY;
- }
-
- ret = i40evf_aq_set_rss_key(hw, adapter->vsi.id, rss_key);
- if (ret) {
- dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n",
- i40evf_stat_str(hw, ret),
- i40evf_aq_str(hw, hw->aq.asq_last_status));
- return ret;
-
- }
-
- ret = i40evf_aq_set_rss_lut(hw, adapter->vsi.id, false,
- adapter->rss_lut, adapter->rss_lut_size);
- if (ret) {
- dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n",
- i40evf_stat_str(hw, ret),
- i40evf_aq_str(hw, hw->aq.asq_last_status));
- }
-
- return ret;
-
-}
-
-/**
- * i40evf_config_rss_reg - Configure RSS keys and lut by writing registers
- * @adapter: board private structure
- *
- * Returns 0 on success, negative on failure
- **/
-static int i40evf_config_rss_reg(struct i40evf_adapter *adapter)
-{
- struct i40e_hw *hw = &adapter->hw;
- u32 *dw;
- u16 i;
-
- dw = (u32 *)adapter->rss_key;
- for (i = 0; i <= adapter->rss_key_size / 4; i++)
- wr32(hw, I40E_VFQF_HKEY(i), dw[i]);
-
- dw = (u32 *)adapter->rss_lut;
- for (i = 0; i <= adapter->rss_lut_size / 4; i++)
- wr32(hw, I40E_VFQF_HLUT(i), dw[i]);
-
- i40e_flush(hw);
-
- return 0;
-}
-
-/**
- * i40evf_config_rss - Configure RSS keys and lut
- * @adapter: board private structure
- *
- * Returns 0 on success, negative on failure
- **/
-int i40evf_config_rss(struct i40evf_adapter *adapter)
-{
-
- if (RSS_PF(adapter)) {
- adapter->aq_required |= I40EVF_FLAG_AQ_SET_RSS_LUT |
- I40EVF_FLAG_AQ_SET_RSS_KEY;
- return 0;
- } else if (RSS_AQ(adapter)) {
- return i40evf_config_rss_aq(adapter);
- } else {
- return i40evf_config_rss_reg(adapter);
- }
-}
-
-/**
- * i40evf_fill_rss_lut - Fill the lut with default values
- * @adapter: board private structure
- **/
-static void i40evf_fill_rss_lut(struct i40evf_adapter *adapter)
-{
- u16 i;
-
- for (i = 0; i < adapter->rss_lut_size; i++)
- adapter->rss_lut[i] = i % adapter->num_active_queues;
-}
-
-/**
- * i40evf_init_rss - Prepare for RSS
- * @adapter: board private structure
- *
- * Return 0 on success, negative on failure
- **/
-static int i40evf_init_rss(struct i40evf_adapter *adapter)
-{
- struct i40e_hw *hw = &adapter->hw;
- int ret;
-
- if (!RSS_PF(adapter)) {
- /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
- if (adapter->vf_res->vf_cap_flags &
- VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
- adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED;
- else
- adapter->hena = I40E_DEFAULT_RSS_HENA;
-
- wr32(hw, I40E_VFQF_HENA(0), (u32)adapter->hena);
- wr32(hw, I40E_VFQF_HENA(1), (u32)(adapter->hena >> 32));
- }
-
- i40evf_fill_rss_lut(adapter);
-
- netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size);
- ret = i40evf_config_rss(adapter);
-
- return ret;
-}
-
-/**
- * i40evf_alloc_q_vectors - Allocate memory for interrupt vectors
- * @adapter: board private structure to initialize
- *
- * We allocate one q_vector per queue interrupt. If allocation fails we
- * return -ENOMEM.
- **/
-static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter)
-{
- int q_idx = 0, num_q_vectors;
- struct i40e_q_vector *q_vector;
-
- num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
- adapter->q_vectors = kcalloc(num_q_vectors, sizeof(*q_vector),
- GFP_KERNEL);
- if (!adapter->q_vectors)
- return -ENOMEM;
-
- for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
- q_vector = &adapter->q_vectors[q_idx];
- q_vector->adapter = adapter;
- q_vector->vsi = &adapter->vsi;
- q_vector->v_idx = q_idx;
- q_vector->reg_idx = q_idx;
- cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
- netif_napi_add(adapter->netdev, &q_vector->napi,
- i40evf_napi_poll, NAPI_POLL_WEIGHT);
- }
-
- return 0;
-}
-
-/**
- * i40evf_free_q_vectors - Free memory allocated for interrupt vectors
- * @adapter: board private structure to initialize
- *
- * This function frees the memory allocated to the q_vectors. In addition if
- * NAPI is enabled it will delete any references to the NAPI struct prior
- * to freeing the q_vector.
- **/
-static void i40evf_free_q_vectors(struct i40evf_adapter *adapter)
-{
- int q_idx, num_q_vectors;
- int napi_vectors;
-
- if (!adapter->q_vectors)
- return;
-
- num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
- napi_vectors = adapter->num_active_queues;
-
- for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
- struct i40e_q_vector *q_vector = &adapter->q_vectors[q_idx];
- if (q_idx < napi_vectors)
- netif_napi_del(&q_vector->napi);
- }
- kfree(adapter->q_vectors);
- adapter->q_vectors = NULL;
-}
-
-/**
- * i40evf_reset_interrupt_capability - Reset MSIX setup
- * @adapter: board private structure
- *
- **/
-void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter)
-{
- if (!adapter->msix_entries)
- return;
-
- pci_disable_msix(adapter->pdev);
- kfree(adapter->msix_entries);
- adapter->msix_entries = NULL;
-}
-
-/**
- * i40evf_init_interrupt_scheme - Determine if MSIX is supported and init
- * @adapter: board private structure to initialize
- *
- **/
-int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter)
-{
- int err;
-
- err = i40evf_alloc_queues(adapter);
- if (err) {
- dev_err(&adapter->pdev->dev,
- "Unable to allocate memory for queues\n");
- goto err_alloc_queues;
- }
-
- rtnl_lock();
- err = i40evf_set_interrupt_capability(adapter);
- rtnl_unlock();
- if (err) {
- dev_err(&adapter->pdev->dev,
- "Unable to setup interrupt capabilities\n");
- goto err_set_interrupt;
- }
-
- err = i40evf_alloc_q_vectors(adapter);
- if (err) {
- dev_err(&adapter->pdev->dev,
- "Unable to allocate memory for queue vectors\n");
- goto err_alloc_q_vectors;
- }
-
- /* If we've made it so far while ADq flag being ON, then we haven't
- * bailed out anywhere in middle. And ADq isn't just enabled but actual
- * resources have been allocated in the reset path.
- * Now we can truly claim that ADq is enabled.
- */
- if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
- adapter->num_tc)
- dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created",
- adapter->num_tc);
-
- dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u",
- (adapter->num_active_queues > 1) ? "Enabled" : "Disabled",
- adapter->num_active_queues);
-
- return 0;
-err_alloc_q_vectors:
- i40evf_reset_interrupt_capability(adapter);
-err_set_interrupt:
- i40evf_free_queues(adapter);
-err_alloc_queues:
- return err;
-}
-
-/**
- * i40evf_free_rss - Free memory used by RSS structs
- * @adapter: board private structure
- **/
-static void i40evf_free_rss(struct i40evf_adapter *adapter)
-{
- kfree(adapter->rss_key);
- adapter->rss_key = NULL;
-
- kfree(adapter->rss_lut);
- adapter->rss_lut = NULL;
-}
-
-/**
- * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors
- * @adapter: board private structure
- *
- * Returns 0 on success, negative on failure
- **/
-static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- int err;
-
- if (netif_running(netdev))
- i40evf_free_traffic_irqs(adapter);
- i40evf_free_misc_irq(adapter);
- i40evf_reset_interrupt_capability(adapter);
- i40evf_free_q_vectors(adapter);
- i40evf_free_queues(adapter);
-
- err = i40evf_init_interrupt_scheme(adapter);
- if (err)
- goto err;
-
- netif_tx_stop_all_queues(netdev);
-
- err = i40evf_request_misc_irq(adapter);
- if (err)
- goto err;
-
- set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
-
- i40evf_map_rings_to_vectors(adapter);
-
- if (RSS_AQ(adapter))
- adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS;
- else
- err = i40evf_init_rss(adapter);
-err:
- return err;
-}
-
-/**
- * i40evf_watchdog_timer - Periodic call-back timer
- * @data: pointer to adapter disguised as unsigned long
- **/
-static void i40evf_watchdog_timer(struct timer_list *t)
-{
- struct i40evf_adapter *adapter = from_timer(adapter, t,
- watchdog_timer);
-
- schedule_work(&adapter->watchdog_task);
- /* timer will be rescheduled in watchdog task */
-}
-
-/**
- * i40evf_watchdog_task - Periodic call-back task
- * @work: pointer to work_struct
- **/
-static void i40evf_watchdog_task(struct work_struct *work)
-{
- struct i40evf_adapter *adapter = container_of(work,
- struct i40evf_adapter,
- watchdog_task);
- struct i40e_hw *hw = &adapter->hw;
- u32 reg_val;
-
- if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section))
- goto restart_watchdog;
-
- if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) {
- reg_val = rd32(hw, I40E_VFGEN_RSTAT) &
- I40E_VFGEN_RSTAT_VFR_STATE_MASK;
- if ((reg_val == VIRTCHNL_VFR_VFACTIVE) ||
- (reg_val == VIRTCHNL_VFR_COMPLETED)) {
- /* A chance for redemption! */
- dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n");
- adapter->state = __I40EVF_STARTUP;
- adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED;
- schedule_delayed_work(&adapter->init_task, 10);
- clear_bit(__I40EVF_IN_CRITICAL_TASK,
- &adapter->crit_section);
- /* Don't reschedule the watchdog, since we've restarted
- * the init task. When init_task contacts the PF and
- * gets everything set up again, it'll restart the
- * watchdog for us. Down, boy. Sit. Stay. Woof.
- */
- return;
- }
- adapter->aq_required = 0;
- adapter->current_op = VIRTCHNL_OP_UNKNOWN;
- goto watchdog_done;
- }
-
- if ((adapter->state < __I40EVF_DOWN) ||
- (adapter->flags & I40EVF_FLAG_RESET_PENDING))
- goto watchdog_done;
-
- /* check for reset */
- reg_val = rd32(hw, I40E_VF_ARQLEN1) & I40E_VF_ARQLEN1_ARQENABLE_MASK;
- if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING) && !reg_val) {
- adapter->state = __I40EVF_RESETTING;
- adapter->flags |= I40EVF_FLAG_RESET_PENDING;
- dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
- schedule_work(&adapter->reset_task);
- adapter->aq_required = 0;
- adapter->current_op = VIRTCHNL_OP_UNKNOWN;
- goto watchdog_done;
- }
-
- /* Process admin queue tasks. After init, everything gets done
- * here so we don't race on the admin queue.
- */
- if (adapter->current_op) {
- if (!i40evf_asq_done(hw)) {
- dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n");
- i40evf_send_api_ver(adapter);
- }
- goto watchdog_done;
- }
- if (adapter->aq_required & I40EVF_FLAG_AQ_GET_CONFIG) {
- i40evf_send_vf_config_msg(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_QUEUES) {
- i40evf_disable_queues(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) {
- i40evf_map_queues(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_MAC_FILTER) {
- i40evf_add_ether_addrs(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_VLAN_FILTER) {
- i40evf_add_vlans(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_MAC_FILTER) {
- i40evf_del_ether_addrs(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_VLAN_FILTER) {
- i40evf_del_vlans(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) {
- i40evf_enable_vlan_stripping(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) {
- i40evf_disable_vlan_stripping(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) {
- i40evf_configure_queues(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_QUEUES) {
- i40evf_enable_queues(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_RSS) {
- /* This message goes straight to the firmware, not the
- * PF, so we don't have to set current_op as we will
- * not get a response through the ARQ.
- */
- i40evf_init_rss(adapter);
- adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_RSS;
- goto watchdog_done;
- }
- if (adapter->aq_required & I40EVF_FLAG_AQ_GET_HENA) {
- i40evf_get_hena(adapter);
- goto watchdog_done;
- }
- if (adapter->aq_required & I40EVF_FLAG_AQ_SET_HENA) {
- i40evf_set_hena(adapter);
- goto watchdog_done;
- }
- if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_KEY) {
- i40evf_set_rss_key(adapter);
- goto watchdog_done;
- }
- if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_LUT) {
- i40evf_set_rss_lut(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_PROMISC) {
- i40evf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC |
- FLAG_VF_MULTICAST_PROMISC);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_ALLMULTI) {
- i40evf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
- goto watchdog_done;
- }
-
- if ((adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_PROMISC) &&
- (adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_ALLMULTI)) {
- i40evf_set_promiscuous(adapter, 0);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) {
- i40evf_enable_channels(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) {
- i40evf_disable_channels(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) {
- i40evf_add_cloud_filter(adapter);
- goto watchdog_done;
- }
-
- if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) {
- i40evf_del_cloud_filter(adapter);
- goto watchdog_done;
- }
-
- schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
-
- if (adapter->state == __I40EVF_RUNNING)
- i40evf_request_stats(adapter);
-watchdog_done:
- if (adapter->state == __I40EVF_RUNNING)
- i40evf_detect_recover_hung(&adapter->vsi);
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-restart_watchdog:
- if (adapter->state == __I40EVF_REMOVE)
- return;
- if (adapter->aq_required)
- mod_timer(&adapter->watchdog_timer,
- jiffies + msecs_to_jiffies(20));
- else
- mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2));
- schedule_work(&adapter->adminq_task);
-}
-
-static void i40evf_disable_vf(struct i40evf_adapter *adapter)
-{
- struct i40evf_mac_filter *f, *ftmp;
- struct i40evf_vlan_filter *fv, *fvtmp;
- struct i40evf_cloud_filter *cf, *cftmp;
-
- adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
-
- /* We don't use netif_running() because it may be true prior to
- * ndo_open() returning, so we can't assume it means all our open
- * tasks have finished, since we're not holding the rtnl_lock here.
- */
- if (adapter->state == __I40EVF_RUNNING) {
- set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
- netif_carrier_off(adapter->netdev);
- netif_tx_disable(adapter->netdev);
- adapter->link_up = false;
- i40evf_napi_disable_all(adapter);
- i40evf_irq_disable(adapter);
- i40evf_free_traffic_irqs(adapter);
- i40evf_free_all_tx_resources(adapter);
- i40evf_free_all_rx_resources(adapter);
- }
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- /* Delete all of the filters */
- list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
- list_del(&f->list);
- kfree(f);
- }
-
- list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list, list) {
- list_del(&fv->list);
- kfree(fv);
- }
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) {
- list_del(&cf->list);
- kfree(cf);
- adapter->num_cloud_filters--;
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-
- i40evf_free_misc_irq(adapter);
- i40evf_reset_interrupt_capability(adapter);
- i40evf_free_queues(adapter);
- i40evf_free_q_vectors(adapter);
- kfree(adapter->vf_res);
- i40evf_shutdown_adminq(&adapter->hw);
- adapter->netdev->flags &= ~IFF_UP;
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
- adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
- adapter->state = __I40EVF_DOWN;
- wake_up(&adapter->down_waitqueue);
- dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
-}
-
-#define I40EVF_RESET_WAIT_MS 10
-#define I40EVF_RESET_WAIT_COUNT 500
-/**
- * i40evf_reset_task - Call-back task to handle hardware reset
- * @work: pointer to work_struct
- *
- * During reset we need to shut down and reinitialize the admin queue
- * before we can use it to communicate with the PF again. We also clear
- * and reinit the rings because that context is lost as well.
- **/
-static void i40evf_reset_task(struct work_struct *work)
-{
- struct i40evf_adapter *adapter = container_of(work,
- struct i40evf_adapter,
- reset_task);
- struct virtchnl_vf_resource *vfres = adapter->vf_res;
- struct net_device *netdev = adapter->netdev;
- struct i40e_hw *hw = &adapter->hw;
- struct i40evf_vlan_filter *vlf;
- struct i40evf_cloud_filter *cf;
- struct i40evf_mac_filter *f;
- u32 reg_val;
- int i = 0, err;
- bool running;
-
- /* When device is being removed it doesn't make sense to run the reset
- * task, just return in such a case.
- */
- if (test_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section))
- return;
-
- while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
- &adapter->crit_section))
- usleep_range(500, 1000);
- if (CLIENT_ENABLED(adapter)) {
- adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN |
- I40EVF_FLAG_CLIENT_NEEDS_CLOSE |
- I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
- I40EVF_FLAG_SERVICE_CLIENT_REQUESTED);
- cancel_delayed_work_sync(&adapter->client_task);
- i40evf_notify_client_close(&adapter->vsi, true);
- }
- i40evf_misc_irq_disable(adapter);
- if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
- adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
- /* Restart the AQ here. If we have been reset but didn't
- * detect it, or if the PF had to reinit, our AQ will be hosed.
- */
- i40evf_shutdown_adminq(hw);
- i40evf_init_adminq(hw);
- i40evf_request_reset(adapter);
- }
- adapter->flags |= I40EVF_FLAG_RESET_PENDING;
-
- /* poll until we see the reset actually happen */
- for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
- reg_val = rd32(hw, I40E_VF_ARQLEN1) &
- I40E_VF_ARQLEN1_ARQENABLE_MASK;
- if (!reg_val)
- break;
- usleep_range(5000, 10000);
- }
- if (i == I40EVF_RESET_WAIT_COUNT) {
- dev_info(&adapter->pdev->dev, "Never saw reset\n");
- goto continue_reset; /* act like the reset happened */
- }
-
- /* wait until the reset is complete and the PF is responding to us */
- for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
- /* sleep first to make sure a minimum wait time is met */
- msleep(I40EVF_RESET_WAIT_MS);
-
- reg_val = rd32(hw, I40E_VFGEN_RSTAT) &
- I40E_VFGEN_RSTAT_VFR_STATE_MASK;
- if (reg_val == VIRTCHNL_VFR_VFACTIVE)
- break;
- }
-
- pci_set_master(adapter->pdev);
-
- if (i == I40EVF_RESET_WAIT_COUNT) {
- dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
- reg_val);
- i40evf_disable_vf(adapter);
- clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
- return; /* Do not attempt to reinit. It's dead, Jim. */
- }
-
-continue_reset:
- /* We don't use netif_running() because it may be true prior to
- * ndo_open() returning, so we can't assume it means all our open
- * tasks have finished, since we're not holding the rtnl_lock here.
- */
- running = ((adapter->state == __I40EVF_RUNNING) ||
- (adapter->state == __I40EVF_RESETTING));
-
- if (running) {
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
- adapter->link_up = false;
- i40evf_napi_disable_all(adapter);
- }
- i40evf_irq_disable(adapter);
-
- adapter->state = __I40EVF_RESETTING;
- adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
-
- /* free the Tx/Rx rings and descriptors, might be better to just
- * re-use them sometime in the future
- */
- i40evf_free_all_rx_resources(adapter);
- i40evf_free_all_tx_resources(adapter);
-
- adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED;
- /* kill and reinit the admin queue */
- i40evf_shutdown_adminq(hw);
- adapter->current_op = VIRTCHNL_OP_UNKNOWN;
- err = i40evf_init_adminq(hw);
- if (err)
- dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
- err);
- adapter->aq_required = 0;
-
- if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
- err = i40evf_reinit_interrupt_scheme(adapter);
- if (err)
- goto reset_err;
- }
-
- adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG;
- adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- /* re-add all MAC filters */
- list_for_each_entry(f, &adapter->mac_filter_list, list) {
- f->add = true;
- }
- /* re-add all VLAN filters */
- list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
- vlf->add = true;
- }
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- /* check if TCs are running and re-add all cloud filters */
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
- adapter->num_tc) {
- list_for_each_entry(cf, &adapter->cloud_filter_list, list) {
- cf->add = true;
- }
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER;
- i40evf_misc_irq_enable(adapter);
-
- mod_timer(&adapter->watchdog_timer, jiffies + 2);
-
- /* We were running when the reset started, so we need to restore some
- * state here.
- */
- if (running) {
- /* allocate transmit descriptors */
- err = i40evf_setup_all_tx_resources(adapter);
- if (err)
- goto reset_err;
-
- /* allocate receive descriptors */
- err = i40evf_setup_all_rx_resources(adapter);
- if (err)
- goto reset_err;
-
- if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
- err = i40evf_request_traffic_irqs(adapter,
- netdev->name);
- if (err)
- goto reset_err;
-
- adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
- }
-
- i40evf_configure(adapter);
-
- i40evf_up_complete(adapter);
-
- i40evf_irq_enable(adapter, true);
- } else {
- adapter->state = __I40EVF_DOWN;
- wake_up(&adapter->down_waitqueue);
- }
- clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-
- return;
-reset_err:
- clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
- dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
- i40evf_close(netdev);
-}
-
-/**
- * i40evf_adminq_task - worker thread to clean the admin queue
- * @work: pointer to work_struct containing our data
- **/
-static void i40evf_adminq_task(struct work_struct *work)
-{
- struct i40evf_adapter *adapter =
- container_of(work, struct i40evf_adapter, adminq_task);
- struct i40e_hw *hw = &adapter->hw;
- struct i40e_arq_event_info event;
- enum virtchnl_ops v_op;
- i40e_status ret, v_ret;
- u32 val, oldval;
- u16 pending;
-
- if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
- goto out;
-
- event.buf_len = I40EVF_MAX_AQ_BUF_SIZE;
- event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
- if (!event.msg_buf)
- goto out;
-
- do {
- ret = i40evf_clean_arq_element(hw, &event, &pending);
- v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
- v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low);
-
- if (ret || !v_op)
- break; /* No event to process or error cleaning ARQ */
-
- i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf,
- event.msg_len);
- if (pending != 0)
- memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE);
- } while (pending);
-
- if ((adapter->flags &
- (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED)) ||
- adapter->state == __I40EVF_RESETTING)
- goto freedom;
-
- /* check for error indications */
- val = rd32(hw, hw->aq.arq.len);
- if (val == 0xdeadbeef) /* indicates device in reset */
- goto freedom;
- oldval = val;
- if (val & I40E_VF_ARQLEN1_ARQVFE_MASK) {
- dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n");
- val &= ~I40E_VF_ARQLEN1_ARQVFE_MASK;
- }
- if (val & I40E_VF_ARQLEN1_ARQOVFL_MASK) {
- dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n");
- val &= ~I40E_VF_ARQLEN1_ARQOVFL_MASK;
- }
- if (val & I40E_VF_ARQLEN1_ARQCRIT_MASK) {
- dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n");
- val &= ~I40E_VF_ARQLEN1_ARQCRIT_MASK;
- }
- if (oldval != val)
- wr32(hw, hw->aq.arq.len, val);
-
- val = rd32(hw, hw->aq.asq.len);
- oldval = val;
- if (val & I40E_VF_ATQLEN1_ATQVFE_MASK) {
- dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n");
- val &= ~I40E_VF_ATQLEN1_ATQVFE_MASK;
- }
- if (val & I40E_VF_ATQLEN1_ATQOVFL_MASK) {
- dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n");
- val &= ~I40E_VF_ATQLEN1_ATQOVFL_MASK;
- }
- if (val & I40E_VF_ATQLEN1_ATQCRIT_MASK) {
- dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n");
- val &= ~I40E_VF_ATQLEN1_ATQCRIT_MASK;
- }
- if (oldval != val)
- wr32(hw, hw->aq.asq.len, val);
-
-freedom:
- kfree(event.msg_buf);
-out:
- /* re-enable Admin queue interrupt cause */
- i40evf_misc_irq_enable(adapter);
-}
-
-/**
- * i40evf_client_task - worker thread to perform client work
- * @work: pointer to work_struct containing our data
- *
- * This task handles client interactions. Because client calls can be
- * reentrant, we can't handle them in the watchdog.
- **/
-static void i40evf_client_task(struct work_struct *work)
-{
- struct i40evf_adapter *adapter =
- container_of(work, struct i40evf_adapter, client_task.work);
-
- /* If we can't get the client bit, just give up. We'll be rescheduled
- * later.
- */
-
- if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section))
- return;
-
- if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) {
- i40evf_client_subtask(adapter);
- adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
- goto out;
- }
- if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
- i40evf_notify_client_l2_params(&adapter->vsi);
- adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
- goto out;
- }
- if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
- i40evf_notify_client_close(&adapter->vsi, false);
- adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
- goto out;
- }
- if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
- i40evf_notify_client_open(&adapter->vsi);
- adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
- }
-out:
- clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
-}
-
-/**
- * i40evf_free_all_tx_resources - Free Tx Resources for All Queues
- * @adapter: board private structure
- *
- * Free all transmit software resources
- **/
-void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter)
-{
- int i;
-
- if (!adapter->tx_rings)
- return;
-
- for (i = 0; i < adapter->num_active_queues; i++)
- if (adapter->tx_rings[i].desc)
- i40evf_free_tx_resources(&adapter->tx_rings[i]);
-}
-
-/**
- * i40evf_setup_all_tx_resources - allocate all queues Tx resources
- * @adapter: board private structure
- *
- * If this function returns with an error, then it's possible one or
- * more of the rings is populated (while the rest are not). It is the
- * callers duty to clean those orphaned rings.
- *
- * Return 0 on success, negative on failure
- **/
-static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter)
-{
- int i, err = 0;
-
- for (i = 0; i < adapter->num_active_queues; i++) {
- adapter->tx_rings[i].count = adapter->tx_desc_count;
- err = i40evf_setup_tx_descriptors(&adapter->tx_rings[i]);
- if (!err)
- continue;
- dev_err(&adapter->pdev->dev,
- "Allocation for Tx Queue %u failed\n", i);
- break;
- }
-
- return err;
-}
-
-/**
- * i40evf_setup_all_rx_resources - allocate all queues Rx resources
- * @adapter: board private structure
- *
- * If this function returns with an error, then it's possible one or
- * more of the rings is populated (while the rest are not). It is the
- * callers duty to clean those orphaned rings.
- *
- * Return 0 on success, negative on failure
- **/
-static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter)
-{
- int i, err = 0;
-
- for (i = 0; i < adapter->num_active_queues; i++) {
- adapter->rx_rings[i].count = adapter->rx_desc_count;
- err = i40evf_setup_rx_descriptors(&adapter->rx_rings[i]);
- if (!err)
- continue;
- dev_err(&adapter->pdev->dev,
- "Allocation for Rx Queue %u failed\n", i);
- break;
- }
- return err;
-}
-
-/**
- * i40evf_free_all_rx_resources - Free Rx Resources for All Queues
- * @adapter: board private structure
- *
- * Free all receive software resources
- **/
-void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter)
-{
- int i;
-
- if (!adapter->rx_rings)
- return;
-
- for (i = 0; i < adapter->num_active_queues; i++)
- if (adapter->rx_rings[i].desc)
- i40evf_free_rx_resources(&adapter->rx_rings[i]);
-}
-
-/**
- * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth
- * @adapter: board private structure
- * @max_tx_rate: max Tx bw for a tc
- **/
-static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter,
- u64 max_tx_rate)
-{
- int speed = 0, ret = 0;
-
- switch (adapter->link_speed) {
- case I40E_LINK_SPEED_40GB:
- speed = 40000;
- break;
- case I40E_LINK_SPEED_25GB:
- speed = 25000;
- break;
- case I40E_LINK_SPEED_20GB:
- speed = 20000;
- break;
- case I40E_LINK_SPEED_10GB:
- speed = 10000;
- break;
- case I40E_LINK_SPEED_1GB:
- speed = 1000;
- break;
- case I40E_LINK_SPEED_100MB:
- speed = 100;
- break;
- default:
- break;
- }
-
- if (max_tx_rate > speed) {
- dev_err(&adapter->pdev->dev,
- "Invalid tx rate specified\n");
- ret = -EINVAL;
- }
-
- return ret;
-}
-
-/**
- * i40evf_validate_channel_config - validate queue mapping info
- * @adapter: board private structure
- * @mqprio_qopt: queue parameters
- *
- * This function validates if the config provided by the user to
- * configure queue channels is valid or not. Returns 0 on a valid
- * config.
- **/
-static int i40evf_validate_ch_config(struct i40evf_adapter *adapter,
- struct tc_mqprio_qopt_offload *mqprio_qopt)
-{
- u64 total_max_rate = 0;
- int i, num_qps = 0;
- u64 tx_rate = 0;
- int ret = 0;
-
- if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS ||
- mqprio_qopt->qopt.num_tc < 1)
- return -EINVAL;
-
- for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) {
- if (!mqprio_qopt->qopt.count[i] ||
- mqprio_qopt->qopt.offset[i] != num_qps)
- return -EINVAL;
- if (mqprio_qopt->min_rate[i]) {
- dev_err(&adapter->pdev->dev,
- "Invalid min tx rate (greater than 0) specified\n");
- return -EINVAL;
- }
- /*convert to Mbps */
- tx_rate = div_u64(mqprio_qopt->max_rate[i],
- I40EVF_MBPS_DIVISOR);
- total_max_rate += tx_rate;
- num_qps += mqprio_qopt->qopt.count[i];
- }
- if (num_qps > I40EVF_MAX_REQ_QUEUES)
- return -EINVAL;
-
- ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate);
- return ret;
-}
-
-/**
- * i40evf_del_all_cloud_filters - delete all cloud filters
- * on the traffic classes
- **/
-static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter)
-{
- struct i40evf_cloud_filter *cf, *cftmp;
-
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list,
- list) {
- list_del(&cf->list);
- kfree(cf);
- adapter->num_cloud_filters--;
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-}
-
-/**
- * __i40evf_setup_tc - configure multiple traffic classes
- * @netdev: network interface device structure
- * @type_date: tc offload data
- *
- * This function processes the config information provided by the
- * user to configure traffic classes/queue channels and packages the
- * information to request the PF to setup traffic classes.
- *
- * Returns 0 on success.
- **/
-static int __i40evf_setup_tc(struct net_device *netdev, void *type_data)
-{
- struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct virtchnl_vf_resource *vfres = adapter->vf_res;
- u8 num_tc = 0, total_qps = 0;
- int ret = 0, netdev_tc = 0;
- u64 max_tx_rate;
- u16 mode;
- int i;
-
- num_tc = mqprio_qopt->qopt.num_tc;
- mode = mqprio_qopt->mode;
-
- /* delete queue_channel */
- if (!mqprio_qopt->qopt.hw) {
- if (adapter->ch_config.state == __I40EVF_TC_RUNNING) {
- /* reset the tc configuration */
- netdev_reset_tc(netdev);
- adapter->num_tc = 0;
- netif_tx_stop_all_queues(netdev);
- netif_tx_disable(netdev);
- i40evf_del_all_cloud_filters(adapter);
- adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS;
- goto exit;
- } else {
- return -EINVAL;
- }
- }
-
- /* add queue channel */
- if (mode == TC_MQPRIO_MODE_CHANNEL) {
- if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) {
- dev_err(&adapter->pdev->dev, "ADq not supported\n");
- return -EOPNOTSUPP;
- }
- if (adapter->ch_config.state != __I40EVF_TC_INVALID) {
- dev_err(&adapter->pdev->dev, "TC configuration already exists\n");
- return -EINVAL;
- }
-
- ret = i40evf_validate_ch_config(adapter, mqprio_qopt);
- if (ret)
- return ret;
- /* Return if same TC config is requested */
- if (adapter->num_tc == num_tc)
- return 0;
- adapter->num_tc = num_tc;
-
- for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) {
- if (i < num_tc) {
- adapter->ch_config.ch_info[i].count =
- mqprio_qopt->qopt.count[i];
- adapter->ch_config.ch_info[i].offset =
- mqprio_qopt->qopt.offset[i];
- total_qps += mqprio_qopt->qopt.count[i];
- max_tx_rate = mqprio_qopt->max_rate[i];
- /* convert to Mbps */
- max_tx_rate = div_u64(max_tx_rate,
- I40EVF_MBPS_DIVISOR);
- adapter->ch_config.ch_info[i].max_tx_rate =
- max_tx_rate;
- } else {
- adapter->ch_config.ch_info[i].count = 1;
- adapter->ch_config.ch_info[i].offset = 0;
- }
- }
- adapter->ch_config.total_qps = total_qps;
- netif_tx_stop_all_queues(netdev);
- netif_tx_disable(netdev);
- adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS;
- netdev_reset_tc(netdev);
- /* Report the tc mapping up the stack */
- netdev_set_num_tc(adapter->netdev, num_tc);
- for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) {
- u16 qcount = mqprio_qopt->qopt.count[i];
- u16 qoffset = mqprio_qopt->qopt.offset[i];
-
- if (i < num_tc)
- netdev_set_tc_queue(netdev, netdev_tc++, qcount,
- qoffset);
- }
- }
-exit:
- return ret;
-}
-
-/**
- * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel
- * @adapter: board private structure
- * @cls_flower: pointer to struct tc_cls_flower_offload
- * @filter: pointer to cloud filter structure
- */
-static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter,
- struct tc_cls_flower_offload *f,
- struct i40evf_cloud_filter *filter)
-{
- u16 n_proto_mask = 0;
- u16 n_proto_key = 0;
- u8 field_flags = 0;
- u16 addr_type = 0;
- u16 n_proto = 0;
- int i = 0;
- struct virtchnl_filter *vf = &filter->f;
-
- if (f->dissector->used_keys &
- ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
- BIT(FLOW_DISSECTOR_KEY_BASIC) |
- BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
- BIT(FLOW_DISSECTOR_KEY_VLAN) |
- BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
- BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
- BIT(FLOW_DISSECTOR_KEY_PORTS) |
- BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
- dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n",
- f->dissector->used_keys);
- return -EOPNOTSUPP;
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
- struct flow_dissector_key_keyid *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ENC_KEYID,
- f->mask);
-
- if (mask->keyid != 0)
- field_flags |= I40EVF_CLOUD_FIELD_TEN_ID;
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
-
- struct flow_dissector_key_basic *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
- n_proto_key = ntohs(key->n_proto);
- n_proto_mask = ntohs(mask->n_proto);
-
- if (n_proto_key == ETH_P_ALL) {
- n_proto_key = 0;
- n_proto_mask = 0;
- }
- n_proto = n_proto_key & n_proto_mask;
- if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6)
- return -EINVAL;
- if (n_proto == ETH_P_IPV6) {
- /* specify flow type as TCP IPv6 */
- vf->flow_type = VIRTCHNL_TCP_V6_FLOW;
- }
-
- if (key->ip_proto != IPPROTO_TCP) {
- dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n");
- return -EINVAL;
- }
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
- struct flow_dissector_key_eth_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->key);
-
- struct flow_dissector_key_eth_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->mask);
- /* use is_broadcast and is_zero to check for all 0xf or 0 */
- if (!is_zero_ether_addr(mask->dst)) {
- if (is_broadcast_ether_addr(mask->dst)) {
- field_flags |= I40EVF_CLOUD_FIELD_OMAC;
- } else {
- dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n",
- mask->dst);
- return I40E_ERR_CONFIG;
- }
- }
-
- if (!is_zero_ether_addr(mask->src)) {
- if (is_broadcast_ether_addr(mask->src)) {
- field_flags |= I40EVF_CLOUD_FIELD_IMAC;
- } else {
- dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n",
- mask->src);
- return I40E_ERR_CONFIG;
- }
- }
-
- if (!is_zero_ether_addr(key->dst))
- if (is_valid_ether_addr(key->dst) ||
- is_multicast_ether_addr(key->dst)) {
- /* set the mask if a valid dst_mac address */
- for (i = 0; i < ETH_ALEN; i++)
- vf->mask.tcp_spec.dst_mac[i] |= 0xff;
- ether_addr_copy(vf->data.tcp_spec.dst_mac,
- key->dst);
- }
-
- if (!is_zero_ether_addr(key->src))
- if (is_valid_ether_addr(key->src) ||
- is_multicast_ether_addr(key->src)) {
- /* set the mask if a valid dst_mac address */
- for (i = 0; i < ETH_ALEN; i++)
- vf->mask.tcp_spec.src_mac[i] |= 0xff;
- ether_addr_copy(vf->data.tcp_spec.src_mac,
- key->src);
- }
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
- struct flow_dissector_key_vlan *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->key);
- struct flow_dissector_key_vlan *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->mask);
-
- if (mask->vlan_id) {
- if (mask->vlan_id == VLAN_VID_MASK) {
- field_flags |= I40EVF_CLOUD_FIELD_IVLAN;
- } else {
- dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n",
- mask->vlan_id);
- return I40E_ERR_CONFIG;
- }
- }
- vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff);
- vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id);
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
- struct flow_dissector_key_control *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->key);
-
- addr_type = key->addr_type;
- }
-
- if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
- struct flow_dissector_key_ipv4_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->key);
- struct flow_dissector_key_ipv4_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->mask);
-
- if (mask->dst) {
- if (mask->dst == cpu_to_be32(0xffffffff)) {
- field_flags |= I40EVF_CLOUD_FIELD_IIP;
- } else {
- dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n",
- be32_to_cpu(mask->dst));
- return I40E_ERR_CONFIG;
- }
- }
-
- if (mask->src) {
- if (mask->src == cpu_to_be32(0xffffffff)) {
- field_flags |= I40EVF_CLOUD_FIELD_IIP;
- } else {
- dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
- be32_to_cpu(mask->dst));
- return I40E_ERR_CONFIG;
- }
- }
-
- if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) {
- dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n");
- return I40E_ERR_CONFIG;
- }
- if (key->dst) {
- vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff);
- vf->data.tcp_spec.dst_ip[0] = key->dst;
- }
- if (key->src) {
- vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff);
- vf->data.tcp_spec.src_ip[0] = key->src;
- }
- }
-
- if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
- struct flow_dissector_key_ipv6_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->key);
- struct flow_dissector_key_ipv6_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->mask);
-
- /* validate mask, make sure it is not IPV6_ADDR_ANY */
- if (ipv6_addr_any(&mask->dst)) {
- dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n",
- IPV6_ADDR_ANY);
- return I40E_ERR_CONFIG;
- }
-
- /* src and dest IPv6 address should not be LOOPBACK
- * (0:0:0:0:0:0:0:1) which can be represented as ::1
- */
- if (ipv6_addr_loopback(&key->dst) ||
- ipv6_addr_loopback(&key->src)) {
- dev_err(&adapter->pdev->dev,
- "ipv6 addr should not be loopback\n");
- return I40E_ERR_CONFIG;
- }
- if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
- field_flags |= I40EVF_CLOUD_FIELD_IIP;
-
- for (i = 0; i < 4; i++)
- vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff);
- memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32,
- sizeof(vf->data.tcp_spec.dst_ip));
- for (i = 0; i < 4; i++)
- vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff);
- memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32,
- sizeof(vf->data.tcp_spec.src_ip));
- }
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
- struct flow_dissector_key_ports *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->key);
- struct flow_dissector_key_ports *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->mask);
-
- if (mask->src) {
- if (mask->src == cpu_to_be16(0xffff)) {
- field_flags |= I40EVF_CLOUD_FIELD_IIP;
- } else {
- dev_err(&adapter->pdev->dev, "Bad src port mask %u\n",
- be16_to_cpu(mask->src));
- return I40E_ERR_CONFIG;
- }
- }
-
- if (mask->dst) {
- if (mask->dst == cpu_to_be16(0xffff)) {
- field_flags |= I40EVF_CLOUD_FIELD_IIP;
- } else {
- dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n",
- be16_to_cpu(mask->dst));
- return I40E_ERR_CONFIG;
- }
- }
- if (key->dst) {
- vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff);
- vf->data.tcp_spec.dst_port = key->dst;
- }
-
- if (key->src) {
- vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff);
- vf->data.tcp_spec.src_port = key->src;
- }
- }
- vf->field_flags = field_flags;
-
- return 0;
-}
-
-/**
- * i40evf_handle_tclass - Forward to a traffic class on the device
- * @adapter: board private structure
- * @tc: traffic class index on the device
- * @filter: pointer to cloud filter structure
- */
-static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc,
- struct i40evf_cloud_filter *filter)
-{
- if (tc == 0)
- return 0;
- if (tc < adapter->num_tc) {
- if (!filter->f.data.tcp_spec.dst_port) {
- dev_err(&adapter->pdev->dev,
- "Specify destination port to redirect to traffic class other than TC0\n");
- return -EINVAL;
- }
- }
- /* redirect to a traffic class on the same device */
- filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT;
- filter->f.action_meta = tc;
- return 0;
-}
-
-/**
- * i40evf_configure_clsflower - Add tc flower filters
- * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
- */
-static int i40evf_configure_clsflower(struct i40evf_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
-{
- int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
- struct i40evf_cloud_filter *filter = NULL;
- int err = -EINVAL, count = 50;
-
- if (tc < 0) {
- dev_err(&adapter->pdev->dev, "Invalid traffic class\n");
- return -EINVAL;
- }
-
- filter = kzalloc(sizeof(*filter), GFP_KERNEL);
- if (!filter)
- return -ENOMEM;
-
- while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
- &adapter->crit_section)) {
- if (--count == 0)
- goto err;
- udelay(1);
- }
-
- filter->cookie = cls_flower->cookie;
-
- /* set the mask to all zeroes to begin with */
- memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec));
- /* start out with flow type and eth type IPv4 to begin with */
- filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW;
- err = i40evf_parse_cls_flower(adapter, cls_flower, filter);
- if (err < 0)
- goto err;
-
- err = i40evf_handle_tclass(adapter, tc, filter);
- if (err < 0)
- goto err;
-
- /* add filter to the list */
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- list_add_tail(&filter->list, &adapter->cloud_filter_list);
- adapter->num_cloud_filters++;
- filter->add = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER;
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-err:
- if (err)
- kfree(filter);
-
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
- return err;
-}
-
-/* i40evf_find_cf - Find the cloud filter in the list
- * @adapter: Board private structure
- * @cookie: filter specific cookie
- *
- * Returns ptr to the filter object or NULL. Must be called while holding the
- * cloud_filter_list_lock.
- */
-static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter,
- unsigned long *cookie)
-{
- struct i40evf_cloud_filter *filter = NULL;
-
- if (!cookie)
- return NULL;
-
- list_for_each_entry(filter, &adapter->cloud_filter_list, list) {
- if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie)))
- return filter;
- }
- return NULL;
-}
-
-/**
- * i40evf_delete_clsflower - Remove tc flower filters
- * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
- */
-static int i40evf_delete_clsflower(struct i40evf_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
-{
- struct i40evf_cloud_filter *filter = NULL;
- int err = 0;
-
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- filter = i40evf_find_cf(adapter, &cls_flower->cookie);
- if (filter) {
- filter->del = true;
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER;
- } else {
- err = -EINVAL;
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-
- return err;
-}
-
-/**
- * i40evf_setup_tc_cls_flower - flower classifier offloads
- * @netdev: net device to configure
- * @type_data: offload data
- */
-static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
-{
- if (cls_flower->common.chain_index)
- return -EOPNOTSUPP;
-
- switch (cls_flower->command) {
- case TC_CLSFLOWER_REPLACE:
- return i40evf_configure_clsflower(adapter, cls_flower);
- case TC_CLSFLOWER_DESTROY:
- return i40evf_delete_clsflower(adapter, cls_flower);
- case TC_CLSFLOWER_STATS:
- return -EOPNOTSUPP;
- default:
- return -EOPNOTSUPP;
- }
-}
-
-/**
- * i40evf_setup_tc_block_cb - block callback for tc
- * @type: type of offload
- * @type_data: offload data
- * @cb_priv:
- *
- * This function is the block callback for traffic classes
- **/
-static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
- void *cb_priv)
-{
- switch (type) {
- case TC_SETUP_CLSFLOWER:
- return i40evf_setup_tc_cls_flower(cb_priv, type_data);
- default:
- return -EOPNOTSUPP;
- }
-}
-
-/**
- * i40evf_setup_tc_block - register callbacks for tc
- * @netdev: network interface device structure
- * @f: tc offload data
- *
- * This function registers block callbacks for tc
- * offloads
- **/
-static int i40evf_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct i40evf_adapter *adapter = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
-/**
- * i40evf_setup_tc - configure multiple traffic classes
- * @netdev: network interface device structure
- * @type: type of offload
- * @type_date: tc offload data
- *
- * This function is the callback to ndo_setup_tc in the
- * netdev_ops.
- *
- * Returns 0 on success
- **/
-static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
- void *type_data)
-{
- switch (type) {
- case TC_SETUP_QDISC_MQPRIO:
- return __i40evf_setup_tc(netdev, type_data);
- case TC_SETUP_BLOCK:
- return i40evf_setup_tc_block(netdev, type_data);
- default:
- return -EOPNOTSUPP;
- }
-}
-
-/**
- * i40evf_open - Called when a network interface is made active
- * @netdev: network interface device structure
- *
- * Returns 0 on success, negative value on failure
- *
- * The open entry point is called when a network interface is made
- * active by the system (IFF_UP). At this point all resources needed
- * for transmit and receive operations are allocated, the interrupt
- * handler is registered with the OS, the watchdog timer is started,
- * and the stack is notified that the interface is ready.
- **/
-static int i40evf_open(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- int err;
-
- if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) {
- dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
- return -EIO;
- }
-
- while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
- &adapter->crit_section))
- usleep_range(500, 1000);
-
- if (adapter->state != __I40EVF_DOWN) {
- err = -EBUSY;
- goto err_unlock;
- }
-
- /* allocate transmit descriptors */
- err = i40evf_setup_all_tx_resources(adapter);
- if (err)
- goto err_setup_tx;
-
- /* allocate receive descriptors */
- err = i40evf_setup_all_rx_resources(adapter);
- if (err)
- goto err_setup_rx;
-
- /* clear any pending interrupts, may auto mask */
- err = i40evf_request_traffic_irqs(adapter, netdev->name);
- if (err)
- goto err_req_irq;
-
- spin_lock_bh(&adapter->mac_vlan_list_lock);
-
- i40evf_add_filter(adapter, adapter->hw.mac.addr);
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- i40evf_configure(adapter);
-
- i40evf_up_complete(adapter);
-
- i40evf_irq_enable(adapter, true);
-
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-
- return 0;
-
-err_req_irq:
- i40evf_down(adapter);
- i40evf_free_traffic_irqs(adapter);
-err_setup_rx:
- i40evf_free_all_rx_resources(adapter);
-err_setup_tx:
- i40evf_free_all_tx_resources(adapter);
-err_unlock:
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-
- return err;
-}
-
-/**
- * i40evf_close - Disables a network interface
- * @netdev: network interface device structure
- *
- * Returns 0, this is not allowed to fail
- *
- * The close entry point is called when an interface is de-activated
- * by the OS. The hardware is still under the drivers control, but
- * needs to be disabled. All IRQs except vector 0 (reserved for admin queue)
- * are freed, along with all transmit and receive resources.
- **/
-static int i40evf_close(struct net_device *netdev)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- int status;
-
- if (adapter->state <= __I40EVF_DOWN_PENDING)
- return 0;
-
- while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
- &adapter->crit_section))
- usleep_range(500, 1000);
-
- set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
- if (CLIENT_ENABLED(adapter))
- adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
-
- i40evf_down(adapter);
- adapter->state = __I40EVF_DOWN_PENDING;
- i40evf_free_traffic_irqs(adapter);
-
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-
- /* We explicitly don't free resources here because the hardware is
- * still active and can DMA into memory. Resources are cleared in
- * i40evf_virtchnl_completion() after we get confirmation from the PF
- * driver that the rings have been stopped.
- *
- * Also, we wait for state to transition to __I40EVF_DOWN before
- * returning. State change occurs in i40evf_virtchnl_completion() after
- * VF resources are released (which occurs after PF driver processes and
- * responds to admin queue commands).
- */
-
- status = wait_event_timeout(adapter->down_waitqueue,
- adapter->state == __I40EVF_DOWN,
- msecs_to_jiffies(200));
- if (!status)
- netdev_warn(netdev, "Device resources not yet released\n");
- return 0;
-}
-
-/**
- * i40evf_change_mtu - Change the Maximum Transfer Unit
- * @netdev: network interface device structure
- * @new_mtu: new value for maximum frame size
- *
- * Returns 0 on success, negative on failure
- **/
-static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- netdev->mtu = new_mtu;
- if (CLIENT_ENABLED(adapter)) {
- i40evf_notify_client_l2_params(&adapter->vsi);
- adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
- }
- adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
- schedule_work(&adapter->reset_task);
-
- return 0;
-}
-
-/**
- * i40e_set_features - set the netdev feature flags
- * @netdev: ptr to the netdev being adjusted
- * @features: the feature set that the stack is suggesting
- * Note: expects to be called while under rtnl_lock()
- **/
-static int i40evf_set_features(struct net_device *netdev,
- netdev_features_t features)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- /* Don't allow changing VLAN_RX flag when VLAN is set for VF
- * and return an error in this case
- */
- if (VLAN_ALLOWED(adapter)) {
- if (features & NETIF_F_HW_VLAN_CTAG_RX)
- adapter->aq_required |=
- I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
- else
- adapter->aq_required |=
- I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
- } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) {
- return -EINVAL;
- }
-
- return 0;
-}
-
-/**
- * i40evf_features_check - Validate encapsulated packet conforms to limits
- * @skb: skb buff
- * @dev: This physical port's netdev
- * @features: Offload features that the stack believes apply
- **/
-static netdev_features_t i40evf_features_check(struct sk_buff *skb,
- struct net_device *dev,
- netdev_features_t features)
-{
- size_t len;
-
- /* No point in doing any of this if neither checksum nor GSO are
- * being requested for this frame. We can rule out both by just
- * checking for CHECKSUM_PARTIAL
- */
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- return features;
-
- /* We cannot support GSO if the MSS is going to be less than
- * 64 bytes. If it is then we need to drop support for GSO.
- */
- if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
- features &= ~NETIF_F_GSO_MASK;
-
- /* MACLEN can support at most 63 words */
- len = skb_network_header(skb) - skb->data;
- if (len & ~(63 * 2))
- goto out_err;
-
- /* IPLEN and EIPLEN can support at most 127 dwords */
- len = skb_transport_header(skb) - skb_network_header(skb);
- if (len & ~(127 * 4))
- goto out_err;
-
- if (skb->encapsulation) {
- /* L4TUNLEN can support 127 words */
- len = skb_inner_network_header(skb) - skb_transport_header(skb);
- if (len & ~(127 * 2))
- goto out_err;
-
- /* IPLEN can support at most 127 dwords */
- len = skb_inner_transport_header(skb) -
- skb_inner_network_header(skb);
- if (len & ~(127 * 4))
- goto out_err;
- }
-
- /* No need to validate L4LEN as TCP is the only protocol with a
- * a flexible value and we support all possible values supported
- * by TCP, which is at most 15 dwords
- */
-
- return features;
-out_err:
- return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
-}
-
-/**
- * i40evf_fix_features - fix up the netdev feature bits
- * @netdev: our net device
- * @features: desired feature bits
- *
- * Returns fixed-up features bits
- **/
-static netdev_features_t i40evf_fix_features(struct net_device *netdev,
- netdev_features_t features)
-{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
- features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_CTAG_RX |
- NETIF_F_HW_VLAN_CTAG_FILTER);
-
- return features;
-}
-
-static const struct net_device_ops i40evf_netdev_ops = {
- .ndo_open = i40evf_open,
- .ndo_stop = i40evf_close,
- .ndo_start_xmit = i40evf_xmit_frame,
- .ndo_set_rx_mode = i40evf_set_rx_mode,
- .ndo_validate_addr = eth_validate_addr,
- .ndo_set_mac_address = i40evf_set_mac,
- .ndo_change_mtu = i40evf_change_mtu,
- .ndo_tx_timeout = i40evf_tx_timeout,
- .ndo_vlan_rx_add_vid = i40evf_vlan_rx_add_vid,
- .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid,
- .ndo_features_check = i40evf_features_check,
- .ndo_fix_features = i40evf_fix_features,
- .ndo_set_features = i40evf_set_features,
- .ndo_setup_tc = i40evf_setup_tc,
-};
-
-/**
- * i40evf_check_reset_complete - check that VF reset is complete
- * @hw: pointer to hw struct
- *
- * Returns 0 if device is ready to use, or -EBUSY if it's in reset.
- **/
-static int i40evf_check_reset_complete(struct i40e_hw *hw)
-{
- u32 rstat;
- int i;
-
- for (i = 0; i < 100; i++) {
- rstat = rd32(hw, I40E_VFGEN_RSTAT) &
- I40E_VFGEN_RSTAT_VFR_STATE_MASK;
- if ((rstat == VIRTCHNL_VFR_VFACTIVE) ||
- (rstat == VIRTCHNL_VFR_COMPLETED))
- return 0;
- usleep_range(10, 20);
- }
- return -EBUSY;
-}
-
-/**
- * i40evf_process_config - Process the config information we got from the PF
- * @adapter: board private structure
- *
- * Verify that we have a valid config struct, and set up our netdev features
- * and our VSI struct.
- **/
-int i40evf_process_config(struct i40evf_adapter *adapter)
-{
- struct virtchnl_vf_resource *vfres = adapter->vf_res;
- int i, num_req_queues = adapter->num_req_queues;
- struct net_device *netdev = adapter->netdev;
- struct i40e_vsi *vsi = &adapter->vsi;
- netdev_features_t hw_enc_features;
- netdev_features_t hw_features;
-
- /* got VF config message back from PF, now we can parse it */
- for (i = 0; i < vfres->num_vsis; i++) {
- if (vfres->vsi_res[i].vsi_type == VIRTCHNL_VSI_SRIOV)
- adapter->vsi_res = &vfres->vsi_res[i];
- }
- if (!adapter->vsi_res) {
- dev_err(&adapter->pdev->dev, "No LAN VSI found\n");
- return -ENODEV;
- }
-
- if (num_req_queues &&
- num_req_queues != adapter->vsi_res->num_queue_pairs) {
- /* Problem. The PF gave us fewer queues than what we had
- * negotiated in our request. Need a reset to see if we can't
- * get back to a working state.
- */
- dev_err(&adapter->pdev->dev,
- "Requested %d queues, but PF only gave us %d.\n",
- num_req_queues,
- adapter->vsi_res->num_queue_pairs);
- adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
- adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
- i40evf_schedule_reset(adapter);
- return -ENODEV;
- }
- adapter->num_req_queues = 0;
-
- hw_enc_features = NETIF_F_SG |
- NETIF_F_IP_CSUM |
- NETIF_F_IPV6_CSUM |
- NETIF_F_HIGHDMA |
- NETIF_F_SOFT_FEATURES |
- NETIF_F_TSO |
- NETIF_F_TSO_ECN |
- NETIF_F_TSO6 |
- NETIF_F_SCTP_CRC |
- NETIF_F_RXHASH |
- NETIF_F_RXCSUM |
- 0;
-
- /* advertise to stack only if offloads for encapsulated packets is
- * supported
- */
- if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
- hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_IPXIP4 |
- NETIF_F_GSO_IPXIP6 |
- NETIF_F_GSO_UDP_TUNNEL_CSUM |
- NETIF_F_GSO_PARTIAL |
- 0;
-
- if (!(vfres->vf_cap_flags &
- VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
- netdev->gso_partial_features |=
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
- netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
- netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
- netdev->hw_enc_features |= hw_enc_features;
- }
- /* record features VLANs can make use of */
- netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
-
- /* Write features and hw_features separately to avoid polluting
- * with, or dropping, features that are set when we registered.
- */
- hw_features = hw_enc_features;
-
- /* Enable VLAN features if supported */
- if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
- hw_features |= (NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_CTAG_RX);
- /* Enable cloud filter if ADQ is supported */
- if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)
- hw_features |= NETIF_F_HW_TC;
-
- netdev->hw_features |= hw_features;
-
- netdev->features |= hw_features;
-
- if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
- netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-
- /* Do not turn on offloads when they are requested to be turned off.
- * TSO needs minimum 576 bytes to work correctly.
- */
- if (netdev->wanted_features) {
- if (!(netdev->wanted_features & NETIF_F_TSO) ||
- netdev->mtu < 576)
- netdev->features &= ~NETIF_F_TSO;
- if (!(netdev->wanted_features & NETIF_F_TSO6) ||
- netdev->mtu < 576)
- netdev->features &= ~NETIF_F_TSO6;
- if (!(netdev->wanted_features & NETIF_F_TSO_ECN))
- netdev->features &= ~NETIF_F_TSO_ECN;
- if (!(netdev->wanted_features & NETIF_F_GRO))
- netdev->features &= ~NETIF_F_GRO;
- if (!(netdev->wanted_features & NETIF_F_GSO))
- netdev->features &= ~NETIF_F_GSO;
- }
-
- adapter->vsi.id = adapter->vsi_res->vsi_id;
-
- adapter->vsi.back = adapter;
- adapter->vsi.base_vector = 1;
- adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK;
- vsi->netdev = adapter->netdev;
- vsi->qs_handle = adapter->vsi_res->qset_handle;
- if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
- adapter->rss_key_size = vfres->rss_key_size;
- adapter->rss_lut_size = vfres->rss_lut_size;
- } else {
- adapter->rss_key_size = I40EVF_HKEY_ARRAY_SIZE;
- adapter->rss_lut_size = I40EVF_HLUT_ARRAY_SIZE;
- }
-
- return 0;
-}
-
-/**
- * i40evf_init_task - worker thread to perform delayed initialization
- * @work: pointer to work_struct containing our data
- *
- * This task completes the work that was begun in probe. Due to the nature
- * of VF-PF communications, we may need to wait tens of milliseconds to get
- * responses back from the PF. Rather than busy-wait in probe and bog down the
- * whole system, we'll do it in a task so we can sleep.
- * This task only runs during driver init. Once we've established
- * communications with the PF driver and set up our netdev, the watchdog
- * takes over.
- **/
-static void i40evf_init_task(struct work_struct *work)
-{
- struct i40evf_adapter *adapter = container_of(work,
- struct i40evf_adapter,
- init_task.work);
- struct net_device *netdev = adapter->netdev;
- struct i40e_hw *hw = &adapter->hw;
- struct pci_dev *pdev = adapter->pdev;
- int err, bufsz;
-
- switch (adapter->state) {
- case __I40EVF_STARTUP:
- /* driver loaded, probe complete */
- adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED;
- adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
- err = i40e_set_mac_type(hw);
- if (err) {
- dev_err(&pdev->dev, "Failed to set MAC type (%d)\n",
- err);
- goto err;
- }
- err = i40evf_check_reset_complete(hw);
- if (err) {
- dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
- err);
- goto err;
- }
- hw->aq.num_arq_entries = I40EVF_AQ_LEN;
- hw->aq.num_asq_entries = I40EVF_AQ_LEN;
- hw->aq.arq_buf_size = I40EVF_MAX_AQ_BUF_SIZE;
- hw->aq.asq_buf_size = I40EVF_MAX_AQ_BUF_SIZE;
-
- err = i40evf_init_adminq(hw);
- if (err) {
- dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n",
- err);
- goto err;
- }
- err = i40evf_send_api_ver(adapter);
- if (err) {
- dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
- i40evf_shutdown_adminq(hw);
- goto err;
- }
- adapter->state = __I40EVF_INIT_VERSION_CHECK;
- goto restart;
- case __I40EVF_INIT_VERSION_CHECK:
- if (!i40evf_asq_done(hw)) {
- dev_err(&pdev->dev, "Admin queue command never completed\n");
- i40evf_shutdown_adminq(hw);
- adapter->state = __I40EVF_STARTUP;
- goto err;
- }
-
- /* aq msg sent, awaiting reply */
- err = i40evf_verify_api_ver(adapter);
- if (err) {
- if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK)
- err = i40evf_send_api_ver(adapter);
- else
- dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n",
- adapter->pf_version.major,
- adapter->pf_version.minor,
- VIRTCHNL_VERSION_MAJOR,
- VIRTCHNL_VERSION_MINOR);
- goto err;
- }
- err = i40evf_send_vf_config_msg(adapter);
- if (err) {
- dev_err(&pdev->dev, "Unable to send config request (%d)\n",
- err);
- goto err;
- }
- adapter->state = __I40EVF_INIT_GET_RESOURCES;
- goto restart;
- case __I40EVF_INIT_GET_RESOURCES:
- /* aq msg sent, awaiting reply */
- if (!adapter->vf_res) {
- bufsz = sizeof(struct virtchnl_vf_resource) +
- (I40E_MAX_VF_VSI *
- sizeof(struct virtchnl_vsi_resource));
- adapter->vf_res = kzalloc(bufsz, GFP_KERNEL);
- if (!adapter->vf_res)
- goto err;
- }
- err = i40evf_get_vf_config(adapter);
- if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) {
- err = i40evf_send_vf_config_msg(adapter);
- goto err;
- } else if (err == I40E_ERR_PARAM) {
- /* We only get ERR_PARAM if the device is in a very bad
- * state or if we've been disabled for previous bad
- * behavior. Either way, we're done now.
- */
- i40evf_shutdown_adminq(hw);
- dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n");
- return;
- }
- if (err) {
- dev_err(&pdev->dev, "Unable to get VF config (%d)\n",
- err);
- goto err_alloc;
- }
- adapter->state = __I40EVF_INIT_SW;
- break;
- default:
- goto err_alloc;
- }
-
- if (i40evf_process_config(adapter))
- goto err_alloc;
- adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-
- adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED;
-
- netdev->netdev_ops = &i40evf_netdev_ops;
- i40evf_set_ethtool_ops(netdev);
- netdev->watchdog_timeo = 5 * HZ;
-
- /* MTU range: 68 - 9710 */
- netdev->min_mtu = ETH_MIN_MTU;
- netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD;
-
- if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
- dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
- adapter->hw.mac.addr);
- eth_hw_addr_random(netdev);
- ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
- } else {
- adapter->flags |= I40EVF_FLAG_ADDR_SET_BY_PF;
- ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
- ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
- }
-
- timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0);
- mod_timer(&adapter->watchdog_timer, jiffies + 1);
-
- adapter->tx_desc_count = I40EVF_DEFAULT_TXD;
- adapter->rx_desc_count = I40EVF_DEFAULT_RXD;
- err = i40evf_init_interrupt_scheme(adapter);
- if (err)
- goto err_sw_init;
- i40evf_map_rings_to_vectors(adapter);
- if (adapter->vf_res->vf_cap_flags &
- VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
- adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
-
- err = i40evf_request_misc_irq(adapter);
- if (err)
- goto err_sw_init;
-
- netif_carrier_off(netdev);
- adapter->link_up = false;
-
- if (!adapter->netdev_registered) {
- err = register_netdev(netdev);
- if (err)
- goto err_register;
- }
-
- adapter->netdev_registered = true;
-
- netif_tx_stop_all_queues(netdev);
- if (CLIENT_ALLOWED(adapter)) {
- err = i40evf_lan_add_device(adapter);
- if (err)
- dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
- err);
- }
-
- dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
- if (netdev->features & NETIF_F_GRO)
- dev_info(&pdev->dev, "GRO is enabled\n");
-
- adapter->state = __I40EVF_DOWN;
- set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
- i40evf_misc_irq_enable(adapter);
- wake_up(&adapter->down_waitqueue);
-
- adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
- adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
- if (!adapter->rss_key || !adapter->rss_lut)
- goto err_mem;
-
- if (RSS_AQ(adapter)) {
- adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS;
- mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
- } else {
- i40evf_init_rss(adapter);
- }
- return;
-restart:
- schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30));
- return;
-err_mem:
- i40evf_free_rss(adapter);
-err_register:
- i40evf_free_misc_irq(adapter);
-err_sw_init:
- i40evf_reset_interrupt_capability(adapter);
-err_alloc:
- kfree(adapter->vf_res);
- adapter->vf_res = NULL;
-err:
- /* Things went into the weeds, so try again later */
- if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) {
- dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n");
- adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
- i40evf_shutdown_adminq(hw);
- adapter->state = __I40EVF_STARTUP;
- schedule_delayed_work(&adapter->init_task, HZ * 5);
- return;
- }
- schedule_delayed_work(&adapter->init_task, HZ);
-}
-
-/**
- * i40evf_shutdown - Shutdown the device in preparation for a reboot
- * @pdev: pci device structure
- **/
-static void i40evf_shutdown(struct pci_dev *pdev)
-{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct i40evf_adapter *adapter = netdev_priv(netdev);
-
- netif_device_detach(netdev);
-
- if (netif_running(netdev))
- i40evf_close(netdev);
-
- /* Prevent the watchdog from running. */
- adapter->state = __I40EVF_REMOVE;
- adapter->aq_required = 0;
-
-#ifdef CONFIG_PM
- pci_save_state(pdev);
-
-#endif
- pci_disable_device(pdev);
-}
-
-/**
- * i40evf_probe - Device Initialization Routine
- * @pdev: PCI device information struct
- * @ent: entry in i40evf_pci_tbl
- *
- * Returns 0 on success, negative on failure
- *
- * i40evf_probe initializes an adapter identified by a pci_dev structure.
- * The OS initialization, configuring of the adapter private structure,
- * and a hardware reset occur.
- **/
-static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
-{
- struct net_device *netdev;
- struct i40evf_adapter *adapter = NULL;
- struct i40e_hw *hw = NULL;
- int err;
-
- err = pci_enable_device(pdev);
- if (err)
- return err;
-
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (err) {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "DMA configuration failed: 0x%x\n", err);
- goto err_dma;
- }
- }
-
- err = pci_request_regions(pdev, i40evf_driver_name);
- if (err) {
- dev_err(&pdev->dev,
- "pci_request_regions failed 0x%x\n", err);
- goto err_pci_reg;
- }
-
- pci_enable_pcie_error_reporting(pdev);
-
- pci_set_master(pdev);
-
- netdev = alloc_etherdev_mq(sizeof(struct i40evf_adapter),
- I40EVF_MAX_REQ_QUEUES);
- if (!netdev) {
- err = -ENOMEM;
- goto err_alloc_etherdev;
- }
-
- SET_NETDEV_DEV(netdev, &pdev->dev);
-
- pci_set_drvdata(pdev, netdev);
- adapter = netdev_priv(netdev);
-
- adapter->netdev = netdev;
- adapter->pdev = pdev;
-
- hw = &adapter->hw;
- hw->back = adapter;
-
- adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
- adapter->state = __I40EVF_STARTUP;
-
- /* Call save state here because it relies on the adapter struct. */
- pci_save_state(pdev);
-
- hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
- pci_resource_len(pdev, 0));
- if (!hw->hw_addr) {
- err = -EIO;
- goto err_ioremap;
- }
- hw->vendor_id = pdev->vendor;
- hw->device_id = pdev->device;
- pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
- hw->subsystem_vendor_id = pdev->subsystem_vendor;
- hw->subsystem_device_id = pdev->subsystem_device;
- hw->bus.device = PCI_SLOT(pdev->devfn);
- hw->bus.func = PCI_FUNC(pdev->devfn);
- hw->bus.bus_id = pdev->bus->number;
-
- /* set up the locks for the AQ, do this only once in probe
- * and destroy them only once in remove
- */
- mutex_init(&hw->aq.asq_mutex);
- mutex_init(&hw->aq.arq_mutex);
-
- spin_lock_init(&adapter->mac_vlan_list_lock);
- spin_lock_init(&adapter->cloud_filter_list_lock);
-
- INIT_LIST_HEAD(&adapter->mac_filter_list);
- INIT_LIST_HEAD(&adapter->vlan_filter_list);
- INIT_LIST_HEAD(&adapter->cloud_filter_list);
-
- INIT_WORK(&adapter->reset_task, i40evf_reset_task);
- INIT_WORK(&adapter->adminq_task, i40evf_adminq_task);
- INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task);
- INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task);
- INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task);
- schedule_delayed_work(&adapter->init_task,
- msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
-
- /* Setup the wait queue for indicating transition to down status */
- init_waitqueue_head(&adapter->down_waitqueue);
-
- return 0;
-
-err_ioremap:
- free_netdev(netdev);
-err_alloc_etherdev:
- pci_release_regions(pdev);
-err_pci_reg:
-err_dma:
- pci_disable_device(pdev);
- return err;
-}
-
-#ifdef CONFIG_PM
-/**
- * i40evf_suspend - Power management suspend routine
- * @pdev: PCI device information struct
- * @state: unused
- *
- * Called when the system (VM) is entering sleep/suspend.
- **/
-static int i40evf_suspend(struct pci_dev *pdev, pm_message_t state)
-{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- int retval = 0;
-
- netif_device_detach(netdev);
-
- while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
- &adapter->crit_section))
- usleep_range(500, 1000);
-
- if (netif_running(netdev)) {
- rtnl_lock();
- i40evf_down(adapter);
- rtnl_unlock();
- }
- i40evf_free_misc_irq(adapter);
- i40evf_reset_interrupt_capability(adapter);
-
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
-
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-
- pci_disable_device(pdev);
-
- return 0;
-}
-
-/**
- * i40evf_resume - Power management resume routine
- * @pdev: PCI device information struct
- *
- * Called when the system (VM) is resumed from sleep/suspend.
- **/
-static int i40evf_resume(struct pci_dev *pdev)
-{
- struct i40evf_adapter *adapter = pci_get_drvdata(pdev);
- struct net_device *netdev = adapter->netdev;
- u32 err;
-
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- /* pci_restore_state clears dev->state_saved so call
- * pci_save_state to restore it.
- */
- pci_save_state(pdev);
-
- err = pci_enable_device_mem(pdev);
- if (err) {
- dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n");
- return err;
- }
- pci_set_master(pdev);
-
- rtnl_lock();
- err = i40evf_set_interrupt_capability(adapter);
- if (err) {
- rtnl_unlock();
- dev_err(&pdev->dev, "Cannot enable MSI-X interrupts.\n");
- return err;
- }
- err = i40evf_request_misc_irq(adapter);
- rtnl_unlock();
- if (err) {
- dev_err(&pdev->dev, "Cannot get interrupt vector.\n");
- return err;
- }
-
- schedule_work(&adapter->reset_task);
-
- netif_device_attach(netdev);
-
- return err;
-}
-
-#endif /* CONFIG_PM */
-/**
- * i40evf_remove - Device Removal Routine
- * @pdev: PCI device information struct
- *
- * i40evf_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device. The could be caused by a
- * Hot-Plug event, or because the driver is going to be removed from
- * memory.
- **/
-static void i40evf_remove(struct pci_dev *pdev)
-{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40evf_vlan_filter *vlf, *vlftmp;
- struct i40evf_mac_filter *f, *ftmp;
- struct i40evf_cloud_filter *cf, *cftmp;
- struct i40e_hw *hw = &adapter->hw;
- int err;
- /* Indicate we are in remove and not to run reset_task */
- set_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section);
- cancel_delayed_work_sync(&adapter->init_task);
- cancel_work_sync(&adapter->reset_task);
- cancel_delayed_work_sync(&adapter->client_task);
- if (adapter->netdev_registered) {
- unregister_netdev(netdev);
- adapter->netdev_registered = false;
- }
- if (CLIENT_ALLOWED(adapter)) {
- err = i40evf_lan_del_device(adapter);
- if (err)
- dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
- err);
- }
-
- /* Shut down all the garbage mashers on the detention level */
- adapter->state = __I40EVF_REMOVE;
- adapter->aq_required = 0;
- adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
- i40evf_request_reset(adapter);
- msleep(50);
- /* If the FW isn't responding, kick it once, but only once. */
- if (!i40evf_asq_done(hw)) {
- i40evf_request_reset(adapter);
- msleep(50);
- }
- i40evf_free_all_tx_resources(adapter);
- i40evf_free_all_rx_resources(adapter);
- i40evf_misc_irq_disable(adapter);
- i40evf_free_misc_irq(adapter);
- i40evf_reset_interrupt_capability(adapter);
- i40evf_free_q_vectors(adapter);
-
- if (adapter->watchdog_timer.function)
- del_timer_sync(&adapter->watchdog_timer);
-
- i40evf_free_rss(adapter);
-
- if (hw->aq.asq.count)
- i40evf_shutdown_adminq(hw);
-
- /* destroy the locks only once, here */
- mutex_destroy(&hw->aq.arq_mutex);
- mutex_destroy(&hw->aq.asq_mutex);
-
- iounmap(hw->hw_addr);
- pci_release_regions(pdev);
- i40evf_free_all_tx_resources(adapter);
- i40evf_free_all_rx_resources(adapter);
- i40evf_free_queues(adapter);
- kfree(adapter->vf_res);
- spin_lock_bh(&adapter->mac_vlan_list_lock);
- /* If we got removed before an up/down sequence, we've got a filter
- * hanging out there that we need to get rid of.
- */
- list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
- list_del(&f->list);
- kfree(f);
- }
- list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list,
- list) {
- list_del(&vlf->list);
- kfree(vlf);
- }
-
- spin_unlock_bh(&adapter->mac_vlan_list_lock);
-
- spin_lock_bh(&adapter->cloud_filter_list_lock);
- list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) {
- list_del(&cf->list);
- kfree(cf);
- }
- spin_unlock_bh(&adapter->cloud_filter_list_lock);
-
- free_netdev(netdev);
-
- pci_disable_pcie_error_reporting(pdev);
-
- pci_disable_device(pdev);
-}
-
-static struct pci_driver i40evf_driver = {
- .name = i40evf_driver_name,
- .id_table = i40evf_pci_tbl,
- .probe = i40evf_probe,
- .remove = i40evf_remove,
-#ifdef CONFIG_PM
- .suspend = i40evf_suspend,
- .resume = i40evf_resume,
-#endif
- .shutdown = i40evf_shutdown,
-};
-
-/**
- * i40e_init_module - Driver Registration Routine
- *
- * i40e_init_module is the first routine called when the driver is
- * loaded. All it does is register with the PCI subsystem.
- **/
-static int __init i40evf_init_module(void)
-{
- int ret;
-
- pr_info("i40evf: %s - version %s\n", i40evf_driver_string,
- i40evf_driver_version);
-
- pr_info("%s\n", i40evf_copyright);
-
- i40evf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1,
- i40evf_driver_name);
- if (!i40evf_wq) {
- pr_err("%s: Failed to create workqueue\n", i40evf_driver_name);
- return -ENOMEM;
- }
- ret = pci_register_driver(&i40evf_driver);
- return ret;
-}
-
-module_init(i40evf_init_module);
-
-/**
- * i40e_exit_module - Driver Exit Cleanup Routine
- *
- * i40e_exit_module is called just before the driver is removed
- * from memory.
- **/
-static void __exit i40evf_exit_module(void)
-{
- pci_unregister_driver(&i40evf_driver);
- destroy_workqueue(i40evf_wq);
-}
-
-module_exit(i40evf_exit_module);
-
-/* i40evf_main.c */
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
new file mode 100644
index 0000000..c997063
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2013 - 2018 Intel Corporation.
+#
+# Makefile for the Intel(R) Ethernet Adaptive Virtual Function (iavf)
+# driver
+#
+#
+
+ccflags-y += -I$(src)
+subdir-ccflags-y += -I$(src)
+
+obj-$(CONFIG_IAVF) += iavf.o
+
+iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \
+ iavf_txrx.o iavf_common.o iavf_adminq.o iavf_client.o
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
new file mode 100644
index 0000000..29de3ae
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -0,0 +1,418 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_H_
+#define _IAVF_H_
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+#include <linux/interrupt.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/sctp.h>
+#include <linux/ipv6.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/delay.h>
+#include <linux/gfp.h>
+#include <linux/skbuff.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/socket.h>
+#include <linux/jiffies.h>
+#include <net/ip6_checksum.h>
+#include <net/pkt_cls.h>
+#include <net/udp.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_mirred.h>
+
+#include "iavf_type.h"
+#include <linux/avf/virtchnl.h>
+#include "iavf_txrx.h"
+
+#define DEFAULT_DEBUG_LEVEL_SHIFT 3
+#define PFX "iavf: "
+
+/* VSI state flags shared with common code */
+enum iavf_vsi_state_t {
+ __IAVF_VSI_DOWN,
+ /* This must be last as it determines the size of the BITMAP */
+ __IAVF_VSI_STATE_SIZE__,
+};
+
+/* dummy struct to make common code less painful */
+struct iavf_vsi {
+ struct iavf_adapter *back;
+ struct net_device *netdev;
+ unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+ u16 seid;
+ u16 id;
+ DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__);
+ int base_vector;
+ u16 work_limit;
+ u16 qs_handle;
+ void *priv; /* client driver data reference. */
+};
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IAVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */
+#define IAVF_DEFAULT_TXD 512
+#define IAVF_DEFAULT_RXD 512
+#define IAVF_MAX_TXD 4096
+#define IAVF_MIN_TXD 64
+#define IAVF_MAX_RXD 4096
+#define IAVF_MIN_RXD 64
+#define IAVF_REQ_DESCRIPTOR_MULTIPLE 32
+#define IAVF_MAX_AQ_BUF_SIZE 4096
+#define IAVF_AQ_LEN 32
+#define IAVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */
+
+#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+
+#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i]))
+#define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i]))
+#define IAVF_TX_CTXTDESC(R, i) \
+ (&(((struct iavf_tx_context_desc *)((R)->desc))[i]))
+#define IAVF_MAX_REQ_QUEUES 4
+
+#define IAVF_HKEY_ARRAY_SIZE ((IAVF_VFQF_HKEY_MAX_INDEX + 1) * 4)
+#define IAVF_HLUT_ARRAY_SIZE ((IAVF_VFQF_HLUT_MAX_INDEX + 1) * 4)
+#define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */
+
+/* MAX_MSIX_Q_VECTORS of these are allocated,
+ * but we only use one per queue-specific vector.
+ */
+struct iavf_q_vector {
+ struct iavf_adapter *adapter;
+ struct iavf_vsi *vsi;
+ struct napi_struct napi;
+ struct iavf_ring_container rx;
+ struct iavf_ring_container tx;
+ u32 ring_mask;
+ u8 itr_countdown; /* when 0 should adjust adaptive ITR */
+ u8 num_ringpairs; /* total number of ring pairs in vector */
+ u16 v_idx; /* index in the vsi->q_vector array. */
+ u16 reg_idx; /* register index of the interrupt */
+ char name[IFNAMSIZ + 15];
+ bool arm_wb_state;
+ cpumask_t affinity_mask;
+ struct irq_affinity_notify affinity_notify;
+};
+
+/* Helper macros to switch between ints/sec and what the register uses.
+ * And yes, it's the same math going both ways. The lowest value
+ * supported by all of the iavf hardware is 8.
+ */
+#define EITR_INTS_PER_SEC_TO_REG(_eitr) \
+ ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8)
+#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG
+
+#define IAVF_DESC_UNUSED(R) \
+ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+ (R)->next_to_clean - (R)->next_to_use - 1)
+
+#define OTHER_VECTOR 1
+#define NONQ_VECS (OTHER_VECTOR)
+
+#define MIN_MSIX_Q_VECTORS 1
+#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS)
+
+#define IAVF_QUEUE_END_OF_LIST 0x7FF
+#define IAVF_FREE_VECTOR 0x7FFF
+struct iavf_mac_filter {
+ struct list_head list;
+ u8 macaddr[ETH_ALEN];
+ bool remove; /* filter needs to be removed */
+ bool add; /* filter needs to be added */
+};
+
+struct iavf_vlan_filter {
+ struct list_head list;
+ u16 vlan;
+ bool remove; /* filter needs to be removed */
+ bool add; /* filter needs to be added */
+};
+
+#define IAVF_MAX_TRAFFIC_CLASS 4
+/* State of traffic class creation */
+enum iavf_tc_state_t {
+ __IAVF_TC_INVALID, /* no traffic class, default state */
+ __IAVF_TC_RUNNING, /* traffic classes have been created */
+};
+
+/* channel info */
+struct iavf_channel_config {
+ struct virtchnl_channel_info ch_info[IAVF_MAX_TRAFFIC_CLASS];
+ enum iavf_tc_state_t state;
+ u8 total_qps;
+};
+
+/* State of cloud filter */
+enum iavf_cloud_filter_state_t {
+ __IAVF_CF_INVALID, /* cloud filter not added */
+ __IAVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */
+ __IAVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */
+ __IAVF_CF_ACTIVE, /* cloud filter is active */
+};
+
+/* Driver state. The order of these is important! */
+enum iavf_state_t {
+ __IAVF_STARTUP, /* driver loaded, probe complete */
+ __IAVF_REMOVE, /* driver is being unloaded */
+ __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */
+ __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */
+ __IAVF_INIT_SW, /* got resources, setting up structs */
+ __IAVF_RESETTING, /* in reset */
+ __IAVF_COMM_FAILED, /* communication with PF failed */
+ /* Below here, watchdog is running */
+ __IAVF_DOWN, /* ready, can be opened */
+ __IAVF_DOWN_PENDING, /* descending, waiting for watchdog */
+ __IAVF_TESTING, /* in ethtool self-test */
+ __IAVF_RUNNING, /* opened, working */
+};
+
+enum iavf_critical_section_t {
+ __IAVF_IN_CRITICAL_TASK, /* cannot be interrupted */
+ __IAVF_IN_CLIENT_TASK,
+ __IAVF_IN_REMOVE_TASK, /* device being removed */
+};
+
+#define IAVF_CLOUD_FIELD_OMAC 0x01
+#define IAVF_CLOUD_FIELD_IMAC 0x02
+#define IAVF_CLOUD_FIELD_IVLAN 0x04
+#define IAVF_CLOUD_FIELD_TEN_ID 0x08
+#define IAVF_CLOUD_FIELD_IIP 0x10
+
+#define IAVF_CF_FLAGS_OMAC IAVF_CLOUD_FIELD_OMAC
+#define IAVF_CF_FLAGS_IMAC IAVF_CLOUD_FIELD_IMAC
+#define IAVF_CF_FLAGS_IMAC_IVLAN (IAVF_CLOUD_FIELD_IMAC |\
+ IAVF_CLOUD_FIELD_IVLAN)
+#define IAVF_CF_FLAGS_IMAC_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\
+ IAVF_CLOUD_FIELD_TEN_ID)
+#define IAVF_CF_FLAGS_OMAC_TEN_ID_IMAC (IAVF_CLOUD_FIELD_OMAC |\
+ IAVF_CLOUD_FIELD_IMAC |\
+ IAVF_CLOUD_FIELD_TEN_ID)
+#define IAVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\
+ IAVF_CLOUD_FIELD_IVLAN |\
+ IAVF_CLOUD_FIELD_TEN_ID)
+#define IAVF_CF_FLAGS_IIP IAVF_CLOUD_FIELD_IIP
+
+/* bookkeeping of cloud filters */
+struct iavf_cloud_filter {
+ enum iavf_cloud_filter_state_t state;
+ struct list_head list;
+ struct virtchnl_filter f;
+ unsigned long cookie;
+ bool del; /* filter needs to be deleted */
+ bool add; /* filter needs to be added */
+};
+
+/* board specific private data structure */
+struct iavf_adapter {
+ struct work_struct reset_task;
+ struct work_struct adminq_task;
+ struct delayed_work client_task;
+ struct delayed_work init_task;
+ wait_queue_head_t down_waitqueue;
+ struct iavf_q_vector *q_vectors;
+ struct list_head vlan_filter_list;
+ struct list_head mac_filter_list;
+ /* Lock to protect accesses to MAC and VLAN lists */
+ spinlock_t mac_vlan_list_lock;
+ char misc_vector_name[IFNAMSIZ + 9];
+ int num_active_queues;
+ int num_req_queues;
+
+ /* TX */
+ struct iavf_ring *tx_rings;
+ u32 tx_timeout_count;
+ u32 tx_desc_count;
+
+ /* RX */
+ struct iavf_ring *rx_rings;
+ u64 hw_csum_rx_error;
+ u32 rx_desc_count;
+ int num_msix_vectors;
+ int num_iwarp_msix;
+ int iwarp_base_vector;
+ u32 client_pending;
+ struct iavf_client_instance *cinst;
+ struct msix_entry *msix_entries;
+
+ u32 flags;
+#define IAVF_FLAG_RX_CSUM_ENABLED BIT(0)
+#define IAVF_FLAG_PF_COMMS_FAILED BIT(3)
+#define IAVF_FLAG_RESET_PENDING BIT(4)
+#define IAVF_FLAG_RESET_NEEDED BIT(5)
+#define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6)
+#define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9)
+#define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10)
+#define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11)
+#define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12)
+#define IAVF_FLAG_PROMISC_ON BIT(13)
+#define IAVF_FLAG_ALLMULTI_ON BIT(14)
+#define IAVF_FLAG_LEGACY_RX BIT(15)
+#define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16)
+#define IAVF_FLAG_QUEUES_DISABLED BIT(17)
+/* duplicates for common code */
+#define IAVF_FLAG_DCB_ENABLED 0
+ /* flags for admin queue service task */
+ u32 aq_required;
+#define IAVF_FLAG_AQ_ENABLE_QUEUES BIT(0)
+#define IAVF_FLAG_AQ_DISABLE_QUEUES BIT(1)
+#define IAVF_FLAG_AQ_ADD_MAC_FILTER BIT(2)
+#define IAVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3)
+#define IAVF_FLAG_AQ_DEL_MAC_FILTER BIT(4)
+#define IAVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5)
+#define IAVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6)
+#define IAVF_FLAG_AQ_MAP_VECTORS BIT(7)
+#define IAVF_FLAG_AQ_HANDLE_RESET BIT(8)
+#define IAVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */
+#define IAVF_FLAG_AQ_GET_CONFIG BIT(10)
+/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */
+#define IAVF_FLAG_AQ_GET_HENA BIT(11)
+#define IAVF_FLAG_AQ_SET_HENA BIT(12)
+#define IAVF_FLAG_AQ_SET_RSS_KEY BIT(13)
+#define IAVF_FLAG_AQ_SET_RSS_LUT BIT(14)
+#define IAVF_FLAG_AQ_REQUEST_PROMISC BIT(15)
+#define IAVF_FLAG_AQ_RELEASE_PROMISC BIT(16)
+#define IAVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17)
+#define IAVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18)
+#define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19)
+#define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20)
+#define IAVF_FLAG_AQ_ENABLE_CHANNELS BIT(21)
+#define IAVF_FLAG_AQ_DISABLE_CHANNELS BIT(22)
+#define IAVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23)
+#define IAVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24)
+
+ /* OS defined structs */
+ struct net_device *netdev;
+ struct pci_dev *pdev;
+
+ struct iavf_hw hw; /* defined in iavf_type.h */
+
+ enum iavf_state_t state;
+ unsigned long crit_section;
+
+ struct delayed_work watchdog_task;
+ bool netdev_registered;
+ bool link_up;
+ enum virtchnl_link_speed link_speed;
+ enum virtchnl_ops current_op;
+#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
+ (_a)->vf_res->vf_cap_flags & \
+ VIRTCHNL_VF_OFFLOAD_IWARP : \
+ 0)
+#define CLIENT_ENABLED(_a) ((_a)->cinst)
+/* RSS by the PF should be preferred over RSS via other methods. */
+#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \
+ VIRTCHNL_VF_OFFLOAD_RSS_PF)
+#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \
+ VIRTCHNL_VF_OFFLOAD_RSS_AQ)
+#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \
+ (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \
+ VIRTCHNL_VF_OFFLOAD_RSS_PF)))
+#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
+ VIRTCHNL_VF_OFFLOAD_VLAN)
+ struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
+ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
+ struct virtchnl_version_info pf_version;
+#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
+ ((_a)->pf_version.minor == 1))
+ u16 msg_enable;
+ struct iavf_eth_stats current_stats;
+ struct iavf_vsi vsi;
+ u32 aq_wait_count;
+ /* RSS stuff */
+ u64 hena;
+ u16 rss_key_size;
+ u16 rss_lut_size;
+ u8 *rss_key;
+ u8 *rss_lut;
+ /* ADQ related members */
+ struct iavf_channel_config ch_config;
+ u8 num_tc;
+ struct list_head cloud_filter_list;
+ /* lock to protect access to the cloud filter list */
+ spinlock_t cloud_filter_list_lock;
+ u16 num_cloud_filters;
+};
+
+
+/* Ethtool Private Flags */
+
+/* lan device, used by client interface */
+struct iavf_device {
+ struct list_head list;
+ struct iavf_adapter *vf;
+};
+
+/* needed by iavf_ethtool.c */
+extern char iavf_driver_name[];
+extern const char iavf_driver_version[];
+extern struct workqueue_struct *iavf_wq;
+
+int iavf_up(struct iavf_adapter *adapter);
+void iavf_down(struct iavf_adapter *adapter);
+int iavf_process_config(struct iavf_adapter *adapter);
+void iavf_schedule_reset(struct iavf_adapter *adapter);
+void iavf_reset(struct iavf_adapter *adapter);
+void iavf_set_ethtool_ops(struct net_device *netdev);
+void iavf_update_stats(struct iavf_adapter *adapter);
+void iavf_reset_interrupt_capability(struct iavf_adapter *adapter);
+int iavf_init_interrupt_scheme(struct iavf_adapter *adapter);
+void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask);
+void iavf_free_all_tx_resources(struct iavf_adapter *adapter);
+void iavf_free_all_rx_resources(struct iavf_adapter *adapter);
+
+void iavf_napi_add_all(struct iavf_adapter *adapter);
+void iavf_napi_del_all(struct iavf_adapter *adapter);
+
+int iavf_send_api_ver(struct iavf_adapter *adapter);
+int iavf_verify_api_ver(struct iavf_adapter *adapter);
+int iavf_send_vf_config_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_config(struct iavf_adapter *adapter);
+void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
+void iavf_configure_queues(struct iavf_adapter *adapter);
+void iavf_deconfigure_queues(struct iavf_adapter *adapter);
+void iavf_enable_queues(struct iavf_adapter *adapter);
+void iavf_disable_queues(struct iavf_adapter *adapter);
+void iavf_map_queues(struct iavf_adapter *adapter);
+int iavf_request_queues(struct iavf_adapter *adapter, int num);
+void iavf_add_ether_addrs(struct iavf_adapter *adapter);
+void iavf_del_ether_addrs(struct iavf_adapter *adapter);
+void iavf_add_vlans(struct iavf_adapter *adapter);
+void iavf_del_vlans(struct iavf_adapter *adapter);
+void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags);
+void iavf_request_stats(struct iavf_adapter *adapter);
+void iavf_request_reset(struct iavf_adapter *adapter);
+void iavf_get_hena(struct iavf_adapter *adapter);
+void iavf_set_hena(struct iavf_adapter *adapter);
+void iavf_set_rss_key(struct iavf_adapter *adapter);
+void iavf_set_rss_lut(struct iavf_adapter *adapter);
+void iavf_enable_vlan_stripping(struct iavf_adapter *adapter);
+void iavf_disable_vlan_stripping(struct iavf_adapter *adapter);
+void iavf_virtchnl_completion(struct iavf_adapter *adapter,
+ enum virtchnl_ops v_opcode,
+ enum iavf_status v_retval, u8 *msg, u16 msglen);
+int iavf_config_rss(struct iavf_adapter *adapter);
+int iavf_lan_add_device(struct iavf_adapter *adapter);
+int iavf_lan_del_device(struct iavf_adapter *adapter);
+void iavf_client_subtask(struct iavf_adapter *adapter);
+void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len);
+void iavf_notify_client_l2_params(struct iavf_vsi *vsi);
+void iavf_notify_client_open(struct iavf_vsi *vsi);
+void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset);
+void iavf_enable_channels(struct iavf_adapter *adapter);
+void iavf_disable_channels(struct iavf_adapter *adapter);
+void iavf_add_cloud_filter(struct iavf_adapter *adapter);
+void iavf_del_cloud_filter(struct iavf_adapter *adapter);
+#endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
similarity index 60%
rename from drivers/net/ethernet/intel/i40evf/i40e_adminq.c
rename to drivers/net/ethernet/intel/iavf/iavf_adminq.c
index 21a0dbf..9fa3fa9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -1,66 +1,54 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
-#include "i40e_status.h"
-#include "i40e_type.h"
-#include "i40e_register.h"
-#include "i40e_adminq.h"
-#include "i40e_prototype.h"
+#include "iavf_status.h"
+#include "iavf_type.h"
+#include "iavf_register.h"
+#include "iavf_adminq.h"
+#include "iavf_prototype.h"
/**
- * i40e_is_nvm_update_op - return true if this is an NVM update operation
- * @desc: API request descriptor
- **/
-static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc)
-{
- return (desc->opcode == i40e_aqc_opc_nvm_erase) ||
- (desc->opcode == i40e_aqc_opc_nvm_update);
-}
-
-/**
- * i40e_adminq_init_regs - Initialize AdminQ registers
+ * iavf_adminq_init_regs - Initialize AdminQ registers
* @hw: pointer to the hardware structure
*
* This assumes the alloc_asq and alloc_arq functions have already been called
**/
-static void i40e_adminq_init_regs(struct i40e_hw *hw)
+static void iavf_adminq_init_regs(struct iavf_hw *hw)
{
/* set head and tail registers in our local struct */
- if (i40e_is_vf(hw)) {
- hw->aq.asq.tail = I40E_VF_ATQT1;
- hw->aq.asq.head = I40E_VF_ATQH1;
- hw->aq.asq.len = I40E_VF_ATQLEN1;
- hw->aq.asq.bal = I40E_VF_ATQBAL1;
- hw->aq.asq.bah = I40E_VF_ATQBAH1;
- hw->aq.arq.tail = I40E_VF_ARQT1;
- hw->aq.arq.head = I40E_VF_ARQH1;
- hw->aq.arq.len = I40E_VF_ARQLEN1;
- hw->aq.arq.bal = I40E_VF_ARQBAL1;
- hw->aq.arq.bah = I40E_VF_ARQBAH1;
- }
+ hw->aq.asq.tail = IAVF_VF_ATQT1;
+ hw->aq.asq.head = IAVF_VF_ATQH1;
+ hw->aq.asq.len = IAVF_VF_ATQLEN1;
+ hw->aq.asq.bal = IAVF_VF_ATQBAL1;
+ hw->aq.asq.bah = IAVF_VF_ATQBAH1;
+ hw->aq.arq.tail = IAVF_VF_ARQT1;
+ hw->aq.arq.head = IAVF_VF_ARQH1;
+ hw->aq.arq.len = IAVF_VF_ARQLEN1;
+ hw->aq.arq.bal = IAVF_VF_ARQBAL1;
+ hw->aq.arq.bah = IAVF_VF_ARQBAH1;
}
/**
- * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings
+ * iavf_alloc_adminq_asq_ring - Allocate Admin Queue send rings
* @hw: pointer to the hardware structure
**/
-static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw)
+static enum iavf_status iavf_alloc_adminq_asq_ring(struct iavf_hw *hw)
{
- i40e_status ret_code;
+ enum iavf_status ret_code;
- ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
- i40e_mem_atq_ring,
+ ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
+ iavf_mem_atq_ring,
(hw->aq.num_asq_entries *
- sizeof(struct i40e_aq_desc)),
- I40E_ADMINQ_DESC_ALIGNMENT);
+ sizeof(struct iavf_aq_desc)),
+ IAVF_ADMINQ_DESC_ALIGNMENT);
if (ret_code)
return ret_code;
- ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf,
+ ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf,
(hw->aq.num_asq_entries *
- sizeof(struct i40e_asq_cmd_details)));
+ sizeof(struct iavf_asq_cmd_details)));
if (ret_code) {
- i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf);
+ iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf);
return ret_code;
}
@@ -68,55 +56,55 @@
}
/**
- * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings
+ * iavf_alloc_adminq_arq_ring - Allocate Admin Queue receive rings
* @hw: pointer to the hardware structure
**/
-static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw)
+static enum iavf_status iavf_alloc_adminq_arq_ring(struct iavf_hw *hw)
{
- i40e_status ret_code;
+ enum iavf_status ret_code;
- ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
- i40e_mem_arq_ring,
+ ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
+ iavf_mem_arq_ring,
(hw->aq.num_arq_entries *
- sizeof(struct i40e_aq_desc)),
- I40E_ADMINQ_DESC_ALIGNMENT);
+ sizeof(struct iavf_aq_desc)),
+ IAVF_ADMINQ_DESC_ALIGNMENT);
return ret_code;
}
/**
- * i40e_free_adminq_asq - Free Admin Queue send rings
+ * iavf_free_adminq_asq - Free Admin Queue send rings
* @hw: pointer to the hardware structure
*
* This assumes the posted send buffers have already been cleaned
* and de-allocated
**/
-static void i40e_free_adminq_asq(struct i40e_hw *hw)
+static void iavf_free_adminq_asq(struct iavf_hw *hw)
{
- i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf);
+ iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf);
}
/**
- * i40e_free_adminq_arq - Free Admin Queue receive rings
+ * iavf_free_adminq_arq - Free Admin Queue receive rings
* @hw: pointer to the hardware structure
*
* This assumes the posted receive buffers have already been cleaned
* and de-allocated
**/
-static void i40e_free_adminq_arq(struct i40e_hw *hw)
+static void iavf_free_adminq_arq(struct iavf_hw *hw)
{
- i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf);
+ iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf);
}
/**
- * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue
+ * iavf_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue
* @hw: pointer to the hardware structure
**/
-static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw)
+static enum iavf_status iavf_alloc_arq_bufs(struct iavf_hw *hw)
{
- i40e_status ret_code;
- struct i40e_aq_desc *desc;
- struct i40e_dma_mem *bi;
+ struct iavf_aq_desc *desc;
+ struct iavf_dma_mem *bi;
+ enum iavf_status ret_code;
int i;
/* We'll be allocating the buffer info memory first, then we can
@@ -124,28 +112,29 @@
*/
/* buffer_info structures do not need alignment */
- ret_code = i40e_allocate_virt_mem(hw, &hw->aq.arq.dma_head,
- (hw->aq.num_arq_entries * sizeof(struct i40e_dma_mem)));
+ ret_code = iavf_allocate_virt_mem(hw, &hw->aq.arq.dma_head,
+ (hw->aq.num_arq_entries *
+ sizeof(struct iavf_dma_mem)));
if (ret_code)
goto alloc_arq_bufs;
- hw->aq.arq.r.arq_bi = (struct i40e_dma_mem *)hw->aq.arq.dma_head.va;
+ hw->aq.arq.r.arq_bi = (struct iavf_dma_mem *)hw->aq.arq.dma_head.va;
/* allocate the mapped buffers */
for (i = 0; i < hw->aq.num_arq_entries; i++) {
bi = &hw->aq.arq.r.arq_bi[i];
- ret_code = i40e_allocate_dma_mem(hw, bi,
- i40e_mem_arq_buf,
+ ret_code = iavf_allocate_dma_mem(hw, bi,
+ iavf_mem_arq_buf,
hw->aq.arq_buf_size,
- I40E_ADMINQ_DESC_ALIGNMENT);
+ IAVF_ADMINQ_DESC_ALIGNMENT);
if (ret_code)
goto unwind_alloc_arq_bufs;
/* now configure the descriptors for use */
- desc = I40E_ADMINQ_DESC(hw->aq.arq, i);
+ desc = IAVF_ADMINQ_DESC(hw->aq.arq, i);
- desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
- if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
- desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+ desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+ if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
+ desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
desc->opcode = 0;
/* This is in accordance with Admin queue design, there is no
* register for buffer size configuration
@@ -169,36 +158,37 @@
/* don't try to free the one that failed... */
i--;
for (; i >= 0; i--)
- i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
- i40e_free_virt_mem(hw, &hw->aq.arq.dma_head);
+ iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+ iavf_free_virt_mem(hw, &hw->aq.arq.dma_head);
return ret_code;
}
/**
- * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue
+ * iavf_alloc_asq_bufs - Allocate empty buffer structs for the send queue
* @hw: pointer to the hardware structure
**/
-static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw)
+static enum iavf_status iavf_alloc_asq_bufs(struct iavf_hw *hw)
{
- i40e_status ret_code;
- struct i40e_dma_mem *bi;
+ struct iavf_dma_mem *bi;
+ enum iavf_status ret_code;
int i;
/* No mapped memory needed yet, just the buffer info structures */
- ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.dma_head,
- (hw->aq.num_asq_entries * sizeof(struct i40e_dma_mem)));
+ ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.dma_head,
+ (hw->aq.num_asq_entries *
+ sizeof(struct iavf_dma_mem)));
if (ret_code)
goto alloc_asq_bufs;
- hw->aq.asq.r.asq_bi = (struct i40e_dma_mem *)hw->aq.asq.dma_head.va;
+ hw->aq.asq.r.asq_bi = (struct iavf_dma_mem *)hw->aq.asq.dma_head.va;
/* allocate the mapped buffers */
for (i = 0; i < hw->aq.num_asq_entries; i++) {
bi = &hw->aq.asq.r.asq_bi[i];
- ret_code = i40e_allocate_dma_mem(hw, bi,
- i40e_mem_asq_buf,
+ ret_code = iavf_allocate_dma_mem(hw, bi,
+ iavf_mem_asq_buf,
hw->aq.asq_buf_size,
- I40E_ADMINQ_DESC_ALIGNMENT);
+ IAVF_ADMINQ_DESC_ALIGNMENT);
if (ret_code)
goto unwind_alloc_asq_bufs;
}
@@ -209,63 +199,63 @@
/* don't try to free the one that failed... */
i--;
for (; i >= 0; i--)
- i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
- i40e_free_virt_mem(hw, &hw->aq.asq.dma_head);
+ iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+ iavf_free_virt_mem(hw, &hw->aq.asq.dma_head);
return ret_code;
}
/**
- * i40e_free_arq_bufs - Free receive queue buffer info elements
+ * iavf_free_arq_bufs - Free receive queue buffer info elements
* @hw: pointer to the hardware structure
**/
-static void i40e_free_arq_bufs(struct i40e_hw *hw)
+static void iavf_free_arq_bufs(struct iavf_hw *hw)
{
int i;
/* free descriptors */
for (i = 0; i < hw->aq.num_arq_entries; i++)
- i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+ iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
/* free the descriptor memory */
- i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf);
+ iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf);
/* free the dma header */
- i40e_free_virt_mem(hw, &hw->aq.arq.dma_head);
+ iavf_free_virt_mem(hw, &hw->aq.arq.dma_head);
}
/**
- * i40e_free_asq_bufs - Free send queue buffer info elements
+ * iavf_free_asq_bufs - Free send queue buffer info elements
* @hw: pointer to the hardware structure
**/
-static void i40e_free_asq_bufs(struct i40e_hw *hw)
+static void iavf_free_asq_bufs(struct iavf_hw *hw)
{
int i;
/* only unmap if the address is non-NULL */
for (i = 0; i < hw->aq.num_asq_entries; i++)
if (hw->aq.asq.r.asq_bi[i].pa)
- i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+ iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
/* free the buffer info list */
- i40e_free_virt_mem(hw, &hw->aq.asq.cmd_buf);
+ iavf_free_virt_mem(hw, &hw->aq.asq.cmd_buf);
/* free the descriptor memory */
- i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf);
+ iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf);
/* free the dma header */
- i40e_free_virt_mem(hw, &hw->aq.asq.dma_head);
+ iavf_free_virt_mem(hw, &hw->aq.asq.dma_head);
}
/**
- * i40e_config_asq_regs - configure ASQ registers
+ * iavf_config_asq_regs - configure ASQ registers
* @hw: pointer to the hardware structure
*
* Configure base address and length registers for the transmit queue
**/
-static i40e_status i40e_config_asq_regs(struct i40e_hw *hw)
+static enum iavf_status iavf_config_asq_regs(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
u32 reg = 0;
/* Clear Head and Tail */
@@ -274,27 +264,27 @@
/* set starting point */
wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries |
- I40E_VF_ATQLEN1_ATQENABLE_MASK));
+ IAVF_VF_ATQLEN1_ATQENABLE_MASK));
wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa));
wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa));
/* Check one register to verify that config was applied */
reg = rd32(hw, hw->aq.asq.bal);
if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
- ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+ ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
return ret_code;
}
/**
- * i40e_config_arq_regs - ARQ register configuration
+ * iavf_config_arq_regs - ARQ register configuration
* @hw: pointer to the hardware structure
*
* Configure base address and length registers for the receive (event queue)
**/
-static i40e_status i40e_config_arq_regs(struct i40e_hw *hw)
+static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
u32 reg = 0;
/* Clear Head and Tail */
@@ -303,7 +293,7 @@
/* set starting point */
wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries |
- I40E_VF_ARQLEN1_ARQENABLE_MASK));
+ IAVF_VF_ARQLEN1_ARQENABLE_MASK));
wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa));
wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa));
@@ -313,13 +303,13 @@
/* Check one register to verify that config was applied */
reg = rd32(hw, hw->aq.arq.bal);
if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
- ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+ ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
return ret_code;
}
/**
- * i40e_init_asq - main initialization routine for ASQ
+ * iavf_init_asq - main initialization routine for ASQ
* @hw: pointer to the hardware structure
*
* This is the main initialization routine for the Admin Send Queue
@@ -331,20 +321,20 @@
* Do *NOT* hold the lock when calling this as the memory allocation routines
* called are not going to be atomic context safe
**/
-static i40e_status i40e_init_asq(struct i40e_hw *hw)
+static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
if (hw->aq.asq.count > 0) {
/* queue already initialized */
- ret_code = I40E_ERR_NOT_READY;
+ ret_code = IAVF_ERR_NOT_READY;
goto init_adminq_exit;
}
/* verify input for valid configuration */
if ((hw->aq.num_asq_entries == 0) ||
(hw->aq.asq_buf_size == 0)) {
- ret_code = I40E_ERR_CONFIG;
+ ret_code = IAVF_ERR_CONFIG;
goto init_adminq_exit;
}
@@ -352,17 +342,17 @@
hw->aq.asq.next_to_clean = 0;
/* allocate the ring memory */
- ret_code = i40e_alloc_adminq_asq_ring(hw);
+ ret_code = iavf_alloc_adminq_asq_ring(hw);
if (ret_code)
goto init_adminq_exit;
/* allocate buffers in the rings */
- ret_code = i40e_alloc_asq_bufs(hw);
+ ret_code = iavf_alloc_asq_bufs(hw);
if (ret_code)
goto init_adminq_free_rings;
/* initialize base registers */
- ret_code = i40e_config_asq_regs(hw);
+ ret_code = iavf_config_asq_regs(hw);
if (ret_code)
goto init_adminq_free_rings;
@@ -371,14 +361,14 @@
goto init_adminq_exit;
init_adminq_free_rings:
- i40e_free_adminq_asq(hw);
+ iavf_free_adminq_asq(hw);
init_adminq_exit:
return ret_code;
}
/**
- * i40e_init_arq - initialize ARQ
+ * iavf_init_arq - initialize ARQ
* @hw: pointer to the hardware structure
*
* The main initialization routine for the Admin Receive (Event) Queue.
@@ -390,20 +380,20 @@
* Do *NOT* hold the lock when calling this as the memory allocation routines
* called are not going to be atomic context safe
**/
-static i40e_status i40e_init_arq(struct i40e_hw *hw)
+static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
if (hw->aq.arq.count > 0) {
/* queue already initialized */
- ret_code = I40E_ERR_NOT_READY;
+ ret_code = IAVF_ERR_NOT_READY;
goto init_adminq_exit;
}
/* verify input for valid configuration */
if ((hw->aq.num_arq_entries == 0) ||
(hw->aq.arq_buf_size == 0)) {
- ret_code = I40E_ERR_CONFIG;
+ ret_code = IAVF_ERR_CONFIG;
goto init_adminq_exit;
}
@@ -411,17 +401,17 @@
hw->aq.arq.next_to_clean = 0;
/* allocate the ring memory */
- ret_code = i40e_alloc_adminq_arq_ring(hw);
+ ret_code = iavf_alloc_adminq_arq_ring(hw);
if (ret_code)
goto init_adminq_exit;
/* allocate buffers in the rings */
- ret_code = i40e_alloc_arq_bufs(hw);
+ ret_code = iavf_alloc_arq_bufs(hw);
if (ret_code)
goto init_adminq_free_rings;
/* initialize base registers */
- ret_code = i40e_config_arq_regs(hw);
+ ret_code = iavf_config_arq_regs(hw);
if (ret_code)
goto init_adminq_free_rings;
@@ -430,26 +420,26 @@
goto init_adminq_exit;
init_adminq_free_rings:
- i40e_free_adminq_arq(hw);
+ iavf_free_adminq_arq(hw);
init_adminq_exit:
return ret_code;
}
/**
- * i40e_shutdown_asq - shutdown the ASQ
+ * iavf_shutdown_asq - shutdown the ASQ
* @hw: pointer to the hardware structure
*
* The main shutdown routine for the Admin Send Queue
**/
-static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
+static enum iavf_status iavf_shutdown_asq(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
mutex_lock(&hw->aq.asq_mutex);
if (hw->aq.asq.count == 0) {
- ret_code = I40E_ERR_NOT_READY;
+ ret_code = IAVF_ERR_NOT_READY;
goto shutdown_asq_out;
}
@@ -463,7 +453,7 @@
hw->aq.asq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
- i40e_free_asq_bufs(hw);
+ iavf_free_asq_bufs(hw);
shutdown_asq_out:
mutex_unlock(&hw->aq.asq_mutex);
@@ -471,19 +461,19 @@
}
/**
- * i40e_shutdown_arq - shutdown ARQ
+ * iavf_shutdown_arq - shutdown ARQ
* @hw: pointer to the hardware structure
*
* The main shutdown routine for the Admin Receive Queue
**/
-static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
+static enum iavf_status iavf_shutdown_arq(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
mutex_lock(&hw->aq.arq_mutex);
if (hw->aq.arq.count == 0) {
- ret_code = I40E_ERR_NOT_READY;
+ ret_code = IAVF_ERR_NOT_READY;
goto shutdown_arq_out;
}
@@ -497,7 +487,7 @@
hw->aq.arq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
- i40e_free_arq_bufs(hw);
+ iavf_free_arq_bufs(hw);
shutdown_arq_out:
mutex_unlock(&hw->aq.arq_mutex);
@@ -505,7 +495,7 @@
}
/**
- * i40evf_init_adminq - main initialization routine for Admin Queue
+ * iavf_init_adminq - main initialization routine for Admin Queue
* @hw: pointer to the hardware structure
*
* Prior to calling this function, drivers *MUST* set the following fields
@@ -515,32 +505,32 @@
* - hw->aq.arq_buf_size
* - hw->aq.asq_buf_size
**/
-i40e_status i40evf_init_adminq(struct i40e_hw *hw)
+enum iavf_status iavf_init_adminq(struct iavf_hw *hw)
{
- i40e_status ret_code;
+ enum iavf_status ret_code;
/* verify input for valid configuration */
if ((hw->aq.num_arq_entries == 0) ||
(hw->aq.num_asq_entries == 0) ||
(hw->aq.arq_buf_size == 0) ||
(hw->aq.asq_buf_size == 0)) {
- ret_code = I40E_ERR_CONFIG;
+ ret_code = IAVF_ERR_CONFIG;
goto init_adminq_exit;
}
/* Set up register offsets */
- i40e_adminq_init_regs(hw);
+ iavf_adminq_init_regs(hw);
/* setup ASQ command write back timeout */
- hw->aq.asq_cmd_timeout = I40E_ASQ_CMD_TIMEOUT;
+ hw->aq.asq_cmd_timeout = IAVF_ASQ_CMD_TIMEOUT;
/* allocate the ASQ */
- ret_code = i40e_init_asq(hw);
+ ret_code = iavf_init_asq(hw);
if (ret_code)
goto init_adminq_destroy_locks;
/* allocate the ARQ */
- ret_code = i40e_init_arq(hw);
+ ret_code = iavf_init_arq(hw);
if (ret_code)
goto init_adminq_free_asq;
@@ -548,7 +538,7 @@
goto init_adminq_exit;
init_adminq_free_asq:
- i40e_shutdown_asq(hw);
+ iavf_shutdown_asq(hw);
init_adminq_destroy_locks:
init_adminq_exit:
@@ -556,84 +546,80 @@
}
/**
- * i40evf_shutdown_adminq - shutdown routine for the Admin Queue
+ * iavf_shutdown_adminq - shutdown routine for the Admin Queue
* @hw: pointer to the hardware structure
**/
-i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw)
+enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw)
{
- i40e_status ret_code = 0;
+ enum iavf_status ret_code = 0;
- if (i40evf_check_asq_alive(hw))
- i40evf_aq_queue_shutdown(hw, true);
+ if (iavf_check_asq_alive(hw))
+ iavf_aq_queue_shutdown(hw, true);
- i40e_shutdown_asq(hw);
- i40e_shutdown_arq(hw);
-
- if (hw->nvm_buff.va)
- i40e_free_virt_mem(hw, &hw->nvm_buff);
+ iavf_shutdown_asq(hw);
+ iavf_shutdown_arq(hw);
return ret_code;
}
/**
- * i40e_clean_asq - cleans Admin send queue
+ * iavf_clean_asq - cleans Admin send queue
* @hw: pointer to the hardware structure
*
* returns the number of free desc
**/
-static u16 i40e_clean_asq(struct i40e_hw *hw)
+static u16 iavf_clean_asq(struct iavf_hw *hw)
{
- struct i40e_adminq_ring *asq = &(hw->aq.asq);
- struct i40e_asq_cmd_details *details;
+ struct iavf_adminq_ring *asq = &hw->aq.asq;
+ struct iavf_asq_cmd_details *details;
u16 ntc = asq->next_to_clean;
- struct i40e_aq_desc desc_cb;
- struct i40e_aq_desc *desc;
+ struct iavf_aq_desc desc_cb;
+ struct iavf_aq_desc *desc;
- desc = I40E_ADMINQ_DESC(*asq, ntc);
- details = I40E_ADMINQ_DETAILS(*asq, ntc);
+ desc = IAVF_ADMINQ_DESC(*asq, ntc);
+ details = IAVF_ADMINQ_DETAILS(*asq, ntc);
while (rd32(hw, hw->aq.asq.head) != ntc) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
if (details->callback) {
- I40E_ADMINQ_CALLBACK cb_func =
- (I40E_ADMINQ_CALLBACK)details->callback;
+ IAVF_ADMINQ_CALLBACK cb_func =
+ (IAVF_ADMINQ_CALLBACK)details->callback;
desc_cb = *desc;
cb_func(hw, &desc_cb);
}
- memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+ memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
memset((void *)details, 0,
- sizeof(struct i40e_asq_cmd_details));
+ sizeof(struct iavf_asq_cmd_details));
ntc++;
if (ntc == asq->count)
ntc = 0;
- desc = I40E_ADMINQ_DESC(*asq, ntc);
- details = I40E_ADMINQ_DETAILS(*asq, ntc);
+ desc = IAVF_ADMINQ_DESC(*asq, ntc);
+ details = IAVF_ADMINQ_DETAILS(*asq, ntc);
}
asq->next_to_clean = ntc;
- return I40E_DESC_UNUSED(asq);
+ return IAVF_DESC_UNUSED(asq);
}
/**
- * i40evf_asq_done - check if FW has processed the Admin Send Queue
+ * iavf_asq_done - check if FW has processed the Admin Send Queue
* @hw: pointer to the hw struct
*
* Returns true if the firmware has processed all descriptors on the
* admin send queue. Returns false if there are still requests pending.
**/
-bool i40evf_asq_done(struct i40e_hw *hw)
+bool iavf_asq_done(struct iavf_hw *hw)
{
/* AQ designers suggest use of head for better
* timing reliability than DD bit
*/
return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use;
-
}
/**
- * i40evf_asq_send_command - send command to Admin Queue
+ * iavf_asq_send_command - send command to Admin Queue
* @hw: pointer to the hw struct
* @desc: prefilled descriptor describing the command (non DMA mem)
* @buff: buffer to use for indirect commands
@@ -643,40 +629,40 @@
* This is the main send command driver routine for the Admin Queue send
* queue. It runs the queue, cleans the queue, etc
**/
-i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
- struct i40e_aq_desc *desc,
- void *buff, /* can be NULL */
- u16 buff_size,
- struct i40e_asq_cmd_details *cmd_details)
+enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
+ struct iavf_aq_desc *desc,
+ void *buff, /* can be NULL */
+ u16 buff_size,
+ struct iavf_asq_cmd_details *cmd_details)
{
- i40e_status status = 0;
- struct i40e_dma_mem *dma_buff = NULL;
- struct i40e_asq_cmd_details *details;
- struct i40e_aq_desc *desc_on_ring;
+ struct iavf_dma_mem *dma_buff = NULL;
+ struct iavf_asq_cmd_details *details;
+ struct iavf_aq_desc *desc_on_ring;
bool cmd_completed = false;
+ enum iavf_status status = 0;
u16 retval = 0;
u32 val = 0;
mutex_lock(&hw->aq.asq_mutex);
if (hw->aq.asq.count == 0) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Admin queue not initialized.\n");
- status = I40E_ERR_QUEUE_EMPTY;
+ status = IAVF_ERR_QUEUE_EMPTY;
goto asq_send_command_error;
}
- hw->aq.asq_last_status = I40E_AQ_RC_OK;
+ hw->aq.asq_last_status = IAVF_AQ_RC_OK;
val = rd32(hw, hw->aq.asq.head);
if (val >= hw->aq.num_asq_entries) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQTX: head overrun at %d\n", val);
- status = I40E_ERR_QUEUE_EMPTY;
+ status = IAVF_ERR_QUEUE_EMPTY;
goto asq_send_command_error;
}
- details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
+ details = IAVF_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
if (cmd_details) {
*details = *cmd_details;
@@ -691,7 +677,7 @@
cpu_to_le32(lower_32_bits(details->cookie));
}
} else {
- memset(details, 0, sizeof(struct i40e_asq_cmd_details));
+ memset(details, 0, sizeof(struct iavf_asq_cmd_details));
}
/* clear requested flags and then set additional flags if defined */
@@ -699,19 +685,19 @@
desc->flags |= cpu_to_le16(details->flags_ena);
if (buff_size > hw->aq.asq_buf_size) {
- i40e_debug(hw,
- I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw,
+ IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Invalid buffer size: %d.\n",
buff_size);
- status = I40E_ERR_INVALID_SIZE;
+ status = IAVF_ERR_INVALID_SIZE;
goto asq_send_command_error;
}
if (details->postpone && !details->async) {
- i40e_debug(hw,
- I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw,
+ IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Async flag not set along with postpone flag");
- status = I40E_ERR_PARAM;
+ status = IAVF_ERR_PARAM;
goto asq_send_command_error;
}
@@ -722,23 +708,23 @@
/* the clean function called here could be called in a separate thread
* in case of asynchronous completions
*/
- if (i40e_clean_asq(hw) == 0) {
- i40e_debug(hw,
- I40E_DEBUG_AQ_MESSAGE,
+ if (iavf_clean_asq(hw) == 0) {
+ iavf_debug(hw,
+ IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Error queue is full.\n");
- status = I40E_ERR_ADMIN_QUEUE_FULL;
+ status = IAVF_ERR_ADMIN_QUEUE_FULL;
goto asq_send_command_error;
}
/* initialize the temp desc pointer with the right desc */
- desc_on_ring = I40E_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use);
+ desc_on_ring = IAVF_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use);
/* if the desc is available copy the temp desc to the right place */
*desc_on_ring = *desc;
/* if buff is not NULL assume indirect command */
- if (buff != NULL) {
- dma_buff = &(hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]);
+ if (buff) {
+ dma_buff = &hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use];
/* copy the user buff into the respective DMA buff */
memcpy(dma_buff->va, buff, buff_size);
desc_on_ring->datalen = cpu_to_le16(buff_size);
@@ -753,9 +739,9 @@
}
/* bump the tail */
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n");
- i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring,
- buff, buff_size);
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n");
+ iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc_on_ring,
+ buff, buff_size);
(hw->aq.asq.next_to_use)++;
if (hw->aq.asq.next_to_use == hw->aq.asq.count)
hw->aq.asq.next_to_use = 0;
@@ -772,7 +758,7 @@
/* AQ designers suggest use of head for better
* timing reliability than DD bit
*/
- if (i40evf_asq_done(hw))
+ if (iavf_asq_done(hw))
break;
udelay(50);
total_delay += 50;
@@ -780,14 +766,14 @@
}
/* if ready, copy the desc back to temp */
- if (i40evf_asq_done(hw)) {
+ if (iavf_asq_done(hw)) {
*desc = *desc_on_ring;
- if (buff != NULL)
+ if (buff)
memcpy(buff, dma_buff->va, buff_size);
retval = le16_to_cpu(desc->retval);
if (retval != 0) {
- i40e_debug(hw,
- I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw,
+ IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Command completed with error 0x%X.\n",
retval);
@@ -795,19 +781,18 @@
retval &= 0xff;
}
cmd_completed = true;
- if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
+ if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_OK)
status = 0;
- else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
- status = I40E_ERR_NOT_READY;
+ else if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_EBUSY)
+ status = IAVF_ERR_NOT_READY;
else
- status = I40E_ERR_ADMIN_QUEUE_ERROR;
- hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
+ status = IAVF_ERR_ADMIN_QUEUE_ERROR;
+ hw->aq.asq_last_status = (enum iavf_admin_queue_err)retval;
}
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQTX: desc and buffer writeback:\n");
- i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff,
- buff_size);
+ iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size);
/* save writeback aq if requested */
if (details->wb_desc)
@@ -816,14 +801,14 @@
/* update the error if time out occurred */
if ((!cmd_completed) &&
(!details->async && !details->postpone)) {
- if (rd32(hw, hw->aq.asq.len) & I40E_VF_ATQLEN1_ATQCRIT_MASK) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) {
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQTX: AQ Critical error.\n");
- status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
+ status = IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
} else {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQTX: Writeback timeout.\n");
- status = I40E_ERR_ADMIN_QUEUE_TIMEOUT;
+ status = IAVF_ERR_ADMIN_QUEUE_TIMEOUT;
}
}
@@ -833,23 +818,22 @@
}
/**
- * i40evf_fill_default_direct_cmd_desc - AQ descriptor helper function
+ * iavf_fill_default_direct_cmd_desc - AQ descriptor helper function
* @desc: pointer to the temp descriptor (non DMA mem)
* @opcode: the opcode can be used to decide which flags to turn off or on
*
* Fill the desc with default values
**/
-void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
- u16 opcode)
+void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode)
{
/* zero out the desc */
- memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+ memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
desc->opcode = cpu_to_le16(opcode);
- desc->flags = cpu_to_le16(I40E_AQ_FLAG_SI);
+ desc->flags = cpu_to_le16(IAVF_AQ_FLAG_SI);
}
/**
- * i40evf_clean_arq_element
+ * iavf_clean_arq_element
* @hw: pointer to the hw struct
* @e: event info from the receive descriptor, includes any buffers
* @pending: number of events that could be left to process
@@ -858,14 +842,14 @@
* the contents through e. It can also return how many events are
* left to process through 'pending'
**/
-i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
- struct i40e_arq_event_info *e,
- u16 *pending)
+enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
+ struct iavf_arq_event_info *e,
+ u16 *pending)
{
- i40e_status ret_code = 0;
u16 ntc = hw->aq.arq.next_to_clean;
- struct i40e_aq_desc *desc;
- struct i40e_dma_mem *bi;
+ struct iavf_aq_desc *desc;
+ enum iavf_status ret_code = 0;
+ struct iavf_dma_mem *bi;
u16 desc_idx;
u16 datalen;
u16 flags;
@@ -878,31 +862,31 @@
mutex_lock(&hw->aq.arq_mutex);
if (hw->aq.arq.count == 0) {
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
"AQRX: Admin queue not initialized.\n");
- ret_code = I40E_ERR_QUEUE_EMPTY;
+ ret_code = IAVF_ERR_QUEUE_EMPTY;
goto clean_arq_element_err;
}
/* set next_to_use to head */
- ntu = rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK;
+ ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK;
if (ntu == ntc) {
/* nothing to do - shouldn't need to update ring's values */
- ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK;
+ ret_code = IAVF_ERR_ADMIN_QUEUE_NO_WORK;
goto clean_arq_element_out;
}
/* now clean the next descriptor */
- desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc);
+ desc = IAVF_ADMINQ_DESC(hw->aq.arq, ntc);
desc_idx = ntc;
hw->aq.arq_last_status =
- (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
+ (enum iavf_admin_queue_err)le16_to_cpu(desc->retval);
flags = le16_to_cpu(desc->flags);
- if (flags & I40E_AQ_FLAG_ERR) {
- ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
- i40e_debug(hw,
- I40E_DEBUG_AQ_MESSAGE,
+ if (flags & IAVF_AQ_FLAG_ERR) {
+ ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
+ iavf_debug(hw,
+ IAVF_DEBUG_AQ_MESSAGE,
"AQRX: Event received with error 0x%X.\n",
hw->aq.arq_last_status);
}
@@ -910,24 +894,24 @@
e->desc = *desc;
datalen = le16_to_cpu(desc->datalen);
e->msg_len = min(datalen, e->buf_len);
- if (e->msg_buf != NULL && (e->msg_len != 0))
+ if (e->msg_buf && (e->msg_len != 0))
memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
e->msg_len);
- i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
- i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf,
- hw->aq.arq_buf_size);
+ iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
+ iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf,
+ hw->aq.arq_buf_size);
/* Restore the original datalen and buffer address in the desc,
* FW updates datalen to indicate the event message
* size
*/
bi = &hw->aq.arq.r.arq_bi[ntc];
- memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+ memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
- desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
- if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
- desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+ desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+ if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
+ desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
desc->datalen = cpu_to_le16((u16)bi->size);
desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
@@ -943,7 +927,7 @@
clean_arq_element_out:
/* Set pending if needed, unlock and return */
- if (pending != NULL)
+ if (pending)
*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
clean_arq_element_err:
@@ -951,17 +935,3 @@
return ret_code;
}
-
-void i40evf_resume_aq(struct i40e_hw *hw)
-{
- /* Registers are reset after PF reset */
- hw->aq.asq.next_to_use = 0;
- hw->aq.asq.next_to_clean = 0;
-
- i40e_config_asq_regs(hw);
-
- hw->aq.arq.next_to_use = 0;
- hw->aq.arq.next_to_clean = 0;
-
- i40e_config_arq_regs(hw);
-}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.h b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
new file mode 100644
index 0000000..baf2fe2
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_ADMINQ_H_
+#define _IAVF_ADMINQ_H_
+
+#include "iavf_osdep.h"
+#include "iavf_status.h"
+#include "iavf_adminq_cmd.h"
+
+#define IAVF_ADMINQ_DESC(R, i) \
+ (&(((struct iavf_aq_desc *)((R).desc_buf.va))[i]))
+
+#define IAVF_ADMINQ_DESC_ALIGNMENT 4096
+
+struct iavf_adminq_ring {
+ struct iavf_virt_mem dma_head; /* space for dma structures */
+ struct iavf_dma_mem desc_buf; /* descriptor ring memory */
+ struct iavf_virt_mem cmd_buf; /* command buffer memory */
+
+ union {
+ struct iavf_dma_mem *asq_bi;
+ struct iavf_dma_mem *arq_bi;
+ } r;
+
+ u16 count; /* Number of descriptors */
+ u16 rx_buf_len; /* Admin Receive Queue buffer length */
+
+ /* used for interrupt processing */
+ u16 next_to_use;
+ u16 next_to_clean;
+
+ /* used for queue tracking */
+ u32 head;
+ u32 tail;
+ u32 len;
+ u32 bah;
+ u32 bal;
+};
+
+/* ASQ transaction details */
+struct iavf_asq_cmd_details {
+ void *callback; /* cast from type IAVF_ADMINQ_CALLBACK */
+ u64 cookie;
+ u16 flags_ena;
+ u16 flags_dis;
+ bool async;
+ bool postpone;
+ struct iavf_aq_desc *wb_desc;
+};
+
+#define IAVF_ADMINQ_DETAILS(R, i) \
+ (&(((struct iavf_asq_cmd_details *)((R).cmd_buf.va))[i]))
+
+/* ARQ event information */
+struct iavf_arq_event_info {
+ struct iavf_aq_desc desc;
+ u16 msg_len;
+ u16 buf_len;
+ u8 *msg_buf;
+};
+
+/* Admin Queue information */
+struct iavf_adminq_info {
+ struct iavf_adminq_ring arq; /* receive queue */
+ struct iavf_adminq_ring asq; /* send queue */
+ u32 asq_cmd_timeout; /* send queue cmd write back timeout*/
+ u16 num_arq_entries; /* receive queue depth */
+ u16 num_asq_entries; /* send queue depth */
+ u16 arq_buf_size; /* receive queue buffer size */
+ u16 asq_buf_size; /* send queue buffer size */
+ u16 fw_maj_ver; /* firmware major version */
+ u16 fw_min_ver; /* firmware minor version */
+ u32 fw_build; /* firmware build number */
+ u16 api_maj_ver; /* api major version */
+ u16 api_min_ver; /* api minor version */
+
+ struct mutex asq_mutex; /* Send queue lock */
+ struct mutex arq_mutex; /* Receive queue lock */
+
+ /* last status values on send and receive queues */
+ enum iavf_admin_queue_err asq_last_status;
+ enum iavf_admin_queue_err arq_last_status;
+};
+
+/**
+ * iavf_aq_rc_to_posix - convert errors to user-land codes
+ * aq_ret: AdminQ handler error code can override aq_rc
+ * aq_rc: AdminQ firmware error code to convert
+ **/
+static inline int iavf_aq_rc_to_posix(int aq_ret, int aq_rc)
+{
+ int aq_to_posix[] = {
+ 0, /* IAVF_AQ_RC_OK */
+ -EPERM, /* IAVF_AQ_RC_EPERM */
+ -ENOENT, /* IAVF_AQ_RC_ENOENT */
+ -ESRCH, /* IAVF_AQ_RC_ESRCH */
+ -EINTR, /* IAVF_AQ_RC_EINTR */
+ -EIO, /* IAVF_AQ_RC_EIO */
+ -ENXIO, /* IAVF_AQ_RC_ENXIO */
+ -E2BIG, /* IAVF_AQ_RC_E2BIG */
+ -EAGAIN, /* IAVF_AQ_RC_EAGAIN */
+ -ENOMEM, /* IAVF_AQ_RC_ENOMEM */
+ -EACCES, /* IAVF_AQ_RC_EACCES */
+ -EFAULT, /* IAVF_AQ_RC_EFAULT */
+ -EBUSY, /* IAVF_AQ_RC_EBUSY */
+ -EEXIST, /* IAVF_AQ_RC_EEXIST */
+ -EINVAL, /* IAVF_AQ_RC_EINVAL */
+ -ENOTTY, /* IAVF_AQ_RC_ENOTTY */
+ -ENOSPC, /* IAVF_AQ_RC_ENOSPC */
+ -ENOSYS, /* IAVF_AQ_RC_ENOSYS */
+ -ERANGE, /* IAVF_AQ_RC_ERANGE */
+ -EPIPE, /* IAVF_AQ_RC_EFLUSHED */
+ -ESPIPE, /* IAVF_AQ_RC_BAD_ADDR */
+ -EROFS, /* IAVF_AQ_RC_EMODE */
+ -EFBIG, /* IAVF_AQ_RC_EFBIG */
+ };
+
+ /* aq_rc is invalid if AQ timed out */
+ if (aq_ret == IAVF_ERR_ADMIN_QUEUE_TIMEOUT)
+ return -EAGAIN;
+
+ if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0]))))
+ return -ERANGE;
+
+ return aq_to_posix[aq_rc];
+}
+
+/* general information */
+#define IAVF_AQ_LARGE_BUF 512
+#define IAVF_ASQ_CMD_TIMEOUT 250000 /* usecs */
+
+void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode);
+
+#endif /* _IAVF_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
new file mode 100644
index 0000000..bc51230
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
@@ -0,0 +1,528 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_ADMINQ_CMD_H_
+#define _IAVF_ADMINQ_CMD_H_
+
+/* This header file defines the iavf Admin Queue commands and is shared between
+ * iavf Firmware and Software.
+ *
+ * This file needs to comply with the Linux Kernel coding style.
+ */
+
+#define IAVF_FW_API_VERSION_MAJOR 0x0001
+#define IAVF_FW_API_VERSION_MINOR_X722 0x0005
+#define IAVF_FW_API_VERSION_MINOR_X710 0x0008
+
+#define IAVF_FW_MINOR_VERSION(_h) ((_h)->mac.type == IAVF_MAC_XL710 ? \
+ IAVF_FW_API_VERSION_MINOR_X710 : \
+ IAVF_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs */
+#define IAVF_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+
+struct iavf_aq_desc {
+ __le16 flags;
+ __le16 opcode;
+ __le16 datalen;
+ __le16 retval;
+ __le32 cookie_high;
+ __le32 cookie_low;
+ union {
+ struct {
+ __le32 param0;
+ __le32 param1;
+ __le32 param2;
+ __le32 param3;
+ } internal;
+ struct {
+ __le32 param0;
+ __le32 param1;
+ __le32 addr_high;
+ __le32 addr_low;
+ } external;
+ u8 raw[16];
+ } params;
+};
+
+/* Flags sub-structure
+ * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
+
+/* command flags and offsets*/
+#define IAVF_AQ_FLAG_DD_SHIFT 0
+#define IAVF_AQ_FLAG_CMP_SHIFT 1
+#define IAVF_AQ_FLAG_ERR_SHIFT 2
+#define IAVF_AQ_FLAG_VFE_SHIFT 3
+#define IAVF_AQ_FLAG_LB_SHIFT 9
+#define IAVF_AQ_FLAG_RD_SHIFT 10
+#define IAVF_AQ_FLAG_VFC_SHIFT 11
+#define IAVF_AQ_FLAG_BUF_SHIFT 12
+#define IAVF_AQ_FLAG_SI_SHIFT 13
+#define IAVF_AQ_FLAG_EI_SHIFT 14
+#define IAVF_AQ_FLAG_FE_SHIFT 15
+
+#define IAVF_AQ_FLAG_DD BIT(IAVF_AQ_FLAG_DD_SHIFT) /* 0x1 */
+#define IAVF_AQ_FLAG_CMP BIT(IAVF_AQ_FLAG_CMP_SHIFT) /* 0x2 */
+#define IAVF_AQ_FLAG_ERR BIT(IAVF_AQ_FLAG_ERR_SHIFT) /* 0x4 */
+#define IAVF_AQ_FLAG_VFE BIT(IAVF_AQ_FLAG_VFE_SHIFT) /* 0x8 */
+#define IAVF_AQ_FLAG_LB BIT(IAVF_AQ_FLAG_LB_SHIFT) /* 0x200 */
+#define IAVF_AQ_FLAG_RD BIT(IAVF_AQ_FLAG_RD_SHIFT) /* 0x400 */
+#define IAVF_AQ_FLAG_VFC BIT(IAVF_AQ_FLAG_VFC_SHIFT) /* 0x800 */
+#define IAVF_AQ_FLAG_BUF BIT(IAVF_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
+#define IAVF_AQ_FLAG_SI BIT(IAVF_AQ_FLAG_SI_SHIFT) /* 0x2000 */
+#define IAVF_AQ_FLAG_EI BIT(IAVF_AQ_FLAG_EI_SHIFT) /* 0x4000 */
+#define IAVF_AQ_FLAG_FE BIT(IAVF_AQ_FLAG_FE_SHIFT) /* 0x8000 */
+
+/* error codes */
+enum iavf_admin_queue_err {
+ IAVF_AQ_RC_OK = 0, /* success */
+ IAVF_AQ_RC_EPERM = 1, /* Operation not permitted */
+ IAVF_AQ_RC_ENOENT = 2, /* No such element */
+ IAVF_AQ_RC_ESRCH = 3, /* Bad opcode */
+ IAVF_AQ_RC_EINTR = 4, /* operation interrupted */
+ IAVF_AQ_RC_EIO = 5, /* I/O error */
+ IAVF_AQ_RC_ENXIO = 6, /* No such resource */
+ IAVF_AQ_RC_E2BIG = 7, /* Arg too long */
+ IAVF_AQ_RC_EAGAIN = 8, /* Try again */
+ IAVF_AQ_RC_ENOMEM = 9, /* Out of memory */
+ IAVF_AQ_RC_EACCES = 10, /* Permission denied */
+ IAVF_AQ_RC_EFAULT = 11, /* Bad address */
+ IAVF_AQ_RC_EBUSY = 12, /* Device or resource busy */
+ IAVF_AQ_RC_EEXIST = 13, /* object already exists */
+ IAVF_AQ_RC_EINVAL = 14, /* Invalid argument */
+ IAVF_AQ_RC_ENOTTY = 15, /* Not a typewriter */
+ IAVF_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */
+ IAVF_AQ_RC_ENOSYS = 17, /* Function not implemented */
+ IAVF_AQ_RC_ERANGE = 18, /* Parameter out of range */
+ IAVF_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */
+ IAVF_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */
+ IAVF_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */
+ IAVF_AQ_RC_EFBIG = 22, /* File too large */
+};
+
+/* Admin Queue command opcodes */
+enum iavf_admin_queue_opc {
+ /* aq commands */
+ iavf_aqc_opc_get_version = 0x0001,
+ iavf_aqc_opc_driver_version = 0x0002,
+ iavf_aqc_opc_queue_shutdown = 0x0003,
+ iavf_aqc_opc_set_pf_context = 0x0004,
+
+ /* resource ownership */
+ iavf_aqc_opc_request_resource = 0x0008,
+ iavf_aqc_opc_release_resource = 0x0009,
+
+ iavf_aqc_opc_list_func_capabilities = 0x000A,
+ iavf_aqc_opc_list_dev_capabilities = 0x000B,
+
+ /* Proxy commands */
+ iavf_aqc_opc_set_proxy_config = 0x0104,
+ iavf_aqc_opc_set_ns_proxy_table_entry = 0x0105,
+
+ /* LAA */
+ iavf_aqc_opc_mac_address_read = 0x0107,
+ iavf_aqc_opc_mac_address_write = 0x0108,
+
+ /* PXE */
+ iavf_aqc_opc_clear_pxe_mode = 0x0110,
+
+ /* WoL commands */
+ iavf_aqc_opc_set_wol_filter = 0x0120,
+ iavf_aqc_opc_get_wake_reason = 0x0121,
+
+ /* internal switch commands */
+ iavf_aqc_opc_get_switch_config = 0x0200,
+ iavf_aqc_opc_add_statistics = 0x0201,
+ iavf_aqc_opc_remove_statistics = 0x0202,
+ iavf_aqc_opc_set_port_parameters = 0x0203,
+ iavf_aqc_opc_get_switch_resource_alloc = 0x0204,
+ iavf_aqc_opc_set_switch_config = 0x0205,
+ iavf_aqc_opc_rx_ctl_reg_read = 0x0206,
+ iavf_aqc_opc_rx_ctl_reg_write = 0x0207,
+
+ iavf_aqc_opc_add_vsi = 0x0210,
+ iavf_aqc_opc_update_vsi_parameters = 0x0211,
+ iavf_aqc_opc_get_vsi_parameters = 0x0212,
+
+ iavf_aqc_opc_add_pv = 0x0220,
+ iavf_aqc_opc_update_pv_parameters = 0x0221,
+ iavf_aqc_opc_get_pv_parameters = 0x0222,
+
+ iavf_aqc_opc_add_veb = 0x0230,
+ iavf_aqc_opc_update_veb_parameters = 0x0231,
+ iavf_aqc_opc_get_veb_parameters = 0x0232,
+
+ iavf_aqc_opc_delete_element = 0x0243,
+
+ iavf_aqc_opc_add_macvlan = 0x0250,
+ iavf_aqc_opc_remove_macvlan = 0x0251,
+ iavf_aqc_opc_add_vlan = 0x0252,
+ iavf_aqc_opc_remove_vlan = 0x0253,
+ iavf_aqc_opc_set_vsi_promiscuous_modes = 0x0254,
+ iavf_aqc_opc_add_tag = 0x0255,
+ iavf_aqc_opc_remove_tag = 0x0256,
+ iavf_aqc_opc_add_multicast_etag = 0x0257,
+ iavf_aqc_opc_remove_multicast_etag = 0x0258,
+ iavf_aqc_opc_update_tag = 0x0259,
+ iavf_aqc_opc_add_control_packet_filter = 0x025A,
+ iavf_aqc_opc_remove_control_packet_filter = 0x025B,
+ iavf_aqc_opc_add_cloud_filters = 0x025C,
+ iavf_aqc_opc_remove_cloud_filters = 0x025D,
+ iavf_aqc_opc_clear_wol_switch_filters = 0x025E,
+
+ iavf_aqc_opc_add_mirror_rule = 0x0260,
+ iavf_aqc_opc_delete_mirror_rule = 0x0261,
+
+ /* Dynamic Device Personalization */
+ iavf_aqc_opc_write_personalization_profile = 0x0270,
+ iavf_aqc_opc_get_personalization_profile_list = 0x0271,
+
+ /* DCB commands */
+ iavf_aqc_opc_dcb_ignore_pfc = 0x0301,
+ iavf_aqc_opc_dcb_updated = 0x0302,
+ iavf_aqc_opc_set_dcb_parameters = 0x0303,
+
+ /* TX scheduler */
+ iavf_aqc_opc_configure_vsi_bw_limit = 0x0400,
+ iavf_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406,
+ iavf_aqc_opc_configure_vsi_tc_bw = 0x0407,
+ iavf_aqc_opc_query_vsi_bw_config = 0x0408,
+ iavf_aqc_opc_query_vsi_ets_sla_config = 0x040A,
+ iavf_aqc_opc_configure_switching_comp_bw_limit = 0x0410,
+
+ iavf_aqc_opc_enable_switching_comp_ets = 0x0413,
+ iavf_aqc_opc_modify_switching_comp_ets = 0x0414,
+ iavf_aqc_opc_disable_switching_comp_ets = 0x0415,
+ iavf_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416,
+ iavf_aqc_opc_configure_switching_comp_bw_config = 0x0417,
+ iavf_aqc_opc_query_switching_comp_ets_config = 0x0418,
+ iavf_aqc_opc_query_port_ets_config = 0x0419,
+ iavf_aqc_opc_query_switching_comp_bw_config = 0x041A,
+ iavf_aqc_opc_suspend_port_tx = 0x041B,
+ iavf_aqc_opc_resume_port_tx = 0x041C,
+ iavf_aqc_opc_configure_partition_bw = 0x041D,
+ /* hmc */
+ iavf_aqc_opc_query_hmc_resource_profile = 0x0500,
+ iavf_aqc_opc_set_hmc_resource_profile = 0x0501,
+
+ /* phy commands*/
+ iavf_aqc_opc_get_phy_abilities = 0x0600,
+ iavf_aqc_opc_set_phy_config = 0x0601,
+ iavf_aqc_opc_set_mac_config = 0x0603,
+ iavf_aqc_opc_set_link_restart_an = 0x0605,
+ iavf_aqc_opc_get_link_status = 0x0607,
+ iavf_aqc_opc_set_phy_int_mask = 0x0613,
+ iavf_aqc_opc_get_local_advt_reg = 0x0614,
+ iavf_aqc_opc_set_local_advt_reg = 0x0615,
+ iavf_aqc_opc_get_partner_advt = 0x0616,
+ iavf_aqc_opc_set_lb_modes = 0x0618,
+ iavf_aqc_opc_get_phy_wol_caps = 0x0621,
+ iavf_aqc_opc_set_phy_debug = 0x0622,
+ iavf_aqc_opc_upload_ext_phy_fm = 0x0625,
+ iavf_aqc_opc_run_phy_activity = 0x0626,
+ iavf_aqc_opc_set_phy_register = 0x0628,
+ iavf_aqc_opc_get_phy_register = 0x0629,
+
+ /* NVM commands */
+ iavf_aqc_opc_nvm_read = 0x0701,
+ iavf_aqc_opc_nvm_erase = 0x0702,
+ iavf_aqc_opc_nvm_update = 0x0703,
+ iavf_aqc_opc_nvm_config_read = 0x0704,
+ iavf_aqc_opc_nvm_config_write = 0x0705,
+ iavf_aqc_opc_oem_post_update = 0x0720,
+ iavf_aqc_opc_thermal_sensor = 0x0721,
+
+ /* virtualization commands */
+ iavf_aqc_opc_send_msg_to_pf = 0x0801,
+ iavf_aqc_opc_send_msg_to_vf = 0x0802,
+ iavf_aqc_opc_send_msg_to_peer = 0x0803,
+
+ /* alternate structure */
+ iavf_aqc_opc_alternate_write = 0x0900,
+ iavf_aqc_opc_alternate_write_indirect = 0x0901,
+ iavf_aqc_opc_alternate_read = 0x0902,
+ iavf_aqc_opc_alternate_read_indirect = 0x0903,
+ iavf_aqc_opc_alternate_write_done = 0x0904,
+ iavf_aqc_opc_alternate_set_mode = 0x0905,
+ iavf_aqc_opc_alternate_clear_port = 0x0906,
+
+ /* LLDP commands */
+ iavf_aqc_opc_lldp_get_mib = 0x0A00,
+ iavf_aqc_opc_lldp_update_mib = 0x0A01,
+ iavf_aqc_opc_lldp_add_tlv = 0x0A02,
+ iavf_aqc_opc_lldp_update_tlv = 0x0A03,
+ iavf_aqc_opc_lldp_delete_tlv = 0x0A04,
+ iavf_aqc_opc_lldp_stop = 0x0A05,
+ iavf_aqc_opc_lldp_start = 0x0A06,
+
+ /* Tunnel commands */
+ iavf_aqc_opc_add_udp_tunnel = 0x0B00,
+ iavf_aqc_opc_del_udp_tunnel = 0x0B01,
+ iavf_aqc_opc_set_rss_key = 0x0B02,
+ iavf_aqc_opc_set_rss_lut = 0x0B03,
+ iavf_aqc_opc_get_rss_key = 0x0B04,
+ iavf_aqc_opc_get_rss_lut = 0x0B05,
+
+ /* Async Events */
+ iavf_aqc_opc_event_lan_overflow = 0x1001,
+
+ /* OEM commands */
+ iavf_aqc_opc_oem_parameter_change = 0xFE00,
+ iavf_aqc_opc_oem_device_status_change = 0xFE01,
+ iavf_aqc_opc_oem_ocsd_initialize = 0xFE02,
+ iavf_aqc_opc_oem_ocbb_initialize = 0xFE03,
+
+ /* debug commands */
+ iavf_aqc_opc_debug_read_reg = 0xFF03,
+ iavf_aqc_opc_debug_write_reg = 0xFF04,
+ iavf_aqc_opc_debug_modify_reg = 0xFF07,
+ iavf_aqc_opc_debug_dump_internals = 0xFF08,
+};
+
+/* command structures and indirect data structures */
+
+/* Structure naming conventions:
+ * - no suffix for direct command descriptor structures
+ * - _data for indirect sent data
+ * - _resp for indirect return data (data which is both will use _data)
+ * - _completion for direct return data
+ * - _element_ for repeated elements (may also be _data or _resp)
+ *
+ * Command structures are expected to overlay the params.raw member of the basic
+ * descriptor, and as such cannot exceed 16 bytes in length.
+ */
+
+/* This macro is used to generate a compilation error if a structure
+ * is not exactly the correct length. It gives a divide by zero error if the
+ * structure is not of the correct size, otherwise it creates an enum that is
+ * never used.
+ */
+#define IAVF_CHECK_STRUCT_LEN(n, X) enum iavf_static_assert_enum_##X \
+ { iavf_static_assert_##X = (n) / ((sizeof(struct X) == (n)) ? 1 : 0) }
+
+/* This macro is used extensively to ensure that command structures are 16
+ * bytes in length as they have to map to the raw array of that size.
+ */
+#define IAVF_CHECK_CMD_LENGTH(X) IAVF_CHECK_STRUCT_LEN(16, X)
+
+/* Queue Shutdown (direct 0x0003) */
+struct iavf_aqc_queue_shutdown {
+ __le32 driver_unloading;
+#define IAVF_AQ_DRIVER_UNLOADING 0x1
+ u8 reserved[12];
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_queue_shutdown);
+
+struct iavf_aqc_vsi_properties_data {
+ /* first 96 byte are written by SW */
+ __le16 valid_sections;
+#define IAVF_AQ_VSI_PROP_SWITCH_VALID 0x0001
+#define IAVF_AQ_VSI_PROP_SECURITY_VALID 0x0002
+#define IAVF_AQ_VSI_PROP_VLAN_VALID 0x0004
+#define IAVF_AQ_VSI_PROP_CAS_PV_VALID 0x0008
+#define IAVF_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010
+#define IAVF_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020
+#define IAVF_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040
+#define IAVF_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080
+#define IAVF_AQ_VSI_PROP_OUTER_UP_VALID 0x0100
+#define IAVF_AQ_VSI_PROP_SCHED_VALID 0x0200
+ /* switch section */
+ __le16 switch_id; /* 12bit id combined with flags below */
+#define IAVF_AQ_VSI_SW_ID_SHIFT 0x0000
+#define IAVF_AQ_VSI_SW_ID_MASK (0xFFF << IAVF_AQ_VSI_SW_ID_SHIFT)
+#define IAVF_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000
+#define IAVF_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000
+#define IAVF_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000
+ u8 sw_reserved[2];
+ /* security section */
+ u8 sec_flags;
+#define IAVF_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01
+#define IAVF_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02
+#define IAVF_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04
+ u8 sec_reserved;
+ /* VLAN section */
+ __le16 pvid; /* VLANS include priority bits */
+ __le16 fcoe_pvid;
+ u8 port_vlan_flags;
+#define IAVF_AQ_VSI_PVLAN_MODE_SHIFT 0x00
+#define IAVF_AQ_VSI_PVLAN_MODE_MASK (0x03 << \
+ IAVF_AQ_VSI_PVLAN_MODE_SHIFT)
+#define IAVF_AQ_VSI_PVLAN_MODE_TAGGED 0x01
+#define IAVF_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02
+#define IAVF_AQ_VSI_PVLAN_MODE_ALL 0x03
+#define IAVF_AQ_VSI_PVLAN_INSERT_PVID 0x04
+#define IAVF_AQ_VSI_PVLAN_EMOD_SHIFT 0x03
+#define IAVF_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \
+ IAVF_AQ_VSI_PVLAN_EMOD_SHIFT)
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR_UP 0x08
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR 0x10
+#define IAVF_AQ_VSI_PVLAN_EMOD_NOTHING 0x18
+ u8 pvlan_reserved[3];
+ /* ingress egress up sections */
+ __le32 ingress_table; /* bitmap, 3 bits per up */
+#define IAVF_AQ_VSI_UP_TABLE_UP0_SHIFT 0
+#define IAVF_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP0_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP1_SHIFT 3
+#define IAVF_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP1_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP2_SHIFT 6
+#define IAVF_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP2_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP3_SHIFT 9
+#define IAVF_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP3_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP4_SHIFT 12
+#define IAVF_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP4_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP5_SHIFT 15
+#define IAVF_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP5_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP6_SHIFT 18
+#define IAVF_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP6_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP7_SHIFT 21
+#define IAVF_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \
+ IAVF_AQ_VSI_UP_TABLE_UP7_SHIFT)
+ __le32 egress_table; /* same defines as for ingress table */
+ /* cascaded PV section */
+ __le16 cas_pv_tag;
+ u8 cas_pv_flags;
+#define IAVF_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00
+#define IAVF_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \
+ IAVF_AQ_VSI_CAS_PV_TAGX_SHIFT)
+#define IAVF_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00
+#define IAVF_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01
+#define IAVF_AQ_VSI_CAS_PV_TAGX_COPY 0x02
+#define IAVF_AQ_VSI_CAS_PV_INSERT_TAG 0x10
+#define IAVF_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20
+#define IAVF_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40
+ u8 cas_pv_reserved;
+ /* queue mapping section */
+ __le16 mapping_flags;
+#define IAVF_AQ_VSI_QUE_MAP_CONTIG 0x0
+#define IAVF_AQ_VSI_QUE_MAP_NONCONTIG 0x1
+ __le16 queue_mapping[16];
+#define IAVF_AQ_VSI_QUEUE_SHIFT 0x0
+#define IAVF_AQ_VSI_QUEUE_MASK (0x7FF << IAVF_AQ_VSI_QUEUE_SHIFT)
+ __le16 tc_mapping[8];
+#define IAVF_AQ_VSI_TC_QUE_OFFSET_SHIFT 0
+#define IAVF_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \
+ IAVF_AQ_VSI_TC_QUE_OFFSET_SHIFT)
+#define IAVF_AQ_VSI_TC_QUE_NUMBER_SHIFT 9
+#define IAVF_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \
+ IAVF_AQ_VSI_TC_QUE_NUMBER_SHIFT)
+ /* queueing option section */
+ u8 queueing_opt_flags;
+#define IAVF_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04
+#define IAVF_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08
+#define IAVF_AQ_VSI_QUE_OPT_TCP_ENA 0x10
+#define IAVF_AQ_VSI_QUE_OPT_FCOE_ENA 0x20
+#define IAVF_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00
+#define IAVF_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40
+ u8 queueing_opt_reserved[3];
+ /* scheduler section */
+ u8 up_enable_bits;
+ u8 sched_reserved;
+ /* outer up section */
+ __le32 outer_up_table; /* same structure and defines as ingress tbl */
+ u8 cmd_reserved[8];
+ /* last 32 bytes are written by FW */
+ __le16 qs_handle[8];
+#define IAVF_AQ_VSI_QS_HANDLE_INVALID 0xFFFF
+ __le16 stat_counter_idx;
+ __le16 sched_id;
+ u8 resp_reserved[12];
+};
+
+IAVF_CHECK_STRUCT_LEN(128, iavf_aqc_vsi_properties_data);
+
+/* Get VEB Parameters (direct 0x0232)
+ * uses iavf_aqc_switch_seid for the descriptor
+ */
+struct iavf_aqc_get_veb_parameters_completion {
+ __le16 seid;
+ __le16 switch_id;
+ __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */
+ __le16 statistic_index;
+ __le16 vebs_used;
+ __le16 vebs_free;
+ u8 reserved[4];
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_veb_parameters_completion);
+
+#define IAVF_LINK_SPEED_100MB_SHIFT 0x1
+#define IAVF_LINK_SPEED_1000MB_SHIFT 0x2
+#define IAVF_LINK_SPEED_10GB_SHIFT 0x3
+#define IAVF_LINK_SPEED_40GB_SHIFT 0x4
+#define IAVF_LINK_SPEED_20GB_SHIFT 0x5
+#define IAVF_LINK_SPEED_25GB_SHIFT 0x6
+
+enum iavf_aq_link_speed {
+ IAVF_LINK_SPEED_UNKNOWN = 0,
+ IAVF_LINK_SPEED_100MB = BIT(IAVF_LINK_SPEED_100MB_SHIFT),
+ IAVF_LINK_SPEED_1GB = BIT(IAVF_LINK_SPEED_1000MB_SHIFT),
+ IAVF_LINK_SPEED_10GB = BIT(IAVF_LINK_SPEED_10GB_SHIFT),
+ IAVF_LINK_SPEED_40GB = BIT(IAVF_LINK_SPEED_40GB_SHIFT),
+ IAVF_LINK_SPEED_20GB = BIT(IAVF_LINK_SPEED_20GB_SHIFT),
+ IAVF_LINK_SPEED_25GB = BIT(IAVF_LINK_SPEED_25GB_SHIFT),
+};
+
+/* Send to PF command (indirect 0x0801) id is only used by PF
+ * Send to VF command (indirect 0x0802) id is only used by PF
+ * Send to Peer PF command (indirect 0x0803)
+ */
+struct iavf_aqc_pf_vf_message {
+ __le32 id;
+ u8 reserved[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_pf_vf_message);
+
+struct iavf_aqc_get_set_rss_key {
+#define IAVF_AQC_SET_RSS_KEY_VSI_VALID BIT(15)
+#define IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0
+#define IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \
+ IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT)
+ __le16 vsi_id;
+ u8 reserved[6];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_set_rss_key);
+
+struct iavf_aqc_get_set_rss_key_data {
+ u8 standard_rss_key[0x28];
+ u8 extended_hash_key[0xc];
+};
+
+IAVF_CHECK_STRUCT_LEN(0x34, iavf_aqc_get_set_rss_key_data);
+
+struct iavf_aqc_get_set_rss_lut {
+#define IAVF_AQC_SET_RSS_LUT_VSI_VALID BIT(15)
+#define IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0
+#define IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \
+ IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT)
+ __le16 vsi_id;
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \
+ BIT(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT)
+
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1
+ __le16 flags;
+ u8 reserved[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_set_rss_lut);
+#endif /* _IAVF_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_alloc.h b/drivers/net/ethernet/intel/iavf/iavf_alloc.h
new file mode 100644
index 0000000..2711573
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_alloc.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_ALLOC_H_
+#define _IAVF_ALLOC_H_
+
+struct iavf_hw;
+
+/* Memory allocation types */
+enum iavf_memory_type {
+ iavf_mem_arq_buf = 0, /* ARQ indirect command buffer */
+ iavf_mem_asq_buf = 1,
+ iavf_mem_atq_buf = 2, /* ATQ indirect command buffer */
+ iavf_mem_arq_ring = 3, /* ARQ descriptor ring */
+ iavf_mem_atq_ring = 4, /* ATQ descriptor ring */
+ iavf_mem_pd = 5, /* Page Descriptor */
+ iavf_mem_bp = 6, /* Backing Page - 4KB */
+ iavf_mem_bp_jumbo = 7, /* Backing Page - > 4KB */
+ iavf_mem_reserved
+};
+
+/* prototype for functions used for dynamic memory allocation */
+enum iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw,
+ struct iavf_dma_mem *mem,
+ enum iavf_memory_type type,
+ u64 size, u32 alignment);
+enum iavf_status iavf_free_dma_mem(struct iavf_hw *hw,
+ struct iavf_dma_mem *mem);
+enum iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw,
+ struct iavf_virt_mem *mem, u32 size);
+enum iavf_status iavf_free_virt_mem(struct iavf_hw *hw,
+ struct iavf_virt_mem *mem);
+
+#endif /* _IAVF_ALLOC_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c
new file mode 100644
index 0000000..0c77e41
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.c
@@ -0,0 +1,578 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include <linux/list.h>
+#include <linux/errno.h>
+
+#include "iavf.h"
+#include "iavf_prototype.h"
+#include "iavf_client.h"
+
+static
+const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR;
+static struct iavf_client *vf_registered_client;
+static LIST_HEAD(iavf_devices);
+static DEFINE_MUTEX(iavf_device_mutex);
+
+static u32 iavf_client_virtchnl_send(struct iavf_info *ldev,
+ struct iavf_client *client,
+ u8 *msg, u16 len);
+
+static int iavf_client_setup_qvlist(struct iavf_info *ldev,
+ struct iavf_client *client,
+ struct iavf_qvlist_info *qvlist_info);
+
+static struct iavf_ops iavf_lan_ops = {
+ .virtchnl_send = iavf_client_virtchnl_send,
+ .setup_qvlist = iavf_client_setup_qvlist,
+};
+
+/**
+ * iavf_client_get_params - retrieve relevant client parameters
+ * @vsi: VSI with parameters
+ * @params: client param struct
+ **/
+static
+void iavf_client_get_params(struct iavf_vsi *vsi, struct iavf_params *params)
+{
+ int i;
+
+ memset(params, 0, sizeof(struct iavf_params));
+ params->mtu = vsi->netdev->mtu;
+ params->link_up = vsi->back->link_up;
+
+ for (i = 0; i < IAVF_MAX_USER_PRIORITY; i++) {
+ params->qos.prio_qos[i].tc = 0;
+ params->qos.prio_qos[i].qs_handle = vsi->qs_handle;
+ }
+}
+
+/**
+ * iavf_notify_client_message - call the client message receive callback
+ * @vsi: the VSI associated with this client
+ * @msg: message buffer
+ * @len: length of message
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len)
+{
+ struct iavf_client_instance *cinst;
+
+ if (!vsi)
+ return;
+
+ cinst = vsi->back->cinst;
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->virtchnl_receive) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance virtchnl_receive function\n");
+ return;
+ }
+ cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client,
+ msg, len);
+}
+
+/**
+ * iavf_notify_client_l2_params - call the client notify callback
+ * @vsi: the VSI with l2 param changes
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void iavf_notify_client_l2_params(struct iavf_vsi *vsi)
+{
+ struct iavf_client_instance *cinst;
+ struct iavf_params params;
+
+ if (!vsi)
+ return;
+
+ cinst = vsi->back->cinst;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->l2_param_change) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance l2_param_change function\n");
+ return;
+ }
+ iavf_client_get_params(vsi, ¶ms);
+ cinst->lan_info.params = params;
+ cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
+ ¶ms);
+}
+
+/**
+ * iavf_notify_client_open - call the client open callback
+ * @vsi: the VSI with netdev opened
+ *
+ * If there is a client to this netdev, call the client with open
+ **/
+void iavf_notify_client_open(struct iavf_vsi *vsi)
+{
+ struct iavf_adapter *adapter = vsi->back;
+ struct iavf_client_instance *cinst = adapter->cinst;
+ int ret;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->open) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance open function\n");
+ return;
+ }
+ if (!(test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state))) {
+ ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
+ if (!ret)
+ set_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
+ }
+}
+
+/**
+ * iavf_client_release_qvlist - send a message to the PF to release iwarp qv map
+ * @ldev: pointer to L2 context.
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int iavf_client_release_qvlist(struct iavf_info *ldev)
+{
+ struct iavf_adapter *adapter = ldev->vf;
+ enum iavf_status err;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ err = iavf_aq_send_msg_to_pf(&adapter->hw,
+ VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
+ IAVF_SUCCESS, NULL, 0, NULL);
+
+ if (err)
+ dev_err(&adapter->pdev->dev,
+ "Unable to send iWarp vector release message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+
+ return err;
+}
+
+/**
+ * iavf_notify_client_close - call the client close callback
+ * @vsi: the VSI with netdev closed
+ * @reset: true when close called due to reset pending
+ *
+ * If there is a client to this netdev, call the client with close
+ **/
+void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset)
+{
+ struct iavf_adapter *adapter = vsi->back;
+ struct iavf_client_instance *cinst = adapter->cinst;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->close) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance close function\n");
+ return;
+ }
+ cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
+ iavf_client_release_qvlist(&cinst->lan_info);
+ clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
+}
+
+/**
+ * iavf_client_add_instance - add a client instance to the instance list
+ * @adapter: pointer to the board struct
+ *
+ * Returns cinst ptr on success, NULL on failure
+ **/
+static struct iavf_client_instance *
+iavf_client_add_instance(struct iavf_adapter *adapter)
+{
+ struct iavf_client_instance *cinst = NULL;
+ struct iavf_vsi *vsi = &adapter->vsi;
+ struct netdev_hw_addr *mac = NULL;
+ struct iavf_params params;
+
+ if (!vf_registered_client)
+ goto out;
+
+ if (adapter->cinst) {
+ cinst = adapter->cinst;
+ goto out;
+ }
+
+ cinst = kzalloc(sizeof(*cinst), GFP_KERNEL);
+ if (!cinst)
+ goto out;
+
+ cinst->lan_info.vf = (void *)adapter;
+ cinst->lan_info.netdev = vsi->netdev;
+ cinst->lan_info.pcidev = adapter->pdev;
+ cinst->lan_info.fid = 0;
+ cinst->lan_info.ftype = IAVF_CLIENT_FTYPE_VF;
+ cinst->lan_info.hw_addr = adapter->hw.hw_addr;
+ cinst->lan_info.ops = &iavf_lan_ops;
+ cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR;
+ cinst->lan_info.version.minor = IAVF_CLIENT_VERSION_MINOR;
+ cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD;
+ iavf_client_get_params(vsi, ¶ms);
+ cinst->lan_info.params = params;
+ set_bit(__IAVF_CLIENT_INSTANCE_NONE, &cinst->state);
+
+ cinst->lan_info.msix_count = adapter->num_iwarp_msix;
+ cinst->lan_info.msix_entries =
+ &adapter->msix_entries[adapter->iwarp_base_vector];
+
+ mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
+ struct netdev_hw_addr, list);
+ if (mac)
+ ether_addr_copy(cinst->lan_info.lanmac, mac->addr);
+ else
+ dev_err(&adapter->pdev->dev, "MAC address list is empty!\n");
+
+ cinst->client = vf_registered_client;
+ adapter->cinst = cinst;
+out:
+ return cinst;
+}
+
+/**
+ * iavf_client_del_instance - removes a client instance from the list
+ * @adapter: pointer to the board struct
+ *
+ **/
+static
+void iavf_client_del_instance(struct iavf_adapter *adapter)
+{
+ kfree(adapter->cinst);
+ adapter->cinst = NULL;
+}
+
+/**
+ * iavf_client_subtask - client maintenance work
+ * @adapter: board private structure
+ **/
+void iavf_client_subtask(struct iavf_adapter *adapter)
+{
+ struct iavf_client *client = vf_registered_client;
+ struct iavf_client_instance *cinst;
+ int ret = 0;
+
+ if (adapter->state < __IAVF_DOWN)
+ return;
+
+ /* first check client is registered */
+ if (!client)
+ return;
+
+ /* Add the client instance to the instance list */
+ cinst = iavf_client_add_instance(adapter);
+ if (!cinst)
+ return;
+
+ dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
+ client->name);
+
+ if (!test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+ /* Send an Open request to the client */
+
+ if (client->ops && client->ops->open)
+ ret = client->ops->open(&cinst->lan_info, client);
+ if (!ret)
+ set_bit(__IAVF_CLIENT_INSTANCE_OPENED,
+ &cinst->state);
+ else
+ /* remove client instance */
+ iavf_client_del_instance(adapter);
+ }
+}
+
+/**
+ * iavf_lan_add_device - add a lan device struct to the list of lan devices
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or none 0 on error
+ **/
+int iavf_lan_add_device(struct iavf_adapter *adapter)
+{
+ struct iavf_device *ldev;
+ int ret = 0;
+
+ mutex_lock(&iavf_device_mutex);
+ list_for_each_entry(ldev, &iavf_devices, list) {
+ if (ldev->vf == adapter) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+ ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+ if (!ldev) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ldev->vf = adapter;
+ INIT_LIST_HEAD(&ldev->list);
+ list_add(&ldev->list, &iavf_devices);
+ dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+ adapter->hw.bus.bus_id, adapter->hw.bus.device,
+ adapter->hw.bus.func);
+
+ /* Since in some cases register may have happened before a device gets
+ * added, we can schedule a subtask to go initiate the clients.
+ */
+ adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
+
+out:
+ mutex_unlock(&iavf_device_mutex);
+ return ret;
+}
+
+/**
+ * iavf_lan_del_device - removes a lan device from the device list
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int iavf_lan_del_device(struct iavf_adapter *adapter)
+{
+ struct iavf_device *ldev, *tmp;
+ int ret = -ENODEV;
+
+ mutex_lock(&iavf_device_mutex);
+ list_for_each_entry_safe(ldev, tmp, &iavf_devices, list) {
+ if (ldev->vf == adapter) {
+ dev_info(&adapter->pdev->dev,
+ "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+ adapter->hw.bus.bus_id, adapter->hw.bus.device,
+ adapter->hw.bus.func);
+ list_del(&ldev->list);
+ kfree(ldev);
+ ret = 0;
+ break;
+ }
+ }
+
+ mutex_unlock(&iavf_device_mutex);
+ return ret;
+}
+
+/**
+ * iavf_client_release - release client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void iavf_client_release(struct iavf_client *client)
+{
+ struct iavf_client_instance *cinst;
+ struct iavf_device *ldev;
+ struct iavf_adapter *adapter;
+
+ mutex_lock(&iavf_device_mutex);
+ list_for_each_entry(ldev, &iavf_devices, list) {
+ adapter = ldev->vf;
+ cinst = adapter->cinst;
+ if (!cinst)
+ continue;
+ if (test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+ if (client->ops && client->ops->close)
+ client->ops->close(&cinst->lan_info, client,
+ false);
+ iavf_client_release_qvlist(&cinst->lan_info);
+ clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
+
+ dev_warn(&adapter->pdev->dev,
+ "Client %s instance closed\n", client->name);
+ }
+ /* delete the client instance */
+ iavf_client_del_instance(adapter);
+ dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n",
+ client->name);
+ }
+ mutex_unlock(&iavf_device_mutex);
+}
+
+/**
+ * iavf_client_prepare - prepare client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void iavf_client_prepare(struct iavf_client *client)
+{
+ struct iavf_device *ldev;
+ struct iavf_adapter *adapter;
+
+ mutex_lock(&iavf_device_mutex);
+ list_for_each_entry(ldev, &iavf_devices, list) {
+ adapter = ldev->vf;
+ /* Signal the watchdog to service the client */
+ adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ }
+ mutex_unlock(&iavf_device_mutex);
+}
+
+/**
+ * iavf_client_virtchnl_send - send a message to the PF instance
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @msg: pointer to message buffer
+ * @len: message length
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static u32 iavf_client_virtchnl_send(struct iavf_info *ldev,
+ struct iavf_client *client,
+ u8 *msg, u16 len)
+{
+ struct iavf_adapter *adapter = ldev->vf;
+ enum iavf_status err;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP,
+ IAVF_SUCCESS, msg, len, NULL);
+ if (err)
+ dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+
+ return err;
+}
+
+/**
+ * iavf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @qvlist_info: queue and vector list
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int iavf_client_setup_qvlist(struct iavf_info *ldev,
+ struct iavf_client *client,
+ struct iavf_qvlist_info *qvlist_info)
+{
+ struct virtchnl_iwarp_qvlist_info *v_qvlist_info;
+ struct iavf_adapter *adapter = ldev->vf;
+ struct iavf_qv_info *qv_info;
+ enum iavf_status err;
+ u32 v_idx, i;
+ size_t msg_size;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ /* A quick check on whether the vectors belong to the client */
+ for (i = 0; i < qvlist_info->num_vectors; i++) {
+ qv_info = &qvlist_info->qv_info[i];
+ if (!qv_info)
+ continue;
+ v_idx = qv_info->v_idx;
+ if ((v_idx >=
+ (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) ||
+ (v_idx < adapter->iwarp_base_vector))
+ return -EINVAL;
+ }
+
+ v_qvlist_info = (struct virtchnl_iwarp_qvlist_info *)qvlist_info;
+ msg_size = struct_size(v_qvlist_info, qv_info,
+ v_qvlist_info->num_vectors - 1);
+
+ adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
+ err = iavf_aq_send_msg_to_pf(&adapter->hw,
+ VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, IAVF_SUCCESS,
+ (u8 *)v_qvlist_info, msg_size, NULL);
+
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Unable to send iWarp vector config message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+ goto out;
+ }
+
+ err = -EBUSY;
+ for (i = 0; i < 5; i++) {
+ msleep(100);
+ if (!(adapter->client_pending &
+ BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) {
+ err = 0;
+ break;
+ }
+ }
+out:
+ return err;
+}
+
+/**
+ * iavf_register_client - Register a iavf client driver with the L2 driver
+ * @client: pointer to the iavf_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int iavf_register_client(struct iavf_client *client)
+{
+ int ret = 0;
+
+ if (!client) {
+ ret = -EIO;
+ goto out;
+ }
+
+ if (strlen(client->name) == 0) {
+ pr_info("iavf: Failed to register client with no name\n");
+ ret = -EIO;
+ goto out;
+ }
+
+ if (vf_registered_client) {
+ pr_info("iavf: Client %s has already been registered!\n",
+ client->name);
+ ret = -EEXIST;
+ goto out;
+ }
+
+ if ((client->version.major != IAVF_CLIENT_VERSION_MAJOR) ||
+ (client->version.minor != IAVF_CLIENT_VERSION_MINOR)) {
+ pr_info("iavf: Failed to register client %s due to mismatched client interface version\n",
+ client->name);
+ pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n",
+ client->version.major, client->version.minor,
+ client->version.build,
+ iavf_client_interface_version_str);
+ ret = -EIO;
+ goto out;
+ }
+
+ vf_registered_client = client;
+
+ iavf_client_prepare(client);
+
+ pr_info("iavf: Registered client %s with return code %d\n",
+ client->name, ret);
+out:
+ return ret;
+}
+EXPORT_SYMBOL(iavf_register_client);
+
+/**
+ * iavf_unregister_client - Unregister a iavf client driver with the L2 driver
+ * @client: pointer to the iavf_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int iavf_unregister_client(struct iavf_client *client)
+{
+ int ret = 0;
+
+ /* When a unregister request comes through we would have to send
+ * a close for each of the client instances that were opened.
+ * client_release function is called to handle this.
+ */
+ iavf_client_release(client);
+
+ if (vf_registered_client != client) {
+ pr_info("iavf: Client %s has not been registered\n",
+ client->name);
+ ret = -ENODEV;
+ goto out;
+ }
+ vf_registered_client = NULL;
+ pr_info("iavf: Unregistered client %s\n", client->name);
+out:
+ return ret;
+}
+EXPORT_SYMBOL(iavf_unregister_client);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h
new file mode 100644
index 0000000..9a7cf39
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_CLIENT_H_
+#define _IAVF_CLIENT_H_
+
+#define IAVF_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define IAVF_CLIENT_VERSION_MAJOR 0
+#define IAVF_CLIENT_VERSION_MINOR 01
+#define IAVF_CLIENT_VERSION_BUILD 00
+#define IAVF_CLIENT_VERSION_STR \
+ __stringify(IAVF_CLIENT_VERSION_MAJOR) "." \
+ __stringify(IAVF_CLIENT_VERSION_MINOR) "." \
+ __stringify(IAVF_CLIENT_VERSION_BUILD)
+
+struct iavf_client_version {
+ u8 major;
+ u8 minor;
+ u8 build;
+ u8 rsvd;
+};
+
+enum iavf_client_state {
+ __IAVF_CLIENT_NULL,
+ __IAVF_CLIENT_REGISTERED
+};
+
+enum iavf_client_instance_state {
+ __IAVF_CLIENT_INSTANCE_NONE,
+ __IAVF_CLIENT_INSTANCE_OPENED,
+};
+
+struct iavf_ops;
+struct iavf_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define IAVF_QUEUE_TYPE_PE_AEQ 0x80
+#define IAVF_QUEUE_INVALID_IDX 0xFFFF
+
+struct iavf_qv_info {
+ u32 v_idx; /* msix_vector */
+ u16 ceq_idx;
+ u16 aeq_idx;
+ u8 itr_idx;
+};
+
+struct iavf_qvlist_info {
+ u32 num_vectors;
+ struct iavf_qv_info qv_info[1];
+};
+
+#define IAVF_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct iavf_prio_qos_params {
+ u16 qs_handle; /* qs handle for prio */
+ u8 tc; /* TC mapped to prio */
+ u8 reserved;
+};
+
+#define IAVF_CLIENT_MAX_USER_PRIORITY 8
+/* Struct to hold Client QoS */
+struct iavf_qos_params {
+ struct iavf_prio_qos_params prio_qos[IAVF_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct iavf_params {
+ struct iavf_qos_params qos;
+ u16 mtu;
+ u16 link_up; /* boolean */
+};
+
+/* Structure to hold LAN device info for a client device */
+struct iavf_info {
+ struct iavf_client_version version;
+ u8 lanmac[6];
+ struct net_device *netdev;
+ struct pci_dev *pcidev;
+ u8 __iomem *hw_addr;
+ u8 fid; /* function id, PF id or VF id */
+#define IAVF_CLIENT_FTYPE_PF 0
+#define IAVF_CLIENT_FTYPE_VF 1
+ u8 ftype; /* function type, PF or VF */
+ void *vf; /* cast to iavf_adapter */
+
+ /* All L2 params that could change during the life span of the device
+ * and needs to be communicated to the client when they change
+ */
+ struct iavf_params params;
+ struct iavf_ops *ops;
+
+ u16 msix_count; /* number of msix vectors*/
+ /* Array down below will be dynamically allocated based on msix_count */
+ struct msix_entry *msix_entries;
+ u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+};
+
+struct iavf_ops {
+ /* setup_q_vector_list enables queues with a particular vector */
+ int (*setup_qvlist)(struct iavf_info *ldev, struct iavf_client *client,
+ struct iavf_qvlist_info *qv_info);
+
+ u32 (*virtchnl_send)(struct iavf_info *ldev, struct iavf_client *client,
+ u8 *msg, u16 len);
+
+ /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
+ void (*request_reset)(struct iavf_info *ldev,
+ struct iavf_client *client);
+};
+
+struct iavf_client_ops {
+ /* Should be called from register_client() or whenever the driver is
+ * ready to create a specific client instance.
+ */
+ int (*open)(struct iavf_info *ldev, struct iavf_client *client);
+
+ /* Should be closed when netdev is unavailable or when unregister
+ * call comes in. If the close happens due to a reset, set the reset
+ * bit to true.
+ */
+ void (*close)(struct iavf_info *ldev, struct iavf_client *client,
+ bool reset);
+
+ /* called when some l2 managed parameters changes - mss */
+ void (*l2_param_change)(struct iavf_info *ldev,
+ struct iavf_client *client,
+ struct iavf_params *params);
+
+ /* called when a message is received from the PF */
+ int (*virtchnl_receive)(struct iavf_info *ldev,
+ struct iavf_client *client,
+ u8 *msg, u16 len);
+};
+
+/* Client device */
+struct iavf_client_instance {
+ struct list_head list;
+ struct iavf_info lan_info;
+ struct iavf_client *client;
+ unsigned long state;
+};
+
+struct iavf_client {
+ struct list_head list; /* list of registered clients */
+ char name[IAVF_CLIENT_STR_LENGTH];
+ struct iavf_client_version version;
+ unsigned long state; /* client state */
+ atomic_t ref_cnt; /* Count of all the client devices of this kind */
+ u32 flags;
+#define IAVF_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0)
+#define IAVF_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2)
+ u8 type;
+#define IAVF_CLIENT_IWARP 0
+ struct iavf_client_ops *ops; /* client ops provided by the client */
+};
+
+/* used by clients */
+int iavf_register_client(struct iavf_client *client);
+int iavf_unregister_client(struct iavf_client *client);
+#endif /* _IAVF_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
new file mode 100644
index 0000000..8547fc8
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -0,0 +1,956 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "iavf_type.h"
+#include "iavf_adminq.h"
+#include "iavf_prototype.h"
+#include <linux/avf/virtchnl.h>
+
+/**
+ * iavf_set_mac_type - Sets MAC type
+ * @hw: pointer to the HW structure
+ *
+ * This function sets the mac type of the adapter based on the
+ * vendor ID and device ID stored in the hw structure.
+ **/
+enum iavf_status iavf_set_mac_type(struct iavf_hw *hw)
+{
+ enum iavf_status status = 0;
+
+ if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
+ switch (hw->device_id) {
+ case IAVF_DEV_ID_X722_VF:
+ hw->mac.type = IAVF_MAC_X722_VF;
+ break;
+ case IAVF_DEV_ID_VF:
+ case IAVF_DEV_ID_VF_HV:
+ case IAVF_DEV_ID_ADAPTIVE_VF:
+ hw->mac.type = IAVF_MAC_VF;
+ break;
+ default:
+ hw->mac.type = IAVF_MAC_GENERIC;
+ break;
+ }
+ } else {
+ status = IAVF_ERR_DEVICE_NOT_SUPPORTED;
+ }
+
+ hw_dbg(hw, "found mac: %d, returns: %d\n", hw->mac.type, status);
+ return status;
+}
+
+/**
+ * iavf_aq_str - convert AQ err code to a string
+ * @hw: pointer to the HW structure
+ * @aq_err: the AQ error code to convert
+ **/
+const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err)
+{
+ switch (aq_err) {
+ case IAVF_AQ_RC_OK:
+ return "OK";
+ case IAVF_AQ_RC_EPERM:
+ return "IAVF_AQ_RC_EPERM";
+ case IAVF_AQ_RC_ENOENT:
+ return "IAVF_AQ_RC_ENOENT";
+ case IAVF_AQ_RC_ESRCH:
+ return "IAVF_AQ_RC_ESRCH";
+ case IAVF_AQ_RC_EINTR:
+ return "IAVF_AQ_RC_EINTR";
+ case IAVF_AQ_RC_EIO:
+ return "IAVF_AQ_RC_EIO";
+ case IAVF_AQ_RC_ENXIO:
+ return "IAVF_AQ_RC_ENXIO";
+ case IAVF_AQ_RC_E2BIG:
+ return "IAVF_AQ_RC_E2BIG";
+ case IAVF_AQ_RC_EAGAIN:
+ return "IAVF_AQ_RC_EAGAIN";
+ case IAVF_AQ_RC_ENOMEM:
+ return "IAVF_AQ_RC_ENOMEM";
+ case IAVF_AQ_RC_EACCES:
+ return "IAVF_AQ_RC_EACCES";
+ case IAVF_AQ_RC_EFAULT:
+ return "IAVF_AQ_RC_EFAULT";
+ case IAVF_AQ_RC_EBUSY:
+ return "IAVF_AQ_RC_EBUSY";
+ case IAVF_AQ_RC_EEXIST:
+ return "IAVF_AQ_RC_EEXIST";
+ case IAVF_AQ_RC_EINVAL:
+ return "IAVF_AQ_RC_EINVAL";
+ case IAVF_AQ_RC_ENOTTY:
+ return "IAVF_AQ_RC_ENOTTY";
+ case IAVF_AQ_RC_ENOSPC:
+ return "IAVF_AQ_RC_ENOSPC";
+ case IAVF_AQ_RC_ENOSYS:
+ return "IAVF_AQ_RC_ENOSYS";
+ case IAVF_AQ_RC_ERANGE:
+ return "IAVF_AQ_RC_ERANGE";
+ case IAVF_AQ_RC_EFLUSHED:
+ return "IAVF_AQ_RC_EFLUSHED";
+ case IAVF_AQ_RC_BAD_ADDR:
+ return "IAVF_AQ_RC_BAD_ADDR";
+ case IAVF_AQ_RC_EMODE:
+ return "IAVF_AQ_RC_EMODE";
+ case IAVF_AQ_RC_EFBIG:
+ return "IAVF_AQ_RC_EFBIG";
+ }
+
+ snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
+ return hw->err_str;
+}
+
+/**
+ * iavf_stat_str - convert status err code to a string
+ * @hw: pointer to the HW structure
+ * @stat_err: the status error code to convert
+ **/
+const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err)
+{
+ switch (stat_err) {
+ case 0:
+ return "OK";
+ case IAVF_ERR_NVM:
+ return "IAVF_ERR_NVM";
+ case IAVF_ERR_NVM_CHECKSUM:
+ return "IAVF_ERR_NVM_CHECKSUM";
+ case IAVF_ERR_PHY:
+ return "IAVF_ERR_PHY";
+ case IAVF_ERR_CONFIG:
+ return "IAVF_ERR_CONFIG";
+ case IAVF_ERR_PARAM:
+ return "IAVF_ERR_PARAM";
+ case IAVF_ERR_MAC_TYPE:
+ return "IAVF_ERR_MAC_TYPE";
+ case IAVF_ERR_UNKNOWN_PHY:
+ return "IAVF_ERR_UNKNOWN_PHY";
+ case IAVF_ERR_LINK_SETUP:
+ return "IAVF_ERR_LINK_SETUP";
+ case IAVF_ERR_ADAPTER_STOPPED:
+ return "IAVF_ERR_ADAPTER_STOPPED";
+ case IAVF_ERR_INVALID_MAC_ADDR:
+ return "IAVF_ERR_INVALID_MAC_ADDR";
+ case IAVF_ERR_DEVICE_NOT_SUPPORTED:
+ return "IAVF_ERR_DEVICE_NOT_SUPPORTED";
+ case IAVF_ERR_MASTER_REQUESTS_PENDING:
+ return "IAVF_ERR_MASTER_REQUESTS_PENDING";
+ case IAVF_ERR_INVALID_LINK_SETTINGS:
+ return "IAVF_ERR_INVALID_LINK_SETTINGS";
+ case IAVF_ERR_AUTONEG_NOT_COMPLETE:
+ return "IAVF_ERR_AUTONEG_NOT_COMPLETE";
+ case IAVF_ERR_RESET_FAILED:
+ return "IAVF_ERR_RESET_FAILED";
+ case IAVF_ERR_SWFW_SYNC:
+ return "IAVF_ERR_SWFW_SYNC";
+ case IAVF_ERR_NO_AVAILABLE_VSI:
+ return "IAVF_ERR_NO_AVAILABLE_VSI";
+ case IAVF_ERR_NO_MEMORY:
+ return "IAVF_ERR_NO_MEMORY";
+ case IAVF_ERR_BAD_PTR:
+ return "IAVF_ERR_BAD_PTR";
+ case IAVF_ERR_RING_FULL:
+ return "IAVF_ERR_RING_FULL";
+ case IAVF_ERR_INVALID_PD_ID:
+ return "IAVF_ERR_INVALID_PD_ID";
+ case IAVF_ERR_INVALID_QP_ID:
+ return "IAVF_ERR_INVALID_QP_ID";
+ case IAVF_ERR_INVALID_CQ_ID:
+ return "IAVF_ERR_INVALID_CQ_ID";
+ case IAVF_ERR_INVALID_CEQ_ID:
+ return "IAVF_ERR_INVALID_CEQ_ID";
+ case IAVF_ERR_INVALID_AEQ_ID:
+ return "IAVF_ERR_INVALID_AEQ_ID";
+ case IAVF_ERR_INVALID_SIZE:
+ return "IAVF_ERR_INVALID_SIZE";
+ case IAVF_ERR_INVALID_ARP_INDEX:
+ return "IAVF_ERR_INVALID_ARP_INDEX";
+ case IAVF_ERR_INVALID_FPM_FUNC_ID:
+ return "IAVF_ERR_INVALID_FPM_FUNC_ID";
+ case IAVF_ERR_QP_INVALID_MSG_SIZE:
+ return "IAVF_ERR_QP_INVALID_MSG_SIZE";
+ case IAVF_ERR_QP_TOOMANY_WRS_POSTED:
+ return "IAVF_ERR_QP_TOOMANY_WRS_POSTED";
+ case IAVF_ERR_INVALID_FRAG_COUNT:
+ return "IAVF_ERR_INVALID_FRAG_COUNT";
+ case IAVF_ERR_QUEUE_EMPTY:
+ return "IAVF_ERR_QUEUE_EMPTY";
+ case IAVF_ERR_INVALID_ALIGNMENT:
+ return "IAVF_ERR_INVALID_ALIGNMENT";
+ case IAVF_ERR_FLUSHED_QUEUE:
+ return "IAVF_ERR_FLUSHED_QUEUE";
+ case IAVF_ERR_INVALID_PUSH_PAGE_INDEX:
+ return "IAVF_ERR_INVALID_PUSH_PAGE_INDEX";
+ case IAVF_ERR_INVALID_IMM_DATA_SIZE:
+ return "IAVF_ERR_INVALID_IMM_DATA_SIZE";
+ case IAVF_ERR_TIMEOUT:
+ return "IAVF_ERR_TIMEOUT";
+ case IAVF_ERR_OPCODE_MISMATCH:
+ return "IAVF_ERR_OPCODE_MISMATCH";
+ case IAVF_ERR_CQP_COMPL_ERROR:
+ return "IAVF_ERR_CQP_COMPL_ERROR";
+ case IAVF_ERR_INVALID_VF_ID:
+ return "IAVF_ERR_INVALID_VF_ID";
+ case IAVF_ERR_INVALID_HMCFN_ID:
+ return "IAVF_ERR_INVALID_HMCFN_ID";
+ case IAVF_ERR_BACKING_PAGE_ERROR:
+ return "IAVF_ERR_BACKING_PAGE_ERROR";
+ case IAVF_ERR_NO_PBLCHUNKS_AVAILABLE:
+ return "IAVF_ERR_NO_PBLCHUNKS_AVAILABLE";
+ case IAVF_ERR_INVALID_PBLE_INDEX:
+ return "IAVF_ERR_INVALID_PBLE_INDEX";
+ case IAVF_ERR_INVALID_SD_INDEX:
+ return "IAVF_ERR_INVALID_SD_INDEX";
+ case IAVF_ERR_INVALID_PAGE_DESC_INDEX:
+ return "IAVF_ERR_INVALID_PAGE_DESC_INDEX";
+ case IAVF_ERR_INVALID_SD_TYPE:
+ return "IAVF_ERR_INVALID_SD_TYPE";
+ case IAVF_ERR_MEMCPY_FAILED:
+ return "IAVF_ERR_MEMCPY_FAILED";
+ case IAVF_ERR_INVALID_HMC_OBJ_INDEX:
+ return "IAVF_ERR_INVALID_HMC_OBJ_INDEX";
+ case IAVF_ERR_INVALID_HMC_OBJ_COUNT:
+ return "IAVF_ERR_INVALID_HMC_OBJ_COUNT";
+ case IAVF_ERR_INVALID_SRQ_ARM_LIMIT:
+ return "IAVF_ERR_INVALID_SRQ_ARM_LIMIT";
+ case IAVF_ERR_SRQ_ENABLED:
+ return "IAVF_ERR_SRQ_ENABLED";
+ case IAVF_ERR_ADMIN_QUEUE_ERROR:
+ return "IAVF_ERR_ADMIN_QUEUE_ERROR";
+ case IAVF_ERR_ADMIN_QUEUE_TIMEOUT:
+ return "IAVF_ERR_ADMIN_QUEUE_TIMEOUT";
+ case IAVF_ERR_BUF_TOO_SHORT:
+ return "IAVF_ERR_BUF_TOO_SHORT";
+ case IAVF_ERR_ADMIN_QUEUE_FULL:
+ return "IAVF_ERR_ADMIN_QUEUE_FULL";
+ case IAVF_ERR_ADMIN_QUEUE_NO_WORK:
+ return "IAVF_ERR_ADMIN_QUEUE_NO_WORK";
+ case IAVF_ERR_BAD_IWARP_CQE:
+ return "IAVF_ERR_BAD_IWARP_CQE";
+ case IAVF_ERR_NVM_BLANK_MODE:
+ return "IAVF_ERR_NVM_BLANK_MODE";
+ case IAVF_ERR_NOT_IMPLEMENTED:
+ return "IAVF_ERR_NOT_IMPLEMENTED";
+ case IAVF_ERR_PE_DOORBELL_NOT_ENABLED:
+ return "IAVF_ERR_PE_DOORBELL_NOT_ENABLED";
+ case IAVF_ERR_DIAG_TEST_FAILED:
+ return "IAVF_ERR_DIAG_TEST_FAILED";
+ case IAVF_ERR_NOT_READY:
+ return "IAVF_ERR_NOT_READY";
+ case IAVF_NOT_SUPPORTED:
+ return "IAVF_NOT_SUPPORTED";
+ case IAVF_ERR_FIRMWARE_API_VERSION:
+ return "IAVF_ERR_FIRMWARE_API_VERSION";
+ case IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR:
+ return "IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR";
+ }
+
+ snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err);
+ return hw->err_str;
+}
+
+/**
+ * iavf_debug_aq
+ * @hw: debug mask related to admin queue
+ * @mask: debug mask
+ * @desc: pointer to admin queue descriptor
+ * @buffer: pointer to command buffer
+ * @buf_len: max length of buffer
+ *
+ * Dumps debug log about adminq command with descriptor contents.
+ **/
+void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc,
+ void *buffer, u16 buf_len)
+{
+ struct iavf_aq_desc *aq_desc = (struct iavf_aq_desc *)desc;
+ u8 *buf = (u8 *)buffer;
+
+ if ((!(mask & hw->debug_mask)) || !desc)
+ return;
+
+ iavf_debug(hw, mask,
+ "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
+ le16_to_cpu(aq_desc->opcode),
+ le16_to_cpu(aq_desc->flags),
+ le16_to_cpu(aq_desc->datalen),
+ le16_to_cpu(aq_desc->retval));
+ iavf_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n",
+ le32_to_cpu(aq_desc->cookie_high),
+ le32_to_cpu(aq_desc->cookie_low));
+ iavf_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n",
+ le32_to_cpu(aq_desc->params.internal.param0),
+ le32_to_cpu(aq_desc->params.internal.param1));
+ iavf_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n",
+ le32_to_cpu(aq_desc->params.external.addr_high),
+ le32_to_cpu(aq_desc->params.external.addr_low));
+
+ if (buffer && aq_desc->datalen) {
+ u16 len = le16_to_cpu(aq_desc->datalen);
+
+ iavf_debug(hw, mask, "AQ CMD Buffer:\n");
+ if (buf_len < len)
+ len = buf_len;
+ /* write the full 16-byte chunks */
+ if (hw->debug_mask & mask) {
+ char prefix[27];
+
+ snprintf(prefix, sizeof(prefix),
+ "iavf %02x:%02x.%x: \t0x",
+ hw->bus.bus_id,
+ hw->bus.device,
+ hw->bus.func);
+
+ print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
+ 16, 1, buf, len, false);
+ }
+ }
+}
+
+/**
+ * iavf_check_asq_alive
+ * @hw: pointer to the hw struct
+ *
+ * Returns true if Queue is enabled else false.
+ **/
+bool iavf_check_asq_alive(struct iavf_hw *hw)
+{
+ if (hw->aq.asq.len)
+ return !!(rd32(hw, hw->aq.asq.len) &
+ IAVF_VF_ATQLEN1_ATQENABLE_MASK);
+ else
+ return false;
+}
+
+/**
+ * iavf_aq_queue_shutdown
+ * @hw: pointer to the hw struct
+ * @unloading: is the driver unloading itself
+ *
+ * Tell the Firmware that we're shutting down the AdminQ and whether
+ * or not the driver is unloading as well.
+ **/
+enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading)
+{
+ struct iavf_aq_desc desc;
+ struct iavf_aqc_queue_shutdown *cmd =
+ (struct iavf_aqc_queue_shutdown *)&desc.params.raw;
+ enum iavf_status status;
+
+ iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_queue_shutdown);
+
+ if (unloading)
+ cmd->driver_unloading = cpu_to_le32(IAVF_AQ_DRIVER_UNLOADING);
+ status = iavf_asq_send_command(hw, &desc, NULL, 0, NULL);
+
+ return status;
+}
+
+/**
+ * iavf_aq_get_set_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: vsi fw index
+ * @pf_lut: for PF table set true, for VSI table set false
+ * @lut: pointer to the lut buffer provided by the caller
+ * @lut_size: size of the lut buffer
+ * @set: set true to set the table, false to get the table
+ *
+ * Internal function to get or set RSS look up table
+ **/
+static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
+ u16 vsi_id, bool pf_lut,
+ u8 *lut, u16 lut_size,
+ bool set)
+{
+ enum iavf_status status;
+ struct iavf_aq_desc desc;
+ struct iavf_aqc_get_set_rss_lut *cmd_resp =
+ (struct iavf_aqc_get_set_rss_lut *)&desc.params.raw;
+
+ if (set)
+ iavf_fill_default_direct_cmd_desc(&desc,
+ iavf_aqc_opc_set_rss_lut);
+ else
+ iavf_fill_default_direct_cmd_desc(&desc,
+ iavf_aqc_opc_get_rss_lut);
+
+ /* Indirect command */
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
+
+ cmd_resp->vsi_id =
+ cpu_to_le16((u16)((vsi_id <<
+ IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
+ IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK));
+ cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_LUT_VSI_VALID);
+
+ if (pf_lut)
+ cmd_resp->flags |= cpu_to_le16((u16)
+ ((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
+ IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
+ IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+ else
+ cmd_resp->flags |= cpu_to_le16((u16)
+ ((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
+ IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
+ IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+
+ status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL);
+
+ return status;
+}
+
+/**
+ * iavf_aq_get_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: vsi fw index
+ * @pf_lut: for PF table set true, for VSI table set false
+ * @lut: pointer to the lut buffer provided by the caller
+ * @lut_size: size of the lut buffer
+ *
+ * get the RSS lookup table, PF or VSI type
+ **/
+enum iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id,
+ bool pf_lut, u8 *lut, u16 lut_size)
+{
+ return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size,
+ false);
+}
+
+/**
+ * iavf_aq_set_rss_lut
+ * @hw: pointer to the hardware structure
+ * @vsi_id: vsi fw index
+ * @pf_lut: for PF table set true, for VSI table set false
+ * @lut: pointer to the lut buffer provided by the caller
+ * @lut_size: size of the lut buffer
+ *
+ * set the RSS lookup table, PF or VSI type
+ **/
+enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id,
+ bool pf_lut, u8 *lut, u16 lut_size)
+{
+ return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true);
+}
+
+/**
+ * iavf_aq_get_set_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: vsi fw index
+ * @key: pointer to key info struct
+ * @set: set true to set the key, false to get the key
+ *
+ * get the RSS key per VSI
+ **/
+static enum
+iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
+ struct iavf_aqc_get_set_rss_key_data *key,
+ bool set)
+{
+ enum iavf_status status;
+ struct iavf_aq_desc desc;
+ struct iavf_aqc_get_set_rss_key *cmd_resp =
+ (struct iavf_aqc_get_set_rss_key *)&desc.params.raw;
+ u16 key_size = sizeof(struct iavf_aqc_get_set_rss_key_data);
+
+ if (set)
+ iavf_fill_default_direct_cmd_desc(&desc,
+ iavf_aqc_opc_set_rss_key);
+ else
+ iavf_fill_default_direct_cmd_desc(&desc,
+ iavf_aqc_opc_get_rss_key);
+
+ /* Indirect command */
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
+
+ cmd_resp->vsi_id =
+ cpu_to_le16((u16)((vsi_id <<
+ IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
+ IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK));
+ cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_KEY_VSI_VALID);
+
+ status = iavf_asq_send_command(hw, &desc, key, key_size, NULL);
+
+ return status;
+}
+
+/**
+ * iavf_aq_get_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: vsi fw index
+ * @key: pointer to key info struct
+ *
+ **/
+enum iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id,
+ struct iavf_aqc_get_set_rss_key_data *key)
+{
+ return iavf_aq_get_set_rss_key(hw, vsi_id, key, false);
+}
+
+/**
+ * iavf_aq_set_rss_key
+ * @hw: pointer to the hw struct
+ * @vsi_id: vsi fw index
+ * @key: pointer to key info struct
+ *
+ * set the RSS key per VSI
+ **/
+enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
+ struct iavf_aqc_get_set_rss_key_data *key)
+{
+ return iavf_aq_get_set_rss_key(hw, vsi_id, key, true);
+}
+
+/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the
+ * hardware to a bit-field that can be used by SW to more easily determine the
+ * packet type.
+ *
+ * Macros are used to shorten the table lines and make this table human
+ * readable.
+ *
+ * We store the PTYPE in the top byte of the bit field - this is just so that
+ * we can check that the table doesn't have a row missing, as the index into
+ * the table should be the PTYPE.
+ *
+ * Typical work flow:
+ *
+ * IF NOT iavf_ptype_lookup[ptype].known
+ * THEN
+ * Packet is unknown
+ * ELSE IF iavf_ptype_lookup[ptype].outer_ip == IAVF_RX_PTYPE_OUTER_IP
+ * Use the rest of the fields to look at the tunnels, inner protocols, etc
+ * ELSE
+ * Use the enum iavf_rx_l2_ptype to decode the packet type
+ * ENDIF
+ */
+
+/* macro to make the table lines short */
+#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+ { PTYPE, \
+ 1, \
+ IAVF_RX_PTYPE_OUTER_##OUTER_IP, \
+ IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \
+ IAVF_RX_PTYPE_##OUTER_FRAG, \
+ IAVF_RX_PTYPE_TUNNEL_##T, \
+ IAVF_RX_PTYPE_TUNNEL_END_##TE, \
+ IAVF_RX_PTYPE_##TEF, \
+ IAVF_RX_PTYPE_INNER_PROT_##I, \
+ IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL }
+
+#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \
+ { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+
+/* shorter macros makes the table fit but are terse */
+#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG
+#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG
+#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC
+
+/* Lookup table mapping the HW PTYPE to the bit field for decoding */
+struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = {
+ /* L2 Packet types */
+ IAVF_PTT_UNUSED_ENTRY(0),
+ IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2),
+ IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ IAVF_PTT_UNUSED_ENTRY(4),
+ IAVF_PTT_UNUSED_ENTRY(5),
+ IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ IAVF_PTT_UNUSED_ENTRY(8),
+ IAVF_PTT_UNUSED_ENTRY(9),
+ IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
+ IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+
+ /* Non Tunneled IPv4 */
+ IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(25),
+ IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4),
+ IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv4 */
+ IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(32),
+ IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv6 */
+ IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(39),
+ IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT */
+ IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> IPv4 */
+ IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(47),
+ IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> IPv6 */
+ IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(54),
+ IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC */
+ IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> MAC --> IPv4 */
+ IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(62),
+ IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT -> MAC --> IPv6 */
+ IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(69),
+ IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC/VLAN */
+ IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
+ IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(77),
+ IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
+ IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(84),
+ IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* Non Tunneled IPv6 */
+ IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
+ IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3),
+ IAVF_PTT_UNUSED_ENTRY(91),
+ IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4),
+ IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv4 */
+ IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(98),
+ IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv6 */
+ IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(105),
+ IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT */
+ IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> IPv4 */
+ IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(113),
+ IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> IPv6 */
+ IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(120),
+ IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC */
+ IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv4 */
+ IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(128),
+ IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv6 */
+ IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(135),
+ IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN */
+ IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
+ IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(143),
+ IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
+ IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ IAVF_PTT_UNUSED_ENTRY(150),
+ IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* unused entries */
+ IAVF_PTT_UNUSED_ENTRY(154),
+ IAVF_PTT_UNUSED_ENTRY(155),
+ IAVF_PTT_UNUSED_ENTRY(156),
+ IAVF_PTT_UNUSED_ENTRY(157),
+ IAVF_PTT_UNUSED_ENTRY(158),
+ IAVF_PTT_UNUSED_ENTRY(159),
+
+ IAVF_PTT_UNUSED_ENTRY(160),
+ IAVF_PTT_UNUSED_ENTRY(161),
+ IAVF_PTT_UNUSED_ENTRY(162),
+ IAVF_PTT_UNUSED_ENTRY(163),
+ IAVF_PTT_UNUSED_ENTRY(164),
+ IAVF_PTT_UNUSED_ENTRY(165),
+ IAVF_PTT_UNUSED_ENTRY(166),
+ IAVF_PTT_UNUSED_ENTRY(167),
+ IAVF_PTT_UNUSED_ENTRY(168),
+ IAVF_PTT_UNUSED_ENTRY(169),
+
+ IAVF_PTT_UNUSED_ENTRY(170),
+ IAVF_PTT_UNUSED_ENTRY(171),
+ IAVF_PTT_UNUSED_ENTRY(172),
+ IAVF_PTT_UNUSED_ENTRY(173),
+ IAVF_PTT_UNUSED_ENTRY(174),
+ IAVF_PTT_UNUSED_ENTRY(175),
+ IAVF_PTT_UNUSED_ENTRY(176),
+ IAVF_PTT_UNUSED_ENTRY(177),
+ IAVF_PTT_UNUSED_ENTRY(178),
+ IAVF_PTT_UNUSED_ENTRY(179),
+
+ IAVF_PTT_UNUSED_ENTRY(180),
+ IAVF_PTT_UNUSED_ENTRY(181),
+ IAVF_PTT_UNUSED_ENTRY(182),
+ IAVF_PTT_UNUSED_ENTRY(183),
+ IAVF_PTT_UNUSED_ENTRY(184),
+ IAVF_PTT_UNUSED_ENTRY(185),
+ IAVF_PTT_UNUSED_ENTRY(186),
+ IAVF_PTT_UNUSED_ENTRY(187),
+ IAVF_PTT_UNUSED_ENTRY(188),
+ IAVF_PTT_UNUSED_ENTRY(189),
+
+ IAVF_PTT_UNUSED_ENTRY(190),
+ IAVF_PTT_UNUSED_ENTRY(191),
+ IAVF_PTT_UNUSED_ENTRY(192),
+ IAVF_PTT_UNUSED_ENTRY(193),
+ IAVF_PTT_UNUSED_ENTRY(194),
+ IAVF_PTT_UNUSED_ENTRY(195),
+ IAVF_PTT_UNUSED_ENTRY(196),
+ IAVF_PTT_UNUSED_ENTRY(197),
+ IAVF_PTT_UNUSED_ENTRY(198),
+ IAVF_PTT_UNUSED_ENTRY(199),
+
+ IAVF_PTT_UNUSED_ENTRY(200),
+ IAVF_PTT_UNUSED_ENTRY(201),
+ IAVF_PTT_UNUSED_ENTRY(202),
+ IAVF_PTT_UNUSED_ENTRY(203),
+ IAVF_PTT_UNUSED_ENTRY(204),
+ IAVF_PTT_UNUSED_ENTRY(205),
+ IAVF_PTT_UNUSED_ENTRY(206),
+ IAVF_PTT_UNUSED_ENTRY(207),
+ IAVF_PTT_UNUSED_ENTRY(208),
+ IAVF_PTT_UNUSED_ENTRY(209),
+
+ IAVF_PTT_UNUSED_ENTRY(210),
+ IAVF_PTT_UNUSED_ENTRY(211),
+ IAVF_PTT_UNUSED_ENTRY(212),
+ IAVF_PTT_UNUSED_ENTRY(213),
+ IAVF_PTT_UNUSED_ENTRY(214),
+ IAVF_PTT_UNUSED_ENTRY(215),
+ IAVF_PTT_UNUSED_ENTRY(216),
+ IAVF_PTT_UNUSED_ENTRY(217),
+ IAVF_PTT_UNUSED_ENTRY(218),
+ IAVF_PTT_UNUSED_ENTRY(219),
+
+ IAVF_PTT_UNUSED_ENTRY(220),
+ IAVF_PTT_UNUSED_ENTRY(221),
+ IAVF_PTT_UNUSED_ENTRY(222),
+ IAVF_PTT_UNUSED_ENTRY(223),
+ IAVF_PTT_UNUSED_ENTRY(224),
+ IAVF_PTT_UNUSED_ENTRY(225),
+ IAVF_PTT_UNUSED_ENTRY(226),
+ IAVF_PTT_UNUSED_ENTRY(227),
+ IAVF_PTT_UNUSED_ENTRY(228),
+ IAVF_PTT_UNUSED_ENTRY(229),
+
+ IAVF_PTT_UNUSED_ENTRY(230),
+ IAVF_PTT_UNUSED_ENTRY(231),
+ IAVF_PTT_UNUSED_ENTRY(232),
+ IAVF_PTT_UNUSED_ENTRY(233),
+ IAVF_PTT_UNUSED_ENTRY(234),
+ IAVF_PTT_UNUSED_ENTRY(235),
+ IAVF_PTT_UNUSED_ENTRY(236),
+ IAVF_PTT_UNUSED_ENTRY(237),
+ IAVF_PTT_UNUSED_ENTRY(238),
+ IAVF_PTT_UNUSED_ENTRY(239),
+
+ IAVF_PTT_UNUSED_ENTRY(240),
+ IAVF_PTT_UNUSED_ENTRY(241),
+ IAVF_PTT_UNUSED_ENTRY(242),
+ IAVF_PTT_UNUSED_ENTRY(243),
+ IAVF_PTT_UNUSED_ENTRY(244),
+ IAVF_PTT_UNUSED_ENTRY(245),
+ IAVF_PTT_UNUSED_ENTRY(246),
+ IAVF_PTT_UNUSED_ENTRY(247),
+ IAVF_PTT_UNUSED_ENTRY(248),
+ IAVF_PTT_UNUSED_ENTRY(249),
+
+ IAVF_PTT_UNUSED_ENTRY(250),
+ IAVF_PTT_UNUSED_ENTRY(251),
+ IAVF_PTT_UNUSED_ENTRY(252),
+ IAVF_PTT_UNUSED_ENTRY(253),
+ IAVF_PTT_UNUSED_ENTRY(254),
+ IAVF_PTT_UNUSED_ENTRY(255)
+};
+
+/**
+ * iavf_aq_send_msg_to_pf
+ * @hw: pointer to the hardware structure
+ * @v_opcode: opcodes for VF-PF communication
+ * @v_retval: return error code
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ * @cmd_details: pointer to command details
+ *
+ * Send message to PF driver using admin queue. By default, this message
+ * is sent asynchronously, i.e. iavf_asq_send_command() does not wait for
+ * completion before returning.
+ **/
+enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
+ enum virtchnl_ops v_opcode,
+ enum iavf_status v_retval,
+ u8 *msg, u16 msglen,
+ struct iavf_asq_cmd_details *cmd_details)
+{
+ struct iavf_asq_cmd_details details;
+ struct iavf_aq_desc desc;
+ enum iavf_status status;
+
+ iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_send_msg_to_pf);
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_SI);
+ desc.cookie_high = cpu_to_le32(v_opcode);
+ desc.cookie_low = cpu_to_le32(v_retval);
+ if (msglen) {
+ desc.flags |= cpu_to_le16((u16)(IAVF_AQ_FLAG_BUF
+ | IAVF_AQ_FLAG_RD));
+ if (msglen > IAVF_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_LB);
+ desc.datalen = cpu_to_le16(msglen);
+ }
+ if (!cmd_details) {
+ memset(&details, 0, sizeof(details));
+ details.async = true;
+ cmd_details = &details;
+ }
+ status = iavf_asq_send_command(hw, &desc, msg, msglen, cmd_details);
+ return status;
+}
+
+/**
+ * iavf_vf_parse_hw_config
+ * @hw: pointer to the hardware structure
+ * @msg: pointer to the virtual channel VF resource structure
+ *
+ * Given a VF resource message from the PF, populate the hw struct
+ * with appropriate information.
+ **/
+void iavf_vf_parse_hw_config(struct iavf_hw *hw,
+ struct virtchnl_vf_resource *msg)
+{
+ struct virtchnl_vsi_resource *vsi_res;
+ int i;
+
+ vsi_res = &msg->vsi_res[0];
+
+ hw->dev_caps.num_vsis = msg->num_vsis;
+ hw->dev_caps.num_rx_qp = msg->num_queue_pairs;
+ hw->dev_caps.num_tx_qp = msg->num_queue_pairs;
+ hw->dev_caps.num_msix_vectors_vf = msg->max_vectors;
+ hw->dev_caps.dcb = msg->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_L2;
+ hw->dev_caps.fcoe = 0;
+ for (i = 0; i < msg->num_vsis; i++) {
+ if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) {
+ ether_addr_copy(hw->mac.perm_addr,
+ vsi_res->default_mac_addr);
+ ether_addr_copy(hw->mac.addr,
+ vsi_res->default_mac_addr);
+ }
+ vsi_res++;
+ }
+}
+
+/**
+ * iavf_vf_reset
+ * @hw: pointer to the hardware structure
+ *
+ * Send a VF_RESET message to the PF. Does not wait for response from PF
+ * as none will be forthcoming. Immediately after calling this function,
+ * the admin queue should be shut down and (optionally) reinitialized.
+ **/
+enum iavf_status iavf_vf_reset(struct iavf_hw *hw)
+{
+ return iavf_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF,
+ 0, NULL, 0, NULL);
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_devids.h b/drivers/net/ethernet/intel/iavf/iavf_devids.h
new file mode 100644
index 0000000..8eb7b69
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_devids.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_DEVIDS_H_
+#define _IAVF_DEVIDS_H_
+
+/* Device IDs for the VF driver */
+#define IAVF_DEV_ID_VF 0x154C
+#define IAVF_DEV_ID_VF_HV 0x1571
+#define IAVF_DEV_ID_ADAPTIVE_VF 0x1889
+#define IAVF_DEV_ID_X722_VF 0x37CD
+#endif /* _IAVF_DEVIDS_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
new file mode 100644
index 0000000..dad3eec
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -0,0 +1,1036 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+/* ethtool support for iavf */
+#include "iavf.h"
+
+#include <linux/uaccess.h>
+
+/* ethtool statistics helpers */
+
+/**
+ * struct iavf_stats - definition for an ethtool statistic
+ * @stat_string: statistic name to display in ethtool -S output
+ * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64)
+ * @stat_offset: offsetof() the stat from a base pointer
+ *
+ * This structure defines a statistic to be added to the ethtool stats buffer.
+ * It defines a statistic as offset from a common base pointer. Stats should
+ * be defined in constant arrays using the IAVF_STAT macro, with every element
+ * of the array using the same _type for calculating the sizeof_stat and
+ * stat_offset.
+ *
+ * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or
+ * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from
+ * the iavf_add_ethtool_stat() helper function.
+ *
+ * The @stat_string is interpreted as a format string, allowing formatted
+ * values to be inserted while looping over multiple structures for a given
+ * statistics array. Thus, every statistic string in an array should have the
+ * same type and number of format specifiers, to be formatted by variadic
+ * arguments to the iavf_add_stat_string() helper function.
+ **/
+struct iavf_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int sizeof_stat;
+ int stat_offset;
+};
+
+/* Helper macro to define an iavf_stat structure with proper size and type.
+ * Use this when defining constant statistics arrays. Note that @_type expects
+ * only a type name and is used multiple times.
+ */
+#define IAVF_STAT(_type, _name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(_type, _stat), \
+ .stat_offset = offsetof(_type, _stat) \
+}
+
+/* Helper macro for defining some statistics related to queues */
+#define IAVF_QUEUE_STAT(_name, _stat) \
+ IAVF_STAT(struct iavf_ring, _name, _stat)
+
+/* Stats associated with a Tx or Rx ring */
+static const struct iavf_stats iavf_gstrings_queue_stats[] = {
+ IAVF_QUEUE_STAT("%s-%u.packets", stats.packets),
+ IAVF_QUEUE_STAT("%s-%u.bytes", stats.bytes),
+};
+
+/**
+ * iavf_add_one_ethtool_stat - copy the stat into the supplied buffer
+ * @data: location to store the stat value
+ * @pointer: basis for where to copy from
+ * @stat: the stat definition
+ *
+ * Copies the stat data defined by the pointer and stat structure pair into
+ * the memory supplied as data. Used to implement iavf_add_ethtool_stats and
+ * iavf_add_queue_stats. If the pointer is null, data will be zero'd.
+ */
+static void
+iavf_add_one_ethtool_stat(u64 *data, void *pointer,
+ const struct iavf_stats *stat)
+{
+ char *p;
+
+ if (!pointer) {
+ /* ensure that the ethtool data buffer is zero'd for any stats
+ * which don't have a valid pointer.
+ */
+ *data = 0;
+ return;
+ }
+
+ p = (char *)pointer + stat->stat_offset;
+ switch (stat->sizeof_stat) {
+ case sizeof(u64):
+ *data = *((u64 *)p);
+ break;
+ case sizeof(u32):
+ *data = *((u32 *)p);
+ break;
+ case sizeof(u16):
+ *data = *((u16 *)p);
+ break;
+ case sizeof(u8):
+ *data = *((u8 *)p);
+ break;
+ default:
+ WARN_ONCE(1, "unexpected stat size for %s",
+ stat->stat_string);
+ *data = 0;
+ }
+}
+
+/**
+ * __iavf_add_ethtool_stats - copy stats into the ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location to copy stats from
+ * @stats: array of stats to copy
+ * @size: the size of the stats definition
+ *
+ * Copy the stats defined by the stats array using the pointer as a base into
+ * the data buffer supplied by ethtool. Updates the data pointer to point to
+ * the next empty location for successive calls to __iavf_add_ethtool_stats.
+ * If pointer is null, set the data values to zero and update the pointer to
+ * skip these stats.
+ **/
+static void
+__iavf_add_ethtool_stats(u64 **data, void *pointer,
+ const struct iavf_stats stats[],
+ const unsigned int size)
+{
+ unsigned int i;
+
+ for (i = 0; i < size; i++)
+ iavf_add_one_ethtool_stat((*data)++, pointer, &stats[i]);
+}
+
+/**
+ * iavf_add_ethtool_stats - copy stats into ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location where stats are stored
+ * @stats: static const array of stat definitions
+ *
+ * Macro to ease the use of __iavf_add_ethtool_stats by taking a static
+ * constant stats array and passing the ARRAY_SIZE(). This avoids typos by
+ * ensuring that we pass the size associated with the given stats array.
+ *
+ * The parameter @stats is evaluated twice, so parameters with side effects
+ * should be avoided.
+ **/
+#define iavf_add_ethtool_stats(data, pointer, stats) \
+ __iavf_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
+/**
+ * iavf_add_queue_stats - copy queue statistics into supplied buffer
+ * @data: ethtool stats buffer
+ * @ring: the ring to copy
+ *
+ * Queue statistics must be copied while protected by
+ * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats.
+ * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the
+ * ring pointer is null, zero out the queue stat values and update the data
+ * pointer. Otherwise safely copy the stats from the ring into the supplied
+ * buffer and update the data pointer when finished.
+ *
+ * This function expects to be called while under rcu_read_lock().
+ **/
+static void
+iavf_add_queue_stats(u64 **data, struct iavf_ring *ring)
+{
+ const unsigned int size = ARRAY_SIZE(iavf_gstrings_queue_stats);
+ const struct iavf_stats *stats = iavf_gstrings_queue_stats;
+ unsigned int start;
+ unsigned int i;
+
+ /* To avoid invalid statistics values, ensure that we keep retrying
+ * the copy until we get a consistent value according to
+ * u64_stats_fetch_retry_irq. But first, make sure our ring is
+ * non-null before attempting to access its syncp.
+ */
+ do {
+ start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp);
+ for (i = 0; i < size; i++)
+ iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]);
+ } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start));
+
+ /* Once we successfully copy the stats in, update the data pointer */
+ *data += size;
+}
+
+/**
+ * __iavf_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ * @size: size of the stats array
+ *
+ * Format and copy the strings described by stats into the buffer pointed at
+ * by p.
+ **/
+static void __iavf_add_stat_strings(u8 **p, const struct iavf_stats stats[],
+ const unsigned int size, ...)
+{
+ unsigned int i;
+
+ for (i = 0; i < size; i++) {
+ va_list args;
+
+ va_start(args, size);
+ vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
+ *p += ETH_GSTRING_LEN;
+ va_end(args);
+ }
+}
+
+/**
+ * iavf_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ *
+ * Format and copy the strings described by the const static stats value into
+ * the buffer pointed at by p.
+ *
+ * The parameter @stats is evaluated twice, so parameters with side effects
+ * should be avoided. Additionally, stats must be an array such that
+ * ARRAY_SIZE can be called on it.
+ **/
+#define iavf_add_stat_strings(p, stats, ...) \
+ __iavf_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
+
+#define VF_STAT(_name, _stat) \
+ IAVF_STAT(struct iavf_adapter, _name, _stat)
+
+static const struct iavf_stats iavf_gstrings_stats[] = {
+ VF_STAT("rx_bytes", current_stats.rx_bytes),
+ VF_STAT("rx_unicast", current_stats.rx_unicast),
+ VF_STAT("rx_multicast", current_stats.rx_multicast),
+ VF_STAT("rx_broadcast", current_stats.rx_broadcast),
+ VF_STAT("rx_discards", current_stats.rx_discards),
+ VF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol),
+ VF_STAT("tx_bytes", current_stats.tx_bytes),
+ VF_STAT("tx_unicast", current_stats.tx_unicast),
+ VF_STAT("tx_multicast", current_stats.tx_multicast),
+ VF_STAT("tx_broadcast", current_stats.tx_broadcast),
+ VF_STAT("tx_discards", current_stats.tx_discards),
+ VF_STAT("tx_errors", current_stats.tx_errors),
+};
+
+#define IAVF_STATS_LEN ARRAY_SIZE(iavf_gstrings_stats)
+
+#define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats)
+
+/* For now we have one and only one private flag and it is only defined
+ * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead
+ * of leaving all this code sitting around empty we will strip it unless
+ * our one private flag is actually available.
+ */
+struct iavf_priv_flags {
+ char flag_string[ETH_GSTRING_LEN];
+ u32 flag;
+ bool read_only;
+};
+
+#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \
+ .flag_string = _name, \
+ .flag = _flag, \
+ .read_only = _read_only, \
+}
+
+static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = {
+ IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0),
+};
+
+#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags)
+
+/**
+ * iavf_get_link_ksettings - Get Link Speed and Duplex settings
+ * @netdev: network interface device structure
+ * @cmd: ethtool command
+ *
+ * Reports speed/duplex settings. Because this is a VF, we don't know what
+ * kind of link we really have, so we fake it.
+ **/
+static int iavf_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ cmd->base.port = PORT_NONE;
+ /* Set speed and duplex */
+ switch (adapter->link_speed) {
+ case IAVF_LINK_SPEED_40GB:
+ cmd->base.speed = SPEED_40000;
+ break;
+ case IAVF_LINK_SPEED_25GB:
+#ifdef SPEED_25000
+ cmd->base.speed = SPEED_25000;
+#else
+ netdev_info(netdev,
+ "Speed is 25G, display not supported by this version of ethtool.\n");
+#endif
+ break;
+ case IAVF_LINK_SPEED_20GB:
+ cmd->base.speed = SPEED_20000;
+ break;
+ case IAVF_LINK_SPEED_10GB:
+ cmd->base.speed = SPEED_10000;
+ break;
+ case IAVF_LINK_SPEED_1GB:
+ cmd->base.speed = SPEED_1000;
+ break;
+ case IAVF_LINK_SPEED_100MB:
+ cmd->base.speed = SPEED_100;
+ break;
+ default:
+ break;
+ }
+ cmd->base.duplex = DUPLEX_FULL;
+
+ return 0;
+}
+
+/**
+ * iavf_get_sset_count - Get length of string set
+ * @netdev: network interface device structure
+ * @sset: id of string set
+ *
+ * Reports size of various string tables.
+ **/
+static int iavf_get_sset_count(struct net_device *netdev, int sset)
+{
+ if (sset == ETH_SS_STATS)
+ return IAVF_STATS_LEN +
+ (IAVF_QUEUE_STATS_LEN * 2 * IAVF_MAX_REQ_QUEUES);
+ else if (sset == ETH_SS_PRIV_FLAGS)
+ return IAVF_PRIV_FLAGS_STR_LEN;
+ else
+ return -EINVAL;
+}
+
+/**
+ * iavf_get_ethtool_stats - report device statistics
+ * @netdev: network interface device structure
+ * @stats: ethtool statistics structure
+ * @data: pointer to data buffer
+ *
+ * All statistics are added to the data buffer as an array of u64.
+ **/
+static void iavf_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ unsigned int i;
+
+ iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats);
+
+ rcu_read_lock();
+ for (i = 0; i < IAVF_MAX_REQ_QUEUES; i++) {
+ struct iavf_ring *ring;
+
+ /* Avoid accessing un-allocated queues */
+ ring = (i < adapter->num_active_queues ?
+ &adapter->tx_rings[i] : NULL);
+ iavf_add_queue_stats(&data, ring);
+
+ /* Avoid accessing un-allocated queues */
+ ring = (i < adapter->num_active_queues ?
+ &adapter->rx_rings[i] : NULL);
+ iavf_add_queue_stats(&data, ring);
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * iavf_get_priv_flag_strings - Get private flag strings
+ * @netdev: network interface device structure
+ * @data: buffer for string data
+ *
+ * Builds the private flags string table
+ **/
+static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data)
+{
+ unsigned int i;
+
+ for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) {
+ snprintf(data, ETH_GSTRING_LEN, "%s",
+ iavf_gstrings_priv_flags[i].flag_string);
+ data += ETH_GSTRING_LEN;
+ }
+}
+
+/**
+ * iavf_get_stat_strings - Get stat strings
+ * @netdev: network interface device structure
+ * @data: buffer for string data
+ *
+ * Builds the statistics string table
+ **/
+static void iavf_get_stat_strings(struct net_device *netdev, u8 *data)
+{
+ unsigned int i;
+
+ iavf_add_stat_strings(&data, iavf_gstrings_stats);
+
+ /* Queues are always allocated in pairs, so we just use num_tx_queues
+ * for both Tx and Rx queues.
+ */
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ iavf_add_stat_strings(&data, iavf_gstrings_queue_stats,
+ "tx", i);
+ iavf_add_stat_strings(&data, iavf_gstrings_queue_stats,
+ "rx", i);
+ }
+}
+
+/**
+ * iavf_get_strings - Get string set
+ * @netdev: network interface device structure
+ * @sset: id of string set
+ * @data: buffer for string data
+ *
+ * Builds string tables for various string sets
+ **/
+static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ iavf_get_stat_strings(netdev, data);
+ break;
+ case ETH_SS_PRIV_FLAGS:
+ iavf_get_priv_flag_strings(netdev, data);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * iavf_get_priv_flags - report device private flags
+ * @netdev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned. Add new strings for each flag to the iavf_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ **/
+static u32 iavf_get_priv_flags(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ u32 i, ret_flags = 0;
+
+ for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) {
+ const struct iavf_priv_flags *priv_flags;
+
+ priv_flags = &iavf_gstrings_priv_flags[i];
+
+ if (priv_flags->flag & adapter->flags)
+ ret_flags |= BIT(i);
+ }
+
+ return ret_flags;
+}
+
+/**
+ * iavf_set_priv_flags - set private flags
+ * @netdev: network interface device structure
+ * @flags: bit flags to be set
+ **/
+static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ u32 orig_flags, new_flags, changed_flags;
+ u32 i;
+
+ orig_flags = READ_ONCE(adapter->flags);
+ new_flags = orig_flags;
+
+ for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) {
+ const struct iavf_priv_flags *priv_flags;
+
+ priv_flags = &iavf_gstrings_priv_flags[i];
+
+ if (flags & BIT(i))
+ new_flags |= priv_flags->flag;
+ else
+ new_flags &= ~(priv_flags->flag);
+
+ if (priv_flags->read_only &&
+ ((orig_flags ^ new_flags) & ~BIT(i)))
+ return -EOPNOTSUPP;
+ }
+
+ /* Before we finalize any flag changes, any checks which we need to
+ * perform to determine if the new flags will be supported should go
+ * here...
+ */
+
+ /* Compare and exchange the new flags into place. If we failed, that
+ * is if cmpxchg returns anything but the old value, this means
+ * something else must have modified the flags variable since we
+ * copied it. We'll just punt with an error and log something in the
+ * message buffer.
+ */
+ if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) {
+ dev_warn(&adapter->pdev->dev,
+ "Unable to update adapter->flags as it was modified by another thread...\n");
+ return -EAGAIN;
+ }
+
+ changed_flags = orig_flags ^ new_flags;
+
+ /* Process any additional changes needed as a result of flag changes.
+ * The changed_flags value reflects the list of bits that were changed
+ * in the code above.
+ */
+
+ /* issue a reset to force legacy-rx change to take effect */
+ if (changed_flags & IAVF_FLAG_LEGACY_RX) {
+ if (netif_running(netdev)) {
+ adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+ queue_work(iavf_wq, &adapter->reset_task);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * iavf_get_msglevel - Get debug message level
+ * @netdev: network interface device structure
+ *
+ * Returns current debug message level.
+ **/
+static u32 iavf_get_msglevel(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ return adapter->msg_enable;
+}
+
+/**
+ * iavf_set_msglevel - Set debug message level
+ * @netdev: network interface device structure
+ * @data: message level
+ *
+ * Set current debug message level. Higher values cause the driver to
+ * be noisier.
+ **/
+static void iavf_set_msglevel(struct net_device *netdev, u32 data)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ if (IAVF_DEBUG_USER & data)
+ adapter->hw.debug_mask = data;
+ adapter->msg_enable = data;
+}
+
+/**
+ * iavf_get_drvinfo - Get driver info
+ * @netdev: network interface device structure
+ * @drvinfo: ethool driver info structure
+ *
+ * Returns information about the driver and device for display to the user.
+ **/
+static void iavf_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ strlcpy(drvinfo->driver, iavf_driver_name, 32);
+ strlcpy(drvinfo->version, iavf_driver_version, 32);
+ strlcpy(drvinfo->fw_version, "N/A", 4);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN;
+}
+
+/**
+ * iavf_get_ringparam - Get ring parameters
+ * @netdev: network interface device structure
+ * @ring: ethtool ringparam structure
+ *
+ * Returns current ring parameters. TX and RX rings are reported separately,
+ * but the number of rings is not reported.
+ **/
+static void iavf_get_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ ring->rx_max_pending = IAVF_MAX_RXD;
+ ring->tx_max_pending = IAVF_MAX_TXD;
+ ring->rx_pending = adapter->rx_desc_count;
+ ring->tx_pending = adapter->tx_desc_count;
+}
+
+/**
+ * iavf_set_ringparam - Set ring parameters
+ * @netdev: network interface device structure
+ * @ring: ethtool ringparam structure
+ *
+ * Sets ring parameters. TX and RX rings are controlled separately, but the
+ * number of rings is not specified, so all rings get the same settings.
+ **/
+static int iavf_set_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ u32 new_rx_count, new_tx_count;
+
+ if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
+ return -EINVAL;
+
+ new_tx_count = clamp_t(u32, ring->tx_pending,
+ IAVF_MIN_TXD,
+ IAVF_MAX_TXD);
+ new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+
+ new_rx_count = clamp_t(u32, ring->rx_pending,
+ IAVF_MIN_RXD,
+ IAVF_MAX_RXD);
+ new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+
+ /* if nothing to do return success */
+ if ((new_tx_count == adapter->tx_desc_count) &&
+ (new_rx_count == adapter->rx_desc_count))
+ return 0;
+
+ adapter->tx_desc_count = new_tx_count;
+ adapter->rx_desc_count = new_rx_count;
+
+ if (netif_running(netdev)) {
+ adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+ queue_work(iavf_wq, &adapter->reset_task);
+ }
+
+ return 0;
+}
+
+/**
+ * __iavf_get_coalesce - get per-queue coalesce settings
+ * @netdev: the netdev to check
+ * @ec: ethtool coalesce data structure
+ * @queue: which queue to pick
+ *
+ * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs
+ * are per queue. If queue is <0 then we default to queue 0 as the
+ * representative value.
+ **/
+static int __iavf_get_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec, int queue)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_vsi *vsi = &adapter->vsi;
+ struct iavf_ring *rx_ring, *tx_ring;
+
+ ec->tx_max_coalesced_frames = vsi->work_limit;
+ ec->rx_max_coalesced_frames = vsi->work_limit;
+
+ /* Rx and Tx usecs per queue value. If user doesn't specify the
+ * queue, return queue 0's value to represent.
+ */
+ if (queue < 0)
+ queue = 0;
+ else if (queue >= adapter->num_active_queues)
+ return -EINVAL;
+
+ rx_ring = &adapter->rx_rings[queue];
+ tx_ring = &adapter->tx_rings[queue];
+
+ if (ITR_IS_DYNAMIC(rx_ring->itr_setting))
+ ec->use_adaptive_rx_coalesce = 1;
+
+ if (ITR_IS_DYNAMIC(tx_ring->itr_setting))
+ ec->use_adaptive_tx_coalesce = 1;
+
+ ec->rx_coalesce_usecs = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+ ec->tx_coalesce_usecs = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+
+ return 0;
+}
+
+/**
+ * iavf_get_coalesce - Get interrupt coalescing settings
+ * @netdev: network interface device structure
+ * @ec: ethtool coalesce structure
+ *
+ * Returns current coalescing settings. This is referred to elsewhere in the
+ * driver as Interrupt Throttle Rate, as this is how the hardware describes
+ * this functionality. Note that if per-queue settings have been modified this
+ * only represents the settings of queue 0.
+ **/
+static int iavf_get_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ return __iavf_get_coalesce(netdev, ec, -1);
+}
+
+/**
+ * iavf_get_per_queue_coalesce - get coalesce values for specific queue
+ * @netdev: netdev to read
+ * @ec: coalesce settings from ethtool
+ * @queue: the queue to read
+ *
+ * Read specific queue's coalesce settings.
+ **/
+static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
+ struct ethtool_coalesce *ec)
+{
+ return __iavf_get_coalesce(netdev, ec, queue);
+}
+
+/**
+ * iavf_set_itr_per_queue - set ITR values for specific queue
+ * @adapter: the VF adapter struct to set values for
+ * @ec: coalesce settings from ethtool
+ * @queue: the queue to modify
+ *
+ * Change the ITR settings for a specific queue.
+ **/
+static void iavf_set_itr_per_queue(struct iavf_adapter *adapter,
+ struct ethtool_coalesce *ec, int queue)
+{
+ struct iavf_ring *rx_ring = &adapter->rx_rings[queue];
+ struct iavf_ring *tx_ring = &adapter->tx_rings[queue];
+ struct iavf_q_vector *q_vector;
+
+ rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
+ tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
+
+ rx_ring->itr_setting |= IAVF_ITR_DYNAMIC;
+ if (!ec->use_adaptive_rx_coalesce)
+ rx_ring->itr_setting ^= IAVF_ITR_DYNAMIC;
+
+ tx_ring->itr_setting |= IAVF_ITR_DYNAMIC;
+ if (!ec->use_adaptive_tx_coalesce)
+ tx_ring->itr_setting ^= IAVF_ITR_DYNAMIC;
+
+ q_vector = rx_ring->q_vector;
+ q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
+
+ q_vector = tx_ring->q_vector;
+ q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
+
+ /* The interrupt handler itself will take care of programming
+ * the Tx and Rx ITR values based on the values we have entered
+ * into the q_vector, no need to write the values now.
+ */
+}
+
+/**
+ * __iavf_set_coalesce - set coalesce settings for particular queue
+ * @netdev: the netdev to change
+ * @ec: ethtool coalesce settings
+ * @queue: the queue to change
+ *
+ * Sets the coalesce settings for a particular queue.
+ **/
+static int __iavf_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec, int queue)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_vsi *vsi = &adapter->vsi;
+ int i;
+
+ if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+ vsi->work_limit = ec->tx_max_coalesced_frames_irq;
+
+ if (ec->rx_coalesce_usecs == 0) {
+ if (ec->use_adaptive_rx_coalesce)
+ netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n");
+ } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) ||
+ (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) {
+ netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
+ return -EINVAL;
+ } else if (ec->tx_coalesce_usecs == 0) {
+ if (ec->use_adaptive_tx_coalesce)
+ netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n");
+ } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) ||
+ (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) {
+ netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n");
+ return -EINVAL;
+ }
+
+ /* Rx and Tx usecs has per queue value. If user doesn't specify the
+ * queue, apply to all queues.
+ */
+ if (queue < 0) {
+ for (i = 0; i < adapter->num_active_queues; i++)
+ iavf_set_itr_per_queue(adapter, ec, i);
+ } else if (queue < adapter->num_active_queues) {
+ iavf_set_itr_per_queue(adapter, ec, queue);
+ } else {
+ netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n",
+ adapter->num_active_queues - 1);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * iavf_set_coalesce - Set interrupt coalescing settings
+ * @netdev: network interface device structure
+ * @ec: ethtool coalesce structure
+ *
+ * Change current coalescing settings for every queue.
+ **/
+static int iavf_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ return __iavf_set_coalesce(netdev, ec, -1);
+}
+
+/**
+ * iavf_set_per_queue_coalesce - set specific queue's coalesce settings
+ * @netdev: the netdev to change
+ * @ec: ethtool's coalesce settings
+ * @queue: the queue to modify
+ *
+ * Modifies a specific queue's coalesce settings.
+ */
+static int iavf_set_per_queue_coalesce(struct net_device *netdev, u32 queue,
+ struct ethtool_coalesce *ec)
+{
+ return __iavf_set_coalesce(netdev, ec, queue);
+}
+
+/**
+ * iavf_get_rxnfc - command to get RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ * @rule_locs: pointer to store rule locations
+ *
+ * Returns Success if the command is supported.
+ **/
+static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_GRXRINGS:
+ cmd->data = adapter->num_active_queues;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXFH:
+ netdev_info(netdev,
+ "RSS hash info is not available to vf, use pf.\n");
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+/**
+ * iavf_get_channels: get the number of channels supported by the device
+ * @netdev: network interface device structure
+ * @ch: channel information structure
+ *
+ * For the purposes of our device, we only use combined channels, i.e. a tx/rx
+ * queue pair. Report one extra channel to match our "other" MSI-X vector.
+ **/
+static void iavf_get_channels(struct net_device *netdev,
+ struct ethtool_channels *ch)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ /* Report maximum channels */
+ ch->max_combined = IAVF_MAX_REQ_QUEUES;
+
+ ch->max_other = NONQ_VECS;
+ ch->other_count = NONQ_VECS;
+
+ ch->combined_count = adapter->num_active_queues;
+}
+
+/**
+ * iavf_set_channels: set the new channel count
+ * @netdev: network interface device structure
+ * @ch: channel information structure
+ *
+ * Negotiate a new number of channels with the PF then do a reset. During
+ * reset we'll realloc queues and fix the RSS table. Returns 0 on success,
+ * negative on failure.
+ **/
+static int iavf_set_channels(struct net_device *netdev,
+ struct ethtool_channels *ch)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ int num_req = ch->combined_count;
+
+ if (num_req != adapter->num_active_queues &&
+ !(adapter->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) {
+ dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n");
+ return -EINVAL;
+ }
+
+ if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
+ adapter->num_tc) {
+ dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n");
+ return -EINVAL;
+ }
+
+ /* All of these should have already been checked by ethtool before this
+ * even gets to us, but just to be sure.
+ */
+ if (num_req <= 0 || num_req > IAVF_MAX_REQ_QUEUES)
+ return -EINVAL;
+
+ if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS)
+ return -EINVAL;
+
+ adapter->num_req_queues = num_req;
+ return iavf_request_queues(adapter, num_req);
+}
+
+/**
+ * iavf_get_rxfh_key_size - get the RSS hash key size
+ * @netdev: network interface device structure
+ *
+ * Returns the table size.
+ **/
+static u32 iavf_get_rxfh_key_size(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ return adapter->rss_key_size;
+}
+
+/**
+ * iavf_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * @netdev: network interface device structure
+ *
+ * Returns the table size.
+ **/
+static u32 iavf_get_rxfh_indir_size(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ return adapter->rss_lut_size;
+}
+
+/**
+ * iavf_get_rxfh - get the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key
+ * @hfunc: hash function in use
+ *
+ * Reads the indirection table directly from the hardware. Always returns 0.
+ **/
+static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+ u8 *hfunc)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ u16 i;
+
+ if (hfunc)
+ *hfunc = ETH_RSS_HASH_TOP;
+ if (!indir)
+ return 0;
+
+ memcpy(key, adapter->rss_key, adapter->rss_key_size);
+
+ /* Each 32 bits pointed by 'indir' is stored with a lut entry */
+ for (i = 0; i < adapter->rss_lut_size; i++)
+ indir[i] = (u32)adapter->rss_lut[i];
+
+ return 0;
+}
+
+/**
+ * iavf_set_rxfh - set the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key
+ * @hfunc: hash function to use
+ *
+ * Returns -EINVAL if the table specifies an inavlid queue id, otherwise
+ * returns 0 after programming the table.
+ **/
+static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir,
+ const u8 *key, const u8 hfunc)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ u16 i;
+
+ /* We do not allow change in unsupported parameters */
+ if (key ||
+ (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+ return -EOPNOTSUPP;
+ if (!indir)
+ return 0;
+
+ if (key)
+ memcpy(adapter->rss_key, key, adapter->rss_key_size);
+
+ /* Each 32 bits pointed by 'indir' is stored with a lut entry */
+ for (i = 0; i < adapter->rss_lut_size; i++)
+ adapter->rss_lut[i] = (u8)(indir[i]);
+
+ return iavf_config_rss(adapter);
+}
+
+static const struct ethtool_ops iavf_ethtool_ops = {
+ .get_drvinfo = iavf_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_ringparam = iavf_get_ringparam,
+ .set_ringparam = iavf_set_ringparam,
+ .get_strings = iavf_get_strings,
+ .get_ethtool_stats = iavf_get_ethtool_stats,
+ .get_sset_count = iavf_get_sset_count,
+ .get_priv_flags = iavf_get_priv_flags,
+ .set_priv_flags = iavf_set_priv_flags,
+ .get_msglevel = iavf_get_msglevel,
+ .set_msglevel = iavf_set_msglevel,
+ .get_coalesce = iavf_get_coalesce,
+ .set_coalesce = iavf_set_coalesce,
+ .get_per_queue_coalesce = iavf_get_per_queue_coalesce,
+ .set_per_queue_coalesce = iavf_set_per_queue_coalesce,
+ .get_rxnfc = iavf_get_rxnfc,
+ .get_rxfh_indir_size = iavf_get_rxfh_indir_size,
+ .get_rxfh = iavf_get_rxfh,
+ .set_rxfh = iavf_set_rxfh,
+ .get_channels = iavf_get_channels,
+ .set_channels = iavf_set_channels,
+ .get_rxfh_key_size = iavf_get_rxfh_key_size,
+ .get_link_ksettings = iavf_get_link_ksettings,
+};
+
+/**
+ * iavf_set_ethtool_ops - Initialize ethtool ops struct
+ * @netdev: network interface device structure
+ *
+ * Sets ethtool ops struct in our netdev so that ethtool can call
+ * our functions.
+ **/
+void iavf_set_ethtool_ops(struct net_device *netdev)
+{
+ netdev->ethtool_ops = &iavf_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
new file mode 100644
index 0000000..821987d
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -0,0 +1,3990 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "iavf.h"
+#include "iavf_prototype.h"
+#include "iavf_client.h"
+/* All iavf tracepoints are defined by the include below, which must
+ * be included exactly once across the whole kernel with
+ * CREATE_TRACE_POINTS defined
+ */
+#define CREATE_TRACE_POINTS
+#include "iavf_trace.h"
+
+static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter);
+static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter);
+static int iavf_close(struct net_device *netdev);
+static int iavf_init_get_resources(struct iavf_adapter *adapter);
+static int iavf_check_reset_complete(struct iavf_hw *hw);
+
+char iavf_driver_name[] = "iavf";
+static const char iavf_driver_string[] =
+ "Intel(R) Ethernet Adaptive Virtual Function Network Driver";
+
+#define DRV_KERN "-k"
+
+#define DRV_VERSION_MAJOR 3
+#define DRV_VERSION_MINOR 2
+#define DRV_VERSION_BUILD 3
+#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
+ __stringify(DRV_VERSION_MINOR) "." \
+ __stringify(DRV_VERSION_BUILD) \
+ DRV_KERN
+const char iavf_driver_version[] = DRV_VERSION;
+static const char iavf_copyright[] =
+ "Copyright (c) 2013 - 2018 Intel Corporation.";
+
+/* iavf_pci_tbl - PCI Device ID Table
+ *
+ * Wildcard entries (PCI_ANY_ID) should come last
+ * Last entry must be all 0s
+ *
+ * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
+ * Class, Class Mask, private data (not used) }
+ */
+static const struct pci_device_id iavf_pci_tbl[] = {
+ {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF), 0},
+ {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF_HV), 0},
+ {PCI_VDEVICE(INTEL, IAVF_DEV_ID_X722_VF), 0},
+ {PCI_VDEVICE(INTEL, IAVF_DEV_ID_ADAPTIVE_VF), 0},
+ /* required last entry */
+ {0, }
+};
+
+MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);
+
+MODULE_ALIAS("i40evf");
+MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
+MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+
+static const struct net_device_ops iavf_netdev_ops;
+struct workqueue_struct *iavf_wq;
+
+/**
+ * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to fill out
+ * @size: size of memory requested
+ * @alignment: what to align the allocation to
+ **/
+enum iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw,
+ struct iavf_dma_mem *mem,
+ u64 size, u32 alignment)
+{
+ struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back;
+
+ if (!mem)
+ return IAVF_ERR_PARAM;
+
+ mem->size = ALIGN(size, alignment);
+ mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size,
+ (dma_addr_t *)&mem->pa, GFP_KERNEL);
+ if (mem->va)
+ return 0;
+ else
+ return IAVF_ERR_NO_MEMORY;
+}
+
+/**
+ * iavf_free_dma_mem_d - OS specific memory free for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to free
+ **/
+enum iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw,
+ struct iavf_dma_mem *mem)
+{
+ struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back;
+
+ if (!mem || !mem->va)
+ return IAVF_ERR_PARAM;
+ dma_free_coherent(&adapter->pdev->dev, mem->size,
+ mem->va, (dma_addr_t)mem->pa);
+ return 0;
+}
+
+/**
+ * iavf_allocate_virt_mem_d - OS specific memory alloc for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to fill out
+ * @size: size of memory requested
+ **/
+enum iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw,
+ struct iavf_virt_mem *mem, u32 size)
+{
+ if (!mem)
+ return IAVF_ERR_PARAM;
+
+ mem->size = size;
+ mem->va = kzalloc(size, GFP_KERNEL);
+
+ if (mem->va)
+ return 0;
+ else
+ return IAVF_ERR_NO_MEMORY;
+}
+
+/**
+ * iavf_free_virt_mem_d - OS specific memory free for shared code
+ * @hw: pointer to the HW structure
+ * @mem: ptr to mem struct to free
+ **/
+enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw,
+ struct iavf_virt_mem *mem)
+{
+ if (!mem)
+ return IAVF_ERR_PARAM;
+
+ /* it's ok to kfree a NULL pointer */
+ kfree(mem->va);
+
+ return 0;
+}
+
+/**
+ * iavf_schedule_reset - Set the flags and schedule a reset event
+ * @adapter: board private structure
+ **/
+void iavf_schedule_reset(struct iavf_adapter *adapter)
+{
+ if (!(adapter->flags &
+ (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
+ adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+ queue_work(iavf_wq, &adapter->reset_task);
+ }
+}
+
+/**
+ * iavf_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ **/
+static void iavf_tx_timeout(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ adapter->tx_timeout_count++;
+ iavf_schedule_reset(adapter);
+}
+
+/**
+ * iavf_misc_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ **/
+static void iavf_misc_irq_disable(struct iavf_adapter *adapter)
+{
+ struct iavf_hw *hw = &adapter->hw;
+
+ if (!adapter->msix_entries)
+ return;
+
+ wr32(hw, IAVF_VFINT_DYN_CTL01, 0);
+
+ iavf_flush(hw);
+
+ synchronize_irq(adapter->msix_entries[0].vector);
+}
+
+/**
+ * iavf_misc_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ **/
+static void iavf_misc_irq_enable(struct iavf_adapter *adapter)
+{
+ struct iavf_hw *hw = &adapter->hw;
+
+ wr32(hw, IAVF_VFINT_DYN_CTL01, IAVF_VFINT_DYN_CTL01_INTENA_MASK |
+ IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK);
+ wr32(hw, IAVF_VFINT_ICR0_ENA1, IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK);
+
+ iavf_flush(hw);
+}
+
+/**
+ * iavf_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ **/
+static void iavf_irq_disable(struct iavf_adapter *adapter)
+{
+ int i;
+ struct iavf_hw *hw = &adapter->hw;
+
+ if (!adapter->msix_entries)
+ return;
+
+ for (i = 1; i < adapter->num_msix_vectors; i++) {
+ wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), 0);
+ synchronize_irq(adapter->msix_entries[i].vector);
+ }
+ iavf_flush(hw);
+}
+
+/**
+ * iavf_irq_enable_queues - Enable interrupt for specified queues
+ * @adapter: board private structure
+ * @mask: bitmap of queues to enable
+ **/
+void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask)
+{
+ struct iavf_hw *hw = &adapter->hw;
+ int i;
+
+ for (i = 1; i < adapter->num_msix_vectors; i++) {
+ if (mask & BIT(i - 1)) {
+ wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1),
+ IAVF_VFINT_DYN_CTLN1_INTENA_MASK |
+ IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK);
+ }
+ }
+}
+
+/**
+ * iavf_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ * @flush: boolean value whether to run rd32()
+ **/
+void iavf_irq_enable(struct iavf_adapter *adapter, bool flush)
+{
+ struct iavf_hw *hw = &adapter->hw;
+
+ iavf_misc_irq_enable(adapter);
+ iavf_irq_enable_queues(adapter, ~0);
+
+ if (flush)
+ iavf_flush(hw);
+}
+
+/**
+ * iavf_msix_aq - Interrupt handler for vector 0
+ * @irq: interrupt number
+ * @data: pointer to netdev
+ **/
+static irqreturn_t iavf_msix_aq(int irq, void *data)
+{
+ struct net_device *netdev = data;
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_hw *hw = &adapter->hw;
+
+ /* handle non-queue interrupts, these reads clear the registers */
+ rd32(hw, IAVF_VFINT_ICR01);
+ rd32(hw, IAVF_VFINT_ICR0_ENA1);
+
+ /* schedule work on the private workqueue */
+ queue_work(iavf_wq, &adapter->adminq_task);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * iavf_msix_clean_rings - MSIX mode Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ **/
+static irqreturn_t iavf_msix_clean_rings(int irq, void *data)
+{
+ struct iavf_q_vector *q_vector = data;
+
+ if (!q_vector->tx.ring && !q_vector->rx.ring)
+ return IRQ_HANDLED;
+
+ napi_schedule_irqoff(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * iavf_map_vector_to_rxq - associate irqs with rx queues
+ * @adapter: board private structure
+ * @v_idx: interrupt number
+ * @r_idx: queue number
+ **/
+static void
+iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx)
+{
+ struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx];
+ struct iavf_ring *rx_ring = &adapter->rx_rings[r_idx];
+ struct iavf_hw *hw = &adapter->hw;
+
+ rx_ring->q_vector = q_vector;
+ rx_ring->next = q_vector->rx.ring;
+ rx_ring->vsi = &adapter->vsi;
+ q_vector->rx.ring = rx_ring;
+ q_vector->rx.count++;
+ q_vector->rx.next_update = jiffies + 1;
+ q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
+ q_vector->ring_mask |= BIT(r_idx);
+ wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx),
+ q_vector->rx.current_itr >> 1);
+ q_vector->rx.current_itr = q_vector->rx.target_itr;
+}
+
+/**
+ * iavf_map_vector_to_txq - associate irqs with tx queues
+ * @adapter: board private structure
+ * @v_idx: interrupt number
+ * @t_idx: queue number
+ **/
+static void
+iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx)
+{
+ struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx];
+ struct iavf_ring *tx_ring = &adapter->tx_rings[t_idx];
+ struct iavf_hw *hw = &adapter->hw;
+
+ tx_ring->q_vector = q_vector;
+ tx_ring->next = q_vector->tx.ring;
+ tx_ring->vsi = &adapter->vsi;
+ q_vector->tx.ring = tx_ring;
+ q_vector->tx.count++;
+ q_vector->tx.next_update = jiffies + 1;
+ q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
+ q_vector->num_ringpairs++;
+ wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx),
+ q_vector->tx.target_itr >> 1);
+ q_vector->tx.current_itr = q_vector->tx.target_itr;
+}
+
+/**
+ * iavf_map_rings_to_vectors - Maps descriptor rings to vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function maps descriptor rings to the queue-specific vectors
+ * we were allotted through the MSI-X enabling code. Ideally, we'd have
+ * one vector per ring/queue, but on a constrained vector budget, we
+ * group the rings as "efficiently" as possible. You would add new
+ * mapping configurations in here.
+ **/
+static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter)
+{
+ int rings_remaining = adapter->num_active_queues;
+ int ridx = 0, vidx = 0;
+ int q_vectors;
+
+ q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+
+ for (; ridx < rings_remaining; ridx++) {
+ iavf_map_vector_to_rxq(adapter, vidx, ridx);
+ iavf_map_vector_to_txq(adapter, vidx, ridx);
+
+ /* In the case where we have more queues than vectors, continue
+ * round-robin on vectors until all queues are mapped.
+ */
+ if (++vidx >= q_vectors)
+ vidx = 0;
+ }
+
+ adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
+}
+
+/**
+ * iavf_irq_affinity_notify - Callback for affinity changes
+ * @notify: context as to what irq was changed
+ * @mask: the new affinity mask
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * so that we may register to receive changes to the irq affinity masks.
+ **/
+static void iavf_irq_affinity_notify(struct irq_affinity_notify *notify,
+ const cpumask_t *mask)
+{
+ struct iavf_q_vector *q_vector =
+ container_of(notify, struct iavf_q_vector, affinity_notify);
+
+ cpumask_copy(&q_vector->affinity_mask, mask);
+}
+
+/**
+ * iavf_irq_affinity_release - Callback for affinity notifier release
+ * @ref: internal core kernel usage
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * to inform the current notification subscriber that they will no longer
+ * receive notifications.
+ **/
+static void iavf_irq_affinity_release(struct kref *ref) {}
+
+/**
+ * iavf_request_traffic_irqs - Initialize MSI-X interrupts
+ * @adapter: board private structure
+ * @basename: device basename
+ *
+ * Allocates MSI-X vectors for tx and rx handling, and requests
+ * interrupts from the kernel.
+ **/
+static int
+iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename)
+{
+ unsigned int vector, q_vectors;
+ unsigned int rx_int_idx = 0, tx_int_idx = 0;
+ int irq_num, err;
+ int cpu;
+
+ iavf_irq_disable(adapter);
+ /* Decrement for Other and TCP Timer vectors */
+ q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+
+ for (vector = 0; vector < q_vectors; vector++) {
+ struct iavf_q_vector *q_vector = &adapter->q_vectors[vector];
+
+ irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
+
+ if (q_vector->tx.ring && q_vector->rx.ring) {
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "iavf-%s-TxRx-%d", basename, rx_int_idx++);
+ tx_int_idx++;
+ } else if (q_vector->rx.ring) {
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "iavf-%s-rx-%d", basename, rx_int_idx++);
+ } else if (q_vector->tx.ring) {
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "iavf-%s-tx-%d", basename, tx_int_idx++);
+ } else {
+ /* skip this unused q_vector */
+ continue;
+ }
+ err = request_irq(irq_num,
+ iavf_msix_clean_rings,
+ 0,
+ q_vector->name,
+ q_vector);
+ if (err) {
+ dev_info(&adapter->pdev->dev,
+ "Request_irq failed, error: %d\n", err);
+ goto free_queue_irqs;
+ }
+ /* register for affinity change notifications */
+ q_vector->affinity_notify.notify = iavf_irq_affinity_notify;
+ q_vector->affinity_notify.release =
+ iavf_irq_affinity_release;
+ irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
+ /* Spread the IRQ affinity hints across online CPUs. Note that
+ * get_cpu_mask returns a mask with a permanent lifetime so
+ * it's safe to use as a hint for irq_set_affinity_hint.
+ */
+ cpu = cpumask_local_spread(q_vector->v_idx, -1);
+ irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
+ }
+
+ return 0;
+
+free_queue_irqs:
+ while (vector) {
+ vector--;
+ irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
+ irq_set_affinity_notifier(irq_num, NULL);
+ irq_set_affinity_hint(irq_num, NULL);
+ free_irq(irq_num, &adapter->q_vectors[vector]);
+ }
+ return err;
+}
+
+/**
+ * iavf_request_misc_irq - Initialize MSI-X interrupts
+ * @adapter: board private structure
+ *
+ * Allocates MSI-X vector 0 and requests interrupts from the kernel. This
+ * vector is only for the admin queue, and stays active even when the netdev
+ * is closed.
+ **/
+static int iavf_request_misc_irq(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int err;
+
+ snprintf(adapter->misc_vector_name,
+ sizeof(adapter->misc_vector_name) - 1, "iavf-%s:mbx",
+ dev_name(&adapter->pdev->dev));
+ err = request_irq(adapter->msix_entries[0].vector,
+ &iavf_msix_aq, 0,
+ adapter->misc_vector_name, netdev);
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "request_irq for %s failed: %d\n",
+ adapter->misc_vector_name, err);
+ free_irq(adapter->msix_entries[0].vector, netdev);
+ }
+ return err;
+}
+
+/**
+ * iavf_free_traffic_irqs - Free MSI-X interrupts
+ * @adapter: board private structure
+ *
+ * Frees all MSI-X vectors other than 0.
+ **/
+static void iavf_free_traffic_irqs(struct iavf_adapter *adapter)
+{
+ int vector, irq_num, q_vectors;
+
+ if (!adapter->msix_entries)
+ return;
+
+ q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+
+ for (vector = 0; vector < q_vectors; vector++) {
+ irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
+ irq_set_affinity_notifier(irq_num, NULL);
+ irq_set_affinity_hint(irq_num, NULL);
+ free_irq(irq_num, &adapter->q_vectors[vector]);
+ }
+}
+
+/**
+ * iavf_free_misc_irq - Free MSI-X miscellaneous vector
+ * @adapter: board private structure
+ *
+ * Frees MSI-X vector 0.
+ **/
+static void iavf_free_misc_irq(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+
+ if (!adapter->msix_entries)
+ return;
+
+ free_irq(adapter->msix_entries[0].vector, netdev);
+}
+
+/**
+ * iavf_configure_tx - Configure Transmit Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Tx unit of the MAC after a reset.
+ **/
+static void iavf_configure_tx(struct iavf_adapter *adapter)
+{
+ struct iavf_hw *hw = &adapter->hw;
+ int i;
+
+ for (i = 0; i < adapter->num_active_queues; i++)
+ adapter->tx_rings[i].tail = hw->hw_addr + IAVF_QTX_TAIL1(i);
+}
+
+/**
+ * iavf_configure_rx - Configure Receive Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ **/
+static void iavf_configure_rx(struct iavf_adapter *adapter)
+{
+ unsigned int rx_buf_len = IAVF_RXBUFFER_2048;
+ struct iavf_hw *hw = &adapter->hw;
+ int i;
+
+ /* Legacy Rx will always default to a 2048 buffer size. */
+#if (PAGE_SIZE < 8192)
+ if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) {
+ struct net_device *netdev = adapter->netdev;
+
+ /* For jumbo frames on systems with 4K pages we have to use
+ * an order 1 page, so we might as well increase the size
+ * of our Rx buffer to make better use of the available space
+ */
+ rx_buf_len = IAVF_RXBUFFER_3072;
+
+ /* We use a 1536 buffer size for configurations with
+ * standard Ethernet mtu. On x86 this gives us enough room
+ * for shared info and 192 bytes of padding.
+ */
+ if (!IAVF_2K_TOO_SMALL_WITH_PADDING &&
+ (netdev->mtu <= ETH_DATA_LEN))
+ rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN;
+ }
+#endif
+
+ for (i = 0; i < adapter->num_active_queues; i++) {
+ adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
+ adapter->rx_rings[i].rx_buf_len = rx_buf_len;
+
+ if (adapter->flags & IAVF_FLAG_LEGACY_RX)
+ clear_ring_build_skb_enabled(&adapter->rx_rings[i]);
+ else
+ set_ring_build_skb_enabled(&adapter->rx_rings[i]);
+ }
+}
+
+/**
+ * iavf_find_vlan - Search filter list for specific vlan filter
+ * @adapter: board private structure
+ * @vlan: vlan tag
+ *
+ * Returns ptr to the filter object or NULL. Must be called while holding the
+ * mac_vlan_list_lock.
+ **/
+static struct
+iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan)
+{
+ struct iavf_vlan_filter *f;
+
+ list_for_each_entry(f, &adapter->vlan_filter_list, list) {
+ if (vlan == f->vlan)
+ return f;
+ }
+ return NULL;
+}
+
+/**
+ * iavf_add_vlan - Add a vlan filter to the list
+ * @adapter: board private structure
+ * @vlan: VLAN tag
+ *
+ * Returns ptr to the filter object or NULL when no memory available.
+ **/
+static struct
+iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan)
+{
+ struct iavf_vlan_filter *f = NULL;
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ f = iavf_find_vlan(adapter, vlan);
+ if (!f) {
+ f = kzalloc(sizeof(*f), GFP_ATOMIC);
+ if (!f)
+ goto clearout;
+
+ f->vlan = vlan;
+
+ list_add_tail(&f->list, &adapter->vlan_filter_list);
+ f->add = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
+ }
+
+clearout:
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+ return f;
+}
+
+/**
+ * iavf_del_vlan - Remove a vlan filter from the list
+ * @adapter: board private structure
+ * @vlan: VLAN tag
+ **/
+static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan)
+{
+ struct iavf_vlan_filter *f;
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ f = iavf_find_vlan(adapter, vlan);
+ if (f) {
+ f->remove = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER;
+ }
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+}
+
+/**
+ * iavf_vlan_rx_add_vid - Add a VLAN filter to a device
+ * @netdev: network device struct
+ * @proto: unused protocol data
+ * @vid: VLAN tag
+ **/
+static int iavf_vlan_rx_add_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ if (!VLAN_ALLOWED(adapter))
+ return -EIO;
+ if (iavf_add_vlan(adapter, vid) == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
+/**
+ * iavf_vlan_rx_kill_vid - Remove a VLAN filter from a device
+ * @netdev: network device struct
+ * @proto: unused protocol data
+ * @vid: VLAN tag
+ **/
+static int iavf_vlan_rx_kill_vid(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ if (VLAN_ALLOWED(adapter)) {
+ iavf_del_vlan(adapter, vid);
+ return 0;
+ }
+ return -EIO;
+}
+
+/**
+ * iavf_find_filter - Search filter list for specific mac filter
+ * @adapter: board private structure
+ * @macaddr: the MAC address
+ *
+ * Returns ptr to the filter object or NULL. Must be called while holding the
+ * mac_vlan_list_lock.
+ **/
+static struct
+iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter,
+ const u8 *macaddr)
+{
+ struct iavf_mac_filter *f;
+
+ if (!macaddr)
+ return NULL;
+
+ list_for_each_entry(f, &adapter->mac_filter_list, list) {
+ if (ether_addr_equal(macaddr, f->macaddr))
+ return f;
+ }
+ return NULL;
+}
+
+/**
+ * iavf_add_filter - Add a mac filter to the filter list
+ * @adapter: board private structure
+ * @macaddr: the MAC address
+ *
+ * Returns ptr to the filter object or NULL when no memory available.
+ **/
+static struct
+iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
+ const u8 *macaddr)
+{
+ struct iavf_mac_filter *f;
+
+ if (!macaddr)
+ return NULL;
+
+ f = iavf_find_filter(adapter, macaddr);
+ if (!f) {
+ f = kzalloc(sizeof(*f), GFP_ATOMIC);
+ if (!f)
+ return f;
+
+ ether_addr_copy(f->macaddr, macaddr);
+
+ list_add_tail(&f->list, &adapter->mac_filter_list);
+ f->add = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
+ } else {
+ f->remove = false;
+ }
+
+ return f;
+}
+
+/**
+ * iavf_set_mac - NDO callback to set port mac address
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_set_mac(struct net_device *netdev, void *p)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_hw *hw = &adapter->hw;
+ struct iavf_mac_filter *f;
+ struct sockaddr *addr = p;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
+ return 0;
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ f = iavf_find_filter(adapter, hw->mac.addr);
+ if (f) {
+ f->remove = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER;
+ }
+
+ f = iavf_add_filter(adapter, addr->sa_data);
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ if (f) {
+ ether_addr_copy(hw->mac.addr, addr->sa_data);
+ }
+
+ return (f == NULL) ? -ENOMEM : 0;
+}
+
+/**
+ * iavf_addr_sync - Callback for dev_(mc|uc)_sync to add address
+ * @netdev: the netdevice
+ * @addr: address to add
+ *
+ * Called by __dev_(mc|uc)_sync when an address needs to be added. We call
+ * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
+ */
+static int iavf_addr_sync(struct net_device *netdev, const u8 *addr)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ if (iavf_add_filter(adapter, addr))
+ return 0;
+ else
+ return -ENOMEM;
+}
+
+/**
+ * iavf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address
+ * @netdev: the netdevice
+ * @addr: address to add
+ *
+ * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call
+ * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
+ */
+static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_mac_filter *f;
+
+ /* Under some circumstances, we might receive a request to delete
+ * our own device address from our uc list. Because we store the
+ * device address in the VSI's MAC/VLAN filter list, we need to ignore
+ * such requests and not delete our device address from this list.
+ */
+ if (ether_addr_equal(addr, netdev->dev_addr))
+ return 0;
+
+ f = iavf_find_filter(adapter, addr);
+ if (f) {
+ f->remove = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER;
+ }
+ return 0;
+}
+
+/**
+ * iavf_set_rx_mode - NDO callback to set the netdev filters
+ * @netdev: network interface device structure
+ **/
+static void iavf_set_rx_mode(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+ __dev_uc_sync(netdev, iavf_addr_sync, iavf_addr_unsync);
+ __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync);
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ if (netdev->flags & IFF_PROMISC &&
+ !(adapter->flags & IAVF_FLAG_PROMISC_ON))
+ adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC;
+ else if (!(netdev->flags & IFF_PROMISC) &&
+ adapter->flags & IAVF_FLAG_PROMISC_ON)
+ adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC;
+
+ if (netdev->flags & IFF_ALLMULTI &&
+ !(adapter->flags & IAVF_FLAG_ALLMULTI_ON))
+ adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI;
+ else if (!(netdev->flags & IFF_ALLMULTI) &&
+ adapter->flags & IAVF_FLAG_ALLMULTI_ON)
+ adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI;
+}
+
+/**
+ * iavf_napi_enable_all - enable NAPI on all queue vectors
+ * @adapter: board private structure
+ **/
+static void iavf_napi_enable_all(struct iavf_adapter *adapter)
+{
+ int q_idx;
+ struct iavf_q_vector *q_vector;
+ int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+
+ for (q_idx = 0; q_idx < q_vectors; q_idx++) {
+ struct napi_struct *napi;
+
+ q_vector = &adapter->q_vectors[q_idx];
+ napi = &q_vector->napi;
+ napi_enable(napi);
+ }
+}
+
+/**
+ * iavf_napi_disable_all - disable NAPI on all queue vectors
+ * @adapter: board private structure
+ **/
+static void iavf_napi_disable_all(struct iavf_adapter *adapter)
+{
+ int q_idx;
+ struct iavf_q_vector *q_vector;
+ int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+
+ for (q_idx = 0; q_idx < q_vectors; q_idx++) {
+ q_vector = &adapter->q_vectors[q_idx];
+ napi_disable(&q_vector->napi);
+ }
+}
+
+/**
+ * iavf_configure - set up transmit and receive data structures
+ * @adapter: board private structure
+ **/
+static void iavf_configure(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ iavf_set_rx_mode(netdev);
+
+ iavf_configure_tx(adapter);
+ iavf_configure_rx(adapter);
+ adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES;
+
+ for (i = 0; i < adapter->num_active_queues; i++) {
+ struct iavf_ring *ring = &adapter->rx_rings[i];
+
+ iavf_alloc_rx_buffers(ring, IAVF_DESC_UNUSED(ring));
+ }
+}
+
+/**
+ * iavf_up_complete - Finish the last steps of bringing up a connection
+ * @adapter: board private structure
+ *
+ * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock.
+ **/
+static void iavf_up_complete(struct iavf_adapter *adapter)
+{
+ adapter->state = __IAVF_RUNNING;
+ clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+
+ iavf_napi_enable_all(adapter);
+
+ adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES;
+ if (CLIENT_ENABLED(adapter))
+ adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN;
+ mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_down - Shutdown the connection processing
+ * @adapter: board private structure
+ *
+ * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock.
+ **/
+void iavf_down(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct iavf_vlan_filter *vlf;
+ struct iavf_mac_filter *f;
+ struct iavf_cloud_filter *cf;
+
+ if (adapter->state <= __IAVF_DOWN_PENDING)
+ return;
+
+ netif_carrier_off(netdev);
+ netif_tx_disable(netdev);
+ adapter->link_up = false;
+ iavf_napi_disable_all(adapter);
+ iavf_irq_disable(adapter);
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ /* clear the sync flag on all filters */
+ __dev_uc_unsync(adapter->netdev, NULL);
+ __dev_mc_unsync(adapter->netdev, NULL);
+
+ /* remove all MAC filters */
+ list_for_each_entry(f, &adapter->mac_filter_list, list) {
+ f->remove = true;
+ }
+
+ /* remove all VLAN filters */
+ list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
+ vlf->remove = true;
+ }
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ /* remove all cloud filters */
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ list_for_each_entry(cf, &adapter->cloud_filter_list, list) {
+ cf->del = true;
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+
+ if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) &&
+ adapter->state != __IAVF_RESETTING) {
+ /* cancel any current operation */
+ adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ /* Schedule operations to close down the HW. Don't wait
+ * here for this to complete. The watchdog is still running
+ * and it will take care of this.
+ */
+ adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER;
+ adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES;
+ }
+
+ mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_acquire_msix_vectors - Setup the MSIX capability
+ * @adapter: board private structure
+ * @vectors: number of vectors to request
+ *
+ * Work with the OS to set up the MSIX vectors needed.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int
+iavf_acquire_msix_vectors(struct iavf_adapter *adapter, int vectors)
+{
+ int err, vector_threshold;
+
+ /* We'll want at least 3 (vector_threshold):
+ * 0) Other (Admin Queue and link, mostly)
+ * 1) TxQ[0] Cleanup
+ * 2) RxQ[0] Cleanup
+ */
+ vector_threshold = MIN_MSIX_COUNT;
+
+ /* The more we get, the more we will assign to Tx/Rx Cleanup
+ * for the separate queues...where Rx Cleanup >= Tx Cleanup.
+ * Right now, we simply care about how many we'll get; we'll
+ * set them up later while requesting irq's.
+ */
+ err = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ vector_threshold, vectors);
+ if (err < 0) {
+ dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n");
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+ return err;
+ }
+
+ /* Adjust for only the vectors we'll use, which is minimum
+ * of max_msix_q_vectors + NONQ_VECS, or the number of
+ * vectors we were allocated.
+ */
+ adapter->num_msix_vectors = err;
+ return 0;
+}
+
+/**
+ * iavf_free_queues - Free memory for all rings
+ * @adapter: board private structure to initialize
+ *
+ * Free all of the memory associated with queue pairs.
+ **/
+static void iavf_free_queues(struct iavf_adapter *adapter)
+{
+ if (!adapter->vsi_res)
+ return;
+ adapter->num_active_queues = 0;
+ kfree(adapter->tx_rings);
+ adapter->tx_rings = NULL;
+ kfree(adapter->rx_rings);
+ adapter->rx_rings = NULL;
+}
+
+/**
+ * iavf_alloc_queues - Allocate memory for all rings
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one ring per queue at run-time since we don't know the
+ * number of queues at compile-time. The polling_netdev array is
+ * intended for Multiqueue, but should work fine with a single queue.
+ **/
+static int iavf_alloc_queues(struct iavf_adapter *adapter)
+{
+ int i, num_active_queues;
+
+ /* If we're in reset reallocating queues we don't actually know yet for
+ * certain the PF gave us the number of queues we asked for but we'll
+ * assume it did. Once basic reset is finished we'll confirm once we
+ * start negotiating config with PF.
+ */
+ if (adapter->num_req_queues)
+ num_active_queues = adapter->num_req_queues;
+ else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
+ adapter->num_tc)
+ num_active_queues = adapter->ch_config.total_qps;
+ else
+ num_active_queues = min_t(int,
+ adapter->vsi_res->num_queue_pairs,
+ (int)(num_online_cpus()));
+
+
+ adapter->tx_rings = kcalloc(num_active_queues,
+ sizeof(struct iavf_ring), GFP_KERNEL);
+ if (!adapter->tx_rings)
+ goto err_out;
+ adapter->rx_rings = kcalloc(num_active_queues,
+ sizeof(struct iavf_ring), GFP_KERNEL);
+ if (!adapter->rx_rings)
+ goto err_out;
+
+ for (i = 0; i < num_active_queues; i++) {
+ struct iavf_ring *tx_ring;
+ struct iavf_ring *rx_ring;
+
+ tx_ring = &adapter->tx_rings[i];
+
+ tx_ring->queue_index = i;
+ tx_ring->netdev = adapter->netdev;
+ tx_ring->dev = &adapter->pdev->dev;
+ tx_ring->count = adapter->tx_desc_count;
+ tx_ring->itr_setting = IAVF_ITR_TX_DEF;
+ if (adapter->flags & IAVF_FLAG_WB_ON_ITR_CAPABLE)
+ tx_ring->flags |= IAVF_TXR_FLAGS_WB_ON_ITR;
+
+ rx_ring = &adapter->rx_rings[i];
+ rx_ring->queue_index = i;
+ rx_ring->netdev = adapter->netdev;
+ rx_ring->dev = &adapter->pdev->dev;
+ rx_ring->count = adapter->rx_desc_count;
+ rx_ring->itr_setting = IAVF_ITR_RX_DEF;
+ }
+
+ adapter->num_active_queues = num_active_queues;
+
+ return 0;
+
+err_out:
+ iavf_free_queues(adapter);
+ return -ENOMEM;
+}
+
+/**
+ * iavf_set_interrupt_capability - set MSI-X or FAIL if not supported
+ * @adapter: board private structure to initialize
+ *
+ * Attempt to configure the interrupts using the best available
+ * capabilities of the hardware and the kernel.
+ **/
+static int iavf_set_interrupt_capability(struct iavf_adapter *adapter)
+{
+ int vector, v_budget;
+ int pairs = 0;
+ int err = 0;
+
+ if (!adapter->vsi_res) {
+ err = -EIO;
+ goto out;
+ }
+ pairs = adapter->num_active_queues;
+
+ /* It's easy to be greedy for MSI-X vectors, but it really doesn't do
+ * us much good if we have more vectors than CPUs. However, we already
+ * limit the total number of queues by the number of CPUs so we do not
+ * need any further limiting here.
+ */
+ v_budget = min_t(int, pairs + NONQ_VECS,
+ (int)adapter->vf_res->max_vectors);
+
+ adapter->msix_entries = kcalloc(v_budget,
+ sizeof(struct msix_entry), GFP_KERNEL);
+ if (!adapter->msix_entries) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ for (vector = 0; vector < v_budget; vector++)
+ adapter->msix_entries[vector].entry = vector;
+
+ err = iavf_acquire_msix_vectors(adapter, v_budget);
+
+out:
+ netif_set_real_num_rx_queues(adapter->netdev, pairs);
+ netif_set_real_num_tx_queues(adapter->netdev, pairs);
+ return err;
+}
+
+/**
+ * iavf_config_rss_aq - Configure RSS keys and lut by using AQ commands
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int iavf_config_rss_aq(struct iavf_adapter *adapter)
+{
+ struct iavf_aqc_get_set_rss_key_data *rss_key =
+ (struct iavf_aqc_get_set_rss_key_data *)adapter->rss_key;
+ struct iavf_hw *hw = &adapter->hw;
+ int ret = 0;
+
+ if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+ /* bail because we already have a command pending */
+ dev_err(&adapter->pdev->dev, "Cannot configure RSS, command %d pending\n",
+ adapter->current_op);
+ return -EBUSY;
+ }
+
+ ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key);
+ if (ret) {
+ dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n",
+ iavf_stat_str(hw, ret),
+ iavf_aq_str(hw, hw->aq.asq_last_status));
+ return ret;
+
+ }
+
+ ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false,
+ adapter->rss_lut, adapter->rss_lut_size);
+ if (ret) {
+ dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n",
+ iavf_stat_str(hw, ret),
+ iavf_aq_str(hw, hw->aq.asq_last_status));
+ }
+
+ return ret;
+
+}
+
+/**
+ * iavf_config_rss_reg - Configure RSS keys and lut by writing registers
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_config_rss_reg(struct iavf_adapter *adapter)
+{
+ struct iavf_hw *hw = &adapter->hw;
+ u32 *dw;
+ u16 i;
+
+ dw = (u32 *)adapter->rss_key;
+ for (i = 0; i <= adapter->rss_key_size / 4; i++)
+ wr32(hw, IAVF_VFQF_HKEY(i), dw[i]);
+
+ dw = (u32 *)adapter->rss_lut;
+ for (i = 0; i <= adapter->rss_lut_size / 4; i++)
+ wr32(hw, IAVF_VFQF_HLUT(i), dw[i]);
+
+ iavf_flush(hw);
+
+ return 0;
+}
+
+/**
+ * iavf_config_rss - Configure RSS keys and lut
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+int iavf_config_rss(struct iavf_adapter *adapter)
+{
+
+ if (RSS_PF(adapter)) {
+ adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_LUT |
+ IAVF_FLAG_AQ_SET_RSS_KEY;
+ return 0;
+ } else if (RSS_AQ(adapter)) {
+ return iavf_config_rss_aq(adapter);
+ } else {
+ return iavf_config_rss_reg(adapter);
+ }
+}
+
+/**
+ * iavf_fill_rss_lut - Fill the lut with default values
+ * @adapter: board private structure
+ **/
+static void iavf_fill_rss_lut(struct iavf_adapter *adapter)
+{
+ u16 i;
+
+ for (i = 0; i < adapter->rss_lut_size; i++)
+ adapter->rss_lut[i] = i % adapter->num_active_queues;
+}
+
+/**
+ * iavf_init_rss - Prepare for RSS
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int iavf_init_rss(struct iavf_adapter *adapter)
+{
+ struct iavf_hw *hw = &adapter->hw;
+ int ret;
+
+ if (!RSS_PF(adapter)) {
+ /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
+ if (adapter->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED;
+ else
+ adapter->hena = IAVF_DEFAULT_RSS_HENA;
+
+ wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena);
+ wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32));
+ }
+
+ iavf_fill_rss_lut(adapter);
+ netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size);
+ ret = iavf_config_rss(adapter);
+
+ return ret;
+}
+
+/**
+ * iavf_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt. If allocation fails we
+ * return -ENOMEM.
+ **/
+static int iavf_alloc_q_vectors(struct iavf_adapter *adapter)
+{
+ int q_idx = 0, num_q_vectors;
+ struct iavf_q_vector *q_vector;
+
+ num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+ adapter->q_vectors = kcalloc(num_q_vectors, sizeof(*q_vector),
+ GFP_KERNEL);
+ if (!adapter->q_vectors)
+ return -ENOMEM;
+
+ for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+ q_vector = &adapter->q_vectors[q_idx];
+ q_vector->adapter = adapter;
+ q_vector->vsi = &adapter->vsi;
+ q_vector->v_idx = q_idx;
+ q_vector->reg_idx = q_idx;
+ cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
+ netif_napi_add(adapter->netdev, &q_vector->napi,
+ iavf_napi_poll, NAPI_POLL_WEIGHT);
+ }
+
+ return 0;
+}
+
+/**
+ * iavf_free_q_vectors - Free memory allocated for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function frees the memory allocated to the q_vectors. In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ **/
+static void iavf_free_q_vectors(struct iavf_adapter *adapter)
+{
+ int q_idx, num_q_vectors;
+ int napi_vectors;
+
+ if (!adapter->q_vectors)
+ return;
+
+ num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+ napi_vectors = adapter->num_active_queues;
+
+ for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+ struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx];
+
+ if (q_idx < napi_vectors)
+ netif_napi_del(&q_vector->napi);
+ }
+ kfree(adapter->q_vectors);
+ adapter->q_vectors = NULL;
+}
+
+/**
+ * iavf_reset_interrupt_capability - Reset MSIX setup
+ * @adapter: board private structure
+ *
+ **/
+void iavf_reset_interrupt_capability(struct iavf_adapter *adapter)
+{
+ if (!adapter->msix_entries)
+ return;
+
+ pci_disable_msix(adapter->pdev);
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+}
+
+/**
+ * iavf_init_interrupt_scheme - Determine if MSIX is supported and init
+ * @adapter: board private structure to initialize
+ *
+ **/
+int iavf_init_interrupt_scheme(struct iavf_adapter *adapter)
+{
+ int err;
+
+ err = iavf_alloc_queues(adapter);
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Unable to allocate memory for queues\n");
+ goto err_alloc_queues;
+ }
+
+ rtnl_lock();
+ err = iavf_set_interrupt_capability(adapter);
+ rtnl_unlock();
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Unable to setup interrupt capabilities\n");
+ goto err_set_interrupt;
+ }
+
+ err = iavf_alloc_q_vectors(adapter);
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Unable to allocate memory for queue vectors\n");
+ goto err_alloc_q_vectors;
+ }
+
+ /* If we've made it so far while ADq flag being ON, then we haven't
+ * bailed out anywhere in middle. And ADq isn't just enabled but actual
+ * resources have been allocated in the reset path.
+ * Now we can truly claim that ADq is enabled.
+ */
+ if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
+ adapter->num_tc)
+ dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created",
+ adapter->num_tc);
+
+ dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u",
+ (adapter->num_active_queues > 1) ? "Enabled" : "Disabled",
+ adapter->num_active_queues);
+
+ return 0;
+err_alloc_q_vectors:
+ iavf_reset_interrupt_capability(adapter);
+err_set_interrupt:
+ iavf_free_queues(adapter);
+err_alloc_queues:
+ return err;
+}
+
+/**
+ * iavf_free_rss - Free memory used by RSS structs
+ * @adapter: board private structure
+ **/
+static void iavf_free_rss(struct iavf_adapter *adapter)
+{
+ kfree(adapter->rss_key);
+ adapter->rss_key = NULL;
+
+ kfree(adapter->rss_lut);
+ adapter->rss_lut = NULL;
+}
+
+/**
+ * iavf_reinit_interrupt_scheme - Reallocate queues and vectors
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int err;
+
+ if (netif_running(netdev))
+ iavf_free_traffic_irqs(adapter);
+ iavf_free_misc_irq(adapter);
+ iavf_reset_interrupt_capability(adapter);
+ iavf_free_q_vectors(adapter);
+ iavf_free_queues(adapter);
+
+ err = iavf_init_interrupt_scheme(adapter);
+ if (err)
+ goto err;
+
+ netif_tx_stop_all_queues(netdev);
+
+ err = iavf_request_misc_irq(adapter);
+ if (err)
+ goto err;
+
+ set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+
+ iavf_map_rings_to_vectors(adapter);
+
+ if (RSS_AQ(adapter))
+ adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS;
+ else
+ err = iavf_init_rss(adapter);
+err:
+ return err;
+}
+
+/**
+ * iavf_process_aq_command - process aq_required flags
+ * and sends aq command
+ * @adapter: pointer to iavf adapter structure
+ *
+ * Returns 0 on success
+ * Returns error code if no command was sent
+ * or error code if the command failed.
+ **/
+static int iavf_process_aq_command(struct iavf_adapter *adapter)
+{
+ if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG)
+ return iavf_send_vf_config_msg(adapter);
+ if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
+ iavf_disable_queues(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) {
+ iavf_map_queues(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) {
+ iavf_add_ether_addrs(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) {
+ iavf_add_vlans(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) {
+ iavf_del_ether_addrs(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) {
+ iavf_del_vlans(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) {
+ iavf_enable_vlan_stripping(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) {
+ iavf_disable_vlan_stripping(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) {
+ iavf_configure_queues(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) {
+ iavf_enable_queues(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) {
+ /* This message goes straight to the firmware, not the
+ * PF, so we don't have to set current_op as we will
+ * not get a response through the ARQ.
+ */
+ adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS;
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) {
+ iavf_get_hena(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) {
+ iavf_set_hena(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) {
+ iavf_set_rss_key(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) {
+ iavf_set_rss_lut(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) {
+ iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC |
+ FLAG_VF_MULTICAST_PROMISC);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) {
+ iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
+ return 0;
+ }
+
+ if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) &&
+ (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) {
+ iavf_set_promiscuous(adapter, 0);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) {
+ iavf_enable_channels(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) {
+ iavf_disable_channels(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) {
+ iavf_add_cloud_filter(adapter);
+ return 0;
+ }
+
+ if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) {
+ iavf_del_cloud_filter(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) {
+ iavf_del_cloud_filter(adapter);
+ return 0;
+ }
+ if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) {
+ iavf_add_cloud_filter(adapter);
+ return 0;
+ }
+ return -EAGAIN;
+}
+
+/**
+ * iavf_startup - first step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_STARTUP driver state.
+ * When success the state is changed to __IAVF_INIT_VERSION_CHECK
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_startup(struct iavf_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ struct iavf_hw *hw = &adapter->hw;
+ int err;
+
+ WARN_ON(adapter->state != __IAVF_STARTUP);
+
+ /* driver loaded, probe complete */
+ adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
+ adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
+ err = iavf_set_mac_type(hw);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err);
+ goto err;
+ }
+
+ err = iavf_check_reset_complete(hw);
+ if (err) {
+ dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
+ err);
+ goto err;
+ }
+ hw->aq.num_arq_entries = IAVF_AQ_LEN;
+ hw->aq.num_asq_entries = IAVF_AQ_LEN;
+ hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
+ hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
+
+ err = iavf_init_adminq(hw);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err);
+ goto err;
+ }
+ err = iavf_send_api_ver(adapter);
+ if (err) {
+ dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
+ iavf_shutdown_adminq(hw);
+ goto err;
+ }
+ adapter->state = __IAVF_INIT_VERSION_CHECK;
+err:
+ return err;
+}
+
+/**
+ * iavf_init_version_check - second step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_INIT_VERSION_CHECK driver state.
+ * When success the state is changed to __IAVF_INIT_GET_RESOURCES
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_init_version_check(struct iavf_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ struct iavf_hw *hw = &adapter->hw;
+ int err = -EAGAIN;
+
+ WARN_ON(adapter->state != __IAVF_INIT_VERSION_CHECK);
+
+ if (!iavf_asq_done(hw)) {
+ dev_err(&pdev->dev, "Admin queue command never completed\n");
+ iavf_shutdown_adminq(hw);
+ adapter->state = __IAVF_STARTUP;
+ goto err;
+ }
+
+ /* aq msg sent, awaiting reply */
+ err = iavf_verify_api_ver(adapter);
+ if (err) {
+ if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK)
+ err = iavf_send_api_ver(adapter);
+ else
+ dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n",
+ adapter->pf_version.major,
+ adapter->pf_version.minor,
+ VIRTCHNL_VERSION_MAJOR,
+ VIRTCHNL_VERSION_MINOR);
+ goto err;
+ }
+ err = iavf_send_vf_config_msg(adapter);
+ if (err) {
+ dev_err(&pdev->dev, "Unable to send config request (%d)\n",
+ err);
+ goto err;
+ }
+ adapter->state = __IAVF_INIT_GET_RESOURCES;
+
+err:
+ return err;
+}
+
+/**
+ * iavf_init_get_resources - third step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_INIT_GET_RESOURCES driver state and
+ * finishes driver initialization procedure.
+ * When success the state is changed to __IAVF_DOWN
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_init_get_resources(struct iavf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
+ struct iavf_hw *hw = &adapter->hw;
+ int err = 0, bufsz;
+
+ WARN_ON(adapter->state != __IAVF_INIT_GET_RESOURCES);
+ /* aq msg sent, awaiting reply */
+ if (!adapter->vf_res) {
+ bufsz = sizeof(struct virtchnl_vf_resource) +
+ (IAVF_MAX_VF_VSI *
+ sizeof(struct virtchnl_vsi_resource));
+ adapter->vf_res = kzalloc(bufsz, GFP_KERNEL);
+ if (!adapter->vf_res)
+ goto err;
+ }
+ err = iavf_get_vf_config(adapter);
+ if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK) {
+ err = iavf_send_vf_config_msg(adapter);
+ goto err;
+ } else if (err == IAVF_ERR_PARAM) {
+ /* We only get ERR_PARAM if the device is in a very bad
+ * state or if we've been disabled for previous bad
+ * behavior. Either way, we're done now.
+ */
+ iavf_shutdown_adminq(hw);
+ dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n");
+ return 0;
+ }
+ if (err) {
+ dev_err(&pdev->dev, "Unable to get VF config (%d)\n", err);
+ goto err_alloc;
+ }
+
+ if (iavf_process_config(adapter))
+ goto err_alloc;
+ adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+
+ adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED;
+
+ netdev->netdev_ops = &iavf_netdev_ops;
+ iavf_set_ethtool_ops(netdev);
+ netdev->watchdog_timeo = 5 * HZ;
+
+ /* MTU range: 68 - 9710 */
+ netdev->min_mtu = ETH_MIN_MTU;
+ netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD;
+
+ if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
+ dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
+ adapter->hw.mac.addr);
+ eth_hw_addr_random(netdev);
+ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
+ } else {
+ ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
+ ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
+ }
+
+ adapter->tx_desc_count = IAVF_DEFAULT_TXD;
+ adapter->rx_desc_count = IAVF_DEFAULT_RXD;
+ err = iavf_init_interrupt_scheme(adapter);
+ if (err)
+ goto err_sw_init;
+ iavf_map_rings_to_vectors(adapter);
+ if (adapter->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+ adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE;
+
+ err = iavf_request_misc_irq(adapter);
+ if (err)
+ goto err_sw_init;
+
+ netif_carrier_off(netdev);
+ adapter->link_up = false;
+
+ /* set the semaphore to prevent any callbacks after device registration
+ * up to time when state of driver will be set to __IAVF_DOWN
+ */
+ rtnl_lock();
+ if (!adapter->netdev_registered) {
+ err = register_netdevice(netdev);
+ if (err) {
+ rtnl_unlock();
+ goto err_register;
+ }
+ }
+
+ adapter->netdev_registered = true;
+
+ netif_tx_stop_all_queues(netdev);
+ if (CLIENT_ALLOWED(adapter)) {
+ err = iavf_lan_add_device(adapter);
+ if (err) {
+ rtnl_unlock();
+ dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+ err);
+ }
+ }
+ dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
+ if (netdev->features & NETIF_F_GRO)
+ dev_info(&pdev->dev, "GRO is enabled\n");
+
+ adapter->state = __IAVF_DOWN;
+ set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+ rtnl_unlock();
+
+ iavf_misc_irq_enable(adapter);
+ wake_up(&adapter->down_waitqueue);
+
+ adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
+ adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
+ if (!adapter->rss_key || !adapter->rss_lut)
+ goto err_mem;
+ if (RSS_AQ(adapter))
+ adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS;
+ else
+ iavf_init_rss(adapter);
+
+ return err;
+err_mem:
+ iavf_free_rss(adapter);
+err_register:
+ iavf_free_misc_irq(adapter);
+err_sw_init:
+ iavf_reset_interrupt_capability(adapter);
+err_alloc:
+ kfree(adapter->vf_res);
+ adapter->vf_res = NULL;
+err:
+ return err;
+}
+
+/**
+ * iavf_watchdog_task - Periodic call-back task
+ * @work: pointer to work_struct
+ **/
+static void iavf_watchdog_task(struct work_struct *work)
+{
+ struct iavf_adapter *adapter = container_of(work,
+ struct iavf_adapter,
+ watchdog_task.work);
+ struct iavf_hw *hw = &adapter->hw;
+ u32 reg_val;
+
+ if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section))
+ goto restart_watchdog;
+
+ if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
+ adapter->state = __IAVF_COMM_FAILED;
+
+ switch (adapter->state) {
+ case __IAVF_COMM_FAILED:
+ reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
+ IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
+ if (reg_val == VIRTCHNL_VFR_VFACTIVE ||
+ reg_val == VIRTCHNL_VFR_COMPLETED) {
+ /* A chance for redemption! */
+ dev_err(&adapter->pdev->dev,
+ "Hardware came out of reset. Attempting reinit.\n");
+ adapter->state = __IAVF_STARTUP;
+ adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
+ queue_delayed_work(iavf_wq, &adapter->init_task, 10);
+ clear_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section);
+ /* Don't reschedule the watchdog, since we've restarted
+ * the init task. When init_task contacts the PF and
+ * gets everything set up again, it'll restart the
+ * watchdog for us. Down, boy. Sit. Stay. Woof.
+ */
+ return;
+ }
+ adapter->aq_required = 0;
+ adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ clear_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section);
+ queue_delayed_work(iavf_wq,
+ &adapter->watchdog_task,
+ msecs_to_jiffies(10));
+ goto watchdog_done;
+ case __IAVF_RESETTING:
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ return;
+ case __IAVF_DOWN:
+ case __IAVF_DOWN_PENDING:
+ case __IAVF_TESTING:
+ case __IAVF_RUNNING:
+ if (adapter->current_op) {
+ if (!iavf_asq_done(hw)) {
+ dev_dbg(&adapter->pdev->dev,
+ "Admin queue timeout\n");
+ iavf_send_api_ver(adapter);
+ }
+ } else {
+ if (!iavf_process_aq_command(adapter) &&
+ adapter->state == __IAVF_RUNNING)
+ iavf_request_stats(adapter);
+ }
+ break;
+ case __IAVF_REMOVE:
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ return;
+ default:
+ goto restart_watchdog;
+ }
+
+ /* check for hw reset */
+ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
+ if (!reg_val) {
+ adapter->state = __IAVF_RESETTING;
+ adapter->flags |= IAVF_FLAG_RESET_PENDING;
+ adapter->aq_required = 0;
+ adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
+ queue_work(iavf_wq, &adapter->reset_task);
+ goto watchdog_done;
+ }
+
+ schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
+watchdog_done:
+ if (adapter->state == __IAVF_RUNNING ||
+ adapter->state == __IAVF_COMM_FAILED)
+ iavf_detect_recover_hung(&adapter->vsi);
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+restart_watchdog:
+ if (adapter->aq_required)
+ queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ msecs_to_jiffies(20));
+ else
+ queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ queue_work(iavf_wq, &adapter->adminq_task);
+}
+
+static void iavf_disable_vf(struct iavf_adapter *adapter)
+{
+ struct iavf_mac_filter *f, *ftmp;
+ struct iavf_vlan_filter *fv, *fvtmp;
+ struct iavf_cloud_filter *cf, *cftmp;
+
+ adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
+
+ /* We don't use netif_running() because it may be true prior to
+ * ndo_open() returning, so we can't assume it means all our open
+ * tasks have finished, since we're not holding the rtnl_lock here.
+ */
+ if (adapter->state == __IAVF_RUNNING) {
+ set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+ netif_carrier_off(adapter->netdev);
+ netif_tx_disable(adapter->netdev);
+ adapter->link_up = false;
+ iavf_napi_disable_all(adapter);
+ iavf_irq_disable(adapter);
+ iavf_free_traffic_irqs(adapter);
+ iavf_free_all_tx_resources(adapter);
+ iavf_free_all_rx_resources(adapter);
+ }
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ /* Delete all of the filters */
+ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
+ list_del(&f->list);
+ kfree(f);
+ }
+
+ list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list, list) {
+ list_del(&fv->list);
+ kfree(fv);
+ }
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) {
+ list_del(&cf->list);
+ kfree(cf);
+ adapter->num_cloud_filters--;
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+
+ iavf_free_misc_irq(adapter);
+ iavf_reset_interrupt_capability(adapter);
+ iavf_free_queues(adapter);
+ iavf_free_q_vectors(adapter);
+ kfree(adapter->vf_res);
+ iavf_shutdown_adminq(&adapter->hw);
+ adapter->netdev->flags &= ~IFF_UP;
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
+ adapter->state = __IAVF_DOWN;
+ wake_up(&adapter->down_waitqueue);
+ dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
+}
+
+#define IAVF_RESET_WAIT_MS 10
+#define IAVF_RESET_WAIT_COUNT 500
+/**
+ * iavf_reset_task - Call-back task to handle hardware reset
+ * @work: pointer to work_struct
+ *
+ * During reset we need to shut down and reinitialize the admin queue
+ * before we can use it to communicate with the PF again. We also clear
+ * and reinit the rings because that context is lost as well.
+ **/
+static void iavf_reset_task(struct work_struct *work)
+{
+ struct iavf_adapter *adapter = container_of(work,
+ struct iavf_adapter,
+ reset_task);
+ struct virtchnl_vf_resource *vfres = adapter->vf_res;
+ struct net_device *netdev = adapter->netdev;
+ struct iavf_hw *hw = &adapter->hw;
+ struct iavf_vlan_filter *vlf;
+ struct iavf_cloud_filter *cf;
+ struct iavf_mac_filter *f;
+ u32 reg_val;
+ int i = 0, err;
+ bool running;
+
+ /* When device is being removed it doesn't make sense to run the reset
+ * task, just return in such a case.
+ */
+ if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
+ return;
+
+ while (test_and_set_bit(__IAVF_IN_CLIENT_TASK,
+ &adapter->crit_section))
+ usleep_range(500, 1000);
+ if (CLIENT_ENABLED(adapter)) {
+ adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN |
+ IAVF_FLAG_CLIENT_NEEDS_CLOSE |
+ IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
+ IAVF_FLAG_SERVICE_CLIENT_REQUESTED);
+ cancel_delayed_work_sync(&adapter->client_task);
+ iavf_notify_client_close(&adapter->vsi, true);
+ }
+ iavf_misc_irq_disable(adapter);
+ if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
+ adapter->flags &= ~IAVF_FLAG_RESET_NEEDED;
+ /* Restart the AQ here. If we have been reset but didn't
+ * detect it, or if the PF had to reinit, our AQ will be hosed.
+ */
+ iavf_shutdown_adminq(hw);
+ iavf_init_adminq(hw);
+ iavf_request_reset(adapter);
+ }
+ adapter->flags |= IAVF_FLAG_RESET_PENDING;
+
+ /* poll until we see the reset actually happen */
+ for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) {
+ reg_val = rd32(hw, IAVF_VF_ARQLEN1) &
+ IAVF_VF_ARQLEN1_ARQENABLE_MASK;
+ if (!reg_val)
+ break;
+ usleep_range(5000, 10000);
+ }
+ if (i == IAVF_RESET_WAIT_COUNT) {
+ dev_info(&adapter->pdev->dev, "Never saw reset\n");
+ goto continue_reset; /* act like the reset happened */
+ }
+
+ /* wait until the reset is complete and the PF is responding to us */
+ for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) {
+ /* sleep first to make sure a minimum wait time is met */
+ msleep(IAVF_RESET_WAIT_MS);
+
+ reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
+ IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
+ if (reg_val == VIRTCHNL_VFR_VFACTIVE)
+ break;
+ }
+
+ pci_set_master(adapter->pdev);
+
+ if (i == IAVF_RESET_WAIT_COUNT) {
+ dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
+ reg_val);
+ iavf_disable_vf(adapter);
+ clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+ return; /* Do not attempt to reinit. It's dead, Jim. */
+ }
+
+continue_reset:
+ /* We don't use netif_running() because it may be true prior to
+ * ndo_open() returning, so we can't assume it means all our open
+ * tasks have finished, since we're not holding the rtnl_lock here.
+ */
+ running = ((adapter->state == __IAVF_RUNNING) ||
+ (adapter->state == __IAVF_RESETTING));
+
+ if (running) {
+ netif_carrier_off(netdev);
+ netif_tx_stop_all_queues(netdev);
+ adapter->link_up = false;
+ iavf_napi_disable_all(adapter);
+ }
+ iavf_irq_disable(adapter);
+
+ adapter->state = __IAVF_RESETTING;
+ adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
+
+ /* free the Tx/Rx rings and descriptors, might be better to just
+ * re-use them sometime in the future
+ */
+ iavf_free_all_rx_resources(adapter);
+ iavf_free_all_tx_resources(adapter);
+
+ adapter->flags |= IAVF_FLAG_QUEUES_DISABLED;
+ /* kill and reinit the admin queue */
+ iavf_shutdown_adminq(hw);
+ adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ err = iavf_init_adminq(hw);
+ if (err)
+ dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
+ err);
+ adapter->aq_required = 0;
+
+ if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) {
+ err = iavf_reinit_interrupt_scheme(adapter);
+ if (err)
+ goto reset_err;
+ }
+
+ adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG;
+ adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ /* re-add all MAC filters */
+ list_for_each_entry(f, &adapter->mac_filter_list, list) {
+ f->add = true;
+ }
+ /* re-add all VLAN filters */
+ list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
+ vlf->add = true;
+ }
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ /* check if TCs are running and re-add all cloud filters */
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
+ adapter->num_tc) {
+ list_for_each_entry(cf, &adapter->cloud_filter_list, list) {
+ cf->add = true;
+ }
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER;
+ iavf_misc_irq_enable(adapter);
+
+ mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2);
+
+ /* We were running when the reset started, so we need to restore some
+ * state here.
+ */
+ if (running) {
+ /* allocate transmit descriptors */
+ err = iavf_setup_all_tx_resources(adapter);
+ if (err)
+ goto reset_err;
+
+ /* allocate receive descriptors */
+ err = iavf_setup_all_rx_resources(adapter);
+ if (err)
+ goto reset_err;
+
+ if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) {
+ err = iavf_request_traffic_irqs(adapter, netdev->name);
+ if (err)
+ goto reset_err;
+
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+ }
+
+ iavf_configure(adapter);
+
+ iavf_up_complete(adapter);
+
+ iavf_irq_enable(adapter, true);
+ } else {
+ adapter->state = __IAVF_DOWN;
+ wake_up(&adapter->down_waitqueue);
+ }
+ clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+
+ return;
+reset_err:
+ clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
+ iavf_close(netdev);
+}
+
+/**
+ * iavf_adminq_task - worker thread to clean the admin queue
+ * @work: pointer to work_struct containing our data
+ **/
+static void iavf_adminq_task(struct work_struct *work)
+{
+ struct iavf_adapter *adapter =
+ container_of(work, struct iavf_adapter, adminq_task);
+ struct iavf_hw *hw = &adapter->hw;
+ struct iavf_arq_event_info event;
+ enum virtchnl_ops v_op;
+ enum iavf_status ret, v_ret;
+ u32 val, oldval;
+ u16 pending;
+
+ if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
+ goto out;
+
+ event.buf_len = IAVF_MAX_AQ_BUF_SIZE;
+ event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
+ if (!event.msg_buf)
+ goto out;
+
+ do {
+ ret = iavf_clean_arq_element(hw, &event, &pending);
+ v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
+ v_ret = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
+
+ if (ret || !v_op)
+ break; /* No event to process or error cleaning ARQ */
+
+ iavf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf,
+ event.msg_len);
+ if (pending != 0)
+ memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE);
+ } while (pending);
+
+ if ((adapter->flags &
+ (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
+ adapter->state == __IAVF_RESETTING)
+ goto freedom;
+
+ /* check for error indications */
+ val = rd32(hw, hw->aq.arq.len);
+ if (val == 0xdeadbeef) /* indicates device in reset */
+ goto freedom;
+ oldval = val;
+ if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) {
+ dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n");
+ val &= ~IAVF_VF_ARQLEN1_ARQVFE_MASK;
+ }
+ if (val & IAVF_VF_ARQLEN1_ARQOVFL_MASK) {
+ dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n");
+ val &= ~IAVF_VF_ARQLEN1_ARQOVFL_MASK;
+ }
+ if (val & IAVF_VF_ARQLEN1_ARQCRIT_MASK) {
+ dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n");
+ val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK;
+ }
+ if (oldval != val)
+ wr32(hw, hw->aq.arq.len, val);
+
+ val = rd32(hw, hw->aq.asq.len);
+ oldval = val;
+ if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) {
+ dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n");
+ val &= ~IAVF_VF_ATQLEN1_ATQVFE_MASK;
+ }
+ if (val & IAVF_VF_ATQLEN1_ATQOVFL_MASK) {
+ dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n");
+ val &= ~IAVF_VF_ATQLEN1_ATQOVFL_MASK;
+ }
+ if (val & IAVF_VF_ATQLEN1_ATQCRIT_MASK) {
+ dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n");
+ val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK;
+ }
+ if (oldval != val)
+ wr32(hw, hw->aq.asq.len, val);
+
+freedom:
+ kfree(event.msg_buf);
+out:
+ /* re-enable Admin queue interrupt cause */
+ iavf_misc_irq_enable(adapter);
+}
+
+/**
+ * iavf_client_task - worker thread to perform client work
+ * @work: pointer to work_struct containing our data
+ *
+ * This task handles client interactions. Because client calls can be
+ * reentrant, we can't handle them in the watchdog.
+ **/
+static void iavf_client_task(struct work_struct *work)
+{
+ struct iavf_adapter *adapter =
+ container_of(work, struct iavf_adapter, client_task.work);
+
+ /* If we can't get the client bit, just give up. We'll be rescheduled
+ * later.
+ */
+
+ if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section))
+ return;
+
+ if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) {
+ iavf_client_subtask(adapter);
+ adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ goto out;
+ }
+ if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+ iavf_notify_client_l2_params(&adapter->vsi);
+ adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+ goto out;
+ }
+ if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) {
+ iavf_notify_client_close(&adapter->vsi, false);
+ adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE;
+ goto out;
+ }
+ if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) {
+ iavf_notify_client_open(&adapter->vsi);
+ adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN;
+ }
+out:
+ clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section);
+}
+
+/**
+ * iavf_free_all_tx_resources - Free Tx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all transmit software resources
+ **/
+void iavf_free_all_tx_resources(struct iavf_adapter *adapter)
+{
+ int i;
+
+ if (!adapter->tx_rings)
+ return;
+
+ for (i = 0; i < adapter->num_active_queues; i++)
+ if (adapter->tx_rings[i].desc)
+ iavf_free_tx_resources(&adapter->tx_rings[i]);
+}
+
+/**
+ * iavf_setup_all_tx_resources - allocate all queues Tx resources
+ * @adapter: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not). It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter)
+{
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_active_queues; i++) {
+ adapter->tx_rings[i].count = adapter->tx_desc_count;
+ err = iavf_setup_tx_descriptors(&adapter->tx_rings[i]);
+ if (!err)
+ continue;
+ dev_err(&adapter->pdev->dev,
+ "Allocation for Tx Queue %u failed\n", i);
+ break;
+ }
+
+ return err;
+}
+
+/**
+ * iavf_setup_all_rx_resources - allocate all queues Rx resources
+ * @adapter: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not). It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter)
+{
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_active_queues; i++) {
+ adapter->rx_rings[i].count = adapter->rx_desc_count;
+ err = iavf_setup_rx_descriptors(&adapter->rx_rings[i]);
+ if (!err)
+ continue;
+ dev_err(&adapter->pdev->dev,
+ "Allocation for Rx Queue %u failed\n", i);
+ break;
+ }
+ return err;
+}
+
+/**
+ * iavf_free_all_rx_resources - Free Rx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all receive software resources
+ **/
+void iavf_free_all_rx_resources(struct iavf_adapter *adapter)
+{
+ int i;
+
+ if (!adapter->rx_rings)
+ return;
+
+ for (i = 0; i < adapter->num_active_queues; i++)
+ if (adapter->rx_rings[i].desc)
+ iavf_free_rx_resources(&adapter->rx_rings[i]);
+}
+
+/**
+ * iavf_validate_tx_bandwidth - validate the max Tx bandwidth
+ * @adapter: board private structure
+ * @max_tx_rate: max Tx bw for a tc
+ **/
+static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter,
+ u64 max_tx_rate)
+{
+ int speed = 0, ret = 0;
+
+ switch (adapter->link_speed) {
+ case IAVF_LINK_SPEED_40GB:
+ speed = 40000;
+ break;
+ case IAVF_LINK_SPEED_25GB:
+ speed = 25000;
+ break;
+ case IAVF_LINK_SPEED_20GB:
+ speed = 20000;
+ break;
+ case IAVF_LINK_SPEED_10GB:
+ speed = 10000;
+ break;
+ case IAVF_LINK_SPEED_1GB:
+ speed = 1000;
+ break;
+ case IAVF_LINK_SPEED_100MB:
+ speed = 100;
+ break;
+ default:
+ break;
+ }
+
+ if (max_tx_rate > speed) {
+ dev_err(&adapter->pdev->dev,
+ "Invalid tx rate specified\n");
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+/**
+ * iavf_validate_channel_config - validate queue mapping info
+ * @adapter: board private structure
+ * @mqprio_qopt: queue parameters
+ *
+ * This function validates if the config provided by the user to
+ * configure queue channels is valid or not. Returns 0 on a valid
+ * config.
+ **/
+static int iavf_validate_ch_config(struct iavf_adapter *adapter,
+ struct tc_mqprio_qopt_offload *mqprio_qopt)
+{
+ u64 total_max_rate = 0;
+ int i, num_qps = 0;
+ u64 tx_rate = 0;
+ int ret = 0;
+
+ if (mqprio_qopt->qopt.num_tc > IAVF_MAX_TRAFFIC_CLASS ||
+ mqprio_qopt->qopt.num_tc < 1)
+ return -EINVAL;
+
+ for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) {
+ if (!mqprio_qopt->qopt.count[i] ||
+ mqprio_qopt->qopt.offset[i] != num_qps)
+ return -EINVAL;
+ if (mqprio_qopt->min_rate[i]) {
+ dev_err(&adapter->pdev->dev,
+ "Invalid min tx rate (greater than 0) specified\n");
+ return -EINVAL;
+ }
+ /*convert to Mbps */
+ tx_rate = div_u64(mqprio_qopt->max_rate[i],
+ IAVF_MBPS_DIVISOR);
+ total_max_rate += tx_rate;
+ num_qps += mqprio_qopt->qopt.count[i];
+ }
+ if (num_qps > IAVF_MAX_REQ_QUEUES)
+ return -EINVAL;
+
+ ret = iavf_validate_tx_bandwidth(adapter, total_max_rate);
+ return ret;
+}
+
+/**
+ * iavf_del_all_cloud_filters - delete all cloud filters
+ * on the traffic classes
+ **/
+static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter)
+{
+ struct iavf_cloud_filter *cf, *cftmp;
+
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list,
+ list) {
+ list_del(&cf->list);
+ kfree(cf);
+ adapter->num_cloud_filters--;
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+}
+
+/**
+ * __iavf_setup_tc - configure multiple traffic classes
+ * @netdev: network interface device structure
+ * @type_date: tc offload data
+ *
+ * This function processes the config information provided by the
+ * user to configure traffic classes/queue channels and packages the
+ * information to request the PF to setup traffic classes.
+ *
+ * Returns 0 on success.
+ **/
+static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
+{
+ struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct virtchnl_vf_resource *vfres = adapter->vf_res;
+ u8 num_tc = 0, total_qps = 0;
+ int ret = 0, netdev_tc = 0;
+ u64 max_tx_rate;
+ u16 mode;
+ int i;
+
+ num_tc = mqprio_qopt->qopt.num_tc;
+ mode = mqprio_qopt->mode;
+
+ /* delete queue_channel */
+ if (!mqprio_qopt->qopt.hw) {
+ if (adapter->ch_config.state == __IAVF_TC_RUNNING) {
+ /* reset the tc configuration */
+ netdev_reset_tc(netdev);
+ adapter->num_tc = 0;
+ netif_tx_stop_all_queues(netdev);
+ netif_tx_disable(netdev);
+ iavf_del_all_cloud_filters(adapter);
+ adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS;
+ goto exit;
+ } else {
+ return -EINVAL;
+ }
+ }
+
+ /* add queue channel */
+ if (mode == TC_MQPRIO_MODE_CHANNEL) {
+ if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) {
+ dev_err(&adapter->pdev->dev, "ADq not supported\n");
+ return -EOPNOTSUPP;
+ }
+ if (adapter->ch_config.state != __IAVF_TC_INVALID) {
+ dev_err(&adapter->pdev->dev, "TC configuration already exists\n");
+ return -EINVAL;
+ }
+
+ ret = iavf_validate_ch_config(adapter, mqprio_qopt);
+ if (ret)
+ return ret;
+ /* Return if same TC config is requested */
+ if (adapter->num_tc == num_tc)
+ return 0;
+ adapter->num_tc = num_tc;
+
+ for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) {
+ if (i < num_tc) {
+ adapter->ch_config.ch_info[i].count =
+ mqprio_qopt->qopt.count[i];
+ adapter->ch_config.ch_info[i].offset =
+ mqprio_qopt->qopt.offset[i];
+ total_qps += mqprio_qopt->qopt.count[i];
+ max_tx_rate = mqprio_qopt->max_rate[i];
+ /* convert to Mbps */
+ max_tx_rate = div_u64(max_tx_rate,
+ IAVF_MBPS_DIVISOR);
+ adapter->ch_config.ch_info[i].max_tx_rate =
+ max_tx_rate;
+ } else {
+ adapter->ch_config.ch_info[i].count = 1;
+ adapter->ch_config.ch_info[i].offset = 0;
+ }
+ }
+ adapter->ch_config.total_qps = total_qps;
+ netif_tx_stop_all_queues(netdev);
+ netif_tx_disable(netdev);
+ adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS;
+ netdev_reset_tc(netdev);
+ /* Report the tc mapping up the stack */
+ netdev_set_num_tc(adapter->netdev, num_tc);
+ for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) {
+ u16 qcount = mqprio_qopt->qopt.count[i];
+ u16 qoffset = mqprio_qopt->qopt.offset[i];
+
+ if (i < num_tc)
+ netdev_set_tc_queue(netdev, netdev_tc++, qcount,
+ qoffset);
+ }
+ }
+exit:
+ return ret;
+}
+
+/**
+ * iavf_parse_cls_flower - Parse tc flower filters provided by kernel
+ * @adapter: board private structure
+ * @cls_flower: pointer to struct flow_cls_offload
+ * @filter: pointer to cloud filter structure
+ */
+static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
+ struct flow_cls_offload *f,
+ struct iavf_cloud_filter *filter)
+{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+ struct flow_dissector *dissector = rule->match.dissector;
+ u16 n_proto_mask = 0;
+ u16 n_proto_key = 0;
+ u8 field_flags = 0;
+ u16 addr_type = 0;
+ u16 n_proto = 0;
+ int i = 0;
+ struct virtchnl_filter *vf = &filter->f;
+
+ if (dissector->used_keys &
+ ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+ BIT(FLOW_DISSECTOR_KEY_BASIC) |
+ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_VLAN) |
+ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
+ dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n",
+ dissector->used_keys);
+ return -EOPNOTSUPP;
+ }
+
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_match_enc_keyid match;
+
+ flow_rule_match_enc_keyid(rule, &match);
+ if (match.mask->keyid != 0)
+ field_flags |= IAVF_CLOUD_FIELD_TEN_ID;
+ }
+
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_match_basic match;
+
+ flow_rule_match_basic(rule, &match);
+ n_proto_key = ntohs(match.key->n_proto);
+ n_proto_mask = ntohs(match.mask->n_proto);
+
+ if (n_proto_key == ETH_P_ALL) {
+ n_proto_key = 0;
+ n_proto_mask = 0;
+ }
+ n_proto = n_proto_key & n_proto_mask;
+ if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6)
+ return -EINVAL;
+ if (n_proto == ETH_P_IPV6) {
+ /* specify flow type as TCP IPv6 */
+ vf->flow_type = VIRTCHNL_TCP_V6_FLOW;
+ }
+
+ if (match.key->ip_proto != IPPROTO_TCP) {
+ dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n");
+ return -EINVAL;
+ }
+ }
+
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_match_eth_addrs match;
+
+ flow_rule_match_eth_addrs(rule, &match);
+
+ /* use is_broadcast and is_zero to check for all 0xf or 0 */
+ if (!is_zero_ether_addr(match.mask->dst)) {
+ if (is_broadcast_ether_addr(match.mask->dst)) {
+ field_flags |= IAVF_CLOUD_FIELD_OMAC;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n",
+ match.mask->dst);
+ return IAVF_ERR_CONFIG;
+ }
+ }
+
+ if (!is_zero_ether_addr(match.mask->src)) {
+ if (is_broadcast_ether_addr(match.mask->src)) {
+ field_flags |= IAVF_CLOUD_FIELD_IMAC;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n",
+ match.mask->src);
+ return IAVF_ERR_CONFIG;
+ }
+ }
+
+ if (!is_zero_ether_addr(match.key->dst))
+ if (is_valid_ether_addr(match.key->dst) ||
+ is_multicast_ether_addr(match.key->dst)) {
+ /* set the mask if a valid dst_mac address */
+ for (i = 0; i < ETH_ALEN; i++)
+ vf->mask.tcp_spec.dst_mac[i] |= 0xff;
+ ether_addr_copy(vf->data.tcp_spec.dst_mac,
+ match.key->dst);
+ }
+
+ if (!is_zero_ether_addr(match.key->src))
+ if (is_valid_ether_addr(match.key->src) ||
+ is_multicast_ether_addr(match.key->src)) {
+ /* set the mask if a valid dst_mac address */
+ for (i = 0; i < ETH_ALEN; i++)
+ vf->mask.tcp_spec.src_mac[i] |= 0xff;
+ ether_addr_copy(vf->data.tcp_spec.src_mac,
+ match.key->src);
+ }
+ }
+
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_match_vlan match;
+
+ flow_rule_match_vlan(rule, &match);
+ if (match.mask->vlan_id) {
+ if (match.mask->vlan_id == VLAN_VID_MASK) {
+ field_flags |= IAVF_CLOUD_FIELD_IVLAN;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n",
+ match.mask->vlan_id);
+ return IAVF_ERR_CONFIG;
+ }
+ }
+ vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff);
+ vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id);
+ }
+
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_match_control match;
+
+ flow_rule_match_control(rule, &match);
+ addr_type = match.key->addr_type;
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+ struct flow_match_ipv4_addrs match;
+
+ flow_rule_match_ipv4_addrs(rule, &match);
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be32(0xffffffff)) {
+ field_flags |= IAVF_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n",
+ be32_to_cpu(match.mask->dst));
+ return IAVF_ERR_CONFIG;
+ }
+ }
+
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be32(0xffffffff)) {
+ field_flags |= IAVF_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
+ be32_to_cpu(match.mask->dst));
+ return IAVF_ERR_CONFIG;
+ }
+ }
+
+ if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) {
+ dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n");
+ return IAVF_ERR_CONFIG;
+ }
+ if (match.key->dst) {
+ vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff);
+ vf->data.tcp_spec.dst_ip[0] = match.key->dst;
+ }
+ if (match.key->src) {
+ vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff);
+ vf->data.tcp_spec.src_ip[0] = match.key->src;
+ }
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+ struct flow_match_ipv6_addrs match;
+
+ flow_rule_match_ipv6_addrs(rule, &match);
+
+ /* validate mask, make sure it is not IPV6_ADDR_ANY */
+ if (ipv6_addr_any(&match.mask->dst)) {
+ dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n",
+ IPV6_ADDR_ANY);
+ return IAVF_ERR_CONFIG;
+ }
+
+ /* src and dest IPv6 address should not be LOOPBACK
+ * (0:0:0:0:0:0:0:1) which can be represented as ::1
+ */
+ if (ipv6_addr_loopback(&match.key->dst) ||
+ ipv6_addr_loopback(&match.key->src)) {
+ dev_err(&adapter->pdev->dev,
+ "ipv6 addr should not be loopback\n");
+ return IAVF_ERR_CONFIG;
+ }
+ if (!ipv6_addr_any(&match.mask->dst) ||
+ !ipv6_addr_any(&match.mask->src))
+ field_flags |= IAVF_CLOUD_FIELD_IIP;
+
+ for (i = 0; i < 4; i++)
+ vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff);
+ memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32,
+ sizeof(vf->data.tcp_spec.dst_ip));
+ for (i = 0; i < 4; i++)
+ vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff);
+ memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32,
+ sizeof(vf->data.tcp_spec.src_ip));
+ }
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+ struct flow_match_ports match;
+
+ flow_rule_match_ports(rule, &match);
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be16(0xffff)) {
+ field_flags |= IAVF_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad src port mask %u\n",
+ be16_to_cpu(match.mask->src));
+ return IAVF_ERR_CONFIG;
+ }
+ }
+
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be16(0xffff)) {
+ field_flags |= IAVF_CLOUD_FIELD_IIP;
+ } else {
+ dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n",
+ be16_to_cpu(match.mask->dst));
+ return IAVF_ERR_CONFIG;
+ }
+ }
+ if (match.key->dst) {
+ vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff);
+ vf->data.tcp_spec.dst_port = match.key->dst;
+ }
+
+ if (match.key->src) {
+ vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff);
+ vf->data.tcp_spec.src_port = match.key->src;
+ }
+ }
+ vf->field_flags = field_flags;
+
+ return 0;
+}
+
+/**
+ * iavf_handle_tclass - Forward to a traffic class on the device
+ * @adapter: board private structure
+ * @tc: traffic class index on the device
+ * @filter: pointer to cloud filter structure
+ */
+static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc,
+ struct iavf_cloud_filter *filter)
+{
+ if (tc == 0)
+ return 0;
+ if (tc < adapter->num_tc) {
+ if (!filter->f.data.tcp_spec.dst_port) {
+ dev_err(&adapter->pdev->dev,
+ "Specify destination port to redirect to traffic class other than TC0\n");
+ return -EINVAL;
+ }
+ }
+ /* redirect to a traffic class on the same device */
+ filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT;
+ filter->f.action_meta = tc;
+ return 0;
+}
+
+/**
+ * iavf_configure_clsflower - Add tc flower filters
+ * @adapter: board private structure
+ * @cls_flower: Pointer to struct flow_cls_offload
+ */
+static int iavf_configure_clsflower(struct iavf_adapter *adapter,
+ struct flow_cls_offload *cls_flower)
+{
+ int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
+ struct iavf_cloud_filter *filter = NULL;
+ int err = -EINVAL, count = 50;
+
+ if (tc < 0) {
+ dev_err(&adapter->pdev->dev, "Invalid traffic class\n");
+ return -EINVAL;
+ }
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return -ENOMEM;
+
+ while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section)) {
+ if (--count == 0)
+ goto err;
+ udelay(1);
+ }
+
+ filter->cookie = cls_flower->cookie;
+
+ /* set the mask to all zeroes to begin with */
+ memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec));
+ /* start out with flow type and eth type IPv4 to begin with */
+ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW;
+ err = iavf_parse_cls_flower(adapter, cls_flower, filter);
+ if (err < 0)
+ goto err;
+
+ err = iavf_handle_tclass(adapter, tc, filter);
+ if (err < 0)
+ goto err;
+
+ /* add filter to the list */
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ list_add_tail(&filter->list, &adapter->cloud_filter_list);
+ adapter->num_cloud_filters++;
+ filter->add = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER;
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+err:
+ if (err)
+ kfree(filter);
+
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ return err;
+}
+
+/* iavf_find_cf - Find the cloud filter in the list
+ * @adapter: Board private structure
+ * @cookie: filter specific cookie
+ *
+ * Returns ptr to the filter object or NULL. Must be called while holding the
+ * cloud_filter_list_lock.
+ */
+static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter,
+ unsigned long *cookie)
+{
+ struct iavf_cloud_filter *filter = NULL;
+
+ if (!cookie)
+ return NULL;
+
+ list_for_each_entry(filter, &adapter->cloud_filter_list, list) {
+ if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie)))
+ return filter;
+ }
+ return NULL;
+}
+
+/**
+ * iavf_delete_clsflower - Remove tc flower filters
+ * @adapter: board private structure
+ * @cls_flower: Pointer to struct flow_cls_offload
+ */
+static int iavf_delete_clsflower(struct iavf_adapter *adapter,
+ struct flow_cls_offload *cls_flower)
+{
+ struct iavf_cloud_filter *filter = NULL;
+ int err = 0;
+
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ filter = iavf_find_cf(adapter, &cls_flower->cookie);
+ if (filter) {
+ filter->del = true;
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER;
+ } else {
+ err = -EINVAL;
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+
+ return err;
+}
+
+/**
+ * iavf_setup_tc_cls_flower - flower classifier offloads
+ * @netdev: net device to configure
+ * @type_data: offload data
+ */
+static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
+ struct flow_cls_offload *cls_flower)
+{
+ if (cls_flower->common.chain_index)
+ return -EOPNOTSUPP;
+
+ switch (cls_flower->command) {
+ case FLOW_CLS_REPLACE:
+ return iavf_configure_clsflower(adapter, cls_flower);
+ case FLOW_CLS_DESTROY:
+ return iavf_delete_clsflower(adapter, cls_flower);
+ case FLOW_CLS_STATS:
+ return -EOPNOTSUPP;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+/**
+ * iavf_setup_tc_block_cb - block callback for tc
+ * @type: type of offload
+ * @type_data: offload data
+ * @cb_priv:
+ *
+ * This function is the block callback for traffic classes
+ **/
+static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+ void *cb_priv)
+{
+ switch (type) {
+ case TC_SETUP_CLSFLOWER:
+ return iavf_setup_tc_cls_flower(cb_priv, type_data);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static LIST_HEAD(iavf_block_cb_list);
+
+/**
+ * iavf_setup_tc - configure multiple traffic classes
+ * @netdev: network interface device structure
+ * @type: type of offload
+ * @type_date: tc offload data
+ *
+ * This function is the callback to ndo_setup_tc in the
+ * netdev_ops.
+ *
+ * Returns 0 on success
+ **/
+static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
+ void *type_data)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ switch (type) {
+ case TC_SETUP_QDISC_MQPRIO:
+ return __iavf_setup_tc(netdev, type_data);
+ case TC_SETUP_BLOCK:
+ return flow_block_cb_setup_simple(type_data,
+ &iavf_block_cb_list,
+ iavf_setup_tc_block_cb,
+ adapter, adapter, true);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+/**
+ * iavf_open - Called when a network interface is made active
+ * @netdev: network interface device structure
+ *
+ * Returns 0 on success, negative value on failure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP). At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the watchdog is started,
+ * and the stack is notified that the interface is ready.
+ **/
+static int iavf_open(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ int err;
+
+ if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
+ dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
+ return -EIO;
+ }
+
+ while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section))
+ usleep_range(500, 1000);
+
+ if (adapter->state != __IAVF_DOWN) {
+ err = -EBUSY;
+ goto err_unlock;
+ }
+
+ /* allocate transmit descriptors */
+ err = iavf_setup_all_tx_resources(adapter);
+ if (err)
+ goto err_setup_tx;
+
+ /* allocate receive descriptors */
+ err = iavf_setup_all_rx_resources(adapter);
+ if (err)
+ goto err_setup_rx;
+
+ /* clear any pending interrupts, may auto mask */
+ err = iavf_request_traffic_irqs(adapter, netdev->name);
+ if (err)
+ goto err_req_irq;
+
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+
+ iavf_add_filter(adapter, adapter->hw.mac.addr);
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ iavf_configure(adapter);
+
+ iavf_up_complete(adapter);
+
+ iavf_irq_enable(adapter, true);
+
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+
+ return 0;
+
+err_req_irq:
+ iavf_down(adapter);
+ iavf_free_traffic_irqs(adapter);
+err_setup_rx:
+ iavf_free_all_rx_resources(adapter);
+err_setup_tx:
+ iavf_free_all_tx_resources(adapter);
+err_unlock:
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+
+ return err;
+}
+
+/**
+ * iavf_close - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * Returns 0, this is not allowed to fail
+ *
+ * The close entry point is called when an interface is de-activated
+ * by the OS. The hardware is still under the drivers control, but
+ * needs to be disabled. All IRQs except vector 0 (reserved for admin queue)
+ * are freed, along with all transmit and receive resources.
+ **/
+static int iavf_close(struct net_device *netdev)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ int status;
+
+ if (adapter->state <= __IAVF_DOWN_PENDING)
+ return 0;
+
+ while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section))
+ usleep_range(500, 1000);
+
+ set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+ if (CLIENT_ENABLED(adapter))
+ adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE;
+
+ iavf_down(adapter);
+ adapter->state = __IAVF_DOWN_PENDING;
+ iavf_free_traffic_irqs(adapter);
+
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+
+ /* We explicitly don't free resources here because the hardware is
+ * still active and can DMA into memory. Resources are cleared in
+ * iavf_virtchnl_completion() after we get confirmation from the PF
+ * driver that the rings have been stopped.
+ *
+ * Also, we wait for state to transition to __IAVF_DOWN before
+ * returning. State change occurs in iavf_virtchnl_completion() after
+ * VF resources are released (which occurs after PF driver processes and
+ * responds to admin queue commands).
+ */
+
+ status = wait_event_timeout(adapter->down_waitqueue,
+ adapter->state == __IAVF_DOWN,
+ msecs_to_jiffies(500));
+ if (!status)
+ netdev_warn(netdev, "Device resources not yet released\n");
+ return 0;
+}
+
+/**
+ * iavf_change_mtu - Change the Maximum Transfer Unit
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ netdev->mtu = new_mtu;
+ if (CLIENT_ENABLED(adapter)) {
+ iavf_notify_client_l2_params(&adapter->vsi);
+ adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ }
+ adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+ queue_work(iavf_wq, &adapter->reset_task);
+
+ return 0;
+}
+
+/**
+ * iavf_set_features - set the netdev feature flags
+ * @netdev: ptr to the netdev being adjusted
+ * @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
+ **/
+static int iavf_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ /* Don't allow changing VLAN_RX flag when adapter is not capable
+ * of VLAN offload
+ */
+ if (!VLAN_ALLOWED(adapter)) {
+ if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX)
+ return -EINVAL;
+ } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) {
+ if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ adapter->aq_required |=
+ IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
+ else
+ adapter->aq_required |=
+ IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
+ }
+
+ return 0;
+}
+
+/**
+ * iavf_features_check - Validate encapsulated packet conforms to limits
+ * @skb: skb buff
+ * @dev: This physical port's netdev
+ * @features: Offload features that the stack believes apply
+ **/
+static netdev_features_t iavf_features_check(struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features)
+{
+ size_t len;
+
+ /* No point in doing any of this if neither checksum nor GSO are
+ * being requested for this frame. We can rule out both by just
+ * checking for CHECKSUM_PARTIAL
+ */
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return features;
+
+ /* We cannot support GSO if the MSS is going to be less than
+ * 64 bytes. If it is then we need to drop support for GSO.
+ */
+ if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
+ features &= ~NETIF_F_GSO_MASK;
+
+ /* MACLEN can support at most 63 words */
+ len = skb_network_header(skb) - skb->data;
+ if (len & ~(63 * 2))
+ goto out_err;
+
+ /* IPLEN and EIPLEN can support at most 127 dwords */
+ len = skb_transport_header(skb) - skb_network_header(skb);
+ if (len & ~(127 * 4))
+ goto out_err;
+
+ if (skb->encapsulation) {
+ /* L4TUNLEN can support 127 words */
+ len = skb_inner_network_header(skb) - skb_transport_header(skb);
+ if (len & ~(127 * 2))
+ goto out_err;
+
+ /* IPLEN can support at most 127 dwords */
+ len = skb_inner_transport_header(skb) -
+ skb_inner_network_header(skb);
+ if (len & ~(127 * 4))
+ goto out_err;
+ }
+
+ /* No need to validate L4LEN as TCP is the only protocol with a
+ * a flexible value and we support all possible values supported
+ * by TCP, which is at most 15 dwords
+ */
+
+ return features;
+out_err:
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+}
+
+/**
+ * iavf_fix_features - fix up the netdev feature bits
+ * @netdev: our net device
+ * @features: desired feature bits
+ *
+ * Returns fixed-up features bits
+ **/
+static netdev_features_t iavf_fix_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+ features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER);
+
+ return features;
+}
+
+static const struct net_device_ops iavf_netdev_ops = {
+ .ndo_open = iavf_open,
+ .ndo_stop = iavf_close,
+ .ndo_start_xmit = iavf_xmit_frame,
+ .ndo_set_rx_mode = iavf_set_rx_mode,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_set_mac_address = iavf_set_mac,
+ .ndo_change_mtu = iavf_change_mtu,
+ .ndo_tx_timeout = iavf_tx_timeout,
+ .ndo_vlan_rx_add_vid = iavf_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = iavf_vlan_rx_kill_vid,
+ .ndo_features_check = iavf_features_check,
+ .ndo_fix_features = iavf_fix_features,
+ .ndo_set_features = iavf_set_features,
+ .ndo_setup_tc = iavf_setup_tc,
+};
+
+/**
+ * iavf_check_reset_complete - check that VF reset is complete
+ * @hw: pointer to hw struct
+ *
+ * Returns 0 if device is ready to use, or -EBUSY if it's in reset.
+ **/
+static int iavf_check_reset_complete(struct iavf_hw *hw)
+{
+ u32 rstat;
+ int i;
+
+ for (i = 0; i < 100; i++) {
+ rstat = rd32(hw, IAVF_VFGEN_RSTAT) &
+ IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
+ if ((rstat == VIRTCHNL_VFR_VFACTIVE) ||
+ (rstat == VIRTCHNL_VFR_COMPLETED))
+ return 0;
+ usleep_range(10, 20);
+ }
+ return -EBUSY;
+}
+
+/**
+ * iavf_process_config - Process the config information we got from the PF
+ * @adapter: board private structure
+ *
+ * Verify that we have a valid config struct, and set up our netdev features
+ * and our VSI struct.
+ **/
+int iavf_process_config(struct iavf_adapter *adapter)
+{
+ struct virtchnl_vf_resource *vfres = adapter->vf_res;
+ int i, num_req_queues = adapter->num_req_queues;
+ struct net_device *netdev = adapter->netdev;
+ struct iavf_vsi *vsi = &adapter->vsi;
+ netdev_features_t hw_enc_features;
+ netdev_features_t hw_features;
+
+ /* got VF config message back from PF, now we can parse it */
+ for (i = 0; i < vfres->num_vsis; i++) {
+ if (vfres->vsi_res[i].vsi_type == VIRTCHNL_VSI_SRIOV)
+ adapter->vsi_res = &vfres->vsi_res[i];
+ }
+ if (!adapter->vsi_res) {
+ dev_err(&adapter->pdev->dev, "No LAN VSI found\n");
+ return -ENODEV;
+ }
+
+ if (num_req_queues &&
+ num_req_queues != adapter->vsi_res->num_queue_pairs) {
+ /* Problem. The PF gave us fewer queues than what we had
+ * negotiated in our request. Need a reset to see if we can't
+ * get back to a working state.
+ */
+ dev_err(&adapter->pdev->dev,
+ "Requested %d queues, but PF only gave us %d.\n",
+ num_req_queues,
+ adapter->vsi_res->num_queue_pairs);
+ adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
+ iavf_schedule_reset(adapter);
+ return -ENODEV;
+ }
+ adapter->num_req_queues = 0;
+
+ hw_enc_features = NETIF_F_SG |
+ NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_HIGHDMA |
+ NETIF_F_SOFT_FEATURES |
+ NETIF_F_TSO |
+ NETIF_F_TSO_ECN |
+ NETIF_F_TSO6 |
+ NETIF_F_SCTP_CRC |
+ NETIF_F_RXHASH |
+ NETIF_F_RXCSUM |
+ 0;
+
+ /* advertise to stack only if offloads for encapsulated packets is
+ * supported
+ */
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
+ hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_GRE |
+ NETIF_F_GSO_GRE_CSUM |
+ NETIF_F_GSO_IPXIP4 |
+ NETIF_F_GSO_IPXIP6 |
+ NETIF_F_GSO_UDP_TUNNEL_CSUM |
+ NETIF_F_GSO_PARTIAL |
+ 0;
+
+ if (!(vfres->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
+ netdev->gso_partial_features |=
+ NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+ netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
+ netdev->hw_enc_features |= hw_enc_features;
+ }
+ /* record features VLANs can make use of */
+ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
+
+ /* Write features and hw_features separately to avoid polluting
+ * with, or dropping, features that are set when we registered.
+ */
+ hw_features = hw_enc_features;
+
+ /* Enable VLAN features if supported */
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+ hw_features |= (NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX);
+ /* Enable cloud filter if ADQ is supported */
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)
+ hw_features |= NETIF_F_HW_TC;
+
+ netdev->hw_features |= hw_features;
+
+ netdev->features |= hw_features;
+
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+ netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+ netdev->priv_flags |= IFF_UNICAST_FLT;
+
+ /* Do not turn on offloads when they are requested to be turned off.
+ * TSO needs minimum 576 bytes to work correctly.
+ */
+ if (netdev->wanted_features) {
+ if (!(netdev->wanted_features & NETIF_F_TSO) ||
+ netdev->mtu < 576)
+ netdev->features &= ~NETIF_F_TSO;
+ if (!(netdev->wanted_features & NETIF_F_TSO6) ||
+ netdev->mtu < 576)
+ netdev->features &= ~NETIF_F_TSO6;
+ if (!(netdev->wanted_features & NETIF_F_TSO_ECN))
+ netdev->features &= ~NETIF_F_TSO_ECN;
+ if (!(netdev->wanted_features & NETIF_F_GRO))
+ netdev->features &= ~NETIF_F_GRO;
+ if (!(netdev->wanted_features & NETIF_F_GSO))
+ netdev->features &= ~NETIF_F_GSO;
+ }
+
+ adapter->vsi.id = adapter->vsi_res->vsi_id;
+
+ adapter->vsi.back = adapter;
+ adapter->vsi.base_vector = 1;
+ adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK;
+ vsi->netdev = adapter->netdev;
+ vsi->qs_handle = adapter->vsi_res->qset_handle;
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+ adapter->rss_key_size = vfres->rss_key_size;
+ adapter->rss_lut_size = vfres->rss_lut_size;
+ } else {
+ adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE;
+ adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE;
+ }
+
+ return 0;
+}
+
+/**
+ * iavf_init_task - worker thread to perform delayed initialization
+ * @work: pointer to work_struct containing our data
+ *
+ * This task completes the work that was begun in probe. Due to the nature
+ * of VF-PF communications, we may need to wait tens of milliseconds to get
+ * responses back from the PF. Rather than busy-wait in probe and bog down the
+ * whole system, we'll do it in a task so we can sleep.
+ * This task only runs during driver init. Once we've established
+ * communications with the PF driver and set up our netdev, the watchdog
+ * takes over.
+ **/
+static void iavf_init_task(struct work_struct *work)
+{
+ struct iavf_adapter *adapter = container_of(work,
+ struct iavf_adapter,
+ init_task.work);
+ struct iavf_hw *hw = &adapter->hw;
+
+ switch (adapter->state) {
+ case __IAVF_STARTUP:
+ if (iavf_startup(adapter) < 0)
+ goto init_failed;
+ break;
+ case __IAVF_INIT_VERSION_CHECK:
+ if (iavf_init_version_check(adapter) < 0)
+ goto init_failed;
+ break;
+ case __IAVF_INIT_GET_RESOURCES:
+ if (iavf_init_get_resources(adapter) < 0)
+ goto init_failed;
+ return;
+ default:
+ goto init_failed;
+ }
+
+ queue_delayed_work(iavf_wq, &adapter->init_task,
+ msecs_to_jiffies(30));
+ return;
+init_failed:
+ if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
+ dev_err(&adapter->pdev->dev,
+ "Failed to communicate with PF; waiting before retry\n");
+ adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
+ iavf_shutdown_adminq(hw);
+ adapter->state = __IAVF_STARTUP;
+ queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5);
+ return;
+ }
+ queue_delayed_work(iavf_wq, &adapter->init_task, HZ);
+}
+
+/**
+ * iavf_shutdown - Shutdown the device in preparation for a reboot
+ * @pdev: pci device structure
+ **/
+static void iavf_shutdown(struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ netif_device_detach(netdev);
+
+ if (netif_running(netdev))
+ iavf_close(netdev);
+
+ /* Prevent the watchdog from running. */
+ adapter->state = __IAVF_REMOVE;
+ adapter->aq_required = 0;
+
+#ifdef CONFIG_PM
+ pci_save_state(pdev);
+
+#endif
+ pci_disable_device(pdev);
+}
+
+/**
+ * iavf_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in iavf_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * iavf_probe initializes an adapter identified by a pci_dev structure.
+ * The OS initialization, configuring of the adapter private structure,
+ * and a hardware reset occur.
+ **/
+static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+ struct net_device *netdev;
+ struct iavf_adapter *adapter = NULL;
+ struct iavf_hw *hw = NULL;
+ int err;
+
+ err = pci_enable_device(pdev);
+ if (err)
+ return err;
+
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (err) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev,
+ "DMA configuration failed: 0x%x\n", err);
+ goto err_dma;
+ }
+ }
+
+ err = pci_request_regions(pdev, iavf_driver_name);
+ if (err) {
+ dev_err(&pdev->dev,
+ "pci_request_regions failed 0x%x\n", err);
+ goto err_pci_reg;
+ }
+
+ pci_enable_pcie_error_reporting(pdev);
+
+ pci_set_master(pdev);
+
+ netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter),
+ IAVF_MAX_REQ_QUEUES);
+ if (!netdev) {
+ err = -ENOMEM;
+ goto err_alloc_etherdev;
+ }
+
+ SET_NETDEV_DEV(netdev, &pdev->dev);
+
+ pci_set_drvdata(pdev, netdev);
+ adapter = netdev_priv(netdev);
+
+ adapter->netdev = netdev;
+ adapter->pdev = pdev;
+
+ hw = &adapter->hw;
+ hw->back = adapter;
+
+ adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
+ adapter->state = __IAVF_STARTUP;
+
+ /* Call save state here because it relies on the adapter struct. */
+ pci_save_state(pdev);
+
+ hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
+ pci_resource_len(pdev, 0));
+ if (!hw->hw_addr) {
+ err = -EIO;
+ goto err_ioremap;
+ }
+ hw->vendor_id = pdev->vendor;
+ hw->device_id = pdev->device;
+ pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
+ hw->subsystem_vendor_id = pdev->subsystem_vendor;
+ hw->subsystem_device_id = pdev->subsystem_device;
+ hw->bus.device = PCI_SLOT(pdev->devfn);
+ hw->bus.func = PCI_FUNC(pdev->devfn);
+ hw->bus.bus_id = pdev->bus->number;
+
+ /* set up the locks for the AQ, do this only once in probe
+ * and destroy them only once in remove
+ */
+ mutex_init(&hw->aq.asq_mutex);
+ mutex_init(&hw->aq.arq_mutex);
+
+ spin_lock_init(&adapter->mac_vlan_list_lock);
+ spin_lock_init(&adapter->cloud_filter_list_lock);
+
+ INIT_LIST_HEAD(&adapter->mac_filter_list);
+ INIT_LIST_HEAD(&adapter->vlan_filter_list);
+ INIT_LIST_HEAD(&adapter->cloud_filter_list);
+
+ INIT_WORK(&adapter->reset_task, iavf_reset_task);
+ INIT_WORK(&adapter->adminq_task, iavf_adminq_task);
+ INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task);
+ INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task);
+ INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task);
+ queue_delayed_work(iavf_wq, &adapter->init_task,
+ msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
+
+ /* Setup the wait queue for indicating transition to down status */
+ init_waitqueue_head(&adapter->down_waitqueue);
+
+ return 0;
+
+err_ioremap:
+ free_netdev(netdev);
+err_alloc_etherdev:
+ pci_release_regions(pdev);
+err_pci_reg:
+err_dma:
+ pci_disable_device(pdev);
+ return err;
+}
+
+#ifdef CONFIG_PM
+/**
+ * iavf_suspend - Power management suspend routine
+ * @pdev: PCI device information struct
+ * @state: unused
+ *
+ * Called when the system (VM) is entering sleep/suspend.
+ **/
+static int iavf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ int retval = 0;
+
+ netif_device_detach(netdev);
+
+ while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK,
+ &adapter->crit_section))
+ usleep_range(500, 1000);
+
+ if (netif_running(netdev)) {
+ rtnl_lock();
+ iavf_down(adapter);
+ rtnl_unlock();
+ }
+ iavf_free_misc_irq(adapter);
+ iavf_reset_interrupt_capability(adapter);
+
+ clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+
+ retval = pci_save_state(pdev);
+ if (retval)
+ return retval;
+
+ pci_disable_device(pdev);
+
+ return 0;
+}
+
+/**
+ * iavf_resume - Power management resume routine
+ * @pdev: PCI device information struct
+ *
+ * Called when the system (VM) is resumed from sleep/suspend.
+ **/
+static int iavf_resume(struct pci_dev *pdev)
+{
+ struct iavf_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
+ u32 err;
+
+ pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
+ /* pci_restore_state clears dev->state_saved so call
+ * pci_save_state to restore it.
+ */
+ pci_save_state(pdev);
+
+ err = pci_enable_device_mem(pdev);
+ if (err) {
+ dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n");
+ return err;
+ }
+ pci_set_master(pdev);
+
+ rtnl_lock();
+ err = iavf_set_interrupt_capability(adapter);
+ if (err) {
+ rtnl_unlock();
+ dev_err(&pdev->dev, "Cannot enable MSI-X interrupts.\n");
+ return err;
+ }
+ err = iavf_request_misc_irq(adapter);
+ rtnl_unlock();
+ if (err) {
+ dev_err(&pdev->dev, "Cannot get interrupt vector.\n");
+ return err;
+ }
+
+ queue_work(iavf_wq, &adapter->reset_task);
+
+ netif_device_attach(netdev);
+
+ return err;
+}
+
+#endif /* CONFIG_PM */
+/**
+ * iavf_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * iavf_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device. The could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ **/
+static void iavf_remove(struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_vlan_filter *vlf, *vlftmp;
+ struct iavf_mac_filter *f, *ftmp;
+ struct iavf_cloud_filter *cf, *cftmp;
+ struct iavf_hw *hw = &adapter->hw;
+ int err;
+ /* Indicate we are in remove and not to run reset_task */
+ set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section);
+ cancel_delayed_work_sync(&adapter->init_task);
+ cancel_work_sync(&adapter->reset_task);
+ cancel_delayed_work_sync(&adapter->client_task);
+ if (adapter->netdev_registered) {
+ unregister_netdev(netdev);
+ adapter->netdev_registered = false;
+ }
+ if (CLIENT_ALLOWED(adapter)) {
+ err = iavf_lan_del_device(adapter);
+ if (err)
+ dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+ err);
+ }
+
+ /* Shut down all the garbage mashers on the detention level */
+ adapter->state = __IAVF_REMOVE;
+ adapter->aq_required = 0;
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+ iavf_request_reset(adapter);
+ msleep(50);
+ /* If the FW isn't responding, kick it once, but only once. */
+ if (!iavf_asq_done(hw)) {
+ iavf_request_reset(adapter);
+ msleep(50);
+ }
+ iavf_free_all_tx_resources(adapter);
+ iavf_free_all_rx_resources(adapter);
+ iavf_misc_irq_disable(adapter);
+ iavf_free_misc_irq(adapter);
+ iavf_reset_interrupt_capability(adapter);
+ iavf_free_q_vectors(adapter);
+
+ cancel_delayed_work_sync(&adapter->watchdog_task);
+
+ cancel_work_sync(&adapter->adminq_task);
+
+ iavf_free_rss(adapter);
+
+ if (hw->aq.asq.count)
+ iavf_shutdown_adminq(hw);
+
+ /* destroy the locks only once, here */
+ mutex_destroy(&hw->aq.arq_mutex);
+ mutex_destroy(&hw->aq.asq_mutex);
+
+ iounmap(hw->hw_addr);
+ pci_release_regions(pdev);
+ iavf_free_all_tx_resources(adapter);
+ iavf_free_all_rx_resources(adapter);
+ iavf_free_queues(adapter);
+ kfree(adapter->vf_res);
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+ /* If we got removed before an up/down sequence, we've got a filter
+ * hanging out there that we need to get rid of.
+ */
+ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
+ list_del(&f->list);
+ kfree(f);
+ }
+ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list,
+ list) {
+ list_del(&vlf->list);
+ kfree(vlf);
+ }
+
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
+
+ spin_lock_bh(&adapter->cloud_filter_list_lock);
+ list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) {
+ list_del(&cf->list);
+ kfree(cf);
+ }
+ spin_unlock_bh(&adapter->cloud_filter_list_lock);
+
+ free_netdev(netdev);
+
+ pci_disable_pcie_error_reporting(pdev);
+
+ pci_disable_device(pdev);
+}
+
+static struct pci_driver iavf_driver = {
+ .name = iavf_driver_name,
+ .id_table = iavf_pci_tbl,
+ .probe = iavf_probe,
+ .remove = iavf_remove,
+#ifdef CONFIG_PM
+ .suspend = iavf_suspend,
+ .resume = iavf_resume,
+#endif
+ .shutdown = iavf_shutdown,
+};
+
+/**
+ * iavf_init_module - Driver Registration Routine
+ *
+ * iavf_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ **/
+static int __init iavf_init_module(void)
+{
+ int ret;
+
+ pr_info("iavf: %s - version %s\n", iavf_driver_string,
+ iavf_driver_version);
+
+ pr_info("%s\n", iavf_copyright);
+
+ iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1,
+ iavf_driver_name);
+ if (!iavf_wq) {
+ pr_err("%s: Failed to create workqueue\n", iavf_driver_name);
+ return -ENOMEM;
+ }
+ ret = pci_register_driver(&iavf_driver);
+ return ret;
+}
+
+module_init(iavf_init_module);
+
+/**
+ * iavf_exit_module - Driver Exit Cleanup Routine
+ *
+ * iavf_exit_module is called just before the driver is removed
+ * from memory.
+ **/
+static void __exit iavf_exit_module(void)
+{
+ pci_unregister_driver(&iavf_driver);
+ destroy_workqueue(iavf_wq);
+}
+
+module_exit(iavf_exit_module);
+
+/* iavf_main.c */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_osdep.h b/drivers/net/ethernet/intel/iavf/iavf_osdep.h
new file mode 100644
index 0000000..a452ce9
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_osdep.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_OSDEP_H_
+#define _IAVF_OSDEP_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/tcp.h>
+#include <linux/pci.h>
+
+/* get readq/writeq support for 32 bit kernels, use the low-first version */
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+/* File to be the magic between shared code and
+ * actual OS primitives
+ */
+
+#define hw_dbg(hw, S, A...) do {} while (0)
+
+#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
+#define rd32(a, reg) readl((a)->hw_addr + (reg))
+
+#define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg)))
+#define rd64(a, reg) readq((a)->hw_addr + (reg))
+#define iavf_flush(a) readl((a)->hw_addr + IAVF_VFGEN_RSTAT)
+
+/* memory allocation tracking */
+struct iavf_dma_mem {
+ void *va;
+ dma_addr_t pa;
+ u32 size;
+};
+
+#define iavf_allocate_dma_mem(h, m, unused, s, a) \
+ iavf_allocate_dma_mem_d(h, m, s, a)
+#define iavf_free_dma_mem(h, m) iavf_free_dma_mem_d(h, m)
+
+struct iavf_virt_mem {
+ void *va;
+ u32 size;
+};
+#define iavf_allocate_virt_mem(h, m, s) iavf_allocate_virt_mem_d(h, m, s)
+#define iavf_free_virt_mem(h, m) iavf_free_virt_mem_d(h, m)
+
+#define iavf_debug(h, m, s, ...) \
+do { \
+ if (((m) & (h)->debug_mask)) \
+ pr_info("iavf %02x:%02x.%x " s, \
+ (h)->bus.bus_id, (h)->bus.device, \
+ (h)->bus.func, ##__VA_ARGS__); \
+} while (0)
+
+#endif /* _IAVF_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
new file mode 100644
index 0000000..edebfbb
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_PROTOTYPE_H_
+#define _IAVF_PROTOTYPE_H_
+
+#include "iavf_type.h"
+#include "iavf_alloc.h"
+#include <linux/avf/virtchnl.h>
+
+/* Prototypes for shared code functions that are not in
+ * the standard function pointer structures. These are
+ * mostly because they are needed even before the init
+ * has happened and will assist in the early SW and FW
+ * setup.
+ */
+
+/* adminq functions */
+enum iavf_status iavf_init_adminq(struct iavf_hw *hw);
+enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw);
+void iavf_adminq_init_ring_data(struct iavf_hw *hw);
+enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
+ struct iavf_arq_event_info *e,
+ u16 *events_pending);
+enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
+ struct iavf_aq_desc *desc,
+ void *buff, /* can be NULL */
+ u16 buff_size,
+ struct iavf_asq_cmd_details *cmd_details);
+bool iavf_asq_done(struct iavf_hw *hw);
+
+/* debug function for adminq */
+void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask,
+ void *desc, void *buffer, u16 buf_len);
+
+void iavf_idle_aq(struct iavf_hw *hw);
+void iavf_resume_aq(struct iavf_hw *hw);
+bool iavf_check_asq_alive(struct iavf_hw *hw);
+enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading);
+const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err);
+const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err);
+
+enum iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid,
+ bool pf_lut, u8 *lut, u16 lut_size);
+enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,
+ bool pf_lut, u8 *lut, u16 lut_size);
+enum iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid,
+ struct iavf_aqc_get_set_rss_key_data *key);
+enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid,
+ struct iavf_aqc_get_set_rss_key_data *key);
+
+enum iavf_status iavf_set_mac_type(struct iavf_hw *hw);
+
+extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[];
+
+static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
+{
+ return iavf_ptype_lookup[ptype];
+}
+
+void iavf_vf_parse_hw_config(struct iavf_hw *hw,
+ struct virtchnl_vf_resource *msg);
+enum iavf_status iavf_vf_reset(struct iavf_hw *hw);
+enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
+ enum virtchnl_ops v_opcode,
+ enum iavf_status v_retval,
+ u8 *msg, u16 msglen,
+ struct iavf_asq_cmd_details *cmd_details);
+#endif /* _IAVF_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h
new file mode 100644
index 0000000..bf79333
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_register.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_REGISTER_H_
+#define _IAVF_REGISTER_H_
+
+#define IAVF_VF_ARQBAH1 0x00006000 /* Reset: EMPR */
+#define IAVF_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */
+#define IAVF_VF_ARQH1 0x00007400 /* Reset: EMPR */
+#define IAVF_VF_ARQH1_ARQH_SHIFT 0
+#define IAVF_VF_ARQH1_ARQH_MASK IAVF_MASK(0x3FF, IAVF_VF_ARQH1_ARQH_SHIFT)
+#define IAVF_VF_ARQLEN1 0x00008000 /* Reset: EMPR */
+#define IAVF_VF_ARQLEN1_ARQVFE_SHIFT 28
+#define IAVF_VF_ARQLEN1_ARQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQVFE_SHIFT)
+#define IAVF_VF_ARQLEN1_ARQOVFL_SHIFT 29
+#define IAVF_VF_ARQLEN1_ARQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQOVFL_SHIFT)
+#define IAVF_VF_ARQLEN1_ARQCRIT_SHIFT 30
+#define IAVF_VF_ARQLEN1_ARQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQCRIT_SHIFT)
+#define IAVF_VF_ARQLEN1_ARQENABLE_SHIFT 31
+#define IAVF_VF_ARQLEN1_ARQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQENABLE_SHIFT)
+#define IAVF_VF_ARQT1 0x00007000 /* Reset: EMPR */
+#define IAVF_VF_ATQBAH1 0x00007800 /* Reset: EMPR */
+#define IAVF_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */
+#define IAVF_VF_ATQH1 0x00006400 /* Reset: EMPR */
+#define IAVF_VF_ATQLEN1 0x00006800 /* Reset: EMPR */
+#define IAVF_VF_ATQLEN1_ATQVFE_SHIFT 28
+#define IAVF_VF_ATQLEN1_ATQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQVFE_SHIFT)
+#define IAVF_VF_ATQLEN1_ATQOVFL_SHIFT 29
+#define IAVF_VF_ATQLEN1_ATQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQOVFL_SHIFT)
+#define IAVF_VF_ATQLEN1_ATQCRIT_SHIFT 30
+#define IAVF_VF_ATQLEN1_ATQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQCRIT_SHIFT)
+#define IAVF_VF_ATQLEN1_ATQENABLE_SHIFT 31
+#define IAVF_VF_ATQLEN1_ATQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQENABLE_SHIFT)
+#define IAVF_VF_ATQT1 0x00008400 /* Reset: EMPR */
+#define IAVF_VFGEN_RSTAT 0x00008800 /* Reset: VFR */
+#define IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT 0
+#define IAVF_VFGEN_RSTAT_VFR_STATE_MASK IAVF_MASK(0x3, IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT)
+#define IAVF_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */
+#define IAVF_VFINT_DYN_CTL01_INTENA_SHIFT 0
+#define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT)
+#define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3
+#define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT)
+#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */
+#define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0
+#define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT)
+#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2
+#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT)
+#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3
+#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT)
+#define IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5
+#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24
+#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT)
+#define IAVF_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */
+#define IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30
+#define IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK IAVF_MASK(0x1, IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT)
+#define IAVF_VFINT_ICR0_ENA1_RSVD_SHIFT 31
+#define IAVF_VFINT_ICR01 0x00004800 /* Reset: CORER */
+#define IAVF_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */
+#define IAVF_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */
+#define IAVF_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */
+#define IAVF_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
+#define IAVF_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */
+#define IAVF_VFQF_HKEY_MAX_INDEX 12
+#define IAVF_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */
+#define IAVF_VFQF_HLUT_MAX_INDEX 15
+#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30
+#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT)
+#endif /* _IAVF_REGISTER_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_status.h b/drivers/net/ethernet/intel/iavf/iavf_status.h
new file mode 100644
index 0000000..46e3d1f
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_status.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_STATUS_H_
+#define _IAVF_STATUS_H_
+
+/* Error Codes */
+enum iavf_status {
+ IAVF_SUCCESS = 0,
+ IAVF_ERR_NVM = -1,
+ IAVF_ERR_NVM_CHECKSUM = -2,
+ IAVF_ERR_PHY = -3,
+ IAVF_ERR_CONFIG = -4,
+ IAVF_ERR_PARAM = -5,
+ IAVF_ERR_MAC_TYPE = -6,
+ IAVF_ERR_UNKNOWN_PHY = -7,
+ IAVF_ERR_LINK_SETUP = -8,
+ IAVF_ERR_ADAPTER_STOPPED = -9,
+ IAVF_ERR_INVALID_MAC_ADDR = -10,
+ IAVF_ERR_DEVICE_NOT_SUPPORTED = -11,
+ IAVF_ERR_MASTER_REQUESTS_PENDING = -12,
+ IAVF_ERR_INVALID_LINK_SETTINGS = -13,
+ IAVF_ERR_AUTONEG_NOT_COMPLETE = -14,
+ IAVF_ERR_RESET_FAILED = -15,
+ IAVF_ERR_SWFW_SYNC = -16,
+ IAVF_ERR_NO_AVAILABLE_VSI = -17,
+ IAVF_ERR_NO_MEMORY = -18,
+ IAVF_ERR_BAD_PTR = -19,
+ IAVF_ERR_RING_FULL = -20,
+ IAVF_ERR_INVALID_PD_ID = -21,
+ IAVF_ERR_INVALID_QP_ID = -22,
+ IAVF_ERR_INVALID_CQ_ID = -23,
+ IAVF_ERR_INVALID_CEQ_ID = -24,
+ IAVF_ERR_INVALID_AEQ_ID = -25,
+ IAVF_ERR_INVALID_SIZE = -26,
+ IAVF_ERR_INVALID_ARP_INDEX = -27,
+ IAVF_ERR_INVALID_FPM_FUNC_ID = -28,
+ IAVF_ERR_QP_INVALID_MSG_SIZE = -29,
+ IAVF_ERR_QP_TOOMANY_WRS_POSTED = -30,
+ IAVF_ERR_INVALID_FRAG_COUNT = -31,
+ IAVF_ERR_QUEUE_EMPTY = -32,
+ IAVF_ERR_INVALID_ALIGNMENT = -33,
+ IAVF_ERR_FLUSHED_QUEUE = -34,
+ IAVF_ERR_INVALID_PUSH_PAGE_INDEX = -35,
+ IAVF_ERR_INVALID_IMM_DATA_SIZE = -36,
+ IAVF_ERR_TIMEOUT = -37,
+ IAVF_ERR_OPCODE_MISMATCH = -38,
+ IAVF_ERR_CQP_COMPL_ERROR = -39,
+ IAVF_ERR_INVALID_VF_ID = -40,
+ IAVF_ERR_INVALID_HMCFN_ID = -41,
+ IAVF_ERR_BACKING_PAGE_ERROR = -42,
+ IAVF_ERR_NO_PBLCHUNKS_AVAILABLE = -43,
+ IAVF_ERR_INVALID_PBLE_INDEX = -44,
+ IAVF_ERR_INVALID_SD_INDEX = -45,
+ IAVF_ERR_INVALID_PAGE_DESC_INDEX = -46,
+ IAVF_ERR_INVALID_SD_TYPE = -47,
+ IAVF_ERR_MEMCPY_FAILED = -48,
+ IAVF_ERR_INVALID_HMC_OBJ_INDEX = -49,
+ IAVF_ERR_INVALID_HMC_OBJ_COUNT = -50,
+ IAVF_ERR_INVALID_SRQ_ARM_LIMIT = -51,
+ IAVF_ERR_SRQ_ENABLED = -52,
+ IAVF_ERR_ADMIN_QUEUE_ERROR = -53,
+ IAVF_ERR_ADMIN_QUEUE_TIMEOUT = -54,
+ IAVF_ERR_BUF_TOO_SHORT = -55,
+ IAVF_ERR_ADMIN_QUEUE_FULL = -56,
+ IAVF_ERR_ADMIN_QUEUE_NO_WORK = -57,
+ IAVF_ERR_BAD_IWARP_CQE = -58,
+ IAVF_ERR_NVM_BLANK_MODE = -59,
+ IAVF_ERR_NOT_IMPLEMENTED = -60,
+ IAVF_ERR_PE_DOORBELL_NOT_ENABLED = -61,
+ IAVF_ERR_DIAG_TEST_FAILED = -62,
+ IAVF_ERR_NOT_READY = -63,
+ IAVF_NOT_SUPPORTED = -64,
+ IAVF_ERR_FIRMWARE_API_VERSION = -65,
+ IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66,
+};
+
+#endif /* _IAVF_STATUS_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
similarity index 64%
rename from drivers/net/ethernet/intel/i40evf/i40e_trace.h
rename to drivers/net/ethernet/intel/iavf/iavf_trace.h
index d7a4e68..1058e68 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -3,34 +3,34 @@
/* Modeled on trace-events-sample.h */
-/* The trace subsystem name for i40evf will be "i40evf".
+/* The trace subsystem name for iavf will be "iavf".
*
- * This file is named i40e_trace.h.
+ * This file is named iavf_trace.h.
*
* Since this include file's name is different from the trace
* subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end
* of this file.
*/
#undef TRACE_SYSTEM
-#define TRACE_SYSTEM i40evf
+#define TRACE_SYSTEM iavf
/* See trace-events-sample.h for a detailed description of why this
* guard clause is different from most normal include files.
*/
-#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
-#define _I40E_TRACE_H_
+#if !defined(_IAVF_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _IAVF_TRACE_H_
#include <linux/tracepoint.h>
/**
- * i40e_trace() macro enables shared code to refer to trace points
+ * iavf_trace() macro enables shared code to refer to trace points
* like:
*
- * trace_i40e{,vf}_example(args...)
+ * trace_iavf{,vf}_example(args...)
*
* ... as:
*
- * i40e_trace(example, args...)
+ * iavf_trace(example, args...)
*
* ... to resolve to the PF or VF version of the tracepoint without
* ifdefs, and to allow tracepoints to be disabled entirely at build
@@ -39,29 +39,29 @@
* Trace point should always be referred to in the driver via this
* macro.
*
- * Similarly, i40e_trace_enabled(trace_name) wraps references to
- * trace_i40e{,vf}_<trace_name>_enabled() functions.
+ * Similarly, iavf_trace_enabled(trace_name) wraps references to
+ * trace_iavf{,vf}_<trace_name>_enabled() functions.
*/
-#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name)
-#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name)
+#define _IAVF_TRACE_NAME(trace_name) (trace_ ## iavf ## _ ## trace_name)
+#define IAVF_TRACE_NAME(trace_name) _IAVF_TRACE_NAME(trace_name)
-#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args)
+#define iavf_trace(trace_name, args...) IAVF_TRACE_NAME(trace_name)(args)
-#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)()
+#define iavf_trace_enabled(trace_name) IAVF_TRACE_NAME(trace_name##_enabled)()
/* Events common to PF and VF. Corresponding versions will be defined
- * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace()
+ * for both, named trace_iavf_* and trace_iavf_*. The iavf_trace()
* macro above will select the right trace point name for the driver
* being built from shared code.
*/
/* Events related to a vsi & ring */
DECLARE_EVENT_CLASS(
- i40evf_tx_template,
+ iavf_tx_template,
- TP_PROTO(struct i40e_ring *ring,
- struct i40e_tx_desc *desc,
- struct i40e_tx_buffer *buf),
+ TP_PROTO(struct iavf_ring *ring,
+ struct iavf_tx_desc *desc,
+ struct iavf_tx_buffer *buf),
TP_ARGS(ring, desc, buf),
@@ -93,26 +93,26 @@
);
DEFINE_EVENT(
- i40evf_tx_template, i40evf_clean_tx_irq,
- TP_PROTO(struct i40e_ring *ring,
- struct i40e_tx_desc *desc,
- struct i40e_tx_buffer *buf),
+ iavf_tx_template, iavf_clean_tx_irq,
+ TP_PROTO(struct iavf_ring *ring,
+ struct iavf_tx_desc *desc,
+ struct iavf_tx_buffer *buf),
TP_ARGS(ring, desc, buf));
DEFINE_EVENT(
- i40evf_tx_template, i40evf_clean_tx_irq_unmap,
- TP_PROTO(struct i40e_ring *ring,
- struct i40e_tx_desc *desc,
- struct i40e_tx_buffer *buf),
+ iavf_tx_template, iavf_clean_tx_irq_unmap,
+ TP_PROTO(struct iavf_ring *ring,
+ struct iavf_tx_desc *desc,
+ struct iavf_tx_buffer *buf),
TP_ARGS(ring, desc, buf));
DECLARE_EVENT_CLASS(
- i40evf_rx_template,
+ iavf_rx_template,
- TP_PROTO(struct i40e_ring *ring,
- union i40e_32byte_rx_desc *desc,
+ TP_PROTO(struct iavf_ring *ring,
+ union iavf_32byte_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb),
@@ -138,26 +138,26 @@
);
DEFINE_EVENT(
- i40evf_rx_template, i40evf_clean_rx_irq,
- TP_PROTO(struct i40e_ring *ring,
- union i40e_32byte_rx_desc *desc,
+ iavf_rx_template, iavf_clean_rx_irq,
+ TP_PROTO(struct iavf_ring *ring,
+ union iavf_32byte_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb));
DEFINE_EVENT(
- i40evf_rx_template, i40evf_clean_rx_irq_rx,
- TP_PROTO(struct i40e_ring *ring,
- union i40e_32byte_rx_desc *desc,
+ iavf_rx_template, iavf_clean_rx_irq_rx,
+ TP_PROTO(struct iavf_ring *ring,
+ union iavf_32byte_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb));
DECLARE_EVENT_CLASS(
- i40evf_xmit_template,
+ iavf_xmit_template,
TP_PROTO(struct sk_buff *skb,
- struct i40e_ring *ring),
+ struct iavf_ring *ring),
TP_ARGS(skb, ring),
@@ -180,23 +180,23 @@
);
DEFINE_EVENT(
- i40evf_xmit_template, i40evf_xmit_frame_ring,
+ iavf_xmit_template, iavf_xmit_frame_ring,
TP_PROTO(struct sk_buff *skb,
- struct i40e_ring *ring),
+ struct iavf_ring *ring),
TP_ARGS(skb, ring));
DEFINE_EVENT(
- i40evf_xmit_template, i40evf_xmit_frame_ring_drop,
+ iavf_xmit_template, iavf_xmit_frame_ring_drop,
TP_PROTO(struct sk_buff *skb,
- struct i40e_ring *ring),
+ struct iavf_ring *ring),
TP_ARGS(skb, ring));
/* Events unique to the VF. */
-#endif /* _I40E_TRACE_H_ */
-/* This must be outside ifdef _I40E_TRACE_H */
+#endif /* _IAVF_TRACE_H_ */
+/* This must be outside ifdef _IAVF_TRACE_H */
/* This trace include file is not located in the .../include/trace
* with the kernel tracepoint definitions, because we're a loadable
@@ -205,5 +205,5 @@
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE i40e_trace
+#define TRACE_INCLUDE_FILE iavf_trace
#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
similarity index 71%
rename from drivers/net/ethernet/intel/i40evf/i40e_txrx.c
rename to drivers/net/ethernet/intel/iavf/iavf_txrx.c
index a973071..7a30d5d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2,34 +2,33 @@
/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/prefetch.h>
-#include <net/busy_poll.h>
-#include "i40evf.h"
-#include "i40e_trace.h"
-#include "i40e_prototype.h"
+#include "iavf.h"
+#include "iavf_trace.h"
+#include "iavf_prototype.h"
static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
u32 td_tag)
{
- return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
- ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) |
- ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
- ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
- ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT));
+ return cpu_to_le64(IAVF_TX_DESC_DTYPE_DATA |
+ ((u64)td_cmd << IAVF_TXD_QW1_CMD_SHIFT) |
+ ((u64)td_offset << IAVF_TXD_QW1_OFFSET_SHIFT) |
+ ((u64)size << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) |
+ ((u64)td_tag << IAVF_TXD_QW1_L2TAG1_SHIFT));
}
-#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
+#define IAVF_TXD_CMD (IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_RS)
/**
- * i40e_unmap_and_free_tx_resource - Release a Tx buffer
+ * iavf_unmap_and_free_tx_resource - Release a Tx buffer
* @ring: the ring that owns the buffer
* @tx_buffer: the buffer to free
**/
-static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
- struct i40e_tx_buffer *tx_buffer)
+static void iavf_unmap_and_free_tx_resource(struct iavf_ring *ring,
+ struct iavf_tx_buffer *tx_buffer)
{
if (tx_buffer->skb) {
- if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
+ if (tx_buffer->tx_flags & IAVF_TX_FLAGS_FD_SB)
kfree(tx_buffer->raw_buf);
else
dev_kfree_skb_any(tx_buffer->skb);
@@ -52,10 +51,10 @@
}
/**
- * i40evf_clean_tx_ring - Free any empty Tx buffers
+ * iavf_clean_tx_ring - Free any empty Tx buffers
* @tx_ring: ring to be cleaned
**/
-void i40evf_clean_tx_ring(struct i40e_ring *tx_ring)
+void iavf_clean_tx_ring(struct iavf_ring *tx_ring)
{
unsigned long bi_size;
u16 i;
@@ -66,9 +65,9 @@
/* Free all the Tx ring sk_buffs */
for (i = 0; i < tx_ring->count; i++)
- i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]);
+ iavf_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]);
- bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
+ bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count;
memset(tx_ring->tx_bi, 0, bi_size);
/* Zero out the descriptor ring */
@@ -85,14 +84,14 @@
}
/**
- * i40evf_free_tx_resources - Free Tx resources per queue
+ * iavf_free_tx_resources - Free Tx resources per queue
* @tx_ring: Tx descriptor ring for a specific queue
*
* Free all transmit software resources
**/
-void i40evf_free_tx_resources(struct i40e_ring *tx_ring)
+void iavf_free_tx_resources(struct iavf_ring *tx_ring)
{
- i40evf_clean_tx_ring(tx_ring);
+ iavf_clean_tx_ring(tx_ring);
kfree(tx_ring->tx_bi);
tx_ring->tx_bi = NULL;
@@ -104,14 +103,14 @@
}
/**
- * i40evf_get_tx_pending - how many Tx descriptors not processed
+ * iavf_get_tx_pending - how many Tx descriptors not processed
* @ring: the ring of descriptors
* @in_sw: is tx_pending being checked in SW or HW
*
* Since there is no access to the ring head register
* in XL710, we need to use our local copies
**/
-u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
+u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw)
{
u32 head, tail;
@@ -126,15 +125,15 @@
}
/**
- * i40evf_detect_recover_hung - Function to detect and recover hung_queues
+ * iavf_detect_recover_hung - Function to detect and recover hung_queues
* @vsi: pointer to vsi struct with tx queues
*
* VSI has netdev and netdev has TX queues. This function is to check each of
* those TX queues if they are hung, trigger recovery by issuing SW interrupt.
**/
-void i40evf_detect_recover_hung(struct i40e_vsi *vsi)
+void iavf_detect_recover_hung(struct iavf_vsi *vsi)
{
- struct i40e_ring *tx_ring = NULL;
+ struct iavf_ring *tx_ring = NULL;
struct net_device *netdev;
unsigned int i;
int packets;
@@ -142,7 +141,7 @@
if (!vsi)
return;
- if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ if (test_bit(__IAVF_VSI_DOWN, vsi->state))
return;
netdev = vsi->netdev;
@@ -164,16 +163,16 @@
*/
packets = tx_ring->stats.packets & INT_MAX;
if (tx_ring->tx_stats.prev_pkt_ctr == packets) {
- i40evf_force_wb(vsi, tx_ring->q_vector);
+ iavf_force_wb(vsi, tx_ring->q_vector);
continue;
}
/* Memory barrier between read of packet count and call
- * to i40evf_get_tx_pending()
+ * to iavf_get_tx_pending()
*/
smp_rmb();
tx_ring->tx_stats.prev_pkt_ctr =
- i40evf_get_tx_pending(tx_ring, true) ? packets : -1;
+ iavf_get_tx_pending(tx_ring, true) ? packets : -1;
}
}
}
@@ -181,28 +180,28 @@
#define WB_STRIDE 4
/**
- * i40e_clean_tx_irq - Reclaim resources after transmit completes
+ * iavf_clean_tx_irq - Reclaim resources after transmit completes
* @vsi: the VSI we care about
* @tx_ring: Tx ring to clean
* @napi_budget: Used to determine if we are in netpoll
*
* Returns true if there's any budget left (e.g. the clean is finished)
**/
-static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
- struct i40e_ring *tx_ring, int napi_budget)
+static bool iavf_clean_tx_irq(struct iavf_vsi *vsi,
+ struct iavf_ring *tx_ring, int napi_budget)
{
- u16 i = tx_ring->next_to_clean;
- struct i40e_tx_buffer *tx_buf;
- struct i40e_tx_desc *tx_desc;
+ int i = tx_ring->next_to_clean;
+ struct iavf_tx_buffer *tx_buf;
+ struct iavf_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
unsigned int budget = vsi->work_limit;
tx_buf = &tx_ring->tx_bi[i];
- tx_desc = I40E_TX_DESC(tx_ring, i);
+ tx_desc = IAVF_TX_DESC(tx_ring, i);
i -= tx_ring->count;
do {
- struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
+ struct iavf_tx_desc *eop_desc = tx_buf->next_to_watch;
/* if next_to_watch is not set then there is no work pending */
if (!eop_desc)
@@ -211,10 +210,10 @@
/* prevent any other reads prior to eop_desc */
smp_rmb();
- i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
+ iavf_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
/* if the descriptor isn't done, no work yet to do */
if (!(eop_desc->cmd_type_offset_bsz &
- cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
+ cpu_to_le64(IAVF_TX_DESC_DTYPE_DESC_DONE)))
break;
/* clear next_to_watch to prevent false hangs */
@@ -239,7 +238,7 @@
/* unmap remaining buffers */
while (tx_desc != eop_desc) {
- i40e_trace(clean_tx_irq_unmap,
+ iavf_trace(clean_tx_irq_unmap,
tx_ring, tx_desc, tx_buf);
tx_buf++;
@@ -248,7 +247,7 @@
if (unlikely(!i)) {
i -= tx_ring->count;
tx_buf = tx_ring->tx_bi;
- tx_desc = I40E_TX_DESC(tx_ring, 0);
+ tx_desc = IAVF_TX_DESC(tx_ring, 0);
}
/* unmap any remaining paged data */
@@ -268,7 +267,7 @@
if (unlikely(!i)) {
i -= tx_ring->count;
tx_buf = tx_ring->tx_bi;
- tx_desc = I40E_TX_DESC(tx_ring, 0);
+ tx_desc = IAVF_TX_DESC(tx_ring, 0);
}
prefetch(tx_desc);
@@ -286,18 +285,18 @@
tx_ring->q_vector->tx.total_bytes += total_bytes;
tx_ring->q_vector->tx.total_packets += total_packets;
- if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
+ if (tx_ring->flags & IAVF_TXR_FLAGS_WB_ON_ITR) {
/* check to see if there are < 4 descriptors
* waiting to be written back, then kick the hardware to force
* them to be written back in case we stay in NAPI.
* In this mode on X722 we do not enable Interrupt.
*/
- unsigned int j = i40evf_get_tx_pending(tx_ring, false);
+ unsigned int j = iavf_get_tx_pending(tx_ring, false);
if (budget &&
((j / WB_STRIDE) == 0) && (j > 0) &&
- !test_bit(__I40E_VSI_DOWN, vsi->state) &&
- (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+ !test_bit(__IAVF_VSI_DOWN, vsi->state) &&
+ (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count))
tx_ring->arm_wb = true;
}
@@ -307,14 +306,14 @@
#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2))
if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
- (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
+ (IAVF_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
*/
smp_mb();
if (__netif_subqueue_stopped(tx_ring->netdev,
tx_ring->queue_index) &&
- !test_bit(__I40E_VSI_DOWN, vsi->state)) {
+ !test_bit(__IAVF_VSI_DOWN, vsi->state)) {
netif_wake_subqueue(tx_ring->netdev,
tx_ring->queue_index);
++tx_ring->tx_stats.restart_queue;
@@ -325,75 +324,75 @@
}
/**
- * i40evf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled
+ * iavf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled
* @vsi: the VSI we care about
* @q_vector: the vector on which to enable writeback
*
**/
-static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi,
- struct i40e_q_vector *q_vector)
+static void iavf_enable_wb_on_itr(struct iavf_vsi *vsi,
+ struct iavf_q_vector *q_vector)
{
u16 flags = q_vector->tx.ring[0].flags;
u32 val;
- if (!(flags & I40E_TXR_FLAGS_WB_ON_ITR))
+ if (!(flags & IAVF_TXR_FLAGS_WB_ON_ITR))
return;
if (q_vector->arm_wb_state)
return;
- val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK |
- I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */
+ val = IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK |
+ IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */
wr32(&vsi->back->hw,
- I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), val);
+ IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val);
q_vector->arm_wb_state = true;
}
/**
- * i40evf_force_wb - Issue SW Interrupt so HW does a wb
+ * iavf_force_wb - Issue SW Interrupt so HW does a wb
* @vsi: the VSI we care about
* @q_vector: the vector on which to force writeback
*
**/
-void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector)
{
- u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
- I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */
- I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK |
- I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK
+ u32 val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK |
+ IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */
+ IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK |
+ IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK
/* allow 00 to be written to the index */;
wr32(&vsi->back->hw,
- I40E_VFINT_DYN_CTLN1(q_vector->reg_idx),
+ IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx),
val);
}
-static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector,
- struct i40e_ring_container *rc)
+static inline bool iavf_container_is_rx(struct iavf_q_vector *q_vector,
+ struct iavf_ring_container *rc)
{
return &q_vector->rx == rc;
}
-static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector)
+static inline unsigned int iavf_itr_divisor(struct iavf_q_vector *q_vector)
{
unsigned int divisor;
switch (q_vector->adapter->link_speed) {
- case I40E_LINK_SPEED_40GB:
- divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024;
+ case IAVF_LINK_SPEED_40GB:
+ divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 1024;
break;
- case I40E_LINK_SPEED_25GB:
- case I40E_LINK_SPEED_20GB:
- divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512;
+ case IAVF_LINK_SPEED_25GB:
+ case IAVF_LINK_SPEED_20GB:
+ divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 512;
break;
default:
- case I40E_LINK_SPEED_10GB:
- divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256;
+ case IAVF_LINK_SPEED_10GB:
+ divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 256;
break;
- case I40E_LINK_SPEED_1GB:
- case I40E_LINK_SPEED_100MB:
- divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32;
+ case IAVF_LINK_SPEED_1GB:
+ case IAVF_LINK_SPEED_100MB:
+ divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 32;
break;
}
@@ -401,7 +400,7 @@
}
/**
- * i40e_update_itr - update the dynamic ITR value based on statistics
+ * iavf_update_itr - update the dynamic ITR value based on statistics
* @q_vector: structure containing interrupt and ring information
* @rc: structure containing ring performance data
*
@@ -413,8 +412,8 @@
* on testing data as well as attempting to minimize response time
* while increasing bulk throughput.
**/
-static void i40e_update_itr(struct i40e_q_vector *q_vector,
- struct i40e_ring_container *rc)
+static void iavf_update_itr(struct iavf_q_vector *q_vector,
+ struct iavf_ring_container *rc)
{
unsigned int avg_wire_size, packets, bytes, itr;
unsigned long next_update = jiffies;
@@ -428,9 +427,9 @@
/* For Rx we want to push the delay up and default to low latency.
* for Tx we want to pull the delay down and default to high latency.
*/
- itr = i40e_container_is_rx(q_vector, rc) ?
- I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY :
- I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY;
+ itr = iavf_container_is_rx(q_vector, rc) ?
+ IAVF_ITR_ADAPTIVE_MIN_USECS | IAVF_ITR_ADAPTIVE_LATENCY :
+ IAVF_ITR_ADAPTIVE_MAX_USECS | IAVF_ITR_ADAPTIVE_LATENCY;
/* If we didn't update within up to 1 - 2 jiffies we can assume
* that either packets are coming in so slow there hasn't been
@@ -454,15 +453,15 @@
packets = rc->total_packets;
bytes = rc->total_bytes;
- if (i40e_container_is_rx(q_vector, rc)) {
+ if (iavf_container_is_rx(q_vector, rc)) {
/* If Rx there are 1 to 4 packets and bytes are less than
* 9000 assume insufficient data to use bulk rate limiting
* approach unless Tx is already in bulk rate limiting. We
* are likely latency driven.
*/
if (packets && packets < 4 && bytes < 9000 &&
- (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) {
- itr = I40E_ITR_ADAPTIVE_LATENCY;
+ (q_vector->tx.target_itr & IAVF_ITR_ADAPTIVE_LATENCY)) {
+ itr = IAVF_ITR_ADAPTIVE_LATENCY;
goto adjust_by_size;
}
} else if (packets < 4) {
@@ -471,15 +470,15 @@
* reset the ITR_ADAPTIVE_LATENCY bit for latency mode so
* that the Rx can relax.
*/
- if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS &&
- (q_vector->rx.target_itr & I40E_ITR_MASK) ==
- I40E_ITR_ADAPTIVE_MAX_USECS)
+ if (rc->target_itr == IAVF_ITR_ADAPTIVE_MAX_USECS &&
+ (q_vector->rx.target_itr & IAVF_ITR_MASK) ==
+ IAVF_ITR_ADAPTIVE_MAX_USECS)
goto clear_counts;
} else if (packets > 32) {
/* If we have processed over 32 packets in a single interrupt
* for Tx assume we need to switch over to "bulk" mode.
*/
- rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY;
+ rc->target_itr &= ~IAVF_ITR_ADAPTIVE_LATENCY;
}
/* We have no packets to actually measure against. This means
@@ -491,17 +490,17 @@
* fixed amount.
*/
if (packets < 56) {
- itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC;
- if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) {
- itr &= I40E_ITR_ADAPTIVE_LATENCY;
- itr += I40E_ITR_ADAPTIVE_MAX_USECS;
+ itr = rc->target_itr + IAVF_ITR_ADAPTIVE_MIN_INC;
+ if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) {
+ itr &= IAVF_ITR_ADAPTIVE_LATENCY;
+ itr += IAVF_ITR_ADAPTIVE_MAX_USECS;
}
goto clear_counts;
}
if (packets <= 256) {
itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr);
- itr &= I40E_ITR_MASK;
+ itr &= IAVF_ITR_MASK;
/* Between 56 and 112 is our "goldilocks" zone where we are
* working out "just right". Just report that our current
@@ -516,9 +515,9 @@
* in half per interrupt.
*/
itr /= 2;
- itr &= I40E_ITR_MASK;
- if (itr < I40E_ITR_ADAPTIVE_MIN_USECS)
- itr = I40E_ITR_ADAPTIVE_MIN_USECS;
+ itr &= IAVF_ITR_MASK;
+ if (itr < IAVF_ITR_ADAPTIVE_MIN_USECS)
+ itr = IAVF_ITR_ADAPTIVE_MIN_USECS;
goto clear_counts;
}
@@ -529,7 +528,7 @@
* though for smaller packet sizes there isn't much we can do as
* NAPI polling will likely be kicking in sooner rather than later.
*/
- itr = I40E_ITR_ADAPTIVE_BULK;
+ itr = IAVF_ITR_ADAPTIVE_BULK;
adjust_by_size:
/* If packet counts are 256 or greater we can assume we have a gross
@@ -577,7 +576,7 @@
/* If we are in low latency mode halve our delay which doubles the
* rate to somewhere between 100K to 16K ints/sec
*/
- if (itr & I40E_ITR_ADAPTIVE_LATENCY)
+ if (itr & IAVF_ITR_ADAPTIVE_LATENCY)
avg_wire_size /= 2;
/* Resultant value is 256 times larger than it needs to be. This
@@ -587,12 +586,12 @@
* Use addition as we have already recorded the new latency flag
* for the ITR value.
*/
- itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) *
- I40E_ITR_ADAPTIVE_MIN_INC;
+ itr += DIV_ROUND_UP(avg_wire_size, iavf_itr_divisor(q_vector)) *
+ IAVF_ITR_ADAPTIVE_MIN_INC;
- if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) {
- itr &= I40E_ITR_ADAPTIVE_LATENCY;
- itr += I40E_ITR_ADAPTIVE_MAX_USECS;
+ if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) {
+ itr &= IAVF_ITR_ADAPTIVE_LATENCY;
+ itr += IAVF_ITR_ADAPTIVE_MAX_USECS;
}
clear_counts:
@@ -607,12 +606,12 @@
}
/**
- * i40evf_setup_tx_descriptors - Allocate the Tx descriptors
+ * iavf_setup_tx_descriptors - Allocate the Tx descriptors
* @tx_ring: the tx ring to set up
*
* Return 0 on success, negative on error
**/
-int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
+int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring)
{
struct device *dev = tx_ring->dev;
int bi_size;
@@ -622,13 +621,13 @@
/* warn if we are about to overwrite the pointer */
WARN_ON(tx_ring->tx_bi);
- bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
+ bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count;
tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL);
if (!tx_ring->tx_bi)
goto err;
/* round up to nearest 4K */
- tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
+ tx_ring->size = tx_ring->count * sizeof(struct iavf_tx_desc);
tx_ring->size = ALIGN(tx_ring->size, 4096);
tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
@@ -650,10 +649,10 @@
}
/**
- * i40evf_clean_rx_ring - Free Rx buffers
+ * iavf_clean_rx_ring - Free Rx buffers
* @rx_ring: ring to be cleaned
**/
-void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
+void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
{
unsigned long bi_size;
u16 i;
@@ -669,7 +668,7 @@
/* Free all the Rx ring sk_buffs */
for (i = 0; i < rx_ring->count; i++) {
- struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+ struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
if (!rx_bi->page)
continue;
@@ -685,9 +684,9 @@
/* free resources associated with mapping */
dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
- i40e_rx_pg_size(rx_ring),
+ iavf_rx_pg_size(rx_ring),
DMA_FROM_DEVICE,
- I40E_RX_DMA_ATTR);
+ IAVF_RX_DMA_ATTR);
__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
@@ -695,7 +694,7 @@
rx_bi->page_offset = 0;
}
- bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
+ bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
memset(rx_ring->rx_bi, 0, bi_size);
/* Zero out the descriptor ring */
@@ -707,14 +706,14 @@
}
/**
- * i40evf_free_rx_resources - Free Rx resources
+ * iavf_free_rx_resources - Free Rx resources
* @rx_ring: ring to clean the resources from
*
* Free all receive software resources
**/
-void i40evf_free_rx_resources(struct i40e_ring *rx_ring)
+void iavf_free_rx_resources(struct iavf_ring *rx_ring)
{
- i40evf_clean_rx_ring(rx_ring);
+ iavf_clean_rx_ring(rx_ring);
kfree(rx_ring->rx_bi);
rx_ring->rx_bi = NULL;
@@ -726,19 +725,19 @@
}
/**
- * i40evf_setup_rx_descriptors - Allocate Rx descriptors
+ * iavf_setup_rx_descriptors - Allocate Rx descriptors
* @rx_ring: Rx descriptor ring (for a specific queue) to setup
*
* Returns 0 on success, negative on failure
**/
-int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring)
+int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
{
struct device *dev = rx_ring->dev;
int bi_size;
/* warn if we are about to overwrite the pointer */
WARN_ON(rx_ring->rx_bi);
- bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
+ bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
if (!rx_ring->rx_bi)
goto err;
@@ -746,7 +745,7 @@
u64_stats_init(&rx_ring->syncp);
/* Round up to nearest 4K */
- rx_ring->size = rx_ring->count * sizeof(union i40e_32byte_rx_desc);
+ rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
rx_ring->size = ALIGN(rx_ring->size, 4096);
rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
&rx_ring->dma, GFP_KERNEL);
@@ -769,11 +768,11 @@
}
/**
- * i40e_release_rx_desc - Store the new tail and head values
+ * iavf_release_rx_desc - Store the new tail and head values
* @rx_ring: ring to bump
* @val: new head index
**/
-static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
+static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val)
{
rx_ring->next_to_use = val;
@@ -790,26 +789,26 @@
}
/**
- * i40e_rx_offset - Return expected offset into page to access data
+ * iavf_rx_offset - Return expected offset into page to access data
* @rx_ring: Ring we are requesting offset of
*
* Returns the offset value for ring into the data buffer.
*/
-static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+static inline unsigned int iavf_rx_offset(struct iavf_ring *rx_ring)
{
- return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+ return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0;
}
/**
- * i40e_alloc_mapped_page - recycle or make a new page
+ * iavf_alloc_mapped_page - recycle or make a new page
* @rx_ring: ring to use
* @bi: rx_buffer struct to modify
*
* Returns true if the page was successfully allocated or
* reused.
**/
-static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *bi)
+static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *bi)
{
struct page *page = bi->page;
dma_addr_t dma;
@@ -821,7 +820,7 @@
}
/* alloc new page for storage */
- page = dev_alloc_pages(i40e_rx_pg_order(rx_ring));
+ page = dev_alloc_pages(iavf_rx_pg_order(rx_ring));
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_page_failed++;
return false;
@@ -829,22 +828,22 @@
/* map page for use */
dma = dma_map_page_attrs(rx_ring->dev, page, 0,
- i40e_rx_pg_size(rx_ring),
+ iavf_rx_pg_size(rx_ring),
DMA_FROM_DEVICE,
- I40E_RX_DMA_ATTR);
+ IAVF_RX_DMA_ATTR);
/* if mapping failed free memory back to system since
* there isn't much point in holding memory we can't use
*/
if (dma_mapping_error(rx_ring->dev, dma)) {
- __free_pages(page, i40e_rx_pg_order(rx_ring));
+ __free_pages(page, iavf_rx_pg_order(rx_ring));
rx_ring->rx_stats.alloc_page_failed++;
return false;
}
bi->dma = dma;
bi->page = page;
- bi->page_offset = i40e_rx_offset(rx_ring);
+ bi->page_offset = iavf_rx_offset(rx_ring);
/* initialize pagecnt_bias to 1 representing we fully own page */
bi->pagecnt_bias = 1;
@@ -853,15 +852,15 @@
}
/**
- * i40e_receive_skb - Send a completed packet up the stack
+ * iavf_receive_skb - Send a completed packet up the stack
* @rx_ring: rx ring in play
* @skb: packet to send up
* @vlan_tag: vlan tag for packet
**/
-static void i40e_receive_skb(struct i40e_ring *rx_ring,
+static void iavf_receive_skb(struct iavf_ring *rx_ring,
struct sk_buff *skb, u16 vlan_tag)
{
- struct i40e_q_vector *q_vector = rx_ring->q_vector;
+ struct iavf_q_vector *q_vector = rx_ring->q_vector;
if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
(vlan_tag & VLAN_VID_MASK))
@@ -871,27 +870,27 @@
}
/**
- * i40evf_alloc_rx_buffers - Replace used receive buffers
+ * iavf_alloc_rx_buffers - Replace used receive buffers
* @rx_ring: ring to place buffers on
* @cleaned_count: number of buffers to replace
*
* Returns false if all allocations were successful, true if any fail
**/
-bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
+bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
{
u16 ntu = rx_ring->next_to_use;
- union i40e_rx_desc *rx_desc;
- struct i40e_rx_buffer *bi;
+ union iavf_rx_desc *rx_desc;
+ struct iavf_rx_buffer *bi;
/* do nothing if no valid netdev defined */
if (!rx_ring->netdev || !cleaned_count)
return false;
- rx_desc = I40E_RX_DESC(rx_ring, ntu);
+ rx_desc = IAVF_RX_DESC(rx_ring, ntu);
bi = &rx_ring->rx_bi[ntu];
do {
- if (!i40e_alloc_mapped_page(rx_ring, bi))
+ if (!iavf_alloc_mapped_page(rx_ring, bi))
goto no_buffers;
/* sync the buffer for use by the device */
@@ -909,7 +908,7 @@
bi++;
ntu++;
if (unlikely(ntu == rx_ring->count)) {
- rx_desc = I40E_RX_DESC(rx_ring, 0);
+ rx_desc = IAVF_RX_DESC(rx_ring, 0);
bi = rx_ring->rx_bi;
ntu = 0;
}
@@ -921,13 +920,13 @@
} while (cleaned_count);
if (rx_ring->next_to_use != ntu)
- i40e_release_rx_desc(rx_ring, ntu);
+ iavf_release_rx_desc(rx_ring, ntu);
return false;
no_buffers:
if (rx_ring->next_to_use != ntu)
- i40e_release_rx_desc(rx_ring, ntu);
+ iavf_release_rx_desc(rx_ring, ntu);
/* make sure to come back via polling to try again after
* allocation failure
@@ -936,27 +935,27 @@
}
/**
- * i40e_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
* @vsi: the VSI we care about
* @skb: skb currently being received and modified
* @rx_desc: the receive descriptor
**/
-static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
+static inline void iavf_rx_checksum(struct iavf_vsi *vsi,
struct sk_buff *skb,
- union i40e_rx_desc *rx_desc)
+ union iavf_rx_desc *rx_desc)
{
- struct i40e_rx_ptype_decoded decoded;
+ struct iavf_rx_ptype_decoded decoded;
u32 rx_error, rx_status;
bool ipv4, ipv6;
u8 ptype;
u64 qword;
qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT;
- rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >>
- I40E_RXD_QW1_ERROR_SHIFT;
- rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
- I40E_RXD_QW1_STATUS_SHIFT;
+ ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT;
+ rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >>
+ IAVF_RXD_QW1_ERROR_SHIFT;
+ rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >>
+ IAVF_RXD_QW1_STATUS_SHIFT;
decoded = decode_rx_desc_ptype(ptype);
skb->ip_summed = CHECKSUM_NONE;
@@ -968,45 +967,45 @@
return;
/* did the hardware decode the packet and checksum? */
- if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+ if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
return;
/* both known and outer_ip must be set for the below code to work */
if (!(decoded.known && decoded.outer_ip))
return;
- ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
- (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4);
- ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
- (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6);
+ ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
+ (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4);
+ ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
+ (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6);
if (ipv4 &&
- (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
- BIT(I40E_RX_DESC_ERROR_EIPE_SHIFT))))
+ (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
+ BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
goto checksum_fail;
/* likely incorrect csum if alternate IP extension headers found */
if (ipv6 &&
- rx_status & BIT(I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+ rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
/* don't increment checksum err here, non-fatal err */
return;
/* there was some L4 error, count error and punt packet to the stack */
- if (rx_error & BIT(I40E_RX_DESC_ERROR_L4E_SHIFT))
+ if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
goto checksum_fail;
/* handle packets that were not able to be checksummed due
* to arrival speed, in this case the stack can compute
* the csum.
*/
- if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
+ if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
return;
/* Only report checksum unnecessary for TCP, UDP, or SCTP */
switch (decoded.inner_prot) {
- case I40E_RX_PTYPE_INNER_PROT_TCP:
- case I40E_RX_PTYPE_INNER_PROT_UDP:
- case I40E_RX_PTYPE_INNER_PROT_SCTP:
+ case IAVF_RX_PTYPE_INNER_PROT_TCP:
+ case IAVF_RX_PTYPE_INNER_PROT_UDP:
+ case IAVF_RX_PTYPE_INNER_PROT_SCTP:
skb->ip_summed = CHECKSUM_UNNECESSARY;
/* fall though */
default:
@@ -1020,56 +1019,56 @@
}
/**
- * i40e_ptype_to_htype - get a hash type
+ * iavf_ptype_to_htype - get a hash type
* @ptype: the ptype value from the descriptor
*
* Returns a hash type to be used by skb_set_hash
**/
-static inline int i40e_ptype_to_htype(u8 ptype)
+static inline int iavf_ptype_to_htype(u8 ptype)
{
- struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
+ struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
if (!decoded.known)
return PKT_HASH_TYPE_NONE;
- if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
- decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4)
+ if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4)
return PKT_HASH_TYPE_L4;
- else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
- decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3)
+ else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3)
return PKT_HASH_TYPE_L3;
else
return PKT_HASH_TYPE_L2;
}
/**
- * i40e_rx_hash - set the hash value in the skb
+ * iavf_rx_hash - set the hash value in the skb
* @ring: descriptor ring
* @rx_desc: specific descriptor
* @skb: skb currently being received and modified
* @rx_ptype: Rx packet type
**/
-static inline void i40e_rx_hash(struct i40e_ring *ring,
- union i40e_rx_desc *rx_desc,
+static inline void iavf_rx_hash(struct iavf_ring *ring,
+ union iavf_rx_desc *rx_desc,
struct sk_buff *skb,
u8 rx_ptype)
{
u32 hash;
const __le64 rss_mask =
- cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
- I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
+ cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
+ IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
if (ring->netdev->features & NETIF_F_RXHASH)
return;
if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
- skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+ skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype));
}
}
/**
- * i40evf_process_skb_fields - Populate skb header fields from Rx descriptor
+ * iavf_process_skb_fields - Populate skb header fields from Rx descriptor
* @rx_ring: rx descriptor ring packet is being transacted on
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being populated
@@ -1080,13 +1079,13 @@
* other fields within the skb.
**/
static inline
-void i40evf_process_skb_fields(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, struct sk_buff *skb,
- u8 rx_ptype)
+void iavf_process_skb_fields(struct iavf_ring *rx_ring,
+ union iavf_rx_desc *rx_desc, struct sk_buff *skb,
+ u8 rx_ptype)
{
- i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+ iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
- i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
+ iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
skb_record_rx_queue(skb, rx_ring->queue_index);
@@ -1095,7 +1094,7 @@
}
/**
- * i40e_cleanup_headers - Correct empty headers
+ * iavf_cleanup_headers - Correct empty headers
* @rx_ring: rx descriptor ring packet is being transacted on
* @skb: pointer to current skb being fixed
*
@@ -1107,7 +1106,7 @@
*
* Returns true if an error was encountered and skb was freed.
**/
-static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb)
+static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb)
{
/* if eth_skb_pad returns an error the skb was freed */
if (eth_skb_pad(skb))
@@ -1117,16 +1116,16 @@
}
/**
- * i40e_reuse_rx_page - page flip buffer and store it back on the ring
+ * iavf_reuse_rx_page - page flip buffer and store it back on the ring
* @rx_ring: rx descriptor ring to store buffers on
* @old_buff: donor buffer to have page reused
*
* Synchronizes page for reuse by the adapter
**/
-static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *old_buff)
+static void iavf_reuse_rx_page(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *old_buff)
{
- struct i40e_rx_buffer *new_buff;
+ struct iavf_rx_buffer *new_buff;
u16 nta = rx_ring->next_to_alloc;
new_buff = &rx_ring->rx_bi[nta];
@@ -1143,20 +1142,20 @@
}
/**
- * i40e_page_is_reusable - check if any reuse is possible
+ * iavf_page_is_reusable - check if any reuse is possible
* @page: page struct to check
*
* A page is not reusable if it was allocated under low memory
* conditions, or it's not in the same NUMA node as this CPU.
*/
-static inline bool i40e_page_is_reusable(struct page *page)
+static inline bool iavf_page_is_reusable(struct page *page)
{
return (page_to_nid(page) == numa_mem_id()) &&
!page_is_pfmemalloc(page);
}
/**
- * i40e_can_reuse_rx_page - Determine if this page can be reused by
+ * iavf_can_reuse_rx_page - Determine if this page can be reused by
* the adapter for another receive
*
* @rx_buffer: buffer containing the page
@@ -1182,13 +1181,13 @@
*
* In either case, if the page is reusable its refcount is increased.
**/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
+static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer)
{
unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
struct page *page = rx_buffer->page;
/* Is any reuse possible? */
- if (unlikely(!i40e_page_is_reusable(page)))
+ if (unlikely(!iavf_page_is_reusable(page)))
return false;
#if (PAGE_SIZE < 8192)
@@ -1196,9 +1195,9 @@
if (unlikely((page_count(page) - pagecnt_bias) > 1))
return false;
#else
-#define I40E_LAST_OFFSET \
- (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
- if (rx_buffer->page_offset > I40E_LAST_OFFSET)
+#define IAVF_LAST_OFFSET \
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048)
+ if (rx_buffer->page_offset > IAVF_LAST_OFFSET)
return false;
#endif
@@ -1215,7 +1214,7 @@
}
/**
- * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
+ * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: buffer containing page to add
* @skb: sk_buff to place the data into
@@ -1226,17 +1225,20 @@
*
* The function will then update the page offset.
**/
-static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *rx_buffer,
+static void iavf_add_rx_frag(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *rx_buffer,
struct sk_buff *skb,
unsigned int size)
{
#if (PAGE_SIZE < 8192)
- unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+ unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
+ unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring));
#endif
+ if (!size)
+ return;
+
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
rx_buffer->page_offset, size, truesize);
@@ -1249,17 +1251,20 @@
}
/**
- * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use
* @rx_ring: rx descriptor ring to transact packets on
* @size: size of buffer to add to skb
*
* This function will pull an Rx buffer from the ring and synchronize it
* for use by the CPU.
*/
-static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring,
const unsigned int size)
{
- struct i40e_rx_buffer *rx_buffer;
+ struct iavf_rx_buffer *rx_buffer;
+
+ if (!size)
+ return NULL;
rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
prefetchw(rx_buffer->page);
@@ -1278,7 +1283,7 @@
}
/**
- * i40e_construct_skb - Allocate skb and populate it
+ * iavf_construct_skb - Allocate skb and populate it
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: rx buffer to pull data from
* @size: size of buffer to add to skb
@@ -1287,20 +1292,23 @@
* data from the current receive descriptor, taking care to set up the
* skb correctly.
*/
-static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *rx_buffer,
+static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *rx_buffer,
unsigned int size)
{
- void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+ void *va;
#if (PAGE_SIZE < 8192)
- unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+ unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(size);
#endif
unsigned int headlen;
struct sk_buff *skb;
+ if (!rx_buffer)
+ return NULL;
/* prefetch first cache line of first page */
+ va = page_address(rx_buffer->page) + rx_buffer->page_offset;
prefetch(va);
#if L1_CACHE_BYTES < 128
prefetch(va + L1_CACHE_BYTES);
@@ -1308,15 +1316,15 @@
/* allocate a skb to store the frags */
skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- I40E_RX_HDR_SIZE,
+ IAVF_RX_HDR_SIZE,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
/* Determine available headroom for copy */
headlen = size;
- if (headlen > I40E_RX_HDR_SIZE)
- headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+ if (headlen > IAVF_RX_HDR_SIZE)
+ headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
@@ -1343,7 +1351,7 @@
}
/**
- * i40e_build_skb - Build skb around an existing buffer
+ * iavf_build_skb - Build skb around an existing buffer
* @rx_ring: Rx descriptor ring to transact packets on
* @rx_buffer: Rx buffer to pull data from
* @size: size of buffer to add to skb
@@ -1351,31 +1359,34 @@
* This function builds an skb around an existing Rx buffer, taking care
* to set up the skb correctly and avoid any memcpy overhead.
*/
-static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *rx_buffer,
+static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *rx_buffer,
unsigned int size)
{
- void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+ void *va;
#if (PAGE_SIZE < 8192)
- unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+ unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
- SKB_DATA_ALIGN(I40E_SKB_PAD + size);
+ SKB_DATA_ALIGN(IAVF_SKB_PAD + size);
#endif
struct sk_buff *skb;
+ if (!rx_buffer)
+ return NULL;
/* prefetch first cache line of first page */
+ va = page_address(rx_buffer->page) + rx_buffer->page_offset;
prefetch(va);
#if L1_CACHE_BYTES < 128
prefetch(va + L1_CACHE_BYTES);
#endif
/* build an skb around the page buffer */
- skb = build_skb(va - I40E_SKB_PAD, truesize);
+ skb = build_skb(va - IAVF_SKB_PAD, truesize);
if (unlikely(!skb))
return NULL;
/* update pointers within the skb to store the data */
- skb_reserve(skb, I40E_SKB_PAD);
+ skb_reserve(skb, IAVF_SKB_PAD);
__skb_put(skb, size);
/* buffer is used by skb, update page_offset */
@@ -1389,25 +1400,28 @@
}
/**
- * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * iavf_put_rx_buffer - Clean up used buffer and either recycle or free
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: rx buffer to pull data from
*
* This function will clean up the contents of the rx_buffer. It will
* either recycle the buffer or unmap it and free the associated resources.
*/
-static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
- struct i40e_rx_buffer *rx_buffer)
+static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
+ struct iavf_rx_buffer *rx_buffer)
{
- if (i40e_can_reuse_rx_page(rx_buffer)) {
+ if (!rx_buffer)
+ return;
+
+ if (iavf_can_reuse_rx_page(rx_buffer)) {
/* hand second half of page back to the ring */
- i40e_reuse_rx_page(rx_ring, rx_buffer);
+ iavf_reuse_rx_page(rx_ring, rx_buffer);
rx_ring->rx_stats.page_reuse_count++;
} else {
/* we are not reusing the buffer so unmap it */
dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
- i40e_rx_pg_size(rx_ring),
- DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+ iavf_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR);
__page_frag_cache_drain(rx_buffer->page,
rx_buffer->pagecnt_bias);
}
@@ -1417,7 +1431,7 @@
}
/**
- * i40e_is_non_eop - process handling of non-EOP buffers
+ * iavf_is_non_eop - process handling of non-EOP buffers
* @rx_ring: Rx ring being processed
* @rx_desc: Rx descriptor for current buffer
* @skb: Current socket buffer containing buffer in progress
@@ -1427,8 +1441,8 @@
* sk_buff in the next buffer to be chained and return true indicating
* that this is in fact a non-EOP buffer.
**/
-static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
+static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
+ union iavf_rx_desc *rx_desc,
struct sk_buff *skb)
{
u32 ntc = rx_ring->next_to_clean + 1;
@@ -1437,11 +1451,11 @@
ntc = (ntc < rx_ring->count) ? ntc : 0;
rx_ring->next_to_clean = ntc;
- prefetch(I40E_RX_DESC(rx_ring, ntc));
+ prefetch(IAVF_RX_DESC(rx_ring, ntc));
/* if we are the last buffer then there is nothing else to do */
-#define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT)
- if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF)))
+#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
+ if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
return false;
rx_ring->rx_stats.non_eop_descs++;
@@ -1450,7 +1464,7 @@
}
/**
- * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
+ * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
* @rx_ring: rx descriptor ring to transact packets on
* @budget: Total limit on number of packets to process
*
@@ -1461,29 +1475,29 @@
*
* Returns amount of work completed
**/
-static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
+static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
{
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
struct sk_buff *skb = rx_ring->skb;
- u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+ u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring);
bool failure = false;
while (likely(total_rx_packets < (unsigned int)budget)) {
- struct i40e_rx_buffer *rx_buffer;
- union i40e_rx_desc *rx_desc;
+ struct iavf_rx_buffer *rx_buffer;
+ union iavf_rx_desc *rx_desc;
unsigned int size;
u16 vlan_tag;
u8 rx_ptype;
u64 qword;
/* return some buffers to hardware, one at a time is too slow */
- if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
+ if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
failure = failure ||
- i40evf_alloc_rx_buffers(rx_ring, cleaned_count);
+ iavf_alloc_rx_buffers(rx_ring, cleaned_count);
cleaned_count = 0;
}
- rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
+ rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
/* status_error_len will always be zero for unused descriptors
* because it's cleared in cleanup, and overlaps with hdr_addr
@@ -1497,48 +1511,50 @@
* verified the descriptor has been written back.
*/
dma_rmb();
-
- size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
- I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
- if (!size)
+#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
+ if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
break;
- i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
- rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+ size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >>
+ IAVF_RXD_QW1_LENGTH_PBUF_SHIFT;
+
+ iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
+ rx_buffer = iavf_get_rx_buffer(rx_ring, size);
/* retrieve a buffer from the ring */
if (skb)
- i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+ iavf_add_rx_frag(rx_ring, rx_buffer, skb, size);
else if (ring_uses_build_skb(rx_ring))
- skb = i40e_build_skb(rx_ring, rx_buffer, size);
+ skb = iavf_build_skb(rx_ring, rx_buffer, size);
else
- skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+ skb = iavf_construct_skb(rx_ring, rx_buffer, size);
/* exit if we failed to retrieve a buffer */
if (!skb) {
rx_ring->rx_stats.alloc_buff_failed++;
- rx_buffer->pagecnt_bias++;
+ if (rx_buffer)
+ rx_buffer->pagecnt_bias++;
break;
}
- i40e_put_rx_buffer(rx_ring, rx_buffer);
+ iavf_put_rx_buffer(rx_ring, rx_buffer);
cleaned_count++;
- if (i40e_is_non_eop(rx_ring, rx_desc, skb))
+ if (iavf_is_non_eop(rx_ring, rx_desc, skb))
continue;
/* ERR_MASK will only have valid bits if EOP set, and
* what we are doing here is actually checking
- * I40E_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
+ * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
* the error field
*/
- if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
+ if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
dev_kfree_skb_any(skb);
skb = NULL;
continue;
}
- if (i40e_cleanup_headers(rx_ring, skb)) {
+ if (iavf_cleanup_headers(rx_ring, skb)) {
skb = NULL;
continue;
}
@@ -1547,18 +1563,18 @@
total_rx_bytes += skb->len;
qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
- I40E_RXD_QW1_PTYPE_SHIFT;
+ rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >>
+ IAVF_RXD_QW1_PTYPE_SHIFT;
/* populate checksum, VLAN, and protocol */
- i40evf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+ iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
- vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
+ vlan_tag = (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
- i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
- i40e_receive_skb(rx_ring, skb, vlan_tag);
+ iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
+ iavf_receive_skb(rx_ring, skb, vlan_tag);
skb = NULL;
/* update budget accounting */
@@ -1578,7 +1594,7 @@
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+static inline u32 iavf_buildreg_itr(const int type, u16 itr)
{
u32 val;
@@ -1597,17 +1613,17 @@
* only need to shift by the interval shift - 1 instead of the
* full value.
*/
- itr &= I40E_ITR_MASK;
+ itr &= IAVF_ITR_MASK;
- val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
- (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
- (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1));
+ val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK |
+ (type << IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
+ (itr << (IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1));
return val;
}
/* a small macro to shorten up some long lines */
-#define INTREG I40E_VFINT_DYN_CTLN1
+#define INTREG IAVF_VFINT_DYN_CTLN1
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
@@ -1619,20 +1635,20 @@
#define ITR_COUNTDOWN_START 3
/**
- * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt
+ * iavf_update_enable_itr - Update itr and re-enable MSIX interrupt
* @vsi: the VSI we care about
* @q_vector: q_vector for which itr is being updated and interrupt enabled
*
**/
-static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
- struct i40e_q_vector *q_vector)
+static inline void iavf_update_enable_itr(struct iavf_vsi *vsi,
+ struct iavf_q_vector *q_vector)
{
- struct i40e_hw *hw = &vsi->back->hw;
+ struct iavf_hw *hw = &vsi->back->hw;
u32 intval;
/* These will do nothing if dynamic updates are not enabled */
- i40e_update_itr(q_vector, &q_vector->tx);
- i40e_update_itr(q_vector, &q_vector->rx);
+ iavf_update_itr(q_vector, &q_vector->tx);
+ iavf_update_itr(q_vector, &q_vector->rx);
/* This block of logic allows us to get away with only updating
* one ITR value with each interrupt. The idea is to perform a
@@ -1644,7 +1660,7 @@
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
+ intval = iavf_buildreg_itr(IAVF_RX_ITR,
q_vector->rx.target_itr);
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
@@ -1654,29 +1670,29 @@
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
+ intval = iavf_buildreg_itr(IAVF_TX_ITR,
q_vector->tx.target_itr);
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
+ intval = iavf_buildreg_itr(IAVF_RX_ITR,
q_vector->rx.target_itr);
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
+ intval = iavf_buildreg_itr(IAVF_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
+ if (!test_bit(__IAVF_VSI_DOWN, vsi->state))
wr32(hw, INTREG(q_vector->reg_idx), intval);
}
/**
- * i40evf_napi_poll - NAPI polling Rx/Tx cleanup routine
+ * iavf_napi_poll - NAPI polling Rx/Tx cleanup routine
* @napi: napi struct with our devices info in it
* @budget: amount of work driver is allowed to do this pass, in packets
*
@@ -1684,18 +1700,18 @@
*
* Returns the amount of work done
**/
-int i40evf_napi_poll(struct napi_struct *napi, int budget)
+int iavf_napi_poll(struct napi_struct *napi, int budget)
{
- struct i40e_q_vector *q_vector =
- container_of(napi, struct i40e_q_vector, napi);
- struct i40e_vsi *vsi = q_vector->vsi;
- struct i40e_ring *ring;
+ struct iavf_q_vector *q_vector =
+ container_of(napi, struct iavf_q_vector, napi);
+ struct iavf_vsi *vsi = q_vector->vsi;
+ struct iavf_ring *ring;
bool clean_complete = true;
bool arm_wb = false;
int budget_per_ring;
int work_done = 0;
- if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
+ if (test_bit(__IAVF_VSI_DOWN, vsi->state)) {
napi_complete(napi);
return 0;
}
@@ -1703,8 +1719,8 @@
/* Since the actual Tx work is minimal, we can give the Tx a larger
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
- i40e_for_each_ring(ring, q_vector->tx) {
- if (!i40e_clean_tx_irq(vsi, ring, budget)) {
+ iavf_for_each_ring(ring, q_vector->tx) {
+ if (!iavf_clean_tx_irq(vsi, ring, budget)) {
clean_complete = false;
continue;
}
@@ -1721,8 +1737,8 @@
*/
budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
- i40e_for_each_ring(ring, q_vector->rx) {
- int cleaned = i40e_clean_rx_irq(ring, budget_per_ring);
+ iavf_for_each_ring(ring, q_vector->rx) {
+ int cleaned = iavf_clean_rx_irq(ring, budget_per_ring);
work_done += cleaned;
/* if we clean as many as budgeted, we must not be done */
@@ -1746,7 +1762,7 @@
napi_complete_done(napi, work_done);
/* Force an interrupt */
- i40evf_force_wb(vsi, q_vector);
+ iavf_force_wb(vsi, q_vector);
/* Return budget-1 so that polling stops */
return budget - 1;
@@ -1754,24 +1770,25 @@
tx_only:
if (arm_wb) {
q_vector->tx.ring[0].tx_stats.tx_force_wb++;
- i40e_enable_wb_on_itr(vsi, q_vector);
+ iavf_enable_wb_on_itr(vsi, q_vector);
}
return budget;
}
- if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
+ if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR)
q_vector->arm_wb_state = false;
- /* Work is done so exit the polling mode and re-enable the interrupt */
- napi_complete_done(napi, work_done);
-
- i40e_update_enable_itr(vsi, q_vector);
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ iavf_update_enable_itr(vsi, q_vector);
return min(work_done, budget - 1);
}
/**
- * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * iavf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
* @skb: send buffer
* @tx_ring: ring to send buffer on
* @flags: the tx flags to be set
@@ -1782,9 +1799,9 @@
* Returns error code indicate the frame should be dropped upon error and the
* otherwise returns 0 to indicate the flags has been set properly.
**/
-static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb,
- struct i40e_ring *tx_ring,
- u32 *flags)
+static inline int iavf_tx_prepare_vlan_flags(struct sk_buff *skb,
+ struct iavf_ring *tx_ring,
+ u32 *flags)
{
__be16 protocol = skb->protocol;
u32 tx_flags = 0;
@@ -1804,8 +1821,8 @@
/* if we have a HW VLAN tag being added, default to the HW one */
if (skb_vlan_tag_present(skb)) {
- tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
- tx_flags |= I40E_TX_FLAGS_HW_VLAN;
+ tx_flags |= skb_vlan_tag_get(skb) << IAVF_TX_FLAGS_VLAN_SHIFT;
+ tx_flags |= IAVF_TX_FLAGS_HW_VLAN;
/* else if it is a SW VLAN, check the next protocol and store the tag */
} else if (protocol == htons(ETH_P_8021Q)) {
struct vlan_hdr *vhdr, _vhdr;
@@ -1815,8 +1832,8 @@
return -EINVAL;
protocol = vhdr->h_vlan_encapsulated_proto;
- tx_flags |= ntohs(vhdr->h_vlan_TCI) << I40E_TX_FLAGS_VLAN_SHIFT;
- tx_flags |= I40E_TX_FLAGS_SW_VLAN;
+ tx_flags |= ntohs(vhdr->h_vlan_TCI) << IAVF_TX_FLAGS_VLAN_SHIFT;
+ tx_flags |= IAVF_TX_FLAGS_SW_VLAN;
}
out:
@@ -1825,14 +1842,14 @@
}
/**
- * i40e_tso - set up the tso context descriptor
+ * iavf_tso - set up the tso context descriptor
* @first: pointer to first Tx buffer for xmit
* @hdr_len: ptr to the size of the packet header
* @cd_type_cmd_tso_mss: Quad Word 1
*
* Returns 0 if no TSO can happen, 1 if tso is going, or error
**/
-static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len,
+static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len,
u64 *cd_type_cmd_tso_mss)
{
struct sk_buff *skb = first->skb;
@@ -1923,17 +1940,17 @@
first->bytecount += (first->gso_segs - 1) * *hdr_len;
/* find the field values */
- cd_cmd = I40E_TX_CTX_DESC_TSO;
+ cd_cmd = IAVF_TX_CTX_DESC_TSO;
cd_tso_len = skb->len - *hdr_len;
cd_mss = gso_size;
- *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
- (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
- (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
+ *cd_type_cmd_tso_mss |= (cd_cmd << IAVF_TXD_CTX_QW1_CMD_SHIFT) |
+ (cd_tso_len << IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) |
+ (cd_mss << IAVF_TXD_CTX_QW1_MSS_SHIFT);
return 1;
}
/**
- * i40e_tx_enable_csum - Enable Tx checksum offloads
+ * iavf_tx_enable_csum - Enable Tx checksum offloads
* @skb: send buffer
* @tx_flags: pointer to Tx flags currently set
* @td_cmd: Tx descriptor command bits to set
@@ -1941,9 +1958,9 @@
* @tx_ring: Tx descriptor ring
* @cd_tunneling: ptr to context desc bits
**/
-static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
+static int iavf_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
u32 *td_cmd, u32 *td_offset,
- struct i40e_ring *tx_ring,
+ struct iavf_ring *tx_ring,
u32 *cd_tunneling)
{
union {
@@ -1968,19 +1985,19 @@
l4.hdr = skb_transport_header(skb);
/* compute outer L2 header size */
- offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+ offset = ((ip.hdr - skb->data) / 2) << IAVF_TX_DESC_LENGTH_MACLEN_SHIFT;
if (skb->encapsulation) {
u32 tunnel = 0;
/* define outer network header type */
- if (*tx_flags & I40E_TX_FLAGS_IPV4) {
- tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
- I40E_TX_CTX_EXT_IP_IPV4 :
- I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+ if (*tx_flags & IAVF_TX_FLAGS_IPV4) {
+ tunnel |= (*tx_flags & IAVF_TX_FLAGS_TSO) ?
+ IAVF_TX_CTX_EXT_IP_IPV4 :
+ IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM;
l4_proto = ip.v4->protocol;
- } else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
- tunnel |= I40E_TX_CTX_EXT_IP_IPV6;
+ } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) {
+ tunnel |= IAVF_TX_CTX_EXT_IP_IPV6;
exthdr = ip.hdr + sizeof(*ip.v6);
l4_proto = ip.v6->nexthdr;
@@ -1992,20 +2009,20 @@
/* define outer transport */
switch (l4_proto) {
case IPPROTO_UDP:
- tunnel |= I40E_TXD_CTX_UDP_TUNNELING;
- *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
+ tunnel |= IAVF_TXD_CTX_UDP_TUNNELING;
+ *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL;
break;
case IPPROTO_GRE:
- tunnel |= I40E_TXD_CTX_GRE_TUNNELING;
- *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
+ tunnel |= IAVF_TXD_CTX_GRE_TUNNELING;
+ *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL;
break;
case IPPROTO_IPIP:
case IPPROTO_IPV6:
- *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
+ *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL;
l4.hdr = skb_inner_network_header(skb);
break;
default:
- if (*tx_flags & I40E_TX_FLAGS_TSO)
+ if (*tx_flags & IAVF_TX_FLAGS_TSO)
return -1;
skb_checksum_help(skb);
@@ -2014,20 +2031,20 @@
/* compute outer L3 header size */
tunnel |= ((l4.hdr - ip.hdr) / 4) <<
- I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT;
+ IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT;
/* switch IP header pointer from outer to inner header */
ip.hdr = skb_inner_network_header(skb);
/* compute tunnel header size */
tunnel |= ((ip.hdr - l4.hdr) / 2) <<
- I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+ IAVF_TXD_CTX_QW0_NATLEN_SHIFT;
/* indicate if we need to offload outer UDP header */
- if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+ if ((*tx_flags & IAVF_TX_FLAGS_TSO) &&
!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
- tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+ tunnel |= IAVF_TXD_CTX_QW0_L4T_CS_MASK;
/* record tunnel offload values */
*cd_tunneling |= tunnel;
@@ -2037,24 +2054,24 @@
l4_proto = 0;
/* reset type as we transition from outer to inner headers */
- *tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
+ *tx_flags &= ~(IAVF_TX_FLAGS_IPV4 | IAVF_TX_FLAGS_IPV6);
if (ip.v4->version == 4)
- *tx_flags |= I40E_TX_FLAGS_IPV4;
+ *tx_flags |= IAVF_TX_FLAGS_IPV4;
if (ip.v6->version == 6)
- *tx_flags |= I40E_TX_FLAGS_IPV6;
+ *tx_flags |= IAVF_TX_FLAGS_IPV6;
}
/* Enable IP checksum offloads */
- if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+ if (*tx_flags & IAVF_TX_FLAGS_IPV4) {
l4_proto = ip.v4->protocol;
/* the stack computes the IP header already, the only time we
* need the hardware to recompute it is in the case of TSO.
*/
- cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
- I40E_TX_DESC_CMD_IIPT_IPV4_CSUM :
- I40E_TX_DESC_CMD_IIPT_IPV4;
- } else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
- cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+ cmd |= (*tx_flags & IAVF_TX_FLAGS_TSO) ?
+ IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM :
+ IAVF_TX_DESC_CMD_IIPT_IPV4;
+ } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) {
+ cmd |= IAVF_TX_DESC_CMD_IIPT_IPV6;
exthdr = ip.hdr + sizeof(*ip.v6);
l4_proto = ip.v6->nexthdr;
@@ -2064,29 +2081,29 @@
}
/* compute inner L3 header size */
- offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
+ offset |= ((l4.hdr - ip.hdr) / 4) << IAVF_TX_DESC_LENGTH_IPLEN_SHIFT;
/* Enable L4 checksum offloads */
switch (l4_proto) {
case IPPROTO_TCP:
/* enable checksum offloads */
- cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
- offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_TCP;
+ offset |= l4.tcp->doff << IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
break;
case IPPROTO_SCTP:
/* enable SCTP checksum offload */
- cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
+ cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_SCTP;
offset |= (sizeof(struct sctphdr) >> 2) <<
- I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
break;
case IPPROTO_UDP:
/* enable UDP checksum offload */
- cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
+ cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_UDP;
offset |= (sizeof(struct udphdr) >> 2) <<
- I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+ IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
break;
default:
- if (*tx_flags & I40E_TX_FLAGS_TSO)
+ if (*tx_flags & IAVF_TX_FLAGS_TSO)
return -1;
skb_checksum_help(skb);
return 0;
@@ -2099,25 +2116,25 @@
}
/**
- * i40e_create_tx_ctx Build the Tx context descriptor
+ * iavf_create_tx_ctx Build the Tx context descriptor
* @tx_ring: ring to create the descriptor on
* @cd_type_cmd_tso_mss: Quad Word 1
* @cd_tunneling: Quad Word 0 - bits 0-31
* @cd_l2tag2: Quad Word 0 - bits 32-63
**/
-static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
+static void iavf_create_tx_ctx(struct iavf_ring *tx_ring,
const u64 cd_type_cmd_tso_mss,
const u32 cd_tunneling, const u32 cd_l2tag2)
{
- struct i40e_tx_context_desc *context_desc;
+ struct iavf_tx_context_desc *context_desc;
int i = tx_ring->next_to_use;
- if ((cd_type_cmd_tso_mss == I40E_TX_DESC_DTYPE_CONTEXT) &&
+ if ((cd_type_cmd_tso_mss == IAVF_TX_DESC_DTYPE_CONTEXT) &&
!cd_tunneling && !cd_l2tag2)
return;
/* grab the next descriptor */
- context_desc = I40E_TX_CTXTDESC(tx_ring, i);
+ context_desc = IAVF_TX_CTXTDESC(tx_ring, i);
i++;
tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
@@ -2130,7 +2147,7 @@
}
/**
- * __i40evf_chk_linearize - Check if there are more than 8 buffers per packet
+ * __iavf_chk_linearize - Check if there are more than 8 buffers per packet
* @skb: send buffer
*
* Note: Our HW can't DMA more than 8 buffers to build a packet on the wire
@@ -2142,20 +2159,20 @@
* the segment payload in the first descriptor, and another 7 for the
* fragments.
**/
-bool __i40evf_chk_linearize(struct sk_buff *skb)
+bool __iavf_chk_linearize(struct sk_buff *skb)
{
- const struct skb_frag_struct *frag, *stale;
+ const skb_frag_t *frag, *stale;
int nr_frags, sum;
/* no need to check if number of frags is less than 7 */
nr_frags = skb_shinfo(skb)->nr_frags;
- if (nr_frags < (I40E_MAX_BUFFER_TXD - 1))
+ if (nr_frags < (IAVF_MAX_BUFFER_TXD - 1))
return false;
/* We need to walk through the list and validate that each group
* of 6 fragments totals at least gso_size.
*/
- nr_frags -= I40E_MAX_BUFFER_TXD - 2;
+ nr_frags -= IAVF_MAX_BUFFER_TXD - 2;
frag = &skb_shinfo(skb)->frags[0];
/* Initialize size to the negative value of gso_size minus 1. We
@@ -2187,17 +2204,17 @@
* figure out what the remainder would be in the last
* descriptor associated with the fragment.
*/
- if (stale_size > I40E_MAX_DATA_PER_TXD) {
- int align_pad = -(stale->page_offset) &
- (I40E_MAX_READ_REQ_SIZE - 1);
+ if (stale_size > IAVF_MAX_DATA_PER_TXD) {
+ int align_pad = -(skb_frag_off(stale)) &
+ (IAVF_MAX_READ_REQ_SIZE - 1);
sum -= align_pad;
stale_size -= align_pad;
do {
- sum -= I40E_MAX_DATA_PER_TXD_ALIGNED;
- stale_size -= I40E_MAX_DATA_PER_TXD_ALIGNED;
- } while (stale_size > I40E_MAX_DATA_PER_TXD);
+ sum -= IAVF_MAX_DATA_PER_TXD_ALIGNED;
+ stale_size -= IAVF_MAX_DATA_PER_TXD_ALIGNED;
+ } while (stale_size > IAVF_MAX_DATA_PER_TXD);
}
/* if sum is negative we failed to make sufficient progress */
@@ -2214,20 +2231,20 @@
}
/**
- * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions
+ * __iavf_maybe_stop_tx - 2nd level check for tx stop conditions
* @tx_ring: the ring to be checked
* @size: the size buffer we want to assure is available
*
* Returns -EBUSY if a stop is needed, else 0
**/
-int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size)
{
netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
/* Memory barrier before checking head and tail */
smp_mb();
/* Check again in a case another CPU has just made room available. */
- if (likely(I40E_DESC_UNUSED(tx_ring) < size))
+ if (likely(IAVF_DESC_UNUSED(tx_ring) < size))
return -EBUSY;
/* A reprieve! - use start_queue because it doesn't call schedule */
@@ -2237,7 +2254,7 @@
}
/**
- * i40evf_tx_map - Build the Tx descriptor
+ * iavf_tx_map - Build the Tx descriptor
* @tx_ring: ring to send buffer on
* @skb: send buffer
* @first: first buffer info buffer to use
@@ -2246,34 +2263,34 @@
* @td_cmd: the command field in the descriptor
* @td_offset: offset for checksum or crc
**/
-static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
- struct i40e_tx_buffer *first, u32 tx_flags,
- const u8 hdr_len, u32 td_cmd, u32 td_offset)
+static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
+ struct iavf_tx_buffer *first, u32 tx_flags,
+ const u8 hdr_len, u32 td_cmd, u32 td_offset)
{
unsigned int data_len = skb->data_len;
unsigned int size = skb_headlen(skb);
- struct skb_frag_struct *frag;
- struct i40e_tx_buffer *tx_bi;
- struct i40e_tx_desc *tx_desc;
+ skb_frag_t *frag;
+ struct iavf_tx_buffer *tx_bi;
+ struct iavf_tx_desc *tx_desc;
u16 i = tx_ring->next_to_use;
u32 td_tag = 0;
dma_addr_t dma;
- if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
- td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
- td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >>
- I40E_TX_FLAGS_VLAN_SHIFT;
+ if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) {
+ td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1;
+ td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >>
+ IAVF_TX_FLAGS_VLAN_SHIFT;
}
first->tx_flags = tx_flags;
dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
- tx_desc = I40E_TX_DESC(tx_ring, i);
+ tx_desc = IAVF_TX_DESC(tx_ring, i);
tx_bi = first;
for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
- unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED;
+ unsigned int max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED;
if (dma_mapping_error(tx_ring->dev, dma))
goto dma_error;
@@ -2283,10 +2300,10 @@
dma_unmap_addr_set(tx_bi, dma, dma);
/* align size to end of page */
- max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1);
+ max_data += -dma & (IAVF_MAX_READ_REQ_SIZE - 1);
tx_desc->buffer_addr = cpu_to_le64(dma);
- while (unlikely(size > I40E_MAX_DATA_PER_TXD)) {
+ while (unlikely(size > IAVF_MAX_DATA_PER_TXD)) {
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, td_offset,
max_data, td_tag);
@@ -2295,14 +2312,14 @@
i++;
if (i == tx_ring->count) {
- tx_desc = I40E_TX_DESC(tx_ring, 0);
+ tx_desc = IAVF_TX_DESC(tx_ring, 0);
i = 0;
}
dma += max_data;
size -= max_data;
- max_data = I40E_MAX_DATA_PER_TXD_ALIGNED;
+ max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED;
tx_desc->buffer_addr = cpu_to_le64(dma);
}
@@ -2316,7 +2333,7 @@
i++;
if (i == tx_ring->count) {
- tx_desc = I40E_TX_DESC(tx_ring, 0);
+ tx_desc = IAVF_TX_DESC(tx_ring, 0);
i = 0;
}
@@ -2337,13 +2354,15 @@
tx_ring->next_to_use = i;
- i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+ iavf_maybe_stop_tx(tx_ring, DESC_NEEDED);
/* write last descriptor with RS and EOP bits */
- td_cmd |= I40E_TXD_CMD;
+ td_cmd |= IAVF_TXD_CMD;
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, td_offset, size, td_tag);
+ skb_tx_timestamp(skb);
+
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch.
*
@@ -2356,13 +2375,8 @@
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return;
@@ -2373,7 +2387,7 @@
/* clear dma mappings for failed tx_bi map */
for (;;) {
tx_bi = &tx_ring->tx_bi[i];
- i40e_unmap_and_free_tx_resource(tx_ring, tx_bi);
+ iavf_unmap_and_free_tx_resource(tx_ring, tx_bi);
if (tx_bi == first)
break;
if (i == 0)
@@ -2385,18 +2399,18 @@
}
/**
- * i40e_xmit_frame_ring - Sends buffer on Tx ring
+ * iavf_xmit_frame_ring - Sends buffer on Tx ring
* @skb: send buffer
* @tx_ring: ring to send buffer on
*
* Returns NETDEV_TX_OK if sent, else an error code
**/
-static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
- struct i40e_ring *tx_ring)
+static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb,
+ struct iavf_ring *tx_ring)
{
- u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT;
+ u64 cd_type_cmd_tso_mss = IAVF_TX_DESC_DTYPE_CONTEXT;
u32 cd_tunneling = 0, cd_l2tag2 = 0;
- struct i40e_tx_buffer *first;
+ struct iavf_tx_buffer *first;
u32 td_offset = 0;
u32 tx_flags = 0;
__be16 protocol;
@@ -2407,25 +2421,25 @@
/* prefetch the data, we'll need it later */
prefetch(skb->data);
- i40e_trace(xmit_frame_ring, skb, tx_ring);
+ iavf_trace(xmit_frame_ring, skb, tx_ring);
- count = i40e_xmit_descriptor_count(skb);
- if (i40e_chk_linearize(skb, count)) {
+ count = iavf_xmit_descriptor_count(skb);
+ if (iavf_chk_linearize(skb, count)) {
if (__skb_linearize(skb)) {
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
- count = i40e_txd_use_count(skb->len);
+ count = iavf_txd_use_count(skb->len);
tx_ring->tx_stats.tx_linearize++;
}
- /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
- * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
+ /* need: 1 descriptor per page * PAGE_SIZE/IAVF_MAX_DATA_PER_TXD,
+ * + 1 desc for skb_head_len/IAVF_MAX_DATA_PER_TXD,
* + 4 desc gap to avoid the cache line where head is,
* + 1 desc for context descriptor,
* otherwise try next time
*/
- if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+ if (iavf_maybe_stop_tx(tx_ring, count + 4 + 1)) {
tx_ring->tx_stats.tx_busy++;
return NETDEV_TX_BUSY;
}
@@ -2437,7 +2451,7 @@
first->gso_segs = 1;
/* prepare the xmit flags */
- if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
+ if (iavf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
goto out_drop;
/* obtain protocol of skb */
@@ -2445,64 +2459,62 @@
/* setup IPv4/IPv6 offloads */
if (protocol == htons(ETH_P_IP))
- tx_flags |= I40E_TX_FLAGS_IPV4;
+ tx_flags |= IAVF_TX_FLAGS_IPV4;
else if (protocol == htons(ETH_P_IPV6))
- tx_flags |= I40E_TX_FLAGS_IPV6;
+ tx_flags |= IAVF_TX_FLAGS_IPV6;
- tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss);
+ tso = iavf_tso(first, &hdr_len, &cd_type_cmd_tso_mss);
if (tso < 0)
goto out_drop;
else if (tso)
- tx_flags |= I40E_TX_FLAGS_TSO;
+ tx_flags |= IAVF_TX_FLAGS_TSO;
/* Always offload the checksum, since it's in the data descriptor */
- tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
+ tso = iavf_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
tx_ring, &cd_tunneling);
if (tso < 0)
goto out_drop;
- skb_tx_timestamp(skb);
-
/* always enable CRC insertion offload */
- td_cmd |= I40E_TX_DESC_CMD_ICRC;
+ td_cmd |= IAVF_TX_DESC_CMD_ICRC;
- i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
+ iavf_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
cd_tunneling, cd_l2tag2);
- i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
- td_cmd, td_offset);
+ iavf_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
+ td_cmd, td_offset);
return NETDEV_TX_OK;
out_drop:
- i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring);
+ iavf_trace(xmit_frame_ring_drop, first->skb, tx_ring);
dev_kfree_skb_any(first->skb);
first->skb = NULL;
return NETDEV_TX_OK;
}
/**
- * i40evf_xmit_frame - Selects the correct VSI and Tx queue to send buffer
+ * iavf_xmit_frame - Selects the correct VSI and Tx queue to send buffer
* @skb: send buffer
* @netdev: network interface device structure
*
* Returns NETDEV_TX_OK if sent, else an error code
**/
-netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
- struct i40evf_adapter *adapter = netdev_priv(netdev);
- struct i40e_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping];
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+ struct iavf_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping];
/* hardware can't handle really short frames, hardware padding works
* beyond this point
*/
- if (unlikely(skb->len < I40E_MIN_TX_LEN)) {
- if (skb_pad(skb, I40E_MIN_TX_LEN - skb->len))
+ if (unlikely(skb->len < IAVF_MIN_TX_LEN)) {
+ if (skb_pad(skb, IAVF_MIN_TX_LEN - skb->len))
return NETDEV_TX_OK;
- skb->len = I40E_MIN_TX_LEN;
- skb_set_tail_pointer(skb, I40E_MIN_TX_LEN);
+ skb->len = IAVF_MIN_TX_LEN;
+ skb_set_tail_pointer(skb, IAVF_MIN_TX_LEN);
}
- return i40e_xmit_frame_ring(skb, tx_ring);
+ return iavf_xmit_frame_ring(skb, tx_ring);
}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
new file mode 100644
index 0000000..dd3348f
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -0,0 +1,523 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_TXRX_H_
+#define _IAVF_TXRX_H_
+
+/* Interrupt Throttling and Rate Limiting Goodies */
+#define IAVF_DEFAULT_IRQ_WORK 256
+
+/* The datasheet for the X710 and XL710 indicate that the maximum value for
+ * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec
+ * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing
+ * the register value which is divided by 2 lets use the actual values and
+ * avoid an excessive amount of translation.
+ */
+#define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */
+#define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */
+#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */
+#define IAVF_ITR_100K 10 /* all values below must be even */
+#define IAVF_ITR_50K 20
+#define IAVF_ITR_20K 50
+#define IAVF_ITR_18K 60
+#define IAVF_ITR_8K 122
+#define IAVF_MAX_ITR 8160 /* maximum value as per datasheet */
+#define ITR_TO_REG(setting) ((setting) & ~IAVF_ITR_DYNAMIC)
+#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~IAVF_ITR_MASK)
+#define ITR_IS_DYNAMIC(setting) (!!((setting) & IAVF_ITR_DYNAMIC))
+
+#define IAVF_ITR_RX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC)
+#define IAVF_ITR_TX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC)
+
+/* 0x40 is the enable bit for interrupt rate limiting, and must be set if
+ * the value of the rate limit is non-zero
+ */
+#define INTRL_ENA BIT(6)
+#define IAVF_MAX_INTRL 0x3B /* reg uses 4 usec resolution */
+#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2)
+#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0)
+#define IAVF_INTRL_8K 125 /* 8000 ints/sec */
+#define IAVF_INTRL_62K 16 /* 62500 ints/sec */
+#define IAVF_INTRL_83K 12 /* 83333 ints/sec */
+
+#define IAVF_QUEUE_END_OF_LIST 0x7FF
+
+/* this enum matches hardware bits and is meant to be used by DYN_CTLN
+ * registers and QINT registers or more generally anywhere in the manual
+ * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
+ * register but instead is a special value meaning "don't update" ITR0/1/2.
+ */
+enum iavf_dyn_idx_t {
+ IAVF_IDX_ITR0 = 0,
+ IAVF_IDX_ITR1 = 1,
+ IAVF_IDX_ITR2 = 2,
+ IAVF_ITR_NONE = 3 /* ITR_NONE must not be used as an index */
+};
+
+/* these are indexes into ITRN registers */
+#define IAVF_RX_ITR IAVF_IDX_ITR0
+#define IAVF_TX_ITR IAVF_IDX_ITR1
+#define IAVF_PE_ITR IAVF_IDX_ITR2
+
+/* Supported RSS offloads */
+#define IAVF_DEFAULT_RSS_HENA ( \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD))
+
+#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+
+/* Supported Rx Buffer Sizes (a multiple of 128) */
+#define IAVF_RXBUFFER_256 256
+#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */
+#define IAVF_RXBUFFER_2048 2048
+#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */
+#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */
+
+/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
+ * reserve 2 more, and skb_shared_info adds an additional 384 bytes more,
+ * this adds up to 512 bytes of extra data meaning the smallest allocation
+ * we could have is 1K.
+ * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab)
+ * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
+ */
+#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256
+#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
+#define iavf_rx_desc iavf_32byte_rx_desc
+
+#define IAVF_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+/* Attempt to maximize the headroom available for incoming frames. We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame. This leaves us with 512 bytes of room. From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ * up negative. In these cases we should fall back to the legacy
+ * receive path.
+ */
+#if (PAGE_SIZE < 8192)
+#define IAVF_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048))
+
+static inline int iavf_compute_pad(int rx_buf_len)
+{
+ int page_size, pad_size;
+
+ page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+ pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+ return pad_size;
+}
+
+static inline int iavf_skb_pad(void)
+{
+ int rx_buf_len;
+
+ /* If a 2K buffer cannot handle a standard Ethernet frame then
+ * optimize padding for a 3K buffer instead of a 1.5K buffer.
+ *
+ * For a 3K buffer we need to add enough padding to allow for
+ * tailroom due to NET_IP_ALIGN possibly shifting us out of
+ * cache-line alignment.
+ */
+ if (IAVF_2K_TOO_SMALL_WITH_PADDING)
+ rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+ else
+ rx_buf_len = IAVF_RXBUFFER_1536;
+
+ /* if needed make room for NET_IP_ALIGN */
+ rx_buf_len -= NET_IP_ALIGN;
+
+ return iavf_compute_pad(rx_buf_len);
+}
+
+#define IAVF_SKB_PAD iavf_skb_pad()
+#else
+#define IAVF_2K_TOO_SMALL_WITH_PADDING false
+#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#endif
+
+/**
+ * iavf_test_staterr - tests bits in Rx descriptor status and error fields
+ * @rx_desc: pointer to receive descriptor (in le64 format)
+ * @stat_err_bits: value to mask
+ *
+ * This function does some fast chicanery in order to return the
+ * value of the mask which is really only used for boolean tests.
+ * The status_error_len doesn't need to be shifted because it begins
+ * at offset zero.
+ */
+static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
+ const u64 stat_err_bits)
+{
+ return !!(rx_desc->wb.qword1.status_error_len &
+ cpu_to_le64(stat_err_bits));
+}
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IAVF_RX_INCREMENT(r, i) \
+ do { \
+ (i)++; \
+ if ((i) == (r)->count) \
+ i = 0; \
+ r->next_to_clean = i; \
+ } while (0)
+
+#define IAVF_RX_NEXT_DESC(r, i, n) \
+ do { \
+ (i)++; \
+ if ((i) == (r)->count) \
+ i = 0; \
+ (n) = IAVF_RX_DESC((r), (i)); \
+ } while (0)
+
+#define IAVF_RX_NEXT_DESC_PREFETCH(r, i, n) \
+ do { \
+ IAVF_RX_NEXT_DESC((r), (i), (n)); \
+ prefetch((n)); \
+ } while (0)
+
+#define IAVF_MAX_BUFFER_TXD 8
+#define IAVF_MIN_TX_LEN 17
+
+/* The size limit for a transmit buffer in a descriptor is (16K - 1).
+ * In order to align with the read requests we will align the value to
+ * the nearest 4K which represents our maximum read request size.
+ */
+#define IAVF_MAX_READ_REQ_SIZE 4096
+#define IAVF_MAX_DATA_PER_TXD (16 * 1024 - 1)
+#define IAVF_MAX_DATA_PER_TXD_ALIGNED \
+ (IAVF_MAX_DATA_PER_TXD & ~(IAVF_MAX_READ_REQ_SIZE - 1))
+
+/**
+ * iavf_txd_use_count - estimate the number of descriptors needed for Tx
+ * @size: transmit request size in bytes
+ *
+ * Due to hardware alignment restrictions (4K alignment), we need to
+ * assume that we can have no more than 12K of data per descriptor, even
+ * though each descriptor can take up to 16K - 1 bytes of aligned memory.
+ * Thus, we need to divide by 12K. But division is slow! Instead,
+ * we decompose the operation into shifts and one relatively cheap
+ * multiply operation.
+ *
+ * To divide by 12K, we first divide by 4K, then divide by 3:
+ * To divide by 4K, shift right by 12 bits
+ * To divide by 3, multiply by 85, then divide by 256
+ * (Divide by 256 is done by shifting right by 8 bits)
+ * Finally, we add one to round up. Because 256 isn't an exact multiple of
+ * 3, we'll underestimate near each multiple of 12K. This is actually more
+ * accurate as we have 4K - 1 of wiggle room that we can fit into the last
+ * segment. For our purposes this is accurate out to 1M which is orders of
+ * magnitude greater than our largest possible GSO size.
+ *
+ * This would then be implemented as:
+ * return (((size >> 12) * 85) >> 8) + 1;
+ *
+ * Since multiplication and division are commutative, we can reorder
+ * operations into:
+ * return ((size * 85) >> 20) + 1;
+ */
+static inline unsigned int iavf_txd_use_count(unsigned int size)
+{
+ return ((size * 85) >> 20) + 1;
+}
+
+/* Tx Descriptors needed, worst case */
+#define DESC_NEEDED (MAX_SKB_FRAGS + 6)
+#define IAVF_MIN_DESC_PENDING 4
+
+#define IAVF_TX_FLAGS_HW_VLAN BIT(1)
+#define IAVF_TX_FLAGS_SW_VLAN BIT(2)
+#define IAVF_TX_FLAGS_TSO BIT(3)
+#define IAVF_TX_FLAGS_IPV4 BIT(4)
+#define IAVF_TX_FLAGS_IPV6 BIT(5)
+#define IAVF_TX_FLAGS_FCCRC BIT(6)
+#define IAVF_TX_FLAGS_FSO BIT(7)
+#define IAVF_TX_FLAGS_FD_SB BIT(9)
+#define IAVF_TX_FLAGS_VXLAN_TUNNEL BIT(10)
+#define IAVF_TX_FLAGS_VLAN_MASK 0xffff0000
+#define IAVF_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000
+#define IAVF_TX_FLAGS_VLAN_PRIO_SHIFT 29
+#define IAVF_TX_FLAGS_VLAN_SHIFT 16
+
+struct iavf_tx_buffer {
+ struct iavf_tx_desc *next_to_watch;
+ union {
+ struct sk_buff *skb;
+ void *raw_buf;
+ };
+ unsigned int bytecount;
+ unsigned short gso_segs;
+
+ DEFINE_DMA_UNMAP_ADDR(dma);
+ DEFINE_DMA_UNMAP_LEN(len);
+ u32 tx_flags;
+};
+
+struct iavf_rx_buffer {
+ dma_addr_t dma;
+ struct page *page;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+ __u32 page_offset;
+#else
+ __u16 page_offset;
+#endif
+ __u16 pagecnt_bias;
+};
+
+struct iavf_queue_stats {
+ u64 packets;
+ u64 bytes;
+};
+
+struct iavf_tx_queue_stats {
+ u64 restart_queue;
+ u64 tx_busy;
+ u64 tx_done_old;
+ u64 tx_linearize;
+ u64 tx_force_wb;
+ int prev_pkt_ctr;
+ u64 tx_lost_interrupt;
+};
+
+struct iavf_rx_queue_stats {
+ u64 non_eop_descs;
+ u64 alloc_page_failed;
+ u64 alloc_buff_failed;
+ u64 page_reuse_count;
+ u64 realloc_count;
+};
+
+enum iavf_ring_state_t {
+ __IAVF_TX_FDIR_INIT_DONE,
+ __IAVF_TX_XPS_INIT_DONE,
+ __IAVF_RING_STATE_NBITS /* must be last */
+};
+
+/* some useful defines for virtchannel interface, which
+ * is the only remaining user of header split
+ */
+#define IAVF_RX_DTYPE_NO_SPLIT 0
+#define IAVF_RX_DTYPE_HEADER_SPLIT 1
+#define IAVF_RX_DTYPE_SPLIT_ALWAYS 2
+#define IAVF_RX_SPLIT_L2 0x1
+#define IAVF_RX_SPLIT_IP 0x2
+#define IAVF_RX_SPLIT_TCP_UDP 0x4
+#define IAVF_RX_SPLIT_SCTP 0x8
+
+/* struct that defines a descriptor ring, associated with a VSI */
+struct iavf_ring {
+ struct iavf_ring *next; /* pointer to next ring in q_vector */
+ void *desc; /* Descriptor ring memory */
+ struct device *dev; /* Used for DMA mapping */
+ struct net_device *netdev; /* netdev ring maps to */
+ union {
+ struct iavf_tx_buffer *tx_bi;
+ struct iavf_rx_buffer *rx_bi;
+ };
+ DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS);
+ u16 queue_index; /* Queue number of ring */
+ u8 dcb_tc; /* Traffic class of ring */
+ u8 __iomem *tail;
+
+ /* high bit set means dynamic, use accessors routines to read/write.
+ * hardware only supports 2us resolution for the ITR registers.
+ * these values always store the USER setting, and must be converted
+ * before programming to a register.
+ */
+ u16 itr_setting;
+
+ u16 count; /* Number of descriptors */
+ u16 reg_idx; /* HW register index of the ring */
+ u16 rx_buf_len;
+
+ /* used in interrupt processing */
+ u16 next_to_use;
+ u16 next_to_clean;
+
+ u8 atr_sample_rate;
+ u8 atr_count;
+
+ bool ring_active; /* is ring online or not */
+ bool arm_wb; /* do something to arm write back */
+ u8 packet_stride;
+
+ u16 flags;
+#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0)
+#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1)
+
+ /* stats structs */
+ struct iavf_queue_stats stats;
+ struct u64_stats_sync syncp;
+ union {
+ struct iavf_tx_queue_stats tx_stats;
+ struct iavf_rx_queue_stats rx_stats;
+ };
+
+ unsigned int size; /* length of descriptor ring in bytes */
+ dma_addr_t dma; /* physical address of ring */
+
+ struct iavf_vsi *vsi; /* Backreference to associated VSI */
+ struct iavf_q_vector *q_vector; /* Backreference to associated vector */
+
+ struct rcu_head rcu; /* to avoid race on free */
+ u16 next_to_alloc;
+ struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must
+ * return before it sees the EOP for
+ * the current packet, we save that skb
+ * here and resume receiving this
+ * packet the next time
+ * iavf_clean_rx_ring_irq() is called
+ * for this ring.
+ */
+} ____cacheline_internodealigned_in_smp;
+
+static inline bool ring_uses_build_skb(struct iavf_ring *ring)
+{
+ return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED);
+}
+
+static inline void set_ring_build_skb_enabled(struct iavf_ring *ring)
+{
+ ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring)
+{
+ ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002
+#define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002
+#define IAVF_ITR_ADAPTIVE_MAX_USECS 0x007e
+#define IAVF_ITR_ADAPTIVE_LATENCY 0x8000
+#define IAVF_ITR_ADAPTIVE_BULK 0x0000
+#define ITR_IS_BULK(x) (!((x) & IAVF_ITR_ADAPTIVE_LATENCY))
+
+struct iavf_ring_container {
+ struct iavf_ring *ring; /* pointer to linked list of ring(s) */
+ unsigned long next_update; /* jiffies value of next update */
+ unsigned int total_bytes; /* total bytes processed this int */
+ unsigned int total_packets; /* total packets processed this int */
+ u16 count;
+ u16 target_itr; /* target ITR setting for ring(s) */
+ u16 current_itr; /* current ITR setting for ring(s) */
+};
+
+/* iterator for handling rings in ring container */
+#define iavf_for_each_ring(pos, head) \
+ for (pos = (head).ring; pos != NULL; pos = pos->next)
+
+static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring->rx_buf_len > (PAGE_SIZE / 2))
+ return 1;
+#endif
+ return 0;
+}
+
+#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring))
+
+bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count);
+netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+void iavf_clean_tx_ring(struct iavf_ring *tx_ring);
+void iavf_clean_rx_ring(struct iavf_ring *rx_ring);
+int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring);
+int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring);
+void iavf_free_tx_resources(struct iavf_ring *tx_ring);
+void iavf_free_rx_resources(struct iavf_ring *rx_ring);
+int iavf_napi_poll(struct napi_struct *napi, int budget);
+void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector);
+u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw);
+void iavf_detect_recover_hung(struct iavf_vsi *vsi);
+int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size);
+bool __iavf_chk_linearize(struct sk_buff *skb);
+
+/**
+ * iavf_xmit_descriptor_count - calculate number of Tx descriptors needed
+ * @skb: send buffer
+ * @tx_ring: ring to send buffer on
+ *
+ * Returns number of data descriptors needed for this skb. Returns 0 to indicate
+ * there is not enough descriptors available in this ring since we need at least
+ * one descriptor.
+ **/
+static inline int iavf_xmit_descriptor_count(struct sk_buff *skb)
+{
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+ unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+ int count = 0, size = skb_headlen(skb);
+
+ for (;;) {
+ count += iavf_txd_use_count(size);
+
+ if (!nr_frags--)
+ break;
+
+ size = skb_frag_size(frag++);
+ }
+
+ return count;
+}
+
+/**
+ * iavf_maybe_stop_tx - 1st level check for Tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size: the size buffer we want to assure is available
+ *
+ * Returns 0 if stop is not needed
+ **/
+static inline int iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size)
+{
+ if (likely(IAVF_DESC_UNUSED(tx_ring) >= size))
+ return 0;
+ return __iavf_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * iavf_chk_linearize - Check if there are more than 8 fragments per packet
+ * @skb: send buffer
+ * @count: number of buffers used
+ *
+ * Note: Our HW can't scatter-gather more than 8 fragments to build
+ * a packet on the wire and so we need to figure out the cases where we
+ * need to linearize the skb.
+ **/
+static inline bool iavf_chk_linearize(struct sk_buff *skb, int count)
+{
+ /* Both TSO and single send will work if count is less than 8 */
+ if (likely(count < IAVF_MAX_BUFFER_TXD))
+ return false;
+
+ if (skb_is_gso(skb))
+ return __iavf_chk_linearize(skb);
+
+ /* we can support up to 8 data buffers for a single send */
+ return count != IAVF_MAX_BUFFER_TXD;
+}
+/**
+ * @ring: Tx ring to find the netdev equivalent of
+ **/
+static inline struct netdev_queue *txring_txq(const struct iavf_ring *ring)
+{
+ return netdev_get_tx_queue(ring->netdev, ring->queue_index);
+}
+#endif /* _IAVF_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
new file mode 100644
index 0000000..7190a40
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -0,0 +1,688 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_TYPE_H_
+#define _IAVF_TYPE_H_
+
+#include "iavf_status.h"
+#include "iavf_osdep.h"
+#include "iavf_register.h"
+#include "iavf_adminq.h"
+#include "iavf_devids.h"
+
+#define IAVF_RXQ_CTX_DBUFF_SHIFT 7
+
+/* IAVF_MASK is a macro used on 32 bit registers */
+#define IAVF_MASK(mask, shift) ((u32)(mask) << (shift))
+
+#define IAVF_MAX_VSI_QP 16
+#define IAVF_MAX_VF_VSI 3
+#define IAVF_MAX_CHAINED_RX_BUFFERS 5
+
+/* forward declaration */
+struct iavf_hw;
+typedef void (*IAVF_ADMINQ_CALLBACK)(struct iavf_hw *, struct iavf_aq_desc *);
+
+/* Data type manipulation macros. */
+
+#define IAVF_DESC_UNUSED(R) \
+ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+ (R)->next_to_clean - (R)->next_to_use - 1)
+
+/* bitfields for Tx queue mapping in QTX_CTL */
+#define IAVF_QTX_CTL_VF_QUEUE 0x0
+#define IAVF_QTX_CTL_VM_QUEUE 0x1
+#define IAVF_QTX_CTL_PF_QUEUE 0x2
+
+/* debug masks - set these bits in hw->debug_mask to control output */
+enum iavf_debug_mask {
+ IAVF_DEBUG_INIT = 0x00000001,
+ IAVF_DEBUG_RELEASE = 0x00000002,
+
+ IAVF_DEBUG_LINK = 0x00000010,
+ IAVF_DEBUG_PHY = 0x00000020,
+ IAVF_DEBUG_HMC = 0x00000040,
+ IAVF_DEBUG_NVM = 0x00000080,
+ IAVF_DEBUG_LAN = 0x00000100,
+ IAVF_DEBUG_FLOW = 0x00000200,
+ IAVF_DEBUG_DCB = 0x00000400,
+ IAVF_DEBUG_DIAG = 0x00000800,
+ IAVF_DEBUG_FD = 0x00001000,
+ IAVF_DEBUG_PACKAGE = 0x00002000,
+
+ IAVF_DEBUG_AQ_MESSAGE = 0x01000000,
+ IAVF_DEBUG_AQ_DESCRIPTOR = 0x02000000,
+ IAVF_DEBUG_AQ_DESC_BUFFER = 0x04000000,
+ IAVF_DEBUG_AQ_COMMAND = 0x06000000,
+ IAVF_DEBUG_AQ = 0x0F000000,
+
+ IAVF_DEBUG_USER = 0xF0000000,
+
+ IAVF_DEBUG_ALL = 0xFFFFFFFF
+};
+
+/* These are structs for managing the hardware information and the operations.
+ * The structures of function pointers are filled out at init time when we
+ * know for sure exactly which hardware we're working with. This gives us the
+ * flexibility of using the same main driver code but adapting to slightly
+ * different hardware needs as new parts are developed. For this architecture,
+ * the Firmware and AdminQ are intended to insulate the driver from most of the
+ * future changes, but these structures will also do part of the job.
+ */
+enum iavf_mac_type {
+ IAVF_MAC_UNKNOWN = 0,
+ IAVF_MAC_XL710,
+ IAVF_MAC_VF,
+ IAVF_MAC_X722,
+ IAVF_MAC_X722_VF,
+ IAVF_MAC_GENERIC,
+};
+
+enum iavf_vsi_type {
+ IAVF_VSI_MAIN = 0,
+ IAVF_VSI_VMDQ1 = 1,
+ IAVF_VSI_VMDQ2 = 2,
+ IAVF_VSI_CTRL = 3,
+ IAVF_VSI_FCOE = 4,
+ IAVF_VSI_MIRROR = 5,
+ IAVF_VSI_SRIOV = 6,
+ IAVF_VSI_FDIR = 7,
+ IAVF_VSI_TYPE_UNKNOWN
+};
+
+enum iavf_queue_type {
+ IAVF_QUEUE_TYPE_RX = 0,
+ IAVF_QUEUE_TYPE_TX,
+ IAVF_QUEUE_TYPE_PE_CEQ,
+ IAVF_QUEUE_TYPE_UNKNOWN
+};
+
+#define IAVF_HW_CAP_MAX_GPIO 30
+/* Capabilities of a PF or a VF or the whole device */
+struct iavf_hw_capabilities {
+ bool dcb;
+ bool fcoe;
+ u32 num_vsis;
+ u32 num_rx_qp;
+ u32 num_tx_qp;
+ u32 base_queue;
+ u32 num_msix_vectors_vf;
+};
+
+struct iavf_mac_info {
+ enum iavf_mac_type type;
+ u8 addr[ETH_ALEN];
+ u8 perm_addr[ETH_ALEN];
+ u8 san_addr[ETH_ALEN];
+ u16 max_fcoeq;
+};
+
+/* PCI bus types */
+enum iavf_bus_type {
+ iavf_bus_type_unknown = 0,
+ iavf_bus_type_pci,
+ iavf_bus_type_pcix,
+ iavf_bus_type_pci_express,
+ iavf_bus_type_reserved
+};
+
+/* PCI bus speeds */
+enum iavf_bus_speed {
+ iavf_bus_speed_unknown = 0,
+ iavf_bus_speed_33 = 33,
+ iavf_bus_speed_66 = 66,
+ iavf_bus_speed_100 = 100,
+ iavf_bus_speed_120 = 120,
+ iavf_bus_speed_133 = 133,
+ iavf_bus_speed_2500 = 2500,
+ iavf_bus_speed_5000 = 5000,
+ iavf_bus_speed_8000 = 8000,
+ iavf_bus_speed_reserved
+};
+
+/* PCI bus widths */
+enum iavf_bus_width {
+ iavf_bus_width_unknown = 0,
+ iavf_bus_width_pcie_x1 = 1,
+ iavf_bus_width_pcie_x2 = 2,
+ iavf_bus_width_pcie_x4 = 4,
+ iavf_bus_width_pcie_x8 = 8,
+ iavf_bus_width_32 = 32,
+ iavf_bus_width_64 = 64,
+ iavf_bus_width_reserved
+};
+
+/* Bus parameters */
+struct iavf_bus_info {
+ enum iavf_bus_speed speed;
+ enum iavf_bus_width width;
+ enum iavf_bus_type type;
+
+ u16 func;
+ u16 device;
+ u16 lan_id;
+ u16 bus_id;
+};
+
+#define IAVF_MAX_USER_PRIORITY 8
+/* Port hardware description */
+struct iavf_hw {
+ u8 __iomem *hw_addr;
+ void *back;
+
+ /* subsystem structs */
+ struct iavf_mac_info mac;
+ struct iavf_bus_info bus;
+
+ /* pci info */
+ u16 device_id;
+ u16 vendor_id;
+ u16 subsystem_device_id;
+ u16 subsystem_vendor_id;
+ u8 revision_id;
+
+ /* capabilities for entire device and PCI func */
+ struct iavf_hw_capabilities dev_caps;
+
+ /* Admin Queue info */
+ struct iavf_adminq_info aq;
+
+ /* debug mask */
+ u32 debug_mask;
+ char err_str[16];
+};
+
+struct iavf_driver_version {
+ u8 major_version;
+ u8 minor_version;
+ u8 build_version;
+ u8 subbuild_version;
+ u8 driver_string[32];
+};
+
+/* RX Descriptors */
+union iavf_16byte_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ } read;
+ struct {
+ struct {
+ struct {
+ union {
+ __le16 mirroring_status;
+ __le16 fcoe_ctx_id;
+ } mirr_fcoe;
+ __le16 l2tag1;
+ } lo_dword;
+ union {
+ __le32 rss; /* RSS Hash */
+ __le32 fd_id; /* Flow director filter id */
+ __le32 fcoe_param; /* FCoE DDP Context id */
+ } hi_dword;
+ } qword0;
+ struct {
+ /* ext status/error/pktype/length */
+ __le64 status_error_len;
+ } qword1;
+ } wb; /* writeback */
+};
+
+union iavf_32byte_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ /* bit 0 of hdr_buffer_addr is DD bit */
+ __le64 rsvd1;
+ __le64 rsvd2;
+ } read;
+ struct {
+ struct {
+ struct {
+ union {
+ __le16 mirroring_status;
+ __le16 fcoe_ctx_id;
+ } mirr_fcoe;
+ __le16 l2tag1;
+ } lo_dword;
+ union {
+ __le32 rss; /* RSS Hash */
+ __le32 fcoe_param; /* FCoE DDP Context id */
+ /* Flow director filter id in case of
+ * Programming status desc WB
+ */
+ __le32 fd_id;
+ } hi_dword;
+ } qword0;
+ struct {
+ /* status/error/pktype/length */
+ __le64 status_error_len;
+ } qword1;
+ struct {
+ __le16 ext_status; /* extended status */
+ __le16 rsvd;
+ __le16 l2tag2_1;
+ __le16 l2tag2_2;
+ } qword2;
+ struct {
+ union {
+ __le32 flex_bytes_lo;
+ __le32 pe_status;
+ } lo_dword;
+ union {
+ __le32 flex_bytes_hi;
+ __le32 fd_id;
+ } hi_dword;
+ } qword3;
+ } wb; /* writeback */
+};
+
+enum iavf_rx_desc_status_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_DESC_STATUS_DD_SHIFT = 0,
+ IAVF_RX_DESC_STATUS_EOF_SHIFT = 1,
+ IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2,
+ IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3,
+ IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4,
+ IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */
+ IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7,
+ /* Note: Bit 8 is reserved in X710 and XL710 */
+ IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8,
+ IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */
+ IAVF_RX_DESC_STATUS_FLM_SHIFT = 11,
+ IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */
+ IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14,
+ IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15,
+ IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */
+ /* Note: For non-tunnel packets INT_UDP_0 is the right status for
+ * UDP header
+ */
+ IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18,
+ IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
+};
+
+#define IAVF_RXD_QW1_STATUS_SHIFT 0
+#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
+ << IAVF_RXD_QW1_STATUS_SHIFT)
+
+#define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
+#define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \
+ IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT)
+
+#define IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT
+#define IAVF_RXD_QW1_STATUS_TSYNVALID_MASK \
+ BIT_ULL(IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT)
+
+enum iavf_rx_desc_fltstat_values {
+ IAVF_RX_DESC_FLTSTAT_NO_DATA = 0,
+ IAVF_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */
+ IAVF_RX_DESC_FLTSTAT_RSV = 2,
+ IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3,
+};
+
+#define IAVF_RXD_QW1_ERROR_SHIFT 19
+#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
+
+enum iavf_rx_desc_error_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_DESC_ERROR_RXE_SHIFT = 0,
+ IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1,
+ IAVF_RX_DESC_ERROR_HBO_SHIFT = 2,
+ IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */
+ IAVF_RX_DESC_ERROR_IPE_SHIFT = 3,
+ IAVF_RX_DESC_ERROR_L4E_SHIFT = 4,
+ IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5,
+ IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6,
+ IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7
+};
+
+enum iavf_rx_desc_error_l3l4e_fcoe_masks {
+ IAVF_RX_DESC_ERROR_L3L4E_NONE = 0,
+ IAVF_RX_DESC_ERROR_L3L4E_PROT = 1,
+ IAVF_RX_DESC_ERROR_L3L4E_FC = 2,
+ IAVF_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3,
+ IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4
+};
+
+#define IAVF_RXD_QW1_PTYPE_SHIFT 30
+#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
+
+/* Packet type non-ip values */
+enum iavf_rx_l2_ptype {
+ IAVF_RX_PTYPE_L2_RESERVED = 0,
+ IAVF_RX_PTYPE_L2_MAC_PAY2 = 1,
+ IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2,
+ IAVF_RX_PTYPE_L2_FIP_PAY2 = 3,
+ IAVF_RX_PTYPE_L2_OUI_PAY2 = 4,
+ IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5,
+ IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6,
+ IAVF_RX_PTYPE_L2_ECP_PAY2 = 7,
+ IAVF_RX_PTYPE_L2_EVB_PAY2 = 8,
+ IAVF_RX_PTYPE_L2_QCN_PAY2 = 9,
+ IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10,
+ IAVF_RX_PTYPE_L2_ARP = 11,
+ IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12,
+ IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13,
+ IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14,
+ IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15,
+ IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16,
+ IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17,
+ IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18,
+ IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19,
+ IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20,
+ IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21,
+ IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58,
+ IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87,
+ IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124,
+ IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153
+};
+
+struct iavf_rx_ptype_decoded {
+ u32 ptype:8;
+ u32 known:1;
+ u32 outer_ip:1;
+ u32 outer_ip_ver:1;
+ u32 outer_frag:1;
+ u32 tunnel_type:3;
+ u32 tunnel_end_prot:2;
+ u32 tunnel_end_frag:1;
+ u32 inner_prot:4;
+ u32 payload_layer:3;
+};
+
+enum iavf_rx_ptype_outer_ip {
+ IAVF_RX_PTYPE_OUTER_L2 = 0,
+ IAVF_RX_PTYPE_OUTER_IP = 1
+};
+
+enum iavf_rx_ptype_outer_ip_ver {
+ IAVF_RX_PTYPE_OUTER_NONE = 0,
+ IAVF_RX_PTYPE_OUTER_IPV4 = 0,
+ IAVF_RX_PTYPE_OUTER_IPV6 = 1
+};
+
+enum iavf_rx_ptype_outer_fragmented {
+ IAVF_RX_PTYPE_NOT_FRAG = 0,
+ IAVF_RX_PTYPE_FRAG = 1
+};
+
+enum iavf_rx_ptype_tunnel_type {
+ IAVF_RX_PTYPE_TUNNEL_NONE = 0,
+ IAVF_RX_PTYPE_TUNNEL_IP_IP = 1,
+ IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2,
+ IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3,
+ IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4,
+};
+
+enum iavf_rx_ptype_tunnel_end_prot {
+ IAVF_RX_PTYPE_TUNNEL_END_NONE = 0,
+ IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1,
+ IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2,
+};
+
+enum iavf_rx_ptype_inner_prot {
+ IAVF_RX_PTYPE_INNER_PROT_NONE = 0,
+ IAVF_RX_PTYPE_INNER_PROT_UDP = 1,
+ IAVF_RX_PTYPE_INNER_PROT_TCP = 2,
+ IAVF_RX_PTYPE_INNER_PROT_SCTP = 3,
+ IAVF_RX_PTYPE_INNER_PROT_ICMP = 4,
+ IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5
+};
+
+enum iavf_rx_ptype_payload_layer {
+ IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0,
+ IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1,
+ IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2,
+ IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3,
+};
+
+#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38
+#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \
+ IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
+
+#define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52
+#define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \
+ IAVF_RXD_QW1_LENGTH_HBUF_SHIFT)
+
+#define IAVF_RXD_QW1_LENGTH_SPH_SHIFT 63
+#define IAVF_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(IAVF_RXD_QW1_LENGTH_SPH_SHIFT)
+
+enum iavf_rx_desc_ext_status_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0,
+ IAVF_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1,
+ IAVF_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */
+ IAVF_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */
+ IAVF_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9,
+ IAVF_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10,
+ IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11,
+};
+
+enum iavf_rx_desc_pe_status_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */
+ IAVF_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */
+ IAVF_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */
+ IAVF_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24,
+ IAVF_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25,
+ IAVF_RX_DESC_PE_STATUS_PORTV_SHIFT = 26,
+ IAVF_RX_DESC_PE_STATUS_URG_SHIFT = 27,
+ IAVF_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28,
+ IAVF_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29
+};
+
+#define IAVF_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38
+#define IAVF_RX_PROG_STATUS_DESC_LENGTH 0x2000000
+
+#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2
+#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \
+ IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT)
+
+#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19
+#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \
+ IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT)
+
+enum iavf_rx_prog_status_desc_status_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_PROG_STATUS_DESC_DD_SHIFT = 0,
+ IAVF_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */
+};
+
+enum iavf_rx_prog_status_desc_prog_id_masks {
+ IAVF_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1,
+ IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2,
+ IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4,
+};
+
+enum iavf_rx_prog_status_desc_error_bits {
+ /* Note: These are predefined bit offsets */
+ IAVF_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0,
+ IAVF_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1,
+ IAVF_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2,
+ IAVF_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3
+};
+
+/* TX Descriptor */
+struct iavf_tx_desc {
+ __le64 buffer_addr; /* Address of descriptor's data buf */
+ __le64 cmd_type_offset_bsz;
+};
+
+#define IAVF_TXD_QW1_DTYPE_SHIFT 0
+#define IAVF_TXD_QW1_DTYPE_MASK (0xFUL << IAVF_TXD_QW1_DTYPE_SHIFT)
+
+enum iavf_tx_desc_dtype_value {
+ IAVF_TX_DESC_DTYPE_DATA = 0x0,
+ IAVF_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */
+ IAVF_TX_DESC_DTYPE_CONTEXT = 0x1,
+ IAVF_TX_DESC_DTYPE_FCOE_CTX = 0x2,
+ IAVF_TX_DESC_DTYPE_FILTER_PROG = 0x8,
+ IAVF_TX_DESC_DTYPE_DDP_CTX = 0x9,
+ IAVF_TX_DESC_DTYPE_FLEX_DATA = 0xB,
+ IAVF_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC,
+ IAVF_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD,
+ IAVF_TX_DESC_DTYPE_DESC_DONE = 0xF
+};
+
+#define IAVF_TXD_QW1_CMD_SHIFT 4
+#define IAVF_TXD_QW1_CMD_MASK (0x3FFUL << IAVF_TXD_QW1_CMD_SHIFT)
+
+enum iavf_tx_desc_cmd_bits {
+ IAVF_TX_DESC_CMD_EOP = 0x0001,
+ IAVF_TX_DESC_CMD_RS = 0x0002,
+ IAVF_TX_DESC_CMD_ICRC = 0x0004,
+ IAVF_TX_DESC_CMD_IL2TAG1 = 0x0008,
+ IAVF_TX_DESC_CMD_DUMMY = 0x0010,
+ IAVF_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */
+ IAVF_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */
+ IAVF_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */
+ IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */
+ IAVF_TX_DESC_CMD_FCOET = 0x0080,
+ IAVF_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */
+ IAVF_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */
+};
+
+#define IAVF_TXD_QW1_OFFSET_SHIFT 16
+#define IAVF_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \
+ IAVF_TXD_QW1_OFFSET_SHIFT)
+
+enum iavf_tx_desc_length_fields {
+ /* Note: These are predefined bit offsets */
+ IAVF_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */
+ IAVF_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */
+ IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */
+};
+
+#define IAVF_TXD_QW1_TX_BUF_SZ_SHIFT 34
+#define IAVF_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \
+ IAVF_TXD_QW1_TX_BUF_SZ_SHIFT)
+
+#define IAVF_TXD_QW1_L2TAG1_SHIFT 48
+#define IAVF_TXD_QW1_L2TAG1_MASK (0xFFFFULL << IAVF_TXD_QW1_L2TAG1_SHIFT)
+
+/* Context descriptors */
+struct iavf_tx_context_desc {
+ __le32 tunneling_params;
+ __le16 l2tag2;
+ __le16 rsvd;
+ __le64 type_cmd_tso_mss;
+};
+
+#define IAVF_TXD_CTX_QW1_CMD_SHIFT 4
+#define IAVF_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << IAVF_TXD_CTX_QW1_CMD_SHIFT)
+
+enum iavf_tx_ctx_desc_cmd_bits {
+ IAVF_TX_CTX_DESC_TSO = 0x01,
+ IAVF_TX_CTX_DESC_TSYN = 0x02,
+ IAVF_TX_CTX_DESC_IL2TAG2 = 0x04,
+ IAVF_TX_CTX_DESC_IL2TAG2_IL2H = 0x08,
+ IAVF_TX_CTX_DESC_SWTCH_NOTAG = 0x00,
+ IAVF_TX_CTX_DESC_SWTCH_UPLINK = 0x10,
+ IAVF_TX_CTX_DESC_SWTCH_LOCAL = 0x20,
+ IAVF_TX_CTX_DESC_SWTCH_VSI = 0x30,
+ IAVF_TX_CTX_DESC_SWPE = 0x40
+};
+
+/* Packet Classifier Types for filters */
+enum iavf_filter_pctype {
+ /* Note: Values 0-28 are reserved for future use.
+ * Value 29, 30, 32 are not supported on XL710 and X710.
+ */
+ IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29,
+ IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30,
+ IAVF_FILTER_PCTYPE_NONF_IPV4_UDP = 31,
+ IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32,
+ IAVF_FILTER_PCTYPE_NONF_IPV4_TCP = 33,
+ IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP = 34,
+ IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER = 35,
+ IAVF_FILTER_PCTYPE_FRAG_IPV4 = 36,
+ /* Note: Values 37-38 are reserved for future use.
+ * Value 39, 40, 42 are not supported on XL710 and X710.
+ */
+ IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39,
+ IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40,
+ IAVF_FILTER_PCTYPE_NONF_IPV6_UDP = 41,
+ IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42,
+ IAVF_FILTER_PCTYPE_NONF_IPV6_TCP = 43,
+ IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP = 44,
+ IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER = 45,
+ IAVF_FILTER_PCTYPE_FRAG_IPV6 = 46,
+ /* Note: Value 47 is reserved for future use */
+ IAVF_FILTER_PCTYPE_FCOE_OX = 48,
+ IAVF_FILTER_PCTYPE_FCOE_RX = 49,
+ IAVF_FILTER_PCTYPE_FCOE_OTHER = 50,
+ /* Note: Values 51-62 are reserved for future use */
+ IAVF_FILTER_PCTYPE_L2_PAYLOAD = 63,
+};
+
+#define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT 30
+#define IAVF_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \
+ IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT)
+
+#define IAVF_TXD_CTX_QW1_MSS_SHIFT 50
+#define IAVF_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \
+ IAVF_TXD_CTX_QW1_MSS_SHIFT)
+
+#define IAVF_TXD_CTX_QW1_VSI_SHIFT 50
+#define IAVF_TXD_CTX_QW1_VSI_MASK (0x1FFULL << IAVF_TXD_CTX_QW1_VSI_SHIFT)
+
+#define IAVF_TXD_CTX_QW0_EXT_IP_SHIFT 0
+#define IAVF_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \
+ IAVF_TXD_CTX_QW0_EXT_IP_SHIFT)
+
+enum iavf_tx_ctx_desc_eipt_offload {
+ IAVF_TX_CTX_EXT_IP_NONE = 0x0,
+ IAVF_TX_CTX_EXT_IP_IPV6 = 0x1,
+ IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2,
+ IAVF_TX_CTX_EXT_IP_IPV4 = 0x3
+};
+
+#define IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2
+#define IAVF_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \
+ IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT)
+
+#define IAVF_TXD_CTX_QW0_NATT_SHIFT 9
+#define IAVF_TXD_CTX_QW0_NATT_MASK (0x3ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT)
+
+#define IAVF_TXD_CTX_UDP_TUNNELING BIT_ULL(IAVF_TXD_CTX_QW0_NATT_SHIFT)
+#define IAVF_TXD_CTX_GRE_TUNNELING (0x2ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT)
+
+#define IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT 11
+#define IAVF_TXD_CTX_QW0_EIP_NOINC_MASK \
+ BIT_ULL(IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT)
+
+#define IAVF_TXD_CTX_EIP_NOINC_IPID_CONST IAVF_TXD_CTX_QW0_EIP_NOINC_MASK
+
+#define IAVF_TXD_CTX_QW0_NATLEN_SHIFT 12
+#define IAVF_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \
+ IAVF_TXD_CTX_QW0_NATLEN_SHIFT)
+
+#define IAVF_TXD_CTX_QW0_DECTTL_SHIFT 19
+#define IAVF_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \
+ IAVF_TXD_CTX_QW0_DECTTL_SHIFT)
+
+#define IAVF_TXD_CTX_QW0_L4T_CS_SHIFT 23
+#define IAVF_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(IAVF_TXD_CTX_QW0_L4T_CS_SHIFT)
+
+/* Statistics collected by each port, VSI, VEB, and S-channel */
+struct iavf_eth_stats {
+ u64 rx_bytes; /* gorc */
+ u64 rx_unicast; /* uprc */
+ u64 rx_multicast; /* mprc */
+ u64 rx_broadcast; /* bprc */
+ u64 rx_discards; /* rdpc */
+ u64 rx_unknown_protocol; /* rupp */
+ u64 tx_bytes; /* gotc */
+ u64 tx_unicast; /* uptc */
+ u64 tx_multicast; /* mptc */
+ u64 tx_broadcast; /* bptc */
+ u64 tx_discards; /* tdpc */
+ u64 tx_errors; /* tepc */
+};
+#endif /* _IAVF_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
similarity index 68%
rename from drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
rename to drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 565677d..c46770e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1,16 +1,16 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
-#include "i40evf.h"
-#include "i40e_prototype.h"
-#include "i40evf_client.h"
+#include "iavf.h"
+#include "iavf_prototype.h"
+#include "iavf_client.h"
/* busy wait delay in msec */
-#define I40EVF_BUSY_WAIT_DELAY 10
-#define I40EVF_BUSY_WAIT_COUNT 50
+#define IAVF_BUSY_WAIT_DELAY 10
+#define IAVF_BUSY_WAIT_COUNT 50
/**
- * i40evf_send_pf_msg
+ * iavf_send_pf_msg
* @adapter: adapter structure
* @op: virtual channel opcode
* @msg: pointer to message buffer
@@ -18,60 +18,60 @@
*
* Send message to PF and print status if failure.
**/
-static int i40evf_send_pf_msg(struct i40evf_adapter *adapter,
- enum virtchnl_ops op, u8 *msg, u16 len)
+static int iavf_send_pf_msg(struct iavf_adapter *adapter,
+ enum virtchnl_ops op, u8 *msg, u16 len)
{
- struct i40e_hw *hw = &adapter->hw;
- i40e_status err;
+ struct iavf_hw *hw = &adapter->hw;
+ enum iavf_status err;
- if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
+ if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
return 0; /* nothing to see here, move along */
- err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
+ err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
if (err)
dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
- op, i40evf_stat_str(hw, err),
- i40evf_aq_str(hw, hw->aq.asq_last_status));
+ op, iavf_stat_str(hw, err),
+ iavf_aq_str(hw, hw->aq.asq_last_status));
return err;
}
/**
- * i40evf_send_api_ver
+ * iavf_send_api_ver
* @adapter: adapter structure
*
* Send API version admin queue message to the PF. The reply is not checked
* in this function. Returns 0 if the message was successfully
- * sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not.
+ * sent, or one of the IAVF_ADMIN_QUEUE_ERROR_ statuses if not.
**/
-int i40evf_send_api_ver(struct i40evf_adapter *adapter)
+int iavf_send_api_ver(struct iavf_adapter *adapter)
{
struct virtchnl_version_info vvi;
vvi.major = VIRTCHNL_VERSION_MAJOR;
vvi.minor = VIRTCHNL_VERSION_MINOR;
- return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi,
- sizeof(vvi));
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi,
+ sizeof(vvi));
}
/**
- * i40evf_verify_api_ver
+ * iavf_verify_api_ver
* @adapter: adapter structure
*
* Compare API versions with the PF. Must be called after admin queue is
* initialized. Returns 0 if API versions match, -EIO if they do not,
- * I40E_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors
+ * IAVF_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors
* from the firmware are propagated.
**/
-int i40evf_verify_api_ver(struct i40evf_adapter *adapter)
+int iavf_verify_api_ver(struct iavf_adapter *adapter)
{
struct virtchnl_version_info *pf_vvi;
- struct i40e_hw *hw = &adapter->hw;
- struct i40e_arq_event_info event;
+ struct iavf_hw *hw = &adapter->hw;
+ struct iavf_arq_event_info event;
enum virtchnl_ops op;
- i40e_status err;
+ enum iavf_status err;
- event.buf_len = I40EVF_MAX_AQ_BUF_SIZE;
+ event.buf_len = IAVF_MAX_AQ_BUF_SIZE;
event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
if (!event.msg_buf) {
err = -ENOMEM;
@@ -79,8 +79,8 @@
}
while (1) {
- err = i40evf_clean_arq_element(hw, &event, NULL);
- /* When the AQ is empty, i40evf_clean_arq_element will return
+ err = iavf_clean_arq_element(hw, &event, NULL);
+ /* When the AQ is empty, iavf_clean_arq_element will return
* nonzero and this loop will terminate.
*/
if (err)
@@ -92,7 +92,7 @@
}
- err = (i40e_status)le32_to_cpu(event.desc.cookie_low);
+ err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
if (err)
goto out_alloc;
@@ -118,14 +118,14 @@
}
/**
- * i40evf_send_vf_config_msg
+ * iavf_send_vf_config_msg
* @adapter: adapter structure
*
* Send VF configuration request admin queue message to the PF. The reply
* is not checked in this function. Returns 0 if the message was
- * successfully sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not.
+ * successfully sent, or one of the IAVF_ADMIN_QUEUE_ERROR_ statuses if not.
**/
-int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter)
+int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
{
u32 caps;
@@ -142,19 +142,43 @@
VIRTCHNL_VF_OFFLOAD_ADQ;
adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG;
if (PF_IS_V11(adapter))
- return i40evf_send_pf_msg(adapter,
- VIRTCHNL_OP_GET_VF_RESOURCES,
- (u8 *)&caps, sizeof(caps));
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES,
+ (u8 *)&caps, sizeof(caps));
else
- return i40evf_send_pf_msg(adapter,
- VIRTCHNL_OP_GET_VF_RESOURCES,
- NULL, 0);
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES,
+ NULL, 0);
}
/**
- * i40evf_get_vf_config
+ * iavf_validate_num_queues
+ * @adapter: adapter structure
+ *
+ * Validate that the number of queues the PF has sent in
+ * VIRTCHNL_OP_GET_VF_RESOURCES is not larger than the VF can handle.
+ **/
+static void iavf_validate_num_queues(struct iavf_adapter *adapter)
+{
+ if (adapter->vf_res->num_queue_pairs > IAVF_MAX_REQ_QUEUES) {
+ struct virtchnl_vsi_resource *vsi_res;
+ int i;
+
+ dev_info(&adapter->pdev->dev, "Received %d queues, but can only have a max of %d\n",
+ adapter->vf_res->num_queue_pairs,
+ IAVF_MAX_REQ_QUEUES);
+ dev_info(&adapter->pdev->dev, "Fixing by reducing queues to %d\n",
+ IAVF_MAX_REQ_QUEUES);
+ adapter->vf_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES;
+ for (i = 0; i < adapter->vf_res->num_vsis; i++) {
+ vsi_res = &adapter->vf_res->vsi_res[i];
+ vsi_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES;
+ }
+ }
+}
+
+/**
+ * iavf_get_vf_config
* @adapter: private adapter structure
*
* Get VF configuration from PF and populate hw structure. Must be called after
@@ -162,16 +186,16 @@
* with maximum timeout. Response from PF is returned in the buffer for further
* processing by the caller.
**/
-int i40evf_get_vf_config(struct i40evf_adapter *adapter)
+int iavf_get_vf_config(struct iavf_adapter *adapter)
{
- struct i40e_hw *hw = &adapter->hw;
- struct i40e_arq_event_info event;
+ struct iavf_hw *hw = &adapter->hw;
+ struct iavf_arq_event_info event;
enum virtchnl_ops op;
- i40e_status err;
+ enum iavf_status err;
u16 len;
len = sizeof(struct virtchnl_vf_resource) +
- I40E_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource);
+ IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource);
event.buf_len = len;
event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
if (!event.msg_buf) {
@@ -180,10 +204,10 @@
}
while (1) {
- /* When the AQ is empty, i40evf_clean_arq_element will return
+ /* When the AQ is empty, iavf_clean_arq_element will return
* nonzero and this loop will terminate.
*/
- err = i40evf_clean_arq_element(hw, &event, NULL);
+ err = iavf_clean_arq_element(hw, &event, NULL);
if (err)
goto out_alloc;
op =
@@ -192,10 +216,15 @@
break;
}
- err = (i40e_status)le32_to_cpu(event.desc.cookie_low);
+ err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len));
- i40e_vf_parse_hw_config(hw, adapter->vf_res);
+ /* some PFs send more queues than we should have so validate that
+ * we aren't getting too many queues
+ */
+ if (!err)
+ iavf_validate_num_queues(adapter);
+ iavf_vf_parse_hw_config(hw, adapter->vf_res);
out_alloc:
kfree(event.msg_buf);
out:
@@ -203,17 +232,18 @@
}
/**
- * i40evf_configure_queues
+ * iavf_configure_queues
* @adapter: adapter structure
*
* Request that the PF set up our (previously allocated) queues.
**/
-void i40evf_configure_queues(struct i40evf_adapter *adapter)
+void iavf_configure_queues(struct iavf_adapter *adapter)
{
struct virtchnl_vsi_queue_config_info *vqci;
struct virtchnl_queue_pair_info *vqpi;
int pairs = adapter->num_active_queues;
- int i, len, max_frame = I40E_MAX_RXBUFFER;
+ int i, max_frame = IAVF_MAX_RXBUFFER;
+ size_t len;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -222,16 +252,15 @@
return;
}
adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES;
- len = sizeof(struct virtchnl_vsi_queue_config_info) +
- (sizeof(struct virtchnl_queue_pair_info) * pairs);
+ len = struct_size(vqci, qpair, pairs);
vqci = kzalloc(len, GFP_KERNEL);
if (!vqci)
return;
/* Limit maximum frame size when jumbo frames is not enabled */
- if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) &&
+ if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) &&
(adapter->netdev->mtu <= ETH_DATA_LEN))
- max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+ max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN;
vqci->vsi_id = adapter->vsi_res->vsi_id;
vqci->num_queue_pairs = pairs;
@@ -251,23 +280,23 @@
vqpi->rxq.max_pkt_size = max_frame;
vqpi->rxq.databuffer_size =
ALIGN(adapter->rx_rings[i].rx_buf_len,
- BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
+ BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT));
vqpi++;
}
- adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_QUEUES;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
- (u8 *)vqci, len);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
+ (u8 *)vqci, len);
kfree(vqci);
}
/**
- * i40evf_enable_queues
+ * iavf_enable_queues
* @adapter: adapter structure
*
* Request that the PF enable all of our queues.
**/
-void i40evf_enable_queues(struct i40evf_adapter *adapter)
+void iavf_enable_queues(struct iavf_adapter *adapter)
{
struct virtchnl_queue_select vqs;
@@ -281,18 +310,18 @@
vqs.vsi_id = adapter->vsi_res->vsi_id;
vqs.tx_queues = BIT(adapter->num_active_queues) - 1;
vqs.rx_queues = vqs.tx_queues;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_QUEUES;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES,
- (u8 *)&vqs, sizeof(vqs));
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_QUEUES;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES,
+ (u8 *)&vqs, sizeof(vqs));
}
/**
- * i40evf_disable_queues
+ * iavf_disable_queues
* @adapter: adapter structure
*
* Request that the PF disable all of our queues.
**/
-void i40evf_disable_queues(struct i40evf_adapter *adapter)
+void iavf_disable_queues(struct iavf_adapter *adapter)
{
struct virtchnl_queue_select vqs;
@@ -306,24 +335,25 @@
vqs.vsi_id = adapter->vsi_res->vsi_id;
vqs.tx_queues = BIT(adapter->num_active_queues) - 1;
vqs.rx_queues = vqs.tx_queues;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_QUEUES;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES,
- (u8 *)&vqs, sizeof(vqs));
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_QUEUES;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES,
+ (u8 *)&vqs, sizeof(vqs));
}
/**
- * i40evf_map_queues
+ * iavf_map_queues
* @adapter: adapter structure
*
* Request that the PF map queues to interrupt vectors. Misc causes, including
* admin queue, are always mapped to vector 0.
**/
-void i40evf_map_queues(struct i40evf_adapter *adapter)
+void iavf_map_queues(struct iavf_adapter *adapter)
{
struct virtchnl_irq_map_info *vimi;
struct virtchnl_vector_map *vecmap;
- int v_idx, q_vectors, len;
- struct i40e_q_vector *q_vector;
+ struct iavf_q_vector *q_vector;
+ int v_idx, q_vectors;
+ size_t len;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -335,9 +365,7 @@
q_vectors = adapter->num_msix_vectors - NONQ_VECS;
- len = sizeof(struct virtchnl_irq_map_info) +
- (adapter->num_msix_vectors *
- sizeof(struct virtchnl_vector_map));
+ len = struct_size(vimi, vecmap, adapter->num_msix_vectors);
vimi = kzalloc(len, GFP_KERNEL);
if (!vimi)
return;
@@ -352,8 +380,8 @@
vecmap->vector_id = v_idx + NONQ_VECS;
vecmap->txq_map = q_vector->ring_mask;
vecmap->rxq_map = q_vector->ring_mask;
- vecmap->rxitr_idx = I40E_RX_ITR;
- vecmap->txitr_idx = I40E_TX_ITR;
+ vecmap->rxitr_idx = IAVF_RX_ITR;
+ vecmap->txitr_idx = IAVF_TX_ITR;
}
/* Misc vector last - this is only for AdminQ messages */
vecmap = &vimi->vecmap[v_idx];
@@ -362,21 +390,21 @@
vecmap->txq_map = 0;
vecmap->rxq_map = 0;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP,
- (u8 *)vimi, len);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_MAP_VECTORS;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP,
+ (u8 *)vimi, len);
kfree(vimi);
}
/**
- * i40evf_request_queues
+ * iavf_request_queues
* @adapter: adapter structure
* @num: number of requested queues
*
* We get a default number of queues from the PF. This enables us to request a
* different number. Returns 0 on success, negative on failure
**/
-int i40evf_request_queues(struct i40evf_adapter *adapter, int num)
+int iavf_request_queues(struct iavf_adapter *adapter, int num)
{
struct virtchnl_vf_res_request vfres;
@@ -387,26 +415,27 @@
return -EBUSY;
}
- vfres.num_queue_pairs = num;
+ vfres.num_queue_pairs = min_t(int, num, num_online_cpus());
adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES;
- adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
- return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES,
- (u8 *)&vfres, sizeof(vfres));
+ adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES,
+ (u8 *)&vfres, sizeof(vfres));
}
/**
- * i40evf_add_ether_addrs
+ * iavf_add_ether_addrs
* @adapter: adapter structure
*
* Request that the PF add one or more addresses to our filters.
**/
-void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
+void iavf_add_ether_addrs(struct iavf_adapter *adapter)
{
struct virtchnl_ether_addr_list *veal;
- int len, i = 0, count = 0;
- struct i40evf_mac_filter *f;
+ struct iavf_mac_filter *f;
+ int i = 0, count = 0;
bool more = false;
+ size_t len;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -422,21 +451,19 @@
count++;
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
return;
}
adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR;
- len = sizeof(struct virtchnl_ether_addr_list) +
- (count * sizeof(struct virtchnl_ether_addr));
- if (len > I40EVF_MAX_AQ_BUF_SIZE) {
+ len = struct_size(veal, list, count);
+ if (len > IAVF_MAX_AQ_BUF_SIZE) {
dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n");
- count = (I40EVF_MAX_AQ_BUF_SIZE -
+ count = (IAVF_MAX_AQ_BUF_SIZE -
sizeof(struct virtchnl_ether_addr_list)) /
sizeof(struct virtchnl_ether_addr);
- len = sizeof(struct virtchnl_ether_addr_list) +
- (count * sizeof(struct virtchnl_ether_addr));
+ len = struct_size(veal, list, count);
more = true;
}
@@ -458,27 +485,27 @@
}
}
if (!more)
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR,
- (u8 *)veal, len);
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, (u8 *)veal, len);
kfree(veal);
}
/**
- * i40evf_del_ether_addrs
+ * iavf_del_ether_addrs
* @adapter: adapter structure
*
* Request that the PF remove one or more addresses from our filters.
**/
-void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
+void iavf_del_ether_addrs(struct iavf_adapter *adapter)
{
struct virtchnl_ether_addr_list *veal;
- struct i40evf_mac_filter *f, *ftmp;
- int len, i = 0, count = 0;
+ struct iavf_mac_filter *f, *ftmp;
+ int i = 0, count = 0;
bool more = false;
+ size_t len;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -494,21 +521,19 @@
count++;
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
return;
}
adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR;
- len = sizeof(struct virtchnl_ether_addr_list) +
- (count * sizeof(struct virtchnl_ether_addr));
- if (len > I40EVF_MAX_AQ_BUF_SIZE) {
+ len = struct_size(veal, list, count);
+ if (len > IAVF_MAX_AQ_BUF_SIZE) {
dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n");
- count = (I40EVF_MAX_AQ_BUF_SIZE -
+ count = (IAVF_MAX_AQ_BUF_SIZE -
sizeof(struct virtchnl_ether_addr_list)) /
sizeof(struct virtchnl_ether_addr);
- len = sizeof(struct virtchnl_ether_addr_list) +
- (count * sizeof(struct virtchnl_ether_addr));
+ len = struct_size(veal, list, count);
more = true;
}
veal = kzalloc(len, GFP_ATOMIC);
@@ -530,26 +555,25 @@
}
}
if (!more)
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR,
- (u8 *)veal, len);
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, (u8 *)veal, len);
kfree(veal);
}
/**
- * i40evf_add_vlans
+ * iavf_add_vlans
* @adapter: adapter structure
*
* Request that the PF add one or more VLAN filters to our VSI.
**/
-void i40evf_add_vlans(struct i40evf_adapter *adapter)
+void iavf_add_vlans(struct iavf_adapter *adapter)
{
struct virtchnl_vlan_filter_list *vvfl;
int len, i = 0, count = 0;
- struct i40evf_vlan_filter *f;
+ struct iavf_vlan_filter *f;
bool more = false;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
@@ -566,7 +590,7 @@
count++;
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
return;
}
@@ -574,9 +598,9 @@
len = sizeof(struct virtchnl_vlan_filter_list) +
(count * sizeof(u16));
- if (len > I40EVF_MAX_AQ_BUF_SIZE) {
+ if (len > IAVF_MAX_AQ_BUF_SIZE) {
dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n");
- count = (I40EVF_MAX_AQ_BUF_SIZE -
+ count = (IAVF_MAX_AQ_BUF_SIZE -
sizeof(struct virtchnl_vlan_filter_list)) /
sizeof(u16);
len = sizeof(struct virtchnl_vlan_filter_list) +
@@ -601,24 +625,24 @@
}
}
if (!more)
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len);
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len);
kfree(vvfl);
}
/**
- * i40evf_del_vlans
+ * iavf_del_vlans
* @adapter: adapter structure
*
* Request that the PF remove one or more VLAN filters from our VSI.
**/
-void i40evf_del_vlans(struct i40evf_adapter *adapter)
+void iavf_del_vlans(struct iavf_adapter *adapter)
{
struct virtchnl_vlan_filter_list *vvfl;
- struct i40evf_vlan_filter *f, *ftmp;
+ struct iavf_vlan_filter *f, *ftmp;
int len, i = 0, count = 0;
bool more = false;
@@ -636,7 +660,7 @@
count++;
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
return;
}
@@ -644,9 +668,9 @@
len = sizeof(struct virtchnl_vlan_filter_list) +
(count * sizeof(u16));
- if (len > I40EVF_MAX_AQ_BUF_SIZE) {
+ if (len > IAVF_MAX_AQ_BUF_SIZE) {
dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n");
- count = (I40EVF_MAX_AQ_BUF_SIZE -
+ count = (IAVF_MAX_AQ_BUF_SIZE -
sizeof(struct virtchnl_vlan_filter_list)) /
sizeof(u16);
len = sizeof(struct virtchnl_vlan_filter_list) +
@@ -672,22 +696,22 @@
}
}
if (!more)
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER;
spin_unlock_bh(&adapter->mac_vlan_list_lock);
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len);
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len);
kfree(vvfl);
}
/**
- * i40evf_set_promiscuous
+ * iavf_set_promiscuous
* @adapter: adapter structure
* @flags: bitmask to control unicast/multicast promiscuous.
*
* Request that the PF enable promiscuous mode for our VSI.
**/
-void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags)
+void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags)
{
struct virtchnl_promisc_info vpi;
int promisc_all;
@@ -702,39 +726,39 @@
promisc_all = FLAG_VF_UNICAST_PROMISC |
FLAG_VF_MULTICAST_PROMISC;
if ((flags & promisc_all) == promisc_all) {
- adapter->flags |= I40EVF_FLAG_PROMISC_ON;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_PROMISC;
+ adapter->flags |= IAVF_FLAG_PROMISC_ON;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC;
dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n");
}
if (flags & FLAG_VF_MULTICAST_PROMISC) {
- adapter->flags |= I40EVF_FLAG_ALLMULTI_ON;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_ALLMULTI;
+ adapter->flags |= IAVF_FLAG_ALLMULTI_ON;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI;
dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n");
}
if (!flags) {
- adapter->flags &= ~(I40EVF_FLAG_PROMISC_ON |
- I40EVF_FLAG_ALLMULTI_ON);
- adapter->aq_required &= ~(I40EVF_FLAG_AQ_RELEASE_PROMISC |
- I40EVF_FLAG_AQ_RELEASE_ALLMULTI);
+ adapter->flags &= ~(IAVF_FLAG_PROMISC_ON |
+ IAVF_FLAG_ALLMULTI_ON);
+ adapter->aq_required &= ~(IAVF_FLAG_AQ_RELEASE_PROMISC |
+ IAVF_FLAG_AQ_RELEASE_ALLMULTI);
dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n");
}
adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE;
vpi.vsi_id = adapter->vsi_res->vsi_id;
vpi.flags = flags;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
- (u8 *)&vpi, sizeof(vpi));
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
+ (u8 *)&vpi, sizeof(vpi));
}
/**
- * i40evf_request_stats
+ * iavf_request_stats
* @adapter: adapter structure
*
* Request VSI statistics from PF.
**/
-void i40evf_request_stats(struct i40evf_adapter *adapter)
+void iavf_request_stats(struct iavf_adapter *adapter)
{
struct virtchnl_queue_select vqs;
@@ -745,19 +769,19 @@
adapter->current_op = VIRTCHNL_OP_GET_STATS;
vqs.vsi_id = adapter->vsi_res->vsi_id;
/* queue maps are ignored for this message - only the vsi is used */
- if (i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS,
- (u8 *)&vqs, sizeof(vqs)))
+ if (iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, (u8 *)&vqs,
+ sizeof(vqs)))
/* if the request failed, don't lock out others */
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
}
/**
- * i40evf_get_hena
+ * iavf_get_hena
* @adapter: adapter structure
*
* Request hash enable capabilities from PF
**/
-void i40evf_get_hena(struct i40evf_adapter *adapter)
+void iavf_get_hena(struct iavf_adapter *adapter)
{
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -766,18 +790,17 @@
return;
}
adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_HENA;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS,
- NULL, 0);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0);
}
/**
- * i40evf_set_hena
+ * iavf_set_hena
* @adapter: adapter structure
*
* Request the PF to set our RSS hash capabilities
**/
-void i40evf_set_hena(struct i40evf_adapter *adapter)
+void iavf_set_hena(struct iavf_adapter *adapter)
{
struct virtchnl_rss_hena vrh;
@@ -789,18 +812,18 @@
}
vrh.hena = adapter->hena;
adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_HENA;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA,
- (u8 *)&vrh, sizeof(vrh));
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh,
+ sizeof(vrh));
}
/**
- * i40evf_set_rss_key
+ * iavf_set_rss_key
* @adapter: adapter structure
*
* Request the PF to set our RSS hash key
**/
-void i40evf_set_rss_key(struct i40evf_adapter *adapter)
+void iavf_set_rss_key(struct iavf_adapter *adapter)
{
struct virtchnl_rss_key *vrk;
int len;
@@ -821,19 +844,18 @@
memcpy(vrk->key, adapter->rss_key, adapter->rss_key_size);
adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_KEY;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_KEY;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY,
- (u8 *)vrk, len);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_KEY;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, (u8 *)vrk, len);
kfree(vrk);
}
/**
- * i40evf_set_rss_lut
+ * iavf_set_rss_lut
* @adapter: adapter structure
*
* Request the PF to set our RSS lookup table
**/
-void i40evf_set_rss_lut(struct i40evf_adapter *adapter)
+void iavf_set_rss_lut(struct iavf_adapter *adapter)
{
struct virtchnl_rss_lut *vrl;
int len;
@@ -853,19 +875,18 @@
vrl->lut_entries = adapter->rss_lut_size;
memcpy(vrl->lut, adapter->rss_lut, adapter->rss_lut_size);
adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_LUT;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_LUT;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT,
- (u8 *)vrl, len);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_LUT;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, (u8 *)vrl, len);
kfree(vrl);
}
/**
- * i40evf_enable_vlan_stripping
+ * iavf_enable_vlan_stripping
* @adapter: adapter structure
*
* Request VLAN header stripping to be enabled
**/
-void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter)
+void iavf_enable_vlan_stripping(struct iavf_adapter *adapter)
{
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -874,18 +895,17 @@
return;
}
adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING,
- NULL, 0);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, NULL, 0);
}
/**
- * i40evf_disable_vlan_stripping
+ * iavf_disable_vlan_stripping
* @adapter: adapter structure
*
* Request VLAN header stripping to be disabled
**/
-void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter)
+void iavf_disable_vlan_stripping(struct iavf_adapter *adapter)
{
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -894,18 +914,17 @@
return;
}
adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING,
- NULL, 0);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, NULL, 0);
}
/**
- * i40evf_print_link_message - print link up or down
+ * iavf_print_link_message - print link up or down
* @adapter: adapter structure
*
* Log a message telling the world of our wonderous link status
*/
-static void i40evf_print_link_message(struct i40evf_adapter *adapter)
+static void iavf_print_link_message(struct iavf_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
char *speed = "Unknown ";
@@ -916,22 +935,22 @@
}
switch (adapter->link_speed) {
- case I40E_LINK_SPEED_40GB:
+ case IAVF_LINK_SPEED_40GB:
speed = "40 G";
break;
- case I40E_LINK_SPEED_25GB:
+ case IAVF_LINK_SPEED_25GB:
speed = "25 G";
break;
- case I40E_LINK_SPEED_20GB:
+ case IAVF_LINK_SPEED_20GB:
speed = "20 G";
break;
- case I40E_LINK_SPEED_10GB:
+ case IAVF_LINK_SPEED_10GB:
speed = "10 G";
break;
- case I40E_LINK_SPEED_1GB:
+ case IAVF_LINK_SPEED_1GB:
speed = "1000 M";
break;
- case I40E_LINK_SPEED_100MB:
+ case IAVF_LINK_SPEED_100MB:
speed = "100 M";
break;
default:
@@ -942,16 +961,16 @@
}
/**
- * i40evf_enable_channel
+ * iavf_enable_channel
* @adapter: adapter structure
*
* Request that the PF enable channels as specified by
* the user via tc tool.
**/
-void i40evf_enable_channels(struct i40evf_adapter *adapter)
+void iavf_enable_channels(struct iavf_adapter *adapter)
{
struct virtchnl_tc_info *vti = NULL;
- u16 len;
+ size_t len;
int i;
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
@@ -961,9 +980,7 @@
return;
}
- len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) +
- sizeof(struct virtchnl_tc_info);
-
+ len = struct_size(vti, list, adapter->num_tc - 1);
vti = kzalloc(len, GFP_KERNEL);
if (!vti)
return;
@@ -976,22 +993,21 @@
adapter->ch_config.ch_info[i].max_tx_rate;
}
- adapter->ch_config.state = __I40EVF_TC_RUNNING;
- adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->ch_config.state = __IAVF_TC_RUNNING;
+ adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS,
- (u8 *)vti, len);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_CHANNELS;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, (u8 *)vti, len);
kfree(vti);
}
/**
- * i40evf_disable_channel
+ * iavf_disable_channel
* @adapter: adapter structure
*
* Request that the PF disable channels that are configured
**/
-void i40evf_disable_channels(struct i40evf_adapter *adapter)
+void iavf_disable_channels(struct iavf_adapter *adapter)
{
if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -1000,23 +1016,22 @@
return;
}
- adapter->ch_config.state = __I40EVF_TC_INVALID;
- adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->ch_config.state = __IAVF_TC_INVALID;
+ adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS;
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS;
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS,
- NULL, 0);
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_CHANNELS;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, NULL, 0);
}
/**
- * i40evf_print_cloud_filter
+ * iavf_print_cloud_filter
* @adapter: adapter structure
* @f: cloud filter to print
*
* Print the cloud filter
**/
-static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter,
- struct virtchnl_filter *f)
+static void iavf_print_cloud_filter(struct iavf_adapter *adapter,
+ struct virtchnl_filter *f)
{
switch (f->flow_type) {
case VIRTCHNL_TCP_V4_FLOW:
@@ -1043,15 +1058,15 @@
}
/**
- * i40evf_add_cloud_filter
+ * iavf_add_cloud_filter
* @adapter: adapter structure
*
* Request that the PF add cloud filters as specified
* by the user via tc tool.
**/
-void i40evf_add_cloud_filter(struct i40evf_adapter *adapter)
+void iavf_add_cloud_filter(struct iavf_adapter *adapter)
{
- struct i40evf_cloud_filter *cf;
+ struct iavf_cloud_filter *cf;
struct virtchnl_filter *f;
int len = 0, count = 0;
@@ -1068,7 +1083,7 @@
}
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_CLOUD_FILTER;
return;
}
adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER;
@@ -1082,25 +1097,24 @@
if (cf->add) {
memcpy(f, &cf->f, sizeof(struct virtchnl_filter));
cf->add = false;
- cf->state = __I40EVF_CF_ADD_PENDING;
- i40evf_send_pf_msg(adapter,
- VIRTCHNL_OP_ADD_CLOUD_FILTER,
- (u8 *)f, len);
+ cf->state = __IAVF_CF_ADD_PENDING;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_CLOUD_FILTER,
+ (u8 *)f, len);
}
}
kfree(f);
}
/**
- * i40evf_del_cloud_filter
+ * iavf_del_cloud_filter
* @adapter: adapter structure
*
* Request that the PF delete cloud filters as specified
* by the user via tc tool.
**/
-void i40evf_del_cloud_filter(struct i40evf_adapter *adapter)
+void iavf_del_cloud_filter(struct iavf_adapter *adapter)
{
- struct i40evf_cloud_filter *cf, *cftmp;
+ struct iavf_cloud_filter *cf, *cftmp;
struct virtchnl_filter *f;
int len = 0, count = 0;
@@ -1117,7 +1131,7 @@
}
}
if (!count) {
- adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER;
+ adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_CLOUD_FILTER;
return;
}
adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER;
@@ -1131,30 +1145,29 @@
if (cf->del) {
memcpy(f, &cf->f, sizeof(struct virtchnl_filter));
cf->del = false;
- cf->state = __I40EVF_CF_DEL_PENDING;
- i40evf_send_pf_msg(adapter,
- VIRTCHNL_OP_DEL_CLOUD_FILTER,
- (u8 *)f, len);
+ cf->state = __IAVF_CF_DEL_PENDING;
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_CLOUD_FILTER,
+ (u8 *)f, len);
}
}
kfree(f);
}
/**
- * i40evf_request_reset
+ * iavf_request_reset
* @adapter: adapter structure
*
* Request that the PF reset this VF. No response is expected.
**/
-void i40evf_request_reset(struct i40evf_adapter *adapter)
+void iavf_request_reset(struct iavf_adapter *adapter)
{
/* Don't check CURRENT_OP - this is always higher priority */
- i40evf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0);
+ iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0);
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
}
/**
- * i40evf_virtchnl_completion
+ * iavf_virtchnl_completion
* @adapter: adapter structure
* @v_opcode: opcode sent by PF
* @v_retval: retval sent by PF
@@ -1165,10 +1178,9 @@
* wait, we fire off our requests and assume that no errors will be returned.
* This function handles the reply messages.
**/
-void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
- enum virtchnl_ops v_opcode,
- i40e_status v_retval,
- u8 *msg, u16 msglen)
+void iavf_virtchnl_completion(struct iavf_adapter *adapter,
+ enum virtchnl_ops v_opcode,
+ enum iavf_status v_retval, u8 *msg, u16 msglen)
{
struct net_device *netdev = adapter->netdev;
@@ -1176,6 +1188,7 @@
struct virtchnl_pf_event *vpe =
(struct virtchnl_pf_event *)msg;
bool link_up = vpe->event_data.link_event.link_status;
+
switch (vpe->event) {
case VIRTCHNL_EVENT_LINK_CHANGE:
adapter->link_speed =
@@ -1193,7 +1206,7 @@
* after we enable queues and actually prepared
* to send traffic.
*/
- if (adapter->state != __I40EVF_RUNNING)
+ if (adapter->state != __IAVF_RUNNING)
break;
/* For ADq enabled VF, we reconfigure VSIs and
@@ -1201,7 +1214,7 @@
* queues are enabled.
*/
if (adapter->flags &
- I40EVF_FLAG_QUEUES_DISABLED)
+ IAVF_FLAG_QUEUES_DISABLED)
break;
}
@@ -1213,14 +1226,14 @@
netif_tx_stop_all_queues(netdev);
netif_carrier_off(netdev);
}
- i40evf_print_link_message(adapter);
+ iavf_print_link_message(adapter);
break;
case VIRTCHNL_EVENT_RESET_IMPENDING:
dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n");
- if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) {
- adapter->flags |= I40EVF_FLAG_RESET_PENDING;
+ if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) {
+ adapter->flags |= IAVF_FLAG_RESET_PENDING;
dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
- schedule_work(&adapter->reset_task);
+ queue_work(iavf_wq, &adapter->reset_task);
}
break;
default:
@@ -1234,48 +1247,50 @@
switch (v_opcode) {
case VIRTCHNL_OP_ADD_VLAN:
dev_err(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
+ iavf_stat_str(&adapter->hw, v_retval));
break;
case VIRTCHNL_OP_ADD_ETH_ADDR:
dev_err(&adapter->pdev->dev, "Failed to add MAC filter, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
+ iavf_stat_str(&adapter->hw, v_retval));
+ /* restore administratively set MAC address */
+ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
break;
case VIRTCHNL_OP_DEL_VLAN:
dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
+ iavf_stat_str(&adapter->hw, v_retval));
break;
case VIRTCHNL_OP_DEL_ETH_ADDR:
dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
+ iavf_stat_str(&adapter->hw, v_retval));
break;
case VIRTCHNL_OP_ENABLE_CHANNELS:
dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
- adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
- adapter->ch_config.state = __I40EVF_TC_INVALID;
+ iavf_stat_str(&adapter->hw, v_retval));
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->ch_config.state = __IAVF_TC_INVALID;
netdev_reset_tc(netdev);
netif_tx_start_all_queues(netdev);
break;
case VIRTCHNL_OP_DISABLE_CHANNELS:
dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n",
- i40evf_stat_str(&adapter->hw, v_retval));
- adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
- adapter->ch_config.state = __I40EVF_TC_RUNNING;
+ iavf_stat_str(&adapter->hw, v_retval));
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->ch_config.state = __IAVF_TC_RUNNING;
netif_tx_start_all_queues(netdev);
break;
case VIRTCHNL_OP_ADD_CLOUD_FILTER: {
- struct i40evf_cloud_filter *cf, *cftmp;
+ struct iavf_cloud_filter *cf, *cftmp;
list_for_each_entry_safe(cf, cftmp,
&adapter->cloud_filter_list,
list) {
- if (cf->state == __I40EVF_CF_ADD_PENDING) {
- cf->state = __I40EVF_CF_INVALID;
+ if (cf->state == __IAVF_CF_ADD_PENDING) {
+ cf->state = __IAVF_CF_INVALID;
dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n",
- i40evf_stat_str(&adapter->hw,
- v_retval));
- i40evf_print_cloud_filter(adapter,
- &cf->f);
+ iavf_stat_str(&adapter->hw,
+ v_retval));
+ iavf_print_cloud_filter(adapter,
+ &cf->f);
list_del(&cf->list);
kfree(cf);
adapter->num_cloud_filters--;
@@ -1284,32 +1299,36 @@
}
break;
case VIRTCHNL_OP_DEL_CLOUD_FILTER: {
- struct i40evf_cloud_filter *cf;
+ struct iavf_cloud_filter *cf;
list_for_each_entry(cf, &adapter->cloud_filter_list,
list) {
- if (cf->state == __I40EVF_CF_DEL_PENDING) {
- cf->state = __I40EVF_CF_ACTIVE;
+ if (cf->state == __IAVF_CF_DEL_PENDING) {
+ cf->state = __IAVF_CF_ACTIVE;
dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n",
- i40evf_stat_str(&adapter->hw,
- v_retval));
- i40evf_print_cloud_filter(adapter,
- &cf->f);
+ iavf_stat_str(&adapter->hw,
+ v_retval));
+ iavf_print_cloud_filter(adapter,
+ &cf->f);
}
}
}
break;
default:
dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n",
- v_retval,
- i40evf_stat_str(&adapter->hw, v_retval),
+ v_retval, iavf_stat_str(&adapter->hw, v_retval),
v_opcode);
}
}
switch (v_opcode) {
+ case VIRTCHNL_OP_ADD_ETH_ADDR: {
+ if (!ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr))
+ ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
+ }
+ break;
case VIRTCHNL_OP_GET_STATS: {
- struct i40e_eth_stats *stats =
- (struct i40e_eth_stats *)msg;
+ struct iavf_eth_stats *stats =
+ (struct iavf_eth_stats *)msg;
netdev->stats.rx_packets = stats->rx_unicast +
stats->rx_multicast +
stats->rx_broadcast;
@@ -1326,25 +1345,33 @@
break;
case VIRTCHNL_OP_GET_VF_RESOURCES: {
u16 len = sizeof(struct virtchnl_vf_resource) +
- I40E_MAX_VF_VSI *
+ IAVF_MAX_VF_VSI *
sizeof(struct virtchnl_vsi_resource);
memcpy(adapter->vf_res, msg, min(msglen, len));
- i40e_vf_parse_hw_config(&adapter->hw, adapter->vf_res);
- /* restore current mac address */
- ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
- i40evf_process_config(adapter);
+ iavf_validate_num_queues(adapter);
+ iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res);
+ if (is_zero_ether_addr(adapter->hw.mac.addr)) {
+ /* restore current mac address */
+ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
+ } else {
+ /* refresh current mac address if changed */
+ ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
+ ether_addr_copy(netdev->perm_addr,
+ adapter->hw.mac.addr);
+ }
+ iavf_process_config(adapter);
}
break;
case VIRTCHNL_OP_ENABLE_QUEUES:
/* enable transmits */
- i40evf_irq_enable(adapter, true);
- adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED;
+ iavf_irq_enable(adapter, true);
+ adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED;
break;
case VIRTCHNL_OP_DISABLE_QUEUES:
- i40evf_free_all_tx_resources(adapter);
- i40evf_free_all_rx_resources(adapter);
- if (adapter->state == __I40EVF_DOWN_PENDING) {
- adapter->state = __I40EVF_DOWN;
+ iavf_free_all_tx_resources(adapter);
+ iavf_free_all_rx_resources(adapter);
+ if (adapter->state == __IAVF_DOWN_PENDING) {
+ adapter->state = __IAVF_DOWN;
wake_up(&adapter->down_waitqueue);
}
break;
@@ -1363,8 +1390,7 @@
* care about that.
*/
if (msglen && CLIENT_ENABLED(adapter))
- i40evf_notify_client_message(&adapter->vsi,
- msg, msglen);
+ iavf_notify_client_message(&adapter->vsi, msg, msglen);
break;
case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
@@ -1373,6 +1399,7 @@
break;
case VIRTCHNL_OP_GET_RSS_HENA_CAPS: {
struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg;
+
if (msglen == sizeof(*vrh))
adapter->hena = vrh->hena;
else
@@ -1383,32 +1410,33 @@
case VIRTCHNL_OP_REQUEST_QUEUES: {
struct virtchnl_vf_res_request *vfres =
(struct virtchnl_vf_res_request *)msg;
+
if (vfres->num_queue_pairs != adapter->num_req_queues) {
dev_info(&adapter->pdev->dev,
"Requested %d queues, PF can support %d\n",
adapter->num_req_queues,
vfres->num_queue_pairs);
adapter->num_req_queues = 0;
- adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
}
}
break;
case VIRTCHNL_OP_ADD_CLOUD_FILTER: {
- struct i40evf_cloud_filter *cf;
+ struct iavf_cloud_filter *cf;
list_for_each_entry(cf, &adapter->cloud_filter_list, list) {
- if (cf->state == __I40EVF_CF_ADD_PENDING)
- cf->state = __I40EVF_CF_ACTIVE;
+ if (cf->state == __IAVF_CF_ADD_PENDING)
+ cf->state = __IAVF_CF_ACTIVE;
}
}
break;
case VIRTCHNL_OP_DEL_CLOUD_FILTER: {
- struct i40evf_cloud_filter *cf, *cftmp;
+ struct iavf_cloud_filter *cf, *cftmp;
list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list,
list) {
- if (cf->state == __I40EVF_CF_DEL_PENDING) {
- cf->state = __I40EVF_CF_INVALID;
+ if (cf->state == __IAVF_CF_DEL_PENDING) {
+ cf->state = __IAVF_CF_INVALID;
list_del(&cf->list);
kfree(cf);
adapter->num_cloud_filters--;
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 4058673..9edde96 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -13,5 +13,9 @@
ice_nvm.o \
ice_switch.o \
ice_sched.o \
+ ice_lib.o \
ice_txrx.o \
+ ice_flex_pipe.o \
ice_ethtool.o
+ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o
+ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_lib.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 6759172..45e1006 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -8,6 +8,7 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/firmware.h>
#include <linux/netdevice.h>
#include <linux/compiler.h>
#include <linux/etherdevice.h>
@@ -26,31 +27,38 @@
#include <linux/bitmap.h>
#include <linux/log2.h>
#include <linux/ip.h>
+#include <linux/sctp.h>
#include <linux/ipv6.h>
#include <linux/if_bridge.h>
+#include <linux/ctype.h>
+#include <linux/avf/virtchnl.h>
#include <net/ipv6.h>
#include "ice_devids.h"
#include "ice_type.h"
#include "ice_txrx.h"
+#include "ice_dcb.h"
#include "ice_switch.h"
#include "ice_common.h"
#include "ice_sched.h"
+#include "ice_virtchnl_pf.h"
+#include "ice_sriov.h"
extern const char ice_drv_ver[];
#define ICE_BAR0 0
-#define ICE_DFLT_NUM_DESC 128
#define ICE_REQ_DESC_MULTIPLE 32
-#define ICE_MIN_NUM_DESC ICE_REQ_DESC_MULTIPLE
+#define ICE_MIN_NUM_DESC 64
#define ICE_MAX_NUM_DESC 8160
+#define ICE_DFLT_MIN_RX_DESC 512
+#define ICE_DFLT_NUM_TX_DESC 256
+#define ICE_DFLT_NUM_RX_DESC 2048
+
#define ICE_DFLT_TRAFFIC_CLASS BIT(0)
#define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16)
-#define ICE_ETHTOOL_FWVER_LEN 32
#define ICE_AQ_LEN 64
+#define ICE_MBXSQ_LEN 64
+#define ICE_MBXRQ_LEN 512
#define ICE_MIN_MSIX 2
#define ICE_NO_VSI 0xffff
-#define ICE_MAX_VSI_ALLOC 130
-#define ICE_MAX_TXQS 2048
-#define ICE_MAX_RXQS 2048
#define ICE_VSI_MAP_CONTIG 0
#define ICE_VSI_MAP_SCATTER 1
#define ICE_MAX_SCATTER_TXQS 16
@@ -62,13 +70,16 @@
#define ICE_RES_VALID_BIT 0x8000
#define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1)
#define ICE_INVAL_Q_INDEX 0xffff
+#define ICE_INVAL_VFID 256
+
+#define ICE_MAX_RESET_WAIT 20
#define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4)
#define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
#define ICE_MAX_MTU (ICE_AQ_SET_MAC_FRAME_SIZE_MAX - \
- ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN)
+ (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)))
#define ICE_UP_TABLE_TRANSLATE(val, i) \
(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
@@ -82,37 +93,70 @@
#define ice_for_each_vsi(pf, i) \
for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++)
-/* Macros for each tx/rx ring in a VSI */
+/* Macros for each Tx/Rx ring in a VSI */
#define ice_for_each_txq(vsi, i) \
for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
#define ice_for_each_rxq(vsi, i) \
for ((i) = 0; (i) < (vsi)->num_rxq; (i)++)
-/* Macros for each allocated tx/rx ring whether used or not in a VSI */
+/* Macros for each allocated Tx/Rx ring whether used or not in a VSI */
#define ice_for_each_alloc_txq(vsi, i) \
for ((i) = 0; (i) < (vsi)->alloc_txq; (i)++)
#define ice_for_each_alloc_rxq(vsi, i) \
for ((i) = 0; (i) < (vsi)->alloc_rxq; (i)++)
+#define ice_for_each_q_vector(vsi, i) \
+ for ((i) = 0; (i) < (vsi)->num_q_vectors; (i)++)
+
+#define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_MCAST_TX | \
+ ICE_PROMISC_UCAST_RX | ICE_PROMISC_MCAST_RX)
+
+#define ICE_UCAST_VLAN_PROMISC_BITS (ICE_PROMISC_UCAST_TX | \
+ ICE_PROMISC_MCAST_TX | \
+ ICE_PROMISC_UCAST_RX | \
+ ICE_PROMISC_MCAST_RX | \
+ ICE_PROMISC_VLAN_TX | \
+ ICE_PROMISC_VLAN_RX)
+
+#define ICE_MCAST_PROMISC_BITS (ICE_PROMISC_MCAST_TX | ICE_PROMISC_MCAST_RX)
+
+#define ICE_MCAST_VLAN_PROMISC_BITS (ICE_PROMISC_MCAST_TX | \
+ ICE_PROMISC_MCAST_RX | \
+ ICE_PROMISC_VLAN_TX | \
+ ICE_PROMISC_VLAN_RX)
+
struct ice_tc_info {
u16 qoffset;
- u16 qcount;
+ u16 qcount_tx;
+ u16 qcount_rx;
+ u8 netdev_tc;
};
struct ice_tc_cfg {
u8 numtc; /* Total number of enabled TCs */
- u8 ena_tc; /* TX map */
+ u8 ena_tc; /* Tx map */
struct ice_tc_info tc_info[ICE_MAX_TRAFFIC_CLASS];
};
struct ice_res_tracker {
u16 num_entries;
- u16 search_hint;
+ u16 end;
u16 list[1];
};
+struct ice_qs_cfg {
+ struct mutex *qs_mutex; /* will be assigned to &pf->avail_q_mutex */
+ unsigned long *pf_map;
+ unsigned long pf_map_size;
+ unsigned int q_count;
+ unsigned int scatter_count;
+ u16 *vsi_map;
+ u16 vsi_map_offset;
+ u8 mapping_mode;
+};
+
struct ice_sw {
struct ice_pf *pf;
u16 sw_id; /* switch ID for this switch */
@@ -120,9 +164,11 @@
};
enum ice_state {
+ __ICE_TESTING,
__ICE_DOWN,
__ICE_NEEDS_RESTART,
- __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */
+ __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */
+ __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */
__ICE_PFR_REQ, /* set by driver and peers */
__ICE_CORER_REQ, /* set by driver and peers */
__ICE_GLOBR_REQ, /* set by driver and peers */
@@ -131,10 +177,25 @@
__ICE_EMPR_RECV, /* set by OICR handler */
__ICE_SUSPENDED, /* set on module remove path */
__ICE_RESET_FAILED, /* set by reset/rebuild */
+ /* When checking for the PF to be in a nominal operating state, the
+ * bits that are grouped at the beginning of the list need to be
+ * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
+ * be checked. If you need to add a bit into consideration for nominal
+ * operating state, it must be added before
+ * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position
+ * without appropriate consideration.
+ */
+ __ICE_STATE_NOMINAL_CHECK_BITS,
__ICE_ADMINQ_EVENT_PENDING,
+ __ICE_MAILBOXQ_EVENT_PENDING,
+ __ICE_MDD_EVENT_PENDING,
+ __ICE_VFLR_EVENT_PENDING,
__ICE_FLTR_OVERFLOW_PROMISC,
+ __ICE_VF_DIS,
__ICE_CFG_BUSY,
__ICE_SERVICE_SCHED,
+ __ICE_SERVICE_DIS,
+ __ICE_OICR_INTR_DIS, /* Global OICR interrupt disabled */
__ICE_STATE_NBITS /* must be last */
};
@@ -152,8 +213,8 @@
struct ice_sw *vsw; /* switch this VSI is on */
struct ice_pf *back; /* back pointer to PF */
struct ice_port_info *port_info; /* back pointer to port_info */
- struct ice_ring **rx_rings; /* rx ring array */
- struct ice_ring **tx_rings; /* tx ring array */
+ struct ice_ring **rx_rings; /* Rx ring array */
+ struct ice_ring **tx_rings; /* Tx ring array */
struct ice_q_vector **q_vectors; /* q_vector array */
irqreturn_t (*irq_handler)(int irq, void *data);
@@ -161,20 +222,20 @@
u64 tx_linearize;
DECLARE_BITMAP(state, __ICE_STATE_NBITS);
DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS);
- unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
unsigned int current_netdev_flags;
u32 tx_restart;
u32 tx_busy;
u32 rx_buf_failed;
u32 rx_page_failed;
int num_q_vectors;
- int base_vector;
+ int base_vector; /* IRQ base for OS reserved vectors */
enum ice_vsi_type type;
- u16 vsi_num; /* HW (absolute) index of this VSI */
- u16 idx; /* software index in pf->vsi[] */
+ u16 vsi_num; /* HW (absolute) index of this VSI */
+ u16 idx; /* software index in pf->vsi[] */
- /* Interrupt thresholds */
- u16 work_lmt;
+ s16 vf_id; /* VF ID for SR-IOV VSIs */
+
+ u16 ethtype; /* Ethernet protocol for pause frame */
/* RSS config */
u16 rss_table_size; /* HW RSS table size */
@@ -196,54 +257,89 @@
struct list_head tmp_sync_list; /* MAC filters to be synced */
struct list_head tmp_unsync_list; /* MAC filters to be unsynced */
- u8 irqs_ready;
- u8 current_isup; /* Sync 'link up' logging */
- u8 stat_offsets_loaded;
+ u8 irqs_ready:1;
+ u8 current_isup:1; /* Sync 'link up' logging */
+ u8 stat_offsets_loaded:1;
+ u8 vlan_ena:1;
/* queue information */
u8 tx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
u8 rx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
- u16 txq_map[ICE_MAX_TXQS]; /* index in pf->avail_txqs */
- u16 rxq_map[ICE_MAX_RXQS]; /* index in pf->avail_rxqs */
+ u16 *txq_map; /* index in pf->avail_txqs */
+ u16 *rxq_map; /* index in pf->avail_rxqs */
u16 alloc_txq; /* Allocated Tx queues */
u16 num_txq; /* Used Tx queues */
u16 alloc_rxq; /* Allocated Rx queues */
u16 num_rxq; /* Used Rx queues */
- u16 num_desc;
+ u16 num_rx_desc;
+ u16 num_tx_desc;
struct ice_tc_cfg tc_cfg;
} ____cacheline_internodealigned_in_smp;
/* struct that defines an interrupt vector */
struct ice_q_vector {
struct ice_vsi *vsi;
- cpumask_t affinity_mask;
+
+ u16 v_idx; /* index in the vsi->q_vector array. */
+ u16 reg_idx;
+ u8 num_ring_rx; /* total number of Rx rings in vector */
+ u8 num_ring_tx; /* total number of Tx rings in vector */
+ u8 itr_countdown; /* when 0 should adjust adaptive ITR */
+ /* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
+ * value to the device
+ */
+ u8 intrl;
+
struct napi_struct napi;
+
struct ice_ring_container rx;
struct ice_ring_container tx;
+
+ cpumask_t affinity_mask;
struct irq_affinity_notify affinity_notify;
- u16 v_idx; /* index in the vsi->q_vector array. */
- u8 num_ring_tx; /* total number of tx rings in vector */
- u8 num_ring_rx; /* total number of rx rings in vector */
+
char name[ICE_INT_NAME_STR_LEN];
} ____cacheline_internodealigned_in_smp;
enum ice_pf_flags {
- ICE_FLAG_MSIX_ENA,
ICE_FLAG_FLTR_SYNC,
ICE_FLAG_RSS_ENA,
+ ICE_FLAG_SRIOV_ENA,
+ ICE_FLAG_SRIOV_CAPABLE,
+ ICE_FLAG_DCB_CAPABLE,
+ ICE_FLAG_DCB_ENA,
+ ICE_FLAG_ADV_FEATURES,
+ ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
+ ICE_FLAG_NO_MEDIA,
+ ICE_FLAG_FW_LLDP_AGENT,
+ ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */
ICE_PF_FLAGS_NBITS /* must be last */
};
struct ice_pf {
struct pci_dev *pdev;
+
+ /* OS reserved IRQ details */
struct msix_entry *msix_entries;
struct ice_res_tracker *irq_tracker;
+ /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
+ * number of MSIX vectors needed for all SR-IOV VFs from the number of
+ * MSIX vectors allowed on this PF.
+ */
+ u16 sriov_base_vector;
+
struct ice_vsi **vsi; /* VSIs created by the driver */
struct ice_sw *first_sw; /* first switch created by firmware */
+ /* Virtchnl/SR-IOV config info */
+ struct ice_vf *vf;
+ int num_alloc_vfs; /* actual number of VFs allocated */
+ u16 num_vfs_supported; /* num VFs supported for this PF */
+ u16 num_vf_qps; /* num queue pairs per VF */
+ u16 num_vf_msix; /* num vectors per VF */
DECLARE_BITMAP(state, __ICE_STATE_NBITS);
- DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS);
- DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS);
DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS);
+ unsigned long *avail_txqs; /* bitmap to track PF Tx queue usage */
+ unsigned long *avail_rxqs; /* bitmap to track PF Rx queue usage */
unsigned long serv_tmr_period;
unsigned long serv_tmr_prev;
struct timer_list serv_tmr;
@@ -252,13 +348,13 @@
struct mutex sw_mutex; /* lock for protecting VSI alloc flow */
u32 msg_enable;
u32 hw_csum_rx_error;
- u32 oicr_idx; /* Other interrupt cause vector index */
+ u32 oicr_idx; /* Other interrupt cause MSIX vector index */
+ u32 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */
+ u16 max_pf_txqs; /* Total Tx queues PF wide */
+ u16 max_pf_rxqs; /* Total Rx queues PF wide */
u32 num_lan_msix; /* Total MSIX vectors for base driver */
- u32 num_avail_msix; /* remaining MSIX vectors left unclaimed */
- u16 num_lan_tx; /* num lan tx queues setup */
- u16 num_lan_rx; /* num lan rx queues setup */
- u16 q_left_tx; /* remaining num tx queues left unclaimed */
- u16 q_left_rx; /* remaining num rx queues left unclaimed */
+ u16 num_lan_tx; /* num LAN Tx queues setup */
+ u16 num_lan_rx; /* num LAN Rx queues setup */
u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */
u16 num_alloc_vsi;
u16 corer_count; /* Core reset count */
@@ -269,8 +365,15 @@
struct ice_hw_port_stats stats;
struct ice_hw_port_stats stats_prev;
struct ice_hw hw;
- u8 stat_prev_loaded; /* has previous stats been loaded */
+ u8 stat_prev_loaded:1; /* has previous stats been loaded */
+#ifdef CONFIG_DCB
+ u16 dcbx_cap;
+#endif /* CONFIG_DCB */
+ u32 tx_timeout_count;
+ unsigned long tx_timeout_last_recovery;
+ u32 tx_timeout_recovery_level;
char int_name[ICE_INT_NAME_STR_LEN];
+ u32 sw_int_count;
};
struct ice_netdev_priv {
@@ -279,15 +382,16 @@
/**
* ice_irq_dynamic_ena - Enable default interrupt generation settings
- * @hw: pointer to hw struct
- * @vsi: pointer to vsi struct, can be NULL
+ * @hw: pointer to HW struct
+ * @vsi: pointer to VSI struct, can be NULL
* @q_vector: pointer to q_vector, can be NULL
*/
-static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
- struct ice_q_vector *q_vector)
+static inline void
+ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
+ struct ice_q_vector *q_vector)
{
- u32 vector = (vsi && q_vector) ? vsi->base_vector + q_vector->v_idx :
- ((struct ice_pf *)hw->back)->oicr_idx;
+ u32 vector = (vsi && q_vector) ? q_vector->reg_idx :
+ ((struct ice_pf *)hw->back)->oicr_idx;
int itr = ICE_ITR_NONE;
u32 val;
@@ -302,18 +406,52 @@
wr32(hw, GLINT_DYN_CTL(vector), val);
}
-static inline void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
+/**
+ * ice_netdev_to_pf - Retrieve the PF struct associated with a netdev
+ * @netdev: pointer to the netdev struct
+ */
+static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev)
{
- vsi->tc_cfg.ena_tc = ICE_DFLT_TRAFFIC_CLASS;
- vsi->tc_cfg.numtc = 1;
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+
+ return np->vsi->back;
}
+/**
+ * ice_get_main_vsi - Get the PF VSI
+ * @pf: PF instance
+ *
+ * returns pf->vsi[0], which by definition is the PF VSI
+ */
+static inline struct ice_vsi *ice_get_main_vsi(struct ice_pf *pf)
+{
+ if (pf->vsi)
+ return pf->vsi[0];
+
+ return NULL;
+}
+
+int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
+int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
void ice_set_ethtool_ops(struct net_device *netdev);
+void ice_set_ethtool_safe_mode_ops(struct net_device *netdev);
+u16 ice_get_avail_txq_count(struct ice_pf *pf);
+u16 ice_get_avail_rxq_count(struct ice_pf *pf);
+void ice_update_vsi_stats(struct ice_vsi *vsi);
+void ice_update_pf_stats(struct ice_pf *pf);
int ice_up(struct ice_vsi *vsi);
int ice_down(struct ice_vsi *vsi);
+int ice_vsi_cfg(struct ice_vsi *vsi);
+struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
+#ifdef CONFIG_DCB
+int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked);
+void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked);
+#endif /* CONFIG_DCB */
+int ice_open(struct net_device *netdev);
+int ice_stop(struct net_device *netdev);
#endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index a0614f4..023e3d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -5,7 +5,7 @@
#define _ICE_ADMINQ_CMD_H_
/* This header file defines the Admin Queue commands, error codes and
- * descriptor format. It is shared between Firmware and Software.
+ * descriptor format. It is shared between Firmware and Software.
*/
#define ICE_MAX_VSI 768
@@ -33,11 +33,22 @@
u8 api_patch;
};
+/* Send driver version (indirect 0x0002) */
+struct ice_aqc_driver_ver {
+ u8 major_ver;
+ u8 minor_ver;
+ u8 build_ver;
+ u8 subbuild_ver;
+ u8 reserved[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
/* Queue Shutdown (direct 0x0003) */
struct ice_aqc_q_shutdown {
+ u8 driver_unloading;
#define ICE_AQC_DRIVER_UNLOADING BIT(0)
- __le32 driver_unloading;
- u8 reserved[12];
+ u8 reserved[15];
};
/* Request resource ownership (direct 0x0008)
@@ -62,7 +73,7 @@
#define ICE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS 180000
#define ICE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS 1000
#define ICE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS 3000
- /* For SDP: pin id of the SDP */
+ /* For SDP: pin ID of the SDP */
__le32 res_number;
/* Status is only used for ICE_AQC_RES_ID_GLBL_LOCK */
__le16 status;
@@ -87,7 +98,11 @@
/* Device/Function buffer entry, repeated per reported capability */
struct ice_aqc_list_caps_elem {
__le16 cap;
+#define ICE_AQC_CAPS_VALID_FUNCTIONS 0x0005
+#define ICE_AQC_CAPS_SRIOV 0x0012
+#define ICE_AQC_CAPS_VF 0x0013
#define ICE_AQC_CAPS_VSI 0x0017
+#define ICE_AQC_CAPS_DCB 0x0018
#define ICE_AQC_CAPS_RSS 0x0040
#define ICE_AQC_CAPS_RXQS 0x0041
#define ICE_AQC_CAPS_TXQS 0x0042
@@ -117,11 +132,9 @@
#define ICE_AQC_MAN_MAC_WOL_ADDR_VALID BIT(7)
#define ICE_AQC_MAN_MAC_READ_S 4
#define ICE_AQC_MAN_MAC_READ_M (0xF << ICE_AQC_MAN_MAC_READ_S)
- u8 lport_num;
- u8 lport_num_valid;
-#define ICE_AQC_MAN_MAC_PORT_NUM_IS_VALID BIT(0)
+ u8 rsvd[2];
u8 num_addr; /* Used in response */
- u8 reserved[3];
+ u8 rsvd1[3];
__le32 addr_high;
__le32 addr_low;
};
@@ -137,7 +150,7 @@
/* Manage MAC address, write command - direct (0x0108) */
struct ice_aqc_manage_mac_write {
- u8 port_num;
+ u8 rsvd;
u8 flags;
#define ICE_AQC_MAN_MAC_WR_MC_MAG_EN BIT(0)
#define ICE_AQC_MAN_MAC_WR_WOL_LAA_PFR_KEEP BIT(1)
@@ -443,6 +456,8 @@
u8 reserved[24];
};
+#define ICE_MAX_NUM_RECIPES 64
+
/* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3)
*/
struct ice_aqc_sw_rules {
@@ -458,7 +473,7 @@
};
/* Add/Update/Get/Remove lookup Rx/Tx command/response entry
- * This structures describes the lookup rules and associated actions. "index"
+ * This structures describes the lookup rules and associated actions. "index"
* is returned as part of a response to a successful Add command, and can be
* used to identify the rule for Update/Get/Remove commands.
*/
@@ -652,8 +667,13 @@
/* Update TSE (indirect 0x0403)
* Get TSE (indirect 0x0404)
+ * Add TSE (indirect 0x0401)
+ * Delete TSE (indirect 0x040F)
+ * Move TSE (indirect 0x0408)
+ * Suspend Nodes (indirect 0x0409)
+ * Resume Nodes (indirect 0x040A)
*/
-struct ice_aqc_get_cfg_elem {
+struct ice_aqc_sched_elem_cmd {
__le16 num_elem_req; /* Used by commands */
__le16 num_elem_resp; /* Used by responses */
__le32 reserved;
@@ -669,18 +689,6 @@
__le32 teid[1];
};
-/* Add TSE (indirect 0x0401)
- * Delete TSE (indirect 0x040F)
- * Move TSE (indirect 0x0408)
- */
-struct ice_aqc_add_move_delete_elem {
- __le16 num_grps_req;
- __le16 num_grps_updated;
- __le32 reserved;
- __le32 addr_high;
- __le32 addr_low;
-};
-
struct ice_aqc_elem_info_bw {
__le16 bw_profile_idx;
__le16 bw_alloc;
@@ -734,6 +742,10 @@
struct ice_aqc_txsched_elem_data generic[1];
};
+struct ice_aqc_get_elem {
+ struct ice_aqc_txsched_elem_data generic[1];
+};
+
struct ice_aqc_get_topo_elem {
struct ice_aqc_txsched_topo_grp_info_hdr hdr;
struct ice_aqc_txsched_elem_data
@@ -745,6 +757,32 @@
__le32 teid[1];
};
+/* Query Port ETS (indirect 0x040E)
+ *
+ * This indirect command is used to query port TC node configuration.
+ */
+struct ice_aqc_query_port_ets {
+ __le32 port_teid;
+ __le32 reserved;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+struct ice_aqc_port_ets_elem {
+ u8 tc_valid_bits;
+ u8 reserved[3];
+ /* 3 bits for UP per TC 0-7, 4th byte reserved */
+ __le32 up2tc;
+ u8 tc_bw_share[8];
+ __le32 port_eir_prof_id;
+ __le32 port_cir_prof_id;
+ /* 3 bits per Node priority to TC 0-7, 4th byte reserved */
+ __le32 tc_node_prio;
+#define ICE_TC_NODE_PRIO_S 0x4
+ u8 reserved1[4];
+ __le32 tc_node_teid[8]; /* Used for response, reserved in command */
+};
+
/* Query Scheduler Resource Allocation (indirect 0x0412)
* This indirect command retrieves the scheduler resources allocated by
* EMP Firmware to the given PF.
@@ -771,9 +809,8 @@
u8 chunk_size;
__le16 max_device_nodes;
__le16 max_pf_nodes;
- u8 rsvd0[2];
- __le16 max_shared_rate_lmtr;
- __le16 max_children;
+ u8 rsvd0[4];
+ __le16 max_sibl_grp_sz;
__le16 max_cir_rl_profiles;
__le16 max_eir_rl_profiles;
__le16 max_srl_profiles;
@@ -846,11 +883,46 @@
#define ICE_PHY_TYPE_LOW_40GBASE_KR4 BIT_ULL(33)
#define ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC BIT_ULL(34)
#define ICE_PHY_TYPE_LOW_40G_XLAUI BIT_ULL(35)
+#define ICE_PHY_TYPE_LOW_50GBASE_CR2 BIT_ULL(36)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR2 BIT_ULL(37)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR2 BIT_ULL(38)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR2 BIT_ULL(39)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC BIT_ULL(40)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2 BIT_ULL(41)
+#define ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC BIT_ULL(42)
+#define ICE_PHY_TYPE_LOW_50G_AUI2 BIT_ULL(43)
+#define ICE_PHY_TYPE_LOW_50GBASE_CP BIT_ULL(44)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR BIT_ULL(45)
+#define ICE_PHY_TYPE_LOW_50GBASE_FR BIT_ULL(46)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR BIT_ULL(47)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4 BIT_ULL(48)
+#define ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC BIT_ULL(49)
+#define ICE_PHY_TYPE_LOW_50G_AUI1 BIT_ULL(50)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR4 BIT_ULL(51)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR4 BIT_ULL(52)
+#define ICE_PHY_TYPE_LOW_100GBASE_LR4 BIT_ULL(53)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR4 BIT_ULL(54)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC BIT_ULL(55)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4 BIT_ULL(56)
+#define ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC BIT_ULL(57)
+#define ICE_PHY_TYPE_LOW_100G_AUI4 BIT_ULL(58)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 BIT_ULL(59)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 BIT_ULL(60)
+#define ICE_PHY_TYPE_LOW_100GBASE_CP2 BIT_ULL(61)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR2 BIT_ULL(62)
+#define ICE_PHY_TYPE_LOW_100GBASE_DR BIT_ULL(63)
#define ICE_PHY_TYPE_LOW_MAX_INDEX 63
+/* The second set of defines is for phy_type_high. */
+#define ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4 BIT_ULL(0)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC BIT_ULL(1)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2 BIT_ULL(2)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC BIT_ULL(3)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2 BIT_ULL(4)
+#define ICE_PHY_TYPE_HIGH_MAX_INDEX 19
struct ice_aqc_get_phy_caps_data {
__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
- __le64 reserved;
+ __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
u8 caps;
#define ICE_AQC_PHY_EN_TX_LINK_PAUSE BIT(0)
#define ICE_AQC_PHY_EN_RX_LINK_PAUSE BIT(1)
@@ -858,6 +930,8 @@
#define ICE_AQC_PHY_EN_LINK BIT(3)
#define ICE_AQC_PHY_AN_MODE BIT(4)
#define ICE_AQC_GET_PHY_EN_MOD_QUAL BIT(5)
+#define ICE_AQC_PHY_EN_AUTO_FEC BIT(7)
+#define ICE_AQC_PHY_CAPS_MASK ICE_M(0xff, 0)
u8 low_power_ctrl;
#define ICE_AQC_PHY_EN_D3COLD_LOW_POWER_AUTONEG BIT(0)
__le16 eee_cap;
@@ -870,6 +944,7 @@
#define ICE_AQC_PHY_EEE_EN_40GBASE_KR4 BIT(6)
__le16 eeer_value;
u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */
+ u8 phy_fw_ver[8];
u8 link_fec_options;
#define ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN BIT(0)
#define ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ BIT(1)
@@ -878,6 +953,8 @@
#define ICE_AQC_PHY_FEC_25G_RS_544_REQ BIT(4)
#define ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN BIT(6)
#define ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN BIT(7)
+#define ICE_AQC_PHY_FEC_MASK ICE_M(0xdf, 0)
+ u8 rsvd1; /* Byte 35 reserved */
u8 extended_compliance_code;
#define ICE_MODULE_TYPE_TOTAL_BYTE 3
u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE];
@@ -892,13 +969,14 @@
#define ICE_AQC_MOD_TYPE_BYTE2_SFP_PLUS 0xA0
#define ICE_AQC_MOD_TYPE_BYTE2_QSFP_PLUS 0x86
u8 qualified_module_count;
+ u8 rsvd2[7]; /* Bytes 47:41 reserved */
#define ICE_AQC_QUAL_MOD_COUNT_MAX 16
struct {
u8 v_oui[3];
- u8 rsvd1;
+ u8 rsvd3;
u8 v_part[16];
__le32 v_rev;
- __le64 rsvd8;
+ __le64 rsvd4;
} qual_modules[ICE_AQC_QUAL_MOD_COUNT_MAX];
};
@@ -915,13 +993,16 @@
/* Set PHY config command data structure */
struct ice_aqc_set_phy_cfg_data {
__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
- __le64 rsvd0;
+ __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
u8 caps;
-#define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0)
-#define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1)
-#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2)
-#define ICE_AQ_PHY_ENA_LINK BIT(3)
-#define ICE_AQ_PHY_ENA_ATOMIC_LINK BIT(5)
+#define ICE_AQ_PHY_ENA_VALID_MASK ICE_M(0xef, 0)
+#define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0)
+#define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1)
+#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2)
+#define ICE_AQ_PHY_ENA_LINK BIT(3)
+#define ICE_AQ_PHY_ENA_AUTO_LINK_UPDT BIT(5)
+#define ICE_AQ_PHY_ENA_LESM BIT(6)
+#define ICE_AQ_PHY_ENA_AUTO_FEC BIT(7)
u8 low_power_ctrl;
__le16 eee_cap; /* Value from ice_aqc_get_phy_caps */
__le16 eeer_value;
@@ -985,7 +1066,7 @@
u8 ext_info;
#define ICE_AQ_LINK_PHY_TEMP_ALARM BIT(0)
#define ICE_AQ_LINK_EXCESSIVE_ERRORS BIT(1) /* Excessive Link Errors */
- /* Port TX Suspended */
+ /* Port Tx Suspended */
#define ICE_AQ_LINK_TX_S 2
#define ICE_AQ_LINK_TX_M (0x03 << ICE_AQ_LINK_TX_S)
#define ICE_AQ_LINK_TX_ACTIVE 0
@@ -997,6 +1078,7 @@
#define ICE_AQ_LINK_25G_KR_FEC_EN BIT(0)
#define ICE_AQ_LINK_25G_RS_528_FEC_EN BIT(1)
#define ICE_AQ_LINK_25G_RS_544_FEC_EN BIT(2)
+#define ICE_AQ_FEC_MASK ICE_M(0x7, 0)
/* Pacing Config */
#define ICE_AQ_CFG_PACING_S 3
#define ICE_AQ_CFG_PACING_M (0xF << ICE_AQ_CFG_PACING_S)
@@ -1022,10 +1104,12 @@
#define ICE_AQ_LINK_SPEED_20GB BIT(6)
#define ICE_AQ_LINK_SPEED_25GB BIT(7)
#define ICE_AQ_LINK_SPEED_40GB BIT(8)
+#define ICE_AQ_LINK_SPEED_50GB BIT(9)
+#define ICE_AQ_LINK_SPEED_100GB BIT(10)
#define ICE_AQ_LINK_SPEED_UNKNOWN BIT(15)
__le32 reserved3; /* Aligns next field to 8-byte boundary */
__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
- __le64 reserved4;
+ __le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
};
/* Set event mask command (direct 0x0613) */
@@ -1045,6 +1129,24 @@
u8 reserved1[6];
};
+/* Set MAC Loopback command (direct 0x0620) */
+struct ice_aqc_set_mac_lb {
+ u8 lb_mode;
+#define ICE_AQ_MAC_LB_EN BIT(0)
+#define ICE_AQ_MAC_LB_OSC_CLK BIT(1)
+ u8 reserved[15];
+};
+
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ice_aqc_set_port_id_led {
+ u8 lport_num;
+ u8 lport_num_valid;
+ u8 ident_mode;
+#define ICE_AQC_PORT_IDENT_LED_BLINK BIT(0)
+#define ICE_AQC_PORT_IDENT_LED_ORIG 0
+ u8 rsvd[13];
+};
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
@@ -1056,10 +1158,10 @@
#define ICE_AQC_NVM_LAST_CMD BIT(0)
#define ICE_AQC_NVM_PCIR_REQ BIT(0) /* Used by NVM Update reply */
#define ICE_AQC_NVM_PRESERVATION_S 1
-#define ICE_AQC_NVM_PRESERVATION_M (3 << CSR_AQ_NVM_PRESERVATION_S)
-#define ICE_AQC_NVM_NO_PRESERVATION (0 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVATION_M (3 << ICE_AQC_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_NO_PRESERVATION (0 << ICE_AQC_NVM_PRESERVATION_S)
#define ICE_AQC_NVM_PRESERVE_ALL BIT(1)
-#define ICE_AQC_NVM_PRESERVE_SELECTED (3 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVE_SELECTED (3 << ICE_AQC_NVM_PRESERVATION_S)
#define ICE_AQC_NVM_FLASH_ONLY BIT(7)
__le16 module_typeid;
__le16 length;
@@ -1068,6 +1170,150 @@
__le32 addr_low;
};
+/* NVM Checksum Command (direct, 0x0706) */
+struct ice_aqc_nvm_checksum {
+ u8 flags;
+#define ICE_AQC_NVM_CHECKSUM_VERIFY BIT(0)
+#define ICE_AQC_NVM_CHECKSUM_RECALC BIT(1)
+ u8 rsvd;
+ __le16 checksum; /* Used only by response */
+#define ICE_AQC_NVM_CHECKSUM_CORRECT 0xBABA
+ u8 rsvd2[12];
+};
+
+/**
+ * Send to PF command (indirect 0x0801) ID is only used by PF
+ *
+ * Send to VF command (indirect 0x0802) ID is only used by PF
+ *
+ */
+struct ice_aqc_pf_vf_msg {
+ __le32 id;
+ u32 reserved;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Get LLDP MIB (indirect 0x0A00)
+ * Note: This is also used by the LLDP MIB Change Event (0x0A01)
+ * as the format is the same.
+ */
+struct ice_aqc_lldp_get_mib {
+ u8 type;
+#define ICE_AQ_LLDP_MIB_TYPE_S 0
+#define ICE_AQ_LLDP_MIB_TYPE_M (0x3 << ICE_AQ_LLDP_MIB_TYPE_S)
+#define ICE_AQ_LLDP_MIB_LOCAL 0
+#define ICE_AQ_LLDP_MIB_REMOTE 1
+#define ICE_AQ_LLDP_MIB_LOCAL_AND_REMOTE 2
+#define ICE_AQ_LLDP_BRID_TYPE_S 2
+#define ICE_AQ_LLDP_BRID_TYPE_M (0x3 << ICE_AQ_LLDP_BRID_TYPE_S)
+#define ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID 0
+#define ICE_AQ_LLDP_BRID_TYPE_NON_TPMR 1
+/* Tx pause flags in the 0xA01 event use ICE_AQ_LLDP_TX_* */
+#define ICE_AQ_LLDP_TX_S 0x4
+#define ICE_AQ_LLDP_TX_M (0x03 << ICE_AQ_LLDP_TX_S)
+#define ICE_AQ_LLDP_TX_ACTIVE 0
+#define ICE_AQ_LLDP_TX_SUSPENDED 1
+#define ICE_AQ_LLDP_TX_FLUSHED 3
+/* The following bytes are reserved for the Get LLDP MIB command (0x0A00)
+ * and in the LLDP MIB Change Event (0x0A01). They are valid for the
+ * Get LLDP MIB (0x0A00) response only.
+ */
+ u8 reserved1;
+ __le16 local_len;
+ __le16 remote_len;
+ u8 reserved2[2];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Configure LLDP MIB Change Event (direct 0x0A01) */
+/* For MIB Change Event use ice_aqc_lldp_get_mib structure above */
+struct ice_aqc_lldp_set_mib_change {
+ u8 command;
+#define ICE_AQ_LLDP_MIB_UPDATE_ENABLE 0x0
+#define ICE_AQ_LLDP_MIB_UPDATE_DIS 0x1
+ u8 reserved[15];
+};
+
+/* Stop LLDP (direct 0x0A05) */
+struct ice_aqc_lldp_stop {
+ u8 command;
+#define ICE_AQ_LLDP_AGENT_STATE_MASK BIT(0)
+#define ICE_AQ_LLDP_AGENT_STOP 0x0
+#define ICE_AQ_LLDP_AGENT_SHUTDOWN ICE_AQ_LLDP_AGENT_STATE_MASK
+#define ICE_AQ_LLDP_AGENT_PERSIST_DIS BIT(1)
+ u8 reserved[15];
+};
+
+/* Start LLDP (direct 0x0A06) */
+struct ice_aqc_lldp_start {
+ u8 command;
+#define ICE_AQ_LLDP_AGENT_START BIT(0)
+#define ICE_AQ_LLDP_AGENT_PERSIST_ENA BIT(1)
+ u8 reserved[15];
+};
+
+/* Get CEE DCBX Oper Config (0x0A07)
+ * The command uses the generic descriptor struct and
+ * returns the struct below as an indirect response.
+ */
+struct ice_aqc_get_cee_dcb_cfg_resp {
+ u8 oper_num_tc;
+ u8 oper_prio_tc[4];
+ u8 oper_tc_bw[8];
+ u8 oper_pfc_en;
+ __le16 oper_app_prio;
+#define ICE_AQC_CEE_APP_FCOE_S 0
+#define ICE_AQC_CEE_APP_FCOE_M (0x7 << ICE_AQC_CEE_APP_FCOE_S)
+#define ICE_AQC_CEE_APP_ISCSI_S 3
+#define ICE_AQC_CEE_APP_ISCSI_M (0x7 << ICE_AQC_CEE_APP_ISCSI_S)
+#define ICE_AQC_CEE_APP_FIP_S 8
+#define ICE_AQC_CEE_APP_FIP_M (0x7 << ICE_AQC_CEE_APP_FIP_S)
+ __le32 tlv_status;
+#define ICE_AQC_CEE_PG_STATUS_S 0
+#define ICE_AQC_CEE_PG_STATUS_M (0x7 << ICE_AQC_CEE_PG_STATUS_S)
+#define ICE_AQC_CEE_PFC_STATUS_S 3
+#define ICE_AQC_CEE_PFC_STATUS_M (0x7 << ICE_AQC_CEE_PFC_STATUS_S)
+#define ICE_AQC_CEE_FCOE_STATUS_S 8
+#define ICE_AQC_CEE_FCOE_STATUS_M (0x7 << ICE_AQC_CEE_FCOE_STATUS_S)
+#define ICE_AQC_CEE_ISCSI_STATUS_S 11
+#define ICE_AQC_CEE_ISCSI_STATUS_M (0x7 << ICE_AQC_CEE_ISCSI_STATUS_S)
+#define ICE_AQC_CEE_FIP_STATUS_S 16
+#define ICE_AQC_CEE_FIP_STATUS_M (0x7 << ICE_AQC_CEE_FIP_STATUS_S)
+ u8 reserved[12];
+};
+
+/* Set Local LLDP MIB (indirect 0x0A08)
+ * Used to replace the local MIB of a given LLDP agent. e.g. DCBX
+ */
+struct ice_aqc_lldp_set_local_mib {
+ u8 type;
+#define SET_LOCAL_MIB_TYPE_DCBX_M BIT(0)
+#define SET_LOCAL_MIB_TYPE_LOCAL_MIB 0
+#define SET_LOCAL_MIB_TYPE_CEE_M BIT(1)
+#define SET_LOCAL_MIB_TYPE_CEE_WILLING 0
+#define SET_LOCAL_MIB_TYPE_CEE_NON_WILLING SET_LOCAL_MIB_TYPE_CEE_M
+ u8 reserved0;
+ __le16 length;
+ u8 reserved1[4];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Stop/Start LLDP Agent (direct 0x0A09)
+ * Used for stopping/starting specific LLDP agent. e.g. DCBX.
+ * The same structure is used for the response, with the command field
+ * being used as the status field.
+ */
+struct ice_aqc_lldp_stop_start_specific_agent {
+ u8 command;
+#define ICE_AQC_START_STOP_AGENT_M BIT(0)
+#define ICE_AQC_START_STOP_AGENT_STOP_DCBX 0
+#define ICE_AQC_START_STOP_AGENT_START_DCBX ICE_AQC_START_STOP_AGENT_M
+ u8 reserved[15];
+};
+
/* Get/Set RSS key (indirect 0x0B04/0x0B02) */
struct ice_aqc_get_set_rss_key {
#define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15)
@@ -1081,6 +1327,9 @@
#define ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE 0x28
#define ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE 0xC
+#define ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE \
+ (ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE + \
+ ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE)
struct ice_aqc_get_set_rss_keys {
u8 standard_rss_key[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
@@ -1088,7 +1337,7 @@
};
/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
-struct ice_aqc_get_set_rss_lut {
+struct ice_aqc_get_set_rss_lut {
#define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15)
#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0
#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S)
@@ -1122,7 +1371,7 @@
__le32 addr_low;
};
-/* Add TX LAN Queues (indirect 0x0C30) */
+/* Add Tx LAN Queues (indirect 0x0C30) */
struct ice_aqc_add_txqs {
u8 num_qgrps;
u8 reserved[3];
@@ -1131,7 +1380,7 @@
__le32 addr_low;
};
-/* This is the descriptor of each queue entry for the Add TX LAN Queues
+/* This is the descriptor of each queue entry for the Add Tx LAN Queues
* command (0x0C30). Only used within struct ice_aqc_add_tx_qgrp.
*/
struct ice_aqc_add_txqs_perq {
@@ -1143,7 +1392,7 @@
struct ice_aqc_txsched_elem info;
};
-/* The format of the command buffer for Add TX LAN Queues (0x0C30)
+/* The format of the command buffer for Add Tx LAN Queues (0x0C30)
* is an array of the following structs. Please note that the length of
* each struct ice_aqc_add_tx_qgrp is variable due
* to the variable number of queues in each group!
@@ -1155,7 +1404,7 @@
struct ice_aqc_add_txqs_perq txqs[1];
};
-/* Disable TX LAN Queues (indirect 0x0C31) */
+/* Disable Tx LAN Queues (indirect 0x0C31) */
struct ice_aqc_dis_txqs {
u8 cmd_type;
#define ICE_AQC_Q_DIS_CMD_S 0
@@ -1177,7 +1426,7 @@
__le32 addr_low;
};
-/* The buffer for Disable TX LAN Queues (indirect 0x0C31)
+/* The buffer for Disable Tx LAN Queues (indirect 0x0C31)
* contains the following structures, arrayed one after the
* other.
* Note: Since the q_id is 16 bits wide, if the
@@ -1203,6 +1452,134 @@
struct ice_aqc_dis_txq_item qgrps[1];
};
+/* Configure Firmware Logging Command (indirect 0xFF09)
+ * Logging Information Read Response (indirect 0xFF10)
+ * Note: The 0xFF10 command has no input parameters.
+ */
+struct ice_aqc_fw_logging {
+ u8 log_ctrl;
+#define ICE_AQC_FW_LOG_AQ_EN BIT(0)
+#define ICE_AQC_FW_LOG_UART_EN BIT(1)
+ u8 rsvd0;
+ u8 log_ctrl_valid; /* Not used by 0xFF10 Response */
+#define ICE_AQC_FW_LOG_AQ_VALID BIT(0)
+#define ICE_AQC_FW_LOG_UART_VALID BIT(1)
+ u8 rsvd1[5];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+enum ice_aqc_fw_logging_mod {
+ ICE_AQC_FW_LOG_ID_GENERAL = 0,
+ ICE_AQC_FW_LOG_ID_CTRL,
+ ICE_AQC_FW_LOG_ID_LINK,
+ ICE_AQC_FW_LOG_ID_LINK_TOPO,
+ ICE_AQC_FW_LOG_ID_DNL,
+ ICE_AQC_FW_LOG_ID_I2C,
+ ICE_AQC_FW_LOG_ID_SDP,
+ ICE_AQC_FW_LOG_ID_MDIO,
+ ICE_AQC_FW_LOG_ID_ADMINQ,
+ ICE_AQC_FW_LOG_ID_HDMA,
+ ICE_AQC_FW_LOG_ID_LLDP,
+ ICE_AQC_FW_LOG_ID_DCBX,
+ ICE_AQC_FW_LOG_ID_DCB,
+ ICE_AQC_FW_LOG_ID_NETPROXY,
+ ICE_AQC_FW_LOG_ID_NVM,
+ ICE_AQC_FW_LOG_ID_AUTH,
+ ICE_AQC_FW_LOG_ID_VPD,
+ ICE_AQC_FW_LOG_ID_IOSF,
+ ICE_AQC_FW_LOG_ID_PARSER,
+ ICE_AQC_FW_LOG_ID_SW,
+ ICE_AQC_FW_LOG_ID_SCHEDULER,
+ ICE_AQC_FW_LOG_ID_TXQ,
+ ICE_AQC_FW_LOG_ID_RSVD,
+ ICE_AQC_FW_LOG_ID_POST,
+ ICE_AQC_FW_LOG_ID_WATCHDOG,
+ ICE_AQC_FW_LOG_ID_TASK_DISPATCH,
+ ICE_AQC_FW_LOG_ID_MNG,
+ ICE_AQC_FW_LOG_ID_MAX,
+};
+
+/* This is the buffer for both of the logging commands.
+ * The entry array size depends on the datalen parameter in the descriptor.
+ * There will be a total of datalen / 2 entries.
+ */
+struct ice_aqc_fw_logging_data {
+ __le16 entry[1];
+#define ICE_AQC_FW_LOG_ID_S 0
+#define ICE_AQC_FW_LOG_ID_M (0xFFF << ICE_AQC_FW_LOG_ID_S)
+
+#define ICE_AQC_FW_LOG_CONF_SUCCESS 0 /* Used by response */
+#define ICE_AQC_FW_LOG_CONF_BAD_INDX BIT(12) /* Used by response */
+
+#define ICE_AQC_FW_LOG_EN_S 12
+#define ICE_AQC_FW_LOG_EN_M (0xF << ICE_AQC_FW_LOG_EN_S)
+#define ICE_AQC_FW_LOG_INFO_EN BIT(12) /* Used by command */
+#define ICE_AQC_FW_LOG_INIT_EN BIT(13) /* Used by command */
+#define ICE_AQC_FW_LOG_FLOW_EN BIT(14) /* Used by command */
+#define ICE_AQC_FW_LOG_ERR_EN BIT(15) /* Used by command */
+};
+
+/* Get/Clear FW Log (indirect 0xFF11) */
+struct ice_aqc_get_clear_fw_log {
+ u8 flags;
+#define ICE_AQC_FW_LOG_CLEAR BIT(0)
+#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL BIT(1)
+ u8 rsvd1[7];
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Download Package (indirect 0x0C40) */
+/* Also used for Update Package (indirect 0x0C42) */
+struct ice_aqc_download_pkg {
+ u8 flags;
+#define ICE_AQC_DOWNLOAD_PKG_LAST_BUF 0x01
+ u8 reserved[3];
+ __le32 reserved1;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+struct ice_aqc_download_pkg_resp {
+ __le32 error_offset;
+ __le32 error_info;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Get Package Info List (indirect 0x0C43) */
+struct ice_aqc_get_pkg_info_list {
+ __le32 reserved1;
+ __le32 reserved2;
+ __le32 addr_high;
+ __le32 addr_low;
+};
+
+/* Version format for packages */
+struct ice_pkg_ver {
+ u8 major;
+ u8 minor;
+ u8 update;
+ u8 draft;
+};
+
+#define ICE_PKG_NAME_SIZE 32
+
+struct ice_aqc_get_pkg_info {
+ struct ice_pkg_ver ver;
+ char name[ICE_PKG_NAME_SIZE];
+ u8 is_in_nvm;
+ u8 is_active;
+ u8 is_active_at_boot;
+ u8 is_modified;
+};
+
+/* Get Package Info List response buffer format (0x0C43) */
+struct ice_aqc_get_pkg_info_resp {
+ __le32 count;
+ struct ice_aqc_get_pkg_info pkg_info[1];
+};
/**
* struct ice_aq_desc - Admin Queue (AQ) descriptor
* @flags: ICE_AQ_FLAG_* flags
@@ -1214,10 +1591,10 @@
* @params: command-specific parameters
*
* Descriptor format for commands the driver posts on the Admin Transmit Queue
- * (ATQ). The firmware writes back onto the command descriptor and returns
- * the result of the command. Asynchronous events that are not an immediate
+ * (ATQ). The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
* result of the command are written to the Admin Receive Queue (ARQ) using
- * the same descriptor format. Descriptors are in little-endian notation with
+ * the same descriptor format. Descriptors are in little-endian notation with
* 32-bit words.
*/
struct ice_aq_desc {
@@ -1231,6 +1608,7 @@
u8 raw[16];
struct ice_aqc_generic generic;
struct ice_aqc_get_ver get_ver;
+ struct ice_aqc_driver_ver driver_ver;
struct ice_aqc_q_shutdown q_shutdown;
struct ice_aqc_req_res res_owner;
struct ice_aqc_manage_mac_read mac_read;
@@ -1240,18 +1618,32 @@
struct ice_aqc_get_phy_caps get_phy;
struct ice_aqc_set_phy_cfg set_phy;
struct ice_aqc_restart_an restart_an;
+ struct ice_aqc_set_port_id_led set_port_id_led;
struct ice_aqc_get_sw_cfg get_sw_conf;
struct ice_aqc_sw_rules sw_rules;
struct ice_aqc_get_topo get_topo;
- struct ice_aqc_get_cfg_elem get_update_elem;
+ struct ice_aqc_sched_elem_cmd sched_elem_cmd;
struct ice_aqc_query_txsched_res query_sched_res;
- struct ice_aqc_add_move_delete_elem add_move_delete_elem;
+ struct ice_aqc_query_port_ets port_ets;
struct ice_aqc_nvm nvm;
+ struct ice_aqc_nvm_checksum nvm_checksum;
+ struct ice_aqc_pf_vf_msg virt;
+ struct ice_aqc_lldp_get_mib lldp_get_mib;
+ struct ice_aqc_lldp_set_mib_change lldp_set_event;
+ struct ice_aqc_lldp_stop lldp_stop;
+ struct ice_aqc_lldp_start lldp_start;
+ struct ice_aqc_lldp_set_local_mib lldp_set_mib;
+ struct ice_aqc_lldp_stop_start_specific_agent lldp_agent_ctrl;
struct ice_aqc_get_set_rss_lut get_set_rss_lut;
struct ice_aqc_get_set_rss_key get_set_rss_key;
struct ice_aqc_add_txqs add_txqs;
struct ice_aqc_dis_txqs dis_txqs;
struct ice_aqc_add_get_update_free_vsi vsi_cmd;
+ struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
+ struct ice_aqc_fw_logging fw_logging;
+ struct ice_aqc_get_clear_fw_log get_clear_fw_log;
+ struct ice_aqc_download_pkg download_pkg;
+ struct ice_aqc_set_mac_lb set_mac_lb;
struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
struct ice_aqc_set_event_mask set_event_mask;
struct ice_aqc_get_link_status get_link_status;
@@ -1275,17 +1667,26 @@
/* error codes */
enum ice_aq_err {
- ICE_AQ_RC_OK = 0, /* success */
+ ICE_AQ_RC_OK = 0, /* Success */
+ ICE_AQ_RC_EPERM = 1, /* Operation not permitted */
+ ICE_AQ_RC_ENOENT = 2, /* No such element */
ICE_AQ_RC_ENOMEM = 9, /* Out of memory */
ICE_AQ_RC_EBUSY = 12, /* Device or resource busy */
- ICE_AQ_RC_EEXIST = 13, /* object already exists */
+ ICE_AQ_RC_EEXIST = 13, /* Object already exists */
ICE_AQ_RC_ENOSPC = 16, /* No space left or allocation failure */
+ ICE_AQ_RC_ENOSYS = 17, /* Function not implemented */
+ ICE_AQ_RC_ENOSEC = 24, /* Missing security manifest */
+ ICE_AQ_RC_EBADSIG = 25, /* Bad RSA signature */
+ ICE_AQ_RC_ESVN = 26, /* SVN number prohibits this package */
+ ICE_AQ_RC_EBADMAN = 27, /* Manifest hash mismatch */
+ ICE_AQ_RC_EBADBUF = 28, /* Buffer hash mismatches manifest */
};
/* Admin Queue command opcodes */
enum ice_adminq_opc {
/* AQ commands */
ice_aqc_opc_get_ver = 0x0001,
+ ice_aqc_opc_driver_ver = 0x0002,
ice_aqc_opc_q_shutdown = 0x0003,
/* resource ownership */
@@ -1325,8 +1726,10 @@
/* transmit scheduler commands */
ice_aqc_opc_get_dflt_topo = 0x0400,
ice_aqc_opc_add_sched_elems = 0x0401,
+ ice_aqc_opc_get_sched_elems = 0x0404,
ice_aqc_opc_suspend_sched_elems = 0x0409,
ice_aqc_opc_resume_sched_elems = 0x040A,
+ ice_aqc_opc_query_port_ets = 0x040E,
ice_aqc_opc_delete_sched_elems = 0x040F,
ice_aqc_opc_query_sched_res = 0x0412,
@@ -1336,9 +1739,24 @@
ice_aqc_opc_restart_an = 0x0605,
ice_aqc_opc_get_link_status = 0x0607,
ice_aqc_opc_set_event_mask = 0x0613,
+ ice_aqc_opc_set_mac_lb = 0x0620,
+ ice_aqc_opc_set_port_id_led = 0x06E9,
/* NVM commands */
ice_aqc_opc_nvm_read = 0x0701,
+ ice_aqc_opc_nvm_checksum = 0x0706,
+
+ /* PF/VF mailbox commands */
+ ice_mbx_opc_send_msg_to_pf = 0x0801,
+ ice_mbx_opc_send_msg_to_vf = 0x0802,
+ /* LLDP commands */
+ ice_aqc_opc_lldp_get_mib = 0x0A00,
+ ice_aqc_opc_lldp_set_mib_change = 0x0A01,
+ ice_aqc_opc_lldp_stop = 0x0A05,
+ ice_aqc_opc_lldp_start = 0x0A06,
+ ice_aqc_opc_get_cee_dcb_cfg = 0x0A07,
+ ice_aqc_opc_lldp_set_local_mib = 0x0A08,
+ ice_aqc_opc_lldp_stop_start_specific_agent = 0x0A09,
/* RSS commands */
ice_aqc_opc_set_rss_key = 0x0B02,
@@ -1346,9 +1764,17 @@
ice_aqc_opc_get_rss_key = 0x0B04,
ice_aqc_opc_get_rss_lut = 0x0B05,
- /* TX queue handling commands/events */
+ /* Tx queue handling commands/events */
ice_aqc_opc_add_txqs = 0x0C30,
ice_aqc_opc_dis_txqs = 0x0C31,
+
+ /* package commands */
+ ice_aqc_opc_download_pkg = 0x0C40,
+ ice_aqc_opc_get_pkg_info_list = 0x0C43,
+
+ /* debug commands */
+ ice_aqc_opc_fw_logging = 0xFF09,
+ ice_aqc_opc_fw_logging_info = 0xFF10,
};
#endif /* _ICE_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 661beea..3a6b395 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -7,16 +7,16 @@
#define ICE_PF_RESET_WAIT_COUNT 200
-#define ICE_NIC_FLX_ENTRY(hw, mdid, idx) \
- wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(ICE_RXDID_FLEX_NIC), \
+#define ICE_PROG_FLEX_ENTRY(hw, rxdid, mdid, idx) \
+ wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(rxdid), \
((ICE_RX_OPC_MDID << \
GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \
GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \
(((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \
GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M))
-#define ICE_NIC_FLX_FLG_ENTRY(hw, flg_0, flg_1, flg_2, flg_3, idx) \
- wr32((hw), GLFLXP_RXDID_FLAGS(ICE_RXDID_FLEX_NIC, idx), \
+#define ICE_PROG_FLG_ENTRY(hw, rxdid, flg_0, flg_1, flg_2, flg_3, idx) \
+ wr32((hw), GLFLXP_RXDID_FLAGS(rxdid, idx), \
(((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \
GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \
(((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \
@@ -31,7 +31,7 @@
* @hw: pointer to the HW structure
*
* This function sets the MAC type of the adapter based on the
- * vendor ID and device ID stored in the hw structure.
+ * vendor ID and device ID stored in the HW structure.
*/
static enum ice_status ice_set_mac_type(struct ice_hw *hw)
{
@@ -43,6 +43,20 @@
}
/**
+ * ice_dev_onetime_setup - Temporary HW/FW workarounds
+ * @hw: pointer to the HW structure
+ *
+ * This function provides temporary workarounds for certain issues
+ * that are expected to be fixed in the HW/FW.
+ */
+void ice_dev_onetime_setup(struct ice_hw *hw)
+{
+#define MBX_PF_VT_PFALLOC 0x00231E80
+ /* set VFs per PF */
+ wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF));
+}
+
+/**
* ice_clear_pf_cfg - Clear PF configuration
* @hw: pointer to the hardware structure
*
@@ -60,7 +74,7 @@
/**
* ice_aq_manage_mac_read - manage MAC address read command
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @buf: a virtual buffer to hold the manage MAC read response
* @buf_size: Size of the virtual buffer
* @cd: pointer to command details structure or NULL
@@ -125,7 +139,7 @@
*
* Returns the various PHY capabilities supported on the Port (0x0600)
*/
-static enum ice_status
+enum ice_status
ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
struct ice_aqc_get_phy_caps_data *pcaps,
struct ice_sq_cd *cd)
@@ -148,8 +162,10 @@
cmd->param0 |= cpu_to_le16(report_mode);
status = ice_aq_send_cmd(pi->hw, &desc, pcaps, pcaps_size, cd);
- if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP)
+ if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP) {
pi->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low);
+ pi->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high);
+ }
return status;
}
@@ -166,6 +182,9 @@
return ICE_MEDIA_UNKNOWN;
hw_link_info = &pi->phy.link_info;
+ if (hw_link_info->phy_type_low && hw_link_info->phy_type_high)
+ /* If more than one media type is selected, report unknown */
+ return ICE_MEDIA_UNKNOWN;
if (hw_link_info->phy_type_low) {
switch (hw_link_info->phy_type_low) {
@@ -179,6 +198,15 @@
case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
case ICE_PHY_TYPE_LOW_40GBASE_SR4:
case ICE_PHY_TYPE_LOW_40GBASE_LR4:
+ case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_SR:
+ case ICE_PHY_TYPE_LOW_50GBASE_FR:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR:
+ case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+ case ICE_PHY_TYPE_LOW_100GBASE_DR:
return ICE_MEDIA_FIBER;
case ICE_PHY_TYPE_LOW_100BASE_TX:
case ICE_PHY_TYPE_LOW_1000BASE_T:
@@ -192,6 +220,11 @@
case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
case ICE_PHY_TYPE_LOW_25GBASE_CR1:
case ICE_PHY_TYPE_LOW_40GBASE_CR4:
+ case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_CP:
+ case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+ case ICE_PHY_TYPE_LOW_100GBASE_CP2:
return ICE_MEDIA_DA;
case ICE_PHY_TYPE_LOW_1000BASE_KX:
case ICE_PHY_TYPE_LOW_2500BASE_KX:
@@ -202,10 +235,18 @@
case ICE_PHY_TYPE_LOW_25GBASE_KR1:
case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
case ICE_PHY_TYPE_LOW_40GBASE_KR4:
+ case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+ case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+ case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+ return ICE_MEDIA_BACKPLANE;
+ }
+ } else {
+ switch (hw_link_info->phy_type_high) {
+ case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
return ICE_MEDIA_BACKPLANE;
}
}
-
return ICE_MEDIA_UNKNOWN;
}
@@ -222,21 +263,23 @@
ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
struct ice_link_status *link, struct ice_sq_cd *cd)
{
- struct ice_link_status *hw_link_info_old, *hw_link_info;
struct ice_aqc_get_link_status_data link_data = { 0 };
struct ice_aqc_get_link_status *resp;
+ struct ice_link_status *li_old, *li;
enum ice_media_type *hw_media_type;
struct ice_fc_info *hw_fc_info;
bool tx_pause, rx_pause;
struct ice_aq_desc desc;
enum ice_status status;
+ struct ice_hw *hw;
u16 cmd_flags;
if (!pi)
return ICE_ERR_PARAM;
- hw_link_info_old = &pi->phy.link_info_old;
+ hw = pi->hw;
+ li_old = &pi->phy.link_info_old;
hw_media_type = &pi->phy.media_type;
- hw_link_info = &pi->phy.link_info;
+ li = &pi->phy.link_info;
hw_fc_info = &pi->fc;
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_status);
@@ -245,24 +288,27 @@
resp->cmd_flags = cpu_to_le16(cmd_flags);
resp->lport_num = pi->lport;
- status = ice_aq_send_cmd(pi->hw, &desc, &link_data, sizeof(link_data),
- cd);
+ status = ice_aq_send_cmd(hw, &desc, &link_data, sizeof(link_data), cd);
if (status)
return status;
/* save off old link status information */
- *hw_link_info_old = *hw_link_info;
+ *li_old = *li;
/* update current link status information */
- hw_link_info->link_speed = le16_to_cpu(link_data.link_speed);
- hw_link_info->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+ li->link_speed = le16_to_cpu(link_data.link_speed);
+ li->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+ li->phy_type_high = le64_to_cpu(link_data.phy_type_high);
*hw_media_type = ice_get_media_type(pi);
- hw_link_info->link_info = link_data.link_info;
- hw_link_info->an_info = link_data.an_info;
- hw_link_info->ext_info = link_data.ext_info;
- hw_link_info->max_frame_size = le16_to_cpu(link_data.max_frame_size);
- hw_link_info->pacing = link_data.cfg & ICE_AQ_CFG_PACING_M;
+ li->link_info = link_data.link_info;
+ li->an_info = link_data.an_info;
+ li->ext_info = link_data.ext_info;
+ li->max_frame_size = le16_to_cpu(link_data.max_frame_size);
+ li->fec_info = link_data.cfg & ICE_AQ_FEC_MASK;
+ li->topo_media_conflict = link_data.topo_media_conflict;
+ li->pacing = link_data.cfg & (ICE_AQ_CFG_PACING_M |
+ ICE_AQ_CFG_PACING_TYPE_M);
/* update fc info */
tx_pause = !!(link_data.an_info & ICE_AQ_LINK_PAUSE_TX);
@@ -276,49 +322,116 @@
else
hw_fc_info->current_mode = ICE_FC_NONE;
- hw_link_info->lse_ena =
- !!(resp->cmd_flags & cpu_to_le16(ICE_AQ_LSE_IS_ENABLED));
+ li->lse_ena = !!(resp->cmd_flags & cpu_to_le16(ICE_AQ_LSE_IS_ENABLED));
+
+ ice_debug(hw, ICE_DBG_LINK, "link_speed = 0x%x\n", li->link_speed);
+ ice_debug(hw, ICE_DBG_LINK, "phy_type_low = 0x%llx\n",
+ (unsigned long long)li->phy_type_low);
+ ice_debug(hw, ICE_DBG_LINK, "phy_type_high = 0x%llx\n",
+ (unsigned long long)li->phy_type_high);
+ ice_debug(hw, ICE_DBG_LINK, "media_type = 0x%x\n", *hw_media_type);
+ ice_debug(hw, ICE_DBG_LINK, "link_info = 0x%x\n", li->link_info);
+ ice_debug(hw, ICE_DBG_LINK, "an_info = 0x%x\n", li->an_info);
+ ice_debug(hw, ICE_DBG_LINK, "ext_info = 0x%x\n", li->ext_info);
+ ice_debug(hw, ICE_DBG_LINK, "lse_ena = 0x%x\n", li->lse_ena);
+ ice_debug(hw, ICE_DBG_LINK, "max_frame = 0x%x\n", li->max_frame_size);
+ ice_debug(hw, ICE_DBG_LINK, "pacing = 0x%x\n", li->pacing);
/* save link status information */
if (link)
- *link = *hw_link_info;
+ *link = *li;
/* flag cleared so calling functions don't call AQ again */
pi->phy.get_link_info = false;
- return status;
+ return 0;
}
/**
- * ice_init_flex_parser - initialize rx flex parser
+ * ice_init_flex_flags
* @hw: pointer to the hardware structure
+ * @prof_id: Rx Descriptor Builder profile ID
*
- * Function to initialize flex descriptors
+ * Function to initialize Rx flex flags
*/
-static void ice_init_flex_parser(struct ice_hw *hw)
+static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id)
{
u8 idx = 0;
- ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_LOW, 0);
- ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_HIGH, 1);
- ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_LOWER, 2);
- ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_HIGH, 3);
- ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_FRG, ICE_RXFLG_UDP_GRE,
- ICE_RXFLG_PKT_DSI, ICE_RXFLG_FIN, idx++);
- ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_SYN, ICE_RXFLG_RST,
- ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++);
- ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI,
- ICE_RXFLG_EVLAN_x8100, ICE_RXFLG_EVLAN_x9100,
- idx++);
- ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_VLAN_x8100, ICE_RXFLG_TNL_VLAN,
- ICE_RXFLG_TNL_MAC, ICE_RXFLG_TNL0, idx++);
- ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2,
- ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx);
+ /* Flex-flag fields (0-2) are programmed with FLG64 bits with layout:
+ * flexiflags0[5:0] - TCP flags, is_packet_fragmented, is_packet_UDP_GRE
+ * flexiflags1[3:0] - Not used for flag programming
+ * flexiflags2[7:0] - Tunnel and VLAN types
+ * 2 invalid fields in last index
+ */
+ switch (prof_id) {
+ /* Rx flex flags are currently programmed for the NIC profiles only.
+ * Different flag bit programming configurations can be added per
+ * profile as needed.
+ */
+ case ICE_RXDID_FLEX_NIC:
+ case ICE_RXDID_FLEX_NIC_2:
+ ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_FRG,
+ ICE_FLG_UDP_GRE, ICE_FLG_PKT_DSI,
+ ICE_FLG_FIN, idx++);
+ /* flex flag 1 is not used for flexi-flag programming, skipping
+ * these four FLG64 bits.
+ */
+ ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_SYN, ICE_FLG_RST,
+ ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx++);
+ ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_DSI,
+ ICE_FLG_PKT_DSI, ICE_FLG_EVLAN_x8100,
+ ICE_FLG_EVLAN_x9100, idx++);
+ ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_VLAN_x8100,
+ ICE_FLG_TNL_VLAN, ICE_FLG_TNL_MAC,
+ ICE_FLG_TNL0, idx++);
+ ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_TNL1, ICE_FLG_TNL2,
+ ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx);
+ break;
+
+ default:
+ ice_debug(hw, ICE_DBG_INIT,
+ "Flag programming for profile ID %d not supported\n",
+ prof_id);
+ }
+}
+
+/**
+ * ice_init_flex_flds
+ * @hw: pointer to the hardware structure
+ * @prof_id: Rx Descriptor Builder profile ID
+ *
+ * Function to initialize flex descriptors
+ */
+static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id)
+{
+ enum ice_flex_rx_mdid mdid;
+
+ switch (prof_id) {
+ case ICE_RXDID_FLEX_NIC:
+ case ICE_RXDID_FLEX_NIC_2:
+ ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_LOW, 0);
+ ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_HIGH, 1);
+ ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_FLOW_ID_LOWER, 2);
+
+ mdid = (prof_id == ICE_RXDID_FLEX_NIC_2) ?
+ ICE_RX_MDID_SRC_VSI : ICE_RX_MDID_FLOW_ID_HIGH;
+
+ ICE_PROG_FLEX_ENTRY(hw, prof_id, mdid, 3);
+
+ ice_init_flex_flags(hw, prof_id);
+ break;
+
+ default:
+ ice_debug(hw, ICE_DBG_INIT,
+ "Field init for profile ID %d not supported\n",
+ prof_id);
+ }
}
/**
* ice_init_fltr_mgmt_struct - initializes filter management list and locks
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*/
static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
{
@@ -333,49 +446,311 @@
INIT_LIST_HEAD(&sw->vsi_list_map_head);
- mutex_init(&sw->mac_list_lock);
- INIT_LIST_HEAD(&sw->mac_list_head);
-
- mutex_init(&sw->vlan_list_lock);
- INIT_LIST_HEAD(&sw->vlan_list_head);
-
- mutex_init(&sw->eth_m_list_lock);
- INIT_LIST_HEAD(&sw->eth_m_list_head);
-
- mutex_init(&sw->promisc_list_lock);
- INIT_LIST_HEAD(&sw->promisc_list_head);
-
- mutex_init(&sw->mac_vlan_list_lock);
- INIT_LIST_HEAD(&sw->mac_vlan_list_head);
-
- return 0;
+ return ice_init_def_sw_recp(hw);
}
/**
* ice_cleanup_fltr_mgmt_struct - cleanup filter management list and locks
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*/
static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw)
{
struct ice_switch_info *sw = hw->switch_info;
struct ice_vsi_list_map_info *v_pos_map;
struct ice_vsi_list_map_info *v_tmp_map;
+ struct ice_sw_recipe *recps;
+ u8 i;
list_for_each_entry_safe(v_pos_map, v_tmp_map, &sw->vsi_list_map_head,
list_entry) {
list_del(&v_pos_map->list_entry);
devm_kfree(ice_hw_to_dev(hw), v_pos_map);
}
+ recps = hw->switch_info->recp_list;
+ for (i = 0; i < ICE_SW_LKUP_LAST; i++) {
+ struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry;
- mutex_destroy(&sw->mac_list_lock);
- mutex_destroy(&sw->vlan_list_lock);
- mutex_destroy(&sw->eth_m_list_lock);
- mutex_destroy(&sw->promisc_list_lock);
- mutex_destroy(&sw->mac_vlan_list_lock);
-
+ recps[i].root_rid = i;
+ mutex_destroy(&recps[i].filt_rule_lock);
+ list_for_each_entry_safe(lst_itr, tmp_entry,
+ &recps[i].filt_rules, list_entry) {
+ list_del(&lst_itr->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), lst_itr);
+ }
+ }
+ ice_rm_all_sw_replay_rule_info(hw);
+ devm_kfree(ice_hw_to_dev(hw), sw->recp_list);
devm_kfree(ice_hw_to_dev(hw), sw);
}
+#define ICE_FW_LOG_DESC_SIZE(n) (sizeof(struct ice_aqc_fw_logging_data) + \
+ (((n) - 1) * sizeof(((struct ice_aqc_fw_logging_data *)0)->entry)))
+#define ICE_FW_LOG_DESC_SIZE_MAX \
+ ICE_FW_LOG_DESC_SIZE(ICE_AQC_FW_LOG_ID_MAX)
+
+/**
+ * ice_get_fw_log_cfg - get FW logging configuration
+ * @hw: pointer to the HW struct
+ */
+static enum ice_status ice_get_fw_log_cfg(struct ice_hw *hw)
+{
+ struct ice_aqc_fw_logging_data *config;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+ u16 size;
+
+ size = ICE_FW_LOG_DESC_SIZE_MAX;
+ config = devm_kzalloc(ice_hw_to_dev(hw), size, GFP_KERNEL);
+ if (!config)
+ return ICE_ERR_NO_MEMORY;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info);
+
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_BUF);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ status = ice_aq_send_cmd(hw, &desc, config, size, NULL);
+ if (!status) {
+ u16 i;
+
+ /* Save FW logging information into the HW structure */
+ for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
+ u16 v, m, flgs;
+
+ v = le16_to_cpu(config->entry[i]);
+ m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S;
+ flgs = (v & ICE_AQC_FW_LOG_EN_M) >> ICE_AQC_FW_LOG_EN_S;
+
+ if (m < ICE_AQC_FW_LOG_ID_MAX)
+ hw->fw_log.evnts[m].cur = flgs;
+ }
+ }
+
+ devm_kfree(ice_hw_to_dev(hw), config);
+
+ return status;
+}
+
+/**
+ * ice_cfg_fw_log - configure FW logging
+ * @hw: pointer to the HW struct
+ * @enable: enable certain FW logging events if true, disable all if false
+ *
+ * This function enables/disables the FW logging via Rx CQ events and a UART
+ * port based on predetermined configurations. FW logging via the Rx CQ can be
+ * enabled/disabled for individual PF's. However, FW logging via the UART can
+ * only be enabled/disabled for all PFs on the same device.
+ *
+ * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in
+ * hw->fw_log need to be set accordingly, e.g. based on user-provided input,
+ * before initializing the device.
+ *
+ * When re/configuring FW logging, callers need to update the "cfg" elements of
+ * the hw->fw_log.evnts array with the desired logging event configurations for
+ * modules of interest. When disabling FW logging completely, the callers can
+ * just pass false in the "enable" parameter. On completion, the function will
+ * update the "cur" element of the hw->fw_log.evnts array with the resulting
+ * logging event configurations of the modules that are being re/configured. FW
+ * logging modules that are not part of a reconfiguration operation retain their
+ * previous states.
+ *
+ * Before resetting the device, it is recommended that the driver disables FW
+ * logging before shutting down the control queue. When disabling FW logging
+ * ("enable" = false), the latest configurations of FW logging events stored in
+ * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after
+ * a device reset.
+ *
+ * When enabling FW logging to emit log messages via the Rx CQ during the
+ * device's initialization phase, a mechanism alternative to interrupt handlers
+ * needs to be used to extract FW log messages from the Rx CQ periodically and
+ * to prevent the Rx CQ from being full and stalling other types of control
+ * messages from FW to SW. Interrupts are typically disabled during the device's
+ * initialization phase.
+ */
+static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable)
+{
+ struct ice_aqc_fw_logging_data *data = NULL;
+ struct ice_aqc_fw_logging *cmd;
+ enum ice_status status = 0;
+ u16 i, chgs = 0, len = 0;
+ struct ice_aq_desc desc;
+ u8 actv_evnts = 0;
+ void *buf = NULL;
+
+ if (!hw->fw_log.cq_en && !hw->fw_log.uart_en)
+ return 0;
+
+ /* Disable FW logging only when the control queue is still responsive */
+ if (!enable &&
+ (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq)))
+ return 0;
+
+ /* Get current FW log settings */
+ status = ice_get_fw_log_cfg(hw);
+ if (status)
+ return status;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging);
+ cmd = &desc.params.fw_logging;
+
+ /* Indicate which controls are valid */
+ if (hw->fw_log.cq_en)
+ cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID;
+
+ if (hw->fw_log.uart_en)
+ cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID;
+
+ if (enable) {
+ /* Fill in an array of entries with FW logging modules and
+ * logging events being reconfigured.
+ */
+ for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
+ u16 val;
+
+ /* Keep track of enabled event types */
+ actv_evnts |= hw->fw_log.evnts[i].cfg;
+
+ if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur)
+ continue;
+
+ if (!data) {
+ data = devm_kzalloc(ice_hw_to_dev(hw),
+ ICE_FW_LOG_DESC_SIZE_MAX,
+ GFP_KERNEL);
+ if (!data)
+ return ICE_ERR_NO_MEMORY;
+ }
+
+ val = i << ICE_AQC_FW_LOG_ID_S;
+ val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S;
+ data->entry[chgs++] = cpu_to_le16(val);
+ }
+
+ /* Only enable FW logging if at least one module is specified.
+ * If FW logging is currently enabled but all modules are not
+ * enabled to emit log messages, disable FW logging altogether.
+ */
+ if (actv_evnts) {
+ /* Leave if there is effectively no change */
+ if (!chgs)
+ goto out;
+
+ if (hw->fw_log.cq_en)
+ cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN;
+
+ if (hw->fw_log.uart_en)
+ cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN;
+
+ buf = data;
+ len = ICE_FW_LOG_DESC_SIZE(chgs);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ }
+ }
+
+ status = ice_aq_send_cmd(hw, &desc, buf, len, NULL);
+ if (!status) {
+ /* Update the current configuration to reflect events enabled.
+ * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW
+ * logging mode is enabled for the device. They do not reflect
+ * actual modules being enabled to emit log messages. So, their
+ * values remain unchanged even when all modules are disabled.
+ */
+ u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX;
+
+ hw->fw_log.actv_evnts = actv_evnts;
+ for (i = 0; i < cnt; i++) {
+ u16 v, m;
+
+ if (!enable) {
+ /* When disabling all FW logging events as part
+ * of device's de-initialization, the original
+ * configurations are retained, and can be used
+ * to reconfigure FW logging later if the device
+ * is re-initialized.
+ */
+ hw->fw_log.evnts[i].cur = 0;
+ continue;
+ }
+
+ v = le16_to_cpu(data->entry[i]);
+ m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S;
+ hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg;
+ }
+ }
+
+out:
+ if (data)
+ devm_kfree(ice_hw_to_dev(hw), data);
+
+ return status;
+}
+
+/**
+ * ice_output_fw_log
+ * @hw: pointer to the HW struct
+ * @desc: pointer to the AQ message descriptor
+ * @buf: pointer to the buffer accompanying the AQ message
+ *
+ * Formats a FW Log message and outputs it via the standard driver logs.
+ */
+void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf)
+{
+ ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg Start ]\n");
+ ice_debug_array(hw, ICE_DBG_FW_LOG, 16, 1, (u8 *)buf,
+ le16_to_cpu(desc->datalen));
+ ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg End ]\n");
+}
+
+/**
+ * ice_get_itr_intrl_gran - determine int/intrl granularity
+ * @hw: pointer to the HW struct
+ *
+ * Determines the ITR/intrl granularities based on the maximum aggregate
+ * bandwidth according to the device's configuration during power-on.
+ */
+static void ice_get_itr_intrl_gran(struct ice_hw *hw)
+{
+ u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) &
+ GL_PWR_MODE_CTL_CAR_MAX_BW_M) >>
+ GL_PWR_MODE_CTL_CAR_MAX_BW_S;
+
+ switch (max_agg_bw) {
+ case ICE_MAX_AGG_BW_200G:
+ case ICE_MAX_AGG_BW_100G:
+ case ICE_MAX_AGG_BW_50G:
+ hw->itr_gran = ICE_ITR_GRAN_ABOVE_25;
+ hw->intrl_gran = ICE_INTRL_GRAN_ABOVE_25;
+ break;
+ case ICE_MAX_AGG_BW_25G:
+ hw->itr_gran = ICE_ITR_GRAN_MAX_25;
+ hw->intrl_gran = ICE_INTRL_GRAN_MAX_25;
+ break;
+ }
+}
+
+/**
+ * ice_get_nvm_version - get cached NVM version data
+ * @hw: pointer to the hardware structure
+ * @oem_ver: 8 bit NVM version
+ * @oem_build: 16 bit NVM build number
+ * @oem_patch: 8 NVM patch number
+ * @ver_hi: high 16 bits of the NVM version
+ * @ver_lo: low 16 bits of the NVM version
+ */
+void
+ice_get_nvm_version(struct ice_hw *hw, u8 *oem_ver, u16 *oem_build,
+ u8 *oem_patch, u8 *ver_hi, u8 *ver_lo)
+{
+ struct ice_nvm_info *nvm = &hw->nvm;
+
+ *oem_ver = (u8)((nvm->oem_ver & ICE_OEM_VER_MASK) >> ICE_OEM_VER_SHIFT);
+ *oem_patch = (u8)(nvm->oem_ver & ICE_OEM_VER_PATCH_MASK);
+ *oem_build = (u16)((nvm->oem_ver & ICE_OEM_VER_BUILD_MASK) >>
+ ICE_OEM_VER_BUILD_SHIFT);
+ *ver_hi = (nvm->ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT;
+ *ver_lo = (nvm->ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT;
+}
+
/**
* ice_init_hw - main hardware initialization routine
* @hw: pointer to the hardware structure
@@ -400,16 +775,17 @@
if (status)
return status;
- /* set these values to minimum allowed */
- hw->itr_gran_200 = ICE_ITR_GRAN_MIN_200;
- hw->itr_gran_100 = ICE_ITR_GRAN_MIN_100;
- hw->itr_gran_50 = ICE_ITR_GRAN_MIN_50;
- hw->itr_gran_25 = ICE_ITR_GRAN_MIN_25;
+ ice_get_itr_intrl_gran(hw);
- status = ice_init_all_ctrlq(hw);
+ status = ice_create_all_ctrlq(hw);
if (status)
goto err_unroll_cqinit;
+ /* Enable FW logging. Not fatal if this fails. */
+ status = ice_cfg_fw_log(hw, true);
+ if (status)
+ ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n");
+
status = ice_clear_pf_cfg(hw);
if (status)
goto err_unroll_cqinit;
@@ -431,7 +807,7 @@
goto err_unroll_cqinit;
}
- /* set the back pointer to hw */
+ /* set the back pointer to HW */
hw->port_info->hw = hw;
/* Initialize port_info struct with switch configuration data */
@@ -441,7 +817,7 @@
hw->evb_veb = true;
- /* Query the allocated resources for tx scheduler */
+ /* Query the allocated resources for Tx scheduler */
status = ice_sched_query_res_alloc(hw);
if (status) {
ice_debug(hw, ICE_DBG_SCHED,
@@ -472,10 +848,20 @@
if (status)
goto err_unroll_sched;
+ /* need a valid SW entry point to build a Tx tree */
+ if (!hw->sw_entry_point_layer) {
+ ice_debug(hw, ICE_DBG_SCHED, "invalid sw entry point\n");
+ status = ICE_ERR_CFG;
+ goto err_unroll_sched;
+ }
+ INIT_LIST_HEAD(&hw->agg_list);
+
status = ice_init_fltr_mgmt_struct(hw);
if (status)
goto err_unroll_sched;
+ ice_dev_onetime_setup(hw);
+
/* Get MAC information */
/* A single port can report up to two (LAN and WoL) addresses */
mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
@@ -494,8 +880,11 @@
if (status)
goto err_unroll_fltr_mgmt_struct;
- ice_init_flex_parser(hw);
-
+ ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC);
+ ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2);
+ status = ice_init_hw_tbls(hw);
+ if (status)
+ goto err_unroll_fltr_mgmt_struct;
return 0;
err_unroll_fltr_mgmt_struct:
@@ -505,25 +894,38 @@
err_unroll_alloc:
devm_kfree(ice_hw_to_dev(hw), hw->port_info);
err_unroll_cqinit:
- ice_shutdown_all_ctrlq(hw);
+ ice_destroy_all_ctrlq(hw);
return status;
}
/**
* ice_deinit_hw - unroll initialization operations done by ice_init_hw
* @hw: pointer to the hardware structure
+ *
+ * This should be called only during nominal operation, not as a result of
+ * ice_init_hw() failing since ice_init_hw() will take care of unrolling
+ * applicable initializations if it fails for any reason.
*/
void ice_deinit_hw(struct ice_hw *hw)
{
+ ice_cleanup_fltr_mgmt_struct(hw);
+
ice_sched_cleanup_all(hw);
- ice_shutdown_all_ctrlq(hw);
+ ice_sched_clear_agg(hw);
+ ice_free_seg(hw);
+ ice_free_hw_tbls(hw);
if (hw->port_info) {
devm_kfree(ice_hw_to_dev(hw), hw->port_info);
hw->port_info = NULL;
}
- ice_cleanup_fltr_mgmt_struct(hw);
+ /* Attempt to disable FW logging before shutting down control queues */
+ ice_cfg_fw_log(hw, false);
+ ice_destroy_all_ctrlq(hw);
+
+ /* Clear VSI contexts if not already cleared */
+ ice_clear_all_vsi_ctx(hw);
}
/**
@@ -652,6 +1054,8 @@
ice_debug(hw, ICE_DBG_INIT, "GlobalR requested\n");
val = GLGEN_RTRIG_GLOBR_M;
break;
+ default:
+ return ICE_ERR_PARAM;
}
val |= rd32(hw, GLGEN_RTRIG);
@@ -666,9 +1070,9 @@
* ice_copy_rxq_ctx_to_hw
* @hw: pointer to the hardware structure
* @ice_rxq_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
*
- * Copies rxq context from dense structure to hw register space
+ * Copies rxq context from dense structure to HW register space
*/
static enum ice_status
ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index)
@@ -681,7 +1085,7 @@
if (rxq_index > QRX_CTRL_MAX_INDEX)
return ICE_ERR_PARAM;
- /* Copy each dword separately to hw */
+ /* Copy each dword separately to HW */
for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) {
wr32(hw, QRX_CONTEXT(i, rxq_index),
*((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
@@ -715,6 +1119,7 @@
ICE_CTX_STORE(ice_rlan_ctx, tphdata_ena, 1, 195),
ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196),
ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198),
+ ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201),
{ 0 }
};
@@ -722,10 +1127,11 @@
* ice_write_rxq_ctx
* @hw: pointer to the hardware structure
* @rlan_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
*
* Converts rxq context from sparse to dense structure and then writes
- * it to hw register space
+ * it to HW register space and enables the hardware to prefetch descriptors
+ * instead of only fetching them on demand
*/
enum ice_status
ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
@@ -733,6 +1139,11 @@
{
u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 };
+ if (!rlan_ctx)
+ return ICE_ERR_BAD_PTR;
+
+ rlan_ctx->prefena = 1;
+
ice_set_ctx((u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info);
return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index);
}
@@ -748,6 +1159,7 @@
ICE_CTX_STORE(ice_tlan_ctx, vmvf_type, 2, 78),
ICE_CTX_STORE(ice_tlan_ctx, src_vsi, 10, 80),
ICE_CTX_STORE(ice_tlan_ctx, tsyn_ena, 1, 90),
+ ICE_CTX_STORE(ice_tlan_ctx, internal_usage_flag, 1, 91),
ICE_CTX_STORE(ice_tlan_ctx, alt_vlan, 1, 92),
ICE_CTX_STORE(ice_tlan_ctx, cpuid, 8, 93),
ICE_CTX_STORE(ice_tlan_ctx, wb_mode, 1, 101),
@@ -766,7 +1178,7 @@
ICE_CTX_STORE(ice_tlan_ctx, drop_ena, 1, 165),
ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx, 2, 166),
ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx, 3, 168),
- ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 110, 171),
+ ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 122, 171),
{ 0 }
};
@@ -780,8 +1192,9 @@
*
* Dumps debug log about control command with descriptor contents.
*/
-void ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc,
- void *buf, u16 buf_len)
+void
+ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc, void *buf,
+ u16 buf_len)
{
struct ice_aq_desc *cq_desc = (struct ice_aq_desc *)desc;
u16 len;
@@ -821,9 +1234,15 @@
/* FW Admin Queue command wrappers */
+/* Software lock/mutex that is meant to be held while the Global Config Lock
+ * in firmware is acquired by the software to prevent most (but not all) types
+ * of AQ commands from being sent to FW
+ */
+DEFINE_MUTEX(ice_global_cfg_lock_sw);
+
/**
* ice_aq_send_cmd - send FW Admin Queue command to FW Admin Queue
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @desc: descriptor describing the command
* @buf: buffer to use for indirect commands (NULL for direct commands)
* @buf_size: size of buffer for indirect commands (0 for direct commands)
@@ -835,12 +1254,43 @@
ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
u16 buf_size, struct ice_sq_cd *cd)
{
- return ice_sq_send_cmd(hw, &hw->adminq, desc, buf, buf_size, cd);
+ struct ice_aqc_req_res *cmd = &desc->params.res_owner;
+ bool lock_acquired = false;
+ enum ice_status status;
+
+ /* When a package download is in process (i.e. when the firmware's
+ * Global Configuration Lock resource is held), only the Download
+ * Package, Get Version, Get Package Info List and Release Resource
+ * (with resource ID set to Global Config Lock) AdminQ commands are
+ * allowed; all others must block until the package download completes
+ * and the Global Config Lock is released. See also
+ * ice_acquire_global_cfg_lock().
+ */
+ switch (le16_to_cpu(desc->opcode)) {
+ case ice_aqc_opc_download_pkg:
+ case ice_aqc_opc_get_pkg_info_list:
+ case ice_aqc_opc_get_ver:
+ break;
+ case ice_aqc_opc_release_res:
+ if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK)
+ break;
+ /* fall-through */
+ default:
+ mutex_lock(&ice_global_cfg_lock_sw);
+ lock_acquired = true;
+ break;
+ }
+
+ status = ice_sq_send_cmd(hw, &hw->adminq, desc, buf, buf_size, cd);
+ if (lock_acquired)
+ mutex_unlock(&ice_global_cfg_lock_sw);
+
+ return status;
}
/**
* ice_aq_get_fw_ver
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @cd: pointer to command details structure or NULL
*
* Get the firmware version (0x0001) from the admin queue commands
@@ -873,8 +1323,45 @@
}
/**
+ * ice_aq_send_driver_ver
+ * @hw: pointer to the HW struct
+ * @dv: driver's major, minor version
+ * @cd: pointer to command details structure or NULL
+ *
+ * Send the driver version (0x0002) to the firmware
+ */
+enum ice_status
+ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_driver_ver *cmd;
+ struct ice_aq_desc desc;
+ u16 len;
+
+ cmd = &desc.params.driver_ver;
+
+ if (!dv)
+ return ICE_ERR_PARAM;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_ver);
+
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ cmd->major_ver = dv->major_ver;
+ cmd->minor_ver = dv->minor_ver;
+ cmd->build_ver = dv->build_ver;
+ cmd->subbuild_ver = dv->subbuild_ver;
+
+ len = 0;
+ while (len < sizeof(dv->driver_string) &&
+ isascii(dv->driver_string[len]) && dv->driver_string[len])
+ len++;
+
+ return ice_aq_send_cmd(hw, &desc, dv->driver_string, len, cd);
+}
+
+/**
* ice_aq_q_shutdown
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @unloading: is the driver unloading itself
*
* Tell the Firmware that we're shutting down the AdminQ and whether
@@ -890,21 +1377,36 @@
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown);
if (unloading)
- cmd->driver_unloading = cpu_to_le32(ICE_AQC_DRIVER_UNLOADING);
+ cmd->driver_unloading = ICE_AQC_DRIVER_UNLOADING;
return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
}
/**
* ice_aq_req_res
- * @hw: pointer to the hw struct
- * @res: resource id
+ * @hw: pointer to the HW struct
+ * @res: resource ID
* @access: access type
* @sdp_number: resource number
* @timeout: the maximum time in ms that the driver may hold the resource
* @cd: pointer to command details structure or NULL
*
- * requests common resource using the admin queue commands (0x0008)
+ * Requests common resource using the admin queue commands (0x0008).
+ * When attempting to acquire the Global Config Lock, the driver can
+ * learn of three states:
+ * 1) ICE_SUCCESS - acquired lock, and can perform download package
+ * 2) ICE_ERR_AQ_ERROR - did not get lock, driver should fail to load
+ * 3) ICE_ERR_AQ_NO_WORK - did not get lock, but another driver has
+ * successfully downloaded the package; the driver does
+ * not have to download the package and can continue
+ * loading
+ *
+ * Note that if the caller is in an acquire lock, perform action, release lock
+ * phase of operation, it is possible that the FW may detect a timeout and issue
+ * a CORER. In this case, the driver will receive a CORER interrupt and will
+ * have to determine its cause. The calling thread that is handling this flow
+ * will likely get an error propagated back to it indicating the Download
+ * Package, Update Package or the Release Resource AQ commands timed out.
*/
static enum ice_status
ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
@@ -922,13 +1424,43 @@
cmd_resp->res_id = cpu_to_le16(res);
cmd_resp->access_type = cpu_to_le16(access);
cmd_resp->res_number = cpu_to_le32(sdp_number);
+ cmd_resp->timeout = cpu_to_le32(*timeout);
+ *timeout = 0;
status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+
/* The completion specifies the maximum time in ms that the driver
* may hold the resource in the Timeout field.
- * If the resource is held by someone else, the command completes with
- * busy return value and the timeout field indicates the maximum time
- * the current owner of the resource has to free it.
+ */
+
+ /* Global config lock response utilizes an additional status field.
+ *
+ * If the Global config lock resource is held by some other driver, the
+ * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field
+ * and the timeout field indicates the maximum time the current owner
+ * of the resource has to free it.
+ */
+ if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) {
+ if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) {
+ *timeout = le32_to_cpu(cmd_resp->timeout);
+ return 0;
+ } else if (le16_to_cpu(cmd_resp->status) ==
+ ICE_AQ_RES_GLBL_IN_PROG) {
+ *timeout = le32_to_cpu(cmd_resp->timeout);
+ return ICE_ERR_AQ_ERROR;
+ } else if (le16_to_cpu(cmd_resp->status) ==
+ ICE_AQ_RES_GLBL_DONE) {
+ return ICE_ERR_AQ_NO_WORK;
+ }
+
+ /* invalid FW response, force a timeout immediately */
+ *timeout = 0;
+ return ICE_ERR_AQ_ERROR;
+ }
+
+ /* If the resource is held by some other driver, the command completes
+ * with a busy return value and the timeout field indicates the maximum
+ * time the current owner of the resource has to free it.
*/
if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY)
*timeout = le32_to_cpu(cmd_resp->timeout);
@@ -938,8 +1470,8 @@
/**
* ice_aq_release_res
- * @hw: pointer to the hw struct
- * @res: resource id
+ * @hw: pointer to the HW struct
+ * @res: resource ID
* @sdp_number: resource number
* @cd: pointer to command details structure or NULL
*
@@ -965,32 +1497,30 @@
/**
* ice_acquire_res
* @hw: pointer to the HW structure
- * @res: resource id
+ * @res: resource ID
* @access: access type (read or write)
+ * @timeout: timeout in milliseconds
*
* This function will attempt to acquire the ownership of a resource.
*/
enum ice_status
ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
- enum ice_aq_res_access_type access)
+ enum ice_aq_res_access_type access, u32 timeout)
{
#define ICE_RES_POLLING_DELAY_MS 10
u32 delay = ICE_RES_POLLING_DELAY_MS;
+ u32 time_left = timeout;
enum ice_status status;
- u32 time_left = 0;
- u32 timeout;
status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL);
- /* An admin queue return code of ICE_AQ_RC_EEXIST means that another
- * driver has previously acquired the resource and performed any
- * necessary updates; in this case the caller does not obtain the
- * resource and has no further work to do.
+ /* A return code of ICE_ERR_AQ_NO_WORK means that another driver has
+ * previously acquired the resource and performed any necessary updates;
+ * in this case the caller does not obtain the resource and has no
+ * further work to do.
*/
- if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) {
- status = ICE_ERR_AQ_NO_WORK;
+ if (status == ICE_ERR_AQ_NO_WORK)
goto ice_acquire_res_exit;
- }
if (status)
ice_debug(hw, ICE_DBG_RES,
@@ -1003,11 +1533,9 @@
timeout = (timeout > delay) ? timeout - delay : 0;
status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL);
- if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) {
+ if (status == ICE_ERR_AQ_NO_WORK)
/* lock free, but no work to do */
- status = ICE_ERR_AQ_NO_WORK;
break;
- }
if (!status)
/* lock acquired */
@@ -1031,7 +1559,7 @@
/**
* ice_release_res
* @hw: pointer to the HW structure
- * @res: resource id
+ * @res: resource ID
*
* This function will release a resource using the proper Admin Command.
*/
@@ -1043,7 +1571,7 @@
status = ice_aq_release_res(hw, res, 0, NULL);
/* there are some rare cases when trying to release the resource
- * results in an admin Q timeout, so handle them correctly
+ * results in an admin queue timeout, so handle them correctly
*/
while ((status == ICE_ERR_AQ_TIMEOUT) &&
(total_delay < hw->adminq.sq_cmd_timeout)) {
@@ -1054,8 +1582,31 @@
}
/**
+ * ice_get_num_per_func - determine number of resources per PF
+ * @hw: pointer to the HW structure
+ * @max: value to be evenly split between each PF
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of resources
+ * per PF based on the max value passed in.
+ */
+static u32 ice_get_num_per_func(struct ice_hw *hw, u32 max)
+{
+ u8 funcs;
+
+#define ICE_CAPS_VALID_FUNCS_M 0xFF
+ funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+ ICE_CAPS_VALID_FUNCS_M);
+
+ if (!funcs)
+ return 0;
+
+ return max / funcs;
+}
+
+/**
* ice_parse_caps - parse function/device capabilities
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @buf: pointer to a buffer containing function/device capability records
* @cap_count: number of capability records in the list
* @opc: type of capabilities list to parse
@@ -1070,6 +1621,7 @@
struct ice_hw_func_caps *func_p = NULL;
struct ice_hw_dev_caps *dev_p = NULL;
struct ice_hw_common_caps *caps;
+ char const *prefix;
u32 i;
if (!buf)
@@ -1080,9 +1632,11 @@
if (opc == ice_aqc_opc_list_dev_caps) {
dev_p = &hw->dev_caps;
caps = &dev_p->common_cap;
+ prefix = "dev cap";
} else if (opc == ice_aqc_opc_list_func_caps) {
func_p = &hw->func_caps;
caps = &func_p->common_cap;
+ prefix = "func cap";
} else {
ice_debug(hw, ICE_DBG_INIT, "wrong opcode\n");
return;
@@ -1095,72 +1649,114 @@
u16 cap = le16_to_cpu(cap_resp->cap);
switch (cap) {
+ case ICE_AQC_CAPS_VALID_FUNCTIONS:
+ caps->valid_functions = number;
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: valid_functions (bitmap) = %d\n", prefix,
+ caps->valid_functions);
+ break;
+ case ICE_AQC_CAPS_SRIOV:
+ caps->sr_iov_1_1 = (number == 1);
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: sr_iov_1_1 = %d\n", prefix,
+ caps->sr_iov_1_1);
+ break;
+ case ICE_AQC_CAPS_VF:
+ if (dev_p) {
+ dev_p->num_vfs_exposed = number;
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: num_vfs_exposed = %d\n", prefix,
+ dev_p->num_vfs_exposed);
+ } else if (func_p) {
+ func_p->num_allocd_vfs = number;
+ func_p->vf_base_id = logical_id;
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: num_allocd_vfs = %d\n", prefix,
+ func_p->num_allocd_vfs);
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: vf_base_id = %d\n", prefix,
+ func_p->vf_base_id);
+ }
+ break;
case ICE_AQC_CAPS_VSI:
if (dev_p) {
dev_p->num_vsi_allocd_to_host = number;
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Dev.VSI cnt = %d\n",
+ "%s: num_vsi_allocd_to_host = %d\n",
+ prefix,
dev_p->num_vsi_allocd_to_host);
} else if (func_p) {
- func_p->guaranteed_num_vsi = number;
+ func_p->guar_num_vsi =
+ ice_get_num_per_func(hw, ICE_MAX_VSI);
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Func.VSI cnt = %d\n",
- func_p->guaranteed_num_vsi);
+ "%s: guar_num_vsi (fw) = %d\n",
+ prefix, number);
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: guar_num_vsi = %d\n",
+ prefix, func_p->guar_num_vsi);
}
break;
+ case ICE_AQC_CAPS_DCB:
+ caps->dcb = (number == 1);
+ caps->active_tc_bitmap = logical_id;
+ caps->maxtc = phys_id;
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: dcb = %d\n", prefix, caps->dcb);
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: active_tc_bitmap = %d\n", prefix,
+ caps->active_tc_bitmap);
+ ice_debug(hw, ICE_DBG_INIT,
+ "%s: maxtc = %d\n", prefix, caps->maxtc);
+ break;
case ICE_AQC_CAPS_RSS:
caps->rss_table_size = number;
caps->rss_table_entry_width = logical_id;
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: RSS table size = %d\n",
+ "%s: rss_table_size = %d\n", prefix,
caps->rss_table_size);
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: RSS table width = %d\n",
+ "%s: rss_table_entry_width = %d\n", prefix,
caps->rss_table_entry_width);
break;
case ICE_AQC_CAPS_RXQS:
caps->num_rxq = number;
caps->rxq_first_id = phys_id;
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Num Rx Qs = %d\n", caps->num_rxq);
+ "%s: num_rxq = %d\n", prefix,
+ caps->num_rxq);
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Rx first queue ID = %d\n",
+ "%s: rxq_first_id = %d\n", prefix,
caps->rxq_first_id);
break;
case ICE_AQC_CAPS_TXQS:
caps->num_txq = number;
caps->txq_first_id = phys_id;
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Num Tx Qs = %d\n", caps->num_txq);
+ "%s: num_txq = %d\n", prefix,
+ caps->num_txq);
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Tx first queue ID = %d\n",
+ "%s: txq_first_id = %d\n", prefix,
caps->txq_first_id);
break;
case ICE_AQC_CAPS_MSIX:
caps->num_msix_vectors = number;
caps->msix_vector_first_id = phys_id;
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: MSIX vector count = %d\n",
+ "%s: num_msix_vectors = %d\n", prefix,
caps->num_msix_vectors);
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: MSIX first vector index = %d\n",
+ "%s: msix_vector_first_id = %d\n", prefix,
caps->msix_vector_first_id);
break;
case ICE_AQC_CAPS_MAX_MTU:
caps->max_mtu = number;
- if (dev_p)
- ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Dev.MaxMTU = %d\n",
- caps->max_mtu);
- else if (func_p)
- ice_debug(hw, ICE_DBG_INIT,
- "HW caps: func.MaxMTU = %d\n",
- caps->max_mtu);
+ ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
+ prefix, caps->max_mtu);
break;
default:
ice_debug(hw, ICE_DBG_INIT,
- "HW caps: Unknown capability[%d]: 0x%x\n", i,
- cap);
+ "%s: unknown capability[%d]: 0x%x\n", prefix,
+ i, cap);
break;
}
}
@@ -1168,10 +1764,10 @@
/**
* ice_aq_discover_caps - query function/device capabilities
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @buf: a virtual buffer to hold the capabilities
* @buf_size: Size of the virtual buffer
- * @data_size: Size of the returned data, or buf size needed if AQ err==ENOMEM
+ * @cap_count: cap count needed if AQ err==ENOMEM
* @opc: capabilities type to discover - pass in the command opcode
* @cd: pointer to command details structure or NULL
*
@@ -1179,7 +1775,7 @@
* the firmware.
*/
static enum ice_status
-ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u16 *data_size,
+ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
enum ice_adminq_opc opc, struct ice_sq_cd *cd)
{
struct ice_aqc_list_caps *cmd;
@@ -1197,61 +1793,146 @@
status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
if (!status)
ice_parse_caps(hw, buf, le32_to_cpu(cmd->count), opc);
- *data_size = le16_to_cpu(desc.datalen);
+ else if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOMEM)
+ *cap_count = le32_to_cpu(cmd->count);
+ return status;
+}
+
+/**
+ * ice_discover_caps - get info about the HW
+ * @hw: pointer to the hardware structure
+ * @opc: capabilities type to discover - pass in the command opcode
+ */
+static enum ice_status
+ice_discover_caps(struct ice_hw *hw, enum ice_adminq_opc opc)
+{
+ enum ice_status status;
+ u32 cap_count;
+ u16 cbuf_len;
+ u8 retries;
+
+ /* The driver doesn't know how many capabilities the device will return
+ * so the buffer size required isn't known ahead of time. The driver
+ * starts with cbuf_len and if this turns out to be insufficient, the
+ * device returns ICE_AQ_RC_ENOMEM and also the cap_count it needs.
+ * The driver then allocates the buffer based on the count and retries
+ * the operation. So it follows that the retry count is 2.
+ */
+#define ICE_GET_CAP_BUF_COUNT 40
+#define ICE_GET_CAP_RETRY_COUNT 2
+
+ cap_count = ICE_GET_CAP_BUF_COUNT;
+ retries = ICE_GET_CAP_RETRY_COUNT;
+
+ do {
+ void *cbuf;
+
+ cbuf_len = (u16)(cap_count *
+ sizeof(struct ice_aqc_list_caps_elem));
+ cbuf = devm_kzalloc(ice_hw_to_dev(hw), cbuf_len, GFP_KERNEL);
+ if (!cbuf)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &cap_count,
+ opc, NULL);
+ devm_kfree(ice_hw_to_dev(hw), cbuf);
+
+ if (!status || hw->adminq.sq_last_status != ICE_AQ_RC_ENOMEM)
+ break;
+
+ /* If ENOMEM is returned, try again with bigger buffer */
+ } while (--retries);
return status;
}
/**
+ * ice_set_safe_mode_caps - Override dev/func capabilities when in safe mode
+ * @hw: pointer to the hardware structure
+ */
+void ice_set_safe_mode_caps(struct ice_hw *hw)
+{
+ struct ice_hw_func_caps *func_caps = &hw->func_caps;
+ struct ice_hw_dev_caps *dev_caps = &hw->dev_caps;
+ u32 valid_func, rxq_first_id, txq_first_id;
+ u32 msix_vector_first_id, max_mtu;
+ u32 num_func = 0;
+ u8 i;
+
+ /* cache some func_caps values that should be restored after memset */
+ valid_func = func_caps->common_cap.valid_functions;
+ txq_first_id = func_caps->common_cap.txq_first_id;
+ rxq_first_id = func_caps->common_cap.rxq_first_id;
+ msix_vector_first_id = func_caps->common_cap.msix_vector_first_id;
+ max_mtu = func_caps->common_cap.max_mtu;
+
+ /* unset func capabilities */
+ memset(func_caps, 0, sizeof(*func_caps));
+
+ /* restore cached values */
+ func_caps->common_cap.valid_functions = valid_func;
+ func_caps->common_cap.txq_first_id = txq_first_id;
+ func_caps->common_cap.rxq_first_id = rxq_first_id;
+ func_caps->common_cap.msix_vector_first_id = msix_vector_first_id;
+ func_caps->common_cap.max_mtu = max_mtu;
+
+ /* one Tx and one Rx queue in safe mode */
+ func_caps->common_cap.num_rxq = 1;
+ func_caps->common_cap.num_txq = 1;
+
+ /* two MSIX vectors, one for traffic and one for misc causes */
+ func_caps->common_cap.num_msix_vectors = 2;
+ func_caps->guar_num_vsi = 1;
+
+ /* cache some dev_caps values that should be restored after memset */
+ valid_func = dev_caps->common_cap.valid_functions;
+ txq_first_id = dev_caps->common_cap.txq_first_id;
+ rxq_first_id = dev_caps->common_cap.rxq_first_id;
+ msix_vector_first_id = dev_caps->common_cap.msix_vector_first_id;
+ max_mtu = dev_caps->common_cap.max_mtu;
+
+ /* unset dev capabilities */
+ memset(dev_caps, 0, sizeof(*dev_caps));
+
+ /* restore cached values */
+ dev_caps->common_cap.valid_functions = valid_func;
+ dev_caps->common_cap.txq_first_id = txq_first_id;
+ dev_caps->common_cap.rxq_first_id = rxq_first_id;
+ dev_caps->common_cap.msix_vector_first_id = msix_vector_first_id;
+ dev_caps->common_cap.max_mtu = max_mtu;
+
+ /* valid_func is a bitmap. get number of functions */
+#define ICE_MAX_FUNCS 8
+ for (i = 0; i < ICE_MAX_FUNCS; i++)
+ if (valid_func & BIT(i))
+ num_func++;
+
+ /* one Tx and one Rx queue per function in safe mode */
+ dev_caps->common_cap.num_rxq = num_func;
+ dev_caps->common_cap.num_txq = num_func;
+
+ /* two MSIX vectors per function */
+ dev_caps->common_cap.num_msix_vectors = 2 * num_func;
+}
+
+/**
* ice_get_caps - get info about the HW
* @hw: pointer to the hardware structure
*/
enum ice_status ice_get_caps(struct ice_hw *hw)
{
enum ice_status status;
- u16 data_size = 0;
- u16 cbuf_len;
- u8 retries;
- /* The driver doesn't know how many capabilities the device will return
- * so the buffer size required isn't known ahead of time. The driver
- * starts with cbuf_len and if this turns out to be insufficient, the
- * device returns ICE_AQ_RC_ENOMEM and also the buffer size it needs.
- * The driver then allocates the buffer of this size and retries the
- * operation. So it follows that the retry count is 2.
- */
-#define ICE_GET_CAP_BUF_COUNT 40
-#define ICE_GET_CAP_RETRY_COUNT 2
-
- cbuf_len = ICE_GET_CAP_BUF_COUNT *
- sizeof(struct ice_aqc_list_caps_elem);
-
- retries = ICE_GET_CAP_RETRY_COUNT;
-
- do {
- void *cbuf;
-
- cbuf = devm_kzalloc(ice_hw_to_dev(hw), cbuf_len, GFP_KERNEL);
- if (!cbuf)
- return ICE_ERR_NO_MEMORY;
-
- status = ice_aq_discover_caps(hw, cbuf, cbuf_len, &data_size,
- ice_aqc_opc_list_func_caps, NULL);
- devm_kfree(ice_hw_to_dev(hw), cbuf);
-
- if (!status || hw->adminq.sq_last_status != ICE_AQ_RC_ENOMEM)
- break;
-
- /* If ENOMEM is returned, try again with bigger buffer */
- cbuf_len = data_size;
- } while (--retries);
+ status = ice_discover_caps(hw, ice_aqc_opc_list_dev_caps);
+ if (!status)
+ status = ice_discover_caps(hw, ice_aqc_opc_list_func_caps);
return status;
}
/**
* ice_aq_manage_mac_write - manage MAC address write command
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @mac_addr: MAC address to be written as LAA/LAA+WoL/Port address
* @flags: flags to control write behavior
* @cd: pointer to command details structure or NULL
@@ -1259,7 +1940,7 @@
* This function is used to write MAC address to the NVM (0x0108).
*/
enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
struct ice_sq_cd *cd)
{
struct ice_aqc_manage_mac_write *cmd;
@@ -1271,15 +1952,15 @@
cmd->flags = flags;
/* Prep values for flags, sah, sal */
- cmd->sah = htons(*((u16 *)mac_addr));
- cmd->sal = htonl(*((u32 *)(mac_addr + 2)));
+ cmd->sah = htons(*((const u16 *)mac_addr));
+ cmd->sal = htonl(*((const u32 *)(mac_addr + 2)));
return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
}
/**
* ice_aq_clear_pxe_mode
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* Tell the firmware that the driver is taking over from PXE (0x0110).
*/
@@ -1295,7 +1976,7 @@
/**
* ice_clear_pxe_mode - clear pxe operations mode
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* Make sure all PXE mode settings are cleared, including things
* like descriptor fetch/write-back mode.
@@ -1307,8 +1988,184 @@
}
/**
+ * ice_get_link_speed_based_on_phy_type - returns link speed
+ * @phy_type_low: lower part of phy_type
+ * @phy_type_high: higher part of phy_type
+ *
+ * This helper function will convert an entry in PHY type structure
+ * [phy_type_low, phy_type_high] to its corresponding link speed.
+ * Note: In the structure of [phy_type_low, phy_type_high], there should
+ * be one bit set, as this function will convert one PHY type to its
+ * speed.
+ * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
+ * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
+ */
+static u16
+ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
+{
+ u16 speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
+ u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
+
+ switch (phy_type_low) {
+ case ICE_PHY_TYPE_LOW_100BASE_TX:
+ case ICE_PHY_TYPE_LOW_100M_SGMII:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_100MB;
+ break;
+ case ICE_PHY_TYPE_LOW_1000BASE_T:
+ case ICE_PHY_TYPE_LOW_1000BASE_SX:
+ case ICE_PHY_TYPE_LOW_1000BASE_LX:
+ case ICE_PHY_TYPE_LOW_1000BASE_KX:
+ case ICE_PHY_TYPE_LOW_1G_SGMII:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_1000MB;
+ break;
+ case ICE_PHY_TYPE_LOW_2500BASE_T:
+ case ICE_PHY_TYPE_LOW_2500BASE_X:
+ case ICE_PHY_TYPE_LOW_2500BASE_KX:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_2500MB;
+ break;
+ case ICE_PHY_TYPE_LOW_5GBASE_T:
+ case ICE_PHY_TYPE_LOW_5GBASE_KR:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_5GB;
+ break;
+ case ICE_PHY_TYPE_LOW_10GBASE_T:
+ case ICE_PHY_TYPE_LOW_10G_SFI_DA:
+ case ICE_PHY_TYPE_LOW_10GBASE_SR:
+ case ICE_PHY_TYPE_LOW_10GBASE_LR:
+ case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1:
+ case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_10G_SFI_C2C:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_10GB;
+ break;
+ case ICE_PHY_TYPE_LOW_25GBASE_T:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR1:
+ case ICE_PHY_TYPE_LOW_25GBASE_SR:
+ case ICE_PHY_TYPE_LOW_25GBASE_LR:
+ case ICE_PHY_TYPE_LOW_25GBASE_KR:
+ case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
+ case ICE_PHY_TYPE_LOW_25GBASE_KR1:
+ case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_25GB;
+ break;
+ case ICE_PHY_TYPE_LOW_40GBASE_CR4:
+ case ICE_PHY_TYPE_LOW_40GBASE_SR4:
+ case ICE_PHY_TYPE_LOW_40GBASE_LR4:
+ case ICE_PHY_TYPE_LOW_40GBASE_KR4:
+ case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_40G_XLAUI:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB;
+ break;
+ case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+ case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_LAUI2:
+ case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_AUI2:
+ case ICE_PHY_TYPE_LOW_50GBASE_CP:
+ case ICE_PHY_TYPE_LOW_50GBASE_SR:
+ case ICE_PHY_TYPE_LOW_50GBASE_FR:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR:
+ case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+ case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_AUI1:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_50GB;
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+ case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_100G_CAUI4:
+ case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_100G_AUI4:
+ case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+ case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+ case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+ case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+ case ICE_PHY_TYPE_LOW_100GBASE_DR:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_100GB;
+ break;
+ default:
+ speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
+ break;
+ }
+
+ switch (phy_type_high) {
+ case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+ case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+ case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+ case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+ case ICE_PHY_TYPE_HIGH_100G_AUI2:
+ speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB;
+ break;
+ default:
+ speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
+ break;
+ }
+
+ if (speed_phy_type_low == ICE_AQ_LINK_SPEED_UNKNOWN &&
+ speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+ return ICE_AQ_LINK_SPEED_UNKNOWN;
+ else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+ speed_phy_type_high != ICE_AQ_LINK_SPEED_UNKNOWN)
+ return ICE_AQ_LINK_SPEED_UNKNOWN;
+ else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+ speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+ return speed_phy_type_low;
+ else
+ return speed_phy_type_high;
+}
+
+/**
+ * ice_update_phy_type
+ * @phy_type_low: pointer to the lower part of phy_type
+ * @phy_type_high: pointer to the higher part of phy_type
+ * @link_speeds_bitmap: targeted link speeds bitmap
+ *
+ * Note: For the link_speeds_bitmap structure, you can check it at
+ * [ice_aqc_get_link_status->link_speed]. Caller can pass in
+ * link_speeds_bitmap include multiple speeds.
+ *
+ * Each entry in this [phy_type_low, phy_type_high] structure will
+ * present a certain link speed. This helper function will turn on bits
+ * in [phy_type_low, phy_type_high] structure based on the value of
+ * link_speeds_bitmap input parameter.
+ */
+void
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+ u16 link_speeds_bitmap)
+{
+ u64 pt_high;
+ u64 pt_low;
+ int index;
+ u16 speed;
+
+ /* We first check with low part of phy_type */
+ for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) {
+ pt_low = BIT_ULL(index);
+ speed = ice_get_link_speed_based_on_phy_type(pt_low, 0);
+
+ if (link_speeds_bitmap & speed)
+ *phy_type_low |= BIT_ULL(index);
+ }
+
+ /* We then check with high part of phy_type */
+ for (index = 0; index <= ICE_PHY_TYPE_HIGH_MAX_INDEX; index++) {
+ pt_high = BIT_ULL(index);
+ speed = ice_get_link_speed_based_on_phy_type(0, pt_high);
+
+ if (link_speeds_bitmap & speed)
+ *phy_type_high |= BIT_ULL(index);
+ }
+}
+
+/**
* ice_aq_set_phy_cfg
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @lport: logical port number
* @cfg: structure with PHY configuration data to be set
* @cd: pointer to command details structure or NULL
@@ -1318,19 +2175,38 @@
* mode as the PF may not have the privilege to set some of the PHY Config
* parameters. This status will be indicated by the command response (0x0601).
*/
-static enum ice_status
+enum ice_status
ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd)
{
- struct ice_aqc_set_phy_cfg *cmd;
struct ice_aq_desc desc;
if (!cfg)
return ICE_ERR_PARAM;
- cmd = &desc.params.set_phy;
+ /* Ensure that only valid bits of cfg->caps can be turned on. */
+ if (cfg->caps & ~ICE_AQ_PHY_ENA_VALID_MASK) {
+ ice_debug(hw, ICE_DBG_PHY,
+ "Invalid bit is set in ice_aqc_set_phy_cfg_data->caps : 0x%x\n",
+ cfg->caps);
+
+ cfg->caps &= ICE_AQ_PHY_ENA_VALID_MASK;
+ }
+
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg);
- cmd->lport_num = lport;
+ desc.params.set_phy.lport_num = lport;
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ ice_debug(hw, ICE_DBG_LINK, "phy_type_low = 0x%llx\n",
+ (unsigned long long)le64_to_cpu(cfg->phy_type_low));
+ ice_debug(hw, ICE_DBG_LINK, "phy_type_high = 0x%llx\n",
+ (unsigned long long)le64_to_cpu(cfg->phy_type_high));
+ ice_debug(hw, ICE_DBG_LINK, "caps = 0x%x\n", cfg->caps);
+ ice_debug(hw, ICE_DBG_LINK, "low_power_ctrl = 0x%x\n",
+ cfg->low_power_ctrl);
+ ice_debug(hw, ICE_DBG_LINK, "eee_cap = 0x%x\n", cfg->eee_cap);
+ ice_debug(hw, ICE_DBG_LINK, "eeer_value = 0x%x\n", cfg->eeer_value);
+ ice_debug(hw, ICE_DBG_LINK, "link_fec_opt = 0x%x\n", cfg->link_fec_opt);
return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
}
@@ -1339,39 +2215,39 @@
* ice_update_link_info - update status of the HW network link
* @pi: port info structure of the interested logical port
*/
-static enum ice_status
-ice_update_link_info(struct ice_port_info *pi)
+enum ice_status ice_update_link_info(struct ice_port_info *pi)
{
- struct ice_aqc_get_phy_caps_data *pcaps;
- struct ice_phy_info *phy_info;
+ struct ice_link_status *li;
enum ice_status status;
- struct ice_hw *hw;
if (!pi)
return ICE_ERR_PARAM;
- hw = pi->hw;
+ li = &pi->phy.link_info;
- pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL);
- if (!pcaps)
- return ICE_ERR_NO_MEMORY;
-
- phy_info = &pi->phy;
status = ice_aq_get_link_info(pi, true, NULL, NULL);
if (status)
- goto out;
+ return status;
- if (phy_info->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
- status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG,
+ if (li->link_info & ICE_AQ_MEDIA_AVAILABLE) {
+ struct ice_aqc_get_phy_caps_data *pcaps;
+ struct ice_hw *hw;
+
+ hw = pi->hw;
+ pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps),
+ GFP_KERNEL);
+ if (!pcaps)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP,
pcaps, NULL);
- if (status)
- goto out;
+ if (!status)
+ memcpy(li->module_type, &pcaps->module_type,
+ sizeof(li->module_type));
- memcpy(phy_info->link_info.module_type, &pcaps->module_type,
- sizeof(phy_info->link_info.module_type));
+ devm_kfree(ice_hw_to_dev(hw), pcaps);
}
-out:
- devm_kfree(ice_hw_to_dev(hw), pcaps);
+
return status;
}
@@ -1379,12 +2255,12 @@
* ice_set_fc
* @pi: port information structure
* @aq_failures: pointer to status code, specific to ice_set_fc routine
- * @atomic_restart: enable automatic link update
+ * @ena_auto_link_update: enable automatic link update
*
* Set the requested flow control mode.
*/
enum ice_status
-ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart)
+ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)
{
struct ice_aqc_set_phy_cfg_data cfg = { 0 };
struct ice_aqc_get_phy_caps_data *pcaps;
@@ -1416,7 +2292,7 @@
if (!pcaps)
return ICE_ERR_NO_MEMORY;
- /* Get the current phy config */
+ /* Get the current PHY config */
status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
NULL);
if (status) {
@@ -1427,16 +2303,19 @@
/* clear the old pause settings */
cfg.caps = pcaps->caps & ~(ICE_AQC_PHY_EN_TX_LINK_PAUSE |
ICE_AQC_PHY_EN_RX_LINK_PAUSE);
+
/* set the new capabilities */
cfg.caps |= pause_mask;
+
/* If the capabilities have changed, then set the new config */
if (cfg.caps != pcaps->caps) {
int retry_count, retry_max = 10;
/* Auto restart link so settings take effect */
- if (atomic_restart)
- cfg.caps |= ICE_AQ_PHY_ENA_ATOMIC_LINK;
+ if (ena_auto_link_update)
+ cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
/* Copy over all the old settings */
+ cfg.phy_type_high = pcaps->phy_type_high;
cfg.phy_type_low = pcaps->phy_type_low;
cfg.low_power_ctrl = pcaps->low_power_ctrl;
cfg.eee_cap = pcaps->eee_cap;
@@ -1473,6 +2352,71 @@
}
/**
+ * ice_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data
+ * @caps: PHY ability structure to copy date from
+ * @cfg: PHY configuration structure to copy data to
+ *
+ * Helper function to copy AQC PHY get ability data to PHY set configuration
+ * data structure
+ */
+void
+ice_copy_phy_caps_to_cfg(struct ice_aqc_get_phy_caps_data *caps,
+ struct ice_aqc_set_phy_cfg_data *cfg)
+{
+ if (!caps || !cfg)
+ return;
+
+ cfg->phy_type_low = caps->phy_type_low;
+ cfg->phy_type_high = caps->phy_type_high;
+ cfg->caps = caps->caps;
+ cfg->low_power_ctrl = caps->low_power_ctrl;
+ cfg->eee_cap = caps->eee_cap;
+ cfg->eeer_value = caps->eeer_value;
+ cfg->link_fec_opt = caps->link_fec_options;
+}
+
+/**
+ * ice_cfg_phy_fec - Configure PHY FEC data based on FEC mode
+ * @cfg: PHY configuration data to set FEC mode
+ * @fec: FEC mode to configure
+ *
+ * Caller should copy ice_aqc_get_phy_caps_data.caps ICE_AQC_PHY_EN_AUTO_FEC
+ * (bit 7) and ice_aqc_get_phy_caps_data.link_fec_options to cfg.caps
+ * ICE_AQ_PHY_ENA_AUTO_FEC (bit 7) and cfg.link_fec_options before calling.
+ */
+void
+ice_cfg_phy_fec(struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec)
+{
+ switch (fec) {
+ case ICE_FEC_BASER:
+ /* Clear RS bits, and AND BASE-R ability
+ * bits and OR request bits.
+ */
+ cfg->link_fec_opt &= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN |
+ ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN;
+ cfg->link_fec_opt |= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ |
+ ICE_AQC_PHY_FEC_25G_KR_REQ;
+ break;
+ case ICE_FEC_RS:
+ /* Clear BASE-R bits, and AND RS ability
+ * bits and OR request bits.
+ */
+ cfg->link_fec_opt &= ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN;
+ cfg->link_fec_opt |= ICE_AQC_PHY_FEC_25G_RS_528_REQ |
+ ICE_AQC_PHY_FEC_25G_RS_544_REQ;
+ break;
+ case ICE_FEC_NONE:
+ /* Clear all FEC option bits. */
+ cfg->link_fec_opt &= ~ICE_AQC_PHY_FEC_MASK;
+ break;
+ case ICE_FEC_AUTO:
+ /* AND auto FEC bit, and all caps bits. */
+ cfg->caps &= ICE_AQC_PHY_CAPS_MASK;
+ break;
+ }
+}
+
+/**
* ice_get_link_status - get status of the HW network link
* @pi: port information structure
* @link_up: pointer to bool (true/false = linkup/linkdown)
@@ -1536,7 +2480,7 @@
/**
* ice_aq_set_event_mask
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @port_num: port number of the physical function
* @mask: event mask to be set
* @cd: pointer to command details structure or NULL
@@ -1557,6 +2501,56 @@
cmd->lport_num = port_num;
cmd->event_mask = cpu_to_le16(mask);
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_mac_loopback
+ * @hw: pointer to the HW struct
+ * @ena_lpbk: Enable or Disable loopback
+ * @cd: pointer to command details structure or NULL
+ *
+ * Enable/disable loopback on a given port
+ */
+enum ice_status
+ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_set_mac_lb *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.set_mac_lb;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_lb);
+ if (ena_lpbk)
+ cmd->lb_mode = ICE_AQ_MAC_LB_EN;
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_port_id_led
+ * @pi: pointer to the port information
+ * @is_orig_mode: is this LED set to original mode (by the net-list)
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set LED value for the given port (0x06e9)
+ */
+enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_set_port_id_led *cmd;
+ struct ice_hw *hw = pi->hw;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.set_port_id_led;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_id_led);
+
+ if (is_orig_mode)
+ cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_ORIG;
+ else
+ cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_BLINK;
return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
}
@@ -1654,7 +2648,7 @@
/**
* ice_aq_get_rss_lut
* @hw: pointer to the hardware structure
- * @vsi_id: VSI FW index
+ * @vsi_handle: software VSI handle
* @lut_type: LUT table type
* @lut: pointer to the LUT buffer provided by the caller
* @lut_size: size of the LUT buffer
@@ -1662,17 +2656,20 @@
* get the RSS lookup table, PF or VSI type
*/
enum ice_status
-ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
- u16 lut_size)
+ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type,
+ u8 *lut, u16 lut_size)
{
- return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0,
- false);
+ if (!ice_is_vsi_valid(hw, vsi_handle) || !lut)
+ return ICE_ERR_PARAM;
+
+ return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle),
+ lut_type, lut, lut_size, 0, false);
}
/**
* ice_aq_set_rss_lut
* @hw: pointer to the hardware structure
- * @vsi_id: VSI FW index
+ * @vsi_handle: software VSI handle
* @lut_type: LUT table type
* @lut: pointer to the LUT buffer provided by the caller
* @lut_size: size of the LUT buffer
@@ -1680,16 +2677,19 @@
* set the RSS lookup table, PF or VSI type
*/
enum ice_status
-ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
- u16 lut_size)
+ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type,
+ u8 *lut, u16 lut_size)
{
- return __ice_aq_get_set_rss_lut(hw, vsi_id, lut_type, lut, lut_size, 0,
- true);
+ if (!ice_is_vsi_valid(hw, vsi_handle) || !lut)
+ return ICE_ERR_PARAM;
+
+ return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle),
+ lut_type, lut, lut_size, 0, true);
}
/**
* __ice_aq_get_set_rss_key
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @vsi_id: VSI FW index
* @key: pointer to key info struct
* @set: set true to set the key, false to get the key
@@ -1724,32 +2724,40 @@
/**
* ice_aq_get_rss_key
- * @hw: pointer to the hw struct
- * @vsi_id: VSI FW index
+ * @hw: pointer to the HW struct
+ * @vsi_handle: software VSI handle
* @key: pointer to key info struct
*
* get the RSS key per VSI
*/
enum ice_status
-ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id,
+ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle,
struct ice_aqc_get_set_rss_keys *key)
{
- return __ice_aq_get_set_rss_key(hw, vsi_id, key, false);
+ if (!ice_is_vsi_valid(hw, vsi_handle) || !key)
+ return ICE_ERR_PARAM;
+
+ return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle),
+ key, false);
}
/**
* ice_aq_set_rss_key
- * @hw: pointer to the hw struct
- * @vsi_id: VSI FW index
+ * @hw: pointer to the HW struct
+ * @vsi_handle: software VSI handle
* @keys: pointer to key info struct
*
* set the RSS key per VSI
*/
enum ice_status
-ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id,
+ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle,
struct ice_aqc_get_set_rss_keys *keys)
{
- return __ice_aq_get_set_rss_key(hw, vsi_id, keys, true);
+ if (!ice_is_vsi_valid(hw, vsi_handle) || !keys)
+ return ICE_ERR_PARAM;
+
+ return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle),
+ keys, true);
}
/**
@@ -1820,6 +2828,8 @@
* @num_qgrps: number of groups in the list
* @qg_list: the list of groups to disable
* @buf_size: the total size of the qg_list buffer in bytes
+ * @rst_src: if called due to reset, specifies the reset source
+ * @vmvf_num: the relative VM or VF number that is undergoing the reset
* @cd: pointer to command details structure or NULL
*
* Disable LAN Tx queue (0x0C31)
@@ -1827,23 +2837,58 @@
static enum ice_status
ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
struct ice_aqc_dis_txq_item *qg_list, u16 buf_size,
+ enum ice_disq_rst_src rst_src, u16 vmvf_num,
struct ice_sq_cd *cd)
{
struct ice_aqc_dis_txqs *cmd;
struct ice_aq_desc desc;
+ enum ice_status status;
u16 i, sz = 0;
cmd = &desc.params.dis_txqs;
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs);
- if (!qg_list)
+ /* qg_list can be NULL only in VM/VF reset flow */
+ if (!qg_list && !rst_src)
return ICE_ERR_PARAM;
if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS)
return ICE_ERR_PARAM;
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
cmd->num_entries = num_qgrps;
+ cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) &
+ ICE_AQC_Q_DIS_TIMEOUT_M);
+
+ switch (rst_src) {
+ case ICE_VM_RESET:
+ cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET;
+ cmd->vmvf_and_timeout |=
+ cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M);
+ break;
+ case ICE_VF_RESET:
+ cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET;
+ /* In this case, FW expects vmvf_num to be absolute VF ID */
+ cmd->vmvf_and_timeout |=
+ cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) &
+ ICE_AQC_Q_DIS_VMVF_NUM_M);
+ break;
+ case ICE_NO_RESET:
+ default:
+ break;
+ }
+
+ /* flush pipe on time out */
+ cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE;
+ /* If no queue group info, we are in a reset flow. Issue the AQ */
+ if (!qg_list)
+ goto do_aq;
+
+ /* set RD bit to indicate that command buffer is provided by the driver
+ * and it needs to be read by the firmware
+ */
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
for (i = 0; i < num_qgrps; ++i) {
/* Calculate the size taken up by the queue IDs in this group */
sz += qg_list[i].num_qs * sizeof(qg_list[i].q_id);
@@ -1859,7 +2904,18 @@
if (buf_size != sz)
return ICE_ERR_PARAM;
- return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+do_aq:
+ status = ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+ if (status) {
+ if (!qg_list)
+ ice_debug(hw, ICE_DBG_SCHED, "VM%d disable failed %d\n",
+ vmvf_num, hw->adminq.sq_last_status);
+ else
+ ice_debug(hw, ICE_DBG_SCHED, "disable queue %d failed %d\n",
+ le16_to_cpu(qg_list[0].q_id[0]),
+ hw->adminq.sq_last_status);
+ }
+ return status;
}
/* End of FW Admin Queue command wrappers */
@@ -1870,8 +2926,8 @@
* @dest_ctx: the context to be written to
* @ce_info: a description of the struct to be filled
*/
-static void ice_write_byte(u8 *src_ctx, u8 *dest_ctx,
- const struct ice_ctx_ele *ce_info)
+static void
+ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
{
u8 src_byte, dest_byte, mask;
u8 *from, *dest;
@@ -1909,8 +2965,8 @@
* @dest_ctx: the context to be written to
* @ce_info: a description of the struct to be filled
*/
-static void ice_write_word(u8 *src_ctx, u8 *dest_ctx,
- const struct ice_ctx_ele *ce_info)
+static void
+ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
{
u16 src_word, mask;
__le16 dest_word;
@@ -1952,8 +3008,8 @@
* @dest_ctx: the context to be written to
* @ce_info: a description of the struct to be filled
*/
-static void ice_write_dword(u8 *src_ctx, u8 *dest_ctx,
- const struct ice_ctx_ele *ce_info)
+static void
+ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
{
u32 src_dword, mask;
__le32 dest_dword;
@@ -2003,8 +3059,8 @@
* @dest_ctx: the context to be written to
* @ce_info: a description of the struct to be filled
*/
-static void ice_write_qword(u8 *src_ctx, u8 *dest_ctx,
- const struct ice_ctx_ele *ce_info)
+static void
+ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
{
u64 src_qword, mask;
__le64 dest_qword;
@@ -2086,24 +3142,50 @@
}
/**
+ * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC
+ * @hw: pointer to the HW struct
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
+ * @q_handle: software queue handle
+ */
+static struct ice_q_ctx *
+ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle)
+{
+ struct ice_vsi_ctx *vsi;
+ struct ice_q_ctx *q_ctx;
+
+ vsi = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!vsi)
+ return NULL;
+ if (q_handle >= vsi->num_lan_q_entries[tc])
+ return NULL;
+ if (!vsi->lan_q_ctx[tc])
+ return NULL;
+ q_ctx = vsi->lan_q_ctx[tc];
+ return &q_ctx[q_handle];
+}
+
+/**
* ice_ena_vsi_txq
* @pi: port information structure
- * @vsi_id: VSI id
- * @tc: tc number
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
+ * @q_handle: software queue handle
* @num_qgrps: Number of added queue groups
* @buf: list of queue groups to be added
* @buf_size: size of buffer for indirect command
* @cd: pointer to command details structure or NULL
*
- * This function adds one lan q
+ * This function adds one LAN queue
*/
enum ice_status
-ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps,
- struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
+ u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
struct ice_sq_cd *cd)
{
struct ice_aqc_txsched_elem_data node = { 0 };
struct ice_sched_node *parent;
+ struct ice_q_ctx *q_ctx;
enum ice_status status;
struct ice_hw *hw;
@@ -2115,15 +3197,27 @@
hw = pi->hw;
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
mutex_lock(&pi->sched_lock);
+ q_ctx = ice_get_lan_q_ctx(hw, vsi_handle, tc, q_handle);
+ if (!q_ctx) {
+ ice_debug(hw, ICE_DBG_SCHED, "Enaq: invalid queue handle %d\n",
+ q_handle);
+ status = ICE_ERR_PARAM;
+ goto ena_txq_exit;
+ }
+
/* find a parent node */
- parent = ice_sched_get_free_qparent(pi, vsi_id, tc,
+ parent = ice_sched_get_free_qparent(pi, vsi_handle, tc,
ICE_SCHED_NODE_OWNER_LAN);
if (!parent) {
status = ICE_ERR_PARAM;
goto ena_txq_exit;
}
+
buf->parent_teid = parent->info.node_teid;
node.parent_teid = parent->info.node_teid;
/* Mark that the values in the "generic" section as valid. The default
@@ -2135,19 +3229,24 @@
* Bit 5-6.
* - Bit 7 is reserved.
* Without setting the generic section as valid in valid_sections, the
- * Admin Q command will fail with error code ICE_AQ_RC_EINVAL.
+ * Admin queue command will fail with error code ICE_AQ_RC_EINVAL.
*/
buf->txqs[0].info.valid_sections = ICE_AQC_ELEM_VALID_GENERIC;
- /* add the lan q */
+ /* add the LAN queue */
status = ice_aq_add_lan_txq(hw, num_qgrps, buf, buf_size, cd);
- if (status)
+ if (status) {
+ ice_debug(hw, ICE_DBG_SCHED, "enable queue %d failed %d\n",
+ le16_to_cpu(buf->txqs[0].txq_id),
+ hw->adminq.sq_last_status);
goto ena_txq_exit;
+ }
node.node_teid = buf->txqs[0].q_teid;
node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF;
+ q_ctx->q_handle = q_handle;
- /* add a leaf node into schduler tree q layer */
+ /* add a leaf node into schduler tree queue layer */
status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, &node);
ena_txq_exit:
@@ -2158,24 +3257,43 @@
/**
* ice_dis_vsi_txq
* @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
* @num_queues: number of queues
+ * @q_handles: pointer to software queue handle array
* @q_ids: pointer to the q_id array
* @q_teids: pointer to queue node teids
+ * @rst_src: if called due to reset, specifies the reset source
+ * @vmvf_num: the relative VM or VF number that is undergoing the reset
* @cd: pointer to command details structure or NULL
*
* This function removes queues and their corresponding nodes in SW DB
*/
enum ice_status
-ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
- u32 *q_teids, struct ice_sq_cd *cd)
+ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
+ u16 *q_handles, u16 *q_ids, u32 *q_teids,
+ enum ice_disq_rst_src rst_src, u16 vmvf_num,
+ struct ice_sq_cd *cd)
{
enum ice_status status = ICE_ERR_DOES_NOT_EXIST;
struct ice_aqc_dis_txq_item qg_list;
+ struct ice_q_ctx *q_ctx;
u16 i;
if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
return ICE_ERR_CFG;
+ if (!num_queues) {
+ /* if queue is disabled already yet the disable queue command
+ * has to be sent to complete the VF reset, then call
+ * ice_aq_dis_lan_txq without any queue information
+ */
+ if (rst_src)
+ return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src,
+ vmvf_num, NULL);
+ return ICE_ERR_CFG;
+ }
+
mutex_lock(&pi->sched_lock);
for (i = 0; i < num_queues; i++) {
@@ -2184,32 +3302,45 @@
node = ice_sched_find_node_by_teid(pi->root, q_teids[i]);
if (!node)
continue;
+ q_ctx = ice_get_lan_q_ctx(pi->hw, vsi_handle, tc, q_handles[i]);
+ if (!q_ctx) {
+ ice_debug(pi->hw, ICE_DBG_SCHED, "invalid queue handle%d\n",
+ q_handles[i]);
+ continue;
+ }
+ if (q_ctx->q_handle != q_handles[i]) {
+ ice_debug(pi->hw, ICE_DBG_SCHED, "Err:handles %d %d\n",
+ q_ctx->q_handle, q_handles[i]);
+ continue;
+ }
qg_list.parent_teid = node->info.parent_teid;
qg_list.num_qs = 1;
qg_list.q_id[0] = cpu_to_le16(q_ids[i]);
status = ice_aq_dis_lan_txq(pi->hw, 1, &qg_list,
- sizeof(qg_list), cd);
+ sizeof(qg_list), rst_src, vmvf_num,
+ cd);
if (status)
break;
ice_free_sched_node(pi, node);
+ q_ctx->q_handle = ICE_INVAL_Q_HANDLE;
}
mutex_unlock(&pi->sched_lock);
return status;
}
/**
- * ice_cfg_vsi_qs - configure the new/exisiting VSI queues
+ * ice_cfg_vsi_qs - configure the new/existing VSI queues
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc_bitmap: TC bitmap
* @maxqs: max queues array per TC
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
*
* This function adds/updates the VSI queues per TC.
*/
static enum ice_status
-ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
u16 *maxqs, u8 owner)
{
enum ice_status status = 0;
@@ -2218,14 +3349,17 @@
if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
return ICE_ERR_CFG;
+ if (!ice_is_vsi_valid(pi->hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
mutex_lock(&pi->sched_lock);
- for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+ ice_for_each_traffic_class(i) {
/* configuration is possible only if TC node is present */
if (!ice_sched_get_tc_node(pi, i))
continue;
- status = ice_sched_cfg_vsi(pi, vsi_id, i, maxqs[i], owner,
+ status = ice_sched_cfg_vsi(pi, vsi_handle, i, maxqs[i], owner,
ice_is_tc_ena(tc_bitmap, i));
if (status)
break;
@@ -2236,18 +3370,182 @@
}
/**
- * ice_cfg_vsi_lan - configure VSI lan queues
+ * ice_cfg_vsi_lan - configure VSI LAN queues
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc_bitmap: TC bitmap
- * @max_lanqs: max lan queues array per TC
+ * @max_lanqs: max LAN queues array per TC
*
- * This function adds/updates the VSI lan queues per TC.
+ * This function adds/updates the VSI LAN queues per TC.
*/
enum ice_status
-ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
u16 *max_lanqs)
{
- return ice_cfg_vsi_qs(pi, vsi_id, tc_bitmap, max_lanqs,
+ return ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, max_lanqs,
ICE_SCHED_NODE_OWNER_LAN);
}
+
+/**
+ * ice_replay_pre_init - replay pre initialization
+ * @hw: pointer to the HW struct
+ *
+ * Initializes required config data for VSI, FD, ACL, and RSS before replay.
+ */
+static enum ice_status ice_replay_pre_init(struct ice_hw *hw)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ u8 i;
+
+ /* Delete old entries from replay filter list head if there is any */
+ ice_rm_all_sw_replay_rule_info(hw);
+ /* In start of replay, move entries into replay_rules list, it
+ * will allow adding rules entries back to filt_rules list,
+ * which is operational list.
+ */
+ for (i = 0; i < ICE_SW_LKUP_LAST; i++)
+ list_replace_init(&sw->recp_list[i].filt_rules,
+ &sw->recp_list[i].filt_replay_rules);
+
+ return 0;
+}
+
+/**
+ * ice_replay_vsi - replay VSI configuration
+ * @hw: pointer to the HW struct
+ * @vsi_handle: driver VSI handle
+ *
+ * Restore all VSI configuration after reset. It is required to call this
+ * function with main VSI first.
+ */
+enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle)
+{
+ enum ice_status status;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ /* Replay pre-initialization if there is any */
+ if (vsi_handle == ICE_MAIN_VSI_HANDLE) {
+ status = ice_replay_pre_init(hw);
+ if (status)
+ return status;
+ }
+
+ /* Replay per VSI all filters */
+ status = ice_replay_vsi_all_fltr(hw, vsi_handle);
+ return status;
+}
+
+/**
+ * ice_replay_post - post replay configuration cleanup
+ * @hw: pointer to the HW struct
+ *
+ * Post replay cleanup.
+ */
+void ice_replay_post(struct ice_hw *hw)
+{
+ /* Delete old entries from replay filter list head */
+ ice_rm_all_sw_replay_rule_info(hw);
+}
+
+/**
+ * ice_stat_update40 - read 40 bit stat from the chip and update stat values
+ * @hw: ptr to the hardware info
+ * @reg: offset of 64 bit HW register to read from
+ * @prev_stat_loaded: bool to specify if previous stats are loaded
+ * @prev_stat: ptr to previous loaded stat value
+ * @cur_stat: ptr to current stat value
+ */
+void
+ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+ u64 *prev_stat, u64 *cur_stat)
+{
+ u64 new_data = rd64(hw, reg) & (BIT_ULL(40) - 1);
+
+ /* device stats are not reset at PFR, they likely will not be zeroed
+ * when the driver starts. Thus, save the value from the first read
+ * without adding to the statistic value so that we report stats which
+ * count up from zero.
+ */
+ if (!prev_stat_loaded) {
+ *prev_stat = new_data;
+ return;
+ }
+
+ /* Calculate the difference between the new and old values, and then
+ * add it to the software stat value.
+ */
+ if (new_data >= *prev_stat)
+ *cur_stat += new_data - *prev_stat;
+ else
+ /* to manage the potential roll-over */
+ *cur_stat += (new_data + BIT_ULL(40)) - *prev_stat;
+
+ /* Update the previously stored value to prepare for next read */
+ *prev_stat = new_data;
+}
+
+/**
+ * ice_stat_update32 - read 32 bit stat from the chip and update stat values
+ * @hw: ptr to the hardware info
+ * @reg: offset of HW register to read from
+ * @prev_stat_loaded: bool to specify if previous stats are loaded
+ * @prev_stat: ptr to previous loaded stat value
+ * @cur_stat: ptr to current stat value
+ */
+void
+ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+ u64 *prev_stat, u64 *cur_stat)
+{
+ u32 new_data;
+
+ new_data = rd32(hw, reg);
+
+ /* device stats are not reset at PFR, they likely will not be zeroed
+ * when the driver starts. Thus, save the value from the first read
+ * without adding to the statistic value so that we report stats which
+ * count up from zero.
+ */
+ if (!prev_stat_loaded) {
+ *prev_stat = new_data;
+ return;
+ }
+
+ /* Calculate the difference between the new and old values, and then
+ * add it to the software stat value.
+ */
+ if (new_data >= *prev_stat)
+ *cur_stat += new_data - *prev_stat;
+ else
+ /* to manage the potential roll-over */
+ *cur_stat += (new_data + BIT_ULL(32)) - *prev_stat;
+
+ /* Update the previously stored value to prepare for next read */
+ *prev_stat = new_data;
+}
+
+/**
+ * ice_sched_query_elem - query element information from HW
+ * @hw: pointer to the HW struct
+ * @node_teid: node TEID to be queried
+ * @buf: buffer to element information
+ *
+ * This function queries HW element information
+ */
+enum ice_status
+ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
+ struct ice_aqc_get_elem *buf)
+{
+ u16 buf_size, num_elem_ret = 0;
+ enum ice_status status;
+
+ buf_size = sizeof(*buf);
+ memset(buf, 0, buf_size);
+ buf->generic[0].node_teid = cpu_to_le32(node_teid);
+ status = ice_aq_query_sched_elems(hw, 1, buf, buf_size, &num_elem_ret,
+ NULL);
+ if (status || num_elem_ret != 1)
+ ice_debug(hw, ICE_DBG_SCHED, "query element failed\n");
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 9a55191..c3df92f 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -6,64 +6,102 @@
#include "ice.h"
#include "ice_type.h"
+#include "ice_flex_pipe.h"
#include "ice_switch.h"
+#include <linux/avf/virtchnl.h>
-void ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf,
- u16 buf_len);
+enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw);
+
+void
+ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf, u16 buf_len);
enum ice_status ice_init_hw(struct ice_hw *hw);
void ice_deinit_hw(struct ice_hw *hw);
enum ice_status ice_check_reset(struct ice_hw *hw);
enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req);
+enum ice_status ice_create_all_ctrlq(struct ice_hw *hw);
enum ice_status ice_init_all_ctrlq(struct ice_hw *hw);
void ice_shutdown_all_ctrlq(struct ice_hw *hw);
+void ice_destroy_all_ctrlq(struct ice_hw *hw);
enum ice_status
ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
struct ice_rq_event_info *e, u16 *pending);
enum ice_status
ice_get_link_status(struct ice_port_info *pi, bool *link_up);
+enum ice_status ice_update_link_info(struct ice_port_info *pi);
enum ice_status
ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
- enum ice_aq_res_access_type access);
+ enum ice_aq_res_access_type access, u32 timeout);
void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
enum ice_status ice_init_nvm(struct ice_hw *hw);
enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data);
+enum ice_status
ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
struct ice_aq_desc *desc, void *buf, u16 buf_size,
struct ice_sq_cd *cd);
void ice_clear_pxe_mode(struct ice_hw *hw);
enum ice_status ice_get_caps(struct ice_hw *hw);
+
+void ice_set_safe_mode_caps(struct ice_hw *hw);
+
+void ice_dev_onetime_setup(struct ice_hw *hw);
+
enum ice_status
ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
u32 rxq_index);
enum ice_status
-ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut,
u16 lut_size);
enum ice_status
-ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut,
+ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut,
u16 lut_size);
enum ice_status
-ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_id,
+ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle,
struct ice_aqc_get_set_rss_keys *keys);
enum ice_status
-ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_id,
+ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle,
struct ice_aqc_get_set_rss_keys *keys);
+
bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
extern const struct ice_ctx_ele ice_tlan_ctx_info[];
enum ice_status
ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info);
+
+extern struct mutex ice_global_cfg_lock_sw;
+
enum ice_status
ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
void *buf, u16 buf_size, struct ice_sq_cd *cd);
enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd);
+
enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
+ struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
+ struct ice_aqc_get_phy_caps_data *caps,
+ struct ice_sq_cd *cd);
+void
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+ u16 link_speeds_bitmap);
+enum ice_status
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
struct ice_sq_cd *cd);
enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
enum ice_status
-ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart);
+ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
+ struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd);
+enum ice_status
+ice_set_fc(struct ice_port_info *pi, u8 *aq_failures,
+ bool ena_auto_link_update);
+void
+ice_cfg_phy_fec(struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec);
+void
+ice_copy_phy_caps_to_cfg(struct ice_aqc_get_phy_caps_data *caps,
+ struct ice_aqc_set_phy_cfg_data *cfg);
enum ice_status
ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
struct ice_sq_cd *cd);
@@ -74,13 +112,37 @@
ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
struct ice_sq_cd *cd);
enum ice_status
-ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
- u32 *q_teids, struct ice_sq_cd *cmd_details);
+ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd);
+
enum ice_status
-ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_id, u8 tc_bitmap,
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+ struct ice_sq_cd *cd);
+
+enum ice_status
+ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
+ u16 *q_handle, u16 *q_ids, u32 *q_teids,
+ enum ice_disq_rst_src rst_src, u16 vmvf_num,
+ struct ice_sq_cd *cd);
+enum ice_status
+ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
u16 *max_lanqs);
enum ice_status
-ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps,
- struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
+ u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
struct ice_sq_cd *cd);
+enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle);
+void ice_replay_post(struct ice_hw *hw);
+void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf);
+void
+ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+ u64 *prev_stat, u64 *cur_stat);
+void
+ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+ u64 *prev_stat, u64 *cur_stat);
+void
+ice_get_nvm_version(struct ice_hw *hw, u8 *oem_ver, u16 *oem_build,
+ u8 *oem_patch, u8 *ver_hi, u8 *ver_lo);
+enum ice_status
+ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
+ struct ice_aqc_get_elem *buf);
#endif /* _ICE_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index e783976..2353166 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -3,6 +3,26 @@
#include "ice_common.h"
+#define ICE_CQ_INIT_REGS(qinfo, prefix) \
+do { \
+ (qinfo)->sq.head = prefix##_ATQH; \
+ (qinfo)->sq.tail = prefix##_ATQT; \
+ (qinfo)->sq.len = prefix##_ATQLEN; \
+ (qinfo)->sq.bah = prefix##_ATQBAH; \
+ (qinfo)->sq.bal = prefix##_ATQBAL; \
+ (qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M; \
+ (qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M; \
+ (qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M; \
+ (qinfo)->rq.head = prefix##_ARQH; \
+ (qinfo)->rq.tail = prefix##_ARQT; \
+ (qinfo)->rq.len = prefix##_ARQLEN; \
+ (qinfo)->rq.bah = prefix##_ARQBAH; \
+ (qinfo)->rq.bal = prefix##_ARQBAL; \
+ (qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M; \
+ (qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M; \
+ (qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M; \
+} while (0)
+
/**
* ice_adminq_init_regs - Initialize AdminQ registers
* @hw: pointer to the hardware structure
@@ -13,28 +33,25 @@
{
struct ice_ctl_q_info *cq = &hw->adminq;
- cq->sq.head = PF_FW_ATQH;
- cq->sq.tail = PF_FW_ATQT;
- cq->sq.len = PF_FW_ATQLEN;
- cq->sq.bah = PF_FW_ATQBAH;
- cq->sq.bal = PF_FW_ATQBAL;
- cq->sq.len_mask = PF_FW_ATQLEN_ATQLEN_M;
- cq->sq.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M;
- cq->sq.head_mask = PF_FW_ATQH_ATQH_M;
+ ICE_CQ_INIT_REGS(cq, PF_FW);
+}
- cq->rq.head = PF_FW_ARQH;
- cq->rq.tail = PF_FW_ARQT;
- cq->rq.len = PF_FW_ARQLEN;
- cq->rq.bah = PF_FW_ARQBAH;
- cq->rq.bal = PF_FW_ARQBAL;
- cq->rq.len_mask = PF_FW_ARQLEN_ARQLEN_M;
- cq->rq.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M;
- cq->rq.head_mask = PF_FW_ARQH_ARQH_M;
+/**
+ * ice_mailbox_init_regs - Initialize Mailbox registers
+ * @hw: pointer to the hardware structure
+ *
+ * This assumes the alloc_sq and alloc_rq functions have already been called
+ */
+static void ice_mailbox_init_regs(struct ice_hw *hw)
+{
+ struct ice_ctl_q_info *cq = &hw->mailboxq;
+
+ ICE_CQ_INIT_REGS(cq, PF_MBX);
}
/**
* ice_check_sq_alive
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @cq: pointer to the specific Control queue
*
* Returns true if Queue is enabled else false.
@@ -101,37 +118,20 @@
}
/**
- * ice_free_ctrlq_sq_ring - Free Control Transmit Queue (ATQ) rings
+ * ice_free_cq_ring - Free control queue ring
* @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
+ * @ring: pointer to the specific control queue ring
*
- * This assumes the posted send buffers have already been cleaned
+ * This assumes the posted buffers have already been cleaned
* and de-allocated
*/
-static void ice_free_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static void ice_free_cq_ring(struct ice_hw *hw, struct ice_ctl_q_ring *ring)
{
- dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size,
- cq->sq.desc_buf.va, cq->sq.desc_buf.pa);
- cq->sq.desc_buf.va = NULL;
- cq->sq.desc_buf.pa = 0;
- cq->sq.desc_buf.size = 0;
-}
-
-/**
- * ice_free_ctrlq_rq_ring - Free Control Receive Queue (ARQ) rings
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- *
- * This assumes the posted receive buffers have already been cleaned
- * and de-allocated
- */
-static void ice_free_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
- dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.desc_buf.size,
- cq->rq.desc_buf.va, cq->rq.desc_buf.pa);
- cq->rq.desc_buf.va = NULL;
- cq->rq.desc_buf.pa = 0;
- cq->rq.desc_buf.size = 0;
+ dmam_free_coherent(ice_hw_to_dev(hw), ring->desc_buf.size,
+ ring->desc_buf.va, ring->desc_buf.pa);
+ ring->desc_buf.va = NULL;
+ ring->desc_buf.pa = 0;
+ ring->desc_buf.size = 0;
}
/**
@@ -250,54 +250,23 @@
return ICE_ERR_NO_MEMORY;
}
-/**
- * ice_free_rq_bufs - Free ARQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static enum ice_status
+ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries)
{
- int i;
+ /* Clear Head and Tail */
+ wr32(hw, ring->head, 0);
+ wr32(hw, ring->tail, 0);
- /* free descriptors */
- for (i = 0; i < cq->num_rq_entries; i++) {
- dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.r.rq_bi[i].size,
- cq->rq.r.rq_bi[i].va, cq->rq.r.rq_bi[i].pa);
- cq->rq.r.rq_bi[i].va = NULL;
- cq->rq.r.rq_bi[i].pa = 0;
- cq->rq.r.rq_bi[i].size = 0;
- }
+ /* set starting point */
+ wr32(hw, ring->len, (num_entries | ring->len_ena_mask));
+ wr32(hw, ring->bal, lower_32_bits(ring->desc_buf.pa));
+ wr32(hw, ring->bah, upper_32_bits(ring->desc_buf.pa));
- /* free the dma header */
- devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head);
-}
+ /* Check one register to verify that config was applied */
+ if (rd32(hw, ring->bal) != lower_32_bits(ring->desc_buf.pa))
+ return ICE_ERR_AQ_ERROR;
-/**
- * ice_free_sq_bufs - Free ATQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
- int i;
-
- /* only unmap if the address is non-NULL */
- for (i = 0; i < cq->num_sq_entries; i++)
- if (cq->sq.r.sq_bi[i].pa) {
- dmam_free_coherent(ice_hw_to_dev(hw),
- cq->sq.r.sq_bi[i].size,
- cq->sq.r.sq_bi[i].va,
- cq->sq.r.sq_bi[i].pa);
- cq->sq.r.sq_bi[i].va = NULL;
- cq->sq.r.sq_bi[i].pa = 0;
- cq->sq.r.sq_bi[i].size = 0;
- }
-
- /* free the buffer info list */
- devm_kfree(ice_hw_to_dev(hw), cq->sq.cmd_buf);
-
- /* free the dma header */
- devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head);
+ return 0;
}
/**
@@ -310,23 +279,7 @@
static enum ice_status
ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
{
- u32 reg = 0;
-
- /* Clear Head and Tail */
- wr32(hw, cq->sq.head, 0);
- wr32(hw, cq->sq.tail, 0);
-
- /* set starting point */
- wr32(hw, cq->sq.len, (cq->num_sq_entries | cq->sq.len_ena_mask));
- wr32(hw, cq->sq.bal, lower_32_bits(cq->sq.desc_buf.pa));
- wr32(hw, cq->sq.bah, upper_32_bits(cq->sq.desc_buf.pa));
-
- /* Check one register to verify that config was applied */
- reg = rd32(hw, cq->sq.bal);
- if (reg != lower_32_bits(cq->sq.desc_buf.pa))
- return ICE_ERR_AQ_ERROR;
-
- return 0;
+ return ice_cfg_cq_regs(hw, &cq->sq, cq->num_sq_entries);
}
/**
@@ -334,30 +287,20 @@
* @hw: pointer to the hardware structure
* @cq: pointer to the specific Control queue
*
- * Configure base address and length registers for the receive (event q)
+ * Configure base address and length registers for the receive (event queue)
*/
static enum ice_status
ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
{
- u32 reg = 0;
+ enum ice_status status;
- /* Clear Head and Tail */
- wr32(hw, cq->rq.head, 0);
- wr32(hw, cq->rq.tail, 0);
-
- /* set starting point */
- wr32(hw, cq->rq.len, (cq->num_rq_entries | cq->rq.len_ena_mask));
- wr32(hw, cq->rq.bal, lower_32_bits(cq->rq.desc_buf.pa));
- wr32(hw, cq->rq.bah, upper_32_bits(cq->rq.desc_buf.pa));
+ status = ice_cfg_cq_regs(hw, &cq->rq, cq->num_rq_entries);
+ if (status)
+ return status;
/* Update tail in the HW to post pre-allocated buffers */
wr32(hw, cq->rq.tail, (u32)(cq->num_rq_entries - 1));
- /* Check one register to verify that config was applied */
- reg = rd32(hw, cq->rq.bal);
- if (reg != lower_32_bits(cq->rq.desc_buf.pa))
- return ICE_ERR_AQ_ERROR;
-
return 0;
}
@@ -367,7 +310,7 @@
* @cq: pointer to the specific Control queue
*
* This is the main initialization routine for the Control Send Queue
- * Prior to calling this function, drivers *MUST* set the following fields
+ * Prior to calling this function, the driver *MUST* set the following fields
* in the cq->structure:
* - cq->num_sq_entries
* - cq->sq_buf_size
@@ -414,7 +357,7 @@
goto init_ctrlq_exit;
init_ctrlq_free_rings:
- ice_free_ctrlq_sq_ring(hw, cq);
+ ice_free_cq_ring(hw, &cq->sq);
init_ctrlq_exit:
return ret_code;
@@ -426,7 +369,7 @@
* @cq: pointer to the specific Control queue
*
* The main initialization routine for the Admin Receive (Event) Queue.
- * Prior to calling this function, drivers *MUST* set the following fields
+ * Prior to calling this function, the driver *MUST* set the following fields
* in the cq->structure:
* - cq->num_rq_entries
* - cq->rq_buf_size
@@ -473,12 +416,33 @@
goto init_ctrlq_exit;
init_ctrlq_free_rings:
- ice_free_ctrlq_rq_ring(hw, cq);
+ ice_free_cq_ring(hw, &cq->rq);
init_ctrlq_exit:
return ret_code;
}
+#define ICE_FREE_CQ_BUFS(hw, qi, ring) \
+do { \
+ int i; \
+ /* free descriptors */ \
+ for (i = 0; i < (qi)->num_##ring##_entries; i++) \
+ if ((qi)->ring.r.ring##_bi[i].pa) { \
+ dmam_free_coherent(ice_hw_to_dev(hw), \
+ (qi)->ring.r.ring##_bi[i].size,\
+ (qi)->ring.r.ring##_bi[i].va,\
+ (qi)->ring.r.ring##_bi[i].pa);\
+ (qi)->ring.r.ring##_bi[i].va = NULL; \
+ (qi)->ring.r.ring##_bi[i].pa = 0; \
+ (qi)->ring.r.ring##_bi[i].size = 0; \
+ } \
+ /* free the buffer info list */ \
+ if ((qi)->ring.cmd_buf) \
+ devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf); \
+ /* free DMA head */ \
+ devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head); \
+} while (0)
+
/**
* ice_shutdown_sq - shutdown the Control ATQ
* @hw: pointer to the hardware structure
@@ -508,8 +472,8 @@
cq->sq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers and the ring itself */
- ice_free_sq_bufs(hw, cq);
- ice_free_ctrlq_sq_ring(hw, cq);
+ ICE_FREE_CQ_BUFS(hw, cq, sq);
+ ice_free_cq_ring(hw, &cq->sq);
shutdown_sq_out:
mutex_unlock(&cq->sq_lock);
@@ -576,8 +540,8 @@
cq->rq.count = 0;
/* free ring buffers and the ring itself */
- ice_free_rq_bufs(hw, cq);
- ice_free_ctrlq_rq_ring(hw, cq);
+ ICE_FREE_CQ_BUFS(hw, cq, rq);
+ ice_free_cq_ring(hw, &cq->rq);
shutdown_rq_out:
mutex_unlock(&cq->rq_lock);
@@ -605,14 +569,8 @@
return 0;
init_ctrlq_free_rq:
- if (cq->rq.head) {
- ice_shutdown_rq(hw, cq);
- mutex_destroy(&cq->rq_lock);
- }
- if (cq->sq.head) {
- ice_shutdown_sq(hw, cq);
- mutex_destroy(&cq->sq_lock);
- }
+ ice_shutdown_rq(hw, cq);
+ ice_shutdown_sq(hw, cq);
return status;
}
@@ -621,13 +579,14 @@
* @hw: pointer to the hardware structure
* @q_type: specific Control queue type
*
- * Prior to calling this function, drivers *MUST* set the following fields
+ * Prior to calling this function, the driver *MUST* set the following fields
* in the cq->structure:
* - cq->num_sq_entries
* - cq->num_rq_entries
* - cq->rq_buf_size
* - cq->sq_buf_size
*
+ * NOTE: this function does not initialize the controlq locks
*/
static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
{
@@ -639,6 +598,10 @@
ice_adminq_init_regs(hw);
cq = &hw->adminq;
break;
+ case ICE_CTL_Q_MAILBOX:
+ ice_mailbox_init_regs(hw);
+ cq = &hw->mailboxq;
+ break;
default:
return ICE_ERR_PARAM;
}
@@ -649,8 +612,6 @@
!cq->rq_buf_size || !cq->sq_buf_size) {
return ICE_ERR_CFG;
}
- mutex_init(&cq->sq_lock);
- mutex_init(&cq->rq_lock);
/* setup SQ command write back timeout */
cq->sq_cmd_timeout = ICE_CTL_Q_SQ_CMD_TIMEOUT;
@@ -658,7 +619,7 @@
/* allocate the ATQ */
ret_code = ice_init_sq(hw, cq);
if (ret_code)
- goto init_ctrlq_destroy_locks;
+ return ret_code;
/* allocate the ARQ */
ret_code = ice_init_rq(hw, cq);
@@ -670,9 +631,6 @@
init_ctrlq_free_sq:
ice_shutdown_sq(hw, cq);
-init_ctrlq_destroy_locks:
- mutex_destroy(&cq->sq_lock);
- mutex_destroy(&cq->rq_lock);
return ret_code;
}
@@ -680,12 +638,14 @@
* ice_init_all_ctrlq - main initialization routine for all control queues
* @hw: pointer to the hardware structure
*
- * Prior to calling this function, drivers *MUST* set the following fields
+ * Prior to calling this function, the driver MUST* set the following fields
* in the cq->structure for all control queues:
* - cq->num_sq_entries
* - cq->num_rq_entries
* - cq->rq_buf_size
* - cq->sq_buf_size
+ *
+ * NOTE: this function does not initialize the controlq locks.
*/
enum ice_status ice_init_all_ctrlq(struct ice_hw *hw)
{
@@ -696,13 +656,56 @@
if (ret_code)
return ret_code;
- return ice_init_check_adminq(hw);
+ ret_code = ice_init_check_adminq(hw);
+ if (ret_code)
+ return ret_code;
+
+ /* Init Mailbox queue */
+ return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX);
+}
+
+/**
+ * ice_init_ctrlq_locks - Initialize locks for a control queue
+ * @cq: pointer to the control queue
+ *
+ * Initializes the send and receive queue locks for a given control queue.
+ */
+static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq)
+{
+ mutex_init(&cq->sq_lock);
+ mutex_init(&cq->rq_lock);
+}
+
+/**
+ * ice_create_all_ctrlq - main initialization routine for all control queues
+ * @hw: pointer to the hardware structure
+ *
+ * Prior to calling this function, the driver *MUST* set the following fields
+ * in the cq->structure for all control queues:
+ * - cq->num_sq_entries
+ * - cq->num_rq_entries
+ * - cq->rq_buf_size
+ * - cq->sq_buf_size
+ *
+ * This function creates all the control queue locks and then calls
+ * ice_init_all_ctrlq. It should be called once during driver load. If the
+ * driver needs to re-initialize control queues at run time it should call
+ * ice_init_all_ctrlq instead.
+ */
+enum ice_status ice_create_all_ctrlq(struct ice_hw *hw)
+{
+ ice_init_ctrlq_locks(&hw->adminq);
+ ice_init_ctrlq_locks(&hw->mailboxq);
+
+ return ice_init_all_ctrlq(hw);
}
/**
* ice_shutdown_ctrlq - shutdown routine for any control queue
* @hw: pointer to the hardware structure
* @q_type: specific Control queue type
+ *
+ * NOTE: this function does not destroy the control queue locks.
*/
static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
{
@@ -714,28 +717,62 @@
if (ice_check_sq_alive(hw, cq))
ice_aq_q_shutdown(hw, true);
break;
+ case ICE_CTL_Q_MAILBOX:
+ cq = &hw->mailboxq;
+ break;
default:
return;
}
- if (cq->sq.head) {
- ice_shutdown_sq(hw, cq);
- mutex_destroy(&cq->sq_lock);
- }
- if (cq->rq.head) {
- ice_shutdown_rq(hw, cq);
- mutex_destroy(&cq->rq_lock);
- }
+ ice_shutdown_sq(hw, cq);
+ ice_shutdown_rq(hw, cq);
}
/**
* ice_shutdown_all_ctrlq - shutdown routine for all control queues
* @hw: pointer to the hardware structure
+ *
+ * NOTE: this function does not destroy the control queue locks. The driver
+ * may call this at runtime to shutdown and later restart control queues, such
+ * as in response to a reset event.
*/
void ice_shutdown_all_ctrlq(struct ice_hw *hw)
{
/* Shutdown FW admin queue */
ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+ /* Shutdown PF-VF Mailbox */
+ ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
+}
+
+/**
+ * ice_destroy_ctrlq_locks - Destroy locks for a control queue
+ * @cq: pointer to the control queue
+ *
+ * Destroys the send and receive queue locks for a given control queue.
+ */
+static void
+ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq)
+{
+ mutex_destroy(&cq->sq_lock);
+ mutex_destroy(&cq->rq_lock);
+}
+
+/**
+ * ice_destroy_all_ctrlq - exit routine for all control queues
+ * @hw: pointer to the hardware structure
+ *
+ * This function shuts down all the control queues and then destroys the
+ * control queue locks. It should be called once during driver unload. The
+ * driver should call ice_shutdown_all_ctrlq if it needs to shut down and
+ * reinitialize control queues, such as in response to a reset event.
+ */
+void ice_destroy_all_ctrlq(struct ice_hw *hw)
+{
+ /* shut down all the control queues first */
+ ice_shutdown_all_ctrlq(hw);
+
+ ice_destroy_ctrlq_locks(&hw->adminq);
+ ice_destroy_ctrlq_locks(&hw->mailboxq);
}
/**
@@ -774,7 +811,7 @@
/**
* ice_sq_done - check if FW has processed the Admin Send Queue (ATQ)
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @cq: pointer to the specific Control queue
*
* Returns true if the firmware has processed all descriptors on the
@@ -790,14 +827,14 @@
/**
* ice_sq_send_cmd - send command to Control Queue (ATQ)
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @cq: pointer to the specific Control queue
* @desc: prefilled descriptor describing the command (non DMA mem)
* @buf: buffer to use for indirect commands (or NULL for direct commands)
* @buf_size: size of buffer for indirect commands (or 0 for direct commands)
* @cd: pointer to command details structure
*
- * This is the main send command routine for the ATQ. It runs the q,
+ * This is the main send command routine for the ATQ. It runs the queue,
* cleans the queue, etc.
*/
enum ice_status
@@ -814,6 +851,9 @@
u16 retval = 0;
u32 val = 0;
+ /* if reset is in progress return a soft error */
+ if (hw->reset_ongoing)
+ return ICE_ERR_RESET_ONGOING;
mutex_lock(&cq->sq_lock);
cq->sq_last_status = ICE_AQ_RC_OK;
@@ -855,7 +895,7 @@
details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use);
if (cd)
- memcpy(details, cd, sizeof(*details));
+ *details = *cd;
else
memset(details, 0, sizeof(*details));
@@ -982,13 +1022,13 @@
/**
* ice_clean_rq_elem
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @cq: pointer to the specific Control queue
* @e: event info from the receive descriptor, includes any buffers
* @pending: number of events that could be left to process
*
* This function cleans one Admin Receive Queue element and returns
- * the contents through e. It can also return how many events are
+ * the contents through e. It can also return how many events are
* left to process through 'pending'.
*/
enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index ea02b89..44945c2 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -8,6 +8,7 @@
/* Maximum buffer lengths for all control queue types */
#define ICE_AQ_MAX_BUF_LEN 4096
+#define ICE_MBXQ_MAX_BUF_LEN 4096
#define ICE_CTL_Q_DESC(R, i) \
(&(((struct ice_aq_desc *)((R).desc_buf.va))[i]))
@@ -18,23 +19,23 @@
/* Defines that help manage the driver vs FW API checks.
* Take a look at ice_aq_ver_check in ice_controlq.c for actual usage.
- *
*/
#define EXP_FW_API_VER_BRANCH 0x00
-#define EXP_FW_API_VER_MAJOR 0x00
-#define EXP_FW_API_VER_MINOR 0x01
+#define EXP_FW_API_VER_MAJOR 0x01
+#define EXP_FW_API_VER_MINOR 0x03
/* Different control queue types: These are mainly for SW consumption. */
enum ice_ctl_q {
ICE_CTL_Q_UNKNOWN = 0,
ICE_CTL_Q_ADMIN,
+ ICE_CTL_Q_MAILBOX,
};
/* Control Queue default settings */
#define ICE_CTL_Q_SQ_CMD_TIMEOUT 250 /* msecs */
struct ice_ctl_q_ring {
- void *dma_head; /* Virtual address to dma head */
+ void *dma_head; /* Virtual address to DMA head */
struct ice_dma_mem desc_buf; /* descriptor ring memory */
void *cmd_buf; /* command buffer memory */
@@ -78,6 +79,7 @@
/* Control Queue information */
struct ice_ctl_q_info {
enum ice_ctl_q qtype;
+ enum ice_aq_err rq_last_status; /* last status on receive queue */
struct ice_ctl_q_ring rq; /* receive queue */
struct ice_ctl_q_ring sq; /* send queue */
u32 sq_cmd_timeout; /* send queue cmd write back timeout */
@@ -85,10 +87,9 @@
u16 num_sq_entries; /* send queue depth */
u16 rq_buf_size; /* receive queue buffer size */
u16 sq_buf_size; /* send queue buffer size */
+ enum ice_aq_err sq_last_status; /* last status on send queue */
struct mutex sq_lock; /* Send queue lock */
struct mutex rq_lock; /* Receive queue lock */
- enum ice_aq_err sq_last_status; /* last status on send queue */
- enum ice_aq_err rq_last_status; /* last status on receive queue */
};
#endif /* _ICE_CONTROLQ_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
new file mode 100644
index 0000000..dd7efff
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -0,0 +1,1441 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_sched.h"
+#include "ice_dcb.h"
+
+/**
+ * ice_aq_get_lldp_mib
+ * @hw: pointer to the HW struct
+ * @bridge_type: type of bridge requested
+ * @mib_type: Local, Remote or both Local and Remote MIBs
+ * @buf: pointer to the caller-supplied buffer to store the MIB block
+ * @buf_size: size of the buffer (in bytes)
+ * @local_len: length of the returned Local LLDP MIB
+ * @remote_len: length of the returned Remote LLDP MIB
+ * @cd: pointer to command details structure or NULL
+ *
+ * Requests the complete LLDP MIB (entire packet). (0x0A00)
+ */
+static enum ice_status
+ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
+ u16 buf_size, u16 *local_len, u16 *remote_len,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_get_mib *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ cmd = &desc.params.lldp_get_mib;
+
+ if (buf_size == 0 || !buf)
+ return ICE_ERR_PARAM;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib);
+
+ cmd->type = mib_type & ICE_AQ_LLDP_MIB_TYPE_M;
+ cmd->type |= (bridge_type << ICE_AQ_LLDP_BRID_TYPE_S) &
+ ICE_AQ_LLDP_BRID_TYPE_M;
+
+ desc.datalen = cpu_to_le16(buf_size);
+
+ status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+ if (!status) {
+ if (local_len)
+ *local_len = le16_to_cpu(cmd->local_len);
+ if (remote_len)
+ *remote_len = le16_to_cpu(cmd->remote_len);
+ }
+
+ return status;
+}
+
+/**
+ * ice_aq_cfg_lldp_mib_change
+ * @hw: pointer to the HW struct
+ * @ena_update: Enable or Disable event posting
+ * @cd: pointer to command details structure or NULL
+ *
+ * Enable or Disable posting of an event on ARQ when LLDP MIB
+ * associated with the interface changes (0x0A01)
+ */
+static enum ice_status
+ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_set_mib_change *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.lldp_set_event;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_mib_change);
+
+ if (!ena_update)
+ cmd->command |= ICE_AQ_LLDP_MIB_UPDATE_DIS;
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_stop_lldp
+ * @hw: pointer to the HW struct
+ * @shutdown_lldp_agent: True if LLDP Agent needs to be Shutdown
+ * False if LLDP Agent needs to be Stopped
+ * @persist: True if Stop/Shutdown of LLDP Agent needs to be persistent across
+ * reboots
+ * @cd: pointer to command details structure or NULL
+ *
+ * Stop or Shutdown the embedded LLDP Agent (0x0A05)
+ */
+enum ice_status
+ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_stop *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.lldp_stop;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_stop);
+
+ if (shutdown_lldp_agent)
+ cmd->command |= ICE_AQ_LLDP_AGENT_SHUTDOWN;
+
+ if (persist)
+ cmd->command |= ICE_AQ_LLDP_AGENT_PERSIST_DIS;
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_start_lldp
+ * @hw: pointer to the HW struct
+ * @persist: True if Start of LLDP Agent needs to be persistent across reboots
+ * @cd: pointer to command details structure or NULL
+ *
+ * Start the embedded LLDP Agent on all ports. (0x0A06)
+ */
+enum ice_status
+ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_start *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.lldp_start;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_start);
+
+ cmd->command = ICE_AQ_LLDP_AGENT_START;
+
+ if (persist)
+ cmd->command |= ICE_AQ_LLDP_AGENT_PERSIST_ENA;
+
+ return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_lldp_mib - Set the LLDP MIB
+ * @hw: pointer to the HW struct
+ * @mib_type: Local, Remote or both Local and Remote MIBs
+ * @buf: pointer to the caller-supplied buffer to store the MIB block
+ * @buf_size: size of the buffer (in bytes)
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set the LLDP MIB. (0x0A08)
+ */
+static enum ice_status
+ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_set_local_mib *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.lldp_set_mib;
+
+ if (buf_size == 0 || !buf)
+ return ICE_ERR_PARAM;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib);
+
+ desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD);
+ desc.datalen = cpu_to_le16(buf_size);
+
+ cmd->type = mib_type;
+ cmd->length = cpu_to_le16(buf_size);
+
+ return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+}
+
+/**
+ * ice_get_dcbx_status
+ * @hw: pointer to the HW struct
+ *
+ * Get the DCBX status from the Firmware
+ */
+static u8 ice_get_dcbx_status(struct ice_hw *hw)
+{
+ u32 reg;
+
+ reg = rd32(hw, PRTDCB_GENS);
+ return (u8)((reg & PRTDCB_GENS_DCBX_STATUS_M) >>
+ PRTDCB_GENS_DCBX_STATUS_S);
+}
+
+/**
+ * ice_parse_ieee_ets_common_tlv
+ * @buf: Data buffer to be parsed for ETS CFG/REC data
+ * @ets_cfg: Container to store parsed data
+ *
+ * Parses the common data of IEEE 802.1Qaz ETS CFG/REC TLV
+ */
+static void
+ice_parse_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg)
+{
+ u8 offset = 0;
+ int i;
+
+ /* Priority Assignment Table (4 octets)
+ * Octets:| 1 | 2 | 3 | 4 |
+ * -----------------------------------------
+ * |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+ * -----------------------------------------
+ * Bits:|7 4|3 0|7 4|3 0|7 4|3 0|7 4|3 0|
+ * -----------------------------------------
+ */
+ for (i = 0; i < 4; i++) {
+ ets_cfg->prio_table[i * 2] =
+ ((buf[offset] & ICE_IEEE_ETS_PRIO_1_M) >>
+ ICE_IEEE_ETS_PRIO_1_S);
+ ets_cfg->prio_table[i * 2 + 1] =
+ ((buf[offset] & ICE_IEEE_ETS_PRIO_0_M) >>
+ ICE_IEEE_ETS_PRIO_0_S);
+ offset++;
+ }
+
+ /* TC Bandwidth Table (8 octets)
+ * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+ * ---------------------------------
+ * |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+ * ---------------------------------
+ *
+ * TSA Assignment Table (8 octets)
+ * Octets:| 9 | 10| 11| 12| 13| 14| 15| 16|
+ * ---------------------------------
+ * |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+ * ---------------------------------
+ */
+ ice_for_each_traffic_class(i) {
+ ets_cfg->tcbwtable[i] = buf[offset];
+ ets_cfg->tsatable[i] = buf[ICE_MAX_TRAFFIC_CLASS + offset++];
+ }
+}
+
+/**
+ * ice_parse_ieee_etscfg_tlv
+ * @tlv: IEEE 802.1Qaz ETS CFG TLV
+ * @dcbcfg: Local store to update ETS CFG data
+ *
+ * Parses IEEE 802.1Qaz ETS CFG TLV
+ */
+static void
+ice_parse_ieee_etscfg_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_dcb_ets_cfg *etscfg;
+ u8 *buf = tlv->tlvinfo;
+
+ /* First Octet post subtype
+ * --------------------------
+ * |will-|CBS | Re- | Max |
+ * |ing | |served| TCs |
+ * --------------------------
+ * |1bit | 1bit|3 bits|3bits|
+ */
+ etscfg = &dcbcfg->etscfg;
+ etscfg->willing = ((buf[0] & ICE_IEEE_ETS_WILLING_M) >>
+ ICE_IEEE_ETS_WILLING_S);
+ etscfg->cbs = ((buf[0] & ICE_IEEE_ETS_CBS_M) >> ICE_IEEE_ETS_CBS_S);
+ etscfg->maxtcs = ((buf[0] & ICE_IEEE_ETS_MAXTC_M) >>
+ ICE_IEEE_ETS_MAXTC_S);
+
+ /* Begin parsing at Priority Assignment Table (offset 1 in buf) */
+ ice_parse_ieee_ets_common_tlv(&buf[1], etscfg);
+}
+
+/**
+ * ice_parse_ieee_etsrec_tlv
+ * @tlv: IEEE 802.1Qaz ETS REC TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Parses IEEE 802.1Qaz ETS REC TLV
+ */
+static void
+ice_parse_ieee_etsrec_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u8 *buf = tlv->tlvinfo;
+
+ /* Begin parsing at Priority Assignment Table (offset 1 in buf) */
+ ice_parse_ieee_ets_common_tlv(&buf[1], &dcbcfg->etsrec);
+}
+
+/**
+ * ice_parse_ieee_pfccfg_tlv
+ * @tlv: IEEE 802.1Qaz PFC CFG TLV
+ * @dcbcfg: Local store to update PFC CFG data
+ *
+ * Parses IEEE 802.1Qaz PFC CFG TLV
+ */
+static void
+ice_parse_ieee_pfccfg_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u8 *buf = tlv->tlvinfo;
+
+ /* ----------------------------------------
+ * |will-|MBC | Re- | PFC | PFC Enable |
+ * |ing | |served| cap | |
+ * -----------------------------------------
+ * |1bit | 1bit|2 bits|4bits| 1 octet |
+ */
+ dcbcfg->pfc.willing = ((buf[0] & ICE_IEEE_PFC_WILLING_M) >>
+ ICE_IEEE_PFC_WILLING_S);
+ dcbcfg->pfc.mbc = ((buf[0] & ICE_IEEE_PFC_MBC_M) >> ICE_IEEE_PFC_MBC_S);
+ dcbcfg->pfc.pfccap = ((buf[0] & ICE_IEEE_PFC_CAP_M) >>
+ ICE_IEEE_PFC_CAP_S);
+ dcbcfg->pfc.pfcena = buf[1];
+}
+
+/**
+ * ice_parse_ieee_app_tlv
+ * @tlv: IEEE 802.1Qaz APP TLV
+ * @dcbcfg: Local store to update APP PRIO data
+ *
+ * Parses IEEE 802.1Qaz APP PRIO TLV
+ */
+static void
+ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u16 offset = 0;
+ u16 typelen;
+ int i = 0;
+ u16 len;
+ u8 *buf;
+
+ typelen = ntohs(tlv->typelen);
+ len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+ buf = tlv->tlvinfo;
+
+ /* Removing sizeof(ouisubtype) and reserved byte from len.
+ * Remaining len div 3 is number of APP TLVs.
+ */
+ len -= (sizeof(tlv->ouisubtype) + 1);
+
+ /* Move offset to App Priority Table */
+ offset++;
+
+ /* Application Priority Table (3 octets)
+ * Octets:| 1 | 2 | 3 |
+ * -----------------------------------------
+ * |Priority|Rsrvd| Sel | Protocol ID |
+ * -----------------------------------------
+ * Bits:|23 21|20 19|18 16|15 0|
+ * -----------------------------------------
+ */
+ while (offset < len) {
+ dcbcfg->app[i].priority = ((buf[offset] &
+ ICE_IEEE_APP_PRIO_M) >>
+ ICE_IEEE_APP_PRIO_S);
+ dcbcfg->app[i].selector = ((buf[offset] &
+ ICE_IEEE_APP_SEL_M) >>
+ ICE_IEEE_APP_SEL_S);
+ dcbcfg->app[i].prot_id = (buf[offset + 1] << 0x8) |
+ buf[offset + 2];
+ /* Move to next app */
+ offset += 3;
+ i++;
+ if (i >= ICE_DCBX_MAX_APPS)
+ break;
+ }
+
+ dcbcfg->numapps = i;
+}
+
+/**
+ * ice_parse_ieee_tlv
+ * @tlv: IEEE 802.1Qaz TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Get the TLV subtype and send it to parsing function
+ * based on the subtype value
+ */
+static void
+ice_parse_ieee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ u32 ouisubtype;
+ u8 subtype;
+
+ ouisubtype = ntohl(tlv->ouisubtype);
+ subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
+ ICE_LLDP_TLV_SUBTYPE_S);
+ switch (subtype) {
+ case ICE_IEEE_SUBTYPE_ETS_CFG:
+ ice_parse_ieee_etscfg_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_SUBTYPE_ETS_REC:
+ ice_parse_ieee_etsrec_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_SUBTYPE_PFC_CFG:
+ ice_parse_ieee_pfccfg_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_SUBTYPE_APP_PRI:
+ ice_parse_ieee_app_tlv(tlv, dcbcfg);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * ice_parse_cee_pgcfg_tlv
+ * @tlv: CEE DCBX PG CFG TLV
+ * @dcbcfg: Local store to update ETS CFG data
+ *
+ * Parses CEE DCBX PG CFG TLV
+ */
+static void
+ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_dcb_ets_cfg *etscfg;
+ u8 *buf = tlv->tlvinfo;
+ u16 offset = 0;
+ int i;
+
+ etscfg = &dcbcfg->etscfg;
+
+ if (tlv->en_will_err & ICE_CEE_FEAT_TLV_WILLING_M)
+ etscfg->willing = 1;
+
+ etscfg->cbs = 0;
+ /* Priority Group Table (4 octets)
+ * Octets:| 1 | 2 | 3 | 4 |
+ * -----------------------------------------
+ * |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+ * -----------------------------------------
+ * Bits:|7 4|3 0|7 4|3 0|7 4|3 0|7 4|3 0|
+ * -----------------------------------------
+ */
+ for (i = 0; i < 4; i++) {
+ etscfg->prio_table[i * 2] =
+ ((buf[offset] & ICE_CEE_PGID_PRIO_1_M) >>
+ ICE_CEE_PGID_PRIO_1_S);
+ etscfg->prio_table[i * 2 + 1] =
+ ((buf[offset] & ICE_CEE_PGID_PRIO_0_M) >>
+ ICE_CEE_PGID_PRIO_0_S);
+ offset++;
+ }
+
+ /* PG Percentage Table (8 octets)
+ * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+ * ---------------------------------
+ * |pg0|pg1|pg2|pg3|pg4|pg5|pg6|pg7|
+ * ---------------------------------
+ */
+ ice_for_each_traffic_class(i) {
+ etscfg->tcbwtable[i] = buf[offset++];
+
+ if (etscfg->prio_table[i] == ICE_CEE_PGID_STRICT)
+ dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT;
+ else
+ dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS;
+ }
+
+ /* Number of TCs supported (1 octet) */
+ etscfg->maxtcs = buf[offset];
+}
+
+/**
+ * ice_parse_cee_pfccfg_tlv
+ * @tlv: CEE DCBX PFC CFG TLV
+ * @dcbcfg: Local store to update PFC CFG data
+ *
+ * Parses CEE DCBX PFC CFG TLV
+ */
+static void
+ice_parse_cee_pfccfg_tlv(struct ice_cee_feat_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u8 *buf = tlv->tlvinfo;
+
+ if (tlv->en_will_err & ICE_CEE_FEAT_TLV_WILLING_M)
+ dcbcfg->pfc.willing = 1;
+
+ /* ------------------------
+ * | PFC Enable | PFC TCs |
+ * ------------------------
+ * | 1 octet | 1 octet |
+ */
+ dcbcfg->pfc.pfcena = buf[0];
+ dcbcfg->pfc.pfccap = buf[1];
+}
+
+/**
+ * ice_parse_cee_app_tlv
+ * @tlv: CEE DCBX APP TLV
+ * @dcbcfg: Local store to update APP PRIO data
+ *
+ * Parses CEE DCBX APP PRIO TLV
+ */
+static void
+ice_parse_cee_app_tlv(struct ice_cee_feat_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ u16 len, typelen, offset = 0;
+ struct ice_cee_app_prio *app;
+ u8 i;
+
+ typelen = ntohs(tlv->hdr.typelen);
+ len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+
+ dcbcfg->numapps = len / sizeof(*app);
+ if (!dcbcfg->numapps)
+ return;
+ if (dcbcfg->numapps > ICE_DCBX_MAX_APPS)
+ dcbcfg->numapps = ICE_DCBX_MAX_APPS;
+
+ for (i = 0; i < dcbcfg->numapps; i++) {
+ u8 up, selector;
+
+ app = (struct ice_cee_app_prio *)(tlv->tlvinfo + offset);
+ for (up = 0; up < ICE_MAX_USER_PRIORITY; up++)
+ if (app->prio_map & BIT(up))
+ break;
+
+ dcbcfg->app[i].priority = up;
+
+ /* Get Selector from lower 2 bits, and convert to IEEE */
+ selector = (app->upper_oui_sel & ICE_CEE_APP_SELECTOR_M);
+ switch (selector) {
+ case ICE_CEE_APP_SEL_ETHTYPE:
+ dcbcfg->app[i].selector = ICE_APP_SEL_ETHTYPE;
+ break;
+ case ICE_CEE_APP_SEL_TCPIP:
+ dcbcfg->app[i].selector = ICE_APP_SEL_TCPIP;
+ break;
+ default:
+ /* Keep selector as it is for unknown types */
+ dcbcfg->app[i].selector = selector;
+ }
+
+ dcbcfg->app[i].prot_id = ntohs(app->protocol);
+ /* Move to next app */
+ offset += sizeof(*app);
+ }
+}
+
+/**
+ * ice_parse_cee_tlv
+ * @tlv: CEE DCBX TLV
+ * @dcbcfg: Local store to update DCBX config data
+ *
+ * Get the TLV subtype and send it to parsing function
+ * based on the subtype value
+ */
+static void
+ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_cee_feat_tlv *sub_tlv;
+ u8 subtype, feat_tlv_count = 0;
+ u16 len, tlvlen, typelen;
+ u32 ouisubtype;
+
+ ouisubtype = ntohl(tlv->ouisubtype);
+ subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
+ ICE_LLDP_TLV_SUBTYPE_S);
+ /* Return if not CEE DCBX */
+ if (subtype != ICE_CEE_DCBX_TYPE)
+ return;
+
+ typelen = ntohs(tlv->typelen);
+ tlvlen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+ len = sizeof(tlv->typelen) + sizeof(ouisubtype) +
+ sizeof(struct ice_cee_ctrl_tlv);
+ /* Return if no CEE DCBX Feature TLVs */
+ if (tlvlen <= len)
+ return;
+
+ sub_tlv = (struct ice_cee_feat_tlv *)((char *)tlv + len);
+ while (feat_tlv_count < ICE_CEE_MAX_FEAT_TYPE) {
+ u16 sublen;
+
+ typelen = ntohs(sub_tlv->hdr.typelen);
+ sublen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+ subtype = (u8)((typelen & ICE_LLDP_TLV_TYPE_M) >>
+ ICE_LLDP_TLV_TYPE_S);
+ switch (subtype) {
+ case ICE_CEE_SUBTYPE_PG_CFG:
+ ice_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg);
+ break;
+ case ICE_CEE_SUBTYPE_PFC_CFG:
+ ice_parse_cee_pfccfg_tlv(sub_tlv, dcbcfg);
+ break;
+ case ICE_CEE_SUBTYPE_APP_PRI:
+ ice_parse_cee_app_tlv(sub_tlv, dcbcfg);
+ break;
+ default:
+ return; /* Invalid Sub-type return */
+ }
+ feat_tlv_count++;
+ /* Move to next sub TLV */
+ sub_tlv = (struct ice_cee_feat_tlv *)
+ ((char *)sub_tlv + sizeof(sub_tlv->hdr.typelen) +
+ sublen);
+ }
+}
+
+/**
+ * ice_parse_org_tlv
+ * @tlv: Organization specific TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Currently only IEEE 802.1Qaz TLV is supported, all others
+ * will be returned
+ */
+static void
+ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ u32 ouisubtype;
+ u32 oui;
+
+ ouisubtype = ntohl(tlv->ouisubtype);
+ oui = ((ouisubtype & ICE_LLDP_TLV_OUI_M) >> ICE_LLDP_TLV_OUI_S);
+ switch (oui) {
+ case ICE_IEEE_8021QAZ_OUI:
+ ice_parse_ieee_tlv(tlv, dcbcfg);
+ break;
+ case ICE_CEE_DCBX_OUI:
+ ice_parse_cee_tlv(tlv, dcbcfg);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * ice_lldp_to_dcb_cfg
+ * @lldpmib: LLDPDU to be parsed
+ * @dcbcfg: store for LLDPDU data
+ *
+ * Parse DCB configuration from the LLDPDU
+ */
+static enum ice_status
+ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_lldp_org_tlv *tlv;
+ enum ice_status ret = 0;
+ u16 offset = 0;
+ u16 typelen;
+ u16 type;
+ u16 len;
+
+ if (!lldpmib || !dcbcfg)
+ return ICE_ERR_PARAM;
+
+ /* set to the start of LLDPDU */
+ lldpmib += ETH_HLEN;
+ tlv = (struct ice_lldp_org_tlv *)lldpmib;
+ while (1) {
+ typelen = ntohs(tlv->typelen);
+ type = ((typelen & ICE_LLDP_TLV_TYPE_M) >> ICE_LLDP_TLV_TYPE_S);
+ len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+ offset += sizeof(typelen) + len;
+
+ /* END TLV or beyond LLDPDU size */
+ if (type == ICE_TLV_TYPE_END || offset > ICE_LLDPDU_SIZE)
+ break;
+
+ switch (type) {
+ case ICE_TLV_TYPE_ORG:
+ ice_parse_org_tlv(tlv, dcbcfg);
+ break;
+ default:
+ break;
+ }
+
+ /* Move to next TLV */
+ tlv = (struct ice_lldp_org_tlv *)
+ ((char *)tlv + sizeof(tlv->typelen) + len);
+ }
+
+ return ret;
+}
+
+/**
+ * ice_aq_get_dcb_cfg
+ * @hw: pointer to the HW struct
+ * @mib_type: MIB type for the query
+ * @bridgetype: bridge type for the query (remote)
+ * @dcbcfg: store for LLDPDU data
+ *
+ * Query DCB configuration from the firmware
+ */
+enum ice_status
+ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ enum ice_status ret;
+ u8 *lldpmib;
+
+ /* Allocate the LLDPDU */
+ lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL);
+ if (!lldpmib)
+ return ICE_ERR_NO_MEMORY;
+
+ ret = ice_aq_get_lldp_mib(hw, bridgetype, mib_type, (void *)lldpmib,
+ ICE_LLDPDU_SIZE, NULL, NULL, NULL);
+
+ if (!ret)
+ /* Parse LLDP MIB to get DCB configuration */
+ ret = ice_lldp_to_dcb_cfg(lldpmib, dcbcfg);
+
+ devm_kfree(ice_hw_to_dev(hw), lldpmib);
+
+ return ret;
+}
+
+/**
+ * ice_aq_start_stop_dcbx - Start/Stop DCBX service in FW
+ * @hw: pointer to the HW struct
+ * @start_dcbx_agent: True if DCBX Agent needs to be started
+ * False if DCBX Agent needs to be stopped
+ * @dcbx_agent_status: FW indicates back the DCBX agent status
+ * True if DCBX Agent is active
+ * False if DCBX Agent is stopped
+ * @cd: pointer to command details structure or NULL
+ *
+ * Start/Stop the embedded dcbx Agent. In case that this wrapper function
+ * returns ICE_SUCCESS, caller will need to check if FW returns back the same
+ * value as stated in dcbx_agent_status, and react accordingly. (0x0A09)
+ */
+enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
+ bool *dcbx_agent_status, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_lldp_stop_start_specific_agent *cmd;
+ enum ice_status status;
+ struct ice_aq_desc desc;
+ u16 opcode;
+
+ cmd = &desc.params.lldp_agent_ctrl;
+
+ opcode = ice_aqc_opc_lldp_stop_start_specific_agent;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, opcode);
+
+ if (start_dcbx_agent)
+ cmd->command = ICE_AQC_START_STOP_AGENT_START_DCBX;
+
+ status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+
+ *dcbx_agent_status = false;
+
+ if (!status &&
+ cmd->command == ICE_AQC_START_STOP_AGENT_START_DCBX)
+ *dcbx_agent_status = true;
+
+ return status;
+}
+
+/**
+ * ice_aq_get_cee_dcb_cfg
+ * @hw: pointer to the HW struct
+ * @buff: response buffer that stores CEE operational configuration
+ * @cd: pointer to command details structure or NULL
+ *
+ * Get CEE DCBX mode operational configuration from firmware (0x0A07)
+ */
+static enum ice_status
+ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
+ struct ice_aqc_get_cee_dcb_cfg_resp *buff,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aq_desc desc;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cee_dcb_cfg);
+
+ return ice_aq_send_cmd(hw, &desc, (void *)buff, sizeof(*buff), cd);
+}
+
+/**
+ * ice_cee_to_dcb_cfg
+ * @cee_cfg: pointer to CEE configuration struct
+ * @dcbcfg: DCB configuration struct
+ *
+ * Convert CEE configuration from firmware to DCB configuration
+ */
+static void
+ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
+ u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift;
+ u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
+ u8 i, err, sync, oper, app_index, ice_app_sel_type;
+ u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift;
+ u16 ice_app_prot_id_type;
+
+ /* CEE PG data to ETS config */
+ dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
+
+ /* Note that the FW creates the oper_prio_tc nibbles reversed
+ * from those in the CEE Priority Group sub-TLV.
+ */
+ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) {
+ dcbcfg->etscfg.prio_table[i * 2] =
+ ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_0_M) >>
+ ICE_CEE_PGID_PRIO_0_S);
+ dcbcfg->etscfg.prio_table[i * 2 + 1] =
+ ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_1_M) >>
+ ICE_CEE_PGID_PRIO_1_S);
+ }
+
+ ice_for_each_traffic_class(i) {
+ dcbcfg->etscfg.tcbwtable[i] = cee_cfg->oper_tc_bw[i];
+
+ if (dcbcfg->etscfg.prio_table[i] == ICE_CEE_PGID_STRICT) {
+ /* Map it to next empty TC */
+ dcbcfg->etscfg.prio_table[i] = cee_cfg->oper_num_tc - 1;
+ dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT;
+ } else {
+ dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS;
+ }
+ }
+
+ /* CEE PFC data to ETS config */
+ dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en;
+ dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS;
+
+ app_index = 0;
+ for (i = 0; i < 3; i++) {
+ if (i == 0) {
+ /* FCoE APP */
+ ice_aqc_cee_status_mask = ICE_AQC_CEE_FCOE_STATUS_M;
+ ice_aqc_cee_status_shift = ICE_AQC_CEE_FCOE_STATUS_S;
+ ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FCOE_M;
+ ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FCOE_S;
+ ice_app_sel_type = ICE_APP_SEL_ETHTYPE;
+ ice_app_prot_id_type = ICE_APP_PROT_ID_FCOE;
+ } else if (i == 1) {
+ /* iSCSI APP */
+ ice_aqc_cee_status_mask = ICE_AQC_CEE_ISCSI_STATUS_M;
+ ice_aqc_cee_status_shift = ICE_AQC_CEE_ISCSI_STATUS_S;
+ ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_ISCSI_M;
+ ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S;
+ ice_app_sel_type = ICE_APP_SEL_TCPIP;
+ ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI;
+ } else {
+ /* FIP APP */
+ ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M;
+ ice_aqc_cee_status_shift = ICE_AQC_CEE_FIP_STATUS_S;
+ ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FIP_M;
+ ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FIP_S;
+ ice_app_sel_type = ICE_APP_SEL_ETHTYPE;
+ ice_app_prot_id_type = ICE_APP_PROT_ID_FIP;
+ }
+
+ status = (tlv_status & ice_aqc_cee_status_mask) >>
+ ice_aqc_cee_status_shift;
+ err = (status & ICE_TLV_STATUS_ERR) ? 1 : 0;
+ sync = (status & ICE_TLV_STATUS_SYNC) ? 1 : 0;
+ oper = (status & ICE_TLV_STATUS_OPER) ? 1 : 0;
+ /* Add FCoE/iSCSI/FIP APP if Error is False and
+ * Oper/Sync is True
+ */
+ if (!err && sync && oper) {
+ dcbcfg->app[app_index].priority =
+ (app_prio & ice_aqc_cee_app_mask) >>
+ ice_aqc_cee_app_shift;
+ dcbcfg->app[app_index].selector = ice_app_sel_type;
+ dcbcfg->app[app_index].prot_id = ice_app_prot_id_type;
+ app_index++;
+ }
+ }
+
+ dcbcfg->numapps = app_index;
+}
+
+/**
+ * ice_get_ieee_dcb_cfg
+ * @pi: port information structure
+ * @dcbx_mode: mode of DCBX (IEEE or CEE)
+ *
+ * Get IEEE or CEE mode DCB configuration from the Firmware
+ */
+static enum ice_status
+ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode)
+{
+ struct ice_dcbx_cfg *dcbx_cfg = NULL;
+ enum ice_status ret;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ if (dcbx_mode == ICE_DCBX_MODE_IEEE)
+ dcbx_cfg = &pi->local_dcbx_cfg;
+ else if (dcbx_mode == ICE_DCBX_MODE_CEE)
+ dcbx_cfg = &pi->desired_dcbx_cfg;
+
+ /* Get Local DCB Config in case of ICE_DCBX_MODE_IEEE
+ * or get CEE DCB Desired Config in case of ICE_DCBX_MODE_CEE
+ */
+ ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_LOCAL,
+ ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
+ if (ret)
+ goto out;
+
+ /* Get Remote DCB Config */
+ dcbx_cfg = &pi->remote_dcbx_cfg;
+ ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+ ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
+ /* Don't treat ENOENT as an error for Remote MIBs */
+ if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+ ret = 0;
+
+out:
+ return ret;
+}
+
+/**
+ * ice_get_dcb_cfg
+ * @pi: port information structure
+ *
+ * Get DCB configuration from the Firmware
+ */
+enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi)
+{
+ struct ice_aqc_get_cee_dcb_cfg_resp cee_cfg;
+ struct ice_dcbx_cfg *dcbx_cfg;
+ enum ice_status ret;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL);
+ if (!ret) {
+ /* CEE mode */
+ dcbx_cfg = &pi->local_dcbx_cfg;
+ dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE;
+ dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status);
+ ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg);
+ ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
+ } else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
+ /* CEE mode not enabled try querying IEEE data */
+ dcbx_cfg = &pi->local_dcbx_cfg;
+ dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE;
+ ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_IEEE);
+ }
+
+ return ret;
+}
+
+/**
+ * ice_init_dcb
+ * @hw: pointer to the HW struct
+ * @enable_mib_change: enable MIB change event
+ *
+ * Update DCB configuration from the Firmware
+ */
+enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change)
+{
+ struct ice_port_info *pi = hw->port_info;
+ enum ice_status ret = 0;
+
+ if (!hw->func_caps.common_cap.dcb)
+ return ICE_ERR_NOT_SUPPORTED;
+
+ pi->is_sw_lldp = true;
+
+ /* Get DCBX status */
+ pi->dcbx_status = ice_get_dcbx_status(hw);
+
+ if (pi->dcbx_status == ICE_DCBX_STATUS_DONE ||
+ pi->dcbx_status == ICE_DCBX_STATUS_IN_PROGRESS ||
+ pi->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED) {
+ /* Get current DCBX configuration */
+ ret = ice_get_dcb_cfg(pi);
+ pi->is_sw_lldp = (hw->adminq.sq_last_status == ICE_AQ_RC_EPERM);
+ if (ret)
+ return ret;
+ } else if (pi->dcbx_status == ICE_DCBX_STATUS_DIS) {
+ return ICE_ERR_NOT_READY;
+ }
+
+ /* Configure the LLDP MIB change event */
+ if (enable_mib_change) {
+ ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL);
+ if (!ret)
+ pi->is_sw_lldp = false;
+ }
+
+ return ret;
+}
+
+/**
+ * ice_cfg_lldp_mib_change
+ * @hw: pointer to the HW struct
+ * @ena_mib: enable/disable MIB change event
+ *
+ * Configure (disable/enable) MIB
+ */
+enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib)
+{
+ struct ice_port_info *pi = hw->port_info;
+ enum ice_status ret;
+
+ if (!hw->func_caps.common_cap.dcb)
+ return ICE_ERR_NOT_SUPPORTED;
+
+ /* Get DCBX status */
+ pi->dcbx_status = ice_get_dcbx_status(hw);
+
+ if (pi->dcbx_status == ICE_DCBX_STATUS_DIS)
+ return ICE_ERR_NOT_READY;
+
+ ret = ice_aq_cfg_lldp_mib_change(hw, ena_mib, NULL);
+ if (!ret)
+ pi->is_sw_lldp = !ena_mib;
+
+ return ret;
+}
+
+/**
+ * ice_add_ieee_ets_common_tlv
+ * @buf: Data buffer to be populated with ice_dcb_ets_cfg data
+ * @ets_cfg: Container for ice_dcb_ets_cfg data
+ *
+ * Populate the TLV buffer with ice_dcb_ets_cfg data
+ */
+static void
+ice_add_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg)
+{
+ u8 priority0, priority1;
+ u8 offset = 0;
+ int i;
+
+ /* Priority Assignment Table (4 octets)
+ * Octets:| 1 | 2 | 3 | 4 |
+ * -----------------------------------------
+ * |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+ * -----------------------------------------
+ * Bits:|7 4|3 0|7 4|3 0|7 4|3 0|7 4|3 0|
+ * -----------------------------------------
+ */
+ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) {
+ priority0 = ets_cfg->prio_table[i * 2] & 0xF;
+ priority1 = ets_cfg->prio_table[i * 2 + 1] & 0xF;
+ buf[offset] = (priority0 << ICE_IEEE_ETS_PRIO_1_S) | priority1;
+ offset++;
+ }
+
+ /* TC Bandwidth Table (8 octets)
+ * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+ * ---------------------------------
+ * |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+ * ---------------------------------
+ *
+ * TSA Assignment Table (8 octets)
+ * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+ * ---------------------------------
+ * |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+ * ---------------------------------
+ */
+ ice_for_each_traffic_class(i) {
+ buf[offset] = ets_cfg->tcbwtable[i];
+ buf[ICE_MAX_TRAFFIC_CLASS + offset] = ets_cfg->tsatable[i];
+ offset++;
+ }
+}
+
+/**
+ * ice_add_ieee_ets_tlv - Prepare ETS TLV in IEEE format
+ * @tlv: Fill the ETS config data in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Prepare IEEE 802.1Qaz ETS CFG TLV
+ */
+static void
+ice_add_ieee_ets_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_dcb_ets_cfg *etscfg;
+ u8 *buf = tlv->tlvinfo;
+ u8 maxtcwilling = 0;
+ u32 ouisubtype;
+ u16 typelen;
+
+ typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+ ICE_IEEE_ETS_TLV_LEN);
+ tlv->typelen = htons(typelen);
+
+ ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+ ICE_IEEE_SUBTYPE_ETS_CFG);
+ tlv->ouisubtype = htonl(ouisubtype);
+
+ /* First Octet post subtype
+ * --------------------------
+ * |will-|CBS | Re- | Max |
+ * |ing | |served| TCs |
+ * --------------------------
+ * |1bit | 1bit|3 bits|3bits|
+ */
+ etscfg = &dcbcfg->etscfg;
+ if (etscfg->willing)
+ maxtcwilling = BIT(ICE_IEEE_ETS_WILLING_S);
+ maxtcwilling |= etscfg->maxtcs & ICE_IEEE_ETS_MAXTC_M;
+ buf[0] = maxtcwilling;
+
+ /* Begin adding at Priority Assignment Table (offset 1 in buf) */
+ ice_add_ieee_ets_common_tlv(&buf[1], etscfg);
+}
+
+/**
+ * ice_add_ieee_etsrec_tlv - Prepare ETS Recommended TLV in IEEE format
+ * @tlv: Fill ETS Recommended TLV in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Prepare IEEE 802.1Qaz ETS REC TLV
+ */
+static void
+ice_add_ieee_etsrec_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ struct ice_dcb_ets_cfg *etsrec;
+ u8 *buf = tlv->tlvinfo;
+ u32 ouisubtype;
+ u16 typelen;
+
+ typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+ ICE_IEEE_ETS_TLV_LEN);
+ tlv->typelen = htons(typelen);
+
+ ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+ ICE_IEEE_SUBTYPE_ETS_REC);
+ tlv->ouisubtype = htonl(ouisubtype);
+
+ etsrec = &dcbcfg->etsrec;
+
+ /* First Octet is reserved */
+ /* Begin adding at Priority Assignment Table (offset 1 in buf) */
+ ice_add_ieee_ets_common_tlv(&buf[1], etsrec);
+}
+
+/**
+ * ice_add_ieee_pfc_tlv - Prepare PFC TLV in IEEE format
+ * @tlv: Fill PFC TLV in IEEE format
+ * @dcbcfg: Local store which holds the PFC CFG data
+ *
+ * Prepare IEEE 802.1Qaz PFC CFG TLV
+ */
+static void
+ice_add_ieee_pfc_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+ u8 *buf = tlv->tlvinfo;
+ u32 ouisubtype;
+ u16 typelen;
+
+ typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+ ICE_IEEE_PFC_TLV_LEN);
+ tlv->typelen = htons(typelen);
+
+ ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+ ICE_IEEE_SUBTYPE_PFC_CFG);
+ tlv->ouisubtype = htonl(ouisubtype);
+
+ /* ----------------------------------------
+ * |will-|MBC | Re- | PFC | PFC Enable |
+ * |ing | |served| cap | |
+ * -----------------------------------------
+ * |1bit | 1bit|2 bits|4bits| 1 octet |
+ */
+ if (dcbcfg->pfc.willing)
+ buf[0] = BIT(ICE_IEEE_PFC_WILLING_S);
+
+ if (dcbcfg->pfc.mbc)
+ buf[0] |= BIT(ICE_IEEE_PFC_MBC_S);
+
+ buf[0] |= dcbcfg->pfc.pfccap & 0xF;
+ buf[1] = dcbcfg->pfc.pfcena;
+}
+
+/**
+ * ice_add_ieee_app_pri_tlv - Prepare APP TLV in IEEE format
+ * @tlv: Fill APP TLV in IEEE format
+ * @dcbcfg: Local store which holds the APP CFG data
+ *
+ * Prepare IEEE 802.1Qaz APP CFG TLV
+ */
+static void
+ice_add_ieee_app_pri_tlv(struct ice_lldp_org_tlv *tlv,
+ struct ice_dcbx_cfg *dcbcfg)
+{
+ u16 typelen, len, offset = 0;
+ u8 priority, selector, i = 0;
+ u8 *buf = tlv->tlvinfo;
+ u32 ouisubtype;
+
+ /* No APP TLVs then just return */
+ if (dcbcfg->numapps == 0)
+ return;
+ ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+ ICE_IEEE_SUBTYPE_APP_PRI);
+ tlv->ouisubtype = htonl(ouisubtype);
+
+ /* Move offset to App Priority Table */
+ offset++;
+ /* Application Priority Table (3 octets)
+ * Octets:| 1 | 2 | 3 |
+ * -----------------------------------------
+ * |Priority|Rsrvd| Sel | Protocol ID |
+ * -----------------------------------------
+ * Bits:|23 21|20 19|18 16|15 0|
+ * -----------------------------------------
+ */
+ while (i < dcbcfg->numapps) {
+ priority = dcbcfg->app[i].priority & 0x7;
+ selector = dcbcfg->app[i].selector & 0x7;
+ buf[offset] = (priority << ICE_IEEE_APP_PRIO_S) | selector;
+ buf[offset + 1] = (dcbcfg->app[i].prot_id >> 0x8) & 0xFF;
+ buf[offset + 2] = dcbcfg->app[i].prot_id & 0xFF;
+ /* Move to next app */
+ offset += 3;
+ i++;
+ if (i >= ICE_DCBX_MAX_APPS)
+ break;
+ }
+ /* len includes size of ouisubtype + 1 reserved + 3*numapps */
+ len = sizeof(tlv->ouisubtype) + 1 + (i * 3);
+ typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | (len & 0x1FF));
+ tlv->typelen = htons(typelen);
+}
+
+/**
+ * ice_add_dcb_tlv - Add all IEEE TLVs
+ * @tlv: Fill TLV data in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ * @tlvid: Type of IEEE TLV
+ *
+ * Add tlv information
+ */
+static void
+ice_add_dcb_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg,
+ u16 tlvid)
+{
+ switch (tlvid) {
+ case ICE_IEEE_TLV_ID_ETS_CFG:
+ ice_add_ieee_ets_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_TLV_ID_ETS_REC:
+ ice_add_ieee_etsrec_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_TLV_ID_PFC_CFG:
+ ice_add_ieee_pfc_tlv(tlv, dcbcfg);
+ break;
+ case ICE_IEEE_TLV_ID_APP_PRI:
+ ice_add_ieee_app_pri_tlv(tlv, dcbcfg);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * ice_dcb_cfg_to_lldp - Convert DCB configuration to MIB format
+ * @lldpmib: pointer to the HW struct
+ * @miblen: length of LLDP MIB
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Convert the DCB configuration to MIB format
+ */
+static void
+ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg)
+{
+ u16 len, offset = 0, tlvid = ICE_TLV_ID_START;
+ struct ice_lldp_org_tlv *tlv;
+ u16 typelen;
+
+ tlv = (struct ice_lldp_org_tlv *)lldpmib;
+ while (1) {
+ ice_add_dcb_tlv(tlv, dcbcfg, tlvid++);
+ typelen = ntohs(tlv->typelen);
+ len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+ if (len)
+ offset += len + 2;
+ /* END TLV or beyond LLDPDU size */
+ if (tlvid >= ICE_TLV_ID_END_OF_LLDPPDU ||
+ offset > ICE_LLDPDU_SIZE)
+ break;
+ /* Move to next TLV */
+ if (len)
+ tlv = (struct ice_lldp_org_tlv *)
+ ((char *)tlv + sizeof(tlv->typelen) + len);
+ }
+ *miblen = offset;
+}
+
+/**
+ * ice_set_dcb_cfg - Set the local LLDP MIB to FW
+ * @pi: port information structure
+ *
+ * Set DCB configuration to the Firmware
+ */
+enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi)
+{
+ u8 mib_type, *lldpmib = NULL;
+ struct ice_dcbx_cfg *dcbcfg;
+ enum ice_status ret;
+ struct ice_hw *hw;
+ u16 miblen;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+
+ hw = pi->hw;
+
+ /* update the HW local config */
+ dcbcfg = &pi->local_dcbx_cfg;
+ /* Allocate the LLDPDU */
+ lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL);
+ if (!lldpmib)
+ return ICE_ERR_NO_MEMORY;
+
+ mib_type = SET_LOCAL_MIB_TYPE_LOCAL_MIB;
+ if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING)
+ mib_type |= SET_LOCAL_MIB_TYPE_CEE_NON_WILLING;
+
+ ice_dcb_cfg_to_lldp(lldpmib, &miblen, dcbcfg);
+ ret = ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, miblen,
+ NULL);
+
+ devm_kfree(ice_hw_to_dev(hw), lldpmib);
+
+ return ret;
+}
+
+/**
+ * ice_aq_query_port_ets - query port ets configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @cd: pointer to command details structure or NULL
+ *
+ * query current port ets configuration
+ */
+static enum ice_status
+ice_aq_query_port_ets(struct ice_port_info *pi,
+ struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_query_port_ets *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+ cmd = &desc.params.port_ets;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_port_ets);
+ cmd->port_teid = pi->root->info.node_teid;
+
+ status = ice_aq_send_cmd(pi->hw, &desc, buf, buf_size, cd);
+ return status;
+}
+
+/**
+ * ice_update_port_tc_tree_cfg - update TC tree configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ *
+ * update the SW DB with the new TC changes
+ */
+static enum ice_status
+ice_update_port_tc_tree_cfg(struct ice_port_info *pi,
+ struct ice_aqc_port_ets_elem *buf)
+{
+ struct ice_sched_node *node, *tc_node;
+ struct ice_aqc_get_elem elem;
+ enum ice_status status = 0;
+ u32 teid1, teid2;
+ u8 i, j;
+
+ if (!pi)
+ return ICE_ERR_PARAM;
+ /* suspend the missing TC nodes */
+ for (i = 0; i < pi->root->num_children; i++) {
+ teid1 = le32_to_cpu(pi->root->children[i]->info.node_teid);
+ ice_for_each_traffic_class(j) {
+ teid2 = le32_to_cpu(buf->tc_node_teid[j]);
+ if (teid1 == teid2)
+ break;
+ }
+ if (j < ICE_MAX_TRAFFIC_CLASS)
+ continue;
+ /* TC is missing */
+ pi->root->children[i]->in_use = false;
+ }
+ /* add the new TC nodes */
+ ice_for_each_traffic_class(j) {
+ teid2 = le32_to_cpu(buf->tc_node_teid[j]);
+ if (teid2 == ICE_INVAL_TEID)
+ continue;
+ /* Is it already present in the tree ? */
+ for (i = 0; i < pi->root->num_children; i++) {
+ tc_node = pi->root->children[i];
+ if (!tc_node)
+ continue;
+ teid1 = le32_to_cpu(tc_node->info.node_teid);
+ if (teid1 == teid2) {
+ tc_node->tc_num = j;
+ tc_node->in_use = true;
+ break;
+ }
+ }
+ if (i < pi->root->num_children)
+ continue;
+ /* new TC */
+ status = ice_sched_query_elem(pi->hw, teid2, &elem);
+ if (!status)
+ status = ice_sched_add_node(pi, 1, &elem.generic[0]);
+ if (status)
+ break;
+ /* update the TC number */
+ node = ice_sched_find_node_by_teid(pi->root, teid2);
+ if (node)
+ node->tc_num = j;
+ }
+ return status;
+}
+
+/**
+ * ice_query_port_ets - query port ets configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @cd: pointer to command details structure or NULL
+ *
+ * query current port ets configuration and update the
+ * SW DB with the TC changes
+ */
+enum ice_status
+ice_query_port_ets(struct ice_port_info *pi,
+ struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+ struct ice_sq_cd *cd)
+{
+ enum ice_status status;
+
+ mutex_lock(&pi->sched_lock);
+ status = ice_aq_query_port_ets(pi, buf, buf_size, cd);
+ if (!status)
+ status = ice_update_port_tc_tree_cfg(pi, buf);
+ mutex_unlock(&pi->sched_lock);
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h
new file mode 100644
index 0000000..ee138f9
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_DCB_H_
+#define _ICE_DCB_H_
+
+#include "ice_type.h"
+
+#define ICE_DCBX_STATUS_NOT_STARTED 0
+#define ICE_DCBX_STATUS_IN_PROGRESS 1
+#define ICE_DCBX_STATUS_DONE 2
+#define ICE_DCBX_STATUS_DIS 7
+
+#define ICE_TLV_TYPE_END 0
+#define ICE_TLV_TYPE_ORG 127
+
+#define ICE_IEEE_8021QAZ_OUI 0x0080C2
+#define ICE_IEEE_SUBTYPE_ETS_CFG 9
+#define ICE_IEEE_SUBTYPE_ETS_REC 10
+#define ICE_IEEE_SUBTYPE_PFC_CFG 11
+#define ICE_IEEE_SUBTYPE_APP_PRI 12
+
+#define ICE_CEE_DCBX_OUI 0x001B21
+#define ICE_CEE_DCBX_TYPE 2
+#define ICE_CEE_SUBTYPE_PG_CFG 2
+#define ICE_CEE_SUBTYPE_PFC_CFG 3
+#define ICE_CEE_SUBTYPE_APP_PRI 4
+#define ICE_CEE_MAX_FEAT_TYPE 3
+/* Defines for LLDP TLV header */
+#define ICE_LLDP_TLV_LEN_S 0
+#define ICE_LLDP_TLV_LEN_M (0x01FF << ICE_LLDP_TLV_LEN_S)
+#define ICE_LLDP_TLV_TYPE_S 9
+#define ICE_LLDP_TLV_TYPE_M (0x7F << ICE_LLDP_TLV_TYPE_S)
+#define ICE_LLDP_TLV_SUBTYPE_S 0
+#define ICE_LLDP_TLV_SUBTYPE_M (0xFF << ICE_LLDP_TLV_SUBTYPE_S)
+#define ICE_LLDP_TLV_OUI_S 8
+#define ICE_LLDP_TLV_OUI_M (0xFFFFFFUL << ICE_LLDP_TLV_OUI_S)
+
+/* Defines for IEEE ETS TLV */
+#define ICE_IEEE_ETS_MAXTC_S 0
+#define ICE_IEEE_ETS_MAXTC_M (0x7 << ICE_IEEE_ETS_MAXTC_S)
+#define ICE_IEEE_ETS_CBS_S 6
+#define ICE_IEEE_ETS_CBS_M BIT(ICE_IEEE_ETS_CBS_S)
+#define ICE_IEEE_ETS_WILLING_S 7
+#define ICE_IEEE_ETS_WILLING_M BIT(ICE_IEEE_ETS_WILLING_S)
+#define ICE_IEEE_ETS_PRIO_0_S 0
+#define ICE_IEEE_ETS_PRIO_0_M (0x7 << ICE_IEEE_ETS_PRIO_0_S)
+#define ICE_IEEE_ETS_PRIO_1_S 4
+#define ICE_IEEE_ETS_PRIO_1_M (0x7 << ICE_IEEE_ETS_PRIO_1_S)
+#define ICE_CEE_PGID_PRIO_0_S 0
+#define ICE_CEE_PGID_PRIO_0_M (0xF << ICE_CEE_PGID_PRIO_0_S)
+#define ICE_CEE_PGID_PRIO_1_S 4
+#define ICE_CEE_PGID_PRIO_1_M (0xF << ICE_CEE_PGID_PRIO_1_S)
+#define ICE_CEE_PGID_STRICT 15
+
+/* Defines for IEEE TSA types */
+#define ICE_IEEE_TSA_STRICT 0
+#define ICE_IEEE_TSA_ETS 2
+
+/* Defines for IEEE PFC TLV */
+#define ICE_IEEE_PFC_CAP_S 0
+#define ICE_IEEE_PFC_CAP_M (0xF << ICE_IEEE_PFC_CAP_S)
+#define ICE_IEEE_PFC_MBC_S 6
+#define ICE_IEEE_PFC_MBC_M BIT(ICE_IEEE_PFC_MBC_S)
+#define ICE_IEEE_PFC_WILLING_S 7
+#define ICE_IEEE_PFC_WILLING_M BIT(ICE_IEEE_PFC_WILLING_S)
+
+/* Defines for IEEE APP TLV */
+#define ICE_IEEE_APP_SEL_S 0
+#define ICE_IEEE_APP_SEL_M (0x7 << ICE_IEEE_APP_SEL_S)
+#define ICE_IEEE_APP_PRIO_S 5
+#define ICE_IEEE_APP_PRIO_M (0x7 << ICE_IEEE_APP_PRIO_S)
+
+/* TLV definitions for preparing MIB */
+#define ICE_IEEE_TLV_ID_ETS_CFG 3
+#define ICE_IEEE_TLV_ID_ETS_REC 4
+#define ICE_IEEE_TLV_ID_PFC_CFG 5
+#define ICE_IEEE_TLV_ID_APP_PRI 6
+#define ICE_TLV_ID_END_OF_LLDPPDU 7
+#define ICE_TLV_ID_START ICE_IEEE_TLV_ID_ETS_CFG
+
+#define ICE_IEEE_ETS_TLV_LEN 25
+#define ICE_IEEE_PFC_TLV_LEN 6
+#define ICE_IEEE_APP_TLV_LEN 11
+
+/* IEEE 802.1AB LLDP Organization specific TLV */
+struct ice_lldp_org_tlv {
+ __be16 typelen;
+ __be32 ouisubtype;
+ u8 tlvinfo[1];
+} __packed;
+
+struct ice_cee_tlv_hdr {
+ __be16 typelen;
+ u8 operver;
+ u8 maxver;
+};
+
+struct ice_cee_ctrl_tlv {
+ struct ice_cee_tlv_hdr hdr;
+ __be32 seqno;
+ __be32 ackno;
+};
+
+struct ice_cee_feat_tlv {
+ struct ice_cee_tlv_hdr hdr;
+ u8 en_will_err; /* Bits: |En|Will|Err|Reserved(5)| */
+#define ICE_CEE_FEAT_TLV_ENA_M 0x80
+#define ICE_CEE_FEAT_TLV_WILLING_M 0x40
+#define ICE_CEE_FEAT_TLV_ERR_M 0x20
+ u8 subtype;
+ u8 tlvinfo[1];
+};
+
+struct ice_cee_app_prio {
+ __be16 protocol;
+ u8 upper_oui_sel; /* Bits: |Upper OUI(6)|Selector(2)| */
+#define ICE_CEE_APP_SELECTOR_M 0x03
+ __be16 lower_oui;
+ u8 prio_map;
+} __packed;
+
+enum ice_status
+ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
+ struct ice_dcbx_cfg *dcbcfg);
+enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi);
+enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi);
+enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change);
+enum ice_status
+ice_query_port_ets(struct ice_port_info *pi,
+ struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+ struct ice_sq_cd *cmd_details);
+#ifdef CONFIG_DCB
+enum ice_status
+ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
+ struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
+ bool *dcbx_agent_status, struct ice_sq_cd *cd);
+enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib);
+#else /* CONFIG_DCB */
+static inline enum ice_status
+ice_aq_stop_lldp(struct ice_hw __always_unused *hw,
+ bool __always_unused shutdown_lldp_agent,
+ bool __always_unused persist,
+ struct ice_sq_cd __always_unused *cd)
+{
+ return 0;
+}
+
+static inline enum ice_status
+ice_aq_start_lldp(struct ice_hw __always_unused *hw,
+ bool __always_unused persist,
+ struct ice_sq_cd __always_unused *cd)
+{
+ return 0;
+}
+
+static inline enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw,
+ bool __always_unused start_dcbx_agent,
+ bool *dcbx_agent_status,
+ struct ice_sq_cd __always_unused *cd)
+{
+ *dcbx_agent_status = false;
+
+ return 0;
+}
+
+static inline enum ice_status
+ice_cfg_lldp_mib_change(struct ice_hw __always_unused *hw,
+ bool __always_unused ena_mib)
+{
+ return 0;
+}
+
+#endif /* CONFIG_DCB */
+#endif /* _ICE_DCB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
new file mode 100644
index 0000000..dd47869
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_dcb_lib.h"
+
+/**
+ * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration
+ * @vsi: the VSI being configured
+ * @ena_tc: TC map to be enabled
+ */
+void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
+{
+ struct net_device *netdev = vsi->netdev;
+ struct ice_pf *pf = vsi->back;
+ struct ice_dcbx_cfg *dcbcfg;
+ u8 netdev_tc;
+ int i;
+
+ if (!netdev)
+ return;
+
+ if (!ena_tc) {
+ netdev_reset_tc(netdev);
+ return;
+ }
+
+ if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc))
+ return;
+
+ dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
+
+ ice_for_each_traffic_class(i)
+ if (vsi->tc_cfg.ena_tc & BIT(i))
+ netdev_set_tc_queue(netdev,
+ vsi->tc_cfg.tc_info[i].netdev_tc,
+ vsi->tc_cfg.tc_info[i].qcount_tx,
+ vsi->tc_cfg.tc_info[i].qoffset);
+
+ for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+ u8 ets_tc = dcbcfg->etscfg.prio_table[i];
+
+ /* Get the mapped netdev TC# for the UP */
+ netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc;
+ netdev_set_prio_tc_map(netdev, i, netdev_tc);
+ }
+}
+
+/**
+ * ice_dcb_get_ena_tc - return bitmap of enabled TCs
+ * @dcbcfg: DCB config to evaluate for enabled TCs
+ */
+u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg)
+{
+ u8 i, num_tc, ena_tc = 1;
+
+ num_tc = ice_dcb_get_num_tc(dcbcfg);
+
+ for (i = 0; i < num_tc; i++)
+ ena_tc |= BIT(i);
+
+ return ena_tc;
+}
+
+/**
+ * ice_dcb_get_num_tc - Get the number of TCs from DCBX config
+ * @dcbcfg: config to retrieve number of TCs from
+ */
+u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg)
+{
+ bool tc_unused = false;
+ u8 num_tc = 0;
+ u8 ret = 0;
+ int i;
+
+ /* Scan the ETS Config Priority Table to find traffic classes
+ * enabled and create a bitmask of enabled TCs
+ */
+ for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
+ num_tc |= BIT(dcbcfg->etscfg.prio_table[i]);
+
+ /* Scan bitmask for contiguous TCs starting with TC0 */
+ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+ if (num_tc & BIT(i)) {
+ if (!tc_unused) {
+ ret++;
+ } else {
+ pr_err("Non-contiguous TCs - Disabling DCB\n");
+ return 1;
+ }
+ } else {
+ tc_unused = true;
+ }
+ }
+
+ /* There is always at least 1 TC */
+ if (!ret)
+ ret = 1;
+
+ return ret;
+}
+
+/**
+ * ice_vsi_cfg_dcb_rings - Update rings to reflect DCB TC
+ * @vsi: VSI owner of rings being updated
+ */
+void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
+{
+ struct ice_ring *tx_ring, *rx_ring;
+ u16 qoffset, qcount;
+ int i, n;
+
+ if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) {
+ /* Reset the TC information */
+ for (i = 0; i < vsi->num_txq; i++) {
+ tx_ring = vsi->tx_rings[i];
+ tx_ring->dcb_tc = 0;
+ }
+ for (i = 0; i < vsi->num_rxq; i++) {
+ rx_ring = vsi->rx_rings[i];
+ rx_ring->dcb_tc = 0;
+ }
+ return;
+ }
+
+ ice_for_each_traffic_class(n) {
+ if (!(vsi->tc_cfg.ena_tc & BIT(n)))
+ break;
+
+ qoffset = vsi->tc_cfg.tc_info[n].qoffset;
+ qcount = vsi->tc_cfg.tc_info[n].qcount_tx;
+ for (i = qoffset; i < (qoffset + qcount); i++) {
+ tx_ring = vsi->tx_rings[i];
+ rx_ring = vsi->rx_rings[i];
+ tx_ring->dcb_tc = n;
+ rx_ring->dcb_tc = n;
+ }
+ }
+}
+
+/**
+ * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs
+ * @pf: pointer to the PF struct
+ *
+ * Assumed caller has already disabled all VSIs before
+ * calling this function. Reconfiguring DCB based on
+ * local_dcbx_cfg.
+ */
+static void ice_pf_dcb_recfg(struct ice_pf *pf)
+{
+ struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
+ u8 tc_map = 0;
+ int v, ret;
+
+ /* Update each VSI */
+ ice_for_each_vsi(pf, v) {
+ if (!pf->vsi[v])
+ continue;
+
+ if (pf->vsi[v]->type == ICE_VSI_PF)
+ tc_map = ice_dcb_get_ena_tc(dcbcfg);
+ else
+ tc_map = ICE_DFLT_TRAFFIC_CLASS;
+
+ ret = ice_vsi_cfg_tc(pf->vsi[v], tc_map);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to config TC for VSI index: %d\n",
+ pf->vsi[v]->idx);
+ continue;
+ }
+
+ ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+ }
+}
+
+/**
+ * ice_pf_dcb_cfg - Apply new DCB configuration
+ * @pf: pointer to the PF struct
+ * @new_cfg: DCBX config to apply
+ * @locked: is the RTNL held
+ */
+static
+int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
+{
+ struct ice_dcbx_cfg *old_cfg, *curr_cfg;
+ struct ice_aqc_port_ets_elem buf = { 0 };
+ int ret = 0;
+
+ curr_cfg = &pf->hw.port_info->local_dcbx_cfg;
+
+ /* Enable DCB tagging only when more than one TC */
+ if (ice_dcb_get_num_tc(new_cfg) > 1) {
+ dev_dbg(&pf->pdev->dev, "DCB tagging enabled (num TC > 1)\n");
+ set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+ } else {
+ dev_dbg(&pf->pdev->dev, "DCB tagging disabled (num TC = 1)\n");
+ clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+ }
+
+ if (!memcmp(new_cfg, curr_cfg, sizeof(*new_cfg))) {
+ dev_dbg(&pf->pdev->dev, "No change in DCB config required\n");
+ return ret;
+ }
+
+ /* Store old config in case FW config fails */
+ old_cfg = devm_kzalloc(&pf->pdev->dev, sizeof(*old_cfg), GFP_KERNEL);
+ memcpy(old_cfg, curr_cfg, sizeof(*old_cfg));
+
+ /* avoid race conditions by holding the lock while disabling and
+ * re-enabling the VSI
+ */
+ if (!locked)
+ rtnl_lock();
+ ice_pf_dis_all_vsi(pf, true);
+
+ memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg));
+ memcpy(&curr_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec));
+
+ /* Only send new config to HW if we are in SW LLDP mode. Otherwise,
+ * the new config came from the HW in the first place.
+ */
+ if (pf->hw.port_info->is_sw_lldp) {
+ ret = ice_set_dcb_cfg(pf->hw.port_info);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Set DCB Config failed\n");
+ /* Restore previous settings to local config */
+ memcpy(curr_cfg, old_cfg, sizeof(*curr_cfg));
+ goto out;
+ }
+ }
+
+ ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+ goto out;
+ }
+
+ ice_pf_dcb_recfg(pf);
+
+out:
+ ice_pf_ena_all_vsi(pf, true);
+ if (!locked)
+ rtnl_unlock();
+ devm_kfree(&pf->pdev->dev, old_cfg);
+ return ret;
+}
+
+/**
+ * ice_cfg_etsrec_defaults - Set default ETS recommended DCB config
+ * @pi: port information structure
+ */
+static void ice_cfg_etsrec_defaults(struct ice_port_info *pi)
+{
+ struct ice_dcbx_cfg *dcbcfg = &pi->local_dcbx_cfg;
+ u8 i;
+
+ /* Ensure ETS recommended DCB configuration is not already set */
+ if (dcbcfg->etsrec.maxtcs)
+ return;
+
+ /* In CEE mode, set the default to 1 TC */
+ dcbcfg->etsrec.maxtcs = 1;
+ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+ dcbcfg->etsrec.tcbwtable[i] = i ? 0 : 100;
+ dcbcfg->etsrec.tsatable[i] = i ? ICE_IEEE_TSA_STRICT :
+ ICE_IEEE_TSA_ETS;
+ }
+}
+
+/**
+ * ice_dcb_need_recfg - Check if DCB needs reconfig
+ * @pf: board private structure
+ * @old_cfg: current DCB config
+ * @new_cfg: new DCB config
+ */
+static bool
+ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
+ struct ice_dcbx_cfg *new_cfg)
+{
+ bool need_reconfig = false;
+
+ /* Check if ETS configuration has changed */
+ if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,
+ sizeof(new_cfg->etscfg))) {
+ /* If Priority Table has changed reconfig is needed */
+ if (memcmp(&new_cfg->etscfg.prio_table,
+ &old_cfg->etscfg.prio_table,
+ sizeof(new_cfg->etscfg.prio_table))) {
+ need_reconfig = true;
+ dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");
+ }
+
+ if (memcmp(&new_cfg->etscfg.tcbwtable,
+ &old_cfg->etscfg.tcbwtable,
+ sizeof(new_cfg->etscfg.tcbwtable)))
+ dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");
+
+ if (memcmp(&new_cfg->etscfg.tsatable,
+ &old_cfg->etscfg.tsatable,
+ sizeof(new_cfg->etscfg.tsatable)))
+ dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");
+ }
+
+ /* Check if PFC configuration has changed */
+ if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {
+ need_reconfig = true;
+ dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");
+ }
+
+ /* Check if APP Table has changed */
+ if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {
+ need_reconfig = true;
+ dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
+ }
+
+ dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);
+ return need_reconfig;
+}
+
+/**
+ * ice_dcb_rebuild - rebuild DCB post reset
+ * @pf: physical function instance
+ */
+void ice_dcb_rebuild(struct ice_pf *pf)
+{
+ struct ice_dcbx_cfg *local_dcbx_cfg, *desired_dcbx_cfg, *prev_cfg;
+ struct ice_aqc_port_ets_elem buf = { 0 };
+ enum ice_status ret;
+
+ ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+ goto dcb_error;
+ }
+
+ /* If DCB was not enabled previously, we are done */
+ if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags))
+ return;
+
+ local_dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg;
+ desired_dcbx_cfg = &pf->hw.port_info->desired_dcbx_cfg;
+
+ /* Save current willing state and force FW to unwilling */
+ local_dcbx_cfg->etscfg.willing = 0x0;
+ local_dcbx_cfg->pfc.willing = 0x0;
+ local_dcbx_cfg->app_mode = ICE_DCBX_APPS_NON_WILLING;
+
+ ice_cfg_etsrec_defaults(pf->hw.port_info);
+ ret = ice_set_dcb_cfg(pf->hw.port_info);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Failed to set DCB to unwilling\n");
+ goto dcb_error;
+ }
+
+ /* Retrieve DCB config and ensure same as current in SW */
+ prev_cfg = devm_kmemdup(&pf->pdev->dev, local_dcbx_cfg,
+ sizeof(*prev_cfg), GFP_KERNEL);
+ if (!prev_cfg) {
+ dev_err(&pf->pdev->dev, "Failed to alloc space for DCB cfg\n");
+ goto dcb_error;
+ }
+
+ ice_init_dcb(&pf->hw, true);
+ if (pf->hw.port_info->dcbx_status == ICE_DCBX_STATUS_DIS)
+ pf->hw.port_info->is_sw_lldp = true;
+ else
+ pf->hw.port_info->is_sw_lldp = false;
+
+ if (ice_dcb_need_recfg(pf, prev_cfg, local_dcbx_cfg)) {
+ /* difference in cfg detected - disable DCB till next MIB */
+ dev_err(&pf->pdev->dev, "Set local MIB not accurate\n");
+ goto dcb_error;
+ }
+
+ /* fetched config congruent to previous configuration */
+ devm_kfree(&pf->pdev->dev, prev_cfg);
+
+ /* Set the local desired config */
+ if (local_dcbx_cfg->dcbx_mode == ICE_DCBX_MODE_CEE)
+ memcpy(local_dcbx_cfg, desired_dcbx_cfg,
+ sizeof(*local_dcbx_cfg));
+
+ ice_cfg_etsrec_defaults(pf->hw.port_info);
+ ret = ice_set_dcb_cfg(pf->hw.port_info);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Failed to set desired config\n");
+ goto dcb_error;
+ }
+ dev_info(&pf->pdev->dev, "DCB restored after reset\n");
+ ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+ goto dcb_error;
+ }
+
+ return;
+
+dcb_error:
+ dev_err(&pf->pdev->dev, "Disabling DCB until new settings occur\n");
+ prev_cfg = devm_kzalloc(&pf->pdev->dev, sizeof(*prev_cfg), GFP_KERNEL);
+ prev_cfg->etscfg.willing = true;
+ prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
+ prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
+ memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec));
+ ice_pf_dcb_cfg(pf, prev_cfg, false);
+ devm_kfree(&pf->pdev->dev, prev_cfg);
+}
+
+/**
+ * ice_dcb_init_cfg - set the initial DCB config in SW
+ * @pf: PF to apply config to
+ * @locked: Is the RTNL held
+ */
+static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked)
+{
+ struct ice_dcbx_cfg *newcfg;
+ struct ice_port_info *pi;
+ int ret = 0;
+
+ pi = pf->hw.port_info;
+ newcfg = devm_kzalloc(&pf->pdev->dev, sizeof(*newcfg), GFP_KERNEL);
+ if (!newcfg)
+ return -ENOMEM;
+
+ memcpy(newcfg, &pi->local_dcbx_cfg, sizeof(*newcfg));
+ memset(&pi->local_dcbx_cfg, 0, sizeof(*newcfg));
+
+ dev_info(&pf->pdev->dev, "Configuring initial DCB values\n");
+ if (ice_pf_dcb_cfg(pf, newcfg, locked))
+ ret = -EINVAL;
+
+ devm_kfree(&pf->pdev->dev, newcfg);
+
+ return ret;
+}
+
+/**
+ * ice_dcb_sw_default_config - Apply a default DCB config
+ * @pf: PF to apply config to
+ * @locked: was this function called with RTNL held
+ */
+static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked)
+{
+ struct ice_aqc_port_ets_elem buf = { 0 };
+ struct ice_dcbx_cfg *dcbcfg;
+ struct ice_port_info *pi;
+ struct ice_hw *hw;
+ int ret;
+
+ hw = &pf->hw;
+ pi = hw->port_info;
+ dcbcfg = devm_kzalloc(&pf->pdev->dev, sizeof(*dcbcfg), GFP_KERNEL);
+
+ memset(dcbcfg, 0, sizeof(*dcbcfg));
+ memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg));
+
+ dcbcfg->etscfg.willing = 1;
+ dcbcfg->etscfg.maxtcs = hw->func_caps.common_cap.maxtc;
+ dcbcfg->etscfg.tcbwtable[0] = 100;
+ dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
+
+ memcpy(&dcbcfg->etsrec, &dcbcfg->etscfg,
+ sizeof(dcbcfg->etsrec));
+ dcbcfg->etsrec.willing = 0;
+
+ dcbcfg->pfc.willing = 1;
+ dcbcfg->pfc.pfccap = hw->func_caps.common_cap.maxtc;
+
+ dcbcfg->numapps = 1;
+ dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE;
+ dcbcfg->app[0].priority = 3;
+ dcbcfg->app[0].prot_id = ICE_APP_PROT_ID_FCOE;
+
+ ret = ice_pf_dcb_cfg(pf, dcbcfg, locked);
+ devm_kfree(&pf->pdev->dev, dcbcfg);
+ if (ret)
+ return ret;
+
+ return ice_query_port_ets(pi, &buf, sizeof(buf), NULL);
+}
+
+/**
+ * ice_init_pf_dcb - initialize DCB for a PF
+ * @pf: PF to initialize DCB for
+ * @locked: Was function called with RTNL held
+ */
+int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
+{
+ struct device *dev = &pf->pdev->dev;
+ struct ice_port_info *port_info;
+ struct ice_hw *hw = &pf->hw;
+ int err;
+
+ port_info = hw->port_info;
+
+ err = ice_init_dcb(hw, false);
+ if (err && !port_info->is_sw_lldp) {
+ dev_err(&pf->pdev->dev, "Error initializing DCB %d\n", err);
+ goto dcb_init_err;
+ }
+
+ dev_info(&pf->pdev->dev,
+ "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n",
+ pf->hw.func_caps.common_cap.maxtc);
+ if (err) {
+ /* FW LLDP is disabled, activate SW DCBX/LLDP mode */
+ dev_info(&pf->pdev->dev,
+ "FW LLDP is disabled, DCBx/LLDP in SW mode.\n");
+ clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
+ err = ice_dcb_sw_dflt_cfg(pf, locked);
+ if (err) {
+ dev_err(&pf->pdev->dev,
+ "Failed to set local DCB config %d\n", err);
+ err = -EIO;
+ goto dcb_init_err;
+ }
+
+ pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+ return 0;
+ }
+
+ set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
+
+ /* DCBX in FW and LLDP enabled in FW */
+ pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_IEEE;
+
+ err = ice_dcb_init_cfg(pf, locked);
+ if (err)
+ goto dcb_init_err;
+
+ return err;
+
+dcb_init_err:
+ dev_err(dev, "DCB init failed\n");
+ return err;
+}
+
+/**
+ * ice_update_dcb_stats - Update DCB stats counters
+ * @pf: PF whose stats needs to be updated
+ */
+void ice_update_dcb_stats(struct ice_pf *pf)
+{
+ struct ice_hw_port_stats *prev_ps, *cur_ps;
+ struct ice_hw *hw = &pf->hw;
+ u8 port;
+ int i;
+
+ port = hw->port_info->lport;
+ prev_ps = &pf->stats_prev;
+ cur_ps = &pf->stats;
+
+ for (i = 0; i < 8; i++) {
+ ice_stat_update32(hw, GLPRT_PXOFFRXC(port, i),
+ pf->stat_prev_loaded,
+ &prev_ps->priority_xoff_rx[i],
+ &cur_ps->priority_xoff_rx[i]);
+ ice_stat_update32(hw, GLPRT_PXONRXC(port, i),
+ pf->stat_prev_loaded,
+ &prev_ps->priority_xon_rx[i],
+ &cur_ps->priority_xon_rx[i]);
+ ice_stat_update32(hw, GLPRT_PXONTXC(port, i),
+ pf->stat_prev_loaded,
+ &prev_ps->priority_xon_tx[i],
+ &cur_ps->priority_xon_tx[i]);
+ ice_stat_update32(hw, GLPRT_PXOFFTXC(port, i),
+ pf->stat_prev_loaded,
+ &prev_ps->priority_xoff_tx[i],
+ &cur_ps->priority_xoff_tx[i]);
+ ice_stat_update32(hw, GLPRT_RXON2OFFCNT(port, i),
+ pf->stat_prev_loaded,
+ &prev_ps->priority_xon_2_xoff[i],
+ &cur_ps->priority_xon_2_xoff[i]);
+ }
+}
+
+/**
+ * ice_tx_prepare_vlan_flags_dcb - prepare VLAN tagging for DCB
+ * @tx_ring: ring to send buffer on
+ * @first: pointer to struct ice_tx_buf
+ */
+int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
+ struct ice_tx_buf *first)
+{
+ struct sk_buff *skb = first->skb;
+
+ if (!test_bit(ICE_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
+ return 0;
+
+ /* Insert 802.1p priority into VLAN header */
+ if ((first->tx_flags & (ICE_TX_FLAGS_HW_VLAN | ICE_TX_FLAGS_SW_VLAN)) ||
+ skb->priority != TC_PRIO_CONTROL) {
+ first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M;
+ /* Mask the lower 3 bits to set the 802.1p priority */
+ first->tx_flags |= (skb->priority & 0x7) <<
+ ICE_TX_FLAGS_VLAN_PR_S;
+ if (first->tx_flags & ICE_TX_FLAGS_SW_VLAN) {
+ struct vlan_ethhdr *vhdr;
+ int rc;
+
+ rc = skb_cow_head(skb, 0);
+ if (rc < 0)
+ return rc;
+ vhdr = (struct vlan_ethhdr *)skb->data;
+ vhdr->h_vlan_TCI = htons(first->tx_flags >>
+ ICE_TX_FLAGS_VLAN_S);
+ } else {
+ first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_dcb_process_lldp_set_mib_change - Process MIB change
+ * @pf: ptr to ice_pf
+ * @event: pointer to the admin queue receive event
+ */
+void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
+ struct ice_rq_event_info *event)
+{
+ struct ice_aqc_port_ets_elem buf = { 0 };
+ struct ice_aqc_lldp_get_mib *mib;
+ struct ice_dcbx_cfg tmp_dcbx_cfg;
+ bool need_reconfig = false;
+ struct ice_port_info *pi;
+ u8 type;
+ int ret;
+
+ /* Not DCB capable or capability disabled */
+ if (!(test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)))
+ return;
+
+ if (pf->dcbx_cap & DCB_CAP_DCBX_HOST) {
+ dev_dbg(&pf->pdev->dev,
+ "MIB Change Event in HOST mode\n");
+ return;
+ }
+
+ pi = pf->hw.port_info;
+ mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+ /* Ignore if event is not for Nearest Bridge */
+ type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) &
+ ICE_AQ_LLDP_BRID_TYPE_M);
+ dev_dbg(&pf->pdev->dev, "LLDP event MIB bridge type 0x%x\n", type);
+ if (type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID)
+ return;
+
+ /* Check MIB Type and return if event for Remote MIB update */
+ type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M;
+ dev_dbg(&pf->pdev->dev,
+ "LLDP event mib type %s\n", type ? "remote" : "local");
+ if (type == ICE_AQ_LLDP_MIB_REMOTE) {
+ /* Update the remote cached instance and return */
+ ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+ ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
+ &pi->remote_dcbx_cfg);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Failed to get remote DCB config\n");
+ return;
+ }
+ }
+
+ /* store the old configuration */
+ tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg;
+
+ /* Reset the old DCBX configuration data */
+ memset(&pi->local_dcbx_cfg, 0, sizeof(pi->local_dcbx_cfg));
+
+ /* Get updated DCBX data from firmware */
+ ret = ice_get_dcb_cfg(pf->hw.port_info);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Failed to get DCB config\n");
+ return;
+ }
+
+ /* No change detected in DCBX configs */
+ if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
+ dev_dbg(&pf->pdev->dev,
+ "No change detected in DCBX configuration.\n");
+ return;
+ }
+
+ need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg,
+ &pi->local_dcbx_cfg);
+ if (!need_reconfig)
+ return;
+
+ /* Enable DCB tagging only when more than one TC */
+ if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) {
+ dev_dbg(&pf->pdev->dev, "DCB tagging enabled (num TC > 1)\n");
+ set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+ } else {
+ dev_dbg(&pf->pdev->dev, "DCB tagging disabled (num TC = 1)\n");
+ clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+ }
+
+ rtnl_lock();
+ ice_pf_dis_all_vsi(pf, true);
+
+ ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+ rtnl_unlock();
+ return;
+ }
+
+ /* changes in configuration update VSI */
+ ice_pf_dcb_recfg(pf);
+
+ ice_pf_ena_all_vsi(pf, true);
+ rtnl_unlock();
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
new file mode 100644
index 0000000..661a6f7
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_DCB_LIB_H_
+#define _ICE_DCB_LIB_H_
+
+#include "ice.h"
+#include "ice_lib.h"
+
+#ifdef CONFIG_DCB
+#define ICE_TC_MAX_BW 100 /* Default Max BW percentage */
+
+void ice_dcb_rebuild(struct ice_pf *pf);
+u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg);
+u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg);
+void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi);
+int ice_init_pf_dcb(struct ice_pf *pf, bool locked);
+void ice_update_dcb_stats(struct ice_pf *pf);
+int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
+ struct ice_tx_buf *first);
+void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
+ struct ice_rq_event_info *event);
+void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
+static inline void
+ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring)
+{
+ tlan_ctx->cgd_num = ring->dcb_tc;
+}
+#else
+#define ice_dcb_rebuild(pf) do {} while (0)
+
+static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
+{
+ return ICE_DFLT_TRAFFIC_CLASS;
+}
+
+static inline u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
+{
+ return 1;
+}
+
+static inline int
+ice_init_pf_dcb(struct ice_pf *pf, bool __always_unused locked)
+{
+ dev_dbg(&pf->pdev->dev, "DCB not supported\n");
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring,
+ struct ice_tx_buf __always_unused *first)
+{
+ return 0;
+}
+
+#define ice_update_dcb_stats(pf) do {} while (0)
+#define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
+#define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0)
+#define ice_set_cgd_num(tlan_ctx, ring) do {} while (0)
+#define ice_vsi_cfg_netdev_tc(vsi, ena_tc) do {} while (0)
+#endif /* CONFIG_DCB */
+#endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index 0e14d72..f8d5c66 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -5,15 +5,11 @@
#define _ICE_DEVIDS_H_
/* Device IDs */
-/* Intel(R) Ethernet Controller C810 for backplane */
-#define ICE_DEV_ID_C810_BACKPLANE 0x1591
-/* Intel(R) Ethernet Controller C810 for QSFP */
-#define ICE_DEV_ID_C810_QSFP 0x1592
-/* Intel(R) Ethernet Controller C810 for SFP */
-#define ICE_DEV_ID_C810_SFP 0x1593
-/* Intel(R) Ethernet Controller C810/X557-AT 10GBASE-T */
-#define ICE_DEV_ID_C810_10G_BASE_T 0x1594
-/* Intel(R) Ethernet Controller C810 1GbE */
-#define ICE_DEV_ID_C810_SGMII 0x1595
+/* Intel(R) Ethernet Controller E810-C for backplane */
+#define ICE_DEV_ID_E810C_BACKPLANE 0x1591
+/* Intel(R) Ethernet Controller E810-C for QSFP */
+#define ICE_DEV_ID_E810C_QSFP 0x1592
+/* Intel(R) Ethernet Controller E810-C for SFP */
+#define ICE_DEV_ID_E810C_SFP 0x1593
#endif /* _ICE_DEVIDS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 4c5c87b..7e23034 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4,6 +4,8 @@
/* ethtool support for ice */
#include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
struct ice_stats {
char stat_string[ETH_GSTRING_LEN];
@@ -33,26 +35,50 @@
#define ICE_PF_STATS_LEN ARRAY_SIZE(ice_gstrings_pf_stats)
#define ICE_VSI_STATS_LEN ARRAY_SIZE(ice_gstrings_vsi_stats)
-#define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_VSI_STATS_LEN + \
- ice_q_stats_len(n))
+#define ICE_PFC_STATS_LEN ( \
+ (FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_rx) + \
+ FIELD_SIZEOF(struct ice_pf, stats.priority_xon_rx) + \
+ FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_tx) + \
+ FIELD_SIZEOF(struct ice_pf, stats.priority_xon_tx)) \
+ / sizeof(u64))
+#define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_PFC_STATS_LEN + \
+ ICE_VSI_STATS_LEN + ice_q_stats_len(n))
static const struct ice_stats ice_gstrings_vsi_stats[] = {
- ICE_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
ICE_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
- ICE_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
+ ICE_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
ICE_VSI_STAT("rx_multicast", eth_stats.rx_multicast),
- ICE_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
+ ICE_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
ICE_VSI_STAT("rx_broadcast", eth_stats.rx_broadcast),
- ICE_VSI_STAT("tx_bytes", eth_stats.tx_bytes),
+ ICE_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
ICE_VSI_STAT("rx_bytes", eth_stats.rx_bytes),
- ICE_VSI_STAT("rx_discards", eth_stats.rx_discards),
- ICE_VSI_STAT("tx_errors", eth_stats.tx_errors),
- ICE_VSI_STAT("tx_linearize", tx_linearize),
+ ICE_VSI_STAT("tx_bytes", eth_stats.tx_bytes),
+ ICE_VSI_STAT("rx_dropped", eth_stats.rx_discards),
ICE_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
ICE_VSI_STAT("rx_alloc_fail", rx_buf_failed),
ICE_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
+ ICE_VSI_STAT("tx_errors", eth_stats.tx_errors),
+ ICE_VSI_STAT("tx_linearize", tx_linearize),
};
+enum ice_ethtool_test_id {
+ ICE_ETH_TEST_REG = 0,
+ ICE_ETH_TEST_EEPROM,
+ ICE_ETH_TEST_INTR,
+ ICE_ETH_TEST_LOOP,
+ ICE_ETH_TEST_LINK,
+};
+
+static const char ice_gstrings_test[][ETH_GSTRING_LEN] = {
+ "Register test (offline)",
+ "EEPROM test (offline)",
+ "Interrupt test (offline)",
+ "Loopback test (offline)",
+ "Link test (on/offline)",
+};
+
+#define ICE_TEST_LEN (sizeof(ice_gstrings_test) / ETH_GSTRING_LEN)
+
/* These PF_STATs might look like duplicates of some NETDEV_STATs,
* but they aren't. This device is capable of supporting multiple
* VSIs/netdevs on a single PF. The NETDEV_STATs are for individual
@@ -62,49 +88,49 @@
* The PF_STATs are appended to the netdev stats only when ethtool -S
* is queried on the base PF netdev.
*/
-static struct ice_stats ice_gstrings_pf_stats[] = {
- ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes),
- ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes),
- ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast),
- ICE_PF_STAT("rx_unicast", stats.eth.rx_unicast),
- ICE_PF_STAT("tx_multicast", stats.eth.tx_multicast),
- ICE_PF_STAT("rx_multicast", stats.eth.rx_multicast),
- ICE_PF_STAT("tx_broadcast", stats.eth.tx_broadcast),
- ICE_PF_STAT("rx_broadcast", stats.eth.rx_broadcast),
- ICE_PF_STAT("tx_errors", stats.eth.tx_errors),
- ICE_PF_STAT("tx_size_64", stats.tx_size_64),
- ICE_PF_STAT("rx_size_64", stats.rx_size_64),
- ICE_PF_STAT("tx_size_127", stats.tx_size_127),
- ICE_PF_STAT("rx_size_127", stats.rx_size_127),
- ICE_PF_STAT("tx_size_255", stats.tx_size_255),
- ICE_PF_STAT("rx_size_255", stats.rx_size_255),
- ICE_PF_STAT("tx_size_511", stats.tx_size_511),
- ICE_PF_STAT("rx_size_511", stats.rx_size_511),
- ICE_PF_STAT("tx_size_1023", stats.tx_size_1023),
- ICE_PF_STAT("rx_size_1023", stats.rx_size_1023),
- ICE_PF_STAT("tx_size_1522", stats.tx_size_1522),
- ICE_PF_STAT("rx_size_1522", stats.rx_size_1522),
- ICE_PF_STAT("tx_size_big", stats.tx_size_big),
- ICE_PF_STAT("rx_size_big", stats.rx_size_big),
- ICE_PF_STAT("link_xon_tx", stats.link_xon_tx),
- ICE_PF_STAT("link_xon_rx", stats.link_xon_rx),
- ICE_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
- ICE_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
- ICE_PF_STAT("tx_dropped_link_down", stats.tx_dropped_link_down),
- ICE_PF_STAT("rx_undersize", stats.rx_undersize),
- ICE_PF_STAT("rx_fragments", stats.rx_fragments),
- ICE_PF_STAT("rx_oversize", stats.rx_oversize),
- ICE_PF_STAT("rx_jabber", stats.rx_jabber),
- ICE_PF_STAT("rx_csum_bad", hw_csum_rx_error),
- ICE_PF_STAT("rx_length_errors", stats.rx_len_errors),
- ICE_PF_STAT("rx_dropped", stats.eth.rx_discards),
- ICE_PF_STAT("rx_crc_errors", stats.crc_errors),
- ICE_PF_STAT("illegal_bytes", stats.illegal_bytes),
- ICE_PF_STAT("mac_local_faults", stats.mac_local_faults),
- ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+static const struct ice_stats ice_gstrings_pf_stats[] = {
+ ICE_PF_STAT("rx_bytes.nic", stats.eth.rx_bytes),
+ ICE_PF_STAT("tx_bytes.nic", stats.eth.tx_bytes),
+ ICE_PF_STAT("rx_unicast.nic", stats.eth.rx_unicast),
+ ICE_PF_STAT("tx_unicast.nic", stats.eth.tx_unicast),
+ ICE_PF_STAT("rx_multicast.nic", stats.eth.rx_multicast),
+ ICE_PF_STAT("tx_multicast.nic", stats.eth.tx_multicast),
+ ICE_PF_STAT("rx_broadcast.nic", stats.eth.rx_broadcast),
+ ICE_PF_STAT("tx_broadcast.nic", stats.eth.tx_broadcast),
+ ICE_PF_STAT("tx_errors.nic", stats.eth.tx_errors),
+ ICE_PF_STAT("rx_size_64.nic", stats.rx_size_64),
+ ICE_PF_STAT("tx_size_64.nic", stats.tx_size_64),
+ ICE_PF_STAT("rx_size_127.nic", stats.rx_size_127),
+ ICE_PF_STAT("tx_size_127.nic", stats.tx_size_127),
+ ICE_PF_STAT("rx_size_255.nic", stats.rx_size_255),
+ ICE_PF_STAT("tx_size_255.nic", stats.tx_size_255),
+ ICE_PF_STAT("rx_size_511.nic", stats.rx_size_511),
+ ICE_PF_STAT("tx_size_511.nic", stats.tx_size_511),
+ ICE_PF_STAT("rx_size_1023.nic", stats.rx_size_1023),
+ ICE_PF_STAT("tx_size_1023.nic", stats.tx_size_1023),
+ ICE_PF_STAT("rx_size_1522.nic", stats.rx_size_1522),
+ ICE_PF_STAT("tx_size_1522.nic", stats.tx_size_1522),
+ ICE_PF_STAT("rx_size_big.nic", stats.rx_size_big),
+ ICE_PF_STAT("tx_size_big.nic", stats.tx_size_big),
+ ICE_PF_STAT("link_xon_rx.nic", stats.link_xon_rx),
+ ICE_PF_STAT("link_xon_tx.nic", stats.link_xon_tx),
+ ICE_PF_STAT("link_xoff_rx.nic", stats.link_xoff_rx),
+ ICE_PF_STAT("link_xoff_tx.nic", stats.link_xoff_tx),
+ ICE_PF_STAT("tx_dropped_link_down.nic", stats.tx_dropped_link_down),
+ ICE_PF_STAT("rx_undersize.nic", stats.rx_undersize),
+ ICE_PF_STAT("rx_fragments.nic", stats.rx_fragments),
+ ICE_PF_STAT("rx_oversize.nic", stats.rx_oversize),
+ ICE_PF_STAT("rx_jabber.nic", stats.rx_jabber),
+ ICE_PF_STAT("rx_csum_bad.nic", hw_csum_rx_error),
+ ICE_PF_STAT("rx_length_errors.nic", stats.rx_len_errors),
+ ICE_PF_STAT("rx_dropped.nic", stats.eth.rx_discards),
+ ICE_PF_STAT("rx_crc_errors.nic", stats.crc_errors),
+ ICE_PF_STAT("illegal_bytes.nic", stats.illegal_bytes),
+ ICE_PF_STAT("mac_local_faults.nic", stats.mac_local_faults),
+ ICE_PF_STAT("mac_remote_faults.nic", stats.mac_remote_faults),
};
-static u32 ice_regs_dump_list[] = {
+static const u32 ice_regs_dump_list[] = {
PFGEN_STATE,
PRTGEN_STATUS,
QRX_CTRL(0),
@@ -112,33 +138,28 @@
QINT_RQCTL(0),
PFINT_OICR_ENA,
QRX_ITR(0),
+ PF0INT_ITR_0(0),
+ PF0INT_ITR_1(0),
+ PF0INT_ITR_2(0),
};
-/**
- * ice_nvm_version_str - format the NVM version strings
- * @hw: ptr to the hardware info
- */
-static char *ice_nvm_version_str(struct ice_hw *hw)
-{
- static char buf[ICE_ETHTOOL_FWVER_LEN];
- u8 ver, patch;
- u32 full_ver;
- u16 build;
+struct ice_priv_flag {
+ char name[ETH_GSTRING_LEN];
+ u32 bitno; /* bit position in pf->flags */
+};
- full_ver = hw->nvm.oem_ver;
- ver = (u8)((full_ver & ICE_OEM_VER_MASK) >> ICE_OEM_VER_SHIFT);
- build = (u16)((full_ver & ICE_OEM_VER_BUILD_MASK) >>
- ICE_OEM_VER_BUILD_SHIFT);
- patch = (u8)(full_ver & ICE_OEM_VER_PATCH_MASK);
-
- snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d",
- (hw->nvm.ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT,
- (hw->nvm.ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT,
- hw->nvm.eetrack, ver, build, patch);
-
- return buf;
+#define ICE_PRIV_FLAG(_name, _bitno) { \
+ .name = _name, \
+ .bitno = _bitno, \
}
+static const struct ice_priv_flag ice_gstrings_priv_flags[] = {
+ ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA),
+ ICE_PRIV_FLAG("fw-lldp-agent", ICE_FLAG_FW_LLDP_AGENT),
+};
+
+#define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags)
+
static void
ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
{
@@ -152,6 +173,7 @@
sizeof(drvinfo->fw_version));
strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
sizeof(drvinfo->bus_info));
+ drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE;
}
static int ice_get_regs_len(struct net_device __always_unused *netdev)
@@ -203,6 +225,620 @@
#endif /* !CONFIG_DYNAMIC_DEBUG */
}
+static int ice_get_eeprom_len(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+ return (int)(pf->hw.nvm.sr_words * sizeof(u16));
+}
+
+static int
+ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+ u8 *bytes)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ u16 first_word, last_word, nwords;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+ struct device *dev;
+ int ret = 0;
+ u16 *buf;
+
+ dev = &pf->pdev->dev;
+
+ eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+ first_word = eeprom->offset >> 1;
+ last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+ nwords = last_word - first_word + 1;
+
+ buf = devm_kcalloc(dev, nwords, sizeof(u16), GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ status = ice_read_sr_buf(hw, first_word, &nwords, buf);
+ if (status) {
+ dev_err(dev, "ice_read_sr_buf failed, err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ eeprom->len = sizeof(u16) * nwords;
+ ret = -EIO;
+ goto out;
+ }
+
+ memcpy(bytes, (u8 *)buf + (eeprom->offset & 1), eeprom->len);
+out:
+ devm_kfree(dev, buf);
+ return ret;
+}
+
+/**
+ * ice_active_vfs - check if there are any active VFs
+ * @pf: board private structure
+ *
+ * Returns true if an active VF is found, otherwise returns false
+ */
+static bool ice_active_vfs(struct ice_pf *pf)
+{
+ struct ice_vf *vf = pf->vf;
+ int i;
+
+ for (i = 0; i < pf->num_alloc_vfs; i++, vf++)
+ if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+ return true;
+ return false;
+}
+
+/**
+ * ice_link_test - perform a link test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_link_test(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ enum ice_status status;
+ bool link_up = false;
+
+ netdev_info(netdev, "link test\n");
+ status = ice_get_link_status(np->vsi->port_info, &link_up);
+ if (status) {
+ netdev_err(netdev, "link query error, status = %d\n", status);
+ return 1;
+ }
+
+ if (!link_up)
+ return 2;
+
+ return 0;
+}
+
+/**
+ * ice_eeprom_test - perform an EEPROM test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_eeprom_test(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+ netdev_info(netdev, "EEPROM test\n");
+ return !!(ice_nvm_validate_checksum(&pf->hw));
+}
+
+/**
+ * ice_reg_pattern_test
+ * @hw: pointer to the HW struct
+ * @reg: reg to be tested
+ * @mask: bits to be touched
+ */
+static int ice_reg_pattern_test(struct ice_hw *hw, u32 reg, u32 mask)
+{
+ struct ice_pf *pf = (struct ice_pf *)hw->back;
+ static const u32 patterns[] = {
+ 0x5A5A5A5A, 0xA5A5A5A5,
+ 0x00000000, 0xFFFFFFFF
+ };
+ u32 val, orig_val;
+ int i;
+
+ orig_val = rd32(hw, reg);
+ for (i = 0; i < ARRAY_SIZE(patterns); ++i) {
+ u32 pattern = patterns[i] & mask;
+
+ wr32(hw, reg, pattern);
+ val = rd32(hw, reg);
+ if (val == pattern)
+ continue;
+ dev_err(&pf->pdev->dev,
+ "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n"
+ , __func__, reg, pattern, val);
+ return 1;
+ }
+
+ wr32(hw, reg, orig_val);
+ val = rd32(hw, reg);
+ if (val != orig_val) {
+ dev_err(&pf->pdev->dev,
+ "%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n"
+ , __func__, reg, orig_val, val);
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_reg_test - perform a register test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_reg_test(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_hw *hw = np->vsi->port_info->hw;
+ u32 int_elements = hw->func_caps.common_cap.num_msix_vectors ?
+ hw->func_caps.common_cap.num_msix_vectors - 1 : 1;
+ struct ice_diag_reg_test_info {
+ u32 address;
+ u32 mask;
+ u32 elem_num;
+ u32 elem_size;
+ } ice_reg_list[] = {
+ {GLINT_ITR(0, 0), 0x00000fff, int_elements,
+ GLINT_ITR(0, 1) - GLINT_ITR(0, 0)},
+ {GLINT_ITR(1, 0), 0x00000fff, int_elements,
+ GLINT_ITR(1, 1) - GLINT_ITR(1, 0)},
+ {GLINT_ITR(0, 0), 0x00000fff, int_elements,
+ GLINT_ITR(2, 1) - GLINT_ITR(2, 0)},
+ {GLINT_CTL, 0xffff0001, 1, 0}
+ };
+ int i;
+
+ netdev_dbg(netdev, "Register test\n");
+ for (i = 0; i < ARRAY_SIZE(ice_reg_list); ++i) {
+ u32 j;
+
+ for (j = 0; j < ice_reg_list[i].elem_num; ++j) {
+ u32 mask = ice_reg_list[i].mask;
+ u32 reg = ice_reg_list[i].address +
+ (j * ice_reg_list[i].elem_size);
+
+ /* bail on failure (non-zero return) */
+ if (ice_reg_pattern_test(hw, reg, mask))
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_lbtest_prepare_rings - configure Tx/Rx test rings
+ * @vsi: pointer to the VSI structure
+ *
+ * Function configures rings of a VSI for loopback test without
+ * enabling interrupts or informing the kernel about new queues.
+ *
+ * Returns 0 on success, negative on failure.
+ */
+static int ice_lbtest_prepare_rings(struct ice_vsi *vsi)
+{
+ int status;
+
+ status = ice_vsi_setup_tx_rings(vsi);
+ if (status)
+ goto err_setup_tx_ring;
+
+ status = ice_vsi_setup_rx_rings(vsi);
+ if (status)
+ goto err_setup_rx_ring;
+
+ status = ice_vsi_cfg(vsi);
+ if (status)
+ goto err_setup_rx_ring;
+
+ status = ice_vsi_start_rx_rings(vsi);
+ if (status)
+ goto err_start_rx_ring;
+
+ return status;
+
+err_start_rx_ring:
+ ice_vsi_free_rx_rings(vsi);
+err_setup_rx_ring:
+ ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
+err_setup_tx_ring:
+ ice_vsi_free_tx_rings(vsi);
+
+ return status;
+}
+
+/**
+ * ice_lbtest_disable_rings - disable Tx/Rx test rings after loopback test
+ * @vsi: pointer to the VSI structure
+ *
+ * Function stops and frees VSI rings after a loopback test.
+ * Returns 0 on success, negative on failure.
+ */
+static int ice_lbtest_disable_rings(struct ice_vsi *vsi)
+{
+ int status;
+
+ status = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
+ if (status)
+ netdev_err(vsi->netdev, "Failed to stop Tx rings, VSI %d error %d\n",
+ vsi->vsi_num, status);
+
+ status = ice_vsi_stop_rx_rings(vsi);
+ if (status)
+ netdev_err(vsi->netdev, "Failed to stop Rx rings, VSI %d error %d\n",
+ vsi->vsi_num, status);
+
+ ice_vsi_free_tx_rings(vsi);
+ ice_vsi_free_rx_rings(vsi);
+
+ return status;
+}
+
+/**
+ * ice_lbtest_create_frame - create test packet
+ * @pf: pointer to the PF structure
+ * @ret_data: allocated frame buffer
+ * @size: size of the packet data
+ *
+ * Function allocates a frame with a test pattern on specific offsets.
+ * Returns 0 on success, non-zero on failure.
+ */
+static int ice_lbtest_create_frame(struct ice_pf *pf, u8 **ret_data, u16 size)
+{
+ u8 *data;
+
+ if (!pf)
+ return -EINVAL;
+
+ data = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* Since the ethernet test frame should always be at least
+ * 64 bytes long, fill some octets in the payload with test data.
+ */
+ memset(data, 0xFF, size);
+ data[32] = 0xDE;
+ data[42] = 0xAD;
+ data[44] = 0xBE;
+ data[46] = 0xEF;
+
+ *ret_data = data;
+
+ return 0;
+}
+
+/**
+ * ice_lbtest_check_frame - verify received loopback frame
+ * @frame: pointer to the raw packet data
+ *
+ * Function verifies received test frame with a pattern.
+ * Returns true if frame matches the pattern, false otherwise.
+ */
+static bool ice_lbtest_check_frame(u8 *frame)
+{
+ /* Validate bytes of a frame under offsets chosen earlier */
+ if (frame[32] == 0xDE &&
+ frame[42] == 0xAD &&
+ frame[44] == 0xBE &&
+ frame[46] == 0xEF &&
+ frame[48] == 0xFF)
+ return true;
+
+ return false;
+}
+
+/**
+ * ice_diag_send - send test frames to the test ring
+ * @tx_ring: pointer to the transmit ring
+ * @data: pointer to the raw packet data
+ * @size: size of the packet to send
+ *
+ * Function sends loopback packets on a test Tx ring.
+ */
+static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size)
+{
+ struct ice_tx_desc *tx_desc;
+ struct ice_tx_buf *tx_buf;
+ dma_addr_t dma;
+ u64 td_cmd;
+
+ tx_desc = ICE_TX_DESC(tx_ring, tx_ring->next_to_use);
+ tx_buf = &tx_ring->tx_buf[tx_ring->next_to_use];
+
+ dma = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE);
+ if (dma_mapping_error(tx_ring->dev, dma))
+ return -EINVAL;
+
+ tx_desc->buf_addr = cpu_to_le64(dma);
+
+ /* These flags are required for a descriptor to be pushed out */
+ td_cmd = (u64)(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS);
+ tx_desc->cmd_type_offset_bsz =
+ cpu_to_le64(ICE_TX_DESC_DTYPE_DATA |
+ (td_cmd << ICE_TXD_QW1_CMD_S) |
+ ((u64)0 << ICE_TXD_QW1_OFFSET_S) |
+ ((u64)size << ICE_TXD_QW1_TX_BUF_SZ_S) |
+ ((u64)0 << ICE_TXD_QW1_L2TAG1_S));
+
+ tx_buf->next_to_watch = tx_desc;
+
+ /* Force memory write to complete before letting h/w know
+ * there are new descriptors to fetch.
+ */
+ wmb();
+
+ tx_ring->next_to_use++;
+ if (tx_ring->next_to_use >= tx_ring->count)
+ tx_ring->next_to_use = 0;
+
+ writel_relaxed(tx_ring->next_to_use, tx_ring->tail);
+
+ /* Wait until the packets get transmitted to the receive queue. */
+ usleep_range(1000, 2000);
+ dma_unmap_single(tx_ring->dev, dma, size, DMA_TO_DEVICE);
+
+ return 0;
+}
+
+#define ICE_LB_FRAME_SIZE 64
+/**
+ * ice_lbtest_receive_frames - receive and verify test frames
+ * @rx_ring: pointer to the receive ring
+ *
+ * Function receives loopback packets and verify their correctness.
+ * Returns number of received valid frames.
+ */
+static int ice_lbtest_receive_frames(struct ice_ring *rx_ring)
+{
+ struct ice_rx_buf *rx_buf;
+ int valid_frames, i;
+ u8 *received_buf;
+
+ valid_frames = 0;
+
+ for (i = 0; i < rx_ring->count; i++) {
+ union ice_32b_rx_flex_desc *rx_desc;
+
+ rx_desc = ICE_RX_DESC(rx_ring, i);
+
+ if (!(rx_desc->wb.status_error0 &
+ cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+ continue;
+
+ rx_buf = &rx_ring->rx_buf[i];
+ received_buf = page_address(rx_buf->page);
+
+ if (ice_lbtest_check_frame(received_buf))
+ valid_frames++;
+ }
+
+ return valid_frames;
+}
+
+/**
+ * ice_loopback_test - perform a loopback test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_loopback_test(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *orig_vsi = np->vsi, *test_vsi;
+ struct ice_pf *pf = orig_vsi->back;
+ struct ice_ring *tx_ring, *rx_ring;
+ u8 broadcast[ETH_ALEN], ret = 0;
+ int num_frames, valid_frames;
+ LIST_HEAD(tmp_list);
+ u8 *tx_frame;
+ int i;
+
+ netdev_info(netdev, "loopback test\n");
+
+ test_vsi = ice_lb_vsi_setup(pf, pf->hw.port_info);
+ if (!test_vsi) {
+ netdev_err(netdev, "Failed to create a VSI for the loopback test");
+ return 1;
+ }
+
+ test_vsi->netdev = netdev;
+ tx_ring = test_vsi->tx_rings[0];
+ rx_ring = test_vsi->rx_rings[0];
+
+ if (ice_lbtest_prepare_rings(test_vsi)) {
+ ret = 2;
+ goto lbtest_vsi_close;
+ }
+
+ if (ice_alloc_rx_bufs(rx_ring, rx_ring->count)) {
+ ret = 3;
+ goto lbtest_rings_dis;
+ }
+
+ /* Enable MAC loopback in firmware */
+ if (ice_aq_set_mac_loopback(&pf->hw, true, NULL)) {
+ ret = 4;
+ goto lbtest_mac_dis;
+ }
+
+ /* Test VSI needs to receive broadcast packets */
+ eth_broadcast_addr(broadcast);
+ if (ice_add_mac_to_list(test_vsi, &tmp_list, broadcast)) {
+ ret = 5;
+ goto lbtest_mac_dis;
+ }
+
+ if (ice_add_mac(&pf->hw, &tmp_list)) {
+ ret = 6;
+ goto free_mac_list;
+ }
+
+ if (ice_lbtest_create_frame(pf, &tx_frame, ICE_LB_FRAME_SIZE)) {
+ ret = 7;
+ goto remove_mac_filters;
+ }
+
+ num_frames = min_t(int, tx_ring->count, 32);
+ for (i = 0; i < num_frames; i++) {
+ if (ice_diag_send(tx_ring, tx_frame, ICE_LB_FRAME_SIZE)) {
+ ret = 8;
+ goto lbtest_free_frame;
+ }
+ }
+
+ valid_frames = ice_lbtest_receive_frames(rx_ring);
+ if (!valid_frames)
+ ret = 9;
+ else if (valid_frames != num_frames)
+ ret = 10;
+
+lbtest_free_frame:
+ devm_kfree(&pf->pdev->dev, tx_frame);
+remove_mac_filters:
+ if (ice_remove_mac(&pf->hw, &tmp_list))
+ netdev_err(netdev, "Could not remove MAC filter for the test VSI");
+free_mac_list:
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_list);
+lbtest_mac_dis:
+ /* Disable MAC loopback after the test is completed. */
+ if (ice_aq_set_mac_loopback(&pf->hw, false, NULL))
+ netdev_err(netdev, "Could not disable MAC loopback\n");
+lbtest_rings_dis:
+ if (ice_lbtest_disable_rings(test_vsi))
+ netdev_err(netdev, "Could not disable test rings\n");
+lbtest_vsi_close:
+ test_vsi->netdev = NULL;
+ if (ice_vsi_release(test_vsi))
+ netdev_err(netdev, "Failed to remove the test VSI");
+
+ return ret;
+}
+
+/**
+ * ice_intr_test - perform an interrupt test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_intr_test(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+ u16 swic_old = pf->sw_int_count;
+
+ netdev_info(netdev, "interrupt test\n");
+
+ wr32(&pf->hw, GLINT_DYN_CTL(pf->oicr_idx),
+ GLINT_DYN_CTL_SW_ITR_INDX_M |
+ GLINT_DYN_CTL_INTENA_MSK_M |
+ GLINT_DYN_CTL_SWINT_TRIG_M);
+
+ usleep_range(1000, 2000);
+ return (swic_old == pf->sw_int_count);
+}
+
+/**
+ * ice_self_test - handler function for performing a self-test by ethtool
+ * @netdev: network interface device structure
+ * @eth_test: ethtool_test structure
+ * @data: required by ethtool.self_test
+ *
+ * This function is called after invoking 'ethtool -t devname' command where
+ * devname is the name of the network device on which ethtool should operate.
+ * It performs a set of self-tests to check if a device works properly.
+ */
+static void
+ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test,
+ u64 *data)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ bool if_running = netif_running(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+ if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+ netdev_info(netdev, "offline testing starting\n");
+
+ set_bit(__ICE_TESTING, pf->state);
+
+ if (ice_active_vfs(pf)) {
+ dev_warn(&pf->pdev->dev,
+ "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n");
+ data[ICE_ETH_TEST_REG] = 1;
+ data[ICE_ETH_TEST_EEPROM] = 1;
+ data[ICE_ETH_TEST_INTR] = 1;
+ data[ICE_ETH_TEST_LOOP] = 1;
+ data[ICE_ETH_TEST_LINK] = 1;
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+ clear_bit(__ICE_TESTING, pf->state);
+ goto skip_ol_tests;
+ }
+ /* If the device is online then take it offline */
+ if (if_running)
+ /* indicate we're in test mode */
+ ice_stop(netdev);
+
+ data[ICE_ETH_TEST_LINK] = ice_link_test(netdev);
+ data[ICE_ETH_TEST_EEPROM] = ice_eeprom_test(netdev);
+ data[ICE_ETH_TEST_INTR] = ice_intr_test(netdev);
+ data[ICE_ETH_TEST_LOOP] = ice_loopback_test(netdev);
+ data[ICE_ETH_TEST_REG] = ice_reg_test(netdev);
+
+ if (data[ICE_ETH_TEST_LINK] ||
+ data[ICE_ETH_TEST_EEPROM] ||
+ data[ICE_ETH_TEST_LOOP] ||
+ data[ICE_ETH_TEST_INTR] ||
+ data[ICE_ETH_TEST_REG])
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ clear_bit(__ICE_TESTING, pf->state);
+
+ if (if_running) {
+ int status = ice_open(netdev);
+
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Could not open device %s, err %d",
+ pf->int_name, status);
+ }
+ }
+ } else {
+ /* Online tests */
+ netdev_info(netdev, "online testing starting\n");
+
+ data[ICE_ETH_TEST_LINK] = ice_link_test(netdev);
+ if (data[ICE_ETH_TEST_LINK])
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+
+ /* Offline only tests, not run in online; pass by default */
+ data[ICE_ETH_TEST_REG] = 0;
+ data[ICE_ETH_TEST_EEPROM] = 0;
+ data[ICE_ETH_TEST_INTR] = 0;
+ data[ICE_ETH_TEST_LOOP] = 0;
+ }
+
+skip_ol_tests:
+ netdev_info(netdev, "testing finished\n");
+}
+
static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -220,17 +856,17 @@
ice_for_each_alloc_txq(vsi, i) {
snprintf(p, ETH_GSTRING_LEN,
- "tx-queue-%u.tx_packets", i);
+ "tx_queue_%u_packets", i);
p += ETH_GSTRING_LEN;
- snprintf(p, ETH_GSTRING_LEN, "tx-queue-%u.tx_bytes", i);
+ snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_bytes", i);
p += ETH_GSTRING_LEN;
}
ice_for_each_alloc_rxq(vsi, i) {
snprintf(p, ETH_GSTRING_LEN,
- "rx-queue-%u.rx_packets", i);
+ "rx_queue_%u_packets", i);
p += ETH_GSTRING_LEN;
- snprintf(p, ETH_GSTRING_LEN, "rx-queue-%u.rx_bytes", i);
+ snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_bytes", i);
p += ETH_GSTRING_LEN;
}
@@ -238,17 +874,392 @@
return;
for (i = 0; i < ICE_PF_STATS_LEN; i++) {
- snprintf(p, ETH_GSTRING_LEN, "port.%s",
+ snprintf(p, ETH_GSTRING_LEN, "%s",
ice_gstrings_pf_stats[i].stat_string);
p += ETH_GSTRING_LEN;
}
+ for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "tx_priority_%u_xon.nic", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN,
+ "tx_priority_%u_xoff.nic", i);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+ snprintf(p, ETH_GSTRING_LEN,
+ "rx_priority_%u_xon.nic", i);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN,
+ "rx_priority_%u_xoff.nic", i);
+ p += ETH_GSTRING_LEN;
+ }
+ break;
+ case ETH_SS_TEST:
+ memcpy(data, ice_gstrings_test, ICE_TEST_LEN * ETH_GSTRING_LEN);
+ break;
+ case ETH_SS_PRIV_FLAGS:
+ for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ ice_gstrings_priv_flags[i].name);
+ p += ETH_GSTRING_LEN;
+ }
break;
default:
break;
}
}
+static int
+ice_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ bool led_active;
+
+ switch (state) {
+ case ETHTOOL_ID_ACTIVE:
+ led_active = true;
+ break;
+ case ETHTOOL_ID_INACTIVE:
+ led_active = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (ice_aq_set_port_id_led(np->vsi->port_info, !led_active, NULL))
+ return -EIO;
+
+ return 0;
+}
+
+/**
+ * ice_set_fec_cfg - Set link FEC options
+ * @netdev: network interface device structure
+ * @req_fec: FEC mode to configure
+ */
+static int ice_set_fec_cfg(struct net_device *netdev, enum ice_fec_mode req_fec)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_aqc_set_phy_cfg_data config = { 0 };
+ struct ice_aqc_get_phy_caps_data *caps;
+ struct ice_vsi *vsi = np->vsi;
+ u8 sw_cfg_caps, sw_cfg_fec;
+ struct ice_port_info *pi;
+ enum ice_status status;
+ int err = 0;
+
+ pi = vsi->port_info;
+ if (!pi)
+ return -EOPNOTSUPP;
+
+ /* Changing the FEC parameters is not supported if not the PF VSI */
+ if (vsi->type != ICE_VSI_PF) {
+ netdev_info(netdev, "Changing FEC parameters only supported for PF VSI\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Get last SW configuration */
+ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+ if (!caps)
+ return -ENOMEM;
+
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG,
+ caps, NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ /* Copy SW configuration returned from PHY caps to PHY config */
+ ice_copy_phy_caps_to_cfg(caps, &config);
+ sw_cfg_caps = caps->caps;
+ sw_cfg_fec = caps->link_fec_options;
+
+ /* Get toloplogy caps, then copy PHY FEC topoloy caps to PHY config */
+ memset(caps, 0, sizeof(*caps));
+
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP,
+ caps, NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ config.caps |= (caps->caps & ICE_AQC_PHY_EN_AUTO_FEC);
+ config.link_fec_opt = caps->link_fec_options;
+
+ ice_cfg_phy_fec(&config, req_fec);
+
+ /* If FEC mode has changed, then set PHY configuration and enable AN. */
+ if ((config.caps & ICE_AQ_PHY_ENA_AUTO_FEC) !=
+ (sw_cfg_caps & ICE_AQC_PHY_EN_AUTO_FEC) ||
+ config.link_fec_opt != sw_cfg_fec) {
+ if (caps->caps & ICE_AQC_PHY_AN_MODE)
+ config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+
+ status = ice_aq_set_phy_cfg(pi->hw, pi->lport, &config, NULL);
+
+ if (status)
+ err = -EAGAIN;
+ }
+
+done:
+ devm_kfree(&vsi->back->pdev->dev, caps);
+ return err;
+}
+
+/**
+ * ice_set_fecparam - Set FEC link options
+ * @netdev: network interface device structure
+ * @fecparam: Ethtool structure to retrieve FEC parameters
+ */
+static int
+ice_set_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ enum ice_fec_mode fec;
+
+ switch (fecparam->fec) {
+ case ETHTOOL_FEC_AUTO:
+ fec = ICE_FEC_AUTO;
+ break;
+ case ETHTOOL_FEC_RS:
+ fec = ICE_FEC_RS;
+ break;
+ case ETHTOOL_FEC_BASER:
+ fec = ICE_FEC_BASER;
+ break;
+ case ETHTOOL_FEC_OFF:
+ case ETHTOOL_FEC_NONE:
+ fec = ICE_FEC_NONE;
+ break;
+ default:
+ dev_warn(&vsi->back->pdev->dev, "Unsupported FEC mode: %d\n",
+ fecparam->fec);
+ return -EINVAL;
+ }
+
+ return ice_set_fec_cfg(netdev, fec);
+}
+
+/**
+ * ice_get_fecparam - Get link FEC options
+ * @netdev: network interface device structure
+ * @fecparam: Ethtool structure to retrieve FEC parameters
+ */
+static int
+ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_aqc_get_phy_caps_data *caps;
+ struct ice_link_status *link_info;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_port_info *pi;
+ enum ice_status status;
+ int err = 0;
+
+ pi = vsi->port_info;
+
+ if (!pi)
+ return -EOPNOTSUPP;
+ link_info = &pi->phy.link_info;
+
+ /* Set FEC mode based on negotiated link info */
+ switch (link_info->fec_info) {
+ case ICE_AQ_LINK_25G_KR_FEC_EN:
+ fecparam->active_fec = ETHTOOL_FEC_BASER;
+ break;
+ case ICE_AQ_LINK_25G_RS_528_FEC_EN:
+ /* fall through */
+ case ICE_AQ_LINK_25G_RS_544_FEC_EN:
+ fecparam->active_fec = ETHTOOL_FEC_RS;
+ break;
+ default:
+ fecparam->active_fec = ETHTOOL_FEC_OFF;
+ break;
+ }
+
+ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+ if (!caps)
+ return -ENOMEM;
+
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP,
+ caps, NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ /* Set supported/configured FEC modes based on PHY capability */
+ if (caps->caps & ICE_AQC_PHY_EN_AUTO_FEC)
+ fecparam->fec |= ETHTOOL_FEC_AUTO;
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+ fecparam->fec |= ETHTOOL_FEC_BASER;
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
+ fecparam->fec |= ETHTOOL_FEC_RS;
+ if (caps->link_fec_options == 0)
+ fecparam->fec |= ETHTOOL_FEC_OFF;
+
+done:
+ devm_kfree(&vsi->back->pdev->dev, caps);
+ return err;
+}
+
+/**
+ * ice_get_priv_flags - report device private flags
+ * @netdev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned. Add new strings for each flag to the ice_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ */
+static u32 ice_get_priv_flags(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ u32 i, ret_flags = 0;
+
+ for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+ const struct ice_priv_flag *priv_flag;
+
+ priv_flag = &ice_gstrings_priv_flags[i];
+
+ if (test_bit(priv_flag->bitno, pf->flags))
+ ret_flags |= BIT(i);
+ }
+
+ return ret_flags;
+}
+
+/**
+ * ice_set_priv_flags - set private flags
+ * @netdev: network interface device structure
+ * @flags: bit flags to be set
+ */
+static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ DECLARE_BITMAP(change_flags, ICE_PF_FLAGS_NBITS);
+ DECLARE_BITMAP(orig_flags, ICE_PF_FLAGS_NBITS);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ int ret = 0;
+ u32 i;
+
+ if (flags > BIT(ICE_PRIV_FLAG_ARRAY_SIZE))
+ return -EINVAL;
+
+ set_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
+
+ bitmap_copy(orig_flags, pf->flags, ICE_PF_FLAGS_NBITS);
+ for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+ const struct ice_priv_flag *priv_flag;
+
+ priv_flag = &ice_gstrings_priv_flags[i];
+
+ if (flags & BIT(i))
+ set_bit(priv_flag->bitno, pf->flags);
+ else
+ clear_bit(priv_flag->bitno, pf->flags);
+ }
+
+ bitmap_xor(change_flags, pf->flags, orig_flags, ICE_PF_FLAGS_NBITS);
+
+ if (test_bit(ICE_FLAG_FW_LLDP_AGENT, change_flags)) {
+ if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) {
+ enum ice_status status;
+
+ /* Disable FW LLDP engine */
+ status = ice_cfg_lldp_mib_change(&pf->hw, false);
+
+ /* If unregistering for LLDP events fails, this is
+ * not an error state, as there shouldn't be any
+ * events to respond to.
+ */
+ if (status)
+ dev_info(&pf->pdev->dev,
+ "Failed to unreg for LLDP events\n");
+
+ /* The AQ call to stop the FW LLDP agent will generate
+ * an error if the agent is already stopped.
+ */
+ status = ice_aq_stop_lldp(&pf->hw, true, true, NULL);
+ if (status)
+ dev_warn(&pf->pdev->dev,
+ "Fail to stop LLDP agent\n");
+ /* Use case for having the FW LLDP agent stopped
+ * will likely not need DCB, so failure to init is
+ * not a concern of ethtool
+ */
+ status = ice_init_pf_dcb(pf, true);
+ if (status)
+ dev_warn(&pf->pdev->dev, "Fail to init DCB\n");
+
+ /* Forward LLDP packets to default VSI so that they
+ * are passed up the stack
+ */
+ ice_cfg_sw_lldp(vsi, false, true);
+ } else {
+ enum ice_status status;
+ bool dcbx_agent_status;
+
+ /* AQ command to start FW LLDP agent will return an
+ * error if the agent is already started
+ */
+ status = ice_aq_start_lldp(&pf->hw, true, NULL);
+ if (status)
+ dev_warn(&pf->pdev->dev,
+ "Fail to start LLDP Agent\n");
+
+ /* AQ command to start FW DCBX agent will fail if
+ * the agent is already started
+ */
+ status = ice_aq_start_stop_dcbx(&pf->hw, true,
+ &dcbx_agent_status,
+ NULL);
+ if (status)
+ dev_dbg(&pf->pdev->dev,
+ "Failed to start FW DCBX\n");
+
+ dev_info(&pf->pdev->dev, "FW DCBX agent is %s\n",
+ dcbx_agent_status ? "ACTIVE" : "DISABLED");
+
+ /* Failure to configure MIB change or init DCB is not
+ * relevant to ethtool. Print notification that
+ * registration/init failed but do not return error
+ * state to ethtool
+ */
+ status = ice_init_pf_dcb(pf, true);
+ if (status)
+ dev_dbg(&pf->pdev->dev, "Fail to init DCB\n");
+
+ /* Remove rule to direct LLDP packets to default VSI.
+ * The FW LLDP engine will now be consuming them.
+ */
+ ice_cfg_sw_lldp(vsi, false, false);
+
+ /* Register for MIB change events */
+ status = ice_cfg_lldp_mib_change(&pf->hw, true);
+ if (status)
+ dev_dbg(&pf->pdev->dev,
+ "Fail to enable MIB change events\n");
+ }
+ }
+ clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
+ return ret;
+}
+
static int ice_get_sset_count(struct net_device *netdev, int sset)
{
switch (sset) {
@@ -260,10 +1271,10 @@
* a private ethtool flag). This is due to the nature of the
* ethtool stats API.
*
- * User space programs such as ethtool must make 3 separate
+ * Userspace programs such as ethtool must make 3 separate
* ioctl requests, one for size, one for the strings, and
* finally one for the stats. Since these cross into
- * user space, changes to the number or size could result in
+ * userspace, changes to the number or size could result in
* undefined memory access or incorrect string<->value
* correlations for statistics.
*
@@ -272,6 +1283,10 @@
* not safe.
*/
return ICE_ALL_STATS_LEN(netdev);
+ case ETH_SS_TEST:
+ return ICE_TEST_LEN;
+ case ETH_SS_PRIV_FLAGS:
+ return ICE_PRIV_FLAG_ARRAY_SIZE;
default:
return -EOPNOTSUPP;
}
@@ -285,14 +1300,17 @@
struct ice_vsi *vsi = np->vsi;
struct ice_pf *pf = vsi->back;
struct ice_ring *ring;
- unsigned int j = 0;
+ unsigned int j;
int i = 0;
char *p;
+ ice_update_pf_stats(pf);
+ ice_update_vsi_stats(vsi);
+
for (j = 0; j < ICE_VSI_STATS_LEN; j++) {
p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset;
data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat ==
- sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
/* populate per queue stats */
@@ -330,60 +1348,765 @@
data[i++] = (ice_gstrings_pf_stats[j].sizeof_stat ==
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
+
+ for (j = 0; j < ICE_MAX_USER_PRIORITY; j++) {
+ data[i++] = pf->stats.priority_xon_tx[j];
+ data[i++] = pf->stats.priority_xoff_tx[j];
+ }
+
+ for (j = 0; j < ICE_MAX_USER_PRIORITY; j++) {
+ data[i++] = pf->stats.priority_xon_rx[j];
+ data[i++] = pf->stats.priority_xoff_rx[j];
+ }
}
+/**
+ * ice_phy_type_to_ethtool - convert the phy_types to ethtool link modes
+ * @netdev: network interface device structure
+ * @ks: ethtool link ksettings struct to fill out
+ */
+static void
+ice_phy_type_to_ethtool(struct net_device *netdev,
+ struct ethtool_link_ksettings *ks)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_link_status *hw_link_info;
+ bool need_add_adv_mode = false;
+ struct ice_vsi *vsi = np->vsi;
+ u64 phy_types_high;
+ u64 phy_types_low;
+
+ hw_link_info = &vsi->port_info->phy.link_info;
+ phy_types_low = vsi->port_info->phy.phy_type_low;
+ phy_types_high = vsi->port_info->phy.phy_type_high;
+
+ ethtool_link_ksettings_zero_link_mode(ks, supported);
+ ethtool_link_ksettings_zero_link_mode(ks, advertising);
+
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100M_SGMII) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100baseT_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_1G_SGMII) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseKX_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseKX_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_SX ||
+ phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_LX) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseX_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseX_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseT_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseT_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_X ||
+ phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseX_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseX_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 5000baseT_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 5000baseT_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_DA ||
+ phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_C2C) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_SR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseSR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseSR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_LR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseLR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseLR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_C2C) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_SR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_LR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseSR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseSR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseKR_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseKR_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseKR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseKR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseCR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_SR4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseSR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseSR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_LR4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseLR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseLR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseCR2_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 50000baseCR2_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseKR2_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 50000baseKR2_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_FR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseSR2_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 50000baseSR2_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2 ||
+ phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC ||
+ phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2 ||
+ phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC ||
+ phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseCR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+ need_add_adv_mode = true;
+ }
+ if (need_add_adv_mode) {
+ need_add_adv_mode = false;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseCR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseSR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+ need_add_adv_mode = true;
+ }
+ if (need_add_adv_mode) {
+ need_add_adv_mode = false;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseSR4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_LR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_DR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseLR4_ER4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+ need_add_adv_mode = true;
+ }
+ if (need_add_adv_mode) {
+ need_add_adv_mode = false;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseLR4_ER4_Full);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+ phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseKR4_Full);
+ if (!hw_link_info->req_speeds ||
+ hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+ need_add_adv_mode = true;
+ }
+ if (need_add_adv_mode)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseKR4_Full);
+
+ /* Autoneg PHY types */
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
+ phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX ||
+ phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX ||
+ phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S ||
+ phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Autoneg);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+ phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Autoneg);
+ }
+ if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+ phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Autoneg);
+ }
+}
+
+#define TEST_SET_BITS_TIMEOUT 50
+#define TEST_SET_BITS_SLEEP_MAX 2000
+#define TEST_SET_BITS_SLEEP_MIN 1000
+
+/**
+ * ice_get_settings_link_up - Get Link settings for when link is up
+ * @ks: ethtool ksettings to fill in
+ * @netdev: network interface device structure
+ */
+static void
+ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
+ struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_port_info *pi = np->vsi->port_info;
+ struct ethtool_link_ksettings cap_ksettings;
+ struct ice_link_status *link_info;
+ struct ice_vsi *vsi = np->vsi;
+ bool unrecog_phy_high = false;
+ bool unrecog_phy_low = false;
+
+ link_info = &vsi->port_info->phy.link_info;
+
+ /* Initialize supported and advertised settings based on PHY settings */
+ switch (link_info->phy_type_low) {
+ case ICE_PHY_TYPE_LOW_100BASE_TX:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100M_SGMII:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_1000BASE_T:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_1G_SGMII:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_1000BASE_SX:
+ case ICE_PHY_TYPE_LOW_1000BASE_LX:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseX_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_1000BASE_KX:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseKX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseKX_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_2500BASE_T:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_2500BASE_X:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseX_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_2500BASE_KX:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 2500baseX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 2500baseX_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_5GBASE_T:
+ case ICE_PHY_TYPE_LOW_5GBASE_KR:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 5000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 5000baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_10GBASE_T:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_10G_SFI_DA:
+ case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_10G_SFI_C2C:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_10GBASE_SR:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseSR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_10GBASE_LR:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseLR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_25GBASE_T:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
+ case ICE_PHY_TYPE_LOW_25GBASE_CR1:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_25GBASE_SR:
+ case ICE_PHY_TYPE_LOW_25GBASE_LR:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseSR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_25GBASE_KR:
+ case ICE_PHY_TYPE_LOW_25GBASE_KR1:
+ case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseKR_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_40GBASE_CR4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseCR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_40G_XLAUI:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_40GBASE_SR4:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseSR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_40GBASE_LR4:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseLR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_40GBASE_KR4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseKR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_CP:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseCR2_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 50000baseCR2_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_LAUI2:
+ case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_AUI2:
+ case ICE_PHY_TYPE_LOW_50GBASE_SR:
+ case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_50G_AUI1:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseCR2_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseKR2_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 50000baseKR2_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+ case ICE_PHY_TYPE_LOW_50GBASE_FR:
+ case ICE_PHY_TYPE_LOW_50GBASE_LR:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 50000baseSR2_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseCR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseCR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_100G_CAUI4:
+ case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+ case ICE_PHY_TYPE_LOW_100G_AUI4:
+ case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseCR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseCR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseCR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseSR4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_DR:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseLR4_ER4_Full);
+ break;
+ case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+ case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseKR4_Full);
+ break;
+ default:
+ unrecog_phy_low = true;
+ }
+
+ switch (link_info->phy_type_high) {
+ case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100000baseKR4_Full);
+ break;
+ case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+ case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+ case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+ case ICE_PHY_TYPE_HIGH_100G_AUI2:
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100000baseCR4_Full);
+ break;
+ default:
+ unrecog_phy_high = true;
+ }
+
+ if (unrecog_phy_low && unrecog_phy_high) {
+ /* if we got here and link is up something bad is afoot */
+ netdev_info(netdev,
+ "WARNING: Unrecognized PHY_Low (0x%llx).\n",
+ (u64)link_info->phy_type_low);
+ netdev_info(netdev,
+ "WARNING: Unrecognized PHY_High (0x%llx).\n",
+ (u64)link_info->phy_type_high);
+ }
+
+ /* Now that we've worked out everything that could be supported by the
+ * current PHY type, get what is supported by the NVM and intersect
+ * them to get what is truly supported
+ */
+ memset(&cap_ksettings, 0, sizeof(cap_ksettings));
+ ice_phy_type_to_ethtool(netdev, &cap_ksettings);
+ ethtool_intersect_link_masks(ks, &cap_ksettings);
+
+ switch (link_info->link_speed) {
+ case ICE_AQ_LINK_SPEED_100GB:
+ ks->base.speed = SPEED_100000;
+ break;
+ case ICE_AQ_LINK_SPEED_50GB:
+ ks->base.speed = SPEED_50000;
+ break;
+ case ICE_AQ_LINK_SPEED_40GB:
+ ks->base.speed = SPEED_40000;
+ break;
+ case ICE_AQ_LINK_SPEED_25GB:
+ ks->base.speed = SPEED_25000;
+ break;
+ case ICE_AQ_LINK_SPEED_20GB:
+ ks->base.speed = SPEED_20000;
+ break;
+ case ICE_AQ_LINK_SPEED_10GB:
+ ks->base.speed = SPEED_10000;
+ break;
+ case ICE_AQ_LINK_SPEED_5GB:
+ ks->base.speed = SPEED_5000;
+ break;
+ case ICE_AQ_LINK_SPEED_2500MB:
+ ks->base.speed = SPEED_2500;
+ break;
+ case ICE_AQ_LINK_SPEED_1000MB:
+ ks->base.speed = SPEED_1000;
+ break;
+ case ICE_AQ_LINK_SPEED_100MB:
+ ks->base.speed = SPEED_100;
+ break;
+ default:
+ netdev_info(netdev,
+ "WARNING: Unrecognized link_speed (0x%x).\n",
+ link_info->link_speed);
+ break;
+ }
+ ks->base.duplex = DUPLEX_FULL;
+
+ if (link_info->an_info & ICE_AQ_AN_COMPLETED)
+ ethtool_link_ksettings_add_link_mode(ks, lp_advertising,
+ Autoneg);
+
+ /* Set flow control negotiated Rx/Tx pause */
+ switch (pi->fc.current_mode) {
+ case ICE_FC_FULL:
+ ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause);
+ break;
+ case ICE_FC_TX_PAUSE:
+ ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(ks, lp_advertising,
+ Asym_Pause);
+ break;
+ case ICE_FC_RX_PAUSE:
+ ethtool_link_ksettings_add_link_mode(ks, lp_advertising,
+ Asym_Pause);
+ break;
+ case ICE_FC_PFC:
+ /* fall through */
+ default:
+ ethtool_link_ksettings_del_link_mode(ks, lp_advertising, Pause);
+ ethtool_link_ksettings_del_link_mode(ks, lp_advertising,
+ Asym_Pause);
+ break;
+ }
+}
+
+/**
+ * ice_get_settings_link_down - Get the Link settings when link is down
+ * @ks: ethtool ksettings to fill in
+ * @netdev: network interface device structure
+ *
+ * Reports link settings that can be determined when link is down
+ */
+static void
+ice_get_settings_link_down(struct ethtool_link_ksettings *ks,
+ struct net_device *netdev)
+{
+ /* link is down and the driver needs to fall back on
+ * supported PHY types to figure out what info to display
+ */
+ ice_phy_type_to_ethtool(netdev, ks);
+
+ /* With no link, speed and duplex are unknown */
+ ks->base.speed = SPEED_UNKNOWN;
+ ks->base.duplex = DUPLEX_UNKNOWN;
+}
+
+/**
+ * ice_get_link_ksettings - Get Link Speed and Duplex settings
+ * @netdev: network interface device structure
+ * @ks: ethtool ksettings
+ *
+ * Reports speed/duplex settings based on media_type
+ */
static int
ice_get_link_ksettings(struct net_device *netdev,
struct ethtool_link_ksettings *ks)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_aqc_get_phy_caps_data *caps;
struct ice_link_status *hw_link_info;
struct ice_vsi *vsi = np->vsi;
- bool link_up;
+ enum ice_status status;
+ int err = 0;
+ ethtool_link_ksettings_zero_link_mode(ks, supported);
+ ethtool_link_ksettings_zero_link_mode(ks, advertising);
+ ethtool_link_ksettings_zero_link_mode(ks, lp_advertising);
hw_link_info = &vsi->port_info->phy.link_info;
- link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
-
- ethtool_link_ksettings_add_link_mode(ks, supported,
- 10000baseT_Full);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- 10000baseT_Full);
/* set speed and duplex */
- if (link_up) {
- switch (hw_link_info->link_speed) {
- case ICE_AQ_LINK_SPEED_100MB:
- ks->base.speed = SPEED_100;
- break;
- case ICE_AQ_LINK_SPEED_2500MB:
- ks->base.speed = SPEED_2500;
- break;
- case ICE_AQ_LINK_SPEED_5GB:
- ks->base.speed = SPEED_5000;
- break;
- case ICE_AQ_LINK_SPEED_10GB:
- ks->base.speed = SPEED_10000;
- break;
- case ICE_AQ_LINK_SPEED_25GB:
- ks->base.speed = SPEED_25000;
- break;
- case ICE_AQ_LINK_SPEED_40GB:
- ks->base.speed = SPEED_40000;
- break;
- default:
- ks->base.speed = SPEED_UNKNOWN;
- break;
- }
-
- ks->base.duplex = DUPLEX_FULL;
- } else {
- ks->base.speed = SPEED_UNKNOWN;
- ks->base.duplex = DUPLEX_UNKNOWN;
- }
+ if (hw_link_info->link_info & ICE_AQ_LINK_UP)
+ ice_get_settings_link_up(ks, netdev);
+ else
+ ice_get_settings_link_down(ks, netdev);
/* set autoneg settings */
- ks->base.autoneg = ((hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ?
- AUTONEG_ENABLE : AUTONEG_DISABLE);
+ ks->base.autoneg = (hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE;
/* set media type settings */
switch (vsi->port_info->phy.media_type) {
@@ -417,40 +2140,403 @@
/* flow control is symmetric and always supported */
ethtool_link_ksettings_add_link_mode(ks, supported, Pause);
- switch (vsi->port_info->fc.req_mode) {
- case ICE_FC_FULL:
- ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
- break;
- case ICE_FC_TX_PAUSE:
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Asym_Pause);
- break;
- case ICE_FC_RX_PAUSE:
+ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+ if (!caps)
+ return -ENOMEM;
+
+ status = ice_aq_get_phy_caps(vsi->port_info, false,
+ ICE_AQC_REPORT_SW_CFG, caps, NULL);
+ if (status) {
+ err = -EIO;
+ goto done;
+ }
+
+ /* Set the advertised flow control based on the PHY capability */
+ if ((caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) &&
+ (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)) {
ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
ethtool_link_ksettings_add_link_mode(ks, advertising,
Asym_Pause);
- break;
- case ICE_FC_PFC:
- default:
+ } else if (caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Asym_Pause);
+ } else if (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Asym_Pause);
+ } else {
ethtool_link_ksettings_del_link_mode(ks, advertising, Pause);
ethtool_link_ksettings_del_link_mode(ks, advertising,
Asym_Pause);
- break;
}
- return 0;
+ /* Set advertised FEC modes based on PHY capability */
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ)
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+
+ status = ice_aq_get_phy_caps(vsi->port_info, false,
+ ICE_AQC_REPORT_TOPO_CAP, caps, NULL);
+ if (status) {
+ err = -EIO;
+ goto done;
+ }
+
+ /* Set supported FEC modes based on PHY capability */
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN)
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+
+done:
+ devm_kfree(&vsi->back->pdev->dev, caps);
+ return err;
}
/**
- * ice_get_rxnfc - command to get RX flow classification rules
+ * ice_ksettings_find_adv_link_speed - Find advertising link speed
+ * @ks: ethtool ksettings
+ */
+static u16
+ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
+{
+ u16 adv_link_speed = 0;
+
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100baseT_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_100MB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseX_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseT_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseKX_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 2500baseT_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 2500baseX_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 5000baseT_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_5GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseT_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseKR_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_10GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseSR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseLR_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_10GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseCR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseSR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseKR_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_25GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseCR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseSR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseLR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseKR4_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_40GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 50000baseCR2_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 50000baseKR2_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 50000baseSR2_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100000baseCR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100000baseSR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100000baseLR4_ER4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100000baseKR4_Full))
+ adv_link_speed |= ICE_AQ_LINK_SPEED_100GB;
+
+ return adv_link_speed;
+}
+
+/**
+ * ice_setup_autoneg
+ * @p: port info
+ * @ks: ethtool_link_ksettings
+ * @config: configuration that will be sent down to FW
+ * @autoneg_enabled: autonegotiation is enabled or not
+ * @autoneg_changed: will there a change in autonegotiation
+ * @netdev: network interface device structure
+ *
+ * Setup PHY autonegotiation feature
+ */
+static int
+ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
+ struct ice_aqc_set_phy_cfg_data *config,
+ u8 autoneg_enabled, u8 *autoneg_changed,
+ struct net_device *netdev)
+{
+ int err = 0;
+
+ *autoneg_changed = 0;
+
+ /* Check autoneg */
+ if (autoneg_enabled == AUTONEG_ENABLE) {
+ /* If autoneg was not already enabled */
+ if (!(p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)) {
+ /* If autoneg is not supported, return error */
+ if (!ethtool_link_ksettings_test_link_mode(ks,
+ supported,
+ Autoneg)) {
+ netdev_info(netdev, "Autoneg not supported on this phy.\n");
+ err = -EINVAL;
+ } else {
+ /* Autoneg is allowed to change */
+ config->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+ *autoneg_changed = 1;
+ }
+ }
+ } else {
+ /* If autoneg is currently enabled */
+ if (p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) {
+ /* If autoneg is supported 10GBASE_T is the only PHY
+ * that can disable it, so otherwise return error
+ */
+ if (ethtool_link_ksettings_test_link_mode(ks,
+ supported,
+ Autoneg)) {
+ netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
+ err = -EINVAL;
+ } else {
+ /* Autoneg is allowed to change */
+ config->caps &= ~ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+ *autoneg_changed = 1;
+ }
+ }
+ }
+
+ return err;
+}
+
+/**
+ * ice_set_link_ksettings - Set Speed and Duplex
+ * @netdev: network interface device structure
+ * @ks: ethtool ksettings
+ *
+ * Set speed/duplex per media_types advertised/forced
+ */
+static int
+ice_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *ks)
+{
+ u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0;
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ethtool_link_ksettings safe_ks, copy_ks;
+ struct ice_aqc_get_phy_caps_data *abilities;
+ u16 adv_link_speed, curr_link_speed, idx;
+ struct ice_aqc_set_phy_cfg_data config;
+ struct ice_pf *pf = np->vsi->back;
+ struct ice_port_info *p;
+ u8 autoneg_changed = 0;
+ enum ice_status status;
+ u64 phy_type_high;
+ u64 phy_type_low;
+ int err = 0;
+ bool linkup;
+
+ p = np->vsi->port_info;
+
+ if (!p)
+ return -EOPNOTSUPP;
+
+ /* Check if this is LAN VSI */
+ ice_for_each_vsi(pf, idx)
+ if (pf->vsi[idx]->type == ICE_VSI_PF) {
+ if (np->vsi != pf->vsi[idx])
+ return -EOPNOTSUPP;
+ break;
+ }
+
+ if (p->phy.media_type != ICE_MEDIA_BASET &&
+ p->phy.media_type != ICE_MEDIA_FIBER &&
+ p->phy.media_type != ICE_MEDIA_BACKPLANE &&
+ p->phy.media_type != ICE_MEDIA_DA &&
+ p->phy.link_info.link_info & ICE_AQ_LINK_UP)
+ return -EOPNOTSUPP;
+
+ /* copy the ksettings to copy_ks to avoid modifying the original */
+ memcpy(©_ks, ks, sizeof(copy_ks));
+
+ /* save autoneg out of ksettings */
+ autoneg = copy_ks.base.autoneg;
+
+ memset(&safe_ks, 0, sizeof(safe_ks));
+
+ /* Get link modes supported by hardware.*/
+ ice_phy_type_to_ethtool(netdev, &safe_ks);
+
+ /* and check against modes requested by user.
+ * Return an error if unsupported mode was set.
+ */
+ if (!bitmap_subset(copy_ks.link_modes.advertising,
+ safe_ks.link_modes.supported,
+ __ETHTOOL_LINK_MODE_MASK_NBITS))
+ return -EINVAL;
+
+ /* get our own copy of the bits to check against */
+ memset(&safe_ks, 0, sizeof(safe_ks));
+ safe_ks.base.cmd = copy_ks.base.cmd;
+ safe_ks.base.link_mode_masks_nwords =
+ copy_ks.base.link_mode_masks_nwords;
+ ice_get_link_ksettings(netdev, &safe_ks);
+
+ /* set autoneg back to what it currently is */
+ copy_ks.base.autoneg = safe_ks.base.autoneg;
+ /* we don't compare the speed */
+ copy_ks.base.speed = safe_ks.base.speed;
+
+ /* If copy_ks.base and safe_ks.base are not the same now, then they are
+ * trying to set something that we do not support.
+ */
+ if (memcmp(©_ks.base, &safe_ks.base, sizeof(copy_ks.base)))
+ return -EOPNOTSUPP;
+
+ while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
+ timeout--;
+ if (!timeout)
+ return -EBUSY;
+ usleep_range(TEST_SET_BITS_SLEEP_MIN, TEST_SET_BITS_SLEEP_MAX);
+ }
+
+ abilities = devm_kzalloc(&pf->pdev->dev, sizeof(*abilities),
+ GFP_KERNEL);
+ if (!abilities)
+ return -ENOMEM;
+
+ /* Get the current PHY config */
+ status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_SW_CFG, abilities,
+ NULL);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ /* Copy abilities to config in case autoneg is not set below */
+ memset(&config, 0, sizeof(config));
+ config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE;
+ if (abilities->caps & ICE_AQC_PHY_AN_MODE)
+ config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+
+ /* Check autoneg */
+ err = ice_setup_autoneg(p, &safe_ks, &config, autoneg, &autoneg_changed,
+ netdev);
+
+ if (err)
+ goto done;
+
+ /* Call to get the current link speed */
+ p->phy.get_link_info = true;
+ status = ice_get_link_status(p, &linkup);
+ if (status) {
+ err = -EAGAIN;
+ goto done;
+ }
+
+ curr_link_speed = p->phy.link_info.link_speed;
+ adv_link_speed = ice_ksettings_find_adv_link_speed(ks);
+
+ /* If speed didn't get set, set it to what it currently is.
+ * This is needed because if advertise is 0 (as it is when autoneg
+ * is disabled) then speed won't get set.
+ */
+ if (!adv_link_speed)
+ adv_link_speed = curr_link_speed;
+
+ /* Convert the advertise link speeds to their corresponded PHY_TYPE */
+ ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed);
+
+ if (!autoneg_changed && adv_link_speed == curr_link_speed) {
+ netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
+ goto done;
+ }
+
+ /* copy over the rest of the abilities */
+ config.low_power_ctrl = abilities->low_power_ctrl;
+ config.eee_cap = abilities->eee_cap;
+ config.eeer_value = abilities->eeer_value;
+ config.link_fec_opt = abilities->link_fec_options;
+
+ /* save the requested speeds */
+ p->phy.link_info.req_speeds = adv_link_speed;
+
+ /* set link and auto negotiation so changes take effect */
+ config.caps |= ICE_AQ_PHY_ENA_LINK;
+
+ if (phy_type_low || phy_type_high) {
+ config.phy_type_high = cpu_to_le64(phy_type_high) &
+ abilities->phy_type_high;
+ config.phy_type_low = cpu_to_le64(phy_type_low) &
+ abilities->phy_type_low;
+ } else {
+ err = -EAGAIN;
+ netdev_info(netdev, "Nothing changed. No PHY_TYPE is corresponded to advertised link speed.\n");
+ goto done;
+ }
+
+ /* If link is up put link down */
+ if (p->phy.link_info.link_info & ICE_AQ_LINK_UP) {
+ /* Tell the OS link is going down, the link will go
+ * back up when fw says it is ready asynchronously
+ */
+ ice_print_link_msg(np->vsi, false);
+ netif_carrier_off(netdev);
+ netif_tx_stop_all_queues(netdev);
+ }
+
+ /* make the aq call */
+ status = ice_aq_set_phy_cfg(&pf->hw, lport, &config, NULL);
+ if (status) {
+ netdev_info(netdev, "Set phy config failed,\n");
+ err = -EAGAIN;
+ }
+
+done:
+ devm_kfree(&pf->pdev->dev, abilities);
+ clear_bit(__ICE_CFG_BUSY, pf->state);
+
+ return err;
+}
+
+/**
+ * ice_get_rxnfc - command to get Rx flow classification rules
* @netdev: network interface device structure
* @cmd: ethtool rxnfc command
* @rule_locs: buffer to rturn Rx flow classification rules
*
* Returns Success if the command is supported.
*/
-static int ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
- u32 __always_unused *rule_locs)
+static int
+ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+ u32 __always_unused *rule_locs)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
@@ -550,7 +2636,7 @@
vsi->tx_rings[0]->count, new_tx_cnt);
tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
- sizeof(struct ice_ring), GFP_KERNEL);
+ sizeof(*tx_rings), GFP_KERNEL);
if (!tx_rings) {
err = -ENOMEM;
goto done;
@@ -582,7 +2668,7 @@
vsi->rx_rings[0]->count, new_rx_cnt);
rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
- sizeof(struct ice_ring), GFP_KERNEL);
+ sizeof(*rx_rings), GFP_KERNEL);
if (!rx_rings) {
err = -ENOMEM;
goto done;
@@ -672,17 +2758,17 @@
{
/* restart autonegotiation */
struct ice_netdev_priv *np = netdev_priv(netdev);
- struct ice_link_status *hw_link_info;
struct ice_vsi *vsi = np->vsi;
struct ice_port_info *pi;
enum ice_status status;
- bool link_up;
pi = vsi->port_info;
- hw_link_info = &pi->phy.link_info;
- link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+ /* If VSI state is up, then restart autoneg with link up */
+ if (!test_bit(__ICE_DOWN, vsi->back->state))
+ status = ice_aq_set_link_restart_an(pi, true, NULL);
+ else
+ status = ice_aq_set_link_restart_an(pi, false, NULL);
- status = ice_aq_set_link_restart_an(pi, link_up, NULL);
if (status) {
netdev_info(netdev, "link restart failed, err %d aq_err %d\n",
status, pi->hw->adminq.sq_last_status);
@@ -696,39 +2782,68 @@
* ice_get_pauseparam - Get Flow Control status
* @netdev: network interface device structure
* @pause: ethernet pause (flow control) parameters
+ *
+ * Get requested flow control status from PHY capability.
+ * If autoneg is true, then ethtool will send the ETHTOOL_GSET ioctl which
+ * is handled by ice_get_link_ksettings. ice_get_link_ksettings will report
+ * the negotiated Rx/Tx pause via lp_advertising.
*/
static void
ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
- struct ice_port_info *pi;
+ struct ice_port_info *pi = np->vsi->port_info;
+ struct ice_aqc_get_phy_caps_data *pcaps;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_dcbx_cfg *dcbx_cfg;
+ enum ice_status status;
- pi = np->vsi->port_info;
- pause->autoneg =
- ((pi->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) ?
- AUTONEG_ENABLE : AUTONEG_DISABLE);
+ /* Initialize pause params */
+ pause->rx_pause = 0;
+ pause->tx_pause = 0;
- if (pi->fc.current_mode == ICE_FC_RX_PAUSE) {
- pause->rx_pause = 1;
- } else if (pi->fc.current_mode == ICE_FC_TX_PAUSE) {
+ dcbx_cfg = &pi->local_dcbx_cfg;
+
+ pcaps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*pcaps),
+ GFP_KERNEL);
+ if (!pcaps)
+ return;
+
+ /* Get current PHY config */
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+ NULL);
+ if (status)
+ goto out;
+
+ pause->autoneg = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ if (dcbx_cfg->pfc.pfcena)
+ /* PFC enabled so report LFC as off */
+ goto out;
+
+ if (pcaps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE)
pause->tx_pause = 1;
- } else if (pi->fc.current_mode == ICE_FC_FULL) {
+ if (pcaps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)
pause->rx_pause = 1;
- pause->tx_pause = 1;
- }
+
+out:
+ devm_kfree(&vsi->back->pdev->dev, pcaps);
}
/**
* ice_set_pauseparam - Set Flow Control parameter
* @netdev: network interface device structure
- * @pause: return tx/rx flow control status
+ * @pause: return Tx/Rx flow control status
*/
static int
ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_aqc_get_phy_caps_data *pcaps;
struct ice_link_status *hw_link_info;
struct ice_pf *pf = np->vsi->back;
+ struct ice_dcbx_cfg *dcbx_cfg;
struct ice_vsi *vsi = np->vsi;
struct ice_hw *hw = &pf->hw;
struct ice_port_info *pi;
@@ -736,9 +2851,11 @@
u8 aq_failures;
bool link_up;
int err = 0;
+ u32 is_an;
pi = vsi->port_info;
hw_link_info = &pi->phy.link_info;
+ dcbx_cfg = &pi->local_dcbx_cfg;
link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
/* Changing the port's flow control is not supported if this isn't the
@@ -749,7 +2866,30 @@
return -EOPNOTSUPP;
}
- if (pause->autoneg != (hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) {
+ /* Get pause param reports configured and negotiated flow control pause
+ * when ETHTOOL_GLINKSETTINGS is defined. Since ETHTOOL_GLINKSETTINGS is
+ * defined get pause param pause->autoneg reports SW configured setting,
+ * so compare pause->autoneg with SW configured to prevent the user from
+ * using set pause param to chance autoneg.
+ */
+ pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL);
+ if (!pcaps)
+ return -ENOMEM;
+
+ /* Get current PHY config */
+ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+ NULL);
+ if (status) {
+ kfree(pcaps);
+ return -EIO;
+ }
+
+ is_an = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ kfree(pcaps);
+
+ if (pause->autoneg != is_an) {
netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
return -EOPNOTSUPP;
}
@@ -761,6 +2901,10 @@
netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
}
+ if (dcbx_cfg->pfc.pfcena) {
+ netdev_info(netdev, "Priority flow control enabled. Cannot set link flow control.\n");
+ return -EOPNOTSUPP;
+ }
if (pause->rx_pause && pause->tx_pause)
pi->fc.req_mode = ICE_FC_FULL;
else if (pause->rx_pause && !pause->tx_pause)
@@ -823,7 +2967,7 @@
}
/**
- * ice_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * ice_get_rxfh_indir_size - get the Rx flow hash indirection table size
* @netdev: network interface device structure
*
* Returns the table size.
@@ -836,7 +2980,7 @@
}
/**
- * ice_get_rxfh - get the rx flow hash indirection table
+ * ice_get_rxfh - get the Rx flow hash indirection table
* @netdev: network interface device structure
* @indir: indirection table
* @key: hash key
@@ -883,17 +3027,18 @@
}
/**
- * ice_set_rxfh - set the rx flow hash indirection table
+ * ice_set_rxfh - set the Rx flow hash indirection table
* @netdev: network interface device structure
* @indir: indirection table
* @key: hash key
* @hfunc: hash function
*
- * Returns -EINVAL if the table specifies an invalid queue id, otherwise
+ * Returns -EINVAL if the table specifies an invalid queue ID, otherwise
* returns 0 after programming the table.
*/
-static int ice_set_rxfh(struct net_device *netdev, const u32 *indir,
- const u8 *key, const u8 hfunc)
+static int
+ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
+ const u8 hfunc)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
@@ -947,16 +3092,331 @@
return 0;
}
+enum ice_container_type {
+ ICE_RX_CONTAINER,
+ ICE_TX_CONTAINER,
+};
+
+/**
+ * ice_get_rc_coalesce - get ITR values for specific ring container
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @c_type: container type, Rx or Tx
+ * @rc: ring container that the ITR values will come from
+ *
+ * Query the device for ice_ring_container specific ITR values. This is
+ * done per ice_ring_container because each q_vector can have 1 or more rings
+ * and all of said ring(s) will have the same ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
+ struct ice_ring_container *rc)
+{
+ struct ice_pf *pf;
+
+ if (!rc->ring)
+ return -EINVAL;
+
+ pf = rc->ring->vsi->back;
+
+ switch (c_type) {
+ case ICE_RX_CONTAINER:
+ ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+ ec->rx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+ ec->rx_coalesce_usecs_high = rc->ring->q_vector->intrl;
+ break;
+ case ICE_TX_CONTAINER:
+ ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+ ec->tx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+ break;
+ default:
+ dev_dbg(&pf->pdev->dev, "Invalid c_type %d\n", c_type);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_q_coalesce - get a queue's ITR/INTRL (coalesce) settings
+ * @vsi: VSI associated to the queue for getting ITR/INTRL (coalesce) settings
+ * @ec: coalesce settings to program the device with
+ * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
+ *
+ * Return 0 on success, and negative under the following conditions:
+ * 1. Getting Tx or Rx ITR/INTRL (coalesce) settings failed.
+ * 2. The q_num passed in is not a valid number/index for Tx and Rx rings.
+ */
+static int
+ice_get_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num)
+{
+ if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+ if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+ &vsi->rx_rings[q_num]->q_vector->rx))
+ return -EINVAL;
+ if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+ &vsi->tx_rings[q_num]->q_vector->tx))
+ return -EINVAL;
+ } else if (q_num < vsi->num_rxq) {
+ if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+ &vsi->rx_rings[q_num]->q_vector->rx))
+ return -EINVAL;
+ } else if (q_num < vsi->num_txq) {
+ if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+ &vsi->tx_rings[q_num]->q_vector->tx))
+ return -EINVAL;
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * __ice_get_coalesce - get ITR/INTRL values for the device
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @q_num: queue number to get the coalesce settings for
+ *
+ * If the caller passes in a negative q_num then we return coalesce settings
+ * based on queue number 0, else use the actual q_num passed in.
+ */
+static int
+__ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+ int q_num)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (q_num < 0)
+ q_num = 0;
+
+ if (ice_get_q_coalesce(vsi, ec, q_num))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int
+ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+ return __ice_get_coalesce(netdev, ec, -1);
+}
+
+static int
+ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
+ struct ethtool_coalesce *ec)
+{
+ return __ice_get_coalesce(netdev, ec, q_num);
+}
+
+/**
+ * ice_set_rc_coalesce - set ITR values for specific ring container
+ * @c_type: container type, Rx or Tx
+ * @ec: ethtool structure from user to update ITR settings
+ * @rc: ring container that the ITR values will come from
+ * @vsi: VSI associated to the ring container
+ *
+ * Set specific ITR values. This is done per ice_ring_container because each
+ * q_vector can have 1 or more rings and all of said ring(s) will have the same
+ * ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec,
+ struct ice_ring_container *rc, struct ice_vsi *vsi)
+{
+ const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx";
+ u32 use_adaptive_coalesce, coalesce_usecs;
+ struct ice_pf *pf = vsi->back;
+ u16 itr_setting;
+
+ if (!rc->ring)
+ return -EINVAL;
+
+ switch (c_type) {
+ case ICE_RX_CONTAINER:
+ if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL ||
+ (ec->rx_coalesce_usecs_high &&
+ ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) {
+ netdev_info(vsi->netdev,
+ "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n",
+ c_type_str, pf->hw.intrl_gran,
+ ICE_MAX_INTRL);
+ return -EINVAL;
+ }
+ if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) {
+ rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high;
+ wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx),
+ ice_intrl_usec_to_reg(ec->rx_coalesce_usecs_high,
+ pf->hw.intrl_gran));
+ }
+
+ use_adaptive_coalesce = ec->use_adaptive_rx_coalesce;
+ coalesce_usecs = ec->rx_coalesce_usecs;
+
+ break;
+ case ICE_TX_CONTAINER:
+ if (ec->tx_coalesce_usecs_high) {
+ netdev_info(vsi->netdev,
+ "setting %s-usecs-high is not supported\n",
+ c_type_str);
+ return -EINVAL;
+ }
+
+ use_adaptive_coalesce = ec->use_adaptive_tx_coalesce;
+ coalesce_usecs = ec->tx_coalesce_usecs;
+
+ break;
+ default:
+ dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type);
+ return -EINVAL;
+ }
+
+ itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+ if (coalesce_usecs != itr_setting && use_adaptive_coalesce) {
+ netdev_info(vsi->netdev,
+ "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n",
+ c_type_str, c_type_str);
+ return -EINVAL;
+ }
+
+ if (coalesce_usecs > ICE_ITR_MAX) {
+ netdev_info(vsi->netdev,
+ "Invalid value, %s-usecs range is 0-%d\n",
+ c_type_str, ICE_ITR_MAX);
+ return -EINVAL;
+ }
+
+ /* hardware only supports an ITR granularity of 2us */
+ if (coalesce_usecs % 2 != 0) {
+ netdev_info(vsi->netdev,
+ "Invalid value, %s-usecs must be even\n",
+ c_type_str);
+ return -EINVAL;
+ }
+
+ if (use_adaptive_coalesce) {
+ rc->itr_setting |= ICE_ITR_DYNAMIC;
+ } else {
+ /* store user facing value how it was set */
+ rc->itr_setting = coalesce_usecs;
+ /* set to static and convert to value HW understands */
+ rc->target_itr =
+ ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting));
+ }
+
+ return 0;
+}
+
+/**
+ * ice_set_q_coalesce - set a queue's ITR/INTRL (coalesce) settings
+ * @vsi: VSI associated to the queue that need updating
+ * @ec: coalesce settings to program the device with
+ * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
+ *
+ * Return 0 on success, and negative under the following conditions:
+ * 1. Setting Tx or Rx ITR/INTRL (coalesce) settings failed.
+ * 2. The q_num passed in is not a valid number/index for Tx and Rx rings.
+ */
+static int
+ice_set_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num)
+{
+ if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+ if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+ &vsi->rx_rings[q_num]->q_vector->rx,
+ vsi))
+ return -EINVAL;
+
+ if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+ &vsi->tx_rings[q_num]->q_vector->tx,
+ vsi))
+ return -EINVAL;
+ } else if (q_num < vsi->num_rxq) {
+ if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+ &vsi->rx_rings[q_num]->q_vector->rx,
+ vsi))
+ return -EINVAL;
+ } else if (q_num < vsi->num_txq) {
+ if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+ &vsi->tx_rings[q_num]->q_vector->tx,
+ vsi))
+ return -EINVAL;
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * __ice_set_coalesce - set ITR/INTRL values for the device
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @q_num: queue number to get the coalesce settings for
+ *
+ * If the caller passes in a negative q_num then we set the coalesce settings
+ * for all Tx/Rx queues, else use the actual q_num passed in.
+ */
+static int
+__ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+ int q_num)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ if (q_num < 0) {
+ int i;
+
+ ice_for_each_q_vector(vsi, i) {
+ if (ice_set_q_coalesce(vsi, ec, i))
+ return -EINVAL;
+ }
+ goto set_complete;
+ }
+
+ if (ice_set_q_coalesce(vsi, ec, q_num))
+ return -EINVAL;
+
+set_complete:
+
+ return 0;
+}
+
+static int
+ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+ return __ice_set_coalesce(netdev, ec, -1);
+}
+
+static int
+ice_set_per_q_coalesce(struct net_device *netdev, u32 q_num,
+ struct ethtool_coalesce *ec)
+{
+ return __ice_set_coalesce(netdev, ec, q_num);
+}
+
static const struct ethtool_ops ice_ethtool_ops = {
.get_link_ksettings = ice_get_link_ksettings,
+ .set_link_ksettings = ice_set_link_ksettings,
.get_drvinfo = ice_get_drvinfo,
.get_regs_len = ice_get_regs_len,
.get_regs = ice_get_regs,
.get_msglevel = ice_get_msglevel,
.set_msglevel = ice_set_msglevel,
+ .self_test = ice_self_test,
.get_link = ethtool_op_get_link,
+ .get_eeprom_len = ice_get_eeprom_len,
+ .get_eeprom = ice_get_eeprom,
+ .get_coalesce = ice_get_coalesce,
+ .set_coalesce = ice_set_coalesce,
.get_strings = ice_get_strings,
+ .set_phys_id = ice_set_phys_id,
.get_ethtool_stats = ice_get_ethtool_stats,
+ .get_priv_flags = ice_get_priv_flags,
+ .set_priv_flags = ice_set_priv_flags,
.get_sset_count = ice_get_sset_count,
.get_rxnfc = ice_get_rxnfc,
.get_ringparam = ice_get_ringparam,
@@ -968,8 +3428,40 @@
.get_rxfh_indir_size = ice_get_rxfh_indir_size,
.get_rxfh = ice_get_rxfh,
.set_rxfh = ice_set_rxfh,
+ .get_ts_info = ethtool_op_get_ts_info,
+ .get_per_queue_coalesce = ice_get_per_q_coalesce,
+ .set_per_queue_coalesce = ice_set_per_q_coalesce,
+ .get_fecparam = ice_get_fecparam,
+ .set_fecparam = ice_set_fecparam,
};
+static const struct ethtool_ops ice_ethtool_safe_mode_ops = {
+ .get_link_ksettings = ice_get_link_ksettings,
+ .set_link_ksettings = ice_set_link_ksettings,
+ .get_drvinfo = ice_get_drvinfo,
+ .get_regs_len = ice_get_regs_len,
+ .get_regs = ice_get_regs,
+ .get_msglevel = ice_get_msglevel,
+ .set_msglevel = ice_set_msglevel,
+ .get_eeprom_len = ice_get_eeprom_len,
+ .get_eeprom = ice_get_eeprom,
+ .get_strings = ice_get_strings,
+ .get_ethtool_stats = ice_get_ethtool_stats,
+ .get_sset_count = ice_get_sset_count,
+ .get_ringparam = ice_get_ringparam,
+ .set_ringparam = ice_set_ringparam,
+ .nway_reset = ice_nway_reset,
+};
+
+/**
+ * ice_set_ethtool_safe_mode_ops - setup safe mode ethtool ops
+ * @netdev: network interface device structure
+ */
+void ice_set_ethtool_safe_mode_ops(struct net_device *netdev)
+{
+ netdev->ethtool_ops = &ice_ethtool_safe_mode_ops;
+}
+
/**
* ice_set_ethtool_ops - setup netdev ethtool ops
* @netdev: network interface device structure
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
new file mode 100644
index 0000000..cbd53b5
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -0,0 +1,1549 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_flex_pipe.h"
+
+/**
+ * ice_pkg_val_buf
+ * @buf: pointer to the ice buffer
+ *
+ * This helper function validates a buffer's header.
+ */
+static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf)
+{
+ struct ice_buf_hdr *hdr;
+ u16 section_count;
+ u16 data_end;
+
+ hdr = (struct ice_buf_hdr *)buf->buf;
+ /* verify data */
+ section_count = le16_to_cpu(hdr->section_count);
+ if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT)
+ return NULL;
+
+ data_end = le16_to_cpu(hdr->data_end);
+ if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END)
+ return NULL;
+
+ return hdr;
+}
+
+/**
+ * ice_find_buf_table
+ * @ice_seg: pointer to the ice segment
+ *
+ * Returns the address of the buffer table within the ice segment.
+ */
+static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg)
+{
+ struct ice_nvm_table *nvms;
+
+ nvms = (struct ice_nvm_table *)
+ (ice_seg->device_table +
+ le32_to_cpu(ice_seg->device_table_count));
+
+ return (__force struct ice_buf_table *)
+ (nvms->vers + le32_to_cpu(nvms->table_count));
+}
+
+/**
+ * ice_pkg_enum_buf
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ *
+ * This function will enumerate all the buffers in the ice segment. The first
+ * call is made with the ice_seg parameter non-NULL; on subsequent calls,
+ * ice_seg is set to NULL which continues the enumeration. When the function
+ * returns a NULL pointer, then the end of the buffers has been reached, or an
+ * unexpected value has been detected (for example an invalid section count or
+ * an invalid buffer end value).
+ */
+static struct ice_buf_hdr *
+ice_pkg_enum_buf(struct ice_seg *ice_seg, struct ice_pkg_enum *state)
+{
+ if (ice_seg) {
+ state->buf_table = ice_find_buf_table(ice_seg);
+ if (!state->buf_table)
+ return NULL;
+
+ state->buf_idx = 0;
+ return ice_pkg_val_buf(state->buf_table->buf_array);
+ }
+
+ if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count))
+ return ice_pkg_val_buf(state->buf_table->buf_array +
+ state->buf_idx);
+ else
+ return NULL;
+}
+
+/**
+ * ice_pkg_advance_sect
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ *
+ * This helper function will advance the section within the ice segment,
+ * also advancing the buffer if needed.
+ */
+static bool
+ice_pkg_advance_sect(struct ice_seg *ice_seg, struct ice_pkg_enum *state)
+{
+ if (!ice_seg && !state->buf)
+ return false;
+
+ if (!ice_seg && state->buf)
+ if (++state->sect_idx < le16_to_cpu(state->buf->section_count))
+ return true;
+
+ state->buf = ice_pkg_enum_buf(ice_seg, state);
+ if (!state->buf)
+ return false;
+
+ /* start of new buffer, reset section index */
+ state->sect_idx = 0;
+ return true;
+}
+
+/**
+ * ice_pkg_enum_section
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ * @sect_type: section type to enumerate
+ *
+ * This function will enumerate all the sections of a particular type in the
+ * ice segment. The first call is made with the ice_seg parameter non-NULL;
+ * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
+ * When the function returns a NULL pointer, then the end of the matching
+ * sections has been reached.
+ */
+static void *
+ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
+ u32 sect_type)
+{
+ u16 offset, size;
+
+ if (ice_seg)
+ state->type = sect_type;
+
+ if (!ice_pkg_advance_sect(ice_seg, state))
+ return NULL;
+
+ /* scan for next matching section */
+ while (state->buf->section_entry[state->sect_idx].type !=
+ cpu_to_le32(state->type))
+ if (!ice_pkg_advance_sect(NULL, state))
+ return NULL;
+
+ /* validate section */
+ offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
+ if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF)
+ return NULL;
+
+ size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size);
+ if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ)
+ return NULL;
+
+ /* make sure the section fits in the buffer */
+ if (offset + size > ICE_PKG_BUF_SIZE)
+ return NULL;
+
+ state->sect_type =
+ le32_to_cpu(state->buf->section_entry[state->sect_idx].type);
+
+ /* calc pointer to this section */
+ state->sect = ((u8 *)state->buf) +
+ le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
+
+ return state->sect;
+}
+
+/**
+ * ice_acquire_global_cfg_lock
+ * @hw: pointer to the HW structure
+ * @access: access type (read or write)
+ *
+ * This function will request ownership of the global config lock for reading
+ * or writing of the package. When attempting to obtain write access, the
+ * caller must check for the following two return values:
+ *
+ * ICE_SUCCESS - Means the caller has acquired the global config lock
+ * and can perform writing of the package.
+ * ICE_ERR_AQ_NO_WORK - Indicates another driver has already written the
+ * package or has found that no update was necessary; in
+ * this case, the caller can just skip performing any
+ * update of the package.
+ */
+static enum ice_status
+ice_acquire_global_cfg_lock(struct ice_hw *hw,
+ enum ice_aq_res_access_type access)
+{
+ enum ice_status status;
+
+ status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access,
+ ICE_GLOBAL_CFG_LOCK_TIMEOUT);
+
+ if (!status)
+ mutex_lock(&ice_global_cfg_lock_sw);
+ else if (status == ICE_ERR_AQ_NO_WORK)
+ ice_debug(hw, ICE_DBG_PKG,
+ "Global config lock: No work to do\n");
+
+ return status;
+}
+
+/**
+ * ice_release_global_cfg_lock
+ * @hw: pointer to the HW structure
+ *
+ * This function will release the global config lock.
+ */
+static void ice_release_global_cfg_lock(struct ice_hw *hw)
+{
+ mutex_unlock(&ice_global_cfg_lock_sw);
+ ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID);
+}
+
+/**
+ * ice_aq_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package buffer to transfer
+ * @buf_size: the size of the package buffer
+ * @last_buf: last buffer indicator
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cd: pointer to command details structure or NULL
+ *
+ * Download Package (0x0C40)
+ */
+static enum ice_status
+ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+ u16 buf_size, bool last_buf, u32 *error_offset,
+ u32 *error_info, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_download_pkg *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ if (error_offset)
+ *error_offset = 0;
+ if (error_info)
+ *error_info = 0;
+
+ cmd = &desc.params.download_pkg;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ if (last_buf)
+ cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
+
+ status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+ if (status == ICE_ERR_AQ_ERROR) {
+ /* Read error from buffer only when the FW returned an error */
+ struct ice_aqc_download_pkg_resp *resp;
+
+ resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
+ if (error_offset)
+ *error_offset = le32_to_cpu(resp->error_offset);
+ if (error_info)
+ *error_info = le32_to_cpu(resp->error_info);
+ }
+
+ return status;
+}
+
+/**
+ * ice_find_seg_in_pkg
+ * @hw: pointer to the hardware structure
+ * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK)
+ * @pkg_hdr: pointer to the package header to be searched
+ *
+ * This function searches a package file for a particular segment type. On
+ * success it returns a pointer to the segment header, otherwise it will
+ * return NULL.
+ */
+static struct ice_generic_seg_hdr *
+ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
+ struct ice_pkg_hdr *pkg_hdr)
+{
+ u32 i;
+
+ ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n",
+ pkg_hdr->format_ver.major, pkg_hdr->format_ver.minor,
+ pkg_hdr->format_ver.update, pkg_hdr->format_ver.draft);
+
+ /* Search all package segments for the requested segment type */
+ for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) {
+ struct ice_generic_seg_hdr *seg;
+
+ seg = (struct ice_generic_seg_hdr *)
+ ((u8 *)pkg_hdr + le32_to_cpu(pkg_hdr->seg_offset[i]));
+
+ if (le32_to_cpu(seg->seg_type) == seg_type)
+ return seg;
+ }
+
+ return NULL;
+}
+
+/**
+ * ice_dwnld_cfg_bufs
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains global config lock and downloads the package configuration buffers
+ * to the firmware. Metadata buffers are skipped, and the first metadata buffer
+ * found indicates that the rest of the buffers are all metadata buffers.
+ */
+static enum ice_status
+ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+ enum ice_status status;
+ struct ice_buf_hdr *bh;
+ u32 offset, info, i;
+
+ if (!bufs || !count)
+ return ICE_ERR_PARAM;
+
+ /* If the first buffer's first section has its metadata bit set
+ * then there are no buffers to be downloaded, and the operation is
+ * considered a success.
+ */
+ bh = (struct ice_buf_hdr *)bufs;
+ if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
+ return 0;
+
+ /* reset pkg_dwnld_status in case this function is called in the
+ * reset/rebuild flow
+ */
+ hw->pkg_dwnld_status = ICE_AQ_RC_OK;
+
+ status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
+ if (status) {
+ if (status == ICE_ERR_AQ_NO_WORK)
+ hw->pkg_dwnld_status = ICE_AQ_RC_EEXIST;
+ else
+ hw->pkg_dwnld_status = hw->adminq.sq_last_status;
+ return status;
+ }
+
+ for (i = 0; i < count; i++) {
+ bool last = ((i + 1) == count);
+
+ if (!last) {
+ /* check next buffer for metadata flag */
+ bh = (struct ice_buf_hdr *)(bufs + i + 1);
+
+ /* A set metadata flag in the next buffer will signal
+ * that the current buffer will be the last buffer
+ * downloaded
+ */
+ if (le16_to_cpu(bh->section_count))
+ if (le32_to_cpu(bh->section_entry[0].type) &
+ ICE_METADATA_BUF)
+ last = true;
+ }
+
+ bh = (struct ice_buf_hdr *)(bufs + i);
+
+ status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last,
+ &offset, &info, NULL);
+
+ /* Save AQ status from download package */
+ hw->pkg_dwnld_status = hw->adminq.sq_last_status;
+ if (status) {
+ ice_debug(hw, ICE_DBG_PKG,
+ "Pkg download failed: err %d off %d inf %d\n",
+ status, offset, info);
+
+ break;
+ }
+
+ if (last)
+ break;
+ }
+
+ ice_release_global_cfg_lock(hw);
+
+ return status;
+}
+
+/**
+ * ice_aq_get_pkg_info_list
+ * @hw: pointer to the hardware structure
+ * @pkg_info: the buffer which will receive the information list
+ * @buf_size: the size of the pkg_info information buffer
+ * @cd: pointer to command details structure or NULL
+ *
+ * Get Package Info List (0x0C43)
+ */
+static enum ice_status
+ice_aq_get_pkg_info_list(struct ice_hw *hw,
+ struct ice_aqc_get_pkg_info_resp *pkg_info,
+ u16 buf_size, struct ice_sq_cd *cd)
+{
+ struct ice_aq_desc desc;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list);
+
+ return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd);
+}
+
+/**
+ * ice_download_pkg
+ * @hw: pointer to the hardware structure
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package.
+ */
+static enum ice_status
+ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+ struct ice_buf_table *ice_buf_tbl;
+
+ ice_debug(hw, ICE_DBG_PKG, "Segment version: %d.%d.%d.%d\n",
+ ice_seg->hdr.seg_ver.major, ice_seg->hdr.seg_ver.minor,
+ ice_seg->hdr.seg_ver.update, ice_seg->hdr.seg_ver.draft);
+
+ ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
+ le32_to_cpu(ice_seg->hdr.seg_type),
+ le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_name);
+
+ ice_buf_tbl = ice_find_buf_table(ice_seg);
+
+ ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
+ le32_to_cpu(ice_buf_tbl->buf_count));
+
+ return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
+ le32_to_cpu(ice_buf_tbl->buf_count));
+}
+
+/**
+ * ice_init_pkg_info
+ * @hw: pointer to the hardware structure
+ * @pkg_hdr: pointer to the driver's package hdr
+ *
+ * Saves off the package details into the HW structure.
+ */
+static enum ice_status
+ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
+{
+ struct ice_global_metadata_seg *meta_seg;
+ struct ice_generic_seg_hdr *seg_hdr;
+
+ if (!pkg_hdr)
+ return ICE_ERR_PARAM;
+
+ meta_seg = (struct ice_global_metadata_seg *)
+ ice_find_seg_in_pkg(hw, SEGMENT_TYPE_METADATA, pkg_hdr);
+ if (meta_seg) {
+ hw->pkg_ver = meta_seg->pkg_ver;
+ memcpy(hw->pkg_name, meta_seg->pkg_name, sizeof(hw->pkg_name));
+
+ ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n",
+ meta_seg->pkg_ver.major, meta_seg->pkg_ver.minor,
+ meta_seg->pkg_ver.update, meta_seg->pkg_ver.draft,
+ meta_seg->pkg_name);
+ } else {
+ ice_debug(hw, ICE_DBG_INIT,
+ "Did not find metadata segment in driver package\n");
+ return ICE_ERR_CFG;
+ }
+
+ seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr);
+ if (seg_hdr) {
+ hw->ice_pkg_ver = seg_hdr->seg_ver;
+ memcpy(hw->ice_pkg_name, seg_hdr->seg_name,
+ sizeof(hw->ice_pkg_name));
+
+ ice_debug(hw, ICE_DBG_PKG, "Ice Pkg: %d.%d.%d.%d, %s\n",
+ seg_hdr->seg_ver.major, seg_hdr->seg_ver.minor,
+ seg_hdr->seg_ver.update, seg_hdr->seg_ver.draft,
+ seg_hdr->seg_name);
+ } else {
+ ice_debug(hw, ICE_DBG_INIT,
+ "Did not find ice segment in driver package\n");
+ return ICE_ERR_CFG;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_pkg_info
+ * @hw: pointer to the hardware structure
+ *
+ * Store details of the package currently loaded in HW into the HW structure.
+ */
+static enum ice_status ice_get_pkg_info(struct ice_hw *hw)
+{
+ struct ice_aqc_get_pkg_info_resp *pkg_info;
+ enum ice_status status;
+ u16 size;
+ u32 i;
+
+ size = sizeof(*pkg_info) + (sizeof(pkg_info->pkg_info[0]) *
+ (ICE_PKG_CNT - 1));
+ pkg_info = kzalloc(size, GFP_KERNEL);
+ if (!pkg_info)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL);
+ if (status)
+ goto init_pkg_free_alloc;
+
+ for (i = 0; i < le32_to_cpu(pkg_info->count); i++) {
+#define ICE_PKG_FLAG_COUNT 4
+ char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 };
+ u8 place = 0;
+
+ if (pkg_info->pkg_info[i].is_active) {
+ flags[place++] = 'A';
+ hw->active_pkg_ver = pkg_info->pkg_info[i].ver;
+ memcpy(hw->active_pkg_name,
+ pkg_info->pkg_info[i].name,
+ sizeof(hw->active_pkg_name));
+ hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm;
+ }
+ if (pkg_info->pkg_info[i].is_active_at_boot)
+ flags[place++] = 'B';
+ if (pkg_info->pkg_info[i].is_modified)
+ flags[place++] = 'M';
+ if (pkg_info->pkg_info[i].is_in_nvm)
+ flags[place++] = 'N';
+
+ ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n",
+ i, pkg_info->pkg_info[i].ver.major,
+ pkg_info->pkg_info[i].ver.minor,
+ pkg_info->pkg_info[i].ver.update,
+ pkg_info->pkg_info[i].ver.draft,
+ pkg_info->pkg_info[i].name, flags);
+ }
+
+init_pkg_free_alloc:
+ kfree(pkg_info);
+
+ return status;
+}
+
+/**
+ * ice_verify_pkg - verify package
+ * @pkg: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * Verifies various attributes of the package file, including length, format
+ * version, and the requirement of at least one segment.
+ */
+static enum ice_status ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
+{
+ u32 seg_count;
+ u32 i;
+
+ if (len < sizeof(*pkg))
+ return ICE_ERR_BUF_TOO_SHORT;
+
+ if (pkg->format_ver.major != ICE_PKG_FMT_VER_MAJ ||
+ pkg->format_ver.minor != ICE_PKG_FMT_VER_MNR ||
+ pkg->format_ver.update != ICE_PKG_FMT_VER_UPD ||
+ pkg->format_ver.draft != ICE_PKG_FMT_VER_DFT)
+ return ICE_ERR_CFG;
+
+ /* pkg must have at least one segment */
+ seg_count = le32_to_cpu(pkg->seg_count);
+ if (seg_count < 1)
+ return ICE_ERR_CFG;
+
+ /* make sure segment array fits in package length */
+ if (len < sizeof(*pkg) + ((seg_count - 1) * sizeof(pkg->seg_offset)))
+ return ICE_ERR_BUF_TOO_SHORT;
+
+ /* all segments must fit within length */
+ for (i = 0; i < seg_count; i++) {
+ u32 off = le32_to_cpu(pkg->seg_offset[i]);
+ struct ice_generic_seg_hdr *seg;
+
+ /* segment header must fit */
+ if (len < off + sizeof(*seg))
+ return ICE_ERR_BUF_TOO_SHORT;
+
+ seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off);
+
+ /* segment body must fit */
+ if (len < off + le32_to_cpu(seg->seg_size))
+ return ICE_ERR_BUF_TOO_SHORT;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_free_seg - free package segment pointer
+ * @hw: pointer to the hardware structure
+ *
+ * Frees the package segment pointer in the proper manner, depending on if the
+ * segment was allocated or just the passed in pointer was stored.
+ */
+void ice_free_seg(struct ice_hw *hw)
+{
+ if (hw->pkg_copy) {
+ devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy);
+ hw->pkg_copy = NULL;
+ hw->pkg_size = 0;
+ }
+ hw->seg = NULL;
+}
+
+/**
+ * ice_init_pkg_regs - initialize additional package registers
+ * @hw: pointer to the hardware structure
+ */
+static void ice_init_pkg_regs(struct ice_hw *hw)
+{
+#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF
+#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF
+#define ICE_SW_BLK_IDX 0
+
+ /* setup Switch block input mask, which is 48-bits in two parts */
+ wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L);
+ wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H);
+}
+
+/**
+ * ice_chk_pkg_version - check package version for compatibility with driver
+ * @pkg_ver: pointer to a version structure to check
+ *
+ * Check to make sure that the package about to be downloaded is compatible with
+ * the driver. To be compatible, the major and minor components of the package
+ * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR
+ * definitions.
+ */
+static enum ice_status ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver)
+{
+ if (pkg_ver->major != ICE_PKG_SUPP_VER_MAJ ||
+ pkg_ver->minor != ICE_PKG_SUPP_VER_MNR)
+ return ICE_ERR_NOT_SUPPORTED;
+
+ return 0;
+}
+
+/**
+ * ice_init_pkg - initialize/download package
+ * @hw: pointer to the hardware structure
+ * @buf: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * This function initializes a package. The package contains HW tables
+ * required to do packet processing. First, the function extracts package
+ * information such as version. Then it finds the ice configuration segment
+ * within the package; this function then saves a copy of the segment pointer
+ * within the supplied package buffer. Next, the function will cache any hints
+ * from the package, followed by downloading the package itself. Note, that if
+ * a previous PF driver has already downloaded the package successfully, then
+ * the current driver will not have to download the package again.
+ *
+ * The local package contents will be used to query default behavior and to
+ * update specific sections of the HW's version of the package (e.g. to update
+ * the parse graph to understand new protocols).
+ *
+ * This function stores a pointer to the package buffer memory, and it is
+ * expected that the supplied buffer will not be freed immediately. If the
+ * package buffer needs to be freed, such as when read from a file, use
+ * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this
+ * case.
+ */
+enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
+{
+ struct ice_pkg_hdr *pkg;
+ enum ice_status status;
+ struct ice_seg *seg;
+
+ if (!buf || !len)
+ return ICE_ERR_PARAM;
+
+ pkg = (struct ice_pkg_hdr *)buf;
+ status = ice_verify_pkg(pkg, len);
+ if (status) {
+ ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n",
+ status);
+ return status;
+ }
+
+ /* initialize package info */
+ status = ice_init_pkg_info(hw, pkg);
+ if (status)
+ return status;
+
+ /* before downloading the package, check package version for
+ * compatibility with driver
+ */
+ status = ice_chk_pkg_version(&hw->pkg_ver);
+ if (status)
+ return status;
+
+ /* find segment in given package */
+ seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg);
+ if (!seg) {
+ ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n");
+ return ICE_ERR_CFG;
+ }
+
+ /* download package */
+ status = ice_download_pkg(hw, seg);
+ if (status == ICE_ERR_AQ_NO_WORK) {
+ ice_debug(hw, ICE_DBG_INIT,
+ "package previously loaded - no work.\n");
+ status = 0;
+ }
+
+ /* Get information on the package currently loaded in HW, then make sure
+ * the driver is compatible with this version.
+ */
+ if (!status) {
+ status = ice_get_pkg_info(hw);
+ if (!status)
+ status = ice_chk_pkg_version(&hw->active_pkg_ver);
+ }
+
+ if (!status) {
+ hw->seg = seg;
+ /* on successful package download update other required
+ * registers to support the package and fill HW tables
+ * with package content.
+ */
+ ice_init_pkg_regs(hw);
+ ice_fill_blk_tbls(hw);
+ } else {
+ ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n",
+ status);
+ }
+
+ return status;
+}
+
+/**
+ * ice_copy_and_init_pkg - initialize/download a copy of the package
+ * @hw: pointer to the hardware structure
+ * @buf: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * This function copies the package buffer, and then calls ice_init_pkg() to
+ * initialize the copied package contents.
+ *
+ * The copying is necessary if the package buffer supplied is constant, or if
+ * the memory may disappear shortly after calling this function.
+ *
+ * If the package buffer resides in the data segment and can be modified, the
+ * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg().
+ *
+ * However, if the package buffer needs to be copied first, such as when being
+ * read from a file, the caller should use ice_copy_and_init_pkg().
+ *
+ * This function will first copy the package buffer, before calling
+ * ice_init_pkg(). The caller is free to immediately destroy the original
+ * package buffer, as the new copy will be managed by this function and
+ * related routines.
+ */
+enum ice_status ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len)
+{
+ enum ice_status status;
+ u8 *buf_copy;
+
+ if (!buf || !len)
+ return ICE_ERR_PARAM;
+
+ buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL);
+
+ status = ice_init_pkg(hw, buf_copy, len);
+ if (status) {
+ /* Free the copy, since we failed to initialize the package */
+ devm_kfree(ice_hw_to_dev(hw), buf_copy);
+ } else {
+ /* Track the copied pkg so we can free it later */
+ hw->pkg_copy = buf_copy;
+ hw->pkg_size = len;
+ }
+
+ return status;
+}
+
+/* PTG Management */
+
+/**
+ * ice_ptg_find_ptype - Search for packet type group using packet type (ptype)
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @ptype: the ptype to search for
+ * @ptg: pointer to variable that receives the PTG
+ *
+ * This function will search the PTGs for a particular ptype, returning the
+ * PTG ID that contains it through the PTG parameter, with the value of
+ * ICE_DEFAULT_PTG (0) meaning it is part the default PTG.
+ */
+static enum ice_status
+ice_ptg_find_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 *ptg)
+{
+ if (ptype >= ICE_XLT1_CNT || !ptg)
+ return ICE_ERR_PARAM;
+
+ *ptg = hw->blk[blk].xlt1.ptypes[ptype].ptg;
+ return 0;
+}
+
+/**
+ * ice_ptg_alloc_val - Allocates a new packet type group ID by value
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @ptg: the PTG to allocate
+ *
+ * This function allocates a given packet type group ID specified by the PTG
+ * parameter.
+ */
+static void ice_ptg_alloc_val(struct ice_hw *hw, enum ice_block blk, u8 ptg)
+{
+ hw->blk[blk].xlt1.ptg_tbl[ptg].in_use = true;
+}
+
+/**
+ * ice_ptg_remove_ptype - Removes ptype from a particular packet type group
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @ptype: the ptype to remove
+ * @ptg: the PTG to remove the ptype from
+ *
+ * This function will remove the ptype from the specific PTG, and move it to
+ * the default PTG (ICE_DEFAULT_PTG).
+ */
+static enum ice_status
+ice_ptg_remove_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg)
+{
+ struct ice_ptg_ptype **ch;
+ struct ice_ptg_ptype *p;
+
+ if (ptype > ICE_XLT1_CNT - 1)
+ return ICE_ERR_PARAM;
+
+ if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ /* Should not happen if .in_use is set, bad config */
+ if (!hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype)
+ return ICE_ERR_CFG;
+
+ /* find the ptype within this PTG, and bypass the link over it */
+ p = hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype;
+ ch = &hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype;
+ while (p) {
+ if (ptype == (p - hw->blk[blk].xlt1.ptypes)) {
+ *ch = p->next_ptype;
+ break;
+ }
+
+ ch = &p->next_ptype;
+ p = p->next_ptype;
+ }
+
+ hw->blk[blk].xlt1.ptypes[ptype].ptg = ICE_DEFAULT_PTG;
+ hw->blk[blk].xlt1.ptypes[ptype].next_ptype = NULL;
+
+ return 0;
+}
+
+/**
+ * ice_ptg_add_mv_ptype - Adds/moves ptype to a particular packet type group
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @ptype: the ptype to add or move
+ * @ptg: the PTG to add or move the ptype to
+ *
+ * This function will either add or move a ptype to a particular PTG depending
+ * on if the ptype is already part of another group. Note that using a
+ * a destination PTG ID of ICE_DEFAULT_PTG (0) will move the ptype to the
+ * default PTG.
+ */
+static enum ice_status
+ice_ptg_add_mv_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg)
+{
+ enum ice_status status;
+ u8 original_ptg;
+
+ if (ptype > ICE_XLT1_CNT - 1)
+ return ICE_ERR_PARAM;
+
+ if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use && ptg != ICE_DEFAULT_PTG)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ status = ice_ptg_find_ptype(hw, blk, ptype, &original_ptg);
+ if (status)
+ return status;
+
+ /* Is ptype already in the correct PTG? */
+ if (original_ptg == ptg)
+ return 0;
+
+ /* Remove from original PTG and move back to the default PTG */
+ if (original_ptg != ICE_DEFAULT_PTG)
+ ice_ptg_remove_ptype(hw, blk, ptype, original_ptg);
+
+ /* Moving to default PTG? Then we're done with this request */
+ if (ptg == ICE_DEFAULT_PTG)
+ return 0;
+
+ /* Add ptype to PTG at beginning of list */
+ hw->blk[blk].xlt1.ptypes[ptype].next_ptype =
+ hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype;
+ hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype =
+ &hw->blk[blk].xlt1.ptypes[ptype];
+
+ hw->blk[blk].xlt1.ptypes[ptype].ptg = ptg;
+ hw->blk[blk].xlt1.t[ptype] = ptg;
+
+ return 0;
+}
+
+/* Block / table size info */
+struct ice_blk_size_details {
+ u16 xlt1; /* # XLT1 entries */
+ u16 xlt2; /* # XLT2 entries */
+ u16 prof_tcam; /* # profile ID TCAM entries */
+ u16 prof_id; /* # profile IDs */
+ u8 prof_cdid_bits; /* # CDID one-hot bits used in key */
+ u16 prof_redir; /* # profile redirection entries */
+ u16 es; /* # extraction sequence entries */
+ u16 fvw; /* # field vector words */
+ u8 overwrite; /* overwrite existing entries allowed */
+ u8 reverse; /* reverse FV order */
+};
+
+static const struct ice_blk_size_details blk_sizes[ICE_BLK_COUNT] = {
+ /**
+ * Table Definitions
+ * XLT1 - Number of entries in XLT1 table
+ * XLT2 - Number of entries in XLT2 table
+ * TCAM - Number of entries Profile ID TCAM table
+ * CDID - Control Domain ID of the hardware block
+ * PRED - Number of entries in the Profile Redirection Table
+ * FV - Number of entries in the Field Vector
+ * FVW - Width (in WORDs) of the Field Vector
+ * OVR - Overwrite existing table entries
+ * REV - Reverse FV
+ */
+ /* XLT1 , XLT2 ,TCAM, PID,CDID,PRED, FV, FVW */
+ /* Overwrite , Reverse FV */
+ /* SW */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 256, 0, 256, 256, 48,
+ false, false },
+ /* ACL */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 32,
+ false, false },
+ /* FD */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 24,
+ false, true },
+ /* RSS */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 24,
+ true, true },
+ /* PE */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 64, 32, 0, 32, 32, 24,
+ false, false },
+};
+
+enum ice_sid_all {
+ ICE_SID_XLT1_OFF = 0,
+ ICE_SID_XLT2_OFF,
+ ICE_SID_PR_OFF,
+ ICE_SID_PR_REDIR_OFF,
+ ICE_SID_ES_OFF,
+ ICE_SID_OFF_COUNT,
+};
+
+/* VSIG Management */
+
+/**
+ * ice_vsig_find_vsi - find a VSIG that contains a specified VSI
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsi: VSI of interest
+ * @vsig: pointer to receive the VSI group
+ *
+ * This function will lookup the VSI entry in the XLT2 list and return
+ * the VSI group its associated with.
+ */
+static enum ice_status
+ice_vsig_find_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 *vsig)
+{
+ if (!vsig || vsi >= ICE_MAX_VSI)
+ return ICE_ERR_PARAM;
+
+ /* As long as there's a default or valid VSIG associated with the input
+ * VSI, the functions returns a success. Any handling of VSIG will be
+ * done by the following add, update or remove functions.
+ */
+ *vsig = hw->blk[blk].xlt2.vsis[vsi].vsig;
+
+ return 0;
+}
+
+/**
+ * ice_vsig_alloc_val - allocate a new VSIG by value
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsig: the VSIG to allocate
+ *
+ * This function will allocate a given VSIG specified by the VSIG parameter.
+ */
+static u16 ice_vsig_alloc_val(struct ice_hw *hw, enum ice_block blk, u16 vsig)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+
+ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) {
+ INIT_LIST_HEAD(&hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst);
+ hw->blk[blk].xlt2.vsig_tbl[idx].in_use = true;
+ }
+
+ return ICE_VSIG_VALUE(idx, hw->pf_id);
+}
+
+/**
+ * ice_vsig_remove_vsi - remove VSI from VSIG
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsi: VSI to remove
+ * @vsig: VSI group to remove from
+ *
+ * The function will remove the input VSI from its VSI group and move it
+ * to the DEFAULT_VSIG.
+ */
+static enum ice_status
+ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig)
+{
+ struct ice_vsig_vsi **vsi_head, *vsi_cur, *vsi_tgt;
+ u16 idx;
+
+ idx = vsig & ICE_VSIG_IDX_M;
+
+ if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS)
+ return ICE_ERR_PARAM;
+
+ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ /* entry already in default VSIG, don't have to remove */
+ if (idx == ICE_DEFAULT_VSIG)
+ return 0;
+
+ vsi_head = &hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi;
+ if (!(*vsi_head))
+ return ICE_ERR_CFG;
+
+ vsi_tgt = &hw->blk[blk].xlt2.vsis[vsi];
+ vsi_cur = (*vsi_head);
+
+ /* iterate the VSI list, skip over the entry to be removed */
+ while (vsi_cur) {
+ if (vsi_tgt == vsi_cur) {
+ (*vsi_head) = vsi_cur->next_vsi;
+ break;
+ }
+ vsi_head = &vsi_cur->next_vsi;
+ vsi_cur = vsi_cur->next_vsi;
+ }
+
+ /* verify if VSI was removed from group list */
+ if (!vsi_cur)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ vsi_cur->vsig = ICE_DEFAULT_VSIG;
+ vsi_cur->changed = 1;
+ vsi_cur->next_vsi = NULL;
+
+ return 0;
+}
+
+/**
+ * ice_vsig_add_mv_vsi - add or move a VSI to a VSI group
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsi: VSI to move
+ * @vsig: destination VSI group
+ *
+ * This function will move or add the input VSI to the target VSIG.
+ * The function will find the original VSIG the VSI belongs to and
+ * move the entry to the DEFAULT_VSIG, update the original VSIG and
+ * then move entry to the new VSIG.
+ */
+static enum ice_status
+ice_vsig_add_mv_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig)
+{
+ struct ice_vsig_vsi *tmp;
+ enum ice_status status;
+ u16 orig_vsig, idx;
+
+ idx = vsig & ICE_VSIG_IDX_M;
+
+ if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS)
+ return ICE_ERR_PARAM;
+
+ /* if VSIG not in use and VSIG is not default type this VSIG
+ * doesn't exist.
+ */
+ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use &&
+ vsig != ICE_DEFAULT_VSIG)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ status = ice_vsig_find_vsi(hw, blk, vsi, &orig_vsig);
+ if (status)
+ return status;
+
+ /* no update required if vsigs match */
+ if (orig_vsig == vsig)
+ return 0;
+
+ if (orig_vsig != ICE_DEFAULT_VSIG) {
+ /* remove entry from orig_vsig and add to default VSIG */
+ status = ice_vsig_remove_vsi(hw, blk, vsi, orig_vsig);
+ if (status)
+ return status;
+ }
+
+ if (idx == ICE_DEFAULT_VSIG)
+ return 0;
+
+ /* Create VSI entry and add VSIG and prop_mask values */
+ hw->blk[blk].xlt2.vsis[vsi].vsig = vsig;
+ hw->blk[blk].xlt2.vsis[vsi].changed = 1;
+
+ /* Add new entry to the head of the VSIG list */
+ tmp = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi;
+ hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi =
+ &hw->blk[blk].xlt2.vsis[vsi];
+ hw->blk[blk].xlt2.vsis[vsi].next_vsi = tmp;
+ hw->blk[blk].xlt2.t[vsi] = vsig;
+
+ return 0;
+}
+
+/* Block / table section IDs */
+static const u32 ice_blk_sids[ICE_BLK_COUNT][ICE_SID_OFF_COUNT] = {
+ /* SWITCH */
+ { ICE_SID_XLT1_SW,
+ ICE_SID_XLT2_SW,
+ ICE_SID_PROFID_TCAM_SW,
+ ICE_SID_PROFID_REDIR_SW,
+ ICE_SID_FLD_VEC_SW
+ },
+
+ /* ACL */
+ { ICE_SID_XLT1_ACL,
+ ICE_SID_XLT2_ACL,
+ ICE_SID_PROFID_TCAM_ACL,
+ ICE_SID_PROFID_REDIR_ACL,
+ ICE_SID_FLD_VEC_ACL
+ },
+
+ /* FD */
+ { ICE_SID_XLT1_FD,
+ ICE_SID_XLT2_FD,
+ ICE_SID_PROFID_TCAM_FD,
+ ICE_SID_PROFID_REDIR_FD,
+ ICE_SID_FLD_VEC_FD
+ },
+
+ /* RSS */
+ { ICE_SID_XLT1_RSS,
+ ICE_SID_XLT2_RSS,
+ ICE_SID_PROFID_TCAM_RSS,
+ ICE_SID_PROFID_REDIR_RSS,
+ ICE_SID_FLD_VEC_RSS
+ },
+
+ /* PE */
+ { ICE_SID_XLT1_PE,
+ ICE_SID_XLT2_PE,
+ ICE_SID_PROFID_TCAM_PE,
+ ICE_SID_PROFID_REDIR_PE,
+ ICE_SID_FLD_VEC_PE
+ }
+};
+
+/**
+ * ice_init_sw_xlt1_db - init software XLT1 database from HW tables
+ * @hw: pointer to the hardware structure
+ * @blk: the HW block to initialize
+ */
+static void ice_init_sw_xlt1_db(struct ice_hw *hw, enum ice_block blk)
+{
+ u16 pt;
+
+ for (pt = 0; pt < hw->blk[blk].xlt1.count; pt++) {
+ u8 ptg;
+
+ ptg = hw->blk[blk].xlt1.t[pt];
+ if (ptg != ICE_DEFAULT_PTG) {
+ ice_ptg_alloc_val(hw, blk, ptg);
+ ice_ptg_add_mv_ptype(hw, blk, pt, ptg);
+ }
+ }
+}
+
+/**
+ * ice_init_sw_xlt2_db - init software XLT2 database from HW tables
+ * @hw: pointer to the hardware structure
+ * @blk: the HW block to initialize
+ */
+static void ice_init_sw_xlt2_db(struct ice_hw *hw, enum ice_block blk)
+{
+ u16 vsi;
+
+ for (vsi = 0; vsi < hw->blk[blk].xlt2.count; vsi++) {
+ u16 vsig;
+
+ vsig = hw->blk[blk].xlt2.t[vsi];
+ if (vsig) {
+ ice_vsig_alloc_val(hw, blk, vsig);
+ ice_vsig_add_mv_vsi(hw, blk, vsi, vsig);
+ /* no changes at this time, since this has been
+ * initialized from the original package
+ */
+ hw->blk[blk].xlt2.vsis[vsi].changed = 0;
+ }
+ }
+}
+
+/**
+ * ice_init_sw_db - init software database from HW tables
+ * @hw: pointer to the hardware structure
+ */
+static void ice_init_sw_db(struct ice_hw *hw)
+{
+ u16 i;
+
+ for (i = 0; i < ICE_BLK_COUNT; i++) {
+ ice_init_sw_xlt1_db(hw, (enum ice_block)i);
+ ice_init_sw_xlt2_db(hw, (enum ice_block)i);
+ }
+}
+
+/**
+ * ice_fill_tbl - Reads content of a single table type into database
+ * @hw: pointer to the hardware structure
+ * @block_id: Block ID of the table to copy
+ * @sid: Section ID of the table to copy
+ *
+ * Will attempt to read the entire content of a given table of a single block
+ * into the driver database. We assume that the buffer will always
+ * be as large or larger than the data contained in the package. If
+ * this condition is not met, there is most likely an error in the package
+ * contents.
+ */
+static void ice_fill_tbl(struct ice_hw *hw, enum ice_block block_id, u32 sid)
+{
+ u32 dst_len, sect_len, offset = 0;
+ struct ice_prof_redir_section *pr;
+ struct ice_prof_id_section *pid;
+ struct ice_xlt1_section *xlt1;
+ struct ice_xlt2_section *xlt2;
+ struct ice_sw_fv_section *es;
+ struct ice_pkg_enum state;
+ u8 *src, *dst;
+ void *sect;
+
+ /* if the HW segment pointer is null then the first iteration of
+ * ice_pkg_enum_section() will fail. In this case the HW tables will
+ * not be filled and return success.
+ */
+ if (!hw->seg) {
+ ice_debug(hw, ICE_DBG_PKG, "hw->seg is NULL, tables are not filled\n");
+ return;
+ }
+
+ memset(&state, 0, sizeof(state));
+
+ sect = ice_pkg_enum_section(hw->seg, &state, sid);
+
+ while (sect) {
+ switch (sid) {
+ case ICE_SID_XLT1_SW:
+ case ICE_SID_XLT1_FD:
+ case ICE_SID_XLT1_RSS:
+ case ICE_SID_XLT1_ACL:
+ case ICE_SID_XLT1_PE:
+ xlt1 = (struct ice_xlt1_section *)sect;
+ src = xlt1->value;
+ sect_len = le16_to_cpu(xlt1->count) *
+ sizeof(*hw->blk[block_id].xlt1.t);
+ dst = hw->blk[block_id].xlt1.t;
+ dst_len = hw->blk[block_id].xlt1.count *
+ sizeof(*hw->blk[block_id].xlt1.t);
+ break;
+ case ICE_SID_XLT2_SW:
+ case ICE_SID_XLT2_FD:
+ case ICE_SID_XLT2_RSS:
+ case ICE_SID_XLT2_ACL:
+ case ICE_SID_XLT2_PE:
+ xlt2 = (struct ice_xlt2_section *)sect;
+ src = (__force u8 *)xlt2->value;
+ sect_len = le16_to_cpu(xlt2->count) *
+ sizeof(*hw->blk[block_id].xlt2.t);
+ dst = (u8 *)hw->blk[block_id].xlt2.t;
+ dst_len = hw->blk[block_id].xlt2.count *
+ sizeof(*hw->blk[block_id].xlt2.t);
+ break;
+ case ICE_SID_PROFID_TCAM_SW:
+ case ICE_SID_PROFID_TCAM_FD:
+ case ICE_SID_PROFID_TCAM_RSS:
+ case ICE_SID_PROFID_TCAM_ACL:
+ case ICE_SID_PROFID_TCAM_PE:
+ pid = (struct ice_prof_id_section *)sect;
+ src = (u8 *)pid->entry;
+ sect_len = le16_to_cpu(pid->count) *
+ sizeof(*hw->blk[block_id].prof.t);
+ dst = (u8 *)hw->blk[block_id].prof.t;
+ dst_len = hw->blk[block_id].prof.count *
+ sizeof(*hw->blk[block_id].prof.t);
+ break;
+ case ICE_SID_PROFID_REDIR_SW:
+ case ICE_SID_PROFID_REDIR_FD:
+ case ICE_SID_PROFID_REDIR_RSS:
+ case ICE_SID_PROFID_REDIR_ACL:
+ case ICE_SID_PROFID_REDIR_PE:
+ pr = (struct ice_prof_redir_section *)sect;
+ src = pr->redir_value;
+ sect_len = le16_to_cpu(pr->count) *
+ sizeof(*hw->blk[block_id].prof_redir.t);
+ dst = hw->blk[block_id].prof_redir.t;
+ dst_len = hw->blk[block_id].prof_redir.count *
+ sizeof(*hw->blk[block_id].prof_redir.t);
+ break;
+ case ICE_SID_FLD_VEC_SW:
+ case ICE_SID_FLD_VEC_FD:
+ case ICE_SID_FLD_VEC_RSS:
+ case ICE_SID_FLD_VEC_ACL:
+ case ICE_SID_FLD_VEC_PE:
+ es = (struct ice_sw_fv_section *)sect;
+ src = (u8 *)es->fv;
+ sect_len = (u32)(le16_to_cpu(es->count) *
+ hw->blk[block_id].es.fvw) *
+ sizeof(*hw->blk[block_id].es.t);
+ dst = (u8 *)hw->blk[block_id].es.t;
+ dst_len = (u32)(hw->blk[block_id].es.count *
+ hw->blk[block_id].es.fvw) *
+ sizeof(*hw->blk[block_id].es.t);
+ break;
+ default:
+ return;
+ }
+
+ /* if the section offset exceeds destination length, terminate
+ * table fill.
+ */
+ if (offset > dst_len)
+ return;
+
+ /* if the sum of section size and offset exceed destination size
+ * then we are out of bounds of the HW table size for that PF.
+ * Changing section length to fill the remaining table space
+ * of that PF.
+ */
+ if ((offset + sect_len) > dst_len)
+ sect_len = dst_len - offset;
+
+ memcpy(dst + offset, src, sect_len);
+ offset += sect_len;
+ sect = ice_pkg_enum_section(NULL, &state, sid);
+ }
+}
+
+/**
+ * ice_fill_blk_tbls - Read package context for tables
+ * @hw: pointer to the hardware structure
+ *
+ * Reads the current package contents and populates the driver
+ * database with the data iteratively for all advanced feature
+ * blocks. Assume that the HW tables have been allocated.
+ */
+void ice_fill_blk_tbls(struct ice_hw *hw)
+{
+ u8 i;
+
+ for (i = 0; i < ICE_BLK_COUNT; i++) {
+ enum ice_block blk_id = (enum ice_block)i;
+
+ ice_fill_tbl(hw, blk_id, hw->blk[blk_id].xlt1.sid);
+ ice_fill_tbl(hw, blk_id, hw->blk[blk_id].xlt2.sid);
+ ice_fill_tbl(hw, blk_id, hw->blk[blk_id].prof.sid);
+ ice_fill_tbl(hw, blk_id, hw->blk[blk_id].prof_redir.sid);
+ ice_fill_tbl(hw, blk_id, hw->blk[blk_id].es.sid);
+ }
+
+ ice_init_sw_db(hw);
+}
+
+/**
+ * ice_free_hw_tbls - free hardware table memory
+ * @hw: pointer to the hardware structure
+ */
+void ice_free_hw_tbls(struct ice_hw *hw)
+{
+ u8 i;
+
+ for (i = 0; i < ICE_BLK_COUNT; i++) {
+ hw->blk[i].is_list_init = false;
+
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptypes);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptg_tbl);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.t);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.t);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.vsig_tbl);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.vsis);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof.t);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_redir.t);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.t);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.ref_count);
+ devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written);
+ }
+
+ memset(hw->blk, 0, sizeof(hw->blk));
+}
+
+/**
+ * ice_clear_hw_tbls - clear HW tables and flow profiles
+ * @hw: pointer to the hardware structure
+ */
+void ice_clear_hw_tbls(struct ice_hw *hw)
+{
+ u8 i;
+
+ for (i = 0; i < ICE_BLK_COUNT; i++) {
+ struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir;
+ struct ice_prof_tcam *prof = &hw->blk[i].prof;
+ struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1;
+ struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2;
+ struct ice_es *es = &hw->blk[i].es;
+
+ memset(xlt1->ptypes, 0, xlt1->count * sizeof(*xlt1->ptypes));
+ memset(xlt1->ptg_tbl, 0,
+ ICE_MAX_PTGS * sizeof(*xlt1->ptg_tbl));
+ memset(xlt1->t, 0, xlt1->count * sizeof(*xlt1->t));
+
+ memset(xlt2->vsis, 0, xlt2->count * sizeof(*xlt2->vsis));
+ memset(xlt2->vsig_tbl, 0,
+ xlt2->count * sizeof(*xlt2->vsig_tbl));
+ memset(xlt2->t, 0, xlt2->count * sizeof(*xlt2->t));
+
+ memset(prof->t, 0, prof->count * sizeof(*prof->t));
+ memset(prof_redir->t, 0,
+ prof_redir->count * sizeof(*prof_redir->t));
+
+ memset(es->t, 0, es->count * sizeof(*es->t));
+ memset(es->ref_count, 0, es->count * sizeof(*es->ref_count));
+ memset(es->written, 0, es->count * sizeof(*es->written));
+ }
+}
+
+/**
+ * ice_init_hw_tbls - init hardware table memory
+ * @hw: pointer to the hardware structure
+ */
+enum ice_status ice_init_hw_tbls(struct ice_hw *hw)
+{
+ u8 i;
+
+ for (i = 0; i < ICE_BLK_COUNT; i++) {
+ struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir;
+ struct ice_prof_tcam *prof = &hw->blk[i].prof;
+ struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1;
+ struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2;
+ struct ice_es *es = &hw->blk[i].es;
+ u16 j;
+
+ if (hw->blk[i].is_list_init)
+ continue;
+
+ hw->blk[i].is_list_init = true;
+
+ hw->blk[i].overwrite = blk_sizes[i].overwrite;
+ es->reverse = blk_sizes[i].reverse;
+
+ xlt1->sid = ice_blk_sids[i][ICE_SID_XLT1_OFF];
+ xlt1->count = blk_sizes[i].xlt1;
+
+ xlt1->ptypes = devm_kcalloc(ice_hw_to_dev(hw), xlt1->count,
+ sizeof(*xlt1->ptypes), GFP_KERNEL);
+
+ if (!xlt1->ptypes)
+ goto err;
+
+ xlt1->ptg_tbl = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_PTGS,
+ sizeof(*xlt1->ptg_tbl),
+ GFP_KERNEL);
+
+ if (!xlt1->ptg_tbl)
+ goto err;
+
+ xlt1->t = devm_kcalloc(ice_hw_to_dev(hw), xlt1->count,
+ sizeof(*xlt1->t), GFP_KERNEL);
+ if (!xlt1->t)
+ goto err;
+
+ xlt2->sid = ice_blk_sids[i][ICE_SID_XLT2_OFF];
+ xlt2->count = blk_sizes[i].xlt2;
+
+ xlt2->vsis = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count,
+ sizeof(*xlt2->vsis), GFP_KERNEL);
+
+ if (!xlt2->vsis)
+ goto err;
+
+ xlt2->vsig_tbl = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count,
+ sizeof(*xlt2->vsig_tbl),
+ GFP_KERNEL);
+ if (!xlt2->vsig_tbl)
+ goto err;
+
+ for (j = 0; j < xlt2->count; j++)
+ INIT_LIST_HEAD(&xlt2->vsig_tbl[j].prop_lst);
+
+ xlt2->t = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count,
+ sizeof(*xlt2->t), GFP_KERNEL);
+ if (!xlt2->t)
+ goto err;
+
+ prof->sid = ice_blk_sids[i][ICE_SID_PR_OFF];
+ prof->count = blk_sizes[i].prof_tcam;
+ prof->max_prof_id = blk_sizes[i].prof_id;
+ prof->cdid_bits = blk_sizes[i].prof_cdid_bits;
+ prof->t = devm_kcalloc(ice_hw_to_dev(hw), prof->count,
+ sizeof(*prof->t), GFP_KERNEL);
+
+ if (!prof->t)
+ goto err;
+
+ prof_redir->sid = ice_blk_sids[i][ICE_SID_PR_REDIR_OFF];
+ prof_redir->count = blk_sizes[i].prof_redir;
+ prof_redir->t = devm_kcalloc(ice_hw_to_dev(hw),
+ prof_redir->count,
+ sizeof(*prof_redir->t),
+ GFP_KERNEL);
+
+ if (!prof_redir->t)
+ goto err;
+
+ es->sid = ice_blk_sids[i][ICE_SID_ES_OFF];
+ es->count = blk_sizes[i].es;
+ es->fvw = blk_sizes[i].fvw;
+ es->t = devm_kcalloc(ice_hw_to_dev(hw),
+ (u32)(es->count * es->fvw),
+ sizeof(*es->t), GFP_KERNEL);
+ if (!es->t)
+ goto err;
+
+ es->ref_count = devm_kcalloc(ice_hw_to_dev(hw), es->count,
+ sizeof(*es->ref_count),
+ GFP_KERNEL);
+
+ es->written = devm_kcalloc(ice_hw_to_dev(hw), es->count,
+ sizeof(*es->written), GFP_KERNEL);
+ if (!es->ref_count)
+ goto err;
+ }
+ return 0;
+
+err:
+ ice_free_hw_tbls(hw);
+ return ICE_ERR_NO_MEMORY;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
new file mode 100644
index 0000000..37eb282
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_FLEX_PIPE_H_
+#define _ICE_FLEX_PIPE_H_
+
+#include "ice_type.h"
+
+/* Package minimal version supported */
+#define ICE_PKG_SUPP_VER_MAJ 1
+#define ICE_PKG_SUPP_VER_MNR 3
+
+/* Package format version */
+#define ICE_PKG_FMT_VER_MAJ 1
+#define ICE_PKG_FMT_VER_MNR 0
+#define ICE_PKG_FMT_VER_UPD 0
+#define ICE_PKG_FMT_VER_DFT 0
+
+#define ICE_PKG_CNT 4
+
+enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len);
+enum ice_status
+ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len);
+enum ice_status ice_init_hw_tbls(struct ice_hw *hw);
+void ice_free_seg(struct ice_hw *hw);
+void ice_fill_blk_tbls(struct ice_hw *hw);
+void ice_clear_hw_tbls(struct ice_hw *hw);
+void ice_free_hw_tbls(struct ice_hw *hw);
+#endif /* _ICE_FLEX_PIPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
new file mode 100644
index 0000000..5d5a7ea
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -0,0 +1,374 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_FLEX_TYPE_H_
+#define _ICE_FLEX_TYPE_H_
+/* Extraction Sequence (Field Vector) Table */
+struct ice_fv_word {
+ u8 prot_id;
+ u16 off; /* Offset within the protocol header */
+ u8 resvrd;
+} __packed;
+
+#define ICE_MAX_FV_WORDS 48
+struct ice_fv {
+ struct ice_fv_word ew[ICE_MAX_FV_WORDS];
+};
+
+/* Package and segment headers and tables */
+struct ice_pkg_hdr {
+ struct ice_pkg_ver format_ver;
+ __le32 seg_count;
+ __le32 seg_offset[1];
+};
+
+/* generic segment */
+struct ice_generic_seg_hdr {
+#define SEGMENT_TYPE_METADATA 0x00000001
+#define SEGMENT_TYPE_ICE 0x00000010
+ __le32 seg_type;
+ struct ice_pkg_ver seg_ver;
+ __le32 seg_size;
+ char seg_name[ICE_PKG_NAME_SIZE];
+};
+
+/* ice specific segment */
+
+union ice_device_id {
+ struct {
+ __le16 device_id;
+ __le16 vendor_id;
+ } dev_vend_id;
+ __le32 id;
+};
+
+struct ice_device_id_entry {
+ union ice_device_id device;
+ union ice_device_id sub_device;
+};
+
+struct ice_seg {
+ struct ice_generic_seg_hdr hdr;
+ __le32 device_table_count;
+ struct ice_device_id_entry device_table[1];
+};
+
+struct ice_nvm_table {
+ __le32 table_count;
+ __le32 vers[1];
+};
+
+struct ice_buf {
+#define ICE_PKG_BUF_SIZE 4096
+ u8 buf[ICE_PKG_BUF_SIZE];
+};
+
+struct ice_buf_table {
+ __le32 buf_count;
+ struct ice_buf buf_array[1];
+};
+
+/* global metadata specific segment */
+struct ice_global_metadata_seg {
+ struct ice_generic_seg_hdr hdr;
+ struct ice_pkg_ver pkg_ver;
+ __le32 track_id;
+ char pkg_name[ICE_PKG_NAME_SIZE];
+};
+
+#define ICE_MIN_S_OFF 12
+#define ICE_MAX_S_OFF 4095
+#define ICE_MIN_S_SZ 1
+#define ICE_MAX_S_SZ 4084
+
+/* section information */
+struct ice_section_entry {
+ __le32 type;
+ __le16 offset;
+ __le16 size;
+};
+
+#define ICE_MIN_S_COUNT 1
+#define ICE_MAX_S_COUNT 511
+#define ICE_MIN_S_DATA_END 12
+#define ICE_MAX_S_DATA_END 4096
+
+#define ICE_METADATA_BUF 0x80000000
+
+struct ice_buf_hdr {
+ __le16 section_count;
+ __le16 data_end;
+ struct ice_section_entry section_entry[1];
+};
+
+#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz) ((ICE_PKG_BUF_SIZE - \
+ sizeof(struct ice_buf_hdr) - (hd_sz)) / (ent_sz))
+
+/* ice package section IDs */
+#define ICE_SID_XLT1_SW 12
+#define ICE_SID_XLT2_SW 13
+#define ICE_SID_PROFID_TCAM_SW 14
+#define ICE_SID_PROFID_REDIR_SW 15
+#define ICE_SID_FLD_VEC_SW 16
+
+#define ICE_SID_XLT1_ACL 22
+#define ICE_SID_XLT2_ACL 23
+#define ICE_SID_PROFID_TCAM_ACL 24
+#define ICE_SID_PROFID_REDIR_ACL 25
+#define ICE_SID_FLD_VEC_ACL 26
+
+#define ICE_SID_XLT1_FD 32
+#define ICE_SID_XLT2_FD 33
+#define ICE_SID_PROFID_TCAM_FD 34
+#define ICE_SID_PROFID_REDIR_FD 35
+#define ICE_SID_FLD_VEC_FD 36
+
+#define ICE_SID_XLT1_RSS 42
+#define ICE_SID_XLT2_RSS 43
+#define ICE_SID_PROFID_TCAM_RSS 44
+#define ICE_SID_PROFID_REDIR_RSS 45
+#define ICE_SID_FLD_VEC_RSS 46
+
+#define ICE_SID_RXPARSER_BOOST_TCAM 56
+
+#define ICE_SID_XLT1_PE 82
+#define ICE_SID_XLT2_PE 83
+#define ICE_SID_PROFID_TCAM_PE 84
+#define ICE_SID_PROFID_REDIR_PE 85
+#define ICE_SID_FLD_VEC_PE 86
+
+/* Label Metadata section IDs */
+#define ICE_SID_LBL_FIRST 0x80000010
+#define ICE_SID_LBL_RXPARSER_TMEM 0x80000018
+/* The following define MUST be updated to reflect the last label section ID */
+#define ICE_SID_LBL_LAST 0x80000038
+
+enum ice_block {
+ ICE_BLK_SW = 0,
+ ICE_BLK_ACL,
+ ICE_BLK_FD,
+ ICE_BLK_RSS,
+ ICE_BLK_PE,
+ ICE_BLK_COUNT
+};
+
+/* package labels */
+struct ice_label {
+ __le16 value;
+#define ICE_PKG_LABEL_SIZE 64
+ char name[ICE_PKG_LABEL_SIZE];
+};
+
+struct ice_label_section {
+ __le16 count;
+ struct ice_label label[1];
+};
+
+#define ICE_MAX_LABELS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \
+ sizeof(struct ice_label_section) - sizeof(struct ice_label), \
+ sizeof(struct ice_label))
+
+struct ice_sw_fv_section {
+ __le16 count;
+ __le16 base_offset;
+ struct ice_fv fv[1];
+};
+
+/* The BOOST TCAM stores the match packet header in reverse order, meaning
+ * the fields are reversed; in addition, this means that the normally big endian
+ * fields of the packet are now little endian.
+ */
+struct ice_boost_key_value {
+#define ICE_BOOST_REMAINING_HV_KEY 15
+ u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY];
+ __le16 hv_dst_port_key;
+ __le16 hv_src_port_key;
+ u8 tcam_search_key;
+} __packed;
+
+struct ice_boost_key {
+ struct ice_boost_key_value key;
+ struct ice_boost_key_value key2;
+};
+
+/* package Boost TCAM entry */
+struct ice_boost_tcam_entry {
+ __le16 addr;
+ __le16 reserved;
+ /* break up the 40 bytes of key into different fields */
+ struct ice_boost_key key;
+ u8 boost_hit_index_group;
+ /* The following contains bitfields which are not on byte boundaries.
+ * These fields are currently unused by driver software.
+ */
+#define ICE_BOOST_BIT_FIELDS 43
+ u8 bit_fields[ICE_BOOST_BIT_FIELDS];
+};
+
+struct ice_boost_tcam_section {
+ __le16 count;
+ __le16 reserved;
+ struct ice_boost_tcam_entry tcam[1];
+};
+
+#define ICE_MAX_BST_TCAMS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \
+ sizeof(struct ice_boost_tcam_section) - \
+ sizeof(struct ice_boost_tcam_entry), \
+ sizeof(struct ice_boost_tcam_entry))
+
+struct ice_xlt1_section {
+ __le16 count;
+ __le16 offset;
+ u8 value[1];
+} __packed;
+
+struct ice_xlt2_section {
+ __le16 count;
+ __le16 offset;
+ __le16 value[1];
+};
+
+struct ice_prof_redir_section {
+ __le16 count;
+ __le16 offset;
+ u8 redir_value[1];
+};
+
+struct ice_pkg_enum {
+ struct ice_buf_table *buf_table;
+ u32 buf_idx;
+
+ u32 type;
+ struct ice_buf_hdr *buf;
+ u32 sect_idx;
+ void *sect;
+ u32 sect_type;
+
+ u32 entry_idx;
+ void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
+};
+
+struct ice_es {
+ u32 sid;
+ u16 count;
+ u16 fvw;
+ u16 *ref_count;
+ struct list_head prof_map;
+ struct ice_fv_word *t;
+ struct mutex prof_map_lock; /* protect access to profiles list */
+ u8 *written;
+ u8 reverse; /* set to true to reverse FV order */
+};
+
+/* PTYPE Group management */
+
+/* Note: XLT1 table takes 13-bit as input, and results in an 8-bit packet type
+ * group (PTG) ID as output.
+ *
+ * Note: PTG 0 is the default packet type group and it is assumed that all PTYPE
+ * are a part of this group until moved to a new PTG.
+ */
+#define ICE_DEFAULT_PTG 0
+
+struct ice_ptg_entry {
+ struct ice_ptg_ptype *first_ptype;
+ u8 in_use;
+};
+
+struct ice_ptg_ptype {
+ struct ice_ptg_ptype *next_ptype;
+ u8 ptg;
+};
+
+struct ice_vsig_entry {
+ struct list_head prop_lst;
+ struct ice_vsig_vsi *first_vsi;
+ u8 in_use;
+};
+
+struct ice_vsig_vsi {
+ struct ice_vsig_vsi *next_vsi;
+ u32 prop_mask;
+ u16 changed;
+ u16 vsig;
+};
+
+#define ICE_XLT1_CNT 1024
+#define ICE_MAX_PTGS 256
+
+/* XLT1 Table */
+struct ice_xlt1 {
+ struct ice_ptg_entry *ptg_tbl;
+ struct ice_ptg_ptype *ptypes;
+ u8 *t;
+ u32 sid;
+ u16 count;
+};
+
+#define ICE_XLT2_CNT 768
+#define ICE_MAX_VSIGS 768
+
+/* VSIG bit layout:
+ * [0:12]: incremental VSIG index 1 to ICE_MAX_VSIGS
+ * [13:15]: PF number of device
+ */
+#define ICE_VSIG_IDX_M (0x1FFF)
+#define ICE_PF_NUM_S 13
+#define ICE_PF_NUM_M (0x07 << ICE_PF_NUM_S)
+#define ICE_VSIG_VALUE(vsig, pf_id) \
+ (u16)((((u16)(vsig)) & ICE_VSIG_IDX_M) | \
+ (((u16)(pf_id) << ICE_PF_NUM_S) & ICE_PF_NUM_M))
+#define ICE_DEFAULT_VSIG 0
+
+/* XLT2 Table */
+struct ice_xlt2 {
+ struct ice_vsig_entry *vsig_tbl;
+ struct ice_vsig_vsi *vsis;
+ u16 *t;
+ u32 sid;
+ u16 count;
+};
+
+/* Keys are made up of two values, each one-half the size of the key.
+ * For TCAM, the entire key is 80 bits wide (or 2, 40-bit wide values)
+ */
+#define ICE_TCAM_KEY_VAL_SZ 5
+#define ICE_TCAM_KEY_SZ (2 * ICE_TCAM_KEY_VAL_SZ)
+
+struct ice_prof_tcam_entry {
+ __le16 addr;
+ u8 key[ICE_TCAM_KEY_SZ];
+ u8 prof_id;
+} __packed;
+
+struct ice_prof_id_section {
+ __le16 count;
+ struct ice_prof_tcam_entry entry[1];
+} __packed;
+
+struct ice_prof_tcam {
+ u32 sid;
+ u16 count;
+ u16 max_prof_id;
+ struct ice_prof_tcam_entry *t;
+ u8 cdid_bits; /* # CDID bits to use in key, 0, 2, 4, or 8 */
+};
+
+struct ice_prof_redir {
+ u8 *t;
+ u32 sid;
+ u16 count;
+};
+
+/* Tables per block */
+struct ice_blk_info {
+ struct ice_xlt1 xlt1;
+ struct ice_xlt2 xlt2;
+ struct ice_prof_tcam prof;
+ struct ice_prof_redir prof_redir;
+ struct ice_es es;
+ u8 overwrite; /* set to true to allow overwrite of table entries */
+ u8 is_list_init;
+};
+
+#endif /* _ICE_FLEX_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 6076fc8..152fbd5 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -6,251 +6,342 @@
#ifndef _ICE_HW_AUTOGEN_H_
#define _ICE_HW_AUTOGEN_H_
-#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4))
-#define PF_FW_ARQBAH 0x00080180
-#define PF_FW_ARQBAL 0x00080080
-#define PF_FW_ARQH 0x00080380
-#define PF_FW_ARQH_ARQH_S 0
-#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, PF_FW_ARQH_ARQH_S)
-#define PF_FW_ARQLEN 0x00080280
-#define PF_FW_ARQLEN_ARQLEN_S 0
-#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, PF_FW_ARQLEN_ARQLEN_S)
-#define PF_FW_ARQLEN_ARQVFE_S 28
-#define PF_FW_ARQLEN_ARQVFE_M BIT(PF_FW_ARQLEN_ARQVFE_S)
-#define PF_FW_ARQLEN_ARQOVFL_S 29
-#define PF_FW_ARQLEN_ARQOVFL_M BIT(PF_FW_ARQLEN_ARQOVFL_S)
-#define PF_FW_ARQLEN_ARQCRIT_S 30
-#define PF_FW_ARQLEN_ARQCRIT_M BIT(PF_FW_ARQLEN_ARQCRIT_S)
-#define PF_FW_ARQLEN_ARQENABLE_S 31
-#define PF_FW_ARQLEN_ARQENABLE_M BIT(PF_FW_ARQLEN_ARQENABLE_S)
-#define PF_FW_ARQT 0x00080480
-#define PF_FW_ATQBAH 0x00080100
-#define PF_FW_ATQBAL 0x00080000
-#define PF_FW_ATQH 0x00080300
-#define PF_FW_ATQH_ATQH_S 0
-#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, PF_FW_ATQH_ATQH_S)
-#define PF_FW_ATQLEN 0x00080200
-#define PF_FW_ATQLEN_ATQLEN_S 0
-#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, PF_FW_ATQLEN_ATQLEN_S)
-#define PF_FW_ATQLEN_ATQVFE_S 28
-#define PF_FW_ATQLEN_ATQVFE_M BIT(PF_FW_ATQLEN_ATQVFE_S)
-#define PF_FW_ATQLEN_ATQOVFL_S 29
-#define PF_FW_ATQLEN_ATQOVFL_M BIT(PF_FW_ATQLEN_ATQOVFL_S)
-#define PF_FW_ATQLEN_ATQCRIT_S 30
-#define PF_FW_ATQLEN_ATQCRIT_M BIT(PF_FW_ATQLEN_ATQCRIT_S)
-#define PF_FW_ATQLEN_ATQENABLE_S 31
-#define PF_FW_ATQLEN_ATQENABLE_M BIT(PF_FW_ATQLEN_ATQENABLE_S)
-#define PF_FW_ATQT 0x00080400
-
+#define PF0INT_ITR_0(_i) (0x03000004 + ((_i) * 4096))
+#define PF0INT_ITR_1(_i) (0x03000008 + ((_i) * 4096))
+#define PF0INT_ITR_2(_i) (0x0300000C + ((_i) * 4096))
+#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD(_DBQM) (0x000E0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD_HEAD_S 0
+#define QTX_COMM_HEAD_HEAD_M ICE_M(0x1FFF, 0)
+#define PF_FW_ARQBAH 0x00080180
+#define PF_FW_ARQBAL 0x00080080
+#define PF_FW_ARQH 0x00080380
+#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, 0)
+#define PF_FW_ARQLEN 0x00080280
+#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0)
+#define PF_FW_ARQLEN_ARQVFE_M BIT(28)
+#define PF_FW_ARQLEN_ARQOVFL_M BIT(29)
+#define PF_FW_ARQLEN_ARQCRIT_M BIT(30)
+#define PF_FW_ARQLEN_ARQENABLE_M BIT(31)
+#define PF_FW_ARQT 0x00080480
+#define PF_FW_ATQBAH 0x00080100
+#define PF_FW_ATQBAL 0x00080000
+#define PF_FW_ATQH 0x00080300
+#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, 0)
+#define PF_FW_ATQLEN 0x00080200
+#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0)
+#define PF_FW_ATQLEN_ATQVFE_M BIT(28)
+#define PF_FW_ATQLEN_ATQOVFL_M BIT(29)
+#define PF_FW_ATQLEN_ATQCRIT_M BIT(30)
+#define VF_MBX_ARQLEN(_VF) (0x0022BC00 + ((_VF) * 4))
+#define PF_FW_ATQLEN_ATQENABLE_M BIT(31)
+#define PF_FW_ATQT 0x00080400
+#define PF_MBX_ARQBAH 0x0022E400
+#define PF_MBX_ARQBAL 0x0022E380
+#define PF_MBX_ARQH 0x0022E500
+#define PF_MBX_ARQH_ARQH_M ICE_M(0x3FF, 0)
+#define PF_MBX_ARQLEN 0x0022E480
+#define PF_MBX_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0)
+#define PF_MBX_ARQLEN_ARQENABLE_M BIT(31)
+#define PF_MBX_ARQT 0x0022E580
+#define PF_MBX_ATQBAH 0x0022E180
+#define PF_MBX_ATQBAL 0x0022E100
+#define PF_MBX_ATQH 0x0022E280
+#define PF_MBX_ATQH_ATQH_M ICE_M(0x3FF, 0)
+#define PF_MBX_ATQLEN 0x0022E200
+#define PF_MBX_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0)
+#define PF_MBX_ATQLEN_ATQENABLE_M BIT(31)
+#define PF_MBX_ATQT 0x0022E300
+#define PRTDCB_GENS 0x00083020
+#define PRTDCB_GENS_DCBX_STATUS_S 0
+#define PRTDCB_GENS_DCBX_STATUS_M ICE_M(0x7, 0)
+#define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4))
+#define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4))
#define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256))
#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0)
#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S 8
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, 8)
#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S 16
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, 16)
#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S 24
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, 24)
#define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4))
#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0
-#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0)
#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S 30
-#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, 30)
#define GLFLXP_RXDID_FLX_WRD_1(_i) (0x0045c900 + ((_i) * 4))
#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S 0
-#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, 0)
#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S 30
-#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, 30)
#define GLFLXP_RXDID_FLX_WRD_2(_i) (0x0045ca00 + ((_i) * 4))
#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S 0
-#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, 0)
#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S 30
-#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, 30)
#define GLFLXP_RXDID_FLX_WRD_3(_i) (0x0045cb00 + ((_i) * 4))
#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S 0
-#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, 0)
#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S 30
-#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S)
-
-#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4))
-#define QRXFLXP_CNTXT_RXDID_IDX_S 0
-#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, QRXFLXP_CNTXT_RXDID_IDX_S)
-#define QRXFLXP_CNTXT_RXDID_PRIO_S 8
-#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, QRXFLXP_CNTXT_RXDID_PRIO_S)
-#define QRXFLXP_CNTXT_TS_S 11
-#define QRXFLXP_CNTXT_TS_M BIT(QRXFLXP_CNTXT_TS_S)
-#define GLGEN_RSTAT 0x000B8188
-#define GLGEN_RSTAT_DEVSTATE_S 0
-#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, GLGEN_RSTAT_DEVSTATE_S)
-#define GLGEN_RSTCTL 0x000B8180
-#define GLGEN_RSTCTL_GRSTDEL_S 0
-#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S)
-#define GLGEN_RSTAT_RESET_TYPE_S 2
-#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, GLGEN_RSTAT_RESET_TYPE_S)
-#define GLGEN_RTRIG 0x000B8190
-#define GLGEN_RTRIG_CORER_S 0
-#define GLGEN_RTRIG_CORER_M BIT(GLGEN_RTRIG_CORER_S)
-#define GLGEN_RTRIG_GLOBR_S 1
-#define GLGEN_RTRIG_GLOBR_M BIT(GLGEN_RTRIG_GLOBR_S)
-#define GLGEN_STAT 0x000B612C
-#define PFGEN_CTRL 0x00091000
-#define PFGEN_CTRL_PFSWR_S 0
-#define PFGEN_CTRL_PFSWR_M BIT(PFGEN_CTRL_PFSWR_S)
-#define PFGEN_STATE 0x00088000
-#define PRTGEN_STATUS 0x000B8100
-#define PFHMC_ERRORDATA 0x00520500
-#define PFHMC_ERRORINFO 0x00520400
-#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4))
-#define GLINT_DYN_CTL_INTENA_S 0
-#define GLINT_DYN_CTL_INTENA_M BIT(GLINT_DYN_CTL_INTENA_S)
-#define GLINT_DYN_CTL_CLEARPBA_S 1
-#define GLINT_DYN_CTL_CLEARPBA_M BIT(GLINT_DYN_CTL_CLEARPBA_S)
-#define GLINT_DYN_CTL_SWINT_TRIG_S 2
-#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(GLINT_DYN_CTL_SWINT_TRIG_S)
-#define GLINT_DYN_CTL_ITR_INDX_S 3
-#define GLINT_DYN_CTL_SW_ITR_INDX_S 25
-#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S)
-#define GLINT_DYN_CTL_INTENA_MSK_S 31
-#define GLINT_DYN_CTL_INTENA_MSK_M BIT(GLINT_DYN_CTL_INTENA_MSK_S)
-#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4))
-#define PFINT_FW_CTL 0x0016C800
-#define PFINT_FW_CTL_MSIX_INDX_S 0
-#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_FW_CTL_MSIX_INDX_S)
-#define PFINT_FW_CTL_ITR_INDX_S 11
-#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, PFINT_FW_CTL_ITR_INDX_S)
-#define PFINT_FW_CTL_CAUSE_ENA_S 30
-#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S)
-#define PFINT_OICR 0x0016CA00
-#define PFINT_OICR_ECC_ERR_S 16
-#define PFINT_OICR_ECC_ERR_M BIT(PFINT_OICR_ECC_ERR_S)
-#define PFINT_OICR_MAL_DETECT_S 19
-#define PFINT_OICR_MAL_DETECT_M BIT(PFINT_OICR_MAL_DETECT_S)
-#define PFINT_OICR_GRST_S 20
-#define PFINT_OICR_GRST_M BIT(PFINT_OICR_GRST_S)
-#define PFINT_OICR_PCI_EXCEPTION_S 21
-#define PFINT_OICR_PCI_EXCEPTION_M BIT(PFINT_OICR_PCI_EXCEPTION_S)
-#define PFINT_OICR_HMC_ERR_S 26
-#define PFINT_OICR_HMC_ERR_M BIT(PFINT_OICR_HMC_ERR_S)
-#define PFINT_OICR_PE_CRITERR_S 28
-#define PFINT_OICR_PE_CRITERR_M BIT(PFINT_OICR_PE_CRITERR_S)
-#define PFINT_OICR_CTL 0x0016CA80
-#define PFINT_OICR_CTL_MSIX_INDX_S 0
-#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_OICR_CTL_MSIX_INDX_S)
-#define PFINT_OICR_CTL_ITR_INDX_S 11
-#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, PFINT_OICR_CTL_ITR_INDX_S)
-#define PFINT_OICR_CTL_CAUSE_ENA_S 30
-#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(PFINT_OICR_CTL_CAUSE_ENA_S)
-#define PFINT_OICR_ENA 0x0016C900
-#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4))
-#define QINT_RQCTL_MSIX_INDX_S 0
-#define QINT_RQCTL_ITR_INDX_S 11
-#define QINT_RQCTL_CAUSE_ENA_S 30
-#define QINT_RQCTL_CAUSE_ENA_M BIT(QINT_RQCTL_CAUSE_ENA_S)
-#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4))
-#define QINT_TQCTL_MSIX_INDX_S 0
-#define QINT_TQCTL_ITR_INDX_S 11
-#define QINT_TQCTL_CAUSE_ENA_S 30
-#define QINT_TQCTL_CAUSE_ENA_M BIT(QINT_TQCTL_CAUSE_ENA_S)
-#define GLLAN_RCTL_0 0x002941F8
-#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4))
-#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4))
-#define QRX_CTRL_MAX_INDEX 2047
-#define QRX_CTRL_QENA_REQ_S 0
-#define QRX_CTRL_QENA_REQ_M BIT(QRX_CTRL_QENA_REQ_S)
-#define QRX_CTRL_QENA_STAT_S 2
-#define QRX_CTRL_QENA_STAT_M BIT(QRX_CTRL_QENA_STAT_S)
-#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4))
-#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4))
-#define GLNVM_FLA 0x000B6108
-#define GLNVM_FLA_LOCKED_S 6
-#define GLNVM_FLA_LOCKED_M BIT(GLNVM_FLA_LOCKED_S)
-#define GLNVM_GENS 0x000B6100
-#define GLNVM_GENS_SR_SIZE_S 5
-#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, GLNVM_GENS_SR_SIZE_S)
-#define GLNVM_ULD 0x000B6008
-#define GLNVM_ULD_CORER_DONE_S 3
-#define GLNVM_ULD_CORER_DONE_M BIT(GLNVM_ULD_CORER_DONE_S)
-#define GLNVM_ULD_GLOBR_DONE_S 4
-#define GLNVM_ULD_GLOBR_DONE_M BIT(GLNVM_ULD_GLOBR_DONE_S)
-#define PF_FUNC_RID 0x0009E880
-#define PF_FUNC_RID_FUNC_NUM_S 0
-#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, PF_FUNC_RID_FUNC_NUM_S)
-#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8))
-#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8))
-#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8))
-#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8))
-#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8))
-#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8))
-#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8))
-#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8))
-#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8))
-#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8))
-#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8))
-#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8))
-#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8))
-#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8))
-#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8))
-#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8))
-#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8))
-#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8))
-#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8))
-#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8))
-#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8))
-#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8))
-#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8))
-#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8))
-#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8))
-#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8))
-#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8))
-#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8))
-#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8))
-#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8))
-#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8))
-#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8))
-#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8))
-#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8))
-#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8))
-#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8))
-#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8))
-#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8))
-#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8))
-#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8))
-#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8))
-#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8))
-#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8))
-#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8))
-#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8))
-#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8))
-#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8))
-#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8))
-#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8))
-#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8))
-#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8))
-#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8))
-#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8))
-#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8))
-#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8))
-#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8))
-#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8))
-#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8))
-#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8))
-#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8))
-#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8))
-#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8))
-#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8))
-#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8))
-#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8))
-#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8))
-#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8))
-#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8))
-#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8))
-#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8))
-#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4))
-#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4))
-#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8))
-#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8))
-#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8))
-#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8))
-#define VSIQF_HKEY_MAX_INDEX 12
+#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, 30)
+#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4))
+#define QRXFLXP_CNTXT_RXDID_IDX_S 0
+#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, 0)
+#define QRXFLXP_CNTXT_RXDID_PRIO_S 8
+#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, 8)
+#define GLGEN_RSTAT 0x000B8188
+#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0)
+#define GLGEN_RSTCTL 0x000B8180
+#define GLGEN_RSTCTL_GRSTDEL_S 0
+#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S)
+#define GLGEN_RSTAT_RESET_TYPE_S 2
+#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, 2)
+#define GLGEN_RTRIG 0x000B8190
+#define GLGEN_RTRIG_CORER_M BIT(0)
+#define GLGEN_RTRIG_GLOBR_M BIT(1)
+#define GLGEN_STAT 0x000B612C
+#define GLGEN_VFLRSTAT(_i) (0x00093A04 + ((_i) * 4))
+#define PFGEN_CTRL 0x00091000
+#define PFGEN_CTRL_PFSWR_M BIT(0)
+#define PFGEN_STATE 0x00088000
+#define PRTGEN_STATUS 0x000B8100
+#define VFGEN_RSTAT(_VF) (0x00074000 + ((_VF) * 4))
+#define VPGEN_VFRSTAT(_VF) (0x00090800 + ((_VF) * 4))
+#define VPGEN_VFRSTAT_VFRD_M BIT(0)
+#define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4))
+#define VPGEN_VFRTRIG_VFSWR_M BIT(0)
+#define PFHMC_ERRORDATA 0x00520500
+#define PFHMC_ERRORINFO 0x00520400
+#define GLINT_CTL 0x0016CC54
+#define GLINT_CTL_DIS_AUTOMASK_M BIT(0)
+#define GLINT_CTL_ITR_GRAN_200_S 16
+#define GLINT_CTL_ITR_GRAN_200_M ICE_M(0xF, 16)
+#define GLINT_CTL_ITR_GRAN_100_S 20
+#define GLINT_CTL_ITR_GRAN_100_M ICE_M(0xF, 20)
+#define GLINT_CTL_ITR_GRAN_50_S 24
+#define GLINT_CTL_ITR_GRAN_50_M ICE_M(0xF, 24)
+#define GLINT_CTL_ITR_GRAN_25_S 28
+#define GLINT_CTL_ITR_GRAN_25_M ICE_M(0xF, 28)
+#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4))
+#define GLINT_DYN_CTL_INTENA_M BIT(0)
+#define GLINT_DYN_CTL_CLEARPBA_M BIT(1)
+#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(2)
+#define GLINT_DYN_CTL_ITR_INDX_S 3
+#define GLINT_DYN_CTL_ITR_INDX_M ICE_M(0x3, 3)
+#define GLINT_DYN_CTL_INTERVAL_S 5
+#define GLINT_DYN_CTL_INTERVAL_M ICE_M(0xFFF, 5)
+#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25)
+#define GLINT_DYN_CTL_WB_ON_ITR_M BIT(30)
+#define GLINT_DYN_CTL_INTENA_MSK_M BIT(31)
+#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4))
+#define GLINT_RATE(_INT) (0x0015A000 + ((_INT) * 4))
+#define GLINT_RATE_INTRL_ENA_M BIT(6)
+#define GLINT_VECT2FUNC(_INT) (0x00162000 + ((_INT) * 4))
+#define GLINT_VECT2FUNC_VF_NUM_S 0
+#define GLINT_VECT2FUNC_VF_NUM_M ICE_M(0xFF, 0)
+#define GLINT_VECT2FUNC_PF_NUM_S 12
+#define GLINT_VECT2FUNC_PF_NUM_M ICE_M(0x7, 12)
+#define GLINT_VECT2FUNC_IS_PF_S 16
+#define GLINT_VECT2FUNC_IS_PF_M BIT(16)
+#define PFINT_FW_CTL 0x0016C800
+#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0)
+#define PFINT_FW_CTL_ITR_INDX_S 11
+#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, 11)
+#define PFINT_FW_CTL_CAUSE_ENA_M BIT(30)
+#define PFINT_MBX_CTL 0x0016B280
+#define PFINT_MBX_CTL_MSIX_INDX_M ICE_M(0x7FF, 0)
+#define PFINT_MBX_CTL_ITR_INDX_S 11
+#define PFINT_MBX_CTL_ITR_INDX_M ICE_M(0x3, 11)
+#define PFINT_MBX_CTL_CAUSE_ENA_M BIT(30)
+#define PFINT_OICR 0x0016CA00
+#define PFINT_OICR_ECC_ERR_M BIT(16)
+#define PFINT_OICR_MAL_DETECT_M BIT(19)
+#define PFINT_OICR_GRST_M BIT(20)
+#define PFINT_OICR_PCI_EXCEPTION_M BIT(21)
+#define PFINT_OICR_HMC_ERR_M BIT(26)
+#define PFINT_OICR_PE_CRITERR_M BIT(28)
+#define PFINT_OICR_VFLR_M BIT(29)
+#define PFINT_OICR_SWINT_M BIT(31)
+#define PFINT_OICR_CTL 0x0016CA80
+#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0)
+#define PFINT_OICR_CTL_ITR_INDX_S 11
+#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, 11)
+#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(30)
+#define PFINT_OICR_ENA 0x0016C900
+#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4))
+#define QINT_RQCTL_MSIX_INDX_S 0
+#define QINT_RQCTL_MSIX_INDX_M ICE_M(0x7FF, 0)
+#define QINT_RQCTL_ITR_INDX_S 11
+#define QINT_RQCTL_ITR_INDX_M ICE_M(0x3, 11)
+#define QINT_RQCTL_CAUSE_ENA_M BIT(30)
+#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4))
+#define QINT_TQCTL_MSIX_INDX_S 0
+#define QINT_TQCTL_MSIX_INDX_M ICE_M(0x7FF, 0)
+#define QINT_TQCTL_ITR_INDX_S 11
+#define QINT_TQCTL_ITR_INDX_M ICE_M(0x3, 11)
+#define QINT_TQCTL_CAUSE_ENA_M BIT(30)
+#define VPINT_ALLOC(_VF) (0x001D1000 + ((_VF) * 4))
+#define VPINT_ALLOC_FIRST_S 0
+#define VPINT_ALLOC_FIRST_M ICE_M(0x7FF, 0)
+#define VPINT_ALLOC_LAST_S 12
+#define VPINT_ALLOC_LAST_M ICE_M(0x7FF, 12)
+#define VPINT_ALLOC_VALID_M BIT(31)
+#define VPINT_ALLOC_PCI(_VF) (0x0009D000 + ((_VF) * 4))
+#define VPINT_ALLOC_PCI_FIRST_S 0
+#define VPINT_ALLOC_PCI_FIRST_M ICE_M(0x7FF, 0)
+#define VPINT_ALLOC_PCI_LAST_S 12
+#define VPINT_ALLOC_PCI_LAST_M ICE_M(0x7FF, 12)
+#define VPINT_ALLOC_PCI_VALID_M BIT(31)
+#define VPINT_MBX_CTL(_VSI) (0x0016A000 + ((_VSI) * 4))
+#define VPINT_MBX_CTL_CAUSE_ENA_M BIT(30)
+#define GLLAN_RCTL_0 0x002941F8
+#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4))
+#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4))
+#define QRX_CTRL_MAX_INDEX 2047
+#define QRX_CTRL_QENA_REQ_S 0
+#define QRX_CTRL_QENA_REQ_M BIT(0)
+#define QRX_CTRL_QENA_STAT_S 2
+#define QRX_CTRL_QENA_STAT_M BIT(2)
+#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4))
+#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4))
+#define QRX_TAIL_MAX_INDEX 2047
+#define QRX_TAIL_TAIL_S 0
+#define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0)
+#define VPLAN_RX_QBASE(_VF) (0x00072000 + ((_VF) * 4))
+#define VPLAN_RX_QBASE_VFFIRSTQ_S 0
+#define VPLAN_RX_QBASE_VFFIRSTQ_M ICE_M(0x7FF, 0)
+#define VPLAN_RX_QBASE_VFNUMQ_S 16
+#define VPLAN_RX_QBASE_VFNUMQ_M ICE_M(0xFF, 16)
+#define VPLAN_RXQ_MAPENA(_VF) (0x00073000 + ((_VF) * 4))
+#define VPLAN_RXQ_MAPENA_RX_ENA_M BIT(0)
+#define VPLAN_TX_QBASE(_VF) (0x001D1800 + ((_VF) * 4))
+#define VPLAN_TX_QBASE_VFFIRSTQ_S 0
+#define VPLAN_TX_QBASE_VFFIRSTQ_M ICE_M(0x3FFF, 0)
+#define VPLAN_TX_QBASE_VFNUMQ_S 16
+#define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16)
+#define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4))
+#define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0)
+#define GL_MDET_RX 0x00294C00
+#define GL_MDET_RX_QNUM_S 0
+#define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0)
+#define GL_MDET_RX_VF_NUM_S 15
+#define GL_MDET_RX_VF_NUM_M ICE_M(0xFF, 15)
+#define GL_MDET_RX_PF_NUM_S 23
+#define GL_MDET_RX_PF_NUM_M ICE_M(0x7, 23)
+#define GL_MDET_RX_MAL_TYPE_S 26
+#define GL_MDET_RX_MAL_TYPE_M ICE_M(0x1F, 26)
+#define GL_MDET_RX_VALID_M BIT(31)
+#define GL_MDET_TX_PQM 0x002D2E00
+#define GL_MDET_TX_PQM_PF_NUM_S 0
+#define GL_MDET_TX_PQM_PF_NUM_M ICE_M(0x7, 0)
+#define GL_MDET_TX_PQM_VF_NUM_S 4
+#define GL_MDET_TX_PQM_VF_NUM_M ICE_M(0xFF, 4)
+#define GL_MDET_TX_PQM_QNUM_S 12
+#define GL_MDET_TX_PQM_QNUM_M ICE_M(0x3FFF, 12)
+#define GL_MDET_TX_PQM_MAL_TYPE_S 26
+#define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26)
+#define GL_MDET_TX_PQM_VALID_M BIT(31)
+#define GL_MDET_TX_TCLAN 0x000FC068
+#define GL_MDET_TX_TCLAN_QNUM_S 0
+#define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0)
+#define GL_MDET_TX_TCLAN_VF_NUM_S 15
+#define GL_MDET_TX_TCLAN_VF_NUM_M ICE_M(0xFF, 15)
+#define GL_MDET_TX_TCLAN_PF_NUM_S 23
+#define GL_MDET_TX_TCLAN_PF_NUM_M ICE_M(0x7, 23)
+#define GL_MDET_TX_TCLAN_MAL_TYPE_S 26
+#define GL_MDET_TX_TCLAN_MAL_TYPE_M ICE_M(0x1F, 26)
+#define GL_MDET_TX_TCLAN_VALID_M BIT(31)
+#define PF_MDET_RX 0x00294280
+#define PF_MDET_RX_VALID_M BIT(0)
+#define PF_MDET_TX_PQM 0x002D2C80
+#define PF_MDET_TX_PQM_VALID_M BIT(0)
+#define PF_MDET_TX_TCLAN 0x000FC000
+#define PF_MDET_TX_TCLAN_VALID_M BIT(0)
+#define VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4))
+#define VP_MDET_RX_VALID_M BIT(0)
+#define VP_MDET_TX_PQM(_VF) (0x002D2000 + ((_VF) * 4))
+#define VP_MDET_TX_PQM_VALID_M BIT(0)
+#define VP_MDET_TX_TCLAN(_VF) (0x000FB800 + ((_VF) * 4))
+#define VP_MDET_TX_TCLAN_VALID_M BIT(0)
+#define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4))
+#define VP_MDET_TX_TDPU_VALID_M BIT(0)
+#define GLNVM_FLA 0x000B6108
+#define GLNVM_FLA_LOCKED_M BIT(6)
+#define GLNVM_GENS 0x000B6100
+#define GLNVM_GENS_SR_SIZE_S 5
+#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5)
+#define GLNVM_ULD 0x000B6008
+#define GLNVM_ULD_CORER_DONE_M BIT(3)
+#define GLNVM_ULD_GLOBR_DONE_M BIT(4)
+#define GLPCI_CNF2 0x000BE004
+#define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1)
+#define PF_FUNC_RID 0x0009E880
+#define PF_FUNC_RID_FUNC_NUM_S 0
+#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0)
+#define PF_PCI_CIAA 0x0009E580
+#define PF_PCI_CIAA_VF_NUM_S 12
+#define PF_PCI_CIAD 0x0009E500
+#define GL_PWR_MODE_CTL 0x000B820C
+#define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30
+#define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30)
+#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8))
+#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8))
+#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8))
+#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8))
+#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8))
+#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8))
+#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8))
+#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8))
+#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8))
+#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8))
+#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8))
+#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8))
+#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8))
+#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8))
+#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8))
+#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8))
+#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8))
+#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8))
+#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8))
+#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8))
+#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8))
+#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8))
+#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8))
+#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8))
+#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8))
+#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8))
+#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8))
+#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8))
+#define GLPRT_PXOFFRXC(_i, _j) (0x00380500 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXOFFTXC(_i, _j) (0x00380F40 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXONRXC(_i, _j) (0x00380300 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXONTXC(_i, _j) (0x00380D40 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8))
+#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8))
+#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8))
+#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8))
+#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8))
+#define GLPRT_RXON2OFFCNT(_i, _j) (0x00380700 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8))
+#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8))
+#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8))
+#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8))
+#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8))
+#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8))
+#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8))
+#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8))
+#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8))
+#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4))
+#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4))
+#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8))
+#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8))
+#define PF_VT_PFALLOC_HIF 0x0009DD80
+#define VSIQF_HKEY_MAX_INDEX 12
+#define VSIQF_HLUT_MAX_INDEX 15
+#define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4))
+#define VFINT_DYN_CTLN_CLEARPBA_M BIT(1)
+#define PRTRPB_RDPC 0x000AC260
#endif /* _ICE_HW_AUTOGEN_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 068dbc7..2aac8f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -6,11 +6,11 @@
union ice_32byte_rx_desc {
struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
/* bit 0 of hdr_addr is DD bit */
- __le64 rsvd1;
- __le64 rsvd2;
+ __le64 rsvd1;
+ __le64 rsvd2;
} read;
struct {
struct {
@@ -20,7 +20,7 @@
} lo_dword;
union {
__le32 rss; /* RSS Hash */
- __le32 fd_id; /* Flow Director filter id */
+ __le32 fd_id; /* Flow Director filter ID */
} hi_dword;
} qword0;
struct {
@@ -99,21 +99,21 @@
ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3,
};
-/* RX Flex Descriptor
+/* Rx Flex Descriptor
* This descriptor is used instead of the legacy version descriptor when
* ice_rlan_ctx.adv_desc is set
*/
union ice_32b_rx_flex_desc {
struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
- /* bit 0 of hdr_addr is DD bit */
- __le64 rsvd1;
- __le64 rsvd2;
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ /* bit 0 of hdr_addr is DD bit */
+ __le64 rsvd1;
+ __le64 rsvd2;
} read;
struct {
/* Qword 0 */
- u8 rxdid; /* descriptor builder profile id */
+ u8 rxdid; /* descriptor builder profile ID */
u8 mir_id_umb_cast; /* mirror=[5:0], umb=[7:6] */
__le16 ptype_flex_flags0; /* ptype=[9:0], ff0=[15:10] */
__le16 pkt_len; /* [15:14] are reserved */
@@ -149,7 +149,7 @@
/* Rx Flex Descriptor NIC Profile
* This descriptor corresponds to RxDID 2 which contains
- * metadata fields for RSS, flow id and timestamp info
+ * metadata fields for RSS, flow ID and timestamp info
*/
struct ice_32b_rx_flex_desc_nic {
/* Qword 0 */
@@ -188,41 +188,43 @@
* with a specific metadata (profile 7 reserved for HW)
*/
enum ice_rxdid {
- ICE_RXDID_START = 0,
- ICE_RXDID_LEGACY_0 = ICE_RXDID_START,
- ICE_RXDID_LEGACY_1,
- ICE_RXDID_FLX_START,
- ICE_RXDID_FLEX_NIC = ICE_RXDID_FLX_START,
- ICE_RXDID_FLX_LAST = 63,
- ICE_RXDID_LAST = ICE_RXDID_FLX_LAST
+ ICE_RXDID_LEGACY_0 = 0,
+ ICE_RXDID_LEGACY_1 = 1,
+ ICE_RXDID_FLEX_NIC = 2,
+ ICE_RXDID_FLEX_NIC_2 = 6,
+ ICE_RXDID_HW = 7,
+ ICE_RXDID_LAST = 63,
};
/* Receive Flex Descriptor Rx opcode values */
#define ICE_RX_OPC_MDID 0x01
/* Receive Descriptor MDID values */
-#define ICE_RX_MDID_FLOW_ID_LOWER 5
-#define ICE_RX_MDID_FLOW_ID_HIGH 6
-#define ICE_RX_MDID_HASH_LOW 56
-#define ICE_RX_MDID_HASH_HIGH 57
+enum ice_flex_rx_mdid {
+ ICE_RX_MDID_FLOW_ID_LOWER = 5,
+ ICE_RX_MDID_FLOW_ID_HIGH,
+ ICE_RX_MDID_SRC_VSI = 19,
+ ICE_RX_MDID_HASH_LOW = 56,
+ ICE_RX_MDID_HASH_HIGH,
+};
-/* Rx Flag64 packet flag bits */
-enum ice_rx_flg64_bits {
- ICE_RXFLG_PKT_DSI = 0,
- ICE_RXFLG_EVLAN_x8100 = 15,
- ICE_RXFLG_EVLAN_x9100,
- ICE_RXFLG_VLAN_x8100,
- ICE_RXFLG_TNL_MAC = 22,
- ICE_RXFLG_TNL_VLAN,
- ICE_RXFLG_PKT_FRG,
- ICE_RXFLG_FIN = 32,
- ICE_RXFLG_SYN,
- ICE_RXFLG_RST,
- ICE_RXFLG_TNL0 = 38,
- ICE_RXFLG_TNL1,
- ICE_RXFLG_TNL2,
- ICE_RXFLG_UDP_GRE,
- ICE_RXFLG_RSVD = 63
+/* Rx/Tx Flag64 packet flag bits */
+enum ice_flg64_bits {
+ ICE_FLG_PKT_DSI = 0,
+ ICE_FLG_EVLAN_x8100 = 15,
+ ICE_FLG_EVLAN_x9100,
+ ICE_FLG_VLAN_x8100,
+ ICE_FLG_TNL_MAC = 22,
+ ICE_FLG_TNL_VLAN,
+ ICE_FLG_PKT_FRG,
+ ICE_FLG_FIN = 32,
+ ICE_FLG_SYN,
+ ICE_FLG_RST,
+ ICE_FLG_TNL0 = 38,
+ ICE_FLG_TNL1,
+ ICE_FLG_TNL2,
+ ICE_FLG_UDP_GRE,
+ ICE_FLG_RSVD = 63
};
/* for ice_32byte_rx_flex_desc.ptype_flexi_flags0 member */
@@ -254,6 +256,9 @@
#define ICE_RXQ_CTX_SIZE_DWORDS 8
#define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
+#define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS 22
+#define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS 5
+#define GLTCLAN_CQ_CNTX(i, CQ) (GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800))
/* RLAN Rx queue context data
*
@@ -272,19 +277,20 @@
u16 dbuf; /* bigger than needed, see above for reason */
#define ICE_RLAN_CTX_HBUF_S 6
u16 hbuf; /* bigger than needed, see above for reason */
- u8 dtype;
- u8 dsize;
- u8 crcstrip;
- u8 l2tsel;
- u8 hsplit_0;
- u8 hsplit_1;
- u8 showiv;
+ u8 dtype;
+ u8 dsize;
+ u8 crcstrip;
+ u8 l2tsel;
+ u8 hsplit_0;
+ u8 hsplit_1;
+ u8 showiv;
u32 rxmax; /* bigger than needed, see above for reason */
- u8 tphrdesc_ena;
- u8 tphwdesc_ena;
- u8 tphdata_ena;
- u8 tphhead_ena;
+ u8 tphrdesc_ena;
+ u8 tphwdesc_ena;
+ u8 tphdata_ena;
+ u8 tphhead_ena;
u16 lrxqthresh; /* bigger than needed, see above for reason */
+ u8 prefena; /* NOTE: normally must be set to 1 at init */
};
struct ice_ctx_ele {
@@ -317,7 +323,7 @@
ICE_RLAN_RX_HSPLIT_1_SPLIT_ALWAYS = 2,
};
-/* TX Descriptor */
+/* Tx Descriptor */
struct ice_tx_desc {
__le64 buf_addr; /* Address of descriptor's data buf */
__le64 cmd_type_offset_bsz;
@@ -337,11 +343,12 @@
ICE_TX_DESC_CMD_EOP = 0x0001,
ICE_TX_DESC_CMD_RS = 0x0002,
ICE_TX_DESC_CMD_IL2TAG1 = 0x0008,
- ICE_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */
- ICE_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */
- ICE_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */
- ICE_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */
- ICE_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */
+ ICE_TX_DESC_CMD_IIPT_IPV6 = 0x0020,
+ ICE_TX_DESC_CMD_IIPT_IPV4 = 0x0040,
+ ICE_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060,
+ ICE_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100,
+ ICE_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200,
+ ICE_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300,
};
#define ICE_TXD_QW1_OFFSET_S 16
@@ -411,34 +418,36 @@
struct ice_tlan_ctx {
#define ICE_TLAN_CTX_BASE_S 7
u64 base; /* base is defined in 128-byte units */
- u8 port_num;
+ u8 port_num;
u16 cgd_num; /* bigger than needed, see above for reason */
- u8 pf_num;
+ u8 pf_num;
u16 vmvf_num;
- u8 vmvf_type;
+ u8 vmvf_type;
+#define ICE_TLAN_CTX_VMVF_TYPE_VF 0
#define ICE_TLAN_CTX_VMVF_TYPE_VMQ 1
#define ICE_TLAN_CTX_VMVF_TYPE_PF 2
u16 src_vsi;
- u8 tsyn_ena;
- u8 alt_vlan;
+ u8 tsyn_ena;
+ u8 internal_usage_flag;
+ u8 alt_vlan;
u16 cpuid; /* bigger than needed, see above for reason */
- u8 wb_mode;
- u8 tphrd_desc;
- u8 tphrd;
- u8 tphwr_desc;
+ u8 wb_mode;
+ u8 tphrd_desc;
+ u8 tphrd;
+ u8 tphwr_desc;
u16 cmpq_id;
u16 qnum_in_func;
- u8 itr_notification_mode;
- u8 adjust_prof_id;
+ u8 itr_notification_mode;
+ u8 adjust_prof_id;
u32 qlen; /* bigger than needed, see above for reason */
- u8 quanta_prof_idx;
- u8 tso_ena;
+ u8 quanta_prof_idx;
+ u8 tso_ena;
u16 tso_qnum;
- u8 legacy_int;
- u8 drop_ena;
- u8 cache_prof_idx;
- u8 pkt_shaper_prof_idx;
- u8 int_q_state; /* width not needed - internal do not write */
+ u8 legacy_int;
+ u8 drop_ena;
+ u8 cache_prof_idx;
+ u8 pkt_shaper_prof_idx;
+ u8 int_q_state; /* width not needed - internal do not write */
};
/* macro to make the table lines short */
@@ -471,4 +480,18 @@
{
return ice_ptype_lkup[ptype];
}
+
+#define ICE_LINK_SPEED_UNKNOWN 0
+#define ICE_LINK_SPEED_10MBPS 10
+#define ICE_LINK_SPEED_100MBPS 100
+#define ICE_LINK_SPEED_1000MBPS 1000
+#define ICE_LINK_SPEED_2500MBPS 2500
+#define ICE_LINK_SPEED_5000MBPS 5000
+#define ICE_LINK_SPEED_10000MBPS 10000
+#define ICE_LINK_SPEED_20000MBPS 20000
+#define ICE_LINK_SPEED_25000MBPS 25000
+#define ICE_LINK_SPEED_40000MBPS 40000
+#define ICE_LINK_SPEED_50000MBPS 50000
+#define ICE_LINK_SPEED_100000MBPS 100000
+
#endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
new file mode 100644
index 0000000..cc75538
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -0,0 +1,3301 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
+
+/**
+ * ice_setup_rx_ctx - Configure a receive ring context
+ * @ring: The Rx ring to configure
+ *
+ * Configure the Rx descriptor ring in RLAN context.
+ */
+static int ice_setup_rx_ctx(struct ice_ring *ring)
+{
+ struct ice_vsi *vsi = ring->vsi;
+ struct ice_hw *hw = &vsi->back->hw;
+ u32 rxdid = ICE_RXDID_FLEX_NIC;
+ struct ice_rlan_ctx rlan_ctx;
+ u32 regval;
+ u16 pf_q;
+ int err;
+
+ /* what is Rx queue number in global space of 2K Rx queues */
+ pf_q = vsi->rxq_map[ring->q_index];
+
+ /* clear the context structure first */
+ memset(&rlan_ctx, 0, sizeof(rlan_ctx));
+
+ rlan_ctx.base = ring->dma >> 7;
+
+ rlan_ctx.qlen = ring->count;
+
+ /* Receive Packet Data Buffer Size.
+ * The Packet Data Buffer Size is defined in 128 byte units.
+ */
+ rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S;
+
+ /* use 32 byte descriptors */
+ rlan_ctx.dsize = 1;
+
+ /* Strip the Ethernet CRC bytes before the packet is posted to host
+ * memory.
+ */
+ rlan_ctx.crcstrip = 1;
+
+ /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */
+ rlan_ctx.l2tsel = 1;
+
+ rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT;
+ rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT;
+ rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT;
+
+ /* This controls whether VLAN is stripped from inner headers
+ * The VLAN in the inner L2 header is stripped to the receive
+ * descriptor if enabled by this flag.
+ */
+ rlan_ctx.showiv = 0;
+
+ /* Max packet size for this queue - must not be set to a larger value
+ * than 5 x DBUF
+ */
+ rlan_ctx.rxmax = min_t(u16, vsi->max_frame,
+ ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len);
+
+ /* Rx queue threshold in units of 64 */
+ rlan_ctx.lrxqthresh = 1;
+
+ /* Enable Flexible Descriptors in the queue context which
+ * allows this driver to select a specific receive descriptor format
+ */
+ if (vsi->type != ICE_VSI_VF) {
+ regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
+ regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
+ QRXFLXP_CNTXT_RXDID_IDX_M;
+
+ /* increasing context priority to pick up profile ID;
+ * default is 0x01; setting to 0x03 to ensure profile
+ * is programming if prev context is of same priority
+ */
+ regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) &
+ QRXFLXP_CNTXT_RXDID_PRIO_M;
+
+ wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
+ }
+
+ /* Absolute queue number out of 2K needs to be passed */
+ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
+ if (err) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+ pf_q, err);
+ return -EIO;
+ }
+
+ if (vsi->type == ICE_VSI_VF)
+ return 0;
+
+ /* init queue specific tail register */
+ ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
+ writel(0, ring->tail);
+ ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
+
+ return 0;
+}
+
+/**
+ * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
+ * @ring: The Tx ring to configure
+ * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized
+ * @pf_q: queue index in the PF space
+ *
+ * Configure the Tx descriptor ring in TLAN context.
+ */
+static void
+ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
+{
+ struct ice_vsi *vsi = ring->vsi;
+ struct ice_hw *hw = &vsi->back->hw;
+
+ tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S;
+
+ tlan_ctx->port_num = vsi->port_info->lport;
+
+ /* Transmit Queue Length */
+ tlan_ctx->qlen = ring->count;
+
+ ice_set_cgd_num(tlan_ctx, ring);
+
+ /* PF number */
+ tlan_ctx->pf_num = hw->pf_id;
+
+ /* queue belongs to a specific VSI type
+ * VF / VM index should be programmed per vmvf_type setting:
+ * for vmvf_type = VF, it is VF number between 0-256
+ * for vmvf_type = VM, it is VM number between 0-767
+ * for PF or EMP this field should be set to zero
+ */
+ switch (vsi->type) {
+ case ICE_VSI_LB:
+ /* fall through */
+ case ICE_VSI_PF:
+ tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
+ break;
+ case ICE_VSI_VF:
+ /* Firmware expects vmvf_num to be absolute VF ID */
+ tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id;
+ tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
+ break;
+ default:
+ return;
+ }
+
+ /* make sure the context is associated with the right VSI */
+ tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx);
+
+ tlan_ctx->tso_ena = ICE_TX_LEGACY;
+ tlan_ctx->tso_qnum = pf_q;
+
+ /* Legacy or Advanced Host Interface:
+ * 0: Advanced Host Interface
+ * 1: Legacy Host Interface
+ */
+ tlan_ctx->legacy_int = ICE_TX_LEGACY;
+}
+
+/**
+ * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled
+ * @pf: the PF being configured
+ * @pf_q: the PF queue
+ * @ena: enable or disable state of the queue
+ *
+ * This routine will wait for the given Rx queue of the PF to reach the
+ * enabled or disabled state.
+ * Returns -ETIMEDOUT in case of failing to reach the requested state after
+ * multiple retries; else will return 0 in case of success.
+ */
+static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
+{
+ int i;
+
+ for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) {
+ if (ena == !!(rd32(&pf->hw, QRX_CTRL(pf_q)) &
+ QRX_CTRL_QENA_STAT_M))
+ return 0;
+
+ usleep_range(20, 40);
+ }
+
+ return -ETIMEDOUT;
+}
+
+/**
+ * ice_vsi_ctrl_rx_ring - Start or stop a VSI's Rx ring
+ * @vsi: the VSI being configured
+ * @ena: start or stop the Rx rings
+ * @rxq_idx: Rx queue index
+ */
+#ifndef CONFIG_PCI_IOV
+static
+#endif /* !CONFIG_PCI_IOV */
+int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx)
+{
+ int pf_q = vsi->rxq_map[rxq_idx];
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ int ret = 0;
+ u32 rx_reg;
+
+ rx_reg = rd32(hw, QRX_CTRL(pf_q));
+
+ /* Skip if the queue is already in the requested state */
+ if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
+ return 0;
+
+ /* turn on/off the queue */
+ if (ena)
+ rx_reg |= QRX_CTRL_QENA_REQ_M;
+ else
+ rx_reg &= ~QRX_CTRL_QENA_REQ_M;
+ wr32(hw, QRX_CTRL(pf_q), rx_reg);
+
+ /* wait for the change to finish */
+ ret = ice_pf_rxq_wait(pf, pf_q, ena);
+ if (ret)
+ dev_err(&pf->pdev->dev,
+ "VSI idx %d Rx ring %d %sable timeout\n",
+ vsi->idx, pf_q, (ena ? "en" : "dis"));
+
+ return ret;
+}
+
+/**
+ * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings
+ * @vsi: the VSI being configured
+ * @ena: start or stop the Rx rings
+ */
+static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena)
+{
+ int i, ret = 0;
+
+ for (i = 0; i < vsi->num_rxq; i++) {
+ ret = ice_vsi_ctrl_rx_ring(vsi, ena, i);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/**
+ * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the VSI
+ * @vsi: VSI pointer
+ *
+ * On error: returns error code (negative)
+ * On success: returns 0
+ */
+static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+
+ /* allocate memory for both Tx and Rx ring pointers */
+ vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
+ sizeof(*vsi->tx_rings), GFP_KERNEL);
+ if (!vsi->tx_rings)
+ return -ENOMEM;
+
+ vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
+ sizeof(*vsi->rx_rings), GFP_KERNEL);
+ if (!vsi->rx_rings)
+ goto err_rings;
+
+ vsi->txq_map = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
+ sizeof(*vsi->txq_map), GFP_KERNEL);
+
+ if (!vsi->txq_map)
+ goto err_txq_map;
+
+ vsi->rxq_map = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
+ sizeof(*vsi->rxq_map), GFP_KERNEL);
+ if (!vsi->rxq_map)
+ goto err_rxq_map;
+
+
+ /* There is no need to allocate q_vectors for a loopback VSI. */
+ if (vsi->type == ICE_VSI_LB)
+ return 0;
+
+ /* allocate memory for q_vector pointers */
+ vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, vsi->num_q_vectors,
+ sizeof(*vsi->q_vectors), GFP_KERNEL);
+ if (!vsi->q_vectors)
+ goto err_vectors;
+
+ return 0;
+
+err_vectors:
+ devm_kfree(&pf->pdev->dev, vsi->rxq_map);
+err_rxq_map:
+ devm_kfree(&pf->pdev->dev, vsi->txq_map);
+err_txq_map:
+ devm_kfree(&pf->pdev->dev, vsi->rx_rings);
+err_rings:
+ devm_kfree(&pf->pdev->dev, vsi->tx_rings);
+ return -ENOMEM;
+}
+
+/**
+ * ice_vsi_set_num_desc - Set number of descriptors for queues on this VSI
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
+{
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ /* fall through */
+ case ICE_VSI_LB:
+ vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC;
+ vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC;
+ break;
+ default:
+ dev_dbg(&vsi->back->pdev->dev,
+ "Not setting number of Tx/Rx descriptors for VSI type %d\n",
+ vsi->type);
+ break;
+ }
+}
+
+/**
+ * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
+ * @vsi: the VSI being configured
+ * @vf_id: ID of the VF being configured
+ *
+ * Return 0 on success and a negative value on error
+ */
+static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_vf *vf = NULL;
+
+ if (vsi->type == ICE_VSI_VF)
+ vsi->vf_id = vf_id;
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ vsi->alloc_txq = min_t(int, ice_get_avail_txq_count(pf),
+ num_online_cpus());
+
+ pf->num_lan_tx = vsi->alloc_txq;
+
+ /* only 1 Rx queue unless RSS is enabled */
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ vsi->alloc_rxq = 1;
+ else
+ vsi->alloc_rxq = min_t(int, ice_get_avail_rxq_count(pf),
+ num_online_cpus());
+
+ pf->num_lan_rx = vsi->alloc_rxq;
+
+ vsi->num_q_vectors = max_t(int, vsi->alloc_rxq, vsi->alloc_txq);
+ break;
+ case ICE_VSI_VF:
+ vf = &pf->vf[vsi->vf_id];
+ vsi->alloc_txq = vf->num_vf_qs;
+ vsi->alloc_rxq = vf->num_vf_qs;
+ /* pf->num_vf_msix includes (VF miscellaneous vector +
+ * data queue interrupts). Since vsi->num_q_vectors is number
+ * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the
+ * original vector count
+ */
+ vsi->num_q_vectors = pf->num_vf_msix - ICE_NONQ_VECS_VF;
+ break;
+ case ICE_VSI_LB:
+ vsi->alloc_txq = 1;
+ vsi->alloc_rxq = 1;
+ break;
+ default:
+ dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
+ break;
+ }
+
+ ice_vsi_set_num_desc(vsi);
+}
+
+/**
+ * ice_get_free_slot - get the next non-NULL location index in array
+ * @array: array to search
+ * @size: size of the array
+ * @curr: last known occupied index to be used as a search hint
+ *
+ * void * is being used to keep the functionality generic. This lets us use this
+ * function on any array of pointers.
+ */
+static int ice_get_free_slot(void *array, int size, int curr)
+{
+ int **tmp_array = (int **)array;
+ int next;
+
+ if (curr < (size - 1) && !tmp_array[curr + 1]) {
+ next = curr + 1;
+ } else {
+ int i = 0;
+
+ while ((i < size) && (tmp_array[i]))
+ i++;
+ if (i == size)
+ next = ICE_NO_VSI;
+ else
+ next = i;
+ }
+ return next;
+}
+
+/**
+ * ice_vsi_delete - delete a VSI from the switch
+ * @vsi: pointer to VSI being removed
+ */
+void ice_vsi_delete(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_vsi_ctx *ctxt;
+ enum ice_status status;
+
+ ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return;
+
+ if (vsi->type == ICE_VSI_VF)
+ ctxt->vf_num = vsi->vf_id;
+ ctxt->vsi_num = vsi->vsi_num;
+
+ memcpy(&ctxt->info, &vsi->info, sizeof(ctxt->info));
+
+ status = ice_free_vsi(&pf->hw, vsi->idx, ctxt, false, NULL);
+ if (status)
+ dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n",
+ vsi->vsi_num);
+
+ devm_kfree(&pf->pdev->dev, ctxt);
+}
+
+/**
+ * ice_vsi_free_arrays - De-allocate queue and vector pointer arrays for the VSI
+ * @vsi: pointer to VSI being cleared
+ */
+static void ice_vsi_free_arrays(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+
+ /* free the ring and vector containers */
+ if (vsi->q_vectors) {
+ devm_kfree(&pf->pdev->dev, vsi->q_vectors);
+ vsi->q_vectors = NULL;
+ }
+ if (vsi->tx_rings) {
+ devm_kfree(&pf->pdev->dev, vsi->tx_rings);
+ vsi->tx_rings = NULL;
+ }
+ if (vsi->rx_rings) {
+ devm_kfree(&pf->pdev->dev, vsi->rx_rings);
+ vsi->rx_rings = NULL;
+ }
+ if (vsi->txq_map) {
+ devm_kfree(&pf->pdev->dev, vsi->txq_map);
+ vsi->txq_map = NULL;
+ }
+ if (vsi->rxq_map) {
+ devm_kfree(&pf->pdev->dev, vsi->rxq_map);
+ vsi->rxq_map = NULL;
+ }
+}
+
+/**
+ * ice_vsi_clear - clean up and deallocate the provided VSI
+ * @vsi: pointer to VSI being cleared
+ *
+ * This deallocates the VSI's queue resources, removes it from the PF's
+ * VSI array if necessary, and deallocates the VSI
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_vsi_clear(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = NULL;
+
+ if (!vsi)
+ return 0;
+
+ if (!vsi->back)
+ return -EINVAL;
+
+ pf = vsi->back;
+
+ if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) {
+ dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n",
+ vsi->idx);
+ return -EINVAL;
+ }
+
+ mutex_lock(&pf->sw_mutex);
+ /* updates the PF for this cleared VSI */
+
+ pf->vsi[vsi->idx] = NULL;
+ if (vsi->idx < pf->next_vsi)
+ pf->next_vsi = vsi->idx;
+
+ ice_vsi_free_arrays(vsi);
+ mutex_unlock(&pf->sw_mutex);
+ devm_kfree(&pf->pdev->dev, vsi);
+
+ return 0;
+}
+
+/**
+ * ice_msix_clean_rings - MSIX mode Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
+{
+ struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
+
+ if (!q_vector->tx.ring && !q_vector->rx.ring)
+ return IRQ_HANDLED;
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * ice_vsi_alloc - Allocates the next available struct VSI in the PF
+ * @pf: board private structure
+ * @type: type of VSI
+ * @vf_id: ID of the VF being configured
+ *
+ * returns a pointer to a VSI on success, NULL on failure.
+ */
+static struct ice_vsi *
+ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type, u16 vf_id)
+{
+ struct ice_vsi *vsi = NULL;
+
+ /* Need to protect the allocation of the VSIs at the PF level */
+ mutex_lock(&pf->sw_mutex);
+
+ /* If we have already allocated our maximum number of VSIs,
+ * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index
+ * is available to be populated
+ */
+ if (pf->next_vsi == ICE_NO_VSI) {
+ dev_dbg(&pf->pdev->dev, "out of VSI slots!\n");
+ goto unlock_pf;
+ }
+
+ vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL);
+ if (!vsi)
+ goto unlock_pf;
+
+ vsi->type = type;
+ vsi->back = pf;
+ set_bit(__ICE_DOWN, vsi->state);
+
+ vsi->idx = pf->next_vsi;
+
+ if (type == ICE_VSI_VF)
+ ice_vsi_set_num_qs(vsi, vf_id);
+ else
+ ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID);
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ if (ice_vsi_alloc_arrays(vsi))
+ goto err_rings;
+
+ /* Setup default MSIX irq handler for VSI */
+ vsi->irq_handler = ice_msix_clean_rings;
+ break;
+ case ICE_VSI_VF:
+ if (ice_vsi_alloc_arrays(vsi))
+ goto err_rings;
+ break;
+ case ICE_VSI_LB:
+ if (ice_vsi_alloc_arrays(vsi))
+ goto err_rings;
+ break;
+ default:
+ dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
+ goto unlock_pf;
+ }
+
+ /* fill VSI slot in the PF struct */
+ pf->vsi[pf->next_vsi] = vsi;
+
+ /* prepare pf->next_vsi for next use */
+ pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
+ pf->next_vsi);
+ goto unlock_pf;
+
+err_rings:
+ devm_kfree(&pf->pdev->dev, vsi);
+ vsi = NULL;
+unlock_pf:
+ mutex_unlock(&pf->sw_mutex);
+ return vsi;
+}
+
+/**
+ * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
+ * @qs_cfg: gathered variables needed for PF->VSI queues assignment
+ *
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
+ */
+static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
+{
+ int offset, i;
+
+ mutex_lock(qs_cfg->qs_mutex);
+ offset = bitmap_find_next_zero_area(qs_cfg->pf_map, qs_cfg->pf_map_size,
+ 0, qs_cfg->q_count, 0);
+ if (offset >= qs_cfg->pf_map_size) {
+ mutex_unlock(qs_cfg->qs_mutex);
+ return -ENOMEM;
+ }
+
+ bitmap_set(qs_cfg->pf_map, offset, qs_cfg->q_count);
+ for (i = 0; i < qs_cfg->q_count; i++)
+ qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = i + offset;
+ mutex_unlock(qs_cfg->qs_mutex);
+
+ return 0;
+}
+
+/**
+ * __ice_vsi_get_qs_sc - Assign a scattered queues from PF to VSI
+ * @qs_cfg: gathered variables needed for pf->vsi queues assignment
+ *
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
+ */
+static int __ice_vsi_get_qs_sc(struct ice_qs_cfg *qs_cfg)
+{
+ int i, index = 0;
+
+ mutex_lock(qs_cfg->qs_mutex);
+ for (i = 0; i < qs_cfg->q_count; i++) {
+ index = find_next_zero_bit(qs_cfg->pf_map,
+ qs_cfg->pf_map_size, index);
+ if (index >= qs_cfg->pf_map_size)
+ goto err_scatter;
+ set_bit(index, qs_cfg->pf_map);
+ qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = index;
+ }
+ mutex_unlock(qs_cfg->qs_mutex);
+
+ return 0;
+err_scatter:
+ for (index = 0; index < i; index++) {
+ clear_bit(qs_cfg->vsi_map[index], qs_cfg->pf_map);
+ qs_cfg->vsi_map[index + qs_cfg->vsi_map_offset] = 0;
+ }
+ mutex_unlock(qs_cfg->qs_mutex);
+
+ return -ENOMEM;
+}
+
+/**
+ * __ice_vsi_get_qs - helper function for assigning queues from PF to VSI
+ * @qs_cfg: gathered variables needed for pf->vsi queues assignment
+ *
+ * This function first tries to find contiguous space. If it is not successful,
+ * it tries with the scatter approach.
+ *
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
+ */
+static int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg)
+{
+ int ret = 0;
+
+ ret = __ice_vsi_get_qs_contig(qs_cfg);
+ if (ret) {
+ /* contig failed, so try with scatter approach */
+ qs_cfg->mapping_mode = ICE_VSI_MAP_SCATTER;
+ qs_cfg->q_count = min_t(u16, qs_cfg->q_count,
+ qs_cfg->scatter_count);
+ ret = __ice_vsi_get_qs_sc(qs_cfg);
+ }
+ return ret;
+}
+
+/**
+ * ice_vsi_get_qs - Assign queues from PF to VSI
+ * @vsi: the VSI to assign queues to
+ *
+ * Returns 0 on success and a negative value on error
+ */
+static int ice_vsi_get_qs(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_qs_cfg tx_qs_cfg = {
+ .qs_mutex = &pf->avail_q_mutex,
+ .pf_map = pf->avail_txqs,
+ .pf_map_size = pf->max_pf_txqs,
+ .q_count = vsi->alloc_txq,
+ .scatter_count = ICE_MAX_SCATTER_TXQS,
+ .vsi_map = vsi->txq_map,
+ .vsi_map_offset = 0,
+ .mapping_mode = vsi->tx_mapping_mode
+ };
+ struct ice_qs_cfg rx_qs_cfg = {
+ .qs_mutex = &pf->avail_q_mutex,
+ .pf_map = pf->avail_rxqs,
+ .pf_map_size = pf->max_pf_rxqs,
+ .q_count = vsi->alloc_rxq,
+ .scatter_count = ICE_MAX_SCATTER_RXQS,
+ .vsi_map = vsi->rxq_map,
+ .vsi_map_offset = 0,
+ .mapping_mode = vsi->rx_mapping_mode
+ };
+ int ret = 0;
+
+ vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG;
+ vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG;
+
+ ret = __ice_vsi_get_qs(&tx_qs_cfg);
+ if (!ret)
+ ret = __ice_vsi_get_qs(&rx_qs_cfg);
+
+ return ret;
+}
+
+/**
+ * ice_vsi_put_qs - Release queues from VSI to PF
+ * @vsi: the VSI that is going to release queues
+ */
+void ice_vsi_put_qs(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ int i;
+
+ mutex_lock(&pf->avail_q_mutex);
+
+ for (i = 0; i < vsi->alloc_txq; i++) {
+ clear_bit(vsi->txq_map[i], pf->avail_txqs);
+ vsi->txq_map[i] = ICE_INVAL_Q_INDEX;
+ }
+
+ for (i = 0; i < vsi->alloc_rxq; i++) {
+ clear_bit(vsi->rxq_map[i], pf->avail_rxqs);
+ vsi->rxq_map[i] = ICE_INVAL_Q_INDEX;
+ }
+
+ mutex_unlock(&pf->avail_q_mutex);
+}
+
+/**
+ * ice_is_safe_mode
+ * @pf: pointer to the PF struct
+ *
+ * returns true if driver is in safe mode, false otherwise
+ */
+bool ice_is_safe_mode(struct ice_pf *pf)
+{
+ return !test_bit(ICE_FLAG_ADV_FEATURES, pf->flags);
+}
+
+/**
+ * ice_rss_clean - Delete RSS related VSI structures that hold user inputs
+ * @vsi: the VSI being removed
+ */
+static void ice_rss_clean(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf;
+
+ pf = vsi->back;
+
+ if (vsi->rss_hkey_user)
+ devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user);
+ if (vsi->rss_lut_user)
+ devm_kfree(&pf->pdev->dev, vsi->rss_lut_user);
+}
+
+/**
+ * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
+{
+ struct ice_hw_common_caps *cap;
+ struct ice_pf *pf = vsi->back;
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+ vsi->rss_size = 1;
+ return;
+ }
+
+ cap = &pf->hw.func_caps.common_cap;
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ /* PF VSI will inherit RSS instance of PF */
+ vsi->rss_table_size = cap->rss_table_size;
+ vsi->rss_size = min_t(int, num_online_cpus(),
+ BIT(cap->rss_table_entry_width));
+ vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF;
+ break;
+ case ICE_VSI_VF:
+ /* VF VSI will gets a small RSS table
+ * For VSI_LUT, LUT size should be set to 64 bytes
+ */
+ vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE;
+ vsi->rss_size = min_t(int, num_online_cpus(),
+ BIT(cap->rss_table_entry_width));
+ vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI;
+ break;
+ case ICE_VSI_LB:
+ break;
+ default:
+ dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n",
+ vsi->type);
+ break;
+ }
+}
+
+/**
+ * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI
+ * @ctxt: the VSI context being set
+ *
+ * This initializes a default VSI context for all sections except the Queues.
+ */
+static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
+{
+ u32 table = 0;
+
+ memset(&ctxt->info, 0, sizeof(ctxt->info));
+ /* VSI's should be allocated from shared pool */
+ ctxt->alloc_from_pool = true;
+ /* Src pruning enabled by default */
+ ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE;
+ /* Traffic from VSI can be sent to LAN */
+ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA;
+ /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy
+ * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all
+ * packets untagged/tagged.
+ */
+ ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL &
+ ICE_AQ_VSI_VLAN_MODE_M) >>
+ ICE_AQ_VSI_VLAN_MODE_S);
+ /* Have 1:1 UP mapping for both ingress/egress tables */
+ table |= ICE_UP_TABLE_TRANSLATE(0, 0);
+ table |= ICE_UP_TABLE_TRANSLATE(1, 1);
+ table |= ICE_UP_TABLE_TRANSLATE(2, 2);
+ table |= ICE_UP_TABLE_TRANSLATE(3, 3);
+ table |= ICE_UP_TABLE_TRANSLATE(4, 4);
+ table |= ICE_UP_TABLE_TRANSLATE(5, 5);
+ table |= ICE_UP_TABLE_TRANSLATE(6, 6);
+ table |= ICE_UP_TABLE_TRANSLATE(7, 7);
+ ctxt->info.ingress_table = cpu_to_le32(table);
+ ctxt->info.egress_table = cpu_to_le32(table);
+ /* Have 1:1 UP mapping for outer to inner UP table */
+ ctxt->info.outer_up_table = cpu_to_le32(table);
+ /* No Outer tag support outer_tag_flags remains to zero */
+}
+
+/**
+ * ice_vsi_setup_q_map - Setup a VSI queue map
+ * @vsi: the VSI being configured
+ * @ctxt: VSI context structure
+ */
+static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
+{
+ u16 offset = 0, qmap = 0, tx_count = 0;
+ u16 qcount_tx = vsi->alloc_txq;
+ u16 qcount_rx = vsi->alloc_rxq;
+ u16 tx_numq_tc, rx_numq_tc;
+ u16 pow = 0, max_rss = 0;
+ bool ena_tc0 = false;
+ u8 netdev_tc = 0;
+ int i;
+
+ /* at least TC0 should be enabled by default */
+ if (vsi->tc_cfg.numtc) {
+ if (!(vsi->tc_cfg.ena_tc & BIT(0)))
+ ena_tc0 = true;
+ } else {
+ ena_tc0 = true;
+ }
+
+ if (ena_tc0) {
+ vsi->tc_cfg.numtc++;
+ vsi->tc_cfg.ena_tc |= 1;
+ }
+
+ rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+ if (!rx_numq_tc)
+ rx_numq_tc = 1;
+ tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc;
+ if (!tx_numq_tc)
+ tx_numq_tc = 1;
+
+ /* TC mapping is a function of the number of Rx queues assigned to the
+ * VSI for each traffic class and the offset of these queues.
+ * The first 10 bits are for queue offset for TC0, next 4 bits for no:of
+ * queues allocated to TC0. No:of queues is a power-of-2.
+ *
+ * If TC is not enabled, the queue offset is set to 0, and allocate one
+ * queue, this way, traffic for the given TC will be sent to the default
+ * queue.
+ *
+ * Setup number and offset of Rx queues for all TCs for the VSI
+ */
+
+ qcount_rx = rx_numq_tc;
+
+ /* qcount will change if RSS is enabled */
+ if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
+ if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) {
+ if (vsi->type == ICE_VSI_PF)
+ max_rss = ICE_MAX_LG_RSS_QS;
+ else
+ max_rss = ICE_MAX_SMALL_RSS_QS;
+ qcount_rx = min_t(int, rx_numq_tc, max_rss);
+ qcount_rx = min_t(int, qcount_rx, vsi->rss_size);
+ }
+ }
+
+ /* find the (rounded up) power-of-2 of qcount */
+ pow = order_base_2(qcount_rx);
+
+ ice_for_each_traffic_class(i) {
+ if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
+ /* TC is not enabled */
+ vsi->tc_cfg.tc_info[i].qoffset = 0;
+ vsi->tc_cfg.tc_info[i].qcount_rx = 1;
+ vsi->tc_cfg.tc_info[i].qcount_tx = 1;
+ vsi->tc_cfg.tc_info[i].netdev_tc = 0;
+ ctxt->info.tc_mapping[i] = 0;
+ continue;
+ }
+
+ /* TC is enabled */
+ vsi->tc_cfg.tc_info[i].qoffset = offset;
+ vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx;
+ vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc;
+ vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++;
+
+ qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
+ ICE_AQ_VSI_TC_Q_OFFSET_M) |
+ ((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
+ ICE_AQ_VSI_TC_Q_NUM_M);
+ offset += qcount_rx;
+ tx_count += tx_numq_tc;
+ ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
+ }
+
+ /* if offset is non-zero, means it is calculated correctly based on
+ * enabled TCs for a given VSI otherwise qcount_rx will always
+ * be correct and non-zero because it is based off - VSI's
+ * allocated Rx queues which is at least 1 (hence qcount_tx will be
+ * at least 1)
+ */
+ if (offset)
+ vsi->num_rxq = offset;
+ else
+ vsi->num_rxq = qcount_rx;
+
+ vsi->num_txq = tx_count;
+
+ if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
+ dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
+ /* since there is a chance that num_rxq could have been changed
+ * in the above for loop, make num_txq equal to num_rxq.
+ */
+ vsi->num_txq = vsi->num_rxq;
+ }
+
+ /* Rx queue mapping */
+ ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG);
+ /* q_mapping buffer holds the info for the first queue allocated for
+ * this VSI in the PF space and also the number of queues associated
+ * with this VSI.
+ */
+ ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]);
+ ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq);
+}
+
+/**
+ * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI
+ * @ctxt: the VSI context being set
+ * @vsi: the VSI being configured
+ */
+static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
+{
+ u8 lut_type, hash_type;
+ struct ice_pf *pf;
+
+ pf = vsi->back;
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ /* PF VSI will inherit RSS instance of PF */
+ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF;
+ hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
+ break;
+ case ICE_VSI_VF:
+ /* VF VSI will gets a small RSS table which is a VSI LUT type */
+ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
+ hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
+ break;
+ case ICE_VSI_LB:
+ dev_dbg(&pf->pdev->dev, "Unsupported VSI type %d\n", vsi->type);
+ return;
+ default:
+ dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
+ return;
+ }
+
+ ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
+ ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
+ ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
+ ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+}
+
+/**
+ * ice_vsi_init - Create and initialize a VSI
+ * @vsi: the VSI being configured
+ *
+ * This initializes a VSI context depending on the VSI type to be added and
+ * passes it down to the add_vsi aq command to create a new VSI.
+ */
+static int ice_vsi_init(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ struct ice_vsi_ctx *ctxt;
+ int ret = 0;
+
+ ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ ctxt->info = vsi->info;
+ switch (vsi->type) {
+ case ICE_VSI_LB:
+ /* fall through */
+ case ICE_VSI_PF:
+ ctxt->flags = ICE_AQ_VSI_TYPE_PF;
+ break;
+ case ICE_VSI_VF:
+ ctxt->flags = ICE_AQ_VSI_TYPE_VF;
+ /* VF number here is the absolute VF number (0-255) */
+ ctxt->vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ ice_set_dflt_vsi_ctx(ctxt);
+ /* if the switch is in VEB mode, allow VSI loopback */
+ if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
+ ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+
+ /* Set LUT type and HASH type if RSS is enabled */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_set_rss_vsi_ctx(ctxt, vsi);
+
+ ctxt->info.sw_id = vsi->port_info->sw_id;
+ ice_vsi_setup_q_map(vsi, ctxt);
+
+ /* Enable MAC Antispoof with new VSI being initialized or updated */
+ if (vsi->type == ICE_VSI_VF && pf->vf[vsi->vf_id].spoofchk) {
+ ctxt->info.valid_sections |=
+ cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+ ctxt->info.sec_flags |=
+ ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+ }
+
+ /* Allow control frames out of main VSI */
+ if (vsi->type == ICE_VSI_PF) {
+ ctxt->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
+ ctxt->info.valid_sections |=
+ cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+ }
+
+ ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Add VSI failed, err %d\n", ret);
+ return -EIO;
+ }
+
+ /* keep context for update VSI operations */
+ vsi->info = ctxt->info;
+
+ /* record VSI number returned */
+ vsi->vsi_num = ctxt->vsi_num;
+
+ devm_kfree(&pf->pdev->dev, ctxt);
+ return ret;
+}
+
+/**
+ * ice_free_q_vector - Free memory allocated for a specific interrupt vector
+ * @vsi: VSI having the memory freed
+ * @v_idx: index of the vector to be freed
+ */
+static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
+{
+ struct ice_q_vector *q_vector;
+ struct ice_pf *pf = vsi->back;
+ struct ice_ring *ring;
+
+ if (!vsi->q_vectors[v_idx]) {
+ dev_dbg(&pf->pdev->dev, "Queue vector at index %d not found\n",
+ v_idx);
+ return;
+ }
+ q_vector = vsi->q_vectors[v_idx];
+
+ ice_for_each_ring(ring, q_vector->tx)
+ ring->q_vector = NULL;
+ ice_for_each_ring(ring, q_vector->rx)
+ ring->q_vector = NULL;
+
+ /* only VSI with an associated netdev is set up with NAPI */
+ if (vsi->netdev)
+ netif_napi_del(&q_vector->napi);
+
+ devm_kfree(&pf->pdev->dev, q_vector);
+ vsi->q_vectors[v_idx] = NULL;
+}
+
+/**
+ * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors
+ * @vsi: the VSI having memory freed
+ */
+void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
+{
+ int v_idx;
+
+ ice_for_each_q_vector(vsi, v_idx)
+ ice_free_q_vector(vsi, v_idx);
+}
+
+/**
+ * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @vsi: the VSI being configured
+ * @v_idx: index of the vector in the VSI struct
+ *
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
+ */
+static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_q_vector *q_vector;
+
+ /* allocate q_vector */
+ q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL);
+ if (!q_vector)
+ return -ENOMEM;
+
+ q_vector->vsi = vsi;
+ q_vector->v_idx = v_idx;
+ if (vsi->type == ICE_VSI_VF)
+ goto out;
+ /* only set affinity_mask if the CPU is online */
+ if (cpu_online(v_idx))
+ cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
+
+ /* This will not be called in the driver load path because the netdev
+ * will not be created yet. All other cases with register the NAPI
+ * handler here (i.e. resume, reset/rebuild, etc.)
+ */
+ if (vsi->netdev)
+ netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll,
+ NAPI_POLL_WEIGHT);
+
+out:
+ /* tie q_vector and VSI together */
+ vsi->q_vectors[v_idx] = q_vector;
+
+ return 0;
+}
+
+/**
+ * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @vsi: the VSI being configured
+ *
+ * We allocate one q_vector per queue interrupt. If allocation fails we
+ * return -ENOMEM.
+ */
+static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ int v_idx = 0, num_q_vectors;
+ int err;
+
+ if (vsi->q_vectors[0]) {
+ dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n",
+ vsi->vsi_num);
+ return -EEXIST;
+ }
+
+ num_q_vectors = vsi->num_q_vectors;
+
+ for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
+ err = ice_vsi_alloc_q_vector(vsi, v_idx);
+ if (err)
+ goto err_out;
+ }
+
+ return 0;
+
+err_out:
+ while (v_idx--)
+ ice_free_q_vector(vsi, v_idx);
+
+ dev_err(&pf->pdev->dev,
+ "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
+ vsi->num_q_vectors, vsi->vsi_num, err);
+ vsi->num_q_vectors = 0;
+ return err;
+}
+
+/**
+ * ice_vsi_setup_vector_base - Set up the base vector for the given VSI
+ * @vsi: ptr to the VSI
+ *
+ * This should only be called after ice_vsi_alloc() which allocates the
+ * corresponding SW VSI structure and initializes num_queue_pairs for the
+ * newly allocated VSI.
+ *
+ * Returns 0 on success or negative on failure
+ */
+static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ u16 num_q_vectors;
+
+ /* SRIOV doesn't grab irq_tracker entries for each VSI */
+ if (vsi->type == ICE_VSI_VF)
+ return 0;
+
+ if (vsi->base_vector) {
+ dev_dbg(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n",
+ vsi->vsi_num, vsi->base_vector);
+ return -EEXIST;
+ }
+
+ num_q_vectors = vsi->num_q_vectors;
+ /* reserve slots from OS requested IRQs */
+ vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors,
+ vsi->idx);
+ if (vsi->base_vector < 0) {
+ dev_err(&pf->pdev->dev,
+ "Failed to get tracking for %d vectors for VSI %d, err=%d\n",
+ num_q_vectors, vsi->vsi_num, vsi->base_vector);
+ return -ENOENT;
+ }
+ pf->num_avail_sw_msix -= num_q_vectors;
+
+ return 0;
+}
+
+/**
+ * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI
+ * @vsi: the VSI having rings deallocated
+ */
+static void ice_vsi_clear_rings(struct ice_vsi *vsi)
+{
+ int i;
+
+ if (vsi->tx_rings) {
+ for (i = 0; i < vsi->alloc_txq; i++) {
+ if (vsi->tx_rings[i]) {
+ kfree_rcu(vsi->tx_rings[i], rcu);
+ vsi->tx_rings[i] = NULL;
+ }
+ }
+ }
+ if (vsi->rx_rings) {
+ for (i = 0; i < vsi->alloc_rxq; i++) {
+ if (vsi->rx_rings[i]) {
+ kfree_rcu(vsi->rx_rings[i], rcu);
+ vsi->rx_rings[i] = NULL;
+ }
+ }
+ }
+}
+
+/**
+ * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI
+ * @vsi: VSI which is having rings allocated
+ */
+static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ int i;
+
+ /* Allocate Tx rings */
+ for (i = 0; i < vsi->alloc_txq; i++) {
+ struct ice_ring *ring;
+
+ /* allocate with kzalloc(), free with kfree_rcu() */
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+
+ if (!ring)
+ goto err_out;
+
+ ring->q_index = i;
+ ring->reg_idx = vsi->txq_map[i];
+ ring->ring_active = false;
+ ring->vsi = vsi;
+ ring->dev = &pf->pdev->dev;
+ ring->count = vsi->num_tx_desc;
+ vsi->tx_rings[i] = ring;
+ }
+
+ /* Allocate Rx rings */
+ for (i = 0; i < vsi->alloc_rxq; i++) {
+ struct ice_ring *ring;
+
+ /* allocate with kzalloc(), free with kfree_rcu() */
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring)
+ goto err_out;
+
+ ring->q_index = i;
+ ring->reg_idx = vsi->rxq_map[i];
+ ring->ring_active = false;
+ ring->vsi = vsi;
+ ring->netdev = vsi->netdev;
+ ring->dev = &pf->pdev->dev;
+ ring->count = vsi->num_rx_desc;
+ vsi->rx_rings[i] = ring;
+ }
+
+ return 0;
+
+err_out:
+ ice_vsi_clear_rings(vsi);
+ return -ENOMEM;
+}
+
+/**
+ * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors
+ * @vsi: the VSI being configured
+ *
+ * This function maps descriptor rings to the queue-specific vectors allotted
+ * through the MSI-X enabling code. On a constrained vector budget, we map Tx
+ * and Rx rings to the vector as "efficiently" as possible.
+ */
+#ifdef CONFIG_DCB
+void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
+#else
+static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
+#endif /* CONFIG_DCB */
+{
+ int q_vectors = vsi->num_q_vectors;
+ int tx_rings_rem, rx_rings_rem;
+ int v_id;
+
+ /* initially assigning remaining rings count to VSIs num queue value */
+ tx_rings_rem = vsi->num_txq;
+ rx_rings_rem = vsi->num_rxq;
+
+ for (v_id = 0; v_id < q_vectors; v_id++) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[v_id];
+ int tx_rings_per_v, rx_rings_per_v, q_id, q_base;
+
+ /* Tx rings mapping to vector */
+ tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id);
+ q_vector->num_ring_tx = tx_rings_per_v;
+ q_vector->tx.ring = NULL;
+ q_vector->tx.itr_idx = ICE_TX_ITR;
+ q_base = vsi->num_txq - tx_rings_rem;
+
+ for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) {
+ struct ice_ring *tx_ring = vsi->tx_rings[q_id];
+
+ tx_ring->q_vector = q_vector;
+ tx_ring->next = q_vector->tx.ring;
+ q_vector->tx.ring = tx_ring;
+ }
+ tx_rings_rem -= tx_rings_per_v;
+
+ /* Rx rings mapping to vector */
+ rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id);
+ q_vector->num_ring_rx = rx_rings_per_v;
+ q_vector->rx.ring = NULL;
+ q_vector->rx.itr_idx = ICE_RX_ITR;
+ q_base = vsi->num_rxq - rx_rings_rem;
+
+ for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) {
+ struct ice_ring *rx_ring = vsi->rx_rings[q_id];
+
+ rx_ring->q_vector = q_vector;
+ rx_ring->next = q_vector->rx.ring;
+ q_vector->rx.ring = rx_ring;
+ }
+ rx_rings_rem -= rx_rings_per_v;
+ }
+}
+
+/**
+ * ice_vsi_manage_rss_lut - disable/enable RSS
+ * @vsi: the VSI being changed
+ * @ena: boolean value indicating if this is an enable or disable request
+ *
+ * In the event of disable request for RSS, this function will zero out RSS
+ * LUT, while in the event of enable request for RSS, it will reconfigure RSS
+ * LUT.
+ */
+int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena)
+{
+ int err = 0;
+ u8 *lut;
+
+ lut = devm_kzalloc(&vsi->back->pdev->dev, vsi->rss_table_size,
+ GFP_KERNEL);
+ if (!lut)
+ return -ENOMEM;
+
+ if (ena) {
+ if (vsi->rss_lut_user)
+ memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
+ else
+ ice_fill_rss_lut(lut, vsi->rss_table_size,
+ vsi->rss_size);
+ }
+
+ err = ice_set_rss(vsi, NULL, lut, vsi->rss_table_size);
+ devm_kfree(&vsi->back->pdev->dev, lut);
+ return err;
+}
+
+/**
+ * ice_vsi_cfg_rss_lut_key - Configure RSS params for a VSI
+ * @vsi: VSI to be configured
+ */
+static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
+{
+ struct ice_aqc_get_set_rss_keys *key;
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+ int err = 0;
+ u8 *lut;
+
+ vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq);
+
+ lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL);
+ if (!lut)
+ return -ENOMEM;
+
+ if (vsi->rss_lut_user)
+ memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
+ else
+ ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size);
+
+ status = ice_aq_set_rss_lut(&pf->hw, vsi->idx, vsi->rss_lut_type, lut,
+ vsi->rss_table_size);
+
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "set_rss_lut failed, error %d\n", status);
+ err = -EIO;
+ goto ice_vsi_cfg_rss_exit;
+ }
+
+ key = devm_kzalloc(&pf->pdev->dev, sizeof(*key), GFP_KERNEL);
+ if (!key) {
+ err = -ENOMEM;
+ goto ice_vsi_cfg_rss_exit;
+ }
+
+ if (vsi->rss_hkey_user)
+ memcpy(key,
+ (struct ice_aqc_get_set_rss_keys *)vsi->rss_hkey_user,
+ ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE);
+ else
+ netdev_rss_key_fill((void *)key,
+ ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE);
+
+ status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key);
+
+ if (status) {
+ dev_err(&pf->pdev->dev, "set_rss_key failed, error %d\n",
+ status);
+ err = -EIO;
+ }
+
+ devm_kfree(&pf->pdev->dev, key);
+ice_vsi_cfg_rss_exit:
+ devm_kfree(&pf->pdev->dev, lut);
+ return err;
+}
+
+/**
+ * ice_add_mac_to_list - Add a MAC address filter entry to the list
+ * @vsi: the VSI to be forwarded to
+ * @add_list: pointer to the list which contains MAC filter entries
+ * @macaddr: the MAC address to be added.
+ *
+ * Adds MAC address filter entry to the temp list
+ *
+ * Returns 0 on success or ENOMEM on failure.
+ */
+int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
+ const u8 *macaddr)
+{
+ struct ice_fltr_list_entry *tmp;
+ struct ice_pf *pf = vsi->back;
+
+ tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC);
+ if (!tmp)
+ return -ENOMEM;
+
+ tmp->fltr_info.flag = ICE_FLTR_TX;
+ tmp->fltr_info.src_id = ICE_SRC_ID_VSI;
+ tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC;
+ tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ tmp->fltr_info.vsi_handle = vsi->idx;
+ ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr);
+
+ INIT_LIST_HEAD(&tmp->list_entry);
+ list_add(&tmp->list_entry, add_list);
+
+ return 0;
+}
+
+/**
+ * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
+ * @vsi: the VSI to be updated
+ */
+void ice_update_eth_stats(struct ice_vsi *vsi)
+{
+ struct ice_eth_stats *prev_es, *cur_es;
+ struct ice_hw *hw = &vsi->back->hw;
+ u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */
+
+ prev_es = &vsi->eth_stats_prev;
+ cur_es = &vsi->eth_stats;
+
+ ice_stat_update40(hw, GLV_GORCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_bytes, &cur_es->rx_bytes);
+
+ ice_stat_update40(hw, GLV_UPRCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_unicast, &cur_es->rx_unicast);
+
+ ice_stat_update40(hw, GLV_MPRCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_multicast, &cur_es->rx_multicast);
+
+ ice_stat_update40(hw, GLV_BPRCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_broadcast, &cur_es->rx_broadcast);
+
+ ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->rx_discards, &cur_es->rx_discards);
+
+ ice_stat_update40(hw, GLV_GOTCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_bytes, &cur_es->tx_bytes);
+
+ ice_stat_update40(hw, GLV_UPTCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_unicast, &cur_es->tx_unicast);
+
+ ice_stat_update40(hw, GLV_MPTCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_multicast, &cur_es->tx_multicast);
+
+ ice_stat_update40(hw, GLV_BPTCL(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_broadcast, &cur_es->tx_broadcast);
+
+ ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded,
+ &prev_es->tx_errors, &cur_es->tx_errors);
+
+ vsi->stat_offsets_loaded = true;
+}
+
+/**
+ * ice_free_fltr_list - free filter lists helper
+ * @dev: pointer to the device struct
+ * @h: pointer to the list head to be freed
+ *
+ * Helper function to free filter lists previously created using
+ * ice_add_mac_to_list
+ */
+void ice_free_fltr_list(struct device *dev, struct list_head *h)
+{
+ struct ice_fltr_list_entry *e, *tmp;
+
+ list_for_each_entry_safe(e, tmp, h, list_entry) {
+ list_del(&e->list_entry);
+ devm_kfree(dev, e);
+ }
+}
+
+/**
+ * ice_vsi_add_vlan - Add VSI membership for given VLAN
+ * @vsi: the VSI being configured
+ * @vid: VLAN ID to be added
+ */
+int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
+{
+ struct ice_fltr_list_entry *tmp;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+ int err = 0;
+
+ tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+
+ tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
+ tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ tmp->fltr_info.flag = ICE_FLTR_TX;
+ tmp->fltr_info.src_id = ICE_SRC_ID_VSI;
+ tmp->fltr_info.vsi_handle = vsi->idx;
+ tmp->fltr_info.l_data.vlan.vlan_id = vid;
+
+ INIT_LIST_HEAD(&tmp->list_entry);
+ list_add(&tmp->list_entry, &tmp_add_list);
+
+ status = ice_add_vlan(&pf->hw, &tmp_add_list);
+ if (status) {
+ err = -ENODEV;
+ dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n",
+ vid, vsi->vsi_num);
+ }
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+ return err;
+}
+
+/**
+ * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN
+ * @vsi: the VSI being configured
+ * @vid: VLAN ID to be removed
+ *
+ * Returns 0 on success and negative on failure
+ */
+int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
+{
+ struct ice_fltr_list_entry *list;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+ int err = 0;
+
+ list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+ if (!list)
+ return -ENOMEM;
+
+ list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
+ list->fltr_info.vsi_handle = vsi->idx;
+ list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ list->fltr_info.l_data.vlan.vlan_id = vid;
+ list->fltr_info.flag = ICE_FLTR_TX;
+ list->fltr_info.src_id = ICE_SRC_ID_VSI;
+
+ INIT_LIST_HEAD(&list->list_entry);
+ list_add(&list->list_entry, &tmp_add_list);
+
+ status = ice_remove_vlan(&pf->hw, &tmp_add_list);
+ if (status == ICE_ERR_DOES_NOT_EXIST) {
+ dev_dbg(&pf->pdev->dev,
+ "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n",
+ vid, vsi->vsi_num, status);
+ } else if (status) {
+ dev_err(&pf->pdev->dev,
+ "Error removing VLAN %d on vsi %i error: %d\n",
+ vid, vsi->vsi_num, status);
+ err = -EIO;
+ }
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+ return err;
+}
+
+/**
+ * ice_vsi_cfg_rxqs - Configure the VSI for Rx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Rx VSI for operation.
+ */
+int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
+{
+ u16 i;
+
+ if (vsi->type == ICE_VSI_VF)
+ goto setup_rings;
+
+ if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN)
+ vsi->max_frame = vsi->netdev->mtu +
+ ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+ else
+ vsi->max_frame = ICE_RXBUF_2048;
+
+ vsi->rx_buf_len = ICE_RXBUF_2048;
+setup_rings:
+ /* set up individual rings */
+ for (i = 0; i < vsi->num_rxq; i++) {
+ int err;
+
+ err = ice_setup_rx_ctx(vsi->rx_rings[i]);
+ if (err) {
+ dev_err(&vsi->back->pdev->dev,
+ "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+ i, err);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_vsi_cfg_txq - Configure single Tx queue
+ * @vsi: the VSI that queue belongs to
+ * @ring: Tx ring to be configured
+ * @tc_q_idx: queue index within given TC
+ * @qg_buf: queue group buffer
+ * @tc: TC that Tx ring belongs to
+ */
+static int
+ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, u16 tc_q_idx,
+ struct ice_aqc_add_tx_qgrp *qg_buf, u8 tc)
+{
+ struct ice_tlan_ctx tlan_ctx = { 0 };
+ struct ice_aqc_add_txqs_perq *txq;
+ struct ice_pf *pf = vsi->back;
+ u8 buf_len = sizeof(*qg_buf);
+ enum ice_status status;
+ u16 pf_q;
+
+ pf_q = ring->reg_idx;
+ ice_setup_tx_ctx(ring, &tlan_ctx, pf_q);
+ /* copy context contents into the qg_buf */
+ qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
+ ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+ ice_tlan_ctx_info);
+
+ /* init queue specific tail reg. It is referred as
+ * transmit comm scheduler queue doorbell.
+ */
+ ring->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+
+ /* Add unique software queue handle of the Tx queue per
+ * TC into the VSI Tx ring
+ */
+ ring->q_handle = tc_q_idx;
+
+ status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle,
+ 1, qg_buf, buf_len, NULL);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "Failed to set LAN Tx queue context, error: %d\n",
+ status);
+ return -ENODEV;
+ }
+
+ /* Add Tx Queue TEID into the VSI Tx ring from the
+ * response. This will complete configuring and
+ * enabling the queue.
+ */
+ txq = &qg_buf->txqs[0];
+ if (pf_q == le16_to_cpu(txq->txq_id))
+ ring->txq_teid = le32_to_cpu(txq->q_teid);
+
+ return 0;
+}
+
+/**
+ * ice_vsi_cfg_txqs - Configure the VSI for Tx
+ * @vsi: the VSI being configured
+ * @rings: Tx ring array to be configured
+ * @offset: offset within vsi->txq_map
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Tx VSI for operation.
+ */
+static int
+ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, int offset)
+{
+ struct ice_aqc_add_tx_qgrp *qg_buf;
+ struct ice_pf *pf = vsi->back;
+ u16 q_idx = 0, i;
+ int err = 0;
+ u8 tc;
+
+ qg_buf = devm_kzalloc(&pf->pdev->dev, sizeof(*qg_buf), GFP_KERNEL);
+ if (!qg_buf)
+ return -ENOMEM;
+
+ qg_buf->num_txqs = 1;
+
+ /* set up and configure the Tx queues for each enabled TC */
+ ice_for_each_traffic_class(tc) {
+ if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+ break;
+
+ for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+ err = ice_vsi_cfg_txq(vsi, rings[q_idx], i + offset,
+ qg_buf, tc);
+ if (err)
+ goto err_cfg_txqs;
+
+ q_idx++;
+ }
+ }
+err_cfg_txqs:
+ devm_kfree(&pf->pdev->dev, qg_buf);
+ return err;
+}
+
+/**
+ * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Tx VSI for operation.
+ */
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi)
+{
+ return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, 0);
+}
+
+/**
+ * ice_intrl_usec_to_reg - convert interrupt rate limit to register value
+ * @intrl: interrupt rate limit in usecs
+ * @gran: interrupt rate limit granularity in usecs
+ *
+ * This function converts a decimal interrupt rate limit in usecs to the format
+ * expected by firmware.
+ */
+u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran)
+{
+ u32 val = intrl / gran;
+
+ if (val)
+ return val | GLINT_RATE_INTRL_ENA_M;
+ return 0;
+}
+
+/**
+ * ice_cfg_itr_gran - set the ITR granularity to 2 usecs if not already set
+ * @hw: board specific structure
+ */
+static void ice_cfg_itr_gran(struct ice_hw *hw)
+{
+ u32 regval = rd32(hw, GLINT_CTL);
+
+ /* no need to update global register if ITR gran is already set */
+ if (!(regval & GLINT_CTL_DIS_AUTOMASK_M) &&
+ (((regval & GLINT_CTL_ITR_GRAN_200_M) >>
+ GLINT_CTL_ITR_GRAN_200_S) == ICE_ITR_GRAN_US) &&
+ (((regval & GLINT_CTL_ITR_GRAN_100_M) >>
+ GLINT_CTL_ITR_GRAN_100_S) == ICE_ITR_GRAN_US) &&
+ (((regval & GLINT_CTL_ITR_GRAN_50_M) >>
+ GLINT_CTL_ITR_GRAN_50_S) == ICE_ITR_GRAN_US) &&
+ (((regval & GLINT_CTL_ITR_GRAN_25_M) >>
+ GLINT_CTL_ITR_GRAN_25_S) == ICE_ITR_GRAN_US))
+ return;
+
+ regval = ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_200_S) &
+ GLINT_CTL_ITR_GRAN_200_M) |
+ ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_100_S) &
+ GLINT_CTL_ITR_GRAN_100_M) |
+ ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_50_S) &
+ GLINT_CTL_ITR_GRAN_50_M) |
+ ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_25_S) &
+ GLINT_CTL_ITR_GRAN_25_M);
+ wr32(hw, GLINT_CTL, regval);
+}
+
+/**
+ * ice_cfg_itr - configure the initial interrupt throttle values
+ * @hw: pointer to the HW structure
+ * @q_vector: interrupt vector that's being configured
+ *
+ * Configure interrupt throttling values for the ring containers that are
+ * associated with the interrupt vector passed in.
+ */
+static void
+ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector)
+{
+ ice_cfg_itr_gran(hw);
+
+ if (q_vector->num_ring_rx) {
+ struct ice_ring_container *rc = &q_vector->rx;
+
+ /* if this value is set then don't overwrite with default */
+ if (!rc->itr_setting)
+ rc->itr_setting = ICE_DFLT_RX_ITR;
+
+ rc->target_itr = ITR_TO_REG(rc->itr_setting);
+ rc->next_update = jiffies + 1;
+ rc->current_itr = rc->target_itr;
+ wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx),
+ ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
+ }
+
+ if (q_vector->num_ring_tx) {
+ struct ice_ring_container *rc = &q_vector->tx;
+
+ /* if this value is set then don't overwrite with default */
+ if (!rc->itr_setting)
+ rc->itr_setting = ICE_DFLT_TX_ITR;
+
+ rc->target_itr = ITR_TO_REG(rc->itr_setting);
+ rc->next_update = jiffies + 1;
+ rc->current_itr = rc->target_itr;
+ wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx),
+ ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
+ }
+}
+
+/**
+ * ice_cfg_txq_interrupt - configure interrupt on Tx queue
+ * @vsi: the VSI being configured
+ * @txq: Tx queue being mapped to MSI-X vector
+ * @msix_idx: MSI-X vector index within the function
+ * @itr_idx: ITR index of the interrupt cause
+ *
+ * Configure interrupt on Tx queue by associating Tx queue to MSI-X vector
+ * within the function space.
+ */
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx)
+#else
+static void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx)
+#endif /* CONFIG_PCI_IOV */
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 val;
+
+ itr_idx = (itr_idx << QINT_TQCTL_ITR_INDX_S) & QINT_TQCTL_ITR_INDX_M;
+
+ val = QINT_TQCTL_CAUSE_ENA_M | itr_idx |
+ ((msix_idx << QINT_TQCTL_MSIX_INDX_S) & QINT_TQCTL_MSIX_INDX_M);
+
+ wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
+}
+
+/**
+ * ice_cfg_rxq_interrupt - configure interrupt on Rx queue
+ * @vsi: the VSI being configured
+ * @rxq: Rx queue being mapped to MSI-X vector
+ * @msix_idx: MSI-X vector index within the function
+ * @itr_idx: ITR index of the interrupt cause
+ *
+ * Configure interrupt on Rx queue by associating Rx queue to MSI-X vector
+ * within the function space.
+ */
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
+#else
+static void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
+#endif /* CONFIG_PCI_IOV */
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 val;
+
+ itr_idx = (itr_idx << QINT_RQCTL_ITR_INDX_S) & QINT_RQCTL_ITR_INDX_M;
+
+ val = QINT_RQCTL_CAUSE_ENA_M | itr_idx |
+ ((msix_idx << QINT_RQCTL_MSIX_INDX_S) & QINT_RQCTL_MSIX_INDX_M);
+
+ wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
+
+ ice_flush(hw);
+}
+
+/**
+ * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW
+ * @vsi: the VSI being configured
+ *
+ * This configures MSIX mode interrupts for the PF VSI, and should not be used
+ * for the VF VSI.
+ */
+void ice_vsi_cfg_msix(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 txq = 0, rxq = 0;
+ int i, q;
+
+ for (i = 0; i < vsi->num_q_vectors; i++) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+ u16 reg_idx = q_vector->reg_idx;
+
+ ice_cfg_itr(hw, q_vector);
+
+ wr32(hw, GLINT_RATE(reg_idx),
+ ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran));
+
+ /* Both Transmit Queue Interrupt Cause Control register
+ * and Receive Queue Interrupt Cause control register
+ * expects MSIX_INDX field to be the vector index
+ * within the function space and not the absolute
+ * vector index across PF or across device.
+ * For SR-IOV VF VSIs queue vector index always starts
+ * with 1 since first vector index(0) is used for OICR
+ * in VF space. Since VMDq and other PF VSIs are within
+ * the PF function space, use the vector index that is
+ * tracked for this PF.
+ */
+ for (q = 0; q < q_vector->num_ring_tx; q++) {
+ ice_cfg_txq_interrupt(vsi, txq, reg_idx,
+ q_vector->tx.itr_idx);
+ txq++;
+ }
+
+ for (q = 0; q < q_vector->num_ring_rx; q++) {
+ ice_cfg_rxq_interrupt(vsi, rxq, reg_idx,
+ q_vector->rx.itr_idx);
+ rxq++;
+ }
+ }
+}
+
+/**
+ * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx
+ * @vsi: the VSI being changed
+ */
+int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx *ctxt;
+ enum ice_status status;
+ int ret = 0;
+
+ ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ /* Here we are configuring the VSI to let the driver add VLAN tags by
+ * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag
+ * insertion happens in the Tx hot path, in ice_tx_map.
+ */
+ ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
+
+ /* Preserve existing VLAN strip setting */
+ ctxt->info.vlan_flags |= (vsi->info.vlan_flags &
+ ICE_AQ_VSI_VLAN_EMOD_M);
+
+ ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+
+ status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+ if (status) {
+ dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ ret = -EIO;
+ goto out;
+ }
+
+ vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+ devm_kfree(dev, ctxt);
+ return ret;
+}
+
+/**
+ * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx
+ * @vsi: the VSI being changed
+ * @ena: boolean value indicating if this is a enable or disable request
+ */
+int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx *ctxt;
+ enum ice_status status;
+ int ret = 0;
+
+ ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ /* Here we are configuring what the VSI should do with the VLAN tag in
+ * the Rx packet. We can either leave the tag in the packet or put it in
+ * the Rx descriptor.
+ */
+ if (ena)
+ /* Strip VLAN tag from Rx packet and put it in the desc */
+ ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
+ else
+ /* Disable stripping. Leave tag in packet */
+ ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
+
+ /* Allow all packets untagged/tagged */
+ ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
+
+ ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+
+ status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+ if (status) {
+ dev_err(dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
+ ena, status, hw->adminq.sq_last_status);
+ ret = -EIO;
+ goto out;
+ }
+
+ vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+ devm_kfree(dev, ctxt);
+ return ret;
+}
+
+/**
+ * ice_vsi_start_rx_rings - start VSI's Rx rings
+ * @vsi: the VSI whose rings are to be started
+ *
+ * Returns 0 on success and a negative value on error
+ */
+int ice_vsi_start_rx_rings(struct ice_vsi *vsi)
+{
+ return ice_vsi_ctrl_rx_rings(vsi, true);
+}
+
+/**
+ * ice_vsi_stop_rx_rings - stop VSI's Rx rings
+ * @vsi: the VSI
+ *
+ * Returns 0 on success and a negative value on error
+ */
+int ice_vsi_stop_rx_rings(struct ice_vsi *vsi)
+{
+ return ice_vsi_ctrl_rx_rings(vsi, false);
+}
+
+/**
+ * ice_trigger_sw_intr - trigger a software interrupt
+ * @hw: pointer to the HW structure
+ * @q_vector: interrupt vector to trigger the software interrupt for
+ */
+void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector)
+{
+ wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx),
+ (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) |
+ GLINT_DYN_CTL_SWINT_TRIG_M |
+ GLINT_DYN_CTL_INTENA_M);
+}
+
+/**
+ * ice_vsi_stop_tx_ring - Disable single Tx ring
+ * @vsi: the VSI being configured
+ * @rst_src: reset source
+ * @rel_vmvf_num: Relative ID of VF/VM
+ * @ring: Tx ring to be stopped
+ * @txq_meta: Meta data of Tx ring to be stopped
+ */
+#ifndef CONFIG_PCI_IOV
+static
+#endif /* !CONFIG_PCI_IOV */
+int
+ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+ u16 rel_vmvf_num, struct ice_ring *ring,
+ struct ice_txq_meta *txq_meta)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_q_vector *q_vector;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+ u32 val;
+
+ /* clear cause_ena bit for disabled queues */
+ val = rd32(hw, QINT_TQCTL(ring->reg_idx));
+ val &= ~QINT_TQCTL_CAUSE_ENA_M;
+ wr32(hw, QINT_TQCTL(ring->reg_idx), val);
+
+ /* software is expected to wait for 100 ns */
+ ndelay(100);
+
+ /* trigger a software interrupt for the vector
+ * associated to the queue to schedule NAPI handler
+ */
+ q_vector = ring->q_vector;
+ if (q_vector)
+ ice_trigger_sw_intr(hw, q_vector);
+
+ status = ice_dis_vsi_txq(vsi->port_info, txq_meta->vsi_idx,
+ txq_meta->tc, 1, &txq_meta->q_handle,
+ &txq_meta->q_id, &txq_meta->q_teid, rst_src,
+ rel_vmvf_num, NULL);
+
+ /* if the disable queue command was exercised during an
+ * active reset flow, ICE_ERR_RESET_ONGOING is returned.
+ * This is not an error as the reset operation disables
+ * queues at the hardware level anyway.
+ */
+ if (status == ICE_ERR_RESET_ONGOING) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Reset in progress. LAN Tx queues already disabled\n");
+ } else if (status == ICE_ERR_DOES_NOT_EXIST) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "LAN Tx queues do not exist, nothing to disable\n");
+ } else if (status) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to disable LAN Tx queues, error: %d\n", status);
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_fill_txq_meta - Prepare the Tx queue's meta data
+ * @vsi: VSI that ring belongs to
+ * @ring: ring that txq_meta will be based on
+ * @txq_meta: a helper struct that wraps Tx queue's information
+ *
+ * Set up a helper struct that will contain all the necessary fields that
+ * are needed for stopping Tx queue
+ */
+#ifndef CONFIG_PCI_IOV
+static
+#endif /* !CONFIG_PCI_IOV */
+void
+ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring,
+ struct ice_txq_meta *txq_meta)
+{
+ u8 tc = 0;
+
+#ifdef CONFIG_DCB
+ tc = ring->dcb_tc;
+#endif /* CONFIG_DCB */
+ txq_meta->q_id = ring->reg_idx;
+ txq_meta->q_teid = ring->txq_teid;
+ txq_meta->q_handle = ring->q_handle;
+ txq_meta->vsi_idx = vsi->idx;
+ txq_meta->tc = tc;
+}
+
+/**
+ * ice_vsi_stop_tx_rings - Disable Tx rings
+ * @vsi: the VSI being configured
+ * @rst_src: reset source
+ * @rel_vmvf_num: Relative ID of VF/VM
+ * @rings: Tx ring array to be stopped
+ */
+static int
+ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+ u16 rel_vmvf_num, struct ice_ring **rings)
+{
+ u16 i, q_idx = 0;
+ int status;
+ u8 tc;
+
+ if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
+ return -EINVAL;
+
+ /* set up the Tx queue list to be disabled for each enabled TC */
+ ice_for_each_traffic_class(tc) {
+ if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+ break;
+
+ for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+ struct ice_txq_meta txq_meta = { };
+
+ if (!rings || !rings[q_idx])
+ return -EINVAL;
+
+ ice_fill_txq_meta(vsi, rings[q_idx], &txq_meta);
+ status = ice_vsi_stop_tx_ring(vsi, rst_src,
+ rel_vmvf_num,
+ rings[q_idx], &txq_meta);
+
+ if (status)
+ return status;
+
+ q_idx++;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_vsi_stop_lan_tx_rings - Disable LAN Tx rings
+ * @vsi: the VSI being configured
+ * @rst_src: reset source
+ * @rel_vmvf_num: Relative ID of VF/VM
+ */
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+ u16 rel_vmvf_num)
+{
+ return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings);
+}
+
+/**
+ * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI
+ * @vsi: VSI to enable or disable VLAN pruning on
+ * @ena: set to true to enable VLAN pruning and false to disable it
+ * @vlan_promisc: enable valid security flags if not in VLAN promiscuous mode
+ *
+ * returns 0 if VSI is updated, negative otherwise
+ */
+int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc)
+{
+ struct ice_vsi_ctx *ctxt;
+ struct device *dev;
+ struct ice_pf *pf;
+ int status;
+
+ if (!vsi)
+ return -EINVAL;
+
+ pf = vsi->back;
+ dev = &pf->pdev->dev;
+ ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ ctxt->info = vsi->info;
+
+ if (ena) {
+ ctxt->info.sec_flags |=
+ ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S;
+ ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+ } else {
+ ctxt->info.sec_flags &=
+ ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S);
+ ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+ }
+
+ if (!vlan_promisc)
+ ctxt->info.valid_sections =
+ cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID |
+ ICE_AQ_VSI_PROP_SW_VALID);
+
+ status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL);
+ if (status) {
+ netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n",
+ ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status,
+ pf->hw.adminq.sq_last_status);
+ goto err_out;
+ }
+
+ vsi->info.sec_flags = ctxt->info.sec_flags;
+ vsi->info.sw_flags2 = ctxt->info.sw_flags2;
+
+ devm_kfree(dev, ctxt);
+ return 0;
+
+err_out:
+ devm_kfree(dev, ctxt);
+ return -EIO;
+}
+
+static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
+{
+ struct ice_dcbx_cfg *cfg = &vsi->port_info->local_dcbx_cfg;
+
+ vsi->tc_cfg.ena_tc = ice_dcb_get_ena_tc(cfg);
+ vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg);
+}
+
+/**
+ * ice_vsi_set_q_vectors_reg_idx - set the HW register index for all q_vectors
+ * @vsi: VSI to set the q_vectors register index on
+ */
+static int
+ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi)
+{
+ u16 i;
+
+ if (!vsi || !vsi->q_vectors)
+ return -EINVAL;
+
+ ice_for_each_q_vector(vsi, i) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+ if (!q_vector) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to set reg_idx on q_vector %d VSI %d\n",
+ i, vsi->vsi_num);
+ goto clear_reg_idx;
+ }
+
+ if (vsi->type == ICE_VSI_VF) {
+ struct ice_vf *vf = &vsi->back->vf[vsi->vf_id];
+
+ q_vector->reg_idx = ice_calc_vf_reg_idx(vf, q_vector);
+ } else {
+ q_vector->reg_idx =
+ q_vector->v_idx + vsi->base_vector;
+ }
+ }
+
+ return 0;
+
+clear_reg_idx:
+ ice_for_each_q_vector(vsi, i) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+ if (q_vector)
+ q_vector->reg_idx = 0;
+ }
+
+ return -EINVAL;
+}
+
+/**
+ * ice_vsi_add_rem_eth_mac - Program VSI ethertype based filter with rule
+ * @vsi: the VSI being configured
+ * @add_rule: boolean value to add or remove ethertype filter rule
+ */
+static void
+ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule)
+{
+ struct ice_fltr_list_entry *list;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+
+ list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+ if (!list)
+ return;
+
+ list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
+ list->fltr_info.fltr_act = ICE_DROP_PACKET;
+ list->fltr_info.flag = ICE_FLTR_TX;
+ list->fltr_info.src_id = ICE_SRC_ID_VSI;
+ list->fltr_info.vsi_handle = vsi->idx;
+ list->fltr_info.l_data.ethertype_mac.ethertype = vsi->ethtype;
+
+ INIT_LIST_HEAD(&list->list_entry);
+ list_add(&list->list_entry, &tmp_add_list);
+
+ if (add_rule)
+ status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
+ else
+ status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
+
+ if (status)
+ dev_err(&pf->pdev->dev,
+ "Failure Adding or Removing Ethertype on VSI %i error: %d\n",
+ vsi->vsi_num, status);
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+}
+
+/**
+ * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
+ * @vsi: the VSI being configured
+ * @tx: bool to determine Tx or Rx rule
+ * @create: bool to determine create or remove Rule
+ */
+void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
+{
+ struct ice_fltr_list_entry *list;
+ struct ice_pf *pf = vsi->back;
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+
+ list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+ if (!list)
+ return;
+
+ list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
+ list->fltr_info.vsi_handle = vsi->idx;
+ list->fltr_info.l_data.ethertype_mac.ethertype = ETH_P_LLDP;
+
+ if (tx) {
+ list->fltr_info.fltr_act = ICE_DROP_PACKET;
+ list->fltr_info.flag = ICE_FLTR_TX;
+ list->fltr_info.src_id = ICE_SRC_ID_VSI;
+ } else {
+ list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ list->fltr_info.flag = ICE_FLTR_RX;
+ list->fltr_info.src_id = ICE_SRC_ID_LPORT;
+ }
+
+ INIT_LIST_HEAD(&list->list_entry);
+ list_add(&list->list_entry, &tmp_add_list);
+
+ if (create)
+ status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
+ else
+ status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
+
+ if (status)
+ dev_err(&pf->pdev->dev,
+ "Fail %s %s LLDP rule on VSI %i error: %d\n",
+ create ? "adding" : "removing", tx ? "TX" : "RX",
+ vsi->vsi_num, status);
+
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+}
+
+/**
+ * ice_vsi_setup - Set up a VSI by a given type
+ * @pf: board private structure
+ * @pi: pointer to the port_info instance
+ * @type: VSI type
+ * @vf_id: defines VF ID to which this VSI connects. This field is meant to be
+ * used only for ICE_VSI_VF VSI type. For other VSI types, should
+ * fill-in ICE_INVAL_VFID as input.
+ *
+ * This allocates the sw VSI structure and its queue resources.
+ *
+ * Returns pointer to the successfully allocated and configured VSI sw struct on
+ * success, NULL on failure.
+ */
+struct ice_vsi *
+ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
+ enum ice_vsi_type type, u16 vf_id)
+{
+ u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+ struct device *dev = &pf->pdev->dev;
+ enum ice_status status;
+ struct ice_vsi *vsi;
+ int ret, i;
+
+ if (type == ICE_VSI_VF)
+ vsi = ice_vsi_alloc(pf, type, vf_id);
+ else
+ vsi = ice_vsi_alloc(pf, type, ICE_INVAL_VFID);
+
+ if (!vsi) {
+ dev_err(dev, "could not allocate VSI\n");
+ return NULL;
+ }
+
+ vsi->port_info = pi;
+ vsi->vsw = pf->first_sw;
+ if (vsi->type == ICE_VSI_PF)
+ vsi->ethtype = ETH_P_PAUSE;
+
+ if (vsi->type == ICE_VSI_VF)
+ vsi->vf_id = vf_id;
+
+ if (ice_vsi_get_qs(vsi)) {
+ dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n",
+ vsi->idx);
+ goto unroll_get_qs;
+ }
+
+ /* set RSS capabilities */
+ ice_vsi_set_rss_params(vsi);
+
+ /* set TC configuration */
+ ice_vsi_set_tc_cfg(vsi);
+
+ /* create the VSI */
+ ret = ice_vsi_init(vsi);
+ if (ret)
+ goto unroll_get_qs;
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ ret = ice_vsi_alloc_q_vectors(vsi);
+ if (ret)
+ goto unroll_vsi_init;
+
+ ret = ice_vsi_setup_vector_base(vsi);
+ if (ret)
+ goto unroll_alloc_q_vector;
+
+ ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+ if (ret)
+ goto unroll_vector_base;
+
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto unroll_vector_base;
+
+ ice_vsi_map_rings_to_vectors(vsi);
+
+ /* Do not exit if configuring RSS had an issue, at least
+ * receive traffic on first queue. Hence no need to capture
+ * return value
+ */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_vsi_cfg_rss_lut_key(vsi);
+ break;
+ case ICE_VSI_VF:
+ /* VF driver will take care of creating netdev for this type and
+ * map queues to vectors through Virtchnl, PF driver only
+ * creates a VSI and corresponding structures for bookkeeping
+ * purpose
+ */
+ ret = ice_vsi_alloc_q_vectors(vsi);
+ if (ret)
+ goto unroll_vsi_init;
+
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto unroll_alloc_q_vector;
+
+ ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+ if (ret)
+ goto unroll_vector_base;
+
+ /* Do not exit if configuring RSS had an issue, at least
+ * receive traffic on first queue. Hence no need to capture
+ * return value
+ */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_vsi_cfg_rss_lut_key(vsi);
+ break;
+ case ICE_VSI_LB:
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto unroll_vsi_init;
+ break;
+ default:
+ /* clean up the resources and exit */
+ goto unroll_vsi_init;
+ }
+
+ /* configure VSI nodes based on number of queues and TC's */
+ for (i = 0; i < vsi->tc_cfg.numtc; i++)
+ max_txqs[i] = vsi->alloc_txq;
+
+ status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+ max_txqs);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "VSI %d failed lan queue config, error %d\n",
+ vsi->vsi_num, status);
+ goto unroll_vector_base;
+ }
+
+ /* Add switch rule to drop all Tx Flow Control Frames, of look up
+ * type ETHERTYPE from VSIs, and restrict malicious VF from sending
+ * out PAUSE or PFC frames. If enabled, FW can still send FC frames.
+ * The rule is added once for PF VSI in order to create appropriate
+ * recipe, since VSI/VSI list is ignored with drop action...
+ * Also add rules to handle LLDP Tx and Rx packets. Tx LLDP packets
+ * need to be dropped so that VFs cannot send LLDP packets to reconfig
+ * DCB settings in the HW. Also, if the FW DCBX engine is not running
+ * then Rx LLDP packets need to be redirected up the stack.
+ */
+ if (!ice_is_safe_mode(pf)) {
+ if (vsi->type == ICE_VSI_PF) {
+ ice_vsi_add_rem_eth_mac(vsi, true);
+
+ /* Tx LLDP packets */
+ ice_cfg_sw_lldp(vsi, true, true);
+
+ /* Rx LLDP packets */
+ if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+ ice_cfg_sw_lldp(vsi, false, true);
+ }
+ }
+
+ return vsi;
+
+unroll_vector_base:
+ /* reclaim SW interrupts back to the common pool */
+ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+ pf->num_avail_sw_msix += vsi->num_q_vectors;
+unroll_alloc_q_vector:
+ ice_vsi_free_q_vectors(vsi);
+unroll_vsi_init:
+ ice_vsi_delete(vsi);
+unroll_get_qs:
+ ice_vsi_put_qs(vsi);
+ ice_vsi_clear(vsi);
+
+ return NULL;
+}
+
+/**
+ * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW
+ * @vsi: the VSI being cleaned up
+ */
+static void ice_vsi_release_msix(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 txq = 0;
+ u32 rxq = 0;
+ int i, q;
+
+ for (i = 0; i < vsi->num_q_vectors; i++) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+ u16 reg_idx = q_vector->reg_idx;
+
+ wr32(hw, GLINT_ITR(ICE_IDX_ITR0, reg_idx), 0);
+ wr32(hw, GLINT_ITR(ICE_IDX_ITR1, reg_idx), 0);
+ for (q = 0; q < q_vector->num_ring_tx; q++) {
+ wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
+ txq++;
+ }
+
+ for (q = 0; q < q_vector->num_ring_rx; q++) {
+ wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0);
+ rxq++;
+ }
+ }
+
+ ice_flush(hw);
+}
+
+/**
+ * ice_vsi_free_irq - Free the IRQ association with the OS
+ * @vsi: the VSI being configured
+ */
+void ice_vsi_free_irq(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ int base = vsi->base_vector;
+ int i;
+
+ if (!vsi->q_vectors || !vsi->irqs_ready)
+ return;
+
+ ice_vsi_release_msix(vsi);
+ if (vsi->type == ICE_VSI_VF)
+ return;
+
+ vsi->irqs_ready = false;
+ ice_for_each_q_vector(vsi, i) {
+ u16 vector = i + base;
+ int irq_num;
+
+ irq_num = pf->msix_entries[vector].vector;
+
+ /* free only the irqs that were actually requested */
+ if (!vsi->q_vectors[i] ||
+ !(vsi->q_vectors[i]->num_ring_tx ||
+ vsi->q_vectors[i]->num_ring_rx))
+ continue;
+
+ /* clear the affinity notifier in the IRQ descriptor */
+ irq_set_affinity_notifier(irq_num, NULL);
+
+ /* clear the affinity_mask in the IRQ descriptor */
+ irq_set_affinity_hint(irq_num, NULL);
+ synchronize_irq(irq_num);
+ devm_free_irq(&pf->pdev->dev, irq_num,
+ vsi->q_vectors[i]);
+ }
+}
+
+/**
+ * ice_vsi_free_tx_rings - Free Tx resources for VSI queues
+ * @vsi: the VSI having resources freed
+ */
+void ice_vsi_free_tx_rings(struct ice_vsi *vsi)
+{
+ int i;
+
+ if (!vsi->tx_rings)
+ return;
+
+ ice_for_each_txq(vsi, i)
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+ ice_free_tx_ring(vsi->tx_rings[i]);
+}
+
+/**
+ * ice_vsi_free_rx_rings - Free Rx resources for VSI queues
+ * @vsi: the VSI having resources freed
+ */
+void ice_vsi_free_rx_rings(struct ice_vsi *vsi)
+{
+ int i;
+
+ if (!vsi->rx_rings)
+ return;
+
+ ice_for_each_rxq(vsi, i)
+ if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
+ ice_free_rx_ring(vsi->rx_rings[i]);
+}
+
+/**
+ * ice_vsi_close - Shut down a VSI
+ * @vsi: the VSI being shut down
+ */
+void ice_vsi_close(struct ice_vsi *vsi)
+{
+ if (!test_and_set_bit(__ICE_DOWN, vsi->state))
+ ice_down(vsi);
+
+ ice_vsi_free_irq(vsi);
+ ice_vsi_free_tx_rings(vsi);
+ ice_vsi_free_rx_rings(vsi);
+}
+
+/**
+ * ice_free_res - free a block of resources
+ * @res: pointer to the resource
+ * @index: starting index previously returned by ice_get_res
+ * @id: identifier to track owner
+ *
+ * Returns number of resources freed
+ */
+int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
+{
+ int count = 0;
+ int i;
+
+ if (!res || index >= res->end)
+ return -EINVAL;
+
+ id |= ICE_RES_VALID_BIT;
+ for (i = index; i < res->end && res->list[i] == id; i++) {
+ res->list[i] = 0;
+ count++;
+ }
+
+ return count;
+}
+
+/**
+ * ice_search_res - Search the tracker for a block of resources
+ * @res: pointer to the resource
+ * @needed: size of the block needed
+ * @id: identifier to track owner
+ *
+ * Returns the base item index of the block, or -ENOMEM for error
+ */
+static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
+{
+ int start = 0, end = 0;
+
+ if (needed > res->end)
+ return -ENOMEM;
+
+ id |= ICE_RES_VALID_BIT;
+
+ do {
+ /* skip already allocated entries */
+ if (res->list[end++] & ICE_RES_VALID_BIT) {
+ start = end;
+ if ((start + needed) > res->end)
+ break;
+ }
+
+ if (end == (start + needed)) {
+ int i = start;
+
+ /* there was enough, so assign it to the requestor */
+ while (i != end)
+ res->list[i++] = id;
+
+ return start;
+ }
+ } while (end < res->end);
+
+ return -ENOMEM;
+}
+
+/**
+ * ice_get_res - get a block of resources
+ * @pf: board private structure
+ * @res: pointer to the resource
+ * @needed: size of the block needed
+ * @id: identifier to track owner
+ *
+ * Returns the base item index of the block, or negative for error
+ */
+int
+ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
+{
+ if (!res || !pf)
+ return -EINVAL;
+
+ if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) {
+ dev_err(&pf->pdev->dev,
+ "param err: needed=%d, num_entries = %d id=0x%04x\n",
+ needed, res->num_entries, id);
+ return -EINVAL;
+ }
+
+ return ice_search_res(res, needed, id);
+}
+
+/**
+ * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI
+ * @vsi: the VSI being un-configured
+ */
+void ice_vsi_dis_irq(struct ice_vsi *vsi)
+{
+ int base = vsi->base_vector;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 val;
+ int i;
+
+ /* disable interrupt causation from each queue */
+ if (vsi->tx_rings) {
+ ice_for_each_txq(vsi, i) {
+ if (vsi->tx_rings[i]) {
+ u16 reg;
+
+ reg = vsi->tx_rings[i]->reg_idx;
+ val = rd32(hw, QINT_TQCTL(reg));
+ val &= ~QINT_TQCTL_CAUSE_ENA_M;
+ wr32(hw, QINT_TQCTL(reg), val);
+ }
+ }
+ }
+
+ if (vsi->rx_rings) {
+ ice_for_each_rxq(vsi, i) {
+ if (vsi->rx_rings[i]) {
+ u16 reg;
+
+ reg = vsi->rx_rings[i]->reg_idx;
+ val = rd32(hw, QINT_RQCTL(reg));
+ val &= ~QINT_RQCTL_CAUSE_ENA_M;
+ wr32(hw, QINT_RQCTL(reg), val);
+ }
+ }
+ }
+
+ /* disable each interrupt */
+ ice_for_each_q_vector(vsi, i) {
+ if (!vsi->q_vectors[i])
+ continue;
+ wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
+ }
+
+ ice_flush(hw);
+
+ /* don't call synchronize_irq() for VF's from the host */
+ if (vsi->type == ICE_VSI_VF)
+ return;
+
+ ice_for_each_q_vector(vsi, i)
+ synchronize_irq(pf->msix_entries[i + base].vector);
+}
+
+/**
+ * ice_napi_del - Remove NAPI handler for the VSI
+ * @vsi: VSI for which NAPI handler is to be removed
+ */
+void ice_napi_del(struct ice_vsi *vsi)
+{
+ int v_idx;
+
+ if (!vsi->netdev)
+ return;
+
+ ice_for_each_q_vector(vsi, v_idx)
+ netif_napi_del(&vsi->q_vectors[v_idx]->napi);
+}
+
+/**
+ * ice_vsi_release - Delete a VSI and free its resources
+ * @vsi: the VSI being removed
+ *
+ * Returns 0 on success or < 0 on error
+ */
+int ice_vsi_release(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf;
+
+ if (!vsi->back)
+ return -ENODEV;
+ pf = vsi->back;
+
+ /* do not unregister while driver is in the reset recovery pending
+ * state. Since reset/rebuild happens through PF service task workqueue,
+ * it's not a good idea to unregister netdev that is associated to the
+ * PF that is running the work queue items currently. This is done to
+ * avoid check_flush_dependency() warning on this wq
+ */
+ if (vsi->netdev && !ice_is_reset_in_progress(pf->state))
+ unregister_netdev(vsi->netdev);
+
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_rss_clean(vsi);
+
+ /* Disable VSI and free resources */
+ if (vsi->type != ICE_VSI_LB)
+ ice_vsi_dis_irq(vsi);
+ ice_vsi_close(vsi);
+
+ /* SR-IOV determines needed MSIX resources all at once instead of per
+ * VSI since when VFs are spawned we know how many VFs there are and how
+ * many interrupts each VF needs. SR-IOV MSIX resources are also
+ * cleared in the same manner.
+ */
+ if (vsi->type != ICE_VSI_VF) {
+ /* reclaim SW interrupts back to the common pool */
+ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+ pf->num_avail_sw_msix += vsi->num_q_vectors;
+ }
+
+ if (!ice_is_safe_mode(pf)) {
+ if (vsi->type == ICE_VSI_PF) {
+ ice_vsi_add_rem_eth_mac(vsi, false);
+ ice_cfg_sw_lldp(vsi, true, false);
+ /* The Rx rule will only exist to remove if the LLDP FW
+ * engine is currently stopped
+ */
+ if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+ ice_cfg_sw_lldp(vsi, false, false);
+ }
+ }
+
+ ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+ ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+ ice_vsi_delete(vsi);
+ ice_vsi_free_q_vectors(vsi);
+
+ /* make sure unregister_netdev() was called by checking __ICE_DOWN */
+ if (vsi->netdev && test_bit(__ICE_DOWN, vsi->state)) {
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+
+ ice_vsi_clear_rings(vsi);
+
+ ice_vsi_put_qs(vsi);
+
+ /* retain SW VSI data structure since it is needed to unregister and
+ * free VSI netdev when PF is not in reset recovery pending state,\
+ * for ex: during rmmod.
+ */
+ if (!ice_is_reset_in_progress(pf->state))
+ ice_vsi_clear(vsi);
+
+ return 0;
+}
+
+/**
+ * ice_vsi_rebuild - Rebuild VSI after reset
+ * @vsi: VSI to be rebuild
+ *
+ * Returns 0 on success and negative value on failure
+ */
+int ice_vsi_rebuild(struct ice_vsi *vsi)
+{
+ u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+ struct ice_vf *vf = NULL;
+ enum ice_status status;
+ struct ice_pf *pf;
+ int ret, i;
+
+ if (!vsi)
+ return -EINVAL;
+
+ pf = vsi->back;
+ if (vsi->type == ICE_VSI_VF)
+ vf = &pf->vf[vsi->vf_id];
+
+ ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+ ice_vsi_free_q_vectors(vsi);
+
+ /* SR-IOV determines needed MSIX resources all at once instead of per
+ * VSI since when VFs are spawned we know how many VFs there are and how
+ * many interrupts each VF needs. SR-IOV MSIX resources are also
+ * cleared in the same manner.
+ */
+ if (vsi->type != ICE_VSI_VF) {
+ /* reclaim SW interrupts back to the common pool */
+ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+ pf->num_avail_sw_msix += vsi->num_q_vectors;
+ vsi->base_vector = 0;
+ }
+
+ ice_vsi_put_qs(vsi);
+ ice_vsi_clear_rings(vsi);
+ ice_vsi_free_arrays(vsi);
+ ice_dev_onetime_setup(&pf->hw);
+ if (vsi->type == ICE_VSI_VF)
+ ice_vsi_set_num_qs(vsi, vf->vf_id);
+ else
+ ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID);
+
+ ret = ice_vsi_alloc_arrays(vsi);
+ if (ret < 0)
+ goto err_vsi;
+
+ ice_vsi_get_qs(vsi);
+ ice_vsi_set_tc_cfg(vsi);
+
+ /* Initialize VSI struct elements and create VSI in FW */
+ ret = ice_vsi_init(vsi);
+ if (ret < 0)
+ goto err_vsi;
+
+
+ switch (vsi->type) {
+ case ICE_VSI_PF:
+ ret = ice_vsi_alloc_q_vectors(vsi);
+ if (ret)
+ goto err_rings;
+
+ ret = ice_vsi_setup_vector_base(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ice_vsi_map_rings_to_vectors(vsi);
+ /* Do not exit if configuring RSS had an issue, at least
+ * receive traffic on first queue. Hence no need to capture
+ * return value
+ */
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ ice_vsi_cfg_rss_lut_key(vsi);
+ break;
+ case ICE_VSI_VF:
+ ret = ice_vsi_alloc_q_vectors(vsi);
+ if (ret)
+ goto err_rings;
+
+ ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+ if (ret)
+ goto err_vectors;
+
+ ret = ice_vsi_alloc_rings(vsi);
+ if (ret)
+ goto err_vectors;
+
+ break;
+ default:
+ break;
+ }
+
+ /* configure VSI nodes based on number of queues and TC's */
+ for (i = 0; i < vsi->tc_cfg.numtc; i++)
+ max_txqs[i] = vsi->alloc_txq;
+
+ status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+ max_txqs);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "VSI %d failed lan queue config, error %d\n",
+ vsi->vsi_num, status);
+ goto err_vectors;
+ }
+ return 0;
+
+err_vectors:
+ ice_vsi_free_q_vectors(vsi);
+err_rings:
+ if (vsi->netdev) {
+ vsi->current_netdev_flags = 0;
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+err_vsi:
+ ice_vsi_clear(vsi);
+ set_bit(__ICE_RESET_FAILED, pf->state);
+ return ret;
+}
+
+/**
+ * ice_is_reset_in_progress - check for a reset in progress
+ * @state: PF state field
+ */
+bool ice_is_reset_in_progress(unsigned long *state)
+{
+ return test_bit(__ICE_RESET_OICR_RECV, state) ||
+ test_bit(__ICE_PFR_REQ, state) ||
+ test_bit(__ICE_CORER_REQ, state) ||
+ test_bit(__ICE_GLOBR_REQ, state);
+}
+
+#ifdef CONFIG_DCB
+/**
+ * ice_vsi_update_q_map - update our copy of the VSI info with new queue map
+ * @vsi: VSI being configured
+ * @ctx: the context buffer returned from AQ VSI update command
+ */
+static void ice_vsi_update_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctx)
+{
+ vsi->info.mapping_flags = ctx->info.mapping_flags;
+ memcpy(&vsi->info.q_mapping, &ctx->info.q_mapping,
+ sizeof(vsi->info.q_mapping));
+ memcpy(&vsi->info.tc_mapping, ctx->info.tc_mapping,
+ sizeof(vsi->info.tc_mapping));
+}
+
+/**
+ * ice_vsi_cfg_tc - Configure VSI Tx Sched for given TC map
+ * @vsi: VSI to be configured
+ * @ena_tc: TC bitmap
+ *
+ * VSI queues expected to be quiesced before calling this function
+ */
+int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
+{
+ u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+ struct ice_vsi_ctx *ctx;
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+ int i, ret = 0;
+ u8 num_tc = 0;
+
+ ice_for_each_traffic_class(i) {
+ /* build bitmap of enabled TCs */
+ if (ena_tc & BIT(i))
+ num_tc++;
+ /* populate max_txqs per TC */
+ max_txqs[i] = vsi->alloc_txq;
+ }
+
+ vsi->tc_cfg.ena_tc = ena_tc;
+ vsi->tc_cfg.numtc = num_tc;
+
+ ctx = devm_kzalloc(&pf->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->vf_num = 0;
+ ctx->info = vsi->info;
+
+ ice_vsi_setup_q_map(vsi, ctx);
+
+ /* must to indicate which section of VSI context are being modified */
+ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);
+ status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
+ if (status) {
+ dev_info(&pf->pdev->dev, "Failed VSI Update\n");
+ ret = -EIO;
+ goto out;
+ }
+
+ status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+ max_txqs);
+
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "VSI %d failed TC config, error %d\n",
+ vsi->vsi_num, status);
+ ret = -EIO;
+ goto out;
+ }
+ ice_vsi_update_q_map(vsi, ctx);
+ vsi->info.valid_sections = 0;
+
+ ice_vsi_cfg_netdev_tc(vsi, ena_tc);
+out:
+ devm_kfree(&pf->pdev->dev, ctx);
+ return ret;
+}
+#endif /* CONFIG_DCB */
+
+/**
+ * ice_nvm_version_str - format the NVM version strings
+ * @hw: ptr to the hardware info
+ */
+char *ice_nvm_version_str(struct ice_hw *hw)
+{
+ u8 oem_ver, oem_patch, ver_hi, ver_lo;
+ static char buf[ICE_NVM_VER_LEN];
+ u16 oem_build;
+
+ ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, &ver_hi,
+ &ver_lo);
+
+ snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", ver_hi, ver_lo,
+ hw->nvm.eetrack, oem_ver, oem_build, oem_patch);
+
+ return buf;
+}
+
+/**
+ * ice_vsi_cfg_mac_fltr - Add or remove a MAC address filter for a VSI
+ * @vsi: the VSI being configured MAC filter
+ * @macaddr: the MAC address to be added.
+ * @set: Add or delete a MAC filter
+ *
+ * Adds or removes MAC address filter entry for VF VSI
+ */
+enum ice_status
+ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set)
+{
+ LIST_HEAD(tmp_add_list);
+ enum ice_status status;
+
+ /* Update MAC filter list to be added or removed for a VSI */
+ if (ice_add_mac_to_list(vsi, &tmp_add_list, macaddr)) {
+ status = ICE_ERR_NO_MEMORY;
+ goto cfg_mac_fltr_exit;
+ }
+
+ if (set)
+ status = ice_add_mac(&vsi->back->hw, &tmp_add_list);
+ else
+ status = ice_remove_mac(&vsi->back->hw, &tmp_add_list);
+
+cfg_mac_fltr_exit:
+ ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list);
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
new file mode 100644
index 0000000..47bc033
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _ICE_LIB_H_
+#define _ICE_LIB_H_
+
+#include "ice.h"
+
+struct ice_txq_meta {
+ /* Tx-scheduler element identifier */
+ u32 q_teid;
+ /* Entry in VSI's txq_map bitmap */
+ u16 q_id;
+ /* Relative index of Tx queue within TC */
+ u16 q_handle;
+ /* VSI index that Tx queue belongs to */
+ u16 vsi_idx;
+ /* TC number that Tx queue belongs to */
+ u8 tc;
+};
+
+int
+ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
+ const u8 *macaddr);
+
+void ice_free_fltr_list(struct device *dev, struct list_head *h);
+
+void ice_update_eth_stats(struct ice_vsi *vsi);
+
+int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
+
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
+
+void ice_vsi_cfg_msix(struct ice_vsi *vsi);
+
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx);
+
+void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx);
+
+int
+ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+ u16 rel_vmvf_num, struct ice_ring *ring,
+ struct ice_txq_meta *txq_meta);
+
+void ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring,
+ struct ice_txq_meta *txq_meta);
+
+int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx);
+#endif /* CONFIG_PCI_IOV */
+
+int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid);
+
+int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid);
+
+int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi);
+
+int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena);
+
+int ice_vsi_start_rx_rings(struct ice_vsi *vsi);
+
+int ice_vsi_stop_rx_rings(struct ice_vsi *vsi);
+
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+ u16 rel_vmvf_num);
+
+int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc);
+
+void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+
+void ice_vsi_delete(struct ice_vsi *vsi);
+
+int ice_vsi_clear(struct ice_vsi *vsi);
+
+#ifdef CONFIG_DCB
+int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
+#endif /* CONFIG_DCB */
+
+struct ice_vsi *
+ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
+ enum ice_vsi_type type, u16 vf_id);
+
+void ice_napi_del(struct ice_vsi *vsi);
+
+int ice_vsi_release(struct ice_vsi *vsi);
+
+void ice_vsi_close(struct ice_vsi *vsi);
+
+int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id);
+
+int
+ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id);
+
+int ice_vsi_rebuild(struct ice_vsi *vsi);
+
+bool ice_is_reset_in_progress(unsigned long *state);
+
+void ice_vsi_free_q_vectors(struct ice_vsi *vsi);
+
+void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector);
+
+void ice_vsi_put_qs(struct ice_vsi *vsi);
+
+#ifdef CONFIG_DCB
+void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi);
+#endif /* CONFIG_DCB */
+
+void ice_vsi_dis_irq(struct ice_vsi *vsi);
+
+void ice_vsi_free_irq(struct ice_vsi *vsi);
+
+void ice_vsi_free_rx_rings(struct ice_vsi *vsi);
+
+void ice_vsi_free_tx_rings(struct ice_vsi *vsi);
+
+int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena);
+
+u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran);
+
+char *ice_nvm_version_str(struct ice_hw *hw);
+
+enum ice_status
+ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set);
+
+bool ice_is_safe_mode(struct ice_pf *pf);
+#endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 3f047bb..214cd6e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6,17 +6,30 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
-#define DRV_VERSION "ice-0.7.0-k"
+#define DRV_VERSION_MAJOR 0
+#define DRV_VERSION_MINOR 8
+#define DRV_VERSION_BUILD 1
+
+#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
+ __stringify(DRV_VERSION_MINOR) "." \
+ __stringify(DRV_VERSION_BUILD) "-k"
#define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver"
const char ice_drv_ver[] = DRV_VERSION;
static const char ice_driver_string[] = DRV_SUMMARY;
static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
+/* DDP Package file located in firmware search paths (e.g. /lib/firmware/) */
+#define ICE_DDP_PKG_PATH "intel/ice/ddp/"
+#define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg"
+
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION(DRV_SUMMARY);
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
+MODULE_FIRMWARE(ICE_DDP_PKG_FILE);
static int debug = -1;
module_param(debug, int, 0644);
@@ -27,188 +40,145 @@
#endif /* !CONFIG_DYNAMIC_DEBUG */
static struct workqueue_struct *ice_wq;
+static const struct net_device_ops ice_netdev_safe_mode_ops;
static const struct net_device_ops ice_netdev_ops;
-static void ice_pf_dis_all_vsi(struct ice_pf *pf);
-static void ice_rebuild(struct ice_pf *pf);
-static int ice_vsi_release(struct ice_vsi *vsi);
-static void ice_update_vsi_stats(struct ice_vsi *vsi);
-static void ice_update_pf_stats(struct ice_pf *pf);
+static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type);
+
+static void ice_vsi_release_all(struct ice_pf *pf);
/**
- * ice_get_free_slot - get the next non-NULL location index in array
- * @array: array to search
- * @size: size of the array
- * @curr: last known occupied index to be used as a search hint
- *
- * void * is being used to keep the functionality generic. This lets us use this
- * function on any array of pointers.
+ * ice_get_tx_pending - returns number of Tx descriptors not processed
+ * @ring: the ring of descriptors
*/
-static int ice_get_free_slot(void *array, int size, int curr)
+static u16 ice_get_tx_pending(struct ice_ring *ring)
{
- int **tmp_array = (int **)array;
- int next;
+ u16 head, tail;
- if (curr < (size - 1) && !tmp_array[curr + 1]) {
- next = curr + 1;
- } else {
- int i = 0;
+ head = ring->next_to_clean;
+ tail = ring->next_to_use;
- while ((i < size) && (tmp_array[i]))
- i++;
- if (i == size)
- next = ICE_NO_VSI;
- else
- next = i;
- }
- return next;
-}
-
-/**
- * ice_search_res - Search the tracker for a block of resources
- * @res: pointer to the resource
- * @needed: size of the block needed
- * @id: identifier to track owner
- * Returns the base item index of the block, or -ENOMEM for error
- */
-static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
-{
- int start = res->search_hint;
- int end = start;
-
- id |= ICE_RES_VALID_BIT;
-
- do {
- /* skip already allocated entries */
- if (res->list[end++] & ICE_RES_VALID_BIT) {
- start = end;
- if ((start + needed) > res->num_entries)
- break;
- }
-
- if (end == (start + needed)) {
- int i = start;
-
- /* there was enough, so assign it to the requestor */
- while (i != end)
- res->list[i++] = id;
-
- if (end == res->num_entries)
- end = 0;
-
- res->search_hint = end;
- return start;
- }
- } while (1);
-
- return -ENOMEM;
-}
-
-/**
- * ice_get_res - get a block of resources
- * @pf: board private structure
- * @res: pointer to the resource
- * @needed: size of the block needed
- * @id: identifier to track owner
- *
- * Returns the base item index of the block, or -ENOMEM for error
- * The search_hint trick and lack of advanced fit-finding only works
- * because we're highly likely to have all the same sized requests.
- * Linear search time and any fragmentation should be minimal.
- */
-static int
-ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
-{
- int ret;
-
- if (!res || !pf)
- return -EINVAL;
-
- if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) {
- dev_err(&pf->pdev->dev,
- "param err: needed=%d, num_entries = %d id=0x%04x\n",
- needed, res->num_entries, id);
- return -EINVAL;
- }
-
- /* search based on search_hint */
- ret = ice_search_res(res, needed, id);
-
- if (ret < 0) {
- /* previous search failed. Reset search hint and try again */
- res->search_hint = 0;
- ret = ice_search_res(res, needed, id);
- }
-
- return ret;
-}
-
-/**
- * ice_free_res - free a block of resources
- * @res: pointer to the resource
- * @index: starting index previously returned by ice_get_res
- * @id: identifier to track owner
- * Returns number of resources freed
- */
-static int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
-{
- int count = 0;
- int i;
-
- if (!res || index >= res->num_entries)
- return -EINVAL;
-
- id |= ICE_RES_VALID_BIT;
- for (i = index; i < res->num_entries && res->list[i] == id; i++) {
- res->list[i] = 0;
- count++;
- }
-
- return count;
-}
-
-/**
- * ice_add_mac_to_list - Add a mac address filter entry to the list
- * @vsi: the VSI to be forwarded to
- * @add_list: pointer to the list which contains MAC filter entries
- * @macaddr: the MAC address to be added.
- *
- * Adds mac address filter entry to the temp list
- *
- * Returns 0 on success or ENOMEM on failure.
- */
-static int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
- const u8 *macaddr)
-{
- struct ice_fltr_list_entry *tmp;
- struct ice_pf *pf = vsi->back;
-
- tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_ATOMIC);
- if (!tmp)
- return -ENOMEM;
-
- tmp->fltr_info.flag = ICE_FLTR_TX;
- tmp->fltr_info.src = vsi->vsi_num;
- tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC;
- tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
- tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num;
- ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr);
-
- INIT_LIST_HEAD(&tmp->list_entry);
- list_add(&tmp->list_entry, add_list);
-
+ if (head != tail)
+ return (head < tail) ?
+ tail - head : (tail + ring->count - head);
return 0;
}
/**
- * ice_add_mac_to_sync_list - creates list of mac addresses to be synced
+ * ice_check_for_hang_subtask - check for and recover hung queues
+ * @pf: pointer to PF struct
+ */
+static void ice_check_for_hang_subtask(struct ice_pf *pf)
+{
+ struct ice_vsi *vsi = NULL;
+ struct ice_hw *hw;
+ unsigned int i;
+ int packets;
+ u32 v;
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) {
+ vsi = pf->vsi[v];
+ break;
+ }
+
+ if (!vsi || test_bit(__ICE_DOWN, vsi->state))
+ return;
+
+ if (!(vsi->netdev && netif_carrier_ok(vsi->netdev)))
+ return;
+
+ hw = &vsi->back->hw;
+
+ for (i = 0; i < vsi->num_txq; i++) {
+ struct ice_ring *tx_ring = vsi->tx_rings[i];
+
+ if (tx_ring && tx_ring->desc) {
+ /* If packet counter has not changed the queue is
+ * likely stalled, so force an interrupt for this
+ * queue.
+ *
+ * prev_pkt would be negative if there was no
+ * pending work.
+ */
+ packets = tx_ring->stats.pkts & INT_MAX;
+ if (tx_ring->tx_stats.prev_pkt == packets) {
+ /* Trigger sw interrupt to revive the queue */
+ ice_trigger_sw_intr(hw, tx_ring->q_vector);
+ continue;
+ }
+
+ /* Memory barrier between read of packet count and call
+ * to ice_get_tx_pending()
+ */
+ smp_rmb();
+ tx_ring->tx_stats.prev_pkt =
+ ice_get_tx_pending(tx_ring) ? packets : -1;
+ }
+ }
+}
+
+/**
+ * ice_init_mac_fltr - Set initial MAC filters
+ * @pf: board private structure
+ *
+ * Set initial set of MAC filters for PF VSI; configure filters for permanent
+ * address and broadcast address. If an error is encountered, netdevice will be
+ * unregistered.
+ */
+static int ice_init_mac_fltr(struct ice_pf *pf)
+{
+ enum ice_status status;
+ u8 broadcast[ETH_ALEN];
+ struct ice_vsi *vsi;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi)
+ return -EINVAL;
+
+ /* To add a MAC filter, first add the MAC to a list and then
+ * pass the list to ice_add_mac.
+ */
+
+ /* Add a unicast MAC filter so the VSI can get its packets */
+ status = ice_vsi_cfg_mac_fltr(vsi, vsi->port_info->mac.perm_addr, true);
+ if (status)
+ goto unregister;
+
+ /* VSI needs to receive broadcast traffic, so add the broadcast
+ * MAC address to the list as well.
+ */
+ eth_broadcast_addr(broadcast);
+ status = ice_vsi_cfg_mac_fltr(vsi, broadcast, true);
+ if (status)
+ goto unregister;
+
+ return 0;
+unregister:
+ /* We aren't useful with no MAC filters, so unregister if we
+ * had an error
+ */
+ if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
+ dev_err(&pf->pdev->dev,
+ "Could not add MAC filters error %d. Unregistering device\n",
+ status);
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
+
+ return -EIO;
+}
+
+/**
+ * ice_add_mac_to_sync_list - creates list of MAC addresses to be synced
* @netdev: the net device on which the sync is happening
- * @addr: mac address to sync
+ * @addr: MAC address to sync
*
* This is a callback function which is called by the in kernel device sync
* functions (like __dev_uc_sync, __dev_mc_sync, etc). This function only
* populates the tmp_sync_list, which is later used by ice_add_mac to add the
- * mac filters from the hardware.
+ * MAC filters from the hardware.
*/
static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
{
@@ -222,14 +192,14 @@
}
/**
- * ice_add_mac_to_unsync_list - creates list of mac addresses to be unsynced
+ * ice_add_mac_to_unsync_list - creates list of MAC addresses to be unsynced
* @netdev: the net device on which the unsync is happening
- * @addr: mac address to unsync
+ * @addr: MAC address to unsync
*
* This is a callback function which is called by the in kernel device unsync
* functions (like __dev_uc_unsync, __dev_mc_unsync, etc). This function only
* populates the tmp_unsync_list, which is later used by ice_remove_mac to
- * delete the mac filters from the hardware.
+ * delete the MAC filters from the hardware.
*/
static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
{
@@ -243,24 +213,6 @@
}
/**
- * ice_free_fltr_list - free filter lists helper
- * @dev: pointer to the device struct
- * @h: pointer to the list head to be freed
- *
- * Helper function to free filter lists previously created using
- * ice_add_mac_to_list
- */
-static void ice_free_fltr_list(struct device *dev, struct list_head *h)
-{
- struct ice_fltr_list_entry *e, *tmp;
-
- list_for_each_entry_safe(e, tmp, h, list_entry) {
- list_del(&e->list_entry);
- devm_kfree(dev, e);
- }
-}
-
-/**
* ice_vsi_fltr_changed - check if filter state changed
* @vsi: VSI to be checked
*
@@ -274,6 +226,39 @@
}
/**
+ * ice_cfg_promisc - Enable or disable promiscuous mode for a given PF
+ * @vsi: the VSI being configured
+ * @promisc_m: mask of promiscuous config bits
+ * @set_promisc: enable or disable promisc flag request
+ *
+ */
+static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc)
+{
+ struct ice_hw *hw = &vsi->back->hw;
+ enum ice_status status = 0;
+
+ if (vsi->type != ICE_VSI_PF)
+ return 0;
+
+ if (vsi->vlan_ena) {
+ status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
+ set_promisc);
+ } else {
+ if (set_promisc)
+ status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+ 0);
+ else
+ status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+ 0);
+ }
+
+ if (status)
+ return -EIO;
+
+ return 0;
+}
+
+/**
* ice_vsi_sync_fltr - Update the VSI filter list to the HW
* @vsi: ptr to the VSI
*
@@ -288,6 +273,7 @@
struct ice_hw *hw = &pf->hw;
enum ice_status status = 0;
u32 changed_flags = 0;
+ u8 promisc_m;
int err = 0;
if (!vsi->netdev)
@@ -317,7 +303,7 @@
netif_addr_unlock_bh(netdev);
}
- /* Remove mac addresses in the unsync list */
+ /* Remove MAC addresses in the unsync list */
status = ice_remove_mac(hw, &vsi->tmp_unsync_list);
ice_free_fltr_list(dev, &vsi->tmp_unsync_list);
if (status) {
@@ -329,12 +315,16 @@
}
}
- /* Add mac addresses in the sync list */
+ /* Add MAC addresses in the sync list */
status = ice_add_mac(hw, &vsi->tmp_sync_list);
ice_free_fltr_list(dev, &vsi->tmp_sync_list);
- if (status) {
+ /* If filter is added successfully or already exists, do not go into
+ * 'if' condition and report it as error. Instead continue processing
+ * rest of the function.
+ */
+ if (status && status != ICE_ERR_ALREADY_EXISTS) {
netdev_err(netdev, "Failed to add MAC filters\n");
- /* If there is no more space for new umac filters, vsi
+ /* If there is no more space for new umac filters, VSI
* should go into promiscuous mode. There should be some
* space reserved for promiscuous filters.
*/
@@ -351,49 +341,56 @@
}
}
/* check for changes in promiscuous modes */
- if (changed_flags & IFF_ALLMULTI)
- netdev_warn(netdev, "Unsupported configuration\n");
+ if (changed_flags & IFF_ALLMULTI) {
+ if (vsi->current_netdev_flags & IFF_ALLMULTI) {
+ if (vsi->vlan_ena)
+ promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+ else
+ promisc_m = ICE_MCAST_PROMISC_BITS;
+
+ err = ice_cfg_promisc(vsi, promisc_m, true);
+ if (err) {
+ netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags &= ~IFF_ALLMULTI;
+ goto out_promisc;
+ }
+ } else if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) {
+ if (vsi->vlan_ena)
+ promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+ else
+ promisc_m = ICE_MCAST_PROMISC_BITS;
+
+ err = ice_cfg_promisc(vsi, promisc_m, false);
+ if (err) {
+ netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n",
+ vsi->vsi_num);
+ vsi->current_netdev_flags |= IFF_ALLMULTI;
+ goto out_promisc;
+ }
+ }
+ }
if (((changed_flags & IFF_PROMISC) || promisc_forced_on) ||
test_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags)) {
clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
if (vsi->current_netdev_flags & IFF_PROMISC) {
- /* Apply TX filter rule to get traffic from VMs */
- status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true,
- ICE_FLTR_TX);
- if (status) {
- netdev_err(netdev, "Error setting default VSI %i tx rule\n",
- vsi->vsi_num);
- vsi->current_netdev_flags &= ~IFF_PROMISC;
- err = -EIO;
- goto out_promisc;
- }
- /* Apply RX filter rule to get traffic from wire */
- status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, true,
+ /* Apply Rx filter rule to get traffic from wire */
+ status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
ICE_FLTR_RX);
if (status) {
- netdev_err(netdev, "Error setting default VSI %i rx rule\n",
+ netdev_err(netdev, "Error setting default VSI %i Rx rule\n",
vsi->vsi_num);
vsi->current_netdev_flags &= ~IFF_PROMISC;
err = -EIO;
goto out_promisc;
}
} else {
- /* Clear TX filter rule to stop traffic from VMs */
- status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false,
- ICE_FLTR_TX);
- if (status) {
- netdev_err(netdev, "Error clearing default VSI %i tx rule\n",
- vsi->vsi_num);
- vsi->current_netdev_flags |= IFF_PROMISC;
- err = -EIO;
- goto out_promisc;
- }
- /* Clear filter RX to remove traffic from wire */
- status = ice_cfg_dflt_vsi(hw, vsi->vsi_num, false,
+ /* Clear Rx filter to remove traffic from wire */
+ status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
ICE_FLTR_RX);
if (status) {
- netdev_err(netdev, "Error clearing default VSI %i rx rule\n",
+ netdev_err(netdev, "Error clearing default VSI %i Rx rule\n",
vsi->vsi_num);
vsi->current_netdev_flags |= IFF_PROMISC;
err = -EIO;
@@ -428,7 +425,7 @@
clear_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
- for (v = 0; v < pf->num_alloc_vsi; v++)
+ ice_for_each_vsi(pf, v)
if (pf->vsi[v] && ice_vsi_fltr_changed(pf->vsi[v]) &&
ice_vsi_sync_fltr(pf->vsi[v])) {
/* come back and try again later */
@@ -438,12 +435,48 @@
}
/**
- * ice_is_reset_recovery_pending - schedule a reset
- * @state: pf state field
+ * ice_dis_vsi - pause a VSI
+ * @vsi: the VSI being paused
+ * @locked: is the rtnl_lock already held
*/
-static bool ice_is_reset_recovery_pending(unsigned long int *state)
+static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
{
- return test_bit(__ICE_RESET_RECOVERY_PENDING, state);
+ if (test_bit(__ICE_DOWN, vsi->state))
+ return;
+
+ set_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+ if (vsi->type == ICE_VSI_PF && vsi->netdev) {
+ if (netif_running(vsi->netdev)) {
+ if (!locked)
+ rtnl_lock();
+
+ ice_stop(vsi->netdev);
+
+ if (!locked)
+ rtnl_unlock();
+ } else {
+ ice_vsi_close(vsi);
+ }
+ }
+}
+
+/**
+ * ice_pf_dis_all_vsi - Pause all VSIs on a PF
+ * @pf: the PF
+ * @locked: is the rtnl_lock already held
+ */
+#ifdef CONFIG_DCB
+void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#else
+static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#endif /* CONFIG_DCB */
+{
+ int v;
+
+ ice_for_each_vsi(pf, v)
+ if (pf->vsi[v])
+ ice_dis_vsi(pf->vsi[v], locked);
}
/**
@@ -456,23 +489,31 @@
ice_prepare_for_reset(struct ice_pf *pf)
{
struct ice_hw *hw = &pf->hw;
- u32 v;
+ int i;
- ice_for_each_vsi(pf, v)
- if (pf->vsi[v])
- ice_remove_vsi_fltr(hw, pf->vsi[v]->vsi_num);
+ /* already prepared for reset */
+ if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
+ return;
- dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
+ /* Notify VFs of impending reset */
+ if (ice_check_sq_alive(hw, &hw->mailboxq))
+ ice_vc_notify_reset(pf);
+ /* Disable VFs until reset is completed */
+ for (i = 0; i < pf->num_alloc_vfs; i++)
+ ice_set_vf_state_qs_dis(&pf->vf[i]);
+
+ /* clear SW filtering DB */
+ ice_clear_hw_tbls(hw);
/* disable the VSIs and their queues that are not already DOWN */
- /* pf_dis_all_vsi modifies netdev structures -rtnl_lock needed */
- ice_pf_dis_all_vsi(pf);
+ ice_pf_dis_all_vsi(pf, false);
- ice_for_each_vsi(pf, v)
- if (pf->vsi[v])
- pf->vsi[v]->vsi_num = 0;
+ if (hw->port_info)
+ ice_sched_clear_port(hw->port_info);
ice_shutdown_all_ctrlq(hw);
+
+ set_bit(__ICE_PREPARED_FOR_RESET, pf->state);
}
/**
@@ -489,27 +530,30 @@
dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
WARN_ON(in_interrupt());
- /* PFR is a bit of a special case because it doesn't result in an OICR
- * interrupt. So for PFR, we prepare for reset, issue the reset and
- * rebuild sequentially.
- */
- if (reset_type == ICE_RESET_PFR) {
- set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
- ice_prepare_for_reset(pf);
- }
+ ice_prepare_for_reset(pf);
/* trigger the reset */
if (ice_reset(hw, reset_type)) {
dev_err(dev, "reset %d failed\n", reset_type);
set_bit(__ICE_RESET_FAILED, pf->state);
- clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ clear_bit(__ICE_RESET_OICR_RECV, pf->state);
+ clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
+ clear_bit(__ICE_PFR_REQ, pf->state);
+ clear_bit(__ICE_CORER_REQ, pf->state);
+ clear_bit(__ICE_GLOBR_REQ, pf->state);
return;
}
+ /* PFR is a bit of a special case because it doesn't result in an OICR
+ * interrupt. So for PFR, rebuild after the reset and clear the reset-
+ * associated state bits.
+ */
if (reset_type == ICE_RESET_PFR) {
pf->pfr_count++;
- ice_rebuild(pf);
- clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ ice_rebuild(pf, reset_type);
+ clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
+ clear_bit(__ICE_PFR_REQ, pf->state);
+ ice_reset_all_vfs(pf, true);
}
}
@@ -519,77 +563,84 @@
*/
static void ice_reset_subtask(struct ice_pf *pf)
{
- enum ice_reset_req reset_type;
-
- rtnl_lock();
+ enum ice_reset_req reset_type = ICE_RESET_INVAL;
/* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an
- * OICR interrupt. The OICR handler (ice_misc_intr) determines what
- * type of reset happened and sets __ICE_RESET_RECOVERY_PENDING bit in
- * pf->state. So if reset/recovery is pending (as indicated by this bit)
- * we do a rebuild and return.
+ * OICR interrupt. The OICR handler (ice_misc_intr) determines what type
+ * of reset is pending and sets bits in pf->state indicating the reset
+ * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set
+ * prepare for pending reset if not already (for PF software-initiated
+ * global resets the software should already be prepared for it as
+ * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated
+ * by firmware or software on other PFs, that bit is not set so prepare
+ * for the reset now), poll for reset done, rebuild and return.
*/
- if (ice_is_reset_recovery_pending(pf->state)) {
- clear_bit(__ICE_GLOBR_RECV, pf->state);
- clear_bit(__ICE_CORER_RECV, pf->state);
+ if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) {
+ /* Perform the largest reset requested */
+ if (test_and_clear_bit(__ICE_CORER_RECV, pf->state))
+ reset_type = ICE_RESET_CORER;
+ if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state))
+ reset_type = ICE_RESET_GLOBR;
+ if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state))
+ reset_type = ICE_RESET_EMPR;
+ /* return if no valid reset type requested */
+ if (reset_type == ICE_RESET_INVAL)
+ return;
ice_prepare_for_reset(pf);
/* make sure we are ready to rebuild */
- if (ice_check_reset(&pf->hw))
+ if (ice_check_reset(&pf->hw)) {
set_bit(__ICE_RESET_FAILED, pf->state);
- else
- ice_rebuild(pf);
- clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
- goto unlock;
+ } else {
+ /* done with reset. start rebuild */
+ pf->hw.reset_ongoing = false;
+ ice_rebuild(pf, reset_type);
+ /* clear bit to resume normal operations, but
+ * ICE_NEEDS_RESTART bit is set in case rebuild failed
+ */
+ clear_bit(__ICE_RESET_OICR_RECV, pf->state);
+ clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
+ clear_bit(__ICE_PFR_REQ, pf->state);
+ clear_bit(__ICE_CORER_REQ, pf->state);
+ clear_bit(__ICE_GLOBR_REQ, pf->state);
+ ice_reset_all_vfs(pf, true);
+ }
+
+ return;
}
/* No pending resets to finish processing. Check for new resets */
- if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state))
- reset_type = ICE_RESET_GLOBR;
- else if (test_and_clear_bit(__ICE_CORER_REQ, pf->state))
- reset_type = ICE_RESET_CORER;
- else if (test_and_clear_bit(__ICE_PFR_REQ, pf->state))
+ if (test_bit(__ICE_PFR_REQ, pf->state))
reset_type = ICE_RESET_PFR;
- else
- goto unlock;
+ if (test_bit(__ICE_CORER_REQ, pf->state))
+ reset_type = ICE_RESET_CORER;
+ if (test_bit(__ICE_GLOBR_REQ, pf->state))
+ reset_type = ICE_RESET_GLOBR;
+ /* If no valid reset type requested just return */
+ if (reset_type == ICE_RESET_INVAL)
+ return;
- /* reset if not already down or resetting */
+ /* reset if not already down or busy */
if (!test_bit(__ICE_DOWN, pf->state) &&
!test_bit(__ICE_CFG_BUSY, pf->state)) {
ice_do_reset(pf, reset_type);
}
-
-unlock:
- rtnl_unlock();
}
/**
- * ice_watchdog_subtask - periodic tasks not using event driven scheduling
- * @pf: board private structure
+ * ice_print_topo_conflict - print topology conflict message
+ * @vsi: the VSI whose topology status is being checked
*/
-static void ice_watchdog_subtask(struct ice_pf *pf)
+static void ice_print_topo_conflict(struct ice_vsi *vsi)
{
- int i;
-
- /* if interface is down do nothing */
- if (test_bit(__ICE_DOWN, pf->state) ||
- test_bit(__ICE_CFG_BUSY, pf->state))
- return;
-
- /* make sure we don't do these things too often */
- if (time_before(jiffies,
- pf->serv_tmr_prev + pf->serv_tmr_period))
- return;
-
- pf->serv_tmr_prev = jiffies;
-
- /* Update the stats for active netdevs so the network stack
- * can look at updated numbers whenever it cares to
- */
- ice_update_pf_stats(pf);
- for (i = 0; i < pf->num_alloc_vsi; i++)
- if (pf->vsi[i] && pf->vsi[i]->netdev)
- ice_update_vsi_stats(pf->vsi[i]);
+ switch (vsi->port_info->phy.link_info.topo_media_conflict) {
+ case ICE_AQ_LINK_TOPO_CONFLICT:
+ case ICE_AQ_LINK_MEDIA_CONFLICT:
+ netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n");
+ break;
+ default:
+ break;
+ }
}
/**
@@ -599,8 +650,16 @@
*/
void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
{
+ struct ice_aqc_get_phy_caps_data *caps;
+ enum ice_status status;
+ const char *fec_req;
const char *speed;
+ const char *fec;
const char *fc;
+ const char *an;
+
+ if (!vsi)
+ return;
if (vsi->current_isup == isup)
return;
@@ -613,6 +672,12 @@
}
switch (vsi->port_info->phy.link_info.link_speed) {
+ case ICE_AQ_LINK_SPEED_100GB:
+ speed = "100 G";
+ break;
+ case ICE_AQ_LINK_SPEED_50GB:
+ speed = "50 G";
+ break;
case ICE_AQ_LINK_SPEED_40GB:
speed = "40 G";
break;
@@ -644,21 +709,191 @@
switch (vsi->port_info->fc.current_mode) {
case ICE_FC_FULL:
- fc = "RX/TX";
+ fc = "Rx/Tx";
break;
case ICE_FC_TX_PAUSE:
- fc = "TX";
+ fc = "Tx";
break;
case ICE_FC_RX_PAUSE:
- fc = "RX";
+ fc = "Rx";
+ break;
+ case ICE_FC_NONE:
+ fc = "None";
break;
default:
fc = "Unknown";
break;
}
- netdev_info(vsi->netdev, "NIC Link is up %sbps, Flow Control: %s\n",
- speed, fc);
+ /* Get FEC mode based on negotiated link info */
+ switch (vsi->port_info->phy.link_info.fec_info) {
+ case ICE_AQ_LINK_25G_RS_528_FEC_EN:
+ /* fall through */
+ case ICE_AQ_LINK_25G_RS_544_FEC_EN:
+ fec = "RS-FEC";
+ break;
+ case ICE_AQ_LINK_25G_KR_FEC_EN:
+ fec = "FC-FEC/BASE-R";
+ break;
+ default:
+ fec = "NONE";
+ break;
+ }
+
+ /* check if autoneg completed, might be false due to not supported */
+ if (vsi->port_info->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)
+ an = "True";
+ else
+ an = "False";
+
+ /* Get FEC mode requested based on PHY caps last SW configuration */
+ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+ if (!caps) {
+ fec_req = "Unknown";
+ goto done;
+ }
+
+ status = ice_aq_get_phy_caps(vsi->port_info, false,
+ ICE_AQC_REPORT_SW_CFG, caps, NULL);
+ if (status)
+ netdev_info(vsi->netdev, "Get phy capability failed.\n");
+
+ if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ)
+ fec_req = "RS-FEC";
+ else if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+ caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+ fec_req = "FC-FEC/BASE-R";
+ else
+ fec_req = "NONE";
+
+ devm_kfree(&vsi->back->pdev->dev, caps);
+
+done:
+ netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n",
+ speed, fec_req, fec, an, fc);
+ ice_print_topo_conflict(vsi);
+}
+
+/**
+ * ice_vsi_link_event - update the VSI's netdev
+ * @vsi: the VSI on which the link event occurred
+ * @link_up: whether or not the VSI needs to be set up or down
+ */
+static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
+{
+ if (!vsi)
+ return;
+
+ if (test_bit(__ICE_DOWN, vsi->state) || !vsi->netdev)
+ return;
+
+ if (vsi->type == ICE_VSI_PF) {
+ if (link_up == netif_carrier_ok(vsi->netdev))
+ return;
+
+ if (link_up) {
+ netif_carrier_on(vsi->netdev);
+ netif_tx_wake_all_queues(vsi->netdev);
+ } else {
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_all_queues(vsi->netdev);
+ }
+ }
+}
+
+/**
+ * ice_link_event - process the link event
+ * @pf: PF that the link event is associated with
+ * @pi: port_info for the port that the link event is associated with
+ * @link_up: true if the physical link is up and false if it is down
+ * @link_speed: current link speed received from the link event
+ *
+ * Returns 0 on success and negative on failure
+ */
+static int
+ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
+ u16 link_speed)
+{
+ struct ice_phy_info *phy_info;
+ struct ice_vsi *vsi;
+ u16 old_link_speed;
+ bool old_link;
+ int result;
+
+ phy_info = &pi->phy;
+ phy_info->link_info_old = phy_info->link_info;
+
+ old_link = !!(phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
+ old_link_speed = phy_info->link_info_old.link_speed;
+
+ /* update the link info structures and re-enable link events,
+ * don't bail on failure due to other book keeping needed
+ */
+ result = ice_update_link_info(pi);
+ if (result)
+ dev_dbg(&pf->pdev->dev,
+ "Failed to update link status and re-enable link events for port %d\n",
+ pi->lport);
+
+ /* if the old link up/down and speed is the same as the new */
+ if (link_up == old_link && link_speed == old_link_speed)
+ return result;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi || !vsi->port_info)
+ return -EINVAL;
+
+ /* turn off PHY if media was removed */
+ if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) &&
+ !(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) {
+ set_bit(ICE_FLAG_NO_MEDIA, pf->flags);
+
+ result = ice_aq_set_link_restart_an(pi, false, NULL);
+ if (result) {
+ dev_dbg(&pf->pdev->dev,
+ "Failed to set link down, VSI %d error %d\n",
+ vsi->vsi_num, result);
+ return result;
+ }
+ }
+
+ ice_vsi_link_event(vsi, link_up);
+ ice_print_link_msg(vsi, link_up);
+
+ if (pf->num_alloc_vfs)
+ ice_vc_notify_link_state(pf);
+
+ return result;
+}
+
+/**
+ * ice_watchdog_subtask - periodic tasks not using event driven scheduling
+ * @pf: board private structure
+ */
+static void ice_watchdog_subtask(struct ice_pf *pf)
+{
+ int i;
+
+ /* if interface is down do nothing */
+ if (test_bit(__ICE_DOWN, pf->state) ||
+ test_bit(__ICE_CFG_BUSY, pf->state))
+ return;
+
+ /* make sure we don't do these things too often */
+ if (time_before(jiffies,
+ pf->serv_tmr_prev + pf->serv_tmr_period))
+ return;
+
+ pf->serv_tmr_prev = jiffies;
+
+ /* Update the stats for active netdevs so the network stack
+ * can look at updated numbers whenever it cares to
+ */
+ ice_update_pf_stats(pf);
+ ice_for_each_vsi(pf, i)
+ if (pf->vsi[i] && pf->vsi[i]->netdev)
+ ice_update_vsi_stats(pf->vsi[i]);
}
/**
@@ -692,106 +927,25 @@
}
/**
- * ice_vsi_link_event - update the vsi's netdev
- * @vsi: the vsi on which the link event occurred
- * @link_up: whether or not the vsi needs to be set up or down
- */
-static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
-{
- if (!vsi || test_bit(__ICE_DOWN, vsi->state))
- return;
-
- if (vsi->type == ICE_VSI_PF) {
- if (!vsi->netdev) {
- dev_dbg(&vsi->back->pdev->dev,
- "vsi->netdev is not initialized!\n");
- return;
- }
- if (link_up) {
- netif_carrier_on(vsi->netdev);
- netif_tx_wake_all_queues(vsi->netdev);
- } else {
- netif_carrier_off(vsi->netdev);
- netif_tx_stop_all_queues(vsi->netdev);
- }
- }
-}
-
-/**
- * ice_link_event - process the link event
- * @pf: pf that the link event is associated with
- * @pi: port_info for the port that the link event is associated with
- *
- * Returns -EIO if ice_get_link_status() fails
- * Returns 0 on success
+ * ice_handle_link_event - handle link event via ARQ
+ * @pf: PF that the link event is associated with
+ * @event: event structure containing link status info
*/
static int
-ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
+ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
{
- u8 new_link_speed, old_link_speed;
- struct ice_phy_info *phy_info;
- bool new_link_same_as_old;
- bool new_link, old_link;
- u8 lport;
- u16 v;
-
- phy_info = &pi->phy;
- phy_info->link_info_old = phy_info->link_info;
- /* Force ice_get_link_status() to update link info */
- phy_info->get_link_info = true;
-
- old_link = (phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
- old_link_speed = phy_info->link_info_old.link_speed;
-
- lport = pi->lport;
- if (ice_get_link_status(pi, &new_link)) {
- dev_dbg(&pf->pdev->dev,
- "Could not get link status for port %d\n", lport);
- return -EIO;
- }
-
- new_link_speed = phy_info->link_info.link_speed;
-
- new_link_same_as_old = (new_link == old_link &&
- new_link_speed == old_link_speed);
-
- ice_for_each_vsi(pf, v) {
- struct ice_vsi *vsi = pf->vsi[v];
-
- if (!vsi || !vsi->port_info)
- continue;
-
- if (new_link_same_as_old &&
- (test_bit(__ICE_DOWN, vsi->state) ||
- new_link == netif_carrier_ok(vsi->netdev)))
- continue;
-
- if (vsi->port_info->lport == lport) {
- ice_print_link_msg(vsi, new_link);
- ice_vsi_link_event(vsi, new_link);
- }
- }
-
- return 0;
-}
-
-/**
- * ice_handle_link_event - handle link event via ARQ
- * @pf: pf that the link event is associated with
- *
- * Return -EINVAL if port_info is null
- * Return status on succes
- */
-static int ice_handle_link_event(struct ice_pf *pf)
-{
+ struct ice_aqc_get_link_status_data *link_data;
struct ice_port_info *port_info;
int status;
+ link_data = (struct ice_aqc_get_link_status_data *)event->msg_buf;
port_info = pf->hw.port_info;
if (!port_info)
return -EINVAL;
- status = ice_link_event(pf, port_info);
+ status = ice_link_event(pf, port_info,
+ !!(link_data->link_info & ICE_AQ_LINK_UP),
+ le16_to_cpu(link_data->link_speed));
if (status)
dev_dbg(&pf->pdev->dev,
"Could not process link event, error %d\n", status);
@@ -822,6 +976,10 @@
cq = &hw->adminq;
qtype = "Admin";
break;
+ case ICE_CTL_Q_MAILBOX:
+ cq = &hw->mailboxq;
+ qtype = "Mailbox";
+ break;
default:
dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n",
q_type);
@@ -899,10 +1057,19 @@
switch (opcode) {
case ice_aqc_opc_get_link_status:
- if (ice_handle_link_event(pf))
+ if (ice_handle_link_event(pf, &event))
dev_err(&pf->pdev->dev,
"Could not handle link event\n");
break;
+ case ice_mbx_opc_send_msg_to_pf:
+ ice_vc_process_vf_msg(pf, &event);
+ break;
+ case ice_aqc_opc_fw_logging:
+ ice_output_fw_log(hw, &event.desc, event.msg_buf);
+ break;
+ case ice_aqc_opc_lldp_set_mib_change:
+ ice_dcb_process_lldp_set_mib_change(pf, &event);
+ break;
default:
dev_dbg(&pf->pdev->dev,
"%s Receive Queue unknown event 0x%04x ignored\n",
@@ -959,6 +1126,28 @@
}
/**
+ * ice_clean_mailboxq_subtask - clean the MailboxQ rings
+ * @pf: board private structure
+ */
+static void ice_clean_mailboxq_subtask(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+
+ if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state))
+ return;
+
+ if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX))
+ return;
+
+ clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state);
+
+ if (ice_ctrlq_pending(hw, &hw->mailboxq))
+ __ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX);
+
+ ice_flush(hw);
+}
+
+/**
* ice_service_task_schedule - schedule the service task to wake up
* @pf: board private structure
*
@@ -966,8 +1155,9 @@
*/
static void ice_service_task_schedule(struct ice_pf *pf)
{
- if (!test_bit(__ICE_DOWN, pf->state) &&
- !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state))
+ if (!test_bit(__ICE_SERVICE_DIS, pf->state) &&
+ !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) &&
+ !test_bit(__ICE_NEEDS_RESTART, pf->state))
queue_work(ice_wq, &pf->serv_task);
}
@@ -985,6 +1175,34 @@
}
/**
+ * ice_service_task_stop - stop service task and cancel works
+ * @pf: board private structure
+ */
+static void ice_service_task_stop(struct ice_pf *pf)
+{
+ set_bit(__ICE_SERVICE_DIS, pf->state);
+
+ if (pf->serv_tmr.function)
+ del_timer_sync(&pf->serv_tmr);
+ if (pf->serv_task.func)
+ cancel_work_sync(&pf->serv_task);
+
+ clear_bit(__ICE_SERVICE_SCHED, pf->state);
+}
+
+/**
+ * ice_service_task_restart - restart service task and schedule works
+ * @pf: board private structure
+ *
+ * This function is needed for suspend and resume works (e.g WoL scenario)
+ */
+static void ice_service_task_restart(struct ice_pf *pf)
+{
+ clear_bit(__ICE_SERVICE_DIS, pf->state);
+ ice_service_task_schedule(pf);
+}
+
+/**
* ice_service_timer - timer callback to schedule service task
* @t: pointer to timer_list
*/
@@ -997,6 +1215,274 @@
}
/**
+ * ice_handle_mdd_event - handle malicious driver detect event
+ * @pf: pointer to the PF structure
+ *
+ * Called from service task. OICR interrupt handler indicates MDD event
+ */
+static void ice_handle_mdd_event(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+ bool mdd_detected = false;
+ u32 reg;
+ int i;
+
+ if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state))
+ return;
+
+ /* find what triggered the MDD event */
+ reg = rd32(hw, GL_MDET_TX_PQM);
+ if (reg & GL_MDET_TX_PQM_VALID_M) {
+ u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >>
+ GL_MDET_TX_PQM_PF_NUM_S;
+ u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >>
+ GL_MDET_TX_PQM_VF_NUM_S;
+ u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >>
+ GL_MDET_TX_PQM_MAL_TYPE_S;
+ u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >>
+ GL_MDET_TX_PQM_QNUM_S);
+
+ if (netif_msg_tx_err(pf))
+ dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
+ event, queue, pf_num, vf_num);
+ wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
+ mdd_detected = true;
+ }
+
+ reg = rd32(hw, GL_MDET_TX_TCLAN);
+ if (reg & GL_MDET_TX_TCLAN_VALID_M) {
+ u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
+ GL_MDET_TX_TCLAN_PF_NUM_S;
+ u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >>
+ GL_MDET_TX_TCLAN_VF_NUM_S;
+ u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >>
+ GL_MDET_TX_TCLAN_MAL_TYPE_S;
+ u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
+ GL_MDET_TX_TCLAN_QNUM_S);
+
+ if (netif_msg_rx_err(pf))
+ dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
+ event, queue, pf_num, vf_num);
+ wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
+ mdd_detected = true;
+ }
+
+ reg = rd32(hw, GL_MDET_RX);
+ if (reg & GL_MDET_RX_VALID_M) {
+ u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >>
+ GL_MDET_RX_PF_NUM_S;
+ u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >>
+ GL_MDET_RX_VF_NUM_S;
+ u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >>
+ GL_MDET_RX_MAL_TYPE_S;
+ u16 queue = ((reg & GL_MDET_RX_QNUM_M) >>
+ GL_MDET_RX_QNUM_S);
+
+ if (netif_msg_rx_err(pf))
+ dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
+ event, queue, pf_num, vf_num);
+ wr32(hw, GL_MDET_RX, 0xffffffff);
+ mdd_detected = true;
+ }
+
+ if (mdd_detected) {
+ bool pf_mdd_detected = false;
+
+ reg = rd32(hw, PF_MDET_TX_PQM);
+ if (reg & PF_MDET_TX_PQM_VALID_M) {
+ wr32(hw, PF_MDET_TX_PQM, 0xFFFF);
+ dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
+ pf_mdd_detected = true;
+ }
+
+ reg = rd32(hw, PF_MDET_TX_TCLAN);
+ if (reg & PF_MDET_TX_TCLAN_VALID_M) {
+ wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF);
+ dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
+ pf_mdd_detected = true;
+ }
+
+ reg = rd32(hw, PF_MDET_RX);
+ if (reg & PF_MDET_RX_VALID_M) {
+ wr32(hw, PF_MDET_RX, 0xFFFF);
+ dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
+ pf_mdd_detected = true;
+ }
+ /* Queue belongs to the PF initiate a reset */
+ if (pf_mdd_detected) {
+ set_bit(__ICE_NEEDS_RESTART, pf->state);
+ ice_service_task_schedule(pf);
+ }
+ }
+
+ /* check to see if one of the VFs caused the MDD */
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ struct ice_vf *vf = &pf->vf[i];
+
+ bool vf_mdd_detected = false;
+
+ reg = rd32(hw, VP_MDET_TX_PQM(i));
+ if (reg & VP_MDET_TX_PQM_VALID_M) {
+ wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF);
+ vf_mdd_detected = true;
+ dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+ i);
+ }
+
+ reg = rd32(hw, VP_MDET_TX_TCLAN(i));
+ if (reg & VP_MDET_TX_TCLAN_VALID_M) {
+ wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF);
+ vf_mdd_detected = true;
+ dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+ i);
+ }
+
+ reg = rd32(hw, VP_MDET_TX_TDPU(i));
+ if (reg & VP_MDET_TX_TDPU_VALID_M) {
+ wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF);
+ vf_mdd_detected = true;
+ dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
+ i);
+ }
+
+ reg = rd32(hw, VP_MDET_RX(i));
+ if (reg & VP_MDET_RX_VALID_M) {
+ wr32(hw, VP_MDET_RX(i), 0xFFFF);
+ vf_mdd_detected = true;
+ dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
+ i);
+ }
+
+ if (vf_mdd_detected) {
+ vf->num_mdd_events++;
+ if (vf->num_mdd_events &&
+ vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD)
+ dev_info(&pf->pdev->dev,
+ "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n",
+ i, vf->num_mdd_events);
+ }
+ }
+}
+
+/**
+ * ice_force_phys_link_state - Force the physical link state
+ * @vsi: VSI to force the physical link state to up/down
+ * @link_up: true/false indicates to set the physical link to up/down
+ *
+ * Force the physical link state by getting the current PHY capabilities from
+ * hardware and setting the PHY config based on the determined capabilities. If
+ * link changes a link event will be triggered because both the Enable Automatic
+ * Link Update and LESM Enable bits are set when setting the PHY capabilities.
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
+{
+ struct ice_aqc_get_phy_caps_data *pcaps;
+ struct ice_aqc_set_phy_cfg_data *cfg;
+ struct ice_port_info *pi;
+ struct device *dev;
+ int retcode;
+
+ if (!vsi || !vsi->port_info || !vsi->back)
+ return -EINVAL;
+ if (vsi->type != ICE_VSI_PF)
+ return 0;
+
+ dev = &vsi->back->pdev->dev;
+
+ pi = vsi->port_info;
+
+ pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL);
+ if (!pcaps)
+ return -ENOMEM;
+
+ retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+ NULL);
+ if (retcode) {
+ dev_err(dev,
+ "Failed to get phy capabilities, VSI %d error %d\n",
+ vsi->vsi_num, retcode);
+ retcode = -EIO;
+ goto out;
+ }
+
+ /* No change in link */
+ if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) &&
+ link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
+ goto out;
+
+ cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL);
+ if (!cfg) {
+ retcode = -ENOMEM;
+ goto out;
+ }
+
+ cfg->phy_type_low = pcaps->phy_type_low;
+ cfg->phy_type_high = pcaps->phy_type_high;
+ cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+ cfg->low_power_ctrl = pcaps->low_power_ctrl;
+ cfg->eee_cap = pcaps->eee_cap;
+ cfg->eeer_value = pcaps->eeer_value;
+ cfg->link_fec_opt = pcaps->link_fec_options;
+ if (link_up)
+ cfg->caps |= ICE_AQ_PHY_ENA_LINK;
+ else
+ cfg->caps &= ~ICE_AQ_PHY_ENA_LINK;
+
+ retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL);
+ if (retcode) {
+ dev_err(dev, "Failed to set phy config, VSI %d error %d\n",
+ vsi->vsi_num, retcode);
+ retcode = -EIO;
+ }
+
+ devm_kfree(dev, cfg);
+out:
+ devm_kfree(dev, pcaps);
+ return retcode;
+}
+
+/**
+ * ice_check_media_subtask - Check for media; bring link up if detected.
+ * @pf: pointer to PF struct
+ */
+static void ice_check_media_subtask(struct ice_pf *pf)
+{
+ struct ice_port_info *pi;
+ struct ice_vsi *vsi;
+ int err;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi)
+ return;
+
+ /* No need to check for media if it's already present or the interface
+ * is down
+ */
+ if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) ||
+ test_bit(__ICE_DOWN, vsi->state))
+ return;
+
+ /* Refresh link info and check if media is present */
+ pi = vsi->port_info;
+ err = ice_update_link_info(pi);
+ if (err)
+ return;
+
+ if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
+ err = ice_force_phys_link_state(vsi, true);
+ if (err)
+ return;
+ clear_bit(ICE_FLAG_NO_MEDIA, pf->flags);
+
+ /* A Link Status Event will be generated; the event handler
+ * will complete bringing the interface up
+ */
+ }
+}
+
+/**
* ice_service_task - manage and run subtasks
* @work: pointer to work_struct contained by the PF struct
*/
@@ -1010,16 +1496,28 @@
/* process reset requests first */
ice_reset_subtask(pf);
- /* bail if a reset/recovery cycle is pending */
- if (ice_is_reset_recovery_pending(pf->state) ||
- test_bit(__ICE_SUSPENDED, pf->state)) {
+ /* bail if a reset/recovery cycle is pending or rebuild failed */
+ if (ice_is_reset_in_progress(pf->state) ||
+ test_bit(__ICE_SUSPENDED, pf->state) ||
+ test_bit(__ICE_NEEDS_RESTART, pf->state)) {
ice_service_task_complete(pf);
return;
}
- ice_sync_fltr_subtask(pf);
- ice_watchdog_subtask(pf);
ice_clean_adminq_subtask(pf);
+ ice_check_media_subtask(pf);
+ ice_check_for_hang_subtask(pf);
+ ice_sync_fltr_subtask(pf);
+ ice_handle_mdd_event(pf);
+ ice_watchdog_subtask(pf);
+
+ if (ice_is_safe_mode(pf)) {
+ ice_service_task_complete(pf);
+ return;
+ }
+
+ ice_process_vflr_event(pf);
+ ice_clean_mailboxq_subtask(pf);
/* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */
ice_service_task_complete(pf);
@@ -1029,13 +1527,16 @@
* schedule the service task now.
*/
if (time_after(jiffies, (start_time + pf->serv_tmr_period)) ||
+ test_bit(__ICE_MDD_EVENT_PENDING, pf->state) ||
+ test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
+ test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) ||
test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state))
mod_timer(&pf->serv_tmr, jiffies);
}
/**
* ice_set_ctrlq_len - helper function to set controlq length
- * @hw: pointer to the hw instance
+ * @hw: pointer to the HW instance
*/
static void ice_set_ctrlq_len(struct ice_hw *hw)
{
@@ -1043,6 +1544,10 @@
hw->adminq.num_sq_entries = ICE_AQ_LEN;
hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN;
hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN;
+ hw->mailboxq.num_rq_entries = ICE_MBXRQ_LEN;
+ hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN;
+ hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
+ hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
}
/**
@@ -1053,8 +1558,9 @@
* This is a callback function used by the irq_set_affinity_notifier function
* so that we may register to receive changes to the irq affinity masks.
*/
-static void ice_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
+static void
+ice_irq_affinity_notify(struct irq_affinity_notify *notify,
+ const cpumask_t *mask)
{
struct ice_q_vector *q_vector =
container_of(notify, struct ice_q_vector, affinity_notify);
@@ -1073,97 +1579,22 @@
static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
/**
- * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI
- * @vsi: the VSI being un-configured
- */
-static void ice_vsi_dis_irq(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- struct ice_hw *hw = &pf->hw;
- int base = vsi->base_vector;
- u32 val;
- int i;
-
- /* disable interrupt causation from each queue */
- if (vsi->tx_rings) {
- ice_for_each_txq(vsi, i) {
- if (vsi->tx_rings[i]) {
- u16 reg;
-
- reg = vsi->tx_rings[i]->reg_idx;
- val = rd32(hw, QINT_TQCTL(reg));
- val &= ~QINT_TQCTL_CAUSE_ENA_M;
- wr32(hw, QINT_TQCTL(reg), val);
- }
- }
- }
-
- if (vsi->rx_rings) {
- ice_for_each_rxq(vsi, i) {
- if (vsi->rx_rings[i]) {
- u16 reg;
-
- reg = vsi->rx_rings[i]->reg_idx;
- val = rd32(hw, QINT_RQCTL(reg));
- val &= ~QINT_RQCTL_CAUSE_ENA_M;
- wr32(hw, QINT_RQCTL(reg), val);
- }
- }
- }
-
- /* disable each interrupt */
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- for (i = vsi->base_vector;
- i < (vsi->num_q_vectors + vsi->base_vector); i++)
- wr32(hw, GLINT_DYN_CTL(i), 0);
-
- ice_flush(hw);
- for (i = 0; i < vsi->num_q_vectors; i++)
- synchronize_irq(pf->msix_entries[i + base].vector);
- }
-}
-
-/**
* ice_vsi_ena_irq - Enable IRQ for the given VSI
* @vsi: the VSI being configured
*/
static int ice_vsi_ena_irq(struct ice_vsi *vsi)
{
- struct ice_pf *pf = vsi->back;
- struct ice_hw *hw = &pf->hw;
+ struct ice_hw *hw = &vsi->back->hw;
+ int i;
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- int i;
-
- for (i = 0; i < vsi->num_q_vectors; i++)
- ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
- }
+ ice_for_each_q_vector(vsi, i)
+ ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
ice_flush(hw);
return 0;
}
/**
- * ice_vsi_delete - delete a VSI from the switch
- * @vsi: pointer to VSI being removed
- */
-static void ice_vsi_delete(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- struct ice_vsi_ctx ctxt;
- enum ice_status status;
-
- ctxt.vsi_num = vsi->vsi_num;
-
- memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props));
-
- status = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL);
- if (status)
- dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n",
- vsi->vsi_num);
-}
-
-/**
* ice_vsi_req_irq_msix - get MSI-X vectors from the OS for the VSI
* @vsi: the VSI being configured
* @basename: name for the vector
@@ -1197,10 +1628,9 @@
/* skip this unused q_vector */
continue;
}
- err = devm_request_irq(&pf->pdev->dev,
- pf->msix_entries[base + vector].vector,
- vsi->irq_handler, 0, q_vector->name,
- q_vector);
+ err = devm_request_irq(&pf->pdev->dev, irq_num,
+ vsi->irq_handler, 0,
+ q_vector->name, q_vector);
if (err) {
netdev_err(vsi->netdev,
"MSIX request_irq failed, error: %d\n", err);
@@ -1231,467 +1661,6 @@
}
/**
- * ice_vsi_set_rss_params - Setup RSS capabilities per VSI type
- * @vsi: the VSI being configured
- */
-static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
-{
- struct ice_hw_common_caps *cap;
- struct ice_pf *pf = vsi->back;
-
- if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
- vsi->rss_size = 1;
- return;
- }
-
- cap = &pf->hw.func_caps.common_cap;
- switch (vsi->type) {
- case ICE_VSI_PF:
- /* PF VSI will inherit RSS instance of PF */
- vsi->rss_table_size = cap->rss_table_size;
- vsi->rss_size = min_t(int, num_online_cpus(),
- BIT(cap->rss_table_entry_width));
- vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF;
- break;
- default:
- dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
- break;
- }
-}
-
-/**
- * ice_vsi_setup_q_map - Setup a VSI queue map
- * @vsi: the VSI being configured
- * @ctxt: VSI context structure
- */
-static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
-{
- u16 offset = 0, qmap = 0, numq_tc;
- u16 pow = 0, max_rss = 0, qcount;
- u16 qcount_tx = vsi->alloc_txq;
- u16 qcount_rx = vsi->alloc_rxq;
- bool ena_tc0 = false;
- int i;
-
- /* at least TC0 should be enabled by default */
- if (vsi->tc_cfg.numtc) {
- if (!(vsi->tc_cfg.ena_tc & BIT(0)))
- ena_tc0 = true;
- } else {
- ena_tc0 = true;
- }
-
- if (ena_tc0) {
- vsi->tc_cfg.numtc++;
- vsi->tc_cfg.ena_tc |= 1;
- }
-
- numq_tc = qcount_rx / vsi->tc_cfg.numtc;
-
- /* TC mapping is a function of the number of Rx queues assigned to the
- * VSI for each traffic class and the offset of these queues.
- * The first 10 bits are for queue offset for TC0, next 4 bits for no:of
- * queues allocated to TC0. No:of queues is a power-of-2.
- *
- * If TC is not enabled, the queue offset is set to 0, and allocate one
- * queue, this way, traffic for the given TC will be sent to the default
- * queue.
- *
- * Setup number and offset of Rx queues for all TCs for the VSI
- */
-
- /* qcount will change if RSS is enabled */
- if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
- if (vsi->type == ICE_VSI_PF)
- max_rss = ICE_MAX_LG_RSS_QS;
- else
- max_rss = ICE_MAX_SMALL_RSS_QS;
-
- qcount = min_t(int, numq_tc, max_rss);
- qcount = min_t(int, qcount, vsi->rss_size);
- } else {
- qcount = numq_tc;
- }
-
- /* find the (rounded up) power-of-2 of qcount */
- pow = order_base_2(qcount);
-
- for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
- if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
- /* TC is not enabled */
- vsi->tc_cfg.tc_info[i].qoffset = 0;
- vsi->tc_cfg.tc_info[i].qcount = 1;
- ctxt->info.tc_mapping[i] = 0;
- continue;
- }
-
- /* TC is enabled */
- vsi->tc_cfg.tc_info[i].qoffset = offset;
- vsi->tc_cfg.tc_info[i].qcount = qcount;
-
- qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
- ICE_AQ_VSI_TC_Q_OFFSET_M) |
- ((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
- ICE_AQ_VSI_TC_Q_NUM_M);
- offset += qcount;
- ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
- }
-
- vsi->num_txq = qcount_tx;
- vsi->num_rxq = offset;
-
- /* Rx queue mapping */
- ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG);
- /* q_mapping buffer holds the info for the first queue allocated for
- * this VSI in the PF space and also the number of queues associated
- * with this VSI.
- */
- ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]);
- ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq);
-}
-
-/**
- * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI
- * @ctxt: the VSI context being set
- *
- * This initializes a default VSI context for all sections except the Queues.
- */
-static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
-{
- u32 table = 0;
-
- memset(&ctxt->info, 0, sizeof(ctxt->info));
- /* VSI's should be allocated from shared pool */
- ctxt->alloc_from_pool = true;
- /* Src pruning enabled by default */
- ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE;
- /* Traffic from VSI can be sent to LAN */
- ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA;
-
- /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy
- * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all
- * packets untagged/tagged.
- */
- ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL &
- ICE_AQ_VSI_VLAN_MODE_M) >>
- ICE_AQ_VSI_VLAN_MODE_S);
-
- /* Have 1:1 UP mapping for both ingress/egress tables */
- table |= ICE_UP_TABLE_TRANSLATE(0, 0);
- table |= ICE_UP_TABLE_TRANSLATE(1, 1);
- table |= ICE_UP_TABLE_TRANSLATE(2, 2);
- table |= ICE_UP_TABLE_TRANSLATE(3, 3);
- table |= ICE_UP_TABLE_TRANSLATE(4, 4);
- table |= ICE_UP_TABLE_TRANSLATE(5, 5);
- table |= ICE_UP_TABLE_TRANSLATE(6, 6);
- table |= ICE_UP_TABLE_TRANSLATE(7, 7);
- ctxt->info.ingress_table = cpu_to_le32(table);
- ctxt->info.egress_table = cpu_to_le32(table);
- /* Have 1:1 UP mapping for outer to inner UP table */
- ctxt->info.outer_up_table = cpu_to_le32(table);
- /* No Outer tag support outer_tag_flags remains to zero */
-}
-
-/**
- * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI
- * @ctxt: the VSI context being set
- * @vsi: the VSI being configured
- */
-static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
-{
- u8 lut_type, hash_type;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- /* PF VSI will inherit RSS instance of PF */
- lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF;
- hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
- break;
- default:
- dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
- vsi->type);
- return;
- }
-
- ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
- ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
- ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
- ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
-}
-
-/**
- * ice_vsi_add - Create a new VSI or fetch preallocated VSI
- * @vsi: the VSI being configured
- *
- * This initializes a VSI context depending on the VSI type to be added and
- * passes it down to the add_vsi aq command to create a new VSI.
- */
-static int ice_vsi_add(struct ice_vsi *vsi)
-{
- struct ice_vsi_ctx ctxt = { 0 };
- struct ice_pf *pf = vsi->back;
- struct ice_hw *hw = &pf->hw;
- int ret = 0;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- ctxt.flags = ICE_AQ_VSI_TYPE_PF;
- break;
- default:
- return -ENODEV;
- }
-
- ice_set_dflt_vsi_ctx(&ctxt);
- /* if the switch is in VEB mode, allow VSI loopback */
- if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
- ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
-
- /* Set LUT type and HASH type if RSS is enabled */
- if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
- ice_set_rss_vsi_ctx(&ctxt, vsi);
-
- ctxt.info.sw_id = vsi->port_info->sw_id;
- ice_vsi_setup_q_map(vsi, &ctxt);
-
- ret = ice_aq_add_vsi(hw, &ctxt, NULL);
- if (ret) {
- dev_err(&vsi->back->pdev->dev,
- "Add VSI AQ call failed, err %d\n", ret);
- return -EIO;
- }
- vsi->info = ctxt.info;
- vsi->vsi_num = ctxt.vsi_num;
-
- return ret;
-}
-
-/**
- * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW
- * @vsi: the VSI being cleaned up
- */
-static void ice_vsi_release_msix(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- u16 vector = vsi->base_vector;
- struct ice_hw *hw = &pf->hw;
- u32 txq = 0;
- u32 rxq = 0;
- int i, q;
-
- for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
- struct ice_q_vector *q_vector = vsi->q_vectors[i];
-
- wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), 0);
- wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), 0);
- for (q = 0; q < q_vector->num_ring_tx; q++) {
- wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
- txq++;
- }
-
- for (q = 0; q < q_vector->num_ring_rx; q++) {
- wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0);
- rxq++;
- }
- }
-
- ice_flush(hw);
-}
-
-/**
- * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI
- * @vsi: the VSI having rings deallocated
- */
-static void ice_vsi_clear_rings(struct ice_vsi *vsi)
-{
- int i;
-
- if (vsi->tx_rings) {
- for (i = 0; i < vsi->alloc_txq; i++) {
- if (vsi->tx_rings[i]) {
- kfree_rcu(vsi->tx_rings[i], rcu);
- vsi->tx_rings[i] = NULL;
- }
- }
- }
- if (vsi->rx_rings) {
- for (i = 0; i < vsi->alloc_rxq; i++) {
- if (vsi->rx_rings[i]) {
- kfree_rcu(vsi->rx_rings[i], rcu);
- vsi->rx_rings[i] = NULL;
- }
- }
- }
-}
-
-/**
- * ice_vsi_alloc_rings - Allocates Tx and Rx rings for the VSI
- * @vsi: VSI which is having rings allocated
- */
-static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int i;
-
- /* Allocate tx_rings */
- for (i = 0; i < vsi->alloc_txq; i++) {
- struct ice_ring *ring;
-
- /* allocate with kzalloc(), free with kfree_rcu() */
- ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-
- if (!ring)
- goto err_out;
-
- ring->q_index = i;
- ring->reg_idx = vsi->txq_map[i];
- ring->ring_active = false;
- ring->vsi = vsi;
- ring->netdev = vsi->netdev;
- ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
-
- vsi->tx_rings[i] = ring;
- }
-
- /* Allocate rx_rings */
- for (i = 0; i < vsi->alloc_rxq; i++) {
- struct ice_ring *ring;
-
- /* allocate with kzalloc(), free with kfree_rcu() */
- ring = kzalloc(sizeof(*ring), GFP_KERNEL);
- if (!ring)
- goto err_out;
-
- ring->q_index = i;
- ring->reg_idx = vsi->rxq_map[i];
- ring->ring_active = false;
- ring->vsi = vsi;
- ring->netdev = vsi->netdev;
- ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
- vsi->rx_rings[i] = ring;
- }
-
- return 0;
-
-err_out:
- ice_vsi_clear_rings(vsi);
- return -ENOMEM;
-}
-
-/**
- * ice_vsi_free_irq - Free the irq association with the OS
- * @vsi: the VSI being configured
- */
-static void ice_vsi_free_irq(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int base = vsi->base_vector;
-
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- int i;
-
- if (!vsi->q_vectors || !vsi->irqs_ready)
- return;
-
- vsi->irqs_ready = false;
- for (i = 0; i < vsi->num_q_vectors; i++) {
- u16 vector = i + base;
- int irq_num;
-
- irq_num = pf->msix_entries[vector].vector;
-
- /* free only the irqs that were actually requested */
- if (!vsi->q_vectors[i] ||
- !(vsi->q_vectors[i]->num_ring_tx ||
- vsi->q_vectors[i]->num_ring_rx))
- continue;
-
- /* clear the affinity notifier in the IRQ descriptor */
- irq_set_affinity_notifier(irq_num, NULL);
-
- /* clear the affinity_mask in the IRQ descriptor */
- irq_set_affinity_hint(irq_num, NULL);
- synchronize_irq(irq_num);
- devm_free_irq(&pf->pdev->dev, irq_num,
- vsi->q_vectors[i]);
- }
- ice_vsi_release_msix(vsi);
- }
-}
-
-/**
- * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW
- * @vsi: the VSI being configured
- */
-static void ice_vsi_cfg_msix(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- u16 vector = vsi->base_vector;
- struct ice_hw *hw = &pf->hw;
- u32 txq = 0, rxq = 0;
- int i, q, itr;
- u8 itr_gran;
-
- for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
- struct ice_q_vector *q_vector = vsi->q_vectors[i];
-
- itr_gran = hw->itr_gran_200;
-
- if (q_vector->num_ring_rx) {
- q_vector->rx.itr =
- ITR_TO_REG(vsi->rx_rings[rxq]->rx_itr_setting,
- itr_gran);
- q_vector->rx.latency_range = ICE_LOW_LATENCY;
- }
-
- if (q_vector->num_ring_tx) {
- q_vector->tx.itr =
- ITR_TO_REG(vsi->tx_rings[txq]->tx_itr_setting,
- itr_gran);
- q_vector->tx.latency_range = ICE_LOW_LATENCY;
- }
- wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), q_vector->rx.itr);
- wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), q_vector->tx.itr);
-
- /* Both Transmit Queue Interrupt Cause Control register
- * and Receive Queue Interrupt Cause control register
- * expects MSIX_INDX field to be the vector index
- * within the function space and not the absolute
- * vector index across PF or across device.
- * For SR-IOV VF VSIs queue vector index always starts
- * with 1 since first vector index(0) is used for OICR
- * in VF space. Since VMDq and other PF VSIs are withtin
- * the PF function space, use the vector index thats
- * tracked for this PF.
- */
- for (q = 0; q < q_vector->num_ring_tx; q++) {
- u32 val;
-
- itr = ICE_TX_ITR;
- val = QINT_TQCTL_CAUSE_ENA_M |
- (itr << QINT_TQCTL_ITR_INDX_S) |
- (vector << QINT_TQCTL_MSIX_INDX_S);
- wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
- txq++;
- }
-
- for (q = 0; q < q_vector->num_ring_rx; q++) {
- u32 val;
-
- itr = ICE_RX_ITR;
- val = QINT_RQCTL_CAUSE_ENA_M |
- (itr << QINT_RQCTL_ITR_INDX_S) |
- (vector << QINT_RQCTL_MSIX_INDX_S);
- wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
- rxq++;
- }
- }
-
- ice_flush(hw);
-}
-
-/**
* ice_ena_misc_vector - enable the non-queue interrupts
* @pf: board private structure
*/
@@ -1708,6 +1677,7 @@
PFINT_OICR_MAL_DETECT_M |
PFINT_OICR_GRST_M |
PFINT_OICR_PCI_EXCEPTION_M |
+ PFINT_OICR_VFLR_M |
PFINT_OICR_HMC_ERR_M |
PFINT_OICR_PE_CRITERR_M);
@@ -1731,12 +1701,28 @@
u32 oicr, ena_mask;
set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);
+ set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state);
oicr = rd32(hw, PFINT_OICR);
ena_mask = rd32(hw, PFINT_OICR_ENA);
+ if (oicr & PFINT_OICR_SWINT_M) {
+ ena_mask &= ~PFINT_OICR_SWINT_M;
+ pf->sw_int_count++;
+ }
+
+ if (oicr & PFINT_OICR_MAL_DETECT_M) {
+ ena_mask &= ~PFINT_OICR_MAL_DETECT_M;
+ set_bit(__ICE_MDD_EVENT_PENDING, pf->state);
+ }
+ if (oicr & PFINT_OICR_VFLR_M) {
+ ena_mask &= ~PFINT_OICR_VFLR_M;
+ set_bit(__ICE_VFLR_EVENT_PENDING, pf->state);
+ }
+
if (oicr & PFINT_OICR_GRST_M) {
u32 reset;
+
/* we have a reset warning */
ena_mask &= ~PFINT_OICR_GRST_M;
reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
@@ -1746,15 +1732,18 @@
pf->corer_count++;
else if (reset == ICE_RESET_GLOBR)
pf->globr_count++;
- else
+ else if (reset == ICE_RESET_EMPR)
pf->empr_count++;
+ else
+ dev_dbg(&pf->pdev->dev, "Invalid reset type %d\n",
+ reset);
/* If a reset cycle isn't already in progress, we set a bit in
* pf->state so that the service task can start a reset/rebuild.
* We also make note of which reset happened so that peer
* devices/drivers can be informed.
*/
- if (!test_bit(__ICE_RESET_RECOVERY_PENDING, pf->state)) {
+ if (!test_and_set_bit(__ICE_RESET_OICR_RECV, pf->state)) {
if (reset == ICE_RESET_CORER)
set_bit(__ICE_CORER_RECV, pf->state);
else if (reset == ICE_RESET_GLOBR)
@@ -1762,7 +1751,20 @@
else
set_bit(__ICE_EMPR_RECV, pf->state);
- set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ /* There are couple of different bits at play here.
+ * hw->reset_ongoing indicates whether the hardware is
+ * in reset. This is set to true when a reset interrupt
+ * is received and set back to false after the driver
+ * has determined that the hardware is out of reset.
+ *
+ * __ICE_RESET_OICR_RECV in pf->state indicates
+ * that a post reset rebuild is required before the
+ * driver is operational again. This is set above.
+ *
+ * As this is the start of the reset/rebuild cycle, set
+ * both to indicate that.
+ */
+ hw->reset_ongoing = true;
}
}
@@ -1774,7 +1776,7 @@
rd32(hw, PFHMC_ERRORDATA));
}
- /* Report and mask off any remaining unexpected interrupts */
+ /* Report any remaining unexpected interrupts */
oicr &= ena_mask;
if (oicr) {
dev_dbg(&pf->pdev->dev, "unhandled interrupt oicr=0x%08x\n",
@@ -1788,12 +1790,9 @@
set_bit(__ICE_PFR_REQ, pf->state);
ice_service_task_schedule(pf);
}
- ena_mask &= ~oicr;
}
ret = IRQ_HANDLED;
- /* re-enable interrupt causes that are not handled during this pass */
- wr32(hw, PFINT_OICR_ENA, ena_mask);
if (!test_bit(__ICE_DOWN, pf->state)) {
ice_service_task_schedule(pf);
ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1803,205 +1802,24 @@
}
/**
- * ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors
- * @vsi: the VSI being configured
- *
- * This function maps descriptor rings to the queue-specific vectors allotted
- * through the MSI-X enabling code. On a constrained vector budget, we map Tx
- * and Rx rings to the vector as "efficiently" as possible.
+ * ice_dis_ctrlq_interrupts - disable control queue interrupts
+ * @hw: pointer to HW structure
*/
-static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
+static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
{
- int q_vectors = vsi->num_q_vectors;
- int tx_rings_rem, rx_rings_rem;
- int v_id;
+ /* disable Admin queue Interrupt causes */
+ wr32(hw, PFINT_FW_CTL,
+ rd32(hw, PFINT_FW_CTL) & ~PFINT_FW_CTL_CAUSE_ENA_M);
- /* initially assigning remaining rings count to VSIs num queue value */
- tx_rings_rem = vsi->num_txq;
- rx_rings_rem = vsi->num_rxq;
+ /* disable Mailbox queue Interrupt causes */
+ wr32(hw, PFINT_MBX_CTL,
+ rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M);
- for (v_id = 0; v_id < q_vectors; v_id++) {
- struct ice_q_vector *q_vector = vsi->q_vectors[v_id];
- int tx_rings_per_v, rx_rings_per_v, q_id, q_base;
+ /* disable Control queue Interrupt causes */
+ wr32(hw, PFINT_OICR_CTL,
+ rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M);
- /* Tx rings mapping to vector */
- tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id);
- q_vector->num_ring_tx = tx_rings_per_v;
- q_vector->tx.ring = NULL;
- q_base = vsi->num_txq - tx_rings_rem;
-
- for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) {
- struct ice_ring *tx_ring = vsi->tx_rings[q_id];
-
- tx_ring->q_vector = q_vector;
- tx_ring->next = q_vector->tx.ring;
- q_vector->tx.ring = tx_ring;
- }
- tx_rings_rem -= tx_rings_per_v;
-
- /* Rx rings mapping to vector */
- rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id);
- q_vector->num_ring_rx = rx_rings_per_v;
- q_vector->rx.ring = NULL;
- q_base = vsi->num_rxq - rx_rings_rem;
-
- for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) {
- struct ice_ring *rx_ring = vsi->rx_rings[q_id];
-
- rx_ring->q_vector = q_vector;
- rx_ring->next = q_vector->rx.ring;
- q_vector->rx.ring = rx_ring;
- }
- rx_rings_rem -= rx_rings_per_v;
- }
-}
-
-/**
- * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI
- * @vsi: the VSI being configured
- *
- * Return 0 on success and a negative value on error
- */
-static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- vsi->alloc_txq = pf->num_lan_tx;
- vsi->alloc_rxq = pf->num_lan_rx;
- vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE);
- vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx);
- break;
- default:
- dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
- vsi->type);
- break;
- }
-}
-
-/**
- * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi
- * @vsi: VSI pointer
- * @alloc_qvectors: a bool to specify if q_vectors need to be allocated.
- *
- * On error: returns error code (negative)
- * On success: returns 0
- */
-static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors)
-{
- struct ice_pf *pf = vsi->back;
-
- /* allocate memory for both Tx and Rx ring pointers */
- vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
- sizeof(struct ice_ring *), GFP_KERNEL);
- if (!vsi->tx_rings)
- goto err_txrings;
-
- vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
- sizeof(struct ice_ring *), GFP_KERNEL);
- if (!vsi->rx_rings)
- goto err_rxrings;
-
- if (alloc_qvectors) {
- /* allocate memory for q_vector pointers */
- vsi->q_vectors = devm_kcalloc(&pf->pdev->dev,
- vsi->num_q_vectors,
- sizeof(struct ice_q_vector *),
- GFP_KERNEL);
- if (!vsi->q_vectors)
- goto err_vectors;
- }
-
- return 0;
-
-err_vectors:
- devm_kfree(&pf->pdev->dev, vsi->rx_rings);
-err_rxrings:
- devm_kfree(&pf->pdev->dev, vsi->tx_rings);
-err_txrings:
- return -ENOMEM;
-}
-
-/**
- * ice_msix_clean_rings - MSIX mode Interrupt Handler
- * @irq: interrupt number
- * @data: pointer to a q_vector
- */
-static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
-{
- struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
-
- if (!q_vector->tx.ring && !q_vector->rx.ring)
- return IRQ_HANDLED;
-
- napi_schedule(&q_vector->napi);
-
- return IRQ_HANDLED;
-}
-
-/**
- * ice_vsi_alloc - Allocates the next available struct vsi in the PF
- * @pf: board private structure
- * @type: type of VSI
- *
- * returns a pointer to a VSI on success, NULL on failure.
- */
-static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type)
-{
- struct ice_vsi *vsi = NULL;
-
- /* Need to protect the allocation of the VSIs at the PF level */
- mutex_lock(&pf->sw_mutex);
-
- /* If we have already allocated our maximum number of VSIs,
- * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index
- * is available to be populated
- */
- if (pf->next_vsi == ICE_NO_VSI) {
- dev_dbg(&pf->pdev->dev, "out of VSI slots!\n");
- goto unlock_pf;
- }
-
- vsi = devm_kzalloc(&pf->pdev->dev, sizeof(*vsi), GFP_KERNEL);
- if (!vsi)
- goto unlock_pf;
-
- vsi->type = type;
- vsi->back = pf;
- set_bit(__ICE_DOWN, vsi->state);
- vsi->idx = pf->next_vsi;
- vsi->work_lmt = ICE_DFLT_IRQ_WORK;
-
- ice_vsi_set_num_qs(vsi);
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- if (ice_vsi_alloc_arrays(vsi, true))
- goto err_rings;
-
- /* Setup default MSIX irq handler for VSI */
- vsi->irq_handler = ice_msix_clean_rings;
- break;
- default:
- dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
- goto unlock_pf;
- }
-
- /* fill VSI slot in the PF struct */
- pf->vsi[pf->next_vsi] = vsi;
-
- /* prepare pf->next_vsi for next use */
- pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
- pf->next_vsi);
- goto unlock_pf;
-
-err_rings:
- devm_kfree(&pf->pdev->dev, vsi);
- vsi = NULL;
-unlock_pf:
- mutex_unlock(&pf->sw_mutex);
- return vsi;
+ ice_flush(hw);
}
/**
@@ -2010,33 +1828,62 @@
*/
static void ice_free_irq_msix_misc(struct ice_pf *pf)
{
- /* disable OICR interrupt */
- wr32(&pf->hw, PFINT_OICR_ENA, 0);
- ice_flush(&pf->hw);
+ struct ice_hw *hw = &pf->hw;
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
+ ice_dis_ctrlq_interrupts(hw);
+
+ /* disable OICR interrupt */
+ wr32(hw, PFINT_OICR_ENA, 0);
+ ice_flush(hw);
+
+ if (pf->msix_entries) {
synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
devm_free_irq(&pf->pdev->dev,
pf->msix_entries[pf->oicr_idx].vector, pf);
}
+ pf->num_avail_sw_msix += 1;
ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
}
/**
+ * ice_ena_ctrlq_interrupts - enable control queue interrupts
+ * @hw: pointer to HW structure
+ * @reg_idx: HW vector index to associate the control queue interrupts with
+ */
+static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
+{
+ u32 val;
+
+ val = ((reg_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+ PFINT_OICR_CTL_CAUSE_ENA_M);
+ wr32(hw, PFINT_OICR_CTL, val);
+
+ /* enable Admin queue Interrupt causes */
+ val = ((reg_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+ PFINT_FW_CTL_CAUSE_ENA_M);
+ wr32(hw, PFINT_FW_CTL, val);
+
+ /* enable Mailbox queue Interrupt causes */
+ val = ((reg_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
+ PFINT_MBX_CTL_CAUSE_ENA_M);
+ wr32(hw, PFINT_MBX_CTL, val);
+
+ ice_flush(hw);
+}
+
+/**
* ice_req_irq_msix_misc - Setup the misc vector to handle non queue events
* @pf: board private structure
*
* This sets up the handler for MSIX 0, which is used to manage the
- * non-queue interrupts, e.g. AdminQ and errors. This is not used
+ * non-queue interrupts, e.g. AdminQ and errors. This is not used
* when in MSI or Legacy interrupt mode.
*/
static int ice_req_irq_msix_misc(struct ice_pf *pf)
{
struct ice_hw *hw = &pf->hw;
int oicr_idx, err = 0;
- u8 itr_gran;
- u32 val;
if (!pf->int_name[0])
snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
@@ -2047,7 +1894,7 @@
* lost during reset. Note that this function is called only during
* rebuild path and not while reset is in progress.
*/
- if (ice_is_reset_recovery_pending(pf->state))
+ if (ice_is_reset_in_progress(pf->state))
goto skip_req_irq;
/* reserve one vector in irq_tracker for misc interrupts */
@@ -2055,6 +1902,7 @@
if (oicr_idx < 0)
return oicr_idx;
+ pf->num_avail_sw_msix -= 1;
pf->oicr_idx = oicr_idx;
err = devm_request_irq(&pf->pdev->dev,
@@ -2065,25 +1913,16 @@
"devm_request_irq for %s failed: %d\n",
pf->int_name, err);
ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+ pf->num_avail_sw_msix += 1;
return err;
}
skip_req_irq:
ice_ena_misc_vector(pf);
- val = ((pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
- PFINT_OICR_CTL_CAUSE_ENA_M);
- wr32(hw, PFINT_OICR_CTL, val);
-
- /* This enables Admin queue Interrupt causes */
- val = ((pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
- PFINT_FW_CTL_CAUSE_ENA_M);
- wr32(hw, PFINT_FW_CTL, val);
-
- itr_gran = hw->itr_gran_200;
-
+ ice_ena_ctrlq_interrupts(hw, pf->oicr_idx);
wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
- ITR_TO_REG(ICE_ITR_8K, itr_gran));
+ ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
ice_flush(hw);
ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -2092,230 +1931,61 @@
}
/**
- * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
- * @vsi: the VSI getting queues
+ * ice_napi_add - register NAPI handler for the VSI
+ * @vsi: VSI for which NAPI handler is to be registered
*
- * Return 0 on success and a negative value on error
+ * This function is only called in the driver's load path. Registering the NAPI
+ * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume,
+ * reset/rebuild, etc.)
*/
-static int ice_vsi_get_qs_contig(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int offset, ret = 0;
-
- mutex_lock(&pf->avail_q_mutex);
- /* look for contiguous block of queues for tx */
- offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS,
- 0, vsi->alloc_txq, 0);
- if (offset < ICE_MAX_TXQS) {
- int i;
-
- bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq);
- for (i = 0; i < vsi->alloc_txq; i++)
- vsi->txq_map[i] = i + offset;
- } else {
- ret = -ENOMEM;
- vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER;
- }
-
- /* look for contiguous block of queues for rx */
- offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS,
- 0, vsi->alloc_rxq, 0);
- if (offset < ICE_MAX_RXQS) {
- int i;
-
- bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq);
- for (i = 0; i < vsi->alloc_rxq; i++)
- vsi->rxq_map[i] = i + offset;
- } else {
- ret = -ENOMEM;
- vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER;
- }
- mutex_unlock(&pf->avail_q_mutex);
-
- return ret;
-}
-
-/**
- * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI
- * @vsi: the VSI getting queues
- *
- * Return 0 on success and a negative value on error
- */
-static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int i, index = 0;
-
- mutex_lock(&pf->avail_q_mutex);
-
- if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) {
- for (i = 0; i < vsi->alloc_txq; i++) {
- index = find_next_zero_bit(pf->avail_txqs,
- ICE_MAX_TXQS, index);
- if (index < ICE_MAX_TXQS) {
- set_bit(index, pf->avail_txqs);
- vsi->txq_map[i] = index;
- } else {
- goto err_scatter_tx;
- }
- }
- }
-
- if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) {
- for (i = 0; i < vsi->alloc_rxq; i++) {
- index = find_next_zero_bit(pf->avail_rxqs,
- ICE_MAX_RXQS, index);
- if (index < ICE_MAX_RXQS) {
- set_bit(index, pf->avail_rxqs);
- vsi->rxq_map[i] = index;
- } else {
- goto err_scatter_rx;
- }
- }
- }
-
- mutex_unlock(&pf->avail_q_mutex);
- return 0;
-
-err_scatter_rx:
- /* unflag any queues we have grabbed (i is failed position) */
- for (index = 0; index < i; index++) {
- clear_bit(vsi->rxq_map[index], pf->avail_rxqs);
- vsi->rxq_map[index] = 0;
- }
- i = vsi->alloc_txq;
-err_scatter_tx:
- /* i is either position of failed attempt or vsi->alloc_txq */
- for (index = 0; index < i; index++) {
- clear_bit(vsi->txq_map[index], pf->avail_txqs);
- vsi->txq_map[index] = 0;
- }
-
- mutex_unlock(&pf->avail_q_mutex);
- return -ENOMEM;
-}
-
-/**
- * ice_vsi_get_qs - Assign queues from PF to VSI
- * @vsi: the VSI to assign queues to
- *
- * Returns 0 on success and a negative value on error
- */
-static int ice_vsi_get_qs(struct ice_vsi *vsi)
-{
- int ret = 0;
-
- vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG;
- vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG;
-
- /* NOTE: ice_vsi_get_qs_contig() will set the rx/tx mapping
- * modes individually to scatter if assigning contiguous queues
- * to rx or tx fails
- */
- ret = ice_vsi_get_qs_contig(vsi);
- if (ret < 0) {
- if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER)
- vsi->alloc_txq = max_t(u16, vsi->alloc_txq,
- ICE_MAX_SCATTER_TXQS);
- if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER)
- vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq,
- ICE_MAX_SCATTER_RXQS);
- ret = ice_vsi_get_qs_scatter(vsi);
- }
-
- return ret;
-}
-
-/**
- * ice_vsi_put_qs - Release queues from VSI to PF
- * @vsi: the VSI thats going to release queues
- */
-static void ice_vsi_put_qs(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int i;
-
- mutex_lock(&pf->avail_q_mutex);
-
- for (i = 0; i < vsi->alloc_txq; i++) {
- clear_bit(vsi->txq_map[i], pf->avail_txqs);
- vsi->txq_map[i] = ICE_INVAL_Q_INDEX;
- }
-
- for (i = 0; i < vsi->alloc_rxq; i++) {
- clear_bit(vsi->rxq_map[i], pf->avail_rxqs);
- vsi->rxq_map[i] = ICE_INVAL_Q_INDEX;
- }
-
- mutex_unlock(&pf->avail_q_mutex);
-}
-
-/**
- * ice_free_q_vector - Free memory allocated for a specific interrupt vector
- * @vsi: VSI having the memory freed
- * @v_idx: index of the vector to be freed
- */
-static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
-{
- struct ice_q_vector *q_vector;
- struct ice_ring *ring;
-
- if (!vsi->q_vectors[v_idx]) {
- dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n",
- v_idx);
- return;
- }
- q_vector = vsi->q_vectors[v_idx];
-
- ice_for_each_ring(ring, q_vector->tx)
- ring->q_vector = NULL;
- ice_for_each_ring(ring, q_vector->rx)
- ring->q_vector = NULL;
-
- /* only VSI with an associated netdev is set up with NAPI */
- if (vsi->netdev)
- netif_napi_del(&q_vector->napi);
-
- devm_kfree(&vsi->back->pdev->dev, q_vector);
- vsi->q_vectors[v_idx] = NULL;
-}
-
-/**
- * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors
- * @vsi: the VSI having memory freed
- */
-static void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
+static void ice_napi_add(struct ice_vsi *vsi)
{
int v_idx;
- for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
- ice_free_q_vector(vsi, v_idx);
+ if (!vsi->netdev)
+ return;
+
+ ice_for_each_q_vector(vsi, v_idx)
+ netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
+ ice_napi_poll, NAPI_POLL_WEIGHT);
}
/**
- * ice_cfg_netdev - Setup the netdev flags
- * @vsi: the VSI being configured
- *
- * Returns 0 on success, negative value on failure
+ * ice_set_ops - set netdev and ethtools ops for the given netdev
+ * @netdev: netdev instance
*/
-static int ice_cfg_netdev(struct ice_vsi *vsi)
+static void ice_set_ops(struct net_device *netdev)
{
+ struct ice_pf *pf = ice_netdev_to_pf(netdev);
+
+ if (ice_is_safe_mode(pf)) {
+ netdev->netdev_ops = &ice_netdev_safe_mode_ops;
+ ice_set_ethtool_safe_mode_ops(netdev);
+ return;
+ }
+
+ netdev->netdev_ops = &ice_netdev_ops;
+ ice_set_ethtool_ops(netdev);
+}
+
+/**
+ * ice_set_netdev_features - set features for the given netdev
+ * @netdev: netdev instance
+ */
+static void ice_set_netdev_features(struct net_device *netdev)
+{
+ struct ice_pf *pf = ice_netdev_to_pf(netdev);
netdev_features_t csumo_features;
netdev_features_t vlano_features;
netdev_features_t dflt_features;
netdev_features_t tso_features;
- struct ice_netdev_priv *np;
- struct net_device *netdev;
- u8 mac_addr[ETH_ALEN];
- netdev = alloc_etherdev_mqs(sizeof(struct ice_netdev_priv),
- vsi->alloc_txq, vsi->alloc_rxq);
- if (!netdev)
- return -ENOMEM;
-
- vsi->netdev = netdev;
- np = netdev_priv(netdev);
- np->vsi = vsi;
+ if (ice_is_safe_mode(pf)) {
+ /* safe mode */
+ netdev->features = NETIF_F_SG | NETIF_F_HIGHDMA;
+ netdev->hw_features = netdev->features;
+ return;
+ }
dflt_features = NETIF_F_SG |
NETIF_F_HIGHDMA |
@@ -2323,6 +1993,7 @@
csumo_features = NETIF_F_RXCSUM |
NETIF_F_IP_CSUM |
+ NETIF_F_SCTP_CRC |
NETIF_F_IPV6_CSUM;
vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -2342,217 +2013,61 @@
tso_features;
netdev->vlan_features |= dflt_features | csumo_features |
tso_features;
+}
+
+/**
+ * ice_cfg_netdev - Allocate, configure and register a netdev
+ * @vsi: the VSI associated with the new netdev
+ *
+ * Returns 0 on success, negative value on failure
+ */
+static int ice_cfg_netdev(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_netdev_priv *np;
+ struct net_device *netdev;
+ u8 mac_addr[ETH_ALEN];
+ int err;
+
+ netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
+ vsi->alloc_rxq);
+ if (!netdev)
+ return -ENOMEM;
+
+ vsi->netdev = netdev;
+ np = netdev_priv(netdev);
+ np->vsi = vsi;
+
+ ice_set_netdev_features(netdev);
+
+ ice_set_ops(netdev);
if (vsi->type == ICE_VSI_PF) {
- SET_NETDEV_DEV(netdev, &vsi->back->pdev->dev);
+ SET_NETDEV_DEV(netdev, &pf->pdev->dev);
ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
-
ether_addr_copy(netdev->dev_addr, mac_addr);
ether_addr_copy(netdev->perm_addr, mac_addr);
}
netdev->priv_flags |= IFF_UNICAST_FLT;
- /* assign netdev_ops */
- netdev->netdev_ops = &ice_netdev_ops;
+ /* Setup netdev TC information */
+ ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
/* setup watchdog timeout value to be 5 second */
netdev->watchdog_timeo = 5 * HZ;
- ice_set_ethtool_ops(netdev);
-
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = ICE_MAX_MTU;
- return 0;
-}
+ err = register_netdev(vsi->netdev);
+ if (err)
+ return err;
-/**
- * ice_vsi_free_arrays - clean up vsi resources
- * @vsi: pointer to VSI being cleared
- * @free_qvectors: bool to specify if q_vectors should be deallocated
- */
-static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors)
-{
- struct ice_pf *pf = vsi->back;
+ netif_carrier_off(vsi->netdev);
- /* free the ring and vector containers */
- if (free_qvectors && vsi->q_vectors) {
- devm_kfree(&pf->pdev->dev, vsi->q_vectors);
- vsi->q_vectors = NULL;
- }
- if (vsi->tx_rings) {
- devm_kfree(&pf->pdev->dev, vsi->tx_rings);
- vsi->tx_rings = NULL;
- }
- if (vsi->rx_rings) {
- devm_kfree(&pf->pdev->dev, vsi->rx_rings);
- vsi->rx_rings = NULL;
- }
-}
-
-/**
- * ice_vsi_clear - clean up and deallocate the provided vsi
- * @vsi: pointer to VSI being cleared
- *
- * This deallocates the vsi's queue resources, removes it from the PF's
- * VSI array if necessary, and deallocates the VSI
- *
- * Returns 0 on success, negative on failure
- */
-static int ice_vsi_clear(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = NULL;
-
- if (!vsi)
- return 0;
-
- if (!vsi->back)
- return -EINVAL;
-
- pf = vsi->back;
-
- if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) {
- dev_dbg(&pf->pdev->dev, "vsi does not exist at pf->vsi[%d]\n",
- vsi->idx);
- return -EINVAL;
- }
-
- mutex_lock(&pf->sw_mutex);
- /* updates the PF for this cleared vsi */
-
- pf->vsi[vsi->idx] = NULL;
- if (vsi->idx < pf->next_vsi)
- pf->next_vsi = vsi->idx;
-
- ice_vsi_free_arrays(vsi, true);
- mutex_unlock(&pf->sw_mutex);
- devm_kfree(&pf->pdev->dev, vsi);
-
- return 0;
-}
-
-/**
- * ice_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
- * @vsi: the VSI being configured
- * @v_idx: index of the vector in the vsi struct
- *
- * We allocate one q_vector. If allocation fails we return -ENOMEM.
- */
-static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
-{
- struct ice_pf *pf = vsi->back;
- struct ice_q_vector *q_vector;
-
- /* allocate q_vector */
- q_vector = devm_kzalloc(&pf->pdev->dev, sizeof(*q_vector), GFP_KERNEL);
- if (!q_vector)
- return -ENOMEM;
-
- q_vector->vsi = vsi;
- q_vector->v_idx = v_idx;
- /* only set affinity_mask if the CPU is online */
- if (cpu_online(v_idx))
- cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
- if (vsi->netdev)
- netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll,
- NAPI_POLL_WEIGHT);
- /* tie q_vector and vsi together */
- vsi->q_vectors[v_idx] = q_vector;
-
- return 0;
-}
-
-/**
- * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
- * @vsi: the VSI being configured
- *
- * We allocate one q_vector per queue interrupt. If allocation fails we
- * return -ENOMEM.
- */
-static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int v_idx = 0, num_q_vectors;
- int err;
-
- if (vsi->q_vectors[0]) {
- dev_dbg(&pf->pdev->dev, "VSI %d has existing q_vectors\n",
- vsi->vsi_num);
- return -EEXIST;
- }
-
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- num_q_vectors = vsi->num_q_vectors;
- } else {
- err = -EINVAL;
- goto err_out;
- }
-
- for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
- err = ice_vsi_alloc_q_vector(vsi, v_idx);
- if (err)
- goto err_out;
- }
-
- return 0;
-
-err_out:
- while (v_idx--)
- ice_free_q_vector(vsi, v_idx);
-
- dev_err(&pf->pdev->dev,
- "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
- vsi->num_q_vectors, vsi->vsi_num, err);
- vsi->num_q_vectors = 0;
- return err;
-}
-
-/**
- * ice_vsi_setup_vector_base - Set up the base vector for the given VSI
- * @vsi: ptr to the VSI
- *
- * This should only be called after ice_vsi_alloc() which allocates the
- * corresponding SW VSI structure and initializes num_queue_pairs for the
- * newly allocated VSI.
- *
- * Returns 0 on success or negative on failure
- */
-static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- int num_q_vectors = 0;
-
- if (vsi->base_vector) {
- dev_dbg(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n",
- vsi->vsi_num, vsi->base_vector);
- return -EEXIST;
- }
-
- if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- return -ENOENT;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- num_q_vectors = vsi->num_q_vectors;
- break;
- default:
- dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
- vsi->type);
- break;
- }
-
- if (num_q_vectors)
- vsi->base_vector = ice_get_res(pf, pf->irq_tracker,
- num_q_vectors, vsi->idx);
-
- if (vsi->base_vector < 0) {
- dev_err(&pf->pdev->dev,
- "Failed to get tracking for %d vectors for VSI %d, err=%d\n",
- num_q_vectors, vsi->vsi_num, vsi->base_vector);
- return -ENOENT;
- }
+ /* make sure transmit queues start off as stopped */
+ netif_tx_stop_all_queues(vsi->netdev);
return 0;
}
@@ -2572,343 +2087,48 @@
}
/**
- * ice_vsi_cfg_rss - Configure RSS params for a VSI
- * @vsi: VSI to be configured
- */
-static int ice_vsi_cfg_rss(struct ice_vsi *vsi)
-{
- u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
- struct ice_aqc_get_set_rss_keys *key;
- struct ice_pf *pf = vsi->back;
- enum ice_status status;
- int err = 0;
- u8 *lut;
-
- vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq);
-
- lut = devm_kzalloc(&pf->pdev->dev, vsi->rss_table_size, GFP_KERNEL);
- if (!lut)
- return -ENOMEM;
-
- if (vsi->rss_lut_user)
- memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
- else
- ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size);
-
- status = ice_aq_set_rss_lut(&pf->hw, vsi->vsi_num, vsi->rss_lut_type,
- lut, vsi->rss_table_size);
-
- if (status) {
- dev_err(&vsi->back->pdev->dev,
- "set_rss_lut failed, error %d\n", status);
- err = -EIO;
- goto ice_vsi_cfg_rss_exit;
- }
-
- key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL);
- if (!key) {
- err = -ENOMEM;
- goto ice_vsi_cfg_rss_exit;
- }
-
- if (vsi->rss_hkey_user)
- memcpy(seed, vsi->rss_hkey_user,
- ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
- else
- netdev_rss_key_fill((void *)seed,
- ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
- memcpy(&key->standard_rss_key, seed,
- ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
-
- status = ice_aq_set_rss_key(&pf->hw, vsi->vsi_num, key);
-
- if (status) {
- dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n",
- status);
- err = -EIO;
- }
-
- devm_kfree(&pf->pdev->dev, key);
-ice_vsi_cfg_rss_exit:
- devm_kfree(&pf->pdev->dev, lut);
- return err;
-}
-
-/**
- * ice_vsi_reinit_setup - return resource and reallocate resource for a VSI
- * @vsi: pointer to the ice_vsi
- *
- * This reallocates the VSIs queue resources
- *
- * Returns 0 on success and negative value on failure
- */
-static int ice_vsi_reinit_setup(struct ice_vsi *vsi)
-{
- u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
- int ret, i;
-
- if (!vsi)
- return -EINVAL;
-
- ice_vsi_free_q_vectors(vsi);
- ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx);
- vsi->base_vector = 0;
- ice_vsi_clear_rings(vsi);
- ice_vsi_free_arrays(vsi, false);
- ice_vsi_set_num_qs(vsi);
-
- /* Initialize VSI struct elements and create VSI in FW */
- ret = ice_vsi_add(vsi);
- if (ret < 0)
- goto err_vsi;
-
- ret = ice_vsi_alloc_arrays(vsi, false);
- if (ret < 0)
- goto err_vsi;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- if (!vsi->netdev) {
- ret = ice_cfg_netdev(vsi);
- if (ret)
- goto err_rings;
-
- ret = register_netdev(vsi->netdev);
- if (ret)
- goto err_rings;
-
- netif_carrier_off(vsi->netdev);
- netif_tx_stop_all_queues(vsi->netdev);
- }
-
- ret = ice_vsi_alloc_q_vectors(vsi);
- if (ret)
- goto err_rings;
-
- ret = ice_vsi_setup_vector_base(vsi);
- if (ret)
- goto err_vectors;
-
- ret = ice_vsi_alloc_rings(vsi);
- if (ret)
- goto err_vectors;
-
- ice_vsi_map_rings_to_vectors(vsi);
- break;
- default:
- break;
- }
-
- ice_vsi_set_tc_cfg(vsi);
-
- /* configure VSI nodes based on number of queues and TC's */
- for (i = 0; i < vsi->tc_cfg.numtc; i++)
- max_txqs[i] = vsi->num_txq;
-
- ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num,
- vsi->tc_cfg.ena_tc, max_txqs);
- if (ret) {
- dev_info(&vsi->back->pdev->dev,
- "Failed VSI lan queue config\n");
- goto err_vectors;
- }
- return 0;
-
-err_vectors:
- ice_vsi_free_q_vectors(vsi);
-err_rings:
- if (vsi->netdev) {
- vsi->current_netdev_flags = 0;
- unregister_netdev(vsi->netdev);
- free_netdev(vsi->netdev);
- vsi->netdev = NULL;
- }
-err_vsi:
- ice_vsi_clear(vsi);
- set_bit(__ICE_RESET_FAILED, vsi->back->state);
- return ret;
-}
-
-/**
- * ice_vsi_setup - Set up a VSI by a given type
+ * ice_pf_vsi_setup - Set up a PF VSI
* @pf: board private structure
- * @type: VSI type
* @pi: pointer to the port_info instance
*
- * This allocates the sw VSI structure and its queue resources.
- *
- * Returns pointer to the successfully allocated and configure VSI sw struct on
- * success, otherwise returns NULL on failure.
+ * Returns pointer to the successfully allocated VSI software struct
+ * on success, otherwise returns NULL on failure.
*/
static struct ice_vsi *
-ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type,
- struct ice_port_info *pi)
+ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
{
- u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
- struct device *dev = &pf->pdev->dev;
- struct ice_vsi_ctx ctxt = { 0 };
- struct ice_vsi *vsi;
- int ret, i;
-
- vsi = ice_vsi_alloc(pf, type);
- if (!vsi) {
- dev_err(dev, "could not allocate VSI\n");
- return NULL;
- }
-
- vsi->port_info = pi;
- vsi->vsw = pf->first_sw;
-
- if (ice_vsi_get_qs(vsi)) {
- dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n",
- vsi->idx);
- goto err_get_qs;
- }
-
- /* set RSS capabilities */
- ice_vsi_set_rss_params(vsi);
-
- /* create the VSI */
- ret = ice_vsi_add(vsi);
- if (ret)
- goto err_vsi;
-
- ctxt.vsi_num = vsi->vsi_num;
-
- switch (vsi->type) {
- case ICE_VSI_PF:
- ret = ice_cfg_netdev(vsi);
- if (ret)
- goto err_cfg_netdev;
-
- ret = register_netdev(vsi->netdev);
- if (ret)
- goto err_register_netdev;
-
- netif_carrier_off(vsi->netdev);
-
- /* make sure transmit queues start off as stopped */
- netif_tx_stop_all_queues(vsi->netdev);
- ret = ice_vsi_alloc_q_vectors(vsi);
- if (ret)
- goto err_msix;
-
- ret = ice_vsi_setup_vector_base(vsi);
- if (ret)
- goto err_rings;
-
- ret = ice_vsi_alloc_rings(vsi);
- if (ret)
- goto err_rings;
-
- ice_vsi_map_rings_to_vectors(vsi);
-
- /* Do not exit if configuring RSS had an issue, at least
- * receive traffic on first queue. Hence no need to capture
- * return value
- */
- if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
- ice_vsi_cfg_rss(vsi);
- break;
- default:
- /* if vsi type is not recognized, clean up the resources and
- * exit
- */
- goto err_rings;
- }
-
- ice_vsi_set_tc_cfg(vsi);
-
- /* configure VSI nodes based on number of queues and TC's */
- for (i = 0; i < vsi->tc_cfg.numtc; i++)
- max_txqs[i] = vsi->num_txq;
-
- ret = ice_cfg_vsi_lan(vsi->port_info, vsi->vsi_num,
- vsi->tc_cfg.ena_tc, max_txqs);
- if (ret) {
- dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n");
- goto err_rings;
- }
-
- return vsi;
-
-err_rings:
- ice_vsi_free_q_vectors(vsi);
-err_msix:
- if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED)
- unregister_netdev(vsi->netdev);
-err_register_netdev:
- if (vsi->netdev) {
- free_netdev(vsi->netdev);
- vsi->netdev = NULL;
- }
-err_cfg_netdev:
- ret = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL);
- if (ret)
- dev_err(&vsi->back->pdev->dev,
- "Free VSI AQ call failed, err %d\n", ret);
-err_vsi:
- ice_vsi_put_qs(vsi);
-err_get_qs:
- pf->q_left_tx += vsi->alloc_txq;
- pf->q_left_rx += vsi->alloc_rxq;
- ice_vsi_clear(vsi);
-
- return NULL;
+ return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID);
}
/**
- * ice_vsi_add_vlan - Add vsi membership for given vlan
- * @vsi: the vsi being configured
- * @vid: vlan id to be added
+ * ice_lb_vsi_setup - Set up a loopback VSI
+ * @pf: board private structure
+ * @pi: pointer to the port_info instance
+ *
+ * Returns pointer to the successfully allocated VSI software struct
+ * on success, otherwise returns NULL on failure.
*/
-static int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
+struct ice_vsi *
+ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
{
- struct ice_fltr_list_entry *tmp;
- struct ice_pf *pf = vsi->back;
- LIST_HEAD(tmp_add_list);
- enum ice_status status;
- int err = 0;
-
- tmp = devm_kzalloc(&pf->pdev->dev, sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
- return -ENOMEM;
-
- tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
- tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
- tmp->fltr_info.flag = ICE_FLTR_TX;
- tmp->fltr_info.src = vsi->vsi_num;
- tmp->fltr_info.fwd_id.vsi_id = vsi->vsi_num;
- tmp->fltr_info.l_data.vlan.vlan_id = vid;
-
- INIT_LIST_HEAD(&tmp->list_entry);
- list_add(&tmp->list_entry, &tmp_add_list);
-
- status = ice_add_vlan(&pf->hw, &tmp_add_list);
- if (status) {
- err = -ENODEV;
- dev_err(&pf->pdev->dev, "Failure Adding VLAN %d on VSI %i\n",
- vid, vsi->vsi_num);
- }
-
- ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
- return err;
+ return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID);
}
/**
- * ice_vlan_rx_add_vid - Add a vlan id filter to HW offload
+ * ice_vlan_rx_add_vid - Add a VLAN ID filter to HW offload
* @netdev: network interface to be adjusted
* @proto: unused protocol
- * @vid: vlan id to be added
+ * @vid: VLAN ID to be added
*
- * net_device_ops implementation for adding vlan ids
+ * net_device_ops implementation for adding VLAN IDs
*/
-static int ice_vlan_rx_add_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto,
+ u16 vid)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
- int ret = 0;
+ int ret;
if (vid >= VLAN_N_VID) {
netdev_err(netdev, "VLAN id requested %d is out of range %d\n",
@@ -2919,76 +2139,59 @@
if (vsi->info.pvid)
return -EINVAL;
- /* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is
+ /* Enable VLAN pruning when VLAN 0 is added */
+ if (unlikely(!vid)) {
+ ret = ice_cfg_vlan_pruning(vsi, true, false);
+ if (ret)
+ return ret;
+ }
+
+ /* Add all VLAN IDs including 0 to the switch filter. VLAN ID 0 is
* needed to continue allowing all untagged packets since VLAN prune
* list is applied to all packets by the switch
*/
ret = ice_vsi_add_vlan(vsi, vid);
-
- if (!ret)
- set_bit(vid, vsi->active_vlans);
+ if (!ret) {
+ vsi->vlan_ena = true;
+ set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+ }
return ret;
}
/**
- * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN
- * @vsi: the VSI being configured
- * @vid: VLAN id to be removed
- */
-static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
-{
- struct ice_fltr_list_entry *list;
- struct ice_pf *pf = vsi->back;
- LIST_HEAD(tmp_add_list);
-
- list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
- if (!list)
- return;
-
- list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
- list->fltr_info.fwd_id.vsi_id = vsi->vsi_num;
- list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
- list->fltr_info.l_data.vlan.vlan_id = vid;
- list->fltr_info.flag = ICE_FLTR_TX;
- list->fltr_info.src = vsi->vsi_num;
-
- INIT_LIST_HEAD(&list->list_entry);
- list_add(&list->list_entry, &tmp_add_list);
-
- if (ice_remove_vlan(&pf->hw, &tmp_add_list))
- dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n",
- vid, vsi->vsi_num);
-
- ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
-}
-
-/**
- * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
+ * ice_vlan_rx_kill_vid - Remove a VLAN ID filter from HW offload
* @netdev: network interface to be adjusted
* @proto: unused protocol
- * @vid: vlan id to be removed
+ * @vid: VLAN ID to be removed
*
- * net_device_ops implementation for removing vlan ids
+ * net_device_ops implementation for removing VLAN IDs
*/
-static int ice_vlan_rx_kill_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto,
+ u16 vid)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
+ int ret;
if (vsi->info.pvid)
return -EINVAL;
- /* return code is ignored as there is nothing a user
- * can do about failure to remove and a log message was
- * already printed from the other function
+ /* Make sure ice_vsi_kill_vlan is successful before updating VLAN
+ * information
*/
- ice_vsi_kill_vlan(vsi, vid);
+ ret = ice_vsi_kill_vlan(vsi, vid);
+ if (ret)
+ return ret;
- clear_bit(vid, vsi->active_vlans);
+ /* Disable VLAN pruning when VLAN 0 is removed */
+ if (unlikely(!vid))
+ ret = ice_cfg_vlan_pruning(vsi, false, false);
- return 0;
+ vsi->vlan_ena = false;
+ set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+ return ret;
}
/**
@@ -2999,96 +2202,94 @@
*/
static int ice_setup_pf_sw(struct ice_pf *pf)
{
- LIST_HEAD(tmp_add_list);
- u8 broadcast[ETH_ALEN];
struct ice_vsi *vsi;
int status = 0;
- if (!ice_is_reset_recovery_pending(pf->state)) {
- vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info);
- if (!vsi) {
- status = -ENOMEM;
- goto error_exit;
- }
- } else {
- vsi = pf->vsi[0];
- status = ice_vsi_reinit_setup(vsi);
- if (status < 0)
- return -EIO;
- }
+ if (ice_is_reset_in_progress(pf->state))
+ return -EBUSY;
- /* tmp_add_list contains a list of MAC addresses for which MAC
- * filters need to be programmed. Add the VSI's unicast MAC to
- * this list
- */
- status = ice_add_mac_to_list(vsi, &tmp_add_list,
- vsi->port_info->mac.perm_addr);
- if (status)
- goto error_exit;
-
- /* VSI needs to receive broadcast traffic, so add the broadcast
- * MAC address to the list.
- */
- eth_broadcast_addr(broadcast);
- status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast);
- if (status)
- goto error_exit;
-
- /* program MAC filters for entries in tmp_add_list */
- status = ice_add_mac(&pf->hw, &tmp_add_list);
- if (status) {
- dev_err(&pf->pdev->dev, "Could not add MAC filters\n");
+ vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
+ if (!vsi) {
status = -ENOMEM;
- goto error_exit;
+ goto unroll_vsi_setup;
}
- ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+ status = ice_cfg_netdev(vsi);
+ if (status) {
+ status = -ENODEV;
+ goto unroll_vsi_setup;
+ }
+
+ /* registering the NAPI handler requires both the queues and
+ * netdev to be created, which are done in ice_pf_vsi_setup()
+ * and ice_cfg_netdev() respectively
+ */
+ ice_napi_add(vsi);
+
+ status = ice_init_mac_fltr(pf);
+ if (status)
+ goto unroll_napi_add;
+
return status;
-error_exit:
- ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
-
+unroll_napi_add:
if (vsi) {
- ice_vsi_free_q_vectors(vsi);
- if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED)
- unregister_netdev(vsi->netdev);
+ ice_napi_del(vsi);
if (vsi->netdev) {
+ if (vsi->netdev->reg_state == NETREG_REGISTERED)
+ unregister_netdev(vsi->netdev);
free_netdev(vsi->netdev);
vsi->netdev = NULL;
}
+ }
+unroll_vsi_setup:
+ if (vsi) {
+ ice_vsi_free_q_vectors(vsi);
ice_vsi_delete(vsi);
ice_vsi_put_qs(vsi);
- pf->q_left_tx += vsi->alloc_txq;
- pf->q_left_rx += vsi->alloc_rxq;
ice_vsi_clear(vsi);
}
return status;
}
/**
- * ice_determine_q_usage - Calculate queue distribution
- * @pf: board private structure
- *
- * Return -ENOMEM if we don't get enough queues for all ports
+ * ice_get_avail_q_count - Get count of queues in use
+ * @pf_qmap: bitmap to get queue use count from
+ * @lock: pointer to a mutex that protects access to pf_qmap
+ * @size: size of the bitmap
*/
-static void ice_determine_q_usage(struct ice_pf *pf)
+static u16
+ice_get_avail_q_count(unsigned long *pf_qmap, struct mutex *lock, u16 size)
{
- u16 q_left_tx, q_left_rx;
+ u16 count = 0, bit;
- q_left_tx = pf->hw.func_caps.common_cap.num_txq;
- q_left_rx = pf->hw.func_caps.common_cap.num_rxq;
+ mutex_lock(lock);
+ for_each_clear_bit(bit, pf_qmap, size)
+ count++;
+ mutex_unlock(lock);
- pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus());
+ return count;
+}
- /* only 1 rx queue unless RSS is enabled */
- if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
- pf->num_lan_rx = 1;
- else
- pf->num_lan_rx = min_t(int, q_left_rx, num_online_cpus());
+/**
+ * ice_get_avail_txq_count - Get count of Tx queues in use
+ * @pf: pointer to an ice_pf instance
+ */
+u16 ice_get_avail_txq_count(struct ice_pf *pf)
+{
+ return ice_get_avail_q_count(pf->avail_txqs, &pf->avail_q_mutex,
+ pf->max_pf_txqs);
+}
- pf->q_left_tx = q_left_tx - pf->num_lan_tx;
- pf->q_left_rx = q_left_rx - pf->num_lan_rx;
+/**
+ * ice_get_avail_rxq_count - Get count of Rx queues in use
+ * @pf: pointer to an ice_pf instance
+ */
+u16 ice_get_avail_rxq_count(struct ice_pf *pf)
+{
+ return ice_get_avail_q_count(pf->avail_rxqs, &pf->avail_q_mutex,
+ pf->max_pf_rxqs);
}
/**
@@ -3097,40 +2298,77 @@
*/
static void ice_deinit_pf(struct ice_pf *pf)
{
- if (pf->serv_tmr.function)
- del_timer_sync(&pf->serv_tmr);
- if (pf->serv_task.func)
- cancel_work_sync(&pf->serv_task);
+ ice_service_task_stop(pf);
mutex_destroy(&pf->sw_mutex);
mutex_destroy(&pf->avail_q_mutex);
+
+ if (pf->avail_txqs) {
+ bitmap_free(pf->avail_txqs);
+ pf->avail_txqs = NULL;
+ }
+
+ if (pf->avail_rxqs) {
+ bitmap_free(pf->avail_rxqs);
+ pf->avail_rxqs = NULL;
+ }
+}
+
+/**
+ * ice_set_pf_caps - set PFs capability flags
+ * @pf: pointer to the PF instance
+ */
+static void ice_set_pf_caps(struct ice_pf *pf)
+{
+ struct ice_hw_func_caps *func_caps = &pf->hw.func_caps;
+
+ clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+ if (func_caps->common_cap.dcb)
+ set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+#ifdef CONFIG_PCI_IOV
+ clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
+ if (func_caps->common_cap.sr_iov_1_1) {
+ set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
+ pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs,
+ ICE_MAX_VF_COUNT);
+ }
+#endif /* CONFIG_PCI_IOV */
+ clear_bit(ICE_FLAG_RSS_ENA, pf->flags);
+ if (func_caps->common_cap.rss_table_size)
+ set_bit(ICE_FLAG_RSS_ENA, pf->flags);
+
+ pf->max_pf_txqs = func_caps->common_cap.num_txq;
+ pf->max_pf_rxqs = func_caps->common_cap.num_rxq;
}
/**
* ice_init_pf - Initialize general software structures (struct ice_pf)
* @pf: board private structure to initialize
*/
-static void ice_init_pf(struct ice_pf *pf)
+static int ice_init_pf(struct ice_pf *pf)
{
- bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS);
- set_bit(ICE_FLAG_MSIX_ENA, pf->flags);
+ ice_set_pf_caps(pf);
mutex_init(&pf->sw_mutex);
- mutex_init(&pf->avail_q_mutex);
-
- /* Clear avail_[t|r]x_qs bitmaps (set all to avail) */
- mutex_lock(&pf->avail_q_mutex);
- bitmap_zero(pf->avail_txqs, ICE_MAX_TXQS);
- bitmap_zero(pf->avail_rxqs, ICE_MAX_RXQS);
- mutex_unlock(&pf->avail_q_mutex);
-
- if (pf->hw.func_caps.common_cap.rss_table_size)
- set_bit(ICE_FLAG_RSS_ENA, pf->flags);
/* setup service timer and periodic service task */
timer_setup(&pf->serv_tmr, ice_service_timer, 0);
pf->serv_tmr_period = HZ;
INIT_WORK(&pf->serv_task, ice_service_task);
clear_bit(__ICE_SERVICE_SCHED, pf->state);
+
+ mutex_init(&pf->avail_q_mutex);
+ pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL);
+ if (!pf->avail_txqs)
+ return -ENOMEM;
+
+ pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
+ if (!pf->avail_rxqs) {
+ devm_kfree(&pf->pdev->dev, pf->avail_txqs);
+ pf->avail_txqs = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
}
/**
@@ -3149,15 +2387,21 @@
/* reserve one vector for miscellaneous handler */
needed = 1;
+ if (v_left < needed)
+ goto no_hw_vecs_left_err;
v_budget += needed;
v_left -= needed;
/* reserve vectors for LAN traffic */
- pf->num_lan_msix = min_t(int, num_online_cpus(), v_left);
- v_budget += pf->num_lan_msix;
+ needed = min_t(int, num_online_cpus(), v_left);
+ if (v_left < needed)
+ goto no_hw_vecs_left_err;
+ pf->num_lan_msix = needed;
+ v_budget += needed;
+ v_left -= needed;
pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
- sizeof(struct msix_entry), GFP_KERNEL);
+ sizeof(*pf->msix_entries), GFP_KERNEL);
if (!pf->msix_entries) {
err = -ENOMEM;
@@ -3179,17 +2423,18 @@
if (v_actual < v_budget) {
dev_warn(&pf->pdev->dev,
- "not enough vectors. requested = %d, obtained = %d\n",
+ "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
v_budget, v_actual);
- if (v_actual >= (pf->num_lan_msix + 1)) {
- pf->num_avail_msix = v_actual - (pf->num_lan_msix + 1);
- } else if (v_actual >= 2) {
- pf->num_lan_msix = 1;
- pf->num_avail_msix = v_actual - 2;
- } else {
+/* 2 vectors for LAN (traffic + OICR) */
+#define ICE_MIN_LAN_VECS 2
+
+ if (v_actual < ICE_MIN_LAN_VECS) {
+ /* error if we can't get minimum vectors */
pci_disable_msix(pf->pdev);
err = -ERANGE;
goto msix_err;
+ } else {
+ pf->num_lan_msix = ICE_MIN_LAN_VECS;
}
}
@@ -3199,9 +2444,13 @@
devm_kfree(&pf->pdev->dev, pf->msix_entries);
goto exit_err;
+no_hw_vecs_left_err:
+ dev_err(&pf->pdev->dev,
+ "not enough device MSI-X vectors. requested = %d, available = %d\n",
+ needed, v_left);
+ err = -ERANGE;
exit_err:
pf->num_lan_msix = 0;
- clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
return err;
}
@@ -3214,38 +2463,6 @@
pci_disable_msix(pf->pdev);
devm_kfree(&pf->pdev->dev, pf->msix_entries);
pf->msix_entries = NULL;
- clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
-}
-
-/**
- * ice_init_interrupt_scheme - Determine proper interrupt scheme
- * @pf: board private structure to initialize
- */
-static int ice_init_interrupt_scheme(struct ice_pf *pf)
-{
- int vectors = 0;
- ssize_t size;
-
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- vectors = ice_ena_msix_range(pf);
- else
- return -ENODEV;
-
- if (vectors < 0)
- return vectors;
-
- /* set up vector assignment tracking */
- size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors);
-
- pf->irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
- if (!pf->irq_tracker) {
- ice_dis_msix(pf);
- return -ENOMEM;
- }
-
- pf->irq_tracker->num_entries = vectors;
-
- return 0;
}
/**
@@ -3254,8 +2471,7 @@
*/
static void ice_clear_interrupt_scheme(struct ice_pf *pf)
{
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- ice_dis_msix(pf);
+ ice_dis_msix(pf);
if (pf->irq_tracker) {
devm_kfree(&pf->pdev->dev, pf->irq_tracker);
@@ -3264,40 +2480,343 @@
}
/**
+ * ice_init_interrupt_scheme - Determine proper interrupt scheme
+ * @pf: board private structure to initialize
+ */
+static int ice_init_interrupt_scheme(struct ice_pf *pf)
+{
+ int vectors;
+
+ vectors = ice_ena_msix_range(pf);
+
+ if (vectors < 0)
+ return vectors;
+
+ /* set up vector assignment tracking */
+ pf->irq_tracker =
+ devm_kzalloc(&pf->pdev->dev, sizeof(*pf->irq_tracker) +
+ (sizeof(u16) * vectors), GFP_KERNEL);
+ if (!pf->irq_tracker) {
+ ice_dis_msix(pf);
+ return -ENOMEM;
+ }
+
+ /* populate SW interrupts pool with number of OS granted IRQs. */
+ pf->num_avail_sw_msix = vectors;
+ pf->irq_tracker->num_entries = vectors;
+ pf->irq_tracker->end = pf->irq_tracker->num_entries;
+
+ return 0;
+}
+
+/**
+ * ice_log_pkg_init - log result of DDP package load
+ * @hw: pointer to hardware info
+ * @status: status of package load
+ */
+static void
+ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
+{
+ struct ice_pf *pf = (struct ice_pf *)hw->back;
+ struct device *dev = &pf->pdev->dev;
+
+ switch (*status) {
+ case ICE_SUCCESS:
+ /* The package download AdminQ command returned success because
+ * this download succeeded or ICE_ERR_AQ_NO_WORK since there is
+ * already a package loaded on the device.
+ */
+ if (hw->pkg_ver.major == hw->active_pkg_ver.major &&
+ hw->pkg_ver.minor == hw->active_pkg_ver.minor &&
+ hw->pkg_ver.update == hw->active_pkg_ver.update &&
+ hw->pkg_ver.draft == hw->active_pkg_ver.draft &&
+ !memcmp(hw->pkg_name, hw->active_pkg_name,
+ sizeof(hw->pkg_name))) {
+ if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST)
+ dev_info(dev,
+ "DDP package already present on device: %s version %d.%d.%d.%d\n",
+ hw->active_pkg_name,
+ hw->active_pkg_ver.major,
+ hw->active_pkg_ver.minor,
+ hw->active_pkg_ver.update,
+ hw->active_pkg_ver.draft);
+ else
+ dev_info(dev,
+ "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n",
+ hw->active_pkg_name,
+ hw->active_pkg_ver.major,
+ hw->active_pkg_ver.minor,
+ hw->active_pkg_ver.update,
+ hw->active_pkg_ver.draft);
+ } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ ||
+ hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) {
+ dev_err(dev,
+ "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n",
+ hw->active_pkg_name,
+ hw->active_pkg_ver.major,
+ hw->active_pkg_ver.minor,
+ ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
+ *status = ICE_ERR_NOT_SUPPORTED;
+ } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
+ hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) {
+ dev_info(dev,
+ "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n",
+ hw->active_pkg_name,
+ hw->active_pkg_ver.major,
+ hw->active_pkg_ver.minor,
+ hw->active_pkg_ver.update,
+ hw->active_pkg_ver.draft,
+ hw->pkg_name,
+ hw->pkg_ver.major,
+ hw->pkg_ver.minor,
+ hw->pkg_ver.update,
+ hw->pkg_ver.draft);
+ } else {
+ dev_err(dev,
+ "An unknown error occurred when loading the DDP package, please reboot the system. If the problem persists, update the NVM. Entering Safe Mode.\n");
+ *status = ICE_ERR_NOT_SUPPORTED;
+ }
+ break;
+ case ICE_ERR_BUF_TOO_SHORT:
+ /* fall-through */
+ case ICE_ERR_CFG:
+ dev_err(dev,
+ "The DDP package file is invalid. Entering Safe Mode.\n");
+ break;
+ case ICE_ERR_NOT_SUPPORTED:
+ /* Package File version not supported */
+ if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ ||
+ (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
+ hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR))
+ dev_err(dev,
+ "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n");
+ else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ ||
+ (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
+ hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR))
+ dev_err(dev,
+ "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n",
+ ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
+ break;
+ case ICE_ERR_AQ_ERROR:
+ switch (hw->adminq.sq_last_status) {
+ case ICE_AQ_RC_ENOSEC:
+ case ICE_AQ_RC_EBADSIG:
+ dev_err(dev,
+ "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n");
+ return;
+ case ICE_AQ_RC_ESVN:
+ dev_err(dev,
+ "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n");
+ return;
+ case ICE_AQ_RC_EBADMAN:
+ case ICE_AQ_RC_EBADBUF:
+ dev_err(dev,
+ "An error occurred on the device while loading the DDP package. The device will be reset.\n");
+ return;
+ default:
+ break;
+ }
+ /* fall-through */
+ default:
+ dev_err(dev,
+ "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n",
+ *status);
+ break;
+ }
+}
+
+/**
+ * ice_load_pkg - load/reload the DDP Package file
+ * @firmware: firmware structure when firmware requested or NULL for reload
+ * @pf: pointer to the PF instance
+ *
+ * Called on probe and post CORER/GLOBR rebuild to load DDP Package and
+ * initialize HW tables.
+ */
+static void
+ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf)
+{
+ enum ice_status status = ICE_ERR_PARAM;
+ struct device *dev = &pf->pdev->dev;
+ struct ice_hw *hw = &pf->hw;
+
+ /* Load DDP Package */
+ if (firmware && !hw->pkg_copy) {
+ status = ice_copy_and_init_pkg(hw, firmware->data,
+ firmware->size);
+ ice_log_pkg_init(hw, &status);
+ } else if (!firmware && hw->pkg_copy) {
+ /* Reload package during rebuild after CORER/GLOBR reset */
+ status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size);
+ ice_log_pkg_init(hw, &status);
+ } else {
+ dev_err(dev,
+ "The DDP package file failed to load. Entering Safe Mode.\n");
+ }
+
+ if (status) {
+ /* Safe Mode */
+ clear_bit(ICE_FLAG_ADV_FEATURES, pf->flags);
+ return;
+ }
+
+ /* Successful download package is the precondition for advanced
+ * features, hence setting the ICE_FLAG_ADV_FEATURES flag
+ */
+ set_bit(ICE_FLAG_ADV_FEATURES, pf->flags);
+}
+
+/**
+ * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
+ * @pf: pointer to the PF structure
+ *
+ * There is no error returned here because the driver should be able to handle
+ * 128 Byte cache lines, so we only print a warning in case issues are seen,
+ * specifically with Tx.
+ */
+static void ice_verify_cacheline_size(struct ice_pf *pf)
+{
+ if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M)
+ dev_warn(&pf->pdev->dev,
+ "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
+ ICE_CACHE_LINE_BYTES);
+}
+
+/**
+ * ice_send_version - update firmware with driver version
+ * @pf: PF struct
+ *
+ * Returns ICE_SUCCESS on success, else error code
+ */
+static enum ice_status ice_send_version(struct ice_pf *pf)
+{
+ struct ice_driver_ver dv;
+
+ dv.major_ver = DRV_VERSION_MAJOR;
+ dv.minor_ver = DRV_VERSION_MINOR;
+ dv.build_ver = DRV_VERSION_BUILD;
+ dv.subbuild_ver = 0;
+ strscpy((char *)dv.driver_string, DRV_VERSION,
+ sizeof(dv.driver_string));
+ return ice_aq_send_driver_ver(&pf->hw, &dv, NULL);
+}
+
+/**
+ * ice_get_opt_fw_name - return optional firmware file name or NULL
+ * @pf: pointer to the PF instance
+ */
+static char *ice_get_opt_fw_name(struct ice_pf *pf)
+{
+ /* Optional firmware name same as default with additional dash
+ * followed by a EUI-64 identifier (PCIe Device Serial Number)
+ */
+ struct pci_dev *pdev = pf->pdev;
+ char *opt_fw_filename = NULL;
+ u32 dword;
+ u8 dsn[8];
+ int pos;
+
+ /* Determine the name of the optional file using the DSN (two
+ * dwords following the start of the DSN Capability).
+ */
+ pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
+ if (pos) {
+ opt_fw_filename = kzalloc(NAME_MAX, GFP_KERNEL);
+ if (!opt_fw_filename)
+ return NULL;
+
+ pci_read_config_dword(pdev, pos + 4, &dword);
+ put_unaligned_le32(dword, &dsn[0]);
+ pci_read_config_dword(pdev, pos + 8, &dword);
+ put_unaligned_le32(dword, &dsn[4]);
+ snprintf(opt_fw_filename, NAME_MAX,
+ "%sice-%02x%02x%02x%02x%02x%02x%02x%02x.pkg",
+ ICE_DDP_PKG_PATH,
+ dsn[7], dsn[6], dsn[5], dsn[4],
+ dsn[3], dsn[2], dsn[1], dsn[0]);
+ }
+
+ return opt_fw_filename;
+}
+
+/**
+ * ice_request_fw - Device initialization routine
+ * @pf: pointer to the PF instance
+ */
+static void ice_request_fw(struct ice_pf *pf)
+{
+ char *opt_fw_filename = ice_get_opt_fw_name(pf);
+ const struct firmware *firmware = NULL;
+ struct device *dev = &pf->pdev->dev;
+ int err = 0;
+
+ /* optional device-specific DDP (if present) overrides the default DDP
+ * package file. kernel logs a debug message if the file doesn't exist,
+ * and warning messages for other errors.
+ */
+ if (opt_fw_filename) {
+ err = firmware_request_nowarn(&firmware, opt_fw_filename, dev);
+ if (err) {
+ kfree(opt_fw_filename);
+ goto dflt_pkg_load;
+ }
+
+ /* request for firmware was successful. Download to device */
+ ice_load_pkg(firmware, pf);
+ kfree(opt_fw_filename);
+ release_firmware(firmware);
+ return;
+ }
+
+dflt_pkg_load:
+ err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
+ if (err) {
+ dev_err(dev,
+ "The DDP package file was not found or could not be read. Entering Safe Mode\n");
+ return;
+ }
+
+ /* request for firmware was successful. Download to device */
+ ice_load_pkg(firmware, pf);
+ release_firmware(firmware);
+}
+
+/**
* ice_probe - Device initialization routine
* @pdev: PCI device information struct
* @ent: entry in ice_pci_tbl
*
* Returns 0 on success, negative on failure
*/
-static int ice_probe(struct pci_dev *pdev,
- const struct pci_device_id __always_unused *ent)
+static int
+ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
{
+ struct device *dev = &pdev->dev;
struct ice_pf *pf;
struct ice_hw *hw;
int err;
- /* this driver uses devres, see Documentation/driver-model/devres.txt */
+ /* this driver uses devres, see Documentation/driver-api/driver-model/devres.rst */
err = pcim_enable_device(pdev);
if (err)
return err;
err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev));
if (err) {
- dev_err(&pdev->dev, "BAR0 I/O map error %d\n", err);
+ dev_err(dev, "BAR0 I/O map error %d\n", err);
return err;
}
- pf = devm_kzalloc(&pdev->dev, sizeof(*pf), GFP_KERNEL);
+ pf = devm_kzalloc(dev, sizeof(*pf), GFP_KERNEL);
if (!pf)
return -ENOMEM;
- /* set up for high or low dma */
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ /* set up for high or low DMA */
+ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
if (err)
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (err) {
- dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err);
+ dev_err(dev, "DMA configuration failed: 0x%x\n", err);
return err;
}
@@ -3307,6 +2826,8 @@
pf->pdev = pdev;
pci_set_drvdata(pdev, pf);
set_bit(__ICE_DOWN, pf->state);
+ /* Disable service task until DOWN bit is cleared */
+ set_bit(__ICE_SERVICE_DIS, pf->state);
hw = &pf->hw;
hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0];
@@ -3329,28 +2850,47 @@
err = ice_init_hw(hw);
if (err) {
- dev_err(&pdev->dev, "ice_init_hw failed: %d\n", err);
+ dev_err(dev, "ice_init_hw failed: %d\n", err);
err = -EIO;
goto err_exit_unroll;
}
- dev_info(&pdev->dev, "firmware %d.%d.%05d api %d.%d\n",
- hw->fw_maj_ver, hw->fw_min_ver, hw->fw_build,
- hw->api_maj_ver, hw->api_min_ver);
+ dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n",
+ hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch,
+ hw->api_maj_ver, hw->api_min_ver, hw->api_patch,
+ ice_nvm_version_str(hw), hw->fw_build);
- ice_init_pf(pf);
+ ice_request_fw(pf);
- ice_determine_q_usage(pf);
+ /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
+ * set in pf->state, which will cause ice_is_safe_mode to return
+ * true
+ */
+ if (ice_is_safe_mode(pf)) {
+ dev_err(dev,
+ "Package download failed. Advanced features disabled - Device now in Safe Mode\n");
+ /* we already got function/device capabilities but these don't
+ * reflect what the driver needs to do in safe mode. Instead of
+ * adding conditional logic everywhere to ignore these
+ * device/function capabilities, override them.
+ */
+ ice_set_safe_mode_caps(hw);
+ }
- pf->num_alloc_vsi = min_t(u16, ICE_MAX_VSI_ALLOC,
- hw->func_caps.guaranteed_num_vsi);
+ err = ice_init_pf(pf);
+ if (err) {
+ dev_err(dev, "ice_init_pf failed: %d\n", err);
+ goto err_init_pf_unroll;
+ }
+
+ pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
if (!pf->num_alloc_vsi) {
err = -EIO;
goto err_init_pf_unroll;
}
- pf->vsi = devm_kcalloc(&pdev->dev, pf->num_alloc_vsi,
- sizeof(struct ice_vsi *), GFP_KERNEL);
+ pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
+ GFP_KERNEL);
if (!pf->vsi) {
err = -ENOMEM;
goto err_init_pf_unroll;
@@ -3358,35 +2898,37 @@
err = ice_init_interrupt_scheme(pf);
if (err) {
- dev_err(&pdev->dev,
- "ice_init_interrupt_scheme failed: %d\n", err);
+ dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
err = -EIO;
goto err_init_interrupt_unroll;
}
+ /* Driver is mostly up */
+ clear_bit(__ICE_DOWN, pf->state);
+
/* In case of MSIX we are going to setup the misc vector right here
* to handle admin queue events etc. In case of legacy and MSI
* the misc functionality and queue processing is combined in
* the same vector and that gets setup at open.
*/
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- err = ice_req_irq_msix_misc(pf);
- if (err) {
- dev_err(&pdev->dev,
- "setup of misc vector failed: %d\n", err);
- goto err_init_interrupt_unroll;
- }
+ err = ice_req_irq_msix_misc(pf);
+ if (err) {
+ dev_err(dev, "setup of misc vector failed: %d\n", err);
+ goto err_init_interrupt_unroll;
}
/* create switch struct for the switch element created by FW on boot */
- pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(struct ice_sw),
- GFP_KERNEL);
+ pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL);
if (!pf->first_sw) {
err = -ENOMEM;
goto err_msix_misc_unroll;
}
- pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
+ if (hw->evb_veb)
+ pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
+ else
+ pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA;
+
pf->first_sw->pf = pf;
/* record the sw_id available for later use */
@@ -3394,33 +2936,57 @@
err = ice_setup_pf_sw(pf);
if (err) {
- dev_err(&pdev->dev,
- "probe failed due to setup pf switch:%d\n", err);
+ dev_err(dev, "probe failed due to setup PF switch:%d\n", err);
goto err_alloc_sw_unroll;
}
- /* Driver is mostly up */
- clear_bit(__ICE_DOWN, pf->state);
+ clear_bit(__ICE_SERVICE_DIS, pf->state);
+
+ /* tell the firmware we are up */
+ err = ice_send_version(pf);
+ if (err) {
+ dev_err(dev,
+ "probe failed sending driver version %s. error: %d\n",
+ ice_drv_ver, err);
+ goto err_alloc_sw_unroll;
+ }
/* since everything is good, start the service timer */
mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
err = ice_init_link_events(pf->hw.port_info);
if (err) {
- dev_err(&pdev->dev, "ice_init_link_events failed: %d\n", err);
+ dev_err(dev, "ice_init_link_events failed: %d\n", err);
goto err_alloc_sw_unroll;
}
+ ice_verify_cacheline_size(pf);
+
+ /* If no DDP driven features have to be setup, return here */
+ if (ice_is_safe_mode(pf))
+ return 0;
+
+ /* initialize DDP driven features */
+
+ /* Note: DCB init failure is non-fatal to load */
+ if (ice_init_pf_dcb(pf, false)) {
+ clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+ clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+ } else {
+ ice_cfg_lldp_mib_change(&pf->hw, true);
+ }
+
return 0;
err_alloc_sw_unroll:
+ set_bit(__ICE_SERVICE_DIS, pf->state);
set_bit(__ICE_DOWN, pf->state);
devm_kfree(&pf->pdev->dev, pf->first_sw);
err_msix_misc_unroll:
ice_free_irq_msix_misc(pf);
err_init_interrupt_unroll:
ice_clear_interrupt_scheme(pf);
- devm_kfree(&pdev->dev, pf->vsi);
+ devm_kfree(dev, pf->vsi);
err_init_pf_unroll:
ice_deinit_pf(pf);
ice_deinit_hw(hw);
@@ -3436,31 +3002,170 @@
static void ice_remove(struct pci_dev *pdev)
{
struct ice_pf *pf = pci_get_drvdata(pdev);
- int i = 0;
- int err;
+ int i;
if (!pf)
return;
- set_bit(__ICE_DOWN, pf->state);
-
- for (i = 0; i < pf->num_alloc_vsi; i++) {
- if (!pf->vsi[i])
- continue;
-
- err = ice_vsi_release(pf->vsi[i]);
- if (err)
- dev_dbg(&pf->pdev->dev, "Failed to release VSI index %d (err %d)\n",
- i, err);
+ for (i = 0; i < ICE_MAX_RESET_WAIT; i++) {
+ if (!ice_is_reset_in_progress(pf->state))
+ break;
+ msleep(100);
}
+ set_bit(__ICE_DOWN, pf->state);
+ ice_service_task_stop(pf);
+
+ if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags))
+ ice_free_vfs(pf);
+ ice_vsi_release_all(pf);
ice_free_irq_msix_misc(pf);
- ice_clear_interrupt_scheme(pf);
+ ice_for_each_vsi(pf, i) {
+ if (!pf->vsi[i])
+ continue;
+ ice_vsi_free_q_vectors(pf->vsi[i]);
+ }
ice_deinit_pf(pf);
ice_deinit_hw(&pf->hw);
+ ice_clear_interrupt_scheme(pf);
+ /* Issue a PFR as part of the prescribed driver unload flow. Do not
+ * do it via ice_schedule_reset() since there is no need to rebuild
+ * and the service task is already stopped.
+ */
+ ice_reset(&pf->hw, ICE_RESET_PFR);
pci_disable_pcie_error_reporting(pdev);
}
+/**
+ * ice_pci_err_detected - warning that PCI error has been detected
+ * @pdev: PCI device information struct
+ * @err: the type of PCI error
+ *
+ * Called to warn that something happened on the PCI bus and the error handling
+ * is in progress. Allows the driver to gracefully prepare/handle PCI errors.
+ */
+static pci_ers_result_t
+ice_pci_err_detected(struct pci_dev *pdev, enum pci_channel_state err)
+{
+ struct ice_pf *pf = pci_get_drvdata(pdev);
+
+ if (!pf) {
+ dev_err(&pdev->dev, "%s: unrecoverable device error %d\n",
+ __func__, err);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+ ice_service_task_stop(pf);
+
+ if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+ set_bit(__ICE_PFR_REQ, pf->state);
+ ice_prepare_for_reset(pf);
+ }
+ }
+
+ return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * ice_pci_err_slot_reset - a PCI slot reset has just happened
+ * @pdev: PCI device information struct
+ *
+ * Called to determine if the driver can recover from the PCI slot reset by
+ * using a register read to determine if the device is recoverable.
+ */
+static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev)
+{
+ struct ice_pf *pf = pci_get_drvdata(pdev);
+ pci_ers_result_t result;
+ int err;
+ u32 reg;
+
+ err = pci_enable_device_mem(pdev);
+ if (err) {
+ dev_err(&pdev->dev,
+ "Cannot re-enable PCI device after reset, error %d\n",
+ err);
+ result = PCI_ERS_RESULT_DISCONNECT;
+ } else {
+ pci_set_master(pdev);
+ pci_restore_state(pdev);
+ pci_save_state(pdev);
+ pci_wake_from_d3(pdev, false);
+
+ /* Check for life */
+ reg = rd32(&pf->hw, GLGEN_RTRIG);
+ if (!reg)
+ result = PCI_ERS_RESULT_RECOVERED;
+ else
+ result = PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ err = pci_cleanup_aer_uncorrect_error_status(pdev);
+ if (err)
+ dev_dbg(&pdev->dev,
+ "pci_cleanup_aer_uncorrect_error_status failed, error %d\n",
+ err);
+ /* non-fatal, continue */
+
+ return result;
+}
+
+/**
+ * ice_pci_err_resume - restart operations after PCI error recovery
+ * @pdev: PCI device information struct
+ *
+ * Called to allow the driver to bring things back up after PCI error and/or
+ * reset recovery have finished
+ */
+static void ice_pci_err_resume(struct pci_dev *pdev)
+{
+ struct ice_pf *pf = pci_get_drvdata(pdev);
+
+ if (!pf) {
+ dev_err(&pdev->dev,
+ "%s failed, device is unrecoverable\n", __func__);
+ return;
+ }
+
+ if (test_bit(__ICE_SUSPENDED, pf->state)) {
+ dev_dbg(&pdev->dev, "%s failed to resume normal operations!\n",
+ __func__);
+ return;
+ }
+
+ ice_do_reset(pf, ICE_RESET_PFR);
+ ice_service_task_restart(pf);
+ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
+}
+
+/**
+ * ice_pci_err_reset_prepare - prepare device driver for PCI reset
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_prepare(struct pci_dev *pdev)
+{
+ struct ice_pf *pf = pci_get_drvdata(pdev);
+
+ if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+ ice_service_task_stop(pf);
+
+ if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+ set_bit(__ICE_PFR_REQ, pf->state);
+ ice_prepare_for_reset(pf);
+ }
+ }
+}
+
+/**
+ * ice_pci_err_reset_done - PCI reset done, device driver reset can begin
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_done(struct pci_dev *pdev)
+{
+ ice_pci_err_resume(pdev);
+}
+
/* ice_pci_tbl - PCI Device ID Table
*
* Wildcard entries (PCI_ANY_ID) should come last
@@ -3470,21 +3175,29 @@
* Class, Class Mask, private data (not used) }
*/
static const struct pci_device_id ice_pci_tbl[] = {
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_10G_BASE_T), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SGMII), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
/* required last entry */
{ 0, }
};
MODULE_DEVICE_TABLE(pci, ice_pci_tbl);
+static const struct pci_error_handlers ice_pci_err_handler = {
+ .error_detected = ice_pci_err_detected,
+ .slot_reset = ice_pci_err_slot_reset,
+ .reset_prepare = ice_pci_err_reset_prepare,
+ .reset_done = ice_pci_err_reset_done,
+ .resume = ice_pci_err_resume
+};
+
static struct pci_driver ice_driver = {
.name = KBUILD_MODNAME,
.id_table = ice_pci_tbl,
.probe = ice_probe,
.remove = ice_remove,
+ .sriov_configure = ice_sriov_configure,
+ .err_handler = &ice_pci_err_handler
};
/**
@@ -3500,7 +3213,7 @@
pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver);
pr_info("%s\n", ice_copyright);
- ice_wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, KBUILD_MODNAME);
+ ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME);
if (!ice_wq) {
pr_err("Failed to create workqueue\n");
return -ENOMEM;
@@ -3508,7 +3221,7 @@
status = pci_register_driver(&ice_driver);
if (status) {
- pr_err("failed to register pci driver, err %d\n", status);
+ pr_err("failed to register PCI driver, err %d\n", status);
destroy_workqueue(ice_wq);
}
@@ -3531,7 +3244,7 @@
module_exit(ice_module_exit);
/**
- * ice_set_mac_address - NDO callback to set mac address
+ * ice_set_mac_address - NDO callback to set MAC address
* @netdev: network interface device structure
* @pi: pointer to an address structure
*
@@ -3545,10 +3258,8 @@
struct ice_hw *hw = &pf->hw;
struct sockaddr *addr = pi;
enum ice_status status;
- LIST_HEAD(a_mac_list);
- LIST_HEAD(r_mac_list);
u8 flags = 0;
- int err;
+ int err = 0;
u8 *mac;
mac = (u8 *)addr->sa_data;
@@ -3562,68 +3273,49 @@
}
if (test_bit(__ICE_DOWN, pf->state) ||
- ice_is_reset_recovery_pending(pf->state)) {
+ ice_is_reset_in_progress(pf->state)) {
netdev_err(netdev, "can't set mac %pM. device not ready\n",
mac);
return -EBUSY;
}
- /* When we change the mac address we also have to change the mac address
- * based filter rules that were created previously for the old mac
+ /* When we change the MAC address we also have to change the MAC address
+ * based filter rules that were created previously for the old MAC
* address. So first, we remove the old filter rule using ice_remove_mac
- * and then create a new filter rule using ice_add_mac. Note that for
- * both these operations, we first need to form a "list" of mac
- * addresses (even though in this case, we have only 1 mac address to be
- * added/removed) and this done using ice_add_mac_to_list. Depending on
- * the ensuing operation this "list" of mac addresses is either to be
- * added or removed from the filter.
+ * and then create a new filter rule using ice_add_mac via
+ * ice_vsi_cfg_mac_fltr function call for both add and/or remove
+ * filters.
*/
- err = ice_add_mac_to_list(vsi, &r_mac_list, netdev->dev_addr);
- if (err) {
- err = -EADDRNOTAVAIL;
- goto free_lists;
- }
-
- status = ice_remove_mac(hw, &r_mac_list);
+ status = ice_vsi_cfg_mac_fltr(vsi, netdev->dev_addr, false);
if (status) {
err = -EADDRNOTAVAIL;
- goto free_lists;
+ goto err_update_filters;
}
- err = ice_add_mac_to_list(vsi, &a_mac_list, mac);
- if (err) {
- err = -EADDRNOTAVAIL;
- goto free_lists;
- }
-
- status = ice_add_mac(hw, &a_mac_list);
+ status = ice_vsi_cfg_mac_fltr(vsi, mac, true);
if (status) {
err = -EADDRNOTAVAIL;
- goto free_lists;
+ goto err_update_filters;
}
-free_lists:
- /* free list entries */
- ice_free_fltr_list(&pf->pdev->dev, &r_mac_list);
- ice_free_fltr_list(&pf->pdev->dev, &a_mac_list);
-
+err_update_filters:
if (err) {
- netdev_err(netdev, "can't set mac %pM. filter update failed\n",
+ netdev_err(netdev, "can't set MAC %pM. filter update failed\n",
mac);
return err;
}
- /* change the netdev's mac address */
+ /* change the netdev's MAC address */
memcpy(netdev->dev_addr, mac, netdev->addr_len);
- netdev_dbg(vsi->netdev, "updated mac address to %pM\n",
+ netdev_dbg(vsi->netdev, "updated MAC address to %pM\n",
netdev->dev_addr);
- /* write new mac address to the firmware */
+ /* write new MAC address to the firmware */
flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
if (status) {
- netdev_err(netdev, "can't set mac %pM. write to firmware failed.\n",
- mac);
+ netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %d\n",
+ mac, status);
}
return 0;
}
@@ -3660,12 +3352,14 @@
* @tb: pointer to array of nladdr (unused)
* @dev: the net device pointer
* @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
* @flags: instructions from stack about fdb operation
+ * @extack: netlink extended ack
*/
-static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
- struct net_device *dev, const unsigned char *addr,
- u16 vid, u16 flags)
+static int
+ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
+ struct net_device *dev, const unsigned char *addr, u16 vid,
+ u16 flags, struct netlink_ext_ack __always_unused *extack)
{
int err;
@@ -3698,11 +3392,12 @@
* @tb: pointer to array of nladdr (unused)
* @dev: the net device pointer
* @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
*/
-static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
- struct net_device *dev, const unsigned char *addr,
- __always_unused u16 vid)
+static int
+ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ __always_unused u16 vid)
{
int err;
@@ -3722,108 +3417,60 @@
}
/**
- * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx
- * @vsi: the vsi being changed
- */
-static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
-{
- struct device *dev = &vsi->back->pdev->dev;
- struct ice_hw *hw = &vsi->back->hw;
- struct ice_vsi_ctx ctxt = { 0 };
- enum ice_status status;
-
- /* Here we are configuring the VSI to let the driver add VLAN tags by
- * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag
- * insertion happens in the Tx hot path, in ice_tx_map.
- */
- ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
-
- ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
- ctxt.vsi_num = vsi->vsi_num;
-
- status = ice_aq_update_vsi(hw, &ctxt, NULL);
- if (status) {
- dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
- status, hw->adminq.sq_last_status);
- return -EIO;
- }
-
- vsi->info.vlan_flags = ctxt.info.vlan_flags;
- return 0;
-}
-
-/**
- * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx
- * @vsi: the vsi being changed
- * @ena: boolean value indicating if this is a enable or disable request
- */
-static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
-{
- struct device *dev = &vsi->back->pdev->dev;
- struct ice_hw *hw = &vsi->back->hw;
- struct ice_vsi_ctx ctxt = { 0 };
- enum ice_status status;
-
- /* Here we are configuring what the VSI should do with the VLAN tag in
- * the Rx packet. We can either leave the tag in the packet or put it in
- * the Rx descriptor.
- */
- if (ena) {
- /* Strip VLAN tag from Rx packet and put it in the desc */
- ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
- } else {
- /* Disable stripping. Leave tag in packet */
- ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
- }
-
- /* Allow all packets untagged/tagged */
- ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
-
- ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
- ctxt.vsi_num = vsi->vsi_num;
-
- status = ice_aq_update_vsi(hw, &ctxt, NULL);
- if (status) {
- dev_err(dev, "update VSI for VALN strip failed, ena = %d err %d aq_err %d\n",
- ena, status, hw->adminq.sq_last_status);
- return -EIO;
- }
-
- vsi->info.vlan_flags = ctxt.info.vlan_flags;
- return 0;
-}
-
-/**
* ice_set_features - set the netdev feature flags
* @netdev: ptr to the netdev being adjusted
* @features: the feature set that the stack is suggesting
*/
-static int ice_set_features(struct net_device *netdev,
- netdev_features_t features)
+static int
+ice_set_features(struct net_device *netdev, netdev_features_t features)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
int ret = 0;
+ /* Don't set any netdev advanced features with device in Safe Mode */
+ if (ice_is_safe_mode(vsi->back)) {
+ dev_err(&vsi->back->pdev->dev,
+ "Device is in Safe Mode - not enabling advanced netdev features\n");
+ return ret;
+ }
+
+ /* Multiple features can be changed in one call so keep features in
+ * separate if/else statements to guarantee each feature is checked
+ */
+ if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH))
+ ret = ice_vsi_manage_rss_lut(vsi, true);
+ else if (!(features & NETIF_F_RXHASH) &&
+ netdev->features & NETIF_F_RXHASH)
+ ret = ice_vsi_manage_rss_lut(vsi, false);
+
if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
ret = ice_vsi_manage_vlan_stripping(vsi, true);
else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) &&
(netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
ret = ice_vsi_manage_vlan_stripping(vsi, false);
- else if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
- !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
+
+ if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
+ !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
ret = ice_vsi_manage_vlan_insertion(vsi);
else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) &&
(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
ret = ice_vsi_manage_vlan_insertion(vsi);
+ if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+ !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+ ret = ice_cfg_vlan_pruning(vsi, true, false);
+ else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+ (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+ ret = ice_cfg_vlan_pruning(vsi, false, false);
+
return ret;
}
/**
- * ice_vsi_vlan_setup - Setup vlan offload properties on a VSI
- * @vsi: VSI to setup vlan properties for
+ * ice_vsi_vlan_setup - Setup VLAN offload properties on a VSI
+ * @vsi: VSI to setup VLAN properties for
*/
static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
{
@@ -3838,290 +3485,26 @@
}
/**
- * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up
- * @vsi: the VSI being brought back up
- */
-static int ice_restore_vlan(struct ice_vsi *vsi)
-{
- int err;
- u16 vid;
-
- if (!vsi->netdev)
- return -EINVAL;
-
- err = ice_vsi_vlan_setup(vsi);
- if (err)
- return err;
-
- for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) {
- err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid);
- if (err)
- break;
- }
-
- return err;
-}
-
-/**
- * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
- * @ring: The Tx ring to configure
- * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized
- * @pf_q: queue index in the PF space
- *
- * Configure the Tx descriptor ring in TLAN context.
- */
-static void
-ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
-{
- struct ice_vsi *vsi = ring->vsi;
- struct ice_hw *hw = &vsi->back->hw;
-
- tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S;
-
- tlan_ctx->port_num = vsi->port_info->lport;
-
- /* Transmit Queue Length */
- tlan_ctx->qlen = ring->count;
-
- /* PF number */
- tlan_ctx->pf_num = hw->pf_id;
-
- /* queue belongs to a specific VSI type
- * VF / VM index should be programmed per vmvf_type setting:
- * for vmvf_type = VF, it is VF number between 0-256
- * for vmvf_type = VM, it is VM number between 0-767
- * for PF or EMP this field should be set to zero
- */
- switch (vsi->type) {
- case ICE_VSI_PF:
- tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
- break;
- default:
- return;
- }
-
- /* make sure the context is associated with the right VSI */
- tlan_ctx->src_vsi = vsi->vsi_num;
-
- tlan_ctx->tso_ena = ICE_TX_LEGACY;
- tlan_ctx->tso_qnum = pf_q;
-
- /* Legacy or Advanced Host Interface:
- * 0: Advanced Host Interface
- * 1: Legacy Host Interface
- */
- tlan_ctx->legacy_int = ICE_TX_LEGACY;
-}
-
-/**
- * ice_vsi_cfg_txqs - Configure the VSI for Tx
- * @vsi: the VSI being configured
- *
- * Return 0 on success and a negative value on error
- * Configure the Tx VSI for operation.
- */
-static int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
-{
- struct ice_aqc_add_tx_qgrp *qg_buf;
- struct ice_aqc_add_txqs_perq *txq;
- struct ice_pf *pf = vsi->back;
- enum ice_status status;
- u16 buf_len, i, pf_q;
- int err = 0, tc = 0;
- u8 num_q_grps;
-
- buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
- qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
- if (!qg_buf)
- return -ENOMEM;
-
- if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) {
- err = -EINVAL;
- goto err_cfg_txqs;
- }
- qg_buf->num_txqs = 1;
- num_q_grps = 1;
-
- /* set up and configure the tx queues */
- ice_for_each_txq(vsi, i) {
- struct ice_tlan_ctx tlan_ctx = { 0 };
-
- pf_q = vsi->txq_map[i];
- ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q);
- /* copy context contents into the qg_buf */
- qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
- ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
- ice_tlan_ctx_info);
-
- /* init queue specific tail reg. It is referred as transmit
- * comm scheduler queue doorbell.
- */
- vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
- status = ice_ena_vsi_txq(vsi->port_info, vsi->vsi_num, tc,
- num_q_grps, qg_buf, buf_len, NULL);
- if (status) {
- dev_err(&vsi->back->pdev->dev,
- "Failed to set LAN Tx queue context, error: %d\n",
- status);
- err = -ENODEV;
- goto err_cfg_txqs;
- }
-
- /* Add Tx Queue TEID into the VSI tx ring from the response
- * This will complete configuring and enabling the queue.
- */
- txq = &qg_buf->txqs[0];
- if (pf_q == le16_to_cpu(txq->txq_id))
- vsi->tx_rings[i]->txq_teid =
- le32_to_cpu(txq->q_teid);
- }
-err_cfg_txqs:
- devm_kfree(&pf->pdev->dev, qg_buf);
- return err;
-}
-
-/**
- * ice_setup_rx_ctx - Configure a receive ring context
- * @ring: The Rx ring to configure
- *
- * Configure the Rx descriptor ring in RLAN context.
- */
-static int ice_setup_rx_ctx(struct ice_ring *ring)
-{
- struct ice_vsi *vsi = ring->vsi;
- struct ice_hw *hw = &vsi->back->hw;
- u32 rxdid = ICE_RXDID_FLEX_NIC;
- struct ice_rlan_ctx rlan_ctx;
- u32 regval;
- u16 pf_q;
- int err;
-
- /* what is RX queue number in global space of 2K rx queues */
- pf_q = vsi->rxq_map[ring->q_index];
-
- /* clear the context structure first */
- memset(&rlan_ctx, 0, sizeof(rlan_ctx));
-
- rlan_ctx.base = ring->dma >> ICE_RLAN_BASE_S;
-
- rlan_ctx.qlen = ring->count;
-
- /* Receive Packet Data Buffer Size.
- * The Packet Data Buffer Size is defined in 128 byte units.
- */
- rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S;
-
- /* use 32 byte descriptors */
- rlan_ctx.dsize = 1;
-
- /* Strip the Ethernet CRC bytes before the packet is posted to host
- * memory.
- */
- rlan_ctx.crcstrip = 1;
-
- /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */
- rlan_ctx.l2tsel = 1;
-
- rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT;
- rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT;
- rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT;
-
- /* This controls whether VLAN is stripped from inner headers
- * The VLAN in the inner L2 header is stripped to the receive
- * descriptor if enabled by this flag.
- */
- rlan_ctx.showiv = 0;
-
- /* Max packet size for this queue - must not be set to a larger value
- * than 5 x DBUF
- */
- rlan_ctx.rxmax = min_t(u16, vsi->max_frame,
- ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len);
-
- /* Rx queue threshold in units of 64 */
- rlan_ctx.lrxqthresh = 1;
-
- /* Enable Flexible Descriptors in the queue context which
- * allows this driver to select a specific receive descriptor format
- */
- regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
- regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
- QRXFLXP_CNTXT_RXDID_IDX_M;
-
- /* increasing context priority to pick up profile id;
- * default is 0x01; setting to 0x03 to ensure profile
- * is programming if prev context is of same priority
- */
- regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) &
- QRXFLXP_CNTXT_RXDID_PRIO_M;
-
- wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
-
- /* Absolute queue number out of 2K needs to be passed */
- err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
- if (err) {
- dev_err(&vsi->back->pdev->dev,
- "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
- pf_q, err);
- return -EIO;
- }
-
- /* init queue specific tail register */
- ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
- writel(0, ring->tail);
- ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
-
- return 0;
-}
-
-/**
- * ice_vsi_cfg_rxqs - Configure the VSI for Rx
- * @vsi: the VSI being configured
- *
- * Return 0 on success and a negative value on error
- * Configure the Rx VSI for operation.
- */
-static int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
-{
- int err = 0;
- u16 i;
-
- if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN)
- vsi->max_frame = vsi->netdev->mtu +
- ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
- else
- vsi->max_frame = ICE_RXBUF_2048;
-
- vsi->rx_buf_len = ICE_RXBUF_2048;
- /* set up individual rings */
- for (i = 0; i < vsi->num_rxq && !err; i++)
- err = ice_setup_rx_ctx(vsi->rx_rings[i]);
-
- if (err) {
- dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n");
- return -EIO;
- }
- return err;
-}
-
-/**
* ice_vsi_cfg - Setup the VSI
* @vsi: the VSI being configured
*
* Return 0 on success and negative value on error
*/
-static int ice_vsi_cfg(struct ice_vsi *vsi)
+int ice_vsi_cfg(struct ice_vsi *vsi)
{
int err;
if (vsi->netdev) {
ice_set_rx_mode(vsi->netdev);
- err = ice_restore_vlan(vsi);
+
+ err = ice_vsi_vlan_setup(vsi);
+
if (err)
return err;
}
+ ice_vsi_cfg_dcb_rings(vsi);
- err = ice_vsi_cfg_txqs(vsi);
+ err = ice_vsi_cfg_lan_txqs(vsi);
if (!err)
err = ice_vsi_cfg_rxqs(vsi);
@@ -4129,200 +3512,6 @@
}
/**
- * ice_vsi_stop_tx_rings - Disable Tx rings
- * @vsi: the VSI being configured
- */
-static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi)
-{
- struct ice_pf *pf = vsi->back;
- struct ice_hw *hw = &pf->hw;
- enum ice_status status;
- u32 *q_teids, val;
- u16 *q_ids, i;
- int err = 0;
-
- if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
- return -EINVAL;
-
- q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids),
- GFP_KERNEL);
- if (!q_teids)
- return -ENOMEM;
-
- q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids),
- GFP_KERNEL);
- if (!q_ids) {
- err = -ENOMEM;
- goto err_alloc_q_ids;
- }
-
- /* set up the tx queue list to be disabled */
- ice_for_each_txq(vsi, i) {
- u16 v_idx;
-
- if (!vsi->tx_rings || !vsi->tx_rings[i]) {
- err = -EINVAL;
- goto err_out;
- }
-
- q_ids[i] = vsi->txq_map[i];
- q_teids[i] = vsi->tx_rings[i]->txq_teid;
-
- /* clear cause_ena bit for disabled queues */
- val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx));
- val &= ~QINT_TQCTL_CAUSE_ENA_M;
- wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val);
-
- /* software is expected to wait for 100 ns */
- ndelay(100);
-
- /* trigger a software interrupt for the vector associated to
- * the queue to schedule napi handler
- */
- v_idx = vsi->tx_rings[i]->q_vector->v_idx;
- wr32(hw, GLINT_DYN_CTL(vsi->base_vector + v_idx),
- GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M);
- }
- status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids,
- NULL);
- if (status) {
- dev_err(&pf->pdev->dev,
- "Failed to disable LAN Tx queues, error: %d\n",
- status);
- err = -ENODEV;
- }
-
-err_out:
- devm_kfree(&pf->pdev->dev, q_ids);
-
-err_alloc_q_ids:
- devm_kfree(&pf->pdev->dev, q_teids);
-
- return err;
-}
-
-/**
- * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled
- * @pf: the PF being configured
- * @pf_q: the PF queue
- * @ena: enable or disable state of the queue
- *
- * This routine will wait for the given Rx queue of the PF to reach the
- * enabled or disabled state.
- * Returns -ETIMEDOUT in case of failing to reach the requested state after
- * multiple retries; else will return 0 in case of success.
- */
-static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
-{
- int i;
-
- for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) {
- u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
-
- if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
- break;
-
- usleep_range(10, 20);
- }
- if (i >= ICE_Q_WAIT_RETRY_LIMIT)
- return -ETIMEDOUT;
-
- return 0;
-}
-
-/**
- * ice_vsi_ctrl_rx_rings - Start or stop a VSI's rx rings
- * @vsi: the VSI being configured
- * @ena: start or stop the rx rings
- */
-static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena)
-{
- struct ice_pf *pf = vsi->back;
- struct ice_hw *hw = &pf->hw;
- int i, j, ret = 0;
-
- for (i = 0; i < vsi->num_rxq; i++) {
- int pf_q = vsi->rxq_map[i];
- u32 rx_reg;
-
- for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) {
- rx_reg = rd32(hw, QRX_CTRL(pf_q));
- if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) ==
- ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1))
- break;
- usleep_range(1000, 2000);
- }
-
- /* Skip if the queue is already in the requested state */
- if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
- continue;
-
- /* turn on/off the queue */
- if (ena)
- rx_reg |= QRX_CTRL_QENA_REQ_M;
- else
- rx_reg &= ~QRX_CTRL_QENA_REQ_M;
- wr32(hw, QRX_CTRL(pf_q), rx_reg);
-
- /* wait for the change to finish */
- ret = ice_pf_rxq_wait(pf, pf_q, ena);
- if (ret) {
- dev_err(&pf->pdev->dev,
- "VSI idx %d Rx ring %d %sable timeout\n",
- vsi->idx, pf_q, (ena ? "en" : "dis"));
- break;
- }
- }
-
- return ret;
-}
-
-/**
- * ice_vsi_start_rx_rings - start VSI's rx rings
- * @vsi: the VSI whose rings are to be started
- *
- * Returns 0 on success and a negative value on error
- */
-static int ice_vsi_start_rx_rings(struct ice_vsi *vsi)
-{
- return ice_vsi_ctrl_rx_rings(vsi, true);
-}
-
-/**
- * ice_vsi_stop_rx_rings - stop VSI's rx rings
- * @vsi: the VSI
- *
- * Returns 0 on success and a negative value on error
- */
-static int ice_vsi_stop_rx_rings(struct ice_vsi *vsi)
-{
- return ice_vsi_ctrl_rx_rings(vsi, false);
-}
-
-/**
- * ice_vsi_stop_tx_rx_rings - stop VSI's tx and rx rings
- * @vsi: the VSI
- * Returns 0 on success and a negative value on error
- */
-static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi)
-{
- int err_tx, err_rx;
-
- err_tx = ice_vsi_stop_tx_rings(vsi);
- if (err_tx)
- dev_dbg(&vsi->back->pdev->dev, "Failed to disable Tx rings\n");
-
- err_rx = ice_vsi_stop_rx_rings(vsi);
- if (err_rx)
- dev_dbg(&vsi->back->pdev->dev, "Failed to disable Rx rings\n");
-
- if (err_tx || err_rx)
- return -EIO;
-
- return 0;
-}
-
-/**
* ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI
* @vsi: the VSI being configured
*/
@@ -4333,8 +3522,12 @@
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_enable(&vsi->q_vectors[q_idx]->napi);
+ ice_for_each_q_vector(vsi, q_idx) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_enable(&q_vector->napi);
+ }
}
/**
@@ -4348,10 +3541,7 @@
struct ice_pf *pf = vsi->back;
int err;
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- ice_vsi_cfg_msix(vsi);
- else
- return -ENOTSUPP;
+ ice_vsi_cfg_msix(vsi);
/* Enable only Rx rings, Tx rings were enabled by the FW when the
* Tx queue group list was configured and the context bits were
@@ -4375,7 +3565,7 @@
ice_service_task_schedule(pf);
- return err;
+ return 0;
}
/**
@@ -4402,8 +3592,8 @@
* This function fetches stats from the ring considering the atomic operations
* that needs to be performed to read u64 values in 32 bit machine.
*/
-static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts,
- u64 *bytes)
+static void
+ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes)
{
unsigned int start;
*pkts = 0;
@@ -4419,122 +3609,6 @@
}
/**
- * ice_stat_update40 - read 40 bit stat from the chip and update stat values
- * @hw: ptr to the hardware info
- * @hireg: high 32 bit HW register to read from
- * @loreg: low 32 bit HW register to read from
- * @prev_stat_loaded: bool to specify if previous stats are loaded
- * @prev_stat: ptr to previous loaded stat value
- * @cur_stat: ptr to current stat value
- */
-static void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
- bool prev_stat_loaded, u64 *prev_stat,
- u64 *cur_stat)
-{
- u64 new_data;
-
- new_data = rd32(hw, loreg);
- new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32;
-
- /* device stats are not reset at PFR, they likely will not be zeroed
- * when the driver starts. So save the first values read and use them as
- * offsets to be subtracted from the raw values in order to report stats
- * that count from zero.
- */
- if (!prev_stat_loaded)
- *prev_stat = new_data;
- if (likely(new_data >= *prev_stat))
- *cur_stat = new_data - *prev_stat;
- else
- /* to manage the potential roll-over */
- *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat;
- *cur_stat &= 0xFFFFFFFFFFULL;
-}
-
-/**
- * ice_stat_update32 - read 32 bit stat from the chip and update stat values
- * @hw: ptr to the hardware info
- * @reg: HW register to read from
- * @prev_stat_loaded: bool to specify if previous stats are loaded
- * @prev_stat: ptr to previous loaded stat value
- * @cur_stat: ptr to current stat value
- */
-static void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
- u64 *prev_stat, u64 *cur_stat)
-{
- u32 new_data;
-
- new_data = rd32(hw, reg);
-
- /* device stats are not reset at PFR, they likely will not be zeroed
- * when the driver starts. So save the first values read and use them as
- * offsets to be subtracted from the raw values in order to report stats
- * that count from zero.
- */
- if (!prev_stat_loaded)
- *prev_stat = new_data;
- if (likely(new_data >= *prev_stat))
- *cur_stat = new_data - *prev_stat;
- else
- /* to manage the potential roll-over */
- *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat;
-}
-
-/**
- * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
- * @vsi: the VSI to be updated
- */
-static void ice_update_eth_stats(struct ice_vsi *vsi)
-{
- struct ice_eth_stats *prev_es, *cur_es;
- struct ice_hw *hw = &vsi->back->hw;
- u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */
-
- prev_es = &vsi->eth_stats_prev;
- cur_es = &vsi->eth_stats;
-
- ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->rx_bytes,
- &cur_es->rx_bytes);
-
- ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->rx_unicast,
- &cur_es->rx_unicast);
-
- ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->rx_multicast,
- &cur_es->rx_multicast);
-
- ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->rx_broadcast,
- &cur_es->rx_broadcast);
-
- ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded,
- &prev_es->rx_discards, &cur_es->rx_discards);
-
- ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->tx_bytes,
- &cur_es->tx_bytes);
-
- ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->tx_unicast,
- &cur_es->tx_unicast);
-
- ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->tx_multicast,
- &cur_es->tx_multicast);
-
- ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num),
- vsi->stat_offsets_loaded, &prev_es->tx_broadcast,
- &cur_es->tx_broadcast);
-
- ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded,
- &prev_es->tx_errors, &cur_es->tx_errors);
-
- vsi->stat_offsets_loaded = true;
-}
-
-/**
* ice_update_vsi_ring_stats - Update VSI stats counters
* @vsi: the VSI to be updated
*/
@@ -4588,7 +3662,7 @@
* ice_update_vsi_stats - Update VSI stats counters
* @vsi: the VSI to be updated
*/
-static void ice_update_vsi_stats(struct ice_vsi *vsi)
+void ice_update_vsi_stats(struct ice_vsi *vsi)
{
struct rtnl_link_stats64 *cur_ns = &vsi->net_stats;
struct ice_eth_stats *cur_es = &vsi->eth_stats;
@@ -4615,6 +3689,8 @@
cur_ns->rx_errors = pf->stats.crc_errors +
pf->stats.illegal_bytes;
cur_ns->rx_length_errors = pf->stats.rx_len_errors;
+ /* record drops from the port level */
+ cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
}
}
@@ -4622,147 +3698,139 @@
* ice_update_pf_stats - Update PF port stats counters
* @pf: PF whose stats needs to be updated
*/
-static void ice_update_pf_stats(struct ice_pf *pf)
+void ice_update_pf_stats(struct ice_pf *pf)
{
struct ice_hw_port_stats *prev_ps, *cur_ps;
struct ice_hw *hw = &pf->hw;
- u8 pf_id;
+ u8 port;
+ port = hw->port_info->lport;
prev_ps = &pf->stats_prev;
cur_ps = &pf->stats;
- pf_id = hw->pf_id;
- ice_stat_update40(hw, GLPRT_GORCH(pf_id), GLPRT_GORCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.rx_bytes,
+ ice_stat_update40(hw, GLPRT_GORCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.rx_bytes,
&cur_ps->eth.rx_bytes);
- ice_stat_update40(hw, GLPRT_UPRCH(pf_id), GLPRT_UPRCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.rx_unicast,
+ ice_stat_update40(hw, GLPRT_UPRCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.rx_unicast,
&cur_ps->eth.rx_unicast);
- ice_stat_update40(hw, GLPRT_MPRCH(pf_id), GLPRT_MPRCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.rx_multicast,
+ ice_stat_update40(hw, GLPRT_MPRCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.rx_multicast,
&cur_ps->eth.rx_multicast);
- ice_stat_update40(hw, GLPRT_BPRCH(pf_id), GLPRT_BPRCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.rx_broadcast,
+ ice_stat_update40(hw, GLPRT_BPRCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.rx_broadcast,
&cur_ps->eth.rx_broadcast);
- ice_stat_update40(hw, GLPRT_GOTCH(pf_id), GLPRT_GOTCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.tx_bytes,
+ ice_stat_update32(hw, PRTRPB_RDPC, pf->stat_prev_loaded,
+ &prev_ps->eth.rx_discards,
+ &cur_ps->eth.rx_discards);
+
+ ice_stat_update40(hw, GLPRT_GOTCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.tx_bytes,
&cur_ps->eth.tx_bytes);
- ice_stat_update40(hw, GLPRT_UPTCH(pf_id), GLPRT_UPTCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.tx_unicast,
+ ice_stat_update40(hw, GLPRT_UPTCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.tx_unicast,
&cur_ps->eth.tx_unicast);
- ice_stat_update40(hw, GLPRT_MPTCH(pf_id), GLPRT_MPTCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.tx_multicast,
+ ice_stat_update40(hw, GLPRT_MPTCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.tx_multicast,
&cur_ps->eth.tx_multicast);
- ice_stat_update40(hw, GLPRT_BPTCH(pf_id), GLPRT_BPTCL(pf_id),
- pf->stat_prev_loaded, &prev_ps->eth.tx_broadcast,
+ ice_stat_update40(hw, GLPRT_BPTCL(port), pf->stat_prev_loaded,
+ &prev_ps->eth.tx_broadcast,
&cur_ps->eth.tx_broadcast);
- ice_stat_update32(hw, GLPRT_TDOLD(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_TDOLD(port), pf->stat_prev_loaded,
&prev_ps->tx_dropped_link_down,
&cur_ps->tx_dropped_link_down);
- ice_stat_update40(hw, GLPRT_PRC64H(pf_id), GLPRT_PRC64L(pf_id),
- pf->stat_prev_loaded, &prev_ps->rx_size_64,
- &cur_ps->rx_size_64);
+ ice_stat_update40(hw, GLPRT_PRC64L(port), pf->stat_prev_loaded,
+ &prev_ps->rx_size_64, &cur_ps->rx_size_64);
- ice_stat_update40(hw, GLPRT_PRC127H(pf_id), GLPRT_PRC127L(pf_id),
- pf->stat_prev_loaded, &prev_ps->rx_size_127,
- &cur_ps->rx_size_127);
+ ice_stat_update40(hw, GLPRT_PRC127L(port), pf->stat_prev_loaded,
+ &prev_ps->rx_size_127, &cur_ps->rx_size_127);
- ice_stat_update40(hw, GLPRT_PRC255H(pf_id), GLPRT_PRC255L(pf_id),
- pf->stat_prev_loaded, &prev_ps->rx_size_255,
- &cur_ps->rx_size_255);
+ ice_stat_update40(hw, GLPRT_PRC255L(port), pf->stat_prev_loaded,
+ &prev_ps->rx_size_255, &cur_ps->rx_size_255);
- ice_stat_update40(hw, GLPRT_PRC511H(pf_id), GLPRT_PRC511L(pf_id),
- pf->stat_prev_loaded, &prev_ps->rx_size_511,
- &cur_ps->rx_size_511);
+ ice_stat_update40(hw, GLPRT_PRC511L(port), pf->stat_prev_loaded,
+ &prev_ps->rx_size_511, &cur_ps->rx_size_511);
- ice_stat_update40(hw, GLPRT_PRC1023H(pf_id),
- GLPRT_PRC1023L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PRC1023L(port), pf->stat_prev_loaded,
&prev_ps->rx_size_1023, &cur_ps->rx_size_1023);
- ice_stat_update40(hw, GLPRT_PRC1522H(pf_id),
- GLPRT_PRC1522L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PRC1522L(port), pf->stat_prev_loaded,
&prev_ps->rx_size_1522, &cur_ps->rx_size_1522);
- ice_stat_update40(hw, GLPRT_PRC9522H(pf_id),
- GLPRT_PRC9522L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PRC9522L(port), pf->stat_prev_loaded,
&prev_ps->rx_size_big, &cur_ps->rx_size_big);
- ice_stat_update40(hw, GLPRT_PTC64H(pf_id), GLPRT_PTC64L(pf_id),
- pf->stat_prev_loaded, &prev_ps->tx_size_64,
- &cur_ps->tx_size_64);
+ ice_stat_update40(hw, GLPRT_PTC64L(port), pf->stat_prev_loaded,
+ &prev_ps->tx_size_64, &cur_ps->tx_size_64);
- ice_stat_update40(hw, GLPRT_PTC127H(pf_id), GLPRT_PTC127L(pf_id),
- pf->stat_prev_loaded, &prev_ps->tx_size_127,
- &cur_ps->tx_size_127);
+ ice_stat_update40(hw, GLPRT_PTC127L(port), pf->stat_prev_loaded,
+ &prev_ps->tx_size_127, &cur_ps->tx_size_127);
- ice_stat_update40(hw, GLPRT_PTC255H(pf_id), GLPRT_PTC255L(pf_id),
- pf->stat_prev_loaded, &prev_ps->tx_size_255,
- &cur_ps->tx_size_255);
+ ice_stat_update40(hw, GLPRT_PTC255L(port), pf->stat_prev_loaded,
+ &prev_ps->tx_size_255, &cur_ps->tx_size_255);
- ice_stat_update40(hw, GLPRT_PTC511H(pf_id), GLPRT_PTC511L(pf_id),
- pf->stat_prev_loaded, &prev_ps->tx_size_511,
- &cur_ps->tx_size_511);
+ ice_stat_update40(hw, GLPRT_PTC511L(port), pf->stat_prev_loaded,
+ &prev_ps->tx_size_511, &cur_ps->tx_size_511);
- ice_stat_update40(hw, GLPRT_PTC1023H(pf_id),
- GLPRT_PTC1023L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PTC1023L(port), pf->stat_prev_loaded,
&prev_ps->tx_size_1023, &cur_ps->tx_size_1023);
- ice_stat_update40(hw, GLPRT_PTC1522H(pf_id),
- GLPRT_PTC1522L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PTC1522L(port), pf->stat_prev_loaded,
&prev_ps->tx_size_1522, &cur_ps->tx_size_1522);
- ice_stat_update40(hw, GLPRT_PTC9522H(pf_id),
- GLPRT_PTC9522L(pf_id), pf->stat_prev_loaded,
+ ice_stat_update40(hw, GLPRT_PTC9522L(port), pf->stat_prev_loaded,
&prev_ps->tx_size_big, &cur_ps->tx_size_big);
- ice_stat_update32(hw, GLPRT_LXONRXC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_LXONRXC(port), pf->stat_prev_loaded,
&prev_ps->link_xon_rx, &cur_ps->link_xon_rx);
- ice_stat_update32(hw, GLPRT_LXOFFRXC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_LXOFFRXC(port), pf->stat_prev_loaded,
&prev_ps->link_xoff_rx, &cur_ps->link_xoff_rx);
- ice_stat_update32(hw, GLPRT_LXONTXC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_LXONTXC(port), pf->stat_prev_loaded,
&prev_ps->link_xon_tx, &cur_ps->link_xon_tx);
- ice_stat_update32(hw, GLPRT_LXOFFTXC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_LXOFFTXC(port), pf->stat_prev_loaded,
&prev_ps->link_xoff_tx, &cur_ps->link_xoff_tx);
- ice_stat_update32(hw, GLPRT_CRCERRS(pf_id), pf->stat_prev_loaded,
+ ice_update_dcb_stats(pf);
+
+ ice_stat_update32(hw, GLPRT_CRCERRS(port), pf->stat_prev_loaded,
&prev_ps->crc_errors, &cur_ps->crc_errors);
- ice_stat_update32(hw, GLPRT_ILLERRC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_ILLERRC(port), pf->stat_prev_loaded,
&prev_ps->illegal_bytes, &cur_ps->illegal_bytes);
- ice_stat_update32(hw, GLPRT_MLFC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_MLFC(port), pf->stat_prev_loaded,
&prev_ps->mac_local_faults,
&cur_ps->mac_local_faults);
- ice_stat_update32(hw, GLPRT_MRFC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_MRFC(port), pf->stat_prev_loaded,
&prev_ps->mac_remote_faults,
&cur_ps->mac_remote_faults);
- ice_stat_update32(hw, GLPRT_RLEC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
&prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
- ice_stat_update32(hw, GLPRT_RUC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
&prev_ps->rx_undersize, &cur_ps->rx_undersize);
- ice_stat_update32(hw, GLPRT_RFC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_RFC(port), pf->stat_prev_loaded,
&prev_ps->rx_fragments, &cur_ps->rx_fragments);
- ice_stat_update32(hw, GLPRT_ROC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_ROC(port), pf->stat_prev_loaded,
&prev_ps->rx_oversize, &cur_ps->rx_oversize);
- ice_stat_update32(hw, GLPRT_RJC(pf_id), pf->stat_prev_loaded,
+ ice_stat_update32(hw, GLPRT_RJC(port), pf->stat_prev_loaded,
&prev_ps->rx_jabber, &cur_ps->rx_jabber);
pf->stat_prev_loaded = true;
@@ -4782,12 +3850,16 @@
vsi_stats = &vsi->net_stats;
- if (test_bit(__ICE_DOWN, vsi->state) || !vsi->num_txq || !vsi->num_rxq)
+ if (!vsi->num_txq || !vsi->num_rxq)
return;
+
/* netdev packet/byte stats come from ring counter. These are obtained
* by summing up ring counters (done by ice_update_vsi_ring_stats).
+ * But, only call the update routine and read the registers if VSI is
+ * not down.
*/
- ice_update_vsi_ring_stats(vsi);
+ if (!test_bit(__ICE_DOWN, vsi->state))
+ ice_update_vsi_ring_stats(vsi);
stats->tx_packets = vsi_stats->tx_packets;
stats->tx_bytes = vsi_stats->tx_bytes;
stats->rx_packets = vsi_stats->rx_packets;
@@ -4817,8 +3889,12 @@
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_disable(&vsi->q_vectors[q_idx]->napi);
+ ice_for_each_q_vector(vsi, q_idx) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_disable(&q_vector->napi);
+ }
}
/**
@@ -4827,7 +3903,7 @@
*/
int ice_down(struct ice_vsi *vsi)
{
- int i, err;
+ int i, tx_err, rx_err, link_err = 0;
/* Caller of this function is expected to set the
* vsi->state __ICE_DOWN bit
@@ -4838,19 +3914,43 @@
}
ice_vsi_dis_irq(vsi);
- err = ice_vsi_stop_tx_rx_rings(vsi);
+
+ tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
+ if (tx_err)
+ netdev_err(vsi->netdev,
+ "Failed stop Tx rings, VSI %d error %d\n",
+ vsi->vsi_num, tx_err);
+
+ rx_err = ice_vsi_stop_rx_rings(vsi);
+ if (rx_err)
+ netdev_err(vsi->netdev,
+ "Failed stop Rx rings, VSI %d error %d\n",
+ vsi->vsi_num, rx_err);
+
ice_napi_disable_all(vsi);
+ if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
+ link_err = ice_force_phys_link_state(vsi, false);
+ if (link_err)
+ netdev_err(vsi->netdev,
+ "Failed to set physical link down, VSI %d error %d\n",
+ vsi->vsi_num, link_err);
+ }
+
ice_for_each_txq(vsi, i)
ice_clean_tx_ring(vsi->tx_rings[i]);
ice_for_each_rxq(vsi, i)
ice_clean_rx_ring(vsi->rx_rings[i]);
- if (err)
- netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n",
+ if (tx_err || rx_err || link_err) {
+ netdev_err(vsi->netdev,
+ "Failed to close VSI 0x%04X on switch 0x%04X\n",
vsi->vsi_num, vsi->vsw->sw_id);
- return err;
+ return -EIO;
+ }
+
+ return 0;
}
/**
@@ -4859,7 +3959,7 @@
*
* Return 0 on success, negative on failure
*/
-static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
+int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
{
int i, err = 0;
@@ -4870,6 +3970,7 @@
}
ice_for_each_txq(vsi, i) {
+ vsi->tx_rings[i]->netdev = vsi->netdev;
err = ice_setup_tx_ring(vsi->tx_rings[i]);
if (err)
break;
@@ -4884,7 +3985,7 @@
*
* Return 0 on success, negative on failure
*/
-static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
+int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
{
int i, err = 0;
@@ -4895,6 +3996,7 @@
}
ice_for_each_rxq(vsi, i) {
+ vsi->rx_rings[i]->netdev = vsi->netdev;
err = ice_setup_rx_ring(vsi->rx_rings[i]);
if (err)
break;
@@ -4904,56 +4006,6 @@
}
/**
- * ice_vsi_req_irq - Request IRQ from the OS
- * @vsi: The VSI IRQ is being requested for
- * @basename: name for the vector
- *
- * Return 0 on success and a negative value on error
- */
-static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename)
-{
- struct ice_pf *pf = vsi->back;
- int err = -EINVAL;
-
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- err = ice_vsi_req_irq_msix(vsi, basename);
-
- return err;
-}
-
-/**
- * ice_vsi_free_tx_rings - Free Tx resources for VSI queues
- * @vsi: the VSI having resources freed
- */
-static void ice_vsi_free_tx_rings(struct ice_vsi *vsi)
-{
- int i;
-
- if (!vsi->tx_rings)
- return;
-
- ice_for_each_txq(vsi, i)
- if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
- ice_free_tx_ring(vsi->tx_rings[i]);
-}
-
-/**
- * ice_vsi_free_rx_rings - Free Rx resources for VSI queues
- * @vsi: the VSI having resources freed
- */
-static void ice_vsi_free_rx_rings(struct ice_vsi *vsi)
-{
- int i;
-
- if (!vsi->rx_rings)
- return;
-
- ice_for_each_rxq(vsi, i)
- if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
- ice_free_rx_ring(vsi->rx_rings[i]);
-}
-
-/**
* ice_vsi_open - Called when a network interface is made active
* @vsi: the VSI to open
*
@@ -4982,7 +4034,7 @@
snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
- err = ice_vsi_req_irq(vsi, int_name);
+ err = ice_vsi_req_irq_msix(vsi, int_name);
if (err)
goto err_setup_rx;
@@ -5014,146 +4066,165 @@
}
/**
- * ice_vsi_close - Shut down a VSI
- * @vsi: the VSI being shut down
+ * ice_vsi_release_all - Delete all VSIs
+ * @pf: PF from which all VSIs are being removed
*/
-static void ice_vsi_close(struct ice_vsi *vsi)
+static void ice_vsi_release_all(struct ice_pf *pf)
{
- if (!test_and_set_bit(__ICE_DOWN, vsi->state))
- ice_down(vsi);
+ int err, i;
- ice_vsi_free_irq(vsi);
- ice_vsi_free_tx_rings(vsi);
- ice_vsi_free_rx_rings(vsi);
-}
-
-/**
- * ice_rss_clean - Delete RSS related VSI structures that hold user inputs
- * @vsi: the VSI being removed
- */
-static void ice_rss_clean(struct ice_vsi *vsi)
-{
- struct ice_pf *pf;
-
- pf = vsi->back;
-
- if (vsi->rss_hkey_user)
- devm_kfree(&pf->pdev->dev, vsi->rss_hkey_user);
- if (vsi->rss_lut_user)
- devm_kfree(&pf->pdev->dev, vsi->rss_lut_user);
-}
-
-/**
- * ice_vsi_release - Delete a VSI and free its resources
- * @vsi: the VSI being removed
- *
- * Returns 0 on success or < 0 on error
- */
-static int ice_vsi_release(struct ice_vsi *vsi)
-{
- struct ice_pf *pf;
-
- if (!vsi->back)
- return -ENODEV;
- pf = vsi->back;
-
- if (vsi->netdev) {
- unregister_netdev(vsi->netdev);
- free_netdev(vsi->netdev);
- vsi->netdev = NULL;
- }
-
- if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
- ice_rss_clean(vsi);
-
- /* Disable VSI and free resources */
- ice_vsi_dis_irq(vsi);
- ice_vsi_close(vsi);
-
- /* reclaim interrupt vectors back to PF */
- ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx);
- pf->num_avail_msix += vsi->num_q_vectors;
-
- ice_remove_vsi_fltr(&pf->hw, vsi->vsi_num);
- ice_vsi_delete(vsi);
- ice_vsi_free_q_vectors(vsi);
- ice_vsi_clear_rings(vsi);
-
- ice_vsi_put_qs(vsi);
- pf->q_left_tx += vsi->alloc_txq;
- pf->q_left_rx += vsi->alloc_rxq;
-
- ice_vsi_clear(vsi);
-
- return 0;
-}
-
-/**
- * ice_dis_vsi - pause a VSI
- * @vsi: the VSI being paused
- */
-static void ice_dis_vsi(struct ice_vsi *vsi)
-{
- if (test_bit(__ICE_DOWN, vsi->state))
+ if (!pf->vsi)
return;
- set_bit(__ICE_NEEDS_RESTART, vsi->state);
+ ice_for_each_vsi(pf, i) {
+ if (!pf->vsi[i])
+ continue;
- if (vsi->netdev && netif_running(vsi->netdev) &&
- vsi->type == ICE_VSI_PF)
- vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
-
- ice_vsi_close(vsi);
+ err = ice_vsi_release(pf->vsi[i]);
+ if (err)
+ dev_dbg(&pf->pdev->dev,
+ "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n",
+ i, err, pf->vsi[i]->vsi_num);
+ }
}
/**
* ice_ena_vsi - resume a VSI
* @vsi: the VSI being resume
+ * @locked: is the rtnl_lock already held
*/
-static void ice_ena_vsi(struct ice_vsi *vsi)
+static int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
{
- if (!test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state))
- return;
+ int err = 0;
- if (vsi->netdev && netif_running(vsi->netdev))
- vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
- else if (ice_vsi_open(vsi))
- /* this clears the DOWN bit */
- dev_dbg(&vsi->back->pdev->dev, "Failed open VSI 0x%04X on switch 0x%04X\n",
- vsi->vsi_num, vsi->vsw->sw_id);
-}
+ if (!test_bit(__ICE_NEEDS_RESTART, vsi->state))
+ return 0;
-/**
- * ice_pf_dis_all_vsi - Pause all VSIs on a PF
- * @pf: the PF
- */
-static void ice_pf_dis_all_vsi(struct ice_pf *pf)
-{
- int v;
+ clear_bit(__ICE_NEEDS_RESTART, vsi->state);
- ice_for_each_vsi(pf, v)
- if (pf->vsi[v])
- ice_dis_vsi(pf->vsi[v]);
+ if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+ if (netif_running(vsi->netdev)) {
+ if (!locked)
+ rtnl_lock();
+
+ err = ice_open(vsi->netdev);
+
+ if (!locked)
+ rtnl_unlock();
+ }
+ }
+
+ return err;
}
/**
* ice_pf_ena_all_vsi - Resume all VSIs on a PF
* @pf: the PF
+ * @locked: is the rtnl_lock already held
*/
-static void ice_pf_ena_all_vsi(struct ice_pf *pf)
+#ifdef CONFIG_DCB
+int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
{
int v;
ice_for_each_vsi(pf, v)
if (pf->vsi[v])
- ice_ena_vsi(pf->vsi[v]);
+ if (ice_ena_vsi(pf->vsi[v], locked))
+ return -EIO;
+
+ return 0;
+}
+#endif /* CONFIG_DCB */
+
+/**
+ * ice_vsi_rebuild_by_type - Rebuild VSI of a given type
+ * @pf: pointer to the PF instance
+ * @type: VSI type to rebuild
+ *
+ * Iterates through the pf->vsi array and rebuilds VSIs of the requested type
+ */
+static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
+{
+ enum ice_status status;
+ int i, err;
+
+ ice_for_each_vsi(pf, i) {
+ struct ice_vsi *vsi = pf->vsi[i];
+
+ if (!vsi || vsi->type != type)
+ continue;
+
+ /* rebuild the VSI */
+ err = ice_vsi_rebuild(vsi);
+ if (err) {
+ dev_err(&pf->pdev->dev,
+ "rebuild VSI failed, err %d, VSI index %d, type %d\n",
+ err, vsi->idx, type);
+ return err;
+ }
+
+ /* replay filters for the VSI */
+ status = ice_replay_vsi(&pf->hw, vsi->idx);
+ if (status) {
+ dev_err(&pf->pdev->dev,
+ "replay VSI failed, status %d, VSI index %d, type %d\n",
+ status, vsi->idx, type);
+ return -EIO;
+ }
+
+ /* Re-map HW VSI number, using VSI handle that has been
+ * previously validated in ice_replay_vsi() call above
+ */
+ vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx);
+
+ /* enable the VSI */
+ err = ice_ena_vsi(vsi, false);
+ if (err) {
+ dev_err(&pf->pdev->dev,
+ "enable VSI failed, err %d, VSI index %d, type %d\n",
+ err, vsi->idx, type);
+ return err;
+ }
+
+ dev_info(&pf->pdev->dev, "VSI rebuilt. VSI index %d, type %d\n",
+ vsi->idx, type);
+ }
+
+ return 0;
+}
+
+/**
+ * ice_update_pf_netdev_link - Update PF netdev link status
+ * @pf: pointer to the PF instance
+ */
+static void ice_update_pf_netdev_link(struct ice_pf *pf)
+{
+ bool link_up;
+ int i;
+
+ ice_for_each_vsi(pf, i) {
+ struct ice_vsi *vsi = pf->vsi[i];
+
+ if (!vsi || vsi->type != ICE_VSI_PF)
+ return;
+
+ ice_get_link_status(pf->vsi[i]->port_info, &link_up);
+ if (link_up) {
+ netif_carrier_on(pf->vsi[i]->netdev);
+ netif_tx_wake_all_queues(pf->vsi[i]->netdev);
+ } else {
+ netif_carrier_off(pf->vsi[i]->netdev);
+ netif_tx_stop_all_queues(pf->vsi[i]->netdev);
+ }
+ }
}
/**
* ice_rebuild - rebuild after reset
- * @pf: pf to rebuild
+ * @pf: PF to rebuild
+ * @reset_type: type of reset
*/
-static void ice_rebuild(struct ice_pf *pf)
+static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
{
struct device *dev = &pf->pdev->dev;
struct ice_hw *hw = &pf->hw;
@@ -5163,18 +4234,28 @@
if (test_bit(__ICE_DOWN, pf->state))
goto clear_recovery;
- dev_dbg(dev, "rebuilding pf\n");
+ dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type);
ret = ice_init_all_ctrlq(hw);
if (ret) {
dev_err(dev, "control queues init failed %d\n", ret);
- goto fail_reset;
+ goto err_init_ctrlq;
+ }
+
+ /* if DDP was previously loaded successfully */
+ if (!ice_is_safe_mode(pf)) {
+ /* reload the SW DB of filter tables */
+ if (reset_type == ICE_RESET_PFR)
+ ice_fill_blk_tbls(hw);
+ else
+ /* Reload DDP Package after CORER/GLOBR reset */
+ ice_load_pkg(NULL, pf);
}
ret = ice_clear_pf_cfg(hw);
if (ret) {
dev_err(dev, "clear PF configuration failed %d\n", ret);
- goto fail_reset;
+ goto err_init_ctrlq;
}
ice_clear_pxe_mode(hw);
@@ -5182,35 +4263,69 @@
ret = ice_get_caps(hw);
if (ret) {
dev_err(dev, "ice_get_caps failed %d\n", ret);
- goto fail_reset;
+ goto err_init_ctrlq;
}
- /* basic nic switch setup */
- err = ice_setup_pf_sw(pf);
- if (err) {
- dev_err(dev, "ice_setup_pf_sw failed\n");
- goto fail_reset;
- }
+ err = ice_sched_init_port(hw->port_info);
+ if (err)
+ goto err_sched_init_port;
+
+ err = ice_update_link_info(hw->port_info);
+ if (err)
+ dev_err(&pf->pdev->dev, "Get link status error %d\n", err);
/* start misc vector */
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
- err = ice_req_irq_msix_misc(pf);
+ err = ice_req_irq_msix_misc(pf);
+ if (err) {
+ dev_err(dev, "misc vector setup failed: %d\n", err);
+ goto err_sched_init_port;
+ }
+
+ if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
+ ice_dcb_rebuild(pf);
+
+ /* rebuild PF VSI */
+ err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF);
+ if (err) {
+ dev_err(dev, "PF VSI rebuild failed: %d\n", err);
+ goto err_vsi_rebuild;
+ }
+
+ if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
+ err = ice_vsi_rebuild_by_type(pf, ICE_VSI_VF);
if (err) {
- dev_err(dev, "misc vector setup failed: %d\n", err);
- goto fail_reset;
+ dev_err(dev, "VF VSI rebuild failed: %d\n", err);
+ goto err_vsi_rebuild;
}
}
- /* restart the VSIs that were rebuilt and running before the reset */
- ice_pf_ena_all_vsi(pf);
+ ice_update_pf_netdev_link(pf);
+ /* tell the firmware we are up */
+ ret = ice_send_version(pf);
+ if (ret) {
+ dev_err(dev,
+ "Rebuild failed due to error sending driver version: %d\n",
+ ret);
+ goto err_vsi_rebuild;
+ }
+
+ ice_replay_post(hw);
+
+ /* if we get here, reset flow is successful */
+ clear_bit(__ICE_RESET_FAILED, pf->state);
return;
-fail_reset:
+err_vsi_rebuild:
+err_sched_init_port:
+ ice_sched_cleanup_all(hw);
+err_init_ctrlq:
ice_shutdown_all_ctrlq(hw);
set_bit(__ICE_RESET_FAILED, pf->state);
clear_recovery:
- set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state);
+ /* set this bit in PF state to control service task scheduling */
+ set_bit(__ICE_NEEDS_RESTART, pf->state);
+ dev_err(dev, "Rebuild failed, unload and reload driver\n");
}
/**
@@ -5228,22 +4343,22 @@
u8 count = 0;
if (new_mtu == netdev->mtu) {
- netdev_warn(netdev, "mtu is already %u\n", netdev->mtu);
+ netdev_warn(netdev, "MTU is already %u\n", netdev->mtu);
return 0;
}
if (new_mtu < netdev->min_mtu) {
- netdev_err(netdev, "new mtu invalid. min_mtu is %d\n",
+ netdev_err(netdev, "new MTU invalid. min_mtu is %d\n",
netdev->min_mtu);
return -EINVAL;
} else if (new_mtu > netdev->max_mtu) {
- netdev_err(netdev, "new mtu invalid. max_mtu is %d\n",
+ netdev_err(netdev, "new MTU invalid. max_mtu is %d\n",
netdev->min_mtu);
return -EINVAL;
}
/* if a reset is in progress, wait for some time for it to complete */
do {
- if (ice_is_reset_recovery_pending(pf->state)) {
+ if (ice_is_reset_in_progress(pf->state)) {
count++;
usleep_range(1000, 2000);
} else {
@@ -5253,7 +4368,7 @@
} while (count < 100);
if (count == 100) {
- netdev_err(netdev, "can't change mtu. Device is busy\n");
+ netdev_err(netdev, "can't change MTU. Device is busy\n");
return -EBUSY;
}
@@ -5265,18 +4380,18 @@
err = ice_down(vsi);
if (err) {
- netdev_err(netdev, "change mtu if_up err %d\n", err);
+ netdev_err(netdev, "change MTU if_up err %d\n", err);
return err;
}
err = ice_up(vsi);
if (err) {
- netdev_err(netdev, "change mtu if_up err %d\n", err);
+ netdev_err(netdev, "change MTU if_up err %d\n", err);
return err;
}
}
- netdev_dbg(netdev, "changed mtu to %d\n", new_mtu);
+ netdev_info(netdev, "changed MTU to %d\n", new_mtu);
return 0;
}
@@ -5299,7 +4414,7 @@
struct ice_aqc_get_set_rss_keys *buf =
(struct ice_aqc_get_set_rss_keys *)seed;
- status = ice_aq_set_rss_key(hw, vsi->vsi_num, buf);
+ status = ice_aq_set_rss_key(hw, vsi->idx, buf);
if (status) {
dev_err(&pf->pdev->dev,
@@ -5310,8 +4425,8 @@
}
if (lut) {
- status = ice_aq_set_rss_lut(hw, vsi->vsi_num,
- vsi->rss_lut_type, lut, lut_size);
+ status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
+ lut, lut_size);
if (status) {
dev_err(&pf->pdev->dev,
"Cannot set RSS lut, err %d aq_err %d\n",
@@ -5342,7 +4457,7 @@
struct ice_aqc_get_set_rss_keys *buf =
(struct ice_aqc_get_set_rss_keys *)seed;
- status = ice_aq_get_rss_key(hw, vsi->vsi_num, buf);
+ status = ice_aq_get_rss_key(hw, vsi->idx, buf);
if (status) {
dev_err(&pf->pdev->dev,
"Cannot get RSS key, err %d aq_err %d\n",
@@ -5352,8 +4467,8 @@
}
if (lut) {
- status = ice_aq_get_rss_lut(hw, vsi->vsi_num,
- vsi->rss_lut_type, lut, lut_size);
+ status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
+ lut, lut_size);
if (status) {
dev_err(&pf->pdev->dev,
"Cannot get RSS lut, err %d aq_err %d\n",
@@ -5366,27 +4481,292 @@
}
/**
+ * ice_bridge_getlink - Get the hardware bridge mode
+ * @skb: skb buff
+ * @pid: process ID
+ * @seq: RTNL message seq
+ * @dev: the netdev being configured
+ * @filter_mask: filter mask passed in
+ * @nlflags: netlink flags passed in
+ *
+ * Return the bridge mode (VEB/VEPA)
+ */
+static int
+ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+ struct net_device *dev, u32 filter_mask, int nlflags)
+{
+ struct ice_netdev_priv *np = netdev_priv(dev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ u16 bmode;
+
+ bmode = pf->first_sw->bridge_mode;
+
+ return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bmode, 0, 0, nlflags,
+ filter_mask, NULL);
+}
+
+/**
+ * ice_vsi_update_bridge_mode - Update VSI for switching bridge mode (VEB/VEPA)
+ * @vsi: Pointer to VSI structure
+ * @bmode: Hardware bridge mode (VEB/VEPA)
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_aqc_vsi_props *vsi_props;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx *ctxt;
+ enum ice_status status;
+ int ret = 0;
+
+ vsi_props = &vsi->info;
+
+ ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ ctxt->info = vsi->info;
+
+ if (bmode == BRIDGE_MODE_VEB)
+ /* change from VEPA to VEB mode */
+ ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+ else
+ /* change from VEB to VEPA mode */
+ ctxt->info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+ ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
+
+ status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+ if (status) {
+ dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
+ bmode, status, hw->adminq.sq_last_status);
+ ret = -EIO;
+ goto out;
+ }
+ /* Update sw flags for book keeping */
+ vsi_props->sw_flags = ctxt->info.sw_flags;
+
+out:
+ devm_kfree(dev, ctxt);
+ return ret;
+}
+
+/**
+ * ice_bridge_setlink - Set the hardware bridge mode
+ * @dev: the netdev being configured
+ * @nlh: RTNL message
+ * @flags: bridge setlink flags
+ * @extack: netlink extended ack
+ *
+ * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is
+ * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if
+ * not already set for all VSIs connected to this switch. And also update the
+ * unicast switch filter rules for the corresponding switch of the netdev.
+ */
+static int
+ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+ u16 __always_unused flags,
+ struct netlink_ext_ack __always_unused *extack)
+{
+ struct ice_netdev_priv *np = netdev_priv(dev);
+ struct ice_pf *pf = np->vsi->back;
+ struct nlattr *attr, *br_spec;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+ struct ice_sw *pf_sw;
+ int rem, v, err = 0;
+
+ pf_sw = pf->first_sw;
+ /* find the attribute in the netlink message */
+ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+
+ nla_for_each_nested(attr, br_spec, rem) {
+ __u16 mode;
+
+ if (nla_type(attr) != IFLA_BRIDGE_MODE)
+ continue;
+ mode = nla_get_u16(attr);
+ if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB)
+ return -EINVAL;
+ /* Continue if bridge mode is not being flipped */
+ if (mode == pf_sw->bridge_mode)
+ continue;
+ /* Iterates through the PF VSI list and update the loopback
+ * mode of the VSI
+ */
+ ice_for_each_vsi(pf, v) {
+ if (!pf->vsi[v])
+ continue;
+ err = ice_vsi_update_bridge_mode(pf->vsi[v], mode);
+ if (err)
+ return err;
+ }
+
+ hw->evb_veb = (mode == BRIDGE_MODE_VEB);
+ /* Update the unicast switch filter rules for the corresponding
+ * switch of the netdev
+ */
+ status = ice_update_sw_rule_bridge_mode(hw);
+ if (status) {
+ netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n",
+ mode, status, hw->adminq.sq_last_status);
+ /* revert hw->evb_veb */
+ hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
+ return -EIO;
+ }
+
+ pf_sw->bridge_mode = mode;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ */
+static void ice_tx_timeout(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_ring *tx_ring = NULL;
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ int hung_queue = -1;
+ u32 i;
+
+ pf->tx_timeout_count++;
+
+ /* find the stopped queue the same way dev_watchdog() does */
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ unsigned long trans_start;
+ struct netdev_queue *q;
+
+ q = netdev_get_tx_queue(netdev, i);
+ trans_start = q->trans_start;
+ if (netif_xmit_stopped(q) &&
+ time_after(jiffies,
+ trans_start + netdev->watchdog_timeo)) {
+ hung_queue = i;
+ break;
+ }
+ }
+
+ if (i == netdev->num_tx_queues)
+ netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
+ else
+ /* now that we have an index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_txq; i++)
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+ if (hung_queue == vsi->tx_rings[i]->q_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
+ }
+
+ /* Reset recovery level if enough time has elapsed after last timeout.
+ * Also ensure no new reset action happens before next timeout period.
+ */
+ if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ * 20)))
+ pf->tx_timeout_recovery_level = 1;
+ else if (time_before(jiffies, (pf->tx_timeout_last_recovery +
+ netdev->watchdog_timeo)))
+ return;
+
+ if (tx_ring) {
+ struct ice_hw *hw = &pf->hw;
+ u32 head, val = 0;
+
+ head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
+ QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
+ /* Read interrupt register */
+ val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+
+ netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
+ vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
+ head, tx_ring->next_to_use, val);
+ }
+
+ pf->tx_timeout_last_recovery = jiffies;
+ netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
+ pf->tx_timeout_recovery_level, hung_queue);
+
+ switch (pf->tx_timeout_recovery_level) {
+ case 1:
+ set_bit(__ICE_PFR_REQ, pf->state);
+ break;
+ case 2:
+ set_bit(__ICE_CORER_REQ, pf->state);
+ break;
+ case 3:
+ set_bit(__ICE_GLOBR_REQ, pf->state);
+ break;
+ default:
+ netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n");
+ set_bit(__ICE_DOWN, pf->state);
+ set_bit(__ICE_NEEDS_RESTART, vsi->state);
+ set_bit(__ICE_SERVICE_DIS, pf->state);
+ break;
+ }
+
+ ice_service_task_schedule(pf);
+ pf->tx_timeout_recovery_level++;
+}
+
+/**
* ice_open - Called when a network interface becomes active
* @netdev: network interface device structure
*
* The open entry point is called when a network interface is made
- * active by the system (IFF_UP). At this point all resources needed
+ * active by the system (IFF_UP). At this point all resources needed
* for transmit and receive operations are allocated, the interrupt
* handler is registered with the OS, the netdev watchdog is enabled,
* and the stack is notified that the interface is ready.
*
* Returns 0 on success, negative value on failure
*/
-static int ice_open(struct net_device *netdev)
+int ice_open(struct net_device *netdev)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
+ struct ice_port_info *pi;
int err;
+ if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) {
+ netdev_err(netdev, "driver needs to be unloaded and reloaded\n");
+ return -EIO;
+ }
+
netif_carrier_off(netdev);
- err = ice_vsi_open(vsi);
+ pi = vsi->port_info;
+ err = ice_update_link_info(pi);
+ if (err) {
+ netdev_err(netdev, "Failed to get link info, error %d\n",
+ err);
+ return err;
+ }
+ /* Set PHY if there is media, otherwise, turn off PHY */
+ if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
+ err = ice_force_phys_link_state(vsi, true);
+ if (err) {
+ netdev_err(netdev,
+ "Failed to set physical link up, error %d\n",
+ err);
+ return err;
+ }
+ } else {
+ err = ice_aq_set_link_restart_an(pi, false, NULL);
+ if (err) {
+ netdev_err(netdev, "Failed to set PHY state, VSI %d error %d\n",
+ vsi->vsi_num, err);
+ return err;
+ }
+ set_bit(ICE_FLAG_NO_MEDIA, vsi->back->flags);
+ }
+
+ err = ice_vsi_open(vsi);
if (err)
netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
vsi->vsi_num, vsi->vsw->sw_id);
@@ -5398,12 +4778,12 @@
* @netdev: network interface device structure
*
* The stop entry point is called when an interface is de-activated by the OS,
- * and the netdevice enters the DOWN state. The hardware is still under the
+ * and the netdevice enters the DOWN state. The hardware is still under the
* driver's control, but the netdev interface is disabled.
*
* Returns success only - not allowed to fail
*/
-static int ice_stop(struct net_device *netdev)
+int ice_stop(struct net_device *netdev)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
@@ -5427,14 +4807,14 @@
size_t len;
/* No point in doing any of this if neither checksum nor GSO are
- * being requested for this frame. We can rule out both by just
+ * being requested for this frame. We can rule out both by just
* checking for CHECKSUM_PARTIAL
*/
if (skb->ip_summed != CHECKSUM_PARTIAL)
return features;
/* We cannot support GSO if the MSS is going to be less than
- * 64 bytes. If it is then we need to drop support for GSO.
+ * 64 bytes. If it is then we need to drop support for GSO.
*/
if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
features &= ~NETIF_F_GSO_MASK;
@@ -5463,6 +4843,17 @@
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
+static const struct net_device_ops ice_netdev_safe_mode_ops = {
+ .ndo_open = ice_open,
+ .ndo_stop = ice_stop,
+ .ndo_start_xmit = ice_start_xmit,
+ .ndo_set_mac_address = ice_set_mac_address,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = ice_change_mtu,
+ .ndo_get_stats64 = ice_get_stats64,
+ .ndo_tx_timeout = ice_tx_timeout,
+};
+
static const struct net_device_ops ice_netdev_ops = {
.ndo_open = ice_open,
.ndo_stop = ice_stop,
@@ -5473,9 +4864,18 @@
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ice_change_mtu,
.ndo_get_stats64 = ice_get_stats64,
+ .ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
+ .ndo_set_vf_mac = ice_set_vf_mac,
+ .ndo_get_vf_config = ice_get_vf_cfg,
+ .ndo_set_vf_trust = ice_set_vf_trust,
+ .ndo_set_vf_vlan = ice_set_vf_port_vlan,
+ .ndo_set_vf_link_state = ice_set_vf_link_state,
.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
.ndo_set_features = ice_set_features,
+ .ndo_bridge_getlink = ice_bridge_getlink,
+ .ndo_bridge_setlink = ice_bridge_setlink,
.ndo_fdb_add = ice_fdb_add,
.ndo_fdb_del = ice_fdb_del,
+ .ndo_tx_timeout = ice_tx_timeout,
};
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 295a8cd..bcb431f 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -5,7 +5,7 @@
/**
* ice_aq_read_nvm
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @module_typeid: module pointer location in words from the NVM beginning
* @offset: byte offset from the module beginning
* @length: length of the section to be read (in bytes from the offset)
@@ -119,12 +119,69 @@
status = ice_read_sr_aq(hw, offset, 1, data, true);
if (!status)
- *data = le16_to_cpu(*(__le16 *)data);
+ *data = le16_to_cpu(*(__force __le16 *)data);
return status;
}
/**
+ * ice_read_sr_buf_aq - Reads Shadow RAM buf via AQ
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_sr_aq
+ * method. Ownership of the NVM is taken before reading the buffer and later
+ * released.
+ */
+static enum ice_status
+ice_read_sr_buf_aq(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+ enum ice_status status;
+ bool last_cmd = false;
+ u16 words_read = 0;
+ u16 i = 0;
+
+ do {
+ u16 read_size, off_w;
+
+ /* Calculate number of bytes we should read in this step.
+ * It's not allowed to read more than one page at a time or
+ * to cross page boundaries.
+ */
+ off_w = offset % ICE_SR_SECTOR_SIZE_IN_WORDS;
+ read_size = off_w ?
+ min_t(u16, *words,
+ (ICE_SR_SECTOR_SIZE_IN_WORDS - off_w)) :
+ min_t(u16, (*words - words_read),
+ ICE_SR_SECTOR_SIZE_IN_WORDS);
+
+ /* Check if this is last command, if so set proper flag */
+ if ((words_read + read_size) >= *words)
+ last_cmd = true;
+
+ status = ice_read_sr_aq(hw, offset, read_size,
+ data + words_read, last_cmd);
+ if (status)
+ goto read_nvm_buf_aq_exit;
+
+ /* Increment counter for words already read and move offset to
+ * new read location
+ */
+ words_read += read_size;
+ offset += read_size;
+ } while (words_read < *words);
+
+ for (i = 0; i < *words; i++)
+ data[i] = le16_to_cpu(((__force __le16 *)data)[i]);
+
+read_nvm_buf_aq_exit:
+ *words = words_read;
+ return status;
+}
+
+/**
* ice_acquire_nvm - Generic request for acquiring the NVM ownership
* @hw: pointer to the HW structure
* @access: NVM access type (read or write)
@@ -137,7 +194,7 @@
if (hw->nvm.blank_nvm_mode)
return 0;
- return ice_acquire_res(hw, ICE_NVM_RES_ID, access);
+ return ice_acquire_res(hw, ICE_NVM_RES_ID, access, ICE_NVM_TIMEOUT);
}
/**
@@ -178,7 +235,7 @@
/**
* ice_init_nvm - initializes NVM setting
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* This function reads and populates NVM settings such as Shadow RAM size,
* max_timeout, and blank_nvm_mode
@@ -191,7 +248,7 @@
u32 fla, gens_stat;
u8 sr_size;
- /* The SR size is stored regardless of the nvm programming mode
+ /* The SR size is stored regardless of the NVM programming mode
* as the blank mode may be used in the factory line.
*/
gens_stat = rd32(hw, GLNVM_GENS);
@@ -234,3 +291,59 @@
return status;
}
+
+/**
+ * ice_read_sr_buf - Reads Shadow RAM buf and acquire lock if necessary
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_nvm_buf_aq
+ * method. The buf read is preceded by the NVM ownership take
+ * and followed by the release.
+ */
+enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+ enum ice_status status;
+
+ status = ice_acquire_nvm(hw, ICE_RES_READ);
+ if (!status) {
+ status = ice_read_sr_buf_aq(hw, offset, words, data);
+ ice_release_nvm(hw);
+ }
+
+ return status;
+}
+
+/**
+ * ice_nvm_validate_checksum
+ * @hw: pointer to the HW struct
+ *
+ * Verify NVM PFA checksum validity (0x0706)
+ */
+enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw)
+{
+ struct ice_aqc_nvm_checksum *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ status = ice_acquire_nvm(hw, ICE_RES_READ);
+ if (status)
+ return status;
+
+ cmd = &desc.params.nvm_checksum;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_checksum);
+ cmd->flags = ICE_AQC_NVM_CHECKSUM_VERIFY;
+
+ status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+ ice_release_nvm(hw);
+
+ if (!status)
+ if (le16_to_cpu(cmd->checksum) != ICE_AQC_NVM_CHECKSUM_CORRECT)
+ status = ICE_ERR_NVM_CHECKSUM;
+
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index eeae199..2fde965 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -17,7 +17,6 @@
{
struct ice_sched_node *root;
struct ice_hw *hw;
- u16 max_children;
if (!pi)
return ICE_ERR_PARAM;
@@ -28,8 +27,8 @@
if (!root)
return ICE_ERR_NO_MEMORY;
- max_children = le16_to_cpu(hw->layer_info[0].max_children);
- root->children = devm_kcalloc(ice_hw_to_dev(hw), max_children,
+ /* coverity[suspicious_sizeof] */
+ root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0],
sizeof(*root), GFP_KERNEL);
if (!root->children) {
devm_kfree(ice_hw_to_dev(hw), root);
@@ -44,9 +43,9 @@
/**
* ice_sched_find_node_by_teid - Find the Tx scheduler node in SW DB
* @start_node: pointer to the starting ice_sched_node struct in a sub-tree
- * @teid: node teid to search
+ * @teid: node TEID to search
*
- * This function searches for a node matching the teid in the scheduling tree
+ * This function searches for a node matching the TEID in the scheduling tree
* from the SW DB. The search is recursive and is restricted by the number of
* layers it has searched through; stopping at the max supported layer.
*
@@ -67,7 +66,7 @@
start_node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF)
return NULL;
- /* Check if teid matches to any of the children nodes */
+ /* Check if TEID matches to any of the children nodes */
for (i = 0; i < start_node->num_children; i++)
if (ICE_TXSCHED_GET_NODE_TEID(start_node->children[i]) == teid)
return start_node->children[i];
@@ -86,6 +85,59 @@
}
/**
+ * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
+ * @hw: pointer to the HW struct
+ * @cmd_opc: cmd opcode
+ * @elems_req: number of elements to request
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_resp: returns total number of elements response
+ * @cd: pointer to command details structure or NULL
+ *
+ * This function sends a scheduling elements cmd (cmd_opc)
+ */
+static enum ice_status
+ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
+ u16 elems_req, void *buf, u16 buf_size,
+ u16 *elems_resp, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_sched_elem_cmd *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ cmd = &desc.params.sched_elem_cmd;
+ ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
+ cmd->num_elem_req = cpu_to_le16(elems_req);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+ if (!status && elems_resp)
+ *elems_resp = le16_to_cpu(cmd->num_elem_resp);
+
+ return status;
+}
+
+/**
+ * ice_aq_query_sched_elems - query scheduler elements
+ * @hw: pointer to the HW struct
+ * @elems_req: number of elements to query
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements returned
+ * @cd: pointer to command details structure or NULL
+ *
+ * Query scheduling elements (0x0404)
+ */
+enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+ struct ice_aqc_get_elem *buf, u16 buf_size,
+ u16 *elems_ret, struct ice_sq_cd *cd)
+{
+ return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_get_sched_elems,
+ elems_req, (void *)buf, buf_size,
+ elems_ret, cd);
+}
+
+/**
* ice_sched_add_node - Insert the Tx scheduler node in SW DB
* @pi: port information structure
* @layer: Scheduler layer of the node
@@ -98,9 +150,10 @@
struct ice_aqc_txsched_elem_data *info)
{
struct ice_sched_node *parent;
+ struct ice_aqc_get_elem elem;
struct ice_sched_node *node;
+ enum ice_status status;
struct ice_hw *hw;
- u16 max_children;
if (!pi)
return ICE_ERR_PARAM;
@@ -117,12 +170,20 @@
return ICE_ERR_PARAM;
}
+ /* query the current node information from FW before additing it
+ * to the SW DB
+ */
+ status = ice_sched_query_elem(hw, le32_to_cpu(info->node_teid), &elem);
+ if (status)
+ return status;
+
node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL);
if (!node)
return ICE_ERR_NO_MEMORY;
- max_children = le16_to_cpu(hw->layer_info[layer].max_children);
- if (max_children) {
- node->children = devm_kcalloc(ice_hw_to_dev(hw), max_children,
+ if (hw->max_children[layer]) {
+ /* coverity[suspicious_sizeof] */
+ node->children = devm_kcalloc(ice_hw_to_dev(hw),
+ hw->max_children[layer],
sizeof(*node), GFP_KERNEL);
if (!node->children) {
devm_kfree(ice_hw_to_dev(hw), node);
@@ -134,13 +195,13 @@
node->parent = parent;
node->tx_sched_layer = layer;
parent->children[parent->num_children++] = node;
- memcpy(&node->info, info, sizeof(*info));
+ memcpy(&node->info, &elem.generic[0], sizeof(node->info));
return 0;
}
/**
* ice_aq_delete_sched_elems - delete scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @grps_req: number of groups to delete
* @buf: pointer to buffer
* @buf_size: buffer size in bytes
@@ -154,30 +215,19 @@
struct ice_aqc_delete_elem *buf, u16 buf_size,
u16 *grps_del, struct ice_sq_cd *cd)
{
- struct ice_aqc_add_move_delete_elem *cmd;
- struct ice_aq_desc desc;
- enum ice_status status;
-
- cmd = &desc.params.add_move_delete_elem;
- ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_delete_sched_elems);
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
- cmd->num_grps_req = cpu_to_le16(grps_req);
-
- status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
- if (!status && grps_del)
- *grps_del = le16_to_cpu(cmd->num_grps_updated);
-
- return status;
+ return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_delete_sched_elems,
+ grps_req, (void *)buf, buf_size,
+ grps_del, cd);
}
/**
- * ice_sched_remove_elems - remove nodes from hw
- * @hw: pointer to the hw struct
+ * ice_sched_remove_elems - remove nodes from HW
+ * @hw: pointer to the HW struct
* @parent: pointer to the parent node
* @num_nodes: number of nodes
* @node_teids: array of node teids to be deleted
*
- * This function remove nodes from hw
+ * This function remove nodes from HW
*/
static enum ice_status
ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent,
@@ -192,47 +242,35 @@
buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL);
if (!buf)
return ICE_ERR_NO_MEMORY;
+
buf->hdr.parent_teid = parent->info.node_teid;
buf->hdr.num_elems = cpu_to_le16(num_nodes);
for (i = 0; i < num_nodes; i++)
buf->teid[i] = cpu_to_le32(node_teids[i]);
+
status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size,
&num_groups_removed, NULL);
if (status || num_groups_removed != 1)
- ice_debug(hw, ICE_DBG_SCHED, "remove elements failed\n");
+ ice_debug(hw, ICE_DBG_SCHED, "remove node failed FW error %d\n",
+ hw->adminq.sq_last_status);
+
devm_kfree(ice_hw_to_dev(hw), buf);
return status;
}
/**
* ice_sched_get_first_node - get the first node of the given layer
- * @hw: pointer to the hw struct
+ * @pi: port information structure
* @parent: pointer the base node of the subtree
* @layer: layer number
*
* This function retrieves the first node of the given layer from the subtree
*/
static struct ice_sched_node *
-ice_sched_get_first_node(struct ice_hw *hw, struct ice_sched_node *parent,
- u8 layer)
+ice_sched_get_first_node(struct ice_port_info *pi,
+ struct ice_sched_node *parent, u8 layer)
{
- u8 i;
-
- if (layer < hw->sw_entry_point_layer)
- return NULL;
- for (i = 0; i < parent->num_children; i++) {
- struct ice_sched_node *node = parent->children[i];
-
- if (node) {
- if (node->tx_sched_layer == layer)
- return node;
- /* this recursion is intentional, and wouldn't
- * go more than 9 calls
- */
- return ice_sched_get_first_node(hw, node, layer);
- }
- }
- return NULL;
+ return pi->sib_head[parent->tc_num][layer];
}
/**
@@ -246,7 +284,7 @@
{
u8 i;
- if (!pi)
+ if (!pi || !pi->root)
return NULL;
for (i = 0; i < pi->root->num_children; i++)
if (pi->root->children[i]->tc_num == tc)
@@ -282,17 +320,13 @@
node->info.data.elem_type != ICE_AQC_ELEM_TYPE_ROOT_PORT &&
node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF) {
u32 teid = le32_to_cpu(node->info.node_teid);
- enum ice_status status;
- status = ice_sched_remove_elems(hw, node->parent, 1, &teid);
- if (status)
- ice_debug(hw, ICE_DBG_SCHED,
- "remove element failed %d\n", status);
+ ice_sched_remove_elems(hw, node->parent, 1, &teid);
}
parent = node->parent;
/* root has no parent */
if (parent) {
- struct ice_sched_node *p, *tc_node;
+ struct ice_sched_node *p;
/* update the parent */
for (i = 0; i < parent->num_children; i++)
@@ -304,16 +338,7 @@
break;
}
- /* search for previous sibling that points to this node and
- * remove the reference
- */
- tc_node = ice_sched_get_tc_node(pi, node->tc_num);
- if (!tc_node) {
- ice_debug(hw, ICE_DBG_SCHED,
- "Invalid TC number %d\n", node->tc_num);
- goto err_exit;
- }
- p = ice_sched_get_first_node(hw, tc_node, node->tx_sched_layer);
+ p = ice_sched_get_first_node(pi, node, node->tx_sched_layer);
while (p) {
if (p->sibling == node) {
p->sibling = node->sibling;
@@ -321,8 +346,13 @@
}
p = p->sibling;
}
+
+ /* update the sibling head if head is getting removed */
+ if (pi->sib_head[node->tc_num][node->tx_sched_layer] == node)
+ pi->sib_head[node->tc_num][node->tx_sched_layer] =
+ node->sibling;
}
-err_exit:
+
/* leaf nodes have no children */
if (node->children)
devm_kfree(ice_hw_to_dev(hw), node->children);
@@ -331,7 +361,7 @@
/**
* ice_aq_get_dflt_topo - gets default scheduler topology
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @lport: logical port number
* @buf: pointer to buffer
* @buf_size: buffer size in bytes
@@ -361,7 +391,7 @@
/**
* ice_aq_add_sched_elems - adds scheduling element
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @grps_req: the number of groups that are requested to be added
* @buf: pointer to buffer
* @buf_size: buffer size in bytes
@@ -375,57 +405,14 @@
struct ice_aqc_add_elem *buf, u16 buf_size,
u16 *grps_added, struct ice_sq_cd *cd)
{
- struct ice_aqc_add_move_delete_elem *cmd;
- struct ice_aq_desc desc;
- enum ice_status status;
-
- cmd = &desc.params.add_move_delete_elem;
- ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_sched_elems);
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
- cmd->num_grps_req = cpu_to_le16(grps_req);
- status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
- if (!status && grps_added)
- *grps_added = le16_to_cpu(cmd->num_grps_updated);
-
- return status;
-}
-
-/**
- * ice_suspend_resume_elems - suspend/resume scheduler elements
- * @hw: pointer to the hw struct
- * @elems_req: number of elements to suspend
- * @buf: pointer to buffer
- * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements suspended
- * @cd: pointer to command details structure or NULL
- * @cmd_code: command code for suspend or resume
- *
- * suspend/resume scheduler elements
- */
-static enum ice_status
-ice_suspend_resume_elems(struct ice_hw *hw, u16 elems_req,
- struct ice_aqc_suspend_resume_elem *buf, u16 buf_size,
- u16 *elems_ret, struct ice_sq_cd *cd,
- enum ice_adminq_opc cmd_code)
-{
- struct ice_aqc_get_cfg_elem *cmd;
- struct ice_aq_desc desc;
- enum ice_status status;
-
- cmd = &desc.params.get_update_elem;
- ice_fill_dflt_direct_cmd_desc(&desc, cmd_code);
- cmd->num_elem_req = cpu_to_le16(elems_req);
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
- status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
- if (!status && elems_ret)
- *elems_ret = le16_to_cpu(cmd->num_elem_resp);
- return status;
+ return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_add_sched_elems,
+ grps_req, (void *)buf, buf_size,
+ grps_added, cd);
}
/**
* ice_aq_suspend_sched_elems - suspend scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @elems_req: number of elements to suspend
* @buf: pointer to buffer
* @buf_size: buffer size in bytes
@@ -439,13 +426,14 @@
struct ice_aqc_suspend_resume_elem *buf,
u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
{
- return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
- cd, ice_aqc_opc_suspend_sched_elems);
+ return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_suspend_sched_elems,
+ elems_req, (void *)buf, buf_size,
+ elems_ret, cd);
}
/**
* ice_aq_resume_sched_elems - resume scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @elems_req: number of elements to resume
* @buf: pointer to buffer
* @buf_size: buffer size in bytes
@@ -459,13 +447,14 @@
struct ice_aqc_suspend_resume_elem *buf,
u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
{
- return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
- cd, ice_aqc_opc_resume_sched_elems);
+ return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_resume_sched_elems,
+ elems_req, (void *)buf, buf_size,
+ elems_ret, cd);
}
/**
* ice_aq_query_sched_res - query scheduler resource
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @buf_size: buffer size in bytes
* @buf: pointer to buffer
* @cd: pointer to command details structure or NULL
@@ -484,13 +473,13 @@
}
/**
- * ice_sched_suspend_resume_elems - suspend or resume hw nodes
- * @hw: pointer to the hw struct
+ * ice_sched_suspend_resume_elems - suspend or resume HW nodes
+ * @hw: pointer to the HW struct
* @num_nodes: number of nodes
* @node_teids: array of node teids to be suspended or resumed
* @suspend: true means suspend / false means resume
*
- * This function suspends or resumes hw nodes
+ * This function suspends or resumes HW nodes
*/
static enum ice_status
ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
@@ -524,25 +513,62 @@
}
/**
- * ice_sched_clear_tx_topo - clears the schduler tree nodes
- * @pi: port information structure
- *
- * This function removes all the nodes from HW as well as from SW DB.
+ * ice_alloc_lan_q_ctx - allocate LAN queue contexts for the given VSI and TC
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ * @tc: TC number
+ * @new_numqs: number of queues
*/
-static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+static enum ice_status
+ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
+{
+ struct ice_vsi_ctx *vsi_ctx;
+ struct ice_q_ctx *q_ctx;
+
+ vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!vsi_ctx)
+ return ICE_ERR_PARAM;
+ /* allocate LAN queue contexts */
+ if (!vsi_ctx->lan_q_ctx[tc]) {
+ vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw),
+ new_numqs,
+ sizeof(*q_ctx),
+ GFP_KERNEL);
+ if (!vsi_ctx->lan_q_ctx[tc])
+ return ICE_ERR_NO_MEMORY;
+ vsi_ctx->num_lan_q_entries[tc] = new_numqs;
+ return 0;
+ }
+ /* num queues are increased, update the queue contexts */
+ if (new_numqs > vsi_ctx->num_lan_q_entries[tc]) {
+ u16 prev_num = vsi_ctx->num_lan_q_entries[tc];
+
+ q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs,
+ sizeof(*q_ctx), GFP_KERNEL);
+ if (!q_ctx)
+ return ICE_ERR_NO_MEMORY;
+ memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc],
+ prev_num * sizeof(*q_ctx));
+ devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]);
+ vsi_ctx->lan_q_ctx[tc] = q_ctx;
+ vsi_ctx->num_lan_q_entries[tc] = new_numqs;
+ }
+ return 0;
+}
+
+/**
+ * ice_sched_clear_agg - clears the aggregator related information
+ * @hw: pointer to the hardware structure
+ *
+ * This function removes aggregator list and free up aggregator related memory
+ * previously allocated.
+ */
+void ice_sched_clear_agg(struct ice_hw *hw)
{
struct ice_sched_agg_info *agg_info;
- struct ice_sched_vsi_info *vsi_elem;
struct ice_sched_agg_info *atmp;
- struct ice_sched_vsi_info *tmp;
- struct ice_hw *hw;
- if (!pi)
- return;
-
- hw = pi->hw;
-
- list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+ list_for_each_entry_safe(agg_info, atmp, &hw->agg_list, list_entry) {
struct ice_sched_agg_vsi_info *agg_vsi_info;
struct ice_sched_agg_vsi_info *vtmp;
@@ -551,15 +577,21 @@
list_del(&agg_vsi_info->list_entry);
devm_kfree(ice_hw_to_dev(hw), agg_vsi_info);
}
+ list_del(&agg_info->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), agg_info);
}
+}
- /* remove the vsi list */
- list_for_each_entry_safe(vsi_elem, tmp, &pi->vsi_info_list,
- list_entry) {
- list_del(&vsi_elem->list_entry);
- devm_kfree(ice_hw_to_dev(hw), vsi_elem);
- }
-
+/**
+ * ice_sched_clear_tx_topo - clears the scheduler tree nodes
+ * @pi: port information structure
+ *
+ * This function removes all the nodes from HW as well as from SW DB.
+ */
+static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+{
+ if (!pi)
+ return;
if (pi->root) {
ice_free_sched_node(pi, pi->root);
pi->root = NULL;
@@ -572,7 +604,7 @@
*
* Cleanup scheduling elements from SW DB
*/
-static void ice_sched_clear_port(struct ice_port_info *pi)
+void ice_sched_clear_port(struct ice_port_info *pi)
{
if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
return;
@@ -586,19 +618,22 @@
/**
* ice_sched_cleanup_all - cleanup scheduler elements from SW DB for all ports
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* Cleanup scheduling elements from SW DB for all the ports
*/
void ice_sched_cleanup_all(struct ice_hw *hw)
{
- if (!hw || !hw->port_info)
+ if (!hw)
return;
- if (hw->layer_info)
+ if (hw->layer_info) {
devm_kfree(ice_hw_to_dev(hw), hw->layer_info);
+ hw->layer_info = NULL;
+ }
- ice_sched_clear_port(hw->port_info);
+ if (hw->port_info)
+ ice_sched_clear_port(hw->port_info);
hw->num_tx_sched_layers = 0;
hw->num_tx_sched_phys_layers = 0;
@@ -607,41 +642,16 @@
}
/**
- * ice_sched_create_vsi_info_entry - create an empty new VSI entry
- * @pi: port information structure
- * @vsi_id: VSI Id
- *
- * This function creates a new VSI entry and adds it to list
- */
-static struct ice_sched_vsi_info *
-ice_sched_create_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id)
-{
- struct ice_sched_vsi_info *vsi_elem;
-
- if (!pi)
- return NULL;
-
- vsi_elem = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*vsi_elem),
- GFP_KERNEL);
- if (!vsi_elem)
- return NULL;
-
- list_add(&vsi_elem->list_entry, &pi->vsi_info_list);
- vsi_elem->vsi_id = vsi_id;
- return vsi_elem;
-}
-
-/**
- * ice_sched_add_elems - add nodes to hw and SW DB
+ * ice_sched_add_elems - add nodes to HW and SW DB
* @pi: port information structure
* @tc_node: pointer to the branch node
* @parent: pointer to the parent node
* @layer: layer number to add nodes
* @num_nodes: number of nodes
* @num_nodes_added: pointer to num nodes added
- * @first_node_teid: if new nodes are added then return the teid of first node
+ * @first_node_teid: if new nodes are added then return the TEID of first node
*
- * This function add nodes to hw as well as to SW DB for a given layer
+ * This function add nodes to HW as well as to SW DB for a given layer
*/
static enum ice_status
ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
@@ -653,10 +663,10 @@
u16 i, num_groups_added = 0;
enum ice_status status = 0;
struct ice_hw *hw = pi->hw;
- u16 buf_size;
+ size_t buf_size;
u32 teid;
- buf_size = sizeof(*buf) + sizeof(*buf->generic) * (num_nodes - 1);
+ buf_size = struct_size(buf, generic, num_nodes - 1);
buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL);
if (!buf)
return ICE_ERR_NO_MEMORY;
@@ -671,15 +681,20 @@
ICE_AQC_ELEM_VALID_EIR;
buf->generic[i].data.generic = 0;
buf->generic[i].data.cir_bw.bw_profile_idx =
- ICE_SCHED_DFLT_RL_PROF_ID;
+ cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID);
+ buf->generic[i].data.cir_bw.bw_alloc =
+ cpu_to_le16(ICE_SCHED_DFLT_BW_WT);
buf->generic[i].data.eir_bw.bw_profile_idx =
- ICE_SCHED_DFLT_RL_PROF_ID;
+ cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID);
+ buf->generic[i].data.eir_bw.bw_alloc =
+ cpu_to_le16(ICE_SCHED_DFLT_BW_WT);
}
status = ice_aq_add_sched_elems(hw, 1, buf, buf_size,
&num_groups_added, NULL);
if (status || num_groups_added != 1) {
- ice_debug(hw, ICE_DBG_SCHED, "add elements failed\n");
+ ice_debug(hw, ICE_DBG_SCHED, "add node failed FW Error %d\n",
+ hw->adminq.sq_last_status);
devm_kfree(ice_hw_to_dev(hw), buf);
return ICE_ERR_CFG;
}
@@ -697,7 +712,6 @@
teid = le32_to_cpu(buf->generic[i].node_teid);
new_node = ice_sched_find_node_by_teid(parent, teid);
-
if (!new_node) {
ice_debug(hw, ICE_DBG_SCHED,
"Node is missing for teid =%d\n", teid);
@@ -709,14 +723,17 @@
/* add it to previous node sibling pointer */
/* Note: siblings are not linked across branches */
- prev = ice_sched_get_first_node(hw, tc_node, layer);
-
+ prev = ice_sched_get_first_node(pi, tc_node, layer);
if (prev && prev != new_node) {
while (prev->sibling)
prev = prev->sibling;
prev->sibling = new_node;
}
+ /* initialize the sibling head */
+ if (!pi->sib_head[tc_node->tc_num][layer])
+ pi->sib_head[tc_node->tc_num][layer] = new_node;
+
if (i == 0)
*first_node_teid = teid;
}
@@ -732,7 +749,7 @@
* @parent: pointer to parent node
* @layer: layer number to add nodes
* @num_nodes: number of nodes to be added
- * @first_node_teid: pointer to the first node teid
+ * @first_node_teid: pointer to the first node TEID
* @num_nodes_added: pointer to number of nodes added
*
* This function add nodes to a given layer.
@@ -760,8 +777,7 @@
return ICE_ERR_PARAM;
/* max children per node per layer */
- max_child_nodes =
- le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
+ max_child_nodes = hw->max_children[parent->tx_sched_layer];
/* current number of children + required nodes exceed max children ? */
if ((parent->num_children + num_nodes) > max_child_nodes) {
@@ -785,7 +801,7 @@
*num_nodes_added += num_added;
}
- /* Don't modify the first node teid memory if the first node was
+ /* Don't modify the first node TEID memory if the first node was
* added already in the above call. Instead send some temp
* memory for all other recursive calls.
*/
@@ -817,7 +833,7 @@
/**
* ice_sched_get_qgrp_layer - get the current queue group layer number
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* This function returns the current queue group layer number
*/
@@ -829,7 +845,7 @@
/**
* ice_sched_get_vsi_layer - get the current VSI layer number
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
*
* This function returns the current VSI layer number
*/
@@ -840,7 +856,7 @@
* 7 4
* 5 or less sw_entry_point_layer
*/
- /* calculate the vsi layer based on number of layers. */
+ /* calculate the VSI layer based on number of layers. */
if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) {
u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
@@ -851,86 +867,13 @@
}
/**
- * ice_sched_get_num_nodes_per_layer - Get the total number of nodes per layer
- * @pi: pointer to the port info struct
- * @layer: layer number
- *
- * This function calculates the number of nodes present in the scheduler tree
- * including all the branches for a given layer
- */
-static u16
-ice_sched_get_num_nodes_per_layer(struct ice_port_info *pi, u8 layer)
-{
- struct ice_hw *hw;
- u16 num_nodes = 0;
- u8 i;
-
- if (!pi)
- return num_nodes;
-
- hw = pi->hw;
-
- /* Calculate the number of nodes for all TCs */
- for (i = 0; i < pi->root->num_children; i++) {
- struct ice_sched_node *tc_node, *node;
-
- tc_node = pi->root->children[i];
-
- /* Get the first node */
- node = ice_sched_get_first_node(hw, tc_node, layer);
- if (!node)
- continue;
-
- /* count the siblings */
- while (node) {
- num_nodes++;
- node = node->sibling;
- }
- }
-
- return num_nodes;
-}
-
-/**
- * ice_sched_val_max_nodes - check max number of nodes reached or not
- * @pi: port information structure
- * @new_num_nodes_per_layer: pointer to the new number of nodes array
- *
- * This function checks whether the scheduler tree layers have enough space to
- * add new nodes
- */
-static enum ice_status
-ice_sched_validate_for_max_nodes(struct ice_port_info *pi,
- u16 *new_num_nodes_per_layer)
-{
- struct ice_hw *hw = pi->hw;
- u8 i, qg_layer;
- u16 num_nodes;
-
- qg_layer = ice_sched_get_qgrp_layer(hw);
-
- /* walk through all the layers from SW entry point to qgroup layer */
- for (i = hw->sw_entry_point_layer; i <= qg_layer; i++) {
- num_nodes = ice_sched_get_num_nodes_per_layer(pi, i);
- if (num_nodes + new_num_nodes_per_layer[i] >
- le16_to_cpu(hw->layer_info[i].max_pf_nodes)) {
- ice_debug(hw, ICE_DBG_SCHED,
- "max nodes reached for layer = %d\n", i);
- return ICE_ERR_CFG;
- }
- }
- return 0;
-}
-
-/**
* ice_rm_dflt_leaf_node - remove the default leaf node in the tree
* @pi: port information structure
*
* This function removes the leaf node that was created by the FW
* during initialization
*/
-static void
-ice_rm_dflt_leaf_node(struct ice_port_info *pi)
+static void ice_rm_dflt_leaf_node(struct ice_port_info *pi)
{
struct ice_sched_node *node;
@@ -958,8 +901,7 @@
* This function frees all the nodes except root and TC that were created by
* the FW during initialization
*/
-static void
-ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
+static void ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
{
struct ice_sched_node *node;
@@ -1003,14 +945,12 @@
hw = pi->hw;
/* Query the Default Topology from FW */
- buf = devm_kcalloc(ice_hw_to_dev(hw), ICE_TXSCHED_MAX_BRANCHES,
- sizeof(*buf), GFP_KERNEL);
+ buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL);
if (!buf)
return ICE_ERR_NO_MEMORY;
/* Query default scheduling tree topology */
- status = ice_aq_get_dflt_topo(hw, pi->lport, buf,
- sizeof(*buf) * ICE_TXSCHED_MAX_BRANCHES,
+ status = ice_aq_get_dflt_topo(hw, pi->lport, buf, ICE_AQ_MAX_BUF_LEN,
&num_branches, NULL);
if (status)
goto err_init_port;
@@ -1034,7 +974,7 @@
goto err_init_port;
}
- /* If the last node is a leaf node then the index of the Q group
+ /* If the last node is a leaf node then the index of the queue group
* layer is two less than the number of elements.
*/
if (num_elems > 2 && buf[0].generic[num_elems - 1].data.elem_type ==
@@ -1074,8 +1014,6 @@
/* initialize the port for handling the scheduler tree */
pi->port_state = ICE_SCHED_PORT_STATE_READY;
mutex_init(&pi->sched_lock);
- INIT_LIST_HEAD(&pi->agg_list);
- INIT_LIST_HEAD(&pi->vsi_info_list);
err_init_port:
if (status && pi->root) {
@@ -1097,6 +1035,8 @@
{
struct ice_aqc_query_txsched_res_resp *buf;
enum ice_status status = 0;
+ __le16 max_sibl;
+ u16 i;
if (hw->layer_info)
return status;
@@ -1115,10 +1055,22 @@
hw->flattened_layers = buf->sched_props.flattening_bitmap;
hw->max_cgds = buf->sched_props.max_pf_cgds;
- hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
- (hw->num_tx_sched_layers *
- sizeof(*hw->layer_info)),
- GFP_KERNEL);
+ /* max sibling group size of current layer refers to the max children
+ * of the below layer node.
+ * layer 1 node max children will be layer 2 max sibling group size
+ * layer 2 node max children will be layer 3 max sibling group size
+ * and so on. This array will be populated from root (index 0) to
+ * qgroup layer 7. Leaf node has no children.
+ */
+ for (i = 0; i < hw->num_tx_sched_layers; i++) {
+ max_sibl = buf->layer_props[i].max_sibl_grp_sz;
+ hw->max_children[i] = le16_to_cpu(max_sibl);
+ }
+
+ hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
+ (hw->num_tx_sched_layers *
+ sizeof(*hw->layer_info)),
+ GFP_KERNEL);
if (!hw->layer_info) {
status = ICE_ERR_NO_MEMORY;
goto sched_query_out;
@@ -1130,29 +1082,8 @@
}
/**
- * ice_sched_get_vsi_info_entry - Get the vsi entry list for given vsi_id
- * @pi: port information structure
- * @vsi_id: vsi id
- *
- * This function retrieves the vsi list for the given vsi id
- */
-static struct ice_sched_vsi_info *
-ice_sched_get_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id)
-{
- struct ice_sched_vsi_info *list_elem;
-
- if (!pi)
- return NULL;
-
- list_for_each_entry(list_elem, &pi->vsi_info_list, list_entry)
- if (list_elem->vsi_id == vsi_id)
- return list_elem;
- return NULL;
-}
-
-/**
* ice_sched_find_node_in_subtree - Find node in part of base node subtree
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @base: pointer to the base node
* @node: pointer to the node to search
*
@@ -1184,38 +1115,36 @@
}
/**
- * ice_sched_get_free_qparent - Get a free lan or rdma q group node
+ * ice_sched_get_free_qparent - Get a free LAN or RDMA queue group node
* @pi: port information structure
- * @vsi_id: vsi id
+ * @vsi_handle: software VSI handle
* @tc: branch number
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
*
- * This function retrieves a free lan or rdma q group node
+ * This function retrieves a free LAN or RDMA queue group node
*/
struct ice_sched_node *
-ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
+ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
u8 owner)
{
struct ice_sched_node *vsi_node, *qgrp_node = NULL;
- struct ice_sched_vsi_info *list_elem;
+ struct ice_vsi_ctx *vsi_ctx;
u16 max_children;
u8 qgrp_layer;
qgrp_layer = ice_sched_get_qgrp_layer(pi->hw);
- max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children);
+ max_children = pi->hw->max_children[qgrp_layer];
- list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id);
- if (!list_elem)
- goto lan_q_exit;
-
- vsi_node = list_elem->vsi_node[tc];
-
- /* validate invalid VSI id */
+ vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
+ if (!vsi_ctx)
+ return NULL;
+ vsi_node = vsi_ctx->sched.vsi_node[tc];
+ /* validate invalid VSI ID */
if (!vsi_node)
goto lan_q_exit;
- /* get the first q group node from VSI sub-tree */
- qgrp_node = ice_sched_get_first_node(pi->hw, vsi_node, qgrp_layer);
+ /* get the first queue group node from VSI sub-tree */
+ qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
while (qgrp_node) {
/* make sure the qgroup node is part of the VSI subtree */
if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
@@ -1230,27 +1159,27 @@
}
/**
- * ice_sched_get_vsi_node - Get a VSI node based on VSI id
- * @hw: pointer to the hw struct
+ * ice_sched_get_vsi_node - Get a VSI node based on VSI ID
+ * @hw: pointer to the HW struct
* @tc_node: pointer to the TC node
- * @vsi_id: VSI id
+ * @vsi_handle: software VSI handle
*
- * This function retrieves a VSI node for a given VSI id from a given
+ * This function retrieves a VSI node for a given VSI ID from a given
* TC branch
*/
static struct ice_sched_node *
ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node,
- u16 vsi_id)
+ u16 vsi_handle)
{
struct ice_sched_node *node;
u8 vsi_layer;
vsi_layer = ice_sched_get_vsi_layer(hw);
- node = ice_sched_get_first_node(hw, tc_node, vsi_layer);
+ node = ice_sched_get_first_node(hw->port_info, tc_node, vsi_layer);
/* Check whether it already exists */
while (node) {
- if (node->vsi_id == vsi_id)
+ if (node->vsi_handle == vsi_handle)
return node;
node = node->sibling;
}
@@ -1260,7 +1189,7 @@
/**
* ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @num_qs: number of queues
* @num_nodes: num nodes array
*
@@ -1276,12 +1205,10 @@
qgl = ice_sched_get_qgrp_layer(hw);
vsil = ice_sched_get_vsi_layer(hw);
- /* calculate num nodes from q group to VSI layer */
+ /* calculate num nodes from queue group to VSI layer */
for (i = qgl; i > vsil; i--) {
- u16 max_children = le16_to_cpu(hw->layer_info[i].max_children);
-
/* round to the next integer if there is a remainder */
- num = DIV_ROUND_UP(num, max_children);
+ num = DIV_ROUND_UP(num, hw->max_children[i]);
/* need at least one node */
num_nodes[i] = num ? num : 1;
@@ -1291,16 +1218,16 @@
/**
* ice_sched_add_vsi_child_nodes - add VSI child nodes to tree
* @pi: port information structure
- * @vsi_id: VSI id
+ * @vsi_handle: software VSI handle
* @tc_node: pointer to the TC node
* @num_nodes: pointer to the num nodes that needs to be added per layer
- * @owner: node owner (lan or rdma)
+ * @owner: node owner (LAN or RDMA)
*
* This function adds the VSI child nodes to tree. It gets called for
- * lan and rdma separately.
+ * LAN and RDMA separately.
*/
static enum ice_status
-ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id,
+ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
struct ice_sched_node *tc_node, u16 *num_nodes,
u8 owner)
{
@@ -1311,16 +1238,13 @@
u16 num_added = 0;
u8 i, qgl, vsil;
- status = ice_sched_validate_for_max_nodes(pi, num_nodes);
- if (status)
- return status;
-
qgl = ice_sched_get_qgrp_layer(hw);
vsil = ice_sched_get_vsi_layer(hw);
- parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+ parent = ice_sched_get_vsi_node(hw, tc_node, vsi_handle);
for (i = vsil + 1; i <= qgl; i++) {
if (!parent)
return ICE_ERR_CFG;
+
status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i,
num_nodes[i],
&first_node_teid,
@@ -1348,49 +1272,13 @@
}
/**
- * ice_sched_rm_vsi_child_nodes - remove VSI child nodes from the tree
- * @pi: port information structure
- * @vsi_node: pointer to the VSI node
- * @num_nodes: pointer to the num nodes that needs to be removed per layer
- * @owner: node owner (lan or rdma)
- *
- * This function removes the VSI child nodes from the tree. It gets called for
- * lan and rdma separately.
- */
-static void
-ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi,
- struct ice_sched_node *vsi_node, u16 *num_nodes,
- u8 owner)
-{
- struct ice_sched_node *node, *next;
- u8 i, qgl, vsil;
- u16 num;
-
- qgl = ice_sched_get_qgrp_layer(pi->hw);
- vsil = ice_sched_get_vsi_layer(pi->hw);
-
- for (i = qgl; i > vsil; i--) {
- num = num_nodes[i];
- node = ice_sched_get_first_node(pi->hw, vsi_node, i);
- while (node && num) {
- next = node->sibling;
- if (node->owner == owner && !node->num_children) {
- ice_free_sched_node(pi, node);
- num--;
- }
- node = next;
- }
- }
-}
-
-/**
* ice_sched_calc_vsi_support_nodes - calculate number of VSI support nodes
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @tc_node: pointer to TC node
* @num_nodes: pointer to num nodes array
*
* This function calculates the number of supported nodes needed to add this
- * VSI into tx tree including the VSI, parent and intermediate nodes in below
+ * VSI into Tx tree including the VSI, parent and intermediate nodes in below
* layers
*/
static void
@@ -1398,8 +1286,8 @@
struct ice_sched_node *tc_node, u16 *num_nodes)
{
struct ice_sched_node *node;
- u16 max_child;
- u8 i, vsil;
+ u8 vsil;
+ int i;
vsil = ice_sched_get_vsi_layer(hw);
for (i = vsil; i >= hw->sw_entry_point_layer; i--)
@@ -1412,34 +1300,38 @@
/* If intermediate nodes are reached max children
* then add a new one.
*/
- node = ice_sched_get_first_node(hw, tc_node, i);
- max_child = le16_to_cpu(hw->layer_info[i].max_children);
-
+ node = ice_sched_get_first_node(hw->port_info, tc_node,
+ (u8)i);
/* scan all the siblings */
while (node) {
- if (node->num_children < max_child)
+ if (node->num_children < hw->max_children[i])
break;
node = node->sibling;
}
+ /* tree has one intermediate node to add this new VSI.
+ * So no need to calculate supported nodes for below
+ * layers.
+ */
+ if (node)
+ break;
/* all the nodes are full, allocate a new one */
- if (!node)
- num_nodes[i]++;
+ num_nodes[i]++;
}
}
/**
- * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree
+ * ice_sched_add_vsi_support_nodes - add VSI supported nodes into Tx tree
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc_node: pointer to TC node
* @num_nodes: pointer to num nodes array
*
- * This function adds the VSI supported nodes into tx tree including the
+ * This function adds the VSI supported nodes into Tx tree including the
* VSI, its parent and intermediate nodes in below layers
*/
static enum ice_status
-ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id,
+ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
struct ice_sched_node *tc_node, u16 *num_nodes)
{
struct ice_sched_node *parent = tc_node;
@@ -1451,10 +1343,6 @@
if (!pi)
return ICE_ERR_PARAM;
- status = ice_sched_validate_for_max_nodes(pi, num_nodes);
- if (status)
- return status;
-
vsil = ice_sched_get_vsi_layer(pi->hw);
for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) {
status = ice_sched_add_nodes_to_layer(pi, tc_node, parent,
@@ -1477,21 +1365,22 @@
return ICE_ERR_CFG;
if (i == vsil)
- parent->vsi_id = vsi_id;
+ parent->vsi_handle = vsi_handle;
}
+
return 0;
}
/**
* ice_sched_add_vsi_to_topo - add a new VSI into tree
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc: TC number
*
* This function adds a new VSI into scheduler tree
*/
static enum ice_status
-ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_id, u8 tc)
+ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
{
u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
struct ice_sched_node *tc_node;
@@ -1504,14 +1393,15 @@
/* calculate number of supported nodes needed for this VSI */
ice_sched_calc_vsi_support_nodes(hw, tc_node, num_nodes);
- /* add vsi supported nodes to tc subtree */
- return ice_sched_add_vsi_support_nodes(pi, vsi_id, tc_node, num_nodes);
+ /* add VSI supported nodes to TC subtree */
+ return ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
+ num_nodes);
}
/**
* ice_sched_update_vsi_child_nodes - update VSI child nodes
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc: TC number
* @new_numqs: new number of max queues
* @owner: owner of this subtree
@@ -1519,75 +1409,62 @@
* This function updates the VSI child nodes based on the number of queues
*/
static enum ice_status
-ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc,
- u16 new_numqs, u8 owner)
+ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
+ u8 tc, u16 new_numqs, u8 owner)
{
- u16 prev_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
u16 new_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
struct ice_sched_node *vsi_node;
struct ice_sched_node *tc_node;
- struct ice_sched_vsi_info *vsi;
+ struct ice_vsi_ctx *vsi_ctx;
enum ice_status status = 0;
struct ice_hw *hw = pi->hw;
u16 prev_numqs;
- u8 i;
tc_node = ice_sched_get_tc_node(pi, tc);
if (!tc_node)
return ICE_ERR_CFG;
- vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle);
if (!vsi_node)
return ICE_ERR_CFG;
- vsi = ice_sched_get_vsi_info_entry(pi, vsi_id);
- if (!vsi)
- return ICE_ERR_CFG;
-
- if (owner == ICE_SCHED_NODE_OWNER_LAN)
- prev_numqs = vsi->max_lanq[tc];
- else
+ vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!vsi_ctx)
return ICE_ERR_PARAM;
- /* num queues are not changed */
- if (prev_numqs == new_numqs)
+ prev_numqs = vsi_ctx->sched.max_lanq[tc];
+ /* num queues are not changed or less than the previous number */
+ if (new_numqs <= prev_numqs)
return status;
-
- /* calculate number of nodes based on prev/new number of qs */
- if (prev_numqs)
- ice_sched_calc_vsi_child_nodes(hw, prev_numqs, prev_num_nodes);
+ status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs);
+ if (status)
+ return status;
if (new_numqs)
ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
+ /* Keep the max number of queue configuration all the time. Update the
+ * tree only if number of queues > previous number of queues. This may
+ * leave some extra nodes in the tree if number of queues < previous
+ * number but that wouldn't harm anything. Removing those extra nodes
+ * may complicate the code if those nodes are part of SRL or
+ * individually rate limited.
+ */
+ status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
+ new_num_nodes, owner);
+ if (status)
+ return status;
+ vsi_ctx->sched.max_lanq[tc] = new_numqs;
- if (prev_numqs > new_numqs) {
- for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
- new_num_nodes[i] = prev_num_nodes[i] - new_num_nodes[i];
-
- ice_sched_rm_vsi_child_nodes(pi, vsi_node, new_num_nodes,
- owner);
- } else {
- for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
- new_num_nodes[i] -= prev_num_nodes[i];
-
- status = ice_sched_add_vsi_child_nodes(pi, vsi_id, tc_node,
- new_num_nodes, owner);
- if (status)
- return status;
- }
-
- vsi->max_lanq[tc] = new_numqs;
-
- return status;
+ return 0;
}
/**
- * ice_sched_cfg_vsi - configure the new/exisiting VSI
+ * ice_sched_cfg_vsi - configure the new/existing VSI
* @pi: port information structure
- * @vsi_id: VSI Id
+ * @vsi_handle: software VSI handle
* @tc: TC number
* @maxqs: max number of queues
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
* @enable: TC enabled or disabled
*
* This function adds/updates VSI nodes based on the number of queues. If TC is
@@ -1595,27 +1472,24 @@
* disabled then suspend the VSI if it is not already.
*/
enum ice_status
-ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs,
+ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
u8 owner, bool enable)
{
struct ice_sched_node *vsi_node, *tc_node;
- struct ice_sched_vsi_info *vsi;
+ struct ice_vsi_ctx *vsi_ctx;
enum ice_status status = 0;
struct ice_hw *hw = pi->hw;
+ ice_debug(pi->hw, ICE_DBG_SCHED, "add/config VSI %d\n", vsi_handle);
tc_node = ice_sched_get_tc_node(pi, tc);
if (!tc_node)
return ICE_ERR_PARAM;
+ vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!vsi_ctx)
+ return ICE_ERR_PARAM;
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle);
- vsi = ice_sched_get_vsi_info_entry(pi, vsi_id);
- if (!vsi)
- vsi = ice_sched_create_vsi_info_entry(pi, vsi_id);
- if (!vsi)
- return ICE_ERR_NO_MEMORY;
-
- vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
-
- /* suspend the VSI if tc is not enabled */
+ /* suspend the VSI if TC is not enabled */
if (!enable) {
if (vsi_node && vsi_node->in_use) {
u32 teid = le32_to_cpu(vsi_node->info.node_teid);
@@ -1630,18 +1504,26 @@
/* TC is enabled, if it is a new VSI then add it to the tree */
if (!vsi_node) {
- status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc);
+ status = ice_sched_add_vsi_to_topo(pi, vsi_handle, tc);
if (status)
return status;
- vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id);
+
+ vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle);
if (!vsi_node)
return ICE_ERR_CFG;
- vsi->vsi_node[tc] = vsi_node;
+
+ vsi_ctx->sched.vsi_node[tc] = vsi_node;
vsi_node->in_use = true;
+ /* invalidate the max queues whenever VSI gets added first time
+ * into the scheduler tree (boot or after reset). We need to
+ * recreate the child nodes all the time in these cases.
+ */
+ vsi_ctx->sched.max_lanq[tc] = 0;
}
/* update the VSI child nodes */
- status = ice_sched_update_vsi_child_nodes(pi, vsi_id, tc, maxqs, owner);
+ status = ice_sched_update_vsi_child_nodes(pi, vsi_handle, tc, maxqs,
+ owner);
if (status)
return status;
@@ -1656,3 +1538,135 @@
return status;
}
+
+/**
+ * ice_sched_rm_agg_vsi_entry - remove aggregator related VSI info entry
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function removes single aggregator VSI info entry from
+ * aggregator list.
+ */
+static void
+ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
+{
+ struct ice_sched_agg_info *agg_info;
+ struct ice_sched_agg_info *atmp;
+
+ list_for_each_entry_safe(agg_info, atmp, &pi->hw->agg_list,
+ list_entry) {
+ struct ice_sched_agg_vsi_info *agg_vsi_info;
+ struct ice_sched_agg_vsi_info *vtmp;
+
+ list_for_each_entry_safe(agg_vsi_info, vtmp,
+ &agg_info->agg_vsi_list, list_entry)
+ if (agg_vsi_info->vsi_handle == vsi_handle) {
+ list_del(&agg_vsi_info->list_entry);
+ devm_kfree(ice_hw_to_dev(pi->hw),
+ agg_vsi_info);
+ return;
+ }
+ }
+}
+
+/**
+ * ice_sched_is_leaf_node_present - check for a leaf node in the sub-tree
+ * @node: pointer to the sub-tree node
+ *
+ * This function checks for a leaf node presence in a given sub-tree node.
+ */
+static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
+{
+ u8 i;
+
+ for (i = 0; i < node->num_children; i++)
+ if (ice_sched_is_leaf_node_present(node->children[i]))
+ return true;
+ /* check for a leaf node */
+ return (node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF);
+}
+
+/**
+ * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @owner: LAN or RDMA
+ *
+ * This function removes the VSI and its LAN or RDMA children nodes from the
+ * scheduler tree.
+ */
+static enum ice_status
+ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
+{
+ enum ice_status status = ICE_ERR_PARAM;
+ struct ice_vsi_ctx *vsi_ctx;
+ u8 i;
+
+ ice_debug(pi->hw, ICE_DBG_SCHED, "removing VSI %d\n", vsi_handle);
+ if (!ice_is_vsi_valid(pi->hw, vsi_handle))
+ return status;
+ mutex_lock(&pi->sched_lock);
+ vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
+ if (!vsi_ctx)
+ goto exit_sched_rm_vsi_cfg;
+
+ ice_for_each_traffic_class(i) {
+ struct ice_sched_node *vsi_node, *tc_node;
+ u8 j = 0;
+
+ tc_node = ice_sched_get_tc_node(pi, i);
+ if (!tc_node)
+ continue;
+
+ vsi_node = ice_sched_get_vsi_node(pi->hw, tc_node, vsi_handle);
+ if (!vsi_node)
+ continue;
+
+ if (ice_sched_is_leaf_node_present(vsi_node)) {
+ ice_debug(pi->hw, ICE_DBG_SCHED,
+ "VSI has leaf nodes in TC %d\n", i);
+ status = ICE_ERR_IN_USE;
+ goto exit_sched_rm_vsi_cfg;
+ }
+ while (j < vsi_node->num_children) {
+ if (vsi_node->children[j]->owner == owner) {
+ ice_free_sched_node(pi, vsi_node->children[j]);
+
+ /* reset the counter again since the num
+ * children will be updated after node removal
+ */
+ j = 0;
+ } else {
+ j++;
+ }
+ }
+ /* remove the VSI if it has no children */
+ if (!vsi_node->num_children) {
+ ice_free_sched_node(pi, vsi_node);
+ vsi_ctx->sched.vsi_node[i] = NULL;
+
+ /* clean up aggregator related VSI info if any */
+ ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+ }
+ if (owner == ICE_SCHED_NODE_OWNER_LAN)
+ vsi_ctx->sched.max_lanq[i] = 0;
+ }
+ status = 0;
+
+exit_sched_rm_vsi_cfg:
+ mutex_unlock(&pi->sched_lock);
+ return status;
+}
+
+/**
+ * ice_rm_vsi_lan_cfg - remove VSI and its LAN children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function clears the VSI and its LAN children nodes from scheduler tree
+ * for all TCs.
+ */
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle)
+{
+ return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_LAN);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index badadcc..3902a8a 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -12,7 +12,7 @@
struct ice_sched_agg_vsi_info {
struct list_head list_entry;
DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS);
- u16 vsi_id;
+ u16 vsi_handle;
};
struct ice_sched_agg_info {
@@ -24,9 +24,16 @@
};
/* FW AQ command calls */
+enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+ struct ice_aqc_get_elem *buf, u16 buf_size,
+ u16 *elems_ret, struct ice_sq_cd *cd);
enum ice_status ice_sched_init_port(struct ice_port_info *pi);
enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw);
+void ice_sched_clear_port(struct ice_port_info *pi);
void ice_sched_cleanup_all(struct ice_hw *hw);
+void ice_sched_clear_agg(struct ice_hw *hw);
+
struct ice_sched_node *
ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);
enum ice_status
@@ -35,9 +42,10 @@
void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node);
struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc);
struct ice_sched_node *
-ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
+ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
u8 owner);
enum ice_status
-ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs,
+ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
u8 owner, bool enable);
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle);
#endif /* _ICE_SCHED_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
new file mode 100644
index 0000000..d2db0d0
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_adminq_cmd.h"
+#include "ice_sriov.h"
+
+/**
+ * ice_aq_send_msg_to_vf
+ * @hw: pointer to the hardware structure
+ * @vfid: VF ID to send msg
+ * @v_opcode: opcodes for VF-PF communication
+ * @v_retval: return error code
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ * @cd: pointer to command details
+ *
+ * Send message to VF driver (0x0802) using mailbox
+ * queue and asynchronously sending message via
+ * ice_sq_send_cmd() function
+ */
+enum ice_status
+ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
+ u8 *msg, u16 msglen, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_pf_vf_msg *cmd;
+ struct ice_aq_desc desc;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf);
+
+ cmd = &desc.params.virt;
+ cmd->id = cpu_to_le32(vfid);
+
+ desc.cookie_high = cpu_to_le32(v_opcode);
+ desc.cookie_low = cpu_to_le32(v_retval);
+
+ if (msglen)
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd);
+}
+
+/**
+ * ice_conv_link_speed_to_virtchnl
+ * @adv_link_support: determines the format of the returned link speed
+ * @link_speed: variable containing the link_speed to be converted
+ *
+ * Convert link speed supported by HW to link speed supported by virtchnl.
+ * If adv_link_support is true, then return link speed in Mbps. Else return
+ * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller
+ * needs to cast back to an enum virtchnl_link_speed in the case where
+ * adv_link_support is false, but when adv_link_support is true the caller can
+ * expect the speed in Mbps.
+ */
+u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
+{
+ u32 speed;
+
+ if (adv_link_support)
+ switch (link_speed) {
+ case ICE_AQ_LINK_SPEED_10MB:
+ speed = ICE_LINK_SPEED_10MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_100MB:
+ speed = ICE_LINK_SPEED_100MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_1000MB:
+ speed = ICE_LINK_SPEED_1000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_2500MB:
+ speed = ICE_LINK_SPEED_2500MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_5GB:
+ speed = ICE_LINK_SPEED_5000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_10GB:
+ speed = ICE_LINK_SPEED_10000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_20GB:
+ speed = ICE_LINK_SPEED_20000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_25GB:
+ speed = ICE_LINK_SPEED_25000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_40GB:
+ speed = ICE_LINK_SPEED_40000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_50GB:
+ speed = ICE_LINK_SPEED_50000MBPS;
+ break;
+ case ICE_AQ_LINK_SPEED_100GB:
+ speed = ICE_LINK_SPEED_100000MBPS;
+ break;
+ default:
+ speed = ICE_LINK_SPEED_UNKNOWN;
+ break;
+ }
+ else
+ /* Virtchnl speeds are not defined for every speed supported in
+ * the hardware. To maintain compatibility with older AVF
+ * drivers, while reporting the speed the new speed values are
+ * resolved to the closest known virtchnl speeds
+ */
+ switch (link_speed) {
+ case ICE_AQ_LINK_SPEED_10MB:
+ case ICE_AQ_LINK_SPEED_100MB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_100MB;
+ break;
+ case ICE_AQ_LINK_SPEED_1000MB:
+ case ICE_AQ_LINK_SPEED_2500MB:
+ case ICE_AQ_LINK_SPEED_5GB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_1GB;
+ break;
+ case ICE_AQ_LINK_SPEED_10GB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_10GB;
+ break;
+ case ICE_AQ_LINK_SPEED_20GB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_20GB;
+ break;
+ case ICE_AQ_LINK_SPEED_25GB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_25GB;
+ break;
+ case ICE_AQ_LINK_SPEED_40GB:
+ /* fall through */
+ case ICE_AQ_LINK_SPEED_50GB:
+ /* fall through */
+ case ICE_AQ_LINK_SPEED_100GB:
+ speed = (u32)VIRTCHNL_LINK_SPEED_40GB;
+ break;
+ default:
+ speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN;
+ break;
+ }
+
+ return speed;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h
new file mode 100644
index 0000000..3d78a07
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _ICE_SRIOV_H_
+#define _ICE_SRIOV_H_
+
+#include "ice_common.h"
+
+#ifdef CONFIG_PCI_IOV
+enum ice_status
+ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
+ u8 *msg, u16 msglen, struct ice_sq_cd *cd);
+
+u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed);
+#else /* CONFIG_PCI_IOV */
+static inline enum ice_status
+ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw,
+ u16 __always_unused vfid, u32 __always_unused v_opcode,
+ u32 __always_unused v_retval, u8 __always_unused *msg,
+ u16 __always_unused msglen,
+ struct ice_sq_cd __always_unused *cd)
+{
+ return 0;
+}
+
+static inline u32
+ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support,
+ u16 __always_unused link_speed)
+{
+ return 0;
+}
+
+#endif /* CONFIG_PCI_IOV */
+#endif /* _ICE_SRIOV_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index 9a95c4f..c015978 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -6,9 +6,13 @@
/* Error Codes */
enum ice_status {
+ ICE_SUCCESS = 0,
+
+ /* Generic codes : Range -1..-49 */
ICE_ERR_PARAM = -1,
ICE_ERR_NOT_IMPL = -2,
ICE_ERR_NOT_READY = -3,
+ ICE_ERR_NOT_SUPPORTED = -4,
ICE_ERR_BAD_PTR = -5,
ICE_ERR_INVAL_SIZE = -6,
ICE_ERR_DEVICE_NOT_SUPPORTED = -8,
@@ -19,7 +23,10 @@
ICE_ERR_OUT_OF_RANGE = -13,
ICE_ERR_ALREADY_EXISTS = -14,
ICE_ERR_DOES_NOT_EXIST = -15,
+ ICE_ERR_IN_USE = -16,
ICE_ERR_MAX_LIMIT = -17,
+ ICE_ERR_RESET_ONGOING = -18,
+ ICE_ERR_NVM_CHECKSUM = -51,
ICE_ERR_BUF_TOO_SHORT = -52,
ICE_ERR_NVM_BLANK_MODE = -53,
ICE_ERR_AQ_ERROR = -100,
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 6b7ec2a..1acdd43 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -19,7 +19,7 @@
* byte 6 = 0x2: to identify it as locally administered SA MAC
* byte 12 = 0x81 & byte 13 = 0x00:
* In case of VLAN filter first two bytes defines ether type (0x8100)
- * and remaining two bytes are placeholder for programming a given VLAN id
+ * and remaining two bytes are placeholder for programming a given VLAN ID
* In case of Ether type filter it is treated as header without VLAN tag
* and byte 12 and 13 is used to program a given Ether type instead
*/
@@ -51,7 +51,7 @@
/**
* ice_aq_alloc_free_res - command to allocate/free resources
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @num_entries: number of resource entries in buffer
* @buf: Indirect buffer to hold data parameters and response
* @buf_size: size of buffer for indirect commands
@@ -86,6 +86,35 @@
}
/**
+ * ice_init_def_sw_recp - initialize the recipe book keeping tables
+ * @hw: pointer to the HW struct
+ *
+ * Allocate memory for the entire recipe table and initialize the structures/
+ * entries corresponding to basic recipes.
+ */
+enum ice_status ice_init_def_sw_recp(struct ice_hw *hw)
+{
+ struct ice_sw_recipe *recps;
+ u8 i;
+
+ recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES,
+ sizeof(*recps), GFP_KERNEL);
+ if (!recps)
+ return ICE_ERR_NO_MEMORY;
+
+ for (i = 0; i < ICE_SW_LKUP_LAST; i++) {
+ recps[i].root_rid = i;
+ INIT_LIST_HEAD(&recps[i].filt_rules);
+ INIT_LIST_HEAD(&recps[i].filt_replay_rules);
+ mutex_init(&recps[i].filt_rule_lock);
+ }
+
+ hw->switch_info->recp_list = recps;
+
+ return 0;
+}
+
+/**
* ice_aq_get_sw_cfg - get switch configuration
* @hw: pointer to the hardware structure
* @buf: pointer to the result buffer
@@ -100,7 +129,7 @@
*
* NOTE: *req_desc is both an input/output parameter.
* The caller of this function first calls this function with *request_desc set
- * to 0. If the response from f/w has *req_desc set to 0, all the switch
+ * to 0. If the response from f/w has *req_desc set to 0, all the switch
* configuration information has been returned; if non-zero (meaning not all
* the information was returned), the caller should call this function again
* with *req_desc set to the previous value returned by f/w to get the
@@ -134,29 +163,30 @@
/**
* ice_aq_add_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @vsi_ctx: pointer to a VSI context struct
* @cd: pointer to command details structure or NULL
*
* Add a VSI context to the hardware (0x0210)
*/
-enum ice_status
+static enum ice_status
ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
struct ice_sq_cd *cd)
{
struct ice_aqc_add_update_free_vsi_resp *res;
struct ice_aqc_add_get_update_free_vsi *cmd;
- enum ice_status status;
struct ice_aq_desc desc;
+ enum ice_status status;
cmd = &desc.params.vsi_cmd;
- res = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw;
+ res = &desc.params.add_update_free_vsi_res;
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi);
if (!vsi_ctx->alloc_from_pool)
cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num |
ICE_AQ_VSI_IS_VALID);
+ cmd->vf_id = vsi_ctx->vf_num;
cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
@@ -175,14 +205,50 @@
}
/**
+ * ice_aq_free_vsi
+ * @hw: pointer to the HW struct
+ * @vsi_ctx: pointer to a VSI context struct
+ * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources
+ * @cd: pointer to command details structure or NULL
+ *
+ * Free VSI context info from hardware (0x0213)
+ */
+static enum ice_status
+ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
+ bool keep_vsi_alloc, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_add_update_free_vsi_resp *resp;
+ struct ice_aqc_add_get_update_free_vsi *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ cmd = &desc.params.vsi_cmd;
+ resp = &desc.params.add_update_free_vsi_res;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi);
+
+ cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID);
+ if (keep_vsi_alloc)
+ cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC);
+
+ status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+ if (!status) {
+ vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used);
+ vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free);
+ }
+
+ return status;
+}
+
+/**
* ice_aq_update_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @vsi_ctx: pointer to a VSI context struct
* @cd: pointer to command details structure or NULL
*
* Update VSI context in the hardware (0x0211)
*/
-enum ice_status
+static enum ice_status
ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
struct ice_sq_cd *cd)
{
@@ -192,7 +258,7 @@
enum ice_status status;
cmd = &desc.params.vsi_cmd;
- resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw;
+ resp = &desc.params.add_update_free_vsi_res;
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi);
@@ -212,45 +278,199 @@
}
/**
- * ice_aq_free_vsi
- * @hw: pointer to the hw struct
+ * ice_is_vsi_valid - check whether the VSI is valid or not
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ *
+ * check whether the VSI is valid or not
+ */
+bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle)
+{
+ return vsi_handle < ICE_MAX_VSI && hw->vsi_ctx[vsi_handle];
+}
+
+/**
+ * ice_get_hw_vsi_num - return the HW VSI number
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ *
+ * return the HW VSI number
+ * Caution: call this function only if VSI is valid (ice_is_vsi_valid)
+ */
+u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle)
+{
+ return hw->vsi_ctx[vsi_handle]->vsi_num;
+}
+
+/**
+ * ice_get_vsi_ctx - return the VSI context entry for a given VSI handle
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ *
+ * return the VSI context entry for a given VSI handle
+ */
+struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
+{
+ return (vsi_handle >= ICE_MAX_VSI) ? NULL : hw->vsi_ctx[vsi_handle];
+}
+
+/**
+ * ice_save_vsi_ctx - save the VSI context for a given VSI handle
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ * @vsi: VSI context pointer
+ *
+ * save the VSI context entry for a given VSI handle
+ */
+static void
+ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi)
+{
+ hw->vsi_ctx[vsi_handle] = vsi;
+}
+
+/**
+ * ice_clear_vsi_q_ctx - clear VSI queue contexts for all TCs
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ */
+static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle)
+{
+ struct ice_vsi_ctx *vsi;
+ u8 i;
+
+ vsi = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!vsi)
+ return;
+ ice_for_each_traffic_class(i) {
+ if (vsi->lan_q_ctx[i]) {
+ devm_kfree(ice_hw_to_dev(hw), vsi->lan_q_ctx[i]);
+ vsi->lan_q_ctx[i] = NULL;
+ }
+ }
+}
+
+/**
+ * ice_clear_vsi_ctx - clear the VSI context entry
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ *
+ * clear the VSI context entry
+ */
+static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
+{
+ struct ice_vsi_ctx *vsi;
+
+ vsi = ice_get_vsi_ctx(hw, vsi_handle);
+ if (vsi) {
+ ice_clear_vsi_q_ctx(hw, vsi_handle);
+ devm_kfree(ice_hw_to_dev(hw), vsi);
+ hw->vsi_ctx[vsi_handle] = NULL;
+ }
+}
+
+/**
+ * ice_clear_all_vsi_ctx - clear all the VSI context entries
+ * @hw: pointer to the HW struct
+ */
+void ice_clear_all_vsi_ctx(struct ice_hw *hw)
+{
+ u16 i;
+
+ for (i = 0; i < ICE_MAX_VSI; i++)
+ ice_clear_vsi_ctx(hw, i);
+}
+
+/**
+ * ice_add_vsi - add VSI context to the hardware and VSI handle list
+ * @hw: pointer to the HW struct
+ * @vsi_handle: unique VSI handle provided by drivers
+ * @vsi_ctx: pointer to a VSI context struct
+ * @cd: pointer to command details structure or NULL
+ *
+ * Add a VSI context to the hardware also add it into the VSI handle list.
+ * If this function gets called after reset for existing VSIs then update
+ * with the new HW VSI number in the corresponding VSI handle list entry.
+ */
+enum ice_status
+ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
+ struct ice_sq_cd *cd)
+{
+ struct ice_vsi_ctx *tmp_vsi_ctx;
+ enum ice_status status;
+
+ if (vsi_handle >= ICE_MAX_VSI)
+ return ICE_ERR_PARAM;
+ status = ice_aq_add_vsi(hw, vsi_ctx, cd);
+ if (status)
+ return status;
+ tmp_vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+ if (!tmp_vsi_ctx) {
+ /* Create a new VSI context */
+ tmp_vsi_ctx = devm_kzalloc(ice_hw_to_dev(hw),
+ sizeof(*tmp_vsi_ctx), GFP_KERNEL);
+ if (!tmp_vsi_ctx) {
+ ice_aq_free_vsi(hw, vsi_ctx, false, cd);
+ return ICE_ERR_NO_MEMORY;
+ }
+ *tmp_vsi_ctx = *vsi_ctx;
+ ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx);
+ } else {
+ /* update with new HW VSI num */
+ if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num)
+ tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_free_vsi- free VSI context from hardware and VSI handle list
+ * @hw: pointer to the HW struct
+ * @vsi_handle: unique VSI handle
* @vsi_ctx: pointer to a VSI context struct
* @keep_vsi_alloc: keep VSI allocation as part of this PF's resources
* @cd: pointer to command details structure or NULL
*
- * Get VSI context info from hardware (0x0213)
+ * Free VSI context info from hardware as well as from VSI handle list
*/
enum ice_status
-ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
- bool keep_vsi_alloc, struct ice_sq_cd *cd)
+ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
+ bool keep_vsi_alloc, struct ice_sq_cd *cd)
{
- struct ice_aqc_add_update_free_vsi_resp *resp;
- struct ice_aqc_add_get_update_free_vsi *cmd;
- struct ice_aq_desc desc;
enum ice_status status;
- cmd = &desc.params.vsi_cmd;
- resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw;
-
- ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi);
-
- cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID);
- if (keep_vsi_alloc)
- cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC);
-
- status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
- if (!status) {
- vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used);
- vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free);
- }
-
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+ vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle);
+ status = ice_aq_free_vsi(hw, vsi_ctx, keep_vsi_alloc, cd);
+ if (!status)
+ ice_clear_vsi_ctx(hw, vsi_handle);
return status;
}
/**
+ * ice_update_vsi
+ * @hw: pointer to the HW struct
+ * @vsi_handle: unique VSI handle
+ * @vsi_ctx: pointer to a VSI context struct
+ * @cd: pointer to command details structure or NULL
+ *
+ * Update VSI context in the hardware
+ */
+enum ice_status
+ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
+ struct ice_sq_cd *cd)
+{
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+ vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle);
+ return ice_aq_update_vsi(hw, vsi_ctx, cd);
+}
+
+/**
* ice_aq_alloc_free_vsi_list
- * @hw: pointer to the hw struct
- * @vsi_list_id: VSI list id returned or used for lookup
+ * @hw: pointer to the HW struct
+ * @vsi_list_id: VSI list ID returned or used for lookup
* @lkup_type: switch rule filter lookup type
* @opc: switch rules population command type - pass in the command opcode
*
@@ -306,7 +526,7 @@
/**
* ice_aq_sw_rules - add/update/remove switch rules
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
* @rule_list: pointer to switch rule population list
* @rule_list_sz: total size of the rule list in bytes
* @num_rules: number of switch rules in the rule_list
@@ -430,25 +650,58 @@
/**
* ice_fill_sw_info - Helper function to populate lb_en and lan_en
* @hw: pointer to the hardware structure
- * @f_info: filter info structure to fill/update
+ * @fi: filter info structure to fill/update
*
* This helper function populates the lb_en and lan_en elements of the provided
* ice_fltr_info struct using the switch's type and characteristics of the
* switch rule being configured.
*/
-static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *f_info)
+static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
{
- f_info->lb_en = false;
- f_info->lan_en = false;
- if ((f_info->flag & ICE_FLTR_TX) &&
- (f_info->fltr_act == ICE_FWD_TO_VSI ||
- f_info->fltr_act == ICE_FWD_TO_VSI_LIST ||
- f_info->fltr_act == ICE_FWD_TO_Q ||
- f_info->fltr_act == ICE_FWD_TO_QGRP)) {
- f_info->lb_en = true;
- if (!(hw->evb_veb && f_info->lkup_type == ICE_SW_LKUP_MAC &&
- is_unicast_ether_addr(f_info->l_data.mac.mac_addr)))
- f_info->lan_en = true;
+ fi->lb_en = false;
+ fi->lan_en = false;
+ if ((fi->flag & ICE_FLTR_TX) &&
+ (fi->fltr_act == ICE_FWD_TO_VSI ||
+ fi->fltr_act == ICE_FWD_TO_VSI_LIST ||
+ fi->fltr_act == ICE_FWD_TO_Q ||
+ fi->fltr_act == ICE_FWD_TO_QGRP)) {
+ /* Setting LB for prune actions will result in replicated
+ * packets to the internal switch that will be dropped.
+ */
+ if (fi->lkup_type != ICE_SW_LKUP_VLAN)
+ fi->lb_en = true;
+
+ /* Set lan_en to TRUE if
+ * 1. The switch is a VEB AND
+ * 2
+ * 2.1 The lookup is a directional lookup like ethertype,
+ * promiscuous, ethertype-MAC, promiscuous-VLAN
+ * and default-port OR
+ * 2.2 The lookup is VLAN, OR
+ * 2.3 The lookup is MAC with mcast or bcast addr for MAC, OR
+ * 2.4 The lookup is MAC_VLAN with mcast or bcast addr for MAC.
+ *
+ * OR
+ *
+ * The switch is a VEPA.
+ *
+ * In all other cases, the LAN enable has to be set to false.
+ */
+ if (hw->evb_veb) {
+ if (fi->lkup_type == ICE_SW_LKUP_ETHERTYPE ||
+ fi->lkup_type == ICE_SW_LKUP_PROMISC ||
+ fi->lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC ||
+ fi->lkup_type == ICE_SW_LKUP_PROMISC_VLAN ||
+ fi->lkup_type == ICE_SW_LKUP_DFLT ||
+ fi->lkup_type == ICE_SW_LKUP_VLAN ||
+ (fi->lkup_type == ICE_SW_LKUP_MAC &&
+ !is_unicast_ether_addr(fi->l_data.mac.mac_addr)) ||
+ (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN &&
+ !is_unicast_ether_addr(fi->l_data.mac.mac_addr)))
+ fi->lan_en = true;
+ } else {
+ fi->lan_en = true;
+ }
}
}
@@ -464,10 +717,12 @@
struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc)
{
u16 vlan_id = ICE_MAX_VLAN_ID + 1;
- u8 eth_hdr[DUMMY_ETH_HDR_LEN];
void *daddr = NULL;
+ u16 eth_hdr_sz;
+ u8 *eth_hdr;
u32 act = 0;
__be16 *off;
+ u8 q_rgn;
if (opc == ice_aqc_opc_remove_sw_rules) {
s_rule->pdata.lkup_tx_rx.act = 0;
@@ -477,13 +732,16 @@
return;
}
+ eth_hdr_sz = sizeof(dummy_eth_header);
+ eth_hdr = s_rule->pdata.lkup_tx_rx.hdr;
+
/* initialize the ether header with a dummy header */
- memcpy(eth_hdr, dummy_eth_header, sizeof(dummy_eth_header));
+ memcpy(eth_hdr, dummy_eth_header, eth_hdr_sz);
ice_fill_sw_info(hw, f_info);
switch (f_info->fltr_act) {
case ICE_FWD_TO_VSI:
- act |= (f_info->fwd_id.vsi_id << ICE_SINGLE_ACT_VSI_ID_S) &
+ act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) &
ICE_SINGLE_ACT_VSI_ID_M;
if (f_info->lkup_type != ICE_SW_LKUP_VLAN)
act |= ICE_SINGLE_ACT_VSI_FORWARDING |
@@ -503,13 +761,18 @@
act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
ICE_SINGLE_ACT_Q_INDEX_M;
break;
- case ICE_FWD_TO_QGRP:
- act |= ICE_SINGLE_ACT_TO_Q;
- act |= (f_info->qgrp_size << ICE_SINGLE_ACT_Q_REGION_S) &
- ICE_SINGLE_ACT_Q_REGION_M;
- break;
case ICE_DROP_PACKET:
- act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP;
+ act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP |
+ ICE_SINGLE_ACT_VALID_BIT;
+ break;
+ case ICE_FWD_TO_QGRP:
+ q_rgn = f_info->qgrp_size > 0 ?
+ (u8)ilog2(f_info->qgrp_size) : 0;
+ act |= ICE_SINGLE_ACT_TO_Q;
+ act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) &
+ ICE_SINGLE_ACT_Q_INDEX_M;
+ act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) &
+ ICE_SINGLE_ACT_Q_REGION_M;
break;
default:
return;
@@ -536,7 +799,7 @@
daddr = f_info->l_data.ethertype_mac.mac_addr;
/* fall-through */
case ICE_SW_LKUP_ETHERTYPE:
- off = (__be16 *)ð_hdr[ICE_ETH_ETHTYPE_OFFSET];
+ off = (__force __be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET);
*off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype);
break;
case ICE_SW_LKUP_MAC_VLAN:
@@ -563,18 +826,16 @@
s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act);
if (daddr)
- ether_addr_copy(ð_hdr[ICE_ETH_DA_OFFSET], daddr);
+ ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr);
if (!(vlan_id > ICE_MAX_VLAN_ID)) {
- off = (__be16 *)ð_hdr[ICE_ETH_VLAN_TCI_OFFSET];
+ off = (__force __be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET);
*off = cpu_to_be16(vlan_id);
}
/* Create the switch rule with the final dummy Ethernet header */
if (opc != ice_aqc_opc_update_sw_rules)
- s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(sizeof(eth_hdr));
-
- memcpy(s_rule->pdata.lkup_tx_rx.hdr, eth_hdr, sizeof(eth_hdr));
+ s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(eth_hdr_sz);
}
/**
@@ -582,7 +843,7 @@
* @hw: pointer to the hardware structure
* @m_ent: the management entry for which sw marker needs to be added
* @sw_marker: sw marker to tag the Rx descriptor with
- * @l_id: large action resource id
+ * @l_id: large action resource ID
*
* Create a large action to hold software marker and update the switch rule
* entry pointed by m_ent with newly created large action
@@ -594,15 +855,15 @@
struct ice_aqc_sw_rules_elem *lg_act, *rx_tx;
/* For software marker we need 3 large actions
* 1. FWD action: FWD TO VSI or VSI LIST
- * 2. GENERIC VALUE action to hold the profile id
- * 3. GENERIC VALUE action to hold the software marker id
+ * 2. GENERIC VALUE action to hold the profile ID
+ * 3. GENERIC VALUE action to hold the software marker ID
*/
const u16 num_lg_acts = 3;
enum ice_status status;
u16 lg_act_size;
u16 rules_size;
- u16 vsi_info;
u32 act;
+ u16 id;
if (m_ent->fltr_info.lkup_type != ICE_SW_LKUP_MAC)
return ICE_ERR_PARAM;
@@ -610,7 +871,7 @@
/* Create two back-to-back switch rules and submit them to the HW using
* one memory buffer:
* 1. Large Action
- * 2. Look up tx rx
+ * 2. Look up Tx Rx
*/
lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(num_lg_acts);
rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE;
@@ -628,12 +889,11 @@
/* First action VSI forwarding or VSI list forwarding depending on how
* many VSIs
*/
- vsi_info = (m_ent->vsi_count > 1) ?
- m_ent->fltr_info.fwd_id.vsi_list_id :
- m_ent->fltr_info.fwd_id.vsi_id;
+ id = (m_ent->vsi_count > 1) ? m_ent->fltr_info.fwd_id.vsi_list_id :
+ m_ent->fltr_info.fwd_id.hw_vsi_id;
act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT;
- act |= (vsi_info << ICE_LG_ACT_VSI_LIST_ID_S) &
+ act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) &
ICE_LG_ACT_VSI_LIST_ID_M;
if (m_ent->vsi_count > 1)
act |= ICE_LG_ACT_VSI_LIST;
@@ -655,17 +915,17 @@
lg_act->pdata.lg_act.act[2] = cpu_to_le32(act);
- /* call the fill switch rule to fill the lookup tx rx structure */
+ /* call the fill switch rule to fill the lookup Tx Rx structure */
ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx,
ice_aqc_opc_update_sw_rules);
- /* Update the action to point to the large action id */
+ /* Update the action to point to the large action ID */
rx_tx->pdata.lkup_tx_rx.act =
cpu_to_le32(ICE_SINGLE_ACT_PTR |
((l_id << ICE_SINGLE_ACT_PTR_VAL_S) &
ICE_SINGLE_ACT_PTR_VAL_M));
- /* Use the filter rule id of the previously created rule with single
+ /* Use the filter rule ID of the previously created rule with single
* act. Once the update happens, hardware will treat this as large
* action
*/
@@ -686,15 +946,15 @@
/**
* ice_create_vsi_list_map
* @hw: pointer to the hardware structure
- * @vsi_array: array of VSIs to form a VSI list
- * @num_vsi: num VSI in the array
- * @vsi_list_id: VSI list id generated as part of allocate resource
+ * @vsi_handle_arr: array of VSI handles to set in the VSI mapping
+ * @num_vsi: number of VSI handles in the array
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
*
- * Helper function to create a new entry of VSI list id to VSI mapping
- * using the given VSI list id
+ * Helper function to create a new entry of VSI list ID to VSI mapping
+ * using the given VSI list ID
*/
static struct ice_vsi_list_map_info *
-ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi,
+ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
u16 vsi_list_id)
{
struct ice_switch_info *sw = hw->switch_info;
@@ -706,9 +966,9 @@
return NULL;
v_map->vsi_list_id = vsi_list_id;
-
+ v_map->ref_cnt = 1;
for (i = 0; i < num_vsi; i++)
- set_bit(vsi_array[i], v_map->vsi_map);
+ set_bit(vsi_handle_arr[i], v_map->vsi_map);
list_add(&v_map->list_entry, &sw->vsi_list_map_head);
return v_map;
@@ -717,18 +977,18 @@
/**
* ice_update_vsi_list_rule
* @hw: pointer to the hardware structure
- * @vsi_array: array of VSIs to form a VSI list
- * @num_vsi: num VSI in the array
- * @vsi_list_id: VSI list id generated as part of allocate resource
+ * @vsi_handle_arr: array of VSI handles to form a VSI list
+ * @num_vsi: number of VSI handles in the array
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
* @remove: Boolean value to indicate if this is a remove action
* @opc: switch rules population command type - pass in the command opcode
* @lkup_type: lookup type of the filter
*
* Call AQ command to add a new switch rule or update existing switch rule
- * using the given VSI list id
+ * using the given VSI list ID
*/
static enum ice_status
-ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi,
+ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
u16 vsi_list_id, bool remove, enum ice_adminq_opc opc,
enum ice_sw_lkup_type lkup_type)
{
@@ -759,9 +1019,15 @@
s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL);
if (!s_rule)
return ICE_ERR_NO_MEMORY;
-
- for (i = 0; i < num_vsi; i++)
- s_rule->pdata.vsi_list.vsi[i] = cpu_to_le16(vsi_array[i]);
+ for (i = 0; i < num_vsi; i++) {
+ if (!ice_is_vsi_valid(hw, vsi_handle_arr[i])) {
+ status = ICE_ERR_PARAM;
+ goto exit;
+ }
+ /* AQ call requires hw_vsi_id(s) */
+ s_rule->pdata.vsi_list.vsi[i] =
+ cpu_to_le16(ice_get_hw_vsi_num(hw, vsi_handle_arr[i]));
+ }
s_rule->type = cpu_to_le16(type);
s_rule->pdata.vsi_list.number_vsi = cpu_to_le16(num_vsi);
@@ -769,28 +1035,24 @@
status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opc, NULL);
+exit:
devm_kfree(ice_hw_to_dev(hw), s_rule);
return status;
}
/**
* ice_create_vsi_list_rule - Creates and populates a VSI list rule
- * @hw: pointer to the hw struct
- * @vsi_array: array of VSIs to form a VSI list
- * @num_vsi: number of VSIs in the array
+ * @hw: pointer to the HW struct
+ * @vsi_handle_arr: array of VSI handles to form a VSI list
+ * @num_vsi: number of VSI handles in the array
* @vsi_list_id: stores the ID of the VSI list to be created
* @lkup_type: switch rule filter's lookup type
*/
static enum ice_status
-ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_array, u16 num_vsi,
+ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type)
{
enum ice_status status;
- int i;
-
- for (i = 0; i < num_vsi; i++)
- if (vsi_array[i] >= ICE_MAX_VSI)
- return ICE_ERR_OUT_OF_RANGE;
status = ice_aq_alloc_free_vsi_list(hw, vsi_list_id, lkup_type,
ice_aqc_opc_alloc_res);
@@ -798,9 +1060,9 @@
return status;
/* Update the newly created VSI list to include the specified VSIs */
- return ice_update_vsi_list_rule(hw, vsi_array, num_vsi, *vsi_list_id,
- false, ice_aqc_opc_add_sw_rules,
- lkup_type);
+ return ice_update_vsi_list_rule(hw, vsi_handle_arr, num_vsi,
+ *vsi_list_id, false,
+ ice_aqc_opc_add_sw_rules, lkup_type);
}
/**
@@ -816,10 +1078,10 @@
ice_create_pkt_fwd_rule(struct ice_hw *hw,
struct ice_fltr_list_entry *f_entry)
{
- struct ice_switch_info *sw = hw->switch_info;
struct ice_fltr_mgmt_list_entry *fm_entry;
struct ice_aqc_sw_rules_elem *s_rule;
enum ice_sw_lkup_type l_type;
+ struct ice_sw_recipe *recp;
enum ice_status status;
s_rule = devm_kzalloc(ice_hw_to_dev(hw),
@@ -860,31 +1122,9 @@
* calls remove filter AQ command
*/
l_type = fm_entry->fltr_info.lkup_type;
- if (l_type == ICE_SW_LKUP_MAC) {
- mutex_lock(&sw->mac_list_lock);
- list_add(&fm_entry->list_entry, &sw->mac_list_head);
- mutex_unlock(&sw->mac_list_lock);
- } else if (l_type == ICE_SW_LKUP_VLAN) {
- mutex_lock(&sw->vlan_list_lock);
- list_add(&fm_entry->list_entry, &sw->vlan_list_head);
- mutex_unlock(&sw->vlan_list_lock);
- } else if (l_type == ICE_SW_LKUP_ETHERTYPE ||
- l_type == ICE_SW_LKUP_ETHERTYPE_MAC) {
- mutex_lock(&sw->eth_m_list_lock);
- list_add(&fm_entry->list_entry, &sw->eth_m_list_head);
- mutex_unlock(&sw->eth_m_list_lock);
- } else if (l_type == ICE_SW_LKUP_PROMISC ||
- l_type == ICE_SW_LKUP_PROMISC_VLAN) {
- mutex_lock(&sw->promisc_list_lock);
- list_add(&fm_entry->list_entry, &sw->promisc_list_head);
- mutex_unlock(&sw->promisc_list_lock);
- } else if (fm_entry->fltr_info.lkup_type == ICE_SW_LKUP_MAC_VLAN) {
- mutex_lock(&sw->mac_vlan_list_lock);
- list_add(&fm_entry->list_entry, &sw->mac_vlan_list_head);
- mutex_unlock(&sw->mac_vlan_list_lock);
- } else {
- status = ICE_ERR_NOT_IMPL;
- }
+ recp = &hw->switch_info->recp_list[l_type];
+ list_add(&fm_entry->list_entry, &recp->filt_rules);
+
ice_create_pkt_fwd_rule_exit:
devm_kfree(ice_hw_to_dev(hw), s_rule);
return status;
@@ -893,19 +1133,15 @@
/**
* ice_update_pkt_fwd_rule
* @hw: pointer to the hardware structure
- * @rule_id: rule of previously created switch rule to update
- * @vsi_list_id: VSI list id to be updated with
- * @f_info: ice_fltr_info to pull other information for switch rule
+ * @f_info: filter information for switch rule
*
* Call AQ command to update a previously created switch rule with a
- * VSI list id
+ * VSI list ID
*/
static enum ice_status
-ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id,
- struct ice_fltr_info f_info)
+ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info)
{
struct ice_aqc_sw_rules_elem *s_rule;
- struct ice_fltr_info tmp_fltr;
enum ice_status status;
s_rule = devm_kzalloc(ice_hw_to_dev(hw),
@@ -913,14 +1149,9 @@
if (!s_rule)
return ICE_ERR_NO_MEMORY;
- tmp_fltr = f_info;
- tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST;
- tmp_fltr.fwd_id.vsi_list_id = vsi_list_id;
+ ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules);
- ice_fill_sw_rule(hw, &tmp_fltr, s_rule,
- ice_aqc_opc_update_sw_rules);
-
- s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(rule_id);
+ s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(f_info->fltr_rule_id);
/* Update switch rule with new rule set to forward VSI list */
status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1,
@@ -931,7 +1162,48 @@
}
/**
- * ice_handle_vsi_list_mgmt
+ * ice_update_sw_rule_bridge_mode
+ * @hw: pointer to the HW struct
+ *
+ * Updates unicast switch filter rules based on VEB/VEPA mode
+ */
+enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_mgmt_list_entry *fm_entry;
+ enum ice_status status = 0;
+ struct list_head *rule_head;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+
+ rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock;
+ rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules;
+
+ mutex_lock(rule_lock);
+ list_for_each_entry(fm_entry, rule_head, list_entry) {
+ struct ice_fltr_info *fi = &fm_entry->fltr_info;
+ u8 *addr = fi->l_data.mac.mac_addr;
+
+ /* Update unicast Tx rules to reflect the selected
+ * VEB/VEPA mode
+ */
+ if ((fi->flag & ICE_FLTR_TX) && is_unicast_ether_addr(addr) &&
+ (fi->fltr_act == ICE_FWD_TO_VSI ||
+ fi->fltr_act == ICE_FWD_TO_VSI_LIST ||
+ fi->fltr_act == ICE_FWD_TO_Q ||
+ fi->fltr_act == ICE_FWD_TO_QGRP)) {
+ status = ice_update_pkt_fwd_rule(hw, fi);
+ if (status)
+ break;
+ }
+ }
+
+ mutex_unlock(rule_lock);
+
+ return status;
+}
+
+/**
+ * ice_add_update_vsi_list
* @hw: pointer to the hardware structure
* @m_entry: pointer to current filter management list entry
* @cur_fltr: filter information from the book keeping entry
@@ -940,22 +1212,22 @@
* Call AQ command to add or update previously created VSI list with new VSI.
*
* Helper function to do book keeping associated with adding filter information
- * The algorithm to do the booking keeping is described below :
- * When a VSI needs to subscribe to a given filter( MAC/VLAN/Ethtype etc.)
+ * The algorithm to do the book keeping is described below :
+ * When a VSI needs to subscribe to a given filter (MAC/VLAN/Ethtype etc.)
* if only one VSI has been added till now
* Allocate a new VSI list and add two VSIs
* to this list using switch rule command
* Update the previously created switch rule with the
- * newly created VSI list id
+ * newly created VSI list ID
* if a VSI list was previously created
* Add the new VSI to the previously created VSI list set
* using the update switch rule command
*/
static enum ice_status
-ice_handle_vsi_list_mgmt(struct ice_hw *hw,
- struct ice_fltr_mgmt_list_entry *m_entry,
- struct ice_fltr_info *cur_fltr,
- struct ice_fltr_info *new_fltr)
+ice_add_update_vsi_list(struct ice_hw *hw,
+ struct ice_fltr_mgmt_list_entry *m_entry,
+ struct ice_fltr_info *cur_fltr,
+ struct ice_fltr_info *new_fltr)
{
enum ice_status status = 0;
u16 vsi_list_id = 0;
@@ -975,34 +1247,36 @@
* a part of a VSI list. So, create a VSI list with the old and
* new VSIs.
*/
- u16 vsi_id_arr[2];
- u16 fltr_rule;
+ struct ice_fltr_info tmp_fltr;
+ u16 vsi_handle_arr[2];
/* A rule already exists with the new VSI being added */
- if (cur_fltr->fwd_id.vsi_id == new_fltr->fwd_id.vsi_id)
+ if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id)
return ICE_ERR_ALREADY_EXISTS;
- vsi_id_arr[0] = cur_fltr->fwd_id.vsi_id;
- vsi_id_arr[1] = new_fltr->fwd_id.vsi_id;
- status = ice_create_vsi_list_rule(hw, &vsi_id_arr[0], 2,
+ vsi_handle_arr[0] = cur_fltr->vsi_handle;
+ vsi_handle_arr[1] = new_fltr->vsi_handle;
+ status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2,
&vsi_list_id,
new_fltr->lkup_type);
if (status)
return status;
- fltr_rule = cur_fltr->fltr_rule_id;
+ tmp_fltr = *new_fltr;
+ tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id;
+ tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST;
+ tmp_fltr.fwd_id.vsi_list_id = vsi_list_id;
/* Update the previous switch rule of "MAC forward to VSI" to
* "MAC fwd to VSI list"
*/
- status = ice_update_pkt_fwd_rule(hw, fltr_rule, vsi_list_id,
- *new_fltr);
+ status = ice_update_pkt_fwd_rule(hw, &tmp_fltr);
if (status)
return status;
cur_fltr->fwd_id.vsi_list_id = vsi_list_id;
cur_fltr->fltr_act = ICE_FWD_TO_VSI_LIST;
m_entry->vsi_list_info =
- ice_create_vsi_list_map(hw, &vsi_id_arr[0], 2,
+ ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2,
vsi_list_id);
/* If this entry was large action then the large action needs
@@ -1014,25 +1288,28 @@
m_entry->sw_marker_id,
m_entry->lg_act_idx);
} else {
- u16 vsi_id = new_fltr->fwd_id.vsi_id;
+ u16 vsi_handle = new_fltr->vsi_handle;
enum ice_adminq_opc opcode;
+ if (!m_entry->vsi_list_info)
+ return ICE_ERR_CFG;
+
/* A rule already exists with the new VSI being added */
- if (test_bit(vsi_id, m_entry->vsi_list_info->vsi_map))
+ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
return 0;
/* Update the previously created VSI list set with
- * the new VSI id passed in
+ * the new VSI ID passed in
*/
vsi_list_id = cur_fltr->fwd_id.vsi_list_id;
opcode = ice_aqc_opc_update_sw_rules;
- status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id,
- false, opcode,
+ status = ice_update_vsi_list_rule(hw, &vsi_handle, 1,
+ vsi_list_id, false, opcode,
new_fltr->lkup_type);
- /* update VSI list mapping info with new VSI id */
+ /* update VSI list mapping info with new VSI ID */
if (!status)
- set_bit(vsi_id, m_entry->vsi_list_info->vsi_map);
+ set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map);
}
if (!status)
m_entry->vsi_count++;
@@ -1040,54 +1317,325 @@
}
/**
- * ice_find_mac_entry
+ * ice_find_rule_entry - Search a rule entry
* @hw: pointer to the hardware structure
- * @mac_addr: MAC address to search for
+ * @recp_id: lookup type for which the specified rule needs to be searched
+ * @f_info: rule information
*
- * Helper function to search for a MAC entry using a given MAC address
- * Returns pointer to the entry if found.
+ * Helper function to search for a given rule entry
+ * Returns pointer to entry storing the rule if found
*/
static struct ice_fltr_mgmt_list_entry *
-ice_find_mac_entry(struct ice_hw *hw, u8 *mac_addr)
+ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info)
{
- struct ice_fltr_mgmt_list_entry *m_list_itr, *mac_ret = NULL;
+ struct ice_fltr_mgmt_list_entry *list_itr, *ret = NULL;
struct ice_switch_info *sw = hw->switch_info;
+ struct list_head *list_head;
- mutex_lock(&sw->mac_list_lock);
- list_for_each_entry(m_list_itr, &sw->mac_list_head, list_entry) {
- u8 *buf = &m_list_itr->fltr_info.l_data.mac.mac_addr[0];
-
- if (ether_addr_equal(buf, mac_addr)) {
- mac_ret = m_list_itr;
+ list_head = &sw->recp_list[recp_id].filt_rules;
+ list_for_each_entry(list_itr, list_head, list_entry) {
+ if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data,
+ sizeof(f_info->l_data)) &&
+ f_info->flag == list_itr->fltr_info.flag) {
+ ret = list_itr;
break;
}
}
- mutex_unlock(&sw->mac_list_lock);
- return mac_ret;
+ return ret;
}
/**
- * ice_add_shared_mac - Add one MAC shared filter rule
+ * ice_find_vsi_list_entry - Search VSI list map with VSI count 1
* @hw: pointer to the hardware structure
+ * @recp_id: lookup type for which VSI lists needs to be searched
+ * @vsi_handle: VSI handle to be found in VSI list
+ * @vsi_list_id: VSI list ID found containing vsi_handle
+ *
+ * Helper function to search a VSI list with single entry containing given VSI
+ * handle element. This can be extended further to search VSI list with more
+ * than 1 vsi_count. Returns pointer to VSI list entry if found.
+ */
+static struct ice_vsi_list_map_info *
+ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
+ u16 *vsi_list_id)
+{
+ struct ice_vsi_list_map_info *map_info = NULL;
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_mgmt_list_entry *list_itr;
+ struct list_head *list_head;
+
+ list_head = &sw->recp_list[recp_id].filt_rules;
+ list_for_each_entry(list_itr, list_head, list_entry) {
+ if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) {
+ map_info = list_itr->vsi_list_info;
+ if (test_bit(vsi_handle, map_info->vsi_map)) {
+ *vsi_list_id = map_info->vsi_list_id;
+ return map_info;
+ }
+ }
+ }
+ return NULL;
+}
+
+/**
+ * ice_add_rule_internal - add rule for a given lookup type
+ * @hw: pointer to the hardware structure
+ * @recp_id: lookup type (recipe ID) for which rule has to be added
* @f_entry: structure containing MAC forwarding information
*
- * Adds or updates the book keeping list for the MAC addresses
+ * Adds or updates the rule lists for a given recipe
*/
static enum ice_status
-ice_add_shared_mac(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
+ice_add_rule_internal(struct ice_hw *hw, u8 recp_id,
+ struct ice_fltr_list_entry *f_entry)
{
+ struct ice_switch_info *sw = hw->switch_info;
struct ice_fltr_info *new_fltr, *cur_fltr;
struct ice_fltr_mgmt_list_entry *m_entry;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+ enum ice_status status = 0;
+ if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle))
+ return ICE_ERR_PARAM;
+ f_entry->fltr_info.fwd_id.hw_vsi_id =
+ ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle);
+
+ rule_lock = &sw->recp_list[recp_id].filt_rule_lock;
+
+ mutex_lock(rule_lock);
new_fltr = &f_entry->fltr_info;
+ if (new_fltr->flag & ICE_FLTR_RX)
+ new_fltr->src = hw->port_info->lport;
+ else if (new_fltr->flag & ICE_FLTR_TX)
+ new_fltr->src = f_entry->fltr_info.fwd_id.hw_vsi_id;
- m_entry = ice_find_mac_entry(hw, &new_fltr->l_data.mac.mac_addr[0]);
- if (!m_entry)
+ m_entry = ice_find_rule_entry(hw, recp_id, new_fltr);
+ if (!m_entry) {
+ mutex_unlock(rule_lock);
return ice_create_pkt_fwd_rule(hw, f_entry);
+ }
cur_fltr = &m_entry->fltr_info;
+ status = ice_add_update_vsi_list(hw, m_entry, cur_fltr, new_fltr);
+ mutex_unlock(rule_lock);
- return ice_handle_vsi_list_mgmt(hw, m_entry, cur_fltr, new_fltr);
+ return status;
+}
+
+/**
+ * ice_remove_vsi_list_rule
+ * @hw: pointer to the hardware structure
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
+ * @lkup_type: switch rule filter lookup type
+ *
+ * The VSI list should be emptied before this function is called to remove the
+ * VSI list.
+ */
+static enum ice_status
+ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id,
+ enum ice_sw_lkup_type lkup_type)
+{
+ struct ice_aqc_sw_rules_elem *s_rule;
+ enum ice_status status;
+ u16 s_rule_size;
+
+ s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0);
+ s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL);
+ if (!s_rule)
+ return ICE_ERR_NO_MEMORY;
+
+ s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR);
+ s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id);
+
+ /* Free the vsi_list resource that we allocated. It is assumed that the
+ * list is empty at this point.
+ */
+ status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type,
+ ice_aqc_opc_free_res);
+
+ devm_kfree(ice_hw_to_dev(hw), s_rule);
+ return status;
+}
+
+/**
+ * ice_rem_update_vsi_list
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle of the VSI to remove
+ * @fm_list: filter management entry for which the VSI list management needs to
+ * be done
+ */
+static enum ice_status
+ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle,
+ struct ice_fltr_mgmt_list_entry *fm_list)
+{
+ enum ice_sw_lkup_type lkup_type;
+ enum ice_status status = 0;
+ u16 vsi_list_id;
+
+ if (fm_list->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST ||
+ fm_list->vsi_count == 0)
+ return ICE_ERR_PARAM;
+
+ /* A rule with the VSI being removed does not exist */
+ if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map))
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ lkup_type = fm_list->fltr_info.lkup_type;
+ vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id;
+ status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, vsi_list_id, true,
+ ice_aqc_opc_update_sw_rules,
+ lkup_type);
+ if (status)
+ return status;
+
+ fm_list->vsi_count--;
+ clear_bit(vsi_handle, fm_list->vsi_list_info->vsi_map);
+
+ if (fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) {
+ struct ice_fltr_info tmp_fltr_info = fm_list->fltr_info;
+ struct ice_vsi_list_map_info *vsi_list_info =
+ fm_list->vsi_list_info;
+ u16 rem_vsi_handle;
+
+ rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map,
+ ICE_MAX_VSI);
+ if (!ice_is_vsi_valid(hw, rem_vsi_handle))
+ return ICE_ERR_OUT_OF_RANGE;
+
+ /* Make sure VSI list is empty before removing it below */
+ status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1,
+ vsi_list_id, true,
+ ice_aqc_opc_update_sw_rules,
+ lkup_type);
+ if (status)
+ return status;
+
+ tmp_fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ tmp_fltr_info.fwd_id.hw_vsi_id =
+ ice_get_hw_vsi_num(hw, rem_vsi_handle);
+ tmp_fltr_info.vsi_handle = rem_vsi_handle;
+ status = ice_update_pkt_fwd_rule(hw, &tmp_fltr_info);
+ if (status) {
+ ice_debug(hw, ICE_DBG_SW,
+ "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n",
+ tmp_fltr_info.fwd_id.hw_vsi_id, status);
+ return status;
+ }
+
+ fm_list->fltr_info = tmp_fltr_info;
+ }
+
+ if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) ||
+ (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) {
+ struct ice_vsi_list_map_info *vsi_list_info =
+ fm_list->vsi_list_info;
+
+ /* Remove the VSI list since it is no longer used */
+ status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type);
+ if (status) {
+ ice_debug(hw, ICE_DBG_SW,
+ "Failed to remove VSI list %d, error %d\n",
+ vsi_list_id, status);
+ return status;
+ }
+
+ list_del(&vsi_list_info->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), vsi_list_info);
+ fm_list->vsi_list_info = NULL;
+ }
+
+ return status;
+}
+
+/**
+ * ice_remove_rule_internal - Remove a filter rule of a given type
+ * @hw: pointer to the hardware structure
+ * @recp_id: recipe ID for which the rule needs to removed
+ * @f_entry: rule entry containing filter information
+ */
+static enum ice_status
+ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id,
+ struct ice_fltr_list_entry *f_entry)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_mgmt_list_entry *list_elem;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+ enum ice_status status = 0;
+ bool remove_rule = false;
+ u16 vsi_handle;
+
+ if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle))
+ return ICE_ERR_PARAM;
+ f_entry->fltr_info.fwd_id.hw_vsi_id =
+ ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle);
+
+ rule_lock = &sw->recp_list[recp_id].filt_rule_lock;
+ mutex_lock(rule_lock);
+ list_elem = ice_find_rule_entry(hw, recp_id, &f_entry->fltr_info);
+ if (!list_elem) {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ goto exit;
+ }
+
+ if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) {
+ remove_rule = true;
+ } else if (!list_elem->vsi_list_info) {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ goto exit;
+ } else if (list_elem->vsi_list_info->ref_cnt > 1) {
+ /* a ref_cnt > 1 indicates that the vsi_list is being
+ * shared by multiple rules. Decrement the ref_cnt and
+ * remove this rule, but do not modify the list, as it
+ * is in-use by other rules.
+ */
+ list_elem->vsi_list_info->ref_cnt--;
+ remove_rule = true;
+ } else {
+ /* a ref_cnt of 1 indicates the vsi_list is only used
+ * by one rule. However, the original removal request is only
+ * for a single VSI. Update the vsi_list first, and only
+ * remove the rule if there are no further VSIs in this list.
+ */
+ vsi_handle = f_entry->fltr_info.vsi_handle;
+ status = ice_rem_update_vsi_list(hw, vsi_handle, list_elem);
+ if (status)
+ goto exit;
+ /* if VSI count goes to zero after updating the VSI list */
+ if (list_elem->vsi_count == 0)
+ remove_rule = true;
+ }
+
+ if (remove_rule) {
+ /* Remove the lookup rule */
+ struct ice_aqc_sw_rules_elem *s_rule;
+
+ s_rule = devm_kzalloc(ice_hw_to_dev(hw),
+ ICE_SW_RULE_RX_TX_NO_HDR_SIZE,
+ GFP_KERNEL);
+ if (!s_rule) {
+ status = ICE_ERR_NO_MEMORY;
+ goto exit;
+ }
+
+ ice_fill_sw_rule(hw, &list_elem->fltr_info, s_rule,
+ ice_aqc_opc_remove_sw_rules);
+
+ status = ice_aq_sw_rules(hw, s_rule,
+ ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1,
+ ice_aqc_opc_remove_sw_rules, NULL);
+
+ /* Remove a book keeping from the list */
+ devm_kfree(ice_hw_to_dev(hw), s_rule);
+
+ if (status)
+ goto exit;
+
+ list_del(&list_elem->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), list_elem);
+ }
+exit:
+ mutex_unlock(rule_lock);
+ return status;
}
/**
@@ -1106,7 +1654,10 @@
{
struct ice_aqc_sw_rules_elem *s_rule, *r_iter;
struct ice_fltr_list_entry *m_list_itr;
+ struct list_head *rule_head;
u16 elem_sent, total_elem_left;
+ struct ice_switch_info *sw;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
enum ice_status status = 0;
u16 num_unicast = 0;
u16 s_rule_size;
@@ -1114,48 +1665,73 @@
if (!m_list || !hw)
return ICE_ERR_PARAM;
+ s_rule = NULL;
+ sw = hw->switch_info;
+ rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock;
list_for_each_entry(m_list_itr, m_list, list_entry) {
u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0];
+ u16 vsi_handle;
+ u16 hw_vsi_id;
- if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC)
+ m_list_itr->fltr_info.flag = ICE_FLTR_TX;
+ vsi_handle = m_list_itr->fltr_info.vsi_handle;
+ if (!ice_is_vsi_valid(hw, vsi_handle))
return ICE_ERR_PARAM;
- if (is_zero_ether_addr(add))
+ hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+ m_list_itr->fltr_info.fwd_id.hw_vsi_id = hw_vsi_id;
+ /* update the src in case it is VSI num */
+ if (m_list_itr->fltr_info.src_id != ICE_SRC_ID_VSI)
+ return ICE_ERR_PARAM;
+ m_list_itr->fltr_info.src = hw_vsi_id;
+ if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC ||
+ is_zero_ether_addr(add))
return ICE_ERR_PARAM;
if (is_unicast_ether_addr(add) && !hw->ucast_shared) {
/* Don't overwrite the unicast address */
- if (ice_find_mac_entry(hw, add))
+ mutex_lock(rule_lock);
+ if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC,
+ &m_list_itr->fltr_info)) {
+ mutex_unlock(rule_lock);
return ICE_ERR_ALREADY_EXISTS;
+ }
+ mutex_unlock(rule_lock);
num_unicast++;
} else if (is_multicast_ether_addr(add) ||
(is_unicast_ether_addr(add) && hw->ucast_shared)) {
- status = ice_add_shared_mac(hw, m_list_itr);
- if (status) {
- m_list_itr->status = ICE_FLTR_STATUS_FW_FAIL;
- return status;
- }
- m_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS;
+ m_list_itr->status =
+ ice_add_rule_internal(hw, ICE_SW_LKUP_MAC,
+ m_list_itr);
+ if (m_list_itr->status)
+ return m_list_itr->status;
}
}
+ mutex_lock(rule_lock);
/* Exit if no suitable entries were found for adding bulk switch rule */
- if (!num_unicast)
- return 0;
+ if (!num_unicast) {
+ status = 0;
+ goto ice_add_mac_exit;
+ }
+
+ rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules;
/* Allocate switch rule buffer for the bulk update for unicast */
s_rule_size = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE;
s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size,
GFP_KERNEL);
- if (!s_rule)
- return ICE_ERR_NO_MEMORY;
+ if (!s_rule) {
+ status = ICE_ERR_NO_MEMORY;
+ goto ice_add_mac_exit;
+ }
r_iter = s_rule;
list_for_each_entry(m_list_itr, m_list, list_entry) {
struct ice_fltr_info *f_info = &m_list_itr->fltr_info;
- u8 *addr = &f_info->l_data.mac.mac_addr[0];
+ u8 *mac_addr = &f_info->l_data.mac.mac_addr[0];
- if (is_unicast_ether_addr(addr)) {
- ice_fill_sw_rule(hw, &m_list_itr->fltr_info,
- r_iter, ice_aqc_opc_add_sw_rules);
+ if (is_unicast_ether_addr(mac_addr)) {
+ ice_fill_sw_rule(hw, &m_list_itr->fltr_info, r_iter,
+ ice_aqc_opc_add_sw_rules);
r_iter = (struct ice_aqc_sw_rules_elem *)
((u8 *)r_iter + s_rule_size);
}
@@ -1179,15 +1755,14 @@
((u8 *)r_iter + (elem_sent * s_rule_size));
}
- /* Fill up rule id based on the value returned from FW */
+ /* Fill up rule ID based on the value returned from FW */
r_iter = s_rule;
list_for_each_entry(m_list_itr, m_list, list_entry) {
struct ice_fltr_info *f_info = &m_list_itr->fltr_info;
- u8 *addr = &f_info->l_data.mac.mac_addr[0];
- struct ice_switch_info *sw = hw->switch_info;
+ u8 *mac_addr = &f_info->l_data.mac.mac_addr[0];
struct ice_fltr_mgmt_list_entry *fm_entry;
- if (is_unicast_ether_addr(addr)) {
+ if (is_unicast_ether_addr(mac_addr)) {
f_info->fltr_rule_id =
le16_to_cpu(r_iter->pdata.lkup_tx_rx.index);
f_info->fltr_act = ICE_FWD_TO_VSI;
@@ -1203,46 +1778,21 @@
/* The book keeping entries will get removed when
* base driver calls remove filter AQ command
*/
- mutex_lock(&sw->mac_list_lock);
- list_add(&fm_entry->list_entry, &sw->mac_list_head);
- mutex_unlock(&sw->mac_list_lock);
+ list_add(&fm_entry->list_entry, rule_head);
r_iter = (struct ice_aqc_sw_rules_elem *)
((u8 *)r_iter + s_rule_size);
}
}
ice_add_mac_exit:
- devm_kfree(ice_hw_to_dev(hw), s_rule);
+ mutex_unlock(rule_lock);
+ if (s_rule)
+ devm_kfree(ice_hw_to_dev(hw), s_rule);
return status;
}
/**
- * ice_find_vlan_entry
- * @hw: pointer to the hardware structure
- * @vlan_id: VLAN id to search for
- *
- * Helper function to search for a VLAN entry using a given VLAN id
- * Returns pointer to the entry if found.
- */
-static struct ice_fltr_mgmt_list_entry *
-ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id)
-{
- struct ice_fltr_mgmt_list_entry *vlan_list_itr, *vlan_ret = NULL;
- struct ice_switch_info *sw = hw->switch_info;
-
- mutex_lock(&sw->vlan_list_lock);
- list_for_each_entry(vlan_list_itr, &sw->vlan_list_head, list_entry)
- if (vlan_list_itr->fltr_info.l_data.vlan.vlan_id == vlan_id) {
- vlan_ret = vlan_list_itr;
- break;
- }
-
- mutex_unlock(&sw->vlan_list_lock);
- return vlan_ret;
-}
-
-/**
* ice_add_vlan_internal - Add one VLAN based filter rule
* @hw: pointer to the hardware structure
* @f_entry: filter entry containing one VLAN information
@@ -1250,53 +1800,150 @@
static enum ice_status
ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
{
- struct ice_fltr_info *new_fltr, *cur_fltr;
+ struct ice_switch_info *sw = hw->switch_info;
struct ice_fltr_mgmt_list_entry *v_list_itr;
- u16 vlan_id;
+ struct ice_fltr_info *new_fltr, *cur_fltr;
+ enum ice_sw_lkup_type lkup_type;
+ u16 vsi_list_id = 0, vsi_handle;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+ enum ice_status status = 0;
+ if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle))
+ return ICE_ERR_PARAM;
+
+ f_entry->fltr_info.fwd_id.hw_vsi_id =
+ ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle);
new_fltr = &f_entry->fltr_info;
- /* VLAN id should only be 12 bits */
+
+ /* VLAN ID should only be 12 bits */
if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID)
return ICE_ERR_PARAM;
- vlan_id = new_fltr->l_data.vlan.vlan_id;
- v_list_itr = ice_find_vlan_entry(hw, vlan_id);
+ if (new_fltr->src_id != ICE_SRC_ID_VSI)
+ return ICE_ERR_PARAM;
+
+ new_fltr->src = new_fltr->fwd_id.hw_vsi_id;
+ lkup_type = new_fltr->lkup_type;
+ vsi_handle = new_fltr->vsi_handle;
+ rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock;
+ mutex_lock(rule_lock);
+ v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr);
if (!v_list_itr) {
- u16 vsi_id = ICE_VSI_INVAL_ID;
- enum ice_status status;
- u16 vsi_list_id = 0;
+ struct ice_vsi_list_map_info *map_info = NULL;
if (new_fltr->fltr_act == ICE_FWD_TO_VSI) {
- enum ice_sw_lkup_type lkup_type = new_fltr->lkup_type;
-
- /* All VLAN pruning rules use a VSI list.
- * Convert the action to forwarding to a VSI list.
+ /* All VLAN pruning rules use a VSI list. Check if
+ * there is already a VSI list containing VSI that we
+ * want to add. If found, use the same vsi_list_id for
+ * this new VLAN rule or else create a new list.
*/
- vsi_id = new_fltr->fwd_id.vsi_id;
- status = ice_create_vsi_list_rule(hw, &vsi_id, 1,
- &vsi_list_id,
- lkup_type);
- if (status)
- return status;
+ map_info = ice_find_vsi_list_entry(hw, ICE_SW_LKUP_VLAN,
+ vsi_handle,
+ &vsi_list_id);
+ if (!map_info) {
+ status = ice_create_vsi_list_rule(hw,
+ &vsi_handle,
+ 1,
+ &vsi_list_id,
+ lkup_type);
+ if (status)
+ goto exit;
+ }
+ /* Convert the action to forwarding to a VSI list. */
new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST;
new_fltr->fwd_id.vsi_list_id = vsi_list_id;
}
status = ice_create_pkt_fwd_rule(hw, f_entry);
- if (!status && vsi_id != ICE_VSI_INVAL_ID) {
- v_list_itr = ice_find_vlan_entry(hw, vlan_id);
- if (!v_list_itr)
- return ICE_ERR_DOES_NOT_EXIST;
- v_list_itr->vsi_list_info =
- ice_create_vsi_list_map(hw, &vsi_id, 1,
- vsi_list_id);
+ if (!status) {
+ v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN,
+ new_fltr);
+ if (!v_list_itr) {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ goto exit;
+ }
+ /* reuse VSI list for new rule and increment ref_cnt */
+ if (map_info) {
+ v_list_itr->vsi_list_info = map_info;
+ map_info->ref_cnt++;
+ } else {
+ v_list_itr->vsi_list_info =
+ ice_create_vsi_list_map(hw, &vsi_handle,
+ 1, vsi_list_id);
+ }
+ }
+ } else if (v_list_itr->vsi_list_info->ref_cnt == 1) {
+ /* Update existing VSI list to add new VSI ID only if it used
+ * by one VLAN rule.
+ */
+ cur_fltr = &v_list_itr->fltr_info;
+ status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr,
+ new_fltr);
+ } else {
+ /* If VLAN rule exists and VSI list being used by this rule is
+ * referenced by more than 1 VLAN rule. Then create a new VSI
+ * list appending previous VSI with new VSI and update existing
+ * VLAN rule to point to new VSI list ID
+ */
+ struct ice_fltr_info tmp_fltr;
+ u16 vsi_handle_arr[2];
+ u16 cur_handle;
+
+ /* Current implementation only supports reusing VSI list with
+ * one VSI count. We should never hit below condition
+ */
+ if (v_list_itr->vsi_count > 1 &&
+ v_list_itr->vsi_list_info->ref_cnt > 1) {
+ ice_debug(hw, ICE_DBG_SW,
+ "Invalid configuration: Optimization to reuse VSI list with more than one VSI is not being done yet\n");
+ status = ICE_ERR_CFG;
+ goto exit;
}
- return status;
+ cur_handle =
+ find_first_bit(v_list_itr->vsi_list_info->vsi_map,
+ ICE_MAX_VSI);
+
+ /* A rule already exists with the new VSI being added */
+ if (cur_handle == vsi_handle) {
+ status = ICE_ERR_ALREADY_EXISTS;
+ goto exit;
+ }
+
+ vsi_handle_arr[0] = cur_handle;
+ vsi_handle_arr[1] = vsi_handle;
+ status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2,
+ &vsi_list_id, lkup_type);
+ if (status)
+ goto exit;
+
+ tmp_fltr = v_list_itr->fltr_info;
+ tmp_fltr.fltr_rule_id = v_list_itr->fltr_info.fltr_rule_id;
+ tmp_fltr.fwd_id.vsi_list_id = vsi_list_id;
+ tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST;
+ /* Update the previous switch rule to a new VSI list which
+ * includes current VSI that is requested
+ */
+ status = ice_update_pkt_fwd_rule(hw, &tmp_fltr);
+ if (status)
+ goto exit;
+
+ /* before overriding VSI list map info. decrement ref_cnt of
+ * previous VSI list
+ */
+ v_list_itr->vsi_list_info->ref_cnt--;
+
+ /* now update to newly created list */
+ v_list_itr->fltr_info.fwd_id.vsi_list_id = vsi_list_id;
+ v_list_itr->vsi_list_info =
+ ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2,
+ vsi_list_id);
+ v_list_itr->vsi_count++;
}
- cur_fltr = &v_list_itr->fltr_info;
- return ice_handle_vsi_list_mgmt(hw, v_list_itr, cur_fltr, new_fltr);
+exit:
+ mutex_unlock(rule_lock);
+ return status;
}
/**
@@ -1313,335 +1960,120 @@
return ICE_ERR_PARAM;
list_for_each_entry(v_list_itr, v_list, list_entry) {
- enum ice_status status;
-
if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN)
return ICE_ERR_PARAM;
-
- status = ice_add_vlan_internal(hw, v_list_itr);
- if (status) {
- v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL;
- return status;
- }
- v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS;
+ v_list_itr->fltr_info.flag = ICE_FLTR_TX;
+ v_list_itr->status = ice_add_vlan_internal(hw, v_list_itr);
+ if (v_list_itr->status)
+ return v_list_itr->status;
}
return 0;
}
/**
- * ice_remove_vsi_list_rule
+ * ice_add_eth_mac - Add ethertype and MAC based filter rule
* @hw: pointer to the hardware structure
- * @vsi_list_id: VSI list id generated as part of allocate resource
- * @lkup_type: switch rule filter lookup type
- */
-static enum ice_status
-ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id,
- enum ice_sw_lkup_type lkup_type)
-{
- struct ice_aqc_sw_rules_elem *s_rule;
- enum ice_status status;
- u16 s_rule_size;
-
- s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0);
- s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL);
- if (!s_rule)
- return ICE_ERR_NO_MEMORY;
-
- s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR);
- s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id);
- /* FW expects number of VSIs in vsi_list resource to be 0 for clear
- * command. Since memory is zero'ed out during initialization, it's not
- * necessary to explicitly initialize the variable to 0.
- */
-
- status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1,
- ice_aqc_opc_remove_sw_rules, NULL);
- if (!status)
- /* Free the vsi_list resource that we allocated */
- status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type,
- ice_aqc_opc_free_res);
-
- devm_kfree(ice_hw_to_dev(hw), s_rule);
- return status;
-}
-
-/**
- * ice_handle_rem_vsi_list_mgmt
- * @hw: pointer to the hardware structure
- * @vsi_id: ID of the VSI to remove
- * @fm_list_itr: filter management entry for which the VSI list management
- * needs to be done
- */
-static enum ice_status
-ice_handle_rem_vsi_list_mgmt(struct ice_hw *hw, u16 vsi_id,
- struct ice_fltr_mgmt_list_entry *fm_list_itr)
-{
- struct ice_switch_info *sw = hw->switch_info;
- enum ice_status status = 0;
- enum ice_sw_lkup_type lkup_type;
- bool is_last_elem = true;
- bool conv_list = false;
- bool del_list = false;
- u16 vsi_list_id;
-
- lkup_type = fm_list_itr->fltr_info.lkup_type;
- vsi_list_id = fm_list_itr->fltr_info.fwd_id.vsi_list_id;
-
- if (fm_list_itr->vsi_count > 1) {
- status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id,
- true,
- ice_aqc_opc_update_sw_rules,
- lkup_type);
- if (status)
- return status;
- fm_list_itr->vsi_count--;
- is_last_elem = false;
- clear_bit(vsi_id, fm_list_itr->vsi_list_info->vsi_map);
- }
-
- /* For non-VLAN rules that forward packets to a VSI list, convert them
- * to forwarding packets to a VSI if there is only one VSI left in the
- * list. Unused lists are then removed.
- * VLAN rules need to use VSI lists even with only one VSI.
- */
- if (fm_list_itr->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST) {
- if (lkup_type == ICE_SW_LKUP_VLAN) {
- del_list = is_last_elem;
- } else if (fm_list_itr->vsi_count == 1) {
- conv_list = true;
- del_list = true;
- }
- }
-
- if (del_list) {
- /* Remove the VSI list since it is no longer used */
- struct ice_vsi_list_map_info *vsi_list_info =
- fm_list_itr->vsi_list_info;
-
- status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type);
- if (status)
- return status;
-
- if (conv_list) {
- u16 rem_vsi_id;
-
- rem_vsi_id = find_first_bit(vsi_list_info->vsi_map,
- ICE_MAX_VSI);
-
- /* Error out when the expected last element is not in
- * the VSI list map
- */
- if (rem_vsi_id == ICE_MAX_VSI)
- return ICE_ERR_OUT_OF_RANGE;
-
- /* Change the list entry action from VSI_LIST to VSI */
- fm_list_itr->fltr_info.fltr_act = ICE_FWD_TO_VSI;
- fm_list_itr->fltr_info.fwd_id.vsi_id = rem_vsi_id;
- }
-
- list_del(&vsi_list_info->list_entry);
- devm_kfree(ice_hw_to_dev(hw), vsi_list_info);
- fm_list_itr->vsi_list_info = NULL;
- }
-
- if (conv_list) {
- /* Convert the rule's forward action to forwarding packets to
- * a VSI
- */
- struct ice_aqc_sw_rules_elem *s_rule;
-
- s_rule = devm_kzalloc(ice_hw_to_dev(hw),
- ICE_SW_RULE_RX_TX_ETH_HDR_SIZE,
- GFP_KERNEL);
- if (!s_rule)
- return ICE_ERR_NO_MEMORY;
-
- ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule,
- ice_aqc_opc_update_sw_rules);
-
- s_rule->pdata.lkup_tx_rx.index =
- cpu_to_le16(fm_list_itr->fltr_info.fltr_rule_id);
-
- status = ice_aq_sw_rules(hw, s_rule,
- ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1,
- ice_aqc_opc_update_sw_rules, NULL);
- devm_kfree(ice_hw_to_dev(hw), s_rule);
- if (status)
- return status;
- }
-
- if (is_last_elem) {
- /* Remove the lookup rule */
- struct ice_aqc_sw_rules_elem *s_rule;
-
- s_rule = devm_kzalloc(ice_hw_to_dev(hw),
- ICE_SW_RULE_RX_TX_NO_HDR_SIZE,
- GFP_KERNEL);
- if (!s_rule)
- return ICE_ERR_NO_MEMORY;
-
- ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule,
- ice_aqc_opc_remove_sw_rules);
-
- status = ice_aq_sw_rules(hw, s_rule,
- ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1,
- ice_aqc_opc_remove_sw_rules, NULL);
- if (status)
- return status;
-
- /* Remove a book keeping entry from the MAC address list */
- mutex_lock(&sw->mac_list_lock);
- list_del(&fm_list_itr->list_entry);
- mutex_unlock(&sw->mac_list_lock);
- devm_kfree(ice_hw_to_dev(hw), fm_list_itr);
- devm_kfree(ice_hw_to_dev(hw), s_rule);
- }
- return status;
-}
-
-/**
- * ice_remove_mac_entry
- * @hw: pointer to the hardware structure
- * @f_entry: structure containing MAC forwarding information
- */
-static enum ice_status
-ice_remove_mac_entry(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
-{
- struct ice_fltr_mgmt_list_entry *m_entry;
- u16 vsi_id;
- u8 *add;
-
- add = &f_entry->fltr_info.l_data.mac.mac_addr[0];
-
- m_entry = ice_find_mac_entry(hw, add);
- if (!m_entry)
- return ICE_ERR_PARAM;
-
- vsi_id = f_entry->fltr_info.fwd_id.vsi_id;
- return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, m_entry);
-}
-
-/**
- * ice_remove_mac - remove a MAC address based filter rule
- * @hw: pointer to the hardware structure
- * @m_list: list of MAC addresses and forwarding information
+ * @em_list: list of ether type MAC filter, MAC is optional
*
- * This function removes either a MAC filter rule or a specific VSI from a
- * VSI list for a multicast MAC address.
- *
- * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by
- * ice_add_mac. Caller should be aware that this call will only work if all
- * the entries passed into m_list were added previously. It will not attempt to
- * do a partial remove of entries that were found.
+ * This function requires the caller to populate the entries in
+ * the filter list with the necessary fields (including flags to
+ * indicate Tx or Rx rules).
*/
enum ice_status
-ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
+ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list)
{
- struct ice_aqc_sw_rules_elem *s_rule, *r_iter;
- u8 s_rule_size = ICE_SW_RULE_RX_TX_NO_HDR_SIZE;
- struct ice_switch_info *sw = hw->switch_info;
- struct ice_fltr_mgmt_list_entry *m_entry;
- struct ice_fltr_list_entry *m_list_itr;
- u16 elem_sent, total_elem_left;
- enum ice_status status = 0;
- u16 num_unicast = 0;
+ struct ice_fltr_list_entry *em_list_itr;
- if (!m_list)
+ if (!em_list || !hw)
return ICE_ERR_PARAM;
- list_for_each_entry(m_list_itr, m_list, list_entry) {
- u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr;
+ list_for_each_entry(em_list_itr, em_list, list_entry) {
+ enum ice_sw_lkup_type l_type =
+ em_list_itr->fltr_info.lkup_type;
- if (is_unicast_ether_addr(addr) && !hw->ucast_shared)
- num_unicast++;
- else if (is_multicast_ether_addr(addr) ||
- (is_unicast_ether_addr(addr) && hw->ucast_shared))
- ice_remove_mac_entry(hw, m_list_itr);
+ if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC &&
+ l_type != ICE_SW_LKUP_ETHERTYPE)
+ return ICE_ERR_PARAM;
+
+ em_list_itr->status = ice_add_rule_internal(hw, l_type,
+ em_list_itr);
+ if (em_list_itr->status)
+ return em_list_itr->status;
}
-
- /* Exit if no unicast addresses found. Multicast switch rules
- * were added individually
- */
- if (!num_unicast)
- return 0;
-
- /* Allocate switch rule buffer for the bulk update for unicast */
- s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size,
- GFP_KERNEL);
- if (!s_rule)
- return ICE_ERR_NO_MEMORY;
-
- r_iter = s_rule;
- list_for_each_entry(m_list_itr, m_list, list_entry) {
- u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr;
-
- if (is_unicast_ether_addr(addr)) {
- m_entry = ice_find_mac_entry(hw, addr);
- if (!m_entry) {
- status = ICE_ERR_DOES_NOT_EXIST;
- goto ice_remove_mac_exit;
- }
-
- ice_fill_sw_rule(hw, &m_entry->fltr_info,
- r_iter, ice_aqc_opc_remove_sw_rules);
- r_iter = (struct ice_aqc_sw_rules_elem *)
- ((u8 *)r_iter + s_rule_size);
- }
- }
-
- /* Call AQ bulk switch rule update for all unicast addresses */
- r_iter = s_rule;
- /* Call AQ switch rule in AQ_MAX chunk */
- for (total_elem_left = num_unicast; total_elem_left > 0;
- total_elem_left -= elem_sent) {
- struct ice_aqc_sw_rules_elem *entry = r_iter;
-
- elem_sent = min(total_elem_left,
- (u16)(ICE_AQ_MAX_BUF_LEN / s_rule_size));
- status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size,
- elem_sent, ice_aqc_opc_remove_sw_rules,
- NULL);
- if (status)
- break;
- r_iter = (struct ice_aqc_sw_rules_elem *)
- ((u8 *)r_iter + s_rule_size);
- }
-
- list_for_each_entry(m_list_itr, m_list, list_entry) {
- u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr;
-
- if (is_unicast_ether_addr(addr)) {
- m_entry = ice_find_mac_entry(hw, addr);
- if (!m_entry)
- return ICE_ERR_OUT_OF_RANGE;
- mutex_lock(&sw->mac_list_lock);
- list_del(&m_entry->list_entry);
- mutex_unlock(&sw->mac_list_lock);
- devm_kfree(ice_hw_to_dev(hw), m_entry);
- }
- }
-
-ice_remove_mac_exit:
- devm_kfree(ice_hw_to_dev(hw), s_rule);
- return status;
+ return 0;
}
/**
- * ice_cfg_dflt_vsi - add filter rule to set/unset given VSI as default
- * VSI for the switch (represented by swid)
+ * ice_remove_eth_mac - Remove an ethertype (or MAC) based filter rule
* @hw: pointer to the hardware structure
- * @vsi_id: number of VSI to set as default
+ * @em_list: list of ethertype or ethertype MAC entries
+ */
+enum ice_status
+ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list)
+{
+ struct ice_fltr_list_entry *em_list_itr, *tmp;
+
+ if (!em_list || !hw)
+ return ICE_ERR_PARAM;
+
+ list_for_each_entry_safe(em_list_itr, tmp, em_list, list_entry) {
+ enum ice_sw_lkup_type l_type =
+ em_list_itr->fltr_info.lkup_type;
+
+ if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC &&
+ l_type != ICE_SW_LKUP_ETHERTYPE)
+ return ICE_ERR_PARAM;
+
+ em_list_itr->status = ice_remove_rule_internal(hw, l_type,
+ em_list_itr);
+ if (em_list_itr->status)
+ return em_list_itr->status;
+ }
+ return 0;
+}
+
+/**
+ * ice_rem_sw_rule_info
+ * @hw: pointer to the hardware structure
+ * @rule_head: pointer to the switch list structure that we want to delete
+ */
+static void
+ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head)
+{
+ if (!list_empty(rule_head)) {
+ struct ice_fltr_mgmt_list_entry *entry;
+ struct ice_fltr_mgmt_list_entry *tmp;
+
+ list_for_each_entry_safe(entry, tmp, rule_head, list_entry) {
+ list_del(&entry->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), entry);
+ }
+ }
+}
+
+/**
+ * ice_cfg_dflt_vsi - change state of VSI to set/clear default
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to set as default
* @set: true to add the above mentioned switch rule, false to remove it
* @direction: ICE_FLTR_RX or ICE_FLTR_TX
+ *
+ * add filter rule to set/unset given VSI as default VSI for the switch
+ * (represented by swid)
*/
enum ice_status
-ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction)
+ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction)
{
struct ice_aqc_sw_rules_elem *s_rule;
struct ice_fltr_info f_info;
enum ice_adminq_opc opcode;
enum ice_status status;
u16 s_rule_size;
+ u16 hw_vsi_id;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+ hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE :
ICE_SW_RULE_RX_TX_NO_HDR_SIZE;
@@ -1654,15 +2086,17 @@
f_info.lkup_type = ICE_SW_LKUP_DFLT;
f_info.flag = direction;
f_info.fltr_act = ICE_FWD_TO_VSI;
- f_info.fwd_id.vsi_id = vsi_id;
+ f_info.fwd_id.hw_vsi_id = hw_vsi_id;
if (f_info.flag & ICE_FLTR_RX) {
f_info.src = hw->port_info->lport;
+ f_info.src_id = ICE_SRC_ID_LPORT;
if (!set)
f_info.fltr_rule_id =
hw->port_info->dflt_rx_vsi_rule_id;
} else if (f_info.flag & ICE_FLTR_TX) {
- f_info.src = vsi_id;
+ f_info.src_id = ICE_SRC_ID_VSI;
+ f_info.src = hw_vsi_id;
if (!set)
f_info.fltr_rule_id =
hw->port_info->dflt_tx_vsi_rule_id;
@@ -1682,10 +2116,10 @@
u16 index = le16_to_cpu(s_rule->pdata.lkup_tx_rx.index);
if (f_info.flag & ICE_FLTR_TX) {
- hw->port_info->dflt_tx_vsi_num = vsi_id;
+ hw->port_info->dflt_tx_vsi_num = hw_vsi_id;
hw->port_info->dflt_tx_vsi_rule_id = index;
} else if (f_info.flag & ICE_FLTR_RX) {
- hw->port_info->dflt_rx_vsi_num = vsi_id;
+ hw->port_info->dflt_rx_vsi_num = hw_vsi_id;
hw->port_info->dflt_rx_vsi_rule_id = index;
}
} else {
@@ -1704,26 +2138,94 @@
}
/**
- * ice_remove_vlan_internal - Remove one VLAN based filter rule
+ * ice_find_ucast_rule_entry - Search for a unicast MAC filter rule entry
* @hw: pointer to the hardware structure
- * @f_entry: filter entry containing one VLAN information
+ * @recp_id: lookup type for which the specified rule needs to be searched
+ * @f_info: rule information
+ *
+ * Helper function to search for a unicast rule entry - this is to be used
+ * to remove unicast MAC filter that is not shared with other VSIs on the
+ * PF switch.
+ *
+ * Returns pointer to entry storing the rule if found
*/
-static enum ice_status
-ice_remove_vlan_internal(struct ice_hw *hw,
- struct ice_fltr_list_entry *f_entry)
+static struct ice_fltr_mgmt_list_entry *
+ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id,
+ struct ice_fltr_info *f_info)
{
- struct ice_fltr_info *new_fltr;
- struct ice_fltr_mgmt_list_entry *v_list_elem;
- u16 vsi_id;
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_mgmt_list_entry *list_itr;
+ struct list_head *list_head;
- new_fltr = &f_entry->fltr_info;
+ list_head = &sw->recp_list[recp_id].filt_rules;
+ list_for_each_entry(list_itr, list_head, list_entry) {
+ if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data,
+ sizeof(f_info->l_data)) &&
+ f_info->fwd_id.hw_vsi_id ==
+ list_itr->fltr_info.fwd_id.hw_vsi_id &&
+ f_info->flag == list_itr->fltr_info.flag)
+ return list_itr;
+ }
+ return NULL;
+}
- v_list_elem = ice_find_vlan_entry(hw, new_fltr->l_data.vlan.vlan_id);
- if (!v_list_elem)
+/**
+ * ice_remove_mac - remove a MAC address based filter rule
+ * @hw: pointer to the hardware structure
+ * @m_list: list of MAC addresses and forwarding information
+ *
+ * This function removes either a MAC filter rule or a specific VSI from a
+ * VSI list for a multicast MAC address.
+ *
+ * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by
+ * ice_add_mac. Caller should be aware that this call will only work if all
+ * the entries passed into m_list were added previously. It will not attempt to
+ * do a partial remove of entries that were found.
+ */
+enum ice_status
+ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
+{
+ struct ice_fltr_list_entry *list_itr, *tmp;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+
+ if (!m_list)
return ICE_ERR_PARAM;
- vsi_id = f_entry->fltr_info.fwd_id.vsi_id;
- return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, v_list_elem);
+ rule_lock = &hw->switch_info->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock;
+ list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) {
+ enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type;
+ u8 *add = &list_itr->fltr_info.l_data.mac.mac_addr[0];
+ u16 vsi_handle;
+
+ if (l_type != ICE_SW_LKUP_MAC)
+ return ICE_ERR_PARAM;
+
+ vsi_handle = list_itr->fltr_info.vsi_handle;
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ list_itr->fltr_info.fwd_id.hw_vsi_id =
+ ice_get_hw_vsi_num(hw, vsi_handle);
+ if (is_unicast_ether_addr(add) && !hw->ucast_shared) {
+ /* Don't remove the unicast address that belongs to
+ * another VSI on the switch, since it is not being
+ * shared...
+ */
+ mutex_lock(rule_lock);
+ if (!ice_find_ucast_rule_entry(hw, ICE_SW_LKUP_MAC,
+ &list_itr->fltr_info)) {
+ mutex_unlock(rule_lock);
+ return ICE_ERR_DOES_NOT_EXIST;
+ }
+ mutex_unlock(rule_lock);
+ }
+ list_itr->status = ice_remove_rule_internal(hw,
+ ICE_SW_LKUP_MAC,
+ list_itr);
+ if (list_itr->status)
+ return list_itr->status;
+ }
+ return 0;
}
/**
@@ -1734,131 +2236,456 @@
enum ice_status
ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list)
{
- struct ice_fltr_list_entry *v_list_itr;
- enum ice_status status = 0;
+ struct ice_fltr_list_entry *v_list_itr, *tmp;
if (!v_list || !hw)
return ICE_ERR_PARAM;
- list_for_each_entry(v_list_itr, v_list, list_entry) {
- status = ice_remove_vlan_internal(hw, v_list_itr);
- if (status) {
- v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL;
- return status;
- }
- v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS;
+ list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) {
+ enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type;
+
+ if (l_type != ICE_SW_LKUP_VLAN)
+ return ICE_ERR_PARAM;
+ v_list_itr->status = ice_remove_rule_internal(hw,
+ ICE_SW_LKUP_VLAN,
+ v_list_itr);
+ if (v_list_itr->status)
+ return v_list_itr->status;
}
- return status;
+ return 0;
+}
+
+/**
+ * ice_vsi_uses_fltr - Determine if given VSI uses specified filter
+ * @fm_entry: filter entry to inspect
+ * @vsi_handle: VSI handle to compare with filter info
+ */
+static bool
+ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle)
+{
+ return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI &&
+ fm_entry->fltr_info.vsi_handle == vsi_handle) ||
+ (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST &&
+ (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map))));
+}
+
+/**
+ * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to remove filters from
+ * @vsi_list_head: pointer to the list to add entry to
+ * @fi: pointer to fltr_info of filter entry to copy & add
+ *
+ * Helper function, used when creating a list of filters to remove from
+ * a specific VSI. The entry added to vsi_list_head is a COPY of the
+ * original filter entry, with the exception of fltr_info.fltr_act and
+ * fltr_info.fwd_id fields. These are set such that later logic can
+ * extract which VSI to remove the fltr from, and pass on that information.
+ */
+static enum ice_status
+ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle,
+ struct list_head *vsi_list_head,
+ struct ice_fltr_info *fi)
+{
+ struct ice_fltr_list_entry *tmp;
+
+ /* this memory is freed up in the caller function
+ * once filters for this VSI are removed
+ */
+ tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return ICE_ERR_NO_MEMORY;
+
+ tmp->fltr_info = *fi;
+
+ /* Overwrite these fields to indicate which VSI to remove filter from,
+ * so find and remove logic can extract the information from the
+ * list entries. Note that original entries will still have proper
+ * values.
+ */
+ tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ tmp->fltr_info.vsi_handle = vsi_handle;
+ tmp->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+
+ list_add(&tmp->list_entry, vsi_list_head);
+
+ return 0;
}
/**
* ice_add_to_vsi_fltr_list - Add VSI filters to the list
* @hw: pointer to the hardware structure
- * @vsi_id: ID of VSI to remove filters from
+ * @vsi_handle: VSI handle to remove filters from
* @lkup_list_head: pointer to the list that has certain lookup type filters
- * @vsi_list_head: pointer to the list pertaining to VSI with vsi_id
+ * @vsi_list_head: pointer to the list pertaining to VSI with vsi_handle
+ *
+ * Locates all filters in lkup_list_head that are used by the given VSI,
+ * and adds COPIES of those entries to vsi_list_head (intended to be used
+ * to remove the listed filters).
+ * Note that this means all entries in vsi_list_head must be explicitly
+ * deallocated by the caller when done with list.
*/
static enum ice_status
-ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id,
+ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle,
struct list_head *lkup_list_head,
struct list_head *vsi_list_head)
{
struct ice_fltr_mgmt_list_entry *fm_entry;
+ enum ice_status status = 0;
- /* check to make sure VSI id is valid and within boundary */
- if (vsi_id >=
- (sizeof(fm_entry->vsi_list_info->vsi_map) * BITS_PER_BYTE - 1))
+ /* check to make sure VSI ID is valid and within boundary */
+ if (!ice_is_vsi_valid(hw, vsi_handle))
return ICE_ERR_PARAM;
list_for_each_entry(fm_entry, lkup_list_head, list_entry) {
struct ice_fltr_info *fi;
fi = &fm_entry->fltr_info;
- if ((fi->fltr_act == ICE_FWD_TO_VSI &&
- fi->fwd_id.vsi_id == vsi_id) ||
- (fi->fltr_act == ICE_FWD_TO_VSI_LIST &&
- (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))) {
- struct ice_fltr_list_entry *tmp;
+ if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle))
+ continue;
- /* this memory is freed up in the caller function
- * ice_remove_vsi_lkup_fltr() once filters for
- * this VSI are removed
- */
- tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp),
- GFP_KERNEL);
- if (!tmp)
- return ICE_ERR_NO_MEMORY;
+ status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle,
+ vsi_list_head, fi);
+ if (status)
+ return status;
+ }
+ return status;
+}
- memcpy(&tmp->fltr_info, fi, sizeof(*fi));
+/**
+ * ice_determine_promisc_mask
+ * @fi: filter info to parse
+ *
+ * Helper function to determine which ICE_PROMISC_ mask corresponds
+ * to given filter into.
+ */
+static u8 ice_determine_promisc_mask(struct ice_fltr_info *fi)
+{
+ u16 vid = fi->l_data.mac_vlan.vlan_id;
+ u8 *macaddr = fi->l_data.mac.mac_addr;
+ bool is_tx_fltr = false;
+ u8 promisc_mask = 0;
- /* Expected below fields to be set to ICE_FWD_TO_VSI and
- * the particular VSI id since we are only removing this
- * one VSI
- */
- if (fi->fltr_act == ICE_FWD_TO_VSI_LIST) {
- tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
- tmp->fltr_info.fwd_id.vsi_id = vsi_id;
- }
+ if (fi->flag == ICE_FLTR_TX)
+ is_tx_fltr = true;
- list_add(&tmp->list_entry, vsi_list_head);
- }
+ if (is_broadcast_ether_addr(macaddr))
+ promisc_mask |= is_tx_fltr ?
+ ICE_PROMISC_BCAST_TX : ICE_PROMISC_BCAST_RX;
+ else if (is_multicast_ether_addr(macaddr))
+ promisc_mask |= is_tx_fltr ?
+ ICE_PROMISC_MCAST_TX : ICE_PROMISC_MCAST_RX;
+ else if (is_unicast_ether_addr(macaddr))
+ promisc_mask |= is_tx_fltr ?
+ ICE_PROMISC_UCAST_TX : ICE_PROMISC_UCAST_RX;
+ if (vid)
+ promisc_mask |= is_tx_fltr ?
+ ICE_PROMISC_VLAN_TX : ICE_PROMISC_VLAN_RX;
+
+ return promisc_mask;
+}
+
+/**
+ * ice_remove_promisc - Remove promisc based filter rules
+ * @hw: pointer to the hardware structure
+ * @recp_id: recipe ID for which the rule needs to removed
+ * @v_list: list of promisc entries
+ */
+static enum ice_status
+ice_remove_promisc(struct ice_hw *hw, u8 recp_id,
+ struct list_head *v_list)
+{
+ struct ice_fltr_list_entry *v_list_itr, *tmp;
+
+ list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) {
+ v_list_itr->status =
+ ice_remove_rule_internal(hw, recp_id, v_list_itr);
+ if (v_list_itr->status)
+ return v_list_itr->status;
}
return 0;
}
/**
+ * ice_clear_vsi_promisc - clear specified promiscuous mode(s) for given VSI
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to clear mode
+ * @promisc_mask: mask of promiscuous config bits to clear
+ * @vid: VLAN ID to clear VLAN promiscuous
+ */
+enum ice_status
+ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+ u16 vid)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_list_entry *fm_entry, *tmp;
+ struct list_head remove_list_head;
+ struct ice_fltr_mgmt_list_entry *itr;
+ struct list_head *rule_head;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
+ enum ice_status status = 0;
+ u8 recipe_id;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ if (vid)
+ recipe_id = ICE_SW_LKUP_PROMISC_VLAN;
+ else
+ recipe_id = ICE_SW_LKUP_PROMISC;
+
+ rule_head = &sw->recp_list[recipe_id].filt_rules;
+ rule_lock = &sw->recp_list[recipe_id].filt_rule_lock;
+
+ INIT_LIST_HEAD(&remove_list_head);
+
+ mutex_lock(rule_lock);
+ list_for_each_entry(itr, rule_head, list_entry) {
+ u8 fltr_promisc_mask = 0;
+
+ if (!ice_vsi_uses_fltr(itr, vsi_handle))
+ continue;
+
+ fltr_promisc_mask |=
+ ice_determine_promisc_mask(&itr->fltr_info);
+
+ /* Skip if filter is not completely specified by given mask */
+ if (fltr_promisc_mask & ~promisc_mask)
+ continue;
+
+ status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle,
+ &remove_list_head,
+ &itr->fltr_info);
+ if (status) {
+ mutex_unlock(rule_lock);
+ goto free_fltr_list;
+ }
+ }
+ mutex_unlock(rule_lock);
+
+ status = ice_remove_promisc(hw, recipe_id, &remove_list_head);
+
+free_fltr_list:
+ list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) {
+ list_del(&fm_entry->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), fm_entry);
+ }
+
+ return status;
+}
+
+/**
+ * ice_set_vsi_promisc - set given VSI to given promiscuous mode(s)
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to configure
+ * @promisc_mask: mask of promiscuous config bits
+ * @vid: VLAN ID to set VLAN promiscuous
+ */
+enum ice_status
+ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid)
+{
+ enum { UCAST_FLTR = 1, MCAST_FLTR, BCAST_FLTR };
+ struct ice_fltr_list_entry f_list_entry;
+ struct ice_fltr_info new_fltr;
+ enum ice_status status = 0;
+ bool is_tx_fltr;
+ u16 hw_vsi_id;
+ int pkt_type;
+ u8 recipe_id;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+ hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+
+ memset(&new_fltr, 0, sizeof(new_fltr));
+
+ if (promisc_mask & (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX)) {
+ new_fltr.lkup_type = ICE_SW_LKUP_PROMISC_VLAN;
+ new_fltr.l_data.mac_vlan.vlan_id = vid;
+ recipe_id = ICE_SW_LKUP_PROMISC_VLAN;
+ } else {
+ new_fltr.lkup_type = ICE_SW_LKUP_PROMISC;
+ recipe_id = ICE_SW_LKUP_PROMISC;
+ }
+
+ /* Separate filters must be set for each direction/packet type
+ * combination, so we will loop over the mask value, store the
+ * individual type, and clear it out in the input mask as it
+ * is found.
+ */
+ while (promisc_mask) {
+ u8 *mac_addr;
+
+ pkt_type = 0;
+ is_tx_fltr = false;
+
+ if (promisc_mask & ICE_PROMISC_UCAST_RX) {
+ promisc_mask &= ~ICE_PROMISC_UCAST_RX;
+ pkt_type = UCAST_FLTR;
+ } else if (promisc_mask & ICE_PROMISC_UCAST_TX) {
+ promisc_mask &= ~ICE_PROMISC_UCAST_TX;
+ pkt_type = UCAST_FLTR;
+ is_tx_fltr = true;
+ } else if (promisc_mask & ICE_PROMISC_MCAST_RX) {
+ promisc_mask &= ~ICE_PROMISC_MCAST_RX;
+ pkt_type = MCAST_FLTR;
+ } else if (promisc_mask & ICE_PROMISC_MCAST_TX) {
+ promisc_mask &= ~ICE_PROMISC_MCAST_TX;
+ pkt_type = MCAST_FLTR;
+ is_tx_fltr = true;
+ } else if (promisc_mask & ICE_PROMISC_BCAST_RX) {
+ promisc_mask &= ~ICE_PROMISC_BCAST_RX;
+ pkt_type = BCAST_FLTR;
+ } else if (promisc_mask & ICE_PROMISC_BCAST_TX) {
+ promisc_mask &= ~ICE_PROMISC_BCAST_TX;
+ pkt_type = BCAST_FLTR;
+ is_tx_fltr = true;
+ }
+
+ /* Check for VLAN promiscuous flag */
+ if (promisc_mask & ICE_PROMISC_VLAN_RX) {
+ promisc_mask &= ~ICE_PROMISC_VLAN_RX;
+ } else if (promisc_mask & ICE_PROMISC_VLAN_TX) {
+ promisc_mask &= ~ICE_PROMISC_VLAN_TX;
+ is_tx_fltr = true;
+ }
+
+ /* Set filter DA based on packet type */
+ mac_addr = new_fltr.l_data.mac.mac_addr;
+ if (pkt_type == BCAST_FLTR) {
+ eth_broadcast_addr(mac_addr);
+ } else if (pkt_type == MCAST_FLTR ||
+ pkt_type == UCAST_FLTR) {
+ /* Use the dummy ether header DA */
+ ether_addr_copy(mac_addr, dummy_eth_header);
+ if (pkt_type == MCAST_FLTR)
+ mac_addr[0] |= 0x1; /* Set multicast bit */
+ }
+
+ /* Need to reset this to zero for all iterations */
+ new_fltr.flag = 0;
+ if (is_tx_fltr) {
+ new_fltr.flag |= ICE_FLTR_TX;
+ new_fltr.src = hw_vsi_id;
+ } else {
+ new_fltr.flag |= ICE_FLTR_RX;
+ new_fltr.src = hw->port_info->lport;
+ }
+
+ new_fltr.fltr_act = ICE_FWD_TO_VSI;
+ new_fltr.vsi_handle = vsi_handle;
+ new_fltr.fwd_id.hw_vsi_id = hw_vsi_id;
+ f_list_entry.fltr_info = new_fltr;
+
+ status = ice_add_rule_internal(hw, recipe_id, &f_list_entry);
+ if (status)
+ goto set_promisc_exit;
+ }
+
+set_promisc_exit:
+ return status;
+}
+
+/**
+ * ice_set_vlan_vsi_promisc
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to configure
+ * @promisc_mask: mask of promiscuous config bits
+ * @rm_vlan_promisc: Clear VLANs VSI promisc mode
+ *
+ * Configure VSI with all associated VLANs to given promiscuous mode(s)
+ */
+enum ice_status
+ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+ bool rm_vlan_promisc)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ struct ice_fltr_list_entry *list_itr, *tmp;
+ struct list_head vsi_list_head;
+ struct list_head *vlan_head;
+ struct mutex *vlan_lock; /* Lock to protect filter rule list */
+ enum ice_status status;
+ u16 vlan_id;
+
+ INIT_LIST_HEAD(&vsi_list_head);
+ vlan_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock;
+ vlan_head = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rules;
+ mutex_lock(vlan_lock);
+ status = ice_add_to_vsi_fltr_list(hw, vsi_handle, vlan_head,
+ &vsi_list_head);
+ mutex_unlock(vlan_lock);
+ if (status)
+ goto free_fltr_list;
+
+ list_for_each_entry(list_itr, &vsi_list_head, list_entry) {
+ vlan_id = list_itr->fltr_info.l_data.vlan.vlan_id;
+ if (rm_vlan_promisc)
+ status = ice_clear_vsi_promisc(hw, vsi_handle,
+ promisc_mask, vlan_id);
+ else
+ status = ice_set_vsi_promisc(hw, vsi_handle,
+ promisc_mask, vlan_id);
+ if (status)
+ break;
+ }
+
+free_fltr_list:
+ list_for_each_entry_safe(list_itr, tmp, &vsi_list_head, list_entry) {
+ list_del(&list_itr->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), list_itr);
+ }
+ return status;
+}
+
+/**
* ice_remove_vsi_lkup_fltr - Remove lookup type filters for a VSI
* @hw: pointer to the hardware structure
- * @vsi_id: ID of VSI to remove filters from
+ * @vsi_handle: VSI handle to remove filters from
* @lkup: switch rule filter lookup type
*/
static void
-ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id,
+ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle,
enum ice_sw_lkup_type lkup)
{
struct ice_switch_info *sw = hw->switch_info;
struct ice_fltr_list_entry *fm_entry;
struct list_head remove_list_head;
+ struct list_head *rule_head;
struct ice_fltr_list_entry *tmp;
+ struct mutex *rule_lock; /* Lock to protect filter rule list */
enum ice_status status;
INIT_LIST_HEAD(&remove_list_head);
+ rule_lock = &sw->recp_list[lkup].filt_rule_lock;
+ rule_head = &sw->recp_list[lkup].filt_rules;
+ mutex_lock(rule_lock);
+ status = ice_add_to_vsi_fltr_list(hw, vsi_handle, rule_head,
+ &remove_list_head);
+ mutex_unlock(rule_lock);
+ if (status)
+ return;
+
switch (lkup) {
case ICE_SW_LKUP_MAC:
- mutex_lock(&sw->mac_list_lock);
- status = ice_add_to_vsi_fltr_list(hw, vsi_id,
- &sw->mac_list_head,
- &remove_list_head);
- mutex_unlock(&sw->mac_list_lock);
- if (!status) {
- ice_remove_mac(hw, &remove_list_head);
- goto free_fltr_list;
- }
+ ice_remove_mac(hw, &remove_list_head);
break;
case ICE_SW_LKUP_VLAN:
- mutex_lock(&sw->vlan_list_lock);
- status = ice_add_to_vsi_fltr_list(hw, vsi_id,
- &sw->vlan_list_head,
- &remove_list_head);
- mutex_unlock(&sw->vlan_list_lock);
- if (!status) {
- ice_remove_vlan(hw, &remove_list_head);
- goto free_fltr_list;
- }
+ ice_remove_vlan(hw, &remove_list_head);
+ break;
+ case ICE_SW_LKUP_PROMISC:
+ case ICE_SW_LKUP_PROMISC_VLAN:
+ ice_remove_promisc(hw, lkup, &remove_list_head);
break;
case ICE_SW_LKUP_MAC_VLAN:
case ICE_SW_LKUP_ETHERTYPE:
case ICE_SW_LKUP_ETHERTYPE_MAC:
- case ICE_SW_LKUP_PROMISC:
- case ICE_SW_LKUP_PROMISC_VLAN:
case ICE_SW_LKUP_DFLT:
- ice_debug(hw, ICE_DBG_SW,
- "Remove filters for this lookup type hasn't been implemented yet\n");
+ case ICE_SW_LKUP_LAST:
+ default:
+ ice_debug(hw, ICE_DBG_SW, "Unsupported lookup type %d\n", lkup);
break;
}
- return;
-free_fltr_list:
list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) {
list_del(&fm_entry->list_entry);
devm_kfree(ice_hw_to_dev(hw), fm_entry);
@@ -1868,16 +2695,121 @@
/**
* ice_remove_vsi_fltr - Remove all filters for a VSI
* @hw: pointer to the hardware structure
- * @vsi_id: ID of VSI to remove filters from
+ * @vsi_handle: VSI handle to remove filters from
*/
-void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id)
+void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle)
{
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_MAC_VLAN);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_VLAN);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_DFLT);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE_MAC);
- ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC_VLAN);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_MAC_VLAN);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_VLAN);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_DFLT);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_ETHERTYPE_MAC);
+ ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC_VLAN);
+}
+
+/**
+ * ice_replay_vsi_fltr - Replay filters for requested VSI
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: driver VSI handle
+ * @recp_id: Recipe ID for which rules need to be replayed
+ * @list_head: list for which filters need to be replayed
+ *
+ * Replays the filter of recipe recp_id for a VSI represented via vsi_handle.
+ * It is required to pass valid VSI handle.
+ */
+static enum ice_status
+ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id,
+ struct list_head *list_head)
+{
+ struct ice_fltr_mgmt_list_entry *itr;
+ enum ice_status status = 0;
+ u16 hw_vsi_id;
+
+ if (list_empty(list_head))
+ return status;
+ hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+
+ list_for_each_entry(itr, list_head, list_entry) {
+ struct ice_fltr_list_entry f_entry;
+
+ f_entry.fltr_info = itr->fltr_info;
+ if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN &&
+ itr->fltr_info.vsi_handle == vsi_handle) {
+ /* update the src in case it is VSI num */
+ if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI)
+ f_entry.fltr_info.src = hw_vsi_id;
+ status = ice_add_rule_internal(hw, recp_id, &f_entry);
+ if (status)
+ goto end;
+ continue;
+ }
+ if (!itr->vsi_list_info ||
+ !test_bit(vsi_handle, itr->vsi_list_info->vsi_map))
+ continue;
+ /* Clearing it so that the logic can add it back */
+ clear_bit(vsi_handle, itr->vsi_list_info->vsi_map);
+ f_entry.fltr_info.vsi_handle = vsi_handle;
+ f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI;
+ /* update the src in case it is VSI num */
+ if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI)
+ f_entry.fltr_info.src = hw_vsi_id;
+ if (recp_id == ICE_SW_LKUP_VLAN)
+ status = ice_add_vlan_internal(hw, &f_entry);
+ else
+ status = ice_add_rule_internal(hw, recp_id, &f_entry);
+ if (status)
+ goto end;
+ }
+end:
+ return status;
+}
+
+/**
+ * ice_replay_vsi_all_fltr - replay all filters stored in bookkeeping lists
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: driver VSI handle
+ *
+ * Replays filters for requested VSI via vsi_handle.
+ */
+enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ enum ice_status status = 0;
+ u8 i;
+
+ for (i = 0; i < ICE_SW_LKUP_LAST; i++) {
+ struct list_head *head;
+
+ head = &sw->recp_list[i].filt_replay_rules;
+ status = ice_replay_vsi_fltr(hw, vsi_handle, i, head);
+ if (status)
+ return status;
+ }
+ return status;
+}
+
+/**
+ * ice_rm_all_sw_replay_rule_info - deletes filter replay rules
+ * @hw: pointer to the HW struct
+ *
+ * Deletes the filter replay rules.
+ */
+void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw)
+{
+ struct ice_switch_info *sw = hw->switch_info;
+ u8 i;
+
+ if (!sw)
+ return;
+
+ for (i = 0; i < ICE_SW_LKUP_LAST; i++) {
+ if (!list_empty(&sw->recp_list[i].filt_replay_rules)) {
+ struct list_head *l_head;
+
+ l_head = &sw->recp_list[i].filt_replay_rules;
+ ice_rem_sw_rule_info(hw, l_head);
+ }
+ }
}
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 9b8ec12..cb123fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -8,7 +8,16 @@
#define ICE_SW_CFG_MAX_BUF_LEN 2048
#define ICE_DFLT_VSI_INVAL 0xff
+#define ICE_FLTR_RX BIT(0)
+#define ICE_FLTR_TX BIT(1)
+#define ICE_FLTR_TX_RX (ICE_FLTR_RX | ICE_FLTR_TX)
#define ICE_VSI_INVAL_ID 0xffff
+#define ICE_INVAL_Q_HANDLE 0xFFFF
+
+/* VSI queue context structure */
+struct ice_q_ctx {
+ u16 q_handle;
+};
/* VSI context structure for add/get/update/free operations */
struct ice_vsi_ctx {
@@ -17,7 +26,11 @@
u16 vsis_unallocated;
u16 flags;
struct ice_aqc_vsi_props info;
+ struct ice_sched_vsi_info sched;
u8 alloc_from_pool;
+ u8 vf_num;
+ u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS];
+ struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS];
};
enum ice_sw_fwd_act_type {
@@ -39,6 +52,15 @@
ICE_SW_LKUP_DFLT = 5,
ICE_SW_LKUP_ETHERTYPE_MAC = 8,
ICE_SW_LKUP_PROMISC_VLAN = 9,
+ ICE_SW_LKUP_LAST
+};
+
+/* type of filter src ID */
+enum ice_src_id {
+ ICE_SRC_ID_UNKNOWN = 0,
+ ICE_SRC_ID_VSI,
+ ICE_SRC_ID_QUEUE,
+ ICE_SRC_ID_LPORT,
};
struct ice_fltr_info {
@@ -49,12 +71,10 @@
/* rule ID returned by firmware once filter rule is created */
u16 fltr_rule_id;
u16 flag;
-#define ICE_FLTR_RX BIT(0)
-#define ICE_FLTR_TX BIT(1)
-#define ICE_FLTR_TX_RX (ICE_FLTR_RX | ICE_FLTR_TX)
/* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */
u16 src;
+ enum ice_src_id src_id;
union {
struct {
@@ -76,20 +96,27 @@
u16 ethertype;
u8 mac_addr[ETH_ALEN]; /* optional */
} ethertype_mac;
- } l_data;
+ } l_data; /* Make sure to zero out the memory of l_data before using
+ * it or only set the data associated with lookup match
+ * rest everything should be zero
+ */
/* Depending on filter action */
union {
- /* queue id in case of ICE_FWD_TO_Q and starting
- * queue id in case of ICE_FWD_TO_QGRP.
+ /* queue ID in case of ICE_FWD_TO_Q and starting
+ * queue ID in case of ICE_FWD_TO_QGRP.
*/
u16 q_id:11;
- u16 vsi_id:10;
+ u16 hw_vsi_id:10;
u16 vsi_list_id:10;
} fwd_id;
+ /* Sw VSI handle */
+ u16 vsi_handle;
+
/* Set to num_queues if action is ICE_FWD_TO_QGRP. This field
- * determines the range of queues the packet needs to be forwarded to
+ * determines the range of queues the packet needs to be forwarded to.
+ * Note that qgrp_size must be set to a power of 2.
*/
u8 qgrp_size;
@@ -98,32 +125,55 @@
u8 lan_en; /* Indicate if packet can be forwarded to the uplink */
};
-/* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list id */
+struct ice_sw_recipe {
+ struct list_head l_entry;
+
+ /* To protect modification of filt_rule list
+ * defined below
+ */
+ struct mutex filt_rule_lock;
+
+ /* List of type ice_fltr_mgmt_list_entry */
+ struct list_head filt_rules;
+ struct list_head filt_replay_rules;
+
+ /* linked list of type recipe_list_entry */
+ struct list_head rg_list;
+ /* linked list of type ice_sw_fv_list_entry*/
+ struct list_head fv_list;
+ struct ice_aqc_recipe_data_elem *r_buf;
+ u8 recp_count;
+ u8 root_rid;
+ u8 num_profs;
+ u8 *prof_ids;
+
+ /* recipe bitmap: what all recipes makes this recipe */
+ DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES);
+};
+
+/* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list ID */
struct ice_vsi_list_map_info {
struct list_head list_entry;
DECLARE_BITMAP(vsi_map, ICE_MAX_VSI);
u16 vsi_list_id;
-};
-
-enum ice_sw_fltr_status {
- ICE_FLTR_STATUS_NEW = 0,
- ICE_FLTR_STATUS_FW_SUCCESS,
- ICE_FLTR_STATUS_FW_FAIL,
+ /* counter to track how many rules are reusing this VSI list */
+ u16 ref_cnt;
};
struct ice_fltr_list_entry {
struct list_head list_entry;
- enum ice_sw_fltr_status status;
+ enum ice_status status;
struct ice_fltr_info fltr_info;
};
/* This defines an entry in the list that maintains MAC or VLAN membership
* to HW list mapping, since multiple VSIs can subscribe to the same MAC or
* VLAN. As an optimization the VSI list should be created only when a
- * second VSI becomes a subscriber to the VLAN address.
+ * second VSI becomes a subscriber to the same MAC address. VSI lists are always
+ * used for VLAN membership.
*/
struct ice_fltr_mgmt_list_entry {
- /* back pointer to VSI list id to VSI list mapping */
+ /* back pointer to VSI list ID to VSI list mapping */
struct ice_vsi_list_map_info *vsi_list_info;
u16 vsi_count;
#define ICE_INVAL_LG_ACT_INDEX 0xffff
@@ -136,26 +186,64 @@
u8 counter_index;
};
+enum ice_promisc_flags {
+ ICE_PROMISC_UCAST_RX = 0x1,
+ ICE_PROMISC_UCAST_TX = 0x2,
+ ICE_PROMISC_MCAST_RX = 0x4,
+ ICE_PROMISC_MCAST_TX = 0x8,
+ ICE_PROMISC_BCAST_RX = 0x10,
+ ICE_PROMISC_BCAST_TX = 0x20,
+ ICE_PROMISC_VLAN_RX = 0x40,
+ ICE_PROMISC_VLAN_TX = 0x80,
+};
+
/* VSI related commands */
enum ice_status
-ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
+ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
+ struct ice_sq_cd *cd);
+enum ice_status
+ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
+ bool keep_vsi_alloc, struct ice_sq_cd *cd);
+enum ice_status
+ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
struct ice_sq_cd *cd);
-enum ice_status
-ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
- struct ice_sq_cd *cd);
-enum ice_status
-ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
- bool keep_vsi_alloc, struct ice_sq_cd *cd);
-
+bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle);
+struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle);
+void ice_clear_all_vsi_ctx(struct ice_hw *hw);
+/* Switch config */
enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw);
/* Switch/bridge related commands */
+enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw);
enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst);
enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst);
-void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id);
-enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
-enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
enum ice_status
-ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction);
+ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list);
+enum ice_status
+ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list);
+void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle);
+enum ice_status
+ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
+enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
+
+/* Promisc/defport setup for VSIs */
+enum ice_status
+ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction);
+enum ice_status
+ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+ u16 vid);
+enum ice_status
+ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+ u16 vid);
+enum ice_status
+ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+ bool rm_vlan_promisc);
+
+enum ice_status ice_init_def_sw_recp(struct ice_hw *hw);
+u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle);
+bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle);
+
+enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle);
+void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw);
#endif /* _ICE_SWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 0c95c8f..33dd103 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -6,6 +6,7 @@
#include <linux/prefetch.h>
#include <linux/mm.h>
#include "ice.h"
+#include "ice_dcb_lib.h"
#define ICE_RX_HDR_SIZE 256
@@ -48,19 +49,17 @@
*/
void ice_clean_tx_ring(struct ice_ring *tx_ring)
{
- unsigned long size;
u16 i;
/* ring already cleared, nothing to do */
if (!tx_ring->tx_buf)
return;
- /* Free all the Tx ring sk_bufss */
+ /* Free all the Tx ring sk_buffs */
for (i = 0; i < tx_ring->count; i++)
ice_unmap_and_free_tx_buf(tx_ring, &tx_ring->tx_buf[i]);
- size = sizeof(struct ice_tx_buf) * tx_ring->count;
- memset(tx_ring->tx_buf, 0, size);
+ memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count);
/* Zero out the descriptor ring */
memset(tx_ring->desc, 0, tx_ring->size);
@@ -96,17 +95,16 @@
/**
* ice_clean_tx_irq - Reclaim resources after transmit completes
- * @vsi: the VSI we care about
* @tx_ring: Tx ring to clean
* @napi_budget: Used to determine if we are in netpoll
*
* Returns true if there's any budget left (e.g. the clean is finished)
*/
-static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring,
- int napi_budget)
+static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
{
unsigned int total_bytes = 0, total_pkts = 0;
- unsigned int budget = vsi->work_lmt;
+ unsigned int budget = ICE_DFLT_IRQ_WORK;
+ struct ice_vsi *vsi = tx_ring->vsi;
s16 i = tx_ring->next_to_clean;
struct ice_tx_desc *tx_desc;
struct ice_tx_buf *tx_buf;
@@ -115,6 +113,8 @@
tx_desc = ICE_TX_DESC(tx_ring, i);
i -= tx_ring->count;
+ prefetch(&vsi->state);
+
do {
struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;
@@ -207,7 +207,7 @@
smp_mb();
if (__netif_subqueue_stopped(tx_ring->netdev,
tx_ring->q_index) &&
- !test_bit(__ICE_DOWN, vsi->state)) {
+ !test_bit(__ICE_DOWN, vsi->state)) {
netif_wake_subqueue(tx_ring->netdev,
tx_ring->q_index);
++tx_ring->tx_stats.restart_q;
@@ -219,28 +219,28 @@
/**
* ice_setup_tx_ring - Allocate the Tx descriptors
- * @tx_ring: the tx ring to set up
+ * @tx_ring: the Tx ring to set up
*
* Return 0 on success, negative on error
*/
int ice_setup_tx_ring(struct ice_ring *tx_ring)
{
struct device *dev = tx_ring->dev;
- int bi_size;
if (!dev)
return -ENOMEM;
/* warn if we are about to overwrite the pointer */
WARN_ON(tx_ring->tx_buf);
- bi_size = sizeof(struct ice_tx_buf) * tx_ring->count;
- tx_ring->tx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+ tx_ring->tx_buf =
+ devm_kzalloc(dev, sizeof(*tx_ring->tx_buf) * tx_ring->count,
+ GFP_KERNEL);
if (!tx_ring->tx_buf)
return -ENOMEM;
- /* round up to nearest 4K */
- tx_ring->size = tx_ring->count * sizeof(struct ice_tx_desc);
- tx_ring->size = ALIGN(tx_ring->size, 4096);
+ /* round up to nearest page */
+ tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc),
+ PAGE_SIZE);
tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma,
GFP_KERNEL);
if (!tx_ring->desc) {
@@ -251,6 +251,7 @@
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
+ tx_ring->tx_stats.prev_pkt = -1;
return 0;
err:
@@ -266,7 +267,6 @@
void ice_clean_rx_ring(struct ice_ring *rx_ring)
{
struct device *dev = rx_ring->dev;
- unsigned long size;
u16 i;
/* ring already cleared, nothing to do */
@@ -284,15 +284,23 @@
if (!rx_buf->page)
continue;
- dma_unmap_page(dev, rx_buf->dma, PAGE_SIZE, DMA_FROM_DEVICE);
- __free_pages(rx_buf->page, 0);
+ /* Invalidate cache lines that may have been written to by
+ * device so that we avoid corrupting memory.
+ */
+ dma_sync_single_range_for_cpu(dev, rx_buf->dma,
+ rx_buf->page_offset,
+ ICE_RXBUF_2048, DMA_FROM_DEVICE);
+
+ /* free resources associated with mapping */
+ dma_unmap_page_attrs(dev, rx_buf->dma, PAGE_SIZE,
+ DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
rx_buf->page = NULL;
rx_buf->page_offset = 0;
}
- size = sizeof(struct ice_rx_buf) * rx_ring->count;
- memset(rx_ring->rx_buf, 0, size);
+ memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
/* Zero out the descriptor ring */
memset(rx_ring->desc, 0, rx_ring->size);
@@ -323,28 +331,28 @@
/**
* ice_setup_rx_ring - Allocate the Rx descriptors
- * @rx_ring: the rx ring to set up
+ * @rx_ring: the Rx ring to set up
*
* Return 0 on success, negative on error
*/
int ice_setup_rx_ring(struct ice_ring *rx_ring)
{
struct device *dev = rx_ring->dev;
- int bi_size;
if (!dev)
return -ENOMEM;
/* warn if we are about to overwrite the pointer */
WARN_ON(rx_ring->rx_buf);
- bi_size = sizeof(struct ice_rx_buf) * rx_ring->count;
- rx_ring->rx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+ rx_ring->rx_buf =
+ devm_kzalloc(dev, sizeof(*rx_ring->rx_buf) * rx_ring->count,
+ GFP_KERNEL);
if (!rx_ring->rx_buf)
return -ENOMEM;
- /* round up to nearest 4K */
- rx_ring->size = rx_ring->count * sizeof(union ice_32byte_rx_desc);
- rx_ring->size = ALIGN(rx_ring->size, 4096);
+ /* round up to nearest page */
+ rx_ring->size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
+ PAGE_SIZE);
rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma,
GFP_KERNEL);
if (!rx_ring->desc) {
@@ -370,18 +378,28 @@
*/
static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
{
+ u16 prev_ntu = rx_ring->next_to_use;
+
rx_ring->next_to_use = val;
/* update next to alloc since we have filled the ring */
rx_ring->next_to_alloc = val;
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch. (Only
- * applicable for weak-ordered memory model archs,
- * such as IA-64).
+ /* QRX_TAIL will be updated with any tail value, but hardware ignores
+ * the lower 3 bits. This makes it so we only bump tail on meaningful
+ * boundaries. Also, this allows us to bump tail on intervals of 8 up to
+ * the budget depending on the current traffic load.
*/
- wmb();
- writel(val, rx_ring->tail);
+ val &= ~0x7;
+ if (prev_ntu != val) {
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+ writel(val, rx_ring->tail);
+ }
}
/**
@@ -392,8 +410,8 @@
* Returns true if the page was successfully allocated or
* reused.
*/
-static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
- struct ice_rx_buf *bi)
+static bool
+ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi)
{
struct page *page = bi->page;
dma_addr_t dma;
@@ -412,7 +430,8 @@
}
/* map page for use */
- dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
+ DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
/* if mapping failed free memory back to system since
* there isn't much point in holding memory we can't use
@@ -426,6 +445,8 @@
bi->dma = dma;
bi->page = page;
bi->page_offset = 0;
+ page_ref_add(page, USHRT_MAX - 1);
+ bi->pagecnt_bias = USHRT_MAX;
return true;
}
@@ -435,7 +456,13 @@
* @rx_ring: ring to place buffers on
* @cleaned_count: number of buffers to replace
*
- * Returns false if all allocations were successful, true if any fail
+ * Returns false if all allocations were successful, true if any fail. Returning
+ * true signals to the caller that we didn't replace cleaned_count buffers and
+ * there is more work to do.
+ *
+ * First, try to clean "cleaned_count" Rx buffers. Then refill the cleaned Rx
+ * buffers. Then bump tail at most one time. Grouping like this lets us avoid
+ * multiple tail writes per call.
*/
bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
{
@@ -447,13 +474,20 @@
if (!rx_ring->netdev || !cleaned_count)
return false;
- /* get the RX descriptor and buffer based on next_to_use */
+ /* get the Rx descriptor and buffer based on next_to_use */
rx_desc = ICE_RX_DESC(rx_ring, ntu);
bi = &rx_ring->rx_buf[ntu];
do {
+ /* if we fail here, we have work remaining */
if (!ice_alloc_mapped_page(rx_ring, bi))
- goto no_bufs;
+ break;
+
+ /* sync the buffer for use by the device */
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+ bi->page_offset,
+ ICE_RXBUF_2048,
+ DMA_FROM_DEVICE);
/* Refresh the desc even if buffer_addrs didn't change
* because each write-back erases this info.
@@ -478,16 +512,7 @@
if (rx_ring->next_to_use != ntu)
ice_release_rx_desc(rx_ring, ntu);
- return false;
-
-no_bufs:
- if (rx_ring->next_to_use != ntu)
- ice_release_rx_desc(rx_ring, ntu);
-
- /* make sure to come back via polling to try again after
- * allocation failure
- */
- return true;
+ return !!cleaned_count;
}
/**
@@ -500,61 +525,43 @@
}
/**
- * ice_add_rx_frag - Add contents of Rx buffer to sk_buff
- * @rx_buf: buffer containing page to add
- * @rx_desc: descriptor containing length of buffer written by hardware
- * @skb: sk_buf to place the data into
+ * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse
+ * @rx_buf: Rx buffer to adjust
+ * @size: Size of adjustment
*
- * This function will add the data contained in rx_buf->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
- *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * Update the offset within page so that Rx buf will be ready to be reused.
+ * For systems with PAGE_SIZE < 8192 this function will flip the page offset
+ * so the second half of page assigned to Rx buffer will be used, otherwise
+ * the offset is moved by the @size bytes
*/
-static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
- union ice_32b_rx_flex_desc *rx_desc,
- struct sk_buff *skb)
+static void
+ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
{
#if (PAGE_SIZE < 8192)
- unsigned int truesize = ICE_RXBUF_2048;
+ /* flip page offset to other buffer */
+ rx_buf->page_offset ^= size;
#else
- unsigned int last_offset = PAGE_SIZE - ICE_RXBUF_2048;
- unsigned int truesize;
-#endif /* PAGE_SIZE < 8192) */
+ /* move offset up to the next cache line */
+ rx_buf->page_offset += size;
+#endif
+}
- struct page *page;
- unsigned int size;
-
- size = le16_to_cpu(rx_desc->wb.pkt_len) &
- ICE_RX_FLX_DESC_PKT_LEN_M;
-
- page = rx_buf->page;
-
+/**
+ * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
+ * @rx_buf: buffer containing the page
+ *
+ * If page is reusable, we have a green light for calling ice_reuse_rx_page,
+ * which will assign the current buffer to the buffer that next_to_alloc is
+ * pointing to; otherwise, the DMA mapping needs to be destroyed and
+ * page freed
+ */
+static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
+{
#if (PAGE_SIZE >= 8192)
- truesize = ALIGN(size, L1_CACHE_BYTES);
-#endif /* PAGE_SIZE >= 8192) */
-
- /* will the data fit in the skb we allocated? if so, just
- * copy it as it is pretty small anyway
- */
- if (size <= ICE_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
- unsigned char *va = page_address(page) + rx_buf->page_offset;
-
- memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
- /* page is not reserved, we can reuse buffer as-is */
- if (likely(!ice_page_is_reserved(page)))
- return true;
-
- /* this page cannot be reused so discard it */
- __free_pages(page, 0);
- return false;
- }
-
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- rx_buf->page_offset, size, truesize);
+ unsigned int last_offset = PAGE_SIZE - ICE_RXBUF_2048;
+#endif
+ unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
+ struct page *page = rx_buf->page;
/* avoid re-using remote pages */
if (unlikely(ice_page_is_reserved(page)))
@@ -562,36 +569,63 @@
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely(page_count(page) != 1))
+ if (unlikely((page_count(page) - pagecnt_bias) > 1))
return false;
-
- /* flip page offset to other buffer */
- rx_buf->page_offset ^= truesize;
#else
- /* move offset up to the next cache line */
- rx_buf->page_offset += truesize;
-
if (rx_buf->page_offset > last_offset)
return false;
#endif /* PAGE_SIZE < 8192) */
- /* Even if we own the page, we are not allowed to use atomic_set()
- * This would break get_page_unless_zero() users.
+ /* If we have drained the page fragment pool we need to update
+ * the pagecnt_bias and page count so that we fully restock the
+ * number of references the driver holds.
*/
- get_page(rx_buf->page);
+ if (unlikely(pagecnt_bias == 1)) {
+ page_ref_add(page, USHRT_MAX - 1);
+ rx_buf->pagecnt_bias = USHRT_MAX;
+ }
return true;
}
/**
+ * ice_add_rx_frag - Add contents of Rx buffer to sk_buff as a frag
+ * @rx_buf: buffer containing page to add
+ * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
+ *
+ * This function will add the data contained in rx_buf->page to the skb.
+ * It will just attach the page as a frag to the skb.
+ * The function will then update the page offset.
+ */
+static void
+ice_add_rx_frag(struct ice_rx_buf *rx_buf, struct sk_buff *skb,
+ unsigned int size)
+{
+#if (PAGE_SIZE >= 8192)
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#else
+ unsigned int truesize = ICE_RXBUF_2048;
+#endif
+
+ if (!size)
+ return;
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
+ rx_buf->page_offset, size, truesize);
+
+ /* page is being used so we must update the page offset */
+ ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+}
+
+/**
* ice_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
+ * @rx_ring: Rx descriptor ring to store buffers on
* @old_buf: donor buffer to have page reused
*
* Synchronizes page for reuse by the adapter
*/
-static void ice_reuse_rx_page(struct ice_ring *rx_ring,
- struct ice_rx_buf *old_buf)
+static void
+ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
{
u16 nta = rx_ring->next_to_alloc;
struct ice_rx_buf *new_buf;
@@ -602,121 +636,137 @@
nta++;
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
- /* transfer page from old buffer to new buffer */
- *new_buf = *old_buf;
+ /* Transfer page from old buffer to new buffer.
+ * Move each member individually to avoid possible store
+ * forwarding stalls and unnecessary copy of skb.
+ */
+ new_buf->dma = old_buf->dma;
+ new_buf->page = old_buf->page;
+ new_buf->page_offset = old_buf->page_offset;
+ new_buf->pagecnt_bias = old_buf->pagecnt_bias;
}
/**
- * ice_fetch_rx_buf - Allocate skb and populate it
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @skb: skb to be used
+ * @size: size of buffer to add to skb
*
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
*/
-static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring,
- union ice_32b_rx_flex_desc *rx_desc)
+static struct ice_rx_buf *
+ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
+ const unsigned int size)
{
struct ice_rx_buf *rx_buf;
- struct sk_buff *skb;
- struct page *page;
rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
- page = rx_buf->page;
- prefetchw(page);
+ prefetchw(rx_buf->page);
+ *skb = rx_buf->skb;
- skb = rx_buf->skb;
+ if (!size)
+ return rx_buf;
+ /* we are reusing so sync this buffer for CPU use */
+ dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
+ rx_buf->page_offset, size,
+ DMA_FROM_DEVICE);
- if (likely(!skb)) {
- u8 *page_addr = page_address(page) + rx_buf->page_offset;
+ /* We have pulled a buffer for use, so decrement pagecnt_bias */
+ rx_buf->pagecnt_bias--;
- /* prefetch first cache line of first page */
- prefetch(page_addr);
+ return rx_buf;
+}
+
+/**
+ * ice_construct_skb - Allocate skb and populate it
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buf: Rx buffer to pull data from
+ * @size: the length of the packet
+ *
+ * This function allocates an skb. It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
+ */
+static struct sk_buff *
+ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
+ unsigned int size)
+{
+ void *va = page_address(rx_buf->page) + rx_buf->page_offset;
+ unsigned int headlen;
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
#if L1_CACHE_BYTES < 128
- prefetch((void *)(page_addr + L1_CACHE_BYTES));
+ prefetch((u8 *)va + L1_CACHE_BYTES);
#endif /* L1_CACHE_BYTES */
- /* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- ICE_RX_HDR_SIZE,
- GFP_ATOMIC | __GFP_NOWARN);
- if (unlikely(!skb)) {
- rx_ring->rx_stats.alloc_buf_failed++;
- return NULL;
- }
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ return NULL;
- /* we will be copying header into skb->data in
- * pskb_may_pull so it is in our interest to prefetch
- * it now to avoid a possible cache miss
+ skb_record_rx_queue(skb, rx_ring->q_index);
+ /* Determine available headroom for copy */
+ headlen = size;
+ if (headlen > ICE_RX_HDR_SIZE)
+ headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE);
+
+ /* align pull length to size of long to optimize memcpy performance */
+ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+ /* if we exhaust the linear part then add what is left as a frag */
+ size -= headlen;
+ if (size) {
+#if (PAGE_SIZE >= 8192)
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#else
+ unsigned int truesize = ICE_RXBUF_2048;
+#endif
+ skb_add_rx_frag(skb, 0, rx_buf->page,
+ rx_buf->page_offset + headlen, size, truesize);
+ /* buffer is used by skb, update page_offset */
+ ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+ } else {
+ /* buffer is unused, reset bias back to rx_buf; data was copied
+ * onto skb's linear part so there's no need for adjusting
+ * page offset and we can reuse this buffer as-is
*/
- prefetchw(skb->data);
-
- skb_record_rx_queue(skb, rx_ring->q_index);
- } else {
- /* we are reusing so sync this buffer for CPU use */
- dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
- rx_buf->page_offset,
- ICE_RXBUF_2048,
- DMA_FROM_DEVICE);
-
- rx_buf->skb = NULL;
+ rx_buf->pagecnt_bias++;
}
- /* pull page into skb */
- if (ice_add_rx_frag(rx_buf, rx_desc, skb)) {
- /* hand second half of page back to the ring */
- ice_reuse_rx_page(rx_ring, rx_buf);
- rx_ring->rx_stats.page_reuse_count++;
- } else {
- /* we are not reusing the buffer so unmap it */
- dma_unmap_page(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
- DMA_FROM_DEVICE);
- }
-
- /* clear contents of buffer_info */
- rx_buf->page = NULL;
-
return skb;
}
/**
- * ice_pull_tail - ice specific version of skb_pull_tail
- * @skb: pointer to current skb being adjusted
+ * ice_put_rx_buf - Clean up used buffer and either recycle or free
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buf: Rx buffer to pull data from
*
- * This function is an ice specific version of __pskb_pull_tail. The
- * main difference between this version and the original function is that
- * this function can make several assumptions about the state of things
- * that allow for significant optimizations versus the standard function.
- * As a result we can do things like drop a frag and maintain an accurate
- * truesize for the skb.
+ * This function will clean up the contents of the rx_buf. It will
+ * either recycle the buffer or unmap it and free the associated resources.
*/
-static void ice_pull_tail(struct sk_buff *skb)
+static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
{
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
- unsigned int pull_len;
- unsigned char *va;
+ if (!rx_buf)
+ return;
- /* it is valid to use page_address instead of kmap since we are
- * working with pages allocated out of the lomem pool per
- * alloc_page(GFP_ATOMIC)
- */
- va = skb_frag_address(frag);
+ if (ice_can_reuse_rx_page(rx_buf)) {
+ /* hand second half of page back to the ring */
+ ice_reuse_rx_page(rx_ring, rx_buf);
+ rx_ring->rx_stats.page_reuse_count++;
+ } else {
+ /* we are not reusing the buffer so unmap it */
+ dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
+ DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
+ }
- /* we need the header to contain the greater of either ETH_HLEN or
- * 60 bytes if the skb->len is less than 60 for skb_pad.
- */
- pull_len = eth_get_headlen(va, ICE_RX_HDR_SIZE);
-
- /* align pull length to size of long to optimize memcpy performance */
- skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
-
- /* update all of the pointers */
- skb_frag_size_sub(frag, pull_len);
- frag->page_offset += pull_len;
- skb->data_len -= pull_len;
- skb->tail += pull_len;
+ /* clear contents of buffer_info */
+ rx_buf->page = NULL;
+ rx_buf->skb = NULL;
}
/**
@@ -733,10 +783,6 @@
*/
static bool ice_cleanup_headers(struct sk_buff *skb)
{
- /* place header in linear portion of buffer */
- if (skb_is_nonlinear(skb))
- ice_pull_tail(skb);
-
/* if eth_skb_pad returns an error the skb was freed */
if (eth_skb_pad(skb))
return true;
@@ -754,8 +800,8 @@
* The status_error_len doesn't need to be shifted because it begins
* at offset zero.
*/
-static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
- const u16 stat_err_bits)
+static bool
+ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, const u16 stat_err_bits)
{
return !!(rx_desc->wb.status_error0 &
cpu_to_le16(stat_err_bits));
@@ -767,14 +813,14 @@
* @rx_desc: Rx descriptor for current buffer
* @skb: Current socket buffer containing buffer in progress
*
- * This function updates next to clean. If the buffer is an EOP buffer
+ * This function updates next to clean. If the buffer is an EOP buffer
* this function exits returning false, otherwise it will place the
* sk_buff in the next buffer to be chained and return true indicating
* that this is in fact a non-EOP buffer.
*/
-static bool ice_is_non_eop(struct ice_ring *rx_ring,
- union ice_32b_rx_flex_desc *rx_desc,
- struct sk_buff *skb)
+static bool
+ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb)
{
u32 ntc = rx_ring->next_to_clean + 1;
@@ -834,15 +880,16 @@
/**
* ice_rx_csum - Indicate in skb if checksum is good
- * @vsi: the VSI we care about
+ * @ring: the ring we care about
* @skb: skb currently being received and modified
* @rx_desc: the receive descriptor
* @ptype: the packet type decoded by hardware
*
* skb->protocol must be set before this function is called
*/
-static void ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
- union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
+static void
+ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
+ union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
{
struct ice_rx_ptype_decoded decoded;
u32 rx_error, rx_status;
@@ -858,7 +905,7 @@
skb_checksum_none_assert(skb);
/* check if Rx checksum is enabled */
- if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+ if (!(ring->netdev->features & NETIF_F_RXCSUM))
return;
/* check if HW has decoded the packet and checksum */
@@ -898,12 +945,12 @@
return;
checksum_fail:
- vsi->back->hw_csum_rx_error++;
+ ring->vsi->back->hw_csum_rx_error++;
}
/**
* ice_process_skb_fields - Populate skb header fields from Rx descriptor
- * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_ring: Rx descriptor ring packet is being transacted on
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being populated
* @ptype: the packet type decoded by hardware
@@ -912,44 +959,44 @@
* order to populate the hash, checksum, VLAN, protocol, and
* other fields within the skb.
*/
-static void ice_process_skb_fields(struct ice_ring *rx_ring,
- union ice_32b_rx_flex_desc *rx_desc,
- struct sk_buff *skb, u8 ptype)
+static void
+ice_process_skb_fields(struct ice_ring *rx_ring,
+ union ice_32b_rx_flex_desc *rx_desc,
+ struct sk_buff *skb, u8 ptype)
{
ice_rx_hash(rx_ring, rx_desc, skb, ptype);
/* modifies the skb - consumes the enet header */
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
- ice_rx_csum(rx_ring->vsi, skb, rx_desc, ptype);
+ ice_rx_csum(rx_ring, skb, rx_desc, ptype);
}
/**
* ice_receive_skb - Send a completed packet up the stack
- * @rx_ring: rx ring in play
+ * @rx_ring: Rx ring in play
* @skb: packet to send up
- * @vlan_tag: vlan tag for packet
+ * @vlan_tag: VLAN tag for packet
*
* This function sends the completed packet (via. skb) up the stack using
- * gro receive functions (with/without vlan tag)
+ * gro receive functions (with/without VLAN tag)
*/
-static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
- u16 vlan_tag)
+static void
+ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
{
if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
- (vlan_tag & VLAN_VID_MASK)) {
+ (vlan_tag & VLAN_VID_MASK))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
- }
napi_gro_receive(&rx_ring->q_vector->napi, skb);
}
/**
* ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
- * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_ring: Rx descriptor ring to transact packets on
* @budget: Total limit on number of packets to process
*
* This function provides a "bounce buffer" approach to Rx interrupt
- * processing. The advantage to this is that on systems that have
+ * processing. The advantage to this is that on systems that have
* expensive overhead for IOMMU access this provides a means of avoiding
* it by maintaining the mapping of the page to the system.
*
@@ -959,24 +1006,19 @@
{
unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
- bool failure = false;
+ bool failure;
- /* start the loop to process RX packets bounded by 'budget' */
+ /* start the loop to process Rx packets bounded by 'budget' */
while (likely(total_rx_pkts < (unsigned int)budget)) {
union ice_32b_rx_flex_desc *rx_desc;
+ struct ice_rx_buf *rx_buf;
struct sk_buff *skb;
+ unsigned int size;
u16 stat_err_bits;
u16 vlan_tag = 0;
u8 rx_ptype;
- /* return some buffers to hardware, one at a time is too slow */
- if (cleaned_count >= ICE_RX_BUF_WRITE) {
- failure = failure ||
- ice_alloc_rx_bufs(rx_ring, cleaned_count);
- cleaned_count = 0;
- }
-
- /* get the RX desc from RX ring based on 'next_to_clean' */
+ /* get the Rx desc from Rx ring based on 'next_to_clean' */
rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
/* status_error_len will always be zero for unused descriptors
@@ -994,11 +1036,26 @@
*/
dma_rmb();
- /* allocate (if needed) and populate skb */
- skb = ice_fetch_rx_buf(rx_ring, rx_desc);
- if (!skb)
- break;
+ size = le16_to_cpu(rx_desc->wb.pkt_len) &
+ ICE_RX_FLX_DESC_PKT_LEN_M;
+ /* retrieve a buffer from the ring */
+ rx_buf = ice_get_rx_buf(rx_ring, &skb, size);
+
+ if (skb)
+ ice_add_rx_frag(rx_buf, skb, size);
+ else
+ skb = ice_construct_skb(rx_ring, rx_buf, size);
+
+ /* exit if we failed to retrieve a buffer */
+ if (!skb) {
+ rx_ring->rx_stats.alloc_buf_failed++;
+ if (rx_buf)
+ rx_buf->pagecnt_bias++;
+ break;
+ }
+
+ ice_put_rx_buf(rx_ring, rx_buf);
cleaned_count++;
/* skip if it is NOP desc */
@@ -1011,9 +1068,6 @@
continue;
}
- rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
- ICE_RX_FLEX_DESC_PTYPE_M;
-
stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S);
if (ice_test_staterr(rx_desc, stat_err_bits))
vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1);
@@ -1030,6 +1084,9 @@
total_rx_bytes += skb->len;
/* populate checksum, VLAN, and protocol */
+ rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+ ICE_RX_FLEX_DESC_PTYPE_M;
+
ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
/* send completed skb up the stack */
@@ -1039,6 +1096,9 @@
total_rx_pkts++;
}
+ /* return up to cleaned_count buffers to hardware */
+ failure = ice_alloc_rx_bufs(rx_ring, cleaned_count);
+
/* update queue and vector specific stats */
u64_stats_update_begin(&rx_ring->syncp);
rx_ring->stats.pkts += total_rx_pkts;
@@ -1052,6 +1112,357 @@
}
/**
+ * ice_adjust_itr_by_size_and_speed - Adjust ITR based on current traffic
+ * @port_info: port_info structure containing the current link speed
+ * @avg_pkt_size: average size of Tx or Rx packets based on clean routine
+ * @itr: ITR value to update
+ *
+ * Calculate how big of an increment should be applied to the ITR value passed
+ * in based on wmem_default, SKB overhead, Ethernet overhead, and the current
+ * link speed.
+ *
+ * The following is a calculation derived from:
+ * wmem_default / (size + overhead) = desired_pkts_per_int
+ * rate / bits_per_byte / (size + Ethernet overhead) = pkt_rate
+ * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
+ *
+ * Assuming wmem_default is 212992 and overhead is 640 bytes per
+ * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
+ * formula down to:
+ *
+ * wmem_default * bits_per_byte * usecs_per_sec pkt_size + 24
+ * ITR = -------------------------------------------- * --------------
+ * rate pkt_size + 640
+ */
+static unsigned int
+ice_adjust_itr_by_size_and_speed(struct ice_port_info *port_info,
+ unsigned int avg_pkt_size,
+ unsigned int itr)
+{
+ switch (port_info->phy.link_info.link_speed) {
+ case ICE_AQ_LINK_SPEED_100GB:
+ itr += DIV_ROUND_UP(17 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ case ICE_AQ_LINK_SPEED_50GB:
+ itr += DIV_ROUND_UP(34 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ case ICE_AQ_LINK_SPEED_40GB:
+ itr += DIV_ROUND_UP(43 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ case ICE_AQ_LINK_SPEED_25GB:
+ itr += DIV_ROUND_UP(68 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ case ICE_AQ_LINK_SPEED_20GB:
+ itr += DIV_ROUND_UP(85 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ case ICE_AQ_LINK_SPEED_10GB:
+ /* fall through */
+ default:
+ itr += DIV_ROUND_UP(170 * (avg_pkt_size + 24),
+ avg_pkt_size + 640);
+ break;
+ }
+
+ if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
+ itr &= ICE_ITR_ADAPTIVE_LATENCY;
+ itr += ICE_ITR_ADAPTIVE_MAX_USECS;
+ }
+
+ return itr;
+}
+
+/**
+ * ice_update_itr - update the adaptive ITR value based on statistics
+ * @q_vector: structure containing interrupt and ring information
+ * @rc: structure containing ring performance data
+ *
+ * Stores a new ITR value based on packets and byte
+ * counts during the last interrupt. The advantage of per interrupt
+ * computation is faster updates and more accurate ITR for the current
+ * traffic pattern. Constants in this function were computed
+ * based on theoretical maximum wire speed and thresholds were set based
+ * on testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ */
+static void
+ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
+{
+ unsigned long next_update = jiffies;
+ unsigned int packets, bytes, itr;
+ bool container_is_rx;
+
+ if (!rc->ring || !ITR_IS_DYNAMIC(rc->itr_setting))
+ return;
+
+ /* If itr_countdown is set it means we programmed an ITR within
+ * the last 4 interrupt cycles. This has a side effect of us
+ * potentially firing an early interrupt. In order to work around
+ * this we need to throw out any data received for a few
+ * interrupts following the update.
+ */
+ if (q_vector->itr_countdown) {
+ itr = rc->target_itr;
+ goto clear_counts;
+ }
+
+ container_is_rx = (&q_vector->rx == rc);
+ /* For Rx we want to push the delay up and default to low latency.
+ * for Tx we want to pull the delay down and default to high latency.
+ */
+ itr = container_is_rx ?
+ ICE_ITR_ADAPTIVE_MIN_USECS | ICE_ITR_ADAPTIVE_LATENCY :
+ ICE_ITR_ADAPTIVE_MAX_USECS | ICE_ITR_ADAPTIVE_LATENCY;
+
+ /* If we didn't update within up to 1 - 2 jiffies we can assume
+ * that either packets are coming in so slow there hasn't been
+ * any work, or that there is so much work that NAPI is dealing
+ * with interrupt moderation and we don't need to do anything.
+ */
+ if (time_after(next_update, rc->next_update))
+ goto clear_counts;
+
+ prefetch(q_vector->vsi->port_info);
+
+ packets = rc->total_pkts;
+ bytes = rc->total_bytes;
+
+ if (container_is_rx) {
+ /* If Rx there are 1 to 4 packets and bytes are less than
+ * 9000 assume insufficient data to use bulk rate limiting
+ * approach unless Tx is already in bulk rate limiting. We
+ * are likely latency driven.
+ */
+ if (packets && packets < 4 && bytes < 9000 &&
+ (q_vector->tx.target_itr & ICE_ITR_ADAPTIVE_LATENCY)) {
+ itr = ICE_ITR_ADAPTIVE_LATENCY;
+ goto adjust_by_size_and_speed;
+ }
+ } else if (packets < 4) {
+ /* If we have Tx and Rx ITR maxed and Tx ITR is running in
+ * bulk mode and we are receiving 4 or fewer packets just
+ * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so
+ * that the Rx can relax.
+ */
+ if (rc->target_itr == ICE_ITR_ADAPTIVE_MAX_USECS &&
+ (q_vector->rx.target_itr & ICE_ITR_MASK) ==
+ ICE_ITR_ADAPTIVE_MAX_USECS)
+ goto clear_counts;
+ } else if (packets > 32) {
+ /* If we have processed over 32 packets in a single interrupt
+ * for Tx assume we need to switch over to "bulk" mode.
+ */
+ rc->target_itr &= ~ICE_ITR_ADAPTIVE_LATENCY;
+ }
+
+ /* We have no packets to actually measure against. This means
+ * either one of the other queues on this vector is active or
+ * we are a Tx queue doing TSO with too high of an interrupt rate.
+ *
+ * Between 4 and 56 we can assume that our current interrupt delay
+ * is only slightly too low. As such we should increase it by a small
+ * fixed amount.
+ */
+ if (packets < 56) {
+ itr = rc->target_itr + ICE_ITR_ADAPTIVE_MIN_INC;
+ if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
+ itr &= ICE_ITR_ADAPTIVE_LATENCY;
+ itr += ICE_ITR_ADAPTIVE_MAX_USECS;
+ }
+ goto clear_counts;
+ }
+
+ if (packets <= 256) {
+ itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr);
+ itr &= ICE_ITR_MASK;
+
+ /* Between 56 and 112 is our "goldilocks" zone where we are
+ * working out "just right". Just report that our current
+ * ITR is good for us.
+ */
+ if (packets <= 112)
+ goto clear_counts;
+
+ /* If packet count is 128 or greater we are likely looking
+ * at a slight overrun of the delay we want. Try halving
+ * our delay to see if that will cut the number of packets
+ * in half per interrupt.
+ */
+ itr >>= 1;
+ itr &= ICE_ITR_MASK;
+ if (itr < ICE_ITR_ADAPTIVE_MIN_USECS)
+ itr = ICE_ITR_ADAPTIVE_MIN_USECS;
+
+ goto clear_counts;
+ }
+
+ /* The paths below assume we are dealing with a bulk ITR since
+ * number of packets is greater than 256. We are just going to have
+ * to compute a value and try to bring the count under control,
+ * though for smaller packet sizes there isn't much we can do as
+ * NAPI polling will likely be kicking in sooner rather than later.
+ */
+ itr = ICE_ITR_ADAPTIVE_BULK;
+
+adjust_by_size_and_speed:
+
+ /* based on checks above packets cannot be 0 so division is safe */
+ itr = ice_adjust_itr_by_size_and_speed(q_vector->vsi->port_info,
+ bytes / packets, itr);
+
+clear_counts:
+ /* write back value */
+ rc->target_itr = itr;
+
+ /* next update should occur within next jiffy */
+ rc->next_update = next_update + 1;
+
+ rc->total_bytes = 0;
+ rc->total_pkts = 0;
+}
+
+/**
+ * ice_buildreg_itr - build value for writing to the GLINT_DYN_CTL register
+ * @itr_idx: interrupt throttling index
+ * @itr: interrupt throttling value in usecs
+ */
+static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
+{
+ /* The ITR value is reported in microseconds, and the register value is
+ * recorded in 2 microsecond units. For this reason we only need to
+ * shift by the GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S to apply this
+ * granularity as a shift instead of division. The mask makes sure the
+ * ITR value is never odd so we don't accidentally write into the field
+ * prior to the ITR field.
+ */
+ itr &= ICE_ITR_MASK;
+
+ return GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+ (itr_idx << GLINT_DYN_CTL_ITR_INDX_S) |
+ (itr << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S));
+}
+
+/* The act of updating the ITR will cause it to immediately trigger. In order
+ * to prevent this from throwing off adaptive update statistics we defer the
+ * update so that it can only happen so often. So after either Tx or Rx are
+ * updated we make the adaptive scheme wait until either the ITR completely
+ * expires via the next_update expiration or we have been through at least
+ * 3 interrupts.
+ */
+#define ITR_COUNTDOWN_START 3
+
+/**
+ * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
+ * @q_vector: q_vector for which ITR is being updated and interrupt enabled
+ */
+static void ice_update_ena_itr(struct ice_q_vector *q_vector)
+{
+ struct ice_ring_container *tx = &q_vector->tx;
+ struct ice_ring_container *rx = &q_vector->rx;
+ struct ice_vsi *vsi = q_vector->vsi;
+ u32 itr_val;
+
+ /* when exiting WB_ON_ITR lets set a low ITR value and trigger
+ * interrupts to expire right away in case we have more work ready to go
+ * already
+ */
+ if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) {
+ itr_val = ice_buildreg_itr(rx->itr_idx, ICE_WB_ON_ITR_USECS);
+ wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val);
+ /* set target back to last user set value */
+ rx->target_itr = rx->itr_setting;
+ /* set current to what we just wrote and dynamic if needed */
+ rx->current_itr = ICE_WB_ON_ITR_USECS |
+ (rx->itr_setting & ICE_ITR_DYNAMIC);
+ /* allow normal interrupt flow to start */
+ q_vector->itr_countdown = 0;
+ return;
+ }
+
+ /* This will do nothing if dynamic updates are not enabled */
+ ice_update_itr(q_vector, tx);
+ ice_update_itr(q_vector, rx);
+
+ /* This block of logic allows us to get away with only updating
+ * one ITR value with each interrupt. The idea is to perform a
+ * pseudo-lazy update with the following criteria.
+ *
+ * 1. Rx is given higher priority than Tx if both are in same state
+ * 2. If we must reduce an ITR that is given highest priority.
+ * 3. We then give priority to increasing ITR based on amount.
+ */
+ if (rx->target_itr < rx->current_itr) {
+ /* Rx ITR needs to be reduced, this is highest priority */
+ itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
+ rx->current_itr = rx->target_itr;
+ q_vector->itr_countdown = ITR_COUNTDOWN_START;
+ } else if ((tx->target_itr < tx->current_itr) ||
+ ((rx->target_itr - rx->current_itr) <
+ (tx->target_itr - tx->current_itr))) {
+ /* Tx ITR needs to be reduced, this is second priority
+ * Tx ITR needs to be increased more than Rx, fourth priority
+ */
+ itr_val = ice_buildreg_itr(tx->itr_idx, tx->target_itr);
+ tx->current_itr = tx->target_itr;
+ q_vector->itr_countdown = ITR_COUNTDOWN_START;
+ } else if (rx->current_itr != rx->target_itr) {
+ /* Rx ITR needs to be increased, third priority */
+ itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
+ rx->current_itr = rx->target_itr;
+ q_vector->itr_countdown = ITR_COUNTDOWN_START;
+ } else {
+ /* Still have to re-enable the interrupts */
+ itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0);
+ if (q_vector->itr_countdown)
+ q_vector->itr_countdown--;
+ }
+
+ if (!test_bit(__ICE_DOWN, q_vector->vsi->state))
+ wr32(&q_vector->vsi->back->hw,
+ GLINT_DYN_CTL(q_vector->reg_idx),
+ itr_val);
+}
+
+/**
+ * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector
+ * @q_vector: q_vector to set WB_ON_ITR on
+ *
+ * We need to tell hardware to write-back completed descriptors even when
+ * interrupts are disabled. Descriptors will be written back on cache line
+ * boundaries without WB_ON_ITR enabled, but if we don't enable WB_ON_ITR
+ * descriptors may not be written back if they don't fill a cache line until the
+ * next interrupt.
+ *
+ * This sets the write-back frequency to 2 microseconds as that is the minimum
+ * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to
+ * make sure hardware knows we aren't meddling with the INTENA_M bit.
+ */
+static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
+{
+ struct ice_vsi *vsi = q_vector->vsi;
+
+ /* already in WB_ON_ITR mode no need to change it */
+ if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE)
+ return;
+
+ if (q_vector->num_ring_rx)
+ wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
+ ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
+ ICE_RX_ITR));
+
+ if (q_vector->num_ring_tx)
+ wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
+ ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
+ ICE_TX_ITR));
+
+ q_vector->itr_countdown = ICE_IN_WB_ON_ITR_MODE;
+}
+
+/**
* ice_napi_poll - NAPI polling Rx/Tx cleanup routine
* @napi: napi struct with our devices info in it
* @budget: amount of work driver is allowed to do this pass, in packets
@@ -1064,29 +1475,32 @@
{
struct ice_q_vector *q_vector =
container_of(napi, struct ice_q_vector, napi);
- struct ice_vsi *vsi = q_vector->vsi;
- struct ice_pf *pf = vsi->back;
bool clean_complete = true;
- int budget_per_ring = 0;
struct ice_ring *ring;
+ int budget_per_ring;
int work_done = 0;
/* Since the actual Tx work is minimal, we can give the Tx a larger
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
ice_for_each_ring(ring, q_vector->tx)
- if (!ice_clean_tx_irq(vsi, ring, budget))
+ if (!ice_clean_tx_irq(ring, budget))
clean_complete = false;
/* Handle case where we are called by netpoll with a budget of 0 */
- if (budget <= 0)
+ if (unlikely(budget <= 0))
return budget;
- /* We attempt to distribute budget to each Rx queue fairly, but don't
- * allow the budget to go below 1 because that would exit polling early.
- */
- if (q_vector->num_ring_rx)
+ /* normally we have 1 Rx ring per q_vector */
+ if (unlikely(q_vector->num_ring_rx > 1))
+ /* We attempt to distribute budget to each Rx queue fairly, but
+ * don't allow the budget to go below 1 because that would exit
+ * polling early.
+ */
budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
+ else
+ /* Max of 1 Rx ring in this q_vector so give it the budget */
+ budget_per_ring = budget;
ice_for_each_ring(ring, q_vector->rx) {
int cleaned;
@@ -1102,11 +1516,15 @@
if (!clean_complete)
return budget;
- /* Work is done so exit the polling mode and re-enable the interrupt */
- napi_complete_done(napi, work_done);
- if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
- ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
- return 0;
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ ice_update_ena_itr(q_vector);
+ else
+ ice_set_wb_on_itr(q_vector);
+
+ return min_t(int, work_done, budget - 1);
}
/* helper function for building cmd/type/offset */
@@ -1121,7 +1539,7 @@
}
/**
- * __ice_maybe_stop_tx - 2nd level check for tx stop conditions
+ * __ice_maybe_stop_tx - 2nd level check for Tx stop conditions
* @tx_ring: the ring to be checked
* @size: the size buffer we want to assure is available
*
@@ -1144,7 +1562,7 @@
}
/**
- * ice_maybe_stop_tx - 1st level check for tx stop conditions
+ * ice_maybe_stop_tx - 1st level check for Tx stop conditions
* @tx_ring: the ring to be checked
* @size: the size buffer we want to assure is available
*
@@ -1154,6 +1572,7 @@
{
if (likely(ICE_DESC_UNUSED(tx_ring) >= size))
return 0;
+
return __ice_maybe_stop_tx(tx_ring, size);
}
@@ -1173,7 +1592,7 @@
{
u64 td_offset, td_tag, td_cmd;
u16 i = tx_ring->next_to_use;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
unsigned int data_len, size;
struct ice_tx_desc *tx_desc;
struct ice_tx_buf *tx_buf;
@@ -1290,19 +1709,14 @@
ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return;
dma_error:
- /* clear dma mappings for failed tx_buf map */
+ /* clear DMA mappings for failed tx_buf map */
for (;;) {
tx_buf = &tx_ring->tx_buf[i];
ice_unmap_and_free_tx_buf(tx_ring, tx_buf);
@@ -1397,6 +1811,12 @@
offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
break;
case IPPROTO_SCTP:
+ /* enable SCTP checksum offload */
+ cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
+ l4_len = sizeof(struct sctphdr) >> 2;
+ offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+ break;
+
default:
if (first->tx_flags & ICE_TX_FLAGS_TSO)
return -1;
@@ -1410,7 +1830,7 @@
}
/**
- * ice_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * ice_tx_prepare_vlan_flags - prepare generic Tx VLAN tagging flags for HW
* @tx_ring: ring to send buffer on
* @first: pointer to struct ice_tx_buf
*
@@ -1436,7 +1856,7 @@
* to the encapsulated ethertype.
*/
skb->protocol = vlan_get_protocol(skb);
- goto out;
+ return 0;
}
/* if we have a HW VLAN tag being added, default to the HW one */
@@ -1458,8 +1878,7 @@
first->tx_flags |= ICE_TX_FLAGS_SW_VLAN;
}
-out:
- return 0;
+ return ice_tx_prepare_vlan_flags_dcb(tx_ring, first);
}
/**
@@ -1496,6 +1915,7 @@
if (err < 0)
return err;
+ /* cppcheck-suppress unreadVariable */
ip.hdr = skb_network_header(skb);
l4.hdr = skb_transport_header(skb);
@@ -1525,10 +1945,10 @@
cd_mss = skb_shinfo(skb)->gso_size;
/* record cdesc_qw1 with TSO parameters */
- off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX |
- (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
- (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
- (cd_mss << ICE_TXD_CTX_QW1_MSS_S);
+ off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+ (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
+ (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
+ (cd_mss << ICE_TXD_CTX_QW1_MSS_S));
first->tx_flags |= ICE_TX_FLAGS_TSO;
return 1;
}
@@ -1551,30 +1971,30 @@
* Finally, we add one to round up. Because 256 isn't an exact multiple of
* 3, we'll underestimate near each multiple of 12K. This is actually more
* accurate as we have 4K - 1 of wiggle room that we can fit into the last
- * segment. For our purposes this is accurate out to 1M which is orders of
+ * segment. For our purposes this is accurate out to 1M which is orders of
* magnitude greater than our largest possible GSO size.
*
* This would then be implemented as:
- * return (((size >> 12) * 85) >> 8) + 1;
+ * return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR;
*
* Since multiplication and division are commutative, we can reorder
* operations into:
- * return ((size * 85) >> 20) + 1;
+ * return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
*/
static unsigned int ice_txd_use_count(unsigned int size)
{
- return ((size * 85) >> 20) + 1;
+ return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
}
/**
- * ice_xmit_desc_count - calculate number of tx descriptors needed
+ * ice_xmit_desc_count - calculate number of Tx descriptors needed
* @skb: send buffer
*
* Returns number of data descriptors needed for this skb.
*/
static unsigned int ice_xmit_desc_count(struct sk_buff *skb)
{
- const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
unsigned int count = 0, size = skb_headlen(skb);
@@ -1605,7 +2025,7 @@
*/
static bool __ice_chk_linearize(struct sk_buff *skb)
{
- const struct skb_frag_struct *frag, *stale;
+ const skb_frag_t *frag, *stale;
int nr_frags, sum;
/* no need to check if number of frags is less than 7 */
@@ -1619,7 +2039,7 @@
nr_frags -= ICE_MAX_BUF_TXD - 2;
frag = &skb_shinfo(skb)->frags[0];
- /* Initialize size to the negative value of gso_size minus 1. We
+ /* Initialize size to the negative value of gso_size minus 1. We
* use this as the worst case scenerio in which the frag ahead
* of us only provides one byte which is why we are limited to 6
* descriptors for a single transmit as the header and previous
@@ -1687,6 +2107,7 @@
ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
{
struct ice_tx_offload_params offload = { 0 };
+ struct ice_vsi *vsi = tx_ring->vsi;
struct ice_tx_buf *first;
unsigned int count;
int tso, csum;
@@ -1705,7 +2126,8 @@
* + 1 desc for context descriptor,
* otherwise try next time
*/
- if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+ if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE +
+ ICE_DESCS_FOR_CTX_DESC)) {
tx_ring->tx_stats.tx_busy++;
return NETDEV_TX_BUSY;
}
@@ -1733,7 +2155,15 @@
if (csum < 0)
goto out_drop;
- if (tso || offload.cd_tunnel_params) {
+ /* allow CONTROL frames egress from main VSI if FW LLDP disabled */
+ if (unlikely(skb->priority == TC_PRIO_CONTROL &&
+ vsi->type == ICE_VSI_PF &&
+ vsi->port_info->is_sw_lldp))
+ offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+ ICE_TX_CTX_DESC_SWTCH_UPLINK <<
+ ICE_TXD_CTX_QW1_CMD_S);
+
+ if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
struct ice_tx_ctx_desc *cdesc;
int i = tx_ring->next_to_use;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 31bc998..94a9280 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -22,8 +22,21 @@
#define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */
#define ICE_MAX_TXQ_PER_TXQG 128
-/* Tx Descriptors needed, worst case */
-#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
+/* We are assuming that the cache line is always 64 Bytes here for ice.
+ * In order to make sure that is a correct assumption there is a check in probe
+ * to print a warning if the read from GLPCI_CNF2 tells us that the cache line
+ * size is 128 bytes. We do it this way because we do not want to read the
+ * GLPCI_CNF2 register or a variable containing the value on every pass through
+ * the Tx path.
+ */
+#define ICE_CACHE_LINE_BYTES 64
+#define ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \
+ sizeof(struct ice_tx_desc))
+#define ICE_DESCS_FOR_CTX_DESC 1
+#define ICE_DESCS_FOR_SKB_DATA_PTR 1
+/* Tx descriptors needed, worst case */
+#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \
+ ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR)
#define ICE_DESC_UNUSED(R) \
((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
(R)->next_to_clean - (R)->next_to_use - 1)
@@ -32,27 +45,32 @@
#define ICE_TX_FLAGS_HW_VLAN BIT(1)
#define ICE_TX_FLAGS_SW_VLAN BIT(2)
#define ICE_TX_FLAGS_VLAN_M 0xffff0000
+#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000
+#define ICE_TX_FLAGS_VLAN_PR_S 29
#define ICE_TX_FLAGS_VLAN_S 16
+#define ICE_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
struct ice_tx_buf {
struct ice_tx_desc *next_to_watch;
struct sk_buff *skb;
unsigned int bytecount;
unsigned short gso_segs;
u32 tx_flags;
- DEFINE_DMA_UNMAP_ADDR(dma);
DEFINE_DMA_UNMAP_LEN(len);
+ DEFINE_DMA_UNMAP_ADDR(dma);
};
struct ice_tx_offload_params {
- u8 header_len;
+ u64 cd_qw1;
+ struct ice_ring *tx_ring;
u32 td_cmd;
u32 td_offset;
u32 td_l2tag1;
- u16 cd_l2tag2;
u32 cd_tunnel_params;
- u64 cd_qw1;
- struct ice_ring *tx_ring;
+ u16 cd_l2tag2;
+ u8 header_len;
};
struct ice_rx_buf {
@@ -60,6 +78,7 @@
dma_addr_t dma;
struct page *page;
unsigned int page_offset;
+ u16 pagecnt_bias;
};
struct ice_q_stats {
@@ -71,6 +90,7 @@
u64 restart_q;
u64 tx_busy;
u64 tx_linearize;
+ int prev_pkt; /* negative if no pending Tx descriptors */
};
struct ice_rxq_stats {
@@ -102,11 +122,40 @@
/* indices into GLINT_ITR registers */
#define ICE_RX_ITR ICE_IDX_ITR0
#define ICE_TX_ITR ICE_IDX_ITR1
-#define ICE_ITR_DYNAMIC 0x8000 /* use top bit as a flag */
-#define ICE_ITR_8K 0x003E
+#define ICE_ITR_8K 124
+#define ICE_ITR_20K 50
+#define ICE_ITR_MAX 8160
+#define ICE_DFLT_TX_ITR (ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_DFLT_RX_ITR (ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_ITR_DYNAMIC 0x8000 /* used as flag for itr_setting */
+#define ITR_IS_DYNAMIC(setting) (!!((setting) & ICE_ITR_DYNAMIC))
+#define ITR_TO_REG(setting) ((setting) & ~ICE_ITR_DYNAMIC)
+#define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */
+#define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S)
+#define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */
+#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~ICE_ITR_MASK)
-/* apply ITR HW granularity translation to program the HW registers */
-#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> (itr_gran))
+#define ICE_ITR_ADAPTIVE_MIN_INC 0x0002
+#define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002
+#define ICE_ITR_ADAPTIVE_MAX_USECS 0x00FA
+#define ICE_ITR_ADAPTIVE_LATENCY 0x8000
+#define ICE_ITR_ADAPTIVE_BULK 0x0000
+
+#define ICE_DFLT_INTRL 0
+#define ICE_MAX_INTRL 236
+
+#define ICE_WB_ON_ITR_USECS 2
+#define ICE_IN_WB_ON_ITR_MODE 255
+/* Sets WB_ON_ITR and assumes INTENA bit is already cleared, which allows
+ * setting the MSK_M bit to tell hardware to ignore the INTENA_M bit. Also,
+ * set the write-back latency to the usecs passed in.
+ */
+#define ICE_GLINT_DYN_CTL_WB_ON_ITR(usecs, itr_idx) \
+ ((((usecs) << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)) & \
+ GLINT_DYN_CTL_INTERVAL_M) | \
+ (((itr_idx) << GLINT_DYN_CTL_ITR_INDX_S) & \
+ GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | \
+ GLINT_DYN_CTL_WB_ON_ITR_M)
/* Legacy or Advanced Mode Queue */
#define ICE_TX_ADVANCED 0
@@ -114,6 +163,7 @@
/* descriptor ring, associated with a VSI */
struct ice_ring {
+ /* CL1 - 1st cacheline starts here */
struct ice_ring *next; /* pointer to next ring in q_vector */
void *desc; /* Descriptor ring memory */
struct device *dev; /* Used for DMA mapping */
@@ -125,16 +175,11 @@
struct ice_tx_buf *tx_buf;
struct ice_rx_buf *rx_buf;
};
+ /* CL2 - 2nd cacheline starts here */
u16 q_index; /* Queue number of ring */
- u32 txq_teid; /* Added Tx queue TEID */
+ u16 q_handle; /* Queue handle per TC */
- /* high bit set means dynamic, use accessor routines to read/write.
- * hardware supports 2us/1us resolution for the ITR registers.
- * these values always store the USER setting, and must be converted
- * before programming to a register.
- */
- u16 rx_itr_setting;
- u16 tx_itr_setting;
+ u8 ring_active:1; /* is ring online or not */
u16 count; /* Number of descriptors */
u16 reg_idx; /* HW register index of the ring */
@@ -142,8 +187,7 @@
/* used in interrupt processing */
u16 next_to_use;
u16 next_to_clean;
-
- u8 ring_active; /* is ring online or not */
+ u16 next_to_alloc;
/* stats structs */
struct ice_q_stats stats;
@@ -153,26 +197,33 @@
struct ice_rxq_stats rx_stats;
};
- unsigned int size; /* length of descriptor ring in bytes */
- dma_addr_t dma; /* physical address of ring */
struct rcu_head rcu; /* to avoid race on free */
- u16 next_to_alloc;
+ /* CLX - the below items are only accessed infrequently and should be
+ * in their own cache line if possible
+ */
+ dma_addr_t dma; /* physical address of ring */
+ unsigned int size; /* length of descriptor ring in bytes */
+ u32 txq_teid; /* Added Tx queue TEID */
+ u16 rx_buf_len;
+#ifdef CONFIG_DCB
+ u8 dcb_tc; /* Traffic class of ring */
+#endif /* CONFIG_DCB */
} ____cacheline_internodealigned_in_smp;
-enum ice_latency_range {
- ICE_LOWEST_LATENCY = 0,
- ICE_LOW_LATENCY = 1,
- ICE_BULK_LATENCY = 2,
- ICE_ULTRA_LATENCY = 3,
-};
-
struct ice_ring_container {
- /* array of pointers to rings */
+ /* head of linked-list of rings */
struct ice_ring *ring;
+ unsigned long next_update; /* jiffies value of next queue update */
unsigned int total_bytes; /* total bytes processed this int */
unsigned int total_pkts; /* total packets processed this int */
- enum ice_latency_range latency_range;
- u16 itr;
+ u16 itr_idx; /* index in the interrupt vector */
+ u16 target_itr; /* value in usecs divided by the hw->itr_gran */
+ u16 current_itr; /* value in usecs divided by the hw->itr_gran */
+ /* high bit set means dynamic ITR, rest is used to store user
+ * readable ITR value in usecs and must be converted before programming
+ * to a register.
+ */
+ u16 itr_setting;
};
/* iterator for handling rings in ring container */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index ba11b58..6667d17 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -4,28 +4,35 @@
#ifndef _ICE_TYPE_H_
#define _ICE_TYPE_H_
+#define ICE_BYTES_PER_WORD 2
+#define ICE_BYTES_PER_DWORD 4
+
#include "ice_status.h"
#include "ice_hw_autogen.h"
#include "ice_osdep.h"
#include "ice_controlq.h"
#include "ice_lan_tx_rx.h"
+#include "ice_flex_type.h"
-#define ICE_BYTES_PER_WORD 2
-#define ICE_BYTES_PER_DWORD 4
-
-static inline bool ice_is_tc_ena(u8 bitmap, u8 tc)
+static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
{
- return test_bit(tc, (unsigned long *)&bitmap);
+ return test_bit(tc, &bitmap);
}
+/* Driver always calls main vsi_handle first */
+#define ICE_MAIN_VSI_HANDLE 0
+
/* debug masks - set these bits in hw->debug_mask to control output */
#define ICE_DBG_INIT BIT_ULL(1)
+#define ICE_DBG_FW_LOG BIT_ULL(3)
#define ICE_DBG_LINK BIT_ULL(4)
+#define ICE_DBG_PHY BIT_ULL(5)
#define ICE_DBG_QCTX BIT_ULL(6)
#define ICE_DBG_NVM BIT_ULL(7)
#define ICE_DBG_LAN BIT_ULL(8)
#define ICE_DBG_SW BIT_ULL(13)
#define ICE_DBG_SCHED BIT_ULL(14)
+#define ICE_DBG_PKG BIT_ULL(16)
#define ICE_DBG_RES BIT_ULL(17)
#define ICE_DBG_AQ_MSG BIT_ULL(24)
#define ICE_DBG_AQ_CMD BIT_ULL(27)
@@ -34,15 +41,28 @@
enum ice_aq_res_ids {
ICE_NVM_RES_ID = 1,
ICE_SPD_RES_ID,
- ICE_GLOBAL_CFG_LOCK_RES_ID,
- ICE_CHANGE_LOCK_RES_ID
+ ICE_CHANGE_LOCK_RES_ID,
+ ICE_GLOBAL_CFG_LOCK_RES_ID
};
+/* FW update timeout definitions are in milliseconds */
+#define ICE_NVM_TIMEOUT 180000
+#define ICE_CHANGE_LOCK_TIMEOUT 1000
+#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 3000
+
enum ice_aq_res_access_type {
ICE_RES_READ = 1,
ICE_RES_WRITE
};
+struct ice_driver_ver {
+ u8 major_ver;
+ u8 minor_ver;
+ u8 build_ver;
+ u8 subbuild_ver;
+ u8 driver_string[32];
+};
+
enum ice_fc_mode {
ICE_FC_NONE = 0,
ICE_FC_RX_PAUSE,
@@ -52,6 +72,13 @@
ICE_FC_DFLT
};
+enum ice_fec_mode {
+ ICE_FEC_NONE = 0,
+ ICE_FEC_RS,
+ ICE_FEC_BASER,
+ ICE_FEC_AUTO
+};
+
enum ice_set_fc_aq_failures {
ICE_SET_FC_AQ_FAIL_NONE = 0,
ICE_SET_FC_AQ_FAIL_GET,
@@ -76,11 +103,15 @@
enum ice_vsi_type {
ICE_VSI_PF = 0,
+ ICE_VSI_VF,
+ ICE_VSI_LB = 6,
};
struct ice_link_status {
/* Refer to ice_aq_phy_type for bits definition */
u64 phy_type_low;
+ u64 phy_type_high;
+ u8 topo_media_conflict;
u16 max_frame_size;
u16 link_speed;
u16 req_speeds;
@@ -88,6 +119,7 @@
u8 link_info;
u8 an_info;
u8 ext_info;
+ u8 fec_info;
u8 pacing;
/* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of
* ice_aqc_get_phy_caps structure
@@ -95,22 +127,37 @@
u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE];
};
+/* Different reset sources for which a disable queue AQ call has to be made in
+ * order to clean the Tx scheduler as a part of the reset
+ */
+enum ice_disq_rst_src {
+ ICE_NO_RESET = 0,
+ ICE_VM_RESET,
+ ICE_VF_RESET,
+};
+
/* PHY info such as phy_type, etc... */
struct ice_phy_info {
struct ice_link_status link_info;
struct ice_link_status link_info_old;
u64 phy_type_low;
+ u64 phy_type_high;
enum ice_media_type media_type;
u8 get_link_info;
};
/* Common HW capabilities for SW use */
struct ice_hw_common_caps {
- /* TX/RX queues */
- u16 num_rxq; /* Number/Total RX queues */
- u16 rxq_first_id; /* First queue ID for RX queues */
- u16 num_txq; /* Number/Total TX queues */
- u16 txq_first_id; /* First queue ID for TX queues */
+ u32 valid_functions;
+ /* DCB capabilities */
+ u32 active_tc_bitmap;
+ u32 maxtc;
+
+ /* Tx/Rx queues */
+ u16 num_rxq; /* Number/Total Rx queues */
+ u16 rxq_first_id; /* First queue ID for Rx queues */
+ u16 num_txq; /* Number/Total Tx queues */
+ u16 txq_first_id; /* First queue ID for Tx queues */
/* MSI-X vectors */
u16 num_msix_vectors;
@@ -119,20 +166,28 @@
/* Max MTU for function or device */
u16 max_mtu;
+ /* Virtualization support */
+ u8 sr_iov_1_1; /* SR-IOV enabled */
+
/* RSS related capabilities */
u16 rss_table_size; /* 512 for PFs and 64 for VFs */
u8 rss_table_entry_width; /* RSS Entry width in bits */
+
+ u8 dcb;
};
/* Function specific capabilities */
struct ice_hw_func_caps {
struct ice_hw_common_caps common_cap;
- u32 guaranteed_num_vsi;
+ u32 num_allocd_vfs; /* Number of allocated VFs */
+ u32 vf_base_id; /* Logical ID of the first VF */
+ u32 guar_num_vsi;
};
/* Device wide capabilities */
struct ice_hw_dev_caps {
struct ice_hw_common_caps common_cap;
+ u32 num_vfs_exposed; /* Total number of VFs exposed */
u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */
};
@@ -142,11 +197,18 @@
u8 perm_addr[ETH_ALEN];
};
-/* Various RESET request, These are not tied with HW reset types */
+/* Reset types used to determine which kind of reset was requested. These
+ * defines match what the RESET_TYPE field of the GLGEN_RSTAT register.
+ * ICE_RESET_PFR does not match any RESET_TYPE field in the GLGEN_RSTAT register
+ * because its reset source is different than the other types listed.
+ */
enum ice_reset_req {
- ICE_RESET_PFR = 0,
+ ICE_RESET_POR = 0,
+ ICE_RESET_INVAL = 0,
ICE_RESET_CORER = 1,
ICE_RESET_GLOBR = 2,
+ ICE_RESET_EMPR = 3,
+ ICE_RESET_PFR = 4,
};
/* Bus parameters */
@@ -170,17 +232,24 @@
u8 blank_nvm_mode; /* is NVM empty (no FW present) */
};
+#define ICE_NVM_VER_LEN 32
+
/* Max number of port to queue branches w.r.t topology */
#define ICE_MAX_TRAFFIC_CLASS 8
#define ICE_TXSCHED_MAX_BRANCHES ICE_MAX_TRAFFIC_CLASS
+#define ice_for_each_traffic_class(_i) \
+ for ((_i) = 0; (_i) < ICE_MAX_TRAFFIC_CLASS; (_i)++)
+
+#define ICE_INVAL_TEID 0xFFFFFFFF
+
struct ice_sched_node {
struct ice_sched_node *parent;
struct ice_sched_node *sibling; /* next sibling in the same layer */
struct ice_sched_node **children;
struct ice_aqc_txsched_elem_data info;
- u32 agg_id; /* aggregator group id */
- u16 vsi_id;
+ u32 agg_id; /* aggregator group ID */
+ u16 vsi_handle;
u8 in_use; /* suspended or in use */
u8 tx_sched_layer; /* Logical Layer (1-9) */
u8 num_children;
@@ -204,14 +273,14 @@
};
#define ICE_SCHED_DFLT_RL_PROF_ID 0
+#define ICE_SCHED_DFLT_BW_WT 1
-/* vsi type list entry to locate corresponding vsi/ag nodes */
+/* VSI type list entry to locate corresponding VSI/ag nodes */
struct ice_sched_vsi_info {
struct ice_sched_node *vsi_node[ICE_MAX_TRAFFIC_CLASS];
struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS];
struct list_head list_entry;
u16 max_lanq[ICE_MAX_TRAFFIC_CLASS];
- u16 vsi_id;
};
/* driver defines the policy */
@@ -221,15 +290,70 @@
u8 rdma_ena;
};
+/* CEE or IEEE 802.1Qaz ETS Configuration data */
+struct ice_dcb_ets_cfg {
+ u8 willing;
+ u8 cbs;
+ u8 maxtcs;
+ u8 prio_table[ICE_MAX_TRAFFIC_CLASS];
+ u8 tcbwtable[ICE_MAX_TRAFFIC_CLASS];
+ u8 tsatable[ICE_MAX_TRAFFIC_CLASS];
+};
+
+/* CEE or IEEE 802.1Qaz PFC Configuration data */
+struct ice_dcb_pfc_cfg {
+ u8 willing;
+ u8 mbc;
+ u8 pfccap;
+ u8 pfcena;
+};
+
+/* CEE or IEEE 802.1Qaz Application Priority data */
+struct ice_dcb_app_priority_table {
+ u16 prot_id;
+ u8 priority;
+ u8 selector;
+};
+
+#define ICE_MAX_USER_PRIORITY 8
+#define ICE_DCBX_MAX_APPS 32
+#define ICE_LLDPDU_SIZE 1500
+#define ICE_TLV_STATUS_OPER 0x1
+#define ICE_TLV_STATUS_SYNC 0x2
+#define ICE_TLV_STATUS_ERR 0x4
+#define ICE_APP_PROT_ID_FCOE 0x8906
+#define ICE_APP_PROT_ID_ISCSI 0x0cbc
+#define ICE_APP_PROT_ID_FIP 0x8914
+#define ICE_APP_SEL_ETHTYPE 0x1
+#define ICE_APP_SEL_TCPIP 0x2
+#define ICE_CEE_APP_SEL_ETHTYPE 0x0
+#define ICE_CEE_APP_SEL_TCPIP 0x1
+
+struct ice_dcbx_cfg {
+ u32 numapps;
+ u32 tlv_status; /* CEE mode TLV status */
+ struct ice_dcb_ets_cfg etscfg;
+ struct ice_dcb_ets_cfg etsrec;
+ struct ice_dcb_pfc_cfg pfc;
+ struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS];
+ u8 dcbx_mode;
+#define ICE_DCBX_MODE_CEE 0x1
+#define ICE_DCBX_MODE_IEEE 0x2
+ u8 app_mode;
+#define ICE_DCBX_APPS_NON_WILLING 0x1
+};
+
struct ice_port_info {
struct ice_sched_node *root; /* Root Node per Port */
- struct ice_hw *hw; /* back pointer to hw instance */
+ struct ice_hw *hw; /* back pointer to HW instance */
u32 last_node_teid; /* scheduler last node info */
u16 sw_id; /* Initial switch ID belongs to port */
u16 pf_vf_num;
u8 port_state;
#define ICE_SCHED_PORT_STATE_INIT 0x0
#define ICE_SCHED_PORT_STATE_READY 0x1
+ u8 lport;
+#define ICE_LPORT_MASK 0xff
u16 dflt_tx_vsi_rule_id;
u16 dflt_tx_vsi_num;
u16 dflt_rx_vsi_rule_id;
@@ -238,28 +362,39 @@
struct ice_mac_info mac;
struct ice_phy_info phy;
struct mutex sched_lock; /* protect access to TXSched tree */
- struct ice_sched_tx_policy sched_policy;
- struct list_head vsi_info_list;
- struct list_head agg_list; /* lists all aggregator */
- u8 lport;
-#define ICE_LPORT_MASK 0xff
- u8 is_vf;
+ struct ice_sched_node *
+ sib_head[ICE_MAX_TRAFFIC_CLASS][ICE_AQC_TOPO_MAX_LEVEL_NUM];
+ struct ice_dcbx_cfg local_dcbx_cfg; /* Oper/Local Cfg */
+ /* DCBX info */
+ struct ice_dcbx_cfg remote_dcbx_cfg; /* Peer Cfg */
+ struct ice_dcbx_cfg desired_dcbx_cfg; /* CEE Desired Cfg */
+ /* LLDP/DCBX Status */
+ u8 dcbx_status:3; /* see ICE_DCBX_STATUS_DIS */
+ u8 is_sw_lldp:1;
+ u8 is_vf:1;
};
struct ice_switch_info {
- /* Switch VSI lists to MAC/VLAN translation */
- struct mutex mac_list_lock; /* protect MAC list */
- struct list_head mac_list_head;
- struct mutex vlan_list_lock; /* protect VLAN list */
- struct list_head vlan_list_head;
- struct mutex eth_m_list_lock; /* protect ethtype list */
- struct list_head eth_m_list_head;
- struct mutex promisc_list_lock; /* protect promisc mode list */
- struct list_head promisc_list_head;
- struct mutex mac_vlan_list_lock; /* protect MAC-VLAN list */
- struct list_head mac_vlan_list_head;
-
struct list_head vsi_list_map_head;
+ struct ice_sw_recipe *recp_list;
+};
+
+/* FW logging configuration */
+struct ice_fw_log_evnt {
+ u8 cfg : 4; /* New event enables to configure */
+ u8 cur : 4; /* Current/active event enables */
+};
+
+struct ice_fw_log_cfg {
+ u8 cq_en : 1; /* FW logging is enabled via the control queue */
+ u8 uart_en : 1; /* FW logging is enabled via UART for all PFs */
+ u8 actv_evnts; /* Cumulation of currently enabled log events */
+
+#define ICE_FW_LOG_EVNT_INFO (ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S)
+#define ICE_FW_LOG_EVNT_INIT (ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S)
+#define ICE_FW_LOG_EVNT_FLOW (ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S)
+#define ICE_FW_LOG_EVNT_ERR (ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S)
+ struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX];
};
/* Port hardware description */
@@ -280,14 +415,18 @@
u8 pf_id; /* device profile info */
- /* TX Scheduler values */
+ /* Tx Scheduler values */
u16 num_tx_sched_layers;
u16 num_tx_sched_phys_layers;
u8 flattened_layers;
u8 max_cgds;
u8 sw_entry_point_layer;
+ u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM];
+ struct list_head agg_list; /* lists all aggregator */
+ struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI];
u8 evb_veb; /* true for VEB, false for VEPA */
+ u8 reset_ongoing; /* true if HW is in reset, false otherwise */
struct ice_bus_info bus;
struct ice_nvm_info nvm;
struct ice_hw_dev_caps dev_caps; /* device capabilities */
@@ -297,6 +436,7 @@
/* Control Queue info */
struct ice_ctl_q_info adminq;
+ struct ice_ctl_q_info mailboxq;
u8 api_branch; /* API branch version */
u8 api_maj_ver; /* API major version */
@@ -308,18 +448,53 @@
u8 fw_patch; /* firmware patch version */
u32 fw_build; /* firmware build number */
- /* minimum allowed value for different speeds */
-#define ICE_ITR_GRAN_MIN_200 1
-#define ICE_ITR_GRAN_MIN_100 1
-#define ICE_ITR_GRAN_MIN_50 2
-#define ICE_ITR_GRAN_MIN_25 4
+ struct ice_fw_log_cfg fw_log;
+
+/* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL
+ * register. Used for determining the ITR/intrl granularity during
+ * initialization.
+ */
+#define ICE_MAX_AGG_BW_200G 0x0
+#define ICE_MAX_AGG_BW_100G 0X1
+#define ICE_MAX_AGG_BW_50G 0x2
+#define ICE_MAX_AGG_BW_25G 0x3
+ /* ITR granularity for different speeds */
+#define ICE_ITR_GRAN_ABOVE_25 2
+#define ICE_ITR_GRAN_MAX_25 4
/* ITR granularity in 1 us */
- u8 itr_gran_200;
- u8 itr_gran_100;
- u8 itr_gran_50;
- u8 itr_gran_25;
+ u8 itr_gran;
+ /* INTRL granularity for different speeds */
+#define ICE_INTRL_GRAN_ABOVE_25 4
+#define ICE_INTRL_GRAN_MAX_25 8
+ /* INTRL granularity in 1 us */
+ u8 intrl_gran;
+
u8 ucast_shared; /* true if VSIs can share unicast addr */
+ /* Active package version (currently active) */
+ struct ice_pkg_ver active_pkg_ver;
+ u8 active_pkg_name[ICE_PKG_NAME_SIZE];
+ u8 active_pkg_in_nvm;
+
+ enum ice_aq_err pkg_dwnld_status;
+
+ /* Driver's package ver - (from the Metadata seg) */
+ struct ice_pkg_ver pkg_ver;
+ u8 pkg_name[ICE_PKG_NAME_SIZE];
+
+ /* Driver's Ice package version (from the Ice seg) */
+ struct ice_pkg_ver ice_pkg_ver;
+ u8 ice_pkg_name[ICE_PKG_NAME_SIZE];
+
+ /* Pointer to the ice segment */
+ struct ice_seg *seg;
+
+ /* Pointer to allocated copy of pkg memory */
+ u8 *pkg_copy;
+ u32 pkg_size;
+
+ /* HW block tables */
+ struct ice_blk_info blk[ICE_BLK_COUNT];
};
/* Statistics collected by each port, VSI, VEB, and S-channel */
@@ -354,6 +529,11 @@
u64 link_xoff_rx; /* lxoffrxc */
u64 link_xon_tx; /* lxontxc */
u64 link_xoff_tx; /* lxofftxc */
+ u64 priority_xon_rx[8]; /* pxonrxc[8] */
+ u64 priority_xoff_rx[8]; /* pxoffrxc[8] */
+ u64 priority_xon_tx[8]; /* pxontxc[8] */
+ u64 priority_xoff_tx[8]; /* pxofftxc[8] */
+ u64 priority_xon_2_xoff[8]; /* pxon2offc[8] */
u64 rx_size_64; /* prc64 */
u64 rx_size_127; /* prc127 */
u64 rx_size_255; /* prc255 */
@@ -391,4 +571,7 @@
#define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800
#define ICE_SR_WORDS_IN_1KB 512
+/* Hash redirection LUT for VSI - maximum array size */
+#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4)
+
#endif /* _ICE_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
new file mode 100644
index 0000000..b45797f
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -0,0 +1,3275 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_lib.h"
+
+/**
+ * ice_err_to_virt err - translate errors for VF return code
+ * @ice_err: error return code
+ */
+static enum virtchnl_status_code ice_err_to_virt_err(enum ice_status ice_err)
+{
+ switch (ice_err) {
+ case ICE_SUCCESS:
+ return VIRTCHNL_STATUS_SUCCESS;
+ case ICE_ERR_BAD_PTR:
+ case ICE_ERR_INVAL_SIZE:
+ case ICE_ERR_DEVICE_NOT_SUPPORTED:
+ case ICE_ERR_PARAM:
+ case ICE_ERR_CFG:
+ return VIRTCHNL_STATUS_ERR_PARAM;
+ case ICE_ERR_NO_MEMORY:
+ return VIRTCHNL_STATUS_ERR_NO_MEMORY;
+ case ICE_ERR_NOT_READY:
+ case ICE_ERR_RESET_FAILED:
+ case ICE_ERR_FW_API_VER:
+ case ICE_ERR_AQ_ERROR:
+ case ICE_ERR_AQ_TIMEOUT:
+ case ICE_ERR_AQ_FULL:
+ case ICE_ERR_AQ_NO_WORK:
+ case ICE_ERR_AQ_EMPTY:
+ return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+ default:
+ return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+ }
+}
+
+/**
+ * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF
+ * @pf: pointer to the PF structure
+ * @v_opcode: operation code
+ * @v_retval: return value
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ */
+static void
+ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode,
+ enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
+{
+ struct ice_hw *hw = &pf->hw;
+ struct ice_vf *vf = pf->vf;
+ int i;
+
+ for (i = 0; i < pf->num_alloc_vfs; i++, vf++) {
+ /* Not all vfs are enabled so skip the ones that are not */
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) &&
+ !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+ continue;
+
+ /* Ignore return value on purpose - a given VF may fail, but
+ * we need to keep going and send to all of them
+ */
+ ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg,
+ msglen, NULL);
+ }
+}
+
+/**
+ * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event
+ * @vf: pointer to the VF structure
+ * @pfe: pointer to the virtchnl_pf_event to set link speed/status for
+ * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_*
+ * @link_up: whether or not to set the link up/down
+ */
+static void
+ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe,
+ int ice_link_speed, bool link_up)
+{
+ if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) {
+ pfe->event_data.link_event_adv.link_status = link_up;
+ /* Speed in Mbps */
+ pfe->event_data.link_event_adv.link_speed =
+ ice_conv_link_speed_to_virtchnl(true, ice_link_speed);
+ } else {
+ pfe->event_data.link_event.link_status = link_up;
+ /* Legacy method for virtchnl link speeds */
+ pfe->event_data.link_event.link_speed =
+ (enum virtchnl_link_speed)
+ ice_conv_link_speed_to_virtchnl(false, ice_link_speed);
+ }
+}
+
+/**
+ * ice_set_pfe_link_forced - Force the virtchnl_pf_event link speed/status
+ * @vf: pointer to the VF structure
+ * @pfe: pointer to the virtchnl_pf_event to set link speed/status for
+ * @link_up: whether or not to set the link up/down
+ */
+static void
+ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe,
+ bool link_up)
+{
+ u16 link_speed;
+
+ if (link_up)
+ link_speed = ICE_AQ_LINK_SPEED_100GB;
+ else
+ link_speed = ICE_AQ_LINK_SPEED_UNKNOWN;
+
+ ice_set_pfe_link(vf, pfe, link_speed, link_up);
+}
+
+/**
+ * ice_vc_notify_vf_link_state - Inform a VF of link status
+ * @vf: pointer to the VF structure
+ *
+ * send a link status message to a single VF
+ */
+static void ice_vc_notify_vf_link_state(struct ice_vf *vf)
+{
+ struct virtchnl_pf_event pfe = { 0 };
+ struct ice_link_status *ls;
+ struct ice_pf *pf = vf->pf;
+ struct ice_hw *hw;
+
+ hw = &pf->hw;
+ ls = &hw->port_info->phy.link_info;
+
+ pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
+ pfe.severity = PF_EVENT_SEVERITY_INFO;
+
+ /* Always report link is down if the VF queues aren't enabled */
+ if (!vf->num_qs_ena)
+ ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false);
+ else if (vf->link_forced)
+ ice_set_pfe_link_forced(vf, &pfe, vf->link_up);
+ else
+ ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info &
+ ICE_AQ_LINK_UP);
+
+ ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+ VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
+ sizeof(pfe), NULL);
+}
+
+/**
+ * ice_free_vf_res - Free a VF's resources
+ * @vf: pointer to the VF info
+ */
+static void ice_free_vf_res(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ int i, last_vector_idx;
+
+ /* First, disable VF's configuration API to prevent OS from
+ * accessing the VF's VSI after it's freed or invalidated.
+ */
+ clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
+
+ /* free VSI and disconnect it from the parent uplink */
+ if (vf->lan_vsi_idx) {
+ ice_vsi_release(pf->vsi[vf->lan_vsi_idx]);
+ vf->lan_vsi_idx = 0;
+ vf->lan_vsi_num = 0;
+ vf->num_mac = 0;
+ }
+
+ last_vector_idx = vf->first_vector_idx + pf->num_vf_msix - 1;
+ /* Disable interrupts so that VF starts in a known state */
+ for (i = vf->first_vector_idx; i <= last_vector_idx; i++) {
+ wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M);
+ ice_flush(&pf->hw);
+ }
+ /* reset some of the state variables keeping track of the resources */
+ clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
+ clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
+}
+
+/**
+ * ice_dis_vf_mappings
+ * @vf: pointer to the VF structure
+ */
+static void ice_dis_vf_mappings(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ int first, last, v;
+ struct ice_hw *hw;
+
+ hw = &pf->hw;
+ vsi = pf->vsi[vf->lan_vsi_idx];
+
+ wr32(hw, VPINT_ALLOC(vf->vf_id), 0);
+ wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0);
+
+ first = vf->first_vector_idx;
+ last = first + pf->num_vf_msix - 1;
+ for (v = first; v <= last; v++) {
+ u32 reg;
+
+ reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) &
+ GLINT_VECT2FUNC_IS_PF_M) |
+ ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
+ GLINT_VECT2FUNC_PF_NUM_M));
+ wr32(hw, GLINT_VECT2FUNC(v), reg);
+ }
+
+ if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG)
+ wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0);
+ else
+ dev_err(&pf->pdev->dev,
+ "Scattered mode for VF Tx queues is not yet implemented\n");
+
+ if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG)
+ wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0);
+ else
+ dev_err(&pf->pdev->dev,
+ "Scattered mode for VF Rx queues is not yet implemented\n");
+}
+
+/**
+ * ice_sriov_free_msix_res - Reset/free any used MSIX resources
+ * @pf: pointer to the PF structure
+ *
+ * If MSIX entries from the pf->irq_tracker were needed then we need to
+ * reset the irq_tracker->end and give back the entries we needed to
+ * num_avail_sw_msix.
+ *
+ * If no MSIX entries were taken from the pf->irq_tracker then just clear
+ * the pf->sriov_base_vector.
+ *
+ * Returns 0 on success, and -EINVAL on error.
+ */
+static int ice_sriov_free_msix_res(struct ice_pf *pf)
+{
+ struct ice_res_tracker *res;
+
+ if (!pf)
+ return -EINVAL;
+
+ res = pf->irq_tracker;
+ if (!res)
+ return -EINVAL;
+
+ /* give back irq_tracker resources used */
+ if (pf->sriov_base_vector < res->num_entries) {
+ res->end = res->num_entries;
+ pf->num_avail_sw_msix +=
+ res->num_entries - pf->sriov_base_vector;
+ }
+
+ pf->sriov_base_vector = 0;
+
+ return 0;
+}
+
+/**
+ * ice_set_vf_state_qs_dis - Set VF queues state to disabled
+ * @vf: pointer to the VF structure
+ */
+void ice_set_vf_state_qs_dis(struct ice_vf *vf)
+{
+ /* Clear Rx/Tx enabled queues flag */
+ bitmap_zero(vf->txq_ena, ICE_MAX_BASE_QS_PER_VF);
+ bitmap_zero(vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF);
+ vf->num_qs_ena = 0;
+ clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+}
+
+/**
+ * ice_dis_vf_qs - Disable the VF queues
+ * @vf: pointer to the VF structure
+ */
+static void ice_dis_vf_qs(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+
+ ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
+ ice_vsi_stop_rx_rings(vsi);
+ ice_set_vf_state_qs_dis(vf);
+}
+
+/**
+ * ice_free_vfs - Free all VFs
+ * @pf: pointer to the PF structure
+ */
+void ice_free_vfs(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+ int tmp, i;
+
+ if (!pf->vf)
+ return;
+
+ while (test_and_set_bit(__ICE_VF_DIS, pf->state))
+ usleep_range(1000, 2000);
+
+ /* Avoid wait time by stopping all VFs at the same time */
+ for (i = 0; i < pf->num_alloc_vfs; i++)
+ if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[i].vf_states))
+ ice_dis_vf_qs(&pf->vf[i]);
+
+ /* Disable IOV before freeing resources. This lets any VF drivers
+ * running in the host get themselves cleaned up before we yank
+ * the carpet out from underneath their feet.
+ */
+ if (!pci_vfs_assigned(pf->pdev))
+ pci_disable_sriov(pf->pdev);
+ else
+ dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
+
+ tmp = pf->num_alloc_vfs;
+ pf->num_vf_qps = 0;
+ pf->num_alloc_vfs = 0;
+ for (i = 0; i < tmp; i++) {
+ if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) {
+ /* disable VF qp mappings */
+ ice_dis_vf_mappings(&pf->vf[i]);
+ ice_free_vf_res(&pf->vf[i]);
+ }
+ }
+
+ if (ice_sriov_free_msix_res(pf))
+ dev_err(&pf->pdev->dev,
+ "Failed to free MSIX resources used by SR-IOV\n");
+
+ devm_kfree(&pf->pdev->dev, pf->vf);
+ pf->vf = NULL;
+
+ /* This check is for when the driver is unloaded while VFs are
+ * assigned. Setting the number of VFs to 0 through sysfs is caught
+ * before this function ever gets called.
+ */
+ if (!pci_vfs_assigned(pf->pdev)) {
+ int vf_id;
+
+ /* Acknowledge VFLR for all VFs. Without this, VFs will fail to
+ * work correctly when SR-IOV gets re-enabled.
+ */
+ for (vf_id = 0; vf_id < tmp; vf_id++) {
+ u32 reg_idx, bit_idx;
+
+ reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32;
+ bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32;
+ wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
+ }
+ }
+ clear_bit(__ICE_VF_DIS, pf->state);
+ clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags);
+}
+
+/**
+ * ice_trigger_vf_reset - Reset a VF on HW
+ * @vf: pointer to the VF structure
+ * @is_vflr: true if VFLR was issued, false if not
+ * @is_pfr: true if the reset was triggered due to a previous PFR
+ *
+ * Trigger hardware to start a reset for a particular VF. Expects the caller
+ * to wait the proper amount of time to allow hardware to reset the VF before
+ * it cleans up and restores VF functionality.
+ */
+static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
+{
+ struct ice_pf *pf = vf->pf;
+ u32 reg, reg_idx, bit_idx;
+ struct ice_hw *hw;
+ int vf_abs_id, i;
+
+ hw = &pf->hw;
+ vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id;
+
+ /* Inform VF that it is no longer active, as a warning */
+ clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
+
+ /* Disable VF's configuration API during reset. The flag is re-enabled
+ * in ice_alloc_vf_res(), when it's safe again to access VF's VSI.
+ * It's normally disabled in ice_free_vf_res(), but it's safer
+ * to do it earlier to give some time to finish to any VF config
+ * functions that may still be running at this point.
+ */
+ clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
+
+ /* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it
+ * in the case of VFR. If this is done for PFR, it can mess up VF
+ * resets because the VF driver may already have started cleanup
+ * by the time we get here.
+ */
+ if (!is_pfr)
+ wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0);
+
+ /* In the case of a VFLR, the HW has already reset the VF and we
+ * just need to clean up, so don't hit the VFRTRIG register.
+ */
+ if (!is_vflr) {
+ /* reset VF using VPGEN_VFRTRIG reg */
+ reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
+ reg |= VPGEN_VFRTRIG_VFSWR_M;
+ wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
+ }
+ /* clear the VFLR bit in GLGEN_VFLRSTAT */
+ reg_idx = (vf_abs_id) / 32;
+ bit_idx = (vf_abs_id) % 32;
+ wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
+ ice_flush(hw);
+
+ wr32(hw, PF_PCI_CIAA,
+ VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S));
+ for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) {
+ reg = rd32(hw, PF_PCI_CIAD);
+ /* no transactions pending so stop polling */
+ if ((reg & VF_TRANS_PENDING_M) == 0)
+ break;
+
+ dev_err(&pf->pdev->dev,
+ "VF %d PCI transactions stuck\n", vf->vf_id);
+ udelay(ICE_PCI_CIAD_WAIT_DELAY_US);
+ }
+}
+
+/**
+ * ice_vsi_set_pvid_fill_ctxt - Set VSI ctxt for add PVID
+ * @ctxt: the VSI ctxt to fill
+ * @vid: the VLAN ID to set as a PVID
+ */
+static void ice_vsi_set_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt, u16 vid)
+{
+ ctxt->info.vlan_flags = (ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
+ ICE_AQ_VSI_PVLAN_INSERT_PVID |
+ ICE_AQ_VSI_VLAN_EMOD_STR);
+ ctxt->info.pvid = cpu_to_le16(vid);
+ ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+ ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID |
+ ICE_AQ_VSI_PROP_SW_VALID);
+}
+
+/**
+ * ice_vsi_kill_pvid_fill_ctxt - Set VSI ctx for remove PVID
+ * @ctxt: the VSI ctxt to fill
+ */
+static void ice_vsi_kill_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt)
+{
+ ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
+ ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
+ ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+ ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID |
+ ICE_AQ_VSI_PROP_SW_VALID);
+}
+
+/**
+ * ice_vsi_manage_pvid - Enable or disable port VLAN for VSI
+ * @vsi: the VSI to update
+ * @vid: the VLAN ID to set as a PVID
+ * @enable: true for enable PVID false for disable
+ */
+static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable)
+{
+ struct device *dev = &vsi->back->pdev->dev;
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx *ctxt;
+ enum ice_status status;
+ int ret = 0;
+
+ ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+ if (!ctxt)
+ return -ENOMEM;
+
+ ctxt->info = vsi->info;
+ if (enable)
+ ice_vsi_set_pvid_fill_ctxt(ctxt, vid);
+ else
+ ice_vsi_kill_pvid_fill_ctxt(ctxt);
+
+ status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+ if (status) {
+ dev_info(dev, "update VSI for port VLAN failed, err %d aq_err %d\n",
+ status, hw->adminq.sq_last_status);
+ ret = -EIO;
+ goto out;
+ }
+
+ vsi->info = ctxt->info;
+out:
+ devm_kfree(dev, ctxt);
+ return ret;
+}
+
+/**
+ * ice_vf_vsi_setup - Set up a VF VSI
+ * @pf: board private structure
+ * @pi: pointer to the port_info instance
+ * @vf_id: defines VF ID to which this VSI connects.
+ *
+ * Returns pointer to the successfully allocated VSI struct on success,
+ * otherwise returns NULL on failure.
+ */
+static struct ice_vsi *
+ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id)
+{
+ return ice_vsi_setup(pf, pi, ICE_VSI_VF, vf_id);
+}
+
+/**
+ * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space
+ * @pf: pointer to PF structure
+ * @vf: pointer to VF that the first MSIX vector index is being calculated for
+ *
+ * This returns the first MSIX vector index in PF space that is used by this VF.
+ * This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration will have to increment by
+ * 1 to avoid meddling with the OICR index.
+ */
+static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
+{
+ return pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix;
+}
+
+/**
+ * ice_alloc_vsi_res - Setup VF VSI and its resources
+ * @vf: pointer to the VF structure
+ *
+ * Returns 0 on success, negative value on failure
+ */
+static int ice_alloc_vsi_res(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ LIST_HEAD(tmp_add_list);
+ u8 broadcast[ETH_ALEN];
+ struct ice_vsi *vsi;
+ int status = 0;
+
+ /* first vector index is the VFs OICR index */
+ vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
+
+ vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
+ if (!vsi) {
+ dev_err(&pf->pdev->dev, "Failed to create VF VSI\n");
+ return -ENOMEM;
+ }
+
+ vf->lan_vsi_idx = vsi->idx;
+ vf->lan_vsi_num = vsi->vsi_num;
+
+ /* Check if port VLAN exist before, and restore it accordingly */
+ if (vf->port_vlan_id) {
+ ice_vsi_manage_pvid(vsi, vf->port_vlan_id, true);
+ ice_vsi_add_vlan(vsi, vf->port_vlan_id & ICE_VLAN_M);
+ }
+
+ eth_broadcast_addr(broadcast);
+
+ status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast);
+ if (status)
+ goto ice_alloc_vsi_res_exit;
+
+ if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) {
+ status = ice_add_mac_to_list(vsi, &tmp_add_list,
+ vf->dflt_lan_addr.addr);
+ if (status)
+ goto ice_alloc_vsi_res_exit;
+ }
+
+ status = ice_add_mac(&pf->hw, &tmp_add_list);
+ if (status)
+ dev_err(&pf->pdev->dev,
+ "could not add mac filters error %d\n", status);
+ else
+ vf->num_mac = 1;
+
+ /* Clear this bit after VF initialization since we shouldn't reclaim
+ * and reassign interrupts for synchronous or asynchronous VFR events.
+ * We don't want to reconfigure interrupts since AVF driver doesn't
+ * expect vector assignment to be changed unless there is a request for
+ * more vectors.
+ */
+ice_alloc_vsi_res_exit:
+ ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+ return status;
+}
+
+/**
+ * ice_alloc_vf_res - Allocate VF resources
+ * @vf: pointer to the VF structure
+ */
+static int ice_alloc_vf_res(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ int tx_rx_queue_left;
+ int status;
+
+ /* Update number of VF queues, in case VF had requested for queue
+ * changes
+ */
+ tx_rx_queue_left = min_t(int, ice_get_avail_txq_count(pf),
+ ice_get_avail_rxq_count(pf));
+ tx_rx_queue_left += ICE_DFLT_QS_PER_VF;
+ if (vf->num_req_qs && vf->num_req_qs <= tx_rx_queue_left &&
+ vf->num_req_qs != vf->num_vf_qs)
+ vf->num_vf_qs = vf->num_req_qs;
+
+ /* setup VF VSI and necessary resources */
+ status = ice_alloc_vsi_res(vf);
+ if (status)
+ goto ice_alloc_vf_res_exit;
+
+ if (vf->trusted)
+ set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+ else
+ clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+
+ /* VF is now completely initialized */
+ set_bit(ICE_VF_STATE_INIT, vf->vf_states);
+
+ return status;
+
+ice_alloc_vf_res_exit:
+ ice_free_vf_res(vf);
+ return status;
+}
+
+/**
+ * ice_ena_vf_mappings
+ * @vf: pointer to the VF structure
+ *
+ * Enable VF vectors and queues allocation by writing the details into
+ * respective registers.
+ */
+static void ice_ena_vf_mappings(struct ice_vf *vf)
+{
+ int abs_vf_id, abs_first, abs_last;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ int first, last, v;
+ struct ice_hw *hw;
+ u32 reg;
+
+ hw = &pf->hw;
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ first = vf->first_vector_idx;
+ last = (first + pf->num_vf_msix) - 1;
+ abs_first = first + pf->hw.func_caps.common_cap.msix_vector_first_id;
+ abs_last = (abs_first + pf->num_vf_msix) - 1;
+ abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
+
+ /* VF Vector allocation */
+ reg = (((abs_first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) |
+ ((abs_last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) |
+ VPINT_ALLOC_VALID_M);
+ wr32(hw, VPINT_ALLOC(vf->vf_id), reg);
+
+ reg = (((abs_first << VPINT_ALLOC_PCI_FIRST_S)
+ & VPINT_ALLOC_PCI_FIRST_M) |
+ ((abs_last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) |
+ VPINT_ALLOC_PCI_VALID_M);
+ wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);
+ /* map the interrupts to its functions */
+ for (v = first; v <= last; v++) {
+ reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
+ GLINT_VECT2FUNC_VF_NUM_M) |
+ ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
+ GLINT_VECT2FUNC_PF_NUM_M));
+ wr32(hw, GLINT_VECT2FUNC(v), reg);
+ }
+
+ /* Map mailbox interrupt. We put an explicit 0 here to remind us that
+ * VF admin queue interrupts will go to VF MSI-X vector 0.
+ */
+ wr32(hw, VPINT_MBX_CTL(abs_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M | 0);
+ /* set regardless of mapping mode */
+ wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M);
+
+ /* VF Tx queues allocation */
+ if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) {
+ /* set the VF PF Tx queue range
+ * VFNUMQ value should be set to (number of queues - 1). A value
+ * of 0 means 1 queue and a value of 255 means 256 queues
+ */
+ reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) &
+ VPLAN_TX_QBASE_VFFIRSTQ_M) |
+ (((vsi->alloc_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) &
+ VPLAN_TX_QBASE_VFNUMQ_M));
+ wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg);
+ } else {
+ dev_err(&pf->pdev->dev,
+ "Scattered mode for VF Tx queues is not yet implemented\n");
+ }
+
+ /* set regardless of mapping mode */
+ wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M);
+
+ /* VF Rx queues allocation */
+ if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) {
+ /* set the VF PF Rx queue range
+ * VFNUMQ value should be set to (number of queues - 1). A value
+ * of 0 means 1 queue and a value of 255 means 256 queues
+ */
+ reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) &
+ VPLAN_RX_QBASE_VFFIRSTQ_M) |
+ (((vsi->alloc_txq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) &
+ VPLAN_RX_QBASE_VFNUMQ_M));
+ wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg);
+ } else {
+ dev_err(&pf->pdev->dev,
+ "Scattered mode for VF Rx queues is not yet implemented\n");
+ }
+}
+
+/**
+ * ice_determine_res
+ * @pf: pointer to the PF structure
+ * @avail_res: available resources in the PF structure
+ * @max_res: maximum resources that can be given per VF
+ * @min_res: minimum resources that can be given per VF
+ *
+ * Returns non-zero value if resources (queues/vectors) are available or
+ * returns zero if PF cannot accommodate for all num_alloc_vfs.
+ */
+static int
+ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res)
+{
+ bool checked_min_res = false;
+ int res;
+
+ /* start by checking if PF can assign max number of resources for
+ * all num_alloc_vfs.
+ * if yes, return number per VF
+ * If no, divide by 2 and roundup, check again
+ * repeat the loop till we reach a point where even minimum resources
+ * are not available, in that case return 0
+ */
+ res = max_res;
+ while ((res >= min_res) && !checked_min_res) {
+ int num_all_res;
+
+ num_all_res = pf->num_alloc_vfs * res;
+ if (num_all_res <= avail_res)
+ return res;
+
+ if (res == min_res)
+ checked_min_res = true;
+
+ res = DIV_ROUND_UP(res, 2);
+ }
+ return 0;
+}
+
+/**
+ * ice_calc_vf_reg_idx - Calculate the VF's register index in the PF space
+ * @vf: VF to calculate the register index for
+ * @q_vector: a q_vector associated to the VF
+ */
+int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
+{
+ struct ice_pf *pf;
+
+ if (!vf || !q_vector)
+ return -EINVAL;
+
+ pf = vf->pf;
+
+ /* always add one to account for the OICR being the first MSIX */
+ return pf->sriov_base_vector + pf->num_vf_msix * vf->vf_id +
+ q_vector->v_idx + 1;
+}
+
+/**
+ * ice_get_max_valid_res_idx - Get the max valid resource index
+ * @res: pointer to the resource to find the max valid index for
+ *
+ * Start from the end of the ice_res_tracker and return right when we find the
+ * first res->list entry with the ICE_RES_VALID_BIT set. This function is only
+ * valid for SR-IOV because it is the only consumer that manipulates the
+ * res->end and this is always called when res->end is set to res->num_entries.
+ */
+static int ice_get_max_valid_res_idx(struct ice_res_tracker *res)
+{
+ int i;
+
+ if (!res)
+ return -EINVAL;
+
+ for (i = res->num_entries - 1; i >= 0; i--)
+ if (res->list[i] & ICE_RES_VALID_BIT)
+ return i;
+
+ return 0;
+}
+
+/**
+ * ice_sriov_set_msix_res - Set any used MSIX resources
+ * @pf: pointer to PF structure
+ * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
+ *
+ * This function allows SR-IOV resources to be taken from the end of the PF's
+ * allowed HW MSIX vectors so in many cases the irq_tracker will not
+ * be needed. In these cases we just set the pf->sriov_base_vector and return
+ * success.
+ *
+ * If SR-IOV needs to use any pf->irq_tracker entries it updates the
+ * irq_tracker->end based on the first entry needed for SR-IOV. This makes it
+ * so any calls to ice_get_res() using the irq_tracker will not try to use
+ * resources at or beyond the newly set value.
+ *
+ * Return 0 on success, and -EINVAL when there are not enough MSIX vectors in
+ * in the PF's space available for SR-IOV.
+ */
+static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
+{
+ int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker);
+ u16 pf_total_msix_vectors =
+ pf->hw.func_caps.common_cap.num_msix_vectors;
+ struct ice_res_tracker *res = pf->irq_tracker;
+ int sriov_base_vector;
+
+ if (max_valid_res_idx < 0)
+ return max_valid_res_idx;
+
+ sriov_base_vector = pf_total_msix_vectors - num_msix_needed;
+
+ /* make sure we only grab irq_tracker entries from the list end and
+ * that we have enough available MSIX vectors
+ */
+ if (sriov_base_vector <= max_valid_res_idx)
+ return -EINVAL;
+
+ pf->sriov_base_vector = sriov_base_vector;
+
+ /* dip into irq_tracker entries and update used resources */
+ if (num_msix_needed > (pf_total_msix_vectors - res->num_entries)) {
+ pf->num_avail_sw_msix -=
+ res->num_entries - pf->sriov_base_vector;
+ res->end = pf->sriov_base_vector;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_check_avail_res - check if vectors and queues are available
+ * @pf: pointer to the PF structure
+ *
+ * This function is where we calculate actual number of resources for VF VSIs,
+ * we don't reserve ahead of time during probe. Returns success if vectors and
+ * queues resources are available, otherwise returns error code
+ */
+static int ice_check_avail_res(struct ice_pf *pf)
+{
+ int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker);
+ u16 num_msix, num_txq, num_rxq, num_avail_msix;
+
+ if (!pf->num_alloc_vfs || max_valid_res_idx < 0)
+ return -EINVAL;
+
+ /* add 1 to max_valid_res_idx to account for it being 0-based */
+ num_avail_msix = pf->hw.func_caps.common_cap.num_msix_vectors -
+ (max_valid_res_idx + 1);
+
+ /* Grab from HW interrupts common pool
+ * Note: By the time the user decides it needs more vectors in a VF
+ * its already too late since one must decide this prior to creating the
+ * VF interface. So the best we can do is take a guess as to what the
+ * user might want.
+ *
+ * We have two policies for vector allocation:
+ * 1. if num_alloc_vfs is from 1 to 16, then we consider this as small
+ * number of NFV VFs used for NFV appliances, since this is a special
+ * case, we try to assign maximum vectors per VF (65) as much as
+ * possible, based on determine_resources algorithm.
+ * 2. if num_alloc_vfs is from 17 to 256, then its large number of
+ * regular VFs which are not used for any special purpose. Hence try to
+ * grab default interrupt vectors (5 as supported by AVF driver).
+ */
+ if (pf->num_alloc_vfs <= 16) {
+ num_msix = ice_determine_res(pf, num_avail_msix,
+ ICE_MAX_INTR_PER_VF,
+ ICE_MIN_INTR_PER_VF);
+ } else if (pf->num_alloc_vfs <= ICE_MAX_VF_COUNT) {
+ num_msix = ice_determine_res(pf, num_avail_msix,
+ ICE_DFLT_INTR_PER_VF,
+ ICE_MIN_INTR_PER_VF);
+ } else {
+ dev_err(&pf->pdev->dev,
+ "Number of VFs %d exceeds max VF count %d\n",
+ pf->num_alloc_vfs, ICE_MAX_VF_COUNT);
+ return -EIO;
+ }
+
+ if (!num_msix)
+ return -EIO;
+
+ /* Grab from the common pool
+ * start by requesting Default queues (4 as supported by AVF driver),
+ * Note that, the main difference between queues and vectors is, latter
+ * can only be reserved at init time but queues can be requested by VF
+ * at runtime through Virtchnl, that is the reason we start by reserving
+ * few queues.
+ */
+ num_txq = ice_determine_res(pf, ice_get_avail_txq_count(pf),
+ ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF);
+
+ num_rxq = ice_determine_res(pf, ice_get_avail_rxq_count(pf),
+ ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF);
+
+ if (!num_txq || !num_rxq)
+ return -EIO;
+
+ if (ice_sriov_set_msix_res(pf, num_msix * pf->num_alloc_vfs))
+ return -EINVAL;
+
+ /* since AVF driver works with only queue pairs which means, it expects
+ * to have equal number of Rx and Tx queues, so take the minimum of
+ * available Tx or Rx queues
+ */
+ pf->num_vf_qps = min_t(int, num_txq, num_rxq);
+ pf->num_vf_msix = num_msix;
+
+ return 0;
+}
+
+/**
+ * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset
+ * @vf: pointer to the VF structure
+ *
+ * Cleanup a VF after the hardware reset is finished. Expects the caller to
+ * have verified whether the reset is finished properly, and ensure the
+ * minimum amount of wait time has passed. Reallocate VF resources back to make
+ * VF state active
+ */
+static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
+{
+ struct ice_pf *pf = vf->pf;
+ struct ice_hw *hw;
+ u32 reg;
+
+ hw = &pf->hw;
+
+ /* PF software completes the flow by notifying VF that reset flow is
+ * completed. This is done by enabling hardware by clearing the reset
+ * bit in the VPGEN_VFRTRIG reg and setting VFR_STATE in the VFGEN_RSTAT
+ * register to VFR completed (done at the end of this function)
+ * By doing this we allow HW to access VF memory at any point. If we
+ * did it any sooner, HW could access memory while it was being freed
+ * in ice_free_vf_res(), causing an IOMMU fault.
+ *
+ * On the other hand, this needs to be done ASAP, because the VF driver
+ * is waiting for this to happen and may report a timeout. It's
+ * harmless, but it gets logged into Guest OS kernel log, so best avoid
+ * it.
+ */
+ reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
+ reg &= ~VPGEN_VFRTRIG_VFSWR_M;
+ wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
+
+ /* reallocate VF resources to finish resetting the VSI state */
+ if (!ice_alloc_vf_res(vf)) {
+ ice_ena_vf_mappings(vf);
+ set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
+ clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
+ vf->num_vlan = 0;
+ }
+
+ /* Tell the VF driver the reset is done. This needs to be done only
+ * after VF has been fully initialized, because the VF driver may
+ * request resources immediately after setting this flag.
+ */
+ wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
+}
+
+/**
+ * ice_vf_set_vsi_promisc - set given VF VSI to given promiscuous mode(s)
+ * @vf: pointer to the VF info
+ * @vsi: the VSI being configured
+ * @promisc_m: mask of promiscuous config bits
+ * @rm_promisc: promisc flag request from the VF to remove or add filter
+ *
+ * This function configures VF VSI promiscuous mode, based on the VF requests,
+ * for Unicast, Multicast and VLAN
+ */
+static enum ice_status
+ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m,
+ bool rm_promisc)
+{
+ struct ice_pf *pf = vf->pf;
+ enum ice_status status = 0;
+ struct ice_hw *hw;
+
+ hw = &pf->hw;
+ if (vf->num_vlan) {
+ status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
+ rm_promisc);
+ } else if (vf->port_vlan_id) {
+ if (rm_promisc)
+ status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+ vf->port_vlan_id);
+ else
+ status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+ vf->port_vlan_id);
+ } else {
+ if (rm_promisc)
+ status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+ 0);
+ else
+ status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+ 0);
+ }
+
+ return status;
+}
+
+/**
+ * ice_config_res_vfs - Finalize allocation of VFs resources in one go
+ * @pf: pointer to the PF structure
+ *
+ * This function is being called as last part of resetting all VFs, or when
+ * configuring VFs for the first time, where there is no resource to be freed
+ * Returns true if resources were properly allocated for all VFs, and false
+ * otherwise.
+ */
+static bool ice_config_res_vfs(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+ int v;
+
+ if (ice_check_avail_res(pf)) {
+ dev_err(&pf->pdev->dev,
+ "Cannot allocate VF resources, try with fewer number of VFs\n");
+ return false;
+ }
+
+ /* rearm global interrupts */
+ if (test_and_clear_bit(__ICE_OICR_INTR_DIS, pf->state))
+ ice_irq_dynamic_ena(hw, NULL, NULL);
+
+ /* Finish resetting each VF and allocate resources */
+ for (v = 0; v < pf->num_alloc_vfs; v++) {
+ struct ice_vf *vf = &pf->vf[v];
+
+ vf->num_vf_qs = pf->num_vf_qps;
+ dev_dbg(&pf->pdev->dev,
+ "VF-id %d has %d queues configured\n",
+ vf->vf_id, vf->num_vf_qs);
+ ice_cleanup_and_realloc_vf(vf);
+ }
+
+ ice_flush(hw);
+ clear_bit(__ICE_VF_DIS, pf->state);
+
+ return true;
+}
+
+/**
+ * ice_reset_all_vfs - reset all allocated VFs in one go
+ * @pf: pointer to the PF structure
+ * @is_vflr: true if VFLR was issued, false if not
+ *
+ * First, tell the hardware to reset each VF, then do all the waiting in one
+ * chunk, and finally finish restoring each VF after the wait. This is useful
+ * during PF routines which need to reset all VFs, as otherwise it must perform
+ * these resets in a serialized fashion.
+ *
+ * Returns true if any VFs were reset, and false otherwise.
+ */
+bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
+{
+ struct ice_hw *hw = &pf->hw;
+ struct ice_vf *vf;
+ int v, i;
+
+ /* If we don't have any VFs, then there is nothing to reset */
+ if (!pf->num_alloc_vfs)
+ return false;
+
+ /* If VFs have been disabled, there is no need to reset */
+ if (test_and_set_bit(__ICE_VF_DIS, pf->state))
+ return false;
+
+ /* Begin reset on all VFs at once */
+ for (v = 0; v < pf->num_alloc_vfs; v++)
+ ice_trigger_vf_reset(&pf->vf[v], is_vflr, true);
+
+ for (v = 0; v < pf->num_alloc_vfs; v++) {
+ struct ice_vsi *vsi;
+
+ vf = &pf->vf[v];
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states))
+ ice_dis_vf_qs(vf);
+ ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
+ NULL, ICE_VF_RESET, vf->vf_id, NULL);
+ }
+
+ /* HW requires some time to make sure it can flush the FIFO for a VF
+ * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
+ * sequence to make sure that it has completed. We'll keep track of
+ * the VFs using a simple iterator that increments once that VF has
+ * finished resetting.
+ */
+ for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
+
+ /* Check each VF in sequence */
+ while (v < pf->num_alloc_vfs) {
+ u32 reg;
+
+ vf = &pf->vf[v];
+ reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id));
+ if (!(reg & VPGEN_VFRSTAT_VFRD_M)) {
+ /* only delay if the check failed */
+ usleep_range(10, 20);
+ break;
+ }
+
+ /* If the current VF has finished resetting, move on
+ * to the next VF in sequence.
+ */
+ v++;
+ }
+ }
+
+ /* Display a warning if at least one VF didn't manage to reset in
+ * time, but continue on with the operation.
+ */
+ if (v < pf->num_alloc_vfs)
+ dev_warn(&pf->pdev->dev, "VF reset check timeout\n");
+
+ /* free VF resources to begin resetting the VSI state */
+ for (v = 0; v < pf->num_alloc_vfs; v++) {
+ vf = &pf->vf[v];
+
+ ice_free_vf_res(vf);
+
+ /* Free VF queues as well, and reallocate later.
+ * If a given VF has different number of queues
+ * configured, the request for update will come
+ * via mailbox communication.
+ */
+ vf->num_vf_qs = 0;
+ }
+
+ if (ice_sriov_free_msix_res(pf))
+ dev_err(&pf->pdev->dev,
+ "Failed to free MSIX resources used by SR-IOV\n");
+
+ if (!ice_config_res_vfs(pf))
+ return false;
+
+ return true;
+}
+
+/**
+ * ice_reset_vf - Reset a particular VF
+ * @vf: pointer to the VF structure
+ * @is_vflr: true if VFLR was issued, false if not
+ *
+ * Returns true if the VF is reset, false otherwise.
+ */
+static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
+{
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ struct ice_hw *hw;
+ bool rsd = false;
+ u8 promisc_m;
+ u32 reg;
+ int i;
+
+ /* If the PF has been disabled, there is no need resetting VF until
+ * PF is active again.
+ */
+ if (test_bit(__ICE_VF_DIS, pf->state))
+ return false;
+
+ /* If the VF has been disabled, this means something else is
+ * resetting the VF, so we shouldn't continue. Otherwise, set
+ * disable VF state bit for actual reset, and continue.
+ */
+ if (test_and_set_bit(ICE_VF_STATE_DIS, vf->vf_states))
+ return false;
+
+ ice_trigger_vf_reset(vf, is_vflr, false);
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+
+ if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states))
+ ice_dis_vf_qs(vf);
+
+ /* Call Disable LAN Tx queue AQ whether or not queues are
+ * enabled. This is needed for successful completion of VFR.
+ */
+ ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
+ NULL, ICE_VF_RESET, vf->vf_id, NULL);
+
+ hw = &pf->hw;
+ /* poll VPGEN_VFRSTAT reg to make sure
+ * that reset is complete
+ */
+ for (i = 0; i < 10; i++) {
+ /* VF reset requires driver to first reset the VF and then
+ * poll the status register to make sure that the reset
+ * completed successfully.
+ */
+ reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id));
+ if (reg & VPGEN_VFRSTAT_VFRD_M) {
+ rsd = true;
+ break;
+ }
+
+ /* only sleep if the reset is not done */
+ usleep_range(10, 20);
+ }
+
+ /* Display a warning if VF didn't manage to reset in time, but need to
+ * continue on with the operation.
+ */
+ if (!rsd)
+ dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
+ vf->vf_id);
+
+ /* disable promiscuous modes in case they were enabled
+ * ignore any error if disabling process failed
+ */
+ if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+ test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) {
+ if (vf->port_vlan_id || vf->num_vlan)
+ promisc_m = ICE_UCAST_VLAN_PROMISC_BITS;
+ else
+ promisc_m = ICE_UCAST_PROMISC_BITS;
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (ice_vf_set_vsi_promisc(vf, vsi, promisc_m, true))
+ dev_err(&pf->pdev->dev, "disabling promiscuous mode failed\n");
+ }
+
+ /* free VF resources to begin resetting the VSI state */
+ ice_free_vf_res(vf);
+
+ ice_cleanup_and_realloc_vf(vf);
+
+ ice_flush(hw);
+
+ return true;
+}
+
+/**
+ * ice_vc_notify_link_state - Inform all VFs on a PF of link status
+ * @pf: pointer to the PF structure
+ */
+void ice_vc_notify_link_state(struct ice_pf *pf)
+{
+ int i;
+
+ for (i = 0; i < pf->num_alloc_vfs; i++)
+ ice_vc_notify_vf_link_state(&pf->vf[i]);
+}
+
+/**
+ * ice_vc_notify_reset - Send pending reset message to all VFs
+ * @pf: pointer to the PF structure
+ *
+ * indicate a pending reset to all VFs on a given PF
+ */
+void ice_vc_notify_reset(struct ice_pf *pf)
+{
+ struct virtchnl_pf_event pfe;
+
+ if (!pf->num_alloc_vfs)
+ return;
+
+ pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING;
+ pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM;
+ ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, VIRTCHNL_STATUS_SUCCESS,
+ (u8 *)&pfe, sizeof(struct virtchnl_pf_event));
+}
+
+/**
+ * ice_vc_notify_vf_reset - Notify VF of a reset event
+ * @vf: pointer to the VF structure
+ */
+static void ice_vc_notify_vf_reset(struct ice_vf *vf)
+{
+ struct virtchnl_pf_event pfe;
+
+ /* validate the request */
+ if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs)
+ return;
+
+ /* verify if the VF is in either init or active before proceeding */
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) &&
+ !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+ return;
+
+ pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING;
+ pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM;
+ ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+ VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, sizeof(pfe),
+ NULL);
+}
+
+/**
+ * ice_alloc_vfs - Allocate and set up VFs resources
+ * @pf: pointer to the PF structure
+ * @num_alloc_vfs: number of VFs to allocate
+ */
+static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
+{
+ struct ice_hw *hw = &pf->hw;
+ struct ice_vf *vfs;
+ int i, ret;
+
+ /* Disable global interrupt 0 so we don't try to handle the VFLR. */
+ wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
+ ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
+ set_bit(__ICE_OICR_INTR_DIS, pf->state);
+ ice_flush(hw);
+
+ ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
+ if (ret) {
+ pf->num_alloc_vfs = 0;
+ goto err_unroll_intr;
+ }
+ /* allocate memory */
+ vfs = devm_kcalloc(&pf->pdev->dev, num_alloc_vfs, sizeof(*vfs),
+ GFP_KERNEL);
+ if (!vfs) {
+ ret = -ENOMEM;
+ goto err_pci_disable_sriov;
+ }
+ pf->vf = vfs;
+
+ /* apply default profile */
+ for (i = 0; i < num_alloc_vfs; i++) {
+ vfs[i].pf = pf;
+ vfs[i].vf_sw_id = pf->first_sw;
+ vfs[i].vf_id = i;
+
+ /* assign default capabilities */
+ set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
+ vfs[i].spoofchk = true;
+ }
+ pf->num_alloc_vfs = num_alloc_vfs;
+
+ /* VF resources get allocated with initialization */
+ if (!ice_config_res_vfs(pf)) {
+ ret = -EIO;
+ goto err_unroll_sriov;
+ }
+
+ return ret;
+
+err_unroll_sriov:
+ pf->vf = NULL;
+ devm_kfree(&pf->pdev->dev, vfs);
+ vfs = NULL;
+ pf->num_alloc_vfs = 0;
+err_pci_disable_sriov:
+ pci_disable_sriov(pf->pdev);
+err_unroll_intr:
+ /* rearm interrupts here */
+ ice_irq_dynamic_ena(hw, NULL, NULL);
+ clear_bit(__ICE_OICR_INTR_DIS, pf->state);
+ return ret;
+}
+
+/**
+ * ice_pf_state_is_nominal - checks the PF for nominal state
+ * @pf: pointer to PF to check
+ *
+ * Check the PF's state for a collection of bits that would indicate
+ * the PF is in a state that would inhibit normal operation for
+ * driver functionality.
+ *
+ * Returns true if PF is in a nominal state.
+ * Returns false otherwise
+ */
+static bool ice_pf_state_is_nominal(struct ice_pf *pf)
+{
+ DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 };
+
+ if (!pf)
+ return false;
+
+ bitmap_set(check_bits, 0, __ICE_STATE_NOMINAL_CHECK_BITS);
+ if (bitmap_intersects(pf->state, check_bits, __ICE_STATE_NBITS))
+ return false;
+
+ return true;
+}
+
+/**
+ * ice_pci_sriov_ena - Enable or change number of VFs
+ * @pf: pointer to the PF structure
+ * @num_vfs: number of VFs to allocate
+ */
+static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
+{
+ int pre_existing_vfs = pci_num_vf(pf->pdev);
+ struct device *dev = &pf->pdev->dev;
+ int err;
+
+ if (!ice_pf_state_is_nominal(pf)) {
+ dev_err(dev, "Cannot enable SR-IOV, device not ready\n");
+ return -EBUSY;
+ }
+
+ if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) {
+ dev_err(dev, "This device is not capable of SR-IOV\n");
+ return -ENODEV;
+ }
+
+ if (pre_existing_vfs && pre_existing_vfs != num_vfs)
+ ice_free_vfs(pf);
+ else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
+ return num_vfs;
+
+ if (num_vfs > pf->num_vfs_supported) {
+ dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n",
+ num_vfs, pf->num_vfs_supported);
+ return -ENOTSUPP;
+ }
+
+ dev_info(dev, "Allocating %d VFs\n", num_vfs);
+ err = ice_alloc_vfs(pf, num_vfs);
+ if (err) {
+ dev_err(dev, "Failed to enable SR-IOV: %d\n", err);
+ return err;
+ }
+
+ set_bit(ICE_FLAG_SRIOV_ENA, pf->flags);
+ return num_vfs;
+}
+
+/**
+ * ice_sriov_configure - Enable or change number of VFs via sysfs
+ * @pdev: pointer to a pci_dev structure
+ * @num_vfs: number of VFs to allocate
+ *
+ * This function is called when the user updates the number of VFs in sysfs.
+ */
+int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+ struct ice_pf *pf = pci_get_drvdata(pdev);
+
+ if (ice_is_safe_mode(pf)) {
+ dev_err(&pf->pdev->dev,
+ "SR-IOV cannot be configured - Device is in Safe Mode\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (num_vfs)
+ return ice_pci_sriov_ena(pf, num_vfs);
+
+ if (!pci_vfs_assigned(pdev)) {
+ ice_free_vfs(pf);
+ } else {
+ dev_err(&pf->pdev->dev,
+ "can't free VFs because some are assigned to VMs.\n");
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_process_vflr_event - Free VF resources via IRQ calls
+ * @pf: pointer to the PF structure
+ *
+ * called from the VFLR IRQ handler to
+ * free up VF resources and state variables
+ */
+void ice_process_vflr_event(struct ice_pf *pf)
+{
+ struct ice_hw *hw = &pf->hw;
+ int vf_id;
+ u32 reg;
+
+ if (!test_and_clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
+ !pf->num_alloc_vfs)
+ return;
+
+ for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
+ struct ice_vf *vf = &pf->vf[vf_id];
+ u32 reg_idx, bit_idx;
+
+ reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32;
+ bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32;
+ /* read GLGEN_VFLRSTAT register to find out the flr VFs */
+ reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx));
+ if (reg & BIT(bit_idx))
+ /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */
+ ice_reset_vf(vf, true);
+ }
+}
+
+/**
+ * ice_vc_dis_vf - Disable a given VF via SW reset
+ * @vf: pointer to the VF info
+ *
+ * Disable the VF through a SW reset
+ */
+static void ice_vc_dis_vf(struct ice_vf *vf)
+{
+ ice_vc_notify_vf_reset(vf);
+ ice_reset_vf(vf, false);
+}
+
+/**
+ * ice_vc_send_msg_to_vf - Send message to VF
+ * @vf: pointer to the VF info
+ * @v_opcode: virtual channel opcode
+ * @v_retval: virtual channel return value
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * send msg to VF
+ */
+static int
+ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
+ enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
+{
+ enum ice_status aq_ret;
+ struct ice_pf *pf;
+
+ /* validate the request */
+ if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs)
+ return -EINVAL;
+
+ pf = vf->pf;
+
+ /* single place to detect unsuccessful return values */
+ if (v_retval) {
+ vf->num_inval_msgs++;
+ dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n",
+ vf->vf_id, v_opcode, v_retval);
+ if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) {
+ dev_err(&pf->pdev->dev,
+ "Number of invalid messages exceeded for VF %d\n",
+ vf->vf_id);
+ dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n");
+ set_bit(ICE_VF_STATE_DIS, vf->vf_states);
+ return -EIO;
+ }
+ } else {
+ vf->num_valid_msgs++;
+ /* reset the invalid counter, if a valid message is received. */
+ vf->num_inval_msgs = 0;
+ }
+
+ aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval,
+ msg, msglen, NULL);
+ if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) {
+ dev_info(&pf->pdev->dev,
+ "Unable to send the message to VF %d ret %d aq_err %d\n",
+ vf->vf_id, aq_ret, pf->hw.mailboxq.sq_last_status);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_vc_get_ver_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to request the API version used by the PF
+ */
+static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg)
+{
+ struct virtchnl_version_info info = {
+ VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR
+ };
+
+ vf->vf_ver = *(struct virtchnl_version_info *)msg;
+ /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */
+ if (VF_IS_V10(&vf->vf_ver))
+ info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS;
+
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION,
+ VIRTCHNL_STATUS_SUCCESS, (u8 *)&info,
+ sizeof(struct virtchnl_version_info));
+}
+
+/**
+ * ice_vc_get_vf_res_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to request its resources
+ */
+static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_vf_resource *vfres = NULL;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ int len = 0;
+ int ret;
+
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto err;
+ }
+
+ len = sizeof(struct virtchnl_vf_resource);
+
+ vfres = devm_kzalloc(&pf->pdev->dev, len, GFP_KERNEL);
+ if (!vfres) {
+ v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+ len = 0;
+ goto err;
+ }
+ if (VF_IS_V11(&vf->vf_ver))
+ vf->driver_caps = *(u32 *)msg;
+ else
+ vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 |
+ VIRTCHNL_VF_OFFLOAD_RSS_REG |
+ VIRTCHNL_VF_OFFLOAD_VLAN;
+
+ vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2;
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto err;
+ }
+
+ if (!vsi->info.pvid)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF;
+ } else {
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ;
+ else
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG;
+ }
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
+
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES;
+
+ if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED;
+
+ vfres->num_vsis = 1;
+ /* Tx and Rx queue are equal for VF */
+ vfres->num_queue_pairs = vsi->num_txq;
+ vfres->max_vectors = pf->num_vf_msix;
+ vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE;
+ vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE;
+
+ vfres->vsi_res[0].vsi_id = vf->lan_vsi_num;
+ vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV;
+ vfres->vsi_res[0].num_queue_pairs = vsi->num_txq;
+ ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
+ vf->dflt_lan_addr.addr);
+
+ set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
+
+err:
+ /* send the response back to the VF */
+ ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, v_ret,
+ (u8 *)vfres, len);
+
+ devm_kfree(&pf->pdev->dev, vfres);
+ return ret;
+}
+
+/**
+ * ice_vc_reset_vf_msg
+ * @vf: pointer to the VF info
+ *
+ * called from the VF to reset itself,
+ * unlike other virtchnl messages, PF driver
+ * doesn't send the response back to the VF
+ */
+static void ice_vc_reset_vf_msg(struct ice_vf *vf)
+{
+ if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+ ice_reset_vf(vf, false);
+}
+
+/**
+ * ice_find_vsi_from_id
+ * @pf: the PF structure to search for the VSI
+ * @id: ID of the VSI it is searching for
+ *
+ * searches for the VSI with the given ID
+ */
+static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id)
+{
+ int i;
+
+ ice_for_each_vsi(pf, i)
+ if (pf->vsi[i] && pf->vsi[i]->vsi_num == id)
+ return pf->vsi[i];
+
+ return NULL;
+}
+
+/**
+ * ice_vc_isvalid_vsi_id
+ * @vf: pointer to the VF info
+ * @vsi_id: VF relative VSI ID
+ *
+ * check for the valid VSI ID
+ */
+static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
+{
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+
+ vsi = ice_find_vsi_from_id(pf, vsi_id);
+
+ return (vsi && (vsi->vf_id == vf->vf_id));
+}
+
+/**
+ * ice_vc_isvalid_q_id
+ * @vf: pointer to the VF info
+ * @vsi_id: VSI ID
+ * @qid: VSI relative queue ID
+ *
+ * check for the valid queue ID
+ */
+static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid)
+{
+ struct ice_vsi *vsi = ice_find_vsi_from_id(vf->pf, vsi_id);
+ /* allocated Tx and Rx queues should be always equal for VF VSI */
+ return (vsi && (qid < vsi->alloc_txq));
+}
+
+/**
+ * ice_vc_isvalid_ring_len
+ * @ring_len: length of ring
+ *
+ * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE
+ * or zero
+ */
+static bool ice_vc_isvalid_ring_len(u16 ring_len)
+{
+ return ring_len == 0 ||
+ (ring_len >= ICE_MIN_NUM_DESC &&
+ ring_len <= ICE_MAX_NUM_DESC &&
+ !(ring_len % ICE_REQ_DESC_MULTIPLE));
+}
+
+/**
+ * ice_vc_config_rss_key
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS key
+ */
+static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_rss_key *vrk =
+ (struct virtchnl_rss_key *)msg;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi = NULL;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (ice_set_rss(vsi, vrk->key, NULL, 0))
+ v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_config_rss_lut
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS LUT
+ */
+static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
+{
+ struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi = NULL;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE))
+ v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_get_stats_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to get VSI stats
+ */
+static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_queue_select *vqs =
+ (struct virtchnl_queue_select *)msg;
+ struct ice_pf *pf = vf->pf;
+ struct ice_eth_stats stats;
+ struct ice_vsi *vsi;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ memset(&stats, 0, sizeof(struct ice_eth_stats));
+ ice_update_eth_stats(vsi);
+
+ stats = vsi->eth_stats;
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, v_ret,
+ (u8 *)&stats, sizeof(stats));
+}
+
+/**
+ * ice_vc_ena_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to enable all or specific queue(s)
+ */
+static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_queue_select *vqs =
+ (struct virtchnl_queue_select *)msg;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ unsigned long q_map;
+ u16 vf_q_id;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!vqs->rx_queues && !vqs->tx_queues) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vqs->rx_queues > ICE_MAX_BASE_QS_PER_VF ||
+ vqs->tx_queues > ICE_MAX_BASE_QS_PER_VF) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Enable only Rx rings, Tx rings were enabled by the FW when the
+ * Tx queue group list was configured and the context bits were
+ * programmed using ice_vsi_cfg_txqs
+ */
+ q_map = vqs->rx_queues;
+ for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) {
+ if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Skip queue if enabled */
+ if (test_bit(vf_q_id, vf->rxq_ena))
+ continue;
+
+ if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to enable Rx ring %d on VSI %d\n",
+ vf_q_id, vsi->vsi_num);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ set_bit(vf_q_id, vf->rxq_ena);
+ vf->num_qs_ena++;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ q_map = vqs->tx_queues;
+ for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) {
+ if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Skip queue if enabled */
+ if (test_bit(vf_q_id, vf->txq_ena))
+ continue;
+
+ set_bit(vf_q_id, vf->txq_ena);
+ vf->num_qs_ena++;
+ }
+
+ /* Set flag to indicate that queues are enabled */
+ if (v_ret == VIRTCHNL_STATUS_SUCCESS)
+ set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_dis_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to disable all or specific
+ * queue(s)
+ */
+static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_queue_select *vqs =
+ (struct virtchnl_queue_select *)msg;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ unsigned long q_map;
+ u16 vf_q_id;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) &&
+ !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!vqs->rx_queues && !vqs->tx_queues) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vqs->rx_queues > ICE_MAX_BASE_QS_PER_VF ||
+ vqs->tx_queues > ICE_MAX_BASE_QS_PER_VF) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vqs->tx_queues) {
+ q_map = vqs->tx_queues;
+
+ for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) {
+ struct ice_ring *ring = vsi->tx_rings[vf_q_id];
+ struct ice_txq_meta txq_meta = { 0 };
+
+ if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Skip queue if not enabled */
+ if (!test_bit(vf_q_id, vf->txq_ena))
+ continue;
+
+ ice_fill_txq_meta(vsi, ring, &txq_meta);
+
+ if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id,
+ ring, &txq_meta)) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to stop Tx ring %d on VSI %d\n",
+ vf_q_id, vsi->vsi_num);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Clear enabled queues flag */
+ clear_bit(vf_q_id, vf->txq_ena);
+ vf->num_qs_ena--;
+ }
+ }
+
+ if (vqs->rx_queues) {
+ q_map = vqs->rx_queues;
+
+ for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) {
+ if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Skip queue if not enabled */
+ if (!test_bit(vf_q_id, vf->rxq_ena))
+ continue;
+
+ if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to stop Rx ring %d on VSI %d\n",
+ vf_q_id, vsi->vsi_num);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* Clear enabled queues flag */
+ clear_bit(vf_q_id, vf->rxq_ena);
+ vf->num_qs_ena--;
+ }
+ }
+
+ /* Clear enabled queues flag */
+ if (v_ret == VIRTCHNL_STATUS_SUCCESS && !vf->num_qs_ena)
+ clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_irq_map_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to configure the IRQ to queue map
+ */
+static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_irq_map_info *irqmap_info;
+ u16 vsi_id, vsi_q_id, vector_id;
+ struct virtchnl_vector_map *map;
+ struct ice_pf *pf = vf->pf;
+ u16 num_q_vectors_mapped;
+ struct ice_vsi *vsi;
+ unsigned long qmap;
+ int i;
+
+ irqmap_info = (struct virtchnl_irq_map_info *)msg;
+ num_q_vectors_mapped = irqmap_info->num_vectors;
+
+ /* Check to make sure number of VF vectors mapped is not greater than
+ * number of VF vectors originally allocated, and check that
+ * there is actually at least a single VF queue vector mapped
+ */
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+ pf->num_vf_msix < num_q_vectors_mapped ||
+ !irqmap_info->num_vectors) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < num_q_vectors_mapped; i++) {
+ struct ice_q_vector *q_vector;
+
+ map = &irqmap_info->vecmap[i];
+
+ vector_id = map->vector_id;
+ vsi_id = map->vsi_id;
+ /* validate msg params */
+ if (!(vector_id < pf->hw.func_caps.common_cap
+ .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
+ (!vector_id && (map->rxq_map || map->txq_map))) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* No need to map VF miscellaneous or rogue vector */
+ if (!vector_id)
+ continue;
+
+ /* Subtract non queue vector from vector_id passed by VF
+ * to get actual number of VSI queue vector array index
+ */
+ q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF];
+ if (!q_vector) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ /* lookout for the invalid queue index */
+ qmap = map->rxq_map;
+ q_vector->num_ring_rx = 0;
+ for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) {
+ if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+ q_vector->num_ring_rx++;
+ q_vector->rx.itr_idx = map->rxitr_idx;
+ vsi->rx_rings[vsi_q_id]->q_vector = q_vector;
+ ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id,
+ q_vector->rx.itr_idx);
+ }
+
+ qmap = map->txq_map;
+ q_vector->num_ring_tx = 0;
+ for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) {
+ if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+ q_vector->num_ring_tx++;
+ q_vector->tx.itr_idx = map->txitr_idx;
+ vsi->tx_rings[vsi_q_id]->q_vector = q_vector;
+ ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id,
+ q_vector->tx.itr_idx);
+ }
+ }
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to configure the Rx/Tx queues
+ */
+static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_vsi_queue_config_info *qci =
+ (struct virtchnl_vsi_queue_config_info *)msg;
+ struct virtchnl_queue_pair_info *qpi;
+ u16 num_rxq = 0, num_txq = 0;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+ int i;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF ||
+ qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+ dev_err(&pf->pdev->dev,
+ "VF-%d requesting more than supported number of queues: %d\n",
+ vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ for (i = 0; i < qci->num_queue_pairs; i++) {
+ qpi = &qci->qpair[i];
+ if (qpi->txq.vsi_id != qci->vsi_id ||
+ qpi->rxq.vsi_id != qci->vsi_id ||
+ qpi->rxq.queue_id != qpi->txq.queue_id ||
+ qpi->txq.headwb_enabled ||
+ !ice_vc_isvalid_ring_len(qpi->txq.ring_len) ||
+ !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) ||
+ !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+ /* copy Tx queue info from VF into VSI */
+ if (qpi->txq.ring_len > 0) {
+ num_txq++;
+ vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr;
+ vsi->tx_rings[i]->count = qpi->txq.ring_len;
+ }
+
+ /* copy Rx queue info from VF into VSI */
+ if (qpi->rxq.ring_len > 0) {
+ num_rxq++;
+ vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr;
+ vsi->rx_rings[i]->count = qpi->rxq.ring_len;
+
+ if (qpi->rxq.databuffer_size != 0 &&
+ (qpi->rxq.databuffer_size > ((16 * 1024) - 128) ||
+ qpi->rxq.databuffer_size < 1024)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+ vsi->rx_buf_len = qpi->rxq.databuffer_size;
+ vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len;
+ if (qpi->rxq.max_pkt_size >= (16 * 1024) ||
+ qpi->rxq.max_pkt_size < 64) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+ }
+
+ vsi->max_frame = qpi->rxq.max_pkt_size;
+ }
+
+ /* VF can request to configure less than allocated queues
+ * or default allocated queues. So update the VSI with new number
+ */
+ vsi->num_txq = num_txq;
+ vsi->num_rxq = num_rxq;
+ /* All queues of VF VSI are in TC 0 */
+ vsi->tc_cfg.tc_info[0].qcount_tx = num_txq;
+ vsi->tc_cfg.tc_info[0].qcount_rx = num_rxq;
+
+ if (ice_vsi_cfg_lan_txqs(vsi) || ice_vsi_cfg_rxqs(vsi))
+ v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_is_vf_trusted
+ * @vf: pointer to the VF info
+ */
+static bool ice_is_vf_trusted(struct ice_vf *vf)
+{
+ return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+}
+
+/**
+ * ice_can_vf_change_mac
+ * @vf: pointer to the VF info
+ *
+ * Return true if the VF is allowed to change its MAC filters, false otherwise
+ */
+static bool ice_can_vf_change_mac(struct ice_vf *vf)
+{
+ /* If the VF MAC address has been set administratively (via the
+ * ndo_set_vf_mac command), then deny permission to the VF to
+ * add/delete unicast MAC addresses, unless the VF is trusted
+ */
+ if (vf->pf_set_mac && !ice_is_vf_trusted(vf))
+ return false;
+
+ return true;
+}
+
+/**
+ * ice_vc_handle_mac_addr_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ * @set: true if MAC filters are being set, false otherwise
+ *
+ * add guest MAC address filter
+ */
+static int
+ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_ether_addr_list *al =
+ (struct virtchnl_ether_addr_list *)msg;
+ struct ice_pf *pf = vf->pf;
+ enum virtchnl_ops vc_op;
+ enum ice_status status;
+ struct ice_vsi *vsi;
+ int mac_count = 0;
+ int i;
+
+ if (set)
+ vc_op = VIRTCHNL_OP_ADD_ETH_ADDR;
+ else
+ vc_op = VIRTCHNL_OP_DEL_ETH_ADDR;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+ !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto handle_mac_exit;
+ }
+
+ if (set && !ice_is_vf_trusted(vf) &&
+ (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) {
+ dev_err(&pf->pdev->dev,
+ "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n",
+ vf->vf_id);
+ /* There is no need to let VF know about not being trusted
+ * to add more MAC addr, so we can just return success message.
+ */
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto handle_mac_exit;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto handle_mac_exit;
+ }
+
+ for (i = 0; i < al->num_elements; i++) {
+ u8 *maddr = al->list[i].addr;
+
+ if (ether_addr_equal(maddr, vf->dflt_lan_addr.addr) ||
+ is_broadcast_ether_addr(maddr)) {
+ if (set) {
+ /* VF is trying to add filters that the PF
+ * already added. Just continue.
+ */
+ dev_info(&pf->pdev->dev,
+ "MAC %pM already set for VF %d\n",
+ maddr, vf->vf_id);
+ continue;
+ } else {
+ /* VF can't remove dflt_lan_addr/bcast MAC */
+ dev_err(&pf->pdev->dev,
+ "VF can't remove default MAC address or MAC %pM programmed by PF for VF %d\n",
+ maddr, vf->vf_id);
+ continue;
+ }
+ }
+
+ /* check for the invalid cases and bail if necessary */
+ if (is_zero_ether_addr(maddr)) {
+ dev_err(&pf->pdev->dev,
+ "invalid MAC %pM provided for VF %d\n",
+ maddr, vf->vf_id);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto handle_mac_exit;
+ }
+
+ if (is_unicast_ether_addr(maddr) &&
+ !ice_can_vf_change_mac(vf)) {
+ dev_err(&pf->pdev->dev,
+ "can't change unicast MAC for untrusted VF %d\n",
+ vf->vf_id);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto handle_mac_exit;
+ }
+
+ /* program the updated filter list */
+ status = ice_vsi_cfg_mac_fltr(vsi, maddr, set);
+ if (status == ICE_ERR_DOES_NOT_EXIST ||
+ status == ICE_ERR_ALREADY_EXISTS) {
+ dev_info(&pf->pdev->dev,
+ "can't %s MAC filters %pM for VF %d, error %d\n",
+ set ? "add" : "remove", maddr, vf->vf_id,
+ status);
+ } else if (status) {
+ dev_err(&pf->pdev->dev,
+ "can't %s MAC filters for VF %d, error %d\n",
+ set ? "add" : "remove", vf->vf_id, status);
+ v_ret = ice_err_to_virt_err(status);
+ goto handle_mac_exit;
+ }
+
+ mac_count++;
+ }
+
+ /* Track number of MAC filters programmed for the VF VSI */
+ if (set)
+ vf->num_mac += mac_count;
+ else
+ vf->num_mac -= mac_count;
+
+handle_mac_exit:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_add_mac_addr_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * add guest MAC address filter
+ */
+static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg)
+{
+ return ice_vc_handle_mac_addr_msg(vf, msg, true);
+}
+
+/**
+ * ice_vc_del_mac_addr_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * remove guest MAC address filter
+ */
+static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg)
+{
+ return ice_vc_handle_mac_addr_msg(vf, msg, false);
+}
+
+/**
+ * ice_vc_request_qs_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * VFs get a default number of queues but can use this message to request a
+ * different number. If the request is successful, PF will reset the VF and
+ * return 0. If unsuccessful, PF will send message informing VF of number of
+ * available queue pairs via virtchnl message response to VF.
+ */
+static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_vf_res_request *vfres =
+ (struct virtchnl_vf_res_request *)msg;
+ u16 req_queues = vfres->num_queue_pairs;
+ struct ice_pf *pf = vf->pf;
+ u16 max_allowed_vf_queues;
+ u16 tx_rx_queue_left;
+ u16 cur_queues;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ cur_queues = vf->num_vf_qs;
+ tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf),
+ ice_get_avail_rxq_count(pf));
+ max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
+ if (!req_queues) {
+ dev_err(&pf->pdev->dev,
+ "VF %d tried to request 0 queues. Ignoring.\n",
+ vf->vf_id);
+ } else if (req_queues > ICE_MAX_BASE_QS_PER_VF) {
+ dev_err(&pf->pdev->dev,
+ "VF %d tried to request more than %d queues.\n",
+ vf->vf_id, ICE_MAX_BASE_QS_PER_VF);
+ vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF;
+ } else if (req_queues > cur_queues &&
+ req_queues - cur_queues > tx_rx_queue_left) {
+ dev_warn(&pf->pdev->dev,
+ "VF %d requested %u more queues, but only %u left.\n",
+ vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
+ vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues,
+ ICE_MAX_BASE_QS_PER_VF);
+ } else {
+ /* request is successful, then reset VF */
+ vf->num_req_qs = req_queues;
+ ice_vc_dis_vf(vf);
+ dev_info(&pf->pdev->dev,
+ "VF %d granted request of %u queues.\n",
+ vf->vf_id, req_queues);
+ return 0;
+ }
+
+error_param:
+ /* send the response to the VF */
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES,
+ v_ret, (u8 *)vfres, sizeof(*vfres));
+}
+
+/**
+ * ice_set_vf_port_vlan
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @vlan_id: VLAN ID being set
+ * @qos: priority setting
+ * @vlan_proto: VLAN protocol
+ *
+ * program VF Port VLAN ID and/or QoS
+ */
+int
+ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
+ __be16 vlan_proto)
+{
+ u16 vlanprio = vlan_id | (qos << ICE_VLAN_PRIORITY_S);
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+ struct ice_vsi *vsi;
+ struct ice_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ if (vlan_id > ICE_MAX_VLANID || qos > 7) {
+ dev_err(&pf->pdev->dev, "Invalid VF Parameters\n");
+ return -EINVAL;
+ }
+
+ if (vlan_proto != htons(ETH_P_8021Q)) {
+ dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n");
+ return -EPROTONOSUPPORT;
+ }
+
+ vf = &pf->vf[vf_id];
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ if (le16_to_cpu(vsi->info.pvid) == vlanprio) {
+ /* duplicate request, so just return success */
+ dev_info(&pf->pdev->dev,
+ "Duplicate pvid %d request\n", vlanprio);
+ return ret;
+ }
+
+ /* If PVID, then remove all filters on the old VLAN */
+ if (vsi->info.pvid)
+ ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) &
+ VLAN_VID_MASK));
+
+ if (vlan_id || qos) {
+ ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
+ if (ret)
+ goto error_set_pvid;
+ } else {
+ ice_vsi_manage_pvid(vsi, 0, false);
+ vsi->info.pvid = 0;
+ }
+
+ if (vlan_id) {
+ dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n",
+ vlan_id, qos, vf_id);
+
+ /* add new VLAN filter for each MAC */
+ ret = ice_vsi_add_vlan(vsi, vlan_id);
+ if (ret)
+ goto error_set_pvid;
+ }
+
+ /* The Port VLAN needs to be saved across resets the same as the
+ * default LAN MAC address.
+ */
+ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
+
+error_set_pvid:
+ return ret;
+}
+
+/**
+ * ice_vc_process_vlan_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ * @add_v: Add VLAN if true, otherwise delete VLAN
+ *
+ * Process virtchnl op to add or remove programmed guest VLAN ID
+ */
+static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct virtchnl_vlan_filter_list *vfl =
+ (struct virtchnl_vlan_filter_list *)msg;
+ struct ice_pf *pf = vf->pf;
+ bool vlan_promisc = false;
+ struct ice_vsi *vsi;
+ struct ice_hw *hw;
+ int status = 0;
+ u8 promisc_m;
+ int i;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (add_v && !ice_is_vf_trusted(vf) &&
+ vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
+ dev_info(&pf->pdev->dev,
+ "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+ vf->vf_id);
+ /* There is no need to let VF know about being not trusted,
+ * so we can just return success message here
+ */
+ goto error_param;
+ }
+
+ for (i = 0; i < vfl->num_elements; i++) {
+ if (vfl->vlan_id[i] > ICE_MAX_VLANID) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ dev_err(&pf->pdev->dev,
+ "invalid VF VLAN id %d\n", vfl->vlan_id[i]);
+ goto error_param;
+ }
+ }
+
+ hw = &pf->hw;
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (vsi->info.pvid) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (ice_vsi_manage_vlan_stripping(vsi, add_v)) {
+ dev_err(&pf->pdev->dev,
+ "%sable VLAN stripping failed for VSI %i\n",
+ add_v ? "en" : "dis", vsi->vsi_num);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+ test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states))
+ vlan_promisc = true;
+
+ if (add_v) {
+ for (i = 0; i < vfl->num_elements; i++) {
+ u16 vid = vfl->vlan_id[i];
+
+ if (!ice_is_vf_trusted(vf) &&
+ vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
+ dev_info(&pf->pdev->dev,
+ "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+ vf->vf_id);
+ /* There is no need to let VF know about being
+ * not trusted, so we can just return success
+ * message here as well.
+ */
+ goto error_param;
+ }
+
+ if (ice_vsi_add_vlan(vsi, vid)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vf->num_vlan++;
+ /* Enable VLAN pruning when VLAN is added */
+ if (!vlan_promisc) {
+ status = ice_cfg_vlan_pruning(vsi, true, false);
+ if (status) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ dev_err(&pf->pdev->dev,
+ "Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
+ vid, status);
+ goto error_param;
+ }
+ } else {
+ /* Enable Ucast/Mcast VLAN promiscuous mode */
+ promisc_m = ICE_PROMISC_VLAN_TX |
+ ICE_PROMISC_VLAN_RX;
+
+ status = ice_set_vsi_promisc(hw, vsi->idx,
+ promisc_m, vid);
+ if (status) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ dev_err(&pf->pdev->dev,
+ "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n",
+ vid, status);
+ }
+ }
+ }
+ } else {
+ /* In case of non_trusted VF, number of VLAN elements passed
+ * to PF for removal might be greater than number of VLANs
+ * filter programmed for that VF - So, use actual number of
+ * VLANS added earlier with add VLAN opcode. In order to avoid
+ * removing VLAN that doesn't exist, which result to sending
+ * erroneous failed message back to the VF
+ */
+ int num_vf_vlan;
+
+ num_vf_vlan = vf->num_vlan;
+ for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) {
+ u16 vid = vfl->vlan_id[i];
+
+ /* Make sure ice_vsi_kill_vlan is successful before
+ * updating VLAN information
+ */
+ if (ice_vsi_kill_vlan(vsi, vid)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vf->num_vlan--;
+ /* Disable VLAN pruning when the last VLAN is removed */
+ if (!vf->num_vlan)
+ ice_cfg_vlan_pruning(vsi, false, false);
+
+ /* Disable Unicast/Multicast VLAN promiscuous mode */
+ if (vlan_promisc) {
+ promisc_m = ICE_PROMISC_VLAN_TX |
+ ICE_PROMISC_VLAN_RX;
+
+ ice_clear_vsi_promisc(hw, vsi->idx,
+ promisc_m, vid);
+ }
+ }
+ }
+
+error_param:
+ /* send the response to the VF */
+ if (add_v)
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, v_ret,
+ NULL, 0);
+ else
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, v_ret,
+ NULL, 0);
+}
+
+/**
+ * ice_vc_add_vlan_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Add and program guest VLAN ID
+ */
+static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg)
+{
+ return ice_vc_process_vlan_msg(vf, msg, true);
+}
+
+/**
+ * ice_vc_remove_vlan_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * remove programmed guest VLAN ID
+ */
+static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg)
+{
+ return ice_vc_process_vlan_msg(vf, msg, false);
+}
+
+/**
+ * ice_vc_ena_vlan_stripping
+ * @vf: pointer to the VF info
+ *
+ * Enable VLAN header stripping for a given VF
+ */
+static int ice_vc_ena_vlan_stripping(struct ice_vf *vf)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (ice_vsi_manage_vlan_stripping(vsi, true))
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+
+error_param:
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING,
+ v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_dis_vlan_stripping
+ * @vf: pointer to the VF info
+ *
+ * Disable VLAN header stripping for a given VF
+ */
+static int ice_vc_dis_vlan_stripping(struct ice_vf *vf)
+{
+ enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+ struct ice_pf *pf = vf->pf;
+ struct ice_vsi *vsi;
+
+ if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vsi) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto error_param;
+ }
+
+ if (ice_vsi_manage_vlan_stripping(vsi, false))
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+
+error_param:
+ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING,
+ v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_process_vf_msg - Process request from VF
+ * @pf: pointer to the PF structure
+ * @event: pointer to the AQ event
+ *
+ * called from the common asq/arq handler to
+ * process request from VF
+ */
+void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+ u32 v_opcode = le32_to_cpu(event->desc.cookie_high);
+ s16 vf_id = le16_to_cpu(event->desc.retval);
+ u16 msglen = event->msg_len;
+ u8 *msg = event->msg_buf;
+ struct ice_vf *vf = NULL;
+ int err = 0;
+
+ if (vf_id >= pf->num_alloc_vfs) {
+ err = -EINVAL;
+ goto error_handler;
+ }
+
+ vf = &pf->vf[vf_id];
+
+ /* Check if VF is disabled. */
+ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) {
+ err = -EPERM;
+ goto error_handler;
+ }
+
+ /* Perform basic checks on the msg */
+ err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen);
+ if (err) {
+ if (err == VIRTCHNL_STATUS_ERR_PARAM)
+ err = -EPERM;
+ else
+ err = -EINVAL;
+ }
+
+error_handler:
+ if (err) {
+ ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM,
+ NULL, 0);
+ dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n",
+ vf_id, v_opcode, msglen, err);
+ return;
+ }
+
+ switch (v_opcode) {
+ case VIRTCHNL_OP_VERSION:
+ err = ice_vc_get_ver_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_GET_VF_RESOURCES:
+ err = ice_vc_get_vf_res_msg(vf, msg);
+ ice_vc_notify_vf_link_state(vf);
+ break;
+ case VIRTCHNL_OP_RESET_VF:
+ ice_vc_reset_vf_msg(vf);
+ break;
+ case VIRTCHNL_OP_ADD_ETH_ADDR:
+ err = ice_vc_add_mac_addr_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_DEL_ETH_ADDR:
+ err = ice_vc_del_mac_addr_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_CONFIG_VSI_QUEUES:
+ err = ice_vc_cfg_qs_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_ENABLE_QUEUES:
+ err = ice_vc_ena_qs_msg(vf, msg);
+ ice_vc_notify_vf_link_state(vf);
+ break;
+ case VIRTCHNL_OP_DISABLE_QUEUES:
+ err = ice_vc_dis_qs_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_REQUEST_QUEUES:
+ err = ice_vc_request_qs_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_CONFIG_IRQ_MAP:
+ err = ice_vc_cfg_irq_map_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_CONFIG_RSS_KEY:
+ err = ice_vc_config_rss_key(vf, msg);
+ break;
+ case VIRTCHNL_OP_CONFIG_RSS_LUT:
+ err = ice_vc_config_rss_lut(vf, msg);
+ break;
+ case VIRTCHNL_OP_GET_STATS:
+ err = ice_vc_get_stats_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_ADD_VLAN:
+ err = ice_vc_add_vlan_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_DEL_VLAN:
+ err = ice_vc_remove_vlan_msg(vf, msg);
+ break;
+ case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
+ err = ice_vc_ena_vlan_stripping(vf);
+ break;
+ case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
+ err = ice_vc_dis_vlan_stripping(vf);
+ break;
+ case VIRTCHNL_OP_UNKNOWN:
+ default:
+ dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n",
+ v_opcode, vf_id);
+ err = ice_vc_send_msg_to_vf(vf, v_opcode,
+ VIRTCHNL_STATUS_ERR_NOT_SUPPORTED,
+ NULL, 0);
+ break;
+ }
+ if (err) {
+ /* Helper function cares less about error return values here
+ * as it is busy with pending work.
+ */
+ dev_info(&pf->pdev->dev,
+ "PF failed to honor VF %d, opcode %d, error %d\n",
+ vf_id, v_opcode, err);
+ }
+}
+
+/**
+ * ice_get_vf_cfg
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @ivi: VF configuration structure
+ *
+ * return VF configuration
+ */
+int
+ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_vf *vf;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ netdev_err(netdev, "invalid VF id: %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ vf = &pf->vf[vf_id];
+ vsi = pf->vsi[vf->lan_vsi_idx];
+
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ ivi->vf = vf_id;
+ ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr);
+
+ /* VF configuration for VLAN and applicable QoS */
+ ivi->vlan = le16_to_cpu(vsi->info.pvid) & ICE_VLAN_M;
+ ivi->qos = (le16_to_cpu(vsi->info.pvid) & ICE_PRIORITY_M) >>
+ ICE_VLAN_PRIORITY_S;
+
+ ivi->trusted = vf->trusted;
+ ivi->spoofchk = vf->spoofchk;
+ if (!vf->link_forced)
+ ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
+ else if (vf->link_up)
+ ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE;
+ else
+ ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE;
+ ivi->max_tx_rate = vf->tx_rate;
+ ivi->min_tx_rate = 0;
+ return 0;
+}
+
+/**
+ * ice_set_vf_spoofchk
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @ena: flag to enable or disable feature
+ *
+ * Enable or disable VF spoof checking
+ */
+int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_vsi_ctx *ctx;
+ enum ice_status status;
+ struct ice_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ netdev_err(netdev, "invalid VF id: %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ vf = &pf->vf[vf_id];
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ if (ena == vf->spoofchk) {
+ dev_dbg(&pf->pdev->dev, "VF spoofchk already %s\n",
+ ena ? "ON" : "OFF");
+ return 0;
+ }
+
+ ctx = devm_kzalloc(&pf->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+
+ if (ena) {
+ ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+ ctx->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
+ }
+
+ status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
+ if (status) {
+ dev_dbg(&pf->pdev->dev,
+ "Error %d, failed to update VSI* parameters\n", status);
+ ret = -EIO;
+ goto out;
+ }
+
+ vf->spoofchk = ena;
+ vsi->info.sec_flags = ctx->info.sec_flags;
+ vsi->info.sw_flags2 = ctx->info.sw_flags2;
+out:
+ devm_kfree(&pf->pdev->dev, ctx);
+ return ret;
+}
+
+/**
+ * ice_set_vf_mac
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @mac: MAC address
+ *
+ * program VF MAC address
+ */
+int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ netdev_err(netdev, "invalid VF id: %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ vf = &pf->vf[vf_id];
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) {
+ netdev_err(netdev, "%pM not a valid unicast address\n", mac);
+ return -EINVAL;
+ }
+
+ /* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
+ * flow will use the updated dflt_lan_addr and add a MAC filter
+ * using ice_add_mac. Also set pf_set_mac to indicate that the PF has
+ * set the MAC address for this VF.
+ */
+ ether_addr_copy(vf->dflt_lan_addr.addr, mac);
+ vf->pf_set_mac = true;
+ netdev_info(netdev,
+ "MAC on VF %d set to %pM. VF driver will be reinitialized\n",
+ vf_id, mac);
+
+ ice_vc_dis_vf(vf);
+ return ret;
+}
+
+/**
+ * ice_set_vf_trust
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @trusted: Boolean value to enable/disable trusted VF
+ *
+ * Enable or disable a given VF as trusted
+ */
+int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+ struct ice_vf *vf;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ vf = &pf->vf[vf_id];
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ /* Check if already trusted */
+ if (trusted == vf->trusted)
+ return 0;
+
+ vf->trusted = trusted;
+ ice_vc_dis_vf(vf);
+ dev_info(&pf->pdev->dev, "VF %u is now %strusted\n",
+ vf_id, trusted ? "" : "un");
+
+ return 0;
+}
+
+/**
+ * ice_set_vf_link_state
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @link_state: required link state
+ *
+ * Set VF's link state, irrespective of physical link state status
+ */
+int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+ struct virtchnl_pf_event pfe = { 0 };
+ struct ice_link_status *ls;
+ struct ice_vf *vf;
+ struct ice_hw *hw;
+
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
+ return -EINVAL;
+ }
+
+ vf = &pf->vf[vf_id];
+ hw = &pf->hw;
+ ls = &pf->hw.port_info->phy.link_info;
+
+ if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
+ dev_err(&pf->pdev->dev, "vf %d in reset. Try again.\n", vf_id);
+ return -EBUSY;
+ }
+
+ pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
+ pfe.severity = PF_EVENT_SEVERITY_INFO;
+
+ switch (link_state) {
+ case IFLA_VF_LINK_STATE_AUTO:
+ vf->link_forced = false;
+ vf->link_up = ls->link_info & ICE_AQ_LINK_UP;
+ break;
+ case IFLA_VF_LINK_STATE_ENABLE:
+ vf->link_forced = true;
+ vf->link_up = true;
+ break;
+ case IFLA_VF_LINK_STATE_DISABLE:
+ vf->link_forced = true;
+ vf->link_up = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (vf->link_forced)
+ ice_set_pfe_link_forced(vf, &pfe, vf->link_up);
+ else
+ ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up);
+
+ /* Notify the VF of its new link state */
+ ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+ VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
+ sizeof(pfe), NULL);
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
new file mode 100644
index 0000000..0d9880c
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -0,0 +1,197 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _ICE_VIRTCHNL_PF_H_
+#define _ICE_VIRTCHNL_PF_H_
+#include "ice.h"
+
+#define ICE_MAX_VLANID 4095
+#define ICE_VLAN_PRIORITY_S 12
+#define ICE_VLAN_M 0xFFF
+#define ICE_PRIORITY_M 0x7000
+
+/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */
+#define ICE_MAX_VLAN_PER_VF 8
+#define ICE_MAX_MACADDR_PER_VF 12
+
+/* Malicious Driver Detection */
+#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10
+#define ICE_MDD_EVENTS_THRESHOLD 30
+
+/* Static VF transaction/status register def */
+#define VF_DEVICE_STATUS 0xAA
+#define VF_TRANS_PENDING_M 0x20
+
+/* wait defines for polling PF_PCI_CIAD register status */
+#define ICE_PCI_CIAD_WAIT_COUNT 100
+#define ICE_PCI_CIAD_WAIT_DELAY_US 1
+
+/* VF resources default values and limitation */
+#define ICE_MAX_VF_COUNT 256
+#define ICE_MAX_QS_PER_VF 256
+#define ICE_MIN_QS_PER_VF 1
+#define ICE_DFLT_QS_PER_VF 4
+#define ICE_NONQ_VECS_VF 1
+#define ICE_MAX_SCATTER_QS_PER_VF 16
+#define ICE_MAX_BASE_QS_PER_VF 16
+#define ICE_MAX_INTR_PER_VF 65
+#define ICE_MAX_POLICY_INTR_PER_VF 33
+#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1)
+#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1)
+
+/* Specific VF states */
+enum ice_vf_states {
+ ICE_VF_STATE_INIT = 0, /* PF is initializing VF */
+ ICE_VF_STATE_ACTIVE, /* VF resources are allocated for use */
+ ICE_VF_STATE_QS_ENA, /* VF queue(s) enabled */
+ ICE_VF_STATE_DIS,
+ ICE_VF_STATE_MC_PROMISC,
+ ICE_VF_STATE_UC_PROMISC,
+ ICE_VF_STATES_NBITS
+};
+
+/* VF capabilities */
+enum ice_virtchnl_cap {
+ ICE_VIRTCHNL_VF_CAP_L2 = 0,
+ ICE_VIRTCHNL_VF_CAP_PRIVILEGE,
+};
+
+/* VF information structure */
+struct ice_vf {
+ struct ice_pf *pf;
+
+ s16 vf_id; /* VF ID in the PF space */
+ u16 lan_vsi_idx; /* index into PF struct */
+ /* first vector index of this VF in the PF space */
+ int first_vector_idx;
+ struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */
+ struct virtchnl_version_info vf_ver;
+ u32 driver_caps; /* reported by VF driver */
+ struct virtchnl_ether_addr dflt_lan_addr;
+ DECLARE_BITMAP(txq_ena, ICE_MAX_BASE_QS_PER_VF);
+ DECLARE_BITMAP(rxq_ena, ICE_MAX_BASE_QS_PER_VF);
+ u16 port_vlan_id;
+ u8 pf_set_mac:1; /* VF MAC address set by VMM admin */
+ u8 trusted:1;
+ u8 spoofchk:1;
+ u8 link_forced:1;
+ u8 link_up:1; /* only valid if VF link is forced */
+ /* VSI indices - actual VSI pointers are maintained in the PF structure
+ * When assigned, these will be non-zero, because VSI 0 is always
+ * the main LAN VSI for the PF.
+ */
+ u16 lan_vsi_num; /* ID as used by firmware */
+ unsigned int tx_rate; /* Tx bandwidth limit in Mbps */
+ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */
+
+ u64 num_mdd_events; /* number of MDD events detected */
+ u64 num_inval_msgs; /* number of continuous invalid msgs */
+ u64 num_valid_msgs; /* number of valid msgs detected */
+ unsigned long vf_caps; /* VF's adv. capabilities */
+ u8 num_req_qs; /* num of queue pairs requested by VF */
+ u16 num_mac;
+ u16 num_vlan;
+ u16 num_vf_qs; /* num of queue configured per VF */
+ u16 num_qs_ena; /* total num of Tx/Rx queue enabled */
+};
+
+#ifdef CONFIG_PCI_IOV
+void ice_process_vflr_event(struct ice_pf *pf);
+int ice_sriov_configure(struct pci_dev *pdev, int num_vfs);
+int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac);
+int
+ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi);
+
+void ice_free_vfs(struct ice_pf *pf);
+void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event);
+void ice_vc_notify_link_state(struct ice_pf *pf);
+void ice_vc_notify_reset(struct ice_pf *pf);
+bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr);
+
+int
+ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
+ __be16 vlan_proto);
+
+int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted);
+
+int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state);
+
+int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena);
+
+int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector);
+
+void ice_set_vf_state_qs_dis(struct ice_vf *vf);
+#else /* CONFIG_PCI_IOV */
+#define ice_process_vflr_event(pf) do {} while (0)
+#define ice_free_vfs(pf) do {} while (0)
+#define ice_vc_process_vf_msg(pf, event) do {} while (0)
+#define ice_vc_notify_link_state(pf) do {} while (0)
+#define ice_vc_notify_reset(pf) do {} while (0)
+#define ice_set_vf_state_qs_dis(vf) do {} while (0)
+
+static inline bool
+ice_reset_all_vfs(struct ice_pf __always_unused *pf,
+ bool __always_unused is_vflr)
+{
+ return true;
+}
+
+static inline int
+ice_sriov_configure(struct pci_dev __always_unused *pdev,
+ int __always_unused num_vfs)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_set_vf_mac(struct net_device __always_unused *netdev,
+ int __always_unused vf_id, u8 __always_unused *mac)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_get_vf_cfg(struct net_device __always_unused *netdev,
+ int __always_unused vf_id,
+ struct ifla_vf_info __always_unused *ivi)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_set_vf_trust(struct net_device __always_unused *netdev,
+ int __always_unused vf_id, bool __always_unused trusted)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_set_vf_port_vlan(struct net_device __always_unused *netdev,
+ int __always_unused vf_id, u16 __always_unused vid,
+ u8 __always_unused qos, __be16 __always_unused v_proto)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_set_vf_spoofchk(struct net_device __always_unused *netdev,
+ int __always_unused vf_id, bool __always_unused ena)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_set_vf_link_state(struct net_device __always_unused *netdev,
+ int __always_unused vf_id, int __always_unused link_state)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf,
+ struct ice_q_vector __always_unused *q_vector)
+{
+ return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+#endif /* _ICE_VIRTCHNL_PF_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index bafdcf7..8a6ef35 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -466,7 +466,7 @@
? igb_setup_copper_link_82575
: igb_setup_serdes_link_82575;
- if (mac->type == e1000_82580) {
+ if (mac->type == e1000_82580 || mac->type == e1000_i350) {
switch (hw->device_id) {
/* feature not supported on these id's */
case E1000_DEV_ID_DH89XXCC_SGMII:
@@ -638,7 +638,7 @@
dev_spec->sgmii_active = true;
break;
}
- /* fall through for I2C based SGMII */
+ /* fall through - for I2C based SGMII */
case E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES:
/* read media type from SFP EEPROM */
ret_val = igb_set_sfp_media_type_82575(hw);
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 8a28f33..d2e2c50 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -194,6 +194,8 @@
/* enable link status from external LINK_0 and LINK_1 pins */
#define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */
#define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */
+#define E1000_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */
+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */
#define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */
#define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */
#define E1000_CTRL_RST 0x04000000 /* Global reset */
@@ -334,6 +336,7 @@
#define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */
#define I210_RXPBSIZE_MASK 0x0000003F
+#define I210_RXPBSIZE_PB_30KB 0x0000001E
#define I210_RXPBSIZE_PB_32KB 0x00000020
#define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */
#define I210_TXPBSIZE_MASK 0xC0FFFFFF
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 0ad737d..9cb4998 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -409,6 +409,8 @@
#define E1000_I210_TQAVCC(_n) (0x3004 + ((_n) * 0x40))
#define E1000_I210_TQAVHC(_n) (0x300C + ((_n) * 0x40))
+#define E1000_I210_RR2DCDELAY 0x5BF4
+
#define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n))
#define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 5acf3b7..3182b05 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -448,7 +448,7 @@
static int igb_get_regs_len(struct net_device *netdev)
{
-#define IGB_REGS_LEN 739
+#define IGB_REGS_LEN 740
return IGB_REGS_LEN * sizeof(u32);
}
@@ -675,41 +675,44 @@
regs_buff[554] = adapter->stats.b2ogprc;
}
- if (hw->mac.type != e1000_82576)
- return;
- for (i = 0; i < 12; i++)
- regs_buff[555 + i] = rd32(E1000_SRRCTL(i + 4));
- for (i = 0; i < 4; i++)
- regs_buff[567 + i] = rd32(E1000_PSRTYPE(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[571 + i] = rd32(E1000_RDBAL(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[583 + i] = rd32(E1000_RDBAH(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[595 + i] = rd32(E1000_RDLEN(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[607 + i] = rd32(E1000_RDH(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[619 + i] = rd32(E1000_RDT(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[631 + i] = rd32(E1000_RXDCTL(i + 4));
+ if (hw->mac.type == e1000_82576) {
+ for (i = 0; i < 12; i++)
+ regs_buff[555 + i] = rd32(E1000_SRRCTL(i + 4));
+ for (i = 0; i < 4; i++)
+ regs_buff[567 + i] = rd32(E1000_PSRTYPE(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[571 + i] = rd32(E1000_RDBAL(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[583 + i] = rd32(E1000_RDBAH(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[595 + i] = rd32(E1000_RDLEN(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[607 + i] = rd32(E1000_RDH(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[619 + i] = rd32(E1000_RDT(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[631 + i] = rd32(E1000_RXDCTL(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[643 + i] = rd32(E1000_TDBAL(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[655 + i] = rd32(E1000_TDBAH(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[667 + i] = rd32(E1000_TDLEN(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[679 + i] = rd32(E1000_TDH(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[691 + i] = rd32(E1000_TDT(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[703 + i] = rd32(E1000_TXDCTL(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[715 + i] = rd32(E1000_TDWBAL(i + 4));
- for (i = 0; i < 12; i++)
- regs_buff[727 + i] = rd32(E1000_TDWBAH(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[643 + i] = rd32(E1000_TDBAL(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[655 + i] = rd32(E1000_TDBAH(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[667 + i] = rd32(E1000_TDLEN(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[679 + i] = rd32(E1000_TDH(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[691 + i] = rd32(E1000_TDT(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[703 + i] = rd32(E1000_TXDCTL(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[715 + i] = rd32(E1000_TDWBAL(i + 4));
+ for (i = 0; i < 12; i++)
+ regs_buff[727 + i] = rd32(E1000_TDWBAH(i + 4));
+ }
+
+ if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211)
+ regs_buff[739] = rd32(E1000_I210_RR2DCDELAY);
}
static int igb_get_eeprom_len(struct net_device *netdev)
@@ -2113,7 +2116,7 @@
{
struct igb_adapter *adapter = netdev_priv(netdev);
- if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
+ if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER))
return -EOPNOTSUPP;
if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED))
@@ -3158,8 +3161,8 @@
} else if (!edata->eee_enabled) {
dev_err(&adapter->pdev->dev,
"Setting EEE options are not supported with EEE disabled\n");
- return -EINVAL;
- }
+ return -EINVAL;
+ }
adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised);
if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 0796cef..ed7e667 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -39,7 +39,7 @@
#include "igb.h"
#define MAJ 5
-#define MIN 4
+#define MIN 6
#define BUILD 0
#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
__stringify(BUILD) "-k"
@@ -239,7 +239,7 @@
MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
@@ -753,6 +753,8 @@
struct net_device *netdev = igb->netdev;
hw->hw_addr = NULL;
netdev_err(netdev, "PCIe link lost\n");
+ WARN(pci_device_is_present(igb->pdev),
+ "igb: Failed to read reg 0x%x!\n", reg);
}
return value;
@@ -1189,15 +1191,15 @@
{
struct igb_q_vector *q_vector;
struct igb_ring *ring;
- int ring_count, size;
+ int ring_count;
+ size_t size;
/* igb only supports 1 Tx and/or 1 Rx queue per vector */
if (txr_count > 1 || rxr_count > 1)
return -ENOMEM;
ring_count = txr_count + rxr_count;
- size = sizeof(struct igb_q_vector) +
- (sizeof(struct igb_ring) * ring_count);
+ size = struct_size(q_vector, ring, ring_count);
/* allocate q_vector and rings */
q_vector = adapter->q_vector[v_idx];
@@ -1850,13 +1852,12 @@
* configuration' in respect to these parameters.
*/
- netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
- idleslope %d sendslope %d hiCredit %d \
- locredit %d\n",
- (ring->cbs_enable) ? "enabled" : "disabled",
- (ring->launchtime_enable) ? "enabled" : "disabled", queue,
- ring->idleslope, ring->sendslope, ring->hicredit,
- ring->locredit);
+ netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
+ ring->cbs_enable ? "enabled" : "disabled",
+ ring->launchtime_enable ? "enabled" : "disabled",
+ queue,
+ ring->idleslope, ring->sendslope,
+ ring->hicredit, ring->locredit);
}
static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
@@ -1935,7 +1936,7 @@
val = rd32(E1000_RXPBS);
val &= ~I210_RXPBSIZE_MASK;
- val |= I210_RXPBSIZE_PB_32KB;
+ val |= I210_RXPBSIZE_PB_30KB;
wr32(E1000_RXPBS, val);
/* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ
@@ -2064,7 +2065,8 @@
if ((hw->phy.media_type == e1000_media_type_copper) &&
(!(connsw & E1000_CONNSW_AUTOSENSE_EN))) {
swap_now = true;
- } else if (!(connsw & E1000_CONNSW_SERDESD)) {
+ } else if ((hw->phy.media_type != e1000_media_type_copper) &&
+ !(connsw & E1000_CONNSW_SERDESD)) {
/* copper signal takes time to appear */
if (adapter->copper_tries < 4) {
adapter->copper_tries++;
@@ -2370,7 +2372,7 @@
adapter->ei.get_invariants(hw);
adapter->flags &= ~IGB_FLAG_MEDIA_RESET;
}
- if ((mac->type == e1000_82575) &&
+ if ((mac->type == e1000_82575 || mac->type == e1000_i350) &&
(adapter->flags & IGB_FLAG_MAS_ENABLE)) {
igb_enable_mas(adapter);
}
@@ -2481,13 +2483,14 @@
else
igb_reset(adapter);
- return 0;
+ return 1;
}
static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
/* guarantee we can provide a unique filter for the unicast address */
if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -2577,13 +2580,15 @@
#define VLAN_PRIO_FULL_MASK (0x07)
static int igb_parse_cls_flower(struct igb_adapter *adapter,
- struct tc_cls_flower_offload *f,
+ struct flow_cls_offload *f,
int traffic_class,
struct igb_nfc_filter *input)
{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+ struct flow_dissector *dissector = rule->match.dissector;
struct netlink_ext_ack *extack = f->common.extack;
- if (f->dissector->used_keys &
+ if (dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -2593,78 +2598,60 @@
return -EOPNOTSUPP;
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
- struct flow_dissector_key_eth_addrs *key, *mask;
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_match_eth_addrs match;
- key = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->key);
- mask = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->mask);
-
- if (!is_zero_ether_addr(mask->dst)) {
- if (!is_broadcast_ether_addr(mask->dst)) {
+ flow_rule_match_eth_addrs(rule, &match);
+ if (!is_zero_ether_addr(match.mask->dst)) {
+ if (!is_broadcast_ether_addr(match.mask->dst)) {
NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address");
return -EINVAL;
}
input->filter.match_flags |=
IGB_FILTER_FLAG_DST_MAC_ADDR;
- ether_addr_copy(input->filter.dst_addr, key->dst);
+ ether_addr_copy(input->filter.dst_addr, match.key->dst);
}
- if (!is_zero_ether_addr(mask->src)) {
- if (!is_broadcast_ether_addr(mask->src)) {
+ if (!is_zero_ether_addr(match.mask->src)) {
+ if (!is_broadcast_ether_addr(match.mask->src)) {
NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address");
return -EINVAL;
}
input->filter.match_flags |=
IGB_FILTER_FLAG_SRC_MAC_ADDR;
- ether_addr_copy(input->filter.src_addr, key->src);
+ ether_addr_copy(input->filter.src_addr, match.key->src);
}
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key, *mask;
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_match_basic match;
- key = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
- mask = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
-
- if (mask->n_proto) {
- if (mask->n_proto != ETHER_TYPE_FULL_MASK) {
+ flow_rule_match_basic(rule, &match);
+ if (match.mask->n_proto) {
+ if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) {
NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter");
return -EINVAL;
}
input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE;
- input->filter.etype = key->n_proto;
+ input->filter.etype = match.key->n_proto;
}
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
- struct flow_dissector_key_vlan *key, *mask;
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_match_vlan match;
- key = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->key);
- mask = skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->mask);
-
- if (mask->vlan_priority) {
- if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
+ flow_rule_match_vlan(rule, &match);
+ if (match.mask->vlan_priority) {
+ if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority");
return -EINVAL;
}
input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI;
- input->filter.vlan_tci = key->vlan_priority;
+ input->filter.vlan_tci = match.key->vlan_priority;
}
}
@@ -2675,7 +2662,7 @@
}
static int igb_configure_clsflower(struct igb_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct netlink_ext_ack *extack = cls_flower->common.extack;
struct igb_nfc_filter *filter, *f;
@@ -2737,7 +2724,7 @@
}
static int igb_delete_clsflower(struct igb_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct igb_nfc_filter *filter;
int err;
@@ -2767,14 +2754,14 @@
}
static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
switch (cls_flower->command) {
- case TC_CLSFLOWER_REPLACE:
+ case FLOW_CLS_REPLACE:
return igb_configure_clsflower(adapter, cls_flower);
- case TC_CLSFLOWER_DESTROY:
+ case FLOW_CLS_DESTROY:
return igb_delete_clsflower(adapter, cls_flower);
- case TC_CLSFLOWER_STATS:
+ case FLOW_CLS_STATS:
return -EOPNOTSUPP;
default:
return -EOPNOTSUPP;
@@ -2798,25 +2785,6 @@
}
}
-static int igb_setup_tc_block(struct igb_adapter *adapter,
- struct tc_block_offload *f)
-{
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int igb_offload_txtime(struct igb_adapter *adapter,
struct tc_etf_qopt_offload *qopt)
{
@@ -2840,6 +2808,8 @@
return 0;
}
+static LIST_HEAD(igb_block_cb_list);
+
static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
@@ -2849,7 +2819,11 @@
case TC_SETUP_QDISC_CBS:
return igb_offload_cbs(adapter, type_data);
case TC_SETUP_BLOCK:
- return igb_setup_tc_block(adapter, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &igb_block_cb_list,
+ igb_setup_tc_block_cb,
+ adapter, adapter, true);
+
case TC_SETUP_QDISC_ETF:
return igb_offload_txtime(adapter, type_data);
@@ -3468,6 +3442,9 @@
break;
}
}
+
+ dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP);
+
pm_runtime_put_noidle(&pdev->dev);
return 0;
@@ -4756,8 +4733,7 @@
{
u16 i = rx_ring->next_to_clean;
- if (rx_ring->skb)
- dev_kfree_skb(rx_ring->skb);
+ dev_kfree_skb(rx_ring->skb);
rx_ring->skb = NULL;
/* Free all the Rx ring sk_buffs */
@@ -5699,7 +5675,8 @@
* should have been handled by the upper layers.
*/
if (tx_ring->launchtime_enable) {
- ts = ns_to_timespec64(first->skb->tstamp);
+ ts = ktime_to_timespec64(first->skb->tstamp);
+ first->skb->tstamp = ktime_set(0, 0);
context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
} else {
context_desc->seqnum_seed = 0;
@@ -5942,7 +5919,7 @@
struct sk_buff *skb = first->skb;
struct igb_tx_buffer *tx_buffer;
union e1000_adv_tx_desc *tx_desc;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
dma_addr_t dma;
unsigned int data_len, size;
u32 tx_flags = first->tx_flags;
@@ -6019,6 +5996,8 @@
/* set the timestamp */
first->time_stamp = jiffies;
+ skb_tx_timestamp(skb);
+
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch. (Only applicable for weak-ordered
* memory model archs, such as IA-64).
@@ -6040,13 +6019,8 @@
/* Make sure there is space in the ring for the next send. */
igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return 0;
@@ -6101,7 +6075,8 @@
* otherwise try next time
*/
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
- count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+ count += TXD_USE_COUNT(skb_frag_size(
+ &skb_shinfo(skb)->frags[f]));
if (igb_maybe_stop_tx(tx_ring, count + 3)) {
/* this is a hard error */
@@ -6147,8 +6122,6 @@
else if (!tso)
igb_tx_csum(tx_ring, first);
- skb_tx_timestamp(skb);
-
if (igb_tx_map(tx_ring, first, hdr_len))
goto cleanup_tx_tstamp;
@@ -6713,7 +6686,7 @@
igb_setup_dca(adapter);
break;
}
- /* Fall Through since DCA is disabled. */
+ /* Fall Through - since DCA is disabled. */
case DCA_PROVIDER_REMOVE:
if (adapter->flags & IGB_FLAG_DCA_ENABLED) {
/* without this a class_device is left
@@ -7753,11 +7726,13 @@
if (!clean_complete)
return budget;
- /* If not enough Rx work done, exit the polling mode */
- napi_complete_done(napi, work_done);
- igb_ring_irq_enable(q_vector);
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ igb_ring_irq_enable(q_vector);
- return 0;
+ return min(work_done, budget - 1);
}
/**
@@ -8062,7 +8037,7 @@
/* Determine available headroom for copy */
headlen = size;
if (headlen > IGB_RX_HDR_LEN)
- headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
+ headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN);
/* align pull length to size of long to optimize memcpy performance */
memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
@@ -8754,9 +8729,7 @@
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, rctl, status;
u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
-#ifdef CONFIG_PM
- int retval = 0;
-#endif
+ bool wake;
rtnl_lock();
netif_device_detach(netdev);
@@ -8769,12 +8742,6 @@
igb_clear_interrupt_scheme(adapter);
rtnl_unlock();
-#ifdef CONFIG_PM
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-#endif
-
status = rd32(E1000_STATUS);
if (status & E1000_STATUS_LU)
wufc &= ~E1000_WUFC_LNKC;
@@ -8791,10 +8758,6 @@
}
ctrl = rd32(E1000_CTRL);
- /* advertise wake from D3Cold */
- #define E1000_CTRL_ADVD3WUC 0x00100000
- /* phy power management enable */
- #define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
ctrl |= E1000_CTRL_ADVD3WUC;
wr32(E1000_CTRL, ctrl);
@@ -8808,12 +8771,15 @@
wr32(E1000_WUFC, 0);
}
- *enable_wake = wufc || adapter->en_mng_pt;
- if (!*enable_wake)
+ wake = wufc || adapter->en_mng_pt;
+ if (!wake)
igb_power_down_link(adapter);
else
igb_power_up_link(adapter);
+ if (enable_wake)
+ *enable_wake = wake;
+
/* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant.
*/
@@ -8856,22 +8822,7 @@
static int __maybe_unused igb_suspend(struct device *dev)
{
- int retval;
- bool wake;
- struct pci_dev *pdev = to_pci_dev(dev);
-
- retval = __igb_shutdown(pdev, &wake, 0);
- if (retval)
- return retval;
-
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
-
- return 0;
+ return __igb_shutdown(to_pci_dev(dev), NULL, 0);
}
static int __maybe_unused igb_resume(struct device *dev)
@@ -8930,8 +8881,7 @@
static int __maybe_unused igb_runtime_idle(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct net_device *netdev = pci_get_drvdata(pdev);
+ struct net_device *netdev = dev_get_drvdata(dev);
struct igb_adapter *adapter = netdev_priv(netdev);
if (!igb_has_link(adapter))
@@ -8942,22 +8892,7 @@
static int __maybe_unused igb_runtime_suspend(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- int retval;
- bool wake;
-
- retval = __igb_shutdown(pdev, &wake, 1);
- if (retval)
- return retval;
-
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
-
- return 0;
+ return __igb_shutdown(to_pci_dev(dev), NULL, 1);
}
static int __maybe_unused igb_runtime_resume(struct device *dev)
@@ -9086,7 +9021,6 @@
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
pci_ers_result_t result;
- int err;
if (pci_enable_device_mem(pdev)) {
dev_err(&pdev->dev,
@@ -9110,14 +9044,6 @@
result = PCI_ERS_RESULT_RECOVERED;
}
- err = pci_cleanup_aer_uncorrect_error_status(pdev);
- if (err) {
- dev_err(&pdev->dev,
- "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n",
- err);
- /* non-fatal, continue */
- }
-
return result;
}
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 9f4d700..c39e921 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -51,9 +51,17 @@
*
* The 40 bit 82580 SYSTIM overflows every
* 2^40 * 10^-9 / 60 = 18.3 minutes.
+ *
+ * SYSTIM is converted to real time using a timecounter. As
+ * timecounter_cyc2time() allows old timestamps, the timecounter needs
+ * to be updated at least once per half of the SYSTIM interval.
+ * Scheduling of delayed work is not very accurate, and also the NIC
+ * clock can be adjusted to run up to 6% faster and the system clock
+ * up to 10% slower, so we aim for 6 minutes to be sure the actual
+ * interval in the NIC time is shorter than 9.16 minutes.
*/
-#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9)
+#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 6)
#define IGB_PTP_TX_TIMEOUT (HZ * 15)
#define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT)
#define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0)
@@ -269,17 +277,25 @@
return 0;
}
-static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
- struct timespec64 *ts)
+static int igb_ptp_gettimex_82576(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
ptp_caps);
+ struct e1000_hw *hw = &igb->hw;
unsigned long flags;
+ u32 lo, hi;
u64 ns;
spin_lock_irqsave(&igb->tmreg_lock, flags);
- ns = timecounter_read(&igb->tc);
+ ptp_read_system_prets(sts);
+ lo = rd32(E1000_SYSTIML);
+ ptp_read_system_postts(sts);
+ hi = rd32(E1000_SYSTIMH);
+
+ ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
spin_unlock_irqrestore(&igb->tmreg_lock, flags);
@@ -288,16 +304,50 @@
return 0;
}
-static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp,
- struct timespec64 *ts)
+static int igb_ptp_gettimex_82580(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
ptp_caps);
+ struct e1000_hw *hw = &igb->hw;
+ unsigned long flags;
+ u32 lo, hi;
+ u64 ns;
+
+ spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+ ptp_read_system_prets(sts);
+ rd32(E1000_SYSTIMR);
+ ptp_read_system_postts(sts);
+ lo = rd32(E1000_SYSTIML);
+ hi = rd32(E1000_SYSTIMH);
+
+ ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
+
+ spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+ *ts = ns_to_timespec64(ns);
+
+ return 0;
+}
+
+static int igb_ptp_gettimex_i210(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
+{
+ struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+ ptp_caps);
+ struct e1000_hw *hw = &igb->hw;
unsigned long flags;
spin_lock_irqsave(&igb->tmreg_lock, flags);
- igb_ptp_read_i210(igb, ts);
+ ptp_read_system_prets(sts);
+ rd32(E1000_SYSTIMR);
+ ptp_read_system_postts(sts);
+ ts->tv_nsec = rd32(E1000_SYSTIML);
+ ts->tv_sec = rd32(E1000_SYSTIMH);
spin_unlock_irqrestore(&igb->tmreg_lock, flags);
@@ -471,6 +521,19 @@
switch (rq->type) {
case PTP_CLK_REQ_EXTTS:
+ /* Reject requests with unsupported flags */
+ if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
+ PTP_RISING_EDGE |
+ PTP_FALLING_EDGE |
+ PTP_STRICT_FLAGS))
+ return -EOPNOTSUPP;
+
+ /* Reject requests failing to enable both edges. */
+ if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
+ (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+ (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
+ return -EOPNOTSUPP;
+
if (on) {
pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS,
rq->extts.index);
@@ -501,6 +564,10 @@
return 0;
case PTP_CLK_REQ_PEROUT:
+ /* Reject requests with unsupported flags */
+ if (rq->perout.flags)
+ return -EOPNOTSUPP;
+
if (on) {
pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT,
rq->perout.index);
@@ -650,9 +717,12 @@
struct igb_adapter *igb =
container_of(work, struct igb_adapter, ptp_overflow_work.work);
struct timespec64 ts;
+ u64 ns;
- igb->ptp_caps.gettime64(&igb->ptp_caps, &ts);
+ /* Update the timecounter */
+ ns = timecounter_read(&igb->tc);
+ ts = ns_to_timespec64(ns);
pr_debug("igb overflow check at %lld.%09lu\n",
(long long) ts.tv_sec, ts.tv_nsec);
@@ -1118,7 +1188,7 @@
adapter->ptp_caps.pps = 0;
adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576;
adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
- adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+ adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82576;
adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
adapter->ptp_caps.enable = igb_ptp_feature_enable;
adapter->cc.read = igb_ptp_read_82576;
@@ -1137,7 +1207,7 @@
adapter->ptp_caps.pps = 0;
adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
- adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+ adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82580;
adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
adapter->ptp_caps.enable = igb_ptp_feature_enable;
adapter->cc.read = igb_ptp_read_82580;
@@ -1165,7 +1235,7 @@
adapter->ptp_caps.pin_config = adapter->sdp_config;
adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
- adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210;
+ adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_i210;
adapter->ptp_caps.settime64 = igb_ptp_settime_i210;
adapter->ptp_caps.enable = igb_ptp_feature_enable_i210;
adapter->ptp_caps.verify = igb_ptp_verify_pin;
diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c
index 163e583..a3cd7ac 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.c
+++ b/drivers/net/ethernet/intel/igbvf/mbx.c
@@ -241,7 +241,7 @@
s32 err;
u16 i;
- WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+ lockdep_assert_held(&hw->mbx_lock);
/* lock the mailbox to prevent pf/vf race condition */
err = e1000_obtain_mbx_lock_vf(hw);
@@ -279,7 +279,7 @@
s32 err;
u16 i;
- WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+ lockdep_assert_held(&hw->mbx_lock);
/* lock the mailbox to prevent pf/vf race condition */
err = e1000_obtain_mbx_lock_vf(hw);
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index e0c989f..0f2b68f 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1186,10 +1186,13 @@
igbvf_clean_rx_irq(adapter, &work_done, budget);
- /* If not enough Rx work done, exit the polling mode */
- if (work_done < budget) {
- napi_complete_done(napi, work_done);
+ if (work_done == budget)
+ return budget;
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done))) {
if (adapter->requested_itr & 3)
igbvf_set_itr(adapter);
@@ -2171,7 +2174,7 @@
goto dma_error;
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
- const struct skb_frag_struct *frag;
+ const skb_frag_t *frag;
count++;
i++;
@@ -2276,10 +2279,6 @@
tx_ring->buffer_info[first].next_to_watch = tx_desc;
tx_ring->next_to_use = i;
writel(i, adapter->hw.hw_addr + tx_ring->tail);
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
@@ -3011,7 +3010,7 @@
MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
MODULE_DESCRIPTION("Intel(R) Gigabit Virtual Function Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
/* netdev.c */
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
new file mode 100644
index 0000000..88c6f88
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Intel Corporation
+
+#
+# Intel(R) I225-LM/I225-V 2.5G Ethernet Controller
+#
+
+obj-$(CONFIG_IGC) += igc.o
+
+igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
+igc_ethtool.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
new file mode 100644
index 0000000..7e16345
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -0,0 +1,528 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_H_
+#define _IGC_H_
+
+#include <linux/kobject.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+#include <linux/ethtool.h>
+#include <linux/sctp.h>
+
+#include "igc_hw.h"
+
+/* forward declaration */
+void igc_set_ethtool_ops(struct net_device *);
+
+struct igc_adapter;
+struct igc_ring;
+
+void igc_up(struct igc_adapter *adapter);
+void igc_down(struct igc_adapter *adapter);
+int igc_setup_tx_resources(struct igc_ring *ring);
+int igc_setup_rx_resources(struct igc_ring *ring);
+void igc_free_tx_resources(struct igc_ring *ring);
+void igc_free_rx_resources(struct igc_ring *ring);
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter);
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+ const u32 max_rss_queues);
+int igc_reinit_queues(struct igc_adapter *adapter);
+void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
+bool igc_has_link(struct igc_adapter *adapter);
+void igc_reset(struct igc_adapter *adapter);
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
+int igc_add_mac_steering_filter(struct igc_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags);
+int igc_del_mac_steering_filter(struct igc_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags);
+void igc_update_stats(struct igc_adapter *adapter);
+
+extern char igc_driver_name[];
+extern char igc_driver_version[];
+
+#define IGC_REGS_LEN 740
+#define IGC_RETA_SIZE 128
+
+/* Interrupt defines */
+#define IGC_START_ITR 648 /* ~6000 ints/sec */
+#define IGC_FLAG_HAS_MSI BIT(0)
+#define IGC_FLAG_QUEUE_PAIRS BIT(3)
+#define IGC_FLAG_DMAC BIT(4)
+#define IGC_FLAG_NEED_LINK_UPDATE BIT(9)
+#define IGC_FLAG_MEDIA_RESET BIT(10)
+#define IGC_FLAG_MAS_ENABLE BIT(12)
+#define IGC_FLAG_HAS_MSIX BIT(13)
+#define IGC_FLAG_VLAN_PROMISC BIT(15)
+#define IGC_FLAG_RX_LEGACY BIT(16)
+
+#define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6)
+#define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7)
+
+#define IGC_MRQC_ENABLE_RSS_MQ 0x00000002
+#define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000
+#define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000
+
+#define IGC_START_ITR 648 /* ~6000 ints/sec */
+#define IGC_4K_ITR 980
+#define IGC_20K_ITR 196
+#define IGC_70K_ITR 56
+
+#define IGC_DEFAULT_ITR 3 /* dynamic */
+#define IGC_MAX_ITR_USECS 10000
+#define IGC_MIN_ITR_USECS 10
+#define NON_Q_VECTORS 1
+#define MAX_MSIX_ENTRIES 10
+
+/* TX/RX descriptor defines */
+#define IGC_DEFAULT_TXD 256
+#define IGC_DEFAULT_TX_WORK 128
+#define IGC_MIN_TXD 80
+#define IGC_MAX_TXD 4096
+
+#define IGC_DEFAULT_RXD 256
+#define IGC_MIN_RXD 80
+#define IGC_MAX_RXD 4096
+
+/* Transmit and receive queues */
+#define IGC_MAX_RX_QUEUES 4
+#define IGC_MAX_TX_QUEUES 4
+
+#define MAX_Q_VECTORS 8
+#define MAX_STD_JUMBO_FRAME_SIZE 9216
+
+/* Supported Rx Buffer Sizes */
+#define IGC_RXBUFFER_256 256
+#define IGC_RXBUFFER_2048 2048
+#define IGC_RXBUFFER_3072 3072
+
+#define AUTO_ALL_MODES 0
+#define IGC_RX_HDR_LEN IGC_RXBUFFER_256
+
+/* RX and TX descriptor control thresholds.
+ * PTHRESH - MAC will consider prefetch if it has fewer than this number of
+ * descriptors available in its onboard memory.
+ * Setting this to 0 disables RX descriptor prefetch.
+ * HTHRESH - MAC will only prefetch if there are at least this many descriptors
+ * available in host memory.
+ * If PTHRESH is 0, this should also be 0.
+ * WTHRESH - RX descriptor writeback threshold - MAC will delay writing back
+ * descriptors until either it has this many to write back, or the
+ * ITR timer expires.
+ */
+#define IGC_RX_PTHRESH 8
+#define IGC_RX_HTHRESH 8
+#define IGC_TX_PTHRESH 8
+#define IGC_TX_HTHRESH 1
+#define IGC_RX_WTHRESH 4
+#define IGC_TX_WTHRESH 16
+
+#define IGC_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+#define IGC_TS_HDR_LEN 16
+
+#define IGC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+
+#if (PAGE_SIZE < 8192)
+#define IGC_MAX_FRAME_BUILD_SKB \
+ (SKB_WITH_OVERHEAD(IGC_RXBUFFER_2048) - IGC_SKB_PAD - IGC_TS_HDR_LEN)
+#else
+#define IGC_MAX_FRAME_BUILD_SKB (IGC_RXBUFFER_2048 - IGC_TS_HDR_LEN)
+#endif
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IGC_RX_BUFFER_WRITE 16 /* Must be power of 2 */
+
+/* VLAN info */
+#define IGC_TX_FLAGS_VLAN_MASK 0xffff0000
+
+/* igc_test_staterr - tests bits within Rx descriptor status and error fields */
+static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc,
+ const u32 stat_err_bits)
+{
+ return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits);
+}
+
+enum igc_state_t {
+ __IGC_TESTING,
+ __IGC_RESETTING,
+ __IGC_DOWN,
+ __IGC_PTP_TX_IN_PROGRESS,
+};
+
+enum igc_tx_flags {
+ /* cmd_type flags */
+ IGC_TX_FLAGS_VLAN = 0x01,
+ IGC_TX_FLAGS_TSO = 0x02,
+ IGC_TX_FLAGS_TSTAMP = 0x04,
+
+ /* olinfo flags */
+ IGC_TX_FLAGS_IPV4 = 0x10,
+ IGC_TX_FLAGS_CSUM = 0x20,
+};
+
+enum igc_boards {
+ board_base,
+};
+
+/* The largest size we can write to the descriptor is 65535. In order to
+ * maintain a power of two alignment we have to limit ourselves to 32K.
+ */
+#define IGC_MAX_TXD_PWR 15
+#define IGC_MAX_DATA_PER_TXD BIT(IGC_MAX_TXD_PWR)
+
+/* Tx Descriptors needed, worst case */
+#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD)
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
+
+/* wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct igc_tx_buffer {
+ union igc_adv_tx_desc *next_to_watch;
+ unsigned long time_stamp;
+ struct sk_buff *skb;
+ unsigned int bytecount;
+ u16 gso_segs;
+ __be16 protocol;
+
+ DEFINE_DMA_UNMAP_ADDR(dma);
+ DEFINE_DMA_UNMAP_LEN(len);
+ u32 tx_flags;
+};
+
+struct igc_rx_buffer {
+ dma_addr_t dma;
+ struct page *page;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+ __u32 page_offset;
+#else
+ __u16 page_offset;
+#endif
+ __u16 pagecnt_bias;
+};
+
+struct igc_tx_queue_stats {
+ u64 packets;
+ u64 bytes;
+ u64 restart_queue;
+ u64 restart_queue2;
+};
+
+struct igc_rx_queue_stats {
+ u64 packets;
+ u64 bytes;
+ u64 drops;
+ u64 csum_err;
+ u64 alloc_failed;
+};
+
+struct igc_rx_packet_stats {
+ u64 ipv4_packets; /* IPv4 headers processed */
+ u64 ipv4e_packets; /* IPv4E headers with extensions processed */
+ u64 ipv6_packets; /* IPv6 headers processed */
+ u64 ipv6e_packets; /* IPv6E headers with extensions processed */
+ u64 tcp_packets; /* TCP headers processed */
+ u64 udp_packets; /* UDP headers processed */
+ u64 sctp_packets; /* SCTP headers processed */
+ u64 nfs_packets; /* NFS headers processe */
+ u64 other_packets;
+};
+
+struct igc_ring_container {
+ struct igc_ring *ring; /* pointer to linked list of rings */
+ unsigned int total_bytes; /* total bytes processed this int */
+ unsigned int total_packets; /* total packets processed this int */
+ u16 work_limit; /* total work allowed per interrupt */
+ u8 count; /* total number of rings in vector */
+ u8 itr; /* current ITR setting for ring */
+};
+
+struct igc_ring {
+ struct igc_q_vector *q_vector; /* backlink to q_vector */
+ struct net_device *netdev; /* back pointer to net_device */
+ struct device *dev; /* device for dma mapping */
+ union { /* array of buffer info structs */
+ struct igc_tx_buffer *tx_buffer_info;
+ struct igc_rx_buffer *rx_buffer_info;
+ };
+ void *desc; /* descriptor ring memory */
+ unsigned long flags; /* ring specific flags */
+ void __iomem *tail; /* pointer to ring tail register */
+ dma_addr_t dma; /* phys address of the ring */
+ unsigned int size; /* length of desc. ring in bytes */
+
+ u16 count; /* number of desc. in the ring */
+ u8 queue_index; /* logical index of the ring*/
+ u8 reg_idx; /* physical index of the ring */
+ bool launchtime_enable; /* true if LaunchTime is enabled */
+
+ /* everything past this point are written often */
+ u16 next_to_clean;
+ u16 next_to_use;
+ u16 next_to_alloc;
+
+ union {
+ /* TX */
+ struct {
+ struct igc_tx_queue_stats tx_stats;
+ struct u64_stats_sync tx_syncp;
+ struct u64_stats_sync tx_syncp2;
+ };
+ /* RX */
+ struct {
+ struct igc_rx_queue_stats rx_stats;
+ struct igc_rx_packet_stats pkt_stats;
+ struct u64_stats_sync rx_syncp;
+ struct sk_buff *skb;
+ };
+ };
+} ____cacheline_internodealigned_in_smp;
+
+struct igc_q_vector {
+ struct igc_adapter *adapter; /* backlink */
+ void __iomem *itr_register;
+ u32 eims_value; /* EIMS mask value */
+
+ u16 itr_val;
+ u8 set_itr;
+
+ struct igc_ring_container rx, tx;
+
+ struct napi_struct napi;
+
+ struct rcu_head rcu; /* to avoid race with update stats on free */
+ char name[IFNAMSIZ + 9];
+ struct net_device poll_dev;
+
+ /* for dynamic allocation of rings associated with this q_vector */
+ struct igc_ring ring[0] ____cacheline_internodealigned_in_smp;
+};
+
+#define MAX_ETYPE_FILTER (4 - 1)
+
+enum igc_filter_match_flags {
+ IGC_FILTER_FLAG_ETHER_TYPE = 0x1,
+ IGC_FILTER_FLAG_VLAN_TCI = 0x2,
+ IGC_FILTER_FLAG_SRC_MAC_ADDR = 0x4,
+ IGC_FILTER_FLAG_DST_MAC_ADDR = 0x8,
+};
+
+/* RX network flow classification data structure */
+struct igc_nfc_input {
+ /* Byte layout in order, all values with MSB first:
+ * match_flags - 1 byte
+ * etype - 2 bytes
+ * vlan_tci - 2 bytes
+ */
+ u8 match_flags;
+ __be16 etype;
+ __be16 vlan_tci;
+ u8 src_addr[ETH_ALEN];
+ u8 dst_addr[ETH_ALEN];
+};
+
+struct igc_nfc_filter {
+ struct hlist_node nfc_node;
+ struct igc_nfc_input filter;
+ unsigned long cookie;
+ u16 etype_reg_index;
+ u16 sw_idx;
+ u16 action;
+};
+
+struct igc_mac_addr {
+ u8 addr[ETH_ALEN];
+ u8 queue;
+ u8 state; /* bitmask */
+};
+
+#define IGC_MAC_STATE_DEFAULT 0x1
+#define IGC_MAC_STATE_IN_USE 0x2
+#define IGC_MAC_STATE_SRC_ADDR 0x4
+#define IGC_MAC_STATE_QUEUE_STEERING 0x8
+
+#define IGC_MAX_RXNFC_FILTERS 16
+
+/* Board specific private data structure */
+struct igc_adapter {
+ struct net_device *netdev;
+
+ unsigned long state;
+ unsigned int flags;
+ unsigned int num_q_vectors;
+
+ struct msix_entry *msix_entries;
+
+ /* TX */
+ u16 tx_work_limit;
+ u32 tx_timeout_count;
+ int num_tx_queues;
+ struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES];
+
+ /* RX */
+ int num_rx_queues;
+ struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES];
+
+ struct timer_list watchdog_timer;
+ struct timer_list dma_err_timer;
+ struct timer_list phy_info_timer;
+
+ u16 link_speed;
+ u16 link_duplex;
+
+ u8 port_num;
+
+ u8 __iomem *io_addr;
+ /* Interrupt Throttle Rate */
+ u32 rx_itr_setting;
+ u32 tx_itr_setting;
+
+ struct work_struct reset_task;
+ struct work_struct watchdog_task;
+ struct work_struct dma_err_task;
+ bool fc_autoneg;
+
+ u8 tx_timeout_factor;
+
+ int msg_enable;
+ u32 max_frame_size;
+ u32 min_frame_size;
+
+ /* OS defined structs */
+ struct pci_dev *pdev;
+ /* lock for statistics */
+ spinlock_t stats64_lock;
+ struct rtnl_link_stats64 stats64;
+
+ /* structs defined in igc_hw.h */
+ struct igc_hw hw;
+ struct igc_hw_stats stats;
+
+ struct igc_q_vector *q_vector[MAX_Q_VECTORS];
+ u32 eims_enable_mask;
+ u32 eims_other;
+
+ u16 tx_ring_count;
+ u16 rx_ring_count;
+
+ u32 tx_hwtstamp_timeouts;
+ u32 tx_hwtstamp_skipped;
+ u32 rx_hwtstamp_cleared;
+ u32 *shadow_vfta;
+
+ u32 rss_queues;
+ u32 rss_indir_tbl_init;
+
+ /* RX network flow classification support */
+ struct hlist_head nfc_filter_list;
+ struct hlist_head cls_flower_list;
+ unsigned int nfc_filter_count;
+
+ /* lock for RX network flow classification filter */
+ spinlock_t nfc_lock;
+ bool etype_bitmap[MAX_ETYPE_FILTER];
+
+ struct igc_mac_addr *mac_table;
+
+ u8 rss_indir_tbl[IGC_RETA_SIZE];
+
+ unsigned long link_check_timeout;
+ struct igc_info ei;
+};
+
+/* igc_desc_unused - calculate if we have unused descriptors */
+static inline u16 igc_desc_unused(const struct igc_ring *ring)
+{
+ u16 ntc = ring->next_to_clean;
+ u16 ntu = ring->next_to_use;
+
+ return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1;
+}
+
+static inline s32 igc_get_phy_info(struct igc_hw *hw)
+{
+ if (hw->phy.ops.get_phy_info)
+ return hw->phy.ops.get_phy_info(hw);
+
+ return 0;
+}
+
+static inline s32 igc_reset_phy(struct igc_hw *hw)
+{
+ if (hw->phy.ops.reset)
+ return hw->phy.ops.reset(hw);
+
+ return 0;
+}
+
+static inline struct netdev_queue *txring_txq(const struct igc_ring *tx_ring)
+{
+ return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
+}
+
+enum igc_ring_flags_t {
+ IGC_RING_FLAG_RX_3K_BUFFER,
+ IGC_RING_FLAG_RX_BUILD_SKB_ENABLED,
+ IGC_RING_FLAG_RX_SCTP_CSUM,
+ IGC_RING_FLAG_RX_LB_VLAN_BSWAP,
+ IGC_RING_FLAG_TX_CTX_IDX,
+ IGC_RING_FLAG_TX_DETECT_HANG
+};
+
+#define ring_uses_large_buffer(ring) \
+ test_bit(IGC_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+
+#define ring_uses_build_skb(ring) \
+ test_bit(IGC_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
+static inline unsigned int igc_rx_bufsz(struct igc_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring_uses_large_buffer(ring))
+ return IGC_RXBUFFER_3072;
+
+ if (ring_uses_build_skb(ring))
+ return IGC_MAX_FRAME_BUILD_SKB + IGC_TS_HDR_LEN;
+#endif
+ return IGC_RXBUFFER_2048;
+}
+
+static inline unsigned int igc_rx_pg_order(struct igc_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring_uses_large_buffer(ring))
+ return 1;
+#endif
+ return 0;
+}
+
+static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
+{
+ if (hw->phy.ops.read_reg)
+ return hw->phy.ops.read_reg(hw, offset, data);
+
+ return 0;
+}
+
+/* forward declaration */
+void igc_reinit_locked(struct igc_adapter *);
+int igc_add_filter(struct igc_adapter *adapter,
+ struct igc_nfc_filter *input);
+int igc_erase_filter(struct igc_adapter *adapter,
+ struct igc_nfc_filter *input);
+
+#define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
+
+#define IGC_TXD_DCMD (IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS)
+
+#define IGC_RX_DESC(R, i) \
+ (&(((union igc_adv_rx_desc *)((R)->desc))[i]))
+#define IGC_TX_DESC(R, i) \
+ (&(((union igc_adv_tx_desc *)((R)->desc))[i]))
+#define IGC_TX_CTXTDESC(R, i) \
+ (&(((struct igc_adv_tx_context_desc *)((R)->desc))[i]))
+
+#endif /* _IGC_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
new file mode 100644
index 0000000..db289bc
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include <linux/delay.h>
+
+#include "igc_hw.h"
+#include "igc_i225.h"
+#include "igc_mac.h"
+#include "igc_base.h"
+#include "igc.h"
+
+/**
+ * igc_reset_hw_base - Reset hardware
+ * @hw: pointer to the HW structure
+ *
+ * This resets the hardware into a known state. This is a
+ * function pointer entry point called by the api module.
+ */
+static s32 igc_reset_hw_base(struct igc_hw *hw)
+{
+ s32 ret_val;
+ u32 ctrl;
+
+ /* Prevent the PCI-E bus from sticking if there is no TLP connection
+ * on the last TLP read/write transaction when MAC is reset.
+ */
+ ret_val = igc_disable_pcie_master(hw);
+ if (ret_val)
+ hw_dbg("PCI-E Master disable polling has failed.\n");
+
+ hw_dbg("Masking off all interrupts\n");
+ wr32(IGC_IMC, 0xffffffff);
+
+ wr32(IGC_RCTL, 0);
+ wr32(IGC_TCTL, IGC_TCTL_PSP);
+ wrfl();
+
+ usleep_range(10000, 20000);
+
+ ctrl = rd32(IGC_CTRL);
+
+ hw_dbg("Issuing a global reset to MAC\n");
+ wr32(IGC_CTRL, ctrl | IGC_CTRL_DEV_RST);
+
+ ret_val = igc_get_auto_rd_done(hw);
+ if (ret_val) {
+ /* When auto config read does not complete, do not
+ * return with an error. This can happen in situations
+ * where there is no eeprom and prevents getting link.
+ */
+ hw_dbg("Auto Read Done did not complete\n");
+ }
+
+ /* Clear any pending interrupt events. */
+ wr32(IGC_IMC, 0xffffffff);
+ rd32(IGC_ICR);
+
+ return ret_val;
+}
+
+/**
+ * igc_init_nvm_params_base - Init NVM func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_nvm_params_base(struct igc_hw *hw)
+{
+ struct igc_nvm_info *nvm = &hw->nvm;
+ u32 eecd = rd32(IGC_EECD);
+ u16 size;
+
+ size = (u16)((eecd & IGC_EECD_SIZE_EX_MASK) >>
+ IGC_EECD_SIZE_EX_SHIFT);
+
+ /* Added to a constant, "size" becomes the left-shift value
+ * for setting word_size.
+ */
+ size += NVM_WORD_SIZE_BASE_SHIFT;
+
+ /* Just in case size is out of range, cap it to the largest
+ * EEPROM size supported
+ */
+ if (size > 15)
+ size = 15;
+
+ nvm->type = igc_nvm_eeprom_spi;
+ nvm->word_size = BIT(size);
+ nvm->opcode_bits = 8;
+ nvm->delay_usec = 1;
+
+ nvm->page_size = eecd & IGC_EECD_ADDR_BITS ? 32 : 8;
+ nvm->address_bits = eecd & IGC_EECD_ADDR_BITS ?
+ 16 : 8;
+
+ if (nvm->word_size == BIT(15))
+ nvm->page_size = 128;
+
+ return 0;
+}
+
+/**
+ * igc_setup_copper_link_base - Configure copper link settings
+ * @hw: pointer to the HW structure
+ *
+ * Configures the link for auto-neg or forced speed and duplex. Then we check
+ * for link, once link is established calls to configure collision distance
+ * and flow control are called.
+ */
+static s32 igc_setup_copper_link_base(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+ u32 ctrl;
+
+ ctrl = rd32(IGC_CTRL);
+ ctrl |= IGC_CTRL_SLU;
+ ctrl &= ~(IGC_CTRL_FRCSPD | IGC_CTRL_FRCDPX);
+ wr32(IGC_CTRL, ctrl);
+
+ ret_val = igc_setup_copper_link(hw);
+
+ return ret_val;
+}
+
+/**
+ * igc_init_mac_params_base - Init MAC func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_mac_params_base(struct igc_hw *hw)
+{
+ struct igc_dev_spec_base *dev_spec = &hw->dev_spec._base;
+ struct igc_mac_info *mac = &hw->mac;
+
+ /* Set mta register count */
+ mac->mta_reg_count = 128;
+ mac->rar_entry_count = IGC_RAR_ENTRIES;
+
+ /* reset */
+ mac->ops.reset_hw = igc_reset_hw_base;
+
+ mac->ops.acquire_swfw_sync = igc_acquire_swfw_sync_i225;
+ mac->ops.release_swfw_sync = igc_release_swfw_sync_i225;
+
+ /* Allow a single clear of the SW semaphore on I225 */
+ if (mac->type == igc_i225)
+ dev_spec->clear_semaphore_once = true;
+
+ /* physical interface link setup */
+ mac->ops.setup_physical_interface = igc_setup_copper_link_base;
+
+ return 0;
+}
+
+/**
+ * igc_init_phy_params_base - Init PHY func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_phy_params_base(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ s32 ret_val = 0;
+
+ if (hw->phy.media_type != igc_media_type_copper) {
+ phy->type = igc_phy_none;
+ goto out;
+ }
+
+ phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT_2500;
+ phy->reset_delay_us = 100;
+
+ /* set lan id */
+ hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >>
+ IGC_STATUS_FUNC_SHIFT;
+
+ /* Make sure the PHY is in a good state. Several people have reported
+ * firmware leaving the PHY's page select register set to something
+ * other than the default of zero, which causes the PHY ID read to
+ * access something other than the intended register.
+ */
+ ret_val = hw->phy.ops.reset(hw);
+ if (ret_val) {
+ hw_dbg("Error resetting the PHY.\n");
+ goto out;
+ }
+
+ ret_val = igc_get_phy_id(hw);
+ if (ret_val)
+ return ret_val;
+
+ igc_check_for_copper_link(hw);
+
+ /* Verify phy id and set remaining function pointers */
+ switch (phy->id) {
+ case I225_I_PHY_ID:
+ phy->type = igc_phy_i225;
+ break;
+ default:
+ ret_val = -IGC_ERR_PHY;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+static s32 igc_get_invariants_base(struct igc_hw *hw)
+{
+ struct igc_mac_info *mac = &hw->mac;
+ s32 ret_val = 0;
+
+ switch (hw->device_id) {
+ case IGC_DEV_ID_I225_LM:
+ case IGC_DEV_ID_I225_V:
+ case IGC_DEV_ID_I225_I:
+ case IGC_DEV_ID_I220_V:
+ case IGC_DEV_ID_I225_K:
+ mac->type = igc_i225;
+ break;
+ default:
+ return -IGC_ERR_MAC_INIT;
+ }
+
+ hw->phy.media_type = igc_media_type_copper;
+
+ /* mac initialization and operations */
+ ret_val = igc_init_mac_params_base(hw);
+ if (ret_val)
+ goto out;
+
+ /* NVM initialization */
+ ret_val = igc_init_nvm_params_base(hw);
+ switch (hw->mac.type) {
+ case igc_i225:
+ ret_val = igc_init_nvm_params_i225(hw);
+ break;
+ default:
+ break;
+ }
+
+ /* setup PHY parameters */
+ ret_val = igc_init_phy_params_base(hw);
+ if (ret_val)
+ goto out;
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_acquire_phy_base - Acquire rights to access PHY
+ * @hw: pointer to the HW structure
+ *
+ * Acquire access rights to the correct PHY. This is a
+ * function pointer entry point called by the api module.
+ */
+static s32 igc_acquire_phy_base(struct igc_hw *hw)
+{
+ u16 mask = IGC_SWFW_PHY0_SM;
+
+ return hw->mac.ops.acquire_swfw_sync(hw, mask);
+}
+
+/**
+ * igc_release_phy_base - Release rights to access PHY
+ * @hw: pointer to the HW structure
+ *
+ * A wrapper to release access rights to the correct PHY. This is a
+ * function pointer entry point called by the api module.
+ */
+static void igc_release_phy_base(struct igc_hw *hw)
+{
+ u16 mask = IGC_SWFW_PHY0_SM;
+
+ hw->mac.ops.release_swfw_sync(hw, mask);
+}
+
+/**
+ * igc_init_hw_base - Initialize hardware
+ * @hw: pointer to the HW structure
+ *
+ * This inits the hardware readying it for operation.
+ */
+static s32 igc_init_hw_base(struct igc_hw *hw)
+{
+ struct igc_mac_info *mac = &hw->mac;
+ u16 i, rar_count = mac->rar_entry_count;
+ s32 ret_val = 0;
+
+ /* Setup the receive address */
+ igc_init_rx_addrs(hw, rar_count);
+
+ /* Zero out the Multicast HASH table */
+ hw_dbg("Zeroing the MTA\n");
+ for (i = 0; i < mac->mta_reg_count; i++)
+ array_wr32(IGC_MTA, i, 0);
+
+ /* Zero out the Unicast HASH table */
+ hw_dbg("Zeroing the UTA\n");
+ for (i = 0; i < mac->uta_reg_count; i++)
+ array_wr32(IGC_UTA, i, 0);
+
+ /* Setup link and flow control */
+ ret_val = igc_setup_link(hw);
+
+ /* Clear all of the statistics registers (clear on read). It is
+ * important that we do this after we have tried to establish link
+ * because the symbol error count will increment wildly if there
+ * is no link.
+ */
+ igc_clear_hw_cntrs_base(hw);
+
+ return ret_val;
+}
+
+/**
+ * igc_power_down_phy_copper_base - Remove link during PHY power down
+ * @hw: pointer to the HW structure
+ *
+ * In the case of a PHY power down to save power, or to turn off link during a
+ * driver unload, or wake on lan is not enabled, remove the link.
+ */
+void igc_power_down_phy_copper_base(struct igc_hw *hw)
+{
+ /* If the management interface is not enabled, then power down */
+ if (!(igc_enable_mng_pass_thru(hw) || igc_check_reset_block(hw)))
+ igc_power_down_phy_copper(hw);
+}
+
+/**
+ * igc_rx_fifo_flush_base - Clean rx fifo after Rx enable
+ * @hw: pointer to the HW structure
+ *
+ * After Rx enable, if manageability is enabled then there is likely some
+ * bad data at the start of the fifo and possibly in the DMA fifo. This
+ * function clears the fifos and flushes any packets that came in as rx was
+ * being enabled.
+ */
+void igc_rx_fifo_flush_base(struct igc_hw *hw)
+{
+ u32 rctl, rlpml, rxdctl[4], rfctl, temp_rctl, rx_enabled;
+ int i, ms_wait;
+
+ /* disable IPv6 options as per hardware errata */
+ rfctl = rd32(IGC_RFCTL);
+ rfctl |= IGC_RFCTL_IPV6_EX_DIS;
+ wr32(IGC_RFCTL, rfctl);
+
+ if (!(rd32(IGC_MANC) & IGC_MANC_RCV_TCO_EN))
+ return;
+
+ /* Disable all Rx queues */
+ for (i = 0; i < 4; i++) {
+ rxdctl[i] = rd32(IGC_RXDCTL(i));
+ wr32(IGC_RXDCTL(i),
+ rxdctl[i] & ~IGC_RXDCTL_QUEUE_ENABLE);
+ }
+ /* Poll all queues to verify they have shut down */
+ for (ms_wait = 0; ms_wait < 10; ms_wait++) {
+ usleep_range(1000, 2000);
+ rx_enabled = 0;
+ for (i = 0; i < 4; i++)
+ rx_enabled |= rd32(IGC_RXDCTL(i));
+ if (!(rx_enabled & IGC_RXDCTL_QUEUE_ENABLE))
+ break;
+ }
+
+ if (ms_wait == 10)
+ pr_debug("Queue disable timed out after 10ms\n");
+
+ /* Clear RLPML, RCTL.SBP, RFCTL.LEF, and set RCTL.LPE so that all
+ * incoming packets are rejected. Set enable and wait 2ms so that
+ * any packet that was coming in as RCTL.EN was set is flushed
+ */
+ wr32(IGC_RFCTL, rfctl & ~IGC_RFCTL_LEF);
+
+ rlpml = rd32(IGC_RLPML);
+ wr32(IGC_RLPML, 0);
+
+ rctl = rd32(IGC_RCTL);
+ temp_rctl = rctl & ~(IGC_RCTL_EN | IGC_RCTL_SBP);
+ temp_rctl |= IGC_RCTL_LPE;
+
+ wr32(IGC_RCTL, temp_rctl);
+ wr32(IGC_RCTL, temp_rctl | IGC_RCTL_EN);
+ wrfl();
+ usleep_range(2000, 3000);
+
+ /* Enable Rx queues that were previously enabled and restore our
+ * previous state
+ */
+ for (i = 0; i < 4; i++)
+ wr32(IGC_RXDCTL(i), rxdctl[i]);
+ wr32(IGC_RCTL, rctl);
+ wrfl();
+
+ wr32(IGC_RLPML, rlpml);
+ wr32(IGC_RFCTL, rfctl);
+
+ /* Flush receive errors generated by workaround */
+ rd32(IGC_ROC);
+ rd32(IGC_RNBC);
+ rd32(IGC_MPC);
+}
+
+static struct igc_mac_operations igc_mac_ops_base = {
+ .init_hw = igc_init_hw_base,
+ .check_for_link = igc_check_for_copper_link,
+ .rar_set = igc_rar_set,
+ .read_mac_addr = igc_read_mac_addr,
+ .get_speed_and_duplex = igc_get_speed_and_duplex_copper,
+};
+
+static const struct igc_phy_operations igc_phy_ops_base = {
+ .acquire = igc_acquire_phy_base,
+ .release = igc_release_phy_base,
+ .reset = igc_phy_hw_reset,
+ .read_reg = igc_read_phy_reg_gpy,
+ .write_reg = igc_write_phy_reg_gpy,
+};
+
+const struct igc_info igc_base_info = {
+ .get_invariants = igc_get_invariants_base,
+ .mac_ops = &igc_mac_ops_base,
+ .phy_ops = &igc_phy_ops_base,
+};
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
new file mode 100644
index 0000000..ea627ce
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_BASE_H_
+#define _IGC_BASE_H_
+
+/* forward declaration */
+void igc_rx_fifo_flush_base(struct igc_hw *hw);
+void igc_power_down_phy_copper_base(struct igc_hw *hw);
+
+/* Transmit Descriptor - Advanced */
+union igc_adv_tx_desc {
+ struct {
+ __le64 buffer_addr; /* Address of descriptor's data buf */
+ __le32 cmd_type_len;
+ __le32 olinfo_status;
+ } read;
+ struct {
+ __le64 rsvd; /* Reserved */
+ __le32 nxtseq_seed;
+ __le32 status;
+ } wb;
+};
+
+/* Context descriptors */
+struct igc_adv_tx_context_desc {
+ __le32 vlan_macip_lens;
+ __le32 launch_time;
+ __le32 type_tucmd_mlhl;
+ __le32 mss_l4len_idx;
+};
+
+/* Adv Transmit Descriptor Config Masks */
+#define IGC_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE1588 Timestamp packet */
+#define IGC_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */
+#define IGC_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */
+#define IGC_ADVTXD_DCMD_EOP 0x01000000 /* End of Packet */
+#define IGC_ADVTXD_DCMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */
+#define IGC_ADVTXD_DCMD_RS 0x08000000 /* Report Status */
+#define IGC_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor extension (1=Adv) */
+#define IGC_ADVTXD_DCMD_VLE 0x40000000 /* VLAN pkt enable */
+#define IGC_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */
+#define IGC_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */
+
+#define IGC_RAR_ENTRIES 16
+
+/* Receive Descriptor - Advanced */
+union igc_adv_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ } read;
+ struct {
+ struct {
+ union {
+ __le32 data;
+ struct {
+ __le16 pkt_info; /*RSS type, Pkt type*/
+ /* Split Header, header buffer len */
+ __le16 hdr_info;
+ } hs_rss;
+ } lo_dword;
+ union {
+ __le32 rss; /* RSS Hash */
+ struct {
+ __le16 ip_id; /* IP id */
+ __le16 csum; /* Packet Checksum */
+ } csum_ip;
+ } hi_dword;
+ } lower;
+ struct {
+ __le32 status_error; /* ext status/error */
+ __le16 length; /* Packet length */
+ __le16 vlan; /* VLAN tag */
+ } upper;
+ } wb; /* writeback */
+};
+
+/* Additional Transmit Descriptor Control definitions */
+#define IGC_TXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Tx Queue */
+
+/* Additional Receive Descriptor Control definitions */
+#define IGC_RXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Rx Queue */
+
+/* SRRCTL bit definitions */
+#define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */
+#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */
+#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000
+
+#endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
new file mode 100644
index 0000000..f3f2325
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -0,0 +1,405 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_DEFINES_H_
+#define _IGC_DEFINES_H_
+
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define REQ_TX_DESCRIPTOR_MULTIPLE 8
+#define REQ_RX_DESCRIPTOR_MULTIPLE 8
+
+#define IGC_CTRL_EXT_DRV_LOAD 0x10000000 /* Drv loaded bit for FW */
+
+/* Physical Func Reset Done Indication */
+#define IGC_CTRL_EXT_LINK_MODE_MASK 0x00C00000
+
+/* Loop limit on how long we wait for auto-negotiation to complete */
+#define COPPER_LINK_UP_LIMIT 10
+#define PHY_AUTO_NEG_LIMIT 45
+#define PHY_FORCE_LIMIT 20
+
+/* Number of 100 microseconds we wait for PCI Express master disable */
+#define MASTER_DISABLE_TIMEOUT 800
+/*Blocks new Master requests */
+#define IGC_CTRL_GIO_MASTER_DISABLE 0x00000004
+/* Status of Master requests. */
+#define IGC_STATUS_GIO_MASTER_ENABLE 0x00080000
+
+/* Receive Address
+ * Number of high/low register pairs in the RAR. The RAR (Receive Address
+ * Registers) holds the directed and multicast addresses that we monitor.
+ * Technically, we have 16 spots. However, we reserve one of these spots
+ * (RAR[15]) for our directed address used by controllers with
+ * manageability enabled, allowing us room for 15 multicast addresses.
+ */
+#define IGC_RAH_AV 0x80000000 /* Receive descriptor valid */
+#define IGC_RAH_POOL_1 0x00040000
+#define IGC_RAL_MAC_ADDR_LEN 4
+#define IGC_RAH_MAC_ADDR_LEN 2
+
+/* Error Codes */
+#define IGC_SUCCESS 0
+#define IGC_ERR_NVM 1
+#define IGC_ERR_PHY 2
+#define IGC_ERR_CONFIG 3
+#define IGC_ERR_PARAM 4
+#define IGC_ERR_MAC_INIT 5
+#define IGC_ERR_RESET 9
+#define IGC_ERR_MASTER_REQUESTS_PENDING 10
+#define IGC_ERR_BLK_PHY_RESET 12
+#define IGC_ERR_SWFW_SYNC 13
+
+/* Device Control */
+#define IGC_CTRL_DEV_RST 0x20000000 /* Device reset */
+
+#define IGC_CTRL_PHY_RST 0x80000000 /* PHY Reset */
+#define IGC_CTRL_SLU 0x00000040 /* Set link up (Force Link) */
+#define IGC_CTRL_FRCSPD 0x00000800 /* Force Speed */
+#define IGC_CTRL_FRCDPX 0x00001000 /* Force Duplex */
+
+#define IGC_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */
+#define IGC_CTRL_TFCE 0x10000000 /* Transmit flow control enable */
+
+#define IGC_CONNSW_AUTOSENSE_EN 0x1
+
+/* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */
+#define MAX_JUMBO_FRAME_SIZE 0x2600
+
+/* PBA constants */
+#define IGC_PBA_34K 0x0022
+
+/* SW Semaphore Register */
+#define IGC_SWSM_SMBI 0x00000001 /* Driver Semaphore bit */
+#define IGC_SWSM_SWESMBI 0x00000002 /* FW Semaphore bit */
+
+/* SWFW_SYNC Definitions */
+#define IGC_SWFW_EEP_SM 0x1
+#define IGC_SWFW_PHY0_SM 0x2
+
+/* Autoneg Advertisement Register */
+#define NWAY_AR_10T_HD_CAPS 0x0020 /* 10T Half Duplex Capable */
+#define NWAY_AR_10T_FD_CAPS 0x0040 /* 10T Full Duplex Capable */
+#define NWAY_AR_100TX_HD_CAPS 0x0080 /* 100TX Half Duplex Capable */
+#define NWAY_AR_100TX_FD_CAPS 0x0100 /* 100TX Full Duplex Capable */
+#define NWAY_AR_PAUSE 0x0400 /* Pause operation desired */
+#define NWAY_AR_ASM_DIR 0x0800 /* Asymmetric Pause Direction bit */
+
+/* Link Partner Ability Register (Base Page) */
+#define NWAY_LPAR_PAUSE 0x0400 /* LP Pause operation desired */
+#define NWAY_LPAR_ASM_DIR 0x0800 /* LP Asymmetric Pause Direction bit */
+
+/* 1000BASE-T Control Register */
+#define CR_1000T_ASYM_PAUSE 0x0080 /* Advertise asymmetric pause bit */
+#define CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */
+#define CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */
+
+/* 1000BASE-T Status Register */
+#define SR_1000T_REMOTE_RX_STATUS 0x1000 /* Remote receiver OK */
+#define SR_1000T_LOCAL_RX_STATUS 0x2000 /* Local receiver OK */
+
+/* PHY GPY 211 registers */
+#define STANDARD_AN_REG_MASK 0x0007 /* MMD */
+#define ANEG_MULTIGBT_AN_CTRL 0x0020 /* MULTI GBT AN Control Register */
+#define MMD_DEVADDR_SHIFT 16 /* Shift MMD to higher bits */
+#define CR_2500T_FD_CAPS 0x0080 /* Advertise 2500T FD capability */
+
+/* NVM Control */
+/* Number of milliseconds for NVM auto read done after MAC reset. */
+#define AUTO_READ_DONE_TIMEOUT 10
+#define IGC_EECD_AUTO_RD 0x00000200 /* NVM Auto Read done */
+#define IGC_EECD_REQ 0x00000040 /* NVM Access Request */
+#define IGC_EECD_GNT 0x00000080 /* NVM Access Grant */
+/* NVM Addressing bits based on type 0=small, 1=large */
+#define IGC_EECD_ADDR_BITS 0x00000400
+#define IGC_NVM_GRANT_ATTEMPTS 1000 /* NVM # attempts to gain grant */
+#define IGC_EECD_SIZE_EX_MASK 0x00007800 /* NVM Size */
+#define IGC_EECD_SIZE_EX_SHIFT 11
+#define IGC_EECD_FLUPD_I225 0x00800000 /* Update FLASH */
+#define IGC_EECD_FLUDONE_I225 0x04000000 /* Update FLASH done*/
+#define IGC_EECD_FLASH_DETECTED_I225 0x00080000 /* FLASH detected */
+#define IGC_FLUDONE_ATTEMPTS 20000
+#define IGC_EERD_EEWR_MAX_COUNT 512 /* buffered EEPROM words rw */
+
+/* Offset to data in NVM read/write registers */
+#define IGC_NVM_RW_REG_DATA 16
+#define IGC_NVM_RW_REG_DONE 2 /* Offset to READ/WRITE done bit */
+#define IGC_NVM_RW_REG_START 1 /* Start operation */
+#define IGC_NVM_RW_ADDR_SHIFT 2 /* Shift to the address bits */
+#define IGC_NVM_POLL_READ 0 /* Flag for polling for read complete */
+
+/* NVM Word Offsets */
+#define NVM_CHECKSUM_REG 0x003F
+
+/* For checksumming, the sum of all words in the NVM should equal 0xBABA. */
+#define NVM_SUM 0xBABA
+
+#define NVM_PBA_OFFSET_0 8
+#define NVM_PBA_OFFSET_1 9
+#define NVM_RESERVED_WORD 0xFFFF
+#define NVM_PBA_PTR_GUARD 0xFAFA
+#define NVM_WORD_SIZE_BASE_SHIFT 6
+
+/* Collision related configuration parameters */
+#define IGC_COLLISION_THRESHOLD 15
+#define IGC_CT_SHIFT 4
+#define IGC_COLLISION_DISTANCE 63
+#define IGC_COLD_SHIFT 12
+
+/* Device Status */
+#define IGC_STATUS_FD 0x00000001 /* Full duplex.0=half,1=full */
+#define IGC_STATUS_LU 0x00000002 /* Link up.0=no,1=link */
+#define IGC_STATUS_FUNC_MASK 0x0000000C /* PCI Function Mask */
+#define IGC_STATUS_FUNC_SHIFT 2
+#define IGC_STATUS_FUNC_1 0x00000004 /* Function 1 */
+#define IGC_STATUS_TXOFF 0x00000010 /* transmission paused */
+#define IGC_STATUS_SPEED_100 0x00000040 /* Speed 100Mb/s */
+#define IGC_STATUS_SPEED_1000 0x00000080 /* Speed 1000Mb/s */
+#define IGC_STATUS_SPEED_2500 0x00400000 /* Speed 2.5Gb/s */
+
+#define SPEED_10 10
+#define SPEED_100 100
+#define SPEED_1000 1000
+#define SPEED_2500 2500
+#define HALF_DUPLEX 1
+#define FULL_DUPLEX 2
+
+/* 1Gbps and 2.5Gbps half duplex is not supported, nor spec-compliant. */
+#define ADVERTISE_10_HALF 0x0001
+#define ADVERTISE_10_FULL 0x0002
+#define ADVERTISE_100_HALF 0x0004
+#define ADVERTISE_100_FULL 0x0008
+#define ADVERTISE_1000_HALF 0x0010 /* Not used, just FYI */
+#define ADVERTISE_1000_FULL 0x0020
+#define ADVERTISE_2500_HALF 0x0040 /* Not used, just FYI */
+#define ADVERTISE_2500_FULL 0x0080
+
+#define IGC_ALL_SPEED_DUPLEX_2500 ( \
+ ADVERTISE_10_HALF | ADVERTISE_10_FULL | ADVERTISE_100_HALF | \
+ ADVERTISE_100_FULL | ADVERTISE_1000_FULL | ADVERTISE_2500_FULL)
+
+#define AUTONEG_ADVERTISE_SPEED_DEFAULT_2500 IGC_ALL_SPEED_DUPLEX_2500
+
+/* Interrupt Cause Read */
+#define IGC_ICR_TXDW BIT(0) /* Transmit desc written back */
+#define IGC_ICR_TXQE BIT(1) /* Transmit Queue empty */
+#define IGC_ICR_LSC BIT(2) /* Link Status Change */
+#define IGC_ICR_RXSEQ BIT(3) /* Rx sequence error */
+#define IGC_ICR_RXDMT0 BIT(4) /* Rx desc min. threshold (0) */
+#define IGC_ICR_RXO BIT(6) /* Rx overrun */
+#define IGC_ICR_RXT0 BIT(7) /* Rx timer intr (ring 0) */
+#define IGC_ICR_DRSTA BIT(30) /* Device Reset Asserted */
+
+/* If this bit asserted, the driver should claim the interrupt */
+#define IGC_ICR_INT_ASSERTED BIT(31)
+
+#define IGC_ICS_RXT0 IGC_ICR_RXT0 /* Rx timer intr */
+
+#define IMS_ENABLE_MASK ( \
+ IGC_IMS_RXT0 | \
+ IGC_IMS_TXDW | \
+ IGC_IMS_RXDMT0 | \
+ IGC_IMS_RXSEQ | \
+ IGC_IMS_LSC)
+
+/* Interrupt Mask Set */
+#define IGC_IMS_TXDW IGC_ICR_TXDW /* Tx desc written back */
+#define IGC_IMS_RXSEQ IGC_ICR_RXSEQ /* Rx sequence error */
+#define IGC_IMS_LSC IGC_ICR_LSC /* Link Status Change */
+#define IGC_IMS_DOUTSYNC IGC_ICR_DOUTSYNC /* NIC DMA out of sync */
+#define IGC_IMS_DRSTA IGC_ICR_DRSTA /* Device Reset Asserted */
+#define IGC_IMS_RXT0 IGC_ICR_RXT0 /* Rx timer intr */
+#define IGC_IMS_RXDMT0 IGC_ICR_RXDMT0 /* Rx desc min. threshold */
+
+#define IGC_QVECTOR_MASK 0x7FFC /* Q-vector mask */
+#define IGC_ITR_VAL_MASK 0x04 /* ITR value mask */
+
+/* Interrupt Cause Set */
+#define IGC_ICS_LSC IGC_ICR_LSC /* Link Status Change */
+#define IGC_ICS_RXDMT0 IGC_ICR_RXDMT0 /* rx desc min. threshold */
+#define IGC_ICS_DRSTA IGC_ICR_DRSTA /* Device Reset Aserted */
+
+#define IGC_ICR_DOUTSYNC 0x10000000 /* NIC DMA out of sync */
+#define IGC_EITR_CNT_IGNR 0x80000000 /* Don't reset counters on write */
+#define IGC_IVAR_VALID 0x80
+#define IGC_GPIE_NSICR 0x00000001
+#define IGC_GPIE_MSIX_MODE 0x00000010
+#define IGC_GPIE_EIAME 0x40000000
+#define IGC_GPIE_PBA 0x80000000
+
+/* Transmit Descriptor bit definitions */
+#define IGC_TXD_DTYP_D 0x00100000 /* Data Descriptor */
+#define IGC_TXD_DTYP_C 0x00000000 /* Context Descriptor */
+#define IGC_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */
+#define IGC_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */
+#define IGC_TXD_CMD_EOP 0x01000000 /* End of Packet */
+#define IGC_TXD_CMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */
+#define IGC_TXD_CMD_IC 0x04000000 /* Insert Checksum */
+#define IGC_TXD_CMD_RS 0x08000000 /* Report Status */
+#define IGC_TXD_CMD_RPS 0x10000000 /* Report Packet Sent */
+#define IGC_TXD_CMD_DEXT 0x20000000 /* Desc extension (0 = legacy) */
+#define IGC_TXD_CMD_VLE 0x40000000 /* Add VLAN tag */
+#define IGC_TXD_CMD_IDE 0x80000000 /* Enable Tidv register */
+#define IGC_TXD_STAT_DD 0x00000001 /* Descriptor Done */
+#define IGC_TXD_STAT_EC 0x00000002 /* Excess Collisions */
+#define IGC_TXD_STAT_LC 0x00000004 /* Late Collisions */
+#define IGC_TXD_STAT_TU 0x00000008 /* Transmit underrun */
+#define IGC_TXD_CMD_TCP 0x01000000 /* TCP packet */
+#define IGC_TXD_CMD_IP 0x02000000 /* IP packet */
+#define IGC_TXD_CMD_TSE 0x04000000 /* TCP Seg enable */
+#define IGC_TXD_STAT_TC 0x00000004 /* Tx Underrun */
+#define IGC_TXD_EXTCMD_TSTAMP 0x00000010 /* IEEE1588 Timestamp packet */
+
+/* Transmit Control */
+#define IGC_TCTL_EN 0x00000002 /* enable Tx */
+#define IGC_TCTL_PSP 0x00000008 /* pad short packets */
+#define IGC_TCTL_CT 0x00000ff0 /* collision threshold */
+#define IGC_TCTL_COLD 0x003ff000 /* collision distance */
+#define IGC_TCTL_RTLC 0x01000000 /* Re-transmit on late collision */
+#define IGC_TCTL_MULR 0x10000000 /* Multiple request support */
+
+/* Flow Control Constants */
+#define FLOW_CONTROL_ADDRESS_LOW 0x00C28001
+#define FLOW_CONTROL_ADDRESS_HIGH 0x00000100
+#define FLOW_CONTROL_TYPE 0x8808
+/* Enable XON frame transmission */
+#define IGC_FCRTL_XONE 0x80000000
+
+/* Management Control */
+#define IGC_MANC_RCV_TCO_EN 0x00020000 /* Receive TCO Packets Enabled */
+#define IGC_MANC_BLK_PHY_RST_ON_IDE 0x00040000 /* Block phy resets */
+
+/* Receive Control */
+#define IGC_RCTL_RST 0x00000001 /* Software reset */
+#define IGC_RCTL_EN 0x00000002 /* enable */
+#define IGC_RCTL_SBP 0x00000004 /* store bad packet */
+#define IGC_RCTL_UPE 0x00000008 /* unicast promisc enable */
+#define IGC_RCTL_MPE 0x00000010 /* multicast promisc enable */
+#define IGC_RCTL_LPE 0x00000020 /* long packet enable */
+#define IGC_RCTL_LBM_MAC 0x00000040 /* MAC loopback mode */
+#define IGC_RCTL_LBM_TCVR 0x000000C0 /* tcvr loopback mode */
+
+#define IGC_RCTL_RDMTS_HALF 0x00000000 /* Rx desc min thresh size */
+#define IGC_RCTL_BAM 0x00008000 /* broadcast enable */
+
+/* Receive Descriptor bit definitions */
+#define IGC_RXD_STAT_EOP 0x02 /* End of Packet */
+
+#define IGC_RXDEXT_STATERR_CE 0x01000000
+#define IGC_RXDEXT_STATERR_SE 0x02000000
+#define IGC_RXDEXT_STATERR_SEQ 0x04000000
+#define IGC_RXDEXT_STATERR_CXE 0x10000000
+#define IGC_RXDEXT_STATERR_TCPE 0x20000000
+#define IGC_RXDEXT_STATERR_IPE 0x40000000
+#define IGC_RXDEXT_STATERR_RXE 0x80000000
+
+/* Same mask, but for extended and packet split descriptors */
+#define IGC_RXDEXT_ERR_FRAME_ERR_MASK ( \
+ IGC_RXDEXT_STATERR_CE | \
+ IGC_RXDEXT_STATERR_SE | \
+ IGC_RXDEXT_STATERR_SEQ | \
+ IGC_RXDEXT_STATERR_CXE | \
+ IGC_RXDEXT_STATERR_RXE)
+
+#define IGC_MRQC_RSS_FIELD_IPV4_TCP 0x00010000
+#define IGC_MRQC_RSS_FIELD_IPV4 0x00020000
+#define IGC_MRQC_RSS_FIELD_IPV6_TCP_EX 0x00040000
+#define IGC_MRQC_RSS_FIELD_IPV6 0x00100000
+#define IGC_MRQC_RSS_FIELD_IPV6_TCP 0x00200000
+
+/* Header split receive */
+#define IGC_RFCTL_IPV6_EX_DIS 0x00010000
+#define IGC_RFCTL_LEF 0x00040000
+
+#define IGC_RCTL_SZ_256 0x00030000 /* Rx buffer size 256 */
+
+#define IGC_RCTL_MO_SHIFT 12 /* multicast offset shift */
+#define IGC_RCTL_CFIEN 0x00080000 /* canonical form enable */
+#define IGC_RCTL_DPF 0x00400000 /* discard pause frames */
+#define IGC_RCTL_PMCF 0x00800000 /* pass MAC control frames */
+#define IGC_RCTL_SECRC 0x04000000 /* Strip Ethernet CRC */
+
+#define I225_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */
+#define I225_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */
+
+/* Receive Checksum Control */
+#define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */
+#define IGC_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */
+
+/* GPY211 - I225 defines */
+#define GPY_MMD_MASK 0xFFFF0000
+#define GPY_MMD_SHIFT 16
+#define GPY_REG_MASK 0x0000FFFF
+
+#define IGC_MMDAC_FUNC_DATA 0x4000 /* Data, no post increment */
+
+/* MAC definitions */
+#define IGC_FACTPS_MNGCG 0x20000000
+#define IGC_FWSM_MODE_MASK 0xE
+#define IGC_FWSM_MODE_SHIFT 1
+
+/* Management Control */
+#define IGC_MANC_SMBUS_EN 0x00000001 /* SMBus Enabled - RO */
+#define IGC_MANC_ASF_EN 0x00000002 /* ASF Enabled - RO */
+
+/* PHY */
+#define PHY_REVISION_MASK 0xFFFFFFF0
+#define MAX_PHY_REG_ADDRESS 0x1F /* 5 bit address bus (0-0x1F) */
+#define IGC_GEN_POLL_TIMEOUT 1920
+
+/* PHY Control Register */
+#define MII_CR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */
+#define MII_CR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */
+#define MII_CR_POWER_DOWN 0x0800 /* Power down */
+#define MII_CR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */
+#define MII_CR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */
+#define MII_CR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */
+#define MII_CR_SPEED_1000 0x0040
+#define MII_CR_SPEED_100 0x2000
+#define MII_CR_SPEED_10 0x0000
+
+/* PHY Status Register */
+#define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */
+#define MII_SR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */
+
+/* PHY 1000 MII Register/Bit Definitions */
+/* PHY Registers defined by IEEE */
+#define PHY_CONTROL 0x00 /* Control Register */
+#define PHY_STATUS 0x01 /* Status Register */
+#define PHY_ID1 0x02 /* Phy Id Reg (word 1) */
+#define PHY_ID2 0x03 /* Phy Id Reg (word 2) */
+#define PHY_AUTONEG_ADV 0x04 /* Autoneg Advertisement */
+#define PHY_LP_ABILITY 0x05 /* Link Partner Ability (Base Page) */
+#define PHY_1000T_CTRL 0x09 /* 1000Base-T Control Reg */
+#define PHY_1000T_STATUS 0x0A /* 1000Base-T Status Reg */
+
+/* Bit definitions for valid PHY IDs. I = Integrated E = External */
+#define I225_I_PHY_ID 0x67C9DC00
+
+/* MDI Control */
+#define IGC_MDIC_DATA_MASK 0x0000FFFF
+#define IGC_MDIC_REG_MASK 0x001F0000
+#define IGC_MDIC_REG_SHIFT 16
+#define IGC_MDIC_PHY_MASK 0x03E00000
+#define IGC_MDIC_PHY_SHIFT 21
+#define IGC_MDIC_OP_WRITE 0x04000000
+#define IGC_MDIC_OP_READ 0x08000000
+#define IGC_MDIC_READY 0x10000000
+#define IGC_MDIC_INT_EN 0x20000000
+#define IGC_MDIC_ERROR 0x40000000
+#define IGC_MDIC_DEST 0x80000000
+
+#define IGC_N0_QUEUE -1
+
+#define IGC_MAX_MAC_HDR_LEN 127
+#define IGC_MAX_NETWORK_HDR_LEN 511
+
+#define IGC_VLAPQF_QUEUE_SEL(_n, q_idx) ((q_idx) << ((_n) * 4))
+#define IGC_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4))
+#define IGC_VLAPQF_QUEUE_MASK 0x03
+
+#define IGC_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */
+#define IGC_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type:1=IPv4 */
+#define IGC_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet Type of TCP */
+#define IGC_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 packet TYPE of SCTP */
+
+#endif /* _IGC_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
new file mode 100644
index 0000000..ac98f1d
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -0,0 +1,1863 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+/* ethtool support for igc */
+#include <linux/if_vlan.h>
+#include <linux/pm_runtime.h>
+
+#include "igc.h"
+
+/* forward declaration */
+struct igc_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int sizeof_stat;
+ int stat_offset;
+};
+
+#define IGC_STAT(_name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(struct igc_adapter, _stat), \
+ .stat_offset = offsetof(struct igc_adapter, _stat) \
+}
+
+static const struct igc_stats igc_gstrings_stats[] = {
+ IGC_STAT("rx_packets", stats.gprc),
+ IGC_STAT("tx_packets", stats.gptc),
+ IGC_STAT("rx_bytes", stats.gorc),
+ IGC_STAT("tx_bytes", stats.gotc),
+ IGC_STAT("rx_broadcast", stats.bprc),
+ IGC_STAT("tx_broadcast", stats.bptc),
+ IGC_STAT("rx_multicast", stats.mprc),
+ IGC_STAT("tx_multicast", stats.mptc),
+ IGC_STAT("multicast", stats.mprc),
+ IGC_STAT("collisions", stats.colc),
+ IGC_STAT("rx_crc_errors", stats.crcerrs),
+ IGC_STAT("rx_no_buffer_count", stats.rnbc),
+ IGC_STAT("rx_missed_errors", stats.mpc),
+ IGC_STAT("tx_aborted_errors", stats.ecol),
+ IGC_STAT("tx_carrier_errors", stats.tncrs),
+ IGC_STAT("tx_window_errors", stats.latecol),
+ IGC_STAT("tx_abort_late_coll", stats.latecol),
+ IGC_STAT("tx_deferred_ok", stats.dc),
+ IGC_STAT("tx_single_coll_ok", stats.scc),
+ IGC_STAT("tx_multi_coll_ok", stats.mcc),
+ IGC_STAT("tx_timeout_count", tx_timeout_count),
+ IGC_STAT("rx_long_length_errors", stats.roc),
+ IGC_STAT("rx_short_length_errors", stats.ruc),
+ IGC_STAT("rx_align_errors", stats.algnerrc),
+ IGC_STAT("tx_tcp_seg_good", stats.tsctc),
+ IGC_STAT("tx_tcp_seg_failed", stats.tsctfc),
+ IGC_STAT("rx_flow_control_xon", stats.xonrxc),
+ IGC_STAT("rx_flow_control_xoff", stats.xoffrxc),
+ IGC_STAT("tx_flow_control_xon", stats.xontxc),
+ IGC_STAT("tx_flow_control_xoff", stats.xofftxc),
+ IGC_STAT("rx_long_byte_count", stats.gorc),
+ IGC_STAT("tx_dma_out_of_sync", stats.doosync),
+ IGC_STAT("tx_smbus", stats.mgptc),
+ IGC_STAT("rx_smbus", stats.mgprc),
+ IGC_STAT("dropped_smbus", stats.mgpdc),
+ IGC_STAT("os2bmc_rx_by_bmc", stats.o2bgptc),
+ IGC_STAT("os2bmc_tx_by_bmc", stats.b2ospc),
+ IGC_STAT("os2bmc_tx_by_host", stats.o2bspc),
+ IGC_STAT("os2bmc_rx_by_host", stats.b2ogprc),
+ IGC_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+ IGC_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
+ IGC_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
+};
+
+#define IGC_NETDEV_STAT(_net_stat) { \
+ .stat_string = __stringify(_net_stat), \
+ .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \
+ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \
+}
+
+static const struct igc_stats igc_gstrings_net_stats[] = {
+ IGC_NETDEV_STAT(rx_errors),
+ IGC_NETDEV_STAT(tx_errors),
+ IGC_NETDEV_STAT(tx_dropped),
+ IGC_NETDEV_STAT(rx_length_errors),
+ IGC_NETDEV_STAT(rx_over_errors),
+ IGC_NETDEV_STAT(rx_frame_errors),
+ IGC_NETDEV_STAT(rx_fifo_errors),
+ IGC_NETDEV_STAT(tx_fifo_errors),
+ IGC_NETDEV_STAT(tx_heartbeat_errors)
+};
+
+enum igc_diagnostics_results {
+ TEST_REG = 0,
+ TEST_EEP,
+ TEST_IRQ,
+ TEST_LOOP,
+ TEST_LINK
+};
+
+static const char igc_gstrings_test[][ETH_GSTRING_LEN] = {
+ [TEST_REG] = "Register test (offline)",
+ [TEST_EEP] = "Eeprom test (offline)",
+ [TEST_IRQ] = "Interrupt test (offline)",
+ [TEST_LOOP] = "Loopback test (offline)",
+ [TEST_LINK] = "Link test (on/offline)"
+};
+
+#define IGC_TEST_LEN (sizeof(igc_gstrings_test) / ETH_GSTRING_LEN)
+
+#define IGC_GLOBAL_STATS_LEN \
+ (sizeof(igc_gstrings_stats) / sizeof(struct igc_stats))
+#define IGC_NETDEV_STATS_LEN \
+ (sizeof(igc_gstrings_net_stats) / sizeof(struct igc_stats))
+#define IGC_RX_QUEUE_STATS_LEN \
+ (sizeof(struct igc_rx_queue_stats) / sizeof(u64))
+#define IGC_TX_QUEUE_STATS_LEN 3 /* packets, bytes, restart_queue */
+#define IGC_QUEUE_STATS_LEN \
+ ((((struct igc_adapter *)netdev_priv(netdev))->num_rx_queues * \
+ IGC_RX_QUEUE_STATS_LEN) + \
+ (((struct igc_adapter *)netdev_priv(netdev))->num_tx_queues * \
+ IGC_TX_QUEUE_STATS_LEN))
+#define IGC_STATS_LEN \
+ (IGC_GLOBAL_STATS_LEN + IGC_NETDEV_STATS_LEN + IGC_QUEUE_STATS_LEN)
+
+static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGC_PRIV_FLAGS_LEGACY_RX BIT(0)
+ "legacy-rx",
+};
+
+#define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings)
+
+static void igc_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ strlcpy(drvinfo->driver, igc_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, igc_driver_version, sizeof(drvinfo->version));
+
+ /* add fw_version here */
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
+
+ drvinfo->n_priv_flags = IGC_PRIV_FLAGS_STR_LEN;
+}
+
+static int igc_get_regs_len(struct net_device *netdev)
+{
+ return IGC_REGS_LEN * sizeof(u32);
+}
+
+static void igc_get_regs(struct net_device *netdev,
+ struct ethtool_regs *regs, void *p)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ u32 *regs_buff = p;
+ u8 i;
+
+ memset(p, 0, IGC_REGS_LEN * sizeof(u32));
+
+ regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id;
+
+ /* General Registers */
+ regs_buff[0] = rd32(IGC_CTRL);
+ regs_buff[1] = rd32(IGC_STATUS);
+ regs_buff[2] = rd32(IGC_CTRL_EXT);
+ regs_buff[3] = rd32(IGC_MDIC);
+ regs_buff[4] = rd32(IGC_CONNSW);
+
+ /* NVM Register */
+ regs_buff[5] = rd32(IGC_EECD);
+
+ /* Interrupt */
+ /* Reading EICS for EICR because they read the
+ * same but EICS does not clear on read
+ */
+ regs_buff[6] = rd32(IGC_EICS);
+ regs_buff[7] = rd32(IGC_EICS);
+ regs_buff[8] = rd32(IGC_EIMS);
+ regs_buff[9] = rd32(IGC_EIMC);
+ regs_buff[10] = rd32(IGC_EIAC);
+ regs_buff[11] = rd32(IGC_EIAM);
+ /* Reading ICS for ICR because they read the
+ * same but ICS does not clear on read
+ */
+ regs_buff[12] = rd32(IGC_ICS);
+ regs_buff[13] = rd32(IGC_ICS);
+ regs_buff[14] = rd32(IGC_IMS);
+ regs_buff[15] = rd32(IGC_IMC);
+ regs_buff[16] = rd32(IGC_IAC);
+ regs_buff[17] = rd32(IGC_IAM);
+
+ /* Flow Control */
+ regs_buff[18] = rd32(IGC_FCAL);
+ regs_buff[19] = rd32(IGC_FCAH);
+ regs_buff[20] = rd32(IGC_FCTTV);
+ regs_buff[21] = rd32(IGC_FCRTL);
+ regs_buff[22] = rd32(IGC_FCRTH);
+ regs_buff[23] = rd32(IGC_FCRTV);
+
+ /* Receive */
+ regs_buff[24] = rd32(IGC_RCTL);
+ regs_buff[25] = rd32(IGC_RXCSUM);
+ regs_buff[26] = rd32(IGC_RLPML);
+ regs_buff[27] = rd32(IGC_RFCTL);
+
+ /* Transmit */
+ regs_buff[28] = rd32(IGC_TCTL);
+ regs_buff[29] = rd32(IGC_TIPG);
+
+ /* Wake Up */
+
+ /* MAC */
+
+ /* Statistics */
+ regs_buff[30] = adapter->stats.crcerrs;
+ regs_buff[31] = adapter->stats.algnerrc;
+ regs_buff[32] = adapter->stats.symerrs;
+ regs_buff[33] = adapter->stats.rxerrc;
+ regs_buff[34] = adapter->stats.mpc;
+ regs_buff[35] = adapter->stats.scc;
+ regs_buff[36] = adapter->stats.ecol;
+ regs_buff[37] = adapter->stats.mcc;
+ regs_buff[38] = adapter->stats.latecol;
+ regs_buff[39] = adapter->stats.colc;
+ regs_buff[40] = adapter->stats.dc;
+ regs_buff[41] = adapter->stats.tncrs;
+ regs_buff[42] = adapter->stats.sec;
+ regs_buff[43] = adapter->stats.htdpmc;
+ regs_buff[44] = adapter->stats.rlec;
+ regs_buff[45] = adapter->stats.xonrxc;
+ regs_buff[46] = adapter->stats.xontxc;
+ regs_buff[47] = adapter->stats.xoffrxc;
+ regs_buff[48] = adapter->stats.xofftxc;
+ regs_buff[49] = adapter->stats.fcruc;
+ regs_buff[50] = adapter->stats.prc64;
+ regs_buff[51] = adapter->stats.prc127;
+ regs_buff[52] = adapter->stats.prc255;
+ regs_buff[53] = adapter->stats.prc511;
+ regs_buff[54] = adapter->stats.prc1023;
+ regs_buff[55] = adapter->stats.prc1522;
+ regs_buff[56] = adapter->stats.gprc;
+ regs_buff[57] = adapter->stats.bprc;
+ regs_buff[58] = adapter->stats.mprc;
+ regs_buff[59] = adapter->stats.gptc;
+ regs_buff[60] = adapter->stats.gorc;
+ regs_buff[61] = adapter->stats.gotc;
+ regs_buff[62] = adapter->stats.rnbc;
+ regs_buff[63] = adapter->stats.ruc;
+ regs_buff[64] = adapter->stats.rfc;
+ regs_buff[65] = adapter->stats.roc;
+ regs_buff[66] = adapter->stats.rjc;
+ regs_buff[67] = adapter->stats.mgprc;
+ regs_buff[68] = adapter->stats.mgpdc;
+ regs_buff[69] = adapter->stats.mgptc;
+ regs_buff[70] = adapter->stats.tor;
+ regs_buff[71] = adapter->stats.tot;
+ regs_buff[72] = adapter->stats.tpr;
+ regs_buff[73] = adapter->stats.tpt;
+ regs_buff[74] = adapter->stats.ptc64;
+ regs_buff[75] = adapter->stats.ptc127;
+ regs_buff[76] = adapter->stats.ptc255;
+ regs_buff[77] = adapter->stats.ptc511;
+ regs_buff[78] = adapter->stats.ptc1023;
+ regs_buff[79] = adapter->stats.ptc1522;
+ regs_buff[80] = adapter->stats.mptc;
+ regs_buff[81] = adapter->stats.bptc;
+ regs_buff[82] = adapter->stats.tsctc;
+ regs_buff[83] = adapter->stats.iac;
+ regs_buff[84] = adapter->stats.rpthc;
+ regs_buff[85] = adapter->stats.hgptc;
+ regs_buff[86] = adapter->stats.hgorc;
+ regs_buff[87] = adapter->stats.hgotc;
+ regs_buff[88] = adapter->stats.lenerrs;
+ regs_buff[89] = adapter->stats.scvpc;
+ regs_buff[90] = adapter->stats.hrmpc;
+
+ for (i = 0; i < 4; i++)
+ regs_buff[91 + i] = rd32(IGC_SRRCTL(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[95 + i] = rd32(IGC_PSRTYPE(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[99 + i] = rd32(IGC_RDBAL(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[103 + i] = rd32(IGC_RDBAH(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[107 + i] = rd32(IGC_RDLEN(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[111 + i] = rd32(IGC_RDH(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[115 + i] = rd32(IGC_RDT(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[119 + i] = rd32(IGC_RXDCTL(i));
+
+ for (i = 0; i < 10; i++)
+ regs_buff[123 + i] = rd32(IGC_EITR(i));
+ for (i = 0; i < 16; i++)
+ regs_buff[139 + i] = rd32(IGC_RAL(i));
+ for (i = 0; i < 16; i++)
+ regs_buff[145 + i] = rd32(IGC_RAH(i));
+
+ for (i = 0; i < 4; i++)
+ regs_buff[149 + i] = rd32(IGC_TDBAL(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[152 + i] = rd32(IGC_TDBAH(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[156 + i] = rd32(IGC_TDLEN(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[160 + i] = rd32(IGC_TDH(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[164 + i] = rd32(IGC_TDT(i));
+ for (i = 0; i < 4; i++)
+ regs_buff[168 + i] = rd32(IGC_TXDCTL(i));
+}
+
+static u32 igc_get_msglevel(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ return adapter->msg_enable;
+}
+
+static void igc_set_msglevel(struct net_device *netdev, u32 data)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ adapter->msg_enable = data;
+}
+
+static int igc_nway_reset(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ if (netif_running(netdev))
+ igc_reinit_locked(adapter);
+ return 0;
+}
+
+static u32 igc_get_link(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_mac_info *mac = &adapter->hw.mac;
+
+ /* If the link is not reported up to netdev, interrupts are disabled,
+ * and so the physical link state may have changed since we last
+ * looked. Set get_link_status to make sure that the true link
+ * state is interrogated, rather than pulling a cached and possibly
+ * stale link state from the driver.
+ */
+ if (!netif_carrier_ok(netdev))
+ mac->get_link_status = 1;
+
+ return igc_has_link(adapter);
+}
+
+static int igc_get_eeprom_len(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ return adapter->hw.nvm.word_size * 2;
+}
+
+static int igc_get_eeprom(struct net_device *netdev,
+ struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ int first_word, last_word;
+ u16 *eeprom_buff;
+ int ret_val = 0;
+ u16 i;
+
+ if (eeprom->len == 0)
+ return -EINVAL;
+
+ eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+ first_word = eeprom->offset >> 1;
+ last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+
+ eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16),
+ GFP_KERNEL);
+ if (!eeprom_buff)
+ return -ENOMEM;
+
+ if (hw->nvm.type == igc_nvm_eeprom_spi) {
+ ret_val = hw->nvm.ops.read(hw, first_word,
+ last_word - first_word + 1,
+ eeprom_buff);
+ } else {
+ for (i = 0; i < last_word - first_word + 1; i++) {
+ ret_val = hw->nvm.ops.read(hw, first_word + i, 1,
+ &eeprom_buff[i]);
+ if (ret_val)
+ break;
+ }
+ }
+
+ /* Device's eeprom is always little-endian, word addressable */
+ for (i = 0; i < last_word - first_word + 1; i++)
+ le16_to_cpus(&eeprom_buff[i]);
+
+ memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1),
+ eeprom->len);
+ kfree(eeprom_buff);
+
+ return ret_val;
+}
+
+static int igc_set_eeprom(struct net_device *netdev,
+ struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ int max_len, first_word, last_word, ret_val = 0;
+ u16 *eeprom_buff;
+ void *ptr;
+ u16 i;
+
+ if (eeprom->len == 0)
+ return -EOPNOTSUPP;
+
+ if (hw->mac.type >= igc_i225 &&
+ !igc_get_flash_presence_i225(hw)) {
+ return -EOPNOTSUPP;
+ }
+
+ if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16)))
+ return -EFAULT;
+
+ max_len = hw->nvm.word_size * 2;
+
+ first_word = eeprom->offset >> 1;
+ last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+ eeprom_buff = kmalloc(max_len, GFP_KERNEL);
+ if (!eeprom_buff)
+ return -ENOMEM;
+
+ ptr = (void *)eeprom_buff;
+
+ if (eeprom->offset & 1) {
+ /* need read/modify/write of first changed EEPROM word
+ * only the second byte of the word is being modified
+ */
+ ret_val = hw->nvm.ops.read(hw, first_word, 1,
+ &eeprom_buff[0]);
+ ptr++;
+ }
+ if (((eeprom->offset + eeprom->len) & 1) && ret_val == 0) {
+ /* need read/modify/write of last changed EEPROM word
+ * only the first byte of the word is being modified
+ */
+ ret_val = hw->nvm.ops.read(hw, last_word, 1,
+ &eeprom_buff[last_word - first_word]);
+ }
+
+ /* Device's eeprom is always little-endian, word addressable */
+ for (i = 0; i < last_word - first_word + 1; i++)
+ le16_to_cpus(&eeprom_buff[i]);
+
+ memcpy(ptr, bytes, eeprom->len);
+
+ for (i = 0; i < last_word - first_word + 1; i++)
+ eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+
+ ret_val = hw->nvm.ops.write(hw, first_word,
+ last_word - first_word + 1, eeprom_buff);
+
+ /* Update the checksum if nvm write succeeded */
+ if (ret_val == 0)
+ hw->nvm.ops.update(hw);
+
+ /* check if need: igc_set_fw_version(adapter); */
+ kfree(eeprom_buff);
+ return ret_val;
+}
+
+static void igc_get_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ ring->rx_max_pending = IGC_MAX_RXD;
+ ring->tx_max_pending = IGC_MAX_TXD;
+ ring->rx_pending = adapter->rx_ring_count;
+ ring->tx_pending = adapter->tx_ring_count;
+}
+
+static int igc_set_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_ring *temp_ring;
+ u16 new_rx_count, new_tx_count;
+ int i, err = 0;
+
+ if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+ return -EINVAL;
+
+ new_rx_count = min_t(u32, ring->rx_pending, IGC_MAX_RXD);
+ new_rx_count = max_t(u16, new_rx_count, IGC_MIN_RXD);
+ new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE);
+
+ new_tx_count = min_t(u32, ring->tx_pending, IGC_MAX_TXD);
+ new_tx_count = max_t(u16, new_tx_count, IGC_MIN_TXD);
+ new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE);
+
+ if (new_tx_count == adapter->tx_ring_count &&
+ new_rx_count == adapter->rx_ring_count) {
+ /* nothing to do */
+ return 0;
+ }
+
+ while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+
+ if (!netif_running(adapter->netdev)) {
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ adapter->tx_ring[i]->count = new_tx_count;
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ adapter->rx_ring[i]->count = new_rx_count;
+ adapter->tx_ring_count = new_tx_count;
+ adapter->rx_ring_count = new_rx_count;
+ goto clear_reset;
+ }
+
+ if (adapter->num_tx_queues > adapter->num_rx_queues)
+ temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+ adapter->num_tx_queues));
+ else
+ temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+ adapter->num_rx_queues));
+
+ if (!temp_ring) {
+ err = -ENOMEM;
+ goto clear_reset;
+ }
+
+ igc_down(adapter);
+
+ /* We can't just free everything and then setup again,
+ * because the ISRs in MSI-X mode get passed pointers
+ * to the Tx and Rx ring structs.
+ */
+ if (new_tx_count != adapter->tx_ring_count) {
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ memcpy(&temp_ring[i], adapter->tx_ring[i],
+ sizeof(struct igc_ring));
+
+ temp_ring[i].count = new_tx_count;
+ err = igc_setup_tx_resources(&temp_ring[i]);
+ if (err) {
+ while (i) {
+ i--;
+ igc_free_tx_resources(&temp_ring[i]);
+ }
+ goto err_setup;
+ }
+ }
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ igc_free_tx_resources(adapter->tx_ring[i]);
+
+ memcpy(adapter->tx_ring[i], &temp_ring[i],
+ sizeof(struct igc_ring));
+ }
+
+ adapter->tx_ring_count = new_tx_count;
+ }
+
+ if (new_rx_count != adapter->rx_ring_count) {
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ memcpy(&temp_ring[i], adapter->rx_ring[i],
+ sizeof(struct igc_ring));
+
+ temp_ring[i].count = new_rx_count;
+ err = igc_setup_rx_resources(&temp_ring[i]);
+ if (err) {
+ while (i) {
+ i--;
+ igc_free_rx_resources(&temp_ring[i]);
+ }
+ goto err_setup;
+ }
+ }
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ igc_free_rx_resources(adapter->rx_ring[i]);
+
+ memcpy(adapter->rx_ring[i], &temp_ring[i],
+ sizeof(struct igc_ring));
+ }
+
+ adapter->rx_ring_count = new_rx_count;
+ }
+err_setup:
+ igc_up(adapter);
+ vfree(temp_ring);
+clear_reset:
+ clear_bit(__IGC_RESETTING, &adapter->state);
+ return err;
+}
+
+static void igc_get_pauseparam(struct net_device *netdev,
+ struct ethtool_pauseparam *pause)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+
+ pause->autoneg =
+ (adapter->fc_autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+ if (hw->fc.current_mode == igc_fc_rx_pause) {
+ pause->rx_pause = 1;
+ } else if (hw->fc.current_mode == igc_fc_tx_pause) {
+ pause->tx_pause = 1;
+ } else if (hw->fc.current_mode == igc_fc_full) {
+ pause->rx_pause = 1;
+ pause->tx_pause = 1;
+ }
+}
+
+static int igc_set_pauseparam(struct net_device *netdev,
+ struct ethtool_pauseparam *pause)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ int retval = 0;
+
+ adapter->fc_autoneg = pause->autoneg;
+
+ while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+
+ if (adapter->fc_autoneg == AUTONEG_ENABLE) {
+ hw->fc.requested_mode = igc_fc_default;
+ if (netif_running(adapter->netdev)) {
+ igc_down(adapter);
+ igc_up(adapter);
+ } else {
+ igc_reset(adapter);
+ }
+ } else {
+ if (pause->rx_pause && pause->tx_pause)
+ hw->fc.requested_mode = igc_fc_full;
+ else if (pause->rx_pause && !pause->tx_pause)
+ hw->fc.requested_mode = igc_fc_rx_pause;
+ else if (!pause->rx_pause && pause->tx_pause)
+ hw->fc.requested_mode = igc_fc_tx_pause;
+ else if (!pause->rx_pause && !pause->tx_pause)
+ hw->fc.requested_mode = igc_fc_none;
+
+ hw->fc.current_mode = hw->fc.requested_mode;
+
+ retval = ((hw->phy.media_type == igc_media_type_copper) ?
+ igc_force_mac_fc(hw) : igc_setup_link(hw));
+ }
+
+ clear_bit(__IGC_RESETTING, &adapter->state);
+ return retval;
+}
+
+static void igc_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ u8 *p = data;
+ int i;
+
+ switch (stringset) {
+ case ETH_SS_TEST:
+ memcpy(data, *igc_gstrings_test,
+ IGC_TEST_LEN * ETH_GSTRING_LEN);
+ break;
+ case ETH_SS_STATS:
+ for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) {
+ memcpy(p, igc_gstrings_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) {
+ memcpy(p, igc_gstrings_net_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ sprintf(p, "tx_queue_%u_packets", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "tx_queue_%u_bytes", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "tx_queue_%u_restart", i);
+ p += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ sprintf(p, "rx_queue_%u_packets", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_queue_%u_bytes", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_queue_%u_drops", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_queue_%u_csum_err", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_queue_%u_alloc_failed", i);
+ p += ETH_GSTRING_LEN;
+ }
+ /* BUG_ON(p - data != IGC_STATS_LEN * ETH_GSTRING_LEN); */
+ break;
+ case ETH_SS_PRIV_FLAGS:
+ memcpy(data, igc_priv_flags_strings,
+ IGC_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+ break;
+ }
+}
+
+static int igc_get_sset_count(struct net_device *netdev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return IGC_STATS_LEN;
+ case ETH_SS_TEST:
+ return IGC_TEST_LEN;
+ case ETH_SS_PRIV_FLAGS:
+ return IGC_PRIV_FLAGS_STR_LEN;
+ default:
+ return -ENOTSUPP;
+ }
+}
+
+static void igc_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct rtnl_link_stats64 *net_stats = &adapter->stats64;
+ unsigned int start;
+ struct igc_ring *ring;
+ int i, j;
+ char *p;
+
+ spin_lock(&adapter->stats64_lock);
+ igc_update_stats(adapter);
+
+ for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) {
+ p = (char *)adapter + igc_gstrings_stats[i].stat_offset;
+ data[i] = (igc_gstrings_stats[i].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ for (j = 0; j < IGC_NETDEV_STATS_LEN; j++, i++) {
+ p = (char *)net_stats + igc_gstrings_net_stats[j].stat_offset;
+ data[i] = (igc_gstrings_net_stats[j].sizeof_stat ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ for (j = 0; j < adapter->num_tx_queues; j++) {
+ u64 restart2;
+
+ ring = adapter->tx_ring[j];
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
+ data[i] = ring->tx_stats.packets;
+ data[i + 1] = ring->tx_stats.bytes;
+ data[i + 2] = ring->tx_stats.restart_queue;
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp2);
+ restart2 = ring->tx_stats.restart_queue2;
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start));
+ data[i + 2] += restart2;
+
+ i += IGC_TX_QUEUE_STATS_LEN;
+ }
+ for (j = 0; j < adapter->num_rx_queues; j++) {
+ ring = adapter->rx_ring[j];
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
+ data[i] = ring->rx_stats.packets;
+ data[i + 1] = ring->rx_stats.bytes;
+ data[i + 2] = ring->rx_stats.drops;
+ data[i + 3] = ring->rx_stats.csum_err;
+ data[i + 4] = ring->rx_stats.alloc_failed;
+ } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
+ i += IGC_RX_QUEUE_STATS_LEN;
+ }
+ spin_unlock(&adapter->stats64_lock);
+}
+
+static int igc_get_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ if (adapter->rx_itr_setting <= 3)
+ ec->rx_coalesce_usecs = adapter->rx_itr_setting;
+ else
+ ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
+
+ if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) {
+ if (adapter->tx_itr_setting <= 3)
+ ec->tx_coalesce_usecs = adapter->tx_itr_setting;
+ else
+ ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2;
+ }
+
+ return 0;
+}
+
+static int igc_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ int i;
+
+ if (ec->rx_max_coalesced_frames ||
+ ec->rx_coalesce_usecs_irq ||
+ ec->rx_max_coalesced_frames_irq ||
+ ec->tx_max_coalesced_frames ||
+ ec->tx_coalesce_usecs_irq ||
+ ec->stats_block_coalesce_usecs ||
+ ec->use_adaptive_rx_coalesce ||
+ ec->use_adaptive_tx_coalesce ||
+ ec->pkt_rate_low ||
+ ec->rx_coalesce_usecs_low ||
+ ec->rx_max_coalesced_frames_low ||
+ ec->tx_coalesce_usecs_low ||
+ ec->tx_max_coalesced_frames_low ||
+ ec->pkt_rate_high ||
+ ec->rx_coalesce_usecs_high ||
+ ec->rx_max_coalesced_frames_high ||
+ ec->tx_coalesce_usecs_high ||
+ ec->tx_max_coalesced_frames_high ||
+ ec->rate_sample_interval)
+ return -ENOTSUPP;
+
+ if (ec->rx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+ (ec->rx_coalesce_usecs > 3 &&
+ ec->rx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+ ec->rx_coalesce_usecs == 2)
+ return -EINVAL;
+
+ if (ec->tx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+ (ec->tx_coalesce_usecs > 3 &&
+ ec->tx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+ ec->tx_coalesce_usecs == 2)
+ return -EINVAL;
+
+ if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
+ return -EINVAL;
+
+ /* If ITR is disabled, disable DMAC */
+ if (ec->rx_coalesce_usecs == 0) {
+ if (adapter->flags & IGC_FLAG_DMAC)
+ adapter->flags &= ~IGC_FLAG_DMAC;
+ }
+
+ /* convert to rate of irq's per second */
+ if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3)
+ adapter->rx_itr_setting = ec->rx_coalesce_usecs;
+ else
+ adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2;
+
+ /* convert to rate of irq's per second */
+ if (adapter->flags & IGC_FLAG_QUEUE_PAIRS)
+ adapter->tx_itr_setting = adapter->rx_itr_setting;
+ else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3)
+ adapter->tx_itr_setting = ec->tx_coalesce_usecs;
+ else
+ adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2;
+
+ for (i = 0; i < adapter->num_q_vectors; i++) {
+ struct igc_q_vector *q_vector = adapter->q_vector[i];
+
+ q_vector->tx.work_limit = adapter->tx_work_limit;
+ if (q_vector->rx.ring)
+ q_vector->itr_val = adapter->rx_itr_setting;
+ else
+ q_vector->itr_val = adapter->tx_itr_setting;
+ if (q_vector->itr_val && q_vector->itr_val <= 3)
+ q_vector->itr_val = IGC_START_ITR;
+ q_vector->set_itr = 1;
+ }
+
+ return 0;
+}
+
+#define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+static int igc_get_ethtool_nfc_entry(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *cmd)
+{
+ struct ethtool_rx_flow_spec *fsp = &cmd->fs;
+ struct igc_nfc_filter *rule = NULL;
+
+ /* report total rule count */
+ cmd->data = IGC_MAX_RXNFC_FILTERS;
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+ if (fsp->location <= rule->sw_idx)
+ break;
+ }
+
+ if (!rule || fsp->location != rule->sw_idx)
+ return -EINVAL;
+
+ if (rule->filter.match_flags) {
+ fsp->flow_type = ETHER_FLOW;
+ fsp->ring_cookie = rule->action;
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+ fsp->h_u.ether_spec.h_proto = rule->filter.etype;
+ fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
+ }
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+ fsp->flow_type |= FLOW_EXT;
+ fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
+ fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
+ }
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+ ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+ rule->filter.dst_addr);
+ /* As we only support matching by the full
+ * mask, return the mask to userspace
+ */
+ eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+ }
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+ ether_addr_copy(fsp->h_u.ether_spec.h_source,
+ rule->filter.src_addr);
+ /* As we only support matching by the full
+ * mask, return the mask to userspace
+ */
+ eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
+ }
+
+ return 0;
+ }
+ return -EINVAL;
+}
+
+static int igc_get_ethtool_nfc_all(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct igc_nfc_filter *rule;
+ int cnt = 0;
+
+ /* report total rule count */
+ cmd->data = IGC_MAX_RXNFC_FILTERS;
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+ if (cnt == cmd->rule_cnt)
+ return -EMSGSIZE;
+ rule_locs[cnt] = rule->sw_idx;
+ cnt++;
+ }
+
+ cmd->rule_cnt = cnt;
+
+ return 0;
+}
+
+static int igc_get_rss_hash_opts(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *cmd)
+{
+ cmd->data = 0;
+
+ /* Report default options for RSS on igc */
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* Fall through */
+ case UDP_V4_FLOW:
+ if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* Fall through */
+ case SCTP_V4_FLOW:
+ /* Fall through */
+ case AH_ESP_V4_FLOW:
+ /* Fall through */
+ case AH_V4_FLOW:
+ /* Fall through */
+ case ESP_V4_FLOW:
+ /* Fall through */
+ case IPV4_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ case TCP_V6_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* Fall through */
+ case UDP_V6_FLOW:
+ if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* Fall through */
+ case SCTP_V6_FLOW:
+ /* Fall through */
+ case AH_ESP_V6_FLOW:
+ /* Fall through */
+ case AH_V6_FLOW:
+ /* Fall through */
+ case ESP_V6_FLOW:
+ /* Fall through */
+ case IPV6_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct igc_adapter *adapter = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_GRXRINGS:
+ cmd->data = adapter->num_rx_queues;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXCLSRLCNT:
+ cmd->rule_cnt = adapter->nfc_filter_count;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXCLSRULE:
+ ret = igc_get_ethtool_nfc_entry(adapter, cmd);
+ break;
+ case ETHTOOL_GRXCLSRLALL:
+ ret = igc_get_ethtool_nfc_all(adapter, cmd, rule_locs);
+ break;
+ case ETHTOOL_GRXFH:
+ ret = igc_get_rss_hash_opts(adapter, cmd);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+#define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \
+ IGC_FLAG_RSS_FIELD_IPV6_UDP)
+static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *nfc)
+{
+ u32 flags = adapter->flags;
+
+ /* RSS does not support anything other than hashing
+ * to queues on src and dst IPs and ports
+ */
+ if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3))
+ return -EINVAL;
+
+ switch (nfc->flow_type) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ if (!(nfc->data & RXH_IP_SRC) ||
+ !(nfc->data & RXH_IP_DST) ||
+ !(nfc->data & RXH_L4_B_0_1) ||
+ !(nfc->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ break;
+ case UDP_V4_FLOW:
+ if (!(nfc->data & RXH_IP_SRC) ||
+ !(nfc->data & RXH_IP_DST))
+ return -EINVAL;
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ flags &= ~IGC_FLAG_RSS_FIELD_IPV4_UDP;
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ flags |= IGC_FLAG_RSS_FIELD_IPV4_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case UDP_V6_FLOW:
+ if (!(nfc->data & RXH_IP_SRC) ||
+ !(nfc->data & RXH_IP_DST))
+ return -EINVAL;
+ switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ case 0:
+ flags &= ~IGC_FLAG_RSS_FIELD_IPV6_UDP;
+ break;
+ case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ flags |= IGC_FLAG_RSS_FIELD_IPV6_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ if (!(nfc->data & RXH_IP_SRC) ||
+ !(nfc->data & RXH_IP_DST) ||
+ (nfc->data & RXH_L4_B_0_1) ||
+ (nfc->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* if we changed something we need to update flags */
+ if (flags != adapter->flags) {
+ struct igc_hw *hw = &adapter->hw;
+ u32 mrqc = rd32(IGC_MRQC);
+
+ if ((flags & UDP_RSS_FLAGS) &&
+ !(adapter->flags & UDP_RSS_FLAGS))
+ dev_err(&adapter->pdev->dev,
+ "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
+
+ adapter->flags = flags;
+
+ /* Perform hash on these packet types */
+ mrqc |= IGC_MRQC_RSS_FIELD_IPV4 |
+ IGC_MRQC_RSS_FIELD_IPV4_TCP |
+ IGC_MRQC_RSS_FIELD_IPV6 |
+ IGC_MRQC_RSS_FIELD_IPV6_TCP;
+
+ mrqc &= ~(IGC_MRQC_RSS_FIELD_IPV4_UDP |
+ IGC_MRQC_RSS_FIELD_IPV6_UDP);
+
+ if (flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+ mrqc |= IGC_MRQC_RSS_FIELD_IPV4_UDP;
+
+ if (flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+ mrqc |= IGC_MRQC_RSS_FIELD_IPV6_UDP;
+
+ wr32(IGC_MRQC, mrqc);
+ }
+
+ return 0;
+}
+
+static int igc_rxnfc_write_etype_filter(struct igc_adapter *adapter,
+ struct igc_nfc_filter *input)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u8 i;
+ u32 etqf;
+ u16 etype;
+
+ /* find an empty etype filter register */
+ for (i = 0; i < MAX_ETYPE_FILTER; ++i) {
+ if (!adapter->etype_bitmap[i])
+ break;
+ }
+ if (i == MAX_ETYPE_FILTER) {
+ dev_err(&adapter->pdev->dev, "ethtool -N: etype filters are all used.\n");
+ return -EINVAL;
+ }
+
+ adapter->etype_bitmap[i] = true;
+
+ etqf = rd32(IGC_ETQF(i));
+ etype = ntohs(input->filter.etype & ETHER_TYPE_FULL_MASK);
+
+ etqf |= IGC_ETQF_FILTER_ENABLE;
+ etqf &= ~IGC_ETQF_ETYPE_MASK;
+ etqf |= (etype & IGC_ETQF_ETYPE_MASK);
+
+ etqf &= ~IGC_ETQF_QUEUE_MASK;
+ etqf |= ((input->action << IGC_ETQF_QUEUE_SHIFT)
+ & IGC_ETQF_QUEUE_MASK);
+ etqf |= IGC_ETQF_QUEUE_ENABLE;
+
+ wr32(IGC_ETQF(i), etqf);
+
+ input->etype_reg_index = i;
+
+ return 0;
+}
+
+static int igc_rxnfc_write_vlan_prio_filter(struct igc_adapter *adapter,
+ struct igc_nfc_filter *input)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u8 vlan_priority;
+ u16 queue_index;
+ u32 vlapqf;
+
+ vlapqf = rd32(IGC_VLAPQF);
+ vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK)
+ >> VLAN_PRIO_SHIFT;
+ queue_index = (vlapqf >> (vlan_priority * 4)) & IGC_VLAPQF_QUEUE_MASK;
+
+ /* check whether this vlan prio is already set */
+ if (vlapqf & IGC_VLAPQF_P_VALID(vlan_priority) &&
+ queue_index != input->action) {
+ dev_err(&adapter->pdev->dev, "ethtool rxnfc set vlan prio filter failed.\n");
+ return -EEXIST;
+ }
+
+ vlapqf |= IGC_VLAPQF_P_VALID(vlan_priority);
+ vlapqf |= IGC_VLAPQF_QUEUE_SEL(vlan_priority, input->action);
+
+ wr32(IGC_VLAPQF, vlapqf);
+
+ return 0;
+}
+
+int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int err = -EINVAL;
+
+ if (hw->mac.type == igc_i225 &&
+ !(input->filter.match_flags & ~IGC_FILTER_FLAG_SRC_MAC_ADDR)) {
+ dev_err(&adapter->pdev->dev,
+ "i225 doesn't support flow classification rules specifying only source addresses.\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+ err = igc_rxnfc_write_etype_filter(adapter, input);
+ if (err)
+ return err;
+ }
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+ err = igc_add_mac_steering_filter(adapter,
+ input->filter.dst_addr,
+ input->action, 0);
+ err = min_t(int, err, 0);
+ if (err)
+ return err;
+ }
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+ err = igc_add_mac_steering_filter(adapter,
+ input->filter.src_addr,
+ input->action,
+ IGC_MAC_STATE_SRC_ADDR);
+ err = min_t(int, err, 0);
+ if (err)
+ return err;
+ }
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
+ err = igc_rxnfc_write_vlan_prio_filter(adapter, input);
+
+ return err;
+}
+
+static void igc_clear_etype_filter_regs(struct igc_adapter *adapter,
+ u16 reg_index)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 etqf = rd32(IGC_ETQF(reg_index));
+
+ etqf &= ~IGC_ETQF_QUEUE_ENABLE;
+ etqf &= ~IGC_ETQF_QUEUE_MASK;
+ etqf &= ~IGC_ETQF_FILTER_ENABLE;
+
+ wr32(IGC_ETQF(reg_index), etqf);
+
+ adapter->etype_bitmap[reg_index] = false;
+}
+
+static void igc_clear_vlan_prio_filter(struct igc_adapter *adapter,
+ u16 vlan_tci)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u8 vlan_priority;
+ u32 vlapqf;
+
+ vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+
+ vlapqf = rd32(IGC_VLAPQF);
+ vlapqf &= ~IGC_VLAPQF_P_VALID(vlan_priority);
+ vlapqf &= ~IGC_VLAPQF_QUEUE_SEL(vlan_priority,
+ IGC_VLAPQF_QUEUE_MASK);
+
+ wr32(IGC_VLAPQF, vlapqf);
+}
+
+int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+{
+ if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
+ igc_clear_etype_filter_regs(adapter,
+ input->etype_reg_index);
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
+ igc_clear_vlan_prio_filter(adapter,
+ ntohs(input->filter.vlan_tci));
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+ igc_del_mac_steering_filter(adapter, input->filter.src_addr,
+ input->action,
+ IGC_MAC_STATE_SRC_ADDR);
+
+ if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
+ igc_del_mac_steering_filter(adapter, input->filter.dst_addr,
+ input->action, 0);
+
+ return 0;
+}
+
+static int igc_update_ethtool_nfc_entry(struct igc_adapter *adapter,
+ struct igc_nfc_filter *input,
+ u16 sw_idx)
+{
+ struct igc_nfc_filter *rule, *parent;
+ int err = -EINVAL;
+
+ parent = NULL;
+ rule = NULL;
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+ /* hash found, or no matching entry */
+ if (rule->sw_idx >= sw_idx)
+ break;
+ parent = rule;
+ }
+
+ /* if there is an old rule occupying our place remove it */
+ if (rule && rule->sw_idx == sw_idx) {
+ if (!input)
+ err = igc_erase_filter(adapter, rule);
+
+ hlist_del(&rule->nfc_node);
+ kfree(rule);
+ adapter->nfc_filter_count--;
+ }
+
+ /* If no input this was a delete, err should be 0 if a rule was
+ * successfully found and removed from the list else -EINVAL
+ */
+ if (!input)
+ return err;
+
+ /* initialize node */
+ INIT_HLIST_NODE(&input->nfc_node);
+
+ /* add filter to the list */
+ if (parent)
+ hlist_add_behind(&input->nfc_node, &parent->nfc_node);
+ else
+ hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list);
+
+ /* update counts */
+ adapter->nfc_filter_count++;
+
+ return 0;
+}
+
+static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *cmd)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct ethtool_rx_flow_spec *fsp =
+ (struct ethtool_rx_flow_spec *)&cmd->fs;
+ struct igc_nfc_filter *input, *rule;
+ int err = 0;
+
+ if (!(netdev->hw_features & NETIF_F_NTUPLE))
+ return -EOPNOTSUPP;
+
+ /* Don't allow programming if the action is a queue greater than
+ * the number of online Rx queues.
+ */
+ if (fsp->ring_cookie == RX_CLS_FLOW_DISC ||
+ fsp->ring_cookie >= adapter->num_rx_queues) {
+ dev_err(&adapter->pdev->dev, "ethtool -N: The specified action is invalid\n");
+ return -EINVAL;
+ }
+
+ /* Don't allow indexes to exist outside of available space */
+ if (fsp->location >= IGC_MAX_RXNFC_FILTERS) {
+ dev_err(&adapter->pdev->dev, "Location out of range\n");
+ return -EINVAL;
+ }
+
+ if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
+ return -EINVAL;
+
+ input = kzalloc(sizeof(*input), GFP_KERNEL);
+ if (!input)
+ return -ENOMEM;
+
+ if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) {
+ input->filter.etype = fsp->h_u.ether_spec.h_proto;
+ input->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
+ }
+
+ /* Only support matching addresses by the full mask */
+ if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) {
+ input->filter.match_flags |= IGC_FILTER_FLAG_SRC_MAC_ADDR;
+ ether_addr_copy(input->filter.src_addr,
+ fsp->h_u.ether_spec.h_source);
+ }
+
+ /* Only support matching addresses by the full mask */
+ if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+ input->filter.match_flags |= IGC_FILTER_FLAG_DST_MAC_ADDR;
+ ether_addr_copy(input->filter.dst_addr,
+ fsp->h_u.ether_spec.h_dest);
+ }
+
+ if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
+ if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ input->filter.vlan_tci = fsp->h_ext.vlan_tci;
+ input->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
+ }
+
+ input->action = fsp->ring_cookie;
+ input->sw_idx = fsp->location;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+ if (!memcmp(&input->filter, &rule->filter,
+ sizeof(input->filter))) {
+ err = -EEXIST;
+ dev_err(&adapter->pdev->dev,
+ "ethtool: this filter is already set\n");
+ goto err_out_w_lock;
+ }
+ }
+
+ err = igc_add_filter(adapter, input);
+ if (err)
+ goto err_out_w_lock;
+
+ igc_update_ethtool_nfc_entry(adapter, input, input->sw_idx);
+
+ spin_unlock(&adapter->nfc_lock);
+ return 0;
+
+err_out_w_lock:
+ spin_unlock(&adapter->nfc_lock);
+err_out:
+ kfree(input);
+ return err;
+}
+
+static int igc_del_ethtool_nfc_entry(struct igc_adapter *adapter,
+ struct ethtool_rxnfc *cmd)
+{
+ struct ethtool_rx_flow_spec *fsp =
+ (struct ethtool_rx_flow_spec *)&cmd->fs;
+ int err;
+
+ spin_lock(&adapter->nfc_lock);
+ err = igc_update_ethtool_nfc_entry(adapter, NULL, fsp->location);
+ spin_unlock(&adapter->nfc_lock);
+
+ return err;
+}
+
+static int igc_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+ struct igc_adapter *adapter = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXFH:
+ ret = igc_set_rss_hash_opt(adapter, cmd);
+ break;
+ case ETHTOOL_SRXCLSRLINS:
+ ret = igc_add_ethtool_nfc_entry(adapter, cmd);
+ break;
+ case ETHTOOL_SRXCLSRLDEL:
+ ret = igc_del_ethtool_nfc_entry(adapter, cmd);
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 reg = IGC_RETA(0);
+ u32 shift = 0;
+ int i = 0;
+
+ while (i < IGC_RETA_SIZE) {
+ u32 val = 0;
+ int j;
+
+ for (j = 3; j >= 0; j--) {
+ val <<= 8;
+ val |= adapter->rss_indir_tbl[i + j];
+ }
+
+ wr32(reg, val << shift);
+ reg += 4;
+ i += 4;
+ }
+}
+
+static u32 igc_get_rxfh_indir_size(struct net_device *netdev)
+{
+ return IGC_RETA_SIZE;
+}
+
+static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+ u8 *hfunc)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ int i;
+
+ if (hfunc)
+ *hfunc = ETH_RSS_HASH_TOP;
+ if (!indir)
+ return 0;
+ for (i = 0; i < IGC_RETA_SIZE; i++)
+ indir[i] = adapter->rss_indir_tbl[i];
+
+ return 0;
+}
+
+static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
+ const u8 *key, const u8 hfunc)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ u32 num_queues;
+ int i;
+
+ /* We do not allow change in unsupported parameters */
+ if (key ||
+ (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+ return -EOPNOTSUPP;
+ if (!indir)
+ return 0;
+
+ num_queues = adapter->rss_queues;
+
+ /* Verify user input. */
+ for (i = 0; i < IGC_RETA_SIZE; i++)
+ if (indir[i] >= num_queues)
+ return -EINVAL;
+
+ for (i = 0; i < IGC_RETA_SIZE; i++)
+ adapter->rss_indir_tbl[i] = indir[i];
+
+ igc_write_rss_indir_tbl(adapter);
+
+ return 0;
+}
+
+static unsigned int igc_max_channels(struct igc_adapter *adapter)
+{
+ return igc_get_max_rss_queues(adapter);
+}
+
+static void igc_get_channels(struct net_device *netdev,
+ struct ethtool_channels *ch)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ /* Report maximum channels */
+ ch->max_combined = igc_max_channels(adapter);
+
+ /* Report info for other vector */
+ if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+ ch->max_other = NON_Q_VECTORS;
+ ch->other_count = NON_Q_VECTORS;
+ }
+
+ ch->combined_count = adapter->rss_queues;
+}
+
+static int igc_set_channels(struct net_device *netdev,
+ struct ethtool_channels *ch)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ unsigned int count = ch->combined_count;
+ unsigned int max_combined = 0;
+
+ /* Verify they are not requesting separate vectors */
+ if (!count || ch->rx_count || ch->tx_count)
+ return -EINVAL;
+
+ /* Verify other_count is valid and has not been changed */
+ if (ch->other_count != NON_Q_VECTORS)
+ return -EINVAL;
+
+ /* Verify the number of channels doesn't exceed hw limits */
+ max_combined = igc_max_channels(adapter);
+ if (count > max_combined)
+ return -EINVAL;
+
+ if (count != adapter->rss_queues) {
+ adapter->rss_queues = count;
+ igc_set_flag_queue_pairs(adapter, max_combined);
+
+ /* Hardware has to reinitialize queues and interrupts to
+ * match the new configuration.
+ */
+ return igc_reinit_queues(adapter);
+ }
+
+ return 0;
+}
+
+static u32 igc_get_priv_flags(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ u32 priv_flags = 0;
+
+ if (adapter->flags & IGC_FLAG_RX_LEGACY)
+ priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX;
+
+ return priv_flags;
+}
+
+static int igc_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ unsigned int flags = adapter->flags;
+
+ flags &= ~IGC_FLAG_RX_LEGACY;
+ if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX)
+ flags |= IGC_FLAG_RX_LEGACY;
+
+ if (flags != adapter->flags) {
+ adapter->flags = flags;
+
+ /* reset interface to repopulate queues */
+ if (netif_running(netdev))
+ igc_reinit_locked(adapter);
+ }
+
+ return 0;
+}
+
+static int igc_ethtool_begin(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ pm_runtime_get_sync(&adapter->pdev->dev);
+ return 0;
+}
+
+static void igc_ethtool_complete(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ pm_runtime_put(&adapter->pdev->dev);
+}
+
+static int igc_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ u32 status;
+ u32 speed;
+
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+
+ /* supported link modes */
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 2500baseT_Full);
+
+ /* twisted pair */
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = hw->phy.addr;
+
+ /* advertising link modes */
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full);
+
+ /* set autoneg settings */
+ if (hw->mac.autoneg == 1) {
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Autoneg);
+ }
+
+ switch (hw->fc.requested_mode) {
+ case igc_fc_full:
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+ break;
+ case igc_fc_rx_pause:
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
+ break;
+ case igc_fc_tx_pause:
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
+ break;
+ default:
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
+ }
+
+ status = rd32(IGC_STATUS);
+
+ if (status & IGC_STATUS_LU) {
+ if (status & IGC_STATUS_SPEED_1000) {
+ /* For I225, STATUS will indicate 1G speed in both
+ * 1 Gbps and 2.5 Gbps link modes.
+ * An additional bit is used
+ * to differentiate between 1 Gbps and 2.5 Gbps.
+ */
+ if (hw->mac.type == igc_i225 &&
+ (status & IGC_STATUS_SPEED_2500)) {
+ speed = SPEED_2500;
+ } else {
+ speed = SPEED_1000;
+ }
+ } else if (status & IGC_STATUS_SPEED_100) {
+ speed = SPEED_100;
+ } else {
+ speed = SPEED_10;
+ }
+ if ((status & IGC_STATUS_FD) ||
+ hw->phy.media_type != igc_media_type_copper)
+ cmd->base.duplex = DUPLEX_FULL;
+ else
+ cmd->base.duplex = DUPLEX_HALF;
+ } else {
+ speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ }
+ cmd->base.speed = speed;
+ if (hw->mac.autoneg)
+ cmd->base.autoneg = AUTONEG_ENABLE;
+ else
+ cmd->base.autoneg = AUTONEG_DISABLE;
+
+ /* MDI-X => 2; MDI =>1; Invalid =>0 */
+ if (hw->phy.media_type == igc_media_type_copper)
+ cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+ ETH_TP_MDI;
+ else
+ cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
+
+ if (hw->phy.mdix == AUTO_ALL_MODES)
+ cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+ else
+ cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+ return 0;
+}
+
+static int igc_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ u32 advertising;
+
+ /* When adapter in resetting mode, autoneg/speed/duplex
+ * cannot be changed
+ */
+ if (igc_check_reset_block(hw)) {
+ dev_err(&adapter->pdev->dev,
+ "Cannot change link characteristics when reset is active.\n");
+ return -EINVAL;
+ }
+
+ /* MDI setting is only allowed when autoneg enabled because
+ * some hardware doesn't allow MDI setting when speed or
+ * duplex is forced.
+ */
+ if (cmd->base.eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
+ cmd->base.autoneg != AUTONEG_ENABLE) {
+ dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+ return -EINVAL;
+ }
+ }
+
+ while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
+
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
+ hw->mac.autoneg = 1;
+ hw->phy.autoneg_advertised = advertising;
+ if (adapter->fc_autoneg)
+ hw->fc.requested_mode = igc_fc_default;
+ } else {
+ /* calling this overrides forced MDI setting */
+ dev_info(&adapter->pdev->dev,
+ "Force mode currently not supported\n");
+ }
+
+ /* MDI-X => 2; MDI => 1; Auto => 3 */
+ if (cmd->base.eth_tp_mdix_ctrl) {
+ /* fix up the value for auto (3 => 0) as zero is mapped
+ * internally to auto
+ */
+ if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ hw->phy.mdix = AUTO_ALL_MODES;
+ else
+ hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
+ }
+
+ /* reset the link */
+ if (netif_running(adapter->netdev)) {
+ igc_down(adapter);
+ igc_up(adapter);
+ } else {
+ igc_reset(adapter);
+ }
+
+ clear_bit(__IGC_RESETTING, &adapter->state);
+
+ return 0;
+}
+
+static const struct ethtool_ops igc_ethtool_ops = {
+ .get_drvinfo = igc_get_drvinfo,
+ .get_regs_len = igc_get_regs_len,
+ .get_regs = igc_get_regs,
+ .get_msglevel = igc_get_msglevel,
+ .set_msglevel = igc_set_msglevel,
+ .nway_reset = igc_nway_reset,
+ .get_link = igc_get_link,
+ .get_eeprom_len = igc_get_eeprom_len,
+ .get_eeprom = igc_get_eeprom,
+ .set_eeprom = igc_set_eeprom,
+ .get_ringparam = igc_get_ringparam,
+ .set_ringparam = igc_set_ringparam,
+ .get_pauseparam = igc_get_pauseparam,
+ .set_pauseparam = igc_set_pauseparam,
+ .get_strings = igc_get_strings,
+ .get_sset_count = igc_get_sset_count,
+ .get_ethtool_stats = igc_get_ethtool_stats,
+ .get_coalesce = igc_get_coalesce,
+ .set_coalesce = igc_set_coalesce,
+ .get_rxnfc = igc_get_rxnfc,
+ .set_rxnfc = igc_set_rxnfc,
+ .get_rxfh_indir_size = igc_get_rxfh_indir_size,
+ .get_rxfh = igc_get_rxfh,
+ .set_rxfh = igc_set_rxfh,
+ .get_channels = igc_get_channels,
+ .set_channels = igc_set_channels,
+ .get_priv_flags = igc_get_priv_flags,
+ .set_priv_flags = igc_set_priv_flags,
+ .begin = igc_ethtool_begin,
+ .complete = igc_ethtool_complete,
+ .get_link_ksettings = igc_get_link_ksettings,
+ .set_link_ksettings = igc_set_link_ksettings,
+};
+
+void igc_set_ethtool_ops(struct net_device *netdev)
+{
+ netdev->ethtool_ops = &igc_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
new file mode 100644
index 0000000..abb2d72
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -0,0 +1,311 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_HW_H_
+#define _IGC_HW_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+
+#include "igc_regs.h"
+#include "igc_defines.h"
+#include "igc_mac.h"
+#include "igc_phy.h"
+#include "igc_nvm.h"
+#include "igc_i225.h"
+#include "igc_base.h"
+
+#define IGC_DEV_ID_I225_LM 0x15F2
+#define IGC_DEV_ID_I225_V 0x15F3
+#define IGC_DEV_ID_I225_I 0x15F8
+#define IGC_DEV_ID_I220_V 0x15F7
+#define IGC_DEV_ID_I225_K 0x3100
+
+#define IGC_FUNC_0 0
+
+/* Function pointers for the MAC. */
+struct igc_mac_operations {
+ s32 (*check_for_link)(struct igc_hw *hw);
+ s32 (*reset_hw)(struct igc_hw *hw);
+ s32 (*init_hw)(struct igc_hw *hw);
+ s32 (*setup_physical_interface)(struct igc_hw *hw);
+ void (*rar_set)(struct igc_hw *hw, u8 *address, u32 index);
+ s32 (*read_mac_addr)(struct igc_hw *hw);
+ s32 (*get_speed_and_duplex)(struct igc_hw *hw, u16 *speed,
+ u16 *duplex);
+ s32 (*acquire_swfw_sync)(struct igc_hw *hw, u16 mask);
+ void (*release_swfw_sync)(struct igc_hw *hw, u16 mask);
+};
+
+enum igc_mac_type {
+ igc_undefined = 0,
+ igc_i225,
+ igc_num_macs /* List is 1-based, so subtract 1 for true count. */
+};
+
+enum igc_phy_type {
+ igc_phy_unknown = 0,
+ igc_phy_none,
+ igc_phy_i225,
+};
+
+enum igc_media_type {
+ igc_media_type_unknown = 0,
+ igc_media_type_copper = 1,
+ igc_num_media_types
+};
+
+enum igc_nvm_type {
+ igc_nvm_unknown = 0,
+ igc_nvm_eeprom_spi,
+ igc_nvm_flash_hw,
+ igc_nvm_invm,
+};
+
+struct igc_info {
+ s32 (*get_invariants)(struct igc_hw *hw);
+ struct igc_mac_operations *mac_ops;
+ const struct igc_phy_operations *phy_ops;
+ struct igc_nvm_operations *nvm_ops;
+};
+
+extern const struct igc_info igc_base_info;
+
+struct igc_mac_info {
+ struct igc_mac_operations ops;
+
+ u8 addr[ETH_ALEN];
+ u8 perm_addr[ETH_ALEN];
+
+ enum igc_mac_type type;
+
+ u32 collision_delta;
+ u32 ledctl_default;
+ u32 ledctl_mode1;
+ u32 ledctl_mode2;
+ u32 mc_filter_type;
+ u32 tx_packet_delta;
+ u32 txcw;
+
+ u16 mta_reg_count;
+ u16 uta_reg_count;
+
+ u16 rar_entry_count;
+
+ u8 forced_speed_duplex;
+
+ bool adaptive_ifs;
+ bool has_fwsm;
+ bool asf_firmware_present;
+ bool arc_subsystem_valid;
+
+ bool autoneg;
+ bool autoneg_failed;
+ bool get_link_status;
+};
+
+struct igc_nvm_operations {
+ s32 (*acquire)(struct igc_hw *hw);
+ s32 (*read)(struct igc_hw *hw, u16 offset, u16 i, u16 *data);
+ void (*release)(struct igc_hw *hw);
+ s32 (*write)(struct igc_hw *hw, u16 offset, u16 i, u16 *data);
+ s32 (*update)(struct igc_hw *hw);
+ s32 (*validate)(struct igc_hw *hw);
+ s32 (*valid_led_default)(struct igc_hw *hw, u16 *data);
+};
+
+struct igc_phy_operations {
+ s32 (*acquire)(struct igc_hw *hw);
+ s32 (*check_reset_block)(struct igc_hw *hw);
+ s32 (*force_speed_duplex)(struct igc_hw *hw);
+ s32 (*get_phy_info)(struct igc_hw *hw);
+ s32 (*read_reg)(struct igc_hw *hw, u32 address, u16 *data);
+ void (*release)(struct igc_hw *hw);
+ s32 (*reset)(struct igc_hw *hw);
+ s32 (*write_reg)(struct igc_hw *hw, u32 address, u16 data);
+};
+
+struct igc_nvm_info {
+ struct igc_nvm_operations ops;
+ enum igc_nvm_type type;
+
+ u32 flash_bank_size;
+ u32 flash_base_addr;
+
+ u16 word_size;
+ u16 delay_usec;
+ u16 address_bits;
+ u16 opcode_bits;
+ u16 page_size;
+};
+
+struct igc_phy_info {
+ struct igc_phy_operations ops;
+
+ enum igc_phy_type type;
+
+ u32 addr;
+ u32 id;
+ u32 reset_delay_us; /* in usec */
+ u32 revision;
+
+ enum igc_media_type media_type;
+
+ u16 autoneg_advertised;
+ u16 autoneg_mask;
+
+ u8 mdix;
+
+ bool is_mdix;
+ bool reset_disable;
+ bool speed_downgraded;
+ bool autoneg_wait_to_complete;
+};
+
+struct igc_bus_info {
+ u16 func;
+ u16 pci_cmd_word;
+};
+
+enum igc_fc_mode {
+ igc_fc_none = 0,
+ igc_fc_rx_pause,
+ igc_fc_tx_pause,
+ igc_fc_full,
+ igc_fc_default = 0xFF
+};
+
+struct igc_fc_info {
+ u32 high_water; /* Flow control high-water mark */
+ u32 low_water; /* Flow control low-water mark */
+ u16 pause_time; /* Flow control pause timer */
+ bool send_xon; /* Flow control send XON */
+ bool strict_ieee; /* Strict IEEE mode */
+ enum igc_fc_mode current_mode; /* Type of flow control */
+ enum igc_fc_mode requested_mode;
+};
+
+struct igc_dev_spec_base {
+ bool clear_semaphore_once;
+};
+
+struct igc_hw {
+ void *back;
+
+ u8 __iomem *hw_addr;
+ unsigned long io_base;
+
+ struct igc_mac_info mac;
+ struct igc_fc_info fc;
+ struct igc_nvm_info nvm;
+ struct igc_phy_info phy;
+
+ struct igc_bus_info bus;
+
+ union {
+ struct igc_dev_spec_base _base;
+ } dev_spec;
+
+ u16 device_id;
+ u16 subsystem_vendor_id;
+ u16 subsystem_device_id;
+ u16 vendor_id;
+
+ u8 revision_id;
+};
+
+/* Statistics counters collected by the MAC */
+struct igc_hw_stats {
+ u64 crcerrs;
+ u64 algnerrc;
+ u64 symerrs;
+ u64 rxerrc;
+ u64 mpc;
+ u64 scc;
+ u64 ecol;
+ u64 mcc;
+ u64 latecol;
+ u64 colc;
+ u64 dc;
+ u64 tncrs;
+ u64 sec;
+ u64 cexterr;
+ u64 rlec;
+ u64 xonrxc;
+ u64 xontxc;
+ u64 xoffrxc;
+ u64 xofftxc;
+ u64 fcruc;
+ u64 prc64;
+ u64 prc127;
+ u64 prc255;
+ u64 prc511;
+ u64 prc1023;
+ u64 prc1522;
+ u64 gprc;
+ u64 bprc;
+ u64 mprc;
+ u64 gptc;
+ u64 gorc;
+ u64 gotc;
+ u64 rnbc;
+ u64 ruc;
+ u64 rfc;
+ u64 roc;
+ u64 rjc;
+ u64 mgprc;
+ u64 mgpdc;
+ u64 mgptc;
+ u64 tor;
+ u64 tot;
+ u64 tpr;
+ u64 tpt;
+ u64 ptc64;
+ u64 ptc127;
+ u64 ptc255;
+ u64 ptc511;
+ u64 ptc1023;
+ u64 ptc1522;
+ u64 mptc;
+ u64 bptc;
+ u64 tsctc;
+ u64 tsctfc;
+ u64 iac;
+ u64 icrxptc;
+ u64 icrxatc;
+ u64 ictxptc;
+ u64 ictxatc;
+ u64 ictxqec;
+ u64 ictxqmtc;
+ u64 icrxdmtc;
+ u64 icrxoc;
+ u64 cbtmpc;
+ u64 htdpmc;
+ u64 cbrdpc;
+ u64 cbrmpc;
+ u64 rpthc;
+ u64 hgptc;
+ u64 htcbdpc;
+ u64 hgorc;
+ u64 hgotc;
+ u64 lenerrs;
+ u64 scvpc;
+ u64 hrmpc;
+ u64 doosync;
+ u64 o2bgptc;
+ u64 o2bspc;
+ u64 b2ospc;
+ u64 b2ogprc;
+};
+
+struct net_device *igc_get_hw_dev(struct igc_hw *hw);
+#define hw_dbg(format, arg...) \
+ netdev_dbg(igc_get_hw_dev(hw), format, ##arg)
+
+s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
+s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
+void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
+void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
+
+#endif /* _IGC_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
new file mode 100644
index 0000000..c25f555
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include <linux/delay.h>
+
+#include "igc_hw.h"
+
+/**
+ * igc_get_hw_semaphore_i225 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the necessary semaphores for exclusive access to the EEPROM.
+ * Set the EEPROM access request bit and wait for EEPROM access grant bit.
+ * Return successful if access grant bit set, else clear the request for
+ * EEPROM access and return -IGC_ERR_NVM (-1).
+ */
+static s32 igc_acquire_nvm_i225(struct igc_hw *hw)
+{
+ return igc_acquire_swfw_sync_i225(hw, IGC_SWFW_EEP_SM);
+}
+
+/**
+ * igc_release_nvm_i225 - Release exclusive access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Stop any current commands to the EEPROM and clear the EEPROM request bit,
+ * then release the semaphores acquired.
+ */
+static void igc_release_nvm_i225(struct igc_hw *hw)
+{
+ igc_release_swfw_sync_i225(hw, IGC_SWFW_EEP_SM);
+}
+
+/**
+ * igc_get_hw_semaphore_i225 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the HW semaphore to access the PHY or NVM
+ */
+static s32 igc_get_hw_semaphore_i225(struct igc_hw *hw)
+{
+ s32 timeout = hw->nvm.word_size + 1;
+ s32 i = 0;
+ u32 swsm;
+
+ /* Get the SW semaphore */
+ while (i < timeout) {
+ swsm = rd32(IGC_SWSM);
+ if (!(swsm & IGC_SWSM_SMBI))
+ break;
+
+ usleep_range(500, 600);
+ i++;
+ }
+
+ if (i == timeout) {
+ /* In rare circumstances, the SW semaphore may already be held
+ * unintentionally. Clear the semaphore once before giving up.
+ */
+ if (hw->dev_spec._base.clear_semaphore_once) {
+ hw->dev_spec._base.clear_semaphore_once = false;
+ igc_put_hw_semaphore(hw);
+ for (i = 0; i < timeout; i++) {
+ swsm = rd32(IGC_SWSM);
+ if (!(swsm & IGC_SWSM_SMBI))
+ break;
+
+ usleep_range(500, 600);
+ }
+ }
+
+ /* If we do not have the semaphore here, we have to give up. */
+ if (i == timeout) {
+ hw_dbg("Driver can't access device - SMBI bit is set.\n");
+ return -IGC_ERR_NVM;
+ }
+ }
+
+ /* Get the FW semaphore. */
+ for (i = 0; i < timeout; i++) {
+ swsm = rd32(IGC_SWSM);
+ wr32(IGC_SWSM, swsm | IGC_SWSM_SWESMBI);
+
+ /* Semaphore acquired if bit latched */
+ if (rd32(IGC_SWSM) & IGC_SWSM_SWESMBI)
+ break;
+
+ usleep_range(500, 600);
+ }
+
+ if (i == timeout) {
+ /* Release semaphores */
+ igc_put_hw_semaphore(hw);
+ hw_dbg("Driver can't access the NVM\n");
+ return -IGC_ERR_NVM;
+ }
+
+ return 0;
+}
+
+/**
+ * igc_acquire_swfw_sync_i225 - Acquire SW/FW semaphore
+ * @hw: pointer to the HW structure
+ * @mask: specifies which semaphore to acquire
+ *
+ * Acquire the SW/FW semaphore to access the PHY or NVM. The mask
+ * will also specify which port we're acquiring the lock for.
+ */
+s32 igc_acquire_swfw_sync_i225(struct igc_hw *hw, u16 mask)
+{
+ s32 i = 0, timeout = 200;
+ u32 fwmask = mask << 16;
+ u32 swmask = mask;
+ s32 ret_val = 0;
+ u32 swfw_sync;
+
+ while (i < timeout) {
+ if (igc_get_hw_semaphore_i225(hw)) {
+ ret_val = -IGC_ERR_SWFW_SYNC;
+ goto out;
+ }
+
+ swfw_sync = rd32(IGC_SW_FW_SYNC);
+ if (!(swfw_sync & (fwmask | swmask)))
+ break;
+
+ /* Firmware currently using resource (fwmask) */
+ igc_put_hw_semaphore(hw);
+ mdelay(5);
+ i++;
+ }
+
+ if (i == timeout) {
+ hw_dbg("Driver can't access resource, SW_FW_SYNC timeout.\n");
+ ret_val = -IGC_ERR_SWFW_SYNC;
+ goto out;
+ }
+
+ swfw_sync |= swmask;
+ wr32(IGC_SW_FW_SYNC, swfw_sync);
+
+ igc_put_hw_semaphore(hw);
+out:
+ return ret_val;
+}
+
+/**
+ * igc_release_swfw_sync_i225 - Release SW/FW semaphore
+ * @hw: pointer to the HW structure
+ * @mask: specifies which semaphore to acquire
+ *
+ * Release the SW/FW semaphore used to access the PHY or NVM. The mask
+ * will also specify which port we're releasing the lock for.
+ */
+void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask)
+{
+ u32 swfw_sync;
+
+ while (igc_get_hw_semaphore_i225(hw))
+ ; /* Empty */
+
+ swfw_sync = rd32(IGC_SW_FW_SYNC);
+ swfw_sync &= ~mask;
+ wr32(IGC_SW_FW_SYNC, swfw_sync);
+
+ igc_put_hw_semaphore(hw);
+}
+
+/**
+ * igc_read_nvm_srrd_i225 - Reads Shadow Ram using EERD register
+ * @hw: pointer to the HW structure
+ * @offset: offset of word in the Shadow Ram to read
+ * @words: number of words to read
+ * @data: word read from the Shadow Ram
+ *
+ * Reads a 16 bit word from the Shadow Ram using the EERD register.
+ * Uses necessary synchronization semaphores.
+ */
+static s32 igc_read_nvm_srrd_i225(struct igc_hw *hw, u16 offset, u16 words,
+ u16 *data)
+{
+ s32 status = 0;
+ u16 i, count;
+
+ /* We cannot hold synchronization semaphores for too long,
+ * because of forceful takeover procedure. However it is more efficient
+ * to read in bursts than synchronizing access for each word.
+ */
+ for (i = 0; i < words; i += IGC_EERD_EEWR_MAX_COUNT) {
+ count = (words - i) / IGC_EERD_EEWR_MAX_COUNT > 0 ?
+ IGC_EERD_EEWR_MAX_COUNT : (words - i);
+
+ status = hw->nvm.ops.acquire(hw);
+ if (status)
+ break;
+
+ status = igc_read_nvm_eerd(hw, offset, count, data + i);
+ hw->nvm.ops.release(hw);
+ if (status)
+ break;
+ }
+
+ return status;
+}
+
+/**
+ * igc_write_nvm_srwr - Write to Shadow Ram using EEWR
+ * @hw: pointer to the HW structure
+ * @offset: offset within the Shadow Ram to be written to
+ * @words: number of words to write
+ * @data: 16 bit word(s) to be written to the Shadow Ram
+ *
+ * Writes data to Shadow Ram at offset using EEWR register.
+ *
+ * If igc_update_nvm_checksum is not called after this function , the
+ * Shadow Ram will most likely contain an invalid checksum.
+ */
+static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words,
+ u16 *data)
+{
+ struct igc_nvm_info *nvm = &hw->nvm;
+ u32 attempts = 100000;
+ u32 i, k, eewr = 0;
+ s32 ret_val = 0;
+
+ /* A check for invalid values: offset too large, too many words,
+ * too many words for the offset, and not enough words.
+ */
+ if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) ||
+ words == 0) {
+ hw_dbg("nvm parameter(s) out of bounds\n");
+ ret_val = -IGC_ERR_NVM;
+ goto out;
+ }
+
+ for (i = 0; i < words; i++) {
+ eewr = ((offset + i) << IGC_NVM_RW_ADDR_SHIFT) |
+ (data[i] << IGC_NVM_RW_REG_DATA) |
+ IGC_NVM_RW_REG_START;
+
+ wr32(IGC_SRWR, eewr);
+
+ for (k = 0; k < attempts; k++) {
+ if (IGC_NVM_RW_REG_DONE &
+ rd32(IGC_SRWR)) {
+ ret_val = 0;
+ break;
+ }
+ udelay(5);
+ }
+
+ if (ret_val) {
+ hw_dbg("Shadow RAM write EEWR timed out\n");
+ break;
+ }
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_write_nvm_srwr_i225 - Write to Shadow RAM using EEWR
+ * @hw: pointer to the HW structure
+ * @offset: offset within the Shadow RAM to be written to
+ * @words: number of words to write
+ * @data: 16 bit word(s) to be written to the Shadow RAM
+ *
+ * Writes data to Shadow RAM at offset using EEWR register.
+ *
+ * If igc_update_nvm_checksum is not called after this function , the
+ * data will not be committed to FLASH and also Shadow RAM will most likely
+ * contain an invalid checksum.
+ *
+ * If error code is returned, data and Shadow RAM may be inconsistent - buffer
+ * partially written.
+ */
+static s32 igc_write_nvm_srwr_i225(struct igc_hw *hw, u16 offset, u16 words,
+ u16 *data)
+{
+ s32 status = 0;
+ u16 i, count;
+
+ /* We cannot hold synchronization semaphores for too long,
+ * because of forceful takeover procedure. However it is more efficient
+ * to write in bursts than synchronizing access for each word.
+ */
+ for (i = 0; i < words; i += IGC_EERD_EEWR_MAX_COUNT) {
+ count = (words - i) / IGC_EERD_EEWR_MAX_COUNT > 0 ?
+ IGC_EERD_EEWR_MAX_COUNT : (words - i);
+
+ status = hw->nvm.ops.acquire(hw);
+ if (status)
+ break;
+
+ status = igc_write_nvm_srwr(hw, offset, count, data + i);
+ hw->nvm.ops.release(hw);
+ if (status)
+ break;
+ }
+
+ return status;
+}
+
+/**
+ * igc_validate_nvm_checksum_i225 - Validate EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Calculates the EEPROM checksum by reading/adding each word of the EEPROM
+ * and then verifies that the sum of the EEPROM is equal to 0xBABA.
+ */
+static s32 igc_validate_nvm_checksum_i225(struct igc_hw *hw)
+{
+ s32 (*read_op_ptr)(struct igc_hw *hw, u16 offset, u16 count,
+ u16 *data);
+ s32 status = 0;
+
+ status = hw->nvm.ops.acquire(hw);
+ if (status)
+ goto out;
+
+ /* Replace the read function with semaphore grabbing with
+ * the one that skips this for a while.
+ * We have semaphore taken already here.
+ */
+ read_op_ptr = hw->nvm.ops.read;
+ hw->nvm.ops.read = igc_read_nvm_eerd;
+
+ status = igc_validate_nvm_checksum(hw);
+
+ /* Revert original read operation. */
+ hw->nvm.ops.read = read_op_ptr;
+
+ hw->nvm.ops.release(hw);
+
+out:
+ return status;
+}
+
+/**
+ * igc_pool_flash_update_done_i225 - Pool FLUDONE status
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_pool_flash_update_done_i225(struct igc_hw *hw)
+{
+ s32 ret_val = -IGC_ERR_NVM;
+ u32 i, reg;
+
+ for (i = 0; i < IGC_FLUDONE_ATTEMPTS; i++) {
+ reg = rd32(IGC_EECD);
+ if (reg & IGC_EECD_FLUDONE_I225) {
+ ret_val = 0;
+ break;
+ }
+ udelay(5);
+ }
+
+ return ret_val;
+}
+
+/**
+ * igc_update_flash_i225 - Commit EEPROM to the flash
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_update_flash_i225(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+ u32 flup;
+
+ ret_val = igc_pool_flash_update_done_i225(hw);
+ if (ret_val == -IGC_ERR_NVM) {
+ hw_dbg("Flash update time out\n");
+ goto out;
+ }
+
+ flup = rd32(IGC_EECD) | IGC_EECD_FLUPD_I225;
+ wr32(IGC_EECD, flup);
+
+ ret_val = igc_pool_flash_update_done_i225(hw);
+ if (ret_val)
+ hw_dbg("Flash update time out\n");
+ else
+ hw_dbg("Flash update complete\n");
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_update_nvm_checksum_i225 - Update EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Updates the EEPROM checksum by reading/adding each word of the EEPROM
+ * up to the checksum. Then calculates the EEPROM checksum and writes the
+ * value to the EEPROM. Next commit EEPROM data onto the Flash.
+ */
+static s32 igc_update_nvm_checksum_i225(struct igc_hw *hw)
+{
+ u16 checksum = 0;
+ s32 ret_val = 0;
+ u16 i, nvm_data;
+
+ /* Read the first word from the EEPROM. If this times out or fails, do
+ * not continue or we could be in for a very long wait while every
+ * EEPROM read fails
+ */
+ ret_val = igc_read_nvm_eerd(hw, 0, 1, &nvm_data);
+ if (ret_val) {
+ hw_dbg("EEPROM read failed\n");
+ goto out;
+ }
+
+ ret_val = hw->nvm.ops.acquire(hw);
+ if (ret_val)
+ goto out;
+
+ /* Do not use hw->nvm.ops.write, hw->nvm.ops.read
+ * because we do not want to take the synchronization
+ * semaphores twice here.
+ */
+
+ for (i = 0; i < NVM_CHECKSUM_REG; i++) {
+ ret_val = igc_read_nvm_eerd(hw, i, 1, &nvm_data);
+ if (ret_val) {
+ hw->nvm.ops.release(hw);
+ hw_dbg("NVM Read Error while updating checksum.\n");
+ goto out;
+ }
+ checksum += nvm_data;
+ }
+ checksum = (u16)NVM_SUM - checksum;
+ ret_val = igc_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1,
+ &checksum);
+ if (ret_val) {
+ hw->nvm.ops.release(hw);
+ hw_dbg("NVM Write Error while updating checksum.\n");
+ goto out;
+ }
+
+ hw->nvm.ops.release(hw);
+
+ ret_val = igc_update_flash_i225(hw);
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_get_flash_presence_i225 - Check if flash device is detected
+ * @hw: pointer to the HW structure
+ */
+bool igc_get_flash_presence_i225(struct igc_hw *hw)
+{
+ bool ret_val = false;
+ u32 eec = 0;
+
+ eec = rd32(IGC_EECD);
+ if (eec & IGC_EECD_FLASH_DETECTED_I225)
+ ret_val = true;
+
+ return ret_val;
+}
+
+/**
+ * igc_init_nvm_params_i225 - Init NVM func ptrs.
+ * @hw: pointer to the HW structure
+ */
+s32 igc_init_nvm_params_i225(struct igc_hw *hw)
+{
+ struct igc_nvm_info *nvm = &hw->nvm;
+
+ nvm->ops.acquire = igc_acquire_nvm_i225;
+ nvm->ops.release = igc_release_nvm_i225;
+
+ /* NVM Function Pointers */
+ if (igc_get_flash_presence_i225(hw)) {
+ hw->nvm.type = igc_nvm_flash_hw;
+ nvm->ops.read = igc_read_nvm_srrd_i225;
+ nvm->ops.write = igc_write_nvm_srwr_i225;
+ nvm->ops.validate = igc_validate_nvm_checksum_i225;
+ nvm->ops.update = igc_update_nvm_checksum_i225;
+ } else {
+ hw->nvm.type = igc_nvm_invm;
+ nvm->ops.read = igc_read_nvm_eerd;
+ nvm->ops.write = NULL;
+ nvm->ops.validate = NULL;
+ nvm->ops.update = NULL;
+ }
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.h b/drivers/net/ethernet/intel/igc/igc_i225.h
new file mode 100644
index 0000000..7b66e1f
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_i225.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_I225_H_
+#define _IGC_I225_H_
+
+s32 igc_acquire_swfw_sync_i225(struct igc_hw *hw, u16 mask);
+void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask);
+
+s32 igc_init_nvm_params_i225(struct igc_hw *hw);
+bool igc_get_flash_presence_i225(struct igc_hw *hw);
+
+#endif
diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
new file mode 100644
index 0000000..5eeb4c8
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -0,0 +1,786 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include <linux/pci.h>
+#include <linux/delay.h>
+
+#include "igc_mac.h"
+#include "igc_hw.h"
+
+/**
+ * igc_disable_pcie_master - Disables PCI-express master access
+ * @hw: pointer to the HW structure
+ *
+ * Returns 0 (0) if successful, else returns -10
+ * (-IGC_ERR_MASTER_REQUESTS_PENDING) if master disable bit has not caused
+ * the master requests to be disabled.
+ *
+ * Disables PCI-Express master access and verifies there are no pending
+ * requests.
+ */
+s32 igc_disable_pcie_master(struct igc_hw *hw)
+{
+ s32 timeout = MASTER_DISABLE_TIMEOUT;
+ s32 ret_val = 0;
+ u32 ctrl;
+
+ ctrl = rd32(IGC_CTRL);
+ ctrl |= IGC_CTRL_GIO_MASTER_DISABLE;
+ wr32(IGC_CTRL, ctrl);
+
+ while (timeout) {
+ if (!(rd32(IGC_STATUS) &
+ IGC_STATUS_GIO_MASTER_ENABLE))
+ break;
+ usleep_range(2000, 3000);
+ timeout--;
+ }
+
+ if (!timeout) {
+ hw_dbg("Master requests are pending.\n");
+ ret_val = -IGC_ERR_MASTER_REQUESTS_PENDING;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_init_rx_addrs - Initialize receive addresses
+ * @hw: pointer to the HW structure
+ * @rar_count: receive address registers
+ *
+ * Setup the receive address registers by setting the base receive address
+ * register to the devices MAC address and clearing all the other receive
+ * address registers to 0.
+ */
+void igc_init_rx_addrs(struct igc_hw *hw, u16 rar_count)
+{
+ u8 mac_addr[ETH_ALEN] = {0};
+ u32 i;
+
+ /* Setup the receive address */
+ hw_dbg("Programming MAC Address into RAR[0]\n");
+
+ hw->mac.ops.rar_set(hw, hw->mac.addr, 0);
+
+ /* Zero out the other (rar_entry_count - 1) receive addresses */
+ hw_dbg("Clearing RAR[1-%u]\n", rar_count - 1);
+ for (i = 1; i < rar_count; i++)
+ hw->mac.ops.rar_set(hw, mac_addr, i);
+}
+
+/**
+ * igc_set_fc_watermarks - Set flow control high/low watermarks
+ * @hw: pointer to the HW structure
+ *
+ * Sets the flow control high/low threshold (watermark) registers. If
+ * flow control XON frame transmission is enabled, then set XON frame
+ * transmission as well.
+ */
+static s32 igc_set_fc_watermarks(struct igc_hw *hw)
+{
+ u32 fcrtl = 0, fcrth = 0;
+
+ /* Set the flow control receive threshold registers. Normally,
+ * these registers will be set to a default threshold that may be
+ * adjusted later by the driver's runtime code. However, if the
+ * ability to transmit pause frames is not enabled, then these
+ * registers will be set to 0.
+ */
+ if (hw->fc.current_mode & igc_fc_tx_pause) {
+ /* We need to set up the Receive Threshold high and low water
+ * marks as well as (optionally) enabling the transmission of
+ * XON frames.
+ */
+ fcrtl = hw->fc.low_water;
+ if (hw->fc.send_xon)
+ fcrtl |= IGC_FCRTL_XONE;
+
+ fcrth = hw->fc.high_water;
+ }
+ wr32(IGC_FCRTL, fcrtl);
+ wr32(IGC_FCRTH, fcrth);
+
+ return 0;
+}
+
+/**
+ * igc_setup_link - Setup flow control and link settings
+ * @hw: pointer to the HW structure
+ *
+ * Determines which flow control settings to use, then configures flow
+ * control. Calls the appropriate media-specific link configuration
+ * function. Assuming the adapter has a valid link partner, a valid link
+ * should be established. Assumes the hardware has previously been reset
+ * and the transmitter and receiver are not enabled.
+ */
+s32 igc_setup_link(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+
+ /* In the case of the phy reset being blocked, we already have a link.
+ * We do not need to set it up again.
+ */
+ if (igc_check_reset_block(hw))
+ goto out;
+
+ /* If requested flow control is set to default, set flow control
+ * to the both 'rx' and 'tx' pause frames.
+ */
+ if (hw->fc.requested_mode == igc_fc_default)
+ hw->fc.requested_mode = igc_fc_full;
+
+ /* We want to save off the original Flow Control configuration just
+ * in case we get disconnected and then reconnected into a different
+ * hub or switch with different Flow Control capabilities.
+ */
+ hw->fc.current_mode = hw->fc.requested_mode;
+
+ hw_dbg("After fix-ups FlowControl is now = %x\n", hw->fc.current_mode);
+
+ /* Call the necessary media_type subroutine to configure the link. */
+ ret_val = hw->mac.ops.setup_physical_interface(hw);
+ if (ret_val)
+ goto out;
+
+ /* Initialize the flow control address, type, and PAUSE timer
+ * registers to their default values. This is done even if flow
+ * control is disabled, because it does not hurt anything to
+ * initialize these registers.
+ */
+ hw_dbg("Initializing the Flow Control address, type and timer regs\n");
+ wr32(IGC_FCT, FLOW_CONTROL_TYPE);
+ wr32(IGC_FCAH, FLOW_CONTROL_ADDRESS_HIGH);
+ wr32(IGC_FCAL, FLOW_CONTROL_ADDRESS_LOW);
+
+ wr32(IGC_FCTTV, hw->fc.pause_time);
+
+ ret_val = igc_set_fc_watermarks(hw);
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_force_mac_fc - Force the MAC's flow control settings
+ * @hw: pointer to the HW structure
+ *
+ * Force the MAC's flow control settings. Sets the TFCE and RFCE bits in the
+ * device control register to reflect the adapter settings. TFCE and RFCE
+ * need to be explicitly set by software when a copper PHY is used because
+ * autonegotiation is managed by the PHY rather than the MAC. Software must
+ * also configure these bits when link is forced on a fiber connection.
+ */
+s32 igc_force_mac_fc(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+ u32 ctrl;
+
+ ctrl = rd32(IGC_CTRL);
+
+ /* Because we didn't get link via the internal auto-negotiation
+ * mechanism (we either forced link or we got link via PHY
+ * auto-neg), we have to manually enable/disable transmit an
+ * receive flow control.
+ *
+ * The "Case" statement below enables/disable flow control
+ * according to the "hw->fc.current_mode" parameter.
+ *
+ * The possible values of the "fc" parameter are:
+ * 0: Flow control is completely disabled
+ * 1: Rx flow control is enabled (we can receive pause
+ * frames but not send pause frames).
+ * 2: Tx flow control is enabled (we can send pause frames
+ * frames but we do not receive pause frames).
+ * 3: Both Rx and TX flow control (symmetric) is enabled.
+ * other: No other values should be possible at this point.
+ */
+ hw_dbg("hw->fc.current_mode = %u\n", hw->fc.current_mode);
+
+ switch (hw->fc.current_mode) {
+ case igc_fc_none:
+ ctrl &= (~(IGC_CTRL_TFCE | IGC_CTRL_RFCE));
+ break;
+ case igc_fc_rx_pause:
+ ctrl &= (~IGC_CTRL_TFCE);
+ ctrl |= IGC_CTRL_RFCE;
+ break;
+ case igc_fc_tx_pause:
+ ctrl &= (~IGC_CTRL_RFCE);
+ ctrl |= IGC_CTRL_TFCE;
+ break;
+ case igc_fc_full:
+ ctrl |= (IGC_CTRL_TFCE | IGC_CTRL_RFCE);
+ break;
+ default:
+ hw_dbg("Flow control param set incorrectly\n");
+ ret_val = -IGC_ERR_CONFIG;
+ goto out;
+ }
+
+ wr32(IGC_CTRL, ctrl);
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_clear_hw_cntrs_base - Clear base hardware counters
+ * @hw: pointer to the HW structure
+ *
+ * Clears the base hardware counters by reading the counter registers.
+ */
+void igc_clear_hw_cntrs_base(struct igc_hw *hw)
+{
+ rd32(IGC_CRCERRS);
+ rd32(IGC_SYMERRS);
+ rd32(IGC_MPC);
+ rd32(IGC_SCC);
+ rd32(IGC_ECOL);
+ rd32(IGC_MCC);
+ rd32(IGC_LATECOL);
+ rd32(IGC_COLC);
+ rd32(IGC_DC);
+ rd32(IGC_SEC);
+ rd32(IGC_RLEC);
+ rd32(IGC_XONRXC);
+ rd32(IGC_XONTXC);
+ rd32(IGC_XOFFRXC);
+ rd32(IGC_XOFFTXC);
+ rd32(IGC_FCRUC);
+ rd32(IGC_GPRC);
+ rd32(IGC_BPRC);
+ rd32(IGC_MPRC);
+ rd32(IGC_GPTC);
+ rd32(IGC_GORCL);
+ rd32(IGC_GORCH);
+ rd32(IGC_GOTCL);
+ rd32(IGC_GOTCH);
+ rd32(IGC_RNBC);
+ rd32(IGC_RUC);
+ rd32(IGC_RFC);
+ rd32(IGC_ROC);
+ rd32(IGC_RJC);
+ rd32(IGC_TORL);
+ rd32(IGC_TORH);
+ rd32(IGC_TOTL);
+ rd32(IGC_TOTH);
+ rd32(IGC_TPR);
+ rd32(IGC_TPT);
+ rd32(IGC_MPTC);
+ rd32(IGC_BPTC);
+
+ rd32(IGC_PRC64);
+ rd32(IGC_PRC127);
+ rd32(IGC_PRC255);
+ rd32(IGC_PRC511);
+ rd32(IGC_PRC1023);
+ rd32(IGC_PRC1522);
+ rd32(IGC_PTC64);
+ rd32(IGC_PTC127);
+ rd32(IGC_PTC255);
+ rd32(IGC_PTC511);
+ rd32(IGC_PTC1023);
+ rd32(IGC_PTC1522);
+
+ rd32(IGC_ALGNERRC);
+ rd32(IGC_RXERRC);
+ rd32(IGC_TNCRS);
+ rd32(IGC_CEXTERR);
+ rd32(IGC_TSCTC);
+ rd32(IGC_TSCTFC);
+
+ rd32(IGC_MGTPRC);
+ rd32(IGC_MGTPDC);
+ rd32(IGC_MGTPTC);
+
+ rd32(IGC_IAC);
+ rd32(IGC_ICRXOC);
+
+ rd32(IGC_ICRXPTC);
+ rd32(IGC_ICRXATC);
+ rd32(IGC_ICTXPTC);
+ rd32(IGC_ICTXATC);
+ rd32(IGC_ICTXQEC);
+ rd32(IGC_ICTXQMTC);
+ rd32(IGC_ICRXDMTC);
+
+ rd32(IGC_CBTMPC);
+ rd32(IGC_HTDPMC);
+ rd32(IGC_CBRMPC);
+ rd32(IGC_RPTHC);
+ rd32(IGC_HGPTC);
+ rd32(IGC_HTCBDPC);
+ rd32(IGC_HGORCL);
+ rd32(IGC_HGORCH);
+ rd32(IGC_HGOTCL);
+ rd32(IGC_HGOTCH);
+ rd32(IGC_LENERRS);
+}
+
+/**
+ * igc_rar_set - Set receive address register
+ * @hw: pointer to the HW structure
+ * @addr: pointer to the receive address
+ * @index: receive address array register
+ *
+ * Sets the receive address array register at index to the address passed
+ * in by addr.
+ */
+void igc_rar_set(struct igc_hw *hw, u8 *addr, u32 index)
+{
+ u32 rar_low, rar_high;
+
+ /* HW expects these in little endian so we reverse the byte order
+ * from network order (big endian) to little endian
+ */
+ rar_low = ((u32)addr[0] |
+ ((u32)addr[1] << 8) |
+ ((u32)addr[2] << 16) | ((u32)addr[3] << 24));
+
+ rar_high = ((u32)addr[4] | ((u32)addr[5] << 8));
+
+ /* If MAC address zero, no need to set the AV bit */
+ if (rar_low || rar_high)
+ rar_high |= IGC_RAH_AV;
+
+ /* Some bridges will combine consecutive 32-bit writes into
+ * a single burst write, which will malfunction on some parts.
+ * The flushes avoid this.
+ */
+ wr32(IGC_RAL(index), rar_low);
+ wrfl();
+ wr32(IGC_RAH(index), rar_high);
+ wrfl();
+}
+
+/**
+ * igc_check_for_copper_link - Check for link (Copper)
+ * @hw: pointer to the HW structure
+ *
+ * Checks to see of the link status of the hardware has changed. If a
+ * change in link status has been detected, then we read the PHY registers
+ * to get the current speed/duplex if link exists.
+ */
+s32 igc_check_for_copper_link(struct igc_hw *hw)
+{
+ struct igc_mac_info *mac = &hw->mac;
+ s32 ret_val;
+ bool link;
+
+ /* We only want to go out to the PHY registers to see if Auto-Neg
+ * has completed and/or if our link status has changed. The
+ * get_link_status flag is set upon receiving a Link Status
+ * Change or Rx Sequence Error interrupt.
+ */
+ if (!mac->get_link_status) {
+ ret_val = 0;
+ goto out;
+ }
+
+ /* First we want to see if the MII Status Register reports
+ * link. If so, then we want to get the current speed/duplex
+ * of the PHY.
+ */
+ ret_val = igc_phy_has_link(hw, 1, 0, &link);
+ if (ret_val)
+ goto out;
+
+ if (!link)
+ goto out; /* No link detected */
+
+ mac->get_link_status = false;
+
+ /* Check if there was DownShift, must be checked
+ * immediately after link-up
+ */
+ igc_check_downshift(hw);
+
+ /* If we are forcing speed/duplex, then we simply return since
+ * we have already determined whether we have link or not.
+ */
+ if (!mac->autoneg) {
+ ret_val = -IGC_ERR_CONFIG;
+ goto out;
+ }
+
+ /* Auto-Neg is enabled. Auto Speed Detection takes care
+ * of MAC speed/duplex configuration. So we only need to
+ * configure Collision Distance in the MAC.
+ */
+ igc_config_collision_dist(hw);
+
+ /* Configure Flow Control now that Auto-Neg has completed.
+ * First, we need to restore the desired flow control
+ * settings because we may have had to re-autoneg with a
+ * different link partner.
+ */
+ ret_val = igc_config_fc_after_link_up(hw);
+ if (ret_val)
+ hw_dbg("Error configuring flow control\n");
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_config_collision_dist - Configure collision distance
+ * @hw: pointer to the HW structure
+ *
+ * Configures the collision distance to the default value and is used
+ * during link setup. Currently no func pointer exists and all
+ * implementations are handled in the generic version of this function.
+ */
+void igc_config_collision_dist(struct igc_hw *hw)
+{
+ u32 tctl;
+
+ tctl = rd32(IGC_TCTL);
+
+ tctl &= ~IGC_TCTL_COLD;
+ tctl |= IGC_COLLISION_DISTANCE << IGC_COLD_SHIFT;
+
+ wr32(IGC_TCTL, tctl);
+ wrfl();
+}
+
+/**
+ * igc_config_fc_after_link_up - Configures flow control after link
+ * @hw: pointer to the HW structure
+ *
+ * Checks the status of auto-negotiation after link up to ensure that the
+ * speed and duplex were not forced. If the link needed to be forced, then
+ * flow control needs to be forced also. If auto-negotiation is enabled
+ * and did not fail, then we configure flow control based on our link
+ * partner.
+ */
+s32 igc_config_fc_after_link_up(struct igc_hw *hw)
+{
+ u16 mii_status_reg, mii_nway_adv_reg, mii_nway_lp_ability_reg;
+ struct igc_mac_info *mac = &hw->mac;
+ u16 speed, duplex;
+ s32 ret_val = 0;
+
+ /* Check for the case where we have fiber media and auto-neg failed
+ * so we had to force link. In this case, we need to force the
+ * configuration of the MAC to match the "fc" parameter.
+ */
+ if (mac->autoneg_failed) {
+ if (hw->phy.media_type == igc_media_type_copper)
+ ret_val = igc_force_mac_fc(hw);
+ }
+
+ if (ret_val) {
+ hw_dbg("Error forcing flow control settings\n");
+ goto out;
+ }
+
+ /* Check for the case where we have copper media and auto-neg is
+ * enabled. In this case, we need to check and see if Auto-Neg
+ * has completed, and if so, how the PHY and link partner has
+ * flow control configured.
+ */
+ if (hw->phy.media_type == igc_media_type_copper && mac->autoneg) {
+ /* Read the MII Status Register and check to see if AutoNeg
+ * has completed. We read this twice because this reg has
+ * some "sticky" (latched) bits.
+ */
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
+ &mii_status_reg);
+ if (ret_val)
+ goto out;
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
+ &mii_status_reg);
+ if (ret_val)
+ goto out;
+
+ if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) {
+ hw_dbg("Copper PHY and Auto Neg has not completed.\n");
+ goto out;
+ }
+
+ /* The AutoNeg process has completed, so we now need to
+ * read both the Auto Negotiation Advertisement
+ * Register (Address 4) and the Auto_Negotiation Base
+ * Page Ability Register (Address 5) to determine how
+ * flow control was negotiated.
+ */
+ ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV,
+ &mii_nway_adv_reg);
+ if (ret_val)
+ goto out;
+ ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY,
+ &mii_nway_lp_ability_reg);
+ if (ret_val)
+ goto out;
+ /* Two bits in the Auto Negotiation Advertisement Register
+ * (Address 4) and two bits in the Auto Negotiation Base
+ * Page Ability Register (Address 5) determine flow control
+ * for both the PHY and the link partner. The following
+ * table, taken out of the IEEE 802.3ab/D6.0 dated March 25,
+ * 1999, describes these PAUSE resolution bits and how flow
+ * control is determined based upon these settings.
+ * NOTE: DC = Don't Care
+ *
+ * LOCAL DEVICE | LINK PARTNER
+ * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution
+ *-------|---------|-------|---------|--------------------
+ * 0 | 0 | DC | DC | igc_fc_none
+ * 0 | 1 | 0 | DC | igc_fc_none
+ * 0 | 1 | 1 | 0 | igc_fc_none
+ * 0 | 1 | 1 | 1 | igc_fc_tx_pause
+ * 1 | 0 | 0 | DC | igc_fc_none
+ * 1 | DC | 1 | DC | igc_fc_full
+ * 1 | 1 | 0 | 0 | igc_fc_none
+ * 1 | 1 | 0 | 1 | igc_fc_rx_pause
+ *
+ * Are both PAUSE bits set to 1? If so, this implies
+ * Symmetric Flow Control is enabled at both ends. The
+ * ASM_DIR bits are irrelevant per the spec.
+ *
+ * For Symmetric Flow Control:
+ *
+ * LOCAL DEVICE | LINK PARTNER
+ * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+ *-------|---------|-------|---------|--------------------
+ * 1 | DC | 1 | DC | IGC_fc_full
+ *
+ */
+ if ((mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+ (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) {
+ /* Now we need to check if the user selected RX ONLY
+ * of pause frames. In this case, we had to advertise
+ * FULL flow control because we could not advertise RX
+ * ONLY. Hence, we must now check to see if we need to
+ * turn OFF the TRANSMISSION of PAUSE frames.
+ */
+ if (hw->fc.requested_mode == igc_fc_full) {
+ hw->fc.current_mode = igc_fc_full;
+ hw_dbg("Flow Control = FULL.\n");
+ } else {
+ hw->fc.current_mode = igc_fc_rx_pause;
+ hw_dbg("Flow Control = RX PAUSE frames only.\n");
+ }
+ }
+
+ /* For receiving PAUSE frames ONLY.
+ *
+ * LOCAL DEVICE | LINK PARTNER
+ * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+ *-------|---------|-------|---------|--------------------
+ * 0 | 1 | 1 | 1 | igc_fc_tx_pause
+ */
+ else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+ (mii_nway_adv_reg & NWAY_AR_ASM_DIR) &&
+ (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) &&
+ (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) {
+ hw->fc.current_mode = igc_fc_tx_pause;
+ hw_dbg("Flow Control = TX PAUSE frames only.\n");
+ }
+ /* For transmitting PAUSE frames ONLY.
+ *
+ * LOCAL DEVICE | LINK PARTNER
+ * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+ *-------|---------|-------|---------|--------------------
+ * 1 | 1 | 0 | 1 | igc_fc_rx_pause
+ */
+ else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+ (mii_nway_adv_reg & NWAY_AR_ASM_DIR) &&
+ !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) &&
+ (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) {
+ hw->fc.current_mode = igc_fc_rx_pause;
+ hw_dbg("Flow Control = RX PAUSE frames only.\n");
+ }
+ /* Per the IEEE spec, at this point flow control should be
+ * disabled. However, we want to consider that we could
+ * be connected to a legacy switch that doesn't advertise
+ * desired flow control, but can be forced on the link
+ * partner. So if we advertised no flow control, that is
+ * what we will resolve to. If we advertised some kind of
+ * receive capability (Rx Pause Only or Full Flow Control)
+ * and the link partner advertised none, we will configure
+ * ourselves to enable Rx Flow Control only. We can do
+ * this safely for two reasons: If the link partner really
+ * didn't want flow control enabled, and we enable Rx, no
+ * harm done since we won't be receiving any PAUSE frames
+ * anyway. If the intent on the link partner was to have
+ * flow control enabled, then by us enabling RX only, we
+ * can at least receive pause frames and process them.
+ * This is a good idea because in most cases, since we are
+ * predominantly a server NIC, more times than not we will
+ * be asked to delay transmission of packets than asking
+ * our link partner to pause transmission of frames.
+ */
+ else if ((hw->fc.requested_mode == igc_fc_none) ||
+ (hw->fc.requested_mode == igc_fc_tx_pause) ||
+ (hw->fc.strict_ieee)) {
+ hw->fc.current_mode = igc_fc_none;
+ hw_dbg("Flow Control = NONE.\n");
+ } else {
+ hw->fc.current_mode = igc_fc_rx_pause;
+ hw_dbg("Flow Control = RX PAUSE frames only.\n");
+ }
+
+ /* Now we need to do one last check... If we auto-
+ * negotiated to HALF DUPLEX, flow control should not be
+ * enabled per IEEE 802.3 spec.
+ */
+ ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex);
+ if (ret_val) {
+ hw_dbg("Error getting link speed and duplex\n");
+ goto out;
+ }
+
+ if (duplex == HALF_DUPLEX)
+ hw->fc.current_mode = igc_fc_none;
+
+ /* Now we call a subroutine to actually force the MAC
+ * controller to use the correct flow control settings.
+ */
+ ret_val = igc_force_mac_fc(hw);
+ if (ret_val) {
+ hw_dbg("Error forcing flow control settings\n");
+ goto out;
+ }
+ }
+
+out:
+ return 0;
+}
+
+/**
+ * igc_get_auto_rd_done - Check for auto read completion
+ * @hw: pointer to the HW structure
+ *
+ * Check EEPROM for Auto Read done bit.
+ */
+s32 igc_get_auto_rd_done(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+ s32 i = 0;
+
+ while (i < AUTO_READ_DONE_TIMEOUT) {
+ if (rd32(IGC_EECD) & IGC_EECD_AUTO_RD)
+ break;
+ usleep_range(1000, 2000);
+ i++;
+ }
+
+ if (i == AUTO_READ_DONE_TIMEOUT) {
+ hw_dbg("Auto read by HW from NVM has not completed.\n");
+ ret_val = -IGC_ERR_RESET;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_get_speed_and_duplex_copper - Retrieve current speed/duplex
+ * @hw: pointer to the HW structure
+ * @speed: stores the current speed
+ * @duplex: stores the current duplex
+ *
+ * Read the status register for the current speed/duplex and store the current
+ * speed and duplex for copper connections.
+ */
+s32 igc_get_speed_and_duplex_copper(struct igc_hw *hw, u16 *speed,
+ u16 *duplex)
+{
+ u32 status;
+
+ status = rd32(IGC_STATUS);
+ if (status & IGC_STATUS_SPEED_1000) {
+ /* For I225, STATUS will indicate 1G speed in both 1 Gbps
+ * and 2.5 Gbps link modes. An additional bit is used
+ * to differentiate between 1 Gbps and 2.5 Gbps.
+ */
+ if (hw->mac.type == igc_i225 &&
+ (status & IGC_STATUS_SPEED_2500)) {
+ *speed = SPEED_2500;
+ hw_dbg("2500 Mbs, ");
+ } else {
+ *speed = SPEED_1000;
+ hw_dbg("1000 Mbs, ");
+ }
+ } else if (status & IGC_STATUS_SPEED_100) {
+ *speed = SPEED_100;
+ hw_dbg("100 Mbs, ");
+ } else {
+ *speed = SPEED_10;
+ hw_dbg("10 Mbs, ");
+ }
+
+ if (status & IGC_STATUS_FD) {
+ *duplex = FULL_DUPLEX;
+ hw_dbg("Full Duplex\n");
+ } else {
+ *duplex = HALF_DUPLEX;
+ hw_dbg("Half Duplex\n");
+ }
+
+ return 0;
+}
+
+/**
+ * igc_put_hw_semaphore - Release hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Release hardware semaphore used to access the PHY or NVM
+ */
+void igc_put_hw_semaphore(struct igc_hw *hw)
+{
+ u32 swsm;
+
+ swsm = rd32(IGC_SWSM);
+
+ swsm &= ~(IGC_SWSM_SMBI | IGC_SWSM_SWESMBI);
+
+ wr32(IGC_SWSM, swsm);
+}
+
+/**
+ * igc_enable_mng_pass_thru - Enable processing of ARP's
+ * @hw: pointer to the HW structure
+ *
+ * Verifies the hardware needs to leave interface enabled so that frames can
+ * be directed to and from the management interface.
+ */
+bool igc_enable_mng_pass_thru(struct igc_hw *hw)
+{
+ bool ret_val = false;
+ u32 fwsm, factps;
+ u32 manc;
+
+ if (!hw->mac.asf_firmware_present)
+ goto out;
+
+ manc = rd32(IGC_MANC);
+
+ if (!(manc & IGC_MANC_RCV_TCO_EN))
+ goto out;
+
+ if (hw->mac.arc_subsystem_valid) {
+ fwsm = rd32(IGC_FWSM);
+ factps = rd32(IGC_FACTPS);
+
+ if (!(factps & IGC_FACTPS_MNGCG) &&
+ ((fwsm & IGC_FWSM_MODE_MASK) ==
+ (igc_mng_mode_pt << IGC_FWSM_MODE_SHIFT))) {
+ ret_val = true;
+ goto out;
+ }
+ } else {
+ if ((manc & IGC_MANC_SMBUS_EN) &&
+ !(manc & IGC_MANC_ASF_EN)) {
+ ret_val = true;
+ goto out;
+ }
+ }
+
+out:
+ return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_mac.h b/drivers/net/ethernet/intel/igc/igc_mac.h
new file mode 100644
index 0000000..782bc99
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_mac.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_MAC_H_
+#define _IGC_MAC_H_
+
+#include "igc_hw.h"
+#include "igc_phy.h"
+#include "igc_defines.h"
+
+#ifndef IGC_REMOVED
+#define IGC_REMOVED(a) (0)
+#endif /* IGC_REMOVED */
+
+/* forward declaration */
+s32 igc_disable_pcie_master(struct igc_hw *hw);
+s32 igc_check_for_copper_link(struct igc_hw *hw);
+s32 igc_config_fc_after_link_up(struct igc_hw *hw);
+s32 igc_force_mac_fc(struct igc_hw *hw);
+void igc_init_rx_addrs(struct igc_hw *hw, u16 rar_count);
+s32 igc_setup_link(struct igc_hw *hw);
+void igc_clear_hw_cntrs_base(struct igc_hw *hw);
+s32 igc_get_auto_rd_done(struct igc_hw *hw);
+void igc_put_hw_semaphore(struct igc_hw *hw);
+void igc_rar_set(struct igc_hw *hw, u8 *addr, u32 index);
+void igc_config_collision_dist(struct igc_hw *hw);
+
+s32 igc_get_speed_and_duplex_copper(struct igc_hw *hw, u16 *speed,
+ u16 *duplex);
+
+bool igc_enable_mng_pass_thru(struct igc_hw *hw);
+
+enum igc_mng_mode {
+ igc_mng_mode_none = 0,
+ igc_mng_mode_asf,
+ igc_mng_mode_pt,
+ igc_mng_mode_ipmi,
+ igc_mng_mode_host_if_only
+};
+
+#endif
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
new file mode 100644
index 0000000..2488867
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -0,0 +1,4531 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/if_vlan.h>
+#include <linux/aer.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
+
+#include <net/ipv6.h>
+
+#include "igc.h"
+#include "igc_hw.h"
+
+#define DRV_VERSION "0.0.1-k"
+#define DRV_SUMMARY "Intel(R) 2.5G Ethernet Linux Driver"
+
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+
+static int debug = -1;
+
+MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
+MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
+char igc_driver_name[] = "igc";
+char igc_driver_version[] = DRV_VERSION;
+static const char igc_driver_string[] = DRV_SUMMARY;
+static const char igc_copyright[] =
+ "Copyright(c) 2018 Intel Corporation.";
+
+static const struct igc_info *igc_info_tbl[] = {
+ [board_base] = &igc_base_info,
+};
+
+static const struct pci_device_id igc_pci_tbl[] = {
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LM), board_base },
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_V), board_base },
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base },
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base },
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base },
+ /* required last entry */
+ {0, }
+};
+
+MODULE_DEVICE_TABLE(pci, igc_pci_tbl);
+
+/* forward declaration */
+static void igc_clean_tx_ring(struct igc_ring *tx_ring);
+static int igc_sw_init(struct igc_adapter *);
+static void igc_configure(struct igc_adapter *adapter);
+static void igc_power_down_link(struct igc_adapter *adapter);
+static void igc_set_default_mac_filter(struct igc_adapter *adapter);
+static void igc_set_rx_mode(struct net_device *netdev);
+static void igc_write_itr(struct igc_q_vector *q_vector);
+static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector);
+static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx);
+static void igc_set_interrupt_capability(struct igc_adapter *adapter,
+ bool msix);
+static void igc_free_q_vectors(struct igc_adapter *adapter);
+static void igc_irq_disable(struct igc_adapter *adapter);
+static void igc_irq_enable(struct igc_adapter *adapter);
+static void igc_configure_msix(struct igc_adapter *adapter);
+static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *bi);
+
+enum latency_range {
+ lowest_latency = 0,
+ low_latency = 1,
+ bulk_latency = 2,
+ latency_invalid = 255
+};
+
+void igc_reset(struct igc_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ struct igc_hw *hw = &adapter->hw;
+ struct igc_fc_info *fc = &hw->fc;
+ u32 pba, hwm;
+
+ /* Repartition PBA for greater than 9k MTU if required */
+ pba = IGC_PBA_34K;
+
+ /* flow control settings
+ * The high water mark must be low enough to fit one full frame
+ * after transmitting the pause frame. As such we must have enough
+ * space to allow for us to complete our current transmit and then
+ * receive the frame that is in progress from the link partner.
+ * Set it to:
+ * - the full Rx FIFO size minus one full Tx plus one full Rx frame
+ */
+ hwm = (pba << 10) - (adapter->max_frame_size + MAX_JUMBO_FRAME_SIZE);
+
+ fc->high_water = hwm & 0xFFFFFFF0; /* 16-byte granularity */
+ fc->low_water = fc->high_water - 16;
+ fc->pause_time = 0xFFFF;
+ fc->send_xon = 1;
+ fc->current_mode = fc->requested_mode;
+
+ hw->mac.ops.reset_hw(hw);
+
+ if (hw->mac.ops.init_hw(hw))
+ dev_err(&pdev->dev, "Hardware Error\n");
+
+ if (!netif_running(adapter->netdev))
+ igc_power_down_link(adapter);
+
+ igc_get_phy_info(hw);
+}
+
+/**
+ * igc_power_up_link - Power up the phy/serdes link
+ * @adapter: address of board private structure
+ */
+static void igc_power_up_link(struct igc_adapter *adapter)
+{
+ igc_reset_phy(&adapter->hw);
+
+ if (adapter->hw.phy.media_type == igc_media_type_copper)
+ igc_power_up_phy_copper(&adapter->hw);
+
+ igc_setup_link(&adapter->hw);
+}
+
+/**
+ * igc_power_down_link - Power down the phy/serdes link
+ * @adapter: address of board private structure
+ */
+static void igc_power_down_link(struct igc_adapter *adapter)
+{
+ if (adapter->hw.phy.media_type == igc_media_type_copper)
+ igc_power_down_phy_copper_base(&adapter->hw);
+}
+
+/**
+ * igc_release_hw_control - release control of the h/w to f/w
+ * @adapter: address of board private structure
+ *
+ * igc_release_hw_control resets CTRL_EXT:DRV_LOAD bit.
+ * For ASF and Pass Through versions of f/w this means that the
+ * driver is no longer loaded.
+ */
+static void igc_release_hw_control(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 ctrl_ext;
+
+ /* Let firmware take over control of h/w */
+ ctrl_ext = rd32(IGC_CTRL_EXT);
+ wr32(IGC_CTRL_EXT,
+ ctrl_ext & ~IGC_CTRL_EXT_DRV_LOAD);
+}
+
+/**
+ * igc_get_hw_control - get control of the h/w from f/w
+ * @adapter: address of board private structure
+ *
+ * igc_get_hw_control sets CTRL_EXT:DRV_LOAD bit.
+ * For ASF and Pass Through versions of f/w this means that
+ * the driver is loaded.
+ */
+static void igc_get_hw_control(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 ctrl_ext;
+
+ /* Let firmware know the driver has taken over */
+ ctrl_ext = rd32(IGC_CTRL_EXT);
+ wr32(IGC_CTRL_EXT,
+ ctrl_ext | IGC_CTRL_EXT_DRV_LOAD);
+}
+
+/**
+ * igc_free_tx_resources - Free Tx Resources per Queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ */
+void igc_free_tx_resources(struct igc_ring *tx_ring)
+{
+ igc_clean_tx_ring(tx_ring);
+
+ vfree(tx_ring->tx_buffer_info);
+ tx_ring->tx_buffer_info = NULL;
+
+ /* if not set, then don't free */
+ if (!tx_ring->desc)
+ return;
+
+ dma_free_coherent(tx_ring->dev, tx_ring->size,
+ tx_ring->desc, tx_ring->dma);
+
+ tx_ring->desc = NULL;
+}
+
+/**
+ * igc_free_all_tx_resources - Free Tx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all transmit software resources
+ */
+static void igc_free_all_tx_resources(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ igc_free_tx_resources(adapter->tx_ring[i]);
+}
+
+/**
+ * igc_clean_tx_ring - Free Tx Buffers
+ * @tx_ring: ring to be cleaned
+ */
+static void igc_clean_tx_ring(struct igc_ring *tx_ring)
+{
+ u16 i = tx_ring->next_to_clean;
+ struct igc_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+
+ while (i != tx_ring->next_to_use) {
+ union igc_adv_tx_desc *eop_desc, *tx_desc;
+
+ /* Free all the Tx ring sk_buffs */
+ dev_kfree_skb_any(tx_buffer->skb);
+
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+
+ /* check for eop_desc to determine the end of the packet */
+ eop_desc = tx_buffer->next_to_watch;
+ tx_desc = IGC_TX_DESC(tx_ring, i);
+
+ /* unmap remaining buffers */
+ while (tx_desc != eop_desc) {
+ tx_buffer++;
+ tx_desc++;
+ i++;
+ if (unlikely(i == tx_ring->count)) {
+ i = 0;
+ tx_buffer = tx_ring->tx_buffer_info;
+ tx_desc = IGC_TX_DESC(tx_ring, 0);
+ }
+
+ /* unmap any remaining paged data */
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ }
+
+ /* move us one more past the eop_desc for start of next pkt */
+ tx_buffer++;
+ i++;
+ if (unlikely(i == tx_ring->count)) {
+ i = 0;
+ tx_buffer = tx_ring->tx_buffer_info;
+ }
+ }
+
+ /* reset BQL for queue */
+ netdev_tx_reset_queue(txring_txq(tx_ring));
+
+ /* reset next_to_use and next_to_clean */
+ tx_ring->next_to_use = 0;
+ tx_ring->next_to_clean = 0;
+}
+
+/**
+ * igc_clean_all_tx_rings - Free Tx Buffers for all queues
+ * @adapter: board private structure
+ */
+static void igc_clean_all_tx_rings(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ if (adapter->tx_ring[i])
+ igc_clean_tx_ring(adapter->tx_ring[i]);
+}
+
+/**
+ * igc_setup_tx_resources - allocate Tx resources (Descriptors)
+ * @tx_ring: tx descriptor ring (for a specific queue) to setup
+ *
+ * Return 0 on success, negative on failure
+ */
+int igc_setup_tx_resources(struct igc_ring *tx_ring)
+{
+ struct device *dev = tx_ring->dev;
+ int size = 0;
+
+ size = sizeof(struct igc_tx_buffer) * tx_ring->count;
+ tx_ring->tx_buffer_info = vzalloc(size);
+ if (!tx_ring->tx_buffer_info)
+ goto err;
+
+ /* round up to nearest 4K */
+ tx_ring->size = tx_ring->count * sizeof(union igc_adv_tx_desc);
+ tx_ring->size = ALIGN(tx_ring->size, 4096);
+
+ tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
+ &tx_ring->dma, GFP_KERNEL);
+
+ if (!tx_ring->desc)
+ goto err;
+
+ tx_ring->next_to_use = 0;
+ tx_ring->next_to_clean = 0;
+
+ return 0;
+
+err:
+ vfree(tx_ring->tx_buffer_info);
+ dev_err(dev,
+ "Unable to allocate memory for the transmit descriptor ring\n");
+ return -ENOMEM;
+}
+
+/**
+ * igc_setup_all_tx_resources - wrapper to allocate Tx resources for all queues
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ */
+static int igc_setup_all_tx_resources(struct igc_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ err = igc_setup_tx_resources(adapter->tx_ring[i]);
+ if (err) {
+ dev_err(&pdev->dev,
+ "Allocation for Tx Queue %u failed\n", i);
+ for (i--; i >= 0; i--)
+ igc_free_tx_resources(adapter->tx_ring[i]);
+ break;
+ }
+ }
+
+ return err;
+}
+
+/**
+ * igc_clean_rx_ring - Free Rx Buffers per Queue
+ * @rx_ring: ring to free buffers from
+ */
+static void igc_clean_rx_ring(struct igc_ring *rx_ring)
+{
+ u16 i = rx_ring->next_to_clean;
+
+ dev_kfree_skb(rx_ring->skb);
+ rx_ring->skb = NULL;
+
+ /* Free all the Rx ring sk_buffs */
+ while (i != rx_ring->next_to_alloc) {
+ struct igc_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
+
+ /* Invalidate cache lines that may have been written to by
+ * device so that we avoid corrupting memory.
+ */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ buffer_info->dma,
+ buffer_info->page_offset,
+ igc_rx_bufsz(rx_ring),
+ DMA_FROM_DEVICE);
+
+ /* free resources associated with mapping */
+ dma_unmap_page_attrs(rx_ring->dev,
+ buffer_info->dma,
+ igc_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ IGC_RX_DMA_ATTR);
+ __page_frag_cache_drain(buffer_info->page,
+ buffer_info->pagecnt_bias);
+
+ i++;
+ if (i == rx_ring->count)
+ i = 0;
+ }
+
+ rx_ring->next_to_alloc = 0;
+ rx_ring->next_to_clean = 0;
+ rx_ring->next_to_use = 0;
+}
+
+/**
+ * igc_clean_all_rx_rings - Free Rx Buffers for all queues
+ * @adapter: board private structure
+ */
+static void igc_clean_all_rx_rings(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ if (adapter->rx_ring[i])
+ igc_clean_rx_ring(adapter->rx_ring[i]);
+}
+
+/**
+ * igc_free_rx_resources - Free Rx Resources
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ */
+void igc_free_rx_resources(struct igc_ring *rx_ring)
+{
+ igc_clean_rx_ring(rx_ring);
+
+ vfree(rx_ring->rx_buffer_info);
+ rx_ring->rx_buffer_info = NULL;
+
+ /* if not set, then don't free */
+ if (!rx_ring->desc)
+ return;
+
+ dma_free_coherent(rx_ring->dev, rx_ring->size,
+ rx_ring->desc, rx_ring->dma);
+
+ rx_ring->desc = NULL;
+}
+
+/**
+ * igc_free_all_rx_resources - Free Rx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all receive software resources
+ */
+static void igc_free_all_rx_resources(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ igc_free_rx_resources(adapter->rx_ring[i]);
+}
+
+/**
+ * igc_setup_rx_resources - allocate Rx resources (Descriptors)
+ * @rx_ring: rx descriptor ring (for a specific queue) to setup
+ *
+ * Returns 0 on success, negative on failure
+ */
+int igc_setup_rx_resources(struct igc_ring *rx_ring)
+{
+ struct device *dev = rx_ring->dev;
+ int size, desc_len;
+
+ size = sizeof(struct igc_rx_buffer) * rx_ring->count;
+ rx_ring->rx_buffer_info = vzalloc(size);
+ if (!rx_ring->rx_buffer_info)
+ goto err;
+
+ desc_len = sizeof(union igc_adv_rx_desc);
+
+ /* Round up to nearest 4K */
+ rx_ring->size = rx_ring->count * desc_len;
+ rx_ring->size = ALIGN(rx_ring->size, 4096);
+
+ rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
+ &rx_ring->dma, GFP_KERNEL);
+
+ if (!rx_ring->desc)
+ goto err;
+
+ rx_ring->next_to_alloc = 0;
+ rx_ring->next_to_clean = 0;
+ rx_ring->next_to_use = 0;
+
+ return 0;
+
+err:
+ vfree(rx_ring->rx_buffer_info);
+ rx_ring->rx_buffer_info = NULL;
+ dev_err(dev,
+ "Unable to allocate memory for the receive descriptor ring\n");
+ return -ENOMEM;
+}
+
+/**
+ * igc_setup_all_rx_resources - wrapper to allocate Rx resources
+ * (Descriptors) for all queues
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ */
+static int igc_setup_all_rx_resources(struct igc_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ err = igc_setup_rx_resources(adapter->rx_ring[i]);
+ if (err) {
+ dev_err(&pdev->dev,
+ "Allocation for Rx Queue %u failed\n", i);
+ for (i--; i >= 0; i--)
+ igc_free_rx_resources(adapter->rx_ring[i]);
+ break;
+ }
+ }
+
+ return err;
+}
+
+/**
+ * igc_configure_rx_ring - Configure a receive ring after Reset
+ * @adapter: board private structure
+ * @ring: receive ring to be configured
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ */
+static void igc_configure_rx_ring(struct igc_adapter *adapter,
+ struct igc_ring *ring)
+{
+ struct igc_hw *hw = &adapter->hw;
+ union igc_adv_rx_desc *rx_desc;
+ int reg_idx = ring->reg_idx;
+ u32 srrctl = 0, rxdctl = 0;
+ u64 rdba = ring->dma;
+
+ /* disable the queue */
+ wr32(IGC_RXDCTL(reg_idx), 0);
+
+ /* Set DMA base address registers */
+ wr32(IGC_RDBAL(reg_idx),
+ rdba & 0x00000000ffffffffULL);
+ wr32(IGC_RDBAH(reg_idx), rdba >> 32);
+ wr32(IGC_RDLEN(reg_idx),
+ ring->count * sizeof(union igc_adv_rx_desc));
+
+ /* initialize head and tail */
+ ring->tail = adapter->io_addr + IGC_RDT(reg_idx);
+ wr32(IGC_RDH(reg_idx), 0);
+ writel(0, ring->tail);
+
+ /* reset next-to- use/clean to place SW in sync with hardware */
+ ring->next_to_clean = 0;
+ ring->next_to_use = 0;
+
+ /* set descriptor configuration */
+ srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT;
+ if (ring_uses_large_buffer(ring))
+ srrctl |= IGC_RXBUFFER_3072 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+ else
+ srrctl |= IGC_RXBUFFER_2048 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+ srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF;
+
+ wr32(IGC_SRRCTL(reg_idx), srrctl);
+
+ rxdctl |= IGC_RX_PTHRESH;
+ rxdctl |= IGC_RX_HTHRESH << 8;
+ rxdctl |= IGC_RX_WTHRESH << 16;
+
+ /* initialize rx_buffer_info */
+ memset(ring->rx_buffer_info, 0,
+ sizeof(struct igc_rx_buffer) * ring->count);
+
+ /* initialize Rx descriptor 0 */
+ rx_desc = IGC_RX_DESC(ring, 0);
+ rx_desc->wb.upper.length = 0;
+
+ /* enable receive descriptor fetching */
+ rxdctl |= IGC_RXDCTL_QUEUE_ENABLE;
+
+ wr32(IGC_RXDCTL(reg_idx), rxdctl);
+}
+
+/**
+ * igc_configure_rx - Configure receive Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ */
+static void igc_configure_rx(struct igc_adapter *adapter)
+{
+ int i;
+
+ /* Setup the HW Rx Head and Tail Descriptor Pointers and
+ * the Base and Length of the Rx Descriptor Ring
+ */
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ igc_configure_rx_ring(adapter, adapter->rx_ring[i]);
+}
+
+/**
+ * igc_configure_tx_ring - Configure transmit ring after Reset
+ * @adapter: board private structure
+ * @ring: tx ring to configure
+ *
+ * Configure a transmit ring after a reset.
+ */
+static void igc_configure_tx_ring(struct igc_adapter *adapter,
+ struct igc_ring *ring)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int reg_idx = ring->reg_idx;
+ u64 tdba = ring->dma;
+ u32 txdctl = 0;
+
+ /* disable the queue */
+ wr32(IGC_TXDCTL(reg_idx), 0);
+ wrfl();
+ mdelay(10);
+
+ wr32(IGC_TDLEN(reg_idx),
+ ring->count * sizeof(union igc_adv_tx_desc));
+ wr32(IGC_TDBAL(reg_idx),
+ tdba & 0x00000000ffffffffULL);
+ wr32(IGC_TDBAH(reg_idx), tdba >> 32);
+
+ ring->tail = adapter->io_addr + IGC_TDT(reg_idx);
+ wr32(IGC_TDH(reg_idx), 0);
+ writel(0, ring->tail);
+
+ txdctl |= IGC_TX_PTHRESH;
+ txdctl |= IGC_TX_HTHRESH << 8;
+ txdctl |= IGC_TX_WTHRESH << 16;
+
+ txdctl |= IGC_TXDCTL_QUEUE_ENABLE;
+ wr32(IGC_TXDCTL(reg_idx), txdctl);
+}
+
+/**
+ * igc_configure_tx - Configure transmit Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Tx unit of the MAC after a reset.
+ */
+static void igc_configure_tx(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ igc_configure_tx_ring(adapter, adapter->tx_ring[i]);
+}
+
+/**
+ * igc_setup_mrqc - configure the multiple receive queue control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_mrqc(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 j, num_rx_queues;
+ u32 mrqc, rxcsum;
+ u32 rss_key[10];
+
+ netdev_rss_key_fill(rss_key, sizeof(rss_key));
+ for (j = 0; j < 10; j++)
+ wr32(IGC_RSSRK(j), rss_key[j]);
+
+ num_rx_queues = adapter->rss_queues;
+
+ if (adapter->rss_indir_tbl_init != num_rx_queues) {
+ for (j = 0; j < IGC_RETA_SIZE; j++)
+ adapter->rss_indir_tbl[j] =
+ (j * num_rx_queues) / IGC_RETA_SIZE;
+ adapter->rss_indir_tbl_init = num_rx_queues;
+ }
+ igc_write_rss_indir_tbl(adapter);
+
+ /* Disable raw packet checksumming so that RSS hash is placed in
+ * descriptor on writeback. No need to enable TCP/UDP/IP checksum
+ * offloads as they are enabled by default
+ */
+ rxcsum = rd32(IGC_RXCSUM);
+ rxcsum |= IGC_RXCSUM_PCSD;
+
+ /* Enable Receive Checksum Offload for SCTP */
+ rxcsum |= IGC_RXCSUM_CRCOFL;
+
+ /* Don't need to set TUOFL or IPOFL, they default to 1 */
+ wr32(IGC_RXCSUM, rxcsum);
+
+ /* Generate RSS hash based on packet types, TCP/UDP
+ * port numbers and/or IPv4/v6 src and dst addresses
+ */
+ mrqc = IGC_MRQC_RSS_FIELD_IPV4 |
+ IGC_MRQC_RSS_FIELD_IPV4_TCP |
+ IGC_MRQC_RSS_FIELD_IPV6 |
+ IGC_MRQC_RSS_FIELD_IPV6_TCP |
+ IGC_MRQC_RSS_FIELD_IPV6_TCP_EX;
+
+ if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+ mrqc |= IGC_MRQC_RSS_FIELD_IPV4_UDP;
+ if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+ mrqc |= IGC_MRQC_RSS_FIELD_IPV6_UDP;
+
+ mrqc |= IGC_MRQC_ENABLE_RSS_MQ;
+
+ wr32(IGC_MRQC, mrqc);
+}
+
+/**
+ * igc_setup_rctl - configure the receive control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_rctl(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 rctl;
+
+ rctl = rd32(IGC_RCTL);
+
+ rctl &= ~(3 << IGC_RCTL_MO_SHIFT);
+ rctl &= ~(IGC_RCTL_LBM_TCVR | IGC_RCTL_LBM_MAC);
+
+ rctl |= IGC_RCTL_EN | IGC_RCTL_BAM | IGC_RCTL_RDMTS_HALF |
+ (hw->mac.mc_filter_type << IGC_RCTL_MO_SHIFT);
+
+ /* enable stripping of CRC. Newer features require
+ * that the HW strips the CRC.
+ */
+ rctl |= IGC_RCTL_SECRC;
+
+ /* disable store bad packets and clear size bits. */
+ rctl &= ~(IGC_RCTL_SBP | IGC_RCTL_SZ_256);
+
+ /* enable LPE to allow for reception of jumbo frames */
+ rctl |= IGC_RCTL_LPE;
+
+ /* disable queue 0 to prevent tail write w/o re-config */
+ wr32(IGC_RXDCTL(0), 0);
+
+ /* This is useful for sniffing bad packets. */
+ if (adapter->netdev->features & NETIF_F_RXALL) {
+ /* UPE and MPE will be handled by normal PROMISC logic
+ * in set_rx_mode
+ */
+ rctl |= (IGC_RCTL_SBP | /* Receive bad packets */
+ IGC_RCTL_BAM | /* RX All Bcast Pkts */
+ IGC_RCTL_PMCF); /* RX All MAC Ctrl Pkts */
+
+ rctl &= ~(IGC_RCTL_DPF | /* Allow filtered pause */
+ IGC_RCTL_CFIEN); /* Disable VLAN CFIEN Filter */
+ }
+
+ wr32(IGC_RCTL, rctl);
+}
+
+/**
+ * igc_setup_tctl - configure the transmit control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_tctl(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 tctl;
+
+ /* disable queue 0 which icould be enabled by default */
+ wr32(IGC_TXDCTL(0), 0);
+
+ /* Program the Transmit Control Register */
+ tctl = rd32(IGC_TCTL);
+ tctl &= ~IGC_TCTL_CT;
+ tctl |= IGC_TCTL_PSP | IGC_TCTL_RTLC |
+ (IGC_COLLISION_THRESHOLD << IGC_CT_SHIFT);
+
+ /* Enable transmits */
+ tctl |= IGC_TCTL_EN;
+
+ wr32(IGC_TCTL, tctl);
+}
+
+/**
+ * igc_set_mac - Change the Ethernet Address of the NIC
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int igc_set_mac(struct net_device *netdev, void *p)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ struct sockaddr *addr = p;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+ memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
+
+ /* set the correct pool for the new PF MAC address in entry 0 */
+ igc_set_default_mac_filter(adapter);
+
+ return 0;
+}
+
+static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
+ struct igc_tx_buffer *first,
+ u32 vlan_macip_lens, u32 type_tucmd,
+ u32 mss_l4len_idx)
+{
+ struct igc_adv_tx_context_desc *context_desc;
+ u16 i = tx_ring->next_to_use;
+ struct timespec64 ts;
+
+ context_desc = IGC_TX_CTXTDESC(tx_ring, i);
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
+
+ /* set bits to identify this as an advanced context descriptor */
+ type_tucmd |= IGC_TXD_CMD_DEXT | IGC_ADVTXD_DTYP_CTXT;
+
+ /* For 82575, context index must be unique per ring. */
+ if (test_bit(IGC_RING_FLAG_TX_CTX_IDX, &tx_ring->flags))
+ mss_l4len_idx |= tx_ring->reg_idx << 4;
+
+ context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
+ context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd);
+ context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
+
+ /* We assume there is always a valid Tx time available. Invalid times
+ * should have been handled by the upper layers.
+ */
+ if (tx_ring->launchtime_enable) {
+ ts = ktime_to_timespec64(first->skb->tstamp);
+ first->skb->tstamp = ktime_set(0, 0);
+ context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32);
+ } else {
+ context_desc->launch_time = 0;
+ }
+}
+
+static inline bool igc_ipv6_csum_is_sctp(struct sk_buff *skb)
+{
+ unsigned int offset = 0;
+
+ ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL);
+
+ return offset == skb_checksum_start_offset(skb);
+}
+
+static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first)
+{
+ struct sk_buff *skb = first->skb;
+ u32 vlan_macip_lens = 0;
+ u32 type_tucmd = 0;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL) {
+csum_failed:
+ if (!(first->tx_flags & IGC_TX_FLAGS_VLAN) &&
+ !tx_ring->launchtime_enable)
+ return;
+ goto no_csum;
+ }
+
+ switch (skb->csum_offset) {
+ case offsetof(struct tcphdr, check):
+ type_tucmd = IGC_ADVTXD_TUCMD_L4T_TCP;
+ /* fall through */
+ case offsetof(struct udphdr, check):
+ break;
+ case offsetof(struct sctphdr, checksum):
+ /* validate that this is actually an SCTP request */
+ if ((first->protocol == htons(ETH_P_IP) &&
+ (ip_hdr(skb)->protocol == IPPROTO_SCTP)) ||
+ (first->protocol == htons(ETH_P_IPV6) &&
+ igc_ipv6_csum_is_sctp(skb))) {
+ type_tucmd = IGC_ADVTXD_TUCMD_L4T_SCTP;
+ break;
+ }
+ /* fall through */
+ default:
+ skb_checksum_help(skb);
+ goto csum_failed;
+ }
+
+ /* update TX checksum flag */
+ first->tx_flags |= IGC_TX_FLAGS_CSUM;
+ vlan_macip_lens = skb_checksum_start_offset(skb) -
+ skb_network_offset(skb);
+no_csum:
+ vlan_macip_lens |= skb_network_offset(skb) << IGC_ADVTXD_MACLEN_SHIFT;
+ vlan_macip_lens |= first->tx_flags & IGC_TX_FLAGS_VLAN_MASK;
+
+ igc_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
+}
+
+static int __igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
+{
+ struct net_device *netdev = tx_ring->netdev;
+
+ netif_stop_subqueue(netdev, tx_ring->queue_index);
+
+ /* memory barriier comment */
+ smp_mb();
+
+ /* We need to check again in a case another CPU has just
+ * made room available.
+ */
+ if (igc_desc_unused(tx_ring) < size)
+ return -EBUSY;
+
+ /* A reprieve! */
+ netif_wake_subqueue(netdev, tx_ring->queue_index);
+
+ u64_stats_update_begin(&tx_ring->tx_syncp2);
+ tx_ring->tx_stats.restart_queue2++;
+ u64_stats_update_end(&tx_ring->tx_syncp2);
+
+ return 0;
+}
+
+static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
+{
+ if (igc_desc_unused(tx_ring) >= size)
+ return 0;
+ return __igc_maybe_stop_tx(tx_ring, size);
+}
+
+static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
+{
+ /* set type for advanced descriptor with frame checksum insertion */
+ u32 cmd_type = IGC_ADVTXD_DTYP_DATA |
+ IGC_ADVTXD_DCMD_DEXT |
+ IGC_ADVTXD_DCMD_IFCS;
+
+ return cmd_type;
+}
+
+static void igc_tx_olinfo_status(struct igc_ring *tx_ring,
+ union igc_adv_tx_desc *tx_desc,
+ u32 tx_flags, unsigned int paylen)
+{
+ u32 olinfo_status = paylen << IGC_ADVTXD_PAYLEN_SHIFT;
+
+ /* insert L4 checksum */
+ olinfo_status |= (tx_flags & IGC_TX_FLAGS_CSUM) *
+ ((IGC_TXD_POPTS_TXSM << 8) /
+ IGC_TX_FLAGS_CSUM);
+
+ /* insert IPv4 checksum */
+ olinfo_status |= (tx_flags & IGC_TX_FLAGS_IPV4) *
+ (((IGC_TXD_POPTS_IXSM << 8)) /
+ IGC_TX_FLAGS_IPV4);
+
+ tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+}
+
+static int igc_tx_map(struct igc_ring *tx_ring,
+ struct igc_tx_buffer *first,
+ const u8 hdr_len)
+{
+ struct sk_buff *skb = first->skb;
+ struct igc_tx_buffer *tx_buffer;
+ union igc_adv_tx_desc *tx_desc;
+ u32 tx_flags = first->tx_flags;
+ skb_frag_t *frag;
+ u16 i = tx_ring->next_to_use;
+ unsigned int data_len, size;
+ dma_addr_t dma;
+ u32 cmd_type = igc_tx_cmd_type(skb, tx_flags);
+
+ tx_desc = IGC_TX_DESC(tx_ring, i);
+
+ igc_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len);
+
+ size = skb_headlen(skb);
+ data_len = skb->data_len;
+
+ dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
+
+ tx_buffer = first;
+
+ for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+ if (dma_mapping_error(tx_ring->dev, dma))
+ goto dma_error;
+
+ /* record length, and DMA address */
+ dma_unmap_len_set(tx_buffer, len, size);
+ dma_unmap_addr_set(tx_buffer, dma, dma);
+
+ tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+ while (unlikely(size > IGC_MAX_DATA_PER_TXD)) {
+ tx_desc->read.cmd_type_len =
+ cpu_to_le32(cmd_type ^ IGC_MAX_DATA_PER_TXD);
+
+ i++;
+ tx_desc++;
+ if (i == tx_ring->count) {
+ tx_desc = IGC_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+ tx_desc->read.olinfo_status = 0;
+
+ dma += IGC_MAX_DATA_PER_TXD;
+ size -= IGC_MAX_DATA_PER_TXD;
+
+ tx_desc->read.buffer_addr = cpu_to_le64(dma);
+ }
+
+ if (likely(!data_len))
+ break;
+
+ tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size);
+
+ i++;
+ tx_desc++;
+ if (i == tx_ring->count) {
+ tx_desc = IGC_TX_DESC(tx_ring, 0);
+ i = 0;
+ }
+ tx_desc->read.olinfo_status = 0;
+
+ size = skb_frag_size(frag);
+ data_len -= size;
+
+ dma = skb_frag_dma_map(tx_ring->dev, frag, 0,
+ size, DMA_TO_DEVICE);
+
+ tx_buffer = &tx_ring->tx_buffer_info[i];
+ }
+
+ /* write last descriptor with RS and EOP bits */
+ cmd_type |= size | IGC_TXD_DCMD;
+ tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+
+ netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
+
+ /* set the timestamp */
+ first->time_stamp = jiffies;
+
+ skb_tx_timestamp(skb);
+
+ /* Force memory writes to complete before letting h/w know there
+ * are new descriptors to fetch. (Only applicable for weak-ordered
+ * memory model archs, such as IA-64).
+ *
+ * We also need this memory barrier to make certain all of the
+ * status bits have been updated before next_to_watch is written.
+ */
+ wmb();
+
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
+
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
+ tx_ring->next_to_use = i;
+
+ /* Make sure there is space in the ring for the next send. */
+ igc_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
+ writel(i, tx_ring->tail);
+ }
+
+ return 0;
+dma_error:
+ dev_err(tx_ring->dev, "TX DMA map failed\n");
+ tx_buffer = &tx_ring->tx_buffer_info[i];
+
+ /* clear dma mappings for failed tx_buffer_info map */
+ while (tx_buffer != first) {
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer, len, 0);
+
+ if (i-- == 0)
+ i += tx_ring->count;
+ tx_buffer = &tx_ring->tx_buffer_info[i];
+ }
+
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer, len, 0);
+
+ dev_kfree_skb_any(tx_buffer->skb);
+ tx_buffer->skb = NULL;
+
+ tx_ring->next_to_use = i;
+
+ return -1;
+}
+
+static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
+ struct igc_ring *tx_ring)
+{
+ u16 count = TXD_USE_COUNT(skb_headlen(skb));
+ __be16 protocol = vlan_get_protocol(skb);
+ struct igc_tx_buffer *first;
+ u32 tx_flags = 0;
+ unsigned short f;
+ u8 hdr_len = 0;
+
+ /* need: 1 descriptor per page * PAGE_SIZE/IGC_MAX_DATA_PER_TXD,
+ * + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
+ * + 2 desc gap to keep tail from touching head,
+ * + 1 desc for context descriptor,
+ * otherwise try next time
+ */
+ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+ count += TXD_USE_COUNT(skb_frag_size(
+ &skb_shinfo(skb)->frags[f]));
+
+ if (igc_maybe_stop_tx(tx_ring, count + 3)) {
+ /* this is a hard error */
+ return NETDEV_TX_BUSY;
+ }
+
+ /* record the location of the first descriptor for this packet */
+ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+ first->skb = skb;
+ first->bytecount = skb->len;
+ first->gso_segs = 1;
+
+ /* record initial flags and protocol */
+ first->tx_flags = tx_flags;
+ first->protocol = protocol;
+
+ igc_tx_csum(tx_ring, first);
+
+ igc_tx_map(tx_ring, first, hdr_len);
+
+ return NETDEV_TX_OK;
+}
+
+static inline struct igc_ring *igc_tx_queue_mapping(struct igc_adapter *adapter,
+ struct sk_buff *skb)
+{
+ unsigned int r_idx = skb->queue_mapping;
+
+ if (r_idx >= adapter->num_tx_queues)
+ r_idx = r_idx % adapter->num_tx_queues;
+
+ return adapter->tx_ring[r_idx];
+}
+
+static netdev_tx_t igc_xmit_frame(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ /* The minimum packet size with TCTL.PSP set is 17 so pad the skb
+ * in order to meet this minimum size requirement.
+ */
+ if (skb->len < 17) {
+ if (skb_padto(skb, 17))
+ return NETDEV_TX_OK;
+ skb->len = 17;
+ }
+
+ return igc_xmit_frame_ring(skb, igc_tx_queue_mapping(adapter, skb));
+}
+
+static inline void igc_rx_hash(struct igc_ring *ring,
+ union igc_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ if (ring->netdev->features & NETIF_F_RXHASH)
+ skb_set_hash(skb,
+ le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
+ PKT_HASH_TYPE_L3);
+}
+
+/**
+ * igc_process_skb_fields - Populate skb header fields from Rx descriptor
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being populated
+ *
+ * This function checks the ring, descriptor, and packet information in
+ * order to populate the hash, checksum, VLAN, timestamp, protocol, and
+ * other fields within the skb.
+ */
+static void igc_process_skb_fields(struct igc_ring *rx_ring,
+ union igc_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ igc_rx_hash(rx_ring, rx_desc, skb);
+
+ skb_record_rx_queue(skb, rx_ring->queue_index);
+
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+}
+
+static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring,
+ const unsigned int size)
+{
+ struct igc_rx_buffer *rx_buffer;
+
+ rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+ prefetchw(rx_buffer->page);
+
+ /* we are reusing so sync this buffer for CPU use */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ rx_buffer->dma,
+ rx_buffer->page_offset,
+ size,
+ DMA_FROM_DEVICE);
+
+ rx_buffer->pagecnt_bias--;
+
+ return rx_buffer;
+}
+
+/**
+ * igc_add_rx_frag - Add contents of Rx buffer to sk_buff
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: buffer containing page to add
+ * @skb: sk_buff to place the data into
+ * @size: size of buffer to be added
+ *
+ * This function will add the data contained in rx_buffer->page to the skb.
+ */
+static void igc_add_rx_frag(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *rx_buffer,
+ struct sk_buff *skb,
+ unsigned int size)
+{
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+ rx_buffer->page_offset, size, truesize);
+ rx_buffer->page_offset ^= truesize;
+#else
+ unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+ SKB_DATA_ALIGN(IGC_SKB_PAD + size) :
+ SKB_DATA_ALIGN(size);
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+ rx_buffer->page_offset, size, truesize);
+ rx_buffer->page_offset += truesize;
+#endif
+}
+
+static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *rx_buffer,
+ union igc_adv_rx_desc *rx_desc,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+ SKB_DATA_ALIGN(IGC_SKB_PAD + size);
+#endif
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+
+ /* build an skb around the page buffer */
+ skb = build_skb(va - IGC_SKB_PAD, truesize);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* update pointers within the skb to store the data */
+ skb_reserve(skb, IGC_SKB_PAD);
+ __skb_put(skb, size);
+
+ /* update buffer offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+
+ return skb;
+}
+
+static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *rx_buffer,
+ union igc_adv_rx_desc *rx_desc,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+ unsigned int headlen;
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+
+ /* allocate a skb to store the frags */
+ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGC_RX_HDR_LEN);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* Determine available headroom for copy */
+ headlen = size;
+ if (headlen > IGC_RX_HDR_LEN)
+ headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN);
+
+ /* align pull length to size of long to optimize memcpy performance */
+ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+ /* update all of the pointers */
+ size -= headlen;
+ if (size) {
+ skb_add_rx_frag(skb, 0, rx_buffer->page,
+ (va + headlen) - page_address(rx_buffer->page),
+ size, truesize);
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+ } else {
+ rx_buffer->pagecnt_bias++;
+ }
+
+ return skb;
+}
+
+/**
+ * igc_reuse_rx_page - page flip buffer and store it back on the ring
+ * @rx_ring: rx descriptor ring to store buffers on
+ * @old_buff: donor buffer to have page reused
+ *
+ * Synchronizes page for reuse by the adapter
+ */
+static void igc_reuse_rx_page(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *old_buff)
+{
+ u16 nta = rx_ring->next_to_alloc;
+ struct igc_rx_buffer *new_buff;
+
+ new_buff = &rx_ring->rx_buffer_info[nta];
+
+ /* update, and store next to alloc */
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ /* Transfer page from old buffer to new buffer.
+ * Move each member individually to avoid possible store
+ * forwarding stalls.
+ */
+ new_buff->dma = old_buff->dma;
+ new_buff->page = old_buff->page;
+ new_buff->page_offset = old_buff->page_offset;
+ new_buff->pagecnt_bias = old_buff->pagecnt_bias;
+}
+
+static inline bool igc_page_is_reserved(struct page *page)
+{
+ return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
+}
+
+static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer)
+{
+ unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+ struct page *page = rx_buffer->page;
+
+ /* avoid re-using remote pages */
+ if (unlikely(igc_page_is_reserved(page)))
+ return false;
+
+#if (PAGE_SIZE < 8192)
+ /* if we are only owner of page we can reuse it */
+ if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+ return false;
+#else
+#define IGC_LAST_OFFSET \
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGC_RXBUFFER_2048)
+
+ if (rx_buffer->page_offset > IGC_LAST_OFFSET)
+ return false;
+#endif
+
+ /* If we have drained the page fragment pool we need to update
+ * the pagecnt_bias and page count so that we fully restock the
+ * number of references the driver holds.
+ */
+ if (unlikely(!pagecnt_bias)) {
+ page_ref_add(page, USHRT_MAX);
+ rx_buffer->pagecnt_bias = USHRT_MAX;
+ }
+
+ return true;
+}
+
+/**
+ * igc_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ * @skb: current socket buffer containing buffer in progress
+ *
+ * This function updates next to clean. If the buffer is an EOP buffer
+ * this function exits returning false, otherwise it will place the
+ * sk_buff in the next buffer to be chained and return true indicating
+ * that this is in fact a non-EOP buffer.
+ */
+static bool igc_is_non_eop(struct igc_ring *rx_ring,
+ union igc_adv_rx_desc *rx_desc)
+{
+ u32 ntc = rx_ring->next_to_clean + 1;
+
+ /* fetch, update, and store next to clean */
+ ntc = (ntc < rx_ring->count) ? ntc : 0;
+ rx_ring->next_to_clean = ntc;
+
+ prefetch(IGC_RX_DESC(rx_ring, ntc));
+
+ if (likely(igc_test_staterr(rx_desc, IGC_RXD_STAT_EOP)))
+ return false;
+
+ return true;
+}
+
+/**
+ * igc_cleanup_headers - Correct corrupted or empty headers
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being fixed
+ *
+ * Address the case where we are pulling data in on pages only
+ * and as such no data is present in the skb header.
+ *
+ * In addition if skb is not at least 60 bytes we need to pad it so that
+ * it is large enough to qualify as a valid Ethernet frame.
+ *
+ * Returns true if an error was encountered and skb was freed.
+ */
+static bool igc_cleanup_headers(struct igc_ring *rx_ring,
+ union igc_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ if (unlikely((igc_test_staterr(rx_desc,
+ IGC_RXDEXT_ERR_FRAME_ERR_MASK)))) {
+ struct net_device *netdev = rx_ring->netdev;
+
+ if (!(netdev->features & NETIF_F_RXALL)) {
+ dev_kfree_skb_any(skb);
+ return true;
+ }
+ }
+
+ /* if eth_skb_pad returns an error the skb was freed */
+ if (eth_skb_pad(skb))
+ return true;
+
+ return false;
+}
+
+static void igc_put_rx_buffer(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *rx_buffer)
+{
+ if (igc_can_reuse_rx_page(rx_buffer)) {
+ /* hand second half of page back to the ring */
+ igc_reuse_rx_page(rx_ring, rx_buffer);
+ } else {
+ /* We are not reusing the buffer so unmap it and free
+ * any references we are holding to it
+ */
+ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+ igc_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
+ IGC_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buffer->page,
+ rx_buffer->pagecnt_bias);
+ }
+
+ /* clear contents of rx_buffer */
+ rx_buffer->page = NULL;
+}
+
+/**
+ * igc_alloc_rx_buffers - Replace used receive buffers; packet split
+ * @adapter: address of board private structure
+ */
+static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count)
+{
+ union igc_adv_rx_desc *rx_desc;
+ u16 i = rx_ring->next_to_use;
+ struct igc_rx_buffer *bi;
+ u16 bufsz;
+
+ /* nothing to do */
+ if (!cleaned_count)
+ return;
+
+ rx_desc = IGC_RX_DESC(rx_ring, i);
+ bi = &rx_ring->rx_buffer_info[i];
+ i -= rx_ring->count;
+
+ bufsz = igc_rx_bufsz(rx_ring);
+
+ do {
+ if (!igc_alloc_mapped_page(rx_ring, bi))
+ break;
+
+ /* sync the buffer for use by the device */
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+ bi->page_offset, bufsz,
+ DMA_FROM_DEVICE);
+
+ /* Refresh the desc even if buffer_addrs didn't change
+ * because each write-back erases this info.
+ */
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+
+ rx_desc++;
+ bi++;
+ i++;
+ if (unlikely(!i)) {
+ rx_desc = IGC_RX_DESC(rx_ring, 0);
+ bi = rx_ring->rx_buffer_info;
+ i -= rx_ring->count;
+ }
+
+ /* clear the length for the next_to_use descriptor */
+ rx_desc->wb.upper.length = 0;
+
+ cleaned_count--;
+ } while (cleaned_count);
+
+ i += rx_ring->count;
+
+ if (rx_ring->next_to_use != i) {
+ /* record the next descriptor to use */
+ rx_ring->next_to_use = i;
+
+ /* update next to alloc since we have filled the ring */
+ rx_ring->next_to_alloc = i;
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+ writel(i, rx_ring->tail);
+ }
+}
+
+static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
+{
+ unsigned int total_bytes = 0, total_packets = 0;
+ struct igc_ring *rx_ring = q_vector->rx.ring;
+ struct sk_buff *skb = rx_ring->skb;
+ u16 cleaned_count = igc_desc_unused(rx_ring);
+
+ while (likely(total_packets < budget)) {
+ union igc_adv_rx_desc *rx_desc;
+ struct igc_rx_buffer *rx_buffer;
+ unsigned int size;
+
+ /* return some buffers to hardware, one at a time is too slow */
+ if (cleaned_count >= IGC_RX_BUFFER_WRITE) {
+ igc_alloc_rx_buffers(rx_ring, cleaned_count);
+ cleaned_count = 0;
+ }
+
+ rx_desc = IGC_RX_DESC(rx_ring, rx_ring->next_to_clean);
+ size = le16_to_cpu(rx_desc->wb.upper.length);
+ if (!size)
+ break;
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we know the
+ * descriptor has been written back
+ */
+ dma_rmb();
+
+ rx_buffer = igc_get_rx_buffer(rx_ring, size);
+
+ /* retrieve a buffer from the ring */
+ if (skb)
+ igc_add_rx_frag(rx_ring, rx_buffer, skb, size);
+ else if (ring_uses_build_skb(rx_ring))
+ skb = igc_build_skb(rx_ring, rx_buffer, rx_desc, size);
+ else
+ skb = igc_construct_skb(rx_ring, rx_buffer,
+ rx_desc, size);
+
+ /* exit if we failed to retrieve a buffer */
+ if (!skb) {
+ rx_ring->rx_stats.alloc_failed++;
+ rx_buffer->pagecnt_bias++;
+ break;
+ }
+
+ igc_put_rx_buffer(rx_ring, rx_buffer);
+ cleaned_count++;
+
+ /* fetch next buffer in frame if non-eop */
+ if (igc_is_non_eop(rx_ring, rx_desc))
+ continue;
+
+ /* verify the packet layout is correct */
+ if (igc_cleanup_headers(rx_ring, rx_desc, skb)) {
+ skb = NULL;
+ continue;
+ }
+
+ /* probably a little skewed due to removing CRC */
+ total_bytes += skb->len;
+
+ /* populate checksum, timestamp, VLAN, and protocol */
+ igc_process_skb_fields(rx_ring, rx_desc, skb);
+
+ napi_gro_receive(&q_vector->napi, skb);
+
+ /* reset skb pointer */
+ skb = NULL;
+
+ /* update budget accounting */
+ total_packets++;
+ }
+
+ /* place incomplete frames back on ring for completion */
+ rx_ring->skb = skb;
+
+ u64_stats_update_begin(&rx_ring->rx_syncp);
+ rx_ring->rx_stats.packets += total_packets;
+ rx_ring->rx_stats.bytes += total_bytes;
+ u64_stats_update_end(&rx_ring->rx_syncp);
+ q_vector->rx.total_packets += total_packets;
+ q_vector->rx.total_bytes += total_bytes;
+
+ if (cleaned_count)
+ igc_alloc_rx_buffers(rx_ring, cleaned_count);
+
+ return total_packets;
+}
+
+static inline unsigned int igc_rx_offset(struct igc_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? IGC_SKB_PAD : 0;
+}
+
+static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *bi)
+{
+ struct page *page = bi->page;
+ dma_addr_t dma;
+
+ /* since we are recycling buffers we should seldom need to alloc */
+ if (likely(page))
+ return true;
+
+ /* alloc new page for storage */
+ page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
+ if (unlikely(!page)) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ /* map page for use */
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+ igc_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ IGC_RX_DMA_ATTR);
+
+ /* if mapping failed free memory back to system since
+ * there isn't much point in holding memory we can't use
+ */
+ if (dma_mapping_error(rx_ring->dev, dma)) {
+ __free_page(page);
+
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ bi->dma = dma;
+ bi->page = page;
+ bi->page_offset = igc_rx_offset(rx_ring);
+ bi->pagecnt_bias = 1;
+
+ return true;
+}
+
+/**
+ * igc_clean_tx_irq - Reclaim resources after transmit completes
+ * @q_vector: pointer to q_vector containing needed info
+ * @napi_budget: Used to determine if we are in netpoll
+ *
+ * returns true if ring is completely cleaned
+ */
+static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ unsigned int total_bytes = 0, total_packets = 0;
+ unsigned int budget = q_vector->tx.work_limit;
+ struct igc_ring *tx_ring = q_vector->tx.ring;
+ unsigned int i = tx_ring->next_to_clean;
+ struct igc_tx_buffer *tx_buffer;
+ union igc_adv_tx_desc *tx_desc;
+
+ if (test_bit(__IGC_DOWN, &adapter->state))
+ return true;
+
+ tx_buffer = &tx_ring->tx_buffer_info[i];
+ tx_desc = IGC_TX_DESC(tx_ring, i);
+ i -= tx_ring->count;
+
+ do {
+ union igc_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;
+
+ /* if next_to_watch is not set then there is no work pending */
+ if (!eop_desc)
+ break;
+
+ /* prevent any other reads prior to eop_desc */
+ smp_rmb();
+
+ /* if DD is not set pending work has not been completed */
+ if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
+ break;
+
+ /* clear next_to_watch to prevent false hangs */
+ tx_buffer->next_to_watch = NULL;
+
+ /* update the statistics for this packet */
+ total_bytes += tx_buffer->bytecount;
+ total_packets += tx_buffer->gso_segs;
+
+ /* free the skb */
+ napi_consume_skb(tx_buffer->skb, napi_budget);
+
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+
+ /* clear tx_buffer data */
+ dma_unmap_len_set(tx_buffer, len, 0);
+
+ /* clear last DMA location and unmap remaining buffers */
+ while (tx_desc != eop_desc) {
+ tx_buffer++;
+ tx_desc++;
+ i++;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
+ tx_buffer = tx_ring->tx_buffer_info;
+ tx_desc = IGC_TX_DESC(tx_ring, 0);
+ }
+
+ /* unmap any remaining paged data */
+ if (dma_unmap_len(tx_buffer, len)) {
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer, len, 0);
+ }
+ }
+
+ /* move us one more past the eop_desc for start of next pkt */
+ tx_buffer++;
+ tx_desc++;
+ i++;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
+ tx_buffer = tx_ring->tx_buffer_info;
+ tx_desc = IGC_TX_DESC(tx_ring, 0);
+ }
+
+ /* issue prefetch for next Tx descriptor */
+ prefetch(tx_desc);
+
+ /* update budget accounting */
+ budget--;
+ } while (likely(budget));
+
+ netdev_tx_completed_queue(txring_txq(tx_ring),
+ total_packets, total_bytes);
+
+ i += tx_ring->count;
+ tx_ring->next_to_clean = i;
+ u64_stats_update_begin(&tx_ring->tx_syncp);
+ tx_ring->tx_stats.bytes += total_bytes;
+ tx_ring->tx_stats.packets += total_packets;
+ u64_stats_update_end(&tx_ring->tx_syncp);
+ q_vector->tx.total_bytes += total_bytes;
+ q_vector->tx.total_packets += total_packets;
+
+ if (test_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
+ struct igc_hw *hw = &adapter->hw;
+
+ /* Detect a transmit hang in hardware, this serializes the
+ * check with the clearing of time_stamp and movement of i
+ */
+ clear_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags);
+ if (tx_buffer->next_to_watch &&
+ time_after(jiffies, tx_buffer->time_stamp +
+ (adapter->tx_timeout_factor * HZ)) &&
+ !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) {
+ /* detected Tx unit hang */
+ dev_err(tx_ring->dev,
+ "Detected Tx Unit Hang\n"
+ " Tx Queue <%d>\n"
+ " TDH <%x>\n"
+ " TDT <%x>\n"
+ " next_to_use <%x>\n"
+ " next_to_clean <%x>\n"
+ "buffer_info[next_to_clean]\n"
+ " time_stamp <%lx>\n"
+ " next_to_watch <%p>\n"
+ " jiffies <%lx>\n"
+ " desc.status <%x>\n",
+ tx_ring->queue_index,
+ rd32(IGC_TDH(tx_ring->reg_idx)),
+ readl(tx_ring->tail),
+ tx_ring->next_to_use,
+ tx_ring->next_to_clean,
+ tx_buffer->time_stamp,
+ tx_buffer->next_to_watch,
+ jiffies,
+ tx_buffer->next_to_watch->wb.status);
+ netif_stop_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+
+ /* we are about to reset, no point in enabling stuff */
+ return true;
+ }
+ }
+
+#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
+ if (unlikely(total_packets &&
+ netif_carrier_ok(tx_ring->netdev) &&
+ igc_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) {
+ /* Make sure that anybody stopping the queue after this
+ * sees the new next_to_clean.
+ */
+ smp_mb();
+ if (__netif_subqueue_stopped(tx_ring->netdev,
+ tx_ring->queue_index) &&
+ !(test_bit(__IGC_DOWN, &adapter->state))) {
+ netif_wake_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+
+ u64_stats_update_begin(&tx_ring->tx_syncp);
+ tx_ring->tx_stats.restart_queue++;
+ u64_stats_update_end(&tx_ring->tx_syncp);
+ }
+ }
+
+ return !!budget;
+}
+
+/**
+ * igc_up - Open the interface and prepare it to handle traffic
+ * @adapter: board private structure
+ */
+void igc_up(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int i = 0;
+
+ /* hardware has been reset, we need to reload some things */
+ igc_configure(adapter);
+
+ clear_bit(__IGC_DOWN, &adapter->state);
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ napi_enable(&adapter->q_vector[i]->napi);
+
+ if (adapter->msix_entries)
+ igc_configure_msix(adapter);
+ else
+ igc_assign_vector(adapter->q_vector[0], 0);
+
+ /* Clear any pending interrupts. */
+ rd32(IGC_ICR);
+ igc_irq_enable(adapter);
+
+ netif_tx_start_all_queues(adapter->netdev);
+
+ /* start the watchdog. */
+ hw->mac.get_link_status = 1;
+ schedule_work(&adapter->watchdog_task);
+}
+
+/**
+ * igc_update_stats - Update the board statistics counters
+ * @adapter: board private structure
+ */
+void igc_update_stats(struct igc_adapter *adapter)
+{
+ struct rtnl_link_stats64 *net_stats = &adapter->stats64;
+ struct pci_dev *pdev = adapter->pdev;
+ struct igc_hw *hw = &adapter->hw;
+ u64 _bytes, _packets;
+ u64 bytes, packets;
+ unsigned int start;
+ u32 mpc;
+ int i;
+
+ /* Prevent stats update while adapter is being reset, or if the pci
+ * connection is down.
+ */
+ if (adapter->link_speed == 0)
+ return;
+ if (pci_channel_offline(pdev))
+ return;
+
+ packets = 0;
+ bytes = 0;
+
+ rcu_read_lock();
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct igc_ring *ring = adapter->rx_ring[i];
+ u32 rqdpc = rd32(IGC_RQDPC(i));
+
+ if (hw->mac.type >= igc_i225)
+ wr32(IGC_RQDPC(i), 0);
+
+ if (rqdpc) {
+ ring->rx_stats.drops += rqdpc;
+ net_stats->rx_fifo_errors += rqdpc;
+ }
+
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
+ _bytes = ring->rx_stats.bytes;
+ _packets = ring->rx_stats.packets;
+ } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
+ bytes += _bytes;
+ packets += _packets;
+ }
+
+ net_stats->rx_bytes = bytes;
+ net_stats->rx_packets = packets;
+
+ packets = 0;
+ bytes = 0;
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct igc_ring *ring = adapter->tx_ring[i];
+
+ do {
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
+ _bytes = ring->tx_stats.bytes;
+ _packets = ring->tx_stats.packets;
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
+ bytes += _bytes;
+ packets += _packets;
+ }
+ net_stats->tx_bytes = bytes;
+ net_stats->tx_packets = packets;
+ rcu_read_unlock();
+
+ /* read stats registers */
+ adapter->stats.crcerrs += rd32(IGC_CRCERRS);
+ adapter->stats.gprc += rd32(IGC_GPRC);
+ adapter->stats.gorc += rd32(IGC_GORCL);
+ rd32(IGC_GORCH); /* clear GORCL */
+ adapter->stats.bprc += rd32(IGC_BPRC);
+ adapter->stats.mprc += rd32(IGC_MPRC);
+ adapter->stats.roc += rd32(IGC_ROC);
+
+ adapter->stats.prc64 += rd32(IGC_PRC64);
+ adapter->stats.prc127 += rd32(IGC_PRC127);
+ adapter->stats.prc255 += rd32(IGC_PRC255);
+ adapter->stats.prc511 += rd32(IGC_PRC511);
+ adapter->stats.prc1023 += rd32(IGC_PRC1023);
+ adapter->stats.prc1522 += rd32(IGC_PRC1522);
+ adapter->stats.symerrs += rd32(IGC_SYMERRS);
+ adapter->stats.sec += rd32(IGC_SEC);
+
+ mpc = rd32(IGC_MPC);
+ adapter->stats.mpc += mpc;
+ net_stats->rx_fifo_errors += mpc;
+ adapter->stats.scc += rd32(IGC_SCC);
+ adapter->stats.ecol += rd32(IGC_ECOL);
+ adapter->stats.mcc += rd32(IGC_MCC);
+ adapter->stats.latecol += rd32(IGC_LATECOL);
+ adapter->stats.dc += rd32(IGC_DC);
+ adapter->stats.rlec += rd32(IGC_RLEC);
+ adapter->stats.xonrxc += rd32(IGC_XONRXC);
+ adapter->stats.xontxc += rd32(IGC_XONTXC);
+ adapter->stats.xoffrxc += rd32(IGC_XOFFRXC);
+ adapter->stats.xofftxc += rd32(IGC_XOFFTXC);
+ adapter->stats.fcruc += rd32(IGC_FCRUC);
+ adapter->stats.gptc += rd32(IGC_GPTC);
+ adapter->stats.gotc += rd32(IGC_GOTCL);
+ rd32(IGC_GOTCH); /* clear GOTCL */
+ adapter->stats.rnbc += rd32(IGC_RNBC);
+ adapter->stats.ruc += rd32(IGC_RUC);
+ adapter->stats.rfc += rd32(IGC_RFC);
+ adapter->stats.rjc += rd32(IGC_RJC);
+ adapter->stats.tor += rd32(IGC_TORH);
+ adapter->stats.tot += rd32(IGC_TOTH);
+ adapter->stats.tpr += rd32(IGC_TPR);
+
+ adapter->stats.ptc64 += rd32(IGC_PTC64);
+ adapter->stats.ptc127 += rd32(IGC_PTC127);
+ adapter->stats.ptc255 += rd32(IGC_PTC255);
+ adapter->stats.ptc511 += rd32(IGC_PTC511);
+ adapter->stats.ptc1023 += rd32(IGC_PTC1023);
+ adapter->stats.ptc1522 += rd32(IGC_PTC1522);
+
+ adapter->stats.mptc += rd32(IGC_MPTC);
+ adapter->stats.bptc += rd32(IGC_BPTC);
+
+ adapter->stats.tpt += rd32(IGC_TPT);
+ adapter->stats.colc += rd32(IGC_COLC);
+
+ adapter->stats.algnerrc += rd32(IGC_ALGNERRC);
+
+ adapter->stats.tsctc += rd32(IGC_TSCTC);
+ adapter->stats.tsctfc += rd32(IGC_TSCTFC);
+
+ adapter->stats.iac += rd32(IGC_IAC);
+ adapter->stats.icrxoc += rd32(IGC_ICRXOC);
+ adapter->stats.icrxptc += rd32(IGC_ICRXPTC);
+ adapter->stats.icrxatc += rd32(IGC_ICRXATC);
+ adapter->stats.ictxptc += rd32(IGC_ICTXPTC);
+ adapter->stats.ictxatc += rd32(IGC_ICTXATC);
+ adapter->stats.ictxqec += rd32(IGC_ICTXQEC);
+ adapter->stats.ictxqmtc += rd32(IGC_ICTXQMTC);
+ adapter->stats.icrxdmtc += rd32(IGC_ICRXDMTC);
+
+ /* Fill out the OS statistics structure */
+ net_stats->multicast = adapter->stats.mprc;
+ net_stats->collisions = adapter->stats.colc;
+
+ /* Rx Errors */
+
+ /* RLEC on some newer hardware can be incorrect so build
+ * our own version based on RUC and ROC
+ */
+ net_stats->rx_errors = adapter->stats.rxerrc +
+ adapter->stats.crcerrs + adapter->stats.algnerrc +
+ adapter->stats.ruc + adapter->stats.roc +
+ adapter->stats.cexterr;
+ net_stats->rx_length_errors = adapter->stats.ruc +
+ adapter->stats.roc;
+ net_stats->rx_crc_errors = adapter->stats.crcerrs;
+ net_stats->rx_frame_errors = adapter->stats.algnerrc;
+ net_stats->rx_missed_errors = adapter->stats.mpc;
+
+ /* Tx Errors */
+ net_stats->tx_errors = adapter->stats.ecol +
+ adapter->stats.latecol;
+ net_stats->tx_aborted_errors = adapter->stats.ecol;
+ net_stats->tx_window_errors = adapter->stats.latecol;
+ net_stats->tx_carrier_errors = adapter->stats.tncrs;
+
+ /* Tx Dropped needs to be maintained elsewhere */
+
+ /* Management Stats */
+ adapter->stats.mgptc += rd32(IGC_MGTPTC);
+ adapter->stats.mgprc += rd32(IGC_MGTPRC);
+ adapter->stats.mgpdc += rd32(IGC_MGTPDC);
+}
+
+static void igc_nfc_filter_exit(struct igc_adapter *adapter)
+{
+ struct igc_nfc_filter *rule;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+ igc_erase_filter(adapter, rule);
+
+ hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node)
+ igc_erase_filter(adapter, rule);
+
+ spin_unlock(&adapter->nfc_lock);
+}
+
+static void igc_nfc_filter_restore(struct igc_adapter *adapter)
+{
+ struct igc_nfc_filter *rule;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+ igc_add_filter(adapter, rule);
+
+ spin_unlock(&adapter->nfc_lock);
+}
+
+/**
+ * igc_down - Close the interface
+ * @adapter: board private structure
+ */
+void igc_down(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct igc_hw *hw = &adapter->hw;
+ u32 tctl, rctl;
+ int i = 0;
+
+ set_bit(__IGC_DOWN, &adapter->state);
+
+ /* disable receives in the hardware */
+ rctl = rd32(IGC_RCTL);
+ wr32(IGC_RCTL, rctl & ~IGC_RCTL_EN);
+ /* flush and sleep below */
+
+ igc_nfc_filter_exit(adapter);
+
+ /* set trans_start so we don't get spurious watchdogs during reset */
+ netif_trans_update(netdev);
+
+ netif_carrier_off(netdev);
+ netif_tx_stop_all_queues(netdev);
+
+ /* disable transmits in the hardware */
+ tctl = rd32(IGC_TCTL);
+ tctl &= ~IGC_TCTL_EN;
+ wr32(IGC_TCTL, tctl);
+ /* flush both disables and wait for them to finish */
+ wrfl();
+ usleep_range(10000, 20000);
+
+ igc_irq_disable(adapter);
+
+ adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+
+ for (i = 0; i < adapter->num_q_vectors; i++) {
+ if (adapter->q_vector[i]) {
+ napi_synchronize(&adapter->q_vector[i]->napi);
+ napi_disable(&adapter->q_vector[i]->napi);
+ }
+ }
+
+ del_timer_sync(&adapter->watchdog_timer);
+ del_timer_sync(&adapter->phy_info_timer);
+
+ /* record the stats before reset*/
+ spin_lock(&adapter->stats64_lock);
+ igc_update_stats(adapter);
+ spin_unlock(&adapter->stats64_lock);
+
+ adapter->link_speed = 0;
+ adapter->link_duplex = 0;
+
+ if (!pci_channel_offline(adapter->pdev))
+ igc_reset(adapter);
+
+ /* clear VLAN promisc flag so VFTA will be updated if necessary */
+ adapter->flags &= ~IGC_FLAG_VLAN_PROMISC;
+
+ igc_clean_all_tx_rings(adapter);
+ igc_clean_all_rx_rings(adapter);
+}
+
+void igc_reinit_locked(struct igc_adapter *adapter)
+{
+ WARN_ON(in_interrupt());
+ while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+ igc_down(adapter);
+ igc_up(adapter);
+ clear_bit(__IGC_RESETTING, &adapter->state);
+}
+
+static void igc_reset_task(struct work_struct *work)
+{
+ struct igc_adapter *adapter;
+
+ adapter = container_of(work, struct igc_adapter, reset_task);
+
+ netdev_err(adapter->netdev, "Reset adapter\n");
+ igc_reinit_locked(adapter);
+}
+
+/**
+ * igc_change_mtu - Change the Maximum Transfer Unit
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int igc_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct pci_dev *pdev = adapter->pdev;
+
+ /* adjust max frame to be at least the size of a standard frame */
+ if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
+ max_frame = ETH_FRAME_LEN + ETH_FCS_LEN;
+
+ while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+
+ /* igc_down has a dependency on max_frame_size */
+ adapter->max_frame_size = max_frame;
+
+ if (netif_running(netdev))
+ igc_down(adapter);
+
+ dev_info(&pdev->dev, "changing MTU from %d to %d\n",
+ netdev->mtu, new_mtu);
+ netdev->mtu = new_mtu;
+
+ if (netif_running(netdev))
+ igc_up(adapter);
+ else
+ igc_reset(adapter);
+
+ clear_bit(__IGC_RESETTING, &adapter->state);
+
+ return 0;
+}
+
+/**
+ * igc_get_stats - Get System Network Statistics
+ * @netdev: network interface device structure
+ *
+ * Returns the address of the device statistics structure.
+ * The statistics are updated here and also from the timer callback.
+ */
+static struct net_device_stats *igc_get_stats(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ if (!test_bit(__IGC_RESETTING, &adapter->state))
+ igc_update_stats(adapter);
+
+ /* only return the current stats */
+ return &netdev->stats;
+}
+
+static netdev_features_t igc_fix_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ /* Since there is no support for separate Rx/Tx vlan accel
+ * enable/disable make sure Tx flag is always in same state as Rx.
+ */
+ if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ features |= NETIF_F_HW_VLAN_CTAG_TX;
+ else
+ features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
+ return features;
+}
+
+static int igc_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ netdev_features_t changed = netdev->features ^ features;
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ /* Add VLAN support */
+ if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE)))
+ return 0;
+
+ if (!(features & NETIF_F_NTUPLE)) {
+ struct hlist_node *node2;
+ struct igc_nfc_filter *rule;
+
+ spin_lock(&adapter->nfc_lock);
+ hlist_for_each_entry_safe(rule, node2,
+ &adapter->nfc_filter_list, nfc_node) {
+ igc_erase_filter(adapter, rule);
+ hlist_del(&rule->nfc_node);
+ kfree(rule);
+ }
+ spin_unlock(&adapter->nfc_lock);
+ adapter->nfc_filter_count = 0;
+ }
+
+ netdev->features = features;
+
+ if (netif_running(netdev))
+ igc_reinit_locked(adapter);
+ else
+ igc_reset(adapter);
+
+ return 1;
+}
+
+static netdev_features_t
+igc_features_check(struct sk_buff *skb, struct net_device *dev,
+ netdev_features_t features)
+{
+ unsigned int network_hdr_len, mac_hdr_len;
+
+ /* Make certain the headers can be described by a context descriptor */
+ mac_hdr_len = skb_network_header(skb) - skb->data;
+ if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN))
+ return features & ~(NETIF_F_HW_CSUM |
+ NETIF_F_SCTP_CRC |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_TSO |
+ NETIF_F_TSO6);
+
+ network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+ if (unlikely(network_hdr_len > IGC_MAX_NETWORK_HDR_LEN))
+ return features & ~(NETIF_F_HW_CSUM |
+ NETIF_F_SCTP_CRC |
+ NETIF_F_TSO |
+ NETIF_F_TSO6);
+
+ /* We can only support IPv4 TSO in tunnels if we can mangle the
+ * inner IP ID field, so strip TSO if MANGLEID is not supported.
+ */
+ if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID))
+ features &= ~NETIF_F_TSO;
+
+ return features;
+}
+
+/**
+ * igc_configure - configure the hardware for RX and TX
+ * @adapter: private board structure
+ */
+static void igc_configure(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i = 0;
+
+ igc_get_hw_control(adapter);
+ igc_set_rx_mode(netdev);
+
+ igc_setup_tctl(adapter);
+ igc_setup_mrqc(adapter);
+ igc_setup_rctl(adapter);
+
+ igc_nfc_filter_restore(adapter);
+ igc_configure_tx(adapter);
+ igc_configure_rx(adapter);
+
+ igc_rx_fifo_flush_base(&adapter->hw);
+
+ /* call igc_desc_unused which always leaves
+ * at least 1 descriptor unused to make sure
+ * next_to_use != next_to_clean
+ */
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct igc_ring *ring = adapter->rx_ring[i];
+
+ igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
+ }
+}
+
+/**
+ * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
+ * @adapter: address of board private structure
+ * @index: Index of the RAR entry which need to be synced with MAC table
+ */
+static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
+{
+ u8 *addr = adapter->mac_table[index].addr;
+ struct igc_hw *hw = &adapter->hw;
+ u32 rar_low, rar_high;
+
+ /* HW expects these to be in network order when they are plugged
+ * into the registers which are little endian. In order to guarantee
+ * that ordering we need to do an leXX_to_cpup here in order to be
+ * ready for the byteswap that occurs with writel
+ */
+ rar_low = le32_to_cpup((__le32 *)(addr));
+ rar_high = le16_to_cpup((__le16 *)(addr + 4));
+
+ /* Indicate to hardware the Address is Valid. */
+ if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
+ if (is_valid_ether_addr(addr))
+ rar_high |= IGC_RAH_AV;
+
+ rar_high |= IGC_RAH_POOL_1 <<
+ adapter->mac_table[index].queue;
+ }
+
+ wr32(IGC_RAL(index), rar_low);
+ wrfl();
+ wr32(IGC_RAH(index), rar_high);
+ wrfl();
+}
+
+/* Set default MAC address for the PF in the first RAR entry */
+static void igc_set_default_mac_filter(struct igc_adapter *adapter)
+{
+ struct igc_mac_addr *mac_table = &adapter->mac_table[0];
+
+ ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
+ mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+
+ igc_rar_set_index(adapter, 0);
+}
+
+/* If the filter to be added and an already existing filter express
+ * the same address and address type, it should be possible to only
+ * override the other configurations, for example the queue to steer
+ * traffic.
+ */
+static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
+ const u8 *addr, const u8 flags)
+{
+ if (!(entry->state & IGC_MAC_STATE_IN_USE))
+ return true;
+
+ if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
+ (flags & IGC_MAC_STATE_SRC_ADDR))
+ return false;
+
+ if (!ether_addr_equal(addr, entry->addr))
+ return false;
+
+ return true;
+}
+
+/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
+ * 'flags' is used to indicate what kind of match is made, match is by
+ * default for the destination address, if matching by source address
+ * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_add_mac_filter_flags(struct igc_adapter *adapter,
+ const u8 *addr, const u8 queue,
+ const u8 flags)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int rar_entries = hw->mac.rar_entry_count;
+ int i;
+
+ if (is_zero_ether_addr(addr))
+ return -EINVAL;
+
+ /* Search for the first empty entry in the MAC table.
+ * Do not touch entries at the end of the table reserved for the VF MAC
+ * addresses.
+ */
+ for (i = 0; i < rar_entries; i++) {
+ if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
+ addr, flags))
+ continue;
+
+ ether_addr_copy(adapter->mac_table[i].addr, addr);
+ adapter->mac_table[i].queue = queue;
+ adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
+
+ igc_rar_set_index(adapter, i);
+ return i;
+ }
+
+ return -ENOSPC;
+}
+
+int igc_add_mac_steering_filter(struct igc_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags)
+{
+ return igc_add_mac_filter_flags(adapter, addr, queue,
+ IGC_MAC_STATE_QUEUE_STEERING | flags);
+}
+
+/* Remove a MAC filter for 'addr' directing matching traffic to
+ * 'queue', 'flags' is used to indicate what kind of match need to be
+ * removed, match is by default for the destination address, if
+ * matching by source address is to be removed the flag
+ * IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_del_mac_filter_flags(struct igc_adapter *adapter,
+ const u8 *addr, const u8 queue,
+ const u8 flags)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int rar_entries = hw->mac.rar_entry_count;
+ int i;
+
+ if (is_zero_ether_addr(addr))
+ return -EINVAL;
+
+ /* Search for matching entry in the MAC table based on given address
+ * and queue. Do not touch entries at the end of the table reserved
+ * for the VF MAC addresses.
+ */
+ for (i = 0; i < rar_entries; i++) {
+ if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
+ continue;
+ if ((adapter->mac_table[i].state & flags) != flags)
+ continue;
+ if (adapter->mac_table[i].queue != queue)
+ continue;
+ if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
+ continue;
+
+ /* When a filter for the default address is "deleted",
+ * we return it to its initial configuration
+ */
+ if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
+ adapter->mac_table[i].state =
+ IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+ } else {
+ adapter->mac_table[i].state = 0;
+ adapter->mac_table[i].queue = 0;
+ memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+ }
+
+ igc_rar_set_index(adapter, i);
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+int igc_del_mac_steering_filter(struct igc_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags)
+{
+ return igc_del_mac_filter_flags(adapter, addr, queue,
+ IGC_MAC_STATE_QUEUE_STEERING | flags);
+}
+
+/**
+ * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
+ * @netdev: network interface device structure
+ *
+ * The set_rx_mode entry point is called whenever the unicast or multicast
+ * address lists or the network interface flags are updated. This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
+ * promiscuous mode, and all-multi behavior.
+ */
+static void igc_set_rx_mode(struct net_device *netdev)
+{
+}
+
+/**
+ * igc_msix_other - msix other interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t igc_msix_other(int irq, void *data)
+{
+ struct igc_adapter *adapter = data;
+ struct igc_hw *hw = &adapter->hw;
+ u32 icr = rd32(IGC_ICR);
+
+ /* reading ICR causes bit 31 of EICR to be cleared */
+ if (icr & IGC_ICR_DRSTA)
+ schedule_work(&adapter->reset_task);
+
+ if (icr & IGC_ICR_DOUTSYNC) {
+ /* HW is reporting DMA is out of sync */
+ adapter->stats.doosync++;
+ }
+
+ if (icr & IGC_ICR_LSC) {
+ hw->mac.get_link_status = 1;
+ /* guard against interrupt when we're going down */
+ if (!test_bit(__IGC_DOWN, &adapter->state))
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ }
+
+ wr32(IGC_EIMS, adapter->eims_other);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * igc_write_ivar - configure ivar for given MSI-X vector
+ * @hw: pointer to the HW structure
+ * @msix_vector: vector number we are allocating to a given ring
+ * @index: row index of IVAR register to write within IVAR table
+ * @offset: column offset of in IVAR, should be multiple of 8
+ *
+ * The IVAR table consists of 2 columns,
+ * each containing an cause allocation for an Rx and Tx ring, and a
+ * variable number of rows depending on the number of queues supported.
+ */
+static void igc_write_ivar(struct igc_hw *hw, int msix_vector,
+ int index, int offset)
+{
+ u32 ivar = array_rd32(IGC_IVAR0, index);
+
+ /* clear any bits that are currently set */
+ ivar &= ~((u32)0xFF << offset);
+
+ /* write vector and valid bit */
+ ivar |= (msix_vector | IGC_IVAR_VALID) << offset;
+
+ array_wr32(IGC_IVAR0, index, ivar);
+}
+
+static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ struct igc_hw *hw = &adapter->hw;
+ int rx_queue = IGC_N0_QUEUE;
+ int tx_queue = IGC_N0_QUEUE;
+
+ if (q_vector->rx.ring)
+ rx_queue = q_vector->rx.ring->reg_idx;
+ if (q_vector->tx.ring)
+ tx_queue = q_vector->tx.ring->reg_idx;
+
+ switch (hw->mac.type) {
+ case igc_i225:
+ if (rx_queue > IGC_N0_QUEUE)
+ igc_write_ivar(hw, msix_vector,
+ rx_queue >> 1,
+ (rx_queue & 0x1) << 4);
+ if (tx_queue > IGC_N0_QUEUE)
+ igc_write_ivar(hw, msix_vector,
+ tx_queue >> 1,
+ ((tx_queue & 0x1) << 4) + 8);
+ q_vector->eims_value = BIT(msix_vector);
+ break;
+ default:
+ WARN_ONCE(hw->mac.type != igc_i225, "Wrong MAC type\n");
+ break;
+ }
+
+ /* add q_vector eims value to global eims_enable_mask */
+ adapter->eims_enable_mask |= q_vector->eims_value;
+
+ /* configure q_vector to set itr on first interrupt */
+ q_vector->set_itr = 1;
+}
+
+/**
+ * igc_configure_msix - Configure MSI-X hardware
+ * @adapter: Pointer to adapter structure
+ *
+ * igc_configure_msix sets up the hardware to properly
+ * generate MSI-X interrupts.
+ */
+static void igc_configure_msix(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int i, vector = 0;
+ u32 tmp;
+
+ adapter->eims_enable_mask = 0;
+
+ /* set vector for other causes, i.e. link changes */
+ switch (hw->mac.type) {
+ case igc_i225:
+ /* Turn on MSI-X capability first, or our settings
+ * won't stick. And it will take days to debug.
+ */
+ wr32(IGC_GPIE, IGC_GPIE_MSIX_MODE |
+ IGC_GPIE_PBA | IGC_GPIE_EIAME |
+ IGC_GPIE_NSICR);
+
+ /* enable msix_other interrupt */
+ adapter->eims_other = BIT(vector);
+ tmp = (vector++ | IGC_IVAR_VALID) << 8;
+
+ wr32(IGC_IVAR_MISC, tmp);
+ break;
+ default:
+ /* do nothing, since nothing else supports MSI-X */
+ break;
+ } /* switch (hw->mac.type) */
+
+ adapter->eims_enable_mask |= adapter->eims_other;
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ igc_assign_vector(adapter->q_vector[i], vector++);
+
+ wrfl();
+}
+
+static irqreturn_t igc_msix_ring(int irq, void *data)
+{
+ struct igc_q_vector *q_vector = data;
+
+ /* Write the ITR value calculated from the previous interrupt. */
+ igc_write_itr(q_vector);
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * igc_request_msix - Initialize MSI-X interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * igc_request_msix allocates MSI-X vectors and requests interrupts from the
+ * kernel.
+ */
+static int igc_request_msix(struct igc_adapter *adapter)
+{
+ int i = 0, err = 0, vector = 0, free_vector = 0;
+ struct net_device *netdev = adapter->netdev;
+
+ err = request_irq(adapter->msix_entries[vector].vector,
+ &igc_msix_other, 0, netdev->name, adapter);
+ if (err)
+ goto err_out;
+
+ for (i = 0; i < adapter->num_q_vectors; i++) {
+ struct igc_q_vector *q_vector = adapter->q_vector[i];
+
+ vector++;
+
+ q_vector->itr_register = adapter->io_addr + IGC_EITR(vector);
+
+ if (q_vector->rx.ring && q_vector->tx.ring)
+ sprintf(q_vector->name, "%s-TxRx-%u", netdev->name,
+ q_vector->rx.ring->queue_index);
+ else if (q_vector->tx.ring)
+ sprintf(q_vector->name, "%s-tx-%u", netdev->name,
+ q_vector->tx.ring->queue_index);
+ else if (q_vector->rx.ring)
+ sprintf(q_vector->name, "%s-rx-%u", netdev->name,
+ q_vector->rx.ring->queue_index);
+ else
+ sprintf(q_vector->name, "%s-unused", netdev->name);
+
+ err = request_irq(adapter->msix_entries[vector].vector,
+ igc_msix_ring, 0, q_vector->name,
+ q_vector);
+ if (err)
+ goto err_free;
+ }
+
+ igc_configure_msix(adapter);
+ return 0;
+
+err_free:
+ /* free already assigned IRQs */
+ free_irq(adapter->msix_entries[free_vector++].vector, adapter);
+
+ vector--;
+ for (i = 0; i < vector; i++) {
+ free_irq(adapter->msix_entries[free_vector++].vector,
+ adapter->q_vector[i]);
+ }
+err_out:
+ return err;
+}
+
+/**
+ * igc_reset_q_vector - Reset config for interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be reset
+ *
+ * If NAPI is enabled it will delete any references to the
+ * NAPI struct. This is preparation for igc_free_q_vector.
+ */
+static void igc_reset_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+ struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+ /* if we're coming from igc_set_interrupt_capability, the vectors are
+ * not yet allocated
+ */
+ if (!q_vector)
+ return;
+
+ if (q_vector->tx.ring)
+ adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
+
+ if (q_vector->rx.ring)
+ adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
+
+ netif_napi_del(&q_vector->napi);
+}
+
+static void igc_reset_interrupt_capability(struct igc_adapter *adapter)
+{
+ int v_idx = adapter->num_q_vectors;
+
+ if (adapter->msix_entries) {
+ pci_disable_msix(adapter->pdev);
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+ } else if (adapter->flags & IGC_FLAG_HAS_MSI) {
+ pci_disable_msi(adapter->pdev);
+ }
+
+ while (v_idx--)
+ igc_reset_q_vector(adapter, v_idx);
+}
+
+/**
+ * igc_clear_interrupt_scheme - reset the device to a state of no interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * This function resets the device so that it has 0 rx queues, tx queues, and
+ * MSI-X interrupts allocated.
+ */
+static void igc_clear_interrupt_scheme(struct igc_adapter *adapter)
+{
+ igc_free_q_vectors(adapter);
+ igc_reset_interrupt_capability(adapter);
+}
+
+/**
+ * igc_free_q_vectors - Free memory allocated for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function frees the memory allocated to the q_vectors. In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ */
+static void igc_free_q_vectors(struct igc_adapter *adapter)
+{
+ int v_idx = adapter->num_q_vectors;
+
+ adapter->num_tx_queues = 0;
+ adapter->num_rx_queues = 0;
+ adapter->num_q_vectors = 0;
+
+ while (v_idx--) {
+ igc_reset_q_vector(adapter, v_idx);
+ igc_free_q_vector(adapter, v_idx);
+ }
+}
+
+/**
+ * igc_free_q_vector - Free memory allocated for specific interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be freed
+ *
+ * This function frees the memory allocated to the q_vector.
+ */
+static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+ struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+ adapter->q_vector[v_idx] = NULL;
+
+ /* igc_get_stats64() might access the rings on this vector,
+ * we must wait a grace period before freeing it.
+ */
+ if (q_vector)
+ kfree_rcu(q_vector, rcu);
+}
+
+/* Need to wait a few seconds after link up to get diagnostic information from
+ * the phy
+ */
+static void igc_update_phy_info(struct timer_list *t)
+{
+ struct igc_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+
+ igc_get_phy_info(&adapter->hw);
+}
+
+/**
+ * igc_has_link - check shared code for link and determine up/down
+ * @adapter: pointer to driver private info
+ */
+bool igc_has_link(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ bool link_active = false;
+
+ /* get_link_status is set on LSC (link status) interrupt or
+ * rx sequence error interrupt. get_link_status will stay
+ * false until the igc_check_for_link establishes link
+ * for copper adapters ONLY
+ */
+ switch (hw->phy.media_type) {
+ case igc_media_type_copper:
+ if (!hw->mac.get_link_status)
+ return true;
+ hw->mac.ops.check_for_link(hw);
+ link_active = !hw->mac.get_link_status;
+ break;
+ default:
+ case igc_media_type_unknown:
+ break;
+ }
+
+ if (hw->mac.type == igc_i225 &&
+ hw->phy.id == I225_I_PHY_ID) {
+ if (!netif_carrier_ok(adapter->netdev)) {
+ adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+ } else if (!(adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)) {
+ adapter->flags |= IGC_FLAG_NEED_LINK_UPDATE;
+ adapter->link_check_timeout = jiffies;
+ }
+ }
+
+ return link_active;
+}
+
+/**
+ * igc_watchdog - Timer Call-back
+ * @data: pointer to adapter cast into an unsigned long
+ */
+static void igc_watchdog(struct timer_list *t)
+{
+ struct igc_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+ /* Do the rest outside of interrupt context */
+ schedule_work(&adapter->watchdog_task);
+}
+
+static void igc_watchdog_task(struct work_struct *work)
+{
+ struct igc_adapter *adapter = container_of(work,
+ struct igc_adapter,
+ watchdog_task);
+ struct net_device *netdev = adapter->netdev;
+ struct igc_hw *hw = &adapter->hw;
+ struct igc_phy_info *phy = &hw->phy;
+ u16 phy_data, retry_count = 20;
+ u32 connsw;
+ u32 link;
+ int i;
+
+ link = igc_has_link(adapter);
+
+ if (adapter->flags & IGC_FLAG_NEED_LINK_UPDATE) {
+ if (time_after(jiffies, (adapter->link_check_timeout + HZ)))
+ adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+ else
+ link = false;
+ }
+
+ /* Force link down if we have fiber to swap to */
+ if (adapter->flags & IGC_FLAG_MAS_ENABLE) {
+ if (hw->phy.media_type == igc_media_type_copper) {
+ connsw = rd32(IGC_CONNSW);
+ if (!(connsw & IGC_CONNSW_AUTOSENSE_EN))
+ link = 0;
+ }
+ }
+ if (link) {
+ if (!netif_carrier_ok(netdev)) {
+ u32 ctrl;
+
+ hw->mac.ops.get_speed_and_duplex(hw,
+ &adapter->link_speed,
+ &adapter->link_duplex);
+
+ ctrl = rd32(IGC_CTRL);
+ /* Link status message must follow this format */
+ netdev_info(netdev,
+ "igc: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
+ netdev->name,
+ adapter->link_speed,
+ adapter->link_duplex == FULL_DUPLEX ?
+ "Full" : "Half",
+ (ctrl & IGC_CTRL_TFCE) &&
+ (ctrl & IGC_CTRL_RFCE) ? "RX/TX" :
+ (ctrl & IGC_CTRL_RFCE) ? "RX" :
+ (ctrl & IGC_CTRL_TFCE) ? "TX" : "None");
+
+ /* check if SmartSpeed worked */
+ igc_check_downshift(hw);
+ if (phy->speed_downgraded)
+ netdev_warn(netdev, "Link Speed was downgraded by SmartSpeed\n");
+
+ /* adjust timeout factor according to speed/duplex */
+ adapter->tx_timeout_factor = 1;
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ adapter->tx_timeout_factor = 14;
+ break;
+ case SPEED_100:
+ /* maybe add some timeout factor ? */
+ break;
+ }
+
+ if (adapter->link_speed != SPEED_1000)
+ goto no_wait;
+
+ /* wait for Remote receiver status OK */
+retry_read_status:
+ if (!igc_read_phy_reg(hw, PHY_1000T_STATUS,
+ &phy_data)) {
+ if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) &&
+ retry_count) {
+ msleep(100);
+ retry_count--;
+ goto retry_read_status;
+ } else if (!retry_count) {
+ dev_err(&adapter->pdev->dev, "exceed max 2 second\n");
+ }
+ } else {
+ dev_err(&adapter->pdev->dev, "read 1000Base-T Status Reg\n");
+ }
+no_wait:
+ netif_carrier_on(netdev);
+
+ /* link state has changed, schedule phy info update */
+ if (!test_bit(__IGC_DOWN, &adapter->state))
+ mod_timer(&adapter->phy_info_timer,
+ round_jiffies(jiffies + 2 * HZ));
+ }
+ } else {
+ if (netif_carrier_ok(netdev)) {
+ adapter->link_speed = 0;
+ adapter->link_duplex = 0;
+
+ /* Links status message must follow this format */
+ netdev_info(netdev, "igc: %s NIC Link is Down\n",
+ netdev->name);
+ netif_carrier_off(netdev);
+
+ /* link state has changed, schedule phy info update */
+ if (!test_bit(__IGC_DOWN, &adapter->state))
+ mod_timer(&adapter->phy_info_timer,
+ round_jiffies(jiffies + 2 * HZ));
+
+ /* link is down, time to check for alternate media */
+ if (adapter->flags & IGC_FLAG_MAS_ENABLE) {
+ if (adapter->flags & IGC_FLAG_MEDIA_RESET) {
+ schedule_work(&adapter->reset_task);
+ /* return immediately */
+ return;
+ }
+ }
+
+ /* also check for alternate media here */
+ } else if (!netif_carrier_ok(netdev) &&
+ (adapter->flags & IGC_FLAG_MAS_ENABLE)) {
+ if (adapter->flags & IGC_FLAG_MEDIA_RESET) {
+ schedule_work(&adapter->reset_task);
+ /* return immediately */
+ return;
+ }
+ }
+ }
+
+ spin_lock(&adapter->stats64_lock);
+ igc_update_stats(adapter);
+ spin_unlock(&adapter->stats64_lock);
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+ if (!netif_carrier_ok(netdev)) {
+ /* We've lost link, so the controller stops DMA,
+ * but we've got queued Tx work that's never going
+ * to get done, so reset controller to flush Tx.
+ * (Do the reset outside of interrupt context).
+ */
+ if (igc_desc_unused(tx_ring) + 1 < tx_ring->count) {
+ adapter->tx_timeout_count++;
+ schedule_work(&adapter->reset_task);
+ /* return immediately since reset is imminent */
+ return;
+ }
+ }
+
+ /* Force detection of hung controller every watchdog period */
+ set_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags);
+ }
+
+ /* Cause software interrupt to ensure Rx ring is cleaned */
+ if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+ u32 eics = 0;
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ eics |= adapter->q_vector[i]->eims_value;
+ wr32(IGC_EICS, eics);
+ } else {
+ wr32(IGC_ICS, IGC_ICS_RXDMT0);
+ }
+
+ /* Reset the timer */
+ if (!test_bit(__IGC_DOWN, &adapter->state)) {
+ if (adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)
+ mod_timer(&adapter->watchdog_timer,
+ round_jiffies(jiffies + HZ));
+ else
+ mod_timer(&adapter->watchdog_timer,
+ round_jiffies(jiffies + 2 * HZ));
+ }
+}
+
+/**
+ * igc_update_ring_itr - update the dynamic ITR value based on packet size
+ * @q_vector: pointer to q_vector
+ *
+ * Stores a new ITR value based on strictly on packet size. This
+ * algorithm is less sophisticated than that used in igc_update_itr,
+ * due to the difficulty of synchronizing statistics across multiple
+ * receive rings. The divisors and thresholds used by this function
+ * were determined based on theoretical maximum wire speed and testing
+ * data, in order to minimize response time while increasing bulk
+ * throughput.
+ * NOTE: This function is called only when operating in a multiqueue
+ * receive environment.
+ */
+static void igc_update_ring_itr(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ int new_val = q_vector->itr_val;
+ int avg_wire_size = 0;
+ unsigned int packets;
+
+ /* For non-gigabit speeds, just fix the interrupt rate at 4000
+ * ints/sec - ITR timer value of 120 ticks.
+ */
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ case SPEED_100:
+ new_val = IGC_4K_ITR;
+ goto set_itr_val;
+ default:
+ break;
+ }
+
+ packets = q_vector->rx.total_packets;
+ if (packets)
+ avg_wire_size = q_vector->rx.total_bytes / packets;
+
+ packets = q_vector->tx.total_packets;
+ if (packets)
+ avg_wire_size = max_t(u32, avg_wire_size,
+ q_vector->tx.total_bytes / packets);
+
+ /* if avg_wire_size isn't set no work was done */
+ if (!avg_wire_size)
+ goto clear_counts;
+
+ /* Add 24 bytes to size to account for CRC, preamble, and gap */
+ avg_wire_size += 24;
+
+ /* Don't starve jumbo frames */
+ avg_wire_size = min(avg_wire_size, 3000);
+
+ /* Give a little boost to mid-size frames */
+ if (avg_wire_size > 300 && avg_wire_size < 1200)
+ new_val = avg_wire_size / 3;
+ else
+ new_val = avg_wire_size / 2;
+
+ /* conservative mode (itr 3) eliminates the lowest_latency setting */
+ if (new_val < IGC_20K_ITR &&
+ ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+ (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+ new_val = IGC_20K_ITR;
+
+set_itr_val:
+ if (new_val != q_vector->itr_val) {
+ q_vector->itr_val = new_val;
+ q_vector->set_itr = 1;
+ }
+clear_counts:
+ q_vector->rx.total_bytes = 0;
+ q_vector->rx.total_packets = 0;
+ q_vector->tx.total_bytes = 0;
+ q_vector->tx.total_packets = 0;
+}
+
+/**
+ * igc_update_itr - update the dynamic ITR value based on statistics
+ * @q_vector: pointer to q_vector
+ * @ring_container: ring info to update the itr for
+ *
+ * Stores a new ITR value based on packets and byte
+ * counts during the last interrupt. The advantage of per interrupt
+ * computation is faster updates and more accurate ITR for the current
+ * traffic pattern. Constants in this function were computed
+ * based on theoretical maximum wire speed and thresholds were set based
+ * on testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ * NOTE: These calculations are only valid when operating in a single-
+ * queue environment.
+ */
+static void igc_update_itr(struct igc_q_vector *q_vector,
+ struct igc_ring_container *ring_container)
+{
+ unsigned int packets = ring_container->total_packets;
+ unsigned int bytes = ring_container->total_bytes;
+ u8 itrval = ring_container->itr;
+
+ /* no packets, exit with status unchanged */
+ if (packets == 0)
+ return;
+
+ switch (itrval) {
+ case lowest_latency:
+ /* handle TSO and jumbo frames */
+ if (bytes / packets > 8000)
+ itrval = bulk_latency;
+ else if ((packets < 5) && (bytes > 512))
+ itrval = low_latency;
+ break;
+ case low_latency: /* 50 usec aka 20000 ints/s */
+ if (bytes > 10000) {
+ /* this if handles the TSO accounting */
+ if (bytes / packets > 8000)
+ itrval = bulk_latency;
+ else if ((packets < 10) || ((bytes / packets) > 1200))
+ itrval = bulk_latency;
+ else if ((packets > 35))
+ itrval = lowest_latency;
+ } else if (bytes / packets > 2000) {
+ itrval = bulk_latency;
+ } else if (packets <= 2 && bytes < 512) {
+ itrval = lowest_latency;
+ }
+ break;
+ case bulk_latency: /* 250 usec aka 4000 ints/s */
+ if (bytes > 25000) {
+ if (packets > 35)
+ itrval = low_latency;
+ } else if (bytes < 1500) {
+ itrval = low_latency;
+ }
+ break;
+ }
+
+ /* clear work counters since we have the values we need */
+ ring_container->total_bytes = 0;
+ ring_container->total_packets = 0;
+
+ /* write updated itr to ring container */
+ ring_container->itr = itrval;
+}
+
+/**
+ * igc_intr_msi - Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a network interface device structure
+ */
+static irqreturn_t igc_intr_msi(int irq, void *data)
+{
+ struct igc_adapter *adapter = data;
+ struct igc_q_vector *q_vector = adapter->q_vector[0];
+ struct igc_hw *hw = &adapter->hw;
+ /* read ICR disables interrupts using IAM */
+ u32 icr = rd32(IGC_ICR);
+
+ igc_write_itr(q_vector);
+
+ if (icr & IGC_ICR_DRSTA)
+ schedule_work(&adapter->reset_task);
+
+ if (icr & IGC_ICR_DOUTSYNC) {
+ /* HW is reporting DMA is out of sync */
+ adapter->stats.doosync++;
+ }
+
+ if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) {
+ hw->mac.get_link_status = 1;
+ if (!test_bit(__IGC_DOWN, &adapter->state))
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ }
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * igc_intr - Legacy Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a network interface device structure
+ */
+static irqreturn_t igc_intr(int irq, void *data)
+{
+ struct igc_adapter *adapter = data;
+ struct igc_q_vector *q_vector = adapter->q_vector[0];
+ struct igc_hw *hw = &adapter->hw;
+ /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No
+ * need for the IMC write
+ */
+ u32 icr = rd32(IGC_ICR);
+
+ /* IMS will not auto-mask if INT_ASSERTED is not set, and if it is
+ * not set, then the adapter didn't send an interrupt
+ */
+ if (!(icr & IGC_ICR_INT_ASSERTED))
+ return IRQ_NONE;
+
+ igc_write_itr(q_vector);
+
+ if (icr & IGC_ICR_DRSTA)
+ schedule_work(&adapter->reset_task);
+
+ if (icr & IGC_ICR_DOUTSYNC) {
+ /* HW is reporting DMA is out of sync */
+ adapter->stats.doosync++;
+ }
+
+ if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) {
+ hw->mac.get_link_status = 1;
+ /* guard against interrupt when we're going down */
+ if (!test_bit(__IGC_DOWN, &adapter->state))
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
+ }
+
+ napi_schedule(&q_vector->napi);
+
+ return IRQ_HANDLED;
+}
+
+static void igc_set_itr(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ u32 new_itr = q_vector->itr_val;
+ u8 current_itr = 0;
+
+ /* for non-gigabit speeds, just fix the interrupt rate at 4000 */
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ case SPEED_100:
+ current_itr = 0;
+ new_itr = IGC_4K_ITR;
+ goto set_itr_now;
+ default:
+ break;
+ }
+
+ igc_update_itr(q_vector, &q_vector->tx);
+ igc_update_itr(q_vector, &q_vector->rx);
+
+ current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
+
+ /* conservative mode (itr 3) eliminates the lowest_latency setting */
+ if (current_itr == lowest_latency &&
+ ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+ (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+ current_itr = low_latency;
+
+ switch (current_itr) {
+ /* counts and packets in update_itr are dependent on these numbers */
+ case lowest_latency:
+ new_itr = IGC_70K_ITR; /* 70,000 ints/sec */
+ break;
+ case low_latency:
+ new_itr = IGC_20K_ITR; /* 20,000 ints/sec */
+ break;
+ case bulk_latency:
+ new_itr = IGC_4K_ITR; /* 4,000 ints/sec */
+ break;
+ default:
+ break;
+ }
+
+set_itr_now:
+ if (new_itr != q_vector->itr_val) {
+ /* this attempts to bias the interrupt rate towards Bulk
+ * by adding intermediate steps when interrupt rate is
+ * increasing
+ */
+ new_itr = new_itr > q_vector->itr_val ?
+ max((new_itr * q_vector->itr_val) /
+ (new_itr + (q_vector->itr_val >> 2)),
+ new_itr) : new_itr;
+ /* Don't write the value here; it resets the adapter's
+ * internal timer, and causes us to delay far longer than
+ * we should between interrupts. Instead, we write the ITR
+ * value at the beginning of the next interrupt so the timing
+ * ends up being correct.
+ */
+ q_vector->itr_val = new_itr;
+ q_vector->set_itr = 1;
+ }
+}
+
+static void igc_ring_irq_enable(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ struct igc_hw *hw = &adapter->hw;
+
+ if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) ||
+ (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) {
+ if (adapter->num_q_vectors == 1)
+ igc_set_itr(q_vector);
+ else
+ igc_update_ring_itr(q_vector);
+ }
+
+ if (!test_bit(__IGC_DOWN, &adapter->state)) {
+ if (adapter->msix_entries)
+ wr32(IGC_EIMS, q_vector->eims_value);
+ else
+ igc_irq_enable(adapter);
+ }
+}
+
+/**
+ * igc_poll - NAPI Rx polling callback
+ * @napi: napi polling structure
+ * @budget: count of how many packets we should handle
+ */
+static int igc_poll(struct napi_struct *napi, int budget)
+{
+ struct igc_q_vector *q_vector = container_of(napi,
+ struct igc_q_vector,
+ napi);
+ bool clean_complete = true;
+ int work_done = 0;
+
+ if (q_vector->tx.ring)
+ clean_complete = igc_clean_tx_irq(q_vector, budget);
+
+ if (q_vector->rx.ring) {
+ int cleaned = igc_clean_rx_irq(q_vector, budget);
+
+ work_done += cleaned;
+ if (cleaned >= budget)
+ clean_complete = false;
+ }
+
+ /* If all work not completed, return budget and keep polling */
+ if (!clean_complete)
+ return budget;
+
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ igc_ring_irq_enable(q_vector);
+
+ return min(work_done, budget - 1);
+}
+
+/**
+ * igc_set_interrupt_capability - set MSI or MSI-X if supported
+ * @adapter: Pointer to adapter structure
+ *
+ * Attempt to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ */
+static void igc_set_interrupt_capability(struct igc_adapter *adapter,
+ bool msix)
+{
+ int numvecs, i;
+ int err;
+
+ if (!msix)
+ goto msi_only;
+ adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+ /* Number of supported queues. */
+ adapter->num_rx_queues = adapter->rss_queues;
+
+ adapter->num_tx_queues = adapter->rss_queues;
+
+ /* start with one vector for every Rx queue */
+ numvecs = adapter->num_rx_queues;
+
+ /* if Tx handler is separate add 1 for every Tx queue */
+ if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS))
+ numvecs += adapter->num_tx_queues;
+
+ /* store the number of vectors reserved for queues */
+ adapter->num_q_vectors = numvecs;
+
+ /* add 1 vector for link status interrupts */
+ numvecs++;
+
+ adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry),
+ GFP_KERNEL);
+
+ if (!adapter->msix_entries)
+ return;
+
+ /* populate entry values */
+ for (i = 0; i < numvecs; i++)
+ adapter->msix_entries[i].entry = i;
+
+ err = pci_enable_msix_range(adapter->pdev,
+ adapter->msix_entries,
+ numvecs,
+ numvecs);
+ if (err > 0)
+ return;
+
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+
+ igc_reset_interrupt_capability(adapter);
+
+msi_only:
+ adapter->flags &= ~IGC_FLAG_HAS_MSIX;
+
+ adapter->rss_queues = 1;
+ adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+ adapter->num_rx_queues = 1;
+ adapter->num_tx_queues = 1;
+ adapter->num_q_vectors = 1;
+ if (!pci_enable_msi(adapter->pdev))
+ adapter->flags |= IGC_FLAG_HAS_MSI;
+}
+
+static void igc_add_ring(struct igc_ring *ring,
+ struct igc_ring_container *head)
+{
+ head->ring = ring;
+ head->count++;
+}
+
+/**
+ * igc_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_count: q_vectors allocated on adapter, used for ring interleaving
+ * @v_idx: index of vector in adapter struct
+ * @txr_count: total number of Tx rings to allocate
+ * @txr_idx: index of first Tx ring to allocate
+ * @rxr_count: total number of Rx rings to allocate
+ * @rxr_idx: index of first Rx ring to allocate
+ *
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
+ */
+static int igc_alloc_q_vector(struct igc_adapter *adapter,
+ unsigned int v_count, unsigned int v_idx,
+ unsigned int txr_count, unsigned int txr_idx,
+ unsigned int rxr_count, unsigned int rxr_idx)
+{
+ struct igc_q_vector *q_vector;
+ struct igc_ring *ring;
+ int ring_count;
+
+ /* igc only supports 1 Tx and/or 1 Rx queue per vector */
+ if (txr_count > 1 || rxr_count > 1)
+ return -ENOMEM;
+
+ ring_count = txr_count + rxr_count;
+
+ /* allocate q_vector and rings */
+ q_vector = adapter->q_vector[v_idx];
+ if (!q_vector)
+ q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+ GFP_KERNEL);
+ else
+ memset(q_vector, 0, struct_size(q_vector, ring, ring_count));
+ if (!q_vector)
+ return -ENOMEM;
+
+ /* initialize NAPI */
+ netif_napi_add(adapter->netdev, &q_vector->napi,
+ igc_poll, 64);
+
+ /* tie q_vector and adapter together */
+ adapter->q_vector[v_idx] = q_vector;
+ q_vector->adapter = adapter;
+
+ /* initialize work limits */
+ q_vector->tx.work_limit = adapter->tx_work_limit;
+
+ /* initialize ITR configuration */
+ q_vector->itr_register = adapter->io_addr + IGC_EITR(0);
+ q_vector->itr_val = IGC_START_ITR;
+
+ /* initialize pointer to rings */
+ ring = q_vector->ring;
+
+ /* initialize ITR */
+ if (rxr_count) {
+ /* rx or rx/tx vector */
+ if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3)
+ q_vector->itr_val = adapter->rx_itr_setting;
+ } else {
+ /* tx only vector */
+ if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3)
+ q_vector->itr_val = adapter->tx_itr_setting;
+ }
+
+ if (txr_count) {
+ /* assign generic ring traits */
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
+
+ /* configure backlink on ring */
+ ring->q_vector = q_vector;
+
+ /* update q_vector Tx values */
+ igc_add_ring(ring, &q_vector->tx);
+
+ /* apply Tx specific ring traits */
+ ring->count = adapter->tx_ring_count;
+ ring->queue_index = txr_idx;
+
+ /* assign ring to adapter */
+ adapter->tx_ring[txr_idx] = ring;
+
+ /* push pointer to next ring */
+ ring++;
+ }
+
+ if (rxr_count) {
+ /* assign generic ring traits */
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
+
+ /* configure backlink on ring */
+ ring->q_vector = q_vector;
+
+ /* update q_vector Rx values */
+ igc_add_ring(ring, &q_vector->rx);
+
+ /* apply Rx specific ring traits */
+ ring->count = adapter->rx_ring_count;
+ ring->queue_index = rxr_idx;
+
+ /* assign ring to adapter */
+ adapter->rx_ring[rxr_idx] = ring;
+ }
+
+ return 0;
+}
+
+/**
+ * igc_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt. If allocation fails we
+ * return -ENOMEM.
+ */
+static int igc_alloc_q_vectors(struct igc_adapter *adapter)
+{
+ int rxr_remaining = adapter->num_rx_queues;
+ int txr_remaining = adapter->num_tx_queues;
+ int rxr_idx = 0, txr_idx = 0, v_idx = 0;
+ int q_vectors = adapter->num_q_vectors;
+ int err;
+
+ if (q_vectors >= (rxr_remaining + txr_remaining)) {
+ for (; rxr_remaining; v_idx++) {
+ err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+ 0, 0, 1, rxr_idx);
+
+ if (err)
+ goto err_out;
+
+ /* update counts and index */
+ rxr_remaining--;
+ rxr_idx++;
+ }
+ }
+
+ for (; v_idx < q_vectors; v_idx++) {
+ int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
+ int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+
+ err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+ tqpv, txr_idx, rqpv, rxr_idx);
+
+ if (err)
+ goto err_out;
+
+ /* update counts and index */
+ rxr_remaining -= rqpv;
+ txr_remaining -= tqpv;
+ rxr_idx++;
+ txr_idx++;
+ }
+
+ return 0;
+
+err_out:
+ adapter->num_tx_queues = 0;
+ adapter->num_rx_queues = 0;
+ adapter->num_q_vectors = 0;
+
+ while (v_idx--)
+ igc_free_q_vector(adapter, v_idx);
+
+ return -ENOMEM;
+}
+
+/**
+ * igc_cache_ring_register - Descriptor ring to register mapping
+ * @adapter: board private structure to initialize
+ *
+ * Once we know the feature-set enabled for the device, we'll cache
+ * the register offset the descriptor ring is assigned to.
+ */
+static void igc_cache_ring_register(struct igc_adapter *adapter)
+{
+ int i = 0, j = 0;
+
+ switch (adapter->hw.mac.type) {
+ case igc_i225:
+ /* Fall through */
+ default:
+ for (; i < adapter->num_rx_queues; i++)
+ adapter->rx_ring[i]->reg_idx = i;
+ for (; j < adapter->num_tx_queues; j++)
+ adapter->tx_ring[j]->reg_idx = j;
+ break;
+ }
+}
+
+/**
+ * igc_init_interrupt_scheme - initialize interrupts, allocate queues/vectors
+ * @adapter: Pointer to adapter structure
+ *
+ * This function initializes the interrupts and allocates all of the queues.
+ */
+static int igc_init_interrupt_scheme(struct igc_adapter *adapter, bool msix)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ int err = 0;
+
+ igc_set_interrupt_capability(adapter, msix);
+
+ err = igc_alloc_q_vectors(adapter);
+ if (err) {
+ dev_err(&pdev->dev, "Unable to allocate memory for vectors\n");
+ goto err_alloc_q_vectors;
+ }
+
+ igc_cache_ring_register(adapter);
+
+ return 0;
+
+err_alloc_q_vectors:
+ igc_reset_interrupt_capability(adapter);
+ return err;
+}
+
+static void igc_free_irq(struct igc_adapter *adapter)
+{
+ if (adapter->msix_entries) {
+ int vector = 0, i;
+
+ free_irq(adapter->msix_entries[vector++].vector, adapter);
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ free_irq(adapter->msix_entries[vector++].vector,
+ adapter->q_vector[i]);
+ } else {
+ free_irq(adapter->pdev->irq, adapter);
+ }
+}
+
+/**
+ * igc_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ */
+static void igc_irq_disable(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ if (adapter->msix_entries) {
+ u32 regval = rd32(IGC_EIAM);
+
+ wr32(IGC_EIAM, regval & ~adapter->eims_enable_mask);
+ wr32(IGC_EIMC, adapter->eims_enable_mask);
+ regval = rd32(IGC_EIAC);
+ wr32(IGC_EIAC, regval & ~adapter->eims_enable_mask);
+ }
+
+ wr32(IGC_IAM, 0);
+ wr32(IGC_IMC, ~0);
+ wrfl();
+
+ if (adapter->msix_entries) {
+ int vector = 0, i;
+
+ synchronize_irq(adapter->msix_entries[vector++].vector);
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ synchronize_irq(adapter->msix_entries[vector++].vector);
+ } else {
+ synchronize_irq(adapter->pdev->irq);
+ }
+}
+
+/**
+ * igc_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ */
+static void igc_irq_enable(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ if (adapter->msix_entries) {
+ u32 ims = IGC_IMS_LSC | IGC_IMS_DOUTSYNC | IGC_IMS_DRSTA;
+ u32 regval = rd32(IGC_EIAC);
+
+ wr32(IGC_EIAC, regval | adapter->eims_enable_mask);
+ regval = rd32(IGC_EIAM);
+ wr32(IGC_EIAM, regval | adapter->eims_enable_mask);
+ wr32(IGC_EIMS, adapter->eims_enable_mask);
+ wr32(IGC_IMS, ims);
+ } else {
+ wr32(IGC_IMS, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+ wr32(IGC_IAM, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+ }
+}
+
+/**
+ * igc_request_irq - initialize interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * Attempts to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ */
+static int igc_request_irq(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
+ int err = 0;
+
+ if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+ err = igc_request_msix(adapter);
+ if (!err)
+ goto request_done;
+ /* fall back to MSI */
+ igc_free_all_tx_resources(adapter);
+ igc_free_all_rx_resources(adapter);
+
+ igc_clear_interrupt_scheme(adapter);
+ err = igc_init_interrupt_scheme(adapter, false);
+ if (err)
+ goto request_done;
+ igc_setup_all_tx_resources(adapter);
+ igc_setup_all_rx_resources(adapter);
+ igc_configure(adapter);
+ }
+
+ igc_assign_vector(adapter->q_vector[0], 0);
+
+ if (adapter->flags & IGC_FLAG_HAS_MSI) {
+ err = request_irq(pdev->irq, &igc_intr_msi, 0,
+ netdev->name, adapter);
+ if (!err)
+ goto request_done;
+
+ /* fall back to legacy interrupts */
+ igc_reset_interrupt_capability(adapter);
+ adapter->flags &= ~IGC_FLAG_HAS_MSI;
+ }
+
+ err = request_irq(pdev->irq, &igc_intr, IRQF_SHARED,
+ netdev->name, adapter);
+
+ if (err)
+ dev_err(&pdev->dev, "Error %d getting interrupt\n",
+ err);
+
+request_done:
+ return err;
+}
+
+static void igc_write_itr(struct igc_q_vector *q_vector)
+{
+ u32 itr_val = q_vector->itr_val & IGC_QVECTOR_MASK;
+
+ if (!q_vector->set_itr)
+ return;
+
+ if (!itr_val)
+ itr_val = IGC_ITR_VAL_MASK;
+
+ itr_val |= IGC_EITR_CNT_IGNR;
+
+ writel(itr_val, q_vector->itr_register);
+ q_vector->set_itr = 0;
+}
+
+/**
+ * igc_open - Called when a network interface is made active
+ * @netdev: network interface device structure
+ *
+ * Returns 0 on success, negative value on failure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP). At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the watchdog timer is started,
+ * and the stack is notified that the interface is ready.
+ */
+static int __igc_open(struct net_device *netdev, bool resuming)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ int err = 0;
+ int i = 0;
+
+ /* disallow open during test */
+
+ if (test_bit(__IGC_TESTING, &adapter->state)) {
+ WARN_ON(resuming);
+ return -EBUSY;
+ }
+
+ netif_carrier_off(netdev);
+
+ /* allocate transmit descriptors */
+ err = igc_setup_all_tx_resources(adapter);
+ if (err)
+ goto err_setup_tx;
+
+ /* allocate receive descriptors */
+ err = igc_setup_all_rx_resources(adapter);
+ if (err)
+ goto err_setup_rx;
+
+ igc_power_up_link(adapter);
+
+ igc_configure(adapter);
+
+ err = igc_request_irq(adapter);
+ if (err)
+ goto err_req_irq;
+
+ /* Notify the stack of the actual queue counts. */
+ err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
+ if (err)
+ goto err_set_queues;
+
+ err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues);
+ if (err)
+ goto err_set_queues;
+
+ clear_bit(__IGC_DOWN, &adapter->state);
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ napi_enable(&adapter->q_vector[i]->napi);
+
+ /* Clear any pending interrupts. */
+ rd32(IGC_ICR);
+ igc_irq_enable(adapter);
+
+ netif_tx_start_all_queues(netdev);
+
+ /* start the watchdog. */
+ hw->mac.get_link_status = 1;
+ schedule_work(&adapter->watchdog_task);
+
+ return IGC_SUCCESS;
+
+err_set_queues:
+ igc_free_irq(adapter);
+err_req_irq:
+ igc_release_hw_control(adapter);
+ igc_power_down_link(adapter);
+ igc_free_all_rx_resources(adapter);
+err_setup_rx:
+ igc_free_all_tx_resources(adapter);
+err_setup_tx:
+ igc_reset(adapter);
+
+ return err;
+}
+
+static int igc_open(struct net_device *netdev)
+{
+ return __igc_open(netdev, false);
+}
+
+/**
+ * igc_close - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * Returns 0, this is not allowed to fail
+ *
+ * The close entry point is called when an interface is de-activated
+ * by the OS. The hardware is still under the driver's control, but
+ * needs to be disabled. A global MAC reset is issued to stop the
+ * hardware, and all transmit and receive resources are freed.
+ */
+static int __igc_close(struct net_device *netdev, bool suspending)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ WARN_ON(test_bit(__IGC_RESETTING, &adapter->state));
+
+ igc_down(adapter);
+
+ igc_release_hw_control(adapter);
+
+ igc_free_irq(adapter);
+
+ igc_free_all_tx_resources(adapter);
+ igc_free_all_rx_resources(adapter);
+
+ return 0;
+}
+
+static int igc_close(struct net_device *netdev)
+{
+ if (netif_device_present(netdev) || netdev->dismantle)
+ return __igc_close(netdev, false);
+ return 0;
+}
+
+static const struct net_device_ops igc_netdev_ops = {
+ .ndo_open = igc_open,
+ .ndo_stop = igc_close,
+ .ndo_start_xmit = igc_xmit_frame,
+ .ndo_set_mac_address = igc_set_mac,
+ .ndo_change_mtu = igc_change_mtu,
+ .ndo_get_stats = igc_get_stats,
+ .ndo_fix_features = igc_fix_features,
+ .ndo_set_features = igc_set_features,
+ .ndo_features_check = igc_features_check,
+};
+
+/* PCIe configuration access */
+void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+ struct igc_adapter *adapter = hw->back;
+
+ pci_read_config_word(adapter->pdev, reg, value);
+}
+
+void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+ struct igc_adapter *adapter = hw->back;
+
+ pci_write_config_word(adapter->pdev, reg, *value);
+}
+
+s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+ struct igc_adapter *adapter = hw->back;
+
+ if (!pci_is_pcie(adapter->pdev))
+ return -IGC_ERR_CONFIG;
+
+ pcie_capability_read_word(adapter->pdev, reg, value);
+
+ return IGC_SUCCESS;
+}
+
+s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+ struct igc_adapter *adapter = hw->back;
+
+ if (!pci_is_pcie(adapter->pdev))
+ return -IGC_ERR_CONFIG;
+
+ pcie_capability_write_word(adapter->pdev, reg, *value);
+
+ return IGC_SUCCESS;
+}
+
+u32 igc_rd32(struct igc_hw *hw, u32 reg)
+{
+ struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw);
+ u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
+ u32 value = 0;
+
+ if (IGC_REMOVED(hw_addr))
+ return ~value;
+
+ value = readl(&hw_addr[reg]);
+
+ /* reads should not return all F's */
+ if (!(~value) && (!reg || !(~readl(hw_addr)))) {
+ struct net_device *netdev = igc->netdev;
+
+ hw->hw_addr = NULL;
+ netif_device_detach(netdev);
+ netdev_err(netdev, "PCIe link lost, device now detached\n");
+ WARN(pci_device_is_present(igc->pdev),
+ "igc: Failed to read reg 0x%x!\n", reg);
+ }
+
+ return value;
+}
+
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ struct igc_mac_info *mac = &adapter->hw.mac;
+
+ mac->autoneg = 0;
+
+ /* Make sure dplx is at most 1 bit and lsb of speed is not set
+ * for the switch() below to work
+ */
+ if ((spd & 1) || (dplx & ~1))
+ goto err_inval;
+
+ switch (spd + dplx) {
+ case SPEED_10 + DUPLEX_HALF:
+ mac->forced_speed_duplex = ADVERTISE_10_HALF;
+ break;
+ case SPEED_10 + DUPLEX_FULL:
+ mac->forced_speed_duplex = ADVERTISE_10_FULL;
+ break;
+ case SPEED_100 + DUPLEX_HALF:
+ mac->forced_speed_duplex = ADVERTISE_100_HALF;
+ break;
+ case SPEED_100 + DUPLEX_FULL:
+ mac->forced_speed_duplex = ADVERTISE_100_FULL;
+ break;
+ case SPEED_1000 + DUPLEX_FULL:
+ mac->autoneg = 1;
+ adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL;
+ break;
+ case SPEED_1000 + DUPLEX_HALF: /* not supported */
+ goto err_inval;
+ case SPEED_2500 + DUPLEX_FULL:
+ mac->autoneg = 1;
+ adapter->hw.phy.autoneg_advertised = ADVERTISE_2500_FULL;
+ break;
+ case SPEED_2500 + DUPLEX_HALF: /* not supported */
+ default:
+ goto err_inval;
+ }
+
+ /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+ adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
+ return 0;
+
+err_inval:
+ dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n");
+ return -EINVAL;
+}
+
+/**
+ * igc_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in igc_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * igc_probe initializes an adapter identified by a pci_dev structure.
+ * The OS initialization, configuring the adapter private structure,
+ * and a hardware reset occur.
+ */
+static int igc_probe(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
+{
+ struct igc_adapter *adapter;
+ struct net_device *netdev;
+ struct igc_hw *hw;
+ const struct igc_info *ei = igc_info_tbl[ent->driver_data];
+ int err;
+
+ err = pci_enable_device_mem(pdev);
+ if (err)
+ return err;
+
+ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+ if (!err) {
+ err = dma_set_coherent_mask(&pdev->dev,
+ DMA_BIT_MASK(64));
+ } else {
+ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
+ err = dma_set_coherent_mask(&pdev->dev,
+ DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev, "igc: Wrong DMA config\n");
+ goto err_dma;
+ }
+ }
+ }
+
+ err = pci_request_selected_regions(pdev,
+ pci_select_bars(pdev,
+ IORESOURCE_MEM),
+ igc_driver_name);
+ if (err)
+ goto err_pci_reg;
+
+ pci_enable_pcie_error_reporting(pdev);
+
+ pci_set_master(pdev);
+
+ err = -ENOMEM;
+ netdev = alloc_etherdev_mq(sizeof(struct igc_adapter),
+ IGC_MAX_TX_QUEUES);
+
+ if (!netdev)
+ goto err_alloc_etherdev;
+
+ SET_NETDEV_DEV(netdev, &pdev->dev);
+
+ pci_set_drvdata(pdev, netdev);
+ adapter = netdev_priv(netdev);
+ adapter->netdev = netdev;
+ adapter->pdev = pdev;
+ hw = &adapter->hw;
+ hw->back = adapter;
+ adapter->port_num = hw->bus.func;
+ adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
+
+ err = pci_save_state(pdev);
+ if (err)
+ goto err_ioremap;
+
+ err = -EIO;
+ adapter->io_addr = ioremap(pci_resource_start(pdev, 0),
+ pci_resource_len(pdev, 0));
+ if (!adapter->io_addr)
+ goto err_ioremap;
+
+ /* hw->hw_addr can be zeroed, so use adapter->io_addr for unmap */
+ hw->hw_addr = adapter->io_addr;
+
+ netdev->netdev_ops = &igc_netdev_ops;
+ igc_set_ethtool_ops(netdev);
+ netdev->watchdog_timeo = 5 * HZ;
+
+ netdev->mem_start = pci_resource_start(pdev, 0);
+ netdev->mem_end = pci_resource_end(pdev, 0);
+
+ /* PCI config space info */
+ hw->vendor_id = pdev->vendor;
+ hw->device_id = pdev->device;
+ hw->revision_id = pdev->revision;
+ hw->subsystem_vendor_id = pdev->subsystem_vendor;
+ hw->subsystem_device_id = pdev->subsystem_device;
+
+ /* Copy the default MAC and PHY function pointers */
+ memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
+ memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
+
+ /* Initialize skew-specific constants */
+ err = ei->get_invariants(hw);
+ if (err)
+ goto err_sw_init;
+
+ /* Add supported features to the features list*/
+ netdev->features |= NETIF_F_HW_CSUM;
+
+ /* setup the private structure */
+ err = igc_sw_init(adapter);
+ if (err)
+ goto err_sw_init;
+
+ /* copy netdev features into list of user selectable features */
+ netdev->hw_features |= NETIF_F_NTUPLE;
+ netdev->hw_features |= netdev->features;
+
+ /* MTU range: 68 - 9216 */
+ netdev->min_mtu = ETH_MIN_MTU;
+ netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
+
+ /* before reading the NVM, reset the controller to put the device in a
+ * known good starting state
+ */
+ hw->mac.ops.reset_hw(hw);
+
+ if (igc_get_flash_presence_i225(hw)) {
+ if (hw->nvm.ops.validate(hw) < 0) {
+ dev_err(&pdev->dev,
+ "The NVM Checksum Is Not Valid\n");
+ err = -EIO;
+ goto err_eeprom;
+ }
+ }
+
+ if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) {
+ /* copy the MAC address out of the NVM */
+ if (hw->mac.ops.read_mac_addr(hw))
+ dev_err(&pdev->dev, "NVM Read Error\n");
+ }
+
+ memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len);
+
+ if (!is_valid_ether_addr(netdev->dev_addr)) {
+ dev_err(&pdev->dev, "Invalid MAC Address\n");
+ err = -EIO;
+ goto err_eeprom;
+ }
+
+ /* configure RXPBSIZE and TXPBSIZE */
+ wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT);
+ wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+
+ timer_setup(&adapter->watchdog_timer, igc_watchdog, 0);
+ timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0);
+
+ INIT_WORK(&adapter->reset_task, igc_reset_task);
+ INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
+
+ /* Initialize link properties that are user-changeable */
+ adapter->fc_autoneg = true;
+ hw->mac.autoneg = true;
+ hw->phy.autoneg_advertised = 0xaf;
+
+ hw->fc.requested_mode = igc_fc_default;
+ hw->fc.current_mode = igc_fc_default;
+
+ /* reset the hardware with the new settings */
+ igc_reset(adapter);
+
+ /* let the f/w know that the h/w is now under the control of the
+ * driver.
+ */
+ igc_get_hw_control(adapter);
+
+ strncpy(netdev->name, "eth%d", IFNAMSIZ);
+ err = register_netdev(netdev);
+ if (err)
+ goto err_register;
+
+ /* carrier off reporting is important to ethtool even BEFORE open */
+ netif_carrier_off(netdev);
+
+ /* Check if Media Autosense is enabled */
+ adapter->ei = *ei;
+
+ /* print pcie link status and MAC address */
+ pcie_print_link_status(pdev);
+ netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr);
+
+ return 0;
+
+err_register:
+ igc_release_hw_control(adapter);
+err_eeprom:
+ if (!igc_check_reset_block(hw))
+ igc_reset_phy(hw);
+err_sw_init:
+ igc_clear_interrupt_scheme(adapter);
+ iounmap(adapter->io_addr);
+err_ioremap:
+ free_netdev(netdev);
+err_alloc_etherdev:
+ pci_release_selected_regions(pdev,
+ pci_select_bars(pdev, IORESOURCE_MEM));
+err_pci_reg:
+err_dma:
+ pci_disable_device(pdev);
+ return err;
+}
+
+/**
+ * igc_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * igc_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device. This could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ */
+static void igc_remove(struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ set_bit(__IGC_DOWN, &adapter->state);
+
+ del_timer_sync(&adapter->watchdog_timer);
+ del_timer_sync(&adapter->phy_info_timer);
+
+ cancel_work_sync(&adapter->reset_task);
+ cancel_work_sync(&adapter->watchdog_task);
+
+ /* Release control of h/w to f/w. If f/w is AMT enabled, this
+ * would have already happened in close and is redundant.
+ */
+ igc_release_hw_control(adapter);
+ unregister_netdev(netdev);
+
+ igc_clear_interrupt_scheme(adapter);
+ pci_iounmap(pdev, adapter->io_addr);
+ pci_release_mem_regions(pdev);
+
+ kfree(adapter->mac_table);
+ kfree(adapter->shadow_vfta);
+ free_netdev(netdev);
+
+ pci_disable_pcie_error_reporting(pdev);
+
+ pci_disable_device(pdev);
+}
+
+static struct pci_driver igc_driver = {
+ .name = igc_driver_name,
+ .id_table = igc_pci_tbl,
+ .probe = igc_probe,
+ .remove = igc_remove,
+};
+
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+ const u32 max_rss_queues)
+{
+ /* Determine if we need to pair queues. */
+ /* If rss_queues > half of max_rss_queues, pair the queues in
+ * order to conserve interrupts due to limited supply.
+ */
+ if (adapter->rss_queues > (max_rss_queues / 2))
+ adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+ else
+ adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
+}
+
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
+{
+ unsigned int max_rss_queues;
+
+ /* Determine the maximum number of RSS queues supported. */
+ max_rss_queues = IGC_MAX_RX_QUEUES;
+
+ return max_rss_queues;
+}
+
+static void igc_init_queue_configuration(struct igc_adapter *adapter)
+{
+ u32 max_rss_queues;
+
+ max_rss_queues = igc_get_max_rss_queues(adapter);
+ adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
+
+ igc_set_flag_queue_pairs(adapter, max_rss_queues);
+}
+
+/**
+ * igc_sw_init - Initialize general software structures (struct igc_adapter)
+ * @adapter: board private structure to initialize
+ *
+ * igc_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ */
+static int igc_sw_init(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
+ struct igc_hw *hw = &adapter->hw;
+
+ int size = sizeof(struct igc_mac_addr) * hw->mac.rar_entry_count;
+
+ pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
+
+ /* set default ring sizes */
+ adapter->tx_ring_count = IGC_DEFAULT_TXD;
+ adapter->rx_ring_count = IGC_DEFAULT_RXD;
+
+ /* set default ITR values */
+ adapter->rx_itr_setting = IGC_DEFAULT_ITR;
+ adapter->tx_itr_setting = IGC_DEFAULT_ITR;
+
+ /* set default work limits */
+ adapter->tx_work_limit = IGC_DEFAULT_TX_WORK;
+
+ /* adjust max frame to be at least the size of a standard frame */
+ adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
+ VLAN_HLEN;
+ adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+
+ spin_lock_init(&adapter->nfc_lock);
+ spin_lock_init(&adapter->stats64_lock);
+ /* Assume MSI-X interrupts, will be checked during IRQ allocation */
+ adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+ adapter->mac_table = kzalloc(size, GFP_ATOMIC);
+ if (!adapter->mac_table)
+ return -ENOMEM;
+
+ igc_init_queue_configuration(adapter);
+
+ /* This call may decrease the number of queues */
+ if (igc_init_interrupt_scheme(adapter, true)) {
+ dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+ return -ENOMEM;
+ }
+
+ /* Explicitly disable IRQ since the NIC can be in any state. */
+ igc_irq_disable(adapter);
+
+ set_bit(__IGC_DOWN, &adapter->state);
+
+ return 0;
+}
+
+/**
+ * igc_reinit_queues - return error
+ * @adapter: pointer to adapter structure
+ */
+int igc_reinit_queues(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
+ int err = 0;
+
+ if (netif_running(netdev))
+ igc_close(netdev);
+
+ igc_reset_interrupt_capability(adapter);
+
+ if (igc_init_interrupt_scheme(adapter, true)) {
+ dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+ return -ENOMEM;
+ }
+
+ if (netif_running(netdev))
+ err = igc_open(netdev);
+
+ return err;
+}
+
+/**
+ * igc_get_hw_dev - return device
+ * @hw: pointer to hardware structure
+ *
+ * used by hardware layer to print debugging information
+ */
+struct net_device *igc_get_hw_dev(struct igc_hw *hw)
+{
+ struct igc_adapter *adapter = hw->back;
+
+ return adapter->netdev;
+}
+
+/**
+ * igc_init_module - Driver Registration Routine
+ *
+ * igc_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ */
+static int __init igc_init_module(void)
+{
+ int ret;
+
+ pr_info("%s - version %s\n",
+ igc_driver_string, igc_driver_version);
+
+ pr_info("%s\n", igc_copyright);
+
+ ret = pci_register_driver(&igc_driver);
+ return ret;
+}
+
+module_init(igc_init_module);
+
+/**
+ * igc_exit_module - Driver Exit Cleanup Routine
+ *
+ * igc_exit_module is called just before the driver is removed
+ * from memory.
+ */
+static void __exit igc_exit_module(void)
+{
+ pci_unregister_driver(&igc_driver);
+}
+
+module_exit(igc_exit_module);
+/* igc_main.c */
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c
new file mode 100644
index 0000000..58f81ab
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include "igc_mac.h"
+#include "igc_nvm.h"
+
+/**
+ * igc_poll_eerd_eewr_done - Poll for EEPROM read/write completion
+ * @hw: pointer to the HW structure
+ * @ee_reg: EEPROM flag for polling
+ *
+ * Polls the EEPROM status bit for either read or write completion based
+ * upon the value of 'ee_reg'.
+ */
+static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg)
+{
+ s32 ret_val = -IGC_ERR_NVM;
+ u32 attempts = 100000;
+ u32 i, reg = 0;
+
+ for (i = 0; i < attempts; i++) {
+ if (ee_reg == IGC_NVM_POLL_READ)
+ reg = rd32(IGC_EERD);
+ else
+ reg = rd32(IGC_EEWR);
+
+ if (reg & IGC_NVM_RW_REG_DONE) {
+ ret_val = 0;
+ break;
+ }
+
+ udelay(5);
+ }
+
+ return ret_val;
+}
+
+/**
+ * igc_acquire_nvm - Generic request for access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Set the EEPROM access request bit and wait for EEPROM access grant bit.
+ * Return successful if access grant bit set, else clear the request for
+ * EEPROM access and return -IGC_ERR_NVM (-1).
+ */
+s32 igc_acquire_nvm(struct igc_hw *hw)
+{
+ s32 timeout = IGC_NVM_GRANT_ATTEMPTS;
+ u32 eecd = rd32(IGC_EECD);
+ s32 ret_val = 0;
+
+ wr32(IGC_EECD, eecd | IGC_EECD_REQ);
+ eecd = rd32(IGC_EECD);
+
+ while (timeout) {
+ if (eecd & IGC_EECD_GNT)
+ break;
+ udelay(5);
+ eecd = rd32(IGC_EECD);
+ timeout--;
+ }
+
+ if (!timeout) {
+ eecd &= ~IGC_EECD_REQ;
+ wr32(IGC_EECD, eecd);
+ hw_dbg("Could not acquire NVM grant\n");
+ ret_val = -IGC_ERR_NVM;
+ }
+
+ return ret_val;
+}
+
+/**
+ * igc_release_nvm - Release exclusive access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Stop any current commands to the EEPROM and clear the EEPROM request bit.
+ */
+void igc_release_nvm(struct igc_hw *hw)
+{
+ u32 eecd;
+
+ eecd = rd32(IGC_EECD);
+ eecd &= ~IGC_EECD_REQ;
+ wr32(IGC_EECD, eecd);
+}
+
+/**
+ * igc_read_nvm_eerd - Reads EEPROM using EERD register
+ * @hw: pointer to the HW structure
+ * @offset: offset of word in the EEPROM to read
+ * @words: number of words to read
+ * @data: word read from the EEPROM
+ *
+ * Reads a 16 bit word from the EEPROM using the EERD register.
+ */
+s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data)
+{
+ struct igc_nvm_info *nvm = &hw->nvm;
+ u32 i, eerd = 0;
+ s32 ret_val = 0;
+
+ /* A check for invalid values: offset too large, too many words,
+ * and not enough words.
+ */
+ if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) ||
+ words == 0) {
+ hw_dbg("nvm parameter(s) out of bounds\n");
+ ret_val = -IGC_ERR_NVM;
+ goto out;
+ }
+
+ for (i = 0; i < words; i++) {
+ eerd = ((offset + i) << IGC_NVM_RW_ADDR_SHIFT) +
+ IGC_NVM_RW_REG_START;
+
+ wr32(IGC_EERD, eerd);
+ ret_val = igc_poll_eerd_eewr_done(hw, IGC_NVM_POLL_READ);
+ if (ret_val)
+ break;
+
+ data[i] = (rd32(IGC_EERD) >> IGC_NVM_RW_REG_DATA);
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_read_mac_addr - Read device MAC address
+ * @hw: pointer to the HW structure
+ */
+s32 igc_read_mac_addr(struct igc_hw *hw)
+{
+ u32 rar_high;
+ u32 rar_low;
+ u16 i;
+
+ rar_high = rd32(IGC_RAH(0));
+ rar_low = rd32(IGC_RAL(0));
+
+ for (i = 0; i < IGC_RAL_MAC_ADDR_LEN; i++)
+ hw->mac.perm_addr[i] = (u8)(rar_low >> (i * 8));
+
+ for (i = 0; i < IGC_RAH_MAC_ADDR_LEN; i++)
+ hw->mac.perm_addr[i + 4] = (u8)(rar_high >> (i * 8));
+
+ for (i = 0; i < ETH_ALEN; i++)
+ hw->mac.addr[i] = hw->mac.perm_addr[i];
+
+ return 0;
+}
+
+/**
+ * igc_validate_nvm_checksum - Validate EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Calculates the EEPROM checksum by reading/adding each word of the EEPROM
+ * and then verifies that the sum of the EEPROM is equal to 0xBABA.
+ */
+s32 igc_validate_nvm_checksum(struct igc_hw *hw)
+{
+ u16 checksum = 0;
+ u16 i, nvm_data;
+ s32 ret_val = 0;
+
+ for (i = 0; i < (NVM_CHECKSUM_REG + 1); i++) {
+ ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
+ if (ret_val) {
+ hw_dbg("NVM Read Error\n");
+ goto out;
+ }
+ checksum += nvm_data;
+ }
+
+ if (checksum != (u16)NVM_SUM) {
+ hw_dbg("NVM Checksum Invalid\n");
+ ret_val = -IGC_ERR_NVM;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_update_nvm_checksum - Update EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Updates the EEPROM checksum by reading/adding each word of the EEPROM
+ * up to the checksum. Then calculates the EEPROM checksum and writes the
+ * value to the EEPROM.
+ */
+s32 igc_update_nvm_checksum(struct igc_hw *hw)
+{
+ u16 checksum = 0;
+ u16 i, nvm_data;
+ s32 ret_val;
+
+ for (i = 0; i < NVM_CHECKSUM_REG; i++) {
+ ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
+ if (ret_val) {
+ hw_dbg("NVM Read Error while updating checksum.\n");
+ goto out;
+ }
+ checksum += nvm_data;
+ }
+ checksum = (u16)NVM_SUM - checksum;
+ ret_val = hw->nvm.ops.write(hw, NVM_CHECKSUM_REG, 1, &checksum);
+ if (ret_val)
+ hw_dbg("NVM Write Error while updating checksum.\n");
+
+out:
+ return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h
new file mode 100644
index 0000000..f9fc2e9
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_nvm.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_NVM_H_
+#define _IGC_NVM_H_
+
+s32 igc_acquire_nvm(struct igc_hw *hw);
+void igc_release_nvm(struct igc_hw *hw);
+s32 igc_read_mac_addr(struct igc_hw *hw);
+s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data);
+s32 igc_validate_nvm_checksum(struct igc_hw *hw);
+s32 igc_update_nvm_checksum(struct igc_hw *hw);
+
+#endif
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
new file mode 100644
index 0000000..f4b05af
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Intel Corporation */
+
+#include "igc_phy.h"
+
+/**
+ * igc_check_reset_block - Check if PHY reset is blocked
+ * @hw: pointer to the HW structure
+ *
+ * Read the PHY management control register and check whether a PHY reset
+ * is blocked. If a reset is not blocked return 0, otherwise
+ * return IGC_ERR_BLK_PHY_RESET (12).
+ */
+s32 igc_check_reset_block(struct igc_hw *hw)
+{
+ u32 manc;
+
+ manc = rd32(IGC_MANC);
+
+ return (manc & IGC_MANC_BLK_PHY_RST_ON_IDE) ?
+ IGC_ERR_BLK_PHY_RESET : 0;
+}
+
+/**
+ * igc_get_phy_id - Retrieve the PHY ID and revision
+ * @hw: pointer to the HW structure
+ *
+ * Reads the PHY registers and stores the PHY ID and possibly the PHY
+ * revision in the hardware structure.
+ */
+s32 igc_get_phy_id(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ s32 ret_val = 0;
+ u16 phy_id;
+
+ ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id);
+ if (ret_val)
+ goto out;
+
+ phy->id = (u32)(phy_id << 16);
+ usleep_range(200, 500);
+ ret_val = phy->ops.read_reg(hw, PHY_ID2, &phy_id);
+ if (ret_val)
+ goto out;
+
+ phy->id |= (u32)(phy_id & PHY_REVISION_MASK);
+ phy->revision = (u32)(phy_id & ~PHY_REVISION_MASK);
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_phy_has_link - Polls PHY for link
+ * @hw: pointer to the HW structure
+ * @iterations: number of times to poll for link
+ * @usec_interval: delay between polling attempts
+ * @success: pointer to whether polling was successful or not
+ *
+ * Polls the PHY status register for link, 'iterations' number of times.
+ */
+s32 igc_phy_has_link(struct igc_hw *hw, u32 iterations,
+ u32 usec_interval, bool *success)
+{
+ u16 i, phy_status;
+ s32 ret_val = 0;
+
+ for (i = 0; i < iterations; i++) {
+ /* Some PHYs require the PHY_STATUS register to be read
+ * twice due to the link bit being sticky. No harm doing
+ * it across the board.
+ */
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+ if (ret_val && usec_interval > 0) {
+ /* If the first read fails, another entity may have
+ * ownership of the resources, wait and try again to
+ * see if they have relinquished the resources yet.
+ */
+ if (usec_interval >= 1000)
+ mdelay(usec_interval / 1000);
+ else
+ udelay(usec_interval);
+ }
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+ if (ret_val)
+ break;
+ if (phy_status & MII_SR_LINK_STATUS)
+ break;
+ if (usec_interval >= 1000)
+ mdelay(usec_interval / 1000);
+ else
+ udelay(usec_interval);
+ }
+
+ *success = (i < iterations) ? true : false;
+
+ return ret_val;
+}
+
+/**
+ * igc_power_up_phy_copper - Restore copper link in case of PHY power down
+ * @hw: pointer to the HW structure
+ *
+ * In the case of a PHY power down to save power, or to turn off link during a
+ * driver unload, restore the link to previous settings.
+ */
+void igc_power_up_phy_copper(struct igc_hw *hw)
+{
+ u16 mii_reg = 0;
+
+ /* The PHY will retain its settings across a power down/up cycle */
+ hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
+ mii_reg &= ~MII_CR_POWER_DOWN;
+ hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
+}
+
+/**
+ * igc_power_down_phy_copper - Power down copper PHY
+ * @hw: pointer to the HW structure
+ *
+ * Power down PHY to save power when interface is down and wake on lan
+ * is not enabled.
+ */
+void igc_power_down_phy_copper(struct igc_hw *hw)
+{
+ u16 mii_reg = 0;
+
+ /* The PHY will retain its settings across a power down/up cycle */
+ hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
+ mii_reg |= MII_CR_POWER_DOWN;
+
+ /* Temporary workaround - should be removed when PHY will implement
+ * IEEE registers as properly
+ */
+ /* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/
+ usleep_range(1000, 2000);
+}
+
+/**
+ * igc_check_downshift - Checks whether a downshift in speed occurred
+ * @hw: pointer to the HW structure
+ *
+ * Success returns 0, Failure returns 1
+ *
+ * A downshift is detected by querying the PHY link health.
+ */
+s32 igc_check_downshift(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ s32 ret_val;
+
+ switch (phy->type) {
+ case igc_phy_i225:
+ default:
+ /* speed downshift not supported */
+ phy->speed_downgraded = false;
+ ret_val = 0;
+ }
+
+ return ret_val;
+}
+
+/**
+ * igc_phy_hw_reset - PHY hardware reset
+ * @hw: pointer to the HW structure
+ *
+ * Verify the reset block is not blocking us from resetting. Acquire
+ * semaphore (if necessary) and read/set/write the device control reset
+ * bit in the PHY. Wait the appropriate delay time for the device to
+ * reset and release the semaphore (if necessary).
+ */
+s32 igc_phy_hw_reset(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ s32 ret_val;
+ u32 ctrl;
+
+ ret_val = igc_check_reset_block(hw);
+ if (ret_val) {
+ ret_val = 0;
+ goto out;
+ }
+
+ ret_val = phy->ops.acquire(hw);
+ if (ret_val)
+ goto out;
+
+ ctrl = rd32(IGC_CTRL);
+ wr32(IGC_CTRL, ctrl | IGC_CTRL_PHY_RST);
+ wrfl();
+
+ udelay(phy->reset_delay_us);
+
+ wr32(IGC_CTRL, ctrl);
+ wrfl();
+
+ usleep_range(1500, 2000);
+
+ phy->ops.release(hw);
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_phy_setup_autoneg - Configure PHY for auto-negotiation
+ * @hw: pointer to the HW structure
+ *
+ * Reads the MII auto-neg advertisement register and/or the 1000T control
+ * register and if the PHY is already setup for auto-negotiation, then
+ * return successful. Otherwise, setup advertisement and flow control to
+ * the appropriate values for the wanted auto-negotiation.
+ */
+static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ u16 aneg_multigbt_an_ctrl = 0;
+ u16 mii_1000t_ctrl_reg = 0;
+ u16 mii_autoneg_adv_reg;
+ s32 ret_val;
+
+ phy->autoneg_advertised &= phy->autoneg_mask;
+
+ /* Read the MII Auto-Neg Advertisement Register (Address 4). */
+ ret_val = phy->ops.read_reg(hw, PHY_AUTONEG_ADV, &mii_autoneg_adv_reg);
+ if (ret_val)
+ return ret_val;
+
+ if (phy->autoneg_mask & ADVERTISE_1000_FULL) {
+ /* Read the MII 1000Base-T Control Register (Address 9). */
+ ret_val = phy->ops.read_reg(hw, PHY_1000T_CTRL,
+ &mii_1000t_ctrl_reg);
+ if (ret_val)
+ return ret_val;
+ }
+
+ if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
+ hw->phy.id == I225_I_PHY_ID) {
+ /* Read the MULTI GBT AN Control Register - reg 7.32 */
+ ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+ MMD_DEVADDR_SHIFT) |
+ ANEG_MULTIGBT_AN_CTRL,
+ &aneg_multigbt_an_ctrl);
+
+ if (ret_val)
+ return ret_val;
+ }
+
+ /* Need to parse both autoneg_advertised and fc and set up
+ * the appropriate PHY registers. First we will parse for
+ * autoneg_advertised software override. Since we can advertise
+ * a plethora of combinations, we need to check each bit
+ * individually.
+ */
+
+ /* First we clear all the 10/100 mb speed bits in the Auto-Neg
+ * Advertisement Register (Address 4) and the 1000 mb speed bits in
+ * the 1000Base-T Control Register (Address 9).
+ */
+ mii_autoneg_adv_reg &= ~(NWAY_AR_100TX_FD_CAPS |
+ NWAY_AR_100TX_HD_CAPS |
+ NWAY_AR_10T_FD_CAPS |
+ NWAY_AR_10T_HD_CAPS);
+ mii_1000t_ctrl_reg &= ~(CR_1000T_HD_CAPS | CR_1000T_FD_CAPS);
+
+ hw_dbg("autoneg_advertised %x\n", phy->autoneg_advertised);
+
+ /* Do we want to advertise 10 Mb Half Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_10_HALF) {
+ hw_dbg("Advertise 10mb Half duplex\n");
+ mii_autoneg_adv_reg |= NWAY_AR_10T_HD_CAPS;
+ }
+
+ /* Do we want to advertise 10 Mb Full Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_10_FULL) {
+ hw_dbg("Advertise 10mb Full duplex\n");
+ mii_autoneg_adv_reg |= NWAY_AR_10T_FD_CAPS;
+ }
+
+ /* Do we want to advertise 100 Mb Half Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_100_HALF) {
+ hw_dbg("Advertise 100mb Half duplex\n");
+ mii_autoneg_adv_reg |= NWAY_AR_100TX_HD_CAPS;
+ }
+
+ /* Do we want to advertise 100 Mb Full Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_100_FULL) {
+ hw_dbg("Advertise 100mb Full duplex\n");
+ mii_autoneg_adv_reg |= NWAY_AR_100TX_FD_CAPS;
+ }
+
+ /* We do not allow the Phy to advertise 1000 Mb Half Duplex */
+ if (phy->autoneg_advertised & ADVERTISE_1000_HALF)
+ hw_dbg("Advertise 1000mb Half duplex request denied!\n");
+
+ /* Do we want to advertise 1000 Mb Full Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_1000_FULL) {
+ hw_dbg("Advertise 1000mb Full duplex\n");
+ mii_1000t_ctrl_reg |= CR_1000T_FD_CAPS;
+ }
+
+ /* We do not allow the Phy to advertise 2500 Mb Half Duplex */
+ if (phy->autoneg_advertised & ADVERTISE_2500_HALF)
+ hw_dbg("Advertise 2500mb Half duplex request denied!\n");
+
+ /* Do we want to advertise 2500 Mb Full Duplex? */
+ if (phy->autoneg_advertised & ADVERTISE_2500_FULL) {
+ hw_dbg("Advertise 2500mb Full duplex\n");
+ aneg_multigbt_an_ctrl |= CR_2500T_FD_CAPS;
+ } else {
+ aneg_multigbt_an_ctrl &= ~CR_2500T_FD_CAPS;
+ }
+
+ /* Check for a software override of the flow control settings, and
+ * setup the PHY advertisement registers accordingly. If
+ * auto-negotiation is enabled, then software will have to set the
+ * "PAUSE" bits to the correct value in the Auto-Negotiation
+ * Advertisement Register (PHY_AUTONEG_ADV) and re-start auto-
+ * negotiation.
+ *
+ * The possible values of the "fc" parameter are:
+ * 0: Flow control is completely disabled
+ * 1: Rx flow control is enabled (we can receive pause frames
+ * but not send pause frames).
+ * 2: Tx flow control is enabled (we can send pause frames
+ * but we do not support receiving pause frames).
+ * 3: Both Rx and Tx flow control (symmetric) are enabled.
+ * other: No software override. The flow control configuration
+ * in the EEPROM is used.
+ */
+ switch (hw->fc.current_mode) {
+ case igc_fc_none:
+ /* Flow control (Rx & Tx) is completely disabled by a
+ * software over-ride.
+ */
+ mii_autoneg_adv_reg &= ~(NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+ break;
+ case igc_fc_rx_pause:
+ /* Rx Flow control is enabled, and Tx Flow control is
+ * disabled, by a software over-ride.
+ *
+ * Since there really isn't a way to advertise that we are
+ * capable of Rx Pause ONLY, we will advertise that we
+ * support both symmetric and asymmetric Rx PAUSE. Later
+ * (in igc_config_fc_after_link_up) we will disable the
+ * hw's ability to send PAUSE frames.
+ */
+ mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+ break;
+ case igc_fc_tx_pause:
+ /* Tx Flow control is enabled, and Rx Flow control is
+ * disabled, by a software over-ride.
+ */
+ mii_autoneg_adv_reg |= NWAY_AR_ASM_DIR;
+ mii_autoneg_adv_reg &= ~NWAY_AR_PAUSE;
+ break;
+ case igc_fc_full:
+ /* Flow control (both Rx and Tx) is enabled by a software
+ * over-ride.
+ */
+ mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+ break;
+ default:
+ hw_dbg("Flow control param set incorrectly\n");
+ return -IGC_ERR_CONFIG;
+ }
+
+ ret_val = phy->ops.write_reg(hw, PHY_AUTONEG_ADV, mii_autoneg_adv_reg);
+ if (ret_val)
+ return ret_val;
+
+ hw_dbg("Auto-Neg Advertising %x\n", mii_autoneg_adv_reg);
+
+ if (phy->autoneg_mask & ADVERTISE_1000_FULL)
+ ret_val = phy->ops.write_reg(hw, PHY_1000T_CTRL,
+ mii_1000t_ctrl_reg);
+
+ if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
+ hw->phy.id == I225_I_PHY_ID)
+ ret_val = phy->ops.write_reg(hw,
+ (STANDARD_AN_REG_MASK <<
+ MMD_DEVADDR_SHIFT) |
+ ANEG_MULTIGBT_AN_CTRL,
+ aneg_multigbt_an_ctrl);
+
+ return ret_val;
+}
+
+/**
+ * igc_wait_autoneg - Wait for auto-neg completion
+ * @hw: pointer to the HW structure
+ *
+ * Waits for auto-negotiation to complete or for the auto-negotiation time
+ * limit to expire, which ever happens first.
+ */
+static s32 igc_wait_autoneg(struct igc_hw *hw)
+{
+ u16 i, phy_status;
+ s32 ret_val = 0;
+
+ /* Break after autoneg completes or PHY_AUTO_NEG_LIMIT expires. */
+ for (i = PHY_AUTO_NEG_LIMIT; i > 0; i--) {
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+ if (ret_val)
+ break;
+ ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+ if (ret_val)
+ break;
+ if (phy_status & MII_SR_AUTONEG_COMPLETE)
+ break;
+ msleep(100);
+ }
+
+ /* PHY_AUTO_NEG_TIME expiration doesn't guarantee auto-negotiation
+ * has completed.
+ */
+ return ret_val;
+}
+
+/**
+ * igc_copper_link_autoneg - Setup/Enable autoneg for copper link
+ * @hw: pointer to the HW structure
+ *
+ * Performs initial bounds checking on autoneg advertisement parameter, then
+ * configure to advertise the full capability. Setup the PHY to autoneg
+ * and restart the negotiation process between the link partner. If
+ * autoneg_wait_to_complete, then wait for autoneg to complete before exiting.
+ */
+static s32 igc_copper_link_autoneg(struct igc_hw *hw)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ u16 phy_ctrl;
+ s32 ret_val;
+
+ /* Perform some bounds checking on the autoneg advertisement
+ * parameter.
+ */
+ phy->autoneg_advertised &= phy->autoneg_mask;
+
+ /* If autoneg_advertised is zero, we assume it was not defaulted
+ * by the calling code so we set to advertise full capability.
+ */
+ if (phy->autoneg_advertised == 0)
+ phy->autoneg_advertised = phy->autoneg_mask;
+
+ hw_dbg("Reconfiguring auto-neg advertisement params\n");
+ ret_val = igc_phy_setup_autoneg(hw);
+ if (ret_val) {
+ hw_dbg("Error Setting up Auto-Negotiation\n");
+ goto out;
+ }
+ hw_dbg("Restarting Auto-Neg\n");
+
+ /* Restart auto-negotiation by setting the Auto Neg Enable bit and
+ * the Auto Neg Restart bit in the PHY control register.
+ */
+ ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl);
+ if (ret_val)
+ goto out;
+
+ phy_ctrl |= (MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG);
+ ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl);
+ if (ret_val)
+ goto out;
+
+ /* Does the user want to wait for Auto-Neg to complete here, or
+ * check at a later time (for example, callback routine).
+ */
+ if (phy->autoneg_wait_to_complete) {
+ ret_val = igc_wait_autoneg(hw);
+ if (ret_val) {
+ hw_dbg("Error while waiting for autoneg to complete\n");
+ goto out;
+ }
+ }
+
+ hw->mac.get_link_status = true;
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_setup_copper_link - Configure copper link settings
+ * @hw: pointer to the HW structure
+ *
+ * Calls the appropriate function to configure the link for auto-neg or forced
+ * speed and duplex. Then we check for link, once link is established calls
+ * to configure collision distance and flow control are called. If link is
+ * not established, we return -IGC_ERR_PHY (-2).
+ */
+s32 igc_setup_copper_link(struct igc_hw *hw)
+{
+ s32 ret_val = 0;
+ bool link;
+
+ if (hw->mac.autoneg) {
+ /* Setup autoneg and flow control advertisement and perform
+ * autonegotiation.
+ */
+ ret_val = igc_copper_link_autoneg(hw);
+ if (ret_val)
+ goto out;
+ } else {
+ /* PHY will be set to 10H, 10F, 100H or 100F
+ * depending on user settings.
+ */
+ hw_dbg("Forcing Speed and Duplex\n");
+ ret_val = hw->phy.ops.force_speed_duplex(hw);
+ if (ret_val) {
+ hw_dbg("Error Forcing Speed and Duplex\n");
+ goto out;
+ }
+ }
+
+ /* Check link status. Wait up to 100 microseconds for link to become
+ * valid.
+ */
+ ret_val = igc_phy_has_link(hw, COPPER_LINK_UP_LIMIT, 10, &link);
+ if (ret_val)
+ goto out;
+
+ if (link) {
+ hw_dbg("Valid link established!!!\n");
+ igc_config_collision_dist(hw);
+ ret_val = igc_config_fc_after_link_up(hw);
+ } else {
+ hw_dbg("Unable to establish link!!!\n");
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_read_phy_reg_mdic - Read MDI control register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to be read
+ * @data: pointer to the read data
+ *
+ * Reads the MDI control register in the PHY at offset and stores the
+ * information read to data.
+ */
+static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ u32 i, mdic = 0;
+ s32 ret_val = 0;
+
+ if (offset > MAX_PHY_REG_ADDRESS) {
+ hw_dbg("PHY Address %d is out of range\n", offset);
+ ret_val = -IGC_ERR_PARAM;
+ goto out;
+ }
+
+ /* Set up Op-code, Phy Address, and register offset in the MDI
+ * Control register. The MAC will take care of interfacing with the
+ * PHY to retrieve the desired data.
+ */
+ mdic = ((offset << IGC_MDIC_REG_SHIFT) |
+ (phy->addr << IGC_MDIC_PHY_SHIFT) |
+ (IGC_MDIC_OP_READ));
+
+ wr32(IGC_MDIC, mdic);
+
+ /* Poll the ready bit to see if the MDI read completed
+ * Increasing the time out as testing showed failures with
+ * the lower time out
+ */
+ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
+ usleep_range(500, 1000);
+ mdic = rd32(IGC_MDIC);
+ if (mdic & IGC_MDIC_READY)
+ break;
+ }
+ if (!(mdic & IGC_MDIC_READY)) {
+ hw_dbg("MDI Read did not complete\n");
+ ret_val = -IGC_ERR_PHY;
+ goto out;
+ }
+ if (mdic & IGC_MDIC_ERROR) {
+ hw_dbg("MDI Error\n");
+ ret_val = -IGC_ERR_PHY;
+ goto out;
+ }
+ *data = (u16)mdic;
+
+out:
+ return ret_val;
+}
+
+/**
+ * igc_write_phy_reg_mdic - Write MDI control register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to write to
+ * @data: data to write to register at offset
+ *
+ * Writes data to MDI control register in the PHY at offset.
+ */
+static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data)
+{
+ struct igc_phy_info *phy = &hw->phy;
+ u32 i, mdic = 0;
+ s32 ret_val = 0;
+
+ if (offset > MAX_PHY_REG_ADDRESS) {
+ hw_dbg("PHY Address %d is out of range\n", offset);
+ ret_val = -IGC_ERR_PARAM;
+ goto out;
+ }
+
+ /* Set up Op-code, Phy Address, and register offset in the MDI
+ * Control register. The MAC will take care of interfacing with the
+ * PHY to write the desired data.
+ */
+ mdic = (((u32)data) |
+ (offset << IGC_MDIC_REG_SHIFT) |
+ (phy->addr << IGC_MDIC_PHY_SHIFT) |
+ (IGC_MDIC_OP_WRITE));
+
+ wr32(IGC_MDIC, mdic);
+
+ /* Poll the ready bit to see if the MDI read completed
+ * Increasing the time out as testing showed failures with
+ * the lower time out
+ */
+ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
+ usleep_range(500, 1000);
+ mdic = rd32(IGC_MDIC);
+ if (mdic & IGC_MDIC_READY)
+ break;
+ }
+ if (!(mdic & IGC_MDIC_READY)) {
+ hw_dbg("MDI Write did not complete\n");
+ ret_val = -IGC_ERR_PHY;
+ goto out;
+ }
+ if (mdic & IGC_MDIC_ERROR) {
+ hw_dbg("MDI Error\n");
+ ret_val = -IGC_ERR_PHY;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * __igc_access_xmdio_reg - Read/write XMDIO register
+ * @hw: pointer to the HW structure
+ * @address: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: pointer to value to read/write from/to the XMDIO address
+ * @read: boolean flag to indicate read or write
+ */
+static s32 __igc_access_xmdio_reg(struct igc_hw *hw, u16 address,
+ u8 dev_addr, u16 *data, bool read)
+{
+ s32 ret_val;
+
+ ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, dev_addr);
+ if (ret_val)
+ return ret_val;
+
+ ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAAD, address);
+ if (ret_val)
+ return ret_val;
+
+ ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, IGC_MMDAC_FUNC_DATA |
+ dev_addr);
+ if (ret_val)
+ return ret_val;
+
+ if (read)
+ ret_val = hw->phy.ops.read_reg(hw, IGC_MMDAAD, data);
+ else
+ ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAAD, *data);
+ if (ret_val)
+ return ret_val;
+
+ /* Recalibrate the device back to 0 */
+ ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, 0);
+ if (ret_val)
+ return ret_val;
+
+ return ret_val;
+}
+
+/**
+ * igc_read_xmdio_reg - Read XMDIO register
+ * @hw: pointer to the HW structure
+ * @addr: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: value to be read from the EMI address
+ */
+static s32 igc_read_xmdio_reg(struct igc_hw *hw, u16 addr,
+ u8 dev_addr, u16 *data)
+{
+ return __igc_access_xmdio_reg(hw, addr, dev_addr, data, true);
+}
+
+/**
+ * igc_write_xmdio_reg - Write XMDIO register
+ * @hw: pointer to the HW structure
+ * @addr: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: value to be written to the XMDIO address
+ */
+static s32 igc_write_xmdio_reg(struct igc_hw *hw, u16 addr,
+ u8 dev_addr, u16 data)
+{
+ return __igc_access_xmdio_reg(hw, addr, dev_addr, &data, false);
+}
+
+/**
+ * igc_write_phy_reg_gpy - Write GPY PHY register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to write to
+ * @data: data to write at register offset
+ *
+ * Acquires semaphore, if necessary, then writes the data to PHY register
+ * at the offset. Release any acquired semaphores before exiting.
+ */
+s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data)
+{
+ u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+ s32 ret_val;
+
+ offset = offset & GPY_REG_MASK;
+
+ if (!dev_addr) {
+ ret_val = hw->phy.ops.acquire(hw);
+ if (ret_val)
+ return ret_val;
+ ret_val = igc_write_phy_reg_mdic(hw, offset, data);
+ if (ret_val)
+ return ret_val;
+ hw->phy.ops.release(hw);
+ } else {
+ ret_val = igc_write_xmdio_reg(hw, (u16)offset, dev_addr,
+ data);
+ }
+
+ return ret_val;
+}
+
+/**
+ * igc_read_phy_reg_gpy - Read GPY PHY register
+ * @hw: pointer to the HW structure
+ * @offset: lower half is register offset to read to
+ * upper half is MMD to use.
+ * @data: data to read at register offset
+ *
+ * Acquires semaphore, if necessary, then reads the data in the PHY register
+ * at the offset. Release any acquired semaphores before exiting.
+ */
+s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data)
+{
+ u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+ s32 ret_val;
+
+ offset = offset & GPY_REG_MASK;
+
+ if (!dev_addr) {
+ ret_val = hw->phy.ops.acquire(hw);
+ if (ret_val)
+ return ret_val;
+ ret_val = igc_read_phy_reg_mdic(hw, offset, data);
+ if (ret_val)
+ return ret_val;
+ hw->phy.ops.release(hw);
+ } else {
+ ret_val = igc_read_xmdio_reg(hw, (u16)offset, dev_addr,
+ data);
+ }
+
+ return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.h b/drivers/net/ethernet/intel/igc/igc_phy.h
new file mode 100644
index 0000000..25cba33
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_phy.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_PHY_H_
+#define _IGC_PHY_H_
+
+#include "igc_mac.h"
+
+s32 igc_check_reset_block(struct igc_hw *hw);
+s32 igc_phy_hw_reset(struct igc_hw *hw);
+s32 igc_get_phy_id(struct igc_hw *hw);
+s32 igc_phy_has_link(struct igc_hw *hw, u32 iterations,
+ u32 usec_interval, bool *success);
+s32 igc_check_downshift(struct igc_hw *hw);
+s32 igc_setup_copper_link(struct igc_hw *hw);
+void igc_power_up_phy_copper(struct igc_hw *hw);
+void igc_power_down_phy_copper(struct igc_hw *hw);
+s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data);
+s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data);
+
+#endif
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
new file mode 100644
index 0000000..50d7c04
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef _IGC_REGS_H_
+#define _IGC_REGS_H_
+
+/* General Register Descriptions */
+#define IGC_CTRL 0x00000 /* Device Control - RW */
+#define IGC_STATUS 0x00008 /* Device Status - RO */
+#define IGC_EECD 0x00010 /* EEPROM/Flash Control - RW */
+#define IGC_CTRL_EXT 0x00018 /* Extended Device Control - RW */
+#define IGC_MDIC 0x00020 /* MDI Control - RW */
+#define IGC_MDICNFG 0x00E04 /* MDC/MDIO Configuration - RW */
+#define IGC_CONNSW 0x00034 /* Copper/Fiber switch control - RW */
+
+/* Internal Packet Buffer Size Registers */
+#define IGC_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */
+#define IGC_TXPBS 0x03404 /* Tx Packet Buffer Size - RW */
+
+/* NVM Register Descriptions */
+#define IGC_EERD 0x12014 /* EEprom mode read - RW */
+#define IGC_EEWR 0x12018 /* EEprom mode write - RW */
+
+/* Flow Control Register Descriptions */
+#define IGC_FCAL 0x00028 /* FC Address Low - RW */
+#define IGC_FCAH 0x0002C /* FC Address High - RW */
+#define IGC_FCT 0x00030 /* FC Type - RW */
+#define IGC_FCTTV 0x00170 /* FC Transmit Timer - RW */
+#define IGC_FCRTL 0x02160 /* FC Receive Threshold Low - RW */
+#define IGC_FCRTH 0x02168 /* FC Receive Threshold High - RW */
+#define IGC_FCRTV 0x02460 /* FC Refresh Timer Value - RW */
+#define IGC_FCSTS 0x02464 /* FC Status - RO */
+
+/* PCIe Register Description */
+#define IGC_GCR 0x05B00 /* PCIe control- RW */
+
+/* Semaphore registers */
+#define IGC_SW_FW_SYNC 0x05B5C /* SW-FW Synchronization - RW */
+#define IGC_SWSM 0x05B50 /* SW Semaphore */
+#define IGC_FWSM 0x05B54 /* FW Semaphore */
+
+/* Function Active and Power State to MNG */
+#define IGC_FACTPS 0x05B30
+
+/* Interrupt Register Description */
+#define IGC_EICS 0x01520 /* Ext. Interrupt Cause Set - W0 */
+#define IGC_EIMS 0x01524 /* Ext. Interrupt Mask Set/Read - RW */
+#define IGC_EIMC 0x01528 /* Ext. Interrupt Mask Clear - WO */
+#define IGC_EIAC 0x0152C /* Ext. Interrupt Auto Clear - RW */
+#define IGC_EIAM 0x01530 /* Ext. Interrupt Auto Mask - RW */
+#define IGC_ICR 0x01500 /* Intr Cause Read - RC/W1C */
+#define IGC_ICS 0x01504 /* Intr Cause Set - WO */
+#define IGC_IMS 0x01508 /* Intr Mask Set/Read - RW */
+#define IGC_IMC 0x0150C /* Intr Mask Clear - WO */
+#define IGC_IAM 0x01510 /* Intr Ack Auto Mask- RW */
+/* Intr Throttle - RW */
+#define IGC_EITR(_n) (0x01680 + (0x4 * (_n)))
+/* Interrupt Vector Allocation - RW */
+#define IGC_IVAR0 0x01700
+#define IGC_IVAR_MISC 0x01740 /* IVAR for "other" causes - RW */
+#define IGC_GPIE 0x01514 /* General Purpose Intr Enable - RW */
+
+/* Interrupt Cause */
+#define IGC_ICRXPTC 0x04104 /* Rx Packet Timer Expire Count */
+#define IGC_ICRXATC 0x04108 /* Rx Absolute Timer Expire Count */
+#define IGC_ICTXPTC 0x0410C /* Tx Packet Timer Expire Count */
+#define IGC_ICTXATC 0x04110 /* Tx Absolute Timer Expire Count */
+#define IGC_ICTXQEC 0x04118 /* Tx Queue Empty Count */
+#define IGC_ICTXQMTC 0x0411C /* Tx Queue Min Threshold Count */
+#define IGC_ICRXDMTC 0x04120 /* Rx Descriptor Min Threshold Count */
+#define IGC_ICRXOC 0x04124 /* Receiver Overrun Count */
+
+#define IGC_CBTMPC 0x0402C /* Circuit Breaker TX Packet Count */
+#define IGC_HTDPMC 0x0403C /* Host Transmit Discarded Packets */
+#define IGC_CBRMPC 0x040FC /* Circuit Breaker RX Packet Count */
+#define IGC_RPTHC 0x04104 /* Rx Packets To Host */
+#define IGC_HGPTC 0x04118 /* Host Good Packets TX Count */
+#define IGC_HTCBDPC 0x04124 /* Host TX Circ.Breaker Drop Count */
+
+/* MSI-X Table Register Descriptions */
+#define IGC_PBACL 0x05B68 /* MSIx PBA Clear - R/W 1 to clear */
+
+/* RSS registers */
+#define IGC_MRQC 0x05818 /* Multiple Receive Control - RW */
+
+/* Filtering Registers */
+#define IGC_ETQF(_n) (0x05CB0 + (4 * (_n))) /* EType Queue Fltr */
+
+/* ETQF register bit definitions */
+#define IGC_ETQF_FILTER_ENABLE BIT(26)
+#define IGC_ETQF_QUEUE_ENABLE BIT(31)
+#define IGC_ETQF_QUEUE_SHIFT 16
+#define IGC_ETQF_QUEUE_MASK 0x00070000
+#define IGC_ETQF_ETYPE_MASK 0x0000FFFF
+
+/* Redirection Table - RW Array */
+#define IGC_RETA(_i) (0x05C00 + ((_i) * 4))
+/* RSS Random Key - RW Array */
+#define IGC_RSSRK(_i) (0x05C80 + ((_i) * 4))
+
+/* Receive Register Descriptions */
+#define IGC_RCTL 0x00100 /* Rx Control - RW */
+#define IGC_SRRCTL(_n) (0x0C00C + ((_n) * 0x40))
+#define IGC_PSRTYPE(_i) (0x05480 + ((_i) * 4))
+#define IGC_RDBAL(_n) (0x0C000 + ((_n) * 0x40))
+#define IGC_RDBAH(_n) (0x0C004 + ((_n) * 0x40))
+#define IGC_RDLEN(_n) (0x0C008 + ((_n) * 0x40))
+#define IGC_RDH(_n) (0x0C010 + ((_n) * 0x40))
+#define IGC_RDT(_n) (0x0C018 + ((_n) * 0x40))
+#define IGC_RXDCTL(_n) (0x0C028 + ((_n) * 0x40))
+#define IGC_RQDPC(_n) (0x0C030 + ((_n) * 0x40))
+#define IGC_RXCSUM 0x05000 /* Rx Checksum Control - RW */
+#define IGC_RLPML 0x05004 /* Rx Long Packet Max Length */
+#define IGC_RFCTL 0x05008 /* Receive Filter Control*/
+#define IGC_MTA 0x05200 /* Multicast Table Array - RW Array */
+#define IGC_UTA 0x0A000 /* Unicast Table Array - RW */
+#define IGC_RAL(_n) (0x05400 + ((_n) * 0x08))
+#define IGC_RAH(_n) (0x05404 + ((_n) * 0x08))
+#define IGC_VLAPQF 0x055B0 /* VLAN Priority Queue Filter VLAPQF */
+
+/* Transmit Register Descriptions */
+#define IGC_TCTL 0x00400 /* Tx Control - RW */
+#define IGC_TIPG 0x00410 /* Tx Inter-packet gap - RW */
+#define IGC_TDBAL(_n) (0x0E000 + ((_n) * 0x40))
+#define IGC_TDBAH(_n) (0x0E004 + ((_n) * 0x40))
+#define IGC_TDLEN(_n) (0x0E008 + ((_n) * 0x40))
+#define IGC_TDH(_n) (0x0E010 + ((_n) * 0x40))
+#define IGC_TDT(_n) (0x0E018 + ((_n) * 0x40))
+#define IGC_TXDCTL(_n) (0x0E028 + ((_n) * 0x40))
+
+/* MMD Register Descriptions */
+#define IGC_MMDAC 13 /* MMD Access Control */
+#define IGC_MMDAAD 14 /* MMD Access Address/Data */
+
+/* Good transmitted packets counter registers */
+#define IGC_PQGPTC(_n) (0x010014 + (0x100 * (_n)))
+
+/* Statistics Register Descriptions */
+#define IGC_CRCERRS 0x04000 /* CRC Error Count - R/clr */
+#define IGC_ALGNERRC 0x04004 /* Alignment Error Count - R/clr */
+#define IGC_SYMERRS 0x04008 /* Symbol Error Count - R/clr */
+#define IGC_RXERRC 0x0400C /* Receive Error Count - R/clr */
+#define IGC_MPC 0x04010 /* Missed Packet Count - R/clr */
+#define IGC_SCC 0x04014 /* Single Collision Count - R/clr */
+#define IGC_ECOL 0x04018 /* Excessive Collision Count - R/clr */
+#define IGC_MCC 0x0401C /* Multiple Collision Count - R/clr */
+#define IGC_LATECOL 0x04020 /* Late Collision Count - R/clr */
+#define IGC_COLC 0x04028 /* Collision Count - R/clr */
+#define IGC_DC 0x04030 /* Defer Count - R/clr */
+#define IGC_TNCRS 0x04034 /* Tx-No CRS - R/clr */
+#define IGC_SEC 0x04038 /* Sequence Error Count - R/clr */
+#define IGC_CEXTERR 0x0403C /* Carrier Extension Error Count - R/clr */
+#define IGC_RLEC 0x04040 /* Receive Length Error Count - R/clr */
+#define IGC_XONRXC 0x04048 /* XON Rx Count - R/clr */
+#define IGC_XONTXC 0x0404C /* XON Tx Count - R/clr */
+#define IGC_XOFFRXC 0x04050 /* XOFF Rx Count - R/clr */
+#define IGC_XOFFTXC 0x04054 /* XOFF Tx Count - R/clr */
+#define IGC_FCRUC 0x04058 /* Flow Control Rx Unsupported Count- R/clr */
+#define IGC_PRC64 0x0405C /* Packets Rx (64 bytes) - R/clr */
+#define IGC_PRC127 0x04060 /* Packets Rx (65-127 bytes) - R/clr */
+#define IGC_PRC255 0x04064 /* Packets Rx (128-255 bytes) - R/clr */
+#define IGC_PRC511 0x04068 /* Packets Rx (255-511 bytes) - R/clr */
+#define IGC_PRC1023 0x0406C /* Packets Rx (512-1023 bytes) - R/clr */
+#define IGC_PRC1522 0x04070 /* Packets Rx (1024-1522 bytes) - R/clr */
+#define IGC_GPRC 0x04074 /* Good Packets Rx Count - R/clr */
+#define IGC_BPRC 0x04078 /* Broadcast Packets Rx Count - R/clr */
+#define IGC_MPRC 0x0407C /* Multicast Packets Rx Count - R/clr */
+#define IGC_GPTC 0x04080 /* Good Packets Tx Count - R/clr */
+#define IGC_GORCL 0x04088 /* Good Octets Rx Count Low - R/clr */
+#define IGC_GORCH 0x0408C /* Good Octets Rx Count High - R/clr */
+#define IGC_GOTCL 0x04090 /* Good Octets Tx Count Low - R/clr */
+#define IGC_GOTCH 0x04094 /* Good Octets Tx Count High - R/clr */
+#define IGC_RNBC 0x040A0 /* Rx No Buffers Count - R/clr */
+#define IGC_RUC 0x040A4 /* Rx Undersize Count - R/clr */
+#define IGC_RFC 0x040A8 /* Rx Fragment Count - R/clr */
+#define IGC_ROC 0x040AC /* Rx Oversize Count - R/clr */
+#define IGC_RJC 0x040B0 /* Rx Jabber Count - R/clr */
+#define IGC_MGTPRC 0x040B4 /* Management Packets Rx Count - R/clr */
+#define IGC_MGTPDC 0x040B8 /* Management Packets Dropped Count - R/clr */
+#define IGC_MGTPTC 0x040BC /* Management Packets Tx Count - R/clr */
+#define IGC_TORL 0x040C0 /* Total Octets Rx Low - R/clr */
+#define IGC_TORH 0x040C4 /* Total Octets Rx High - R/clr */
+#define IGC_TOTL 0x040C8 /* Total Octets Tx Low - R/clr */
+#define IGC_TOTH 0x040CC /* Total Octets Tx High - R/clr */
+#define IGC_TPR 0x040D0 /* Total Packets Rx - R/clr */
+#define IGC_TPT 0x040D4 /* Total Packets Tx - R/clr */
+#define IGC_PTC64 0x040D8 /* Packets Tx (64 bytes) - R/clr */
+#define IGC_PTC127 0x040DC /* Packets Tx (65-127 bytes) - R/clr */
+#define IGC_PTC255 0x040E0 /* Packets Tx (128-255 bytes) - R/clr */
+#define IGC_PTC511 0x040E4 /* Packets Tx (256-511 bytes) - R/clr */
+#define IGC_PTC1023 0x040E8 /* Packets Tx (512-1023 bytes) - R/clr */
+#define IGC_PTC1522 0x040EC /* Packets Tx (1024-1522 Bytes) - R/clr */
+#define IGC_MPTC 0x040F0 /* Multicast Packets Tx Count - R/clr */
+#define IGC_BPTC 0x040F4 /* Broadcast Packets Tx Count - R/clr */
+#define IGC_TSCTC 0x040F8 /* TCP Segmentation Context Tx - R/clr */
+#define IGC_TSCTFC 0x040FC /* TCP Segmentation Context Tx Fail - R/clr */
+#define IGC_IAC 0x04100 /* Interrupt Assertion Count */
+#define IGC_ICTXPTC 0x0410C /* Interrupt Cause Tx Pkt Timer Expire Count */
+#define IGC_ICTXATC 0x04110 /* Interrupt Cause Tx Abs Timer Expire Count */
+#define IGC_ICTXQEC 0x04118 /* Interrupt Cause Tx Queue Empty Count */
+#define IGC_ICTXQMTC 0x0411C /* Interrupt Cause Tx Queue Min Thresh Count */
+#define IGC_RPTHC 0x04104 /* Rx Packets To Host */
+#define IGC_HGPTC 0x04118 /* Host Good Packets Tx Count */
+#define IGC_RXDMTC 0x04120 /* Rx Descriptor Minimum Threshold Count */
+#define IGC_HGORCL 0x04128 /* Host Good Octets Received Count Low */
+#define IGC_HGORCH 0x0412C /* Host Good Octets Received Count High */
+#define IGC_HGOTCL 0x04130 /* Host Good Octets Transmit Count Low */
+#define IGC_HGOTCH 0x04134 /* Host Good Octets Transmit Count High */
+#define IGC_LENERRS 0x04138 /* Length Errors Count */
+#define IGC_HRMPC 0x0A018 /* Header Redirection Missed Packet Count */
+
+/* Management registers */
+#define IGC_MANC 0x05820 /* Management Control - RW */
+
+/* Shadow Ram Write Register - RW */
+#define IGC_SRWR 0x12018
+
+/* forward declaration */
+struct igc_hw;
+u32 igc_rd32(struct igc_hw *hw, u32 reg);
+
+/* write operations, indexed using DWORDS */
+#define wr32(reg, val) \
+do { \
+ u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
+ if (!IGC_REMOVED(hw_addr)) \
+ writel((val), &hw_addr[(reg)]); \
+} while (0)
+
+#define rd32(reg) (igc_rd32(hw, reg))
+
+#define wrfl() ((void)rd32(IGC_STATUS))
+
+#define array_wr32(reg, offset, value) \
+ wr32((reg) + ((offset) << 2), (value))
+
+#define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2)))
+
+#endif
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 7722153..0940a0d 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -102,7 +102,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) PRO/10GbE Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
@@ -680,8 +680,8 @@
txdr->size = txdr->count * sizeof(struct ixgb_tx_desc);
txdr->size = ALIGN(txdr->size, 4096);
- txdr->desc = dma_zalloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
- GFP_KERNEL);
+ txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
+ GFP_KERNEL);
if (!txdr->desc) {
vfree(txdr->buffer_info);
return -ENOMEM;
@@ -763,8 +763,8 @@
rxdr->size = rxdr->count * sizeof(struct ixgb_rx_desc);
rxdr->size = ALIGN(rxdr->size, 4096);
- rxdr->desc = dma_zalloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
- GFP_KERNEL);
+ rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
+ GFP_KERNEL);
if (!rxdr->desc) {
vfree(rxdr->buffer_info);
@@ -1331,9 +1331,7 @@
}
for (f = 0; f < nr_frags; f++) {
- const struct skb_frag_struct *frag;
-
- frag = &skb_shinfo(skb)->frags[f];
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
len = skb_frag_size(frag);
offset = 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 5414685..4fb0d9e 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -8,7 +8,8 @@
ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
- ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o
+ ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
+ ixgbe_xsk.o
ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \
ixgbe_dcb_82599.o ixgbe_dcb_nl.o
@@ -16,4 +17,4 @@
ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o
ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o
-ixgbe-$(CONFIG_XFRM_OFFLOAD) += ixgbe_ipsec.o
+ixgbe-$(CONFIG_IXGBE_IPSEC) += ixgbe_ipsec.o
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 4fc906c..39e73ad 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -12,6 +12,7 @@
#include <linux/aer.h>
#include <linux/if_vlan.h>
#include <linux/jiffies.h>
+#include <linux/phy.h>
#include <linux/timecounter.h>
#include <linux/net_tstamp.h>
@@ -30,7 +31,6 @@
#include "ixgbe_ipsec.h"
#include <net/xdp.h>
-#include <net/busy_poll.h>
/* common prefix used by pr_<> macros */
#undef pr_fmt
@@ -50,8 +50,6 @@
#define IXGBE_MAX_RXD 4096
#define IXGBE_MIN_RXD 64
-#define IXGBE_ETH_P_LLDP 0x88CC
-
/* flow control */
#define IXGBE_MIN_FCRTL 0x40
#define IXGBE_MAX_FCRTL 0x7FF80
@@ -228,13 +226,17 @@
struct ixgbe_rx_buffer {
struct sk_buff *skb;
dma_addr_t dma;
- struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
- __u32 page_offset;
-#else
- __u16 page_offset;
-#endif
- __u16 pagecnt_bias;
+ union {
+ struct {
+ struct page *page;
+ __u32 page_offset;
+ __u16 pagecnt_bias;
+ };
+ struct {
+ void *addr;
+ u64 handle;
+ };
+ };
};
struct ixgbe_queue_stats {
@@ -271,6 +273,7 @@
__IXGBE_TX_DETECT_HANG,
__IXGBE_HANG_CHECK_ARMED,
__IXGBE_TX_XDP_RING,
+ __IXGBE_TX_DISABLED,
};
#define ring_uses_build_skb(ring) \
@@ -347,6 +350,10 @@
struct ixgbe_rx_queue_stats rx_stats;
};
struct xdp_rxq_info xdp_rxq;
+ struct xdp_umem *xsk_umem;
+ struct zero_copy_allocator zca; /* ZC allocator anchor */
+ u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */
+ u16 rx_buf_len;
} ____cacheline_internodealigned_in_smp;
enum ixgbe_ring_f_enum {
@@ -553,6 +560,7 @@
struct net_device *netdev;
struct bpf_prog *xdp_prog;
struct pci_dev *pdev;
+ struct mii_bus *mii_bus;
unsigned long state;
@@ -605,6 +613,7 @@
#define IXGBE_FLAG2_EEE_ENABLED BIT(15)
#define IXGBE_FLAG2_RX_LEGACY BIT(16)
#define IXGBE_FLAG2_IPSEC_ENABLED BIT(17)
+#define IXGBE_FLAG2_VF_IPSEC_ENABLED BIT(18)
/* Tx fast path data */
int num_tx_queues;
@@ -624,6 +633,7 @@
/* XDP */
int num_xdp_queues;
struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES];
+ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled rings */
/* TX */
struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp;
@@ -760,9 +770,9 @@
#define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */
u32 *rss_key;
-#ifdef CONFIG_XFRM_OFFLOAD
+#ifdef CONFIG_IXGBE_IPSEC
struct ixgbe_ipsec *ipsec;
-#endif /* CONFIG_XFRM_OFFLOAD */
+#endif /* CONFIG_IXGBE_IPSEC */
};
static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
@@ -994,7 +1004,7 @@
void ixgbe_store_reta(struct ixgbe_adapter *adapter);
s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm);
-#ifdef CONFIG_XFRM_OFFLOAD
+#ifdef CONFIG_IXGBE_IPSEC
void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter);
void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter);
void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter);
@@ -1003,15 +1013,30 @@
struct sk_buff *skb);
int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first,
struct ixgbe_ipsec_tx_data *itd);
+void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf);
+int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf);
+int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf);
#else
-static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { };
-static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { };
-static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { };
+static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { }
+static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { }
+static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { }
static inline void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
union ixgbe_adv_rx_desc *rx_desc,
- struct sk_buff *skb) { };
+ struct sk_buff *skb) { }
static inline int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
struct ixgbe_tx_buffer *first,
- struct ixgbe_ipsec_tx_data *itd) { return 0; };
-#endif /* CONFIG_XFRM_OFFLOAD */
+ struct ixgbe_ipsec_tx_data *itd) { return 0; }
+static inline void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter,
+ u32 vf) { }
+static inline int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter,
+ u32 *mbuf, u32 vf) { return -EACCES; }
+static inline int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter,
+ u32 *mbuf, u32 vf) { return -EACCES; }
+#endif /* CONFIG_IXGBE_IPSEC */
+
+static inline bool ixgbe_enabled_xdp_adapter(struct ixgbe_adapter *adapter)
+{
+ return !!adapter->xdp_prog;
+}
+
#endif /* _IXGBE_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 1e49716..109f8de 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1048,7 +1048,7 @@
* clear the multicast table. Also reset num_rar_entries to 128,
* since we modify this value when programming the SAN MAC address.
*/
- hw->mac.num_rar_entries = 128;
+ hw->mac.num_rar_entries = IXGBE_82599_RAR_ENTRIES;
hw->mac.ops.init_rx_addrs(hw);
/* Store the permanent SAN mac address */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
index 50dfb02..171cdc5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -190,22 +190,12 @@
void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter)
{
const char *name = pci_name(adapter->pdev);
- struct dentry *pfile;
+
adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root);
- if (adapter->ixgbe_dbg_adapter) {
- pfile = debugfs_create_file("reg_ops", 0600,
- adapter->ixgbe_dbg_adapter, adapter,
- &ixgbe_dbg_reg_ops_fops);
- if (!pfile)
- e_dev_err("debugfs reg_ops for %s failed\n", name);
- pfile = debugfs_create_file("netdev_ops", 0600,
- adapter->ixgbe_dbg_adapter, adapter,
- &ixgbe_dbg_netdev_ops_fops);
- if (!pfile)
- e_dev_err("debugfs netdev_ops for %s failed\n", name);
- } else {
- e_dev_err("debugfs entry for %s failed\n", name);
- }
+ debugfs_create_file("reg_ops", 0600, adapter->ixgbe_dbg_adapter,
+ adapter, &ixgbe_dbg_reg_ops_fops);
+ debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter,
+ adapter, &ixgbe_dbg_netdev_ops_fops);
}
/**
@@ -224,8 +214,6 @@
void ixgbe_dbg_init(void)
{
ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL);
- if (ixgbe_dbg_root == NULL)
- pr_err("init of debugfs failed\n");
}
/**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index e5a8461..7c52ae8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -136,6 +136,8 @@
static const char ixgbe_priv_flags_strings[][ETH_GSTRING_LEN] = {
#define IXGBE_PRIV_FLAGS_LEGACY_RX BIT(0)
"legacy-rx",
+#define IXGBE_PRIV_FLAGS_VF_IPSEC_EN BIT(1)
+ "vf-ipsec",
};
#define IXGBE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbe_priv_flags_strings)
@@ -2204,7 +2206,8 @@
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE))
+ if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
+ WAKE_FILTER))
return -EOPNOTSUPP;
if (ixgbe_wol_exclusion(adapter, wol))
@@ -3223,7 +3226,8 @@
page_swap = true;
}
- if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap) {
+ if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap ||
+ !(addr_mode & IXGBE_SFF_DDM_IMPLEMENTED)) {
/* We have a SFP, but it does not support SFF-8472 */
modinfo->type = ETH_MODULE_SFF_8079;
modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
@@ -3409,6 +3413,9 @@
if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
priv_flags |= IXGBE_PRIV_FLAGS_LEGACY_RX;
+ if (adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED)
+ priv_flags |= IXGBE_PRIV_FLAGS_VF_IPSEC_EN;
+
return priv_flags;
}
@@ -3421,6 +3428,10 @@
if (priv_flags & IXGBE_PRIV_FLAGS_LEGACY_RX)
flags2 |= IXGBE_FLAG2_RX_LEGACY;
+ flags2 &= ~IXGBE_FLAG2_VF_IPSEC_ENABLED;
+ if (priv_flags & IXGBE_PRIV_FLAGS_VF_IPSEC_EN)
+ flags2 |= IXGBE_FLAG2_VF_IPSEC_ENABLED;
+
if (flags2 != adapter->flags2) {
adapter->flags2 = flags2;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index add124e..113f608 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -4,6 +4,12 @@
#include "ixgbe.h"
#include <net/xfrm.h>
#include <crypto/aead.h>
+#include <linux/if_bridge.h>
+
+#define IXGBE_IPSEC_KEY_BITS 160
+static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+
+static void ixgbe_ipsec_del_sa(struct xfrm_state *xs);
/**
* ixgbe_ipsec_set_tx_sa - set the Tx SA registers
@@ -113,7 +119,6 @@
**/
static void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter)
{
- struct ixgbe_ipsec *ipsec = adapter->ipsec;
struct ixgbe_hw *hw = &adapter->hw;
u32 buf[4] = {0, 0, 0, 0};
u16 idx;
@@ -132,9 +137,6 @@
ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0);
ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0);
}
-
- ipsec->num_rx_sa = 0;
- ipsec->num_tx_sa = 0;
}
/**
@@ -290,6 +292,13 @@
/**
* ixgbe_ipsec_restore - restore the ipsec HW settings after a reset
* @adapter: board private structure
+ *
+ * Reload the HW tables from the SW tables after they've been bashed
+ * by a chip reset.
+ *
+ * Any VF entries are removed from the SW and HW tables since either
+ * (a) the VF also gets reset on PF reset and will ask again for the
+ * offloads, or (b) the VF has been removed by a change in the num_vfs.
**/
void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
{
@@ -305,6 +314,28 @@
ixgbe_ipsec_clear_hw_tables(adapter);
ixgbe_ipsec_start_engine(adapter);
+ /* reload the Rx and Tx keys */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+ struct rx_sa *r = &ipsec->rx_tbl[i];
+ struct tx_sa *t = &ipsec->tx_tbl[i];
+
+ if (r->used) {
+ if (r->mode & IXGBE_RXTXMOD_VF)
+ ixgbe_ipsec_del_sa(r->xs);
+ else
+ ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi,
+ r->key, r->salt,
+ r->mode, r->iptbl_ind);
+ }
+
+ if (t->used) {
+ if (t->mode & IXGBE_RXTXMOD_VF)
+ ixgbe_ipsec_del_sa(t->xs);
+ else
+ ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt);
+ }
+ }
+
/* reload the IP addrs */
for (i = 0; i < IXGBE_IPSEC_MAX_RX_IP_COUNT; i++) {
struct rx_ip_sa *ipsa = &ipsec->ip_tbl[i];
@@ -312,20 +343,6 @@
if (ipsa->used)
ixgbe_ipsec_set_rx_ip(hw, i, ipsa->ipaddr);
}
-
- /* reload the Rx and Tx keys */
- for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
- struct rx_sa *rsa = &ipsec->rx_tbl[i];
- struct tx_sa *tsa = &ipsec->tx_tbl[i];
-
- if (rsa->used)
- ixgbe_ipsec_set_rx_sa(hw, i, rsa->xs->id.spi,
- rsa->key, rsa->salt,
- rsa->mode, rsa->iptbl_ind);
-
- if (tsa->used)
- ixgbe_ipsec_set_tx_sa(hw, i, tsa->key, tsa->salt);
- }
}
/**
@@ -382,6 +399,8 @@
rcu_read_lock();
hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist,
(__force u32)spi) {
+ if (rsa->mode & IXGBE_RXTXMOD_VF)
+ continue;
if (spi == rsa->xs->id.spi &&
((ip4 && *daddr == rsa->xs->id.daddr.a4) ||
(!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6,
@@ -411,7 +430,6 @@
struct net_device *dev = xs->xso.dev;
unsigned char *key_data;
char *alg_name = NULL;
- const char aes_gcm_name[] = "rfc4106(gcm(aes))";
int key_len;
if (!xs->aead) {
@@ -439,9 +457,9 @@
* we don't need to do any byteswapping.
* 160 accounts for 16 byte key and 4 byte salt
*/
- if (key_len == 160) {
+ if (key_len == IXGBE_IPSEC_KEY_BITS) {
*mysalt = ((u32 *)key_data)[4];
- } else if (key_len != 128) {
+ } else if (key_len != (IXGBE_IPSEC_KEY_BITS - (sizeof(*mysalt) * 8))) {
netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n");
return -EINVAL;
} else {
@@ -676,7 +694,8 @@
} else {
struct tx_sa tsa;
- if (adapter->num_vfs)
+ if (adapter->num_vfs &&
+ adapter->bridge_mode != BRIDGE_MODE_VEPA)
return -EOPNOTSUPP;
/* find the first unused index */
@@ -814,6 +833,226 @@
};
/**
+ * ixgbe_ipsec_vf_clear - clear the tables of data for a VF
+ * @adapter: board private structure
+ * @vf: VF id to be removed
+ **/
+void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
+{
+ struct ixgbe_ipsec *ipsec = adapter->ipsec;
+ int i;
+
+ if (!ipsec)
+ return;
+
+ /* search rx sa table */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_rx_sa; i++) {
+ if (!ipsec->rx_tbl[i].used)
+ continue;
+ if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
+ ipsec->rx_tbl[i].vf == vf)
+ ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs);
+ }
+
+ /* search tx sa table */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_tx_sa; i++) {
+ if (!ipsec->tx_tbl[i].used)
+ continue;
+ if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
+ ipsec->tx_tbl[i].vf == vf)
+ ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs);
+ }
+}
+
+/**
+ * ixgbe_ipsec_vf_add_sa - translate VF request to SA add
+ * @adapter: board private structure
+ * @msgbuf: The message buffer
+ * @vf: the VF index
+ *
+ * Make up a new xs and algorithm info from the data sent by the VF.
+ * We only need to sketch in just enough to set up the HW offload.
+ * Put the resulting offload_handle into the return message to the VF.
+ *
+ * Returns 0 or error value
+ **/
+int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
+{
+ struct ixgbe_ipsec *ipsec = adapter->ipsec;
+ struct xfrm_algo_desc *algo;
+ struct sa_mbx_msg *sam;
+ struct xfrm_state *xs;
+ size_t aead_len;
+ u16 sa_idx;
+ u32 pfsa;
+ int err;
+
+ sam = (struct sa_mbx_msg *)(&msgbuf[1]);
+ if (!adapter->vfinfo[vf].trusted ||
+ !(adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED)) {
+ e_warn(drv, "VF %d attempted to add an IPsec SA\n", vf);
+ err = -EACCES;
+ goto err_out;
+ }
+
+ /* Tx IPsec offload doesn't seem to work on this
+ * device, so block these requests for now.
+ */
+ if (!(sam->flags & XFRM_OFFLOAD_INBOUND)) {
+ err = -EOPNOTSUPP;
+ goto err_out;
+ }
+
+ xs = kzalloc(sizeof(*xs), GFP_KERNEL);
+ if (unlikely(!xs)) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ xs->xso.flags = sam->flags;
+ xs->id.spi = sam->spi;
+ xs->id.proto = sam->proto;
+ xs->props.family = sam->family;
+ if (xs->props.family == AF_INET6)
+ memcpy(&xs->id.daddr.a6, sam->addr, sizeof(xs->id.daddr.a6));
+ else
+ memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4));
+ xs->xso.dev = adapter->netdev;
+
+ algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1);
+ if (unlikely(!algo)) {
+ err = -ENOENT;
+ goto err_xs;
+ }
+
+ aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8;
+ xs->aead = kzalloc(aead_len, GFP_KERNEL);
+ if (unlikely(!xs->aead)) {
+ err = -ENOMEM;
+ goto err_xs;
+ }
+
+ xs->props.ealgo = algo->desc.sadb_alg_id;
+ xs->geniv = algo->uinfo.aead.geniv;
+ xs->aead->alg_icv_len = IXGBE_IPSEC_AUTH_BITS;
+ xs->aead->alg_key_len = IXGBE_IPSEC_KEY_BITS;
+ memcpy(xs->aead->alg_key, sam->key, sizeof(sam->key));
+ memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name));
+
+ /* set up the HW offload */
+ err = ixgbe_ipsec_add_sa(xs);
+ if (err)
+ goto err_aead;
+
+ pfsa = xs->xso.offload_handle;
+ if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) {
+ sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX;
+ ipsec->rx_tbl[sa_idx].vf = vf;
+ ipsec->rx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF;
+ } else {
+ sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX;
+ ipsec->tx_tbl[sa_idx].vf = vf;
+ ipsec->tx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF;
+ }
+
+ msgbuf[1] = xs->xso.offload_handle;
+
+ return 0;
+
+err_aead:
+ kzfree(xs->aead);
+err_xs:
+ kzfree(xs);
+err_out:
+ msgbuf[1] = err;
+ return err;
+}
+
+/**
+ * ixgbe_ipsec_vf_del_sa - translate VF request to SA delete
+ * @adapter: board private structure
+ * @msgbuf: The message buffer
+ * @vf: the VF index
+ *
+ * Given the offload_handle sent by the VF, look for the related SA table
+ * entry and use its xs field to call for a delete of the SA.
+ *
+ * Note: We silently ignore requests to delete entries that are already
+ * set to unused because when a VF is set to "DOWN", the PF first
+ * gets a reset and clears all the VF's entries; then the VF's
+ * XFRM stack sends individual deletes for each entry, which the
+ * reset already removed. In the future it might be good to try to
+ * optimize this so not so many unnecessary delete messages are sent.
+ *
+ * Returns 0 or error value
+ **/
+int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
+{
+ struct ixgbe_ipsec *ipsec = adapter->ipsec;
+ struct xfrm_state *xs;
+ u32 pfsa = msgbuf[1];
+ u16 sa_idx;
+
+ if (!adapter->vfinfo[vf].trusted) {
+ e_err(drv, "vf %d attempted to delete an SA\n", vf);
+ return -EPERM;
+ }
+
+ if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) {
+ struct rx_sa *rsa;
+
+ sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX;
+ if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) {
+ e_err(drv, "vf %d SA index %d out of range\n",
+ vf, sa_idx);
+ return -EINVAL;
+ }
+
+ rsa = &ipsec->rx_tbl[sa_idx];
+
+ if (!rsa->used)
+ return 0;
+
+ if (!(rsa->mode & IXGBE_RXTXMOD_VF) ||
+ rsa->vf != vf) {
+ e_err(drv, "vf %d bad Rx SA index %d\n", vf, sa_idx);
+ return -ENOENT;
+ }
+
+ xs = ipsec->rx_tbl[sa_idx].xs;
+ } else {
+ struct tx_sa *tsa;
+
+ sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX;
+ if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) {
+ e_err(drv, "vf %d SA index %d out of range\n",
+ vf, sa_idx);
+ return -EINVAL;
+ }
+
+ tsa = &ipsec->tx_tbl[sa_idx];
+
+ if (!tsa->used)
+ return 0;
+
+ if (!(tsa->mode & IXGBE_RXTXMOD_VF) ||
+ tsa->vf != vf) {
+ e_err(drv, "vf %d bad Tx SA index %d\n", vf, sa_idx);
+ return -ENOENT;
+ }
+
+ xs = ipsec->tx_tbl[sa_idx].xs;
+ }
+
+ ixgbe_ipsec_del_sa(xs);
+
+ /* remove the xs that was made-up in the add request */
+ kzfree(xs);
+
+ return 0;
+}
+
+/**
* ixgbe_ipsec_tx - setup Tx flags for ipsec offload
* @tx_ring: outgoing context
* @first: current data packet
@@ -826,11 +1065,13 @@
struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
struct ixgbe_ipsec *ipsec = adapter->ipsec;
struct xfrm_state *xs;
+ struct sec_path *sp;
struct tx_sa *tsa;
- if (unlikely(!first->skb->sp->len)) {
+ sp = skb_sec_path(first->skb);
+ if (unlikely(!sp->len)) {
netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
- __func__, first->skb->sp->len);
+ __func__, sp->len);
return 0;
}
@@ -920,6 +1161,7 @@
struct xfrm_state *xs = NULL;
struct ipv6hdr *ip6 = NULL;
struct iphdr *ip4 = NULL;
+ struct sec_path *sp;
void *daddr;
__be32 spi;
u8 *c_hdr;
@@ -959,12 +1201,12 @@
if (unlikely(!xs))
return;
- skb->sp = secpath_dup(skb->sp);
- if (unlikely(!skb->sp))
+ sp = secpath_set(skb);
+ if (unlikely(!sp))
return;
- skb->sp->xvec[skb->sp->len++] = xs;
- skb->sp->olen++;
+ sp->xvec[sp->len++] = xs;
+ sp->olen++;
xo = xfrm_offload(skb);
xo->flags = CRYPTO_DONE;
xo->status = CRYPTO_SUCCESS;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h
index 9ef7faa..d2b64ff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h
@@ -26,6 +26,7 @@
#define IXGBE_RXMOD_PROTO_ESP 0x00000004
#define IXGBE_RXMOD_DECRYPT 0x00000008
#define IXGBE_RXMOD_IPV6 0x00000010
+#define IXGBE_RXTXMOD_VF 0x00000020
struct rx_sa {
struct hlist_node hlist;
@@ -37,6 +38,7 @@
u8 iptbl_ind;
bool used;
bool decrypt;
+ u32 vf;
};
struct rx_ip_sa {
@@ -49,8 +51,10 @@
struct xfrm_state *xs;
u32 key[4];
u32 salt;
+ u32 mode;
bool encrypt;
bool used;
+ u32 vf;
};
struct ixgbe_ipsec_tx_data {
@@ -67,4 +71,13 @@
struct tx_sa *tx_tbl;
DECLARE_HASHTABLE(rx_sa_list, 10);
};
+
+struct sa_mbx_msg {
+ __be32 spi;
+ u8 flags;
+ u8 proto;
+ u16 family;
+ __be32 addr[4];
+ u32 key[5];
+};
#endif /* _IXGBE_IPSEC_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index d361f57..cc3196a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -836,12 +836,10 @@
struct ixgbe_ring *ring;
int node = NUMA_NO_NODE;
int cpu = -1;
- int ring_count, size;
+ int ring_count;
u8 tcs = adapter->hw_tcs;
ring_count = txr_count + rxr_count + xdp_count;
- size = sizeof(struct ixgbe_q_vector) +
- (sizeof(struct ixgbe_ring) * ring_count);
/* customize cpu for Flow Director mapping */
if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
@@ -855,9 +853,11 @@
}
/* allocate q_vector and rings */
- q_vector = kzalloc_node(size, GFP_KERNEL, node);
+ q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count),
+ GFP_KERNEL, node);
if (!q_vector)
- q_vector = kzalloc(size, GFP_KERNEL);
+ q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+ GFP_KERNEL);
if (!q_vector)
return -ENOMEM;
@@ -1055,7 +1055,7 @@
int txr_remaining = adapter->num_tx_queues;
int xdp_remaining = adapter->num_xdp_queues;
int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0;
- int err;
+ int err, i;
/* only one q_vector if MSI-X is disabled. */
if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
@@ -1097,6 +1097,21 @@
xdp_idx += xqpv;
}
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ if (adapter->rx_ring[i])
+ adapter->rx_ring[i]->ring_idx = i;
+ }
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ if (adapter->tx_ring[i])
+ adapter->tx_ring[i]->ring_idx = i;
+ }
+
+ for (i = 0; i < adapter->num_xdp_queues; i++) {
+ if (adapter->xdp_ring[i])
+ adapter->xdp_ring[i]->ring_idx = i;
+ }
+
return 0;
err_out:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6cdd58d..91b3780 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -27,6 +27,7 @@
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/atomic.h>
+#include <linux/numa.h>
#include <scsi/fc/fc_fcoe.h>
#include <net/udp_tunnel.h>
#include <net/pkt_cls.h>
@@ -34,12 +35,16 @@
#include <net/tc_act/tc_mirred.h>
#include <net/vxlan.h>
#include <net/mpls.h>
+#include <net/xdp_sock.h>
+#include <net/xfrm.h>
#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
+#include "ixgbe_phy.h"
#include "ixgbe_sriov.h"
#include "ixgbe_model.h"
+#include "ixgbe_txrx_common.h"
char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
@@ -159,7 +164,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
static struct workqueue_struct *ixgbe_wq;
@@ -893,8 +898,8 @@
}
}
-static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
- u64 qmask)
+void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
+ u64 qmask)
{
u32 mask;
@@ -1673,9 +1678,9 @@
* order to populate the hash, checksum, VLAN, timestamp, protocol, and
* other fields within the skb.
**/
-static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
- union ixgbe_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
{
struct net_device *dev = rx_ring->netdev;
u32 flags = rx_ring->q_vector->adapter->flags;
@@ -1708,8 +1713,8 @@
skb->protocol = eth_type_trans(skb, dev);
}
-static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
- struct sk_buff *skb)
+void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
+ struct sk_buff *skb)
{
napi_gro_receive(&q_vector->napi, skb);
}
@@ -1781,7 +1786,7 @@
static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
struct sk_buff *skb)
{
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned char *va;
unsigned int pull_len;
@@ -1796,14 +1801,14 @@
* we need the header to contain the greater of either ETH_HLEN or
* 60 bytes if the skb->len is less than 60 for skb_pad.
*/
- pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
+ pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
/* update all of the pointers */
skb_frag_size_sub(frag, pull_len);
- frag->page_offset += pull_len;
+ skb_frag_off_add(frag, pull_len);
skb->data_len -= pull_len;
skb->tail += pull_len;
}
@@ -1821,13 +1826,7 @@
static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
struct sk_buff *skb)
{
- /* if the page was released unmap it, else just sync our portion */
- if (unlikely(IXGBE_CB(skb)->page_released)) {
- dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma,
- ixgbe_rx_pg_size(rx_ring),
- DMA_FROM_DEVICE,
- IXGBE_RX_DMA_ATTR);
- } else if (ring_uses_build_skb(rx_ring)) {
+ if (ring_uses_build_skb(rx_ring)) {
unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK;
dma_sync_single_range_for_cpu(rx_ring->dev,
@@ -1836,14 +1835,22 @@
skb_headlen(skb),
DMA_FROM_DEVICE);
} else {
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
dma_sync_single_range_for_cpu(rx_ring->dev,
IXGBE_CB(skb)->dma,
- frag->page_offset,
+ skb_frag_off(frag),
skb_frag_size(frag),
DMA_FROM_DEVICE);
}
+
+ /* If the page was released, just unmap it. */
+ if (unlikely(IXGBE_CB(skb)->page_released)) {
+ dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma,
+ ixgbe_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ IXGBE_RX_DMA_ATTR);
+ }
}
/**
@@ -1868,9 +1875,9 @@
*
* Returns true if an error was encountered and skb was freed.
**/
-static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
- union ixgbe_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
{
struct net_device *netdev = rx_ring->netdev;
@@ -2186,14 +2193,6 @@
return skb;
}
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED BIT(0)
-#define IXGBE_XDP_TX BIT(1)
-#define IXGBE_XDP_REDIR BIT(2)
-
-static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_frame *xdpf);
-
static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring,
struct xdp_buff *xdp)
@@ -2625,7 +2624,7 @@
/* 16K ints/sec to 9.2K ints/sec */
avg_wire_size *= 15;
avg_wire_size += 11452;
- } else if (avg_wire_size <= 1980) {
+ } else if (avg_wire_size < 1968) {
/* 9.2K ints/sec to 8K ints/sec */
avg_wire_size *= 5;
avg_wire_size += 22420;
@@ -2658,6 +2657,8 @@
case IXGBE_LINK_SPEED_2_5GB_FULL:
case IXGBE_LINK_SPEED_1GB_FULL:
case IXGBE_LINK_SPEED_10_FULL:
+ if (avg_wire_size > 8064)
+ avg_wire_size = 8064;
itr += DIV_ROUND_UP(avg_wire_size,
IXGBE_ITR_ADAPTIVE_MIN_INC * 64) *
IXGBE_ITR_ADAPTIVE_MIN_INC;
@@ -3167,7 +3168,11 @@
#endif
ixgbe_for_each_ring(ring, q_vector->tx) {
- if (!ixgbe_clean_tx_irq(q_vector, ring, budget))
+ bool wd = ring->xsk_umem ?
+ ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) :
+ ixgbe_clean_tx_irq(q_vector, ring, budget);
+
+ if (!wd)
clean_complete = false;
}
@@ -3183,7 +3188,10 @@
per_ring_budget = budget;
ixgbe_for_each_ring(ring, q_vector->rx) {
- int cleaned = ixgbe_clean_rx_irq(q_vector, ring,
+ int cleaned = ring->xsk_umem ?
+ ixgbe_clean_rx_irq_zc(q_vector, ring,
+ per_ring_budget) :
+ ixgbe_clean_rx_irq(q_vector, ring,
per_ring_budget);
work_done += cleaned;
@@ -3475,6 +3483,10 @@
u32 txdctl = IXGBE_TXDCTL_ENABLE;
u8 reg_idx = ring->reg_idx;
+ ring->xsk_umem = NULL;
+ if (ring_is_xdp(ring))
+ ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
+
/* disable queue to avoid issues while updating state */
IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
IXGBE_WRITE_FLUSH(hw);
@@ -3579,12 +3591,18 @@
else
mtqc |= IXGBE_MTQC_64VF;
} else {
- if (tcs > 4)
+ if (tcs > 4) {
mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
- else if (tcs > 1)
+ } else if (tcs > 1) {
mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
- else
- mtqc = IXGBE_MTQC_64Q_1PB;
+ } else {
+ u8 max_txq = adapter->num_tx_queues +
+ adapter->num_xdp_queues;
+ if (max_txq > 63)
+ mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
+ else
+ mtqc = IXGBE_MTQC_64Q_1PB;
+ }
}
IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc);
@@ -3707,10 +3725,27 @@
srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
/* configure the packet buffer length */
- if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state))
+ if (rx_ring->xsk_umem) {
+ u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr -
+ XDP_PACKET_HEADROOM;
+
+ /* If the MAC support setting RXDCTL.RLPML, the
+ * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
+ * RXDCTL.RLPML is set to the actual UMEM buffer
+ * size. If not, then we are stuck with a 1k buffer
+ * size resolution. In this case frames larger than
+ * the UMEM buffer size viewed in a 1k resolution will
+ * be dropped.
+ */
+ if (hw->mac.type != ixgbe_mac_82599EB)
+ srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ else
+ srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ } else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) {
srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
- else
+ } else {
srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ }
/* configure descriptor type */
srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
@@ -3924,8 +3959,11 @@
else
mrqc = IXGBE_MRQC_VMDQRSS64EN;
- /* Enable L3/L4 for Tx Switched packets */
- mrqc |= IXGBE_MRQC_L3L4TXSWEN;
+ /* Enable L3/L4 for Tx Switched packets only for X550,
+ * older devices do not support this feature
+ */
+ if (hw->mac.type >= ixgbe_mac_X550)
+ mrqc |= IXGBE_MRQC_L3L4TXSWEN;
} else {
if (tcs > 4)
mrqc = IXGBE_MRQC_RTRSS8TCEN;
@@ -4033,6 +4071,19 @@
u32 rxdctl;
u8 reg_idx = ring->reg_idx;
+ xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+ ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
+ if (ring->xsk_umem) {
+ ring->zca.free = ixgbe_zca_free;
+ WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_ZERO_COPY,
+ &ring->zca));
+
+ } else {
+ WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED, NULL));
+ }
+
/* disable queue to avoid use of these values while updating state */
rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
rxdctl &= ~IXGBE_RXDCTL_ENABLE;
@@ -4082,6 +4133,17 @@
#endif
}
+ if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) {
+ u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr -
+ XDP_PACKET_HEADROOM;
+
+ rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
+ IXGBE_RXDCTL_RLPML_EN);
+ rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN;
+
+ ring->rx_buf_len = xsk_buf_len;
+ }
+
/* initialize rx_buffer_info */
memset(ring->rx_buffer_info, 0,
sizeof(struct ixgbe_rx_buffer) * ring->count);
@@ -4095,7 +4157,10 @@
IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
ixgbe_rx_desc_queue_enable(adapter, ring);
- ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
+ if (ring->xsk_umem)
+ ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring));
+ else
+ ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
}
static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
@@ -4245,7 +4310,6 @@
if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
- clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
continue;
@@ -5175,6 +5239,7 @@
struct ixgbe_hw *hw = &adapter->hw;
struct hlist_node *node2;
struct ixgbe_fdir_filter *filter;
+ u64 action;
spin_lock(&adapter->fdir_perfect_lock);
@@ -5183,12 +5248,17 @@
hlist_for_each_entry_safe(filter, node2,
&adapter->fdir_filter_list, fdir_node) {
+ action = filter->action;
+ if (action != IXGBE_FDIR_DROP_QUEUE && action != 0)
+ action =
+ (action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1;
+
ixgbe_fdir_write_perfect_filter_82599(hw,
&filter->filter,
filter->sw_idx,
- (filter->action == IXGBE_FDIR_DROP_QUEUE) ?
+ (action == IXGBE_FDIR_DROP_QUEUE) ?
IXGBE_FDIR_DROP_QUEUE :
- adapter->rx_ring[filter->action]->reg_idx);
+ adapter->rx_ring[action]->reg_idx);
}
spin_unlock(&adapter->fdir_perfect_lock);
@@ -5203,6 +5273,11 @@
u16 i = rx_ring->next_to_clean;
struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
+ if (rx_ring->xsk_umem) {
+ ixgbe_xsk_clean_rx_ring(rx_ring);
+ goto skip_free;
+ }
+
/* Free all the Rx ring sk_buffs */
while (i != rx_ring->next_to_alloc) {
if (rx_buffer->skb) {
@@ -5241,6 +5316,7 @@
}
}
+skip_free:
rx_ring->next_to_alloc = 0;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
@@ -5885,6 +5961,11 @@
u16 i = tx_ring->next_to_clean;
struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+ if (tx_ring->xsk_umem) {
+ ixgbe_xsk_clean_tx_ring(tx_ring);
+ goto out;
+ }
+
while (i != tx_ring->next_to_use) {
union ixgbe_adv_tx_desc *eop_desc, *tx_desc;
@@ -5936,6 +6017,7 @@
if (!ring_is_xdp(tx_ring))
netdev_tx_reset_queue(txring_txq(tx_ring));
+out:
/* reset next_to_use and next_to_clean */
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
@@ -6004,9 +6086,9 @@
/* Disable Rx */
ixgbe_disable_rx(adapter);
- /* synchronize_sched() needed for pending XDP buffers to drain */
+ /* synchronize_rcu() needed for pending XDP buffers to drain */
if (adapter->xdp_ring[0])
- synchronize_sched();
+ synchronize_rcu();
ixgbe_irq_disable(adapter);
@@ -6210,6 +6292,10 @@
if (ixgbe_init_rss_key(adapter))
return -ENOMEM;
+ adapter->af_xdp_zc_qps = bitmap_zalloc(MAX_XDP_QUEUES, GFP_KERNEL);
+ if (!adapter->af_xdp_zc_qps)
+ return -ENOMEM;
+
/* Set MAC specific capability flags and exceptions */
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
@@ -6341,7 +6427,7 @@
{
struct device *dev = tx_ring->dev;
int orig_node = dev_to_node(dev);
- int ring_node = -1;
+ int ring_node = NUMA_NO_NODE;
int size;
size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -6435,8 +6521,8 @@
{
struct device *dev = rx_ring->dev;
int orig_node = dev_to_node(dev);
- int ring_node = -1;
- int size, err;
+ int ring_node = NUMA_NO_NODE;
+ int size;
size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
@@ -6473,13 +6559,6 @@
rx_ring->queue_index) < 0)
goto err;
- err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq,
- MEM_TYPE_PAGE_SHARED, NULL);
- if (err) {
- xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
- goto err;
- }
-
rx_ring->xdp_prog = adapter->xdp_prog;
return 0;
@@ -7777,6 +7856,33 @@
}
/**
+ * ixgbe_check_fw_error - Check firmware for errors
+ * @adapter: the adapter private structure
+ *
+ * Check firmware errors in register FWSM
+ */
+static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 fwsm;
+
+ /* read fwsm.ext_err_ind register and log errors */
+ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+
+ if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
+ !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
+ e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
+ fwsm);
+
+ if (hw->mac.ops.fw_recovery_mode && hw->mac.ops.fw_recovery_mode(hw)) {
+ e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+ return true;
+ }
+
+ return false;
+}
+
+/**
* ixgbe_service_task - manages and runs subtasks
* @work: pointer to work_struct containing our data
**/
@@ -7794,6 +7900,12 @@
ixgbe_service_event_complete(adapter);
return;
}
+ if (ixgbe_check_fw_error(adapter)) {
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ unregister_netdev(adapter->netdev);
+ ixgbe_service_event_complete(adapter);
+ return;
+ }
if (adapter->flags2 & IXGBE_FLAG2_UDP_TUN_REREG_NEEDED) {
rtnl_lock();
adapter->flags2 &= ~IXGBE_FLAG2_UDP_TUN_REREG_NEEDED;
@@ -8068,9 +8180,6 @@
return __ixgbe_maybe_stop_tx(tx_ring, size);
}
-#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
- IXGBE_TXD_CMD_RS)
-
static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
struct ixgbe_tx_buffer *first,
const u8 hdr_len)
@@ -8078,7 +8187,7 @@
struct sk_buff *skb = first->skb;
struct ixgbe_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
dma_addr_t dma;
unsigned int data_len, size;
u32 tx_flags = first->tx_flags;
@@ -8170,6 +8279,8 @@
/* set the timestamp */
first->time_stamp = jiffies;
+ skb_tx_timestamp(skb);
+
/*
* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch. (Only applicable for weak-ordered
@@ -8191,13 +8302,8 @@
ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return 0;
@@ -8377,8 +8483,7 @@
#ifdef IXGBE_FCOE
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
- struct net_device *sb_dev,
- select_queue_fallback_t fallback)
+ struct net_device *sb_dev)
{
struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
@@ -8408,7 +8513,7 @@
break;
/* fall through */
default:
- return fallback(dev, skb, sb_dev);
+ return netdev_pick_tx(dev, skb, sb_dev);
}
f = &adapter->ring_feature[RING_F_FCOE];
@@ -8423,8 +8528,8 @@
}
#endif
-static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_frame *xdpf)
+int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
+ struct xdp_frame *xdpf)
{
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
struct ixgbe_tx_buffer *tx_buffer;
@@ -8501,7 +8606,8 @@
* otherwise try next time
*/
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
- count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+ count += TXD_USE_COUNT(skb_frag_size(
+ &skb_shinfo(skb)->frags[f]));
if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) {
tx_ring->tx_stats.tx_busy++;
@@ -8547,8 +8653,6 @@
}
}
- skb_tx_timestamp(skb);
-
#ifdef CONFIG_PCI_IOV
/*
* Use the l2switch_enable flag - would be false if the DMA
@@ -8595,8 +8699,9 @@
#endif /* IXGBE_FCOE */
-#ifdef CONFIG_XFRM_OFFLOAD
- if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
+#ifdef CONFIG_IXGBE_IPSEC
+ if (xfrm_offload(skb) &&
+ !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
goto out_drop;
#endif
tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
@@ -8645,7 +8750,9 @@
if (skb_put_padto(skb, 17))
return NETDEV_TX_OK;
- tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping];
+ tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)];
+ if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state)))
+ return NETDEV_TX_BUSY;
return ixgbe_xmit_frame_ring(skb, adapter, tx_ring);
}
@@ -8688,6 +8795,15 @@
u16 value;
int rc;
+ if (adapter->mii_bus) {
+ int regnum = addr;
+
+ if (devad != MDIO_DEVAD_NONE)
+ regnum |= (devad << 16) | MII_ADDR_C45;
+
+ return mdiobus_read(adapter->mii_bus, prtad, regnum);
+ }
+
if (prtad != hw->phy.mdio.prtad)
return -EINVAL;
rc = hw->phy.ops.read_reg(hw, addr, devad, &value);
@@ -8702,6 +8818,15 @@
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
+ if (adapter->mii_bus) {
+ int regnum = addr;
+
+ if (devad != MDIO_DEVAD_NONE)
+ regnum |= (devad << 16) | MII_ADDR_C45;
+
+ return mdiobus_write(adapter->mii_bus, prtad, regnum, value);
+ }
+
if (prtad != hw->phy.mdio.prtad)
return -EINVAL;
return hw->phy.ops.write_reg(hw, addr, devad, value);
@@ -9367,6 +9492,10 @@
jump->mat = nexthdr[i].jump;
adapter->jump_tables[link_uhtid] = jump;
break;
+ } else {
+ kfree(mask);
+ kfree(input);
+ kfree(jump);
}
}
return 0;
@@ -9484,27 +9613,6 @@
}
}
-static int ixgbe_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int ixgbe_setup_tc_mqprio(struct net_device *dev,
struct tc_mqprio_qopt *mqprio)
{
@@ -9512,12 +9620,19 @@
return ixgbe_setup_tc(dev, mqprio->num_tc);
}
+static LIST_HEAD(ixgbe_block_cb_list);
+
static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return ixgbe_setup_tc_block(dev, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &ixgbe_block_cb_list,
+ ixgbe_setup_tc_block_cb,
+ adapter, adapter, true);
case TC_SETUP_QDISC_MQPRIO:
return ixgbe_setup_tc_mqprio(dev, type_data);
default:
@@ -9671,7 +9786,7 @@
NETIF_F_HW_VLAN_CTAG_FILTER))
ixgbe_set_rx_mode(netdev);
- return 0;
+ return 1;
}
/**
@@ -9789,7 +9904,8 @@
static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
/* guarantee we can provide a unique filter for the unicast address */
if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -9878,7 +9994,8 @@
}
static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags)
+ struct nlmsghdr *nlh, u16 flags,
+ struct netlink_ext_ack *extack)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct nlattr *attr, *br_spec;
@@ -10089,8 +10206,8 @@
* the TSO, so it's the exception.
*/
if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
-#ifdef CONFIG_XFRM_OFFLOAD
- if (!skb->sp)
+#ifdef CONFIG_IXGBE_IPSEC
+ if (!secpath_exists(skb))
#endif
features &= ~NETIF_F_TSO;
}
@@ -10103,6 +10220,7 @@
int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct bpf_prog *old_prog;
+ bool need_reset;
if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
return -EINVAL;
@@ -10125,9 +10243,10 @@
return -ENOMEM;
old_prog = xchg(&adapter->xdp_prog, prog);
+ need_reset = (!!prog != !!old_prog);
/* If transitioning XDP modes reconfigure rings */
- if (!!prog != !!old_prog) {
+ if (need_reset) {
int err = ixgbe_setup_tc(dev, adapter->hw_tcs);
if (err) {
@@ -10143,6 +10262,15 @@
if (old_prog)
bpf_prog_put(old_prog);
+ /* Kick start the NAPI context if there is an AF_XDP socket open
+ * on that queue id. This so that receiving will start.
+ */
+ if (need_reset && prog)
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ if (adapter->xdp_ring[i]->xsk_umem)
+ (void)ixgbe_xsk_wakeup(adapter->netdev, i,
+ XDP_WAKEUP_RX);
+
return 0;
}
@@ -10157,12 +10285,16 @@
xdp->prog_id = adapter->xdp_prog ?
adapter->xdp_prog->aux->id : 0;
return 0;
+ case XDP_SETUP_XSK_UMEM:
+ return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
+ xdp->xsk.queue_id);
+
default:
return -EINVAL;
}
}
-static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
+void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
{
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch.
@@ -10192,6 +10324,9 @@
if (unlikely(!ring))
return -ENXIO;
+ if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state)))
+ return -ENXIO;
+
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
int err;
@@ -10253,8 +10388,163 @@
.ndo_features_check = ixgbe_features_check,
.ndo_bpf = ixgbe_xdp,
.ndo_xdp_xmit = ixgbe_xdp_xmit,
+ .ndo_xsk_wakeup = ixgbe_xsk_wakeup,
};
+static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring)
+{
+ unsigned long wait_delay, delay_interval;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u8 reg_idx = tx_ring->reg_idx;
+ int wait_loop;
+ u32 txdctl;
+
+ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+
+ /* delay mechanism from ixgbe_disable_tx */
+ delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+ wait_loop = IXGBE_MAX_RX_DESC_POLL;
+ wait_delay = delay_interval;
+
+ while (wait_loop--) {
+ usleep_range(wait_delay, wait_delay + 10);
+ wait_delay += delay_interval * 2;
+ txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+
+ if (!(txdctl & IXGBE_TXDCTL_ENABLE))
+ return;
+ }
+
+ e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n");
+}
+
+static void ixgbe_disable_txr(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring)
+{
+ set_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
+ ixgbe_disable_txr_hw(adapter, tx_ring);
+}
+
+static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *rx_ring)
+{
+ unsigned long wait_delay, delay_interval;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u8 reg_idx = rx_ring->reg_idx;
+ int wait_loop;
+ u32 rxdctl;
+
+ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+ rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+ rxdctl |= IXGBE_RXDCTL_SWFLSH;
+
+ /* write value back with RXDCTL.ENABLE bit cleared */
+ IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+
+ /* RXDCTL.EN may not change on 82598 if link is down, so skip it */
+ if (hw->mac.type == ixgbe_mac_82598EB &&
+ !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+ return;
+
+ /* delay mechanism from ixgbe_disable_rx */
+ delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+ wait_loop = IXGBE_MAX_RX_DESC_POLL;
+ wait_delay = delay_interval;
+
+ while (wait_loop--) {
+ usleep_range(wait_delay, wait_delay + 10);
+ wait_delay += delay_interval * 2;
+ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+
+ if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
+ return;
+ }
+
+ e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n");
+}
+
+static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring)
+{
+ memset(&tx_ring->stats, 0, sizeof(tx_ring->stats));
+ memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
+}
+
+static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring)
+{
+ memset(&rx_ring->stats, 0, sizeof(rx_ring->stats));
+ memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
+}
+
+/**
+ * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings
+ * @adapter: adapter structure
+ * @ring: ring index
+ *
+ * This function disables a certain Rx/Tx/XDP Tx ring. The function
+ * assumes that the netdev is running.
+ **/
+void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
+{
+ struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
+
+ rx_ring = adapter->rx_ring[ring];
+ tx_ring = adapter->tx_ring[ring];
+ xdp_ring = adapter->xdp_ring[ring];
+
+ ixgbe_disable_txr(adapter, tx_ring);
+ if (xdp_ring)
+ ixgbe_disable_txr(adapter, xdp_ring);
+ ixgbe_disable_rxr_hw(adapter, rx_ring);
+
+ if (xdp_ring)
+ synchronize_rcu();
+
+ /* Rx/Tx/XDP Tx share the same napi context. */
+ napi_disable(&rx_ring->q_vector->napi);
+
+ ixgbe_clean_tx_ring(tx_ring);
+ if (xdp_ring)
+ ixgbe_clean_tx_ring(xdp_ring);
+ ixgbe_clean_rx_ring(rx_ring);
+
+ ixgbe_reset_txr_stats(tx_ring);
+ if (xdp_ring)
+ ixgbe_reset_txr_stats(xdp_ring);
+ ixgbe_reset_rxr_stats(rx_ring);
+}
+
+/**
+ * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings
+ * @adapter: adapter structure
+ * @ring: ring index
+ *
+ * This function enables a certain Rx/Tx/XDP Tx ring. The function
+ * assumes that the netdev is running.
+ **/
+void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
+{
+ struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
+
+ rx_ring = adapter->rx_ring[ring];
+ tx_ring = adapter->tx_ring[ring];
+ xdp_ring = adapter->xdp_ring[ring];
+
+ /* Rx/Tx/XDP Tx share the same napi context. */
+ napi_enable(&rx_ring->q_vector->napi);
+
+ ixgbe_configure_tx_ring(adapter, tx_ring);
+ if (xdp_ring)
+ ixgbe_configure_tx_ring(adapter, xdp_ring);
+ ixgbe_configure_rx_ring(adapter, rx_ring);
+
+ clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
+ if (xdp_ring)
+ clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+}
+
/**
* ixgbe_enumerate_functions - Get the number of ports this device has
* @adapter: adapter structure
@@ -10618,7 +10908,7 @@
if (hw->mac.type >= ixgbe_mac_82599EB)
netdev->features |= NETIF_F_SCTP_CRC;
-#ifdef CONFIG_XFRM_OFFLOAD
+#ifdef CONFIG_IXGBE_IPSEC
#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
NETIF_F_HW_ESP_TX_CSUM | \
NETIF_F_GSO_ESP)
@@ -10693,6 +10983,11 @@
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
netdev->features |= NETIF_F_LRO;
+ if (ixgbe_check_fw_error(adapter)) {
+ err = -EIO;
+ goto err_sw_init;
+ }
+
/* make sure the EEPROM is good */
if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
e_dev_err("The EEPROM Checksum Is Not Valid\n");
@@ -10849,6 +11144,8 @@
IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
true);
+ ixgbe_mii_bus_init(hw);
+
return 0;
err_register:
@@ -10861,6 +11158,7 @@
kfree(adapter->jump_tables[0]);
kfree(adapter->mac_table);
kfree(adapter->rss_key);
+ bitmap_free(adapter->af_xdp_zc_qps);
err_ioremap:
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
@@ -10899,6 +11197,8 @@
set_bit(__IXGBE_REMOVING, &adapter->state);
cancel_work_sync(&adapter->service_task);
+ if (adapter->mii_bus)
+ mdiobus_unregister(adapter->mii_bus);
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
@@ -10947,6 +11247,7 @@
kfree(adapter->mac_table);
kfree(adapter->rss_key);
+ bitmap_free(adapter->af_xdp_zc_qps);
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
@@ -11052,8 +11353,6 @@
/* Free device reference count */
pci_dev_put(vfdev);
}
-
- pci_cleanup_aer_uncorrect_error_status(pdev);
}
/*
@@ -11103,7 +11402,6 @@
{
struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
pci_ers_result_t result;
- int err;
if (pci_enable_device_mem(pdev)) {
e_err(probe, "Cannot re-enable PCI device after reset.\n");
@@ -11123,13 +11421,6 @@
result = PCI_ERS_RESULT_RECOVERED;
}
- err = pci_cleanup_aer_uncorrect_error_status(pdev);
- if (err) {
- e_dev_err("pci_cleanup_aer_uncorrect_error_status "
- "failed 0x%0x\n", err);
- /* non-fatal, continue */
- }
-
return result;
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index e085b65..a148534 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -50,6 +50,7 @@
ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */
ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */
ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */
+ ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */
/* This value should always be last */
ixgbe_mbox_api_unknown, /* indicates that API version is not known */
};
@@ -80,6 +81,10 @@
#define IXGBE_VF_UPDATE_XCAST_MODE 0x0c
+/* mailbox API, version 1.4 VF requests */
+#define IXGBE_VF_IPSEC_ADD 0x0d
+#define IXGBE_VF_IPSEC_DEL 0x0e
+
/* length of permanent address message returned from PF */
#define IXGBE_VF_PERMADDR_MSG_LEN 4
/* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 919a7af..2fb9796 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -3,6 +3,7 @@
#include <linux/pci.h>
#include <linux/delay.h>
+#include <linux/iopoll.h>
#include <linux/sched.h>
#include "ixgbe.h"
@@ -658,6 +659,306 @@
return status;
}
+#define IXGBE_HW_READ_REG(addr) IXGBE_READ_REG(hw, addr)
+
+/**
+ * ixgbe_msca_cmd - Write the command register and poll for completion/timeout
+ * @hw: pointer to hardware structure
+ * @cmd: command register value to write
+ **/
+static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd)
+{
+ IXGBE_WRITE_REG(hw, IXGBE_MSCA, cmd);
+
+ return readx_poll_timeout(IXGBE_HW_READ_REG, IXGBE_MSCA, cmd,
+ !(cmd & IXGBE_MSCA_MDI_COMMAND), 10,
+ 10 * IXGBE_MDIO_COMMAND_TIMEOUT);
+}
+
+/**
+ * ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ * @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr,
+ int regnum, u32 gssr)
+{
+ u32 hwaddr, cmd;
+ s32 data;
+
+ if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+ return -EBUSY;
+
+ hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+ if (regnum & MII_ADDR_C45) {
+ hwaddr |= regnum & GENMASK(21, 0);
+ cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+ } else {
+ hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+ cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL |
+ IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND;
+ }
+
+ data = ixgbe_msca_cmd(hw, cmd);
+ if (data < 0)
+ goto mii_bus_read_done;
+
+ /* For a clause 45 access the address cycle just completed, we still
+ * need to do the read command, otherwise just get the data
+ */
+ if (!(regnum & MII_ADDR_C45))
+ goto do_mii_bus_read;
+
+ cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND;
+ data = ixgbe_msca_cmd(hw, cmd);
+ if (data < 0)
+ goto mii_bus_read_done;
+
+do_mii_bus_read:
+ data = IXGBE_READ_REG(hw, IXGBE_MSRWD);
+ data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0);
+
+mii_bus_read_done:
+ hw->mac.ops.release_swfw_sync(hw, gssr);
+ return data;
+}
+
+/**
+ * ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ * @val: value to write
+ * @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr,
+ int regnum, u16 val, u32 gssr)
+{
+ u32 hwaddr, cmd;
+ s32 err;
+
+ if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+ return -EBUSY;
+
+ IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val);
+
+ hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+ if (regnum & MII_ADDR_C45) {
+ hwaddr |= regnum & GENMASK(21, 0);
+ cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+ } else {
+ hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+ cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE |
+ IXGBE_MSCA_MDI_COMMAND;
+ }
+
+ /* For clause 45 this is an address cycle, for clause 22 this is the
+ * entire transaction
+ */
+ err = ixgbe_msca_cmd(hw, cmd);
+ if (err < 0 || !(regnum & MII_ADDR_C45))
+ goto mii_bus_write_done;
+
+ cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND;
+ err = ixgbe_msca_cmd(hw, cmd);
+
+mii_bus_write_done:
+ hw->mac.ops.release_swfw_sync(hw, gssr);
+ return err;
+}
+
+/**
+ * ixgbe_mii_bus_read - Read a clause 22/45 register
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ **/
+static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
+{
+ struct ixgbe_adapter *adapter = bus->priv;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 gssr = hw->phy.phy_semaphore_mask;
+
+ return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ * ixgbe_mii_bus_write - Write a clause 22/45 register
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ * @val: value to write
+ **/
+static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum,
+ u16 val)
+{
+ struct ixgbe_adapter *adapter = bus->priv;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 gssr = hw->phy.phy_semaphore_mask;
+
+ return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ * ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ **/
+static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr,
+ int regnum)
+{
+ struct ixgbe_adapter *adapter = bus->priv;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 gssr = hw->phy.phy_semaphore_mask;
+
+ gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+ return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ * ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a
+ * @hw: pointer to hardware structure
+ * @addr: address
+ * @regnum: register number
+ * @val: value to write
+ **/
+static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr,
+ int regnum, u16 val)
+{
+ struct ixgbe_adapter *adapter = bus->priv;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 gssr = hw->phy.phy_semaphore_mask;
+
+ gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+ return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ * ixgbe_get_first_secondary_devfn - get first device downstream of root port
+ * @devfn: PCI_DEVFN of root port on domain 0, bus 0
+ *
+ * Returns pci_dev pointer to PCI_DEVFN(0, 0) on subordinate side of root
+ * on domain 0, bus 0, devfn = 'devfn'
+ **/
+static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn)
+{
+ struct pci_dev *rp_pdev;
+ int bus;
+
+ rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
+ if (rp_pdev && rp_pdev->subordinate) {
+ bus = rp_pdev->subordinate->number;
+ return pci_get_domain_bus_and_slot(0, bus, 0);
+ }
+
+ return NULL;
+}
+
+/**
+ * ixgbe_x550em_a_has_mii - is this the first ixgbe x550em_a PCI function?
+ * @hw: pointer to hardware structure
+ *
+ * Returns true if hw points to lowest numbered PCI B:D.F x550_em_a device in
+ * the SoC. There are up to 4 MACs sharing a single MDIO bus on the x550em_a,
+ * but we only want to register one MDIO bus.
+ **/
+static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw)
+{
+ struct ixgbe_adapter *adapter = hw->back;
+ struct pci_dev *pdev = adapter->pdev;
+ struct pci_dev *func0_pdev;
+
+ /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
+ * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
+ * It's not valid for function 0 to be disabled and function 1 is up,
+ * so the lowest numbered ixgbe dev will be device 0 function 0 on one
+ * of those two root ports
+ */
+ func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
+ if (func0_pdev) {
+ if (func0_pdev == pdev)
+ return true;
+ else
+ return false;
+ }
+ func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
+ if (func0_pdev == pdev)
+ return true;
+
+ return false;
+}
+
+/**
+ * ixgbe_mii_bus_init - mii_bus structure setup
+ * @hw: pointer to hardware structure
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * ixgbe_mii_bus_init initializes a mii_bus structure in adapter
+ **/
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
+{
+ struct ixgbe_adapter *adapter = hw->back;
+ struct pci_dev *pdev = adapter->pdev;
+ struct device *dev = &adapter->netdev->dev;
+ struct mii_bus *bus;
+ int err = -ENODEV;
+
+ bus = devm_mdiobus_alloc(dev);
+ if (!bus)
+ return -ENOMEM;
+
+ switch (hw->device_id) {
+ /* C3000 SoCs */
+ case IXGBE_DEV_ID_X550EM_A_KR:
+ case IXGBE_DEV_ID_X550EM_A_KR_L:
+ case IXGBE_DEV_ID_X550EM_A_SFP_N:
+ case IXGBE_DEV_ID_X550EM_A_SGMII:
+ case IXGBE_DEV_ID_X550EM_A_SGMII_L:
+ case IXGBE_DEV_ID_X550EM_A_10G_T:
+ case IXGBE_DEV_ID_X550EM_A_SFP:
+ case IXGBE_DEV_ID_X550EM_A_1G_T:
+ case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+ if (!ixgbe_x550em_a_has_mii(hw))
+ goto ixgbe_no_mii_bus;
+ bus->read = &ixgbe_x550em_a_mii_bus_read;
+ bus->write = &ixgbe_x550em_a_mii_bus_write;
+ break;
+ default:
+ bus->read = &ixgbe_mii_bus_read;
+ bus->write = &ixgbe_mii_bus_write;
+ break;
+ }
+
+ /* Use the position of the device in the PCI hierarchy as the id */
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name,
+ pci_name(pdev));
+
+ bus->name = "ixgbe-mdio";
+ bus->priv = adapter;
+ bus->parent = dev;
+ bus->phy_mask = GENMASK(31, 0);
+
+ /* Support clause 22/45 natively. ixgbe_probe() sets MDIO_EMULATE_C22
+ * unfortunately that causes some clause 22 frames to be sent with
+ * clause 45 addressing. We don't want that.
+ */
+ hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
+
+ err = mdiobus_register(bus);
+ if (!err) {
+ adapter->mii_bus = bus;
+ return 0;
+ }
+
+ixgbe_no_mii_bus:
+ devm_mdiobus_free(dev, bus);
+ return err;
+}
+
/**
* ixgbe_setup_phy_link_generic - Set and restart autoneg
* @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 64e44e0..6544c45 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -45,6 +45,7 @@
#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8
#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0
#define IXGBE_SFF_ADDRESSING_MODE 0x4
+#define IXGBE_SFF_DDM_IMPLEMENTED 0x40
#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1
#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8
#define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE 0x23
@@ -120,6 +121,8 @@
/* SFP+ SFF-8472 Compliance code */
#define IXGBE_SFF_SFF_8472_UNSUP 0x00
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw);
+
s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw);
s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw);
s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index b3e0d8b..0be13a9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -72,13 +72,13 @@
#define IXGBE_INCPER_SHIFT_82599 24
#define IXGBE_OVERFLOW_PERIOD (HZ * 30)
-#define IXGBE_PTP_TX_TIMEOUT (HZ * 15)
+#define IXGBE_PTP_TX_TIMEOUT (HZ)
-/* half of a one second clock period, for use with PPS signal. We have to use
- * this instead of something pre-defined like IXGBE_PTP_PPS_HALF_SECOND, in
- * order to force at least 64bits of precision for shifting
+/* We use our own definitions instead of NSEC_PER_SEC because we want to mark
+ * the value as a ULL to force precision when bit shifting.
*/
-#define IXGBE_PTP_PPS_HALF_SECOND 500000000ULL
+#define NS_PER_SEC 1000000000ULL
+#define NS_PER_HALF_SEC 500000000ULL
/* In contrast, the X550 controller has two registers, SYSTIMEH and SYSTIMEL
* which contain measurements of seconds and nanoseconds respectively. This
@@ -141,23 +141,26 @@
#define MAX_TIMADJ 0x7FFFFFFF
/**
- * ixgbe_ptp_setup_sdp_x540
+ * ixgbe_ptp_setup_sdp_X540
* @adapter: private adapter structure
*
* this function enables or disables the clock out feature on SDP0 for
- * the X540 device. It will create a 1second periodic output that can
+ * the X540 device. It will create a 1 second periodic output that can
* be used as the PPS (via an interrupt).
*
- * It calculates when the systime will be on an exact second, and then
- * aligns the start of the PPS signal to that value. The shift is
- * necessary because it can change based on the link speed.
+ * It calculates when the system time will be on an exact second, and then
+ * aligns the start of the PPS signal to that value.
+ *
+ * This works by using the cycle counter shift and mult values in reverse, and
+ * assumes that the values we're shifting will not overflow.
*/
-static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
+static void ixgbe_ptp_setup_sdp_X540(struct ixgbe_adapter *adapter)
{
+ struct cyclecounter *cc = &adapter->hw_cc;
struct ixgbe_hw *hw = &adapter->hw;
- int shift = adapter->hw_cc.shift;
u32 esdp, tsauxc, clktiml, clktimh, trgttiml, trgttimh, rem;
- u64 ns = 0, clock_edge = 0;
+ u64 ns = 0, clock_edge = 0, clock_period;
+ unsigned long flags;
/* disable the pin first */
IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0);
@@ -177,26 +180,33 @@
/* enable the Clock Out feature on SDP0, and allow
* interrupts to occur when the pin changes
*/
- tsauxc = IXGBE_TSAUXC_EN_CLK |
- IXGBE_TSAUXC_SYNCLK |
- IXGBE_TSAUXC_SDP0_INT;
+ tsauxc = (IXGBE_TSAUXC_EN_CLK |
+ IXGBE_TSAUXC_SYNCLK |
+ IXGBE_TSAUXC_SDP0_INT);
- /* clock period (or pulse length) */
- clktiml = (u32)(IXGBE_PTP_PPS_HALF_SECOND << shift);
- clktimh = (u32)((IXGBE_PTP_PPS_HALF_SECOND << shift) >> 32);
-
- /* Account for the cyclecounter wrap-around value by
- * using the converted ns value of the current time to
- * check for when the next aligned second would occur.
+ /* Determine the clock time period to use. This assumes that the
+ * cycle counter shift is small enough to avoid overflow.
*/
- clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIML);
- clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32;
- ns = timecounter_cyc2time(&adapter->hw_tc, clock_edge);
+ clock_period = div_u64((NS_PER_HALF_SEC << cc->shift), cc->mult);
+ clktiml = (u32)(clock_period);
+ clktimh = (u32)(clock_period >> 32);
- div_u64_rem(ns, IXGBE_PTP_PPS_HALF_SECOND, &rem);
- clock_edge += ((IXGBE_PTP_PPS_HALF_SECOND - (u64)rem) << shift);
+ /* Read the current clock time, and save the cycle counter value */
+ spin_lock_irqsave(&adapter->tmreg_lock, flags);
+ ns = timecounter_read(&adapter->hw_tc);
+ clock_edge = adapter->hw_tc.cycle_last;
+ spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
- /* specify the initial clock start time */
+ /* Figure out how many seconds to add in order to round up */
+ div_u64_rem(ns, NS_PER_SEC, &rem);
+
+ /* Figure out how many nanoseconds to add to round the clock edge up
+ * to the next full second
+ */
+ rem = (NS_PER_SEC - rem);
+
+ /* Adjust the clock edge to align with the next full second. */
+ clock_edge += div_u64(((u64)rem << cc->shift), cc->mult);
trgttiml = (u32)clock_edge;
trgttimh = (u32)(clock_edge >> 32);
@@ -212,8 +222,100 @@
}
/**
+ * ixgbe_ptp_setup_sdp_X550
+ * @adapter: private adapter structure
+ *
+ * Enable or disable a clock output signal on SDP 0 for X550 hardware.
+ *
+ * Use the target time feature to align the output signal on the next full
+ * second.
+ *
+ * This works by using the cycle counter shift and mult values in reverse, and
+ * assumes that the values we're shifting will not overflow.
+ */
+static void ixgbe_ptp_setup_sdp_X550(struct ixgbe_adapter *adapter)
+{
+ u32 esdp, tsauxc, freqout, trgttiml, trgttimh, rem, tssdp;
+ struct cyclecounter *cc = &adapter->hw_cc;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u64 ns = 0, clock_edge = 0;
+ struct timespec64 ts;
+ unsigned long flags;
+
+ /* disable the pin first */
+ IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0);
+ IXGBE_WRITE_FLUSH(hw);
+
+ if (!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED))
+ return;
+
+ esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
+
+ /* enable the SDP0 pin as output, and connected to the
+ * native function for Timesync (ClockOut)
+ */
+ esdp |= IXGBE_ESDP_SDP0_DIR |
+ IXGBE_ESDP_SDP0_NATIVE;
+
+ /* enable the Clock Out feature on SDP0, and use Target Time 0 to
+ * enable generation of interrupts on the clock change.
+ */
+#define IXGBE_TSAUXC_DIS_TS_CLEAR 0x40000000
+ tsauxc = (IXGBE_TSAUXC_EN_CLK | IXGBE_TSAUXC_ST0 |
+ IXGBE_TSAUXC_EN_TT0 | IXGBE_TSAUXC_SDP0_INT |
+ IXGBE_TSAUXC_DIS_TS_CLEAR);
+
+ tssdp = (IXGBE_TSSDP_TS_SDP0_EN |
+ IXGBE_TSSDP_TS_SDP0_CLK0);
+
+ /* Determine the clock time period to use. This assumes that the
+ * cycle counter shift is small enough to avoid overflowing a 32bit
+ * value.
+ */
+ freqout = div_u64(NS_PER_HALF_SEC << cc->shift, cc->mult);
+
+ /* Read the current clock time, and save the cycle counter value */
+ spin_lock_irqsave(&adapter->tmreg_lock, flags);
+ ns = timecounter_read(&adapter->hw_tc);
+ clock_edge = adapter->hw_tc.cycle_last;
+ spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+ /* Figure out how far past the next second we are */
+ div_u64_rem(ns, NS_PER_SEC, &rem);
+
+ /* Figure out how many nanoseconds to add to round the clock edge up
+ * to the next full second
+ */
+ rem = (NS_PER_SEC - rem);
+
+ /* Adjust the clock edge to align with the next full second. */
+ clock_edge += div_u64(((u64)rem << cc->shift), cc->mult);
+
+ /* X550 hardware stores the time in 32bits of 'billions of cycles' and
+ * 32bits of 'cycles'. There's no guarantee that cycles represents
+ * nanoseconds. However, we can use the math from a timespec64 to
+ * convert into the hardware representation.
+ *
+ * See ixgbe_ptp_read_X550() for more details.
+ */
+ ts = ns_to_timespec64(clock_edge);
+ trgttiml = (u32)ts.tv_nsec;
+ trgttimh = (u32)ts.tv_sec;
+
+ IXGBE_WRITE_REG(hw, IXGBE_FREQOUT0, freqout);
+ IXGBE_WRITE_REG(hw, IXGBE_TRGTTIML0, trgttiml);
+ IXGBE_WRITE_REG(hw, IXGBE_TRGTTIMH0, trgttimh);
+
+ IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp);
+ IXGBE_WRITE_REG(hw, IXGBE_TSSDP, tssdp);
+ IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc);
+
+ IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
* ixgbe_ptp_read_X550 - read cycle counter value
- * @hw_cc: cyclecounter structure
+ * @cc: cyclecounter structure
*
* This function reads SYSTIME registers. It is called by the cyclecounter
* structure to convert from internal representation into nanoseconds. We need
@@ -221,10 +323,10 @@
* result of SYSTIME is 32bits of "billions of cycles" and 32 bits of
* "cycles", rather than seconds and nanoseconds.
*/
-static u64 ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc)
+static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
{
struct ixgbe_adapter *adapter =
- container_of(hw_cc, struct ixgbe_adapter, hw_cc);
+ container_of(cc, struct ixgbe_adapter, hw_cc);
struct ixgbe_hw *hw = &adapter->hw;
struct timespec64 ts;
@@ -443,22 +545,52 @@
}
/**
- * ixgbe_ptp_gettime
+ * ixgbe_ptp_gettimex
* @ptp: the ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec to hold the PHC timestamp
+ * @sts: structure to hold the system time before and after reading the PHC
*
* read the timecounter and return the correct value on ns,
* after converting it into a struct timespec.
*/
-static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
{
struct ixgbe_adapter *adapter =
container_of(ptp, struct ixgbe_adapter, ptp_caps);
+ struct ixgbe_hw *hw = &adapter->hw;
unsigned long flags;
- u64 ns;
+ u64 ns, stamp;
spin_lock_irqsave(&adapter->tmreg_lock, flags);
- ns = timecounter_read(&adapter->hw_tc);
+
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_X550:
+ case ixgbe_mac_X550EM_x:
+ case ixgbe_mac_x550em_a:
+ /* Upper 32 bits represent billions of cycles, lower 32 bits
+ * represent cycles. However, we use timespec64_to_ns for the
+ * correct math even though the units haven't been corrected
+ * yet.
+ */
+ ptp_read_system_prets(sts);
+ IXGBE_READ_REG(hw, IXGBE_SYSTIMR);
+ ptp_read_system_postts(sts);
+ ts->tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+ ts->tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH);
+ stamp = timespec64_to_ns(ts);
+ break;
+ default:
+ ptp_read_system_prets(sts);
+ stamp = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+ ptp_read_system_postts(sts);
+ stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32;
+ break;
+ }
+
+ ns = timecounter_cyc2time(&adapter->hw_tc, stamp);
+
spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
*ts = ns_to_timespec64(ns);
@@ -567,10 +699,14 @@
{
bool timeout = time_is_before_jiffies(adapter->last_overflow_check +
IXGBE_OVERFLOW_PERIOD);
- struct timespec64 ts;
+ unsigned long flags;
if (timeout) {
- ixgbe_ptp_gettime(&adapter->ptp_caps, &ts);
+ /* Update the timecounter */
+ spin_lock_irqsave(&adapter->tmreg_lock, flags);
+ timecounter_read(&adapter->hw_tc);
+ spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
adapter->last_overflow_check = jiffies;
}
}
@@ -804,6 +940,15 @@
ixgbe_ptp_convert_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
}
+/**
+ * ixgbe_ptp_get_ts_config - get current hardware timestamping configuration
+ * @adapter: pointer to adapter structure
+ * @ifr: ioctl data
+ *
+ * This function returns the current timestamping settings. Rather than
+ * attempt to deconstruct registers to fill in the values, simply keep a copy
+ * of the old settings around, and return a copy when requested.
+ */
int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
{
struct hwtstamp_config *config = &adapter->tstamp_config;
@@ -1216,10 +1361,10 @@
adapter->ptp_caps.pps = 1;
adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
- adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+ adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
- adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_x540;
+ adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X540;
break;
case ixgbe_mac_82599EB:
snprintf(adapter->ptp_caps.name,
@@ -1233,7 +1378,7 @@
adapter->ptp_caps.pps = 0;
adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
- adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+ adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
break;
@@ -1246,13 +1391,13 @@
adapter->ptp_caps.n_alarm = 0;
adapter->ptp_caps.n_ext_ts = 0;
adapter->ptp_caps.n_per_out = 0;
- adapter->ptp_caps.pps = 0;
+ adapter->ptp_caps.pps = 1;
adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550;
adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
- adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+ adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
- adapter->ptp_setup_sdp = NULL;
+ adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X550;
break;
default:
adapter->ptp_clock = NULL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index eea63a9..537dfff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -496,6 +496,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
/* Version 1.1 supports jumbo frames on VFs if PF has
* jumbo frames enabled which means legacy VFs are
* disabled
@@ -699,7 +700,6 @@
u8 num_tcs = adapter->hw_tcs;
u32 reg_val;
u32 queue;
- u32 word;
/* remove VLAN filters beloning to this VF */
ixgbe_clear_vf_vlans(adapter, vf);
@@ -730,6 +730,9 @@
/* reset multicast table array for vf */
adapter->vfinfo[vf].num_vf_mc_hashes = 0;
+ /* clear any ipsec table info */
+ ixgbe_ipsec_vf_clear(adapter, vf);
+
/* Flush and reset the mta with the new values */
ixgbe_set_rx_mode(adapter->netdev);
@@ -754,6 +757,14 @@
}
}
+ IXGBE_WRITE_FLUSH(hw);
+}
+
+static void ixgbe_vf_clear_mbx(struct ixgbe_adapter *adapter, u32 vf)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 word;
+
/* Clear VF's mailbox memory */
for (word = 0; word < IXGBE_VFMAILBOX_SIZE; word++)
IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf), word, 0);
@@ -827,6 +838,8 @@
/* reset the filters for the device */
ixgbe_vf_reset_event(adapter, vf);
+ ixgbe_vf_clear_mbx(adapter, vf);
+
/* set vf mac address */
if (!is_zero_ether_addr(vf_mac))
ixgbe_set_vf_mac(adapter, vf, vf_mac);
@@ -1002,6 +1015,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
adapter->vfinfo[vf].vf_api = api;
return 0;
default:
@@ -1027,6 +1041,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
break;
default:
return -1;
@@ -1067,6 +1082,7 @@
/* verify the PF is supporting the correct API */
switch (adapter->vfinfo[vf].vf_api) {
+ case ixgbe_mbox_api_14:
case ixgbe_mbox_api_13:
case ixgbe_mbox_api_12:
break;
@@ -1099,6 +1115,7 @@
/* verify the PF is supporting the correct API */
switch (adapter->vfinfo[vf].vf_api) {
+ case ixgbe_mbox_api_14:
case ixgbe_mbox_api_13:
case ixgbe_mbox_api_12:
break;
@@ -1124,8 +1141,9 @@
/* promisc introduced in 1.3 version */
if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC)
return -EOPNOTSUPP;
- /* Fall threw */
+ /* Fall through */
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
break;
default:
return -EOPNOTSUPP;
@@ -1251,6 +1269,12 @@
case IXGBE_VF_UPDATE_XCAST_MODE:
retval = ixgbe_update_vf_xcast_mode(adapter, msgbuf, vf);
break;
+ case IXGBE_VF_IPSEC_ADD:
+ retval = ixgbe_ipsec_vf_add_sa(adapter, msgbuf, vf);
+ break;
+ case IXGBE_VF_IPSEC_DEL:
+ retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf);
+ break;
default:
e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
retval = IXGBE_ERR_MBX;
@@ -1621,7 +1645,7 @@
IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_LLDP),
(IXGBE_ETQF_FILTER_EN |
IXGBE_ETQF_TX_ANTISPOOF |
- IXGBE_ETH_P_LLDP));
+ ETH_P_LLDP));
IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FC),
(IXGBE_ETQF_FILTER_EN |
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
new file mode 100644
index 0000000..6d01700
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Intel Corporation. */
+
+#ifndef _IXGBE_TXRX_COMMON_H_
+#define _IXGBE_TXRX_COMMON_H_
+
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED BIT(0)
+#define IXGBE_XDP_TX BIT(1)
+#define IXGBE_XDP_REDIR BIT(2)
+
+#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
+ IXGBE_TXD_CMD_RS)
+
+int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
+ struct xdp_frame *xdpf);
+bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb);
+void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb);
+void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
+ struct sk_buff *skb);
+void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring);
+void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask);
+
+void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring);
+void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring);
+
+struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *ring);
+int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
+ u16 qid);
+
+void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
+
+void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
+int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *rx_ring,
+ const int budget);
+void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring);
+bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *tx_ring, int napi_budget);
+int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring);
+
+#endif /* #define _IXGBE_TXRX_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 41bcbb3..2be1c4c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -924,6 +924,9 @@
/* Firmware Semaphore Register */
#define IXGBE_FWSM_MODE_MASK 0xE
#define IXGBE_FWSM_FW_MODE_PT 0x4
+#define IXGBE_FWSM_FW_NVM_RECOVERY_MODE BIT(5)
+#define IXGBE_FWSM_EXT_ERR_IND_MASK 0x01F80000
+#define IXGBE_FWSM_FW_VAL_BIT BIT(15)
/* ARC Subsystem registers */
#define IXGBE_HICR 0x15F00
@@ -1064,6 +1067,7 @@
#define IXGBE_AUXSTMPL1 0x08C44 /* Auxiliary Time Stamp 1 register Low - RO */
#define IXGBE_AUXSTMPH1 0x08C48 /* Auxiliary Time Stamp 1 register High - RO */
#define IXGBE_TSIM 0x08C68 /* TimeSync Interrupt Mask Register - RW */
+#define IXGBE_TSSDP 0x0003C /* TimeSync SDP Configuration Register - RW */
/* Diagnostic Registers */
#define IXGBE_RDSTATCTL 0x02C20
@@ -2237,11 +2241,18 @@
#define IXGBE_RXDCTL_RLPML_EN 0x00008000
#define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */
-#define IXGBE_TSAUXC_EN_CLK 0x00000004
-#define IXGBE_TSAUXC_SYNCLK 0x00000008
-#define IXGBE_TSAUXC_SDP0_INT 0x00000040
+#define IXGBE_TSAUXC_EN_CLK 0x00000004
+#define IXGBE_TSAUXC_SYNCLK 0x00000008
+#define IXGBE_TSAUXC_SDP0_INT 0x00000040
+#define IXGBE_TSAUXC_EN_TT0 0x00000001
+#define IXGBE_TSAUXC_EN_TT1 0x00000002
+#define IXGBE_TSAUXC_ST0 0x00000010
#define IXGBE_TSAUXC_DISABLE_SYSTIME 0x80000000
+#define IXGBE_TSSDP_TS_SDP0_SEL_MASK 0x000000C0
+#define IXGBE_TSSDP_TS_SDP0_CLK0 0x00000080
+#define IXGBE_TSSDP_TS_SDP0_EN 0x00000100
+
#define IXGBE_TSYNCTXCTL_VALID 0x00000001 /* Tx timestamp valid */
#define IXGBE_TSYNCTXCTL_ENABLED 0x00000010 /* Tx timestamping enabled */
@@ -3461,6 +3472,7 @@
const char *);
s32 (*get_thermal_sensor_data)(struct ixgbe_hw *);
s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
+ bool (*fw_recovery_mode)(struct ixgbe_hw *hw);
void (*disable_rx)(struct ixgbe_hw *hw);
void (*enable_rx)(struct ixgbe_hw *hw);
void (*set_source_address_pruning)(struct ixgbe_hw *, bool,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 9772016..9c42f74 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -1247,6 +1247,20 @@
return 0;
}
+/**
+ * ixgbe_fw_recovery_mode - Check FW NVM recovery mode
+ * @hw: pointer t hardware structure
+ *
+ * Returns true if in FW NVM recovery mode.
+ */
+static bool ixgbe_fw_recovery_mode_X550(struct ixgbe_hw *hw)
+{
+ u32 fwsm;
+
+ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+ return !!(fwsm & IXGBE_FWSM_FW_NVM_RECOVERY_MODE);
+}
+
/** ixgbe_disable_rx_x550 - Disable RX unit
*
* Enables the Rx DMA unit for x550
@@ -3818,6 +3832,7 @@
.enable_rx_buff = &ixgbe_enable_rx_buff_generic, \
.get_thermal_sensor_data = NULL, \
.init_thermal_sensor_thresh = NULL, \
+ .fw_recovery_mode = &ixgbe_fw_recovery_mode_X550, \
.enable_rx = &ixgbe_enable_rx_generic, \
.disable_rx = &ixgbe_disable_rx_x550, \
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
new file mode 100644
index 0000000..d6feaac
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -0,0 +1,749 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
+#include <net/xdp.h>
+
+#include "ixgbe.h"
+#include "ixgbe_txrx_common.h"
+
+struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *ring)
+{
+ bool xdp_on = READ_ONCE(adapter->xdp_prog);
+ int qid = ring->ring_idx;
+
+ if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps))
+ return NULL;
+
+ return xdp_get_umem_from_qid(adapter->netdev, qid);
+}
+
+static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter,
+ struct xdp_umem *umem)
+{
+ struct device *dev = &adapter->pdev->dev;
+ unsigned int i, j;
+ dma_addr_t dma;
+
+ for (i = 0; i < umem->npgs; i++) {
+ dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
+ if (dma_mapping_error(dev, dma))
+ goto out_unmap;
+
+ umem->pages[i].dma = dma;
+ }
+
+ return 0;
+
+out_unmap:
+ for (j = 0; j < i; j++) {
+ dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
+ umem->pages[i].dma = 0;
+ }
+
+ return -1;
+}
+
+static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter,
+ struct xdp_umem *umem)
+{
+ struct device *dev = &adapter->pdev->dev;
+ unsigned int i;
+
+ for (i = 0; i < umem->npgs; i++) {
+ dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
+ DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
+
+ umem->pages[i].dma = 0;
+ }
+}
+
+static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
+ struct xdp_umem *umem,
+ u16 qid)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct xdp_umem_fq_reuse *reuseq;
+ bool if_running;
+ int err;
+
+ if (qid >= adapter->num_rx_queues)
+ return -EINVAL;
+
+ if (qid >= netdev->real_num_rx_queues ||
+ qid >= netdev->real_num_tx_queues)
+ return -EINVAL;
+
+ reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count);
+ if (!reuseq)
+ return -ENOMEM;
+
+ xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
+
+ err = ixgbe_xsk_umem_dma_map(adapter, umem);
+ if (err)
+ return err;
+
+ if_running = netif_running(adapter->netdev) &&
+ ixgbe_enabled_xdp_adapter(adapter);
+
+ if (if_running)
+ ixgbe_txrx_ring_disable(adapter, qid);
+
+ set_bit(qid, adapter->af_xdp_zc_qps);
+
+ if (if_running) {
+ ixgbe_txrx_ring_enable(adapter, qid);
+
+ /* Kick start the NAPI context so that receiving will start */
+ err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
+{
+ struct xdp_umem *umem;
+ bool if_running;
+
+ umem = xdp_get_umem_from_qid(adapter->netdev, qid);
+ if (!umem)
+ return -EINVAL;
+
+ if_running = netif_running(adapter->netdev) &&
+ ixgbe_enabled_xdp_adapter(adapter);
+
+ if (if_running)
+ ixgbe_txrx_ring_disable(adapter, qid);
+
+ clear_bit(qid, adapter->af_xdp_zc_qps);
+ ixgbe_xsk_umem_dma_unmap(adapter, umem);
+
+ if (if_running)
+ ixgbe_txrx_ring_enable(adapter, qid);
+
+ return 0;
+}
+
+int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
+ u16 qid)
+{
+ return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) :
+ ixgbe_xsk_umem_disable(adapter, qid);
+}
+
+static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *rx_ring,
+ struct xdp_buff *xdp)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ int err, result = IXGBE_XDP_PASS;
+ struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
+ u64 offset;
+ u32 act;
+
+ rcu_read_lock();
+ xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
+ offset = xdp->data - xdp->data_hard_start;
+
+ xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
+
+ switch (act) {
+ case XDP_PASS:
+ break;
+ case XDP_TX:
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf)) {
+ result = IXGBE_XDP_CONSUMED;
+ break;
+ }
+ result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+ break;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fallthrough */
+ case XDP_ABORTED:
+ trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+ /* fallthrough -- handle aborts by dropping packet */
+ case XDP_DROP:
+ result = IXGBE_XDP_CONSUMED;
+ break;
+ }
+ rcu_read_unlock();
+ return result;
+}
+
+static struct
+ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring,
+ unsigned int size)
+{
+ struct ixgbe_rx_buffer *bi;
+
+ bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+
+ /* we are reusing so sync this buffer for CPU use */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ bi->dma, 0,
+ size,
+ DMA_BIDIRECTIONAL);
+
+ return bi;
+}
+
+static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
+ struct ixgbe_rx_buffer *obi)
+{
+ u16 nta = rx_ring->next_to_alloc;
+ struct ixgbe_rx_buffer *nbi;
+
+ nbi = &rx_ring->rx_buffer_info[rx_ring->next_to_alloc];
+ /* update, and store next to alloc */
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ /* transfer page from old buffer to new buffer */
+ nbi->dma = obi->dma;
+ nbi->addr = obi->addr;
+ nbi->handle = obi->handle;
+
+ obi->addr = NULL;
+ obi->skb = NULL;
+}
+
+void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
+{
+ struct ixgbe_rx_buffer *bi;
+ struct ixgbe_ring *rx_ring;
+ u64 hr, mask;
+ u16 nta;
+
+ rx_ring = container_of(alloc, struct ixgbe_ring, zca);
+ hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
+ mask = rx_ring->xsk_umem->chunk_mask;
+
+ nta = rx_ring->next_to_alloc;
+ bi = rx_ring->rx_buffer_info;
+
+ nta++;
+ rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+ handle &= mask;
+
+ bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
+ rx_ring->xsk_umem->headroom);
+}
+
+static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
+ struct ixgbe_rx_buffer *bi)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ void *addr = bi->addr;
+ u64 handle, hr;
+
+ if (addr)
+ return true;
+
+ if (!xsk_umem_peek_addr(umem, &handle)) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ return false;
+ }
+
+ hr = umem->headroom + XDP_PACKET_HEADROOM;
+
+ bi->dma = xdp_umem_get_dma(umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
+
+ xsk_umem_discard_addr(umem);
+ return true;
+}
+
+static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring,
+ struct ixgbe_rx_buffer *bi)
+{
+ struct xdp_umem *umem = rx_ring->xsk_umem;
+ u64 handle, hr;
+
+ if (!xsk_umem_peek_addr_rq(umem, &handle)) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ return false;
+ }
+
+ handle &= rx_ring->xsk_umem->chunk_mask;
+
+ hr = umem->headroom + XDP_PACKET_HEADROOM;
+
+ bi->dma = xdp_umem_get_dma(umem, handle);
+ bi->dma += hr;
+
+ bi->addr = xdp_umem_get_data(umem, handle);
+ bi->addr += hr;
+
+ bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
+
+ xsk_umem_discard_addr_rq(umem);
+ return true;
+}
+
+static __always_inline bool
+__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
+ bool alloc(struct ixgbe_ring *rx_ring,
+ struct ixgbe_rx_buffer *bi))
+{
+ union ixgbe_adv_rx_desc *rx_desc;
+ struct ixgbe_rx_buffer *bi;
+ u16 i = rx_ring->next_to_use;
+ bool ok = true;
+
+ /* nothing to do */
+ if (!cleaned_count)
+ return true;
+
+ rx_desc = IXGBE_RX_DESC(rx_ring, i);
+ bi = &rx_ring->rx_buffer_info[i];
+ i -= rx_ring->count;
+
+ do {
+ if (!alloc(rx_ring, bi)) {
+ ok = false;
+ break;
+ }
+
+ /* sync the buffer for use by the device */
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+ bi->page_offset,
+ rx_ring->rx_buf_len,
+ DMA_BIDIRECTIONAL);
+
+ /* Refresh the desc even if buffer_addrs didn't change
+ * because each write-back erases this info.
+ */
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+
+ rx_desc++;
+ bi++;
+ i++;
+ if (unlikely(!i)) {
+ rx_desc = IXGBE_RX_DESC(rx_ring, 0);
+ bi = rx_ring->rx_buffer_info;
+ i -= rx_ring->count;
+ }
+
+ /* clear the length for the next_to_use descriptor */
+ rx_desc->wb.upper.length = 0;
+
+ cleaned_count--;
+ } while (cleaned_count);
+
+ i += rx_ring->count;
+
+ if (rx_ring->next_to_use != i) {
+ rx_ring->next_to_use = i;
+
+ /* update next to alloc since we have filled the ring */
+ rx_ring->next_to_alloc = i;
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+ * applicable for weak-ordered memory model archs,
+ * such as IA-64).
+ */
+ wmb();
+ writel(i, rx_ring->tail);
+ }
+
+ return ok;
+}
+
+void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
+{
+ __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
+ ixgbe_alloc_buffer_slow_zc);
+}
+
+static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring,
+ u16 count)
+{
+ return __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
+ ixgbe_alloc_buffer_zc);
+}
+
+static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
+ struct ixgbe_rx_buffer *bi,
+ struct xdp_buff *xdp)
+{
+ unsigned int metasize = xdp->data - xdp->data_meta;
+ unsigned int datasize = xdp->data_end - xdp->data;
+ struct sk_buff *skb;
+
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ xdp->data_end - xdp->data_hard_start,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ return NULL;
+
+ skb_reserve(skb, xdp->data - xdp->data_hard_start);
+ memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+ if (metasize)
+ skb_metadata_set(skb, metasize);
+
+ ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ return skb;
+}
+
+static void ixgbe_inc_ntc(struct ixgbe_ring *rx_ring)
+{
+ u32 ntc = rx_ring->next_to_clean + 1;
+
+ ntc = (ntc < rx_ring->count) ? ntc : 0;
+ rx_ring->next_to_clean = ntc;
+ prefetch(IXGBE_RX_DESC(rx_ring, ntc));
+}
+
+int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *rx_ring,
+ const int budget)
+{
+ unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+ struct ixgbe_adapter *adapter = q_vector->adapter;
+ u16 cleaned_count = ixgbe_desc_unused(rx_ring);
+ unsigned int xdp_res, xdp_xmit = 0;
+ bool failure = false;
+ struct sk_buff *skb;
+ struct xdp_buff xdp;
+
+ xdp.rxq = &rx_ring->xdp_rxq;
+
+ while (likely(total_rx_packets < budget)) {
+ union ixgbe_adv_rx_desc *rx_desc;
+ struct ixgbe_rx_buffer *bi;
+ unsigned int size;
+
+ /* return some buffers to hardware, one at a time is too slow */
+ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
+ failure = failure ||
+ !ixgbe_alloc_rx_buffers_fast_zc(rx_ring,
+ cleaned_count);
+ cleaned_count = 0;
+ }
+
+ rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
+ size = le16_to_cpu(rx_desc->wb.upper.length);
+ if (!size)
+ break;
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc until we know the
+ * descriptor has been written back
+ */
+ dma_rmb();
+
+ bi = ixgbe_get_rx_buffer_zc(rx_ring, size);
+
+ if (unlikely(!ixgbe_test_staterr(rx_desc,
+ IXGBE_RXD_STAT_EOP))) {
+ struct ixgbe_rx_buffer *next_bi;
+
+ ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ ixgbe_inc_ntc(rx_ring);
+ next_bi =
+ &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+ next_bi->skb = ERR_PTR(-EINVAL);
+ continue;
+ }
+
+ if (unlikely(bi->skb)) {
+ ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ ixgbe_inc_ntc(rx_ring);
+ continue;
+ }
+
+ xdp.data = bi->addr;
+ xdp.data_meta = xdp.data;
+ xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
+ xdp.data_end = xdp.data + size;
+ xdp.handle = bi->handle;
+
+ xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp);
+
+ if (xdp_res) {
+ if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
+ bi->addr = NULL;
+ bi->skb = NULL;
+ } else {
+ ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+ }
+ total_rx_packets++;
+ total_rx_bytes += size;
+
+ cleaned_count++;
+ ixgbe_inc_ntc(rx_ring);
+ continue;
+ }
+
+ /* XDP_PASS path */
+ skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp);
+ if (!skb) {
+ rx_ring->rx_stats.alloc_rx_buff_failed++;
+ break;
+ }
+
+ cleaned_count++;
+ ixgbe_inc_ntc(rx_ring);
+
+ if (eth_skb_pad(skb))
+ continue;
+
+ total_rx_bytes += skb->len;
+ total_rx_packets++;
+
+ ixgbe_process_skb_fields(rx_ring, rx_desc, skb);
+ ixgbe_rx_skb(q_vector, skb);
+ }
+
+ if (xdp_xmit & IXGBE_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & IXGBE_XDP_TX) {
+ struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch.
+ */
+ wmb();
+ writel(ring->next_to_use, ring->tail);
+ }
+
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->stats.packets += total_rx_packets;
+ rx_ring->stats.bytes += total_rx_bytes;
+ u64_stats_update_end(&rx_ring->syncp);
+ q_vector->rx.total_packets += total_rx_packets;
+ q_vector->rx.total_bytes += total_rx_bytes;
+
+ if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+ if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+ xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+ else
+ xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+
+ return (int)total_rx_packets;
+ }
+ return failure ? budget : (int)total_rx_packets;
+}
+
+void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
+{
+ u16 i = rx_ring->next_to_clean;
+ struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i];
+
+ while (i != rx_ring->next_to_alloc) {
+ xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle);
+ i++;
+ bi++;
+ if (i == rx_ring->count) {
+ i = 0;
+ bi = rx_ring->rx_buffer_info;
+ }
+ }
+}
+
+static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
+{
+ union ixgbe_adv_tx_desc *tx_desc = NULL;
+ struct ixgbe_tx_buffer *tx_bi;
+ bool work_done = true;
+ struct xdp_desc desc;
+ dma_addr_t dma;
+ u32 cmd_type;
+
+ while (budget-- > 0) {
+ if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
+ !netif_carrier_ok(xdp_ring->netdev)) {
+ work_done = false;
+ break;
+ }
+
+ if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
+ break;
+
+ dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
+
+ dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
+ DMA_BIDIRECTIONAL);
+
+ tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
+ tx_bi->bytecount = desc.len;
+ tx_bi->xdpf = NULL;
+ tx_bi->gso_segs = 1;
+
+ tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
+ tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+ /* put descriptor type bits */
+ cmd_type = IXGBE_ADVTXD_DTYP_DATA |
+ IXGBE_ADVTXD_DCMD_DEXT |
+ IXGBE_ADVTXD_DCMD_IFCS;
+ cmd_type |= desc.len | IXGBE_TXD_CMD;
+ tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+ tx_desc->read.olinfo_status =
+ cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT);
+
+ xdp_ring->next_to_use++;
+ if (xdp_ring->next_to_use == xdp_ring->count)
+ xdp_ring->next_to_use = 0;
+ }
+
+ if (tx_desc) {
+ ixgbe_xdp_ring_update_tail(xdp_ring);
+ xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+ }
+
+ return !!budget && work_done;
+}
+
+static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring,
+ struct ixgbe_tx_buffer *tx_bi)
+{
+ xdp_return_frame(tx_bi->xdpf);
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_bi, dma),
+ dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_bi, len, 0);
+}
+
+bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *tx_ring, int napi_budget)
+{
+ u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
+ unsigned int total_packets = 0, total_bytes = 0;
+ struct xdp_umem *umem = tx_ring->xsk_umem;
+ union ixgbe_adv_tx_desc *tx_desc;
+ struct ixgbe_tx_buffer *tx_bi;
+ u32 xsk_frames = 0;
+
+ tx_bi = &tx_ring->tx_buffer_info[ntc];
+ tx_desc = IXGBE_TX_DESC(tx_ring, ntc);
+
+ while (ntc != ntu) {
+ if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
+ break;
+
+ total_bytes += tx_bi->bytecount;
+ total_packets += tx_bi->gso_segs;
+
+ if (tx_bi->xdpf)
+ ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi);
+ else
+ xsk_frames++;
+
+ tx_bi->xdpf = NULL;
+
+ tx_bi++;
+ tx_desc++;
+ ntc++;
+ if (unlikely(ntc == tx_ring->count)) {
+ ntc = 0;
+ tx_bi = tx_ring->tx_buffer_info;
+ tx_desc = IXGBE_TX_DESC(tx_ring, 0);
+ }
+
+ /* issue prefetch for next Tx descriptor */
+ prefetch(tx_desc);
+ }
+
+ tx_ring->next_to_clean = ntc;
+
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->stats.bytes += total_bytes;
+ tx_ring->stats.packets += total_packets;
+ u64_stats_update_end(&tx_ring->syncp);
+ q_vector->tx.total_bytes += total_bytes;
+ q_vector->tx.total_packets += total_packets;
+
+ if (xsk_frames)
+ xsk_umem_complete_tx(umem, xsk_frames);
+
+ if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+ xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+
+ return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
+}
+
+int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+ struct ixgbe_ring *ring;
+
+ if (test_bit(__IXGBE_DOWN, &adapter->state))
+ return -ENETDOWN;
+
+ if (!READ_ONCE(adapter->xdp_prog))
+ return -ENXIO;
+
+ if (qid >= adapter->num_xdp_queues)
+ return -ENXIO;
+
+ if (!adapter->xdp_ring[qid]->xsk_umem)
+ return -ENXIO;
+
+ ring = adapter->xdp_ring[qid];
+ if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+ u64 eics = BIT_ULL(ring->q_vector->v_idx);
+
+ ixgbe_irq_rearm_queues(adapter, eics);
+ }
+
+ return 0;
+}
+
+void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
+{
+ u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
+ struct xdp_umem *umem = tx_ring->xsk_umem;
+ struct ixgbe_tx_buffer *tx_bi;
+ u32 xsk_frames = 0;
+
+ while (ntc != ntu) {
+ tx_bi = &tx_ring->tx_buffer_info[ntc];
+
+ if (tx_bi->xdpf)
+ ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi);
+ else
+ xsk_frames++;
+
+ tx_bi->xdpf = NULL;
+
+ ntc++;
+ if (ntc == tx_ring->count)
+ ntc = 0;
+ }
+
+ if (xsk_frames)
+ xsk_umem_complete_tx(umem, xsk_frames);
+}
diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile
index aba1e6a..186a4bb 100644
--- a/drivers/net/ethernet/intel/ixgbevf/Makefile
+++ b/drivers/net/ethernet/intel/ixgbevf/Makefile
@@ -10,4 +10,5 @@
mbx.o \
ethtool.o \
ixgbevf_main.o
+ixgbevf-$(CONFIG_IXGBEVF_IPSEC) += ipsec.o
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 700d8eb..6bace74 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -133,9 +133,14 @@
#define IXGBE_RXDADV_STAT_FCSTAT_NODDP 0x00000010 /* 01: Ctxt w/o DDP */
#define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */
#define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */
+#define IXGBE_RXDADV_STAT_SECP 0x00020000 /* IPsec/MACsec pkt found */
#define IXGBE_RXDADV_RSSTYPE_MASK 0x0000000F
#define IXGBE_RXDADV_PKTTYPE_MASK 0x0000FFF0
+#define IXGBE_RXDADV_PKTTYPE_IPV4 0x00000010 /* IPv4 hdr present */
+#define IXGBE_RXDADV_PKTTYPE_IPV6 0x00000040 /* IPv6 hdr present */
+#define IXGBE_RXDADV_PKTTYPE_IPSEC_ESP 0x00001000 /* IPSec ESP */
+#define IXGBE_RXDADV_PKTTYPE_IPSEC_AH 0x00002000 /* IPSec AH */
#define IXGBE_RXDADV_PKTTYPE_MASK_EX 0x0001FFF0
#define IXGBE_RXDADV_HDRBUFLEN_MASK 0x00007FE0
#define IXGBE_RXDADV_RSCCNT_MASK 0x001E0000
@@ -229,7 +234,7 @@
/* Context descriptors */
struct ixgbe_adv_tx_context_desc {
__le32 vlan_macip_lens;
- __le32 seqnum_seed;
+ __le32 fceof_saidx;
__le32 type_tucmd_mlhl;
__le32 mss_l4len_idx;
};
@@ -250,9 +255,12 @@
#define IXGBE_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */
#define IXGBE_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */
#define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */
+#define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */
+#define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000 /* ESP Encrypt Enable */
#define IXGBE_ADVTXD_IDX_SHIFT 4 /* Adv desc Index shift */
#define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */
#define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */
+#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */
#define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \
IXGBE_ADVTXD_POPTS_SHIFT)
#define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 631c910..54459b6 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -55,6 +55,8 @@
IXGBEVF_STAT("alloc_rx_page", alloc_rx_page),
IXGBEVF_STAT("alloc_rx_page_failed", alloc_rx_page_failed),
IXGBEVF_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed),
+ IXGBEVF_STAT("tx_ipsec", tx_ipsec),
+ IXGBEVF_STAT("rx_ipsec", rx_ipsec),
};
#define IXGBEVF_QUEUE_STATS_LEN ( \
@@ -83,22 +85,16 @@
struct ethtool_link_ksettings *cmd)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
- struct ixgbe_hw *hw = &adapter->hw;
- u32 link_speed = 0;
- bool link_up;
ethtool_link_ksettings_zero_link_mode(cmd, supported);
ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
cmd->base.autoneg = AUTONEG_DISABLE;
cmd->base.port = -1;
- hw->mac.get_link_status = 1;
- hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
-
- if (link_up) {
+ if (adapter->link_up) {
__u32 speed = SPEED_10000;
- switch (link_speed) {
+ switch (adapter->link_speed) {
case IXGBE_LINK_SPEED_10GB_FULL:
speed = SPEED_10000;
break;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
new file mode 100644
index 0000000..5170dd9
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include "ixgbevf.h"
+#include <net/xfrm.h>
+#include <crypto/aead.h>
+
+#define IXGBE_IPSEC_KEY_BITS 160
+static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+
+/**
+ * ixgbevf_ipsec_set_pf_sa - ask the PF to set up an SA
+ * @adapter: board private structure
+ * @xs: xfrm info to be sent to the PF
+ *
+ * Returns: positive offload handle from the PF, or negative error code
+ **/
+static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter,
+ struct xfrm_state *xs)
+{
+ u32 msgbuf[IXGBE_VFMAILBOX_SIZE] = { 0 };
+ struct ixgbe_hw *hw = &adapter->hw;
+ struct sa_mbx_msg *sam;
+ int ret;
+
+ /* send the important bits to the PF */
+ sam = (struct sa_mbx_msg *)(&msgbuf[1]);
+ sam->flags = xs->xso.flags;
+ sam->spi = xs->id.spi;
+ sam->proto = xs->id.proto;
+ sam->family = xs->props.family;
+
+ if (xs->props.family == AF_INET6)
+ memcpy(sam->addr, &xs->id.daddr.a6, sizeof(xs->id.daddr.a6));
+ else
+ memcpy(sam->addr, &xs->id.daddr.a4, sizeof(xs->id.daddr.a4));
+ memcpy(sam->key, xs->aead->alg_key, sizeof(sam->key));
+
+ msgbuf[0] = IXGBE_VF_IPSEC_ADD;
+
+ spin_lock_bh(&adapter->mbx_lock);
+
+ ret = hw->mbx.ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE);
+ if (ret)
+ goto out;
+
+ ret = hw->mbx.ops.read_posted(hw, msgbuf, 2);
+ if (ret)
+ goto out;
+
+ ret = (int)msgbuf[1];
+ if (msgbuf[0] & IXGBE_VT_MSGTYPE_NACK && ret >= 0)
+ ret = -1;
+
+out:
+ spin_unlock_bh(&adapter->mbx_lock);
+
+ return ret;
+}
+
+/**
+ * ixgbevf_ipsec_del_pf_sa - ask the PF to delete an SA
+ * @adapter: board private structure
+ * @pfsa: sa index returned from PF when created, -1 for all
+ *
+ * Returns: 0 on success, or negative error code
+ **/
+static int ixgbevf_ipsec_del_pf_sa(struct ixgbevf_adapter *adapter, int pfsa)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 msgbuf[2];
+ int err;
+
+ memset(msgbuf, 0, sizeof(msgbuf));
+ msgbuf[0] = IXGBE_VF_IPSEC_DEL;
+ msgbuf[1] = (u32)pfsa;
+
+ spin_lock_bh(&adapter->mbx_lock);
+
+ err = hw->mbx.ops.write_posted(hw, msgbuf, 2);
+ if (err)
+ goto out;
+
+ err = hw->mbx.ops.read_posted(hw, msgbuf, 2);
+ if (err)
+ goto out;
+
+out:
+ spin_unlock_bh(&adapter->mbx_lock);
+ return err;
+}
+
+/**
+ * ixgbevf_ipsec_restore - restore the IPsec HW settings after a reset
+ * @adapter: board private structure
+ *
+ * Reload the HW tables from the SW tables after they've been bashed
+ * by a chip reset. While we're here, make sure any stale VF data is
+ * removed, since we go through reset when num_vfs changes.
+ **/
+void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter)
+{
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ if (!(adapter->netdev->features & NETIF_F_HW_ESP))
+ return;
+
+ /* reload the Rx and Tx keys */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+ struct rx_sa *r = &ipsec->rx_tbl[i];
+ struct tx_sa *t = &ipsec->tx_tbl[i];
+ int ret;
+
+ if (r->used) {
+ ret = ixgbevf_ipsec_set_pf_sa(adapter, r->xs);
+ if (ret < 0)
+ netdev_err(netdev, "reload rx_tbl[%d] failed = %d\n",
+ i, ret);
+ }
+
+ if (t->used) {
+ ret = ixgbevf_ipsec_set_pf_sa(adapter, t->xs);
+ if (ret < 0)
+ netdev_err(netdev, "reload tx_tbl[%d] failed = %d\n",
+ i, ret);
+ }
+ }
+}
+
+/**
+ * ixgbevf_ipsec_find_empty_idx - find the first unused security parameter index
+ * @ipsec: pointer to IPsec struct
+ * @rxtable: true if we need to look in the Rx table
+ *
+ * Returns the first unused index in either the Rx or Tx SA table
+ **/
+static
+int ixgbevf_ipsec_find_empty_idx(struct ixgbevf_ipsec *ipsec, bool rxtable)
+{
+ u32 i;
+
+ if (rxtable) {
+ if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT)
+ return -ENOSPC;
+
+ /* search rx sa table */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+ if (!ipsec->rx_tbl[i].used)
+ return i;
+ }
+ } else {
+ if (ipsec->num_tx_sa == IXGBE_IPSEC_MAX_SA_COUNT)
+ return -ENOSPC;
+
+ /* search tx sa table */
+ for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+ if (!ipsec->tx_tbl[i].used)
+ return i;
+ }
+ }
+
+ return -ENOSPC;
+}
+
+/**
+ * ixgbevf_ipsec_find_rx_state - find the state that matches
+ * @ipsec: pointer to IPsec struct
+ * @daddr: inbound address to match
+ * @proto: protocol to match
+ * @spi: SPI to match
+ * @ip4: true if using an IPv4 address
+ *
+ * Returns a pointer to the matching SA state information
+ **/
+static
+struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
+ __be32 *daddr, u8 proto,
+ __be32 spi, bool ip4)
+{
+ struct xfrm_state *ret = NULL;
+ struct rx_sa *rsa;
+
+ rcu_read_lock();
+ hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist,
+ (__force u32)spi) {
+ if (spi == rsa->xs->id.spi &&
+ ((ip4 && *daddr == rsa->xs->id.daddr.a4) ||
+ (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6,
+ sizeof(rsa->xs->id.daddr.a6)))) &&
+ proto == rsa->xs->id.proto) {
+ ret = rsa->xs;
+ xfrm_state_hold(ret);
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+/**
+ * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @xs: pointer to xfrm_state struct
+ * @mykey: pointer to key array to populate
+ * @mysalt: pointer to salt value to populate
+ *
+ * This copies the protocol keys and salt to our own data tables. The
+ * 82599 family only supports the one algorithm.
+ **/
+static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
+ u32 *mykey, u32 *mysalt)
+{
+ struct net_device *dev = xs->xso.dev;
+ unsigned char *key_data;
+ char *alg_name = NULL;
+ int key_len;
+
+ if (!xs->aead) {
+ netdev_err(dev, "Unsupported IPsec algorithm\n");
+ return -EINVAL;
+ }
+
+ if (xs->aead->alg_icv_len != IXGBE_IPSEC_AUTH_BITS) {
+ netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+ IXGBE_IPSEC_AUTH_BITS);
+ return -EINVAL;
+ }
+
+ key_data = &xs->aead->alg_key[0];
+ key_len = xs->aead->alg_key_len;
+ alg_name = xs->aead->alg_name;
+
+ if (strcmp(alg_name, aes_gcm_name)) {
+ netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+ aes_gcm_name);
+ return -EINVAL;
+ }
+
+ /* The key bytes come down in a big endian array of bytes, so
+ * we don't need to do any byte swapping.
+ * 160 accounts for 16 byte key and 4 byte salt
+ */
+ if (key_len > IXGBE_IPSEC_KEY_BITS) {
+ *mysalt = ((u32 *)key_data)[4];
+ } else if (key_len == IXGBE_IPSEC_KEY_BITS) {
+ *mysalt = 0;
+ } else {
+ netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n");
+ return -EINVAL;
+ }
+ memcpy(mykey, key_data, 16);
+
+ return 0;
+}
+
+/**
+ * ixgbevf_ipsec_add_sa - program device with a security association
+ * @xs: pointer to transformer state struct
+ **/
+static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs)
+{
+ struct net_device *dev = xs->xso.dev;
+ struct ixgbevf_adapter *adapter = netdev_priv(dev);
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ u16 sa_idx;
+ int ret;
+
+ if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+ netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n",
+ xs->id.proto);
+ return -EINVAL;
+ }
+
+ if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+ struct rx_sa rsa;
+
+ if (xs->calg) {
+ netdev_err(dev, "Compression offload not supported\n");
+ return -EINVAL;
+ }
+
+ /* find the first unused index */
+ ret = ixgbevf_ipsec_find_empty_idx(ipsec, true);
+ if (ret < 0) {
+ netdev_err(dev, "No space for SA in Rx table!\n");
+ return ret;
+ }
+ sa_idx = (u16)ret;
+
+ memset(&rsa, 0, sizeof(rsa));
+ rsa.used = true;
+ rsa.xs = xs;
+
+ if (rsa.xs->id.proto & IPPROTO_ESP)
+ rsa.decrypt = xs->ealg || xs->aead;
+
+ /* get the key and salt */
+ ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+ if (ret) {
+ netdev_err(dev, "Failed to get key data for Rx SA table\n");
+ return ret;
+ }
+
+ /* get ip for rx sa table */
+ if (xs->props.family == AF_INET6)
+ memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16);
+ else
+ memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4);
+
+ rsa.mode = IXGBE_RXMOD_VALID;
+ if (rsa.xs->id.proto & IPPROTO_ESP)
+ rsa.mode |= IXGBE_RXMOD_PROTO_ESP;
+ if (rsa.decrypt)
+ rsa.mode |= IXGBE_RXMOD_DECRYPT;
+ if (rsa.xs->props.family == AF_INET6)
+ rsa.mode |= IXGBE_RXMOD_IPV6;
+
+ ret = ixgbevf_ipsec_set_pf_sa(adapter, xs);
+ if (ret < 0)
+ return ret;
+ rsa.pfsa = ret;
+
+ /* the preparations worked, so save the info */
+ memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa));
+
+ xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX;
+
+ ipsec->num_rx_sa++;
+
+ /* hash the new entry for faster search in Rx path */
+ hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist,
+ (__force u32)rsa.xs->id.spi);
+ } else {
+ struct tx_sa tsa;
+
+ /* find the first unused index */
+ ret = ixgbevf_ipsec_find_empty_idx(ipsec, false);
+ if (ret < 0) {
+ netdev_err(dev, "No space for SA in Tx table\n");
+ return ret;
+ }
+ sa_idx = (u16)ret;
+
+ memset(&tsa, 0, sizeof(tsa));
+ tsa.used = true;
+ tsa.xs = xs;
+
+ if (xs->id.proto & IPPROTO_ESP)
+ tsa.encrypt = xs->ealg || xs->aead;
+
+ ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+ if (ret) {
+ netdev_err(dev, "Failed to get key data for Tx SA table\n");
+ memset(&tsa, 0, sizeof(tsa));
+ return ret;
+ }
+
+ ret = ixgbevf_ipsec_set_pf_sa(adapter, xs);
+ if (ret < 0)
+ return ret;
+ tsa.pfsa = ret;
+
+ /* the preparations worked, so save the info */
+ memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa));
+
+ xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX;
+
+ ipsec->num_tx_sa++;
+ }
+
+ return 0;
+}
+
+/**
+ * ixgbevf_ipsec_del_sa - clear out this specific SA
+ * @xs: pointer to transformer state struct
+ **/
+static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
+{
+ struct net_device *dev = xs->xso.dev;
+ struct ixgbevf_adapter *adapter = netdev_priv(dev);
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ u16 sa_idx;
+
+ if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+ sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
+
+ if (!ipsec->rx_tbl[sa_idx].used) {
+ netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n",
+ sa_idx, xs->xso.offload_handle);
+ return;
+ }
+
+ ixgbevf_ipsec_del_pf_sa(adapter, ipsec->rx_tbl[sa_idx].pfsa);
+ hash_del_rcu(&ipsec->rx_tbl[sa_idx].hlist);
+ memset(&ipsec->rx_tbl[sa_idx], 0, sizeof(struct rx_sa));
+ ipsec->num_rx_sa--;
+ } else {
+ sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
+
+ if (!ipsec->tx_tbl[sa_idx].used) {
+ netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n",
+ sa_idx, xs->xso.offload_handle);
+ return;
+ }
+
+ ixgbevf_ipsec_del_pf_sa(adapter, ipsec->tx_tbl[sa_idx].pfsa);
+ memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa));
+ ipsec->num_tx_sa--;
+ }
+}
+
+/**
+ * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload
+ * @skb: current data packet
+ * @xs: pointer to transformer state struct
+ **/
+static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+ if (xs->props.family == AF_INET) {
+ /* Offload with IPv4 options is not supported yet */
+ if (ip_hdr(skb)->ihl != 5)
+ return false;
+ } else {
+ /* Offload with IPv6 extension headers is not support yet */
+ if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr))
+ return false;
+ }
+
+ return true;
+}
+
+static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = {
+ .xdo_dev_state_add = ixgbevf_ipsec_add_sa,
+ .xdo_dev_state_delete = ixgbevf_ipsec_del_sa,
+ .xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok,
+};
+
+/**
+ * ixgbevf_ipsec_tx - setup Tx flags for IPsec offload
+ * @tx_ring: outgoing context
+ * @first: current data packet
+ * @itd: ipsec Tx data for later use in building context descriptor
+ **/
+int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
+ struct ixgbevf_tx_buffer *first,
+ struct ixgbevf_ipsec_tx_data *itd)
+{
+ struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev);
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct xfrm_state *xs;
+ struct sec_path *sp;
+ struct tx_sa *tsa;
+ u16 sa_idx;
+
+ sp = skb_sec_path(first->skb);
+ if (unlikely(!sp->len)) {
+ netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
+ __func__, sp->len);
+ return 0;
+ }
+
+ xs = xfrm_input_state(first->skb);
+ if (unlikely(!xs)) {
+ netdev_err(tx_ring->netdev, "%s: no xfrm_input_state() xs = %p\n",
+ __func__, xs);
+ return 0;
+ }
+
+ sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
+ if (unlikely(sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) {
+ netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n",
+ __func__, sa_idx, xs->xso.offload_handle);
+ return 0;
+ }
+
+ tsa = &ipsec->tx_tbl[sa_idx];
+ if (unlikely(!tsa->used)) {
+ netdev_err(tx_ring->netdev, "%s: unused sa_idx=%d\n",
+ __func__, sa_idx);
+ return 0;
+ }
+
+ itd->pfsa = tsa->pfsa - IXGBE_IPSEC_BASE_TX_INDEX;
+
+ first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CSUM;
+
+ if (xs->id.proto == IPPROTO_ESP) {
+ itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP |
+ IXGBE_ADVTXD_TUCMD_L4T_TCP;
+ if (first->protocol == htons(ETH_P_IP))
+ itd->flags |= IXGBE_ADVTXD_TUCMD_IPV4;
+
+ /* The actual trailer length is authlen (16 bytes) plus
+ * 2 bytes for the proto and the padlen values, plus
+ * padlen bytes of padding. This ends up not the same
+ * as the static value found in xs->props.trailer_len (21).
+ *
+ * ... but if we're doing GSO, don't bother as the stack
+ * doesn't add a trailer for those.
+ */
+ if (!skb_is_gso(first->skb)) {
+ /* The "correct" way to get the auth length would be
+ * to use
+ * authlen = crypto_aead_authsize(xs->data);
+ * but since we know we only have one size to worry
+ * about * we can let the compiler use the constant
+ * and save us a few CPU cycles.
+ */
+ const int authlen = IXGBE_IPSEC_AUTH_BITS / 8;
+ struct sk_buff *skb = first->skb;
+ u8 padlen;
+ int ret;
+
+ ret = skb_copy_bits(skb, skb->len - (authlen + 2),
+ &padlen, 1);
+ if (unlikely(ret))
+ return 0;
+ itd->trailer_len = authlen + 2 + padlen;
+ }
+ }
+ if (tsa->encrypt)
+ itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN;
+
+ return 1;
+}
+
+/**
+ * ixgbevf_ipsec_rx - decode IPsec bits from Rx descriptor
+ * @rx_ring: receiving ring
+ * @rx_desc: receive data descriptor
+ * @skb: current data packet
+ *
+ * Determine if there was an IPsec encapsulation noticed, and if so set up
+ * the resulting status for later in the receive stack.
+ **/
+void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ struct ixgbevf_adapter *adapter = netdev_priv(rx_ring->netdev);
+ __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
+ __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH |
+ IXGBE_RXDADV_PKTTYPE_IPSEC_ESP);
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct xfrm_offload *xo = NULL;
+ struct xfrm_state *xs = NULL;
+ struct ipv6hdr *ip6 = NULL;
+ struct iphdr *ip4 = NULL;
+ struct sec_path *sp;
+ void *daddr;
+ __be32 spi;
+ u8 *c_hdr;
+ u8 proto;
+
+ /* Find the IP and crypto headers in the data.
+ * We can assume no VLAN header in the way, b/c the
+ * hw won't recognize the IPsec packet and anyway the
+ * currently VLAN device doesn't support xfrm offload.
+ */
+ if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV4)) {
+ ip4 = (struct iphdr *)(skb->data + ETH_HLEN);
+ daddr = &ip4->daddr;
+ c_hdr = (u8 *)ip4 + ip4->ihl * 4;
+ } else if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV6)) {
+ ip6 = (struct ipv6hdr *)(skb->data + ETH_HLEN);
+ daddr = &ip6->daddr;
+ c_hdr = (u8 *)ip6 + sizeof(struct ipv6hdr);
+ } else {
+ return;
+ }
+
+ switch (pkt_info & ipsec_pkt_types) {
+ case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH):
+ spi = ((struct ip_auth_hdr *)c_hdr)->spi;
+ proto = IPPROTO_AH;
+ break;
+ case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_ESP):
+ spi = ((struct ip_esp_hdr *)c_hdr)->spi;
+ proto = IPPROTO_ESP;
+ break;
+ default:
+ return;
+ }
+
+ xs = ixgbevf_ipsec_find_rx_state(ipsec, daddr, proto, spi, !!ip4);
+ if (unlikely(!xs))
+ return;
+
+ sp = secpath_set(skb);
+ if (unlikely(!sp))
+ return;
+
+ sp->xvec[sp->len++] = xs;
+ sp->olen++;
+ xo = xfrm_offload(skb);
+ xo->flags = CRYPTO_DONE;
+ xo->status = CRYPTO_SUCCESS;
+
+ adapter->rx_ipsec++;
+}
+
+/**
+ * ixgbevf_init_ipsec_offload - initialize registers for IPsec operation
+ * @adapter: board private structure
+ **/
+void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter)
+{
+ struct ixgbevf_ipsec *ipsec;
+ size_t size;
+
+ switch (adapter->hw.api_version) {
+ case ixgbe_mbox_api_14:
+ break;
+ default:
+ return;
+ }
+
+ ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL);
+ if (!ipsec)
+ goto err1;
+ hash_init(ipsec->rx_sa_list);
+
+ size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT;
+ ipsec->rx_tbl = kzalloc(size, GFP_KERNEL);
+ if (!ipsec->rx_tbl)
+ goto err2;
+
+ size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT;
+ ipsec->tx_tbl = kzalloc(size, GFP_KERNEL);
+ if (!ipsec->tx_tbl)
+ goto err2;
+
+ ipsec->num_rx_sa = 0;
+ ipsec->num_tx_sa = 0;
+
+ adapter->ipsec = ipsec;
+
+ adapter->netdev->xfrmdev_ops = &ixgbevf_xfrmdev_ops;
+
+#define IXGBEVF_ESP_FEATURES (NETIF_F_HW_ESP | \
+ NETIF_F_HW_ESP_TX_CSUM | \
+ NETIF_F_GSO_ESP)
+
+ adapter->netdev->features |= IXGBEVF_ESP_FEATURES;
+ adapter->netdev->hw_enc_features |= IXGBEVF_ESP_FEATURES;
+
+ return;
+
+err2:
+ kfree(ipsec->rx_tbl);
+ kfree(ipsec->tx_tbl);
+ kfree(ipsec);
+err1:
+ netdev_err(adapter->netdev, "Unable to allocate memory for SA tables");
+}
+
+/**
+ * ixgbevf_stop_ipsec_offload - tear down the IPsec offload
+ * @adapter: board private structure
+ **/
+void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter)
+{
+ struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+
+ adapter->ipsec = NULL;
+ if (ipsec) {
+ kfree(ipsec->rx_tbl);
+ kfree(ipsec->tx_tbl);
+ kfree(ipsec);
+ }
+}
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.h b/drivers/net/ethernet/intel/ixgbevf/ipsec.h
new file mode 100644
index 0000000..3740725
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#ifndef _IXGBEVF_IPSEC_H_
+#define _IXGBEVF_IPSEC_H_
+
+#define IXGBE_IPSEC_MAX_SA_COUNT 1024
+#define IXGBE_IPSEC_BASE_RX_INDEX 0
+#define IXGBE_IPSEC_BASE_TX_INDEX IXGBE_IPSEC_MAX_SA_COUNT
+#define IXGBE_IPSEC_AUTH_BITS 128
+
+#define IXGBE_RXMOD_VALID 0x00000001
+#define IXGBE_RXMOD_PROTO_ESP 0x00000004
+#define IXGBE_RXMOD_DECRYPT 0x00000008
+#define IXGBE_RXMOD_IPV6 0x00000010
+
+struct rx_sa {
+ struct hlist_node hlist;
+ struct xfrm_state *xs;
+ __be32 ipaddr[4];
+ u32 key[4];
+ u32 salt;
+ u32 mode;
+ u32 pfsa;
+ bool used;
+ bool decrypt;
+};
+
+struct rx_ip_sa {
+ __be32 ipaddr[4];
+ u32 ref_cnt;
+ bool used;
+};
+
+struct tx_sa {
+ struct xfrm_state *xs;
+ u32 key[4];
+ u32 salt;
+ u32 pfsa;
+ bool encrypt;
+ bool used;
+};
+
+struct ixgbevf_ipsec_tx_data {
+ u32 flags;
+ u16 trailer_len;
+ u16 pfsa;
+};
+
+struct ixgbevf_ipsec {
+ u16 num_rx_sa;
+ u16 num_tx_sa;
+ struct rx_sa *rx_tbl;
+ struct tx_sa *tx_tbl;
+ DECLARE_HASHTABLE(rx_sa_list, 10);
+};
+
+struct sa_mbx_msg {
+ __be32 spi;
+ u8 flags;
+ u8 proto;
+ u16 family;
+ __be32 addr[4];
+ u32 key[5];
+};
+#endif /* _IXGBEVF_IPSEC_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 56a1031..ecab686 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -14,6 +14,7 @@
#include <net/xdp.h>
#include "vf.h"
+#include "ipsec.h"
#define IXGBE_MAX_TXD_PWR 14
#define IXGBE_MAX_DATA_PER_TXD BIT(IXGBE_MAX_TXD_PWR)
@@ -163,6 +164,7 @@
#define IXGBE_TX_FLAGS_VLAN BIT(1)
#define IXGBE_TX_FLAGS_TSO BIT(2)
#define IXGBE_TX_FLAGS_IPV4 BIT(3)
+#define IXGBE_TX_FLAGS_IPSEC BIT(4)
#define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000
#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000
#define IXGBE_TX_FLAGS_VLAN_SHIFT 16
@@ -338,6 +340,7 @@
struct ixgbevf_ring *tx_ring[MAX_TX_QUEUES]; /* One per active queue */
u64 restart_queue;
u32 tx_timeout_count;
+ u64 tx_ipsec;
/* RX */
int num_rx_queues;
@@ -348,6 +351,7 @@
u64 alloc_rx_page_failed;
u64 alloc_rx_buff_failed;
u64 alloc_rx_page;
+ u64 rx_ipsec;
struct msix_entry *msix_entries;
@@ -384,6 +388,10 @@
u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE];
u32 flags;
#define IXGBEVF_FLAGS_LEGACY_RX BIT(1)
+
+#ifdef CONFIG_XFRM
+ struct ixgbevf_ipsec *ipsec;
+#endif /* CONFIG_XFRM */
};
enum ixbgevf_state_t {
@@ -451,6 +459,31 @@
extern void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector);
+#ifdef CONFIG_IXGBEVF_IPSEC
+void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter);
+void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter);
+void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter);
+void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb);
+int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
+ struct ixgbevf_tx_buffer *first,
+ struct ixgbevf_ipsec_tx_data *itd);
+#else
+static inline void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter)
+{ }
+static inline void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter)
+{ }
+static inline void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter) { }
+static inline void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb) { }
+static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
+ struct ixgbevf_tx_buffer *first,
+ struct ixgbevf_ipsec_tx_data *itd)
+{ return 0; }
+#endif /* CONFIG_IXGBEVF_IPSEC */
+
void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter);
void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 4093a9c..076f2da 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -30,6 +30,7 @@
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/atomic.h>
+#include <net/xfrm.h>
#include "ixgbevf.h"
@@ -40,7 +41,7 @@
#define DRV_VERSION "4.1.0-k"
const char ixgbevf_driver_version[] = DRV_VERSION;
static char ixgbevf_copyright[] =
- "Copyright (c) 2009 - 2015 Intel Corporation.";
+ "Copyright (c) 2009 - 2018 Intel Corporation.";
static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
[board_82599_vf] = &ixgbevf_82599_vf_info,
@@ -79,7 +80,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
@@ -268,7 +269,7 @@
struct ixgbevf_adapter *adapter = q_vector->adapter;
struct ixgbevf_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
- unsigned int total_bytes = 0, total_packets = 0;
+ unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0;
unsigned int budget = tx_ring->count / 2;
unsigned int i = tx_ring->next_to_clean;
@@ -299,6 +300,8 @@
/* update the statistics for this packet */
total_bytes += tx_buffer->bytecount;
total_packets += tx_buffer->gso_segs;
+ if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC)
+ total_ipsec++;
/* free the skb */
if (ring_is_xdp(tx_ring))
@@ -361,6 +364,7 @@
u64_stats_update_end(&tx_ring->syncp);
q_vector->tx.total_bytes += total_bytes;
q_vector->tx.total_packets += total_packets;
+ adapter->tx_ipsec += total_ipsec;
if (check_for_tx_hang(tx_ring) && ixgbevf_check_tx_hang(tx_ring)) {
struct ixgbe_hw *hw = &adapter->hw;
@@ -516,6 +520,9 @@
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
}
+ if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP))
+ ixgbevf_ipsec_rx(rx_ring, rx_desc, skb);
+
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
}
@@ -889,7 +896,8 @@
/* Determine available headroom for copy */
headlen = size;
if (headlen > IXGBEVF_RX_HDR_SIZE)
- headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE);
+ headlen = eth_get_headlen(skb->dev, xdp->data,
+ IXGBEVF_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
memcpy(__skb_put(skb, headlen), xdp->data,
@@ -1012,7 +1020,7 @@
context_desc = IXGBEVF_TX_CTXTDESC(ring, 0);
context_desc->vlan_macip_lens =
cpu_to_le32(ETH_HLEN << IXGBE_ADVTXD_MACLEN_SHIFT);
- context_desc->seqnum_seed = 0;
+ context_desc->fceof_saidx = 0;
context_desc->type_tucmd_mlhl =
cpu_to_le32(IXGBE_TXD_CMD_DEXT |
IXGBE_ADVTXD_DTYP_CTXT);
@@ -1287,16 +1295,20 @@
/* If all work not completed, return budget and keep polling */
if (!clean_complete)
return budget;
- /* all work done, exit the polling mode */
- napi_complete_done(napi, work_done);
- if (adapter->rx_itr_setting == 1)
- ixgbevf_set_itr(q_vector);
- if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
- !test_bit(__IXGBEVF_REMOVING, &adapter->state))
- ixgbevf_irq_enable_queues(adapter,
- BIT(q_vector->v_idx));
- return 0;
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done))) {
+ if (adapter->rx_itr_setting == 1)
+ ixgbevf_set_itr(q_vector);
+ if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+ !test_bit(__IXGBEVF_REMOVING, &adapter->state))
+ ixgbevf_irq_enable_queues(adapter,
+ BIT(q_vector->v_idx));
+ }
+
+ return min(work_done, budget - 1);
}
/**
@@ -1412,6 +1424,9 @@
*/
/* what was last interrupt timeslice? */
timepassed_us = q_vector->itr >> 2;
+ if (timepassed_us == 0)
+ return;
+
bytes_perint = bytes / timepassed_us; /* bytes/usec */
switch (itr_setting) {
@@ -2200,6 +2215,7 @@
ixgbevf_set_rx_mode(adapter->netdev);
ixgbevf_restore_vlan(adapter);
+ ixgbevf_ipsec_restore(adapter);
ixgbevf_configure_tx(adapter);
ixgbevf_configure_rx(adapter);
@@ -2246,11 +2262,14 @@
static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
- int api[] = { ixgbe_mbox_api_13,
- ixgbe_mbox_api_12,
- ixgbe_mbox_api_11,
- ixgbe_mbox_api_10,
- ixgbe_mbox_api_unknown };
+ static const int api[] = {
+ ixgbe_mbox_api_14,
+ ixgbe_mbox_api_13,
+ ixgbe_mbox_api_12,
+ ixgbe_mbox_api_11,
+ ixgbe_mbox_api_10,
+ ixgbe_mbox_api_unknown
+ };
int err, idx = 0;
spin_lock_bh(&adapter->mbx_lock);
@@ -2501,6 +2520,7 @@
msleep(1);
ixgbevf_down(adapter);
+ pci_set_master(adapter->pdev);
ixgbevf_up(adapter);
clear_bit(__IXGBEVF_RESETTING, &adapter->state);
@@ -2605,6 +2625,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
if (adapter->xdp_prog &&
hw->mac.max_tx_queues == rss)
rss = rss > 3 ? 2 : 1;
@@ -3700,8 +3721,8 @@
}
static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring,
- u32 vlan_macip_lens, u32 type_tucmd,
- u32 mss_l4len_idx)
+ u32 vlan_macip_lens, u32 fceof_saidx,
+ u32 type_tucmd, u32 mss_l4len_idx)
{
struct ixgbe_adv_tx_context_desc *context_desc;
u16 i = tx_ring->next_to_use;
@@ -3715,14 +3736,15 @@
type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT;
context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
- context_desc->seqnum_seed = 0;
+ context_desc->fceof_saidx = cpu_to_le32(fceof_saidx);
context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd);
context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
}
static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
struct ixgbevf_tx_buffer *first,
- u8 *hdr_len)
+ u8 *hdr_len,
+ struct ixgbevf_ipsec_tx_data *itd)
{
u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
struct sk_buff *skb = first->skb;
@@ -3736,6 +3758,7 @@
unsigned char *hdr;
} l4;
u32 paylen, l4_offset;
+ u32 fceof_saidx = 0;
int err;
if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -3761,13 +3784,15 @@
if (ip.v4->version == 4) {
unsigned char *csum_start = skb_checksum_start(skb);
unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4);
+ int len = csum_start - trans_start;
/* IP header will have to cancel out any data that
- * is not a part of the outer IP header
+ * is not a part of the outer IP header, so set to
+ * a reverse csum if needed, else init check to 0.
*/
- ip.v4->check = csum_fold(csum_partial(trans_start,
- csum_start - trans_start,
- 0));
+ ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ?
+ csum_fold(csum_partial(trans_start,
+ len, 0)) : 0;
type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
ip.v4->tot_len = 0;
@@ -3799,13 +3824,16 @@
mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
mss_l4len_idx |= (1u << IXGBE_ADVTXD_IDX_SHIFT);
+ fceof_saidx |= itd->pfsa;
+ type_tucmd |= itd->flags | itd->trailer_len;
+
/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
vlan_macip_lens = l4.hdr - ip.hdr;
vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
- ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
- type_tucmd, mss_l4len_idx);
+ ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd,
+ mss_l4len_idx);
return 1;
}
@@ -3820,10 +3848,12 @@
}
static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
- struct ixgbevf_tx_buffer *first)
+ struct ixgbevf_tx_buffer *first,
+ struct ixgbevf_ipsec_tx_data *itd)
{
struct sk_buff *skb = first->skb;
u32 vlan_macip_lens = 0;
+ u32 fceof_saidx = 0;
u32 type_tucmd = 0;
if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -3862,7 +3892,11 @@
vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
- ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+ fceof_saidx |= itd->pfsa;
+ type_tucmd |= itd->flags | itd->trailer_len;
+
+ ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
+ fceof_saidx, type_tucmd, 0);
}
static __le32 ixgbevf_tx_cmd_type(u32 tx_flags)
@@ -3896,8 +3930,12 @@
if (tx_flags & IXGBE_TX_FLAGS_IPV4)
olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM);
- /* use index 1 context for TSO/FSO/FCOE */
- if (tx_flags & IXGBE_TX_FLAGS_TSO)
+ /* enable IPsec */
+ if (tx_flags & IXGBE_TX_FLAGS_IPSEC)
+ olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IPSEC);
+
+ /* use index 1 context for TSO/FSO/FCOE/IPSEC */
+ if (tx_flags & (IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_IPSEC))
olinfo_status |= cpu_to_le32(1u << IXGBE_ADVTXD_IDX_SHIFT);
/* Check Context must be set if Tx switch is enabled, which it
@@ -3915,7 +3953,7 @@
struct sk_buff *skb = first->skb;
struct ixgbevf_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
dma_addr_t dma;
unsigned int data_len, size;
u32 tx_flags = first->tx_flags;
@@ -3990,6 +4028,8 @@
/* set the timestamp */
first->time_stamp = jiffies;
+ skb_tx_timestamp(skb);
+
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch. (Only applicable for weak-ordered
* memory model archs, such as IA-64).
@@ -4079,6 +4119,7 @@
int tso;
u32 tx_flags = 0;
u16 count = TXD_USE_COUNT(skb_headlen(skb));
+ struct ixgbevf_ipsec_tx_data ipsec_tx = { 0 };
#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
unsigned short f;
#endif
@@ -4097,8 +4138,11 @@
* otherwise try next time
*/
#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
- for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
- count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+
+ count += TXD_USE_COUNT(skb_frag_size(frag));
+ }
#else
count += skb_shinfo(skb)->nr_frags;
#endif
@@ -4123,11 +4167,15 @@
first->tx_flags = tx_flags;
first->protocol = vlan_get_protocol(skb);
- tso = ixgbevf_tso(tx_ring, first, &hdr_len);
+#ifdef CONFIG_IXGBEVF_IPSEC
+ if (xfrm_offload(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
+ goto out_drop;
+#endif
+ tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx);
if (tso < 0)
goto out_drop;
else if (!tso)
- ixgbevf_tx_csum(tx_ring, first);
+ ixgbevf_tx_csum(tx_ring, first, &ipsec_tx);
ixgbevf_tx_map(tx_ring, first, hdr_len);
@@ -4617,6 +4665,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE -
(ETH_HLEN + ETH_FCS_LEN);
break;
@@ -4652,6 +4701,7 @@
pci_set_drvdata(pdev, netdev);
netif_carrier_off(netdev);
+ ixgbevf_init_ipsec_offload(adapter);
ixgbevf_init_last_counter_stats(adapter);
@@ -4718,6 +4768,7 @@
if (netdev->reg_state == NETREG_REGISTERED)
unregister_netdev(netdev);
+ ixgbevf_stop_ipsec_offload(adapter);
ixgbevf_clear_interrupt_scheme(adapter);
ixgbevf_reset_interrupt_capability(adapter);
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h
index bfd9ae1..853796c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.h
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h
@@ -62,6 +62,7 @@
ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */
ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */
ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */
+ ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */
/* This value should always be last */
ixgbe_mbox_api_unknown, /* indicates that API version is not known */
};
@@ -92,6 +93,10 @@
#define IXGBE_VF_UPDATE_XCAST_MODE 0x0c
+/* mailbox API, version 1.4 VF requests */
+#define IXGBE_VF_IPSEC_ADD 0x0d
+#define IXGBE_VF_IPSEC_DEL 0x0e
+
/* length of permanent address message returned from PF */
#define IXGBE_VF_PERMADDR_MSG_LEN 4
/* word in permanent address message with the current multicast type */
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index bf0577e..d5ce496 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -309,6 +309,7 @@
* is not supported for this device type.
*/
switch (hw->api_version) {
+ case ixgbe_mbox_api_14:
case ixgbe_mbox_api_13:
case ixgbe_mbox_api_12:
if (hw->mac.type < ixgbe_mac_X550_vf)
@@ -376,6 +377,7 @@
* or if the operation is not supported for this device type.
*/
switch (hw->api_version) {
+ case ixgbe_mbox_api_14:
case ixgbe_mbox_api_13:
case ixgbe_mbox_api_12:
if (hw->mac.type < ixgbe_mac_X550_vf)
@@ -506,9 +508,8 @@
vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr);
}
- ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, IXGBE_VFMAILBOX_SIZE);
-
- return 0;
+ return ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+ IXGBE_VFMAILBOX_SIZE);
}
/**
@@ -540,6 +541,7 @@
if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC)
return -EOPNOTSUPP;
/* Fall threw */
+ case ixgbe_mbox_api_14:
case ixgbe_mbox_api_13:
break;
default:
@@ -890,6 +892,7 @@
case ixgbe_mbox_api_11:
case ixgbe_mbox_api_12:
case ixgbe_mbox_api_13:
+ case ixgbe_mbox_api_14:
break;
default:
return 0;