Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 1256dbd..fa2cd76 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1,5 +1,5 @@
/*
- * Copyright(c) 2015 - 2018 Intel Corporation.
+ * Copyright(c) 2015 - 2020 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
@@ -69,6 +69,7 @@
#include "affinity.h"
#include "vnic.h"
#include "exp_rcv.h"
+#include "netdev.h"
#undef pr_fmt
#define pr_fmt(fmt) DRIVER_NAME ": " fmt
@@ -78,8 +79,6 @@
*/
#define HFI1_MIN_USER_CTXT_BUFCNT 7
-#define HFI1_MIN_HDRQ_EGRBUF_CNT 2
-#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
#define HFI1_MIN_EAGER_BUFFER_SIZE (4 * 1024) /* 4KB */
#define HFI1_MAX_EAGER_BUFFER_SIZE (256 * 1024) /* 256KB */
@@ -122,8 +121,6 @@
module_param(user_credit_return_threshold, uint, S_IRUGO);
MODULE_PARM_DESC(user_credit_return_threshold, "Credit return threshold for user send contexts, return when unreturned credits passes this many blocks (in percent of allocated blocks, 0 is off)");
-static inline u64 encode_rcv_header_entry_size(u16 size);
-
DEFINE_XARRAY_FLAGS(hfi1_dev_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
static int hfi1_create_kctxt(struct hfi1_devdata *dd,
@@ -154,7 +151,11 @@
/* Control context must use DMA_RTAIL */
if (rcd->ctxt == HFI1_CTRL_CTXT)
rcd->flags |= HFI1_CAP_DMA_RTAIL;
- rcd->seq_cnt = 1;
+ rcd->fast_handler = get_dma_rtail_setting(rcd) ?
+ handle_receive_interrupt_dma_rtail :
+ handle_receive_interrupt_nodma_rtail;
+
+ hfi1_set_seq_cnt(rcd, 1);
rcd->sc = sc_alloc(dd, SC_ACK, rcd->rcvhdrqentsize, dd->node);
if (!rcd->sc) {
@@ -373,6 +374,9 @@
rcd->numa_id = numa;
rcd->rcv_array_groups = dd->rcv_entries.ngroups;
rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
+ rcd->slow_handler = handle_receive_interrupt;
+ rcd->do_interrupt = rcd->slow_handler;
+ rcd->msix_intr = CCE_NUM_MSIX_VECTORS;
mutex_init(&rcd->exp_mutex);
spin_lock_init(&rcd->exp_lock);
@@ -511,23 +515,6 @@
}
/*
- * Convert a receive header entry size that to the encoding used in the CSR.
- *
- * Return a zero if the given size is invalid.
- */
-static inline u64 encode_rcv_header_entry_size(u16 size)
-{
- /* there are only 3 valid receive header entry sizes */
- if (size == 2)
- return 1;
- if (size == 16)
- return 2;
- else if (size == 32)
- return 4;
- return 0; /* invalid */
-}
-
-/*
* Select the largest ccti value over all SLs to determine the intra-
* packet gap for the link.
*
@@ -910,10 +897,10 @@
if (is_ax(dd)) {
atomic_set(&dd->drop_packet, DROP_PACKET_ON);
- dd->do_drop = 1;
+ dd->do_drop = true;
} else {
atomic_set(&dd->drop_packet, DROP_PACKET_OFF);
- dd->do_drop = 0;
+ dd->do_drop = false;
}
/* make sure the link is not "up" */
@@ -929,18 +916,6 @@
if (ret)
goto done;
- /* allocate dummy tail memory for all receive contexts */
- dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
- sizeof(u64),
- &dd->rcvhdrtail_dummy_dma,
- GFP_KERNEL);
-
- if (!dd->rcvhdrtail_dummy_kvaddr) {
- dd_dev_err(dd, "cannot allocate dummy tail memory\n");
- ret = -ENOMEM;
- goto done;
- }
-
/* dd->rcd can be NULL if early initialization failed */
for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) {
/*
@@ -953,8 +928,6 @@
if (!rcd)
continue;
- rcd->do_interrupt = &handle_receive_interrupt;
-
lastfail = hfi1_create_rcvhdrq(dd, rcd);
if (!lastfail)
lastfail = hfi1_setup_eagerbufs(rcd);
@@ -1162,9 +1135,9 @@
dma_free_coherent(&dd->pcidev->dev, rcvhdrq_size(rcd),
rcd->rcvhdrq, rcd->rcvhdrq_dma);
rcd->rcvhdrq = NULL;
- if (rcd->rcvhdrtail_kvaddr) {
+ if (hfi1_rcvhdrtail_kvaddr(rcd)) {
dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
- (void *)rcd->rcvhdrtail_kvaddr,
+ (void *)hfi1_rcvhdrtail_kvaddr(rcd),
rcd->rcvhdrqtailaddr_dma);
rcd->rcvhdrtail_kvaddr = NULL;
}
@@ -1175,7 +1148,7 @@
rcd->egrbufs.rcvtids = NULL;
for (e = 0; e < rcd->egrbufs.alloced; e++) {
- if (rcd->egrbufs.buffers[e].dma)
+ if (rcd->egrbufs.buffers[e].addr)
dma_free_coherent(&dd->pcidev->dev,
rcd->egrbufs.buffers[e].len,
rcd->egrbufs.buffers[e].addr,
@@ -1227,13 +1200,13 @@
}
/**
- * hfi1_clean_devdata - cleans up per-unit data structure
+ * hfi1_free_devdata - cleans up and frees per-unit data structure
* @dd: pointer to a valid devdata structure
*
- * It cleans up all data structures set up by
+ * It cleans up and frees all data structures set up by
* by hfi1_alloc_devdata().
*/
-static void hfi1_clean_devdata(struct hfi1_devdata *dd)
+void hfi1_free_devdata(struct hfi1_devdata *dd)
{
struct hfi1_asic_data *ad;
unsigned long flags;
@@ -1256,27 +1229,15 @@
dd->tx_opstats = NULL;
kfree(dd->comp_vect);
dd->comp_vect = NULL;
+ if (dd->rcvhdrtail_dummy_kvaddr)
+ dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
+ (void *)dd->rcvhdrtail_dummy_kvaddr,
+ dd->rcvhdrtail_dummy_dma);
+ dd->rcvhdrtail_dummy_kvaddr = NULL;
sdma_clean(dd, dd->num_sdma);
rvt_dealloc_device(&dd->verbs_dev.rdi);
}
-static void __hfi1_free_devdata(struct kobject *kobj)
-{
- struct hfi1_devdata *dd =
- container_of(kobj, struct hfi1_devdata, kobj);
-
- hfi1_clean_devdata(dd);
-}
-
-static struct kobj_type hfi1_devdata_type = {
- .release = __hfi1_free_devdata,
-};
-
-void hfi1_free_devdata(struct hfi1_devdata *dd)
-{
- kobject_put(&dd->kobj);
-}
-
/**
* hfi1_alloc_devdata - Allocate our primary per-unit data structure.
* @pdev: Valid PCI device
@@ -1303,7 +1264,6 @@
dd->pport = (struct hfi1_pportdata *)(dd + 1);
dd->pcidev = pdev;
pci_set_drvdata(pdev, dd);
- dd->node = NUMA_NO_NODE;
ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b,
GFP_KERNEL);
@@ -1313,6 +1273,15 @@
goto bail;
}
rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit);
+ /*
+ * If the BIOS does not have the NUMA node information set, select
+ * NUMA 0 so we get consistent performance.
+ */
+ dd->node = pcibus_to_node(pdev->bus);
+ if (dd->node == NUMA_NO_NODE) {
+ dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
+ dd->node = 0;
+ }
/*
* Initialize all locks for the device. This needs to be as early as
@@ -1362,11 +1331,20 @@
goto bail;
}
- kobject_init(&dd->kobj, &hfi1_devdata_type);
+ /* allocate dummy tail memory for all receive contexts */
+ dd->rcvhdrtail_dummy_kvaddr =
+ dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64),
+ &dd->rcvhdrtail_dummy_dma, GFP_KERNEL);
+ if (!dd->rcvhdrtail_dummy_kvaddr) {
+ ret = -ENOMEM;
+ goto bail;
+ }
+
+ atomic_set(&dd->ipoib_rsm_usr_num, 0);
return dd;
bail:
- hfi1_clean_devdata(dd);
+ hfi1_free_devdata(dd);
return ERR_PTR(ret);
}
@@ -1569,13 +1547,6 @@
free_credit_return(dd);
- if (dd->rcvhdrtail_dummy_kvaddr) {
- dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
- (void *)dd->rcvhdrtail_dummy_kvaddr,
- dd->rcvhdrtail_dummy_dma);
- dd->rcvhdrtail_dummy_kvaddr = NULL;
- }
-
/*
* Free any resources still in use (usually just kernel contexts)
* at unload; we do for ctxtcnt, because that's what we allocate.
@@ -1624,29 +1595,6 @@
hfi1_free_devdata(dd);
}
-static int init_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
-{
- if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
- dd_dev_err(dd, "Receive header queue count too small\n");
- return -EINVAL;
- }
-
- if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
- dd_dev_err(dd,
- "Receive header queue count cannot be greater than %u\n",
- HFI1_MAX_HDRQ_EGRBUF_CNT);
- return -EINVAL;
- }
-
- if (thecnt % HDRQ_INCREMENT) {
- dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
- thecnt, HDRQ_INCREMENT);
- return -EINVAL;
- }
-
- return 0;
-}
-
static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
int ret = 0, j, pidx, initfail;
@@ -1674,7 +1622,7 @@
}
/* Validate some global module parameters */
- ret = init_validate_rcvhdrcnt(dd, rcvhdrcnt);
+ ret = hfi1_validate_rcvhdrcnt(dd, rcvhdrcnt);
if (ret)
goto bail;
@@ -1733,9 +1681,6 @@
/* do the generic initialization */
initfail = hfi1_init(dd, 0);
- /* setup vnic */
- hfi1_vnic_setup(dd);
-
ret = hfi1_register_ib_device(dd);
/*
@@ -1774,7 +1719,6 @@
hfi1_device_remove(dd);
if (!ret)
hfi1_unregister_ib_device(dd);
- hfi1_vnic_cleanup(dd);
postinit_cleanup(dd);
if (initfail)
ret = initfail;
@@ -1819,8 +1763,8 @@
/* unregister from IB core */
hfi1_unregister_ib_device(dd);
- /* cleanup vnic */
- hfi1_vnic_cleanup(dd);
+ /* free netdev data */
+ hfi1_netdev_free(dd);
/*
* Disable the IB link, disable interrupts on the device,
@@ -1856,7 +1800,6 @@
int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
{
unsigned amt;
- u64 reg;
if (!rcd->rcvhdrq) {
gfp_t gfp_flags;
@@ -1888,30 +1831,9 @@
goto bail_free;
}
}
- /*
- * These values are per-context:
- * RcvHdrCnt
- * RcvHdrEntSize
- * RcvHdrSize
- */
- reg = ((u64)(rcd->rcvhdrq_cnt >> HDRQ_SIZE_SHIFT)
- & RCV_HDR_CNT_CNT_MASK)
- << RCV_HDR_CNT_CNT_SHIFT;
- write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_CNT, reg);
- reg = (encode_rcv_header_entry_size(rcd->rcvhdrqentsize)
- & RCV_HDR_ENT_SIZE_ENT_SIZE_MASK)
- << RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
- write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_ENT_SIZE, reg);
- reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK)
- << RCV_HDR_SIZE_HDR_SIZE_SHIFT;
- write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_SIZE, reg);
- /*
- * Program dummy tail address for every receive context
- * before enabling any receive context
- */
- write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_TAIL_ADDR,
- dd->rcvhdrtail_dummy_dma);
+ set_hdrq_regs(rcd->dd, rcd->ctxt, rcd->rcvhdrqentsize,
+ rcd->rcvhdrq_cnt);
return 0;