Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index cddb453..0220616 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1,17 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define dev_fmt pr_fmt
#include <linux/device.h>
#include <linux/eventfd.h>
@@ -56,8 +54,6 @@
MODULE_PARM_DESC(disable_idle_d3,
"Disable using the PCI D3 low power state for idle, unused devices");
-static DEFINE_MUTEX(driver_lock);
-
static inline bool vfio_vga_disabled(void)
{
#ifdef CONFIG_VFIO_PCI_VGA
@@ -211,6 +207,57 @@
return false;
}
+static void vfio_pci_probe_power_state(struct vfio_pci_device *vdev)
+{
+ struct pci_dev *pdev = vdev->pdev;
+ u16 pmcsr;
+
+ if (!pdev->pm_cap)
+ return;
+
+ pci_read_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, &pmcsr);
+
+ vdev->needs_pm_restore = !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET);
+}
+
+/*
+ * pci_set_power_state() wrapper handling devices which perform a soft reset on
+ * D3->D0 transition. Save state prior to D0/1/2->D3, stash it on the vdev,
+ * restore when returned to D0. Saved separately from pci_saved_state for use
+ * by PM capability emulation and separately from pci_dev internal saved state
+ * to avoid it being overwritten and consumed around other resets.
+ */
+int vfio_pci_set_power_state(struct vfio_pci_device *vdev, pci_power_t state)
+{
+ struct pci_dev *pdev = vdev->pdev;
+ bool needs_restore = false, needs_save = false;
+ int ret;
+
+ if (vdev->needs_pm_restore) {
+ if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) {
+ pci_save_state(pdev);
+ needs_save = true;
+ }
+
+ if (pdev->current_state >= PCI_D3hot && state <= PCI_D0)
+ needs_restore = true;
+ }
+
+ ret = pci_set_power_state(pdev, state);
+
+ if (!ret) {
+ /* D3 might be unsupported via quirk, skip unless in D3 */
+ if (needs_save && pdev->current_state >= PCI_D3hot) {
+ vdev->pm_save = pci_store_saved_state(pdev);
+ } else if (needs_restore) {
+ pci_load_and_free_saved_state(pdev, &vdev->pm_save);
+ pci_restore_state(pdev);
+ }
+ }
+
+ return ret;
+}
+
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
@@ -218,7 +265,7 @@
u16 cmd;
u8 msix_pos;
- pci_set_power_state(pdev, PCI_D0);
+ vfio_pci_set_power_state(vdev, PCI_D0);
/* Don't allow our initial saved state to include busmaster */
pci_clear_master(pdev);
@@ -238,12 +285,11 @@
pci_save_state(pdev);
vdev->pci_saved_state = pci_store_saved_state(pdev);
if (!vdev->pci_saved_state)
- pr_debug("%s: Couldn't store %s saved state\n",
- __func__, dev_name(&pdev->dev));
+ pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__);
if (likely(!nointxmask)) {
if (vfio_pci_nointx(pdev)) {
- dev_info(&pdev->dev, "Masking broken INTx support\n");
+ pci_info(pdev, "Masking broken INTx support\n");
vdev->nointx = true;
pci_intx(pdev, 0);
} else
@@ -287,16 +333,36 @@
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
if (ret) {
- dev_warn(&vdev->pdev->dev,
- "Failed to setup Intel IGD regions\n");
- vfio_pci_disable(vdev);
- return ret;
+ pci_warn(pdev, "Failed to setup Intel IGD regions\n");
+ goto disable_exit;
+ }
+ }
+
+ if (pdev->vendor == PCI_VENDOR_ID_NVIDIA &&
+ IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
+ ret = vfio_pci_nvdia_v100_nvlink2_init(vdev);
+ if (ret && ret != -ENODEV) {
+ pci_warn(pdev, "Failed to setup NVIDIA NV2 RAM region\n");
+ goto disable_exit;
+ }
+ }
+
+ if (pdev->vendor == PCI_VENDOR_ID_IBM &&
+ IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
+ ret = vfio_pci_ibm_npu2_init(vdev);
+ if (ret && ret != -ENODEV) {
+ pci_warn(pdev, "Failed to setup NVIDIA NV2 ATSD region\n");
+ goto disable_exit;
}
}
vfio_pci_probe_mmaps(vdev);
return 0;
+
+disable_exit:
+ vfio_pci_disable(vdev);
+ return ret;
}
static void vfio_pci_disable(struct vfio_pci_device *vdev)
@@ -357,8 +423,7 @@
* is just busy work.
*/
if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
- pr_info("%s: Couldn't reload %s saved state\n",
- __func__, dev_name(&pdev->dev));
+ pci_info(pdev, "%s: Couldn't reload saved state\n", __func__);
if (!vdev->reset_works)
goto out;
@@ -373,11 +438,20 @@
pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
/*
- * Try to reset the device. The success of this is dependent on
- * being able to lock the device, which is not always possible.
+ * Try to get the locks ourselves to prevent a deadlock. The
+ * success of this is dependent on being able to lock the device,
+ * which is not always possible.
+ * We can not use the "try" reset interface here, which will
+ * overwrite the previously restored configuration information.
*/
- if (vdev->reset_works && !pci_try_reset_function(pdev))
- vdev->needs_reset = false;
+ if (vdev->reset_works && pci_cfg_access_trylock(pdev)) {
+ if (device_trylock(&pdev->dev)) {
+ if (!__pci_reset_function_locked(pdev))
+ vdev->needs_reset = false;
+ device_unlock(&pdev->dev);
+ }
+ pci_cfg_access_unlock(pdev);
+ }
pci_restore_state(pdev);
out:
@@ -386,21 +460,21 @@
vfio_pci_try_bus_reset(vdev);
if (!disable_idle_d3)
- pci_set_power_state(pdev, PCI_D3hot);
+ vfio_pci_set_power_state(vdev, PCI_D3hot);
}
static void vfio_pci_release(void *device_data)
{
struct vfio_pci_device *vdev = device_data;
- mutex_lock(&driver_lock);
+ mutex_lock(&vdev->reflck->lock);
if (!(--vdev->refcnt)) {
vfio_spapr_pci_eeh_release(vdev->pdev);
vfio_pci_disable(vdev);
}
- mutex_unlock(&driver_lock);
+ mutex_unlock(&vdev->reflck->lock);
module_put(THIS_MODULE);
}
@@ -413,7 +487,7 @@
if (!try_module_get(THIS_MODULE))
return -ENODEV;
- mutex_lock(&driver_lock);
+ mutex_lock(&vdev->reflck->lock);
if (!vdev->refcnt) {
ret = vfio_pci_enable(vdev);
@@ -424,7 +498,7 @@
}
vdev->refcnt++;
error:
- mutex_unlock(&driver_lock);
+ mutex_unlock(&vdev->reflck->lock);
if (ret)
module_put(THIS_MODULE);
return ret;
@@ -434,10 +508,14 @@
{
if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
u8 pin;
- pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
- if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && !vdev->nointx && pin)
- return 1;
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) ||
+ vdev->nointx || vdev->pdev->is_virtfn)
+ return 0;
+
+ pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
+
+ return pin ? 1 : 0;
} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
u8 pos;
u16 flags;
@@ -683,6 +761,7 @@
{
void __iomem *io;
size_t size;
+ u16 orig_cmd;
info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
info.flags = 0;
@@ -698,15 +777,23 @@
break;
}
- /* Is it really there? */
- io = pci_map_rom(pdev, &size);
- if (!io || !size) {
- info.size = 0;
- break;
- }
- pci_unmap_rom(pdev, io);
+ /*
+ * Is it really there? Enable memory decode for
+ * implicit access in pci_map_rom().
+ */
+ pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
+ pci_write_config_word(pdev, PCI_COMMAND,
+ orig_cmd | PCI_COMMAND_MEMORY);
- info.flags = VFIO_REGION_INFO_FLAG_READ;
+ io = pci_map_rom(pdev, &size);
+ if (io) {
+ info.flags = VFIO_REGION_INFO_FLAG_READ;
+ pci_unmap_rom(pdev, io);
+ } else {
+ info.size = 0;
+ }
+
+ pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
break;
}
case VFIO_PCI_VGA_REGION_INDEX:
@@ -746,6 +833,12 @@
if (ret)
return ret;
+ if (vdev->region[i].ops->add_capability) {
+ ret = vdev->region[i].ops->add_capability(vdev,
+ &vdev->region[i], &caps);
+ if (ret)
+ return ret;
+ }
}
}
@@ -1113,6 +1206,15 @@
return -EINVAL;
if ((vma->vm_flags & VM_SHARED) == 0)
return -EINVAL;
+ if (index >= VFIO_PCI_NUM_REGIONS) {
+ int regnum = index - VFIO_PCI_NUM_REGIONS;
+ struct vfio_pci_region *region = vdev->region + regnum;
+
+ if (region && region->ops && region->ops->mmap &&
+ (region->flags & VFIO_REGION_INFO_FLAG_MMAP))
+ return region->ops->mmap(vdev, region, vma);
+ return -EINVAL;
+ }
if (index >= VFIO_PCI_ROM_REGION_INDEX)
return -EINVAL;
if (!vdev->bar_mmap_supported[index])
@@ -1155,17 +1257,18 @@
static void vfio_pci_request(void *device_data, unsigned int count)
{
struct vfio_pci_device *vdev = device_data;
+ struct pci_dev *pdev = vdev->pdev;
mutex_lock(&vdev->igate);
if (vdev->req_trigger) {
if (!(count % 10))
- dev_notice_ratelimited(&vdev->pdev->dev,
+ pci_notice_ratelimited(pdev,
"Relaying device request to user (#%u)\n",
count);
eventfd_signal(vdev->req_trigger, 1);
} else if (count == 0) {
- dev_warn(&vdev->pdev->dev,
+ pci_warn(pdev,
"No device request channel registered, blocked until released by user\n");
}
@@ -1183,6 +1286,9 @@
.request = vfio_pci_request,
};
+static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev);
+static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck);
+
static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct vfio_pci_device *vdev;
@@ -1229,12 +1335,22 @@
return ret;
}
+ ret = vfio_pci_reflck_attach(vdev);
+ if (ret) {
+ vfio_del_group_dev(&pdev->dev);
+ vfio_iommu_group_put(group, &pdev->dev);
+ kfree(vdev);
+ return ret;
+ }
+
if (vfio_pci_is_vga(pdev)) {
vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
vga_set_legacy_decoding(pdev,
vfio_pci_set_vga_decode(vdev, false));
}
+ vfio_pci_probe_power_state(vdev);
+
if (!disable_idle_d3) {
/*
* pci-core sets the device power state to an unknown value at
@@ -1245,8 +1361,8 @@
* be able to get to D3. Therefore first do a D0 transition
* before going to D3.
*/
- pci_set_power_state(pdev, PCI_D0);
- pci_set_power_state(pdev, PCI_D3hot);
+ vfio_pci_set_power_state(vdev, PCI_D0);
+ vfio_pci_set_power_state(vdev, PCI_D3hot);
}
return ret;
@@ -1260,9 +1376,16 @@
if (!vdev)
return;
+ vfio_pci_reflck_put(vdev->reflck);
+
vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
kfree(vdev->region);
mutex_destroy(&vdev->ioeventfds_lock);
+
+ if (!disable_idle_d3)
+ vfio_pci_set_power_state(vdev, PCI_D0);
+
+ kfree(vdev->pm_save);
kfree(vdev);
if (vfio_pci_is_vga(pdev)) {
@@ -1271,9 +1394,6 @@
VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
}
-
- if (!disable_idle_d3)
- pci_set_power_state(pdev, PCI_D0);
}
static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
@@ -1316,16 +1436,97 @@
.err_handler = &vfio_err_handlers,
};
+static DEFINE_MUTEX(reflck_lock);
+
+static struct vfio_pci_reflck *vfio_pci_reflck_alloc(void)
+{
+ struct vfio_pci_reflck *reflck;
+
+ reflck = kzalloc(sizeof(*reflck), GFP_KERNEL);
+ if (!reflck)
+ return ERR_PTR(-ENOMEM);
+
+ kref_init(&reflck->kref);
+ mutex_init(&reflck->lock);
+
+ return reflck;
+}
+
+static void vfio_pci_reflck_get(struct vfio_pci_reflck *reflck)
+{
+ kref_get(&reflck->kref);
+}
+
+static int vfio_pci_reflck_find(struct pci_dev *pdev, void *data)
+{
+ struct vfio_pci_reflck **preflck = data;
+ struct vfio_device *device;
+ struct vfio_pci_device *vdev;
+
+ device = vfio_device_get_from_dev(&pdev->dev);
+ if (!device)
+ return 0;
+
+ if (pci_dev_driver(pdev) != &vfio_pci_driver) {
+ vfio_device_put(device);
+ return 0;
+ }
+
+ vdev = vfio_device_data(device);
+
+ if (vdev->reflck) {
+ vfio_pci_reflck_get(vdev->reflck);
+ *preflck = vdev->reflck;
+ vfio_device_put(device);
+ return 1;
+ }
+
+ vfio_device_put(device);
+ return 0;
+}
+
+static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev)
+{
+ bool slot = !pci_probe_reset_slot(vdev->pdev->slot);
+
+ mutex_lock(&reflck_lock);
+
+ if (pci_is_root_bus(vdev->pdev->bus) ||
+ vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_reflck_find,
+ &vdev->reflck, slot) <= 0)
+ vdev->reflck = vfio_pci_reflck_alloc();
+
+ mutex_unlock(&reflck_lock);
+
+ return PTR_ERR_OR_ZERO(vdev->reflck);
+}
+
+static void vfio_pci_reflck_release(struct kref *kref)
+{
+ struct vfio_pci_reflck *reflck = container_of(kref,
+ struct vfio_pci_reflck,
+ kref);
+
+ kfree(reflck);
+ mutex_unlock(&reflck_lock);
+}
+
+static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck)
+{
+ kref_put_mutex(&reflck->kref, vfio_pci_reflck_release, &reflck_lock);
+}
+
struct vfio_devices {
struct vfio_device **devices;
int cur_index;
int max_index;
};
-static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
+static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
{
struct vfio_devices *devs = data;
struct vfio_device *device;
+ struct vfio_pci_device *vdev;
if (devs->cur_index == devs->max_index)
return -ENOSPC;
@@ -1339,16 +1540,28 @@
return -EBUSY;
}
+ vdev = vfio_device_data(device);
+
+ /* Fault if the device is not unused */
+ if (vdev->refcnt) {
+ vfio_device_put(device);
+ return -EBUSY;
+ }
+
devs->devices[devs->cur_index++] = device;
return 0;
}
/*
- * Attempt to do a bus/slot reset if there are devices affected by a reset for
- * this device that are needs_reset and all of the affected devices are unused
- * (!refcnt). Callers are required to hold driver_lock when calling this to
- * prevent device opens and concurrent bus reset attempts. We prevent device
- * unbinds by acquiring and holding a reference to the vfio_device.
+ * If a bus or slot reset is available for the provided device and:
+ * - All of the devices affected by that bus or slot reset are unused
+ * (!refcnt)
+ * - At least one of the affected devices is marked dirty via
+ * needs_reset (such as by lack of FLR support)
+ * Then attempt to perform that bus or slot reset. Callers are required
+ * to hold vdev->reflck->lock, protecting the bus/slot reset group from
+ * concurrent opens. A vfio_device reference is acquired for each device
+ * to prevent unbinds during the reset operation.
*
* NB: vfio-core considers a group to be viable even if some devices are
* bound to drivers like pci-stub or pcieport. Here we require all devices
@@ -1359,7 +1572,7 @@
{
struct vfio_devices devs = { .cur_index = 0 };
int i = 0, ret = -EINVAL;
- bool needs_reset = false, slot = false;
+ bool slot = false;
struct vfio_pci_device *tmp;
if (!pci_probe_reset_slot(vdev->pdev->slot))
@@ -1377,28 +1590,36 @@
return;
if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
- vfio_pci_get_devs, &devs, slot))
+ vfio_pci_get_unused_devs,
+ &devs, slot))
goto put_devs;
+ /* Does at least one need a reset? */
for (i = 0; i < devs.cur_index; i++) {
tmp = vfio_device_data(devs.devices[i]);
- if (tmp->needs_reset)
- needs_reset = true;
- if (tmp->refcnt)
- goto put_devs;
+ if (tmp->needs_reset) {
+ ret = pci_reset_bus(vdev->pdev);
+ break;
+ }
}
- if (needs_reset)
- ret = pci_reset_bus(vdev->pdev);
-
put_devs:
for (i = 0; i < devs.cur_index; i++) {
tmp = vfio_device_data(devs.devices[i]);
- if (!ret)
+
+ /*
+ * If reset was successful, affected devices no longer need
+ * a reset and we should return all the collateral devices
+ * to low power. If not successful, we either didn't reset
+ * the bus or timed out waiting for it, so let's not touch
+ * the power state.
+ */
+ if (!ret) {
tmp->needs_reset = false;
- if (!tmp->refcnt && !disable_idle_d3)
- pci_set_power_state(tmp->pdev, PCI_D3hot);
+ if (tmp != vdev && !disable_idle_d3)
+ vfio_pci_set_power_state(tmp, PCI_D3hot);
+ }
vfio_device_put(devs.devices[i]);
}
@@ -1443,11 +1664,11 @@
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}