OpenCloudOS-Kernel/drivers/virtio/virtio_pci_common.c

653 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio PCI driver - common functionality for all device versions
*
* This module allows virtio devices to be used over a virtual PCI device.
* This can be used with QEMU based VMMs like KVM or Xen.
*
* Copyright IBM Corp. 2007
* Copyright Red Hat, Inc. 2014
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
* Rusty Russell <rusty@rustcorp.com.au>
* Michael S. Tsirkin <mst@redhat.com>
*/
#include "virtio_pci_common.h"
static bool force_legacy = false;
#if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
module_param(force_legacy, bool, 0444);
MODULE_PARM_DESC(force_legacy,
"Force legacy mode for transitional virtio 1 devices");
#endif
/* wait for pending irq handlers */
void vp_synchronize_vectors(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i;
if (vp_dev->intx_enabled)
synchronize_irq(vp_dev->pci_dev->irq);
for (i = 0; i < vp_dev->msix_vectors; ++i)
synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
}
/* the notify function used when creating a virt queue */
bool vp_notify(struct virtqueue *vq)
{
/* we write the queue's selector into the notification register to
* signal the other end */
iowrite16(vq->index, (void __iomem *)vq->priv);
return true;
}
/* Handle a configuration change: Tell driver if it wants to know. */
static irqreturn_t vp_config_changed(int irq, void *opaque)
{
struct virtio_pci_device *vp_dev = opaque;
virtio_config_changed(&vp_dev->vdev);
return IRQ_HANDLED;
}
/* Notify all virtqueues on an interrupt. */
static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
{
struct virtio_pci_device *vp_dev = opaque;
struct virtio_pci_vq_info *info;
irqreturn_t ret = IRQ_NONE;
unsigned long flags;
spin_lock_irqsave(&vp_dev->lock, flags);
list_for_each_entry(info, &vp_dev->virtqueues, node) {
if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
ret = IRQ_HANDLED;
}
spin_unlock_irqrestore(&vp_dev->lock, flags);
return ret;
}
/* A small wrapper to also acknowledge the interrupt when it's handled.
* I really need an EIO hook for the vring so I can ack the interrupt once we
* know that we'll be handling the IRQ but before we invoke the callback since
* the callback may notify the host which results in the host attempting to
* raise an interrupt that we would then mask once we acknowledged the
* interrupt. */
static irqreturn_t vp_interrupt(int irq, void *opaque)
{
struct virtio_pci_device *vp_dev = opaque;
u8 isr;
/* reading the ISR has the effect of also clearing it so it's very
* important to save off the value. */
isr = ioread8(vp_dev->isr);
/* It's definitely not us if the ISR was not high */
if (!isr)
return IRQ_NONE;
/* Configuration change? Tell driver if it wants to know. */
if (isr & VIRTIO_PCI_ISR_CONFIG)
vp_config_changed(irq, opaque);
return vp_vring_interrupt(irq, opaque);
}
static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
bool per_vq_vectors, struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
const char *name = dev_name(&vp_dev->vdev.dev);
unsigned int flags = PCI_IRQ_MSIX;
unsigned int i, v;
int err = -ENOMEM;
vp_dev->msix_vectors = nvectors;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
vp_dev->msix_names = kmalloc_array(nvectors,
sizeof(*vp_dev->msix_names),
GFP_KERNEL);
if (!vp_dev->msix_names)
goto error;
vp_dev->msix_affinity_masks
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
= kcalloc(nvectors, sizeof(*vp_dev->msix_affinity_masks),
GFP_KERNEL);
if (!vp_dev->msix_affinity_masks)
goto error;
for (i = 0; i < nvectors; ++i)
if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
GFP_KERNEL))
goto error;
if (desc) {
flags |= PCI_IRQ_AFFINITY;
desc->pre_vectors++; /* virtio config vector */
}
err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
nvectors, flags, desc);
if (err < 0)
goto error;
vp_dev->msix_enabled = 1;
/* Set the vector used for configuration */
v = vp_dev->msix_used_vectors;
snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
"%s-config", name);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
vp_config_changed, 0, vp_dev->msix_names[v],
vp_dev);
if (err)
goto error;
++vp_dev->msix_used_vectors;
v = vp_dev->config_vector(vp_dev, v);
/* Verify we had enough resources to assign the vector */
if (v == VIRTIO_MSI_NO_VECTOR) {
err = -EBUSY;
goto error;
}
if (!per_vq_vectors) {
/* Shared vector for all VQs */
v = vp_dev->msix_used_vectors;
snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
"%s-virtqueues", name);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
vp_vring_interrupt, 0, vp_dev->msix_names[v],
vp_dev);
if (err)
goto error;
++vp_dev->msix_used_vectors;
}
return 0;
error:
return err;
}
static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
void (*callback)(struct virtqueue *vq),
const char *name,
bool ctx,
u16 msix_vec)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
struct virtqueue *vq;
unsigned long flags;
/* fill out our structure that represents an active queue */
if (!info)
return ERR_PTR(-ENOMEM);
vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
msix_vec);
if (IS_ERR(vq))
goto out_info;
info->vq = vq;
if (callback) {
spin_lock_irqsave(&vp_dev->lock, flags);
list_add(&info->node, &vp_dev->virtqueues);
spin_unlock_irqrestore(&vp_dev->lock, flags);
} else {
INIT_LIST_HEAD(&info->node);
}
vp_dev->vqs[index] = info;
return vq;
out_info:
kfree(info);
return vq;
}
static void vp_del_vq(struct virtqueue *vq)
{
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
unsigned long flags;
/*
* If it fails during re-enable reset vq. This way we won't rejoin
* info->node to the queue. Prevent unexpected irqs.
*/
if (!vq->reset) {
spin_lock_irqsave(&vp_dev->lock, flags);
list_del(&info->node);
spin_unlock_irqrestore(&vp_dev->lock, flags);
}
vp_dev->del_vq(info);
kfree(info);
}
/* the config->del_vqs() implementation */
void vp_del_vqs(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtqueue *vq, *n;
int i;
list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
if (vp_dev->per_vq_vectors) {
int v = vp_dev->vqs[vq->index]->msix_vector;
if (v != VIRTIO_MSI_NO_VECTOR) {
int irq = pci_irq_vector(vp_dev->pci_dev, v);
irq_set_affinity_hint(irq, NULL);
free_irq(irq, vq);
}
}
vp_del_vq(vq);
}
vp_dev->per_vq_vectors = false;
if (vp_dev->intx_enabled) {
free_irq(vp_dev->pci_dev->irq, vp_dev);
vp_dev->intx_enabled = 0;
}
for (i = 0; i < vp_dev->msix_used_vectors; ++i)
free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
virtio_pci: fix a NULL pointer reference in vp_del_vqs If the msix_affinity_masks is alloced failed, then we'll try to free some resources in vp_free_vectors() that may access it directly. We met the following stack in our production: [ 29.296767] BUG: unable to handle kernel NULL pointer dereference at (null) [ 29.311151] IP: [<ffffffffc04fe35a>] vp_free_vectors+0x6a/0x150 [virtio_pci] [ 29.324787] PGD 0 [ 29.333224] Oops: 0000 [#1] SMP [...] [ 29.425175] RIP: 0010:[<ffffffffc04fe35a>] [<ffffffffc04fe35a>] vp_free_vectors+0x6a/0x150 [virtio_pci] [ 29.441405] RSP: 0018:ffff9a55c2dcfa10 EFLAGS: 00010206 [ 29.453491] RAX: 0000000000000000 RBX: ffff9a55c322c400 RCX: 0000000000000000 [ 29.467488] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9a55c322c400 [ 29.481461] RBP: ffff9a55c2dcfa20 R08: 0000000000000000 R09: ffffc1b6806ff020 [ 29.495427] R10: 0000000000000e95 R11: 0000000000aaaaaa R12: 0000000000000000 [ 29.509414] R13: 0000000000010000 R14: ffff9a55bd2d9e98 R15: ffff9a55c322c400 [ 29.523407] FS: 00007fdcba69f8c0(0000) GS:ffff9a55c2840000(0000) knlGS:0000000000000000 [ 29.538472] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 29.551621] CR2: 0000000000000000 CR3: 000000003ce52000 CR4: 00000000003607a0 [ 29.565886] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 29.580055] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 29.594122] Call Trace: [ 29.603446] [<ffffffffc04fe8a2>] vp_request_msix_vectors+0xe2/0x260 [virtio_pci] [ 29.618017] [<ffffffffc04fedc5>] vp_try_to_find_vqs+0x95/0x3b0 [virtio_pci] [ 29.632152] [<ffffffffc04ff117>] vp_find_vqs+0x37/0xb0 [virtio_pci] [ 29.645582] [<ffffffffc057bf63>] init_vq+0x153/0x260 [virtio_blk] [ 29.658831] [<ffffffffc057c1e8>] virtblk_probe+0xe8/0x87f [virtio_blk] [...] Cc: Gonglei <arei.gonglei@huawei.com> Signed-off-by: Longpeng <longpeng2@huawei.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Gonglei <arei.gonglei@huawei.com>
2019-03-09 15:17:40 +08:00
if (vp_dev->msix_affinity_masks) {
for (i = 0; i < vp_dev->msix_vectors; i++)
free_cpumask_var(vp_dev->msix_affinity_masks[i]);
virtio_pci: fix a NULL pointer reference in vp_del_vqs If the msix_affinity_masks is alloced failed, then we'll try to free some resources in vp_free_vectors() that may access it directly. We met the following stack in our production: [ 29.296767] BUG: unable to handle kernel NULL pointer dereference at (null) [ 29.311151] IP: [<ffffffffc04fe35a>] vp_free_vectors+0x6a/0x150 [virtio_pci] [ 29.324787] PGD 0 [ 29.333224] Oops: 0000 [#1] SMP [...] [ 29.425175] RIP: 0010:[<ffffffffc04fe35a>] [<ffffffffc04fe35a>] vp_free_vectors+0x6a/0x150 [virtio_pci] [ 29.441405] RSP: 0018:ffff9a55c2dcfa10 EFLAGS: 00010206 [ 29.453491] RAX: 0000000000000000 RBX: ffff9a55c322c400 RCX: 0000000000000000 [ 29.467488] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9a55c322c400 [ 29.481461] RBP: ffff9a55c2dcfa20 R08: 0000000000000000 R09: ffffc1b6806ff020 [ 29.495427] R10: 0000000000000e95 R11: 0000000000aaaaaa R12: 0000000000000000 [ 29.509414] R13: 0000000000010000 R14: ffff9a55bd2d9e98 R15: ffff9a55c322c400 [ 29.523407] FS: 00007fdcba69f8c0(0000) GS:ffff9a55c2840000(0000) knlGS:0000000000000000 [ 29.538472] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 29.551621] CR2: 0000000000000000 CR3: 000000003ce52000 CR4: 00000000003607a0 [ 29.565886] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 29.580055] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 29.594122] Call Trace: [ 29.603446] [<ffffffffc04fe8a2>] vp_request_msix_vectors+0xe2/0x260 [virtio_pci] [ 29.618017] [<ffffffffc04fedc5>] vp_try_to_find_vqs+0x95/0x3b0 [virtio_pci] [ 29.632152] [<ffffffffc04ff117>] vp_find_vqs+0x37/0xb0 [virtio_pci] [ 29.645582] [<ffffffffc057bf63>] init_vq+0x153/0x260 [virtio_blk] [ 29.658831] [<ffffffffc057c1e8>] virtblk_probe+0xe8/0x87f [virtio_blk] [...] Cc: Gonglei <arei.gonglei@huawei.com> Signed-off-by: Longpeng <longpeng2@huawei.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Gonglei <arei.gonglei@huawei.com>
2019-03-09 15:17:40 +08:00
}
if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
pci_free_irq_vectors(vp_dev->pci_dev);
vp_dev->msix_enabled = 0;
}
vp_dev->msix_vectors = 0;
vp_dev->msix_used_vectors = 0;
kfree(vp_dev->msix_names);
vp_dev->msix_names = NULL;
kfree(vp_dev->msix_affinity_masks);
vp_dev->msix_affinity_masks = NULL;
kfree(vp_dev->vqs);
vp_dev->vqs = NULL;
}
static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
const char * const names[], bool per_vq_vectors,
const bool *ctx,
struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
u16 msix_vec;
int i, err, nvectors, allocated_vectors, queue_idx = 0;
vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
if (!vp_dev->vqs)
return -ENOMEM;
if (per_vq_vectors) {
/* Best option: one for change interrupt, one per vq. */
nvectors = 1;
for (i = 0; i < nvqs; ++i)
if (names[i] && callbacks[i])
++nvectors;
} else {
/* Second best: one for change, shared for all vqs. */
nvectors = 2;
}
err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors,
per_vq_vectors ? desc : NULL);
if (err)
goto error_find;
vp_dev->per_vq_vectors = per_vq_vectors;
allocated_vectors = vp_dev->msix_used_vectors;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
if (!callbacks[i])
msix_vec = VIRTIO_MSI_NO_VECTOR;
else if (vp_dev->per_vq_vectors)
msix_vec = allocated_vectors++;
else
msix_vec = VP_MSIX_VQ_VECTOR;
vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
ctx ? ctx[i] : false,
msix_vec);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
goto error_find;
}
virtio-pci: fix per-vq MSI-X request logic Commit f68d24082e22ccee3077d11aeb6dc5354f0ca7f1 in 2.6.32-rc1 broke requesting IRQs for per-VQ MSI-X vectors: - vector number was used instead of the vector itself - we try to request an IRQ for VQ which does not have a callback handler This is a regression that causes warnings in kernel log, potentially lower performance as we need to scan vq list, and might cause system failure if the interrupt requested is in fact needed by another system. This was not noticed earlier because in most cases we were falling back on shared interrupt for all vqs. The warnings often look like this: virtio-pci 0000:00:03.0: irq 26 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 27 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 28 for MSI/MSI-X IRQ handler type mismatch for IRQ 1 current handler: i8042 Pid: 2400, comm: modprobe Tainted: G W 2.6.32-rc3-11952-gf3ed8d8-dirty #1 Call Trace: [<ffffffff81072aed>] ? __setup_irq+0x299/0x304 [<ffffffff81072ff3>] ? request_threaded_irq+0x144/0x1c1 [<ffffffff813455af>] ? vring_interrupt+0x0/0x30 [<ffffffff81346598>] ? vp_try_to_find_vqs+0x583/0x5c7 [<ffffffffa0015188>] ? skb_recv_done+0x0/0x34 [virtio_net] [<ffffffff81346609>] ? vp_find_vqs+0x2d/0x83 [<ffffffff81345d00>] ? vp_get+0x3c/0x4e [<ffffffffa0016373>] ? virtnet_probe+0x2f1/0x428 [virtio_net] [<ffffffffa0015188>] ? skb_recv_done+0x0/0x34 [virtio_net] [<ffffffffa00150d8>] ? skb_xmit_done+0x0/0x39 [virtio_net] [<ffffffff8110ab92>] ? sysfs_do_create_link+0xcb/0x116 [<ffffffff81345cc2>] ? vp_get_status+0x14/0x16 [<ffffffff81345464>] ? virtio_dev_probe+0xa9/0xc8 [<ffffffff8122b11c>] ? driver_probe_device+0x8d/0x128 [<ffffffff8122b206>] ? __driver_attach+0x4f/0x6f [<ffffffff8122b1b7>] ? __driver_attach+0x0/0x6f [<ffffffff8122a9f9>] ? bus_for_each_dev+0x43/0x74 [<ffffffff8122a374>] ? bus_add_driver+0xea/0x22d [<ffffffff8122b4a3>] ? driver_register+0xa7/0x111 [<ffffffffa001a000>] ? init+0x0/0xc [virtio_net] [<ffffffff81009051>] ? do_one_initcall+0x50/0x148 [<ffffffff8106e117>] ? sys_init_module+0xc5/0x21a [<ffffffff8100af02>] ? system_call_fastpath+0x16/0x1b virtio-pci 0000:00:03.0: irq 26 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 27 for MSI/MSI-X Reported-by: Marcelo Tosatti <mtosatti@redhat.com> Reported-by: Shirley Ma <xma@us.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2009-10-22 21:06:06 +08:00
if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
continue;
/* allocate per-vq irq if available and necessary */
snprintf(vp_dev->msix_names[msix_vec],
sizeof *vp_dev->msix_names,
"%s-%s",
virtio-pci: fix per-vq MSI-X request logic Commit f68d24082e22ccee3077d11aeb6dc5354f0ca7f1 in 2.6.32-rc1 broke requesting IRQs for per-VQ MSI-X vectors: - vector number was used instead of the vector itself - we try to request an IRQ for VQ which does not have a callback handler This is a regression that causes warnings in kernel log, potentially lower performance as we need to scan vq list, and might cause system failure if the interrupt requested is in fact needed by another system. This was not noticed earlier because in most cases we were falling back on shared interrupt for all vqs. The warnings often look like this: virtio-pci 0000:00:03.0: irq 26 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 27 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 28 for MSI/MSI-X IRQ handler type mismatch for IRQ 1 current handler: i8042 Pid: 2400, comm: modprobe Tainted: G W 2.6.32-rc3-11952-gf3ed8d8-dirty #1 Call Trace: [<ffffffff81072aed>] ? __setup_irq+0x299/0x304 [<ffffffff81072ff3>] ? request_threaded_irq+0x144/0x1c1 [<ffffffff813455af>] ? vring_interrupt+0x0/0x30 [<ffffffff81346598>] ? vp_try_to_find_vqs+0x583/0x5c7 [<ffffffffa0015188>] ? skb_recv_done+0x0/0x34 [virtio_net] [<ffffffff81346609>] ? vp_find_vqs+0x2d/0x83 [<ffffffff81345d00>] ? vp_get+0x3c/0x4e [<ffffffffa0016373>] ? virtnet_probe+0x2f1/0x428 [virtio_net] [<ffffffffa0015188>] ? skb_recv_done+0x0/0x34 [virtio_net] [<ffffffffa00150d8>] ? skb_xmit_done+0x0/0x39 [virtio_net] [<ffffffff8110ab92>] ? sysfs_do_create_link+0xcb/0x116 [<ffffffff81345cc2>] ? vp_get_status+0x14/0x16 [<ffffffff81345464>] ? virtio_dev_probe+0xa9/0xc8 [<ffffffff8122b11c>] ? driver_probe_device+0x8d/0x128 [<ffffffff8122b206>] ? __driver_attach+0x4f/0x6f [<ffffffff8122b1b7>] ? __driver_attach+0x0/0x6f [<ffffffff8122a9f9>] ? bus_for_each_dev+0x43/0x74 [<ffffffff8122a374>] ? bus_add_driver+0xea/0x22d [<ffffffff8122b4a3>] ? driver_register+0xa7/0x111 [<ffffffffa001a000>] ? init+0x0/0xc [virtio_net] [<ffffffff81009051>] ? do_one_initcall+0x50/0x148 [<ffffffff8106e117>] ? sys_init_module+0xc5/0x21a [<ffffffff8100af02>] ? system_call_fastpath+0x16/0x1b virtio-pci 0000:00:03.0: irq 26 for MSI/MSI-X virtio-pci 0000:00:03.0: irq 27 for MSI/MSI-X Reported-by: Marcelo Tosatti <mtosatti@redhat.com> Reported-by: Shirley Ma <xma@us.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2009-10-22 21:06:06 +08:00
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
vring_interrupt, 0,
vp_dev->msix_names[msix_vec],
vqs[i]);
if (err)
goto error_find;
}
return 0;
error_find:
vp_del_vqs(vdev);
return err;
}
static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
const char * const names[], const bool *ctx)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i, err, queue_idx = 0;
vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
if (!vp_dev->vqs)
return -ENOMEM;
err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
dev_name(&vdev->dev), vp_dev);
if (err)
goto out_del_vqs;
vp_dev->intx_enabled = 1;
vp_dev->per_vq_vectors = false;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
ctx ? ctx[i] : false,
VIRTIO_MSI_NO_VECTOR);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
goto out_del_vqs;
}
}
return 0;
out_del_vqs:
vp_del_vqs(vdev);
return err;
}
/* the config->find_vqs() implementation */
int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
const char * const names[], const bool *ctx,
struct irq_affinity *desc)
{
int err;
/* Try MSI-X with one vector per queue. */
err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc);
if (!err)
return 0;
/* Fallback: MSI-X with one vector for config, one shared for queues. */
err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
if (!err)
return 0;
/* Is there an interrupt? If not give up. */
if (!(to_vp_device(vdev)->pci_dev->irq))
virtio_pci: don't try to use intxif pin is zero The background is that we use dpu in cloud computing,the arch is x86,80 cores. We will have a lots of virtio devices,like 512 or more. When we probe about 200 virtio_blk devices,it will fail and the stack is printed as follows: [25338.485128] virtio-pci 0000:b3:00.0: virtio_pci: leaving for legacy driver [25338.496174] genirq: Flags mismatch irq 0. 00000080 (virtio418) vs. 00015a00 (timer) [25338.503822] CPU: 20 PID: 5431 Comm: kworker/20:0 Kdump: loaded Tainted: G OE --------- - - 4.18.0-305.30.1.el8.x86_64 [25338.516403] Hardware name: Inspur NF5280M5/YZMB-00882-10E, BIOS 4.1.21 08/25/2021 [25338.523881] Workqueue: events work_for_cpu_fn [25338.528235] Call Trace: [25338.530687] dump_stack+0x5c/0x80 [25338.534000] __setup_irq.cold.53+0x7c/0xd3 [25338.538098] request_threaded_irq+0xf5/0x160 [25338.542371] vp_find_vqs+0xc7/0x190 [25338.545866] init_vq+0x17c/0x2e0 [virtio_blk] [25338.550223] ? ncpus_cmp_func+0x10/0x10 [25338.554061] virtblk_probe+0xe6/0x8a0 [virtio_blk] [25338.558846] virtio_dev_probe+0x158/0x1f0 [25338.562861] really_probe+0x255/0x4a0 [25338.566524] ? __driver_attach_async_helper+0x90/0x90 [25338.571567] driver_probe_device+0x49/0xc0 [25338.575660] bus_for_each_drv+0x79/0xc0 [25338.579499] __device_attach+0xdc/0x160 [25338.583337] bus_probe_device+0x9d/0xb0 [25338.587167] device_add+0x418/0x780 [25338.590654] register_virtio_device+0x9e/0xe0 [25338.595011] virtio_pci_probe+0xb3/0x140 [25338.598941] local_pci_probe+0x41/0x90 [25338.602689] work_for_cpu_fn+0x16/0x20 [25338.606443] process_one_work+0x1a7/0x360 [25338.610456] ? create_worker+0x1a0/0x1a0 [25338.614381] worker_thread+0x1cf/0x390 [25338.618132] ? create_worker+0x1a0/0x1a0 [25338.622051] kthread+0x116/0x130 [25338.625283] ? kthread_flush_work_fn+0x10/0x10 [25338.629731] ret_from_fork+0x1f/0x40 [25338.633395] virtio_blk: probe of virtio418 failed with error -16 The log : "genirq: Flags mismatch irq 0. 00000080 (virtio418) vs. 00015a00 (timer)" was printed because of the irq 0 is used by timer exclusive,and when vp_find_vqs call vp_find_vqs_msix and returns false twice (for whatever reason), then it will call vp_find_vqs_intx as a fallback. Because vp_dev->pci_dev->irq is zero, we request irq 0 with flag IRQF_SHARED, and get a backtrace like above. According to PCI spec about "Interrupt Pin" Register (Offset 3Dh): "The Interrupt Pin register is a read-only register that identifies the legacy interrupt Message(s) the Function uses. Valid values are 01h, 02h, 03h, and 04h that map to legacy interrupt Messages for INTA, INTB, INTC, and INTD respectively. A value of 00h indicates that the Function uses no legacy interrupt Message(s)." So if vp_dev->pci_dev->pin is zero, we should not request legacy interrupt. Signed-off-by: Angus Chen <angus.chen@jaguarmicro.com> Suggested-by: Michael S. Tsirkin <mst@redhat.com> Message-Id: <20220930000915.548-1-angus.chen@jaguarmicro.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-09-30 08:09:15 +08:00
return err;
/* Finally fall back to regular interrupts. */
return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
}
const char *vp_bus_name(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
return pci_name(vp_dev->pci_dev);
}
/* Setup the affinity for a virtqueue:
* - force the affinity for per vq vector
* - OR over all affinities for shared MSI
* - ignore the affinity request if we're using INTX
*/
int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
{
struct virtio_device *vdev = vq->vdev;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
struct cpumask *mask;
unsigned int irq;
if (!vq->callback)
return -EINVAL;
if (vp_dev->msix_enabled) {
mask = vp_dev->msix_affinity_masks[info->msix_vector];
irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
if (!cpu_mask)
irq_set_affinity_hint(irq, NULL);
else {
cpumask_copy(mask, cpu_mask);
irq_set_affinity_hint(irq, mask);
}
}
return 0;
}
const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
if (!vp_dev->per_vq_vectors ||
vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR)
return NULL;
return pci_irq_get_affinity(vp_dev->pci_dev,
vp_dev->vqs[index]->msix_vector);
}
#ifdef CONFIG_PM_SLEEP
static int virtio_pci_freeze(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
int ret;
ret = virtio_device_freeze(&vp_dev->vdev);
if (!ret)
pci_disable_device(pci_dev);
return ret;
}
static int virtio_pci_restore(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
int ret;
ret = pci_enable_device(pci_dev);
if (ret)
return ret;
pci_set_master(pci_dev);
return virtio_device_restore(&vp_dev->vdev);
}
static const struct dev_pm_ops virtio_pci_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
};
#endif
/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
static const struct pci_device_id virtio_pci_id_table[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) },
{ 0 }
};
MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
static void virtio_pci_release_dev(struct device *_d)
{
struct virtio_device *vdev = dev_to_virtio(_d);
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
/* As struct device is a kobject, it's not safe to
* free the memory (including the reference counter itself)
* until it's release callback. */
kfree(vp_dev);
}
static int virtio_pci_probe(struct pci_dev *pci_dev,
const struct pci_device_id *id)
{
struct virtio_pci_device *vp_dev, *reg_dev = NULL;
int rc;
/* allocate our structure and fill it out */
vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
if (!vp_dev)
return -ENOMEM;
pci_set_drvdata(pci_dev, vp_dev);
vp_dev->vdev.dev.parent = &pci_dev->dev;
vp_dev->vdev.dev.release = virtio_pci_release_dev;
vp_dev->pci_dev = pci_dev;
INIT_LIST_HEAD(&vp_dev->virtqueues);
spin_lock_init(&vp_dev->lock);
/* enable the device */
rc = pci_enable_device(pci_dev);
if (rc)
goto err_enable_device;
if (force_legacy) {
rc = virtio_pci_legacy_probe(vp_dev);
/* Also try modern mode if we can't map BAR0 (no IO space). */
if (rc == -ENODEV || rc == -ENOMEM)
rc = virtio_pci_modern_probe(vp_dev);
if (rc)
goto err_probe;
} else {
rc = virtio_pci_modern_probe(vp_dev);
if (rc == -ENODEV)
rc = virtio_pci_legacy_probe(vp_dev);
if (rc)
goto err_probe;
}
pci_set_master(pci_dev);
vp_dev->is_legacy = vp_dev->ldev.ioaddr ? true : false;
rc = register_virtio_device(&vp_dev->vdev);
reg_dev = vp_dev;
if (rc)
goto err_register;
return 0;
err_register:
if (vp_dev->is_legacy)
virtio_pci_legacy_remove(vp_dev);
else
virtio_pci_modern_remove(vp_dev);
err_probe:
pci_disable_device(pci_dev);
err_enable_device:
if (reg_dev)
put_device(&vp_dev->vdev.dev);
else
kfree(vp_dev);
return rc;
}
static void virtio_pci_remove(struct pci_dev *pci_dev)
{
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
struct device *dev = get_device(&vp_dev->vdev.dev);
virtio_pci: Support surprise removal of virtio pci device When a virtio pci device undergo surprise removal (aka async removal in PCIe spec), mark the device as broken so that any upper layer drivers can abort any outstanding operation. When a virtio net pci device undergo surprise removal which is used by a NetworkManager, a below call trace was observed. kernel:watchdog: BUG: soft lockup - CPU#1 stuck for 26s! [kworker/1:1:27059] watchdog: BUG: soft lockup - CPU#1 stuck for 52s! [kworker/1:1:27059] CPU: 1 PID: 27059 Comm: kworker/1:1 Tainted: G S W I L 5.13.0-hotplug+ #8 Hardware name: Dell Inc. PowerEdge R640/0H28RR, BIOS 2.9.4 11/06/2020 Workqueue: events linkwatch_event RIP: 0010:virtnet_send_command+0xfc/0x150 [virtio_net] Call Trace: virtnet_set_rx_mode+0xcf/0x2a7 [virtio_net] ? __hw_addr_create_ex+0x85/0xc0 __dev_mc_add+0x72/0x80 igmp6_group_added+0xa7/0xd0 ipv6_mc_up+0x3c/0x60 ipv6_find_idev+0x36/0x80 addrconf_add_dev+0x1e/0xa0 addrconf_dev_config+0x71/0x130 addrconf_notify+0x1f5/0xb40 ? rtnl_is_locked+0x11/0x20 ? __switch_to_asm+0x42/0x70 ? finish_task_switch+0xaf/0x2c0 ? raw_notifier_call_chain+0x3e/0x50 raw_notifier_call_chain+0x3e/0x50 netdev_state_change+0x67/0x90 linkwatch_do_dev+0x3c/0x50 __linkwatch_run_queue+0xd2/0x220 linkwatch_event+0x21/0x30 process_one_work+0x1c8/0x370 worker_thread+0x30/0x380 ? process_one_work+0x370/0x370 kthread+0x118/0x140 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x1f/0x30 Hence, add the ability to abort the command on surprise removal which prevents infinite loop and system lockup. Signed-off-by: Parav Pandit <parav@nvidia.com> Link: https://lore.kernel.org/r/20210721142648.1525924-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2021-07-21 22:26:48 +08:00
/*
* Device is marked broken on surprise removal so that virtio upper
* layers can abort any ongoing operation.
*/
if (!pci_device_is_present(pci_dev))
virtio_break_device(&vp_dev->vdev);
pci_disable_sriov(pci_dev);
unregister_virtio_device(&vp_dev->vdev);
if (vp_dev->is_legacy)
virtio_pci_legacy_remove(vp_dev);
else
virtio_pci_modern_remove(vp_dev);
pci_disable_device(pci_dev);
put_device(dev);
}
static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs)
{
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
struct virtio_device *vdev = &vp_dev->vdev;
int ret;
if (!(vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_DRIVER_OK))
return -EBUSY;
if (!__virtio_test_bit(vdev, VIRTIO_F_SR_IOV))
return -EINVAL;
if (pci_vfs_assigned(pci_dev))
return -EPERM;
if (num_vfs == 0) {
pci_disable_sriov(pci_dev);
return 0;
}
ret = pci_enable_sriov(pci_dev, num_vfs);
if (ret < 0)
return ret;
return num_vfs;
}
static struct pci_driver virtio_pci_driver = {
.name = "virtio-pci",
.id_table = virtio_pci_id_table,
.probe = virtio_pci_probe,
.remove = virtio_pci_remove,
#ifdef CONFIG_PM_SLEEP
.driver.pm = &virtio_pci_pm_ops,
#endif
.sriov_configure = virtio_pci_sriov_configure,
};
module_pci_driver(virtio_pci_driver);
MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
MODULE_DESCRIPTION("virtio-pci");
MODULE_LICENSE("GPL");
MODULE_VERSION("1");