linux/drivers/virtio/virtio_pci_common.c

577 lines
15 KiB
C
Raw Normal View History

/*
* 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>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#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(vp_dev->msix_entries[i].vector);
}
/* 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 void vp_free_vectors(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i;
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(vp_dev->msix_entries[i].vector, vp_dev);
for (i = 0; i < vp_dev->msix_vectors; i++)
if (vp_dev->msix_affinity_masks[i])
free_cpumask_var(vp_dev->msix_affinity_masks[i]);
if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
pci_disable_msix(vp_dev->pci_dev);
vp_dev->msix_enabled = 0;
}
virtio-pci: fix leaks of msix_affinity_masks vp_dev->msix_vectors should be initialized before allocating msix_affinity_masks, otherwise vp_free_vectors will not free these objects. unreferenced object 0xffff88010f969d88 (size 512): comm "systemd-udevd", pid 158, jiffies 4294673645 (age 80.545s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff816e455e>] kmemleak_alloc+0x5e/0xc0 [<ffffffff811aa7f1>] kmem_cache_alloc_node_trace+0x141/0x2c0 [<ffffffff8133ba23>] alloc_cpumask_var_node+0x23/0x80 [<ffffffff8133ba8e>] alloc_cpumask_var+0xe/0x10 [<ffffffff813fdb3d>] vp_try_to_find_vqs+0x25d/0x810 [<ffffffff813fe171>] vp_find_vqs+0x81/0xb0 [<ffffffffa00d2a05>] init_vqs+0x85/0x120 [virtio_balloon] [<ffffffffa00d2c29>] virtballoon_probe+0xf9/0x1a0 [virtio_balloon] [<ffffffff813fb61e>] virtio_dev_probe+0xde/0x140 [<ffffffff814452b8>] driver_probe_device+0x98/0x3a0 [<ffffffff8144566b>] __driver_attach+0xab/0xb0 [<ffffffff814432f4>] bus_for_each_dev+0x94/0xb0 [<ffffffff81444f4e>] driver_attach+0x1e/0x20 [<ffffffff81444910>] bus_add_driver+0x200/0x280 [<ffffffff81445c14>] driver_register+0x74/0x160 [<ffffffff813fb7d0>] register_virtio_driver+0x20/0x40 v2: change msix_vectors uncoditionaly in vp_free_vectors Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2013-07-02 06:05:13 +00:00
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_entries);
vp_dev->msix_entries = NULL;
kfree(vp_dev->msix_affinity_masks);
vp_dev->msix_affinity_masks = NULL;
}
static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
bool per_vq_vectors)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
const char *name = dev_name(&vp_dev->vdev.dev);
unsigned i, v;
int err = -ENOMEM;
virtio-pci: fix leaks of msix_affinity_masks vp_dev->msix_vectors should be initialized before allocating msix_affinity_masks, otherwise vp_free_vectors will not free these objects. unreferenced object 0xffff88010f969d88 (size 512): comm "systemd-udevd", pid 158, jiffies 4294673645 (age 80.545s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff816e455e>] kmemleak_alloc+0x5e/0xc0 [<ffffffff811aa7f1>] kmem_cache_alloc_node_trace+0x141/0x2c0 [<ffffffff8133ba23>] alloc_cpumask_var_node+0x23/0x80 [<ffffffff8133ba8e>] alloc_cpumask_var+0xe/0x10 [<ffffffff813fdb3d>] vp_try_to_find_vqs+0x25d/0x810 [<ffffffff813fe171>] vp_find_vqs+0x81/0xb0 [<ffffffffa00d2a05>] init_vqs+0x85/0x120 [virtio_balloon] [<ffffffffa00d2c29>] virtballoon_probe+0xf9/0x1a0 [virtio_balloon] [<ffffffff813fb61e>] virtio_dev_probe+0xde/0x140 [<ffffffff814452b8>] driver_probe_device+0x98/0x3a0 [<ffffffff8144566b>] __driver_attach+0xab/0xb0 [<ffffffff814432f4>] bus_for_each_dev+0x94/0xb0 [<ffffffff81444f4e>] driver_attach+0x1e/0x20 [<ffffffff81444910>] bus_add_driver+0x200/0x280 [<ffffffff81445c14>] driver_register+0x74/0x160 [<ffffffff813fb7d0>] register_virtio_driver+0x20/0x40 v2: change msix_vectors uncoditionaly in vp_free_vectors Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2013-07-02 06:05:13 +00:00
vp_dev->msix_vectors = nvectors;
vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
GFP_KERNEL);
if (!vp_dev->msix_entries)
goto error;
vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
GFP_KERNEL);
if (!vp_dev->msix_names)
goto error;
vp_dev->msix_affinity_masks
= kzalloc(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;
for (i = 0; i < nvectors; ++i)
vp_dev->msix_entries[i].entry = i;
err = pci_enable_msix_exact(vp_dev->pci_dev,
vp_dev->msix_entries, nvectors);
if (err)
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(vp_dev->msix_entries[v].vector,
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(vp_dev->msix_entries[v].vector,
vp_vring_interrupt, 0, vp_dev->msix_names[v],
vp_dev);
if (err)
goto error;
++vp_dev->msix_used_vectors;
}
return 0;
error:
vp_free_vectors(vdev);
return err;
}
static int vp_request_intx(struct virtio_device *vdev)
{
int err;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
if (!err)
vp_dev->intx_enabled = 1;
return err;
}
static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
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, 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;
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;
struct virtio_pci_vq_info *info;
list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
info = vp_dev->vqs[vq->index];
virtio: fix out of range array access I have observed the following error on virtio-net module unload: ------------[ cut here ]------------ WARNING: at kernel/irq/manage.c:858 __free_irq+0xa0/0x14c() Hardware name: Bochs Trying to free already-free IRQ 0 Modules linked in: virtio_net(-) virtio_blk virtio_pci virtio_ring virtio af_packet e1000 shpchp aacraid uhci_hcd ohci_hcd ehci_hcd [last unloaded: scsi_wait_scan] Pid: 1957, comm: rmmod Not tainted 2.6.33-rc8-vhost #24 Call Trace: [<ffffffff8103e195>] warn_slowpath_common+0x7c/0x94 [<ffffffff8103e204>] warn_slowpath_fmt+0x41/0x43 [<ffffffff810a7a36>] ? __free_pages+0x5a/0x70 [<ffffffff8107cc00>] __free_irq+0xa0/0x14c [<ffffffff8107cceb>] free_irq+0x3f/0x65 [<ffffffffa0081424>] vp_del_vqs+0x81/0xb1 [virtio_pci] [<ffffffffa0091d29>] virtnet_remove+0xda/0x10b [virtio_net] [<ffffffffa0075200>] virtio_dev_remove+0x22/0x4a [virtio] [<ffffffff812709ee>] __device_release_driver+0x66/0xac [<ffffffff81270ab7>] driver_detach+0x83/0xa9 [<ffffffff8126fc66>] bus_remove_driver+0x91/0xb4 [<ffffffff81270fcf>] driver_unregister+0x6c/0x74 [<ffffffffa0075418>] unregister_virtio_driver+0xe/0x10 [virtio] [<ffffffffa0091c4d>] fini+0x15/0x17 [virtio_net] [<ffffffff8106997b>] sys_delete_module+0x1c3/0x230 [<ffffffff81007465>] ? old_ich_force_enable_hpet+0x117/0x164 [<ffffffff813bb720>] ? do_page_fault+0x29c/0x2cc [<ffffffff81028e58>] sysenter_dispatch+0x7/0x27 ---[ end trace 15e88e4c576cc62b ]--- The bug is in virtio-pci: we use msix_vector as array index to get irq entry, but some vqs do not have a dedicated vector so this causes an out of bounds access. By chance, we seem to often get 0 value, which results in this error. Fix by verifying that vector is legal before using it as index. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Anthony Liguori <aliguori@us.ibm.com> Acked-by: Shirley Ma <xma@us.ibm.com> Acked-by: Amit Shah <amit.shah@redhat.com>
2010-02-25 17:08:55 +00:00
if (vp_dev->per_vq_vectors &&
info->msix_vector != VIRTIO_MSI_NO_VECTOR)
free_irq(vp_dev->msix_entries[info->msix_vector].vector,
vq);
vp_del_vq(vq);
}
vp_dev->per_vq_vectors = false;
vp_free_vectors(vdev);
kfree(vp_dev->vqs);
vp_dev->vqs = NULL;
}
static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[],
bool use_msix,
bool per_vq_vectors)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
u16 msix_vec;
int i, err, nvectors, allocated_vectors;
vp_dev->vqs = kmalloc(nvqs * sizeof *vp_dev->vqs, GFP_KERNEL);
if (!vp_dev->vqs)
return -ENOMEM;
if (!use_msix) {
/* Old style: one normal interrupt for change and all vqs. */
err = vp_request_intx(vdev);
if (err)
goto error_find;
} else {
if (per_vq_vectors) {
/* Best option: one for change interrupt, one per vq. */
nvectors = 1;
for (i = 0; i < nvqs; ++i)
if (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);
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;
} else if (!callbacks[i] || !vp_dev->msix_enabled)
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, i, callbacks[i], names[i], 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 13:06:06 +00:00
if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
continue;
/* allocate per-vq irq if available and necessary */
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 13:06:06 +00:00
snprintf(vp_dev->msix_names[msix_vec],
sizeof *vp_dev->msix_names,
"%s-%s",
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(vp_dev->msix_entries[msix_vec].vector,
vring_interrupt, 0,
vp_dev->msix_names[msix_vec],
vqs[i]);
if (err) {
vp_del_vq(vqs[i]);
goto error_find;
}
}
return 0;
error_find:
vp_del_vqs(vdev);
return err;
}
/* the config->find_vqs() implementation */
int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[])
{
int err;
/* Try MSI-X with one vector per queue. */
err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
if (!err)
return 0;
/* Fallback: MSI-X with one vector for config, one shared for queues. */
err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
true, false);
if (!err)
return 0;
/* Finally fall back to regular interrupts. */
return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
false, false);
}
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, int cpu)
{
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 = vp_dev->msix_entries[info->msix_vector].vector;
if (cpu == -1)
irq_set_affinity_hint(irq, NULL);
else {
cpumask_clear(mask);
cpumask_set_cpu(cpu, mask);
irq_set_affinity_hint(irq, mask);
}
}
return 0;
}
#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;
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);
rc = register_virtio_device(&vp_dev->vdev);
if (rc)
goto err_register;
return 0;
err_register:
if (vp_dev->ioaddr)
virtio_pci_legacy_remove(vp_dev);
else
virtio_pci_modern_remove(vp_dev);
err_probe:
pci_disable_device(pci_dev);
err_enable_device:
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);
unregister_virtio_device(&vp_dev->vdev);
if (vp_dev->ioaddr)
virtio_pci_legacy_remove(vp_dev);
else
virtio_pci_modern_remove(vp_dev);
pci_disable_device(pci_dev);
put_device(dev);
}
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
};
module_pci_driver(virtio_pci_driver);
MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
MODULE_DESCRIPTION("virtio-pci");
MODULE_LICENSE("GPL");
MODULE_VERSION("1");