virtio-pci: fix per-vq MSI-X request logic

PATCH In review Michael S. Tsirkin 2 participants 5 messages Oct 22, 2009 – Oct 23, 2009 virtio core

Share & tools

Michael S. Tsirkin

author maintainer

2009-10-22 13:08 UTC #0 lore raw

PATCH 1/1 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 <[email protected]>

Reported-by Shirley Ma <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---

Rusty, since this is a regression from 2.6.31, I think we want to push this for 2.6.32. Thanks!

 drivers/virtio/virtio_pci.c |   27 +++++++++++++++------------
 1 files changed, 15 insertions(+), 12 deletions(-)

drivers/virtio/virtio_pci.c +15 ~~-12~~

index 4a1f1eb..28d9cf7 100644
@@ -530,19 +530,22 @@ static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			err = PTR_ERR(vqs[i]);
 			goto error_find;
 		}
+
+		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+			continue;
+
 		/* allocate per-vq irq if available and necessary */
-		if (vp_dev->per_vq_vectors) {
-			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(msix_vec, vring_interrupt, 0,
-					  vp_dev->msix_names[msix_vec],
-					  vqs[i]);
-			if (err) {
-				vp_del_vq(vqs[i]);
-				goto error_find;
-			}
+		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;

Signature · 1 line

1.6.5.rc2

Marcelo Tosatti

Tested-by on v1 1/1

2009-10-22 16:17 UTC #1 lore raw

Quoted 6 lines · Michael S. Tsirkin

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

Quoted 7 lines

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.

Works for me. Thanks Michael.

Tested-by Marcelo Tosatti <[email protected]>

Marcelo Tosatti

Tested-by on v1 1/1

2009-10-22 16:20 UTC #2 lore raw

In reply to Michael S. Tsirkin

Quoted 6 lines · Michael S. Tsirkin

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

Quoted 7 lines

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.

Works for me. Thanks Michael.

Tested-by Marcelo Tosatti <[email protected]>

Michael S. Tsirkin

author maintainer Tested-by Shirley Ma Tested-by Marcelo Tosatti on v1 1/1

2009-10-23 11:08 UTC #3 lore raw

In reply to Michael S. Tsirkin

Quoted 47 lines · Michael S. Tsirkin

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

Quoted 6 lines

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 <[email protected]>
Reported-by Shirley Ma <[email protected]>
Signed-off-by Michael S. Tsirkin <[email protected]>

You can now add

Tested-by Shirley Ma <[email protected]>

Tested-by Marcelo Tosatti <[email protected]>

Michael S. Tsirkin

author maintainer Tested-by Shirley Ma Tested-by Marcelo Tosatti on v1 1/1

2009-10-23 11:11 UTC #4 lore raw

In reply to Michael S. Tsirkin

Quoted 47 lines · Michael S. Tsirkin

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

Quoted 6 lines

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 <[email protected]>
Reported-by Shirley Ma <[email protected]>
Signed-off-by Michael S. Tsirkin <[email protected]>

You can now add

Tested-by Shirley Ma <[email protected]>

Tested-by Marcelo Tosatti <[email protected]>