vhost_scsi_set_endpoint() allocates command pools only for I/O virtqueues
that are already set up, but publishes the backend for every virtqueue. If
userspace finishes configuring a skipped queue later, a kick reaches
vhost_scsi_get_cmd() with scsi_tags uninitialized and triggers the
!sb->alloc_hint warning in sbitmap_get().
Leave skipped I/O virtqueues inactive at SET_ENDPOINT. When SET_VRING_ADDR
later completes their setup, allocate the command pools and activate the
queues. Roll back both if access initialization fails.
Fixes: 25b98b64e284 ("vhost scsi: alloc cmds per vq instead of session")
Signed-off-by: Linfeng Sun <[email protected]>
---
I checked QEMU and found no evidence it's affected. I haven't checked
VirtualBox because I am not familiar with it. However, the virtio spec
doesn't require a specific operation order, so a new VMM could still
trigger this issue.
Crash log:
[ 34.698961] ------------[ cut here ]------------
[ 34.699385] WARNING: lib/sbitmap.c:286 at sbitmap_get+0x227/0x270, CPU#0:
vhost-82/88
[ 34.700542] Modules linked in:
[ 34.701309] CPU: 0 UID: 0 PID: 88 Comm: vhost-82 Not tainted 7.3.0-rc2+ #14
PREEMPT(full)
[ 34.701958] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps
fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[ 34.702717] RIP: 0010:sbitmap_get+0x227/0x270
[ 34.703247] Code: 41 8d 5d 01 89 df 44 89 fe e8 f5 3a 46 ff 31 c0 44 39 fb
0f 43 d8 e8 38 46 46 ff 65 41 89 1c 24 e9 25 ff ff ff e8 29 46 46 ff <0f> 0b eb
ba e8 20 46 46 ff 44 89 fe 31 ff 45 31 e4 e8 c3 3b 46 ff
[ 34.704234] RSP: 0018:ffffc90000ec3bb0 EFLAGS: 00000246
[ 34.704677] RAX: 0000000000000000 RBX: ffff88800500dee8 RCX: 0000000000000000
[ 34.705166] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88800500dee8
[ 34.705584] RBP: ffffc90000ec3be0 R08: 0000000000000000 R09: 0000000000000000
[ 34.705988] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000006
[ 34.706477] R13: 0000000000000000 R14: 0000000000000000 R15: ffff8880050094d0
[ 34.706955] FS: 0000000014d05380(0000) GS:ffff888099c36000(0000)
knlGS:0000000000000000
[ 34.707463] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 34.707854] CR2: 00007c0c3c20e000 CR3: 0000000008e47000 CR4: 00000000000006f0
[ 34.708592] Call Trace:
[ 34.709259] <TASK>
[ 34.709822] vhost_scsi_handle_vq+0x4a9/0x1b20
[ 34.710437] ? update_cfs_rq_load_avg+0x2e/0x230
[ 34.710874] vhost_scsi_handle_kick+0x2c/0x40
[ 34.711292] vhost_run_work_list+0xa6/0xf0
[ 34.711673] vhost_task_fn+0x76/0x1b0
[ 34.712003] ? __sanitizer_cov_trace_const_cmp1+0x1a/0x30
[ 34.712506] ? recalc_sigpending+0xe1/0x130
[ 34.712890] ? __pfx_vhost_task_fn+0x10/0x10
[ 34.713325] ret_from_fork+0x37a/0x630
[ 34.713673] ? __pfx_vhost_task_fn+0x10/0x10
[ 34.714031] ret_from_fork_asm+0x1a/0x30
[ 34.714535] RIP: 0033:0x0
[ 34.715201] Code: Unable to access opcode bytes at 0xffffffffffffffd6.
[ 34.715587] RSP: 002b:0000000000000000 EFLAGS: 00000246 ORIG_RAX:
0000000000000010
[ 34.716158] RAX: 0000000000000000 RBX: 000000000048bb20 RCX: 000000000041ca3d
[ 34.716571] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
[ 34.716957] RBP: 00007ffcac47c4e0 R08: 00000000ffffffff R09: 0000000000000000
[ 34.717418] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004
[ 34.717826] R13: 00007ffcac47c778 R14: 00000000004af868 R15: 0000000000000001
[ 34.718363] </TASK>
---
drivers/vhost/scsi.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 42 insertions(+), 2 deletions(-)
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 4f8c0260bc9e..069a6ff4dd40 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -2008,6 +2008,40 @@ static int vhost_scsi_setup_vq_cmds(struct
vhost_virtqueue *vq, int max_cmds)
return -ENOMEM;
}
+/* Callers must hold dev mutex. */
+static int vhost_scsi_activate_vqs(struct vhost_scsi *vs)
+{
+ struct vhost_virtqueue *vq;
+ int i, ret = 0;
+
+ if (!vs->vs_tpg)
+ return 0;
+
+ for (i = VHOST_SCSI_VQ_IO; i < vs->dev.nvqs; i++) {
+ vq = &vs->vqs[i].vq;
+ mutex_lock(&vq->mutex);
+ if (vhost_vq_get_backend(vq) || !vhost_vq_is_setup(vq))
+ goto unlock;
+
+ ret = vhost_scsi_setup_vq_cmds(vq, vq->num);
+ if (ret)
+ goto unlock;
+
+ vhost_vq_set_backend(vq, vs->vs_tpg);
+ ret = vhost_vq_init_access(vq);
+ if (ret) {
+ vhost_vq_set_backend(vq, NULL);
+ vhost_scsi_destroy_vq_cmds(vq);
+ }
+unlock:
+ mutex_unlock(&vq->mutex);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
/*
* Called from vhost_scsi_ioctl() context to walk the list of available
* vhost_scsi_tpg with an active struct vhost_scsi_nexus
@@ -2105,6 +2139,9 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
for (i = 0; i < vs->dev.nvqs; i++) {
vq = &vs->vqs[i].vq;
+ if (i >= VHOST_SCSI_VQ_IO && !vs->vqs[i].scsi_cmds)
+ continue;
+
mutex_lock(&vq->mutex);
vhost_vq_set_backend(vq, vs_tpg);
vhost_vq_init_access(vq);
@@ -2466,10 +2503,13 @@ vhost_scsi_ioctl(struct file *f,
default:
mutex_lock(&vs->dev.mutex);
r = vhost_dev_ioctl(&vs->dev, ioctl, argp);
- if (r == -ENOIOCTLCMD)
+ if (r == -ENOIOCTLCMD) {
r = vhost_vring_ioctl(&vs->dev, ioctl, argp);
- else
+ if (!r && ioctl == VHOST_SET_VRING_ADDR)
+ r = vhost_scsi_activate_vqs(vs);
+ } else {
vhost_scsi_flush(vs);
+ }
mutex_unlock(&vs->dev.mutex);
return r;
}
---
base-commit: dd886653d2038a510a21bff476fa1be0422a4fb9
Best regards,
--
Linfeng Sun <[email protected]>
