Skip to contentSkip to conversation

virtio: validate split queue head count before popping

PATCH Superseded Jia Jia 2 participants 7 messages Jul 9 – Jul 26

lore
Share & tools
lore

Jia Jia

author
#0 lore raw

PATCH 1/1 virtio: validate split queue head count before popping

virtqueue_split_pop() reads the next split avail ring entry after virtio_queue_empty_rcu() reports work. Call virtqueue_num_heads() before consuming that entry, so an avail index distance larger than the queue size is rejected.

virtqueue_num_heads() also keeps the read barrier needed before the avail ring entry is read.

This prevents an invalid split queue state from being expanded into repeated device command processing.

---
Tested with qemu-system-x86_64 11.0.50, built from origin/master f893c46c3931 plus this patch, configured with:
--target-list=x86_64-softmmu --enable-kvm --disable-tcg

The original virtio-iommu live-vring qtest reproducer used for the report completed successfully on the patched build without host OOM, confirming that this reproducer is fixed by the patch.

 hw/virtio/virtio.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
hw/virtio/virtio.c +5 -3
index f4d86a3655..252bff8641 100644
@@ -1751,9 +1751,11 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
     if (virtio_queue_empty_rcu(vq)) {
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
+        goto done;
+    }
 
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;
Signature · 1 line
2.34.1
#1 lore raw
Quoted 31 lines · Jia Jia

virtqueue_split_pop() reads the next split avail ring entry after virtio_queue_empty_rcu() reports work. Call virtqueue_num_heads() before consuming that entry, so an avail index distance larger than the queue size is rejected.

virtqueue_num_heads() also keeps the read barrier needed before the avail ring entry is read.

This prevents an invalid split queue state from being expanded into repeated device command processing.

---
Tested with qemu-system-x86_64 11.0.50, built from origin/master f893c46c3931 plus this patch, configured with:
--target-list=x86_64-softmmu --enable-kvm --disable-tcg

The original virtio-iommu live-vring qtest reproducer used for the report completed successfully on the patched build without host OOM, confirming that this reproducer is fixed by the patch.

 hw/virtio/virtio.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
hw/virtio/virtio.c +0 -0
index f4d86a3655..252bff8641 100644
@@ -1751,9 +1751,11 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
     if (virtio_queue_empty_rcu(vq)) {

hw/virtio/virtio.c static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) · line 1758

Quoted 10 lines
hw/virtio/virtio.c +5 -3
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
+        goto done;
+    }

Do we still need virtio_queue_empty_rcu then? Why?

Quoted 4 lines
hw/virtio/virtio.c +0 -0
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;
Signature · 1 line
2.34.1
#2 lore raw

I think virtio_queue_empty_rcu() is no longer needed after this change.

For this caller, the pieces it covered are either already handled elsewhere or
kept explicitly in the split pop path.

The disabled-device check is already done by virtqueue_pop() before it calls virtqueue_split_pop().

The empty-queue check is covered by virtqueue_num_heads(): rc == 0 is the normal empty case, and rc < 0 is the invalid avail index distance case that this
patch wants to reject.

The read barrier is also covered by virtqueue_num_heads(), since it does smp_rmb() when it returns a positive head count, before the caller reads the avail ring entry with virtqueue_get_head().

The only old check that I think should stay explicit in virtqueue_split_pop() is
!vq->vring.avail. virtqueue_num_heads() does not check that, and the old behavior for an unconfigured split queue was to treat it as empty. So v2 keeps
that guard and replaces the rest of virtio_queue_empty_rcu() with virtqueue_num_heads():

    RCU_READ_LOCK_GUARD();
    if (unlikely(!vq->vring.avail)) {
        goto done;
    }

    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
    if (rc <= 0) {
        goto done;
    }

With that, virtio_queue_empty_rcu() has no remaining users and can be removed.

If this looks right, I can send a v2 patch with this change.

Quoted 53 lines · Michael S. Tsirkin <[email protected]> 于2026年7月9日周四 20:43写道:

hw/virtio/virtio.c static void *virtqueue_split_pop(VirtQueue *vq,

Quoted 30 lines · Jia Jia

virtqueue_split_pop() reads the next split avail ring entry after virtio_queue_empty_rcu() reports work. Call virtqueue_num_heads() before consuming that entry, so an avail index distance larger than the queue size is rejected.

virtqueue_num_heads() also keeps the read barrier needed before the avail ring entry is read.

This prevents an invalid split queue state from being expanded into repeated device command processing.

---
Tested with qemu-system-x86_64 11.0.50, built from origin/master f893c46c3931 plus this patch, configured with:
--target-list=x86_64-softmmu --enable-kvm --disable-tcg

The original virtio-iommu live-vring qtest reproducer used for the report completed successfully on the patched build without host OOM, confirming that this reproducer is fixed by the patch.

 hw/virtio/virtio.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
hw/virtio/virtio.c +0 -0
index f4d86a3655..252bff8641 100644
@@ -1751,9 +1751,11 @@ static void *virtqueue_split_pop(VirtQueue *vq,

size_t sz)

hw/virtio/virtio.c static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) · line 1758

Quoted 11 lines
hw/virtio/virtio.c +5 -3
     if (virtio_queue_empty_rcu(vq)) {
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
+        goto done;
+    }

Do we still need virtio_queue_empty_rcu then? Why?

Quoted 4 lines
hw/virtio/virtio.c +0 -1
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;
--

2.34.1

#3 lore raw
Quoted 17 lines · m'te'a physical

I think virtio_queue_empty_rcu() is no longer needed after this change.

For this caller, the pieces it covered are either already handled elsewhere or kept explicitly in the split pop path.

The disabled-device check is already done by virtqueue_pop() before it calls virtqueue_split_pop().

The empty-queue check is covered by virtqueue_num_heads(): rc == 0 is the normal empty case, and rc < 0 is the invalid avail index distance case that this
patch wants to reject.

The read barrier is also covered by virtqueue_num_heads(), since it does smp_rmb() when it returns a positive head count, before the caller reads the avail ring entry with virtqueue_get_head().

Quoted 6 lines

The only old check that I think should stay explicit in virtqueue_split_pop() is
!vq->vring.avail. virtqueue_num_heads() does not check that, and the old behavior for an unconfigured split queue was to treat it as empty. So v2 keeps that guard and replaces the rest of virtio_queue_empty_rcu() with virtqueue_num_heads():

Yea this is our hacky way to check the mr cache is valid.

Quoted 69 lines

    RCU_READ_LOCK_GUARD();
    if (unlikely(!vq->vring.avail)) {
        goto done;
    }

    rc = virtqueue_num_heads(vq, vq->last_avail_idx); if (rc <= 0) {
        goto done;
    }

With that, virtio_queue_empty_rcu() has no remaining users and can be removed.

If this looks right, I can send a v2 patch with this change.

Michael S. Tsirkin <[email protected]> 于2026年7月9日周四 20:43写道:

    On Thu, Jul 09, 2026 at 06:05:29PM +0800, Jia Jia wrote:
    > virtqueue_split_pop() reads the next split avail ring entry after
    > virtio_queue_empty_rcu() reports work. Call virtqueue_num_heads() before
    > consuming that entry, so an avail index distance larger than the queue
    > size is rejected.
    >
    > virtqueue_num_heads() also keeps the read barrier needed before the avail
    > ring entry is read.
    >
    > This prevents an invalid split queue state from being expanded into
    > repeated device command processing.
    >
    > Link: https://gitlab.com/qemu-project/qemu/-/issues/3930
    > Signed-off-by: Jia Jia <[email protected]>
    > ---
    > Tested with qemu-system-x86_64 11.0.50, built from origin/master
    > f893c46c3931 plus this patch, configured with:
    >   --target-list=x86_64-softmmu --enable-kvm --disable-tcg
    >
    > The original virtio-iommu live-vring qtest reproducer used for the
    > report completed successfully on the patched build without host OOM,
    > confirming that this reproducer is fixed by the patch.
    >
    >  hw/virtio/virtio.c | 8 +++++---
    >  1 file changed, 5 insertions(+), 3 deletions(-)
    >
    > diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
    > index f4d86a3655..252bff8641 100644
    > --- a/hw/virtio/virtio.c
    > +++ b/hw/virtio/virtio.c
    > @@ -1751,9 +1751,11 @@ static void *virtqueue_split_pop(VirtQueue *vq,
    size_t sz)
    >      if (virtio_queue_empty_rcu(vq)) {
    >          goto done;
    >      }
    > -    /* Needed after virtio_queue_empty(), see comment in
    > -     * virtqueue_num_heads(). */
    > -    smp_rmb();
    > +
    > +    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
    > +    if (rc <= 0) {
    > +        goto done;
    > +    }


    Do we still need virtio_queue_empty_rcu then? Why?

    >      /* When we start there are none of either input nor output. */
    >      out_num = in_num = elem_entries = 0;
    > --
    > 2.34.1
author
#4 lore raw

PATCH v2 1/1 virtio: validate split queue head count before popping

virtqueue_split_pop() reads the next split avail ring entry after checking that the ring is configured. Call virtqueue_num_heads() before consuming that entry, so an avail index distance larger than the queue size is rejected.

virtqueue_num_heads() also reports an empty queue and keeps the read barrier needed before the avail ring entry is read. Drop the now unused virtio_queue_empty_rcu() helper.

This prevents an invalid split queue state from being expanded into repeated device command processing.

---
v2:
- Drop virtio_queue_empty_rcu() from the split pop path.
- Keep only the existing !vq->vring.avail early exit before virtqueue_num_heads().
- Remove the now unused virtio_queue_empty_rcu() helper.

Tested with qemu-system-x86_64 11.0.50, built from origin/master f893c46c3931 plus this patch, configured with:
--target-list=x86_64-softmmu --enable-kvm --disable-tcg

The original virtio-iommu live-vring qtest reproducer used for the report completed successfully on the patched build without host OOM, confirming that this reproducer is fixed by the patch.

 hw/virtio/virtio.c | 30 ++++++------------------------
 1 file changed, 6 insertions(+), 24 deletions(-)
hw/virtio/virtio.c +6 -24
index f4d86a3655..68ec3f0751 100644
@@ -716,26 +716,6 @@ static inline bool is_desc_avail(uint16_t flags, bool wrap_counter)
     return (avail != used) && (avail == wrap_counter);
 }
 
-/* Fetch avail_idx from VQ memory only when we really need to know if
- * guest has added some buffers.
- * Called within rcu_read_lock().  */
-static int virtio_queue_empty_rcu(VirtQueue *vq)
-{
-    if (virtio_device_disabled(vq->vdev)) {
-        return 1;
-    }
-
-    if (unlikely(!vq->vring.avail)) {
-        return 1;
-    }
-
-    if (vq->shadow_avail_idx != vq->last_avail_idx) {
-        return 0;
-    }
-
-    return vring_avail_idx(vq) == vq->last_avail_idx;
-}
-
 static int virtio_queue_split_empty(VirtQueue *vq)
 {
     bool empty;
@@ -1748,12 +1728,14 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
     address_space_cache_init_empty(&indirect_desc_cache);
 
     RCU_READ_LOCK_GUARD();
-    if (virtio_queue_empty_rcu(vq)) {
+    if (unlikely(!vq->vring.avail)) {
+        goto done;
+    }
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
 
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;
Signature · 1 line
2.34.1
#5 lore raw
Quoted 11 lines · Jia Jia

virtqueue_split_pop() reads the next split avail ring entry after checking that the ring is configured. Call virtqueue_num_heads() before consuming that entry, so an avail index distance larger than the queue size is rejected.

virtqueue_num_heads() also reports an empty queue and keeps the read barrier needed before the avail ring entry is read. Drop the now unused virtio_queue_empty_rcu() helper.

This prevents an invalid split queue state from being expanded into repeated device command processing.

We can summarize this as:

virtio: reduce code duplication for split ring

virtio_queue_empty_rcu duplicates virtqueue_num_heads for no good reason, let's not do it. As a nice side effect, we gain better handling for misbehaving guests.

Quoted 1 line

not sure this is very relevant.

Quoted 25 lines

---
v2:
- Drop virtio_queue_empty_rcu() from the split pop path.
- Keep only the existing !vq->vring.avail early exit before virtqueue_num_heads().
- Remove the now unused virtio_queue_empty_rcu() helper.

Tested with qemu-system-x86_64 11.0.50, built from origin/master f893c46c3931 plus this patch, configured with:
--target-list=x86_64-softmmu --enable-kvm --disable-tcg

The original virtio-iommu live-vring qtest reproducer used for the report completed successfully on the patched build without host OOM, confirming that this reproducer is fixed by the patch.

 hw/virtio/virtio.c | 30 ++++++------------------------
 1 file changed, 6 insertions(+), 24 deletions(-)
hw/virtio/virtio.c +0 -0
index f4d86a3655..68ec3f0751 100644
@@ -716,26 +716,6 @@ static inline bool is_desc_avail(uint16_t flags, bool wrap_counter)
     return (avail != used) && (avail == wrap_counter);

hw/virtio/virtio.c static inline bool is_desc_avail(uint16_t flags, bool wrap_counter) · line 726

Quoted 10 lines
hw/virtio/virtio.c +0 -8
 }
 
-/* Fetch avail_idx from VQ memory only when we really need to know if
- * guest has added some buffers.
- * Called within rcu_read_lock().  */
-static int virtio_queue_empty_rcu(VirtQueue *vq)
-{
-    if (virtio_device_disabled(vq->vdev)) {
-        return 1;
-    }

This check is no longer there. intentional?

Quoted 36 lines
hw/virtio/virtio.c +6 -16
-
-    if (unlikely(!vq->vring.avail)) {
-        return 1;
-    }
-
-    if (vq->shadow_avail_idx != vq->last_avail_idx) {
-        return 0;
-    }
-
-    return vring_avail_idx(vq) == vq->last_avail_idx;
-}
-
 static int virtio_queue_split_empty(VirtQueue *vq)
 {
     bool empty;
@@ -1748,12 +1728,14 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
     address_space_cache_init_empty(&indirect_desc_cache);
 
     RCU_READ_LOCK_GUARD();
-    if (virtio_queue_empty_rcu(vq)) {
+    if (unlikely(!vq->vring.avail)) {
+        goto done;
+    }
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
 
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;
Signature · 1 line
2.34.1
author
#6 lore raw

PATCH v3 1/1 virtio: reduce code duplication for split ring

virtio_queue_empty_rcu duplicates virtqueue_num_heads for no good reason, let's not do it. As a nice side effect, we gain better handling for misbehaving guests.

The virtio_device_disabled() check in virtio_queue_empty_rcu is redundant because virtqueue_split_pop() is only called through virtqueue_pop(), which already performs the check.

---
v3:
- Rework the commit message to describe split-ring code deduplication.
- Explain why the virtio_device_disabled() check is removed.
- Drop the issue link because this patch addresses the generic split-ring path rather than the virtio-iommu command-processing path.

 hw/virtio/virtio.c | 30 ++++++------------------------
 1 file changed, 6 insertions(+), 24 deletions(-)
hw/virtio/virtio.c +6 -24
index f4d86a3655..68ec3f0751 100644
@@ -716,26 +716,6 @@ static inline bool is_desc_avail(uint16_t flags, bool wrap_counter)
     return (avail != used) && (avail == wrap_counter);
 }
 
-/* Fetch avail_idx from VQ memory only when we really need to know if
- * guest has added some buffers.
- * Called within rcu_read_lock().  */
-static int virtio_queue_empty_rcu(VirtQueue *vq)
-{
-    if (virtio_device_disabled(vq->vdev)) {
-        return 1;
-    }
-
-    if (unlikely(!vq->vring.avail)) {
-        return 1;
-    }
-
-    if (vq->shadow_avail_idx != vq->last_avail_idx) {
-        return 0;
-    }
-
-    return vring_avail_idx(vq) == vq->last_avail_idx;
-}
-
 static int virtio_queue_split_empty(VirtQueue *vq)
 {
     bool empty;
@@ -1748,12 +1728,14 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
     address_space_cache_init_empty(&indirect_desc_cache);
 
     RCU_READ_LOCK_GUARD();
-    if (virtio_queue_empty_rcu(vq)) {
+    if (unlikely(!vq->vring.avail)) {
+        goto done;
+    }
+
+    rc = virtqueue_num_heads(vq, vq->last_avail_idx);
+    if (rc <= 0) {
         goto done;
     }
-    /* Needed after virtio_queue_empty(), see comment in
-     * virtqueue_num_heads(). */
-    smp_rmb();
 
     /* When we start there are none of either input nor output. */
     out_num = in_num = elem_entries = 0;