[Qemu-devel] [PATCHv5] rbd block driver fix race between aio completition and aio cancel

[Qemu-devel] [PATCHv5] rbd block driver fix race between aio completition and aio cancel

[Stefan Priebe]

This one fixes a race which qemu had also in iscsi block driver
between cancellation and io completition.

qemu_rbd_aio_cancel was not synchronously waiting for the end of
the command.

To archieve this it introduces a new status flag which uses
-EINPROGRESS.

Changes since PATCHv4:
- removed unnecessary qemu_vfree of acb->bounce as BH will always
  run

Changes since PATCHv3:
- removed unnecessary if condition in rbd_start_aio as we
  haven't start io yet
- moved acb->status = 0 to rbd_aio_bh_cb so qemu_aio_wait always
  waits until BH was executed

Changes since PATCHv2:
- fixed missing braces
- added vfree for bounce

Signed-off-by: Stefan Priebe <s.priebe@profihost.ag>

---
 block/rbd.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/block/rbd.c b/block/rbd.c
index f3becc7..3bc9c7a 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -77,6 +77,7 @@ typedef struct RBDAIOCB {
     int error;
     struct BDRVRBDState *s;
     int cancelled;
+    int status;
 } RBDAIOCB;
 
 typedef struct RADOSCB {
@@ -376,12 +377,6 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     RBDAIOCB *acb = rcb->acb;
     int64_t r;
 
-    if (acb->cancelled) {
-        qemu_vfree(acb->bounce);
-        qemu_aio_release(acb);
-        goto done;
-    }
-
     r = rcb->ret;
 
     if (acb->cmd == RBD_AIO_WRITE ||
@@ -409,7 +404,6 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     /* Note that acb->bh can be NULL in case where the aio was cancelled */
     acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
     qemu_bh_schedule(acb->bh);
-done:
     g_free(rcb);
 }
 
@@ -568,6 +562,10 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     RBDAIOCB *acb = (RBDAIOCB *) blockacb;
     acb->cancelled = 1;
+
+    while (acb->status == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
 }
 
 static const AIOCBInfo rbd_aiocb_info = {
@@ -639,6 +637,7 @@ static void rbd_aio_bh_cb(void *opaque)
     acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
     qemu_bh_delete(acb->bh);
     acb->bh = NULL;
+    acb->status = 0;
 
     qemu_aio_release(acb);
 }
@@ -685,6 +684,7 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->s = s;
     acb->cancelled = 0;
     acb->bh = NULL;
+    acb->status = -EINPROGRESS;
 
     if (cmd == RBD_AIO_WRITE) {
         qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
-- 
1.7.10.4

Re: [Qemu-devel] [PATCHv5] rbd block driver fix race between aio completition and aio cancel

[Stefan Hajnoczi]

On Thu, Nov 29, 2012 at 10:37 PM, Stefan Priebe <s.priebe@profihost.ag> wrote:
> @@ -568,6 +562,10 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
>  {
>      RBDAIOCB *acb = (RBDAIOCB *) blockacb;
>      acb->cancelled = 1;
> +
> +    while (acb->status == -EINPROGRESS) {
> +        qemu_aio_wait();
> +    }
>  }
>
>  static const AIOCBInfo rbd_aiocb_info = {
> @@ -639,6 +637,7 @@ static void rbd_aio_bh_cb(void *opaque)
>      acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
>      qemu_bh_delete(acb->bh);
>      acb->bh = NULL;
> +    acb->status = 0;
>
>      qemu_aio_release(acb);
>  }

We cannot release acb in rbd_aio_bh_cb() when acb->cancelled == 1
because qemu_rbd_aio_cancel() still accesses it.  This was discussed
in an early version of the patch.

Stefan

Re: [Qemu-devel] [PATCHv5] rbd block driver fix race between aio completition and aio cancel

[Stefan Priebe - Profihost AG]

fixed in V6

Am 30.11.2012 09:26, schrieb Stefan Hajnoczi:
> On Thu, Nov 29, 2012 at 10:37 PM, Stefan Priebe <s.priebe@profihost.ag> wrote:
>> @@ -568,6 +562,10 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
>>   {
>>       RBDAIOCB *acb = (RBDAIOCB *) blockacb;
>>       acb->cancelled = 1;
>> +
>> +    while (acb->status == -EINPROGRESS) {
>> +        qemu_aio_wait();
>> +    }
>>   }
>>
>>   static const AIOCBInfo rbd_aiocb_info = {
>> @@ -639,6 +637,7 @@ static void rbd_aio_bh_cb(void *opaque)
>>       acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
>>       qemu_bh_delete(acb->bh);
>>       acb->bh = NULL;
>> +    acb->status = 0;
>>
>>       qemu_aio_release(acb);
>>   }
>
> We cannot release acb in rbd_aio_bh_cb() when acb->cancelled == 1
> because qemu_rbd_aio_cancel() still accesses it.  This was discussed
> in an early version of the patch.
>
> Stefan
>