diff mbox

[PATCHv4] rbd block driver fix race between aio completition and aio cancel

Message ID 1354199315-21683-1-git-send-email-s.priebe@profihost.ag (mailing list archive)
State New, archived
Headers show

Commit Message

Stefan Priebe - Profihost AG Nov. 29, 2012, 2:28 p.m. UTC
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 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 |   16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

Comments

Paolo Bonzini Nov. 29, 2012, 3:23 p.m. UTC | #1
----- Messaggio originale -----
> Da: "Stefan Priebe" <s.priebe@profihost.ag>
> A: qemu-devel@nongnu.org
> Cc: stefanha@gmail.com, "josh durgin" <josh.durgin@inktank.com>, ceph-devel@vger.kernel.org, pbonzini@redhat.com,
> "Stefan Priebe" <s.priebe@profihost.ag>
> Inviato: Giovedì, 29 novembre 2012 15:28:35
> Oggetto: [PATCHv4] rbd block driver fix race between aio completition and aio cancel
> 
> 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 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 |   16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/block/rbd.c b/block/rbd.c
> index f3becc7..28e94ab 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 +562,12 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB
> *blockacb)
>  {
>      RBDAIOCB *acb = (RBDAIOCB *) blockacb;
>      acb->cancelled = 1;
> +
> +    while (acb->status == -EINPROGRESS) {
> +        qemu_aio_wait();
> +    }
> +
> +    qemu_vfree(acb->bounce);

This vfree is not needed, since the BH will run and do the free.

Otherwise looks ok.

>  }
>  
>  static const AIOCBInfo rbd_aiocb_info = {
> @@ -639,6 +639,7 @@ 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 +686,7 @@ 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
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Stefan Priebe - Profihost AG Nov. 29, 2012, 9:38 p.m. UTC | #2
Hi Paolo,

Am 29.11.2012 16:23, schrieb Paolo Bonzini:
>> +    qemu_vfree(acb->bounce);
>
> This vfree is not needed, since the BH will run and do the free.

new patch v5 sent.

Greets,
Stefan
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/block/rbd.c b/block/rbd.c
index f3becc7..28e94ab 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 +562,12 @@  static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     RBDAIOCB *acb = (RBDAIOCB *) blockacb;
     acb->cancelled = 1;
+
+    while (acb->status == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
+
+    qemu_vfree(acb->bounce);
 }
 
 static const AIOCBInfo rbd_aiocb_info = {
@@ -639,6 +639,7 @@  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 +686,7 @@  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);