block: avoid recursive AioContext acquire in bdrv_inactivate_all()
BDRV_POLL_WHILE() does not support recursive AioContext locking. It
only releases the AioContext lock once regardless of how many times the
caller has acquired it. This results in a hang since the IOThread does
not make progress while the AioContext is still locked.
The following steps trigger the hang:
$ qemu-system-x86_64 -M accel=kvm -m 1G -cpu host \
-object iothread,id=iothread0 \
-device virtio-scsi-pci,iothread=iothread0 \
-drive if=none,id=drive0,file=test.img,format=raw \
-device scsi-hd,drive=drive0 \
-drive if=none,id=drive1,file=test.img,format=raw \
-device scsi-hd,drive=drive1
$ qemu-system-x86_64 ...same options... \
-incoming tcp::1234
(qemu) migrate tcp:127.0.0.1:1234
...hang...
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 20171207201320.19284-2-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/block.c b/block.c
index 9a1a0d1..1c37ce4 100644
--- a/block.c
+++ b/block.c
@@ -4320,9 +4320,15 @@
BdrvNextIterator it;
int ret = 0;
int pass;
+ GSList *aio_ctxs = NULL, *ctx;
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
- aio_context_acquire(bdrv_get_aio_context(bs));
+ AioContext *aio_context = bdrv_get_aio_context(bs);
+
+ if (!g_slist_find(aio_ctxs, aio_context)) {
+ aio_ctxs = g_slist_prepend(aio_ctxs, aio_context);
+ aio_context_acquire(aio_context);
+ }
}
/* We do two passes of inactivation. The first pass calls to drivers'
@@ -4340,9 +4346,11 @@
}
out:
- for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
- aio_context_release(bdrv_get_aio_context(bs));
+ for (ctx = aio_ctxs; ctx != NULL; ctx = ctx->next) {
+ AioContext *aio_context = ctx->data;
+ aio_context_release(aio_context);
}
+ g_slist_free(aio_ctxs);
return ret;
}
