From 17e2a4a47d46dc9c33d5946cbdc1ceb15e34b5ac Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 22 May 2017 14:57:03 +0100 Subject: migration: avoid recursive AioContext locking in save_vmstate() AioContext was designed to allow nested acquire/release calls. It uses a recursive mutex so callers don't need to worry about nesting...or so we thought. BDRV_POLL_WHILE() is used to wait for block I/O requests. It releases the AioContext temporarily around aio_poll(). This gives IOThreads a chance to acquire the AioContext to process I/O completions. It turns out that recursive locking and BDRV_POLL_WHILE() don't mix. BDRV_POLL_WHILE() only releases the AioContext once, so the IOThread will not be able to acquire the AioContext if it was acquired multiple times. Instead of trying to release AioContext n times in BDRV_POLL_WHILE(), this patch simply avoids nested locking in save_vmstate(). It's the simplest fix and we should step back to consider the big picture with all the recent changes to block layer threading. This patch is the final fix to solve 'savevm' hanging with -object iothread. Signed-off-by: Stefan Hajnoczi Reviewed-by: Eric Blake Reviewed-by: Paolo Bonzini Signed-off-by: Kevin Wolf --- migration/savevm.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/migration/savevm.c b/migration/savevm.c index 6bfd489..5846d9c 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2144,6 +2144,14 @@ int save_snapshot(const char *name, Error **errp) goto the_end; } + /* The bdrv_all_create_snapshot() call that follows acquires the AioContext + * for itself. BDRV_POLL_WHILE() does not support nested locking because + * it only releases the lock once. Therefore synchronous I/O will deadlock + * unless we release the AioContext before bdrv_all_create_snapshot(). + */ + aio_context_release(aio_context); + aio_context = NULL; + ret = bdrv_all_create_snapshot(sn, bs, vm_state_size, &bs); if (ret < 0) { error_setg(errp, "Error while creating snapshot on '%s'", @@ -2154,7 +2162,9 @@ int save_snapshot(const char *name, Error **errp) ret = 0; the_end: - aio_context_release(aio_context); + if (aio_context) { + aio_context_release(aio_context); + } if (saved_vm_running) { vm_start(); } -- cgit v1.1