xfs: move allocation stack switch up to xfs_bmapi_allocate

Switching stacks are xfs_alloc_vextent can cause deadlocks when we
run out of worker threads on the allocation workqueue. This can
occur because xfs_bmap_btalloc can make multiple calls to
xfs_alloc_vextent() and even if xfs_alloc_vextent() fails it can
return with the AGF locked in the current allocation transaction.

If we then need to make another allocation, and all the allocation
worker contexts are exhausted because the are blocked waiting for
the AGF lock, holder of the AGF cannot get it's xfs-alloc_vextent
work completed to release the AGF.  Hence allocation effectively
deadlocks.

To avoid this, move the stack switch one layer up to
xfs_bmapi_allocate() so that all of the allocation attempts in a
single switched stack transaction occur in a single worker context.
This avoids the problem of an allocation being blocked waiting for
a worker thread whilst holding the AGF.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

1 files changed, 1 insertions, 41 deletions

diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 43f791b..335206a 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2208,7 +2208,7 @@ xfs_alloc_read_agf(
  * group or loop over the allocation groups to find the result.
  */
 int				/* error */
-__xfs_alloc_vextent(
+xfs_alloc_vextent(
 	xfs_alloc_arg_t	*args)	/* allocation argument structure */
 {
 	xfs_agblock_t	agsize;	/* allocation group size */
@@ -2418,46 +2418,6 @@ error0:
 	return error;
 }
 
-static void
-xfs_alloc_vextent_worker(
-	struct work_struct	*work)
-{
-	struct xfs_alloc_arg	*args = container_of(work,
-						struct xfs_alloc_arg, work);
-	unsigned long		pflags;
-
-	/* we are in a transaction context here */
-	current_set_flags_nested(&pflags, PF_FSTRANS);
-
-	args->result = __xfs_alloc_vextent(args);
-	complete(args->done);
-
-	current_restore_flags_nested(&pflags, PF_FSTRANS);
-}
-
-/*
- * Data allocation requests often come in with little stack to work on. Push
- * them off to a worker thread so there is lots of stack to use. Metadata
- * requests, OTOH, are generally from low stack usage paths, so avoid the
- * context switch overhead here.
- */
-int
-xfs_alloc_vextent(
-	struct xfs_alloc_arg	*args)
-{
-	DECLARE_COMPLETION_ONSTACK(done);
-
-	if (!args->stack_switch)
-		return __xfs_alloc_vextent(args);
-
-
-	args->done = &done;
-	INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);
-	queue_work(xfs_alloc_wq, &args->work);
-	wait_for_completion(&done);
-	return args->result;
-}
-
 /*
  * Free an extent.
  * Just break up the extent address and hand off to xfs_free_ag_extent