summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorZach Brown <zach.brown@oracle.com>2006-12-29 16:47:02 -0800
committerLinus Torvalds <torvalds@woody.osdl.org>2006-12-30 10:55:54 -0800
commit1ebb1101c556b1915ff041655e629a072e64dcda (patch)
treed306821837152a8c772591a9bf136e5e091a7a31
parent43cdff92ad47e0ca024c8a07d29f9bb6119e759c (diff)
downloadlinux-3.10-1ebb1101c556b1915ff041655e629a072e64dcda.tar.gz
linux-3.10-1ebb1101c556b1915ff041655e629a072e64dcda.tar.bz2
linux-3.10-1ebb1101c556b1915ff041655e629a072e64dcda.zip
[PATCH] Fix lock inversion aio_kick_handler()
lockdep found a AB BC CA lock inversion in retry-based AIO: 1) The task struct's alloc_lock (A) is acquired in process context with interrupts enabled. An interrupt might arrive and call wake_up() which grabs the wait queue's q->lock (B). 2) When performing retry-based AIO the AIO core registers aio_wake_function() as the wake funtion for iocb->ki_wait. It is called with the wait queue's q->lock (B) held and then tries to add the iocb to the run list after acquiring the ctx_lock (C). 3) aio_kick_handler() holds the ctx_lock (C) while acquiring the alloc_lock (A) via lock_task() and unuse_mm(). Lockdep emits a warning saying that we're trying to connect the irq-safe q->lock to the irq-unsafe alloc_lock via ctx_lock. This fixes the inversion by calling unuse_mm() in the AIO kick handing path after we've released the ctx_lock. As Ben LaHaise pointed out __put_ioctx could set ctx->mm to NULL, so we must only access ctx->mm while we have the lock. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Suparna Bhattacharya <suparna@in.ibm.com> Acked-by: Benjamin LaHaise <bcrl@kvack.org> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--fs/aio.c7
1 files changed, 3 insertions, 4 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 5f577a63bdf..ee20fc4240e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -599,9 +599,6 @@ static void use_mm(struct mm_struct *mm)
* by the calling kernel thread
* (Note: this routine is intended to be called only
* from a kernel thread context)
- *
- * Comments: Called with ctx->ctx_lock held. This nests
- * task_lock instead ctx_lock.
*/
static void unuse_mm(struct mm_struct *mm)
{
@@ -850,14 +847,16 @@ static void aio_kick_handler(struct work_struct *work)
{
struct kioctx *ctx = container_of(work, struct kioctx, wq.work);
mm_segment_t oldfs = get_fs();
+ struct mm_struct *mm;
int requeue;
set_fs(USER_DS);
use_mm(ctx->mm);
spin_lock_irq(&ctx->ctx_lock);
requeue =__aio_run_iocbs(ctx);
- unuse_mm(ctx->mm);
+ mm = ctx->mm;
spin_unlock_irq(&ctx->ctx_lock);
+ unuse_mm(mm);
set_fs(oldfs);
/*
* we're in a worker thread already, don't use queue_delayed_work,