xfs: fix error handling for synchronous writes

If we get an IO error on a synchronous superblock write, we attach an
error release function to it so that when the last reference goes away
the release function is called and the buffer is invalidated and
unlocked. The buffer is left locked until the release function is
called so that other concurrent users of the buffer will be locked out
until the buffer error is fully processed.

Unfortunately, for the superblock buffer the filesyetm itself holds a
reference to the buffer which prevents the reference count from
dropping to zero and the release function being called. As a result,
once an IO error occurs on a sync write, the buffer will never be
unlocked and all future attempts to lock the buffer will hang.

To make matters worse, this problems is not unique to such buffers;
if there is a concurrent _xfs_buf_find() running, the lookup will grab
a reference to the buffer and then wait on the buffer lock, preventing
the reference count from ever falling to zero and hence unlocking the
buffer.

As such, the whole b_relse function implementation is broken because it
cannot rely on the buffer reference count falling to zero to unlock the
errored buffer. The synchronous write error path is the only path that
uses this callback - it is used to ensure that the synchronous waiter
gets the buffer error before the error state is cleared from the buffer
by the release function.

Given that the only sychronous buffer writes now go through xfs_bwrite
and the error path in question can only occur for a write of a dirty,
logged buffer, we can move most of the b_relse processing to happen
inline in xfs_buf_iodone_callbacks, just like a normal I/O completion.
In addition to that we make sure the error is not cleared in
xfs_buf_iodone_callbacks, so that xfs_bwrite can reliably check it.
Given that xfs_bwrite keeps the buffer locked until it has waited for
it and checked the error this allows to reliably propagate the error
to the caller, and make sure that the buffer is reliably unlocked.

Given that xfs_buf_iodone_callbacks was the only instance of the
b_relse callback we can remove it entirely.

Based on earlier patches by Dave Chinner and Ajeet Yadav.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Ajeet Yadav <ajeet.yadav.77@gmail.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Alex Elder <aelder@sgi.com>

2 files changed, 2 insertions, 12 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 92f1f2acc6ab..ac1c7e8378dd 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -896,7 +896,6 @@ xfs_buf_rele(
 	trace_xfs_buf_rele(bp, _RET_IP_);
 
 	if (!pag) {
-		ASSERT(!bp->b_relse);
 		ASSERT(list_empty(&bp->b_lru));
 		ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
 		if (atomic_dec_and_test(&bp->b_hold))
@@ -908,11 +907,7 @@ xfs_buf_rele(
 
 	ASSERT(atomic_read(&bp->b_hold) > 0);
 	if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
-		if (bp->b_relse) {
-			atomic_inc(&bp->b_hold);
-			spin_unlock(&pag->pag_buf_lock);
-			bp->b_relse(bp);
-		} else if (!(bp->b_flags & XBF_STALE) &&
+		if (!(bp->b_flags & XBF_STALE) &&
 			   atomic_read(&bp->b_lru_ref)) {
 			xfs_buf_lru_add(bp);
 			spin_unlock(&pag->pag_buf_lock);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a76c2428faff..cbe65950e524 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -152,8 +152,6 @@ typedef struct xfs_buftarg {
 
 struct xfs_buf;
 typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
-typedef void (*xfs_buf_relse_t)(struct xfs_buf *);
-typedef int (*xfs_buf_bdstrat_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
@@ -183,7 +181,6 @@ typedef struct xfs_buf {
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_iodone_work;
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
-	xfs_buf_relse_t		b_relse;	/* releasing function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	void			*b_fspriv;
 	void			*b_fspriv2;
@@ -323,7 +320,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_FSPRIVATE2(bp, type)		((type)(bp)->b_fspriv2)
 #define XFS_BUF_SET_FSPRIVATE2(bp, val)		((bp)->b_fspriv2 = (void*)(val))
 #define XFS_BUF_SET_START(bp)			do { } while (0)
-#define XFS_BUF_SET_BRELSE_FUNC(bp, func)	((bp)->b_relse = (func))
 
 #define XFS_BUF_PTR(bp)			(xfs_caddr_t)((bp)->b_addr)
 #define XFS_BUF_SET_PTR(bp, val, cnt)	xfs_buf_associate_memory(bp, val, cnt)
@@ -360,8 +356,7 @@ xfs_buf_set_ref(
 
 static inline void xfs_buf_relse(xfs_buf_t *bp)
 {
-	if (!bp->b_relse)
-		xfs_buf_unlock(bp);
+	xfs_buf_unlock(bp);
 	xfs_buf_rele(bp);
 }