1 files changed, 42 insertions, 81 deletions

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index eac97ef81e2a..45df2b857d48 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -20,7 +20,6 @@
 #include "xfs_types.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -123,11 +122,11 @@ xfs_buf_item_log_check(
 	ASSERT(bip->bli_logged != NULL);
 
 	bp = bip->bli_buf;
-	ASSERT(XFS_BUF_COUNT(bp) > 0);
+	ASSERT(bp->b_length > 0);
 	ASSERT(bp->b_addr != NULL);
 	orig = bip->bli_orig;
 	buffer = bp->b_addr;
-	for (x = 0; x < XFS_BUF_COUNT(bp); x++) {
+	for (x = 0; x < BBTOB(bp->b_length); x++) {
 		if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
 			xfs_emerg(bp->b_mount,
 				"%s: bip %x buffer %x orig %x index %d",
@@ -418,7 +417,6 @@ xfs_buf_item_unpin(
 	if (freed && stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
-		ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
 		ASSERT(XFS_BUF_ISSTALE(bp));
 		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
 
@@ -455,42 +453,42 @@ xfs_buf_item_unpin(
 			bp->b_iodone = NULL;
 		} else {
 			spin_lock(&ailp->xa_lock);
-			xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
+			xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
 			ASSERT(bp->b_fspriv == NULL);
 		}
 		xfs_buf_relse(bp);
+	} else if (freed && remove) {
+		xfs_buf_lock(bp);
+		xfs_buf_ioerror(bp, EIO);
+		XFS_BUF_UNDONE(bp);
+		xfs_buf_stale(bp);
+		xfs_buf_ioend(bp, 0);
 	}
 }
 
-/*
- * This is called to attempt to lock the buffer associated with this
- * buf log item.  Don't sleep on the buffer lock.  If we can't get
- * the lock right away, return 0.  If we can get the lock, take a
- * reference to the buffer. If this is a delayed write buffer that
- * needs AIL help to be written back, invoke the pushbuf routine
- * rather than the normal success path.
- */
 STATIC uint
-xfs_buf_item_trylock(
-	struct xfs_log_item	*lip)
+xfs_buf_item_push(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
+	uint			rval = XFS_ITEM_SUCCESS;
 
 	if (xfs_buf_ispinned(bp))
 		return XFS_ITEM_PINNED;
 	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
 
-	/* take a reference to the buffer.  */
-	xfs_buf_hold(bp);
-
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	trace_xfs_buf_item_trylock(bip);
-	if (XFS_BUF_ISDELAYWRITE(bp))
-		return XFS_ITEM_PUSHBUF;
-	return XFS_ITEM_SUCCESS;
+
+	trace_xfs_buf_item_push(bip);
+
+	if (!xfs_buf_delwri_queue(bp, buffer_list))
+		rval = XFS_ITEM_FLUSHING;
+	xfs_buf_unlock(bp);
+	return rval;
 }
 
 /*
@@ -603,49 +601,6 @@ xfs_buf_item_committed(
 	return lsn;
 }
 
-/*
- * The buffer is locked, but is not a delayed write buffer. This happens
- * if we race with IO completion and hence we don't want to try to write it
- * again. Just release the buffer.
- */
-STATIC void
-xfs_buf_item_push(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
-	struct xfs_buf		*bp = bip->bli_buf;
-
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!XFS_BUF_ISDELAYWRITE(bp));
-
-	trace_xfs_buf_item_push(bip);
-
-	xfs_buf_relse(bp);
-}
-
-/*
- * The buffer is locked and is a delayed write buffer. Promote the buffer
- * in the delayed write queue as the caller knows that they must invoke
- * the xfsbufd to get this buffer written. We have to unlock the buffer
- * to allow the xfsbufd to write it, too.
- */
-STATIC bool
-xfs_buf_item_pushbuf(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
-	struct xfs_buf		*bp = bip->bli_buf;
-
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(XFS_BUF_ISDELAYWRITE(bp));
-
-	trace_xfs_buf_item_pushbuf(bip);
-
-	xfs_buf_delwri_promote(bp);
-	xfs_buf_relse(bp);
-	return true;
-}
-
 STATIC void
 xfs_buf_item_committing(
 	struct xfs_log_item	*lip,
@@ -661,11 +616,9 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_format	= xfs_buf_item_format,
 	.iop_pin	= xfs_buf_item_pin,
 	.iop_unpin	= xfs_buf_item_unpin,
-	.iop_trylock	= xfs_buf_item_trylock,
 	.iop_unlock	= xfs_buf_item_unlock,
 	.iop_committed	= xfs_buf_item_committed,
 	.iop_push	= xfs_buf_item_push,
-	.iop_pushbuf	= xfs_buf_item_pushbuf,
 	.iop_committing = xfs_buf_item_committing
 };
 
@@ -703,7 +656,8 @@ xfs_buf_item_init(
 	 * truncate any pieces.  map_size is the size of the
 	 * bitmap needed to describe the chunks of the buffer.
 	 */
-	chunks = (int)((XFS_BUF_COUNT(bp) + (XFS_BLF_CHUNK - 1)) >> XFS_BLF_SHIFT);
+	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
+								XFS_BLF_SHIFT);
 	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
 
 	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
@@ -713,7 +667,7 @@ xfs_buf_item_init(
 	xfs_buf_hold(bp);
 	bip->bli_format.blf_type = XFS_LI_BUF;
 	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)BTOBB(XFS_BUF_COUNT(bp));
+	bip->bli_format.blf_len = (ushort)bp->b_length;
 	bip->bli_format.blf_map_size = map_size;
 
 #ifdef XFS_TRANS_DEBUG
@@ -725,9 +679,9 @@ xfs_buf_item_init(
 	 * the buffer to indicate which bytes the callers have asked
 	 * to have logged.
 	 */
-	bip->bli_orig = (char *)kmem_alloc(XFS_BUF_COUNT(bp), KM_SLEEP);
-	memcpy(bip->bli_orig, bp->b_addr, XFS_BUF_COUNT(bp));
-	bip->bli_logged = (char *)kmem_zalloc(XFS_BUF_COUNT(bp) / NBBY, KM_SLEEP);
+	bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP);
+	memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length));
+	bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP);
 #endif
 
 	/*
@@ -984,20 +938,27 @@ xfs_buf_iodone_callbacks(
 	 * If the write was asynchronous then no one will be looking for the
 	 * error.  Clear the error state and write the buffer out again.
 	 *
-	 * During sync or umount we'll write all pending buffers again
-	 * synchronous, which will catch these errors if they keep hanging
-	 * around.
+	 * XXX: This helps against transient write errors, but we need to find
+	 * a way to shut the filesystem down if the writes keep failing.
+	 *
+	 * In practice we'll shut the filesystem down soon as non-transient
+	 * erorrs tend to affect the whole device and a failing log write
+	 * will make us give up.  But we really ought to do better here.
 	 */
 	if (XFS_BUF_ISASYNC(bp)) {
+		ASSERT(bp->b_iodone != NULL);
+
+		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+
 		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
 
 		if (!XFS_BUF_ISSTALE(bp)) {
-			xfs_buf_delwri_queue(bp);
-			XFS_BUF_DONE(bp);
+			bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+			xfs_bdstrat_cb(bp);
+		} else {
+			xfs_buf_relse(bp);
 		}
-		ASSERT(bp->b_iodone != NULL);
-		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
-		xfs_buf_relse(bp);
+
 		return;
 	}
 
@@ -1045,6 +1006,6 @@ xfs_buf_iodone(
 	 * Either way, AIL is useless if we're forcing a shutdown.
 	 */
 	spin_lock(&ailp->xa_lock);
-	xfs_trans_ail_delete(ailp, lip);
+	xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
 	xfs_buf_item_free(BUF_ITEM(lip));
 }