Merge branch 'xfs-buf-iosubmit' into for-next

fs/xfs/xfs_bmap_util.c

@@ -1122,14 +1122,6 @@ xfs_zero_remaining_bytes(
 	if (endoff > XFS_ISIZE(ip))
 		endoff = XFS_ISIZE(ip);
 
-	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
-					mp->m_rtdev_targp : mp->m_ddev_targp,
-				  BTOBB(mp->m_sb.sb_blocksize), 0);
-	if (!bp)
-		return -ENOMEM;
-
-	xfs_buf_unlock(bp);
-
 	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
 		uint lock_mode;
 
@@ -1152,42 +1144,24 @@ xfs_zero_remaining_bytes(
 		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
 		if (imap.br_state == XFS_EXT_UNWRITTEN)
 			continue;
-		XFS_BUF_UNDONE(bp);
-		XFS_BUF_UNWRITE(bp);
-		XFS_BUF_READ(bp);
-		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
 
-		if (XFS_FORCED_SHUTDOWN(mp)) {
+		error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
-			error = -EIO;
+				mp->m_rtdev_targp : mp->m_ddev_targp,
-			break;
+				xfs_fsb_to_db(ip, imap.br_startblock),
-		}
+				BTOBB(mp->m_sb.sb_blocksize),
-		xfs_buf_iorequest(bp);
+				0, &bp, NULL);
-		error = xfs_buf_iowait(bp);
+		if (error)
-		if (error) {
+			return error;
-			xfs_buf_ioerror_alert(bp,
+
-					"xfs_zero_remaining_bytes(read)");
-			break;
-		}
 		memset(bp->b_addr +
-			(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
+				(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
-		      0, lastoffset - offset + 1);
+		       0, lastoffset - offset + 1);
-		XFS_BUF_UNDONE(bp);
-		XFS_BUF_UNREAD(bp);
-		XFS_BUF_WRITE(bp);
 
-		if (XFS_FORCED_SHUTDOWN(mp)) {
+		error = xfs_bwrite(bp);
-			error = -EIO;
+		xfs_buf_relse(bp);
-			break;
+		if (error)
-		}
+			return error;
-		xfs_buf_iorequest(bp);
-		error = xfs_buf_iowait(bp);
-		if (error) {
-			xfs_buf_ioerror_alert(bp,
-					"xfs_zero_remaining_bytes(write)");
-			break;
-		}
 	}
-	xfs_buf_free(bp);
 	return error;
 }
 

fs/xfs/xfs_buf.c

@@ -623,10 +623,11 @@ _xfs_buf_read(
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	xfs_buf_iorequest(bp);
+	if (flags & XBF_ASYNC) {
-	if (flags & XBF_ASYNC)
+		xfs_buf_submit(bp);
 		return 0;
-	return xfs_buf_iowait(bp);
+	}
+	return xfs_buf_submit_wait(bp);
 }
 
 xfs_buf_t *
@@ -687,34 +688,39 @@ xfs_buf_readahead_map(
  * Read an uncached buffer from disk. Allocates and returns a locked
  * buffer containing the disk contents or nothing.
  */
-struct xfs_buf *
+int
 xfs_buf_read_uncached(
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		daddr,
 	size_t			numblks,
 	int			flags,
+	struct xfs_buf		**bpp,
 	const struct xfs_buf_ops *ops)
 {
 	struct xfs_buf		*bp;
 
+	*bpp = NULL;
+
 	bp = xfs_buf_get_uncached(target, numblks, flags);
 	if (!bp)
-		return NULL;
+		return -ENOMEM;
 
 	/* set up the buffer for a read IO */
 	ASSERT(bp->b_map_count == 1);
-	bp->b_bn = daddr;
+	bp->b_bn = XFS_BUF_DADDR_NULL;  /* always null for uncached buffers */
 	bp->b_maps[0].bm_bn = daddr;
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+	xfs_buf_submit_wait(bp);
+	if (bp->b_error) {
+		int	error = bp->b_error;
 		xfs_buf_relse(bp);
-		return NULL;
+		return error;
 	}
-	xfs_buf_iorequest(bp);
+
-	xfs_buf_iowait(bp);
+	*bpp = bp;
-	return bp;
+	return 0;
 }
 
 /*
@@ -998,53 +1004,56 @@ xfs_buf_wait_unpin(
  *	Buffer Utility Routines
  */
 
-STATIC void
+void
-xfs_buf_iodone_work(
+xfs_buf_ioend(
-	struct work_struct	*work)
+	struct xfs_buf	*bp)
 {
-	struct xfs_buf		*bp =
+	bool		read = bp->b_flags & XBF_READ;
-		container_of(work, xfs_buf_t, b_iodone_work);
+
-	bool			read = !!(bp->b_flags & XBF_READ);
+	trace_xfs_buf_iodone(bp, _RET_IP_);
 
 	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
 
-	/* only validate buffers that were read without errors */
+	/*
-	if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE))
+	 * Pull in IO completion errors now. We are guaranteed to be running
+	 * single threaded, so we don't need the lock to read b_io_error.
+	 */
+	if (!bp->b_error && bp->b_io_error)
+		xfs_buf_ioerror(bp, bp->b_io_error);
+
+	/* Only validate buffers that were read without errors */
+	if (read && !bp->b_error && bp->b_ops) {
+		ASSERT(!bp->b_iodone);
 		bp->b_ops->verify_read(bp);
+	}
+
+	if (!bp->b_error)
+		bp->b_flags |= XBF_DONE;
 
 	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
-	else {
+	else
-		ASSERT(read && bp->b_ops);
 		complete(&bp->b_iowait);
-	}
+}
+
+static void
+xfs_buf_ioend_work(
+	struct work_struct	*work)
+{
+	struct xfs_buf		*bp =
+		container_of(work, xfs_buf_t, b_iodone_work);
+
+	xfs_buf_ioend(bp);
 }
 
 void
-xfs_buf_ioend(
+xfs_buf_ioend_async(
-	struct xfs_buf	*bp,
+	struct xfs_buf	*bp)
-	int		schedule)
 {
-	bool		read = !!(bp->b_flags & XBF_READ);
+	INIT_WORK(&bp->b_iodone_work, xfs_buf_ioend_work);
-
+	queue_work(xfslogd_workqueue, &bp->b_iodone_work);
-	trace_xfs_buf_iodone(bp, _RET_IP_);
-
-	if (bp->b_error == 0)
-		bp->b_flags |= XBF_DONE;
-
-	if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) {
-		if (schedule) {
-			INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work);
-			queue_work(xfslogd_workqueue, &bp->b_iodone_work);
-		} else {
-			xfs_buf_iodone_work(&bp->b_iodone_work);
-		}
-	} else {
-		bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
-		complete(&bp->b_iowait);
-	}
 }
 
 void
@@ -1067,96 +1076,6 @@ xfs_buf_ioerror_alert(
 		(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
 }
 
-/*
- * Called when we want to stop a buffer from getting written or read.
- * We attach the EIO error, muck with its flags, and call xfs_buf_ioend
- * so that the proper iodone callbacks get called.
- */
-STATIC int
-xfs_bioerror(
-	xfs_buf_t *bp)
-{
-#ifdef XFSERRORDEBUG
-	ASSERT(XFS_BUF_ISREAD(bp) || bp->b_iodone);
-#endif
-
-	/*
-	 * No need to wait until the buffer is unpinned, we aren't flushing it.
-	 */
-	xfs_buf_ioerror(bp, -EIO);
-
-	/*
-	 * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
-	 */
-	XFS_BUF_UNREAD(bp);
-	XFS_BUF_UNDONE(bp);
-	xfs_buf_stale(bp);
-
-	xfs_buf_ioend(bp, 0);
-
-	return -EIO;
-}
-
-/*
- * Same as xfs_bioerror, except that we are releasing the buffer
- * here ourselves, and avoiding the xfs_buf_ioend call.
- * This is meant for userdata errors; metadata bufs come with
- * iodone functions attached, so that we can track down errors.
- */
-int
-xfs_bioerror_relse(
-	struct xfs_buf	*bp)
-{
-	int64_t		fl = bp->b_flags;
-	/*
-	 * No need to wait until the buffer is unpinned.
-	 * We aren't flushing it.
-	 *
-	 * chunkhold expects B_DONE to be set, whether
-	 * we actually finish the I/O or not. We don't want to
-	 * change that interface.
-	 */
-	XFS_BUF_UNREAD(bp);
-	XFS_BUF_DONE(bp);
-	xfs_buf_stale(bp);
-	bp->b_iodone = NULL;
-	if (!(fl & XBF_ASYNC)) {
-		/*
-		 * Mark b_error and B_ERROR _both_.
-		 * Lot's of chunkcache code assumes that.
-		 * There's no reason to mark error for
-		 * ASYNC buffers.
-		 */
-		xfs_buf_ioerror(bp, -EIO);
-		complete(&bp->b_iowait);
-	} else {
-		xfs_buf_relse(bp);
-	}
-
-	return -EIO;
-}
-
-STATIC int
-xfs_bdstrat_cb(
-	struct xfs_buf	*bp)
-{
-	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		trace_xfs_bdstrat_shut(bp, _RET_IP_);
-		/*
-		 * Metadata write that didn't get logged but
-		 * written delayed anyway. These aren't associated
-		 * with a transaction, and can be ignored.
-		 */
-		if (!bp->b_iodone && !XFS_BUF_ISREAD(bp))
-			return xfs_bioerror_relse(bp);
-		else
-			return xfs_bioerror(bp);
-	}
-
-	xfs_buf_iorequest(bp);
-	return 0;
-}
-
 int
 xfs_bwrite(
 	struct xfs_buf		*bp)
@@ -1166,11 +1085,10 @@ xfs_bwrite(
 	ASSERT(xfs_buf_islocked(bp));
 
 	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
+			 XBF_WRITE_FAIL | XBF_DONE);
 
-	xfs_bdstrat_cb(bp);
+	error = xfs_buf_submit_wait(bp);
-
-	error = xfs_buf_iowait(bp);
 	if (error) {
 		xfs_force_shutdown(bp->b_target->bt_mount,
 				   SHUTDOWN_META_IO_ERROR);
@@ -1178,15 +1096,6 @@ xfs_bwrite(
 	return error;
 }
 
-STATIC void
-_xfs_buf_ioend(
-	xfs_buf_t		*bp,
-	int			schedule)
-{
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
-		xfs_buf_ioend(bp, schedule);
-}
-
 STATIC void
 xfs_buf_bio_end_io(
 	struct bio		*bio,
@@ -1198,13 +1107,18 @@ xfs_buf_bio_end_io(
 	 * don't overwrite existing errors - otherwise we can lose errors on
 	 * buffers that require multiple bios to complete.
 	 */
-	if (!bp->b_error)
+	if (error) {
-		xfs_buf_ioerror(bp, error);
+		spin_lock(&bp->b_lock);
+		if (!bp->b_io_error)
+			bp->b_io_error = error;
+		spin_unlock(&bp->b_lock);
+	}
 
 	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
 		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
 
-	_xfs_buf_ioend(bp, 1);
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+		xfs_buf_ioend_async(bp);
 	bio_put(bio);
 }
 
@@ -1283,7 +1197,7 @@ next_chunk:
 	} else {
 		/*
 		 * This is guaranteed not to be the last io reference count
-		 * because the caller (xfs_buf_iorequest) holds a count itself.
+		 * because the caller (xfs_buf_submit) holds a count itself.
 		 */
 		atomic_dec(&bp->b_io_remaining);
 		xfs_buf_ioerror(bp, -EIO);
@@ -1373,53 +1287,131 @@ _xfs_buf_ioapply(
 	blk_finish_plug(&plug);
 }
 
+/*
+ * Asynchronous IO submission path. This transfers the buffer lock ownership and
+ * the current reference to the IO. It is not safe to reference the buffer after
+ * a call to this function unless the caller holds an additional reference
+ * itself.
+ */
 void
-xfs_buf_iorequest(
+xfs_buf_submit(
-	xfs_buf_t		*bp)
+	struct xfs_buf	*bp)
 {
-	trace_xfs_buf_iorequest(bp, _RET_IP_);
+	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+	ASSERT(bp->b_flags & XBF_ASYNC);
+
+	/* on shutdown we stale and complete the buffer immediately */
+	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+		xfs_buf_stale(bp);
+		xfs_buf_ioend(bp);
+		return;
+	}
 
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
+
+	/* clear the internal error state to avoid spurious errors */
+	bp->b_io_error = 0;
+
+	/*
+	 * The caller's reference is released during I/O completion.
+	 * This occurs some time after the last b_io_remaining reference is
+	 * released, so after we drop our Io reference we have to have some
+	 * other reference to ensure the buffer doesn't go away from underneath
+	 * us. Take a direct reference to ensure we have safe access to the
+	 * buffer until we are finished with it.
+	 */
 	xfs_buf_hold(bp);
 
 	/*
-	 * Set the count to 1 initially, this will stop an I/O
+	 * Set the count to 1 initially, this will stop an I/O completion
-	 * completion callout which happens before we have started
+	 * callout which happens before we have started all the I/O from calling
-	 * all the I/O from calling xfs_buf_ioend too early.
+	 * xfs_buf_ioend too early.
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
 	_xfs_buf_ioapply(bp);
+
 	/*
-	 * If _xfs_buf_ioapply failed, we'll get back here with
+	 * If _xfs_buf_ioapply failed, we can get back here with only the IO
-	 * only the reference we took above.  _xfs_buf_ioend will
+	 * reference we took above. If we drop it to zero, run completion so
-	 * drop it to zero, so we'd better not queue it for later,
+	 * that we don't return to the caller with completion still pending.
-	 * or we'll free it before it's done.
 	 */
-	_xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+		if (bp->b_error)
+			xfs_buf_ioend(bp);
+		else
+			xfs_buf_ioend_async(bp);
+	}
 
 	xfs_buf_rele(bp);
+	/* Note: it is not safe to reference bp now we've dropped our ref */
 }
 
 /*
- * Waits for I/O to complete on the buffer supplied.  It returns immediately if
+ * Synchronous buffer IO submission path, read or write.
- * no I/O is pending or there is already a pending error on the buffer, in which
- * case nothing will ever complete.  It returns the I/O error code, if any, or
- * 0 if there was no error.
  */
 int
-xfs_buf_iowait(
+xfs_buf_submit_wait(
-	xfs_buf_t		*bp)
+	struct xfs_buf	*bp)
 {
+	int		error;
+
+	trace_xfs_buf_submit_wait(bp, _RET_IP_);
+
+	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
+
+	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+		xfs_buf_ioerror(bp, -EIO);
+		xfs_buf_stale(bp);
+		bp->b_flags &= ~XBF_DONE;
+		return -EIO;
+	}
+
+	if (bp->b_flags & XBF_WRITE)
+		xfs_buf_wait_unpin(bp);
+
+	/* clear the internal error state to avoid spurious errors */
+	bp->b_io_error = 0;
+
+	/*
+	 * For synchronous IO, the IO does not inherit the submitters reference
+	 * count, nor the buffer lock. Hence we cannot release the reference we
+	 * are about to take until we've waited for all IO completion to occur,
+	 * including any xfs_buf_ioend_async() work that may be pending.
+	 */
+	xfs_buf_hold(bp);
+
+	/*
+	 * Set the count to 1 initially, this will stop an I/O completion
+	 * callout which happens before we have started all the I/O from calling
+	 * xfs_buf_ioend too early.
+	 */
+	atomic_set(&bp->b_io_remaining, 1);
+	_xfs_buf_ioapply(bp);
+
+	/*
+	 * make sure we run completion synchronously if it raced with us and is
+	 * already complete.
+	 */
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+		xfs_buf_ioend(bp);
+
+	/* wait for completion before gathering the error from the buffer */
 	trace_xfs_buf_iowait(bp, _RET_IP_);
-
+	wait_for_completion(&bp->b_iowait);
-	if (!bp->b_error)
-		wait_for_completion(&bp->b_iowait);
-
 	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-	return bp->b_error;
+	error = bp->b_error;
+
+	/*
+	 * all done now, we can release the hold that keeps the buffer
+	 * referenced for the entire IO.
+	 */
+	xfs_buf_rele(bp);
+	return error;
 }
 
 xfs_caddr_t
@@ -1813,13 +1805,19 @@ __xfs_buf_delwri_submit(
 	blk_start_plug(&plug);
 	list_for_each_entry_safe(bp, n, io_list, b_list) {
 		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE;
+		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
 
-		if (!wait) {
+		/*
-			bp->b_flags |= XBF_ASYNC;
+		 * we do all Io submission async. This means if we need to wait
+		 * for IO completion we need to take an extra reference so the
+		 * buffer is still valid on the other side.
+		 */
+		if (wait)
+			xfs_buf_hold(bp);
+		else
 			list_del_init(&bp->b_list);
-		}
+
-		xfs_bdstrat_cb(bp);
+		xfs_buf_submit(bp);
 	}
 	blk_finish_plug(&plug);
 
@@ -1866,7 +1864,10 @@ xfs_buf_delwri_submit(
 		bp = list_first_entry(&io_list, struct xfs_buf, b_list);
 
 		list_del_init(&bp->b_list);
-		error2 = xfs_buf_iowait(bp);
+
+		/* locking the buffer will wait for async IO completion. */
+		xfs_buf_lock(bp);
+		error2 = bp->b_error;
 		xfs_buf_relse(bp);
 		if (!error)
 			error = error2;

fs/xfs/xfs_buf.h

@@ -158,6 +158,7 @@ typedef struct xfs_buf {
 	struct list_head	b_lru;		/* lru list */
 	spinlock_t		b_lock;		/* internal state lock */
 	unsigned int		b_state;	/* internal state flags */
+	int			b_io_error;	/* internal IO error state */
 	wait_queue_head_t	b_waiters;	/* unpin waiters */
 	struct list_head	b_list;
 	struct xfs_perag	*b_pag;		/* contains rbtree root */
@@ -268,9 +269,9 @@ int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
 struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
 				int flags);
-struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
+int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
-				xfs_daddr_t daddr, size_t numblks, int flags,
+			  size_t numblks, int flags, struct xfs_buf **bpp,
-				const struct xfs_buf_ops *ops);
+			  const struct xfs_buf_ops *ops);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
@@ -286,18 +287,16 @@ extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
-extern void xfs_buf_ioend(xfs_buf_t *,	int);
+extern void xfs_buf_ioend(struct xfs_buf *bp);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_iorequest(xfs_buf_t *);
+extern void xfs_buf_submit(struct xfs_buf *bp);
-extern int xfs_buf_iowait(xfs_buf_t *);
+extern int xfs_buf_submit_wait(struct xfs_buf *bp);
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
 #define xfs_buf_zero(bp, off, len) \
 	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
-extern int xfs_bioerror_relse(struct xfs_buf *);
-
 /* Buffer Utility Routines */
 extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
 

fs/xfs/xfs_buf_item.c

@@ -491,7 +491,7 @@ xfs_buf_item_unpin(
 		xfs_buf_ioerror(bp, -EIO);
 		XFS_BUF_UNDONE(bp);
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp, 0);
+		xfs_buf_ioend(bp);
 	}
 }
 
@@ -1081,7 +1081,7 @@ xfs_buf_iodone_callbacks(
 	 * 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
+	 * errors 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)) {
@@ -1094,7 +1094,7 @@ xfs_buf_iodone_callbacks(
 		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
 			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
 				       XBF_DONE | XBF_WRITE_FAIL;
-			xfs_buf_iorequest(bp);
+			xfs_buf_submit(bp);
 		} else {
 			xfs_buf_relse(bp);
 		}
@@ -1115,7 +1115,7 @@ do_callbacks:
 	xfs_buf_do_callbacks(bp);
 	bp->b_fspriv = NULL;
 	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp, 0);
+	xfs_buf_ioend(bp);
 }
 
 /*

fs/xfs/xfs_fsops.c

@@ -172,16 +172,11 @@ xfs_growfs_data_private(
 	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
 		return error;
 	dpct = pct - mp->m_sb.sb_imax_pct;
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-				XFS_FSS_TO_BB(mp, 1), 0, NULL);
+				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
-	if (!bp)
+	if (error)
-		return -EIO;
-	if (bp->b_error) {
-		error = bp->b_error;
-		xfs_buf_relse(bp);
 		return error;
-	}
 	xfs_buf_relse(bp);
 
 	new = nb;	/* use new as a temporary here */

fs/xfs/xfs_inode.c

@@ -3062,7 +3062,7 @@ cluster_corrupt_out:
 			XFS_BUF_UNDONE(bp);
 			xfs_buf_stale(bp);
 			xfs_buf_ioerror(bp, -EIO);
-			xfs_buf_ioend(bp, 0);
+			xfs_buf_ioend(bp);
 		} else {
 			xfs_buf_stale(bp);
 			xfs_buf_relse(bp);

fs/xfs/xfs_log.c

@@ -1678,7 +1678,7 @@ xlog_bdstrat(
 	if (iclog->ic_state & XLOG_STATE_IOERROR) {
 		xfs_buf_ioerror(bp, -EIO);
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp, 0);
+		xfs_buf_ioend(bp);
 		/*
 		 * It would seem logical to return EIO here, but we rely on
 		 * the log state machine to propagate I/O errors instead of
@@ -1688,7 +1688,7 @@ xlog_bdstrat(
 		return 0;
 	}
 
-	xfs_buf_iorequest(bp);
+	xfs_buf_submit(bp);
 	return 0;
 }
 
@@ -3867,18 +3867,17 @@ xlog_state_ioerror(
  * This is called from xfs_force_shutdown, when we're forcibly
  * shutting down the filesystem, typically because of an IO error.
  * Our main objectives here are to make sure that:
- *	a. the filesystem gets marked 'SHUTDOWN' for all interested
+ *	a. if !logerror, flush the logs to disk. Anything modified
+ *	   after this is ignored.
+ *	b. the filesystem gets marked 'SHUTDOWN' for all interested
  *	   parties to find out, 'atomically'.
- *	b. those who're sleeping on log reservations, pinned objects and
+ *	c. those who're sleeping on log reservations, pinned objects and
  *	    other resources get woken up, and be told the bad news.
- *	c. nothing new gets queued up after (a) and (b) are done.
+ *	d. nothing new gets queued up after (b) and (c) are done.
- *	d. if !logerror, flush the iclogs to disk, then seal them off
- *	   for business.
  *
- * Note: for delayed logging the !logerror case needs to flush the regions
+ * Note: for the !logerror case we need to flush the regions held in memory out
- * held in memory out to the iclogs before flushing them to disk. This needs
+ * to disk first. This needs to be done before the log is marked as shutdown,
- * to be done before the log is marked as shutdown, otherwise the flush to the
+ * otherwise the iclog writes will fail.
- * iclogs will fail.
  */
 int
 xfs_log_force_umount(
@@ -3910,16 +3909,16 @@ xfs_log_force_umount(
 		ASSERT(XLOG_FORCED_SHUTDOWN(log));
 		return 1;
 	}
-	retval = 0;
 
 	/*
-	 * Flush the in memory commit item list before marking the log as
+	 * Flush all the completed transactions to disk before marking the log
-	 * being shut down. We need to do it in this order to ensure all the
+	 * being shut down. We need to do it in this order to ensure that
-	 * completed transactions are flushed to disk with the xfs_log_force()
+	 * completed operations are safely on disk before we shut down, and that
-	 * call below.
+	 * we don't have to issue any buffer IO after the shutdown flags are set
+	 * to guarantee this.
 	 */
 	if (!logerror)
-		xlog_cil_force(log);
+		_xfs_log_force(mp, XFS_LOG_SYNC, NULL);
 
 	/*
 	 * mark the filesystem and the as in a shutdown state and wake
@@ -3931,18 +3930,11 @@ xfs_log_force_umount(
 		XFS_BUF_DONE(mp->m_sb_bp);
 
 	/*
-	 * This flag is sort of redundant because of the mount flag, but
+	 * Mark the log and the iclogs with IO error flags to prevent any
-	 * it's good to maintain the separation between the log and the rest
+	 * further log IO from being issued or completed.
-	 * of XFS.
 	 */
 	log->l_flags |= XLOG_IO_ERROR;
-
+	retval = xlog_state_ioerror(log);
-	/*
-	 * If we hit a log error, we want to mark all the iclogs IOERROR
-	 * while we're still holding the loglock.
-	 */
-	if (logerror)
-		retval = xlog_state_ioerror(log);
 	spin_unlock(&log->l_icloglock);
 
 	/*
@@ -3955,19 +3947,6 @@ xfs_log_force_umount(
 	xlog_grant_head_wake_all(&log->l_reserve_head);
 	xlog_grant_head_wake_all(&log->l_write_head);
 
-	if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
-		ASSERT(!logerror);
-		/*
-		 * Force the incore logs to disk before shutting the
-		 * log down completely.
-		 */
-		_xfs_log_force(mp, XFS_LOG_SYNC, NULL);
-
-		spin_lock(&log->l_icloglock);
-		retval = xlog_state_ioerror(log);
-		spin_unlock(&log->l_icloglock);
-	}
-
 	/*
 	 * Wake up everybody waiting on xfs_log_force. Wake the CIL push first
 	 * as if the log writes were completed. The abort handling in the log

fs/xfs/xfs_log_recover.c

@@ -193,12 +193,8 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(log->l_mp))
+	error = xfs_buf_submit_wait(bp);
-		return -EIO;
+	if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
-
-	xfs_buf_iorequest(bp);
-	error = xfs_buf_iowait(bp);
-	if (error)
 		xfs_buf_ioerror_alert(bp, __func__);
 	return error;
 }
@@ -378,12 +374,14 @@ xlog_recover_iodone(
 		 * We're not going to bother about retrying
 		 * this during recovery. One strike!
 		 */
-		xfs_buf_ioerror_alert(bp, __func__);
+		if (!XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		xfs_force_shutdown(bp->b_target->bt_mount,
+			xfs_buf_ioerror_alert(bp, __func__);
-					SHUTDOWN_META_IO_ERROR);
+			xfs_force_shutdown(bp->b_target->bt_mount,
+						SHUTDOWN_META_IO_ERROR);
+		}
 	}
 	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp, 0);
+	xfs_buf_ioend(bp);
 }
 
 /*
@@ -4452,16 +4450,12 @@ xlog_do_recover(
 	XFS_BUF_UNASYNC(bp);
 	bp->b_ops = &xfs_sb_buf_ops;
 
-	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+	error = xfs_buf_submit_wait(bp);
-		xfs_buf_relse(bp);
-		return -EIO;
-	}
-
-	xfs_buf_iorequest(bp);
-	error = xfs_buf_iowait(bp);
 	if (error) {
-		xfs_buf_ioerror_alert(bp, __func__);
+		if (!XFS_FORCED_SHUTDOWN(log->l_mp)) {
-		ASSERT(0);
+			xfs_buf_ioerror_alert(bp, __func__);
+			ASSERT(0);
+		}
 		xfs_buf_relse(bp);
 		return error;
 	}

fs/xfs/xfs_mount.c

@@ -300,21 +300,15 @@ xfs_readsb(
 	 * access to the superblock.
 	 */
 reread:
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				   BTOBB(sector_size), 0, buf_ops);
+				   BTOBB(sector_size), 0, &bp, buf_ops);
-	if (!bp) {
+	if (error) {
-		if (loud)
-			xfs_warn(mp, "SB buffer read failed");
-		return -EIO;
-	}
-	if (bp->b_error) {
-		error = bp->b_error;
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
 		/* bad CRC means corrupted metadata */
 		if (error == -EFSBADCRC)
 			error = -EFSCORRUPTED;
-		goto release_buf;
+		return error;
 	}
 
 	/*
@@ -544,40 +538,43 @@ xfs_set_inoalignment(xfs_mount_t *mp)
  * Check that the data (and log if separate) is an ok size.
  */
 STATIC int
-xfs_check_sizes(xfs_mount_t *mp)
+xfs_check_sizes(
+	struct xfs_mount *mp)
 {
-	xfs_buf_t	*bp;
+	struct xfs_buf	*bp;
 	xfs_daddr_t	d;
+	int		error;
 
 	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
 		xfs_warn(mp, "filesystem size mismatch detected");
 		return -EFBIG;
 	}
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0, NULL);
+					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
-	if (!bp) {
+	if (error) {
 		xfs_warn(mp, "last sector read failed");
-		return -EIO;
+		return error;
 	}
 	xfs_buf_relse(bp);
 
-	if (mp->m_logdev_targp != mp->m_ddev_targp) {
+	if (mp->m_logdev_targp == mp->m_ddev_targp)
-		d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+		return 0;
-		if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
+
-			xfs_warn(mp, "log size mismatch detected");
+	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
-			return -EFBIG;
+	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
-		}
+		xfs_warn(mp, "log size mismatch detected");
-		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
+		return -EFBIG;
-					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, NULL);
-		if (!bp) {
-			xfs_warn(mp, "log device read failed");
-			return -EIO;
-		}
-		xfs_buf_relse(bp);
 	}
+	error = xfs_buf_read_uncached(mp->m_logdev_targp,
+					d - XFS_FSB_TO_BB(mp, 1),
+					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
+		xfs_warn(mp, "log device read failed");
+		return error;
+	}
+	xfs_buf_relse(bp);
 	return 0;
 }
 

fs/xfs/xfs_rtalloc.c

@@ -921,16 +921,11 @@ xfs_growfs_rt(
 	/*
 	 * Read in the last block of the device, make sure it exists.
 	 */
-	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
 				XFS_FSB_TO_BB(mp, nrblocks - 1),
-				XFS_FSB_TO_BB(mp, 1), 0, NULL);
+				XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
-	if (!bp)
+	if (error)
-		return -EIO;
-	if (bp->b_error) {
-		error = bp->b_error;
-		xfs_buf_relse(bp);
 		return error;
-	}
 	xfs_buf_relse(bp);
 
 	/*
@@ -1184,11 +1179,12 @@ xfs_rtallocate_extent(
  */
 int				/* error */
 xfs_rtmount_init(
-	xfs_mount_t	*mp)	/* file system mount structure */
+	struct xfs_mount	*mp)	/* file system mount structure */
 {
-	xfs_buf_t	*bp;	/* buffer for last block of subvolume */
+	struct xfs_buf		*bp;	/* buffer for last block of subvolume */
-	xfs_daddr_t	d;	/* address of last block of subvolume */
+	struct xfs_sb		*sbp;	/* filesystem superblock copy in mount */
-	xfs_sb_t	*sbp;	/* filesystem superblock copy in mount */
+	xfs_daddr_t		d;	/* address of last block of subvolume */
+	int			error;
 
 	sbp = &mp->m_sb;
 	if (sbp->sb_rblocks == 0)
@@ -1214,14 +1210,12 @@ xfs_rtmount_init(
 			(unsigned long long) mp->m_sb.sb_rblocks);
 		return -EFBIG;
 	}
-	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, NULL);
+					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
-	if (!bp || bp->b_error) {
+	if (error) {
 		xfs_warn(mp, "realtime device size check failed");
-		if (bp)
+		return error;
-			xfs_buf_relse(bp);
-		return -EIO;
 	}
 	xfs_buf_relse(bp);
 	return 0;

fs/xfs/xfs_trace.h

@@ -349,7 +349,8 @@ DEFINE_BUF_EVENT(xfs_buf_free);
 DEFINE_BUF_EVENT(xfs_buf_hold);
 DEFINE_BUF_EVENT(xfs_buf_rele);
 DEFINE_BUF_EVENT(xfs_buf_iodone);
-DEFINE_BUF_EVENT(xfs_buf_iorequest);
+DEFINE_BUF_EVENT(xfs_buf_submit);
+DEFINE_BUF_EVENT(xfs_buf_submit_wait);
 DEFINE_BUF_EVENT(xfs_buf_bawrite);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);

fs/xfs/xfs_trans_buf.c

@@ -318,20 +318,10 @@ xfs_trans_read_buf_map(
 			XFS_BUF_READ(bp);
 			bp->b_ops = ops;
 
-			/*
+			error = xfs_buf_submit_wait(bp);
-			 * XXX(hch): clean up the error handling here to be less
-			 * of a mess..
-			 */
-			if (XFS_FORCED_SHUTDOWN(mp)) {
-				trace_xfs_bdstrat_shut(bp, _RET_IP_);
-				xfs_bioerror_relse(bp);
-			} else {
-				xfs_buf_iorequest(bp);
-			}
-
-			error = xfs_buf_iowait(bp);
 			if (error) {
-				xfs_buf_ioerror_alert(bp, __func__);
+				if (!XFS_FORCED_SHUTDOWN(mp))
+					xfs_buf_ioerror_alert(bp, __func__);
 				xfs_buf_relse(bp);
 				/*
 				 * We can gracefully recover from most read