1 files changed, 179 insertions, 49 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 66abe36c1213..99628508cb11 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -39,6 +39,7 @@
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_bmap.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
@@ -163,14 +164,17 @@ xfs_ioend_new_eof(
 }
 
 /*
- * Update on-disk file size now that data has been written to disk.
- * The current in-memory file size is i_size.  If a write is beyond
- * eof i_new_size will be the intended file size until i_size is
- * updated.  If this write does not extend all the way to the valid
- * file size then restrict this update to the end of the write.
+ * Update on-disk file size now that data has been written to disk.  The
+ * current in-memory file size is i_size.  If a write is beyond eof i_new_size
+ * will be the intended file size until i_size is updated.  If this write does
+ * not extend all the way to the valid file size then restrict this update to
+ * the end of the write.
+ *
+ * This function does not block as blocking on the inode lock in IO completion
+ * can lead to IO completion order dependency deadlocks.. If it can't get the
+ * inode ilock it will return EAGAIN. Callers must handle this.
  */
-
-STATIC void
+STATIC int
 xfs_setfilesize(
 	xfs_ioend_t		*ioend)
 {
@@ -181,16 +185,40 @@ xfs_setfilesize(
 	ASSERT(ioend->io_type != IOMAP_READ);
 
 	if (unlikely(ioend->io_error))
-		return;
+		return 0;
+
+	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		return EAGAIN;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	isize = xfs_ioend_new_eof(ioend);
 	if (isize) {
 		ip->i_d.di_size = isize;
-		xfs_mark_inode_dirty_sync(ip);
+		xfs_mark_inode_dirty(ip);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+/*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+	xfs_ioend_t	*ioend,
+	int		wait)
+{
+	if (atomic_dec_and_test(&ioend->io_remaining)) {
+		struct workqueue_struct *wq;
+
+		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+			xfsconvertd_workqueue : xfsdatad_workqueue;
+		queue_work(wq, &ioend->io_work);
+		if (wait)
+			flush_workqueue(wq);
+	}
 }
 
 /*
@@ -198,11 +226,11 @@ xfs_setfilesize(
  */
 STATIC void
 xfs_end_io(
-	struct work_struct	*work)
+	struct work_struct *work)
 {
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_ioend_t	*ioend = container_of(work, xfs_ioend_t, io_work);
+	struct xfs_inode *ip = XFS_I(ioend->io_inode);
+	int		error = 0;
 
 	/*
 	 * For unwritten extents we need to issue transactions to convert a
@@ -210,7 +238,6 @@ xfs_end_io(
 	 */
 	if (ioend->io_type == IOMAP_UNWRITTEN &&
 	    likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
-		int error;
 
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
 						 ioend->io_size);
@@ -222,30 +249,23 @@ xfs_end_io(
 	 * We might have to update the on-disk file size after extending
 	 * writes.
 	 */
-	if (ioend->io_type != IOMAP_READ)
-		xfs_setfilesize(ioend);
-	xfs_destroy_ioend(ioend);
-}
-
-/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
-	xfs_ioend_t	*ioend,
-	int		wait)
-{
-	if (atomic_dec_and_test(&ioend->io_remaining)) {
-		struct workqueue_struct *wq;
-
-		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
-			xfsconvertd_workqueue : xfsdatad_workqueue;
-		queue_work(wq, &ioend->io_work);
-		if (wait)
-			flush_workqueue(wq);
+	if (ioend->io_type != IOMAP_READ) {
+		error = xfs_setfilesize(ioend);
+		ASSERT(!error || error == EAGAIN);
 	}
+
+	/*
+	 * If we didn't complete processing of the ioend, requeue it to the
+	 * tail of the workqueue for another attempt later. Otherwise destroy
+	 * it.
+	 */
+	if (error == EAGAIN) {
+		atomic_inc(&ioend->io_remaining);
+		xfs_finish_ioend(ioend, 0);
+		/* ensure we don't spin on blocked ioends */
+		delay(1);
+	} else
+		xfs_destroy_ioend(ioend);
 }
 
 /*
@@ -341,7 +361,7 @@ xfs_submit_ioend_bio(
 	 * but don't update the inode size until I/O completion.
 	 */
 	if (xfs_ioend_new_eof(ioend))
-		xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
+		xfs_mark_inode_dirty(XFS_I(ioend->io_inode));
 
 	submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
 		   WRITE_SYNC_PLUG : WRITE, bio);
@@ -874,6 +894,125 @@ xfs_cluster_write(
 	}
 }
 
+STATIC void
+xfs_vm_invalidatepage(
+	struct page		*page,
+	unsigned long		offset)
+{
+	trace_xfs_invalidatepage(page->mapping->host, page, offset);
+	block_invalidatepage(page, offset);
+}
+
+/*
+ * If the page has delalloc buffers on it, we need to punch them out before we
+ * invalidate the page. If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
+ * is done on that same region - the delalloc extent is returned when none is
+ * supposed to be there.
+ *
+ * We prevent this by truncating away the delalloc regions on the page before
+ * invalidating it. Because they are delalloc, we can do this without needing a
+ * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
+ * truncation without a transaction as there is no space left for block
+ * reservation (typically why we see a ENOSPC in writeback).
+ *
+ * This is not a performance critical path, so for now just do the punching a
+ * buffer head at a time.
+ */
+STATIC void
+xfs_aops_discard_page(
+	struct page		*page)
+{
+	struct inode		*inode = page->mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct buffer_head	*bh, *head;
+	loff_t			offset = page_offset(page);
+	ssize_t			len = 1 << inode->i_blkbits;
+
+	if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+		goto out_invalidate;
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		goto out_invalidate;
+
+	xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+		"page discard on page %p, inode 0x%llx, offset %llu.",
+			page, ip->i_ino, offset);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	bh = head = page_buffers(page);
+	do {
+		int		done;
+		xfs_fileoff_t	offset_fsb;
+		xfs_bmbt_irec_t	imap;
+		int		nimaps = 1;
+		int		error;
+		xfs_fsblock_t	firstblock;
+		xfs_bmap_free_t flist;
+
+		if (!buffer_delay(bh))
+			goto next_buffer;
+
+		offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+
+		/*
+		 * Map the range first and check that it is a delalloc extent
+		 * before trying to unmap the range. Otherwise we will be
+		 * trying to remove a real extent (which requires a
+		 * transaction) or a hole, which is probably a bad idea...
+		 */
+		error = xfs_bmapi(NULL, ip, offset_fsb, 1,
+				XFS_BMAPI_ENTIRE,  NULL, 0, &imap,
+				&nimaps, NULL, NULL);
+
+		if (error) {
+			/* something screwed, just bail */
+			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+				xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+				"page discard failed delalloc mapping lookup.");
+			}
+			break;
+		}
+		if (!nimaps) {
+			/* nothing there */
+			goto next_buffer;
+		}
+		if (imap.br_startblock != DELAYSTARTBLOCK) {
+			/* been converted, ignore */
+			goto next_buffer;
+		}
+		WARN_ON(imap.br_blockcount == 0);
+
+		/*
+		 * Note: while we initialise the firstblock/flist pair, they
+		 * should never be used because blocks should never be
+		 * allocated or freed for a delalloc extent and hence we need
+		 * don't cancel or finish them after the xfs_bunmapi() call.
+		 */
+		xfs_bmap_init(&flist, &firstblock);
+		error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock,
+					&flist, NULL, &done);
+
+		ASSERT(!flist.xbf_count && !flist.xbf_first);
+		if (error) {
+			/* something screwed, just bail */
+			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+				xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard unable to remove delalloc mapping.");
+			}
+			break;
+		}
+next_buffer:
+		offset += len;
+
+	} while ((bh = bh->b_this_page) != head);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_invalidate:
+	xfs_vm_invalidatepage(page, 0);
+	return;
+}
+
 /*
  * Calling this without startio set means we are being asked to make a dirty
  * page ready for freeing it's buffers.  When called with startio set then
@@ -1125,7 +1264,7 @@ error:
 	 */
 	if (err != -EAGAIN) {
 		if (!unmapped)
-			block_invalidatepage(page, 0);
+			xfs_aops_discard_page(page);
 		ClearPageUptodate(page);
 	}
 	return err;
@@ -1535,15 +1674,6 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-STATIC void
-xfs_vm_invalidatepage(
-	struct page		*page,
-	unsigned long		offset)
-{
-	trace_xfs_invalidatepage(page->mapping->host, page, offset);
-	block_invalidatepage(page, offset);
-}
-
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,