Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: Fix error return for fallocate() on XFS
  xfs: cleanup dmapi macros in the umount path
  xfs: remove incorrect sparse annotation for xfs_iget_cache_miss
  xfs: kill the STATIC_INLINE macro
  xfs: uninline xfs_get_extsz_hint
  xfs: rename xfs_attr_fetch to xfs_attr_get_int
  xfs: simplify xfs_buf_get / xfs_buf_read interfaces
  xfs: remove IO_ISAIO
  xfs: Wrapped journal record corruption on read at recovery
  xfs: cleanup data end I/O handlers
  xfs: use WRITE_SYNC_PLUG for synchronous writeout
  xfs: reset the i_iolock lock class in the reclaim path
  xfs: I/O completion handlers must use NOFS allocations
  xfs: fix mmap_sem/iolock inversion in xfs_free_eofblocks
  xfs: simplify inode teardown

10 files changed, 101 insertions, 139 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 70f9898..87813e4 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -235,71 +235,36 @@ xfs_setfilesize(
 }
 
 /*
- * Buffered IO write completion for delayed allocate extents.
+ * IO write completion.
  */
 STATIC void
-xfs_end_bio_delalloc(
-	struct work_struct	*work)
-{
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
-
-	xfs_setfilesize(ioend);
-	xfs_destroy_ioend(ioend);
-}
-
-/*
- * Buffered IO write completion for regular, written extents.
- */
-STATIC void
-xfs_end_bio_written(
-	struct work_struct	*work)
-{
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
-
-	xfs_setfilesize(ioend);
-	xfs_destroy_ioend(ioend);
-}
-
-/*
- * IO write completion for unwritten extents.
- *
- * Issue transactions to convert a buffer range from unwritten
- * to written extents.
- */
-STATIC void
-xfs_end_bio_unwritten(
+xfs_end_io(
 	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_off_t		offset = ioend->io_offset;
-	size_t			size = ioend->io_size;
-
-	if (likely(!ioend->io_error)) {
-		if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-			int error;
-			error = xfs_iomap_write_unwritten(ip, offset, size);
-			if (error)
-				ioend->io_error = error;
-		}
-		xfs_setfilesize(ioend);
-	}
-	xfs_destroy_ioend(ioend);
-}
 
-/*
- * IO read completion for regular, written extents.
- */
-STATIC void
-xfs_end_bio_read(
-	struct work_struct	*work)
-{
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
+	/*
+	 * For unwritten extents we need to issue transactions to convert a
+	 * range to normal written extens after the data I/O has finished.
+	 */
+	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);
+		if (error)
+			ioend->io_error = error;
+	}
 
+	/*
+	 * 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);
 }
 
@@ -314,10 +279,10 @@ xfs_finish_ioend(
 	int		wait)
 {
 	if (atomic_dec_and_test(&ioend->io_remaining)) {
-		struct workqueue_struct *wq = xfsdatad_workqueue;
-		if (ioend->io_work.func == xfs_end_bio_unwritten)
-			wq = xfsconvertd_workqueue;
+		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);
@@ -355,15 +320,7 @@ xfs_alloc_ioend(
 	ioend->io_offset = 0;
 	ioend->io_size = 0;
 
-	if (type == IOMAP_UNWRITTEN)
-		INIT_WORK(&ioend->io_work, xfs_end_bio_unwritten);
-	else if (type == IOMAP_DELAY)
-		INIT_WORK(&ioend->io_work, xfs_end_bio_delalloc);
-	else if (type == IOMAP_READ)
-		INIT_WORK(&ioend->io_work, xfs_end_bio_read);
-	else
-		INIT_WORK(&ioend->io_work, xfs_end_bio_written);
-
+	INIT_WORK(&ioend->io_work, xfs_end_io);
 	return ioend;
 }
 
@@ -380,7 +337,7 @@ xfs_map_blocks(
 	return -xfs_iomap(XFS_I(inode), offset, count, flags, mapp, &nmaps);
 }
 
-STATIC_INLINE int
+STATIC int
 xfs_iomap_valid(
 	xfs_iomap_t		*iomapp,
 	loff_t			offset)
@@ -412,8 +369,9 @@ xfs_end_bio(
 
 STATIC void
 xfs_submit_ioend_bio(
-	xfs_ioend_t	*ioend,
-	struct bio	*bio)
+	struct writeback_control *wbc,
+	xfs_ioend_t		*ioend,
+	struct bio		*bio)
 {
 	atomic_inc(&ioend->io_remaining);
 	bio->bi_private = ioend;
@@ -426,7 +384,8 @@ xfs_submit_ioend_bio(
 	if (xfs_ioend_new_eof(ioend))
 		xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
 
-	submit_bio(WRITE, bio);
+	submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
+		   WRITE_SYNC_PLUG : WRITE, bio);
 	ASSERT(!bio_flagged(bio, BIO_EOPNOTSUPP));
 	bio_put(bio);
 }
@@ -505,6 +464,7 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
  */
 STATIC void
 xfs_submit_ioend(
+	struct writeback_control *wbc,
 	xfs_ioend_t		*ioend)
 {
 	xfs_ioend_t		*head = ioend;
@@ -533,19 +493,19 @@ xfs_submit_ioend(
  retry:
 				bio = xfs_alloc_ioend_bio(bh);
 			} else if (bh->b_blocknr != lastblock + 1) {
-				xfs_submit_ioend_bio(ioend, bio);
+				xfs_submit_ioend_bio(wbc, ioend, bio);
 				goto retry;
 			}
 
 			if (bio_add_buffer(bio, bh) != bh->b_size) {
-				xfs_submit_ioend_bio(ioend, bio);
+				xfs_submit_ioend_bio(wbc, ioend, bio);
 				goto retry;
 			}
 
 			lastblock = bh->b_blocknr;
 		}
 		if (bio)
-			xfs_submit_ioend_bio(ioend, bio);
+			xfs_submit_ioend_bio(wbc, ioend, bio);
 		xfs_finish_ioend(ioend, 0);
 	} while ((ioend = next) != NULL);
 }
@@ -1191,7 +1151,7 @@ xfs_page_state_convert(
 	}
 
 	if (iohead)
-		xfs_submit_ioend(iohead);
+		xfs_submit_ioend(wbc, iohead);
 
 	return page_dirty;
 
@@ -1528,7 +1488,7 @@ xfs_end_io_direct(
 		 * didn't map an unwritten extent so switch it's completion
 		 * handler.
 		 */
-		INIT_WORK(&ioend->io_work, xfs_end_bio_written);
+		ioend->io_type = IOMAP_NEW;
 		xfs_finish_ioend(ioend, 0);
 	}
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 965df12..4ddc973 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -149,7 +149,7 @@ page_region_mask(
 	return mask;
 }
 
-STATIC_INLINE void
+STATIC void
 set_page_region(
 	struct page	*page,
 	size_t		offset,
@@ -161,7 +161,7 @@ set_page_region(
 		SetPageUptodate(page);
 }
 
-STATIC_INLINE int
+STATIC int
 test_page_region(
 	struct page	*page,
 	size_t		offset,
@@ -582,7 +582,7 @@ found:
  *	although backing storage may not be.
  */
 xfs_buf_t *
-xfs_buf_get_flags(
+xfs_buf_get(
 	xfs_buftarg_t		*target,/* target for buffer		*/
 	xfs_off_t		ioff,	/* starting offset of range	*/
 	size_t			isize,	/* length of range		*/
@@ -661,7 +661,7 @@ _xfs_buf_read(
 }
 
 xfs_buf_t *
-xfs_buf_read_flags(
+xfs_buf_read(
 	xfs_buftarg_t		*target,
 	xfs_off_t		ioff,
 	size_t			isize,
@@ -671,7 +671,7 @@ xfs_buf_read_flags(
 
 	flags |= XBF_READ;
 
-	bp = xfs_buf_get_flags(target, ioff, isize, flags);
+	bp = xfs_buf_get(target, ioff, isize, flags);
 	if (bp) {
 		if (!XFS_BUF_ISDONE(bp)) {
 			XB_TRACE(bp, "read", (unsigned long)flags);
@@ -718,7 +718,7 @@ xfs_buf_readahead(
 		return;
 
 	flags |= (XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
-	xfs_buf_read_flags(target, ioff, isize, flags);
+	xfs_buf_read(target, ioff, isize, flags);
 }
 
 xfs_buf_t *
@@ -1113,7 +1113,7 @@ xfs_bdwrite(
 	xfs_buf_delwri_queue(bp, 1);
 }
 
-STATIC_INLINE void
+STATIC void
 _xfs_buf_ioend(
 	xfs_buf_t		*bp,
 	int			schedule)
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 9b4d666..5f07dd9 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -186,15 +186,10 @@ extern xfs_buf_t *_xfs_buf_find(xfs_buftarg_t *, xfs_off_t, size_t,
 #define xfs_incore(buftarg,blkno,len,lockit) \
 	_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
 
-extern xfs_buf_t *xfs_buf_get_flags(xfs_buftarg_t *, xfs_off_t, size_t,
+extern xfs_buf_t *xfs_buf_get(xfs_buftarg_t *, xfs_off_t, size_t,
 				xfs_buf_flags_t);
-#define xfs_buf_get(target, blkno, len, flags) \
-	xfs_buf_get_flags((target), (blkno), (len), XBF_LOCK | XBF_MAPPED)
-
-extern xfs_buf_t *xfs_buf_read_flags(xfs_buftarg_t *, xfs_off_t, size_t,
+extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
 				xfs_buf_flags_t);
-#define xfs_buf_read(target, blkno, len, flags) \
-	xfs_buf_read_flags((target), (blkno), (len), XBF_LOCK | XBF_MAPPED)
 
 extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *);
 extern xfs_buf_t *xfs_buf_get_noaddr(size_t, xfs_buftarg_t *);
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index eff61e2..e4caeb2 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -52,7 +52,7 @@ xfs_file_aio_read(
 	loff_t			pos)
 {
 	struct file		*file = iocb->ki_filp;
-	int			ioflags = IO_ISAIO;
+	int			ioflags = 0;
 
 	BUG_ON(iocb->ki_pos != pos);
 	if (unlikely(file->f_flags & O_DIRECT))
@@ -71,7 +71,7 @@ xfs_file_aio_write(
 	loff_t			pos)
 {
 	struct file		*file = iocb->ki_filp;
-	int			ioflags = IO_ISAIO;
+	int			ioflags = 0;
 
 	BUG_ON(iocb->ki_pos != pos);
 	if (unlikely(file->f_flags & O_DIRECT))
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index cd42ef7..1f3b4b8 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -573,8 +573,8 @@ xfs_vn_fallocate(
 	bf.l_len = len;
 
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-	error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
-				      0, XFS_ATTR_NOLOCK);
+	error = -xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
+				       0, XFS_ATTR_NOLOCK);
 	if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
 	    offset + len > i_size_read(inode))
 		new_size = offset + len;
@@ -585,7 +585,7 @@ xfs_vn_fallocate(
 
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = new_size;
-		error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
+		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
 	}
 
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 072050f..78dbfcd 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -255,8 +255,6 @@ xfs_read(
 
 	iocb->ki_pos = *offset;
 	ret = generic_file_aio_read(iocb, iovp, segs, *offset);
-	if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
-		ret = wait_on_sync_kiocb(iocb);
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
@@ -774,9 +772,6 @@ write_retry:
 
 	current->backing_dev_info = NULL;
 
-	if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
-		ret = wait_on_sync_kiocb(iocb);
-
 	isize = i_size_read(inode);
 	if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
 		*offset = isize;
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 18a4b8e..1bfb0e9 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -930,13 +930,39 @@ xfs_fs_alloc_inode(
  */
 STATIC void
 xfs_fs_destroy_inode(
-	struct inode	*inode)
+	struct inode		*inode)
 {
-	xfs_inode_t		*ip = XFS_I(inode);
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	xfs_itrace_entry(ip);
 
 	XFS_STATS_INC(vn_reclaim);
-	if (xfs_reclaim(ip))
-		panic("%s: cannot reclaim 0x%p\n", __func__, inode);
+
+	/* bad inode, get out here ASAP */
+	if (is_bad_inode(inode))
+		goto out_reclaim;
+
+	xfs_ioend_wait(ip);
+
+	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+
+	/*
+	 * We should never get here with one of the reclaim flags already set.
+	 */
+	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
+
+	/*
+	 * If we have nothing to flush with this inode then complete the
+	 * teardown now, otherwise delay the flush operation.
+	 */
+	if (!xfs_inode_clean(ip)) {
+		xfs_inode_set_reclaim_tag(ip);
+		return;
+	}
+
+out_reclaim:
+	xfs_ireclaim(ip);
 }
 
 /*
@@ -973,7 +999,6 @@ xfs_fs_inode_init_once(
 
 	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
 		     "xfsino", ip->i_ino);
-	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
 }
 
 /*
@@ -1075,6 +1100,20 @@ xfs_fs_clear_inode(
 	XFS_STATS_INC(vn_remove);
 	XFS_STATS_DEC(vn_active);
 
+	/*
+	 * The iolock is used by the file system to coordinate reads,
+	 * writes, and block truncates.  Up to this point the lock
+	 * protected concurrent accesses by users of the inode.  But
+	 * from here forward we're doing some final processing of the
+	 * inode because we're done with it, and although we reuse the
+	 * iolock for protection it is really a distinct lock class
+	 * (in the lockdep sense) from before.  To keep lockdep happy
+	 * (and basically indicate what we are doing), we explicitly
+	 * re-init the iolock here.
+	 */
+	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
+
 	xfs_inactive(ip);
 }
 
@@ -1092,8 +1131,6 @@ xfs_fs_put_super(
 	struct super_block	*sb)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
-	struct xfs_inode	*rip = mp->m_rootip;
-	int			unmount_event_flags = 0;
 
 	xfs_syncd_stop(mp);
 
@@ -1109,20 +1146,7 @@ xfs_fs_put_super(
 		xfs_sync_attr(mp, 0);
 	}
 
-#ifdef HAVE_DMAPI
-	if (mp->m_flags & XFS_MOUNT_DMAPI) {
-		unmount_event_flags =
-			(mp->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ?
-				0 : DM_FLAGS_UNWANTED;
-		/*
-		 * Ignore error from dmapi here, first unmount is not allowed
-		 * to fail anyway, and second we wouldn't want to fail a
-		 * unmount because of dmapi.
-		 */
-		XFS_SEND_PREUNMOUNT(mp, rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
-				NULL, NULL, 0, 0, unmount_event_flags);
-	}
-#endif
+	XFS_SEND_PREUNMOUNT(mp);
 
 	/*
 	 * Blow away any referenced inode in the filestreams cache.
@@ -1133,10 +1157,7 @@ xfs_fs_put_super(
 
 	XFS_bflush(mp->m_ddev_targp);
 
-	if (mp->m_flags & XFS_MOUNT_DMAPI) {
-		XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
-				unmount_event_flags);
-	}
+	XFS_SEND_UNMOUNT(mp);
 
 	xfs_unmountfs(mp);
 	xfs_freesb(mp);
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 961df0a..d895a3a 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -663,10 +663,9 @@ xfs_syncd_stop(
 	kthread_stop(mp->m_sync_task);
 }
 
-int
+STATIC int
 xfs_reclaim_inode(
 	xfs_inode_t	*ip,
-	int		locked,
 	int		sync_mode)
 {
 	xfs_perag_t	*pag = xfs_get_perag(ip->i_mount, ip->i_ino);
@@ -682,10 +681,6 @@ xfs_reclaim_inode(
 	    !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
 		spin_unlock(&ip->i_flags_lock);
 		write_unlock(&pag->pag_ici_lock);
-		if (locked) {
-			xfs_ifunlock(ip);
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		}
 		return -EAGAIN;
 	}
 	__xfs_iflags_set(ip, XFS_IRECLAIM);
@@ -704,10 +699,8 @@ xfs_reclaim_inode(
 	 * We get the flush lock regardless, though, just to make sure
 	 * we don't free it while it is being flushed.
 	 */
-	if (!locked) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_iflock(ip);
-	}
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_iflock(ip);
 
 	/*
 	 * In the case of a forced shutdown we rely on xfs_iflush() to
@@ -778,7 +771,7 @@ xfs_reclaim_inode_now(
 	}
 	read_unlock(&pag->pag_ici_lock);
 
-	return xfs_reclaim_inode(ip, 0, flags);
+	return xfs_reclaim_inode(ip, flags);
 }
 
 int
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 27920eb..a500b4d 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -44,7 +44,6 @@ void xfs_quiesce_attr(struct xfs_mount *mp);
 
 void xfs_flush_inodes(struct xfs_inode *ip);
 
-int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index ad7fbea..00cabf5 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -36,7 +36,6 @@ struct attrlist_cursor_kern;
 /*
  * Flags for read/write calls - same values as IRIX
  */
-#define IO_ISAIO	0x00001		/* don't wait for completion */
 #define IO_ISDIRECT	0x00004		/* bypass page cache */
 #define IO_INVIS	0x00020		/* don't update inode timestamps */