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

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: stop using the page cache to back the buffer cache
  xfs: register the inode cache shrinker before quotachecks
  xfs: xfs_trans_read_buf() should return an error on failure
  xfs: introduce inode cluster buffer trylocks for xfs_iflush
  vmap: flush vmap aliases when mapping fails
  xfs: preallocation transactions do not need to be synchronous

Fix up trivial conflicts in fs/xfs/linux-2.6/xfs_buf.c due to plug removal.

fs/xfs/linux-2.6/xfs_buf.h

@@ -61,30 +61,11 @@ typedef enum {
 #define XBF_DONT_BLOCK	(1 << 16)/* do not block in current thread */
 
 /* flags used only internally */
-#define _XBF_PAGE_CACHE	(1 << 17)/* backed by pagecache */
 #define _XBF_PAGES	(1 << 18)/* backed by refcounted pages */
 #define	_XBF_RUN_QUEUES	(1 << 19)/* run block device task queue	*/
+#define	_XBF_KMEM	(1 << 20)/* backed by heap memory */
 #define _XBF_DELWRI_Q	(1 << 21)/* buffer on delwri queue */
 
-/*
- * Special flag for supporting metadata blocks smaller than a FSB.
- *
- * In this case we can have multiple xfs_buf_t on a single page and
- * need to lock out concurrent xfs_buf_t readers as they only
- * serialise access to the buffer.
- *
- * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
- * between reads of the page. Hence we can have one thread read the
- * page and modify it, but then race with another thread that thinks
- * the page is not up-to-date and hence reads it again.
- *
- * The result is that the first modifcation to the page is lost.
- * This sort of AGF/AGI reading race can happen when unlinking inodes
- * that require truncation and results in the AGI unlinked list
- * modifications being lost.
- */
-#define _XBF_PAGE_LOCKED	(1 << 22)
-
 typedef unsigned int xfs_buf_flags_t;
 
 #define XFS_BUF_FLAGS \
@@ -100,12 +81,10 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_LOCK,		"LOCK" },  	/* should never be set */\
 	{ XBF_TRYLOCK,		"TRYLOCK" }, 	/* ditto */\
 	{ XBF_DONT_BLOCK,	"DONT_BLOCK" },	/* ditto */\
-	{ _XBF_PAGE_CACHE,	"PAGE_CACHE" }, \
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_RUN_QUEUES,	"RUN_QUEUES" }, \
-	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }
-
+	{ _XBF_KMEM,		"KMEM" }, \
+	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
 
 typedef enum {
 	XBT_FORCE_SLEEP = 0,
@@ -120,7 +99,7 @@ typedef struct xfs_bufhash {
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
-	struct address_space	*bt_mapping;
+	struct backing_dev_info	*bt_bdi;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_bsize;
 	unsigned int		bt_sshift;
@@ -139,17 +118,6 @@ typedef struct xfs_buftarg {
 	unsigned int		bt_lru_nr;
 } xfs_buftarg_t;
 
-/*
- *	xfs_buf_t:  Buffer structure for pagecache-based buffers
- *
- * This buffer structure is used by the pagecache buffer management routines
- * to refer to an assembly of pages forming a logical buffer.
- *
- * The buffer structure is used on a temporary basis only, and discarded when
- * released.  The real data storage is recorded in the pagecache. Buffers are
- * hashed to the block device on which the file system resides.
- */
-
 struct xfs_buf;
 typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
 

fs/xfs/linux-2.6/xfs_file.c

@@ -896,6 +896,7 @@ xfs_file_fallocate(
 	xfs_flock64_t	bf;
 	xfs_inode_t	*ip = XFS_I(inode);
 	int		cmd = XFS_IOC_RESVSP;
+	int		attr_flags = XFS_ATTR_NOLOCK;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
@@ -918,7 +919,10 @@ xfs_file_fallocate(
 			goto out_unlock;
 	}
 
-	error = -xfs_change_file_space(ip, cmd, &bf, 0, XFS_ATTR_NOLOCK);
+	if (file->f_flags & O_DSYNC)
+		attr_flags |= XFS_ATTR_SYNC;
+
+	error = -xfs_change_file_space(ip, cmd, &bf, 0, attr_flags);
 	if (error)
 		goto out_unlock;
 

fs/xfs/linux-2.6/xfs_ioctl.c

@@ -624,6 +624,10 @@ xfs_ioc_space(
 
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		attr_flags |= XFS_ATTR_NONBLOCK;
+
+	if (filp->f_flags & O_DSYNC)
+		attr_flags |= XFS_ATTR_SYNC;
+
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 

fs/xfs/linux-2.6/xfs_super.c

@@ -1078,7 +1078,7 @@ xfs_fs_write_inode(
 			error = 0;
 			goto out_unlock;
 		}
-		error = xfs_iflush(ip, 0);
+		error = xfs_iflush(ip, SYNC_TRYLOCK);
 	}
 
  out_unlock:
@@ -1539,10 +1539,14 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_free_sb;
 
-	error = xfs_mountfs(mp);
-	if (error)
-		goto out_filestream_unmount;
-
+	/*
+	 * we must configure the block size in the superblock before we run the
+	 * full mount process as the mount process can lookup and cache inodes.
+	 * For the same reason we must also initialise the syncd and register
+	 * the inode cache shrinker so that inodes can be reclaimed during
+	 * operations like a quotacheck that iterate all inodes in the
+	 * filesystem.
+	 */
 	sb->s_magic = XFS_SB_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;
 	sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
@@ -1550,6 +1554,16 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
+	error = xfs_syncd_init(mp);
+	if (error)
+		goto out_filestream_unmount;
+
+	xfs_inode_shrinker_register(mp);
+
+	error = xfs_mountfs(mp);
+	if (error)
+		goto out_syncd_stop;
+
 	root = igrab(VFS_I(mp->m_rootip));
 	if (!root) {
 		error = ENOENT;
@@ -1565,14 +1579,11 @@ xfs_fs_fill_super(
 		goto fail_vnrele;
 	}
 
-	error = xfs_syncd_init(mp);
-	if (error)
-		goto fail_vnrele;
-
-	xfs_inode_shrinker_register(mp);
-
 	return 0;
 
+ out_syncd_stop:
+	xfs_inode_shrinker_unregister(mp);
+	xfs_syncd_stop(mp);
  out_filestream_unmount:
 	xfs_filestream_unmount(mp);
  out_free_sb:
@@ -1596,6 +1607,9 @@ xfs_fs_fill_super(
 	}
 
  fail_unmount:
+	xfs_inode_shrinker_unregister(mp);
+	xfs_syncd_stop(mp);
+
 	/*
 	 * Blow away any referenced inode in the filestreams cache.
 	 * This can and will cause log traffic as inodes go inactive

fs/xfs/linux-2.6/xfs_sync.c

@@ -761,8 +761,10 @@ xfs_reclaim_inode(
 	struct xfs_perag	*pag,
 	int			sync_mode)
 {
-	int	error = 0;
+	int	error;
 
+restart:
+	error = 0;
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
@@ -788,9 +790,31 @@ xfs_reclaim_inode(
 	if (xfs_inode_clean(ip))
 		goto reclaim;
 
-	/* Now we have an inode that needs flushing */
-	error = xfs_iflush(ip, sync_mode);
+	/*
+	 * Now we have an inode that needs flushing.
+	 *
+	 * We do a nonblocking flush here even if we are doing a SYNC_WAIT
+	 * reclaim as we can deadlock with inode cluster removal.
+	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
+	 * ip->i_lock, and we are doing the exact opposite here. As a result,
+	 * doing a blocking xfs_itobp() to get the cluster buffer will result
+	 * in an ABBA deadlock with xfs_ifree_cluster().
+	 *
+	 * As xfs_ifree_cluser() must gather all inodes that are active in the
+	 * cache to mark them stale, if we hit this case we don't actually want
+	 * to do IO here - we want the inode marked stale so we can simply
+	 * reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
+	 * just unlock the inode, back off and try again. Hopefully the next
+	 * pass through will see the stale flag set on the inode.
+	 */
+	error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
 	if (sync_mode & SYNC_WAIT) {
+		if (error == EAGAIN) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			/* backoff longer than in xfs_ifree_cluster */
+			delay(2);
+			goto restart;
+		}
 		xfs_iflock(ip);
 		goto reclaim;
 	}

fs/xfs/xfs_inode.c

@@ -2835,7 +2835,7 @@ xfs_iflush(
 	 * Get the buffer containing the on-disk inode.
 	 */
 	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				(flags & SYNC_WAIT) ? XBF_LOCK : XBF_TRYLOCK);
+				(flags & SYNC_TRYLOCK) ? XBF_TRYLOCK : XBF_LOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;

fs/xfs/xfs_inode_item.c

@@ -760,11 +760,11 @@ xfs_inode_item_push(
 	 * Push the inode to it's backing buffer. This will not remove the
 	 * inode from the AIL - a further push will be required to trigger a
 	 * buffer push. However, this allows all the dirty inodes to be pushed
-	 * to the buffer before it is pushed to disk. THe buffer IO completion
-	 * will pull th einode from the AIL, mark it clean and unlock the flush
+	 * to the buffer before it is pushed to disk. The buffer IO completion
+	 * will pull the inode from the AIL, mark it clean and unlock the flush
 	 * lock.
 	 */
-	(void) xfs_iflush(ip, 0);
+	(void) xfs_iflush(ip, SYNC_TRYLOCK);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 }
 

fs/xfs/xfs_trans_buf.c

@@ -383,7 +383,8 @@ xfs_trans_read_buf(
 	bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
 	if (bp == NULL) {
 		*bpp = NULL;
-		return 0;
+		return (flags & XBF_TRYLOCK) ?
+					0 : XFS_ERROR(ENOMEM);
 	}
 	if (XFS_BUF_GETERROR(bp) != 0) {
 	    XFS_BUF_SUPER_STALE(bp);

fs/xfs/xfs_vnodeops.c

@@ -2831,6 +2831,7 @@ xfs_change_file_space(
 		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	if (attr_flags & XFS_ATTR_SYNC)
 		xfs_trans_set_sync(tp);
 
 	error = xfs_trans_commit(tp, 0);

fs/xfs/xfs_vnodeops.h

@@ -18,6 +18,7 @@ int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags);
 #define	XFS_ATTR_NONBLOCK	0x02	/* return EAGAIN if operation would block */
 #define XFS_ATTR_NOLOCK		0x04	/* Don't grab any conflicting locks */
 #define XFS_ATTR_NOACL		0x08	/* Don't call xfs_acl_chmod */
+#define XFS_ATTR_SYNC		0x10	/* synchronous operation required */
 
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_release(struct xfs_inode *ip);