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

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  XFS: Free buffer pages array unconditionally
  xfs: kill xfs_bmbt_rec_32/64 types
  xfs: improve metadata I/O merging in the elevator
  xfs: check for not fully initialized inodes in xfs_ireclaim

fs/xfs/linux-2.6/xfs_buf.c

@@ -292,6 +292,7 @@ _xfs_buf_free_pages(
 {
 	if (bp->b_pages != bp->b_page_array) {
 		kmem_free(bp->b_pages);
+		bp->b_pages = NULL;
 	}
 }
 
@@ -323,9 +324,8 @@ xfs_buf_free(
 				ASSERT(!PagePrivate(page));
 			page_cache_release(page);
 		}
-		_xfs_buf_free_pages(bp);
 	}
-
+	_xfs_buf_free_pages(bp);
 	xfs_buf_deallocate(bp);
 }
 
@@ -1149,10 +1149,14 @@ _xfs_buf_ioapply(
 	if (bp->b_flags & XBF_ORDERED) {
 		ASSERT(!(bp->b_flags & XBF_READ));
 		rw = WRITE_BARRIER;
-	} else if (bp->b_flags & _XBF_RUN_QUEUES) {
+	} else if (bp->b_flags & XBF_LOG_BUFFER) {
 		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
 		bp->b_flags &= ~_XBF_RUN_QUEUES;
 		rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC;
+	} else if (bp->b_flags & _XBF_RUN_QUEUES) {
+		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
+		bp->b_flags &= ~_XBF_RUN_QUEUES;
+		rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META;
 	} else {
 		rw = (bp->b_flags & XBF_WRITE) ? WRITE :
 		     (bp->b_flags & XBF_READ_AHEAD) ? READA : READ;

fs/xfs/linux-2.6/xfs_buf.h

@@ -55,6 +55,7 @@ typedef enum {
 	XBF_FS_MANAGED = (1 << 8),  /* filesystem controls freeing memory  */
  	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
 	XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead		   */
+	XBF_LOG_BUFFER = (1 << 13), /* this is a buffer used for the log   */
 
 	/* flags used only as arguments to access routines */
 	XBF_LOCK = (1 << 14),       /* lock requested			   */

fs/xfs/xfs_bmap_btree.h

@@ -46,20 +46,12 @@ typedef struct xfs_bmdr_block {
 #define BMBT_STARTBLOCK_BITLEN	52
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
-
-#define BMBT_USE_64	1
-
-typedef struct xfs_bmbt_rec_32
-{
-	__uint32_t		l0, l1, l2, l3;
-} xfs_bmbt_rec_32_t;
-typedef struct xfs_bmbt_rec_64
-{
+typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
-} xfs_bmbt_rec_64_t;
+} xfs_bmbt_rec_t;
 
 typedef __uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
-typedef xfs_bmbt_rec_64_t xfs_bmbt_rec_t, xfs_bmdr_rec_t;
+typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
 
 typedef struct xfs_bmbt_rec_host {
 	__uint64_t		l0, l1;

fs/xfs/xfs_iget.c

@@ -478,17 +478,21 @@ xfs_ireclaim(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_perag	*pag;
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
 
 	XFS_STATS_INC(xs_ig_reclaims);
 
 	/*
-	 * Remove the inode from the per-AG radix tree.  It doesn't matter
-	 * if it was never added to it because radix_tree_delete can deal
-	 * with that case just fine.
+	 * Remove the inode from the per-AG radix tree.
+	 *
+	 * Because radix_tree_delete won't complain even if the item was never
+	 * added to the tree assert that it's been there before to catch
+	 * problems with the inode life time early on.
 	 */
 	pag = xfs_get_perag(mp, ip->i_ino);
 	write_lock(&pag->pag_ici_lock);
-	radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino));
+	if (!radix_tree_delete(&pag->pag_ici_root, agino))
+		ASSERT(0);
 	write_unlock(&pag->pag_ici_lock);
 	xfs_put_perag(mp, pag);
 

fs/xfs/xfs_inode_item.h

@@ -127,7 +127,7 @@ static inline int xfs_ilog_fdata(int w)
 #ifdef __KERNEL__
 
 struct xfs_buf;
-struct xfs_bmbt_rec_64;
+struct xfs_bmbt_rec;
 struct xfs_inode;
 struct xfs_mount;
 
@@ -140,9 +140,9 @@ typedef struct xfs_inode_log_item {
 	unsigned short		ili_flags;	   /* misc flags */
 	unsigned short		ili_logged;	   /* flushed logged data */
 	unsigned int		ili_last_fields;   /* fields when flushed */
-	struct xfs_bmbt_rec_64	*ili_extents_buf;  /* array of logged
+	struct xfs_bmbt_rec	*ili_extents_buf;  /* array of logged
 						      data exts */
-	struct xfs_bmbt_rec_64	*ili_aextents_buf; /* array of logged
+	struct xfs_bmbt_rec	*ili_aextents_buf; /* array of logged
 						      attr exts */
 	unsigned int            ili_pushbuf_flag;  /* one bit used in push_ail */
 

fs/xfs/xfs_log.c

@@ -1441,6 +1441,7 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_BUSY(bp);
 	XFS_BUF_ASYNC(bp);
+	bp->b_flags |= XBF_LOG_BUFFER;
 	/*
 	 * Do an ordered write for the log block.
 	 * Its unnecessary to flush the first split block in the log wrap case.
@@ -1478,6 +1479,7 @@ xlog_sync(xlog_t		*log,
 		XFS_BUF_ZEROFLAGS(bp);
 		XFS_BUF_BUSY(bp);
 		XFS_BUF_ASYNC(bp);
+		bp->b_flags |= XBF_LOG_BUFFER;
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			XFS_BUF_ORDERED(bp);
 		dptr = XFS_BUF_PTR(bp);

include/linux/fs.h

@@ -152,6 +152,7 @@ struct inodes_stat_t {
 #define WRITE_SYNC_PLUG	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
 #define WRITE_SYNC	(WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
 #define WRITE_ODIRECT_PLUG	(WRITE | (1 << BIO_RW_SYNCIO))
+#define WRITE_META	(WRITE | (1 << BIO_RW_META))
 #define SWRITE_SYNC_PLUG	\
 			(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
 #define SWRITE_SYNC	(SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))