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

Pull XFS update (part 2) from Ben Myers:
 "Fixes for tracing of xfs_name strings, flag handling in
  open_by_handle, a log space hang with freeze/unfreeze, fstrim offset
  calculations, a section mismatch with xfs_qm_exit, an oops in
  xlog_recover_process_iunlinks, and a deadlock in xfs_rtfree_extent.

  There are also additional trace points for attributes, and the
  addition of a workqueue for allocation to work around kernel stack
  size limitations."

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: add lots of attribute trace points
  xfs: Fix oops on IO error during xlog_recover_process_iunlinks()
  xfs: fix fstrim offset calculations
  xfs: Account log unmount transaction correctly
  xfs: don't cache inodes read through bulkstat
  xfs: trace xfs_name strings correctly
  xfs: introduce an allocation workqueue
  xfs: Fix open flag handling in open_by_handle code
  xfs: fix deadlock in xfs_rtfree_extent
  fs: xfs: fix section mismatch in linux-next

fs/xfs/xfs_alloc.c

@@ -35,6 +35,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 
+struct workqueue_struct *xfs_alloc_wq;
 
 #define XFS_ABSDIFF(a,b)	(((a) <= (b)) ? ((b) - (a)) : ((a) - (b)))
 
@@ -68,7 +69,7 @@ xfs_alloc_lookup_eq(
  * Lookup the first record greater than or equal to [bno, len]
  * in the btree given by cur.
  */
-STATIC int				/* error */
+int				/* error */
 xfs_alloc_lookup_ge(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -2207,7 +2208,7 @@ xfs_alloc_read_agf(
  * group or loop over the allocation groups to find the result.
  */
 int				/* error */
-xfs_alloc_vextent(
+__xfs_alloc_vextent(
 	xfs_alloc_arg_t	*args)	/* allocation argument structure */
 {
 	xfs_agblock_t	agsize;	/* allocation group size */
@@ -2417,6 +2418,37 @@ xfs_alloc_vextent(
 	return error;
 }
 
+static void
+xfs_alloc_vextent_worker(
+	struct work_struct	*work)
+{
+	struct xfs_alloc_arg	*args = container_of(work,
+						struct xfs_alloc_arg, work);
+	unsigned long		pflags;
+
+	/* we are in a transaction context here */
+	current_set_flags_nested(&pflags, PF_FSTRANS);
+
+	args->result = __xfs_alloc_vextent(args);
+	complete(args->done);
+
+	current_restore_flags_nested(&pflags, PF_FSTRANS);
+}
+
+
+int				/* error */
+xfs_alloc_vextent(
+	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+{
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	args->done = &done;
+	INIT_WORK(&args->work, xfs_alloc_vextent_worker);
+	queue_work(xfs_alloc_wq, &args->work);
+	wait_for_completion(&done);
+	return args->result;
+}
+
 /*
  * Free an extent.
  * Just break up the extent address and hand off to xfs_free_ag_extent

fs/xfs/xfs_alloc.h

@@ -25,6 +25,8 @@ struct xfs_perag;
 struct xfs_trans;
 struct xfs_busy_extent;
 
+extern struct workqueue_struct *xfs_alloc_wq;
+
 /*
  * Freespace allocation types.  Argument to xfs_alloc_[v]extent.
  */
@@ -119,6 +121,9 @@ typedef struct xfs_alloc_arg {
 	char		isfl;		/* set if is freelist blocks - !acctg */
 	char		userdata;	/* set if this is user data */
 	xfs_fsblock_t	firstblock;	/* io first block allocated */
+	struct completion *done;
+	struct work_struct work;
+	int		result;
 } xfs_alloc_arg_t;
 
 /*
@@ -243,6 +248,13 @@ xfs_alloc_lookup_le(
 	xfs_extlen_t		len,	/* length of extent */
 	int			*stat);	/* success/failure */
 
+int				/* error */
+xfs_alloc_lookup_ge(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat);	/* success/failure */
+
 int					/* error */
 xfs_alloc_get_rec(
 	struct xfs_btree_cur	*cur,	/* btree cursor */

fs/xfs/xfs_attr.c

@@ -853,6 +853,8 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 {
 	int newsize, forkoff, retval;
 
+	trace_xfs_attr_sf_addname(args);
+
 	retval = xfs_attr_shortform_lookup(args);
 	if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
 		return(retval);
@@ -896,6 +898,8 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int retval, error, committed, forkoff;
 
+	trace_xfs_attr_leaf_addname(args);
+
 	/*
 	 * Read the (only) block in the attribute list in.
 	 */
@@ -920,6 +924,9 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			xfs_da_brelse(args->trans, bp);
 			return(retval);
 		}
+
+		trace_xfs_attr_leaf_replace(args);
+
 		args->op_flags |= XFS_DA_OP_RENAME;	/* an atomic rename */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
@@ -1090,6 +1097,8 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int error, committed, forkoff;
 
+	trace_xfs_attr_leaf_removename(args);
+
 	/*
 	 * Remove the attribute.
 	 */
@@ -1223,6 +1232,8 @@ xfs_attr_node_addname(xfs_da_args_t *args)
 	xfs_mount_t *mp;
 	int committed, retval, error;
 
+	trace_xfs_attr_node_addname(args);
+
 	/*
 	 * Fill in bucket of arguments/results/context to carry around.
 	 */
@@ -1249,6 +1260,9 @@ xfs_attr_node_addname(xfs_da_args_t *args)
 	} else if (retval == EEXIST) {
 		if (args->flags & ATTR_CREATE)
 			goto out;
+
+		trace_xfs_attr_node_replace(args);
+
 		args->op_flags |= XFS_DA_OP_RENAME;	/* atomic rename op */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
@@ -1480,6 +1494,8 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int retval, error, committed, forkoff;
 
+	trace_xfs_attr_node_removename(args);
+
 	/*
 	 * Tie a string around our finger to remind us where we are.
 	 */

fs/xfs/xfs_attr_leaf.c

@@ -235,6 +235,8 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 	xfs_inode_t *dp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_create(args);
+
 	dp = args->dp;
 	ASSERT(dp != NULL);
 	ifp = dp->i_afp;
@@ -268,6 +270,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	xfs_inode_t *dp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_add(args);
+
 	dp = args->dp;
 	mp = dp->i_mount;
 	dp->i_d.di_forkoff = forkoff;
@@ -337,6 +341,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 	xfs_mount_t *mp;
 	xfs_inode_t *dp;
 
+	trace_xfs_attr_sf_remove(args);
+
 	dp = args->dp;
 	mp = dp->i_mount;
 	base = sizeof(xfs_attr_sf_hdr_t);
@@ -405,6 +411,8 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	int i;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_lookup(args);
+
 	ifp = args->dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
 	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
@@ -476,6 +484,8 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	xfs_ifork_t *ifp;
 
+	trace_xfs_attr_sf_to_leaf(args);
+
 	dp = args->dp;
 	ifp = dp->i_afp;
 	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
@@ -775,6 +785,8 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	char *tmpbuffer;
 	int error, i;
 
+	trace_xfs_attr_leaf_to_sf(args);
+
 	dp = args->dp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(dp->i_mount), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
@@ -848,6 +860,8 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	xfs_dablk_t blkno;
 	int error;
 
+	trace_xfs_attr_leaf_to_node(args);
+
 	dp = args->dp;
 	bp1 = bp2 = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
@@ -911,6 +925,8 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_attr_leaf_create(args);
+
 	dp = args->dp;
 	ASSERT(dp != NULL);
 	error = xfs_da_get_buf(args->trans, args->dp, blkno, -1, &bp,
@@ -948,6 +964,8 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	xfs_dablk_t blkno;
 	int error;
 
+	trace_xfs_attr_leaf_split(state->args);
+
 	/*
 	 * Allocate space for a new leaf node.
 	 */
@@ -977,10 +995,13 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	 *
 	 * Insert the "new" entry in the correct block.
 	 */
-	if (state->inleaf)
+	if (state->inleaf) {
+		trace_xfs_attr_leaf_add_old(state->args);
 		error = xfs_attr_leaf_add(oldblk->bp, state->args);
-	else
+	} else {
+		trace_xfs_attr_leaf_add_new(state->args);
 		error = xfs_attr_leaf_add(newblk->bp, state->args);
+	}
 
 	/*
 	 * Update last hashval in each block since we added the name.
@@ -1001,6 +1022,8 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	xfs_attr_leaf_map_t *map;
 	int tablesize, entsize, sum, tmp, i;
 
+	trace_xfs_attr_leaf_add(args);
+
 	leaf = bp->data;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT((args->index >= 0)
@@ -1128,8 +1151,6 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 	       (be32_to_cpu(entry->hashval) <= be32_to_cpu((entry+1)->hashval)));
 
 	/*
-	 * Copy the attribute name and value into the new space.
-	 *
 	 * For "remote" attribute values, simply note that we need to
 	 * allocate space for the "remote" value.  We can't actually
 	 * allocate the extents in this transaction, and we can't decide
@@ -1265,6 +1286,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	args = state->args;
 
+	trace_xfs_attr_leaf_rebalance(args);
+
 	/*
 	 * Check ordering of blocks, reverse if it makes things simpler.
 	 *
@@ -1810,6 +1833,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	xfs_mount_t *mp;
 	char *tmpbuffer;
 
+	trace_xfs_attr_leaf_unbalance(state->args);
+
 	/*
 	 * Set up environment.
 	 */
@@ -1919,6 +1944,8 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	int probe, span;
 	xfs_dahash_t hashval;
 
+	trace_xfs_attr_leaf_lookup(args);
+
 	leaf = bp->data;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
@@ -2445,6 +2472,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	char *name;
 #endif /* DEBUG */
 
+	trace_xfs_attr_leaf_clearflag(args);
 	/*
 	 * Set up the operation.
 	 */
@@ -2509,6 +2537,8 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_attr_leaf_setflag(args);
+
 	/*
 	 * Set up the operation.
 	 */
@@ -2565,6 +2595,8 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	char *name1, *name2;
 #endif /* DEBUG */
 
+	trace_xfs_attr_leaf_flipflags(args);
+
 	/*
 	 * Read the block containing the "old" attr
 	 */

fs/xfs/xfs_bmap.c

@@ -5124,6 +5124,15 @@ xfs_bunmapi(
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
+
+	if (isrt) {
+		/*
+		 * Synchronize by locking the bitmap inode.
+		 */
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+	}
+
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
 	       (nexts == 0 || extno < nexts)) {

fs/xfs/xfs_da_btree.c

@@ -108,6 +108,8 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	int error;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_create(args);
+
 	tp = args->trans;
 	error = xfs_da_get_buf(tp, args->dp, blkno, -1, &bp, whichfork);
 	if (error)
@@ -140,6 +142,8 @@ xfs_da_split(xfs_da_state_t *state)
 	xfs_dabuf_t *bp;
 	int max, action, error, i;
 
+	trace_xfs_da_split(state->args);
+
 	/*
 	 * Walk back up the tree splitting/inserting/adjusting as necessary.
 	 * If we need to insert and there isn't room, split the node, then
@@ -178,10 +182,12 @@ xfs_da_split(xfs_da_state_t *state)
 			state->extravalid = 1;
 			if (state->inleaf) {
 				state->extraafter = 0;	/* before newblk */
+				trace_xfs_attr_leaf_split_before(state->args);
 				error = xfs_attr_leaf_split(state, oldblk,
 							    &state->extrablk);
 			} else {
 				state->extraafter = 1;	/* after newblk */
+				trace_xfs_attr_leaf_split_after(state->args);
 				error = xfs_attr_leaf_split(state, newblk,
 							    &state->extrablk);
 			}
@@ -300,6 +306,8 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	xfs_mount_t *mp;
 	xfs_dir2_leaf_t *leaf;
 
+	trace_xfs_da_root_split(state->args);
+
 	/*
 	 * Copy the existing (incorrect) block from the root node position
 	 * to a free space somewhere.
@@ -380,6 +388,8 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	int newcount, error;
 	int useextra;
 
+	trace_xfs_da_node_split(state->args);
+
 	node = oldblk->bp->data;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 
@@ -466,6 +476,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	int count, tmp;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_rebalance(state->args);
+
 	node1 = blk1->bp->data;
 	node2 = blk2->bp->data;
 	/*
@@ -574,6 +586,8 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	xfs_da_node_entry_t *btree;
 	int tmp;
 
+	trace_xfs_da_node_add(state->args);
+
 	node = oldblk->bp->data;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count)));
@@ -619,6 +633,8 @@ xfs_da_join(xfs_da_state_t *state)
 	xfs_da_state_blk_t *drop_blk, *save_blk;
 	int action, error;
 
+	trace_xfs_da_join(state->args);
+
 	action = 0;
 	drop_blk = &state->path.blk[ state->path.active-1 ];
 	save_blk = &state->altpath.blk[ state->path.active-1 ];
@@ -723,6 +739,8 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	xfs_dabuf_t *bp;
 	int error;
 
+	trace_xfs_da_root_join(state->args);
+
 	args = state->args;
 	ASSERT(args != NULL);
 	ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC);
@@ -941,6 +959,8 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 	xfs_da_node_entry_t *btree;
 	int tmp;
 
+	trace_xfs_da_node_remove(state->args);
+
 	node = drop_blk->bp->data;
 	ASSERT(drop_blk->index < be16_to_cpu(node->hdr.count));
 	ASSERT(drop_blk->index >= 0);
@@ -984,6 +1004,8 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	int tmp;
 	xfs_trans_t *tp;
 
+	trace_xfs_da_node_unbalance(state->args);
+
 	drop_node = drop_blk->bp->data;
 	save_node = save_blk->bp->data;
 	ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
@@ -1230,6 +1252,7 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 		/*
 		 * Link new block in before existing block.
 		 */
+		trace_xfs_da_link_before(args);
 		new_info->forw = cpu_to_be32(old_blk->blkno);
 		new_info->back = old_info->back;
 		if (old_info->back) {
@@ -1251,6 +1274,7 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 		/*
 		 * Link new block in after existing block.
 		 */
+		trace_xfs_da_link_after(args);
 		new_info->forw = old_info->forw;
 		new_info->back = cpu_to_be32(old_blk->blkno);
 		if (old_info->forw) {
@@ -1348,6 +1372,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	 * Unlink the leaf block from the doubly linked chain of leaves.
 	 */
 	if (be32_to_cpu(save_info->back) == drop_blk->blkno) {
+		trace_xfs_da_unlink_back(args);
 		save_info->back = drop_info->back;
 		if (drop_info->back) {
 			error = xfs_da_read_buf(args->trans, args->dp,
@@ -1365,6 +1390,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			xfs_da_buf_done(bp);
 		}
 	} else {
+		trace_xfs_da_unlink_forward(args);
 		save_info->forw = drop_info->forw;
 		if (drop_info->forw) {
 			error = xfs_da_read_buf(args->trans, args->dp,
@@ -1652,6 +1678,8 @@ xfs_da_grow_inode(
 	int			count;
 	int			error;
 
+	trace_xfs_da_grow_inode(args);
+
 	if (args->whichfork == XFS_DATA_FORK) {
 		bno = args->dp->i_mount->m_dirleafblk;
 		count = args->dp->i_mount->m_dirblkfsbs;
@@ -1690,6 +1718,8 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	xfs_dir2_leaf_t *dead_leaf2;
 	xfs_dahash_t dead_hash;
 
+	trace_xfs_da_swap_lastblock(args);
+
 	dead_buf = *dead_bufp;
 	dead_blkno = *dead_blknop;
 	tp = args->trans;
@@ -1878,6 +1908,8 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 	xfs_trans_t *tp;
 	xfs_mount_t *mp;
 
+	trace_xfs_da_shrink_inode(args);
+
 	dp = args->dp;
 	w = args->whichfork;
 	tp = args->trans;

fs/xfs/xfs_discard.c

@@ -37,9 +37,9 @@ STATIC int
 xfs_trim_extents(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
-	xfs_fsblock_t		start,
-	xfs_fsblock_t		end,
-	xfs_fsblock_t		minlen,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen,
 	__uint64_t		*blocks_trimmed)
 {
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
@@ -67,7 +67,7 @@ xfs_trim_extents(
 	/*
 	 * Look up the longest btree in the AGF and start with it.
 	 */
-	error = xfs_alloc_lookup_le(cur, 0,
+	error = xfs_alloc_lookup_ge(cur, 0,
 			    be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i);
 	if (error)
 		goto out_del_cursor;
@@ -77,8 +77,10 @@ xfs_trim_extents(
 	 * enough to be worth discarding.
 	 */
 	while (i) {
-		xfs_agblock_t fbno;
-		xfs_extlen_t flen;
+		xfs_agblock_t	fbno;
+		xfs_extlen_t	flen;
+		xfs_daddr_t	dbno;
+		xfs_extlen_t	dlen;
 
 		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
 		if (error)
@@ -86,10 +88,18 @@ xfs_trim_extents(
 		XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
 		ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest));
 
+		/*
+		 * use daddr format for all range/len calculations as that is
+		 * the format the range/len variables are supplied in by
+		 * userspace.
+		 */
+		dbno = XFS_AGB_TO_DADDR(mp, agno, fbno);
+		dlen = XFS_FSB_TO_BB(mp, flen);
+
 		/*
 		 * Too small?  Give up.
 		 */
-		if (flen < minlen) {
+		if (dlen < minlen) {
 			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
 			goto out_del_cursor;
 		}
@@ -99,8 +109,7 @@ xfs_trim_extents(
 		 * supposed to discard skip it.  Do not bother to trim
 		 * down partially overlapping ranges for now.
 		 */
-		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
-		    XFS_AGB_TO_FSB(mp, agno, fbno) > end) {
+		if (dbno + dlen < start || dbno > end) {
 			trace_xfs_discard_exclude(mp, agno, fbno, flen);
 			goto next_extent;
 		}
@@ -115,10 +124,7 @@ xfs_trim_extents(
 		}
 
 		trace_xfs_discard_extent(mp, agno, fbno, flen);
-		error = -blkdev_issue_discard(bdev,
-				XFS_AGB_TO_DADDR(mp, agno, fbno),
-				XFS_FSB_TO_BB(mp, flen),
-				GFP_NOFS, 0);
+		error = -blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0);
 		if (error)
 			goto out_del_cursor;
 		*blocks_trimmed += flen;
@@ -137,6 +143,15 @@ xfs_trim_extents(
 	return error;
 }
 
+/*
+ * trim a range of the filesystem.
+ *
+ * Note: the parameters passed from userspace are byte ranges into the
+ * filesystem which does not match to the format we use for filesystem block
+ * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
+ * is a linear address range. Hence we need to use DADDR based conversions and
+ * comparisons for determining the correct offset and regions to trim.
+ */
 int
 xfs_ioc_trim(
 	struct xfs_mount		*mp,
@@ -145,7 +160,7 @@ xfs_ioc_trim(
 	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
-	xfs_fsblock_t		start, end, minlen;
+	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
 	__uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
@@ -159,22 +174,22 @@ xfs_ioc_trim(
 
 	/*
 	 * Truncating down the len isn't actually quite correct, but using
-	 * XFS_B_TO_FSB would mean we trivially get overflows for values
+	 * BBTOB would mean we trivially get overflows for values
 	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
 	 * used by the fstrim application.  In the end it really doesn't
 	 * matter as trimming blocks is an advisory interface.
 	 */
-	start = XFS_B_TO_FSBT(mp, range.start);
-	end = start + XFS_B_TO_FSBT(mp, range.len) - 1;
-	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
+	start = BTOBB(range.start);
+	end = start + BTOBBT(range.len) - 1;
+	minlen = BTOBB(max_t(u64, granularity, range.minlen));
 
-	if (start >= mp->m_sb.sb_dblocks)
+	if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks)
 		return -XFS_ERROR(EINVAL);
-	if (end > mp->m_sb.sb_dblocks - 1)
-		end = mp->m_sb.sb_dblocks - 1;
+	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
+		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
 
-	start_agno = XFS_FSB_TO_AGNO(mp, start);
-	end_agno = XFS_FSB_TO_AGNO(mp, end);
+	start_agno = xfs_daddr_to_agno(mp, start);
+	end_agno = xfs_daddr_to_agno(mp, end);
 
 	for (agno = start_agno; agno <= end_agno; agno++) {
 		error = -xfs_trim_extents(mp, agno, start, end, minlen,

fs/xfs/xfs_dquot.c

@@ -1065,7 +1065,7 @@ xfs_qm_init(void)
 	return -ENOMEM;
 }
 
-void __exit
+void
 xfs_qm_exit(void)
 {
 	kmem_zone_destroy(xfs_qm_dqtrxzone);

fs/xfs/xfs_iget.c

@@ -289,7 +289,7 @@ xfs_iget_cache_hit(
 	if (lock_flags != 0)
 		xfs_ilock(ip, lock_flags);
 
-	xfs_iflags_clear(ip, XFS_ISTALE);
+	xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
 	XFS_STATS_INC(xs_ig_found);
 
 	return 0;
@@ -314,6 +314,7 @@ xfs_iget_cache_miss(
 	struct xfs_inode	*ip;
 	int			error;
 	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
+	int			iflags;
 
 	ip = xfs_inode_alloc(mp, ino);
 	if (!ip)
@@ -358,8 +359,11 @@ xfs_iget_cache_miss(
 	 * memory barrier that ensures this detection works correctly at lookup
 	 * time.
 	 */
+	iflags = XFS_INEW;
+	if (flags & XFS_IGET_DONTCACHE)
+		iflags |= XFS_IDONTCACHE;
 	ip->i_udquot = ip->i_gdquot = NULL;
-	xfs_iflags_set(ip, XFS_INEW);
+	xfs_iflags_set(ip, iflags);
 
 	/* insert the new inode */
 	spin_lock(&pag->pag_ici_lock);

fs/xfs/xfs_inode.h

@@ -387,10 +387,11 @@ xfs_set_projid(struct xfs_inode *ip,
 #define XFS_IFLOCK		(1 << __XFS_IFLOCK_BIT)
 #define __XFS_IPINNED_BIT	8	 /* wakeup key for zero pin count */
 #define XFS_IPINNED		(1 << __XFS_IPINNED_BIT)
+#define XFS_IDONTCACHE		(1 << 9) /* don't cache the inode long term */
 
 /*
  * Per-lifetime flags need to be reset when re-using a reclaimable inode during
- * inode lookup. Thi prevents unintended behaviour on the new inode from
+ * inode lookup. This prevents unintended behaviour on the new inode from
  * ocurring.
  */
 #define XFS_IRECLAIM_RESET_FLAGS	\
@@ -553,6 +554,7 @@ do { \
  */
 #define XFS_IGET_CREATE		0x1
 #define XFS_IGET_UNTRUSTED	0x2
+#define XFS_IGET_DONTCACHE	0x4
 
 int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
 			    xfs_ino_t, struct xfs_dinode **,

fs/xfs/xfs_ioctl.c

@@ -209,6 +209,7 @@ xfs_open_by_handle(
 	struct file		*filp;
 	struct inode		*inode;
 	struct dentry		*dentry;
+	fmode_t			fmode;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -XFS_ERROR(EPERM);
@@ -228,26 +229,21 @@ xfs_open_by_handle(
 	hreq->oflags |= O_LARGEFILE;
 #endif
 
-	/* Put open permission in namei format. */
 	permflag = hreq->oflags;
-	if ((permflag+1) & O_ACCMODE)
-		permflag++;
-	if (permflag & O_TRUNC)
-		permflag |= 2;
-
+	fmode = OPEN_FMODE(permflag);
 	if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
-	    (permflag & FMODE_WRITE) && IS_APPEND(inode)) {
+	    (fmode & FMODE_WRITE) && IS_APPEND(inode)) {
 		error = -XFS_ERROR(EPERM);
 		goto out_dput;
 	}
 
-	if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
+	if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
 		error = -XFS_ERROR(EACCES);
 		goto out_dput;
 	}
 
 	/* Can't write directories. */
-	if (S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) {
+	if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
 		error = -XFS_ERROR(EISDIR);
 		goto out_dput;
 	}

fs/xfs/xfs_itable.c

@@ -75,7 +75,8 @@ xfs_bulkstat_one_int(
 		return XFS_ERROR(ENOMEM);
 
 	error = xfs_iget(mp, NULL, ino,
-			 XFS_IGET_UNTRUSTED, XFS_ILOCK_SHARED, &ip);
+			 (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED),
+			 XFS_ILOCK_SHARED, &ip);
 	if (error) {
 		*stat = BULKSTAT_RV_NOTHING;
 		goto out_free;

fs/xfs/xfs_log.c

@@ -726,8 +726,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 				.lv_iovecp = &reg,
 			};
 
-			/* remove inited flag */
+			/* remove inited flag, and account for space used */
 			tic->t_flags = 0;
+			tic->t_curr_res -= sizeof(magic);
 			error = xlog_write(log, &vec, tic, &lsn,
 					   NULL, XLOG_UNMOUNT_TRANS);
 			/*

fs/xfs/xfs_log_recover.c

@@ -3161,37 +3161,26 @@ xlog_recover_process_iunlinks(
 			 */
 			continue;
 		}
+		/*
+		 * Unlock the buffer so that it can be acquired in the normal
+		 * course of the transaction to truncate and free each inode.
+		 * Because we are not racing with anyone else here for the AGI
+		 * buffer, we don't even need to hold it locked to read the
+		 * initial unlinked bucket entries out of the buffer. We keep
+		 * buffer reference though, so that it stays pinned in memory
+		 * while we need the buffer.
+		 */
 		agi = XFS_BUF_TO_AGI(agibp);
+		xfs_buf_unlock(agibp);
 
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) {
 			agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 			while (agino != NULLAGINO) {
-				/*
-				 * Release the agi buffer so that it can
-				 * be acquired in the normal course of the
-				 * transaction to truncate and free the inode.
-				 */
-				xfs_buf_relse(agibp);
-
 				agino = xlog_recover_process_one_iunlink(mp,
 							agno, agino, bucket);
-
-				/*
-				 * Reacquire the agibuffer and continue around
-				 * the loop. This should never fail as we know
-				 * the buffer was good earlier on.
-				 */
-				error = xfs_read_agi(mp, NULL, agno, &agibp);
-				ASSERT(error == 0);
-				agi = XFS_BUF_TO_AGI(agibp);
 			}
 		}
-
-		/*
-		 * Release the buffer for the current agi so we can
-		 * go on to the next one.
-		 */
-		xfs_buf_relse(agibp);
+		xfs_buf_rele(agibp);
 	}
 
 	mp->m_dmevmask = mp_dmevmask;

fs/xfs/xfs_rtalloc.c

@@ -183,6 +183,7 @@ xfs_growfs_rt_alloc(
 		oblocks = map.br_startoff + map.br_blockcount;
 	}
 	return 0;
+
 error:
 	return error;
 }
@@ -2139,11 +2140,9 @@ xfs_rtfree_extent(
 	xfs_buf_t	*sumbp;		/* summary file block buffer */
 
 	mp = tp->t_mountp;
-	/*
-	 * Synchronize by locking the bitmap inode.
-	 */
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
+	ASSERT(mp->m_rbmip->i_itemp != NULL);
+	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
 #if defined(__KERNEL__) && defined(DEBUG)
 	/*

fs/xfs/xfs_super.c

@@ -950,6 +950,22 @@ xfs_fs_evict_inode(
 	xfs_inactive(ip);
 }
 
+/*
+ * We do an unlocked check for XFS_IDONTCACHE here because we are already
+ * serialised against cache hits here via the inode->i_lock and igrab() in
+ * xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
+ * racing with us, and it avoids needing to grab a spinlock here for every inode
+ * we drop the final reference on.
+ */
+STATIC int
+xfs_fs_drop_inode(
+	struct inode		*inode)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	return generic_drop_inode(inode) || (ip->i_flags & XFS_IDONTCACHE);
+}
+
 STATIC void
 xfs_free_fsname(
 	struct xfs_mount	*mp)
@@ -1433,6 +1449,7 @@ static const struct super_operations xfs_super_operations = {
 	.destroy_inode		= xfs_fs_destroy_inode,
 	.dirty_inode		= xfs_fs_dirty_inode,
 	.evict_inode		= xfs_fs_evict_inode,
+	.drop_inode		= xfs_fs_drop_inode,
 	.put_super		= xfs_fs_put_super,
 	.sync_fs		= xfs_fs_sync_fs,
 	.freeze_fs		= xfs_fs_freeze,
@@ -1606,12 +1623,28 @@ xfs_init_workqueues(void)
 	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_NON_REENTRANT, 0);
 	if (!xfs_syncd_wq)
 		return -ENOMEM;
+
+	/*
+	 * The allocation workqueue can be used in memory reclaim situations
+	 * (writepage path), and parallelism is only limited by the number of
+	 * AGs in all the filesystems mounted. Hence use the default large
+	 * max_active value for this workqueue.
+	 */
+	xfs_alloc_wq = alloc_workqueue("xfsalloc", WQ_MEM_RECLAIM, 0);
+	if (!xfs_alloc_wq)
+		goto out_destroy_syncd;
+
 	return 0;
+
+out_destroy_syncd:
+	destroy_workqueue(xfs_syncd_wq);
+	return -ENOMEM;
 }
 
 STATIC void
 xfs_destroy_workqueues(void)
 {
+	destroy_workqueue(xfs_alloc_wq);
 	destroy_workqueue(xfs_syncd_wq);
 }
 

fs/xfs/xfs_trace.h

@@ -627,16 +627,19 @@ DECLARE_EVENT_CLASS(xfs_namespace_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, dp_ino)
+		__field(int, namelen)
 		__dynamic_array(char, name, name->len)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(dp)->i_sb->s_dev;
 		__entry->dp_ino = dp->i_ino;
+		__entry->namelen = name->len;
 		memcpy(__get_str(name), name->name, name->len);
 	),
-	TP_printk("dev %d:%d dp ino 0x%llx name %s",
+	TP_printk("dev %d:%d dp ino 0x%llx name %.*s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dp_ino,
+		  __entry->namelen,
 		  __get_str(name))
 )
 
@@ -658,6 +661,8 @@ TRACE_EVENT(xfs_rename,
 		__field(dev_t, dev)
 		__field(xfs_ino_t, src_dp_ino)
 		__field(xfs_ino_t, target_dp_ino)
+		__field(int, src_namelen)
+		__field(int, target_namelen)
 		__dynamic_array(char, src_name, src_name->len)
 		__dynamic_array(char, target_name, target_name->len)
 	),
@@ -665,15 +670,20 @@ TRACE_EVENT(xfs_rename,
 		__entry->dev = VFS_I(src_dp)->i_sb->s_dev;
 		__entry->src_dp_ino = src_dp->i_ino;
 		__entry->target_dp_ino = target_dp->i_ino;
+		__entry->src_namelen = src_name->len;
+		__entry->target_namelen = target_name->len;
 		memcpy(__get_str(src_name), src_name->name, src_name->len);
-		memcpy(__get_str(target_name), target_name->name, target_name->len);
+		memcpy(__get_str(target_name), target_name->name,
+			target_name->len);
 	),
 	TP_printk("dev %d:%d src dp ino 0x%llx target dp ino 0x%llx"
-		  " src name %s target name %s",
+		  " src name %.*s target name %.*s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->src_dp_ino,
 		  __entry->target_dp_ino,
+		  __entry->src_namelen,
 		  __get_str(src_name),
+		  __entry->target_namelen,
 		  __get_str(target_name))
 )
 
@@ -1408,7 +1418,7 @@ DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed);
 
-DECLARE_EVENT_CLASS(xfs_dir2_class,
+DECLARE_EVENT_CLASS(xfs_da_class,
 	TP_PROTO(struct xfs_da_args *args),
 	TP_ARGS(args),
 	TP_STRUCT__entry(
@@ -1443,7 +1453,7 @@ DECLARE_EVENT_CLASS(xfs_dir2_class,
 )
 
 #define DEFINE_DIR2_EVENT(name) \
-DEFINE_EVENT(xfs_dir2_class, name, \
+DEFINE_EVENT(xfs_da_class, name, \
 	TP_PROTO(struct xfs_da_args *args), \
 	TP_ARGS(args))
 DEFINE_DIR2_EVENT(xfs_dir2_sf_addname);
@@ -1472,6 +1482,64 @@ DEFINE_DIR2_EVENT(xfs_dir2_node_replace);
 DEFINE_DIR2_EVENT(xfs_dir2_node_removename);
 DEFINE_DIR2_EVENT(xfs_dir2_node_to_leaf);
 
+#define DEFINE_ATTR_EVENT(name) \
+DEFINE_EVENT(xfs_da_class, name, \
+	TP_PROTO(struct xfs_da_args *args), \
+	TP_ARGS(args))
+DEFINE_ATTR_EVENT(xfs_attr_sf_add);
+DEFINE_ATTR_EVENT(xfs_attr_sf_addname);
+DEFINE_ATTR_EVENT(xfs_attr_sf_create);
+DEFINE_ATTR_EVENT(xfs_attr_sf_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_sf_remove);
+DEFINE_ATTR_EVENT(xfs_attr_sf_removename);
+DEFINE_ATTR_EVENT(xfs_attr_sf_to_leaf);
+
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add_old);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_add_new);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_addname);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_create);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_replace);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_removename);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split_before);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_split_after);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_clearflag);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_setflag);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_flipflags);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_to_sf);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_to_node);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_rebalance);
+DEFINE_ATTR_EVENT(xfs_attr_leaf_unbalance);
+
+DEFINE_ATTR_EVENT(xfs_attr_node_addname);
+DEFINE_ATTR_EVENT(xfs_attr_node_lookup);
+DEFINE_ATTR_EVENT(xfs_attr_node_replace);
+DEFINE_ATTR_EVENT(xfs_attr_node_removename);
+
+#define DEFINE_DA_EVENT(name) \
+DEFINE_EVENT(xfs_da_class, name, \
+	TP_PROTO(struct xfs_da_args *args), \
+	TP_ARGS(args))
+DEFINE_DA_EVENT(xfs_da_split);
+DEFINE_DA_EVENT(xfs_da_join);
+DEFINE_DA_EVENT(xfs_da_link_before);
+DEFINE_DA_EVENT(xfs_da_link_after);
+DEFINE_DA_EVENT(xfs_da_unlink_back);
+DEFINE_DA_EVENT(xfs_da_unlink_forward);
+DEFINE_DA_EVENT(xfs_da_root_split);
+DEFINE_DA_EVENT(xfs_da_root_join);
+DEFINE_DA_EVENT(xfs_da_node_add);
+DEFINE_DA_EVENT(xfs_da_node_create);
+DEFINE_DA_EVENT(xfs_da_node_split);
+DEFINE_DA_EVENT(xfs_da_node_remove);
+DEFINE_DA_EVENT(xfs_da_node_rebalance);
+DEFINE_DA_EVENT(xfs_da_node_unbalance);
+DEFINE_DA_EVENT(xfs_da_swap_lastblock);
+DEFINE_DA_EVENT(xfs_da_grow_inode);
+DEFINE_DA_EVENT(xfs_da_shrink_inode);
+
 DECLARE_EVENT_CLASS(xfs_dir2_space_class,
 	TP_PROTO(struct xfs_da_args *args, int idx),
 	TP_ARGS(args, idx),