Merge tag 'xfs-5.9-merge-7' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
"There are quite a few changes in this release, the most notable of
which is that we've made inode flushing fully asynchronous, and we no
longer block memory reclaim on this.

Furthermore, we have fixed a long-standing bug in the quota code where
soft limit warnings and inode limits were never tracked properly.

Moving further down the line, the reflink control loops have been
redesigned to behave more efficiently; and numerous small bugs have
been fixed (see below). The xattr and quota code have been extensively
refactored in preparation for more new features coming down the line.

Finally, the behavior of DAX between ext4 and xfs has been stabilized,
which gets us a step closer to removing the experimental tag from that
feature.

We have a few new contributors this time around. Welcome, all!

I anticipate a second pull request next week for a few small bugfixes
that have been trickling in, but this is it for big changes.

Summary:

- Fix some btree block pingponging problems when swapping extents

- Redesign the reflink copy loop so that we only run one remapping
operation per transaction. This helps us avoid running out of block
reservation on highly deduped filesystems.

- Take the MMAPLOCK around filemap_map_pages.

- Make inode reclaim fully async so that we avoid stalling processes
on flushing inodes to disk.

- Reduce inode cluster buffer RMW cycles by attaching the buffer to
dirty inodes so we won't let go of the cluster buffer when we know
we're going to need it soon.

- Add some more checks to the realtime bitmap file scrubber.

- Don't trip false lockdep warnings in fs freeze.

- Remove various redundant lines of code.

- Remove unnecessary calls to xfs_perag_{get,put}.

- Preserve I_VERSION state across remounts.

- Fix an unmount hang due to AIL going to sleep with a non-empty
delwri buffer list.

- Fix an error in the inode allocation space reservation macro that
caused regressions in generic/531.

- Fix a potential livelock when dquot flush fails because the dquot
buffer is locked.

- Fix a miscalculation when reserving inode quota that could cause
users to exceed a hardlimit.

- Refactor struct xfs_dquot to use native types for incore fields
instead of abusing the ondisk struct for this purpose. This will
eventually enable proper y2038+ support, but for now it merely
cleans up the quota function declarations.

- Actually increment the quota softlimit warning counter so that soft
failures turn into hard(er) failures when they exceed the softlimit
warning counter limits set by the administrator.

- Split incore dquot state flags into their own field and namespace,
to avoid mixing them with quota type flags.

- Create a new quota type flags namespace so that we can make it
obvious when a quota function takes a quota type (user, group,
project) as an argument.

- Rename the ondisk dquot flags field to type, as that more
accurately represents what we store in it.

- Drop our bespoke memory allocation flags in favor of GFP_*.

- Rearrange the xattr functions so that we no longer mix metadata
updates and transaction management (e.g. rolling complex
transactions) in the same functions. This work will prepare us for
atomic xattr operations (itself a prerequisite for directory
backrefs) in future release cycles.

- Support FS_DAX_FL (aka FS_XFLAG_DAX) via GETFLAGS/SETFLAGS"

* tag 'xfs-5.9-merge-7' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (117 commits)
fs/xfs: Support that ioctl(SETXFLAGS/GETXFLAGS) can set/get inode DAX on XFS.
xfs: Lift -ENOSPC handler from xfs_attr_leaf_addname
xfs: Simplify xfs_attr_node_addname
xfs: Simplify xfs_attr_leaf_addname
xfs: Add helper function xfs_attr_node_removename_rmt
xfs: Add helper function xfs_attr_node_removename_setup
xfs: Add remote block helper functions
xfs: Add helper function xfs_attr_leaf_mark_incomplete
xfs: Add helpers xfs_attr_is_shortform and xfs_attr_set_shortform
xfs: Remove xfs_trans_roll in xfs_attr_node_removename
xfs: Remove unneeded xfs_trans_roll_inode calls
xfs: Add helper function xfs_attr_node_shrink
xfs: Pull up xfs_attr_rmtval_invalidate
xfs: Refactor xfs_attr_rmtval_remove
xfs: Pull up trans roll in xfs_attr3_leaf_clearflag
xfs: Factor out xfs_attr_rmtval_invalidate
xfs: Pull up trans roll from xfs_attr3_leaf_setflag
xfs: Refactor xfs_attr_try_sf_addname
xfs: Split apart xfs_attr_leaf_addname
xfs: Pull up trans handling in xfs_attr3_leaf_flipflags
...

fs/xfs/kmem.c

···
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
-
-void *
-kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
-	int	retries = 0;
-	gfp_t	lflags = kmem_flags_convert(flags);
-	void	*ptr;
-
-	trace_kmem_zone_alloc(kmem_cache_size(zone), flags, _RET_IP_);
-	do {
-		ptr = kmem_cache_alloc(zone, lflags);
-		if (ptr || (flags & KM_MAYFAIL))
-			return ptr;
-		if (!(++retries % 100))
-			xfs_err(NULL,
-		"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
-				current->comm, current->pid,
-				__func__, lflags);
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
-	} while (1);
-}

fs/xfs/kmem.h

···
 #define kmem_zone	kmem_cache
 #define kmem_zone_t	struct kmem_cache
 
-extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t);
-
-static inline void *
-kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
-	return kmem_zone_alloc(zone, flags | KM_ZERO);
-}
-
 static inline struct page *
 kmem_to_page(void *addr)
 {

fs/xfs/libxfs/xfs_ag.c

···
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp);
 	if (error)
 		goto out_agi;
-	pag = xfs_perag_get(mp, agno);
+
+	pag = agi_bp->b_pag;
 
 	/* Fill out form. */
 	memset(ageo, 0, sizeof(*ageo));
···
 	xfs_ag_geom_health(pag, ageo);
 
 	/* Release resources. */
-	xfs_perag_put(pag);
 	xfs_buf_relse(agf_bp);
 out_agi:
 	xfs_buf_relse(agi_bp);

fs/xfs/libxfs/xfs_ag_resv.h

···
 	xfs_perag_put(pag);
 }
 
-static inline void
-xfs_ag_resv_rmapbt_free(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	struct xfs_perag	*pag;
-
-	pag = xfs_perag_get(mp, agno);
-	xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
-	xfs_perag_put(pag);
-}
-
 #endif	/* __XFS_AG_RESV_H__ */

fs/xfs/libxfs/xfs_alloc.c

···
 STATIC int
 xfs_alloc_update_counters(
 	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
 	struct xfs_buf		*agbp,
 	long			len)
 {
 	struct xfs_agf		*agf = agbp->b_addr;
 
-	pag->pagf_freeblks += len;
+	agbp->b_pag->pagf_freeblks += len;
 	be32_add_cpu(&agf->agf_freeblks, len);
 
 	xfs_trans_agblocks_delta(tp, len);
···
 	}
 
 	if (!args->wasfromfl) {
-		error = xfs_alloc_update_counters(args->tp, args->pag,
-						  args->agbp,
+		error = xfs_alloc_update_counters(args->tp, args->agbp,
 						  -((long)(args->len)));
 		if (error)
 			return error;
···
 	enum xfs_ag_resv_type		type)
 {
 	struct xfs_mount		*mp;
-	struct xfs_perag		*pag;
 	struct xfs_btree_cur		*bno_cur;
 	struct xfs_btree_cur		*cnt_cur;
 	xfs_agblock_t			gtbno; /* start of right neighbor */
···
 	/*
 	 * Update the freespace totals in the ag and superblock.
 	 */
-	pag = xfs_perag_get(mp, agno);
-	error = xfs_alloc_update_counters(tp, pag, agbp, len);
-	xfs_ag_resv_free_extent(pag, type, tp, len);
-	xfs_perag_put(pag);
+	error = xfs_alloc_update_counters(tp, agbp, len);
+	xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len);
 	if (error)
 		goto error0;
 
···
 	ASSERT(xfs_bmap_free_item_zone != NULL);
 	ASSERT(oinfo != NULL);
 
-	new = kmem_zone_alloc(xfs_bmap_free_item_zone, 0);
+	new = kmem_cache_alloc(xfs_bmap_free_item_zone,
+			       GFP_KERNEL | __GFP_NOFAIL);
 	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
 	new->xefi_blockcount = 1;
 	new->xefi_oinfo = *oinfo;
···
 	if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp))
 		agf->agf_flfirst = 0;
 
-	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, -1);
 	xfs_trans_agflist_delta(tp, -1);
···
 		pag->pagf_btreeblks++;
 		logflags |= XFS_AGF_BTREEBLKS;
 	}
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(tp, agbp, logflags);
 	*bnop = bno;
···
 	if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp))
 		agf->agf_fllast = 0;
 
-	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, 1);
 	xfs_trans_agflist_delta(tp, 1);
···
 		pag->pagf_btreeblks--;
 		logflags |= XFS_AGF_BTREEBLKS;
 	}
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(tp, agbp, logflags);
 
···
 	ASSERT(!(*bpp)->b_error);
 
 	agf = (*bpp)->b_addr;
-	pag = xfs_perag_get(mp, agno);
+	pag = (*bpp)->b_pag;
 	if (!pag->pagf_init) {
 		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
 		pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
···
 		       be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
 	}
 #endif
-	xfs_perag_put(pag);
 	return 0;
 }
 

fs/xfs/libxfs/xfs_alloc_btree.c

···
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
 	int			btnum = cur->bc_btnum;
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
+	struct xfs_perag	*pag = agbp->b_pag;
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_roots[btnum] = ptr->s;
 	be32_add_cpu(&agf->agf_levels[btnum], inc);
 	pag->pagf_levels[btnum] += inc;
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
 }
···
 	int			reason)
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
 	struct xfs_perag	*pag;
 	__be32			len;
 	int			numrecs;
···
 	}
 
 	agf->agf_longest = len;
-	pag = xfs_perag_get(cur->bc_mp, seqno);
+	pag = cur->bc_ag.agbp->b_pag;
 	pag->pagf_longest = be32_to_cpu(len);
-	xfs_perag_put(pag);
 	xfs_alloc_log_agf(cur->bc_tp, cur->bc_ag.agbp, XFS_AGF_LONGEST);
 }
 
···
 
 	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;

fs/xfs/libxfs/xfs_attr.c

···
 STATIC int xfs_attr_leaf_get(xfs_da_args_t *args);
 STATIC int xfs_attr_leaf_addname(xfs_da_args_t *args);
 STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args);
+STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp);
 
 /*
  * Internal routines when attribute list is more than one block.
···
 STATIC int xfs_attr_node_get(xfs_da_args_t *args);
 STATIC int xfs_attr_node_addname(xfs_da_args_t *args);
 STATIC int xfs_attr_node_removename(xfs_da_args_t *args);
+STATIC int xfs_attr_node_hasname(xfs_da_args_t *args,
+				 struct xfs_da_state **state);
 STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
 STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
 
···
 	struct xfs_da_args	*args)
 {
 
-	struct xfs_mount	*mp = dp->i_mount;
-	int			error, error2;
+	int			error;
+
+	/*
+	 * Build initial attribute list (if required).
+	 */
+	if (dp->i_afp->if_format == XFS_DINODE_FMT_EXTENTS)
+		xfs_attr_shortform_create(args);
 
 	error = xfs_attr_shortform_addname(args);
 	if (error == -ENOSPC)
···
 	if (!error && !(args->op_flags & XFS_DA_OP_NOTIME))
 		xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG);
 
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
+	if (dp->i_mount->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(args->trans);
 
-	error2 = xfs_trans_commit(args->trans);
-	args->trans = NULL;
-	return error ? error : error2;
+	return error;
+}
+
+/*
+ * Check to see if the attr should be upgraded from non-existent or shortform to
+ * single-leaf-block attribute list.
+ */
+static inline bool
+xfs_attr_is_shortform(
+	struct xfs_inode    *ip)
+{
+	return ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL ||
+	       (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS &&
+		ip->i_afp->if_nextents == 0);
+}
+
+/*
+ * Attempts to set an attr in shortform, or converts short form to leaf form if
+ * there is not enough room.  If the attr is set, the transaction is committed
+ * and set to NULL.
+ */
+STATIC int
+xfs_attr_set_shortform(
+	struct xfs_da_args	*args,
+	struct xfs_buf		**leaf_bp)
+{
+	struct xfs_inode	*dp = args->dp;
+	int			error, error2 = 0;
+
+	/*
+	 * Try to add the attr to the attribute list in the inode.
+	 */
+	error = xfs_attr_try_sf_addname(dp, args);
+	if (error != -ENOSPC) {
+		error2 = xfs_trans_commit(args->trans);
+		args->trans = NULL;
+		return error ? error : error2;
+	}
+	/*
+	 * It won't fit in the shortform, transform to a leaf block.  GROT:
+	 * another possible req'mt for a double-split btree op.
+	 */
+	error = xfs_attr_shortform_to_leaf(args, leaf_bp);
+	if (error)
+		return error;
+
+	/*
+	 * Prevent the leaf buffer from being unlocked so that a concurrent AIL
+	 * push cannot grab the half-baked leaf buffer and run into problems
+	 * with the write verifier. Once we're done rolling the transaction we
+	 * can release the hold and add the attr to the leaf.
+	 */
+	xfs_trans_bhold(args->trans, *leaf_bp);
+	error = xfs_defer_finish(&args->trans);
+	xfs_trans_bhold_release(args->trans, *leaf_bp);
+	if (error) {
+		xfs_trans_brelse(args->trans, *leaf_bp);
+		return error;
+	}
+
+	return 0;
 }
 
 /*
···
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf          *leaf_bp = NULL;
-	int			error;
+	int			error = 0;
 
 	/*
-	 * If the attribute list is non-existent or a shortform list,
-	 * upgrade it to a single-leaf-block attribute list.
+	 * If the attribute list is already in leaf format, jump straight to
+	 * leaf handling.  Otherwise, try to add the attribute to the shortform
+	 * list; if there's no room then convert the list to leaf format and try
+	 * again.
 	 */
-	if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL ||
-	    (dp->i_afp->if_format == XFS_DINODE_FMT_EXTENTS &&
-	     dp->i_afp->if_nextents == 0)) {
+	if (xfs_attr_is_shortform(dp)) {
 
 		/*
-		 * Build initial attribute list (if required).
+		 * If the attr was successfully set in shortform, the
+		 * transaction is committed and set to NULL.  Otherwise, is it
+		 * converted from shortform to leaf, and the transaction is
+		 * retained.
 		 */
-		if (dp->i_afp->if_format == XFS_DINODE_FMT_EXTENTS)
-			xfs_attr_shortform_create(args);
+		error = xfs_attr_set_shortform(args, &leaf_bp);
+		if (error || !args->trans)
+			return error;
+	}
 
-		/*
-		 * Try to add the attr to the attribute list in the inode.
-		 */
-		error = xfs_attr_try_sf_addname(dp, args);
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+		error = xfs_attr_leaf_addname(args);
 		if (error != -ENOSPC)
 			return error;
 
 		/*
-		 * It won't fit in the shortform, transform to a leaf block.
-		 * GROT: another possible req'mt for a double-split btree op.
+		 * Promote the attribute list to the Btree format.
 		 */
-		error = xfs_attr_shortform_to_leaf(args, &leaf_bp);
+		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			return error;
 
 		/*
-		 * Prevent the leaf buffer from being unlocked so that a
-		 * concurrent AIL push cannot grab the half-baked leaf
-		 * buffer and run into problems with the write verifier.
-		 * Once we're done rolling the transaction we can release
-		 * the hold and add the attr to the leaf.
+		 * Finish any deferred work items and roll the transaction once
+		 * more.  The goal here is to call node_addname with the inode
+		 * and transaction in the same state (inode locked and joined,
+		 * transaction clean) no matter how we got to this step.
 		 */
-		xfs_trans_bhold(args->trans, leaf_bp);
 		error = xfs_defer_finish(&args->trans);
-		xfs_trans_bhold_release(args->trans, leaf_bp);
-		if (error) {
-			xfs_trans_brelse(args->trans, leaf_bp);
+		if (error)
 			return error;
-		}
+
+		/*
+		 * Commit the current trans (including the inode) and
+		 * start a new one.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			return error;
 	}
 
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
-		error = xfs_attr_leaf_addname(args);
-	else
-		error = xfs_attr_node_addname(args);
+	error = xfs_attr_node_addname(args);
 	return error;
+}
+
+/*
+ * Return EEXIST if attr is found, or ENOATTR if not
+ */
+int
+xfs_has_attr(
+	struct xfs_da_args	*args)
+{
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_buf		*bp = NULL;
+	int			error;
+
+	if (!xfs_inode_hasattr(dp))
+		return -ENOATTR;
+
+	if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) {
+		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
+		return xfs_attr_sf_findname(args, NULL, NULL);
+	}
+
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+		error = xfs_attr_leaf_hasname(args, &bp);
+
+		if (bp)
+			xfs_trans_brelse(args->trans, bp);
+
+		return error;
+	}
+
+	return xfs_attr_node_hasname(args, NULL);
 }
 
 /*
···
 				args->total, 0, quota_flags);
 		if (error)
 			goto out_trans_cancel;
+
+		error = xfs_has_attr(args);
+		if (error == -EEXIST && (args->attr_flags & XATTR_CREATE))
+			goto out_trans_cancel;
+		if (error == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
+			goto out_trans_cancel;
+		if (error != -ENOATTR && error != -EEXIST)
+			goto out_trans_cancel;
+
 		error = xfs_attr_set_args(args);
 		if (error)
 			goto out_trans_cancel;
···
 		if (!args->trans)
 			goto out_unlock;
 	} else {
+		error = xfs_has_attr(args);
+		if (error != -EEXIST)
+			goto out_trans_cancel;
+
 		error = xfs_attr_remove_args(args);
 		if (error)
 			goto out_trans_cancel;
···
  * External routines when attribute list is one block
  *========================================================================*/
 
-/*
- * Add a name to the leaf attribute list structure
- *
- * This leaf block cannot have a "remote" value, we only call this routine
- * if bmap_one_block() says there is only one block (ie: no remote blks).
- */
-STATIC int
-xfs_attr_leaf_addname(
+/* Store info about a remote block */
+STATIC void
+xfs_attr_save_rmt_blk(
 	struct xfs_da_args	*args)
 {
-	struct xfs_inode	*dp;
-	struct xfs_buf		*bp;
-	int			retval, error, forkoff;
+	args->blkno2 = args->blkno;
+	args->index2 = args->index;
+	args->rmtblkno2 = args->rmtblkno;
+	args->rmtblkcnt2 = args->rmtblkcnt;
+	args->rmtvaluelen2 = args->rmtvaluelen;
+}
 
-	trace_xfs_attr_leaf_addname(args);
+/* Set stored info about a remote block */
+STATIC void
+xfs_attr_restore_rmt_blk(
+	struct xfs_da_args	*args)
+{
+	args->blkno = args->blkno2;
+	args->index = args->index2;
+	args->rmtblkno = args->rmtblkno2;
+	args->rmtblkcnt = args->rmtblkcnt2;
+	args->rmtvaluelen = args->rmtvaluelen2;
+}
 
-	/*
-	 * Read the (only) block in the attribute list in.
-	 */
-	dp = args->dp;
-	args->blkno = 0;
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
-	if (error)
-		return error;
+/*
+ * Tries to add an attribute to an inode in leaf form
+ *
+ * This function is meant to execute as part of a delayed operation and leaves
+ * the transaction handling to the caller.  On success the attribute is added
+ * and the inode and transaction are left dirty.  If there is not enough space,
+ * the attr data is converted to node format and -ENOSPC is returned. Caller is
+ * responsible for handling the dirty inode and transaction or adding the attr
+ * in node format.
+ */
+STATIC int
+xfs_attr_leaf_try_add(
+	struct xfs_da_args	*args,
+	struct xfs_buf		*bp)
+{
+	int			retval;
 
 	/*
 	 * Look up the given attribute in the leaf block.  Figure out if
 	 * the given flags produce an error or call for an atomic rename.
 	 */
-	retval = xfs_attr3_leaf_lookup_int(bp, args);
+	retval = xfs_attr_leaf_hasname(args, &bp);
+	if (retval != -ENOATTR && retval != -EEXIST)
+		return retval;
 	if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
 		goto out_brelse;
 	if (retval == -EEXIST) {
···
 
 		/* save the attribute state for later removal*/
 		args->op_flags |= XFS_DA_OP_RENAME;	/* an atomic rename */
-		args->blkno2 = args->blkno;		/* set 2nd entry info*/
-		args->index2 = args->index;
-		args->rmtblkno2 = args->rmtblkno;
-		args->rmtblkcnt2 = args->rmtblkcnt;
-		args->rmtvaluelen2 = args->rmtvaluelen;
+		xfs_attr_save_rmt_blk(args);
 
 		/*
 		 * clear the remote attr state now that it is saved so that the
···
 	}
 
 	/*
-	 * Add the attribute to the leaf block, transitioning to a Btree
-	 * if required.
+	 * Add the attribute to the leaf block
 	 */
-	retval = xfs_attr3_leaf_add(bp, args);
-	if (retval == -ENOSPC) {
-		/*
-		 * Promote the attribute list to the Btree format, then
-		 * Commit that transaction so that the node_addname() call
-		 * can manage its own transactions.
-		 */
-		error = xfs_attr3_leaf_to_node(args);
-		if (error)
-			return error;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
+	return xfs_attr3_leaf_add(bp, args);
 
-		/*
-		 * Commit the current trans (including the inode) and start
-		 * a new one.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
-			return error;
+out_brelse:
+	xfs_trans_brelse(args->trans, bp);
+	return retval;
+}
 
-		/*
-		 * Fob the whole rest of the problem off on the Btree code.
-		 */
-		error = xfs_attr_node_addname(args);
+
+/*
+ * Add a name to the leaf attribute list structure
+ *
+ * This leaf block cannot have a "remote" value, we only call this routine
+ * if bmap_one_block() says there is only one block (ie: no remote blks).
+ */
+STATIC int
+xfs_attr_leaf_addname(
+	struct xfs_da_args	*args)
+{
+	int			error, forkoff;
+	struct xfs_buf		*bp = NULL;
+	struct xfs_inode	*dp = args->dp;
+
+	trace_xfs_attr_leaf_addname(args);
+
+	error = xfs_attr_leaf_try_add(args, bp);
+	if (error)
 		return error;
-	}
 
 	/*
 	 * Commit the transaction that added the attr name so that
···
 			return error;
 	}
 
-	/*
-	 * If this is an atomic rename operation, we must "flip" the
-	 * incomplete flags on the "new" and "old" attribute/value pairs
-	 * so that one disappears and one appears atomically.  Then we
-	 * must remove the "old" attribute/value pair.
-	 */
-	if (args->op_flags & XFS_DA_OP_RENAME) {
-		/*
-		 * In a separate transaction, set the incomplete flag on the
-		 * "old" attr and clear the incomplete flag on the "new" attr.
-		 */
-		error = xfs_attr3_leaf_flipflags(args);
-		if (error)
-			return error;
-
-		/*
-		 * Dismantle the "old" attribute/value pair by removing
-		 * a "remote" value (if it exists).
-		 */
-		args->index = args->index2;
-		args->blkno = args->blkno2;
-		args->rmtblkno = args->rmtblkno2;
-		args->rmtblkcnt = args->rmtblkcnt2;
-		args->rmtvaluelen = args->rmtvaluelen2;
-		if (args->rmtblkno) {
-			error = xfs_attr_rmtval_remove(args);
-			if (error)
-				return error;
-		}
-
-		/*
-		 * Read in the block containing the "old" attr, then
-		 * remove the "old" attr from that block (neat, huh!)
-		 */
-		error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
-					   &bp);
-		if (error)
-			return error;
-
-		xfs_attr3_leaf_remove(bp, args);
-
-		/*
-		 * If the result is small enough, shrink it all into the inode.
-		 */
-		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
-			/* bp is gone due to xfs_da_shrink_inode */
-			if (error)
-				return error;
-			error = xfs_defer_finish(&args->trans);
-			if (error)
-				return error;
-		}
-
-		/*
-		 * Commit the remove and start the next trans in series.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-
-	} else if (args->rmtblkno > 0) {
+	if (!(args->op_flags & XFS_DA_OP_RENAME)) {
 		/*
 		 * Added a "remote" value, just clear the incomplete flag.
 		 */
-		error = xfs_attr3_leaf_clearflag(args);
+		if (args->rmtblkno > 0)
+			error = xfs_attr3_leaf_clearflag(args);
+
+		return error;
 	}
+
+	/*
+	 * If this is an atomic rename operation, we must "flip" the incomplete
+	 * flags on the "new" and "old" attribute/value pairs so that one
+	 * disappears and one appears atomically.  Then we must remove the "old"
+	 * attribute/value pair.
+	 *
+	 * In a separate transaction, set the incomplete flag on the "old" attr
+	 * and clear the incomplete flag on the "new" attr.
+	 */
+
+	error = xfs_attr3_leaf_flipflags(args);
+	if (error)
+		return error;
+	/*
+	 * Commit the flag value change and start the next trans in series.
+	 */
+	error = xfs_trans_roll_inode(&args->trans, args->dp);
+	if (error)
+		return error;
+
+	/*
+	 * Dismantle the "old" attribute/value pair by removing a "remote" value
+	 * (if it exists).
+	 */
+	xfs_attr_restore_rmt_blk(args);
+
+	if (args->rmtblkno) {
+		error = xfs_attr_rmtval_invalidate(args);
+		if (error)
+			return error;
+
+		error = xfs_attr_rmtval_remove(args);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Read in the block containing the "old" attr, then remove the "old"
+	 * attr from that block (neat, huh!)
+	 */
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
+				   &bp);
+	if (error)
+		return error;
+
+	xfs_attr3_leaf_remove(bp, args);
+
+	/*
+	 * If the result is small enough, shrink it all into the inode.
+	 */
+	forkoff = xfs_attr_shortform_allfit(bp, dp);
+	if (forkoff)
+		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+		/* bp is gone due to xfs_da_shrink_inode */
+
 	return error;
-out_brelse:
-	xfs_trans_brelse(args->trans, bp);
-	return retval;
+}
+
+/*
+ * Return EEXIST if attr is found, or ENOATTR if not
+ */
+STATIC int
+xfs_attr_leaf_hasname(
+	struct xfs_da_args	*args,
+	struct xfs_buf		**bp)
+{
+	int                     error = 0;
+
+	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp);
+	if (error)
+		return error;
+
+	error = xfs_attr3_leaf_lookup_int(*bp, args);
+	if (error != -ENOATTR && error != -EEXIST)
+		xfs_trans_brelse(args->trans, *bp);
+
+	return error;
 }
 
 /*
···
 	 * Remove the attribute.
 	 */
 	dp = args->dp;
-	args->blkno = 0;
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
-	if (error)
-		return error;
 
-	error = xfs_attr3_leaf_lookup_int(bp, args);
+	error = xfs_attr_leaf_hasname(args, &bp);
+
 	if (error == -ENOATTR) {
 		xfs_trans_brelse(args->trans, bp);
 		return error;
-	}
+	} else if (error != -EEXIST)
+		return error;
 
 	xfs_attr3_leaf_remove(bp, args);
 
 	/*
 	 * If the result is small enough, shrink it all into the inode.
 	 */
-	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+	forkoff = xfs_attr_shortform_allfit(bp, dp);
+	if (forkoff)
+		return xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
-		if (error)
-			return error;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
-	}
+
 	return 0;
 }
 
···
 
 	trace_xfs_attr_leaf_get(args);
 
-	args->blkno = 0;
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
-	if (error)
-		return error;
+	error = xfs_attr_leaf_hasname(args, &bp);
 
-	error = xfs_attr3_leaf_lookup_int(bp, args);
-	if (error != -EEXIST)  {
+	if (error == -ENOATTR)  {
 		xfs_trans_brelse(args->trans, bp);
 		return error;
-	}
+	} else if (error != -EEXIST)
+		return error;
+
+
 	error = xfs_attr3_leaf_getvalue(bp, args);
 	xfs_trans_brelse(args->trans, bp);
 	return error;
+}
+
+/*
+ * Return EEXIST if attr is found, or ENOATTR if not
+ * statep: If not null is set to point at the found state.  Caller will
+ *         be responsible for freeing the state in this case.
+ */
+STATIC int
+xfs_attr_node_hasname(
+	struct xfs_da_args	*args,
+	struct xfs_da_state	**statep)
+{
+	struct xfs_da_state	*state;
+	int			retval, error;
+
+	state = xfs_da_state_alloc(args);
+	if (statep != NULL)
+		*statep = NULL;
+
+	/*
+	 * Search to see if name exists, and get back a pointer to it.
+	 */
+	error = xfs_da3_node_lookup_int(state, &retval);
+	if (error) {
+		xfs_da_state_free(state);
+		return error;
+	}
+
+	if (statep != NULL)
+		*statep = state;
+	else
+		xfs_da_state_free(state);
+	return retval;
 }
 
 /*========================================================================
···
 	struct xfs_da_state	*state;
 	struct xfs_da_state_blk	*blk;
 	struct xfs_inode	*dp;
-	struct xfs_mount	*mp;
 	int			retval, error;
 
 	trace_xfs_attr_node_addname(args);
···
 	 * Fill in bucket of arguments/results/context to carry around.
 	 */
 	dp = args->dp;
-	mp = dp->i_mount;
 restart:
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = mp;
-
 	/*
 	 * Search to see if name already exists, and get back a pointer
 	 * to where it should go.
 	 */
-	error = xfs_da3_node_lookup_int(state, &retval);
-	if (error)
+	retval = xfs_attr_node_hasname(args, &state);
+	if (retval != -ENOATTR && retval != -EEXIST)
 		goto out;
+
 	blk = &state->path.blk[ state->path.active-1 ];
 	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
 	if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
···
 
 		/* save the attribute state for later removal*/
 		args->op_flags |= XFS_DA_OP_RENAME;	/* atomic rename op */
-		args->blkno2 = args->blkno;		/* set 2nd entry info*/
-		args->index2 = args->index;
-		args->rmtblkno2 = args->rmtblkno;
-		args->rmtblkcnt2 = args->rmtblkcnt;
-		args->rmtvaluelen2 = args->rmtvaluelen;
+		xfs_attr_save_rmt_blk(args);
 
 		/*
 		 * clear the remote attr state now that it is saved so that the
···
 			return error;
 	}
 
-	/*
-	 * If this is an atomic rename operation, we must "flip" the
-	 * incomplete flags on the "new" and "old" attribute/value pairs
-	 * so that one disappears and one appears atomically.  Then we
-	 * must remove the "old" attribute/value pair.
-	 */
-	if (args->op_flags & XFS_DA_OP_RENAME) {
-		/*
-		 * In a separate transaction, set the incomplete flag on the
-		 * "old" attr and clear the incomplete flag on the "new" attr.
-		 */
-		error = xfs_attr3_leaf_flipflags(args);
-		if (error)
-			goto out;
-
-		/*
-		 * Dismantle the "old" attribute/value pair by removing
-		 * a "remote" value (if it exists).
-		 */
-		args->index = args->index2;
-		args->blkno = args->blkno2;
-		args->rmtblkno = args->rmtblkno2;
-		args->rmtblkcnt = args->rmtblkcnt2;
-		args->rmtvaluelen = args->rmtvaluelen2;
-		if (args->rmtblkno) {
-			error = xfs_attr_rmtval_remove(args);
-			if (error)
-				return error;
-		}
-
-		/*
-		 * Re-find the "old" attribute entry after any split ops.
-		 * The INCOMPLETE flag means that we will find the "old"
-		 * attr, not the "new" one.
-		 */
-		args->attr_filter |= XFS_ATTR_INCOMPLETE;
-		state = xfs_da_state_alloc();
-		state->args = args;
-		state->mp = mp;
-		state->inleaf = 0;
-		error = xfs_da3_node_lookup_int(state, &retval);
-		if (error)
-			goto out;
-
-		/*
-		 * Remove the name and update the hashvals in the tree.
-		 */
-		blk = &state->path.blk[ state->path.active-1 ];
-		ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
-		error = xfs_attr3_leaf_remove(blk->bp, args);
-		xfs_da3_fixhashpath(state, &state->path);
-
-		/*
-		 * Check to see if the tree needs to be collapsed.
-		 */
-		if (retval && (state->path.active > 1)) {
-			error = xfs_da3_join(state);
-			if (error)
-				goto out;
-			error = xfs_defer_finish(&args->trans);
-			if (error)
-				goto out;
-		}
-
-		/*
-		 * Commit and start the next trans in the chain.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
-			goto out;
-
-	} else if (args->rmtblkno > 0) {
+	if (!(args->op_flags & XFS_DA_OP_RENAME)) {
 		/*
 		 * Added a "remote" value, just clear the incomplete flag.
 		 */
-		error = xfs_attr3_leaf_clearflag(args);
+		if (args->rmtblkno > 0)
+			error = xfs_attr3_leaf_clearflag(args);
+		retval = error;
+		goto out;
+	}
+
+	/*
+	 * If this is an atomic rename operation, we must "flip" the incomplete
+	 * flags on the "new" and "old" attribute/value pairs so that one
+	 * disappears and one appears atomically.  Then we must remove the "old"
+	 * attribute/value pair.
+	 *
+	 * In a separate transaction, set the incomplete flag on the "old" attr
+	 * and clear the incomplete flag on the "new" attr.
+	 */
+	error = xfs_attr3_leaf_flipflags(args);
+	if (error)
+		goto out;
+	/*
+	 * Commit the flag value change and start the next trans in series
+	 */
+	error = xfs_trans_roll_inode(&args->trans, args->dp);
+	if (error)
+		goto out;
+
+	/*
+	 * Dismantle the "old" attribute/value pair by removing a "remote" value
+	 * (if it exists).
+	 */
+	xfs_attr_restore_rmt_blk(args);
+
+	if (args->rmtblkno) {
+		error = xfs_attr_rmtval_invalidate(args);
+		if (error)
+			return error;
+
+		error = xfs_attr_rmtval_remove(args);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Re-find the "old" attribute entry after any split ops. The INCOMPLETE
+	 * flag means that we will find the "old" attr, not the "new" one.
+	 */
+	args->attr_filter |= XFS_ATTR_INCOMPLETE;
+	state = xfs_da_state_alloc(args);
+	state->inleaf = 0;
+	error = xfs_da3_node_lookup_int(state, &retval);
+	if (error)
+		goto out;
+
+	/*
+	 * Remove the name and update the hashvals in the tree.
+	 */
+	blk = &state->path.blk[state->path.active-1];
+	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
+	error = xfs_attr3_leaf_remove(blk->bp, args);
+	xfs_da3_fixhashpath(state, &state->path);
+
+	/*
+	 * Check to see if the tree needs to be collapsed.
+	 */
+	if (retval && (state->path.active > 1)) {
+		error = xfs_da3_join(state);
 		if (error)
 			goto out;
 	}
···
 	if (error)
 		return error;
 	return retval;
+}
+
+/*
+ * Shrink an attribute from leaf to shortform
+ */
+STATIC int
+xfs_attr_node_shrink(
+	struct xfs_da_args	*args,
+	struct xfs_da_state     *state)
+{
+	struct xfs_inode	*dp = args->dp;
+	int			error, forkoff;
+	struct xfs_buf		*bp;
+
+	/*
+	 * Have to get rid of the copy of this dabuf in the state.
+	 */
+	ASSERT(state->path.active == 1);
+	ASSERT(state->path.blk[0].bp);
+	state->path.blk[0].bp = NULL;
+
+	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+	if (error)
+		return error;
+
+	forkoff = xfs_attr_shortform_allfit(bp, dp);
+	if (forkoff) {
+		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+		/* bp is gone due to xfs_da_shrink_inode */
+	} else
+		xfs_trans_brelse(args->trans, bp);
+
+	return error;
+}
+
+/*
+ * Mark an attribute entry INCOMPLETE and save pointers to the relevant buffers
+ * for later deletion of the entry.
+ */
+STATIC int
+xfs_attr_leaf_mark_incomplete(
+	struct xfs_da_args	*args,
+	struct xfs_da_state	*state)
+{
+	int			error;
+
+	/*
+	 * Fill in disk block numbers in the state structure
+	 * so that we can get the buffers back after we commit
+	 * several transactions in the following calls.
+	 */
+	error = xfs_attr_fillstate(state);
+	if (error)
+		return error;
+
+	/*
+	 * Mark the attribute as INCOMPLETE
+	 */
+	return xfs_attr3_leaf_setflag(args);
+}
+
+/*
+ * Initial setup for xfs_attr_node_removename.  Make sure the attr is there and
+ * the blocks are valid.  Attr keys with remote blocks will be marked
+ * incomplete.
+ */
+STATIC
+int xfs_attr_node_removename_setup(
+	struct xfs_da_args	*args,
+	struct xfs_da_state	**state)
+{
+	int			error;
+
+	error = xfs_attr_node_hasname(args, state);
+	if (error != -EEXIST)
+		return error;
+
+	ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL);
+	ASSERT((*state)->path.blk[(*state)->path.active - 1].magic ==
+		XFS_ATTR_LEAF_MAGIC);
+
+	if (args->rmtblkno > 0) {
+		error = xfs_attr_leaf_mark_incomplete(args, *state);
+		if (error)
+			return error;
+
+		return xfs_attr_rmtval_invalidate(args);
+	}
+
+	return 0;
+}
+
+STATIC int
+xfs_attr_node_remove_rmt(
+	struct xfs_da_args	*args,
+	struct xfs_da_state	*state)
+{
+	int			error = 0;
+
+	error = xfs_attr_rmtval_remove(args);
+	if (error)
+		return error;
+
+	/*
+	 * Refill the state structure with buffers, the prior calls released our
+	 * buffers.
+	 */
+	return xfs_attr_refillstate(state);
 }
 
 /*
···
 {
 	struct xfs_da_state	*state;
 	struct xfs_da_state_blk	*blk;
-	struct xfs_inode	*dp;
-	struct xfs_buf		*bp;
-	int			retval, error, forkoff;
+	int			retval, error;
+	struct xfs_inode	*dp = args->dp;
 
 	trace_xfs_attr_node_removename(args);
 
-	/*
-	 * Tie a string around our finger to remind us where we are.
-	 */
-	dp = args->dp;
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = dp->i_mount;
-
-	/*
-	 * Search to see if name exists, and get back a pointer to it.
-	 */
-	error = xfs_da3_node_lookup_int(state, &retval);
-	if (error || (retval != -EEXIST)) {
-		if (error == 0)
-			error = retval;
+	error = xfs_attr_node_removename_setup(args, &state);
+	if (error)
 		goto out;
-	}
 
 	/*
 	 * If there is an out-of-line value, de-allocate the blocks.
 	 * This is done before we remove the attribute so that we don't
 	 * overflow the maximum size of a transaction and/or hit a deadlock.
 	 */
-	blk = &state->path.blk[ state->path.active-1 ];
-	ASSERT(blk->bp != NULL);
-	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
 	if (args->rmtblkno > 0) {
-		/*
-		 * Fill in disk block numbers in the state structure
-		 * so that we can get the buffers back after we commit
-		 * several transactions in the following calls.
-		 */
-		error = xfs_attr_fillstate(state);
-		if (error)
-			goto out;
-
-		/*
-		 * Mark the attribute as INCOMPLETE, then bunmapi() the
-		 * remote value.
-		 */
-		error = xfs_attr3_leaf_setflag(args);
-		if (error)
-			goto out;
-		error = xfs_attr_rmtval_remove(args);
-		if (error)
-			goto out;
-
-		/*
-		 * Refill the state structure with buffers, the prior calls
-		 * released our buffers.
-		 */
-		error = xfs_attr_refillstate(state);
+		error = xfs_attr_node_remove_rmt(args, state);
 		if (error)
 			goto out;
 	}
···
 	/*
 	 * If the result is small enough, push it all into the inode.
 	 */
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
-		/*
-		 * Have to get rid of the copy of this dabuf in the state.
-		 */
-		ASSERT(state->path.active == 1);
-		ASSERT(state->path.blk[0].bp);
-		state->path.blk[0].bp = NULL;
-
-		error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
-		if (error)
-			goto out;
-
-		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
-			/* bp is gone due to xfs_da_shrink_inode */
-			if (error)
-				goto out;
-			error = xfs_defer_finish(&args->trans);
-			if (error)
-				goto out;
-		} else
-			xfs_trans_brelse(args->trans, bp);
-	}
-	error = 0;
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+		error = xfs_attr_node_shrink(args, state);
 
 out:
-	xfs_da_state_free(state);
+	if (state)
+		xfs_da_state_free(state);
 	return error;
 }
 
···
  * Returns 0 on successful retrieval, otherwise an error.
  */
 STATIC int
-xfs_attr_node_get(xfs_da_args_t *args)
+xfs_attr_node_get(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	int error, retval;
-	int i;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	int			i;
+	int			error;
 
 	trace_xfs_attr_node_get(args);
-
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = args->dp->i_mount;
 
 	/*
 	 * Search to see if name exists, and get back a pointer to it.
 	 */
-	error = xfs_da3_node_lookup_int(state, &retval);
-	if (error) {
-		retval = error;
-		goto out_release;
-	}
-	if (retval != -EEXIST)
+	error = xfs_attr_node_hasname(args, &state);
+	if (error != -EEXIST)
 		goto out_release;
 
 	/*
 	 * Get the value, local or "remote"
 	 */
 	blk = &state->path.blk[state->path.active - 1];
-	retval = xfs_attr3_leaf_getvalue(blk->bp, args);
+	error = xfs_attr3_leaf_getvalue(blk->bp, args);
 
 	/*
 	 * If not in a transaction, we have to release all the buffers.
 	 */
 out_release:
-	for (i = 0; i < state->path.active; i++) {
+	for (i = 0; state != NULL && i < state->path.active; i++) {
 		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 
-	xfs_da_state_free(state);
-	return retval;
+	if (state)
+		xfs_da_state_free(state);
+	return error;
 }
 
 /* Returns true if the attribute entry name is valid. */

fs/xfs/libxfs/xfs_attr.h

···
 int xfs_attr_get(struct xfs_da_args *args);
 int xfs_attr_set(struct xfs_da_args *args);
 int xfs_attr_set_args(struct xfs_da_args *args);
+int xfs_has_attr(struct xfs_da_args *args);
 int xfs_attr_remove_args(struct xfs_da_args *args);
 bool xfs_attr_namecheck(const void *name, size_t length);
 

fs/xfs/libxfs/xfs_attr_leaf.c

···
 }
 
 /*
+ * Return -EEXIST if attr is found, or -ENOATTR if not
+ * args:  args containing attribute name and namelen
+ * sfep:  If not null, pointer will be set to the last attr entry found on
+	  -EEXIST.  On -ENOATTR pointer is left at the last entry in the list
+ * basep: If not null, pointer is set to the byte offset of the entry in the
+ *	  list on -EEXIST.  On -ENOATTR, pointer is left at the byte offset of
+ *	  the last entry in the list
+ */
+int
+xfs_attr_sf_findname(
+	struct xfs_da_args	 *args,
+	struct xfs_attr_sf_entry **sfep,
+	unsigned int		 *basep)
+{
+	struct xfs_attr_shortform *sf;
+	struct xfs_attr_sf_entry *sfe;
+	unsigned int		base = sizeof(struct xfs_attr_sf_hdr);
+	int			size = 0;
+	int			end;
+	int			i;
+
+	sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
+	sfe = &sf->list[0];
+	end = sf->hdr.count;
+	for (i = 0; i < end; sfe = XFS_ATTR_SF_NEXTENTRY(sfe),
+			     base += size, i++) {
+		size = XFS_ATTR_SF_ENTSIZE(sfe);
+		if (!xfs_attr_match(args, sfe->namelen, sfe->nameval,
+				    sfe->flags))
+			continue;
+		break;
+	}
+
+	if (sfep != NULL)
+		*sfep = sfe;
+
+	if (basep != NULL)
+		*basep = base;
+
+	if (i == end)
+		return -ENOATTR;
+	return -EEXIST;
+}
+
+/*
  * Add a name/value pair to the shortform attribute list.
  * Overflow from the inode has already been checked for.
  */
 void
-xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
+xfs_attr_shortform_add(
+	struct xfs_da_args		*args,
+	int				forkoff)
 {
-	xfs_attr_shortform_t *sf;
-	xfs_attr_sf_entry_t *sfe;
-	int i, offset, size;
-	xfs_mount_t *mp;
-	xfs_inode_t *dp;
-	struct xfs_ifork *ifp;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	int				offset, size;
+	struct xfs_mount		*mp;
+	struct xfs_inode		*dp;
+	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_add(args);
 
···
 	ifp = dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
 	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count; sfe = XFS_ATTR_SF_NEXTENTRY(sfe), i++) {
-		ASSERT(!xfs_attr_match(args, sfe->namelen, sfe->nameval,
-			sfe->flags));
-	}
+	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
+		ASSERT(0);
 
 	offset = (char *)sfe - (char *)sf;
 	size = XFS_ATTR_SF_ENTSIZE_BYNAME(args->namelen, args->valuelen);
···
  * Remove an attribute from the shortform attribute list structure.
  */
 int
-xfs_attr_shortform_remove(xfs_da_args_t *args)
+xfs_attr_shortform_remove(
+	struct xfs_da_args		*args)
 {
-	xfs_attr_shortform_t *sf;
-	xfs_attr_sf_entry_t *sfe;
-	int base, size=0, end, totsize, i;
-	xfs_mount_t *mp;
-	xfs_inode_t *dp;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	int				size = 0, end, totsize;
+	unsigned int			base;
+	struct xfs_mount		*mp;
+	struct xfs_inode		*dp;
+	int				error;
 
 	trace_xfs_attr_sf_remove(args);
 
 	dp = args->dp;
 	mp = dp->i_mount;
-	base = sizeof(xfs_attr_sf_hdr_t);
 	sf = (xfs_attr_shortform_t *)dp->i_afp->if_u1.if_data;
-	sfe = &sf->list[0];
-	end = sf->hdr.count;
-	for (i = 0; i < end; sfe = XFS_ATTR_SF_NEXTENTRY(sfe),
-					base += size, i++) {
-		size = XFS_ATTR_SF_ENTSIZE(sfe);
-		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				sfe->flags))
-			break;
-	}
-	if (i == end)
-		return -ENOATTR;
+
+	error = xfs_attr_sf_findname(args, &sfe, &base);
+	if (error != -EEXIST)
+		return error;
+	size = XFS_ATTR_SF_ENTSIZE(sfe);
 
 	/*
 	 * Fix up the attribute fork data, covering the hole
···
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
 
-	/*
-	 * Commit the flag value change and start the next trans in series.
-	 */
-	return xfs_trans_roll_inode(&args->trans, args->dp);
+	return 0;
 }
 
 /*
···
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
 
-	/*
-	 * Commit the flag value change and start the next trans in series.
-	 */
-	return xfs_trans_roll_inode(&args->trans, args->dp);
+	return 0;
 }
 
 /*
···
 			 XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt)));
 	}
 
-	/*
-	 * Commit the flag value change and start the next trans in series.
-	 */
-	error = xfs_trans_roll_inode(&args->trans, args->dp);
-
-	return error;
+	return 0;
 }

fs/xfs/libxfs/xfs_attr_leaf.h

···
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args,
 			struct xfs_buf **leaf_bp);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
+int	xfs_attr_sf_findname(struct xfs_da_args *args,
+			     struct xfs_attr_sf_entry **sfep,
+			     unsigned int *basep);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
 xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);

fs/xfs/libxfs/xfs_attr_remote.c

···
 }
 
 /*
- * Write the value associated with an attribute into the out-of-line buffer
- * that we have defined for it.
+ * Find a "hole" in the attribute address space large enough for us to drop the
+ * new attribute's value into
  */
-int
-xfs_attr_rmtval_set(
+STATIC int
+xfs_attr_rmt_find_hole(
 	struct xfs_da_args	*args)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
-	struct xfs_bmbt_irec	map;
-	xfs_dablk_t		lblkno;
-	xfs_fileoff_t		lfileoff = 0;
-	uint8_t			*src = args->value;
-	int			blkcnt;
-	int			valuelen;
-	int			nmap;
 	int			error;
-	int			offset = 0;
-
-	trace_xfs_attr_rmtval_set(args);
+	int			blkcnt;
+	xfs_fileoff_t		lfileoff = 0;
 
 	/*
-	 * Find a "hole" in the attribute address space large enough for
-	 * us to drop the new attribute's value into. Because CRC enable
-	 * attributes have headers, we can't just do a straight byte to FSB
-	 * conversion and have to take the header space into account.
+	 * Because CRC enable attributes have headers, we can't just do a
+	 * straight byte to FSB conversion and have to take the header space
+	 * into account.
 	 */
 	blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
 	error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
···
 	if (error)
 		return error;
 
-	args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
+	args->rmtblkno = (xfs_dablk_t)lfileoff;
 	args->rmtblkcnt = blkcnt;
 
-	/*
-	 * Roll through the "value", allocating blocks on disk as required.
-	 */
-	while (blkcnt > 0) {
-		/*
-		 * Allocate a single extent, up to the size of the value.
-		 *
-		 * Note that we have to consider this a data allocation as we
-		 * write the remote attribute without logging the contents.
-		 * Hence we must ensure that we aren't using blocks that are on
-		 * the busy list so that we don't overwrite blocks which have
-		 * recently been freed but their transactions are not yet
-		 * committed to disk. If we overwrite the contents of a busy
-		 * extent and then crash then the block may not contain the
-		 * correct metadata after log recovery occurs.
-		 */
-		nmap = 1;
-		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
-				  &nmap);
-		if (error)
-			return error;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
+	return 0;
+}
 
-		ASSERT(nmap == 1);
-		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
-		       (map.br_startblock != HOLESTARTBLOCK));
-		lblkno += map.br_blockcount;
-		blkcnt -= map.br_blockcount;
-
-		/*
-		 * Start the next trans in the chain.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
-			return error;
-	}
+STATIC int
+xfs_attr_rmtval_set_value(
+	struct xfs_da_args	*args)
+{
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_bmbt_irec	map;
+	xfs_dablk_t		lblkno;
+	uint8_t			*src = args->value;
+	int			blkcnt;
+	int			valuelen;
+	int			nmap;
+	int			error;
+	int			offset = 0;
 
 	/*
 	 * Roll through the "value", copying the attribute value to the
···
 }
 
 /*
+ * Write the value associated with an attribute into the out-of-line buffer
+ * that we have defined for it.
+ */
+int
+xfs_attr_rmtval_set(
+	struct xfs_da_args	*args)
+{
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_bmbt_irec	map;
+	xfs_dablk_t		lblkno;
+	int			blkcnt;
+	int			nmap;
+	int			error;
+
+	trace_xfs_attr_rmtval_set(args);
+
+	error = xfs_attr_rmt_find_hole(args);
+	if (error)
+		return error;
+
+	blkcnt = args->rmtblkcnt;
+	lblkno = (xfs_dablk_t)args->rmtblkno;
+	/*
+	 * Roll through the "value", allocating blocks on disk as required.
+	 */
+	while (blkcnt > 0) {
+		/*
+		 * Allocate a single extent, up to the size of the value.
+		 *
+		 * Note that we have to consider this a data allocation as we
+		 * write the remote attribute without logging the contents.
+		 * Hence we must ensure that we aren't using blocks that are on
+		 * the busy list so that we don't overwrite blocks which have
+		 * recently been freed but their transactions are not yet
+		 * committed to disk. If we overwrite the contents of a busy
+		 * extent and then crash then the block may not contain the
+		 * correct metadata after log recovery occurs.
+		 */
+		nmap = 1;
+		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
+				  &nmap);
+		if (error)
+			return error;
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			return error;
+
+		ASSERT(nmap == 1);
+		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
+		       (map.br_startblock != HOLESTARTBLOCK));
+		lblkno += map.br_blockcount;
+		blkcnt -= map.br_blockcount;
+
+		/*
+		 * Start the next trans in the chain.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			return error;
+	}
+
+	return xfs_attr_rmtval_set_value(args);
+}
+
+/*
  * Remove the value associated with an attribute by deleting the
  * out-of-line buffer that it is stored on.
  */
 int
-xfs_attr_rmtval_remove(
+xfs_attr_rmtval_invalidate(
 	struct xfs_da_args	*args)
 {
 	xfs_dablk_t		lblkno;
 	int			blkcnt;
 	int			error;
-	int			done;
-
-	trace_xfs_attr_rmtval_remove(args);
 
 	/*
 	 * Roll through the "value", invalidating the attribute value's blocks.
···
 		lblkno += map.br_blockcount;
 		blkcnt -= map.br_blockcount;
 	}
+	return 0;
+}
+
+/*
+ * Remove the value associated with an attribute by deleting the
+ * out-of-line buffer that it is stored on.
+ */
+int
+xfs_attr_rmtval_remove(
+	struct xfs_da_args      *args)
+{
+	int			error;
+	int			retval;
+
+	trace_xfs_attr_rmtval_remove(args);
 
 	/*
 	 * Keep de-allocating extents until the remote-value region is gone.
 	 */
-	lblkno = args->rmtblkno;
-	blkcnt = args->rmtblkcnt;
-	done = 0;
-	while (!done) {
-		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
-				    XFS_BMAPI_ATTRFORK, 1, &done);
-		if (error)
-			return error;
-		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
+	do {
+		retval = __xfs_attr_rmtval_remove(args);
+		if (retval && retval != -EAGAIN)
+			return retval;
 
 		/*
 		 * Close out trans and start the next one in the chain.
···
 		error = xfs_trans_roll_inode(&args->trans, args->dp);
 		if (error)
 			return error;
-	}
+	} while (retval == -EAGAIN);
+
 	return 0;
+}
+
+/*
+ * Remove the value associated with an attribute by deleting the out-of-line
+ * buffer that it is stored on. Returns EAGAIN for the caller to refresh the
+ * transaction and re-call the function
+ */
+int
+__xfs_attr_rmtval_remove(
+	struct xfs_da_args	*args)
+{
+	int			error, done;
+
+	/*
+	 * Unmap value blocks for this attr.
+	 */
+	error = xfs_bunmapi(args->trans, args->dp, args->rmtblkno,
+			    args->rmtblkcnt, XFS_BMAPI_ATTRFORK, 1, &done);
+	if (error)
+		return error;
+
+	error = xfs_defer_finish(&args->trans);
+	if (error)
+		return error;
+
+	if (!done)
+		return -EAGAIN;
+
+	return error;
 }

fs/xfs/libxfs/xfs_attr_remote.h

···
 int xfs_attr_rmtval_remove(struct xfs_da_args *args);
 int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
 		xfs_buf_flags_t incore_flags);
-
+int xfs_attr_rmtval_invalidate(struct xfs_da_args *args);
+int __xfs_attr_rmtval_remove(struct xfs_da_args *args);
 #endif /* __XFS_ATTR_REMOTE_H__ */

fs/xfs/libxfs/xfs_bmap.c

···
 #endif
 	ASSERT(xfs_bmap_free_item_zone != NULL);
 
-	new = kmem_zone_alloc(xfs_bmap_free_item_zone, 0);
+	new = kmem_cache_alloc(xfs_bmap_free_item_zone,
+			       GFP_KERNEL | __GFP_NOFAIL);
 	new->xefi_startblock = bno;
 	new->xefi_blockcount = (xfs_extlen_t)len;
 	if (oinfo)
···
 	if (error)
 		goto trans_cancel;
 	ASSERT(ip->i_afp == NULL);
-	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, 0);
+
+	ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone,
+				      GFP_KERNEL | __GFP_NOFAIL);
+
 	ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;

fs/xfs/libxfs/xfs_bmap.h

···
 	{ BMAP_ATTRFORK,	"ATTR" }, \
 	{ BMAP_COWFORK,		"COW" }
 
+/* Return true if the extent is an allocated extent, written or not. */
+static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec)
+{
+	return irec->br_startblock != HOLESTARTBLOCK &&
+		irec->br_startblock != DELAYSTARTBLOCK &&
+		!isnullstartblock(irec->br_startblock);
+}
 
 /*
  * Return true if the extent is a real, allocated extent, or false if it is  a
  * delayed allocation, and unwritten extent or a hole.
  */
-static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec)
+static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
 {
-	return irec->br_state != XFS_EXT_UNWRITTEN &&
-		irec->br_startblock != HOLESTARTBLOCK &&
-		irec->br_startblock != DELAYSTARTBLOCK &&
-		!isnullstartblock(irec->br_startblock);
+	return xfs_bmap_is_real_extent(irec) &&
+	       irec->br_state != XFS_EXT_UNWRITTEN;
 }
 
 /*

fs/xfs/libxfs/xfs_bmap_btree.c

···
 	struct xfs_btree_cur	*cur;
 	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;

fs/xfs/libxfs/xfs_btree_staging.h

···
 	unsigned int		af_blocks;
 };
 
-/* Cursor interactions with with fake roots for AG-rooted btrees. */
+/* Cursor interactions with fake roots for AG-rooted btrees. */
 void xfs_btree_stage_afakeroot(struct xfs_btree_cur *cur,
 		struct xbtree_afakeroot *afake);
 void xfs_btree_commit_afakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
···
 	unsigned int		if_extents;
 };
 
-/* Cursor interactions with with fake roots for inode-rooted btrees. */
+/* Cursor interactions with fake roots for inode-rooted btrees. */
 void xfs_btree_stage_ifakeroot(struct xfs_btree_cur *cur,
 		struct xbtree_ifakeroot *ifake,
 		struct xfs_btree_ops **new_ops);
···
 
 	/*
 	 * Number of free records to leave in each leaf block.  If the caller
-	 * sets this to -1, the slack value will be calculated to be be halfway
+	 * sets this to -1, the slack value will be calculated to be halfway
 	 * between maxrecs and minrecs.  This typically leaves the block 75%
 	 * full.  Note that slack values are not enforced on inode root blocks.
 	 */

fs/xfs/libxfs/xfs_da_btree.c

···
  * Allocate a dir-state structure.
  * We don't put them on the stack since they're large.
  */
-xfs_da_state_t *
-xfs_da_state_alloc(void)
+struct xfs_da_state *
+xfs_da_state_alloc(
+	struct xfs_da_args	*args)
 {
-	return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
+	struct xfs_da_state	*state;
+
+	state = kmem_cache_zalloc(xfs_da_state_zone, GFP_NOFS | __GFP_NOFAIL);
+	state->args = args;
+	state->mp = args->dp->i_mount;
+	return state;
 }
 
 /*

fs/xfs/libxfs/xfs_da_btree.h

···
 				const unsigned char *name, int len);
 
 
-xfs_da_state_t *xfs_da_state_alloc(void);
+struct xfs_da_state *xfs_da_state_alloc(struct xfs_da_args *args);
 void xfs_da_state_free(xfs_da_state_t *state);
 
 void	xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,

fs/xfs/libxfs/xfs_dir2_node.c

···
 	/*
 	 * Allocate and initialize the state (btree cursor).
 	 */
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = args->dp->i_mount;
+	state = xfs_da_state_alloc(args);
 	/*
 	 * Look up the name.  We're not supposed to find it, but
 	 * this gives us the insertion point.
···
 	/*
 	 * Allocate and initialize the btree cursor.
 	 */
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = args->dp->i_mount;
+	state = xfs_da_state_alloc(args);
+
 	/*
 	 * Fill in the path to the entry in the cursor.
 	 */
···
 	/*
 	 * Allocate and initialize the btree cursor.
 	 */
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = args->dp->i_mount;
+	state = xfs_da_state_alloc(args);
 
 	/* Look up the entry we're deleting, set up the cursor. */
 	error = xfs_da3_node_lookup_int(state, &rval);
···
 	/*
 	 * Allocate and initialize the btree cursor.
 	 */
-	state = xfs_da_state_alloc();
-	state->args = args;
-	state->mp = args->dp->i_mount;
+	state = xfs_da_state_alloc(args);
 
 	/*
 	 * We have to save new inode number and ftype since

fs/xfs/libxfs/xfs_dquot_buf.c

···
 xfs_dquot_verify(
 	struct xfs_mount	*mp,
 	struct xfs_disk_dquot	*ddq,
-	xfs_dqid_t		id,
-	uint			type)	/* used only during quotacheck */
+	xfs_dqid_t		id)	/* used only during quotacheck */
 {
+	__u8			ddq_type;
+
 	/*
 	 * We can encounter an uninitialized dquot buffer for 2 reasons:
 	 * 1. If we crash while deleting the quotainode(s), and those blks got
···
 	if (ddq->d_version != XFS_DQUOT_VERSION)
 		return __this_address;
 
-	if (type && ddq->d_flags != type)
+	if (ddq->d_type & ~XFS_DQTYPE_ANY)
 		return __this_address;
-	if (ddq->d_flags != XFS_DQ_USER &&
-	    ddq->d_flags != XFS_DQ_PROJ &&
-	    ddq->d_flags != XFS_DQ_GROUP)
+	ddq_type = ddq->d_type & XFS_DQTYPE_REC_MASK;
+	if (ddq_type != XFS_DQTYPE_USER &&
+	    ddq_type != XFS_DQTYPE_PROJ &&
+	    ddq_type != XFS_DQTYPE_GROUP)
 		return __this_address;
 
 	if (id != -1 && id != be32_to_cpu(ddq->d_id))
···
 xfs_dqblk_verify(
 	struct xfs_mount	*mp,
 	struct xfs_dqblk	*dqb,
-	xfs_dqid_t	 	id,
-	uint		 	type)	/* used only during quotacheck */
+	xfs_dqid_t		id)	/* used only during quotacheck */
 {
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
 	    !uuid_equal(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid))
 		return __this_address;
 
-	return xfs_dquot_verify(mp, &dqb->dd_diskdq, id, type);
+	return xfs_dquot_verify(mp, &dqb->dd_diskdq, id);
 }
 
 /*
···
 	struct xfs_mount	*mp,
 	struct xfs_dqblk	*dqb,
 	xfs_dqid_t		id,
-	uint			type)
+	xfs_dqtype_t		type)
 {
 	/*
 	 * Typically, a repair is only requested by quotacheck.
···
 
 	dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
 	dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION;
-	dqb->dd_diskdq.d_flags = type;
+	dqb->dd_diskdq.d_type = type;
 	dqb->dd_diskdq.d_id = cpu_to_be32(id);
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
···
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		fa = xfs_dqblk_verify(mp, &dqb[i], id + i, 0);
+		fa = xfs_dqblk_verify(mp, &dqb[i], id + i);
 		if (fa) {
 			if (!readahead)
 				xfs_buf_verifier_error(bp, -EFSCORRUPTED,

fs/xfs/libxfs/xfs_format.h

···
 #define XFS_DQUOT_MAGIC		0x4451		/* 'DQ' */
 #define XFS_DQUOT_VERSION	(uint8_t)0x01	/* latest version number */
 
+#define XFS_DQTYPE_USER		0x01		/* user dquot record */
+#define XFS_DQTYPE_PROJ		0x02		/* project dquot record */
+#define XFS_DQTYPE_GROUP	0x04		/* group dquot record */
+
+/* bitmask to determine if this is a user/group/project dquot */
+#define XFS_DQTYPE_REC_MASK	(XFS_DQTYPE_USER | \
+				 XFS_DQTYPE_PROJ | \
+				 XFS_DQTYPE_GROUP)
+
+#define XFS_DQTYPE_ANY		(XFS_DQTYPE_REC_MASK)
+
 /*
- * This is the main portion of the on-disk representation of quota
- * information for a user. This is the q_core of the struct xfs_dquot that
- * is kept in kernel memory. We pad this with some more expansion room
- * to construct the on disk structure.
+ * This is the main portion of the on-disk representation of quota information
+ * for a user.  We pad this with some more expansion room to construct the on
+ * disk structure.
  */
 struct xfs_disk_dquot {
 	__be16		d_magic;	/* dquot magic = XFS_DQUOT_MAGIC */
 	__u8		d_version;	/* dquot version */
-	__u8		d_flags;	/* XFS_DQ_USER/PROJ/GROUP */
+	__u8		d_type;		/* XFS_DQTYPE_USER/PROJ/GROUP */
 	__be32		d_id;		/* user,project,group id */
 	__be64		d_blk_hardlimit;/* absolute limit on disk blks */
 	__be64		d_blk_softlimit;/* preferred limit on disk blks */
···
 } xfs_dqblk_t;
 
 #define XFS_DQUOT_CRC_OFF	offsetof(struct xfs_dqblk, dd_crc)
+
+/*
+ * This defines the unit of allocation of dquots.
+ *
+ * Currently, it is just one file system block, and a 4K blk contains 30
+ * (136 * 30 = 4080) dquots. It's probably not worth trying to make
+ * this more dynamic.
+ *
+ * However, if this number is changed, we have to make sure that we don't
+ * implicitly assume that we do allocations in chunks of a single filesystem
+ * block in the dquot/xqm code.
+ *
+ * This is part of the ondisk format because the structure size is not a power
+ * of two, which leaves slack at the end of the disk block.
+ */
+#define XFS_DQUOT_CLUSTER_SIZE_FSB	(xfs_filblks_t)1
 
 /*
  * Remote symlink format and access functions.

fs/xfs/libxfs/xfs_ialloc.c

···
 	 */
 	be32_add_cpu(&agi->agi_count, newlen);
 	be32_add_cpu(&agi->agi_freecount, newlen);
-	pag = xfs_perag_get(args.mp, agno);
+	pag = agbp->b_pag;
 	pag->pagi_freecount += newlen;
 	pag->pagi_count += newlen;
-	xfs_perag_put(pag);
 	agi->agi_newino = cpu_to_be32(newino);
 
 	/*
···
 	xfs_agnumber_t		agno = be32_to_cpu(agi->agi_seqno);
 	xfs_agnumber_t		pagno = XFS_INO_TO_AGNO(mp, parent);
 	xfs_agino_t		pagino = XFS_INO_TO_AGINO(mp, parent);
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = agbp->b_pag;
 	struct xfs_btree_cur	*cur, *tcur;
 	struct xfs_inobt_rec_incore rec, trec;
 	xfs_ino_t		ino;
···
 	int			offset;
 	int			i, j;
 	int			searchdistance = 10;
-
-	pag = xfs_perag_get(mp, agno);
 
 	ASSERT(pag->pagi_init);
 	ASSERT(pag->pagi_inodeok);
···
 
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
-	xfs_perag_put(pag);
 	*inop = ino;
 	return 0;
 error1:
 	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
 error0:
 	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_perag_put(pag);
 	return error;
 }
 
···
 	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
 	xfs_agnumber_t			pagno = XFS_INO_TO_AGNO(mp, parent);
 	xfs_agino_t			pagino = XFS_INO_TO_AGINO(mp, parent);
-	struct xfs_perag		*pag;
 	struct xfs_btree_cur		*cur;	/* finobt cursor */
 	struct xfs_btree_cur		*icur;	/* inobt cursor */
 	struct xfs_inobt_rec_incore	rec;
···
 
 	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
 		return xfs_dialloc_ag_inobt(tp, agbp, parent, inop);
-
-	pag = xfs_perag_get(mp, agno);
 
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
···
 	 */
 	be32_add_cpu(&agi->agi_freecount, -1);
 	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
-	pag->pagi_freecount--;
+	agbp->b_pag->pagi_freecount--;
 
 	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
 
···
 
 	xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	xfs_perag_put(pag);
 	*inop = ino;
 	return 0;
 
···
 	xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
 error_cur:
 	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_perag_put(pag);
 	return error;
 }
 
···
 {
 	struct xfs_agi			*agi = agbp->b_addr;
 	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
-	struct xfs_perag		*pag;
 	struct xfs_btree_cur		*cur;
 	struct xfs_inobt_rec_incore	rec;
 	int				ilen;
···
 	if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
 	    rec.ir_free == XFS_INOBT_ALL_FREE &&
 	    mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
+		struct xfs_perag	*pag = agbp->b_pag;
+
 		xic->deleted = true;
 		xic->first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino);
 		xic->alloc = xfs_inobt_irec_to_allocmask(&rec);
···
 		be32_add_cpu(&agi->agi_count, -ilen);
 		be32_add_cpu(&agi->agi_freecount, -(ilen - 1));
 		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
-		pag = xfs_perag_get(mp, agno);
 		pag->pagi_freecount -= ilen - 1;
 		pag->pagi_count -= ilen;
-		xfs_perag_put(pag);
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen);
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));
 
···
 		 */
 		be32_add_cpu(&agi->agi_freecount, 1);
 		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
-		pag = xfs_perag_get(mp, agno);
-		pag->pagi_freecount++;
-		xfs_perag_put(pag);
+		agbp->b_pag->pagi_freecount++;
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, 1);
 	}
 
···
 		return error;
 
 	agi = (*bpp)->b_addr;
-	pag = xfs_perag_get(mp, agno);
+	pag = (*bpp)->b_pag;
 	if (!pag->pagi_init) {
 		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
 		pag->pagi_count = be32_to_cpu(agi->agi_count);
···
 	 */
 	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
 		XFS_FORCED_SHUTDOWN(mp));
-	xfs_perag_put(pag);
 	return 0;
 }
 

fs/xfs/libxfs/xfs_ialloc_btree.c

···
 {
 	struct xfs_btree_cur	*cur;
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	cur->bc_btnum = btnum;

fs/xfs/libxfs/xfs_inode_buf.c

···
 #include <linux/iversion.h>
 
 /*
- * Check that none of the inode's in the buffer have a next
- * unlinked field of 0.
- */
-#if defined(DEBUG)
-void
-xfs_inobp_check(
-	xfs_mount_t	*mp,
-	xfs_buf_t	*bp)
-{
-	int		i;
-	xfs_dinode_t	*dip;
-
-	for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) {
-		dip = xfs_buf_offset(bp, i * mp->m_sb.sb_inodesize);
-		if (!dip->di_next_unlinked)  {
-			xfs_alert(mp,
-	"Detected bogus zero next_unlinked field in inode %d buffer 0x%llx.",
-				i, (long long)bp->b_bn);
-		}
-	}
-}
-#endif
-
-/*
  * If we are doing readahead on an inode buffer, we might be in log recovery
  * reading an inode allocation buffer that hasn't yet been replayed, and hence
  * has not had the inode cores stamped into it. Hence for readahead, the buffer
···
  * If the readahead buffer is invalid, we need to mark it with an error and
  * clear the DONE status of the buffer so that a followup read will re-read it
  * from disk. We don't report the error otherwise to avoid warnings during log
- * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
+ * recovery and we don't get unnecessary panics on debug kernels. We use EIO here
  * because all we want to do is say readahead failed; there is no-one to report
  * the error to, so this will distinguish it from a non-ra verifier failure.
- * Changes to this readahead error behavour also need to be reflected in
+ * Changes to this readahead error behaviour also need to be reflected in
  * xfs_dquot_buf_readahead_verify().
  */
 static void
···
 	}
 
 	*bpp = bp;
-	*dipp = xfs_buf_offset(bp, imap->im_boffset);
+	if (dipp)
+		*dipp = xfs_buf_offset(bp, imap->im_boffset);
 	return 0;
 }
 
···
 	/*
 	 * First get the permanent information that is needed to allocate an
 	 * inode. If the inode is unused, mode is zero and we shouldn't mess
-	 * with the unitialized part of it.
+	 * with the uninitialized part of it.
 	 */
 	to->di_flushiter = be16_to_cpu(from->di_flushiter);
 	inode->i_generation = be32_to_cpu(from->di_gen);

fs/xfs/libxfs/xfs_inode_buf.h

···
 void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
 			       struct xfs_dinode *to);
 
-#if defined(DEBUG)
-void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
-#else
-#define	xfs_inobp_check(mp, bp)
-#endif /* DEBUG */
-
 xfs_failaddr_t xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
 			   struct xfs_dinode *dip);
 xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp,

fs/xfs/libxfs/xfs_inode_fork.c

···
 	 * Initialize the extent count early, as the per-format routines may
 	 * depend on it.
 	 */
-	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_NOFS);
+	ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
 	ip->i_afp->if_format = dip->di_aformat;
 	if (unlikely(ip->i_afp->if_format == 0)) /* pre IRIX 6.2 file system */
 		ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
···
 	if (ip->i_cowfp)
 		return;
 
-	ip->i_cowfp = kmem_zone_zalloc(xfs_ifork_zone,
-				       KM_NOFS);
+	ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone,
+				       GFP_NOFS | __GFP_NOFAIL);
 	ip->i_cowfp->if_flags = XFS_IFEXTENTS;
 	ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
 }

fs/xfs/libxfs/xfs_quota_defs.h

···
 typedef uint64_t	xfs_qcnt_t;
 typedef uint16_t	xfs_qwarncnt_t;
 
+typedef uint8_t		xfs_dqtype_t;
+
+#define XFS_DQTYPE_STRINGS \
+	{ XFS_DQTYPE_USER,	"USER" }, \
+	{ XFS_DQTYPE_PROJ,	"PROJ" }, \
+	{ XFS_DQTYPE_GROUP,	"GROUP" }
+
 /*
  * flags for q_flags field in the dquot.
  */
-#define XFS_DQ_USER		0x0001		/* a user quota */
-#define XFS_DQ_PROJ		0x0002		/* project quota */
-#define XFS_DQ_GROUP		0x0004		/* a group quota */
-#define XFS_DQ_DIRTY		0x0008		/* dquot is dirty */
-#define XFS_DQ_FREEING		0x0010		/* dquot is being torn down */
+#define XFS_DQFLAG_DIRTY	(1 << 0)	/* dquot is dirty */
+#define XFS_DQFLAG_FREEING	(1 << 1)	/* dquot is being torn down */
 
-#define XFS_DQ_ALLTYPES		(XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP)
-
-#define XFS_DQ_FLAGS \
-	{ XFS_DQ_USER,		"USER" }, \
-	{ XFS_DQ_PROJ,		"PROJ" }, \
-	{ XFS_DQ_GROUP,		"GROUP" }, \
-	{ XFS_DQ_DIRTY,		"DIRTY" }, \
-	{ XFS_DQ_FREEING,	"FREEING" }
+#define XFS_DQFLAG_STRINGS \
+	{ XFS_DQFLAG_DIRTY,	"DIRTY" }, \
+	{ XFS_DQFLAG_FREEING,	"FREEING" }
 
 /*
  * We have the possibility of all three quota types being active at once, and
···
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp,
-		struct xfs_disk_dquot *ddq, xfs_dqid_t id, uint type);
+		struct xfs_disk_dquot *ddq, xfs_dqid_t id);
 extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp,
-		struct xfs_dqblk *dqb, xfs_dqid_t id, uint type);
+		struct xfs_dqblk *dqb, xfs_dqid_t id);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 extern void xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb,
-		xfs_dqid_t id, uint type);
+		xfs_dqid_t id, xfs_dqtype_t type);
 
 #endif	/* __XFS_QUOTA_H__ */

fs/xfs/libxfs/xfs_refcount_btree.c

···
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
+	struct xfs_perag	*pag = agbp->b_pag;
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_refcount_root = ptr->s;
 	be32_add_cpu(&agf->agf_refcount_level, inc);
 	pag->pagf_refcount_level += inc;
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp,
 			XFS_AGF_REFCOUNT_ROOT | XFS_AGF_REFCOUNT_LEVEL);
···
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agno < mp->m_sb.sb_agcount);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	cur->bc_btnum = XFS_BTNUM_REFC;

fs/xfs/libxfs/xfs_rmap_btree.c

···
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
 	int			btnum = cur->bc_btnum;
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
+	struct xfs_perag	*pag = agbp->b_pag;
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_roots[btnum] = ptr->s;
 	be32_add_cpu(&agf->agf_levels[btnum], inc);
 	pag->pagf_levels[btnum] += inc;
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
 }
···
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
+	struct xfs_perag	*pag;
 	xfs_agblock_t		bno;
 	int			error;
 
···
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 
-	xfs_ag_resv_rmapbt_free(cur->bc_mp, cur->bc_ag.agno);
-
+	pag = cur->bc_ag.agbp->b_pag;
+	xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
 	return 0;
 }
 
···
 {
 	struct xfs_btree_cur	*cur;
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	/* Overlapping btree; 2 keys per pointer. */

fs/xfs/libxfs/xfs_rtbitmap.c

···
 	if (error)
 		return error;
 
-	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_real_extent(&map)))
+	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map)))
 		return -EFSCORRUPTED;
 
 	ASSERT(map.br_startblock != NULLFSBLOCK);

fs/xfs/libxfs/xfs_shared.h

···
 #define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
 #define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
+#define XFS_TRANS_RES_FDBLKS	0x80	/* reserve newly freed blocks */
 /*
  * LOWMODE is used by the allocator to activate the lowspace algorithm - when
  * free space is running low the extent allocator may choose to allocate an

fs/xfs/libxfs/xfs_trans_inode.c

···
 #include "xfs_shared.h"
 #include "xfs_format.h"
 #include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
···
 
 	ASSERT(iip->ili_lock_flags == 0);
 	iip->ili_lock_flags = lock_flags;
+	ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
 
 	/*
 	 * Get a log_item_desc to point at the new item.
···
 }
 
 /*
- * This is called to mark the fields indicated in fieldmask as needing
- * to be logged when the transaction is committed.  The inode must
- * already be associated with the given transaction.
+ * This is called to mark the fields indicated in fieldmask as needing to be
+ * logged when the transaction is committed.  The inode must already be
+ * associated with the given transaction.
  *
- * The values for fieldmask are defined in xfs_inode_item.h.  We always
- * log all of the core inode if any of it has changed, and we always log
- * all of the inline data/extents/b-tree root if any of them has changed.
+ * The values for fieldmask are defined in xfs_inode_item.h.  We always log all
+ * of the core inode if any of it has changed, and we always log all of the
+ * inline data/extents/b-tree root if any of them has changed.
+ *
+ * Grab and pin the cluster buffer associated with this inode to avoid RMW
+ * cycles at inode writeback time. Avoid the need to add error handling to every
+ * xfs_trans_log_inode() call by shutting down on read error.  This will cause
+ * transactions to fail and everything to error out, just like if we return a
+ * read error in a dirty transaction and cancel it.
  */
 void
 xfs_trans_log_inode(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	uint		flags)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	uint			flags)
 {
-	struct inode	*inode = VFS_I(ip);
+	struct xfs_inode_log_item *iip = ip->i_itemp;
+	struct inode		*inode = VFS_I(ip);
+	uint			iversion_flags = 0;
 
-	ASSERT(ip->i_itemp != NULL);
+	ASSERT(iip);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
 
 	/*
 	 * Don't bother with i_lock for the I_DIRTY_TIME check here, as races
···
 	}
 
 	/*
-	 * Record the specific change for fdatasync optimisation. This
-	 * allows fdatasync to skip log forces for inodes that are only
-	 * timestamp dirty. We do this before the change count so that
-	 * the core being logged in this case does not impact on fdatasync
-	 * behaviour.
-	 */
-	ip->i_itemp->ili_fsync_fields |= flags;
-
-	/*
 	 * First time we log the inode in a transaction, bump the inode change
 	 * counter if it is configured for this to occur. While we have the
 	 * inode locked exclusively for metadata modification, we can usually
···
 	 * set however, then go ahead and bump the i_version counter
 	 * unconditionally.
 	 */
-	if (!test_and_set_bit(XFS_LI_DIRTY, &ip->i_itemp->ili_item.li_flags) &&
-	    IS_I_VERSION(VFS_I(ip))) {
-		if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
-			flags |= XFS_ILOG_CORE;
+	if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) {
+		if (IS_I_VERSION(inode) &&
+		    inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE))
+			iversion_flags = XFS_ILOG_CORE;
 	}
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
+	/*
+	 * Record the specific change for fdatasync optimisation. This allows
+	 * fdatasync to skip log forces for inodes that are only timestamp
+	 * dirty.
+	 */
+	spin_lock(&iip->ili_lock);
+	iip->ili_fsync_fields |= flags;
+
+	if (!iip->ili_item.li_buf) {
+		struct xfs_buf	*bp;
+		int		error;
+
+		/*
+		 * We hold the ILOCK here, so this inode is not going to be
+		 * flushed while we are here. Further, because there is no
+		 * buffer attached to the item, we know that there is no IO in
+		 * progress, so nothing will clear the ili_fields while we read
+		 * in the buffer. Hence we can safely drop the spin lock and
+		 * read the buffer knowing that the state will not change from
+		 * here.
+		 */
+		spin_unlock(&iip->ili_lock);
+		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, NULL,
+					&bp, 0);
+		if (error) {
+			xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR);
+			return;
+		}
+
+		/*
+		 * We need an explicit buffer reference for the log item but
+		 * don't want the buffer to remain attached to the transaction.
+		 * Hold the buffer but release the transaction reference once
+		 * we've attached the inode log item to the buffer log item
+		 * list.
+		 */
+		xfs_buf_hold(bp);
+		spin_lock(&iip->ili_lock);
+		iip->ili_item.li_buf = bp;
+		bp->b_flags |= _XBF_INODES;
+		list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
+		xfs_trans_brelse(tp, bp);
+	}
 
 	/*
-	 * Always OR in the bits from the ili_last_fields field.
-	 * This is to coordinate with the xfs_iflush() and xfs_iflush_done()
-	 * routines in the eventual clearing of the ili_fields bits.
-	 * See the big comment in xfs_iflush() for an explanation of
-	 * this coordination mechanism.
+	 * Always OR in the bits from the ili_last_fields field.  This is to
+	 * coordinate with the xfs_iflush() and xfs_iflush_done() routines in
+	 * the eventual clearing of the ili_fields bits.  See the big comment in
+	 * xfs_iflush() for an explanation of this coordination mechanism.
 	 */
-	flags |= ip->i_itemp->ili_last_fields;
-	ip->i_itemp->ili_fields |= flags;
+	iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags);
+	spin_unlock(&iip->ili_lock);
 }
 
 int

fs/xfs/libxfs/xfs_trans_space.h

···
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define	XFS_IALLOC_SPACE_RES(mp)	\
 	(M_IGEO(mp)->ialloc_blks + \
-	 (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+	 ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \
 	  (M_IGEO(mp)->inobt_maxlevels - 1)))
 
 /*

fs/xfs/scrub/bmap.c

···
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
 	    sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) {
+		struct address_space	*mapping = VFS_I(sc->ip)->i_mapping;
+
 		inode_dio_wait(VFS_I(sc->ip));
-		error = filemap_write_and_wait(VFS_I(sc->ip)->i_mapping);
-		if (error)
+
+		/*
+		 * Try to flush all incore state to disk before we examine the
+		 * space mappings for the data fork.  Leave accumulated errors
+		 * in the mapping for the writer threads to consume.
+		 *
+		 * On ENOSPC or EIO writeback errors, we continue into the
+		 * extent mapping checks because write failures do not
+		 * necessarily imply anything about the correctness of the file
+		 * metadata.  The metadata and the file data could be on
+		 * completely separate devices; a media failure might only
+		 * affect a subset of the disk, etc.  We can handle delalloc
+		 * extents in the scrubber, so leaving them in memory is fine.
+		 */
+		error = filemap_fdatawrite(mapping);
+		if (!error)
+			error = filemap_fdatawait_keep_errors(mapping);
+		if (error && (error != -ENOSPC && error != -EIO))
 			goto out;
 	}
 

fs/xfs/scrub/dabtree.c

···
 	ds.dargs.whichfork = whichfork;
 	ds.dargs.trans = sc->tp;
 	ds.dargs.op_flags = XFS_DA_OP_OKNOENT;
-	ds.state = xfs_da_state_alloc();
-	ds.state->args = &ds.dargs;
-	ds.state->mp = mp;
+	ds.state = xfs_da_state_alloc(&ds.dargs);
 	ds.sc = sc;
 	ds.private = private;
 	if (whichfork == XFS_ATTR_FORK) {

fs/xfs/scrub/quota.c

···
 #include "scrub/common.h"
 
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
-static inline uint
+static inline xfs_dqtype_t
 xchk_quota_to_dqtype(
 	struct xfs_scrub	*sc)
 {
 	switch (sc->sm->sm_type) {
 	case XFS_SCRUB_TYPE_UQUOTA:
-		return XFS_DQ_USER;
+		return XFS_DQTYPE_USER;
 	case XFS_SCRUB_TYPE_GQUOTA:
-		return XFS_DQ_GROUP;
+		return XFS_DQTYPE_GROUP;
 	case XFS_SCRUB_TYPE_PQUOTA:
-		return XFS_DQ_PROJ;
+		return XFS_DQTYPE_PROJ;
 	default:
 		return 0;
 	}
···
 	struct xfs_scrub	*sc,
 	struct xfs_inode	*ip)
 {
-	uint			dqtype;
+	xfs_dqtype_t		dqtype;
 	int			error;
 
 	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
···
 STATIC int
 xchk_quota_item(
 	struct xfs_dquot	*dq,
-	uint			dqtype,
+	xfs_dqtype_t		dqtype,
 	void			*priv)
 {
 	struct xchk_quota_info	*sqi = priv;
 	struct xfs_scrub	*sc = sqi->sc;
 	struct xfs_mount	*mp = sc->mp;
-	struct xfs_disk_dquot	*d = &dq->q_core;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	xfs_fileoff_t		offset;
-	unsigned long long	bsoft;
-	unsigned long long	isoft;
-	unsigned long long	rsoft;
-	unsigned long long	bhard;
-	unsigned long long	ihard;
-	unsigned long long	rhard;
-	unsigned long long	bcount;
-	unsigned long long	icount;
-	unsigned long long	rcount;
 	xfs_ino_t		fs_icount;
-	xfs_dqid_t		id = be32_to_cpu(d->d_id);
 	int			error = 0;
 
 	if (xchk_should_terminate(sc, &error))
···
 	 * Except for the root dquot, the actual dquot we got must either have
 	 * the same or higher id as we saw before.
 	 */
-	offset = id / qi->qi_dqperchunk;
-	if (id && id <= sqi->last_id)
+	offset = dq->q_id / qi->qi_dqperchunk;
+	if (dq->q_id && dq->q_id <= sqi->last_id)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
-	sqi->last_id = id;
-
-	/* Did we get the dquot type we wanted? */
-	if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
-		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
-
-	if (d->d_pad0 != cpu_to_be32(0) || d->d_pad != cpu_to_be16(0))
-		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
-
-	/* Check the limits. */
-	bhard = be64_to_cpu(d->d_blk_hardlimit);
-	ihard = be64_to_cpu(d->d_ino_hardlimit);
-	rhard = be64_to_cpu(d->d_rtb_hardlimit);
-
-	bsoft = be64_to_cpu(d->d_blk_softlimit);
-	isoft = be64_to_cpu(d->d_ino_softlimit);
-	rsoft = be64_to_cpu(d->d_rtb_softlimit);
+	sqi->last_id = dq->q_id;
 
 	/*
 	 * Warn if the hard limits are larger than the fs.
···
 	 * Complain about corruption if the soft limit is greater than
 	 * the hard limit.
 	 */
-	if (bhard > mp->m_sb.sb_dblocks)
+	if (dq->q_blk.hardlimit > mp->m_sb.sb_dblocks)
 		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
-	if (bsoft > bhard)
+	if (dq->q_blk.softlimit > dq->q_blk.hardlimit)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
-	if (ihard > M_IGEO(mp)->maxicount)
+	if (dq->q_ino.hardlimit > M_IGEO(mp)->maxicount)
 		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
-	if (isoft > ihard)
+	if (dq->q_ino.softlimit > dq->q_ino.hardlimit)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
-	if (rhard > mp->m_sb.sb_rblocks)
+	if (dq->q_rtb.hardlimit > mp->m_sb.sb_rblocks)
 		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
-	if (rsoft > rhard)
+	if (dq->q_rtb.softlimit > dq->q_rtb.hardlimit)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the resource counts. */
-	bcount = be64_to_cpu(d->d_bcount);
-	icount = be64_to_cpu(d->d_icount);
-	rcount = be64_to_cpu(d->d_rtbcount);
 	fs_icount = percpu_counter_sum(&mp->m_icount);
 
 	/*
···
 	 * if there are no quota limits.
 	 */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-		if (mp->m_sb.sb_dblocks < bcount)
+		if (mp->m_sb.sb_dblocks < dq->q_blk.count)
 			xchk_fblock_set_warning(sc, XFS_DATA_FORK,
 					offset);
 	} else {
-		if (mp->m_sb.sb_dblocks < bcount)
+		if (mp->m_sb.sb_dblocks < dq->q_blk.count)
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					offset);
 	}
-	if (icount > fs_icount || rcount > mp->m_sb.sb_rblocks)
+	if (dq->q_ino.count > fs_icount || dq->q_rtb.count > mp->m_sb.sb_rblocks)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/*
···
 	 * lower limit than the actual usage.  However, we flag it for
 	 * admin review.
 	 */
-	if (id != 0 && bhard != 0 && bcount > bhard)
-		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
-	if (id != 0 && ihard != 0 && icount > ihard)
-		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
-	if (id != 0 && rhard != 0 && rcount > rhard)
+	if (dq->q_id == 0)
+		goto out;
+
+	if (dq->q_blk.hardlimit != 0 &&
+	    dq->q_blk.count > dq->q_blk.hardlimit)
 		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 
+	if (dq->q_ino.hardlimit != 0 &&
+	    dq->q_ino.count > dq->q_ino.hardlimit)
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+
+	if (dq->q_rtb.hardlimit != 0 &&
+	    dq->q_rtb.count > dq->q_rtb.hardlimit)
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+
+out:
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return -EFSCORRUPTED;
 
···
 	struct xchk_quota_info	sqi;
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
-	uint			dqtype;
+	xfs_dqtype_t		dqtype;
 	int			error = 0;
 
 	dqtype = xchk_quota_to_dqtype(sc);

fs/xfs/scrub/repair.c

···
 void
 xrep_force_quotacheck(
 	struct xfs_scrub	*sc,
-	uint			dqtype)
+	xfs_dqtype_t		type)
 {
 	uint			flag;
 
-	flag = xfs_quota_chkd_flag(dqtype);
+	flag = xfs_quota_chkd_flag(type);
 	if (!(flag & sc->mp->m_qflags))
 		return;
 
···
 "inode %llu repair encountered quota error %d, quotacheck forced.",
 				(unsigned long long)sc->ip->i_ino, error);
 		if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
-			xrep_force_quotacheck(sc, XFS_DQ_USER);
+			xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
 		if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
-			xrep_force_quotacheck(sc, XFS_DQ_GROUP);
+			xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
 		if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
-			xrep_force_quotacheck(sc, XFS_DQ_PROJ);
+			xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
 		/* fall through */
 	case -ESRCH:
 		error = 0;

fs/xfs/scrub/repair.h

···
 #ifndef __XFS_SCRUB_REPAIR_H__
 #define __XFS_SCRUB_REPAIR_H__
 
+#include "xfs_quota_defs.h"
+
 static inline int xrep_notsupported(struct xfs_scrub *sc)
 {
 	return -EOPNOTSUPP;
···
 
 int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
 		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
-void xrep_force_quotacheck(struct xfs_scrub *sc, uint dqtype);
+void xrep_force_quotacheck(struct xfs_scrub *sc, xfs_dqtype_t type);
 int xrep_ino_dqattach(struct xfs_scrub *sc);
 
 /* Metadata repairers */

fs/xfs/scrub/rtbitmap.c

···
 #include "xfs_trans.h"
 #include "xfs_rtalloc.h"
 #include "xfs_inode.h"
+#include "xfs_bmap.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 
···
 	return 0;
 }
 
+/* Make sure the entire rtbitmap file is mapped with written extents. */
+STATIC int
+xchk_rtbitmap_check_extents(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_bmbt_irec	map;
+	xfs_rtblock_t		off;
+	int			nmap;
+	int			error = 0;
+
+	for (off = 0; off < mp->m_sb.sb_rbmblocks;) {
+		if (xchk_should_terminate(sc, &error) ||
+		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+			break;
+
+		/* Make sure we have a written extent. */
+		nmap = 1;
+		error = xfs_bmapi_read(mp->m_rbmip, off,
+				mp->m_sb.sb_rbmblocks - off, &map, &nmap,
+				XFS_DATA_FORK);
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
+			break;
+
+		if (nmap != 1 || !xfs_bmap_is_written_extent(&map)) {
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+			break;
+		}
+
+		off += map.br_blockcount;
+	}
+
+	return error;
+}
+
 /* Scrub the realtime bitmap. */
 int
 xchk_rtbitmap(
···
 {
 	int			error;
 
+	/* Is the size of the rtbitmap correct? */
+	if (sc->mp->m_rbmip->i_d.di_size !=
+	    XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)) {
+		xchk_ino_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+		return 0;
+	}
+
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		return error;
+
+	error = xchk_rtbitmap_check_extents(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 

fs/xfs/xfs_bmap_item.c

···
 {
 	struct xfs_bui_log_item		*buip;
 
-	buip = kmem_zone_zalloc(xfs_bui_zone, 0);
+	buip = kmem_cache_zalloc(xfs_bui_zone, GFP_KERNEL | __GFP_NOFAIL);
 
 	xfs_log_item_init(mp, &buip->bui_item, XFS_LI_BUI, &xfs_bui_item_ops);
 	buip->bui_format.bui_nextents = XFS_BUI_MAX_FAST_EXTENTS;
···
 {
 	struct xfs_bud_log_item		*budp;
 
-	budp = kmem_zone_zalloc(xfs_bud_zone, 0);
+	budp = kmem_cache_zalloc(xfs_bud_zone, GFP_KERNEL | __GFP_NOFAIL);
 	xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
 			  &xfs_bud_item_ops);
 	budp->bud_buip = buip;

fs/xfs/xfs_bmap_util.c

···
 	int			lock_flags;
 	uint64_t		f;
 	int			resblks = 0;
+	unsigned int		flags = 0;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
···
 		resblks +=  XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w);
 
 		/*
-		 * Handle the corner case where either inode might straddle the
-		 * btree format boundary. If so, the inode could bounce between
-		 * btree <-> extent format on unmap -> remap cycles, freeing and
-		 * allocating a bmapbt block each time.
+		 * If either inode straddles a bmapbt block allocation boundary,
+		 * the rmapbt algorithm triggers repeated allocs and frees as
+		 * extents are remapped. This can exhaust the block reservation
+		 * prematurely and cause shutdown. Return freed blocks to the
+		 * transaction reservation to counter this behavior.
 		 */
-		if (ipnext == (XFS_IFORK_MAXEXT(ip, w) + 1))
-			resblks += XFS_IFORK_MAXEXT(ip, w);
-		if (tipnext == (XFS_IFORK_MAXEXT(tip, w) + 1))
-			resblks += XFS_IFORK_MAXEXT(tip, w);
+		flags |= XFS_TRANS_RES_FDBLKS;
 	}
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, flags,
+				&tp);
 	if (error)
 		goto out_unlock;
 

fs/xfs/xfs_buf.c

···
 #include "xfs_mount.h"
 #include "xfs_trace.h"
 #include "xfs_log.h"
+#include "xfs_log_recover.h"
+#include "xfs_trans.h"
+#include "xfs_buf_item.h"
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 
···
 	int			i;
 
 	*bpp = NULL;
-	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
-	if (unlikely(!bp))
-		return -ENOMEM;
+	bp = kmem_cache_zalloc(xfs_buf_zone, GFP_NOFS | __GFP_NOFAIL);
 
 	/*
 	 * We don't want certain flags to appear in b_flags unless they are
···
 	 */
 	if (bp->b_flags & XBF_STALE) {
 		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
-		ASSERT(bp->b_iodone == NULL);
 		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
 		bp->b_ops = NULL;
 	}
···
 	if (!bp->b_error && bp->b_io_error)
 		xfs_buf_ioerror(bp, bp->b_io_error);
 
-	/* Only validate buffers that were read without errors */
-	if (read && !bp->b_error && bp->b_ops) {
-		ASSERT(!bp->b_iodone);
-		bp->b_ops->verify_read(bp);
+	if (read) {
+		if (!bp->b_error && bp->b_ops)
+			bp->b_ops->verify_read(bp);
+		if (!bp->b_error)
+			bp->b_flags |= XBF_DONE;
+		xfs_buf_ioend_finish(bp);
+		return;
 	}
 
 	if (!bp->b_error) {
···
 		bp->b_flags |= XBF_DONE;
 	}
 
-	if (bp->b_iodone)
-		(*(bp->b_iodone))(bp);
-	else if (bp->b_flags & XBF_ASYNC)
-		xfs_buf_relse(bp);
-	else
-		complete(&bp->b_iowait);
+	/*
+	 * If this is a log recovery buffer, we aren't doing transactional IO
+	 * yet so we need to let it handle IO completions.
+	 */
+	if (bp->b_flags & _XBF_LOGRECOVERY) {
+		xlog_recover_iodone(bp);
+		return;
+	}
+
+	if (bp->b_flags & _XBF_INODES) {
+		xfs_buf_inode_iodone(bp);
+		return;
+	}
+
+	if (bp->b_flags & _XBF_DQUOTS) {
+		xfs_buf_dquot_iodone(bp);
+		return;
+	}
+	xfs_buf_iodone(bp);
 }
 
 static void

fs/xfs/xfs_buf.h

···
 /*
  *	Base types
  */
+struct xfs_buf;
 
 #define XFS_BUF_DADDR_NULL	((xfs_daddr_t) (-1LL))
 
···
 #define XBF_STALE	 (1 << 6) /* buffer has been staled, do not find it */
 #define XBF_WRITE_FAIL	 (1 << 7) /* async writes have failed on this buffer */
 
-/* flags used only as arguments to access routines */
-#define XBF_TRYLOCK	 (1 << 16)/* lock requested, but do not wait */
-#define XBF_UNMAPPED	 (1 << 17)/* do not map the buffer */
+/* buffer type flags for write callbacks */
+#define _XBF_INODES	 (1 << 16)/* inode buffer */
+#define _XBF_DQUOTS	 (1 << 17)/* dquot buffer */
+#define _XBF_LOGRECOVERY	 (1 << 18)/* log recovery buffer */
 
 /* flags used only internally */
 #define _XBF_PAGES	 (1 << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	 (1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1 << 22)/* buffer on a delwri queue */
+
+/* flags used only as arguments to access routines */
+#define XBF_TRYLOCK	 (1 << 30)/* lock requested, but do not wait */
+#define XBF_UNMAPPED	 (1 << 31)/* do not map the buffer */
 
 typedef unsigned int xfs_buf_flags_t;
 
···
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \
 	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
-	{ XBF_TRYLOCK,		"TRYLOCK" },	/* should never be set */\
-	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
+	{ _XBF_INODES,		"INODES" }, \
+	{ _XBF_DQUOTS,		"DQUOTS" }, \
+	{ _XBF_LOGRECOVERY,		"LOG_RECOVERY" }, \
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
-	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
-
+	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
+	/* The following interface flags should never be set */ \
+	{ XBF_TRYLOCK,		"TRYLOCK" }, \
+	{ XBF_UNMAPPED,		"UNMAPPED" }
 
 /*
  * Internal state flags.
···
 	struct percpu_counter	bt_io_count;
 	struct ratelimit_state	bt_ioerror_rl;
 } xfs_buftarg_t;
-
-struct xfs_buf;
-typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
-
 
 #define XB_PAGES	2
 
···
 	xfs_buftarg_t		*b_target;	/* buffer target (device) */
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_ioend_work;
-	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	struct xfs_buf_log_item	*b_log_item;
 	struct list_head	b_li_list;	/* Log items list head */
···
 #define xfs_buf_islocked(bp) \
 	((bp)->b_sema.count <= 0)
 
+static inline void xfs_buf_relse(xfs_buf_t *bp)
+{
+	xfs_buf_unlock(bp);
+	xfs_buf_rele(bp);
+}
+
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
 extern void xfs_buf_ioend(struct xfs_buf *bp);
+static inline void xfs_buf_ioend_finish(struct xfs_buf *bp)
+{
+	if (bp->b_flags & XBF_ASYNC)
+		xfs_buf_relse(bp);
+	else
+		complete(&bp->b_iowait);
+}
+
 extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 		xfs_failaddr_t failaddr);
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
···
 static inline int xfs_buf_ispinned(struct xfs_buf *bp)
 {
 	return atomic_read(&bp->b_pin_count);
-}
-
-static inline void xfs_buf_relse(xfs_buf_t *bp)
-{
-	xfs_buf_unlock(bp);
-	xfs_buf_rele(bp);
 }
 
 static inline int

fs/xfs/xfs_buf_item.c

···
 #include "xfs_bit.h"
 #include "xfs_mount.h"
 #include "xfs_trans.h"
-#include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode.h"
+#include "xfs_inode_item.h"
+#include "xfs_quota.h"
+#include "xfs_dquot_item.h"
+#include "xfs_dquot.h"
 #include "xfs_trace.h"
 #include "xfs_log.h"
 
···
 	return container_of(lip, struct xfs_buf_log_item, bli_item);
 }
 
-STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
+static void xfs_buf_item_done(struct xfs_buf *bp);
 
 /* Is this log iovec plausibly large enough to contain the buffer log format? */
 bool
···
 		 * the AIL lock.
 		 */
 		if (bip->bli_flags & XFS_BLI_STALE_INODE) {
-			xfs_buf_do_callbacks(bp);
-			bp->b_log_item = NULL;
-			list_del_init(&bp->b_li_list);
-			bp->b_iodone = NULL;
+			xfs_buf_item_done(bp);
+			xfs_iflush_done(bp);
+			ASSERT(list_empty(&bp->b_li_list));
 		} else {
 			xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
···
 		return 0;
 	}
 
-	bip = kmem_zone_zalloc(xfs_buf_item_zone, 0);
+	bip = kmem_cache_zalloc(xfs_buf_item_zone, GFP_KERNEL | __GFP_NOFAIL);
 	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
 	bip->bli_buf = bp;
 
···
 }
 
 /*
- * This is called when the buf log item is no longer needed.  It should
- * free the buf log item associated with the given buffer and clear
- * the buffer's pointer to the buf log item.  If there are no more
- * items in the list, clear the b_iodone field of the buffer (see
- * xfs_buf_attach_iodone() below).
+ * xfs_buf_item_relse() is called when the buf log item is no longer needed.
  */
 void
 xfs_buf_item_relse(
···
 	ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
 
 	bp->b_log_item = NULL;
-	if (list_empty(&bp->b_li_list))
-		bp->b_iodone = NULL;
-
 	xfs_buf_rele(bp);
 	xfs_buf_item_free(bip);
 }
 
-
 /*
- * Add the given log item with its callback to the list of callbacks
- * to be called when the buffer's I/O completes.  If it is not set
- * already, set the buffer's b_iodone() routine to be
- * xfs_buf_iodone_callbacks() and link the log item into the list of
- * items rooted at b_li_list.
+ * Decide if we're going to retry the write after a failure, and prepare
+ * the buffer for retrying the write.
  */
-void
-xfs_buf_attach_iodone(
-	struct xfs_buf		*bp,
-	void			(*cb)(struct xfs_buf *, struct xfs_log_item *),
-	struct xfs_log_item	*lip)
-{
-	ASSERT(xfs_buf_islocked(bp));
-
-	lip->li_cb = cb;
-	list_add_tail(&lip->li_bio_list, &bp->b_li_list);
-
-	ASSERT(bp->b_iodone == NULL ||
-	       bp->b_iodone == xfs_buf_iodone_callbacks);
-	bp->b_iodone = xfs_buf_iodone_callbacks;
-}
-
-/*
- * We can have many callbacks on a buffer. Running the callbacks individually
- * can cause a lot of contention on the AIL lock, so we allow for a single
- * callback to be able to scan the remaining items in bp->b_li_list for other
- * items of the same type and callback to be processed in the first call.
- *
- * As a result, the loop walking the callback list below will also modify the
- * list. it removes the first item from the list and then runs the callback.
- * The loop then restarts from the new first item int the list. This allows the
- * callback to scan and modify the list attached to the buffer and we don't
- * have to care about maintaining a next item pointer.
- */
-STATIC void
-xfs_buf_do_callbacks(
-	struct xfs_buf		*bp)
-{
-	struct xfs_buf_log_item *blip = bp->b_log_item;
-	struct xfs_log_item	*lip;
-
-	/* If there is a buf_log_item attached, run its callback */
-	if (blip) {
-		lip = &blip->bli_item;
-		lip->li_cb(bp, lip);
-	}
-
-	while (!list_empty(&bp->b_li_list)) {
-		lip = list_first_entry(&bp->b_li_list, struct xfs_log_item,
-				       li_bio_list);
-
-		/*
-		 * Remove the item from the list, so we don't have any
-		 * confusion if the item is added to another buf.
-		 * Don't touch the log item after calling its
-		 * callback, because it could have freed itself.
-		 */
-		list_del_init(&lip->li_bio_list);
-		lip->li_cb(bp, lip);
-	}
-}
-
-/*
- * Invoke the error state callback for each log item affected by the failed I/O.
- *
- * If a metadata buffer write fails with a non-permanent error, the buffer is
- * eventually resubmitted and so the completion callbacks are not run. The error
- * state may need to be propagated to the log items attached to the buffer,
- * however, so the next AIL push of the item knows hot to handle it correctly.
- */
-STATIC void
-xfs_buf_do_callbacks_fail(
-	struct xfs_buf		*bp)
-{
-	struct xfs_log_item	*lip;
-	struct xfs_ail		*ailp;
-
-	/*
-	 * Buffer log item errors are handled directly by xfs_buf_item_push()
-	 * and xfs_buf_iodone_callback_error, and they have no IO error
-	 * callbacks. Check only for items in b_li_list.
-	 */
-	if (list_empty(&bp->b_li_list))
-		return;
-
-	lip = list_first_entry(&bp->b_li_list, struct xfs_log_item,
-			li_bio_list);
-	ailp = lip->li_ailp;
-	spin_lock(&ailp->ail_lock);
-	list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
-		if (lip->li_ops->iop_error)
-			lip->li_ops->iop_error(lip, bp);
-	}
-	spin_unlock(&ailp->ail_lock);
-}
-
 static bool
-xfs_buf_iodone_callback_error(
+xfs_buf_ioerror_fail_without_retry(
 	struct xfs_buf		*bp)
 {
-	struct xfs_buf_log_item	*bip = bp->b_log_item;
-	struct xfs_log_item	*lip;
-	struct xfs_mount	*mp;
+	struct xfs_mount	*mp = bp->b_mount;
 	static ulong		lasttime;
 	static xfs_buftarg_t	*lasttarg;
-	struct xfs_error_cfg	*cfg;
-
-	/*
-	 * The failed buffer might not have a buf_log_item attached or the
-	 * log_item list might be empty. Get the mp from the available
-	 * xfs_log_item
-	 */
-	lip = list_first_entry_or_null(&bp->b_li_list, struct xfs_log_item,
-				       li_bio_list);
-	mp = lip ? lip->li_mountp : bip->bli_item.li_mountp;
 
 	/*
 	 * If we've already decided to shutdown the filesystem because of
 	 * I/O errors, there's no point in giving this a retry.
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp))
-		goto out_stale;
+		return true;
 
 	if (bp->b_target != lasttarg ||
 	    time_after(jiffies, (lasttime + 5*HZ))) {
···
 
 	/* synchronous writes will have callers process the error */
 	if (!(bp->b_flags & XBF_ASYNC))
-		goto out_stale;
-
-	trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
-	ASSERT(bp->b_iodone != NULL);
-
-	cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
-
-	/*
-	 * If the write was asynchronous then no one will be looking for the
-	 * error.  If this is the first failure of this type, clear the error
-	 * state and write the buffer out again. This means we always retry an
-	 * async write failure at least once, but we also need to set the buffer
-	 * up to behave correctly now for repeated failures.
-	 */
-	if (!(bp->b_flags & (XBF_STALE | XBF_WRITE_FAIL)) ||
-	     bp->b_last_error != bp->b_error) {
-		bp->b_flags |= (XBF_WRITE | XBF_DONE | XBF_WRITE_FAIL);
-		bp->b_last_error = bp->b_error;
-		if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
-		    !bp->b_first_retry_time)
-			bp->b_first_retry_time = jiffies;
-
-		xfs_buf_ioerror(bp, 0);
-		xfs_buf_submit(bp);
 		return true;
-	}
+	return false;
+}
 
-	/*
-	 * Repeated failure on an async write. Take action according to the
-	 * error configuration we have been set up to use.
-	 */
+static bool
+xfs_buf_ioerror_retry(
+	struct xfs_buf		*bp,
+	struct xfs_error_cfg	*cfg)
+{
+	if ((bp->b_flags & (XBF_STALE | XBF_WRITE_FAIL)) &&
+	    bp->b_last_error == bp->b_error)
+		return false;
+
+	bp->b_flags |= (XBF_WRITE | XBF_DONE | XBF_WRITE_FAIL);
+	bp->b_last_error = bp->b_error;
+	if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
+	    !bp->b_first_retry_time)
+		bp->b_first_retry_time = jiffies;
+	return true;
+}
+
+/*
+ * Account for this latest trip around the retry handler, and decide if
+ * we've failed enough times to constitute a permanent failure.
+ */
+static bool
+xfs_buf_ioerror_permanent(
+	struct xfs_buf		*bp,
+	struct xfs_error_cfg	*cfg)
+{
+	struct xfs_mount	*mp = bp->b_mount;
 
 	if (cfg->max_retries != XFS_ERR_RETRY_FOREVER &&
 	    ++bp->b_retries > cfg->max_retries)
-			goto permanent_error;
+		return true;
 	if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
 	    time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
-			goto permanent_error;
+		return true;
 
 	/* At unmount we may treat errors differently */
 	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
-		goto permanent_error;
+		return true;
 
-	/*
-	 * Still a transient error, run IO completion failure callbacks and let
-	 * the higher layers retry the buffer.
-	 */
-	xfs_buf_do_callbacks_fail(bp);
-	xfs_buf_ioerror(bp, 0);
-	xfs_buf_relse(bp);
-	return true;
+	return false;
+}
+
+/*
+ * On a sync write or shutdown we just want to stale the buffer and let the
+ * caller handle the error in bp->b_error appropriately.
+ *
+ * If the write was asynchronous then no one will be looking for the error.  If
+ * this is the first failure of this type, clear the error state and write the
+ * buffer out again. This means we always retry an async write failure at least
+ * once, but we also need to set the buffer up to behave correctly now for
+ * repeated failures.
+ *
+ * If we get repeated async write failures, then we take action according to the
+ * error configuration we have been set up to use.
+ *
+ * Multi-state return value:
+ *
+ * XBF_IOERROR_FINISH: clear IO error retry state and run callback completions
+ * XBF_IOERROR_DONE: resubmitted immediately, do not run any completions
+ * XBF_IOERROR_FAIL: transient error, run failure callback completions and then
+ *    release the buffer
+ */
+enum {
+	XBF_IOERROR_FINISH,
+	XBF_IOERROR_DONE,
+	XBF_IOERROR_FAIL,
+};
+
+static int
+xfs_buf_iodone_error(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_error_cfg	*cfg;
+
+	if (xfs_buf_ioerror_fail_without_retry(bp))
+		goto out_stale;
+
+	trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+
+	cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
+	if (xfs_buf_ioerror_retry(bp, cfg)) {
+		xfs_buf_ioerror(bp, 0);
+		xfs_buf_submit(bp);
+		return XBF_IOERROR_DONE;
+	}
 
 	/*
 	 * Permanent error - we need to trigger a shutdown if we haven't already
 	 * to indicate that inconsistency will result from this action.
 	 */
-permanent_error:
-	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	if (xfs_buf_ioerror_permanent(bp, cfg)) {
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+		goto out_stale;
+	}
+
+	/* Still considered a transient error. Caller will schedule retries. */
+	return XBF_IOERROR_FAIL;
+
 out_stale:
 	xfs_buf_stale(bp);
 	bp->b_flags |= XBF_DONE;
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
-	return false;
+	return XBF_IOERROR_FINISH;
 }
 
-/*
- * This is the iodone() function for buffers which have had callbacks attached
- * to them by xfs_buf_attach_iodone(). We need to iterate the items on the
- * callback list, mark the buffer as having no more callbacks and then push the
- * buffer through IO completion processing.
- */
-void
-xfs_buf_iodone_callbacks(
+static void
+xfs_buf_item_done(
 	struct xfs_buf		*bp)
 {
-	/*
-	 * If there is an error, process it. Some errors require us
-	 * to run callbacks after failure processing is done so we
-	 * detect that and take appropriate action.
-	 */
-	if (bp->b_error && xfs_buf_iodone_callback_error(bp))
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
+
+	if (!bip)
 		return;
-
-	/*
-	 * Successful IO or permanent error. Either way, we can clear the
-	 * retry state here in preparation for the next error that may occur.
-	 */
-	bp->b_last_error = 0;
-	bp->b_retries = 0;
-	bp->b_first_retry_time = 0;
-
-	xfs_buf_do_callbacks(bp);
-	bp->b_log_item = NULL;
-	list_del_init(&bp->b_li_list);
-	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp);
-}
-
-/*
- * This is the iodone() function for buffers which have been
- * logged.  It is called when they are eventually flushed out.
- * It should remove the buf item from the AIL, and free the buf item.
- * It is called by xfs_buf_iodone_callbacks() above which will take
- * care of cleaning up the buffer itself.
- */
-void
-xfs_buf_iodone(
-	struct xfs_buf		*bp,
-	struct xfs_log_item	*lip)
-{
-	ASSERT(BUF_ITEM(lip)->bli_buf == bp);
-
-	xfs_buf_rele(bp);
 
 	/*
 	 * If we are forcibly shutting down, this may well be off the AIL
···
 	 *
 	 * Either way, AIL is useless if we're forcing a shutdown.
 	 */
-	xfs_trans_ail_delete(lip, SHUTDOWN_CORRUPT_INCORE);
-	xfs_buf_item_free(BUF_ITEM(lip));
+	xfs_trans_ail_delete(&bip->bli_item, SHUTDOWN_CORRUPT_INCORE);
+	bp->b_log_item = NULL;
+	xfs_buf_item_free(bip);
+	xfs_buf_rele(bp);
+}
+
+static inline void
+xfs_buf_clear_ioerror_retry_state(
+	struct xfs_buf		*bp)
+{
+	bp->b_last_error = 0;
+	bp->b_retries = 0;
+	bp->b_first_retry_time = 0;
+}
+
+/*
+ * Inode buffer iodone callback function.
+ */
+void
+xfs_buf_inode_iodone(
+	struct xfs_buf		*bp)
+{
+	if (bp->b_error) {
+		struct xfs_log_item *lip;
+		int ret = xfs_buf_iodone_error(bp);
+
+		if (ret == XBF_IOERROR_FINISH)
+			goto finish_iodone;
+		if (ret == XBF_IOERROR_DONE)
+			return;
+		ASSERT(ret == XBF_IOERROR_FAIL);
+		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
+			set_bit(XFS_LI_FAILED, &lip->li_flags);
+		}
+		xfs_buf_ioerror(bp, 0);
+		xfs_buf_relse(bp);
+		return;
+	}
+
+finish_iodone:
+	xfs_buf_clear_ioerror_retry_state(bp);
+	xfs_buf_item_done(bp);
+	xfs_iflush_done(bp);
+	xfs_buf_ioend_finish(bp);
+}
+
+/*
+ * Dquot buffer iodone callback function.
+ */
+void
+xfs_buf_dquot_iodone(
+	struct xfs_buf		*bp)
+{
+	if (bp->b_error) {
+		struct xfs_log_item *lip;
+		int ret = xfs_buf_iodone_error(bp);
+
+		if (ret == XBF_IOERROR_FINISH)
+			goto finish_iodone;
+		if (ret == XBF_IOERROR_DONE)
+			return;
+		ASSERT(ret == XBF_IOERROR_FAIL);
+		spin_lock(&bp->b_mount->m_ail->ail_lock);
+		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
+			xfs_set_li_failed(lip, bp);
+		}
+		spin_unlock(&bp->b_mount->m_ail->ail_lock);
+		xfs_buf_ioerror(bp, 0);
+		xfs_buf_relse(bp);
+		return;
+	}
+
+finish_iodone:
+	xfs_buf_clear_ioerror_retry_state(bp);
+	/* a newly allocated dquot buffer might have a log item attached */
+	xfs_buf_item_done(bp);
+	xfs_dquot_done(bp);
+	xfs_buf_ioend_finish(bp);
+}
+
+/*
+ * Dirty buffer iodone callback function.
+ *
+ * Note that for things like remote attribute buffers, there may not be a buffer
+ * log item here, so processing the buffer log item must remain be optional.
+ */
+void
+xfs_buf_iodone(
+	struct xfs_buf		*bp)
+{
+	if (bp->b_error) {
+		int ret = xfs_buf_iodone_error(bp);
+
+		if (ret == XBF_IOERROR_FINISH)
+			goto finish_iodone;
+		if (ret == XBF_IOERROR_DONE)
+			return;
+		ASSERT(ret == XBF_IOERROR_FAIL);
+		ASSERT(list_empty(&bp->b_li_list));
+		xfs_buf_ioerror(bp, 0);
+		xfs_buf_relse(bp);
+		return;
+	}
+
+finish_iodone:
+	xfs_buf_clear_ioerror_retry_state(bp);
+	xfs_buf_item_done(bp);
+	xfs_buf_ioend_finish(bp);
 }

fs/xfs/xfs_buf_item.h

···
 bool	xfs_buf_item_put(struct xfs_buf_log_item *);
 void	xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
 bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
-void	xfs_buf_attach_iodone(struct xfs_buf *,
-			      void(*)(struct xfs_buf *, struct xfs_log_item *),
-			      struct xfs_log_item *);
-void	xfs_buf_iodone_callbacks(struct xfs_buf *);
-void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
+void	xfs_buf_inode_iodone(struct xfs_buf *);
+void	xfs_buf_dquot_iodone(struct xfs_buf *);
+void	xfs_buf_iodone(struct xfs_buf *);
 bool	xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
 
 extern kmem_zone_t	*xfs_buf_item_zone;

fs/xfs/xfs_buf_item_recover.c

···
 	if (bp->b_ops) {
 		struct xfs_buf_log_item	*bip;
 
-		ASSERT(!bp->b_iodone || bp->b_iodone == xlog_recover_iodone);
-		bp->b_iodone = xlog_recover_iodone;
+		bp->b_flags |= _XBF_LOGRECOVERY;
 		xfs_buf_item_init(bp, mp);
 		bip = bp->b_log_item;
 		bip->bli_item.li_lsn = current_lsn;
···
 					item->ri_buf[i].i_len, __func__);
 				goto next;
 			}
-			fa = xfs_dquot_verify(mp, item->ri_buf[i].i_addr,
-					       -1, 0);
+			fa = xfs_dquot_verify(mp, item->ri_buf[i].i_addr, -1);
 			if (fa) {
 				xfs_alert(mp,
 	"dquot corrupt at %pS trying to replay into block 0x%llx",
···
 
 	type = 0;
 	if (buf_f->blf_flags & XFS_BLF_UDQUOT_BUF)
-		type |= XFS_DQ_USER;
+		type |= XFS_DQTYPE_USER;
 	if (buf_f->blf_flags & XFS_BLF_PDQUOT_BUF)
-		type |= XFS_DQ_PROJ;
+		type |= XFS_DQTYPE_PROJ;
 	if (buf_f->blf_flags & XFS_BLF_GDQUOT_BUF)
-		type |= XFS_DQ_GROUP;
+		type |= XFS_DQTYPE_GROUP;
 	/*
 	 * This type of quotas was turned off, so ignore this buffer
 	 */
···
 		error = xfs_bwrite(bp);
 	} else {
 		ASSERT(bp->b_mount == mp);
-		bp->b_iodone = xlog_recover_iodone;
+		bp->b_flags |= _XBF_LOGRECOVERY;
 		xfs_buf_delwri_queue(bp, buffer_list);
 	}
 

fs/xfs/xfs_dquot.c

···
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_error.h"
 
 /*
  * Lock order:
···
  */
 void
 xfs_qm_adjust_dqlimits(
-	struct xfs_mount	*mp,
 	struct xfs_dquot	*dq)
 {
+	struct xfs_mount	*mp = dq->q_mount;
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
-	struct xfs_disk_dquot	*d = &dq->q_core;
 	struct xfs_def_quota	*defq;
 	int			prealloc = 0;
 
-	ASSERT(d->d_id);
+	ASSERT(dq->q_id);
 	defq = xfs_get_defquota(q, xfs_dquot_type(dq));
 
-	if (defq->bsoftlimit && !d->d_blk_softlimit) {
-		d->d_blk_softlimit = cpu_to_be64(defq->bsoftlimit);
+	if (!dq->q_blk.softlimit) {
+		dq->q_blk.softlimit = defq->blk.soft;
 		prealloc = 1;
 	}
-	if (defq->bhardlimit && !d->d_blk_hardlimit) {
-		d->d_blk_hardlimit = cpu_to_be64(defq->bhardlimit);
+	if (!dq->q_blk.hardlimit) {
+		dq->q_blk.hardlimit = defq->blk.hard;
 		prealloc = 1;
 	}
-	if (defq->isoftlimit && !d->d_ino_softlimit)
-		d->d_ino_softlimit = cpu_to_be64(defq->isoftlimit);
-	if (defq->ihardlimit && !d->d_ino_hardlimit)
-		d->d_ino_hardlimit = cpu_to_be64(defq->ihardlimit);
-	if (defq->rtbsoftlimit && !d->d_rtb_softlimit)
-		d->d_rtb_softlimit = cpu_to_be64(defq->rtbsoftlimit);
-	if (defq->rtbhardlimit && !d->d_rtb_hardlimit)
-		d->d_rtb_hardlimit = cpu_to_be64(defq->rtbhardlimit);
+	if (!dq->q_ino.softlimit)
+		dq->q_ino.softlimit = defq->ino.soft;
+	if (!dq->q_ino.hardlimit)
+		dq->q_ino.hardlimit = defq->ino.hard;
+	if (!dq->q_rtb.softlimit)
+		dq->q_rtb.softlimit = defq->rtb.soft;
+	if (!dq->q_rtb.hardlimit)
+		dq->q_rtb.hardlimit = defq->rtb.hard;
 
 	if (prealloc)
 		xfs_dquot_set_prealloc_limits(dq);
+}
+
+/*
+ * Determine if this quota counter is over either limit and set the quota
+ * timers as appropriate.
+ */
+static inline void
+xfs_qm_adjust_res_timer(
+	struct xfs_dquot_res	*res,
+	struct xfs_quota_limits	*qlim)
+{
+	ASSERT(res->hardlimit == 0 || res->softlimit <= res->hardlimit);
+
+	if ((res->softlimit && res->count > res->softlimit) ||
+	    (res->hardlimit && res->count > res->hardlimit)) {
+		if (res->timer == 0)
+			res->timer = ktime_get_real_seconds() + qlim->time;
+	} else {
+		if (res->timer == 0)
+			res->warnings = 0;
+		else
+			res->timer = 0;
+	}
 }
 
 /*
···
  */
 void
 xfs_qm_adjust_dqtimers(
-	struct xfs_mount	*mp,
 	struct xfs_dquot	*dq)
 {
+	struct xfs_mount	*mp = dq->q_mount;
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
-	struct xfs_disk_dquot	*d = &dq->q_core;
 	struct xfs_def_quota	*defq;
 
-	ASSERT(d->d_id);
+	ASSERT(dq->q_id);
 	defq = xfs_get_defquota(qi, xfs_dquot_type(dq));
 
-#ifdef DEBUG
-	if (d->d_blk_hardlimit)
-		ASSERT(be64_to_cpu(d->d_blk_softlimit) <=
-		       be64_to_cpu(d->d_blk_hardlimit));
-	if (d->d_ino_hardlimit)
-		ASSERT(be64_to_cpu(d->d_ino_softlimit) <=
-		       be64_to_cpu(d->d_ino_hardlimit));
-	if (d->d_rtb_hardlimit)
-		ASSERT(be64_to_cpu(d->d_rtb_softlimit) <=
-		       be64_to_cpu(d->d_rtb_hardlimit));
-#endif
-
-	if (!d->d_btimer) {
-		if ((d->d_blk_softlimit &&
-		     (be64_to_cpu(d->d_bcount) >
-		      be64_to_cpu(d->d_blk_softlimit))) ||
-		    (d->d_blk_hardlimit &&
-		     (be64_to_cpu(d->d_bcount) >
-		      be64_to_cpu(d->d_blk_hardlimit)))) {
-			d->d_btimer = cpu_to_be32(ktime_get_real_seconds() +
-					defq->btimelimit);
-		} else {
-			d->d_bwarns = 0;
-		}
-	} else {
-		if ((!d->d_blk_softlimit ||
-		     (be64_to_cpu(d->d_bcount) <=
-		      be64_to_cpu(d->d_blk_softlimit))) &&
-		    (!d->d_blk_hardlimit ||
-		    (be64_to_cpu(d->d_bcount) <=
-		     be64_to_cpu(d->d_blk_hardlimit)))) {
-			d->d_btimer = 0;
-		}
-	}
-
-	if (!d->d_itimer) {
-		if ((d->d_ino_softlimit &&
-		     (be64_to_cpu(d->d_icount) >
-		      be64_to_cpu(d->d_ino_softlimit))) ||
-		    (d->d_ino_hardlimit &&
-		     (be64_to_cpu(d->d_icount) >
-		      be64_to_cpu(d->d_ino_hardlimit)))) {
-			d->d_itimer = cpu_to_be32(ktime_get_real_seconds() +
-					defq->itimelimit);
-		} else {
-			d->d_iwarns = 0;
-		}
-	} else {
-		if ((!d->d_ino_softlimit ||
-		     (be64_to_cpu(d->d_icount) <=
-		      be64_to_cpu(d->d_ino_softlimit)))  &&
-		    (!d->d_ino_hardlimit ||
-		     (be64_to_cpu(d->d_icount) <=
-		      be64_to_cpu(d->d_ino_hardlimit)))) {
-			d->d_itimer = 0;
-		}
-	}
-
-	if (!d->d_rtbtimer) {
-		if ((d->d_rtb_softlimit &&
-		     (be64_to_cpu(d->d_rtbcount) >
-		      be64_to_cpu(d->d_rtb_softlimit))) ||
-		    (d->d_rtb_hardlimit &&
-		     (be64_to_cpu(d->d_rtbcount) >
-		      be64_to_cpu(d->d_rtb_hardlimit)))) {
-			d->d_rtbtimer = cpu_to_be32(ktime_get_real_seconds() +
-					defq->rtbtimelimit);
-		} else {
-			d->d_rtbwarns = 0;
-		}
-	} else {
-		if ((!d->d_rtb_softlimit ||
-		     (be64_to_cpu(d->d_rtbcount) <=
-		      be64_to_cpu(d->d_rtb_softlimit))) &&
-		    (!d->d_rtb_hardlimit ||
-		     (be64_to_cpu(d->d_rtbcount) <=
-		      be64_to_cpu(d->d_rtb_hardlimit)))) {
-			d->d_rtbtimer = 0;
-		}
-	}
+	xfs_qm_adjust_res_timer(&dq->q_blk, &defq->blk);
+	xfs_qm_adjust_res_timer(&dq->q_ino, &defq->ino);
+	xfs_qm_adjust_res_timer(&dq->q_rtb, &defq->rtb);
 }
 
 /*
···
 	struct xfs_trans	*tp,
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct xfs_buf		*bp)
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
···
 	ASSERT(tp);
 	ASSERT(xfs_buf_islocked(bp));
 
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		qflag = XFS_UQUOTA_CHKD;
+		blftype = XFS_BLF_UDQUOT_BUF;
+		break;
+	case XFS_DQTYPE_PROJ:
+		qflag = XFS_PQUOTA_CHKD;
+		blftype = XFS_BLF_PDQUOT_BUF;
+		break;
+	case XFS_DQTYPE_GROUP:
+		qflag = XFS_GQUOTA_CHKD;
+		blftype = XFS_BLF_GDQUOT_BUF;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
 	d = bp->b_addr;
 
 	/*
···
 		d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
 		d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
 		d->dd_diskdq.d_id = cpu_to_be32(curid);
-		d->dd_diskdq.d_flags = type;
+		d->dd_diskdq.d_type = type;
 		if (xfs_sb_version_hascrc(&mp->m_sb)) {
 			uuid_copy(&d->dd_uuid, &mp->m_sb.sb_meta_uuid);
 			xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
 					 XFS_DQUOT_CRC_OFF);
 		}
-	}
-
-	if (type & XFS_DQ_USER) {
-		qflag = XFS_UQUOTA_CHKD;
-		blftype = XFS_BLF_UDQUOT_BUF;
-	} else if (type & XFS_DQ_PROJ) {
-		qflag = XFS_PQUOTA_CHKD;
-		blftype = XFS_BLF_PDQUOT_BUF;
-	} else {
-		qflag = XFS_GQUOTA_CHKD;
-		blftype = XFS_BLF_GDQUOT_BUF;
 	}
 
 	xfs_trans_dquot_buf(tp, bp, blftype);
···
 {
 	uint64_t space;
 
-	dqp->q_prealloc_hi_wmark = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
-	dqp->q_prealloc_lo_wmark = be64_to_cpu(dqp->q_core.d_blk_softlimit);
+	dqp->q_prealloc_hi_wmark = dqp->q_blk.hardlimit;
+	dqp->q_prealloc_lo_wmark = dqp->q_blk.softlimit;
 	if (!dqp->q_prealloc_lo_wmark) {
 		dqp->q_prealloc_lo_wmark = dqp->q_prealloc_hi_wmark;
 		do_div(dqp->q_prealloc_lo_wmark, 100);
···
 	struct xfs_trans	*tp = *tpp;
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp;
-	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
+	xfs_dqtype_t		qtype = xfs_dquot_type(dqp);
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, qtype);
 	int			nmaps = 1;
 	int			error;
 
 	trace_xfs_dqalloc(dqp);
 
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
-	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
+	if (!xfs_this_quota_on(dqp->q_mount, qtype)) {
 		/*
 		 * Return if this type of quotas is turned off while we didn't
 		 * have an inode lock
···
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
-			      dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
+	xfs_qm_init_dquot_blk(tp, mp, dqp->q_id, qtype, bp);
 	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
 	/*
···
 {
 	struct xfs_bmbt_irec	map;
 	struct xfs_buf		*bp;
-	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
+	xfs_dqtype_t		qtype = xfs_dquot_type(dqp);
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, qtype);
 	uint			lock_mode;
 	int			nmaps = 1;
 	int			error;
 
 	lock_mode = xfs_ilock_data_map_shared(quotip);
-	if (!xfs_this_quota_on(mp, dqp->dq_flags)) {
+	if (!xfs_this_quota_on(mp, qtype)) {
 		/*
 		 * Return if this type of quotas is turned off while we
 		 * didn't have the quota inode lock.
···
 xfs_dquot_alloc(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type)
+	xfs_dqtype_t		type)
 {
 	struct xfs_dquot	*dqp;
 
-	dqp = kmem_zone_zalloc(xfs_qm_dqzone, 0);
+	dqp = kmem_cache_zalloc(xfs_qm_dqzone, GFP_KERNEL | __GFP_NOFAIL);
 
-	dqp->dq_flags = type;
-	dqp->q_core.d_id = cpu_to_be32(id);
+	dqp->q_type = type;
+	dqp->q_id = id;
 	dqp->q_mount = mp;
 	INIT_LIST_HEAD(&dqp->q_lru);
 	mutex_init(&dqp->q_qlock);
···
 	 * quotas.
 	 */
 	switch (type) {
-	case XFS_DQ_USER:
+	case XFS_DQTYPE_USER:
 		/* uses the default lock class */
 		break;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class);
 		break;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class);
 		break;
 	default:
···
 }
 
 /* Copy the in-core quota fields in from the on-disk buffer. */
-STATIC void
+STATIC int
 xfs_dquot_from_disk(
 	struct xfs_dquot	*dqp,
 	struct xfs_buf		*bp)
 {
 	struct xfs_disk_dquot	*ddqp = bp->b_addr + dqp->q_bufoffset;
 
+	/*
+	 * Ensure that we got the type and ID we were looking for.
+	 * Everything else was checked by the dquot buffer verifier.
+	 */
+	if ((ddqp->d_type & XFS_DQTYPE_REC_MASK) != xfs_dquot_type(dqp) ||
+	    be32_to_cpu(ddqp->d_id) != dqp->q_id) {
+		xfs_alert_tag(bp->b_mount, XFS_PTAG_VERIFIER_ERROR,
+			  "Metadata corruption detected at %pS, quota %u",
+			  __this_address, dqp->q_id);
+		xfs_alert(bp->b_mount, "Unmount and run xfs_repair");
+		return -EFSCORRUPTED;
+	}
+
 	/* copy everything from disk dquot to the incore dquot */
-	memcpy(&dqp->q_core, ddqp, sizeof(struct xfs_disk_dquot));
+	dqp->q_type = ddqp->d_type;
+	dqp->q_blk.hardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
+	dqp->q_blk.softlimit = be64_to_cpu(ddqp->d_blk_softlimit);
+	dqp->q_ino.hardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
+	dqp->q_ino.softlimit = be64_to_cpu(ddqp->d_ino_softlimit);
+	dqp->q_rtb.hardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
+	dqp->q_rtb.softlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+
+	dqp->q_blk.count = be64_to_cpu(ddqp->d_bcount);
+	dqp->q_ino.count = be64_to_cpu(ddqp->d_icount);
+	dqp->q_rtb.count = be64_to_cpu(ddqp->d_rtbcount);
+
+	dqp->q_blk.warnings = be16_to_cpu(ddqp->d_bwarns);
+	dqp->q_ino.warnings = be16_to_cpu(ddqp->d_iwarns);
+	dqp->q_rtb.warnings = be16_to_cpu(ddqp->d_rtbwarns);
+
+	dqp->q_blk.timer = be32_to_cpu(ddqp->d_btimer);
+	dqp->q_ino.timer = be32_to_cpu(ddqp->d_itimer);
+	dqp->q_rtb.timer = be32_to_cpu(ddqp->d_rtbtimer);
 
 	/*
 	 * Reservation counters are defined as reservation plus current usage
 	 * to avoid having to add every time.
 	 */
-	dqp->q_res_bcount = be64_to_cpu(ddqp->d_bcount);
-	dqp->q_res_icount = be64_to_cpu(ddqp->d_icount);
-	dqp->q_res_rtbcount = be64_to_cpu(ddqp->d_rtbcount);
+	dqp->q_blk.reserved = dqp->q_blk.count;
+	dqp->q_ino.reserved = dqp->q_ino.count;
+	dqp->q_rtb.reserved = dqp->q_rtb.count;
 
 	/* initialize the dquot speculative prealloc thresholds */
 	xfs_dquot_set_prealloc_limits(dqp);
+	return 0;
+}
+
+/* Copy the in-core quota fields into the on-disk buffer. */
+void
+xfs_dquot_to_disk(
+	struct xfs_disk_dquot	*ddqp,
+	struct xfs_dquot	*dqp)
+{
+	ddqp->d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+	ddqp->d_version = XFS_DQUOT_VERSION;
+	ddqp->d_type = dqp->q_type;
+	ddqp->d_id = cpu_to_be32(dqp->q_id);
+	ddqp->d_pad0 = 0;
+	ddqp->d_pad = 0;
+
+	ddqp->d_blk_hardlimit = cpu_to_be64(dqp->q_blk.hardlimit);
+	ddqp->d_blk_softlimit = cpu_to_be64(dqp->q_blk.softlimit);
+	ddqp->d_ino_hardlimit = cpu_to_be64(dqp->q_ino.hardlimit);
+	ddqp->d_ino_softlimit = cpu_to_be64(dqp->q_ino.softlimit);
+	ddqp->d_rtb_hardlimit = cpu_to_be64(dqp->q_rtb.hardlimit);
+	ddqp->d_rtb_softlimit = cpu_to_be64(dqp->q_rtb.softlimit);
+
+	ddqp->d_bcount = cpu_to_be64(dqp->q_blk.count);
+	ddqp->d_icount = cpu_to_be64(dqp->q_ino.count);
+	ddqp->d_rtbcount = cpu_to_be64(dqp->q_rtb.count);
+
+	ddqp->d_bwarns = cpu_to_be16(dqp->q_blk.warnings);
+	ddqp->d_iwarns = cpu_to_be16(dqp->q_ino.warnings);
+	ddqp->d_rtbwarns = cpu_to_be16(dqp->q_rtb.warnings);
+
+	ddqp->d_btimer = cpu_to_be32(dqp->q_blk.timer);
+	ddqp->d_itimer = cpu_to_be32(dqp->q_ino.timer);
+	ddqp->d_rtbtimer = cpu_to_be32(dqp->q_rtb.timer);
 }
 
 /* Allocate and initialize the dquot buffer for this in-core dquot. */
···
 xfs_qm_dqread(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	bool			can_alloc,
 	struct xfs_dquot	**dqpp)
 {
···
 	 * further.
 	 */
 	ASSERT(xfs_buf_islocked(bp));
-	xfs_dquot_from_disk(dqp, bp);
-
+	error = xfs_dquot_from_disk(dqp, bp);
 	xfs_buf_relse(bp);
+	if (error)
+		goto err;
+
 	*dqpp = dqp;
 	return error;
 
···
 static int
 xfs_dq_get_next_id(
 	struct xfs_mount	*mp,
-	uint			type,
+	xfs_dqtype_t		type,
 	xfs_dqid_t		*id)
 {
 	struct xfs_inode	*quotip = xfs_quota_inode(mp, type);
···
 	}
 
 	xfs_dqlock(dqp);
-	if (dqp->dq_flags & XFS_DQ_FREEING) {
+	if (dqp->q_flags & XFS_DQFLAG_FREEING) {
 		xfs_dqunlock(dqp);
 		mutex_unlock(&qi->qi_tree_lock);
 		trace_xfs_dqget_freeing(dqp);
···
 static int
 xfs_qm_dqget_checks(
 	struct xfs_mount	*mp,
-	uint			type)
+	xfs_dqtype_t		type)
 {
 	if (WARN_ON_ONCE(!XFS_IS_QUOTA_RUNNING(mp)))
 		return -ESRCH;
 
 	switch (type) {
-	case XFS_DQ_USER:
+	case XFS_DQTYPE_USER:
 		if (!XFS_IS_UQUOTA_ON(mp))
 			return -ESRCH;
 		return 0;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		if (!XFS_IS_GQUOTA_ON(mp))
 			return -ESRCH;
 		return 0;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		if (!XFS_IS_PQUOTA_ON(mp))
 			return -ESRCH;
 		return 0;
···
 xfs_qm_dqget(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	bool			can_alloc,
 	struct xfs_dquot	**O_dqpp)
 {
···
 xfs_qm_dqget_uncached(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct xfs_dquot	**dqpp)
 {
 	int			error;
···
 xfs_dqid_t
 xfs_qm_id_for_quotatype(
 	struct xfs_inode	*ip,
-	uint			type)
+	xfs_dqtype_t		type)
 {
 	switch (type) {
-	case XFS_DQ_USER:
+	case XFS_DQTYPE_USER:
 		return i_uid_read(VFS_I(ip));
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return i_gid_read(VFS_I(ip));
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return ip->i_d.di_projid;
 	}
 	ASSERT(0);
···
 int
 xfs_qm_dqget_inode(
 	struct xfs_inode	*ip,
-	uint			type,
+	xfs_dqtype_t		type,
 	bool			can_alloc,
 	struct xfs_dquot	**O_dqpp)
 {
···
 xfs_qm_dqget_next(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct xfs_dquot	**dqpp)
 {
 	struct xfs_dquot	*dqp;
···
  * from the AIL if it has not been re-logged, and unlocking the dquot's
  * flush lock. This behavior is very similar to that of inodes..
  */
-STATIC void
+static void
 xfs_qm_dqflush_done(
-	struct xfs_buf		*bp,
 	struct xfs_log_item	*lip)
 {
 	struct xfs_dq_logitem	*qip = (struct xfs_dq_logitem *)lip;
···
 	     test_bit(XFS_LI_FAILED, &lip->li_flags))) {
 
 		spin_lock(&ailp->ail_lock);
+		xfs_clear_li_failed(lip);
 		if (lip->li_lsn == qip->qli_flush_lsn) {
 			/* xfs_ail_update_finish() drops the AIL lock */
 			tail_lsn = xfs_ail_delete_one(ailp, lip);
 			xfs_ail_update_finish(ailp, tail_lsn);
 		} else {
-			/*
-			 * Clear the failed state since we are about to drop the
-			 * flush lock
-			 */
-			xfs_clear_li_failed(lip);
 			spin_unlock(&ailp->ail_lock);
 		}
 	}
···
 	 * Release the dq's flush lock since we're done with it.
 	 */
 	xfs_dqfunlock(dqp);
+}
+
+void
+xfs_dquot_done(
+	struct xfs_buf		*bp)
+{
+	struct xfs_log_item	*lip, *n;
+
+	list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
+		list_del_init(&lip->li_bio_list);
+		xfs_qm_dqflush_done(lip);
+	}
+}
+
+/* Check incore dquot for errors before we flush. */
+static xfs_failaddr_t
+xfs_qm_dqflush_check(
+	struct xfs_dquot	*dqp)
+{
+	xfs_dqtype_t		type = xfs_dquot_type(dqp);
+
+	if (type != XFS_DQTYPE_USER &&
+	    type != XFS_DQTYPE_GROUP &&
+	    type != XFS_DQTYPE_PROJ)
+		return __this_address;
+
+	if (dqp->q_id == 0)
+		return NULL;
+
+	if (dqp->q_blk.softlimit && dqp->q_blk.count > dqp->q_blk.softlimit &&
+	    !dqp->q_blk.timer)
+		return __this_address;
+
+	if (dqp->q_ino.softlimit && dqp->q_ino.count > dqp->q_ino.softlimit &&
+	    !dqp->q_ino.timer)
+		return __this_address;
+
+	if (dqp->q_rtb.softlimit && dqp->q_rtb.count > dqp->q_rtb.softlimit &&
+	    !dqp->q_rtb.timer)
+		return __this_address;
+
+	return NULL;
 }
 
 /*
···
 	struct xfs_mount	*mp = dqp->q_mount;
 	struct xfs_log_item	*lip = &dqp->q_logitem.qli_item;
 	struct xfs_buf		*bp;
-	struct xfs_dqblk	*dqb;
-	struct xfs_disk_dquot	*ddqp;
+	struct xfs_dqblk	*dqblk;
 	xfs_failaddr_t		fa;
 	int			error;
 
···
 	if (error)
 		goto out_abort;
 
-	/*
-	 * Calculate the location of the dquot inside the buffer.
-	 */
-	dqb = bp->b_addr + dqp->q_bufoffset;
-	ddqp = &dqb->dd_diskdq;
-
-	/* sanity check the in-core structure before we flush */
-	fa = xfs_dquot_verify(mp, &dqp->q_core, be32_to_cpu(dqp->q_core.d_id),
-			      0);
+	fa = xfs_qm_dqflush_check(dqp);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
-				be32_to_cpu(dqp->q_core.d_id), fa);
+				dqp->q_id, fa);
 		xfs_buf_relse(bp);
 		error = -EFSCORRUPTED;
 		goto out_abort;
 	}
 
-	/* This is the only portion of data that needs to persist */
-	memcpy(ddqp, &dqp->q_core, sizeof(struct xfs_disk_dquot));
+	/* Flush the incore dquot to the ondisk buffer. */
+	dqblk = bp->b_addr + dqp->q_bufoffset;
+	xfs_dquot_to_disk(&dqblk->dd_diskdq, dqp);
 
 	/*
 	 * Clear the dirty field and remember the flush lsn for later use.
 	 */
-	dqp->dq_flags &= ~XFS_DQ_DIRTY;
+	dqp->q_flags &= ~XFS_DQFLAG_DIRTY;
 
 	xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn,
 					&dqp->q_logitem.qli_item.li_lsn);
···
 	 * of a dquot without an up-to-date CRC getting to disk.
 	 */
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
-		dqb->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn);
-		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
+		dqblk->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn);
+		xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
 	}
 
 	/*
-	 * Attach an iodone routine so that we can remove this dquot from the
-	 * AIL and release the flush lock once the dquot is synced to disk.
+	 * Attach the dquot to the buffer so that we can remove this dquot from
+	 * the AIL and release the flush lock once the dquot is synced to disk.
 	 */
-	xfs_buf_attach_iodone(bp, xfs_qm_dqflush_done,
-				  &dqp->q_logitem.qli_item);
+	bp->b_flags |= _XBF_DQUOTS;
+	list_add_tail(&dqp->q_logitem.qli_item.li_bio_list, &bp->b_li_list);
 
 	/*
 	 * If the buffer is pinned then push on the log so we won't
···
 	return 0;
 
 out_abort:
-	dqp->dq_flags &= ~XFS_DQ_DIRTY;
+	dqp->q_flags &= ~XFS_DQFLAG_DIRTY;
 	xfs_trans_ail_delete(lip, 0);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 out_unlock:
···
 {
 	if (d1 && d2) {
 		ASSERT(d1 != d2);
-		if (be32_to_cpu(d1->q_core.d_id) >
-		    be32_to_cpu(d2->q_core.d_id)) {
+		if (d1->q_id > d2->q_id) {
 			mutex_lock(&d2->q_qlock);
 			mutex_lock_nested(&d1->q_qlock, XFS_QLOCK_NESTED);
 		} else {
···
 int
 xfs_qm_dqiterate(
 	struct xfs_mount	*mp,
-	uint			dqtype,
+	xfs_dqtype_t		type,
 	xfs_qm_dqiterate_fn	iter_fn,
 	void			*priv)
 {
···
 	int			error;
 
 	do {
-		error = xfs_qm_dqget_next(mp, id, dqtype, &dq);
+		error = xfs_qm_dqget_next(mp, id, type, &dq);
 		if (error == -ENOENT)
 			return 0;
 		if (error)
 			return error;
 
-		error = iter_fn(dq, dqtype, priv);
-		id = be32_to_cpu(dq->q_core.d_id);
+		error = iter_fn(dq, type, priv);
+		id = dq->q_id;
 		xfs_qm_dqput(dq);
-		id++;
 	} while (error == 0 && id != 0);
 
 	return error;

fs/xfs/xfs_dquot.h

···
 	XFS_QLOWSP_MAX
 };
 
+struct xfs_dquot_res {
+	/* Total resources allocated and reserved. */
+	xfs_qcnt_t		reserved;
+
+	/* Total resources allocated. */
+	xfs_qcnt_t		count;
+
+	/* Absolute and preferred limits. */
+	xfs_qcnt_t		hardlimit;
+	xfs_qcnt_t		softlimit;
+
+	/*
+	 * For root dquots, this is the default grace period, in seconds.
+	 * Otherwise, this is when the quota grace period expires,
+	 * in seconds since the Unix epoch.
+	 */
+	time64_t		timer;
+
+	/*
+	 * For root dquots, this is the maximum number of warnings that will
+	 * be issued for this quota type.  Otherwise, this is the number of
+	 * warnings issued against this quota.  Note that none of this is
+	 * implemented.
+	 */
+	xfs_qwarncnt_t		warnings;
+};
+
 /*
  * The incore dquot structure
  */
 struct xfs_dquot {
-	uint			dq_flags;
 	struct list_head	q_lru;
 	struct xfs_mount	*q_mount;
+	xfs_dqtype_t		q_type;
+	uint16_t		q_flags;
+	xfs_dqid_t		q_id;
 	uint			q_nrefs;
-	xfs_daddr_t		q_blkno;
 	int			q_bufoffset;
+	xfs_daddr_t		q_blkno;
 	xfs_fileoff_t		q_fileoffset;
 
-	struct xfs_disk_dquot	q_core;
+	struct xfs_dquot_res	q_blk;	/* regular blocks */
+	struct xfs_dquot_res	q_ino;	/* inodes */
+	struct xfs_dquot_res	q_rtb;	/* realtime blocks */
+
 	struct xfs_dq_logitem	q_logitem;
-	/* total regular nblks used+reserved */
-	xfs_qcnt_t		q_res_bcount;
-	/* total inos allocd+reserved */
-	xfs_qcnt_t		q_res_icount;
-	/* total realtime blks used+reserved */
-	xfs_qcnt_t		q_res_rtbcount;
+
 	xfs_qcnt_t		q_prealloc_lo_wmark;
 	xfs_qcnt_t		q_prealloc_hi_wmark;
 	int64_t			q_low_space[XFS_QLOWSP_MAX];
···
 	mutex_unlock(&dqp->q_qlock);
 }
 
-static inline int xfs_this_quota_on(struct xfs_mount *mp, int type)
+static inline int
+xfs_dquot_type(const struct xfs_dquot *dqp)
 {
-	switch (type & XFS_DQ_ALLTYPES) {
-	case XFS_DQ_USER:
+	return dqp->q_type & XFS_DQTYPE_REC_MASK;
+}
+
+static inline int xfs_this_quota_on(struct xfs_mount *mp, xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return XFS_IS_UQUOTA_ON(mp);
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return XFS_IS_GQUOTA_ON(mp);
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return XFS_IS_PQUOTA_ON(mp);
 	default:
 		return 0;
 	}
 }
 
-static inline struct xfs_dquot *xfs_inode_dquot(struct xfs_inode *ip, int type)
+static inline struct xfs_dquot *xfs_inode_dquot(
+	struct xfs_inode	*ip,
+	xfs_dqtype_t		type)
 {
-	switch (type & XFS_DQ_ALLTYPES) {
-	case XFS_DQ_USER:
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return ip->i_udquot;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return ip->i_gdquot;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return ip->i_pdquot;
 	default:
 		return NULL;
 	}
+}
+
+/* Decide if the dquot's limits are actually being enforced. */
+static inline bool
+xfs_dquot_is_enforced(
+	const struct xfs_dquot	*dqp)
+{
+	switch (xfs_dquot_type(dqp)) {
+	case XFS_DQTYPE_USER:
+		return XFS_IS_UQUOTA_ENFORCED(dqp->q_mount);
+	case XFS_DQTYPE_GROUP:
+		return XFS_IS_GQUOTA_ENFORCED(dqp->q_mount);
+	case XFS_DQTYPE_PROJ:
+		return XFS_IS_PQUOTA_ENFORCED(dqp->q_mount);
+	}
+	ASSERT(0);
+	return false;
 }
 
 /*
···
 {
 	int64_t freesp;
 
-	freesp = be64_to_cpu(dqp->q_core.d_blk_hardlimit) - dqp->q_res_bcount;
+	freesp = dqp->q_blk.hardlimit - dqp->q_blk.reserved;
 	if (freesp < dqp->q_low_space[XFS_QLOWSP_1_PCNT])
 		return true;
 
 	return false;
 }
 
+void xfs_dquot_to_disk(struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp);
+
 #define XFS_DQ_IS_LOCKED(dqp)	(mutex_is_locked(&((dqp)->q_qlock)))
-#define XFS_DQ_IS_DIRTY(dqp)	((dqp)->dq_flags & XFS_DQ_DIRTY)
-#define XFS_QM_ISUDQ(dqp)	((dqp)->dq_flags & XFS_DQ_USER)
-#define XFS_QM_ISPDQ(dqp)	((dqp)->dq_flags & XFS_DQ_PROJ)
-#define XFS_QM_ISGDQ(dqp)	((dqp)->dq_flags & XFS_DQ_GROUP)
+#define XFS_DQ_IS_DIRTY(dqp)	((dqp)->q_flags & XFS_DQFLAG_DIRTY)
 
 void		xfs_qm_dqdestroy(struct xfs_dquot *dqp);
 int		xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf **bpp);
 void		xfs_qm_dqunpin_wait(struct xfs_dquot *dqp);
-void		xfs_qm_adjust_dqtimers(struct xfs_mount *mp,
-						struct xfs_dquot *d);
-void		xfs_qm_adjust_dqlimits(struct xfs_mount *mp,
-						struct xfs_dquot *d);
-xfs_dqid_t	xfs_qm_id_for_quotatype(struct xfs_inode *ip, uint type);
+void		xfs_qm_adjust_dqtimers(struct xfs_dquot *d);
+void		xfs_qm_adjust_dqlimits(struct xfs_dquot *d);
+xfs_dqid_t	xfs_qm_id_for_quotatype(struct xfs_inode *ip,
+				xfs_dqtype_t type);
 int		xfs_qm_dqget(struct xfs_mount *mp, xfs_dqid_t id,
-					uint type, bool can_alloc,
-					struct xfs_dquot **dqpp);
-int		xfs_qm_dqget_inode(struct xfs_inode *ip, uint type,
-						bool can_alloc,
-						struct xfs_dquot **dqpp);
+				xfs_dqtype_t type, bool can_alloc,
+				struct xfs_dquot **dqpp);
+int		xfs_qm_dqget_inode(struct xfs_inode *ip, xfs_dqtype_t type,
+				bool can_alloc, struct xfs_dquot **dqpp);
 int		xfs_qm_dqget_next(struct xfs_mount *mp, xfs_dqid_t id,
-					uint type, struct xfs_dquot **dqpp);
+				xfs_dqtype_t type, struct xfs_dquot **dqpp);
 int		xfs_qm_dqget_uncached(struct xfs_mount *mp,
-						xfs_dqid_t id, uint type,
-						struct xfs_dquot **dqpp);
+				xfs_dqid_t id, xfs_dqtype_t type,
+				struct xfs_dquot **dqpp);
 void		xfs_qm_dqput(struct xfs_dquot *dqp);
 
 void		xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
···
 	return dqp;
 }
 
-typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq, uint dqtype,
-		void *priv);
-int xfs_qm_dqiterate(struct xfs_mount *mp, uint dqtype,
+typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq,
+		xfs_dqtype_t type, void *priv);
+int xfs_qm_dqiterate(struct xfs_mount *mp, xfs_dqtype_t type,
 		xfs_qm_dqiterate_fn iter_fn, void *priv);
 
 #endif /* __XFS_DQUOT_H__ */

fs/xfs/xfs_dquot_item.c

···
 	struct xfs_log_item	*lip,
 	struct xfs_log_vec	*lv)
 {
+	struct xfs_disk_dquot	ddq;
 	struct xfs_dq_logitem	*qlip = DQUOT_ITEM(lip);
 	struct xfs_log_iovec	*vecp = NULL;
 	struct xfs_dq_logformat	*qlf;
···
 	qlf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_QFORMAT);
 	qlf->qlf_type = XFS_LI_DQUOT;
 	qlf->qlf_size = 2;
-	qlf->qlf_id = be32_to_cpu(qlip->qli_dquot->q_core.d_id);
+	qlf->qlf_id = qlip->qli_dquot->q_id;
 	qlf->qlf_blkno = qlip->qli_dquot->q_blkno;
 	qlf->qlf_len = 1;
 	qlf->qlf_boffset = qlip->qli_dquot->q_bufoffset;
 	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_dq_logformat));
 
-	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_DQUOT,
-			&qlip->qli_dquot->q_core,
+	xfs_dquot_to_disk(&ddq, qlip->qli_dquot);
+
+	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_DQUOT, &ddq,
 			sizeof(struct xfs_disk_dquot));
 }
 
···
 	 */
 	xfs_log_force(dqp->q_mount, 0);
 	wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
-}
-
-/*
- * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer
- * have been failed during writeback
- *
- * this informs the AIL that the dquot is already flush locked on the next push,
- * and acquires a hold on the buffer to ensure that it isn't reclaimed before
- * dirty data makes it to disk.
- */
-STATIC void
-xfs_dquot_item_error(
-	struct xfs_log_item	*lip,
-	struct xfs_buf		*bp)
-{
-	ASSERT(!completion_done(&DQUOT_ITEM(lip)->qli_dquot->q_flush));
-	xfs_set_li_failed(lip, bp);
 }
 
 STATIC uint
···
 	.iop_release	= xfs_qm_dquot_logitem_release,
 	.iop_committing	= xfs_qm_dquot_logitem_committing,
 	.iop_push	= xfs_qm_dquot_logitem_push,
-	.iop_error	= xfs_dquot_item_error
 };
 
 /*

fs/xfs/xfs_dquot_item_recover.c

···
 	if (item->ri_buf[1].i_len < sizeof(struct xfs_disk_dquot))
 		return;
 
-	type = recddq->d_flags & (XFS_DQ_USER | XFS_DQ_PROJ | XFS_DQ_GROUP);
+	type = recddq->d_type & XFS_DQTYPE_REC_MASK;
 	ASSERT(type);
 	if (log->l_quotaoffs_flag & type)
 		return;
···
 	/*
 	 * This type of quotas was turned off, so ignore this record.
 	 */
-	type = recddq->d_flags & (XFS_DQ_USER | XFS_DQ_PROJ | XFS_DQ_GROUP);
+	type = recddq->d_type & XFS_DQTYPE_REC_MASK;
 	ASSERT(type);
 	if (log->l_quotaoffs_flag & type)
 		return 0;
···
 	 */
 	dq_f = item->ri_buf[0].i_addr;
 	ASSERT(dq_f);
-	fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id, 0);
+	fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in log at %pS",
 				dq_f->qlf_id, fa);
···
 
 	ASSERT(dq_f->qlf_size == 2);
 	ASSERT(bp->b_mount == mp);
-	bp->b_iodone = xlog_recover_iodone;
+	bp->b_flags |= _XBF_LOGRECOVERY;
 	xfs_buf_delwri_queue(bp, buffer_list);
 
 out_release:
···
 	 * group/project quotaoff or both.
 	 */
 	if (qoff_f->qf_flags & XFS_UQUOTA_ACCT)
-		log->l_quotaoffs_flag |= XFS_DQ_USER;
+		log->l_quotaoffs_flag |= XFS_DQTYPE_USER;
 	if (qoff_f->qf_flags & XFS_PQUOTA_ACCT)
-		log->l_quotaoffs_flag |= XFS_DQ_PROJ;
+		log->l_quotaoffs_flag |= XFS_DQTYPE_PROJ;
 	if (qoff_f->qf_flags & XFS_GQUOTA_ACCT)
-		log->l_quotaoffs_flag |= XFS_DQ_GROUP;
+		log->l_quotaoffs_flag |= XFS_DQTYPE_GROUP;
 
 	return 0;
 }

fs/xfs/xfs_extfree_item.c

···
 			((nextents - 1) * sizeof(xfs_extent_t)));
 		efip = kmem_zalloc(size, 0);
 	} else {
-		efip = kmem_zone_zalloc(xfs_efi_zone, 0);
+		efip = kmem_cache_zalloc(xfs_efi_zone,
+					 GFP_KERNEL | __GFP_NOFAIL);
 	}
 
 	xfs_log_item_init(mp, &efip->efi_item, XFS_LI_EFI, &xfs_efi_item_ops);
···
 				(nextents - 1) * sizeof(struct xfs_extent),
 				0);
 	} else {
-		efdp = kmem_zone_zalloc(xfs_efd_zone, 0);
+		efdp = kmem_cache_zalloc(xfs_efd_zone,
+					GFP_KERNEL | __GFP_NOFAIL);
 	}
 
 	xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,

fs/xfs/xfs_file.c

···
 {
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_inode_log_item *iip = ip->i_itemp;
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error = 0;
 	int			log_flushed = 0;
···
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	if (xfs_ipincount(ip)) {
 		if (!datasync ||
-		    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
-			lsn = ip->i_itemp->ili_last_lsn;
+		    (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+			lsn = iip->ili_last_lsn;
 	}
 
 	if (lsn) {
 		error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
-		ip->i_itemp->ili_fsync_fields = 0;
+		spin_lock(&iip->ili_lock);
+		iip->ili_fsync_fields = 0;
+		spin_unlock(&iip->ili_lock);
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
···
 	/* Prepare and then clone file data. */
 	ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
 			&len, remap_flags);
-	if (ret < 0 || len == 0)
+	if (ret || len == 0)
 		return ret;
 
 	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
···
 	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_log_force_inode(dest);
 out_unlock:
-	xfs_reflink_remap_unlock(file_in, file_out);
+	xfs_iunlock2_io_mmap(src, dest);
 	if (ret)
 		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
 	return remapped > 0 ? remapped : ret;
···
 	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
 }
 
+static void
+xfs_filemap_map_pages(
+	struct vm_fault		*vmf,
+	pgoff_t			start_pgoff,
+	pgoff_t			end_pgoff)
+{
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
+
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	filemap_map_pages(vmf, start_pgoff, end_pgoff);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+}
+
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
 	.huge_fault	= xfs_filemap_huge_fault,
-	.map_pages	= filemap_map_pages,
+	.map_pages	= xfs_filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
 };

fs/xfs/xfs_icache.c

···
 	struct xfs_inode	*ip;
 
 	/*
-	 * if this didn't occur in transactions, we could use
-	 * KM_MAYFAIL and return NULL here on ENOMEM. Set the
-	 * code up to do this anyway.
+	 * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL
+	 * and return NULL here on ENOMEM.
 	 */
-	ip = kmem_zone_alloc(xfs_inode_zone, 0);
-	if (!ip)
-		return NULL;
+	ip = kmem_cache_alloc(xfs_inode_zone, GFP_KERNEL | __GFP_NOFAIL);
+
 	if (inode_init_always(mp->m_super, VFS_I(ip))) {
 		kmem_cache_free(xfs_inode_zone, ip);
 		return NULL;
···
 {
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
 	XFS_STATS_DEC(ip->i_mount, vn_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
···
 }
 
 /*
- * Queue a new inode reclaim pass if there are reclaimable inodes and there
- * isn't a reclaim pass already in progress. By default it runs every 5s based
- * on the xfs periodic sync default of 30s. Perhaps this should have it's own
- * tunable, but that can be done if this method proves to be ineffective or too
- * aggressive.
+ * Queue background inode reclaim work if there are reclaimable inodes and there
+ * isn't reclaim work already scheduled or in progress.
  */
 static void
 xfs_reclaim_work_queue(
···
 			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
 	}
 	rcu_read_unlock();
-}
-
-/*
- * This is a fast pass over the inode cache to try to get reclaim moving on as
- * many inodes as possible in a short period of time. It kicks itself every few
- * seconds, as well as being kicked by the inode cache shrinker when memory
- * goes low. It scans as quickly as possible avoiding locked inodes or those
- * already being flushed, and once done schedules a future pass.
- */
-void
-xfs_reclaim_worker(
-	struct work_struct *work)
-{
-	struct xfs_mount *mp = container_of(to_delayed_work(work),
-					struct xfs_mount, m_reclaim_work);
-
-	xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
-	xfs_reclaim_work_queue(mp);
 }
 
 static void
···
 }
 
 /*
- * Look up an inode by number in the given file system.
- * The inode is looked up in the cache held in each AG.
- * If the inode is found in the cache, initialise the vfs inode
- * if necessary.
+ * Look up an inode by number in the given file system.  The inode is looked up
+ * in the cache held in each AG.  If the inode is found in the cache, initialise
+ * the vfs inode if necessary.
  *
- * If it is not in core, read it in from the file system's device,
- * add it to the cache and initialise the vfs inode.
+ * If it is not in core, read it in from the file system's device, add it to the
+ * cache and initialise the vfs inode.
  *
  * The inode is locked according to the value of the lock_flags parameter.
- * This flag parameter indicates how and if the inode's IO lock and inode lock
- * should be taken.
- *
- * mp -- the mount point structure for the current file system.  It points
- *       to the inode hash table.
- * tp -- a pointer to the current transaction if there is one.  This is
- *       simply passed through to the xfs_iread() call.
- * ino -- the number of the inode desired.  This is the unique identifier
- *        within the file system for the inode being requested.
- * lock_flags -- flags indicating how to lock the inode.  See the comment
- *		 for xfs_ilock() for a list of valid values.
+ * Inode lookup is only done during metadata operations and not as part of the
+ * data IO path. Hence we only allow locking of the XFS_ILOCK during lookup.
  */
 int
 xfs_iget(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	uint		flags,
-	uint		lock_flags,
-	xfs_inode_t	**ipp)
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino,
+	uint			flags,
+	uint			lock_flags,
+	struct xfs_inode	**ipp)
 {
-	xfs_inode_t	*ip;
-	int		error;
-	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
+	struct xfs_inode	*ip;
+	struct xfs_perag	*pag;
+	xfs_agino_t		agino;
+	int			error;
 
-	/*
-	 * xfs_reclaim_inode() uses the ILOCK to ensure an inode
-	 * doesn't get freed while it's being referenced during a
-	 * radix tree traversal here.  It assumes this function
-	 * aqcuires only the ILOCK (and therefore it has no need to
-	 * involve the IOLOCK in this synchronization).
-	 */
 	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
 
 	/* reject inode numbers outside existing AGs */
···
 
 	ASSERT(rcu_read_lock_held());
 
-	/*
-	 * check for stale RCU freed inode
-	 *
-	 * If the inode has been reallocated, it doesn't matter if it's not in
-	 * the AG we are walking - we are walking for writeback, so if it
-	 * passes all the "valid inode" checks and is dirty, then we'll write
-	 * it back anyway.  If it has been reallocated and still being
-	 * initialised, the XFS_INEW check below will catch it.
-	 */
+	/* Check for stale RCU freed inode */
 	spin_lock(&ip->i_flags_lock);
 	if (!ip->i_ino)
 		goto out_unlock_noent;
···
 
 /*
  * Grab the inode for reclaim exclusively.
- * Return 0 if we grabbed it, non-zero otherwise.
+ *
+ * We have found this inode via a lookup under RCU, so the inode may have
+ * already been freed, or it may be in the process of being recycled by
+ * xfs_iget(). In both cases, the inode will have XFS_IRECLAIM set. If the inode
+ * has been fully recycled by the time we get the i_flags_lock, XFS_IRECLAIMABLE
+ * will not be set. Hence we need to check for both these flag conditions to
+ * avoid inodes that are no longer reclaim candidates.
+ *
+ * Note: checking for other state flags here, under the i_flags_lock or not, is
+ * racy and should be avoided. Those races should be resolved only after we have
+ * ensured that we are able to reclaim this inode and the world can see that we
+ * are going to reclaim it.
+ *
+ * Return true if we grabbed it, false otherwise.
  */
-STATIC int
+static bool
 xfs_reclaim_inode_grab(
-	struct xfs_inode	*ip,
-	int			flags)
+	struct xfs_inode	*ip)
 {
 	ASSERT(rcu_read_lock_held());
 
-	/* quick check for stale RCU freed inode */
-	if (!ip->i_ino)
-		return 1;
-
-	/*
-	 * If we are asked for non-blocking operation, do unlocked checks to
-	 * see if the inode already is being flushed or in reclaim to avoid
-	 * lock traffic.
-	 */
-	if ((flags & SYNC_TRYLOCK) &&
-	    __xfs_iflags_test(ip, XFS_IFLOCK | XFS_IRECLAIM))
-		return 1;
-
-	/*
-	 * The radix tree lock here protects a thread in xfs_iget from racing
-	 * with us starting reclaim on the inode.  Once we have the
-	 * XFS_IRECLAIM flag set it will not touch us.
-	 *
-	 * Due to RCU lookup, we may find inodes that have been freed and only
-	 * have XFS_IRECLAIM set.  Indeed, we may see reallocated inodes that
-	 * aren't candidates for reclaim at all, so we must check the
-	 * XFS_IRECLAIMABLE is set first before proceeding to reclaim.
-	 */
 	spin_lock(&ip->i_flags_lock);
 	if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) ||
 	    __xfs_iflags_test(ip, XFS_IRECLAIM)) {
 		/* not a reclaim candidate. */
 		spin_unlock(&ip->i_flags_lock);
-		return 1;
+		return false;
 	}
 	__xfs_iflags_set(ip, XFS_IRECLAIM);
 	spin_unlock(&ip->i_flags_lock);
-	return 0;
+	return true;
 }
 
 /*
- * Inodes in different states need to be treated differently. The following
- * table lists the inode states and the reclaim actions necessary:
+ * Inode reclaim is non-blocking, so the default action if progress cannot be
+ * made is to "requeue" the inode for reclaim by unlocking it and clearing the
+ * XFS_IRECLAIM flag.  If we are in a shutdown state, we don't care about
+ * blocking anymore and hence we can wait for the inode to be able to reclaim
+ * it.
  *
- *	inode state	     iflush ret		required action
- *      ---------------      ----------         ---------------
- *	bad			-		reclaim
- *	shutdown		EIO		unpin and reclaim
- *	clean, unpinned		0		reclaim
- *	stale, unpinned		0		reclaim
- *	clean, pinned(*)	0		requeue
- *	stale, pinned		EAGAIN		requeue
- *	dirty, async		-		requeue
- *	dirty, sync		0		reclaim
- *
- * (*) dgc: I don't think the clean, pinned state is possible but it gets
- * handled anyway given the order of checks implemented.
- *
- * Also, because we get the flush lock first, we know that any inode that has
- * been flushed delwri has had the flush completed by the time we check that
- * the inode is clean.
- *
- * Note that because the inode is flushed delayed write by AIL pushing, the
- * flush lock may already be held here and waiting on it can result in very
- * long latencies.  Hence for sync reclaims, where we wait on the flush lock,
- * the caller should push the AIL first before trying to reclaim inodes to
- * minimise the amount of time spent waiting.  For background relaim, we only
- * bother to reclaim clean inodes anyway.
- *
- * Hence the order of actions after gaining the locks should be:
- *	bad		=> reclaim
- *	shutdown	=> unpin and reclaim
- *	pinned, async	=> requeue
- *	pinned, sync	=> unpin
- *	stale		=> reclaim
- *	clean		=> reclaim
- *	dirty, async	=> requeue
- *	dirty, sync	=> flush, wait and reclaim
+ * We do no IO here - if callers require inodes to be cleaned they must push the
+ * AIL first to trigger writeback of dirty inodes.  This enables writeback to be
+ * done in the background in a non-blocking manner, and enables memory reclaim
+ * to make progress without blocking.
  */
-STATIC int
+static void
 xfs_reclaim_inode(
 	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	int			sync_mode)
+	struct xfs_perag	*pag)
 {
-	struct xfs_buf		*bp = NULL;
 	xfs_ino_t		ino = ip->i_ino; /* for radix_tree_delete */
-	int			error;
 
-restart:
-	error = 0;
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (!xfs_iflock_nowait(ip)) {
-		if (!(sync_mode & SYNC_WAIT))
-			goto out;
-		xfs_iflock(ip);
-	}
+	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		goto out;
+	if (!xfs_iflock_nowait(ip))
+		goto out_iunlock;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
···
 		xfs_iflush_abort(ip);
 		goto reclaim;
 	}
-	if (xfs_ipincount(ip)) {
-		if (!(sync_mode & SYNC_WAIT))
-			goto out_ifunlock;
-		xfs_iunpin_wait(ip);
-	}
-	if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		goto reclaim;
-	}
-
-	/*
-	 * Never flush out dirty data during non-blocking reclaim, as it would
-	 * just contend with AIL pushing trying to do the same job.
-	 */
-	if (!(sync_mode & SYNC_WAIT))
+	if (xfs_ipincount(ip))
+		goto out_ifunlock;
+	if (!xfs_inode_clean(ip))
 		goto out_ifunlock;
 
-	/*
-	 * Now we have an inode that needs flushing.
-	 *
-	 * Note that xfs_iflush will never block on the inode buffer lock, as
-	 * 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_imap_to_bp() to get the cluster buffer would
-	 * 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 here,  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, &bp);
-	if (error == -EAGAIN) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		/* backoff longer than in xfs_ifree_cluster */
-		delay(2);
-		goto restart;
-	}
-
-	if (!error) {
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-	}
-
+	xfs_ifunlock(ip);
 reclaim:
 	ASSERT(!xfs_isiflocked(ip));
 
···
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_qm_dqdetach(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	ASSERT(xfs_inode_clean(ip));
 
 	__xfs_inode_free(ip);
-	return error;
+	return;
 
 out_ifunlock:
 	xfs_ifunlock(ip);
+out_iunlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
 	xfs_iflags_clear(ip, XFS_IRECLAIM);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	/*
-	 * We could return -EAGAIN here to make reclaim rescan the inode tree in
-	 * a short while. However, this just burns CPU time scanning the tree
-	 * waiting for IO to complete and the reclaim work never goes back to
-	 * the idle state. Instead, return 0 to let the next scheduled
-	 * background reclaim attempt to reclaim the inode again.
-	 */
-	return 0;
 }
 
 /*
···
  * corrupted, we still want to try to reclaim all the inodes. If we don't,
  * then a shut down during filesystem unmount reclaim walk leak all the
  * unreclaimed inodes.
+ *
+ * Returns non-zero if any AGs or inodes were skipped in the reclaim pass
+ * so that callers that want to block until all dirty inodes are written back
+ * and reclaimed can sanely loop.
  */
-STATIC int
+static void
 xfs_reclaim_inodes_ag(
 	struct xfs_mount	*mp,
-	int			flags,
 	int			*nr_to_scan)
 {
 	struct xfs_perag	*pag;
-	int			error = 0;
-	int			last_error = 0;
-	xfs_agnumber_t		ag;
-	int			trylock = flags & SYNC_TRYLOCK;
-	int			skipped;
+	xfs_agnumber_t		ag = 0;
 
-restart:
-	ag = 0;
-	skipped = 0;
 	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
 		unsigned long	first_index = 0;
 		int		done = 0;
···
 
 		ag = pag->pag_agno + 1;
 
-		if (trylock) {
-			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
-				skipped++;
-				xfs_perag_put(pag);
-				continue;
-			}
-			first_index = pag->pag_ici_reclaim_cursor;
-		} else
-			mutex_lock(&pag->pag_ici_reclaim_lock);
-
+		first_index = READ_ONCE(pag->pag_ici_reclaim_cursor);
 		do {
 			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
 			int	i;
···
 			for (i = 0; i < nr_found; i++) {
 				struct xfs_inode *ip = batch[i];
 
-				if (done || xfs_reclaim_inode_grab(ip, flags))
+				if (done || !xfs_reclaim_inode_grab(ip))
 					batch[i] = NULL;
 
 				/*
···
 			rcu_read_unlock();
 
 			for (i = 0; i < nr_found; i++) {
-				if (!batch[i])
-					continue;
-				error = xfs_reclaim_inode(batch[i], pag, flags);
-				if (error && last_error != -EFSCORRUPTED)
-					last_error = error;
+				if (batch[i])
+					xfs_reclaim_inode(batch[i], pag);
 			}
 
 			*nr_to_scan -= XFS_LOOKUP_BATCH;
-
 			cond_resched();
-
 		} while (nr_found && !done && *nr_to_scan > 0);
 
-		if (trylock && !done)
-			pag->pag_ici_reclaim_cursor = first_index;
-		else
-			pag->pag_ici_reclaim_cursor = 0;
-		mutex_unlock(&pag->pag_ici_reclaim_lock);
+		if (done)
+			first_index = 0;
+		WRITE_ONCE(pag->pag_ici_reclaim_cursor, first_index);
 		xfs_perag_put(pag);
 	}
-
-	/*
-	 * if we skipped any AG, and we still have scan count remaining, do
-	 * another pass this time using blocking reclaim semantics (i.e
-	 * waiting on the reclaim locks and ignoring the reclaim cursors). This
-	 * ensure that when we get more reclaimers than AGs we block rather
-	 * than spin trying to execute reclaim.
-	 */
-	if (skipped && (flags & SYNC_WAIT) && *nr_to_scan > 0) {
-		trylock = 0;
-		goto restart;
-	}
-	return last_error;
 }
 
-int
+void
 xfs_reclaim_inodes(
-	xfs_mount_t	*mp,
-	int		mode)
+	struct xfs_mount	*mp)
 {
 	int		nr_to_scan = INT_MAX;
 
-	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
+	while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+		xfs_ail_push_all_sync(mp->m_ail);
+		xfs_reclaim_inodes_ag(mp, &nr_to_scan);
+	};
 }
 
 /*
- * Scan a certain number of inodes for reclaim.
- *
- * When called we make sure that there is a background (fast) inode reclaim in
- * progress, while we will throttle the speed of reclaim via doing synchronous
- * reclaim of inodes. That means if we come across dirty inodes, we wait for
- * them to be cleaned, which we hope will not be very long due to the
- * background walker having already kicked the IO off on those dirty inodes.
+ * The shrinker infrastructure determines how many inodes we should scan for
+ * reclaim. We want as many clean inodes ready to reclaim as possible, so we
+ * push the AIL here. We also want to proactively free up memory if we can to
+ * minimise the amount of work memory reclaim has to do so we kick the
+ * background reclaim if it isn't already scheduled.
  */
 long
 xfs_reclaim_inodes_nr(
···
 	xfs_reclaim_work_queue(mp);
 	xfs_ail_push_all(mp->m_ail);
 
-	return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
+	xfs_reclaim_inodes_ag(mp, &nr_to_scan);
+	return 0;
 }
 
 /*
···
 	return true;
 }
 
+/*
+ * This is a fast pass over the inode cache to try to get reclaim moving on as
+ * many inodes as possible in a short period of time. It kicks itself every few
+ * seconds, as well as being kicked by the inode cache shrinker when memory
+ * goes low.
+ */
+void
+xfs_reclaim_worker(
+	struct work_struct *work)
+{
+	struct xfs_mount *mp = container_of(to_delayed_work(work),
+					struct xfs_mount, m_reclaim_work);
+	int		nr_to_scan = INT_MAX;
+
+	xfs_reclaim_inodes_ag(mp, &nr_to_scan);
+	xfs_reclaim_work_queue(mp);
+}
+
 STATIC int
 xfs_inode_free_eofblocks(
 	struct xfs_inode	*ip,
···
 	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQ_USER);
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_uid = VFS_I(ip)->i_uid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
···
 	}
 
 	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQ_GROUP);
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_gid = VFS_I(ip)->i_gid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_GID;

fs/xfs/xfs_icache.h

···
 	__u64		eof_min_file_size;
 };
 
-#define SYNC_WAIT		0x0001	/* wait for i/o to complete */
-#define SYNC_TRYLOCK		0x0002  /* only try to lock inodes */
-
 /*
  * tags for inode radix tree
  */
···
 
 void xfs_reclaim_worker(struct work_struct *work);
 
-int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
+void xfs_reclaim_inodes(struct xfs_mount *mp);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 

fs/xfs/xfs_icreate_item.c

···
 {
 	struct xfs_icreate_item	*icp;
 
-	icp = kmem_zone_zalloc(xfs_icreate_zone, 0);
+	icp = kmem_cache_zalloc(xfs_icreate_zone, GFP_KERNEL | __GFP_NOFAIL);
 
 	xfs_log_item_init(tp->t_mountp, &icp->ic_item, XFS_LI_ICREATE,
 			  &xfs_icreate_item_ops);

fs/xfs/xfs_inode.c

···
  */
 #define	XFS_ITRUNC_MAX_EXTENTS	2
 
-STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
 STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
 STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
 
···
 		return error;
 	}
 
+	/*
+	 * We do not hold the inode locked across the entire rolling transaction
+	 * here. We only need to hold it for the first transaction that
+	 * xfs_ifree() builds, which may mark the inode XFS_ISTALE if the
+	 * underlying cluster buffer is freed. Relogging an XFS_ISTALE inode
+	 * here breaks the relationship between cluster buffer invalidation and
+	 * stale inode invalidation on cluster buffer item journal commit
+	 * completion, and can result in leaving dirty stale inodes hanging
+	 * around in memory.
+	 *
+	 * We have no need for serialising this inode operation against other
+	 * operations - we freed the inode and hence reallocation is required
+	 * and that will serialise on reallocating the space the deferops need
+	 * to free. Hence we can unlock the inode on the first commit of
+	 * the transaction rather than roll it right through the deferops. This
+	 * avoids relogging the XFS_ISTALE inode.
+	 *
+	 * We check that xfs_ifree() hasn't grown an internal transaction roll
+	 * by asserting that the inode is still locked when it returns.
+	 */
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 	error = xfs_ifree(tp, ip);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
···
 			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
 		}
 		xfs_trans_cancel(tp);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		return error;
 	}
 
···
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
 			__func__, error);
 
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return 0;
 }
 
···
 	xfs_dinode_calc_crc(mp, dip);
 	xfs_trans_inode_buf(tp, ibp);
 	xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
-	xfs_inobp_check(mp, ibp);
 }
 
 /* Set an in-core inode's unlinked pointer and return the old value. */
···
 	}
 
 	if (next_agino != NULLAGINO) {
-		struct xfs_perag	*pag;
 		xfs_agino_t		old_agino;
 
 		/*
···
 		 * agino has been unlinked, add a backref from the next inode
 		 * back to agino.
 		 */
-		pag = xfs_perag_get(mp, agno);
-		error = xfs_iunlink_add_backref(pag, agino, next_agino);
-		xfs_perag_put(pag);
+		error = xfs_iunlink_add_backref(agibp->b_pag, agino, next_agino);
 		if (error)
 			return error;
 	}
···
 	struct xfs_buf		*agibp;
 	struct xfs_buf		*last_ibp;
 	struct xfs_dinode	*last_dip = NULL;
-	struct xfs_perag	*pag = NULL;
 	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
 	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
 	xfs_agino_t		next_agino;
···
 	 * this inode's backref to point from the next inode.
 	 */
 	if (next_agino != NULLAGINO) {
-		pag = xfs_perag_get(mp, agno);
-		error = xfs_iunlink_change_backref(pag, next_agino,
+		error = xfs_iunlink_change_backref(agibp->b_pag, next_agino,
 				NULLAGINO);
 		if (error)
-			goto out;
+			return error;
 	}
 
-	if (head_agino == agino) {
-		/* Point the head of the list to the next unlinked inode. */
-		error = xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
-				next_agino);
-		if (error)
-			goto out;
-	} else {
+	if (head_agino != agino) {
 		struct xfs_imap	imap;
 		xfs_agino_t	prev_agino;
-
-		if (!pag)
-			pag = xfs_perag_get(mp, agno);
 
 		/* We need to search the list for the inode being freed. */
 		error = xfs_iunlink_map_prev(tp, agno, head_agino, agino,
 				&prev_agino, &imap, &last_dip, &last_ibp,
-				pag);
+				agibp->b_pag);
 		if (error)
-			goto out;
+			return error;
 
 		/* Point the previous inode on the list to the next inode. */
 		xfs_iunlink_update_dinode(tp, agno, prev_agino, last_ibp,
···
 		 * change_backref takes care of deleting the backref if
 		 * next_agino is NULLAGINO.
 		 */
-		error = xfs_iunlink_change_backref(pag, agino, next_agino);
-		if (error)
-			goto out;
+		return xfs_iunlink_change_backref(agibp->b_pag, agino,
+				next_agino);
 	}
 
-out:
-	if (pag)
-		xfs_perag_put(pag);
-	return error;
+	/* Point the head of the list to the next unlinked inode. */
+	return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
+			next_agino);
 }
 
 /*
- * Look up the inode number specified and mark it stale if it is found. If it is
- * dirty, return the inode so it can be attached to the cluster buffer so it can
- * be processed appropriately when the cluster free transaction completes.
+ * Look up the inode number specified and if it is not already marked XFS_ISTALE
+ * mark it stale. We should only find clean inodes in this lookup that aren't
+ * already stale.
  */
-static struct xfs_inode *
-xfs_ifree_get_one_inode(
-	struct xfs_perag	*pag,
+static void
+xfs_ifree_mark_inode_stale(
+	struct xfs_buf		*bp,
 	struct xfs_inode	*free_ip,
 	xfs_ino_t		inum)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_perag	*pag = bp->b_pag;
+	struct xfs_inode_log_item *iip;
 	struct xfs_inode	*ip;
 
 retry:
···
 	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));
 
 	/* Inode not in memory, nothing to do */
-	if (!ip)
-		goto out_rcu_unlock;
+	if (!ip) {
+		rcu_read_unlock();
+		return;
+	}
 
 	/*
 	 * because this is an RCU protected lookup, we could find a recently
···
 	spin_lock(&ip->i_flags_lock);
 	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
 		spin_unlock(&ip->i_flags_lock);
-		goto out_rcu_unlock;
+		rcu_read_unlock();
+		return;
 	}
-	spin_unlock(&ip->i_flags_lock);
 
 	/*
 	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
···
 	 */
 	if (ip != free_ip) {
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+			spin_unlock(&ip->i_flags_lock);
 			rcu_read_unlock();
 			delay(1);
 			goto retry;
 		}
-
-		/*
-		 * Check the inode number again in case we're racing with
-		 * freeing in xfs_reclaim_inode().  See the comments in that
-		 * function for more information as to why the initial check is
-		 * not sufficient.
-		 */
-		if (ip->i_ino != inum) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			goto out_rcu_unlock;
-		}
 	}
+	ip->i_flags |= XFS_ISTALE;
+	spin_unlock(&ip->i_flags_lock);
 	rcu_read_unlock();
-
-	xfs_iflock(ip);
-	xfs_iflags_set(ip, XFS_ISTALE);
 
 	/*
-	 * We don't need to attach clean inodes or those only with unlogged
-	 * changes (which we throw away, anyway).
+	 * If we can't get the flush lock, the inode is already attached.  All
+	 * we needed to do here is mark the inode stale so buffer IO completion
+	 * will remove it from the AIL.
 	 */
-	if (!ip->i_itemp || xfs_inode_clean(ip)) {
-		ASSERT(ip != free_ip);
-		xfs_ifunlock(ip);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		goto out_no_inode;
+	iip = ip->i_itemp;
+	if (!xfs_iflock_nowait(ip)) {
+		ASSERT(!list_empty(&iip->ili_item.li_bio_list));
+		ASSERT(iip->ili_last_fields);
+		goto out_iunlock;
 	}
-	return ip;
 
-out_rcu_unlock:
-	rcu_read_unlock();
-out_no_inode:
-	return NULL;
+	/*
+	 * Inodes not attached to the buffer can be released immediately.
+	 * Everything else has to go through xfs_iflush_abort() on journal
+	 * commit as the flock synchronises removal of the inode from the
+	 * cluster buffer against inode reclaim.
+	 */
+	if (!iip || list_empty(&iip->ili_item.li_bio_list)) {
+		xfs_ifunlock(ip);
+		goto out_iunlock;
+	}
+
+	/* we have a dirty inode in memory that has not yet been flushed. */
+	spin_lock(&iip->ili_lock);
+	iip->ili_last_fields = iip->ili_fields;
+	iip->ili_fields = 0;
+	iip->ili_fsync_fields = 0;
+	spin_unlock(&iip->ili_lock);
+	ASSERT(iip->ili_last_fields);
+
+out_iunlock:
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 }
 
 /*
···
  */
 STATIC int
 xfs_ifree_cluster(
-	xfs_inode_t		*free_ip,
-	xfs_trans_t		*tp,
+	struct xfs_inode	*free_ip,
+	struct xfs_trans	*tp,
 	struct xfs_icluster	*xic)
 {
-	xfs_mount_t		*mp = free_ip->i_mount;
+	struct xfs_mount	*mp = free_ip->i_mount;
+	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	struct xfs_buf		*bp;
+	xfs_daddr_t		blkno;
+	xfs_ino_t		inum = xic->first_ino;
 	int			nbufs;
 	int			i, j;
 	int			ioffset;
-	xfs_daddr_t		blkno;
-	xfs_buf_t		*bp;
-	xfs_inode_t		*ip;
-	struct xfs_inode_log_item *iip;
-	struct xfs_log_item	*lip;
-	struct xfs_perag	*pag;
-	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	xfs_ino_t		inum;
 	int			error;
 
-	inum = xic->first_ino;
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
 	nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster;
 
 	for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) {
···
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
 				mp->m_bsize * igeo->blocks_per_cluster,
 				XBF_UNMAPPED, &bp);
-		if (error) {
-			xfs_perag_put(pag);
+		if (error)
 			return error;
-		}
 
 		/*
 		 * This buffer may not have been correctly initialised as we
···
 		bp->b_ops = &xfs_inode_buf_ops;
 
 		/*
-		 * Walk the inodes already attached to the buffer and mark them
-		 * stale. These will all have the flush locks held, so an
-		 * in-memory inode walk can't lock them. By marking them all
-		 * stale first, we will not attempt to lock them in the loop
-		 * below as the XFS_ISTALE flag will be set.
+		 * Now we need to set all the cached clean inodes as XFS_ISTALE,
+		 * too. This requires lookups, and will skip inodes that we've
+		 * already marked XFS_ISTALE.
 		 */
-		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
-			if (lip->li_type == XFS_LI_INODE) {
-				iip = (struct xfs_inode_log_item *)lip;
-				ASSERT(iip->ili_logged == 1);
-				lip->li_cb = xfs_istale_done;
-				xfs_trans_ail_copy_lsn(mp->m_ail,
-							&iip->ili_flush_lsn,
-							&iip->ili_item.li_lsn);
-				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
-			}
-		}
-
-
-		/*
-		 * For each inode in memory attempt to add it to the inode
-		 * buffer and set it up for being staled on buffer IO
-		 * completion.  This is safe as we've locked out tail pushing
-		 * and flushing by locking the buffer.
-		 *
-		 * We have already marked every inode that was part of a
-		 * transaction stale above, which means there is no point in
-		 * even trying to lock them.
-		 */
-		for (i = 0; i < igeo->inodes_per_cluster; i++) {
-			ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i);
-			if (!ip)
-				continue;
-
-			iip = ip->i_itemp;
-			iip->ili_last_fields = iip->ili_fields;
-			iip->ili_fields = 0;
-			iip->ili_fsync_fields = 0;
-			iip->ili_logged = 1;
-			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
-						&iip->ili_item.li_lsn);
-
-			xfs_buf_attach_iodone(bp, xfs_istale_done,
-						  &iip->ili_item);
-
-			if (ip != free_ip)
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		}
+		for (i = 0; i < igeo->inodes_per_cluster; i++)
+			xfs_ifree_mark_inode_stale(bp, free_ip, inum + i);
 
 		xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);
 	}
-
-	xfs_perag_put(pag);
 	return 0;
 }
 
···
 {
 	int			error;
 	struct xfs_icluster	xic = { 0 };
+	struct xfs_inode_log_item *iip = ip->i_itemp;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(VFS_I(ip)->i_nlink == 0);
···
 	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
 
 	/* Don't attempt to replay owner changes for a deleted inode */
-	ip->i_itemp->ili_fields &= ~(XFS_ILOG_AOWNER|XFS_ILOG_DOWNER);
+	spin_lock(&iip->ili_lock);
+	iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER);
+	spin_unlock(&iip->ili_lock);
 
 	/*
 	 * Bump the generation count so no one will be confused
···
 	return error;
 }
 
-STATIC int
-xfs_iflush_cluster(
-	struct xfs_inode	*ip,
-	struct xfs_buf		*bp)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_perag	*pag;
-	unsigned long		first_index, mask;
-	int			cilist_size;
-	struct xfs_inode	**cilist;
-	struct xfs_inode	*cip;
-	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	int			error = 0;
-	int			nr_found;
-	int			clcount = 0;
-	int			i;
-
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-
-	cilist_size = igeo->inodes_per_cluster * sizeof(struct xfs_inode *);
-	cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
-	if (!cilist)
-		goto out_put;
-
-	mask = ~(igeo->inodes_per_cluster - 1);
-	first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
-	rcu_read_lock();
-	/* really need a gang lookup range call here */
-	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
-					first_index, igeo->inodes_per_cluster);
-	if (nr_found == 0)
-		goto out_free;
-
-	for (i = 0; i < nr_found; i++) {
-		cip = cilist[i];
-		if (cip == ip)
-			continue;
-
-		/*
-		 * because this is an RCU protected lookup, we could find a
-		 * recently freed or even reallocated inode during the lookup.
-		 * We need to check under the i_flags_lock for a valid inode
-		 * here. Skip it if it is not valid or the wrong inode.
-		 */
-		spin_lock(&cip->i_flags_lock);
-		if (!cip->i_ino ||
-		    __xfs_iflags_test(cip, XFS_ISTALE)) {
-			spin_unlock(&cip->i_flags_lock);
-			continue;
-		}
-
-		/*
-		 * Once we fall off the end of the cluster, no point checking
-		 * any more inodes in the list because they will also all be
-		 * outside the cluster.
-		 */
-		if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
-			spin_unlock(&cip->i_flags_lock);
-			break;
-		}
-		spin_unlock(&cip->i_flags_lock);
-
-		/*
-		 * Do an un-protected check to see if the inode is dirty and
-		 * is a candidate for flushing.  These checks will be repeated
-		 * later after the appropriate locks are acquired.
-		 */
-		if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
-			continue;
-
-		/*
-		 * Try to get locks.  If any are unavailable or it is pinned,
-		 * then this inode cannot be flushed and is skipped.
-		 */
-
-		if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
-			continue;
-		if (!xfs_iflock_nowait(cip)) {
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-		if (xfs_ipincount(cip)) {
-			xfs_ifunlock(cip);
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
-
-		/*
-		 * Check the inode number again, just to be certain we are not
-		 * racing with freeing in xfs_reclaim_inode(). See the comments
-		 * in that function for more information as to why the initial
-		 * check is not sufficient.
-		 */
-		if (!cip->i_ino) {
-			xfs_ifunlock(cip);
-			xfs_iunlock(cip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
-		/*
-		 * arriving here means that this inode can be flushed.  First
-		 * re-check that it's dirty before flushing.
-		 */
-		if (!xfs_inode_clean(cip)) {
-			error = xfs_iflush_int(cip, bp);
-			if (error) {
-				xfs_iunlock(cip, XFS_ILOCK_SHARED);
-				goto out_free;
-			}
-			clcount++;
-		} else {
-			xfs_ifunlock(cip);
-		}
-		xfs_iunlock(cip, XFS_ILOCK_SHARED);
-	}
-
-	if (clcount) {
-		XFS_STATS_INC(mp, xs_icluster_flushcnt);
-		XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
-	}
-
-out_free:
-	rcu_read_unlock();
-	kmem_free(cilist);
-out_put:
-	xfs_perag_put(pag);
-	return error;
-}
-
-/*
- * Flush dirty inode metadata into the backing buffer.
- *
- * The caller must have the inode lock and the inode flush lock held.  The
- * inode lock will still be held upon return to the caller, and the inode
- * flush lock will be released after the inode has reached the disk.
- *
- * The caller must write out the buffer returned in *bpp and release it.
- */
-int
+static int
 xfs_iflush(
-	struct xfs_inode	*ip,
-	struct xfs_buf		**bpp)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_buf		*bp = NULL;
-	struct xfs_dinode	*dip;
-	int			error;
-
-	XFS_STATS_INC(mp, xs_iflush_count);
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
-	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
-	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-
-	*bpp = NULL;
-
-	xfs_iunpin_wait(ip);
-
-	/*
-	 * For stale inodes we cannot rely on the backing buffer remaining
-	 * stale in cache for the remaining life of the stale inode and so
-	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
-	 * inodes below. We have to check this after ensuring the inode is
-	 * unpinned so that it is safe to reclaim the stale inode after the
-	 * flush call.
-	 */
-	if (xfs_iflags_test(ip, XFS_ISTALE)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
-	/*
-	 * Get the buffer containing the on-disk inode. We are doing a try-lock
-	 * operation here, so we may get an EAGAIN error. In that case, return
-	 * leaving the inode dirty.
-	 *
-	 * If we get any other error, we effectively have a corruption situation
-	 * and we cannot flush the inode. Abort the flush and shut down.
-	 */
-	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK);
-	if (error == -EAGAIN) {
-		xfs_ifunlock(ip);
-		return error;
-	}
-	if (error)
-		goto abort;
-
-	/*
-	 * If the buffer is pinned then push on the log now so we won't
-	 * get stuck waiting in the write for too long.
-	 */
-	if (xfs_buf_ispinned(bp))
-		xfs_log_force(mp, 0);
-
-	/*
-	 * Flush the provided inode then attempt to gather others from the
-	 * cluster into the write.
-	 *
-	 * Note: Once we attempt to flush an inode, we must run buffer
-	 * completion callbacks on any failure. If this fails, simulate an I/O
-	 * failure on the buffer and shut down.
-	 */
-	error = xfs_iflush_int(ip, bp);
-	if (!error)
-		error = xfs_iflush_cluster(ip, bp);
-	if (error) {
-		bp->b_flags |= XBF_ASYNC;
-		xfs_buf_ioend_fail(bp);
-		goto shutdown;
-	}
-
-	*bpp = bp;
-	return 0;
-
-abort:
-	xfs_iflush_abort(ip);
-shutdown:
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-	return error;
-}
-
-STATIC int
-xfs_iflush_int(
 	struct xfs_inode	*ip,
 	struct xfs_buf		*bp)
 {
···
 	ASSERT(xfs_isiflocked(ip));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-	ASSERT(iip != NULL && iip->ili_fields != 0);
+	ASSERT(iip->ili_item.li_buf == bp);
 
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
···
 	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
 	if (XFS_IFORK_Q(ip))
 		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
-	xfs_inobp_check(mp, bp);
 
 	/*
 	 * We've recorded everything logged in the inode, so we'd like to clear
···
 	 * know that the information those bits represent is permanently on
 	 * disk.  As long as the flush completes before the inode is logged
 	 * again, then both ili_fields and ili_last_fields will be cleared.
-	 *
-	 * We can play with the ili_fields bits here, because the inode lock
-	 * must be held exclusively in order to set bits there and the flush
-	 * lock protects the ili_last_fields bits.  Set ili_logged so the flush
-	 * done routine can tell whether or not to look in the AIL.  Also, store
-	 * the current LSN of the inode so that we can tell whether the item has
-	 * moved in the AIL from xfs_iflush_done().  In order to read the lsn we
-	 * need the AIL lock, because it is a 64 bit value that cannot be read
-	 * atomically.
 	 */
 	error = 0;
 flush_out:
+	spin_lock(&iip->ili_lock);
 	iip->ili_last_fields = iip->ili_fields;
 	iip->ili_fields = 0;
 	iip->ili_fsync_fields = 0;
-	iip->ili_logged = 1;
+	spin_unlock(&iip->ili_lock);
 
+	/*
+	 * Store the current LSN of the inode so that we can tell whether the
+	 * item has moved in the AIL from xfs_iflush_done().
+	 */
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 				&iip->ili_item.li_lsn);
 
-	/*
-	 * Attach the inode item callback to the buffer whether the flush
-	 * succeeded or not. If not, the caller will shut down and fail I/O
-	 * completion on the buffer to remove the inode from the AIL and release
-	 * the flush lock.
-	 */
-	xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
-
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
-
-	ASSERT(!list_empty(&bp->b_li_list));
-	ASSERT(bp->b_iodone != NULL);
 	return error;
+}
+
+/*
+ * Non-blocking flush of dirty inode metadata into the backing buffer.
+ *
+ * The caller must have a reference to the inode and hold the cluster buffer
+ * locked. The function will walk across all the inodes on the cluster buffer it
+ * can find and lock without blocking, and flush them to the cluster buffer.
+ *
+ * On successful flushing of at least one inode, the caller must write out the
+ * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and
+ * the caller needs to release the buffer. On failure, the filesystem will be
+ * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED
+ * will be returned.
+ */
+int
+xfs_iflush_cluster(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_log_item	*lip, *n;
+	struct xfs_inode	*ip;
+	struct xfs_inode_log_item *iip;
+	int			clcount = 0;
+	int			error = 0;
+
+	/*
+	 * We must use the safe variant here as on shutdown xfs_iflush_abort()
+	 * can remove itself from the list.
+	 */
+	list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
+		iip = (struct xfs_inode_log_item *)lip;
+		ip = iip->ili_inode;
+
+		/*
+		 * Quick and dirty check to avoid locks if possible.
+		 */
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK))
+			continue;
+		if (xfs_ipincount(ip))
+			continue;
+
+		/*
+		 * The inode is still attached to the buffer, which means it is
+		 * dirty but reclaim might try to grab it. Check carefully for
+		 * that, and grab the ilock while still holding the i_flags_lock
+		 * to guarantee reclaim will not be able to reclaim this inode
+		 * once we drop the i_flags_lock.
+		 */
+		spin_lock(&ip->i_flags_lock);
+		ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK)) {
+			spin_unlock(&ip->i_flags_lock);
+			continue;
+		}
+
+		/*
+		 * ILOCK will pin the inode against reclaim and prevent
+		 * concurrent transactions modifying the inode while we are
+		 * flushing the inode.
+		 */
+		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+			spin_unlock(&ip->i_flags_lock);
+			continue;
+		}
+		spin_unlock(&ip->i_flags_lock);
+
+		/*
+		 * Skip inodes that are already flush locked as they have
+		 * already been written to the buffer.
+		 */
+		if (!xfs_iflock_nowait(ip)) {
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			continue;
+		}
+
+		/*
+		 * Abort flushing this inode if we are shut down because the
+		 * inode may not currently be in the AIL. This can occur when
+		 * log I/O failure unpins the inode without inserting into the
+		 * AIL, leaving a dirty/unpinned inode attached to the buffer
+		 * that otherwise looks like it should be flushed.
+		 */
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			xfs_iunpin_wait(ip);
+			/* xfs_iflush_abort() drops the flush lock */
+			xfs_iflush_abort(ip);
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			error = -EIO;
+			continue;
+		}
+
+		/* don't block waiting on a log force to unpin dirty inodes */
+		if (xfs_ipincount(ip)) {
+			xfs_ifunlock(ip);
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
+			continue;
+		}
+
+		if (!xfs_inode_clean(ip))
+			error = xfs_iflush(ip, bp);
+		else
+			xfs_ifunlock(ip);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		if (error)
+			break;
+		clcount++;
+	}
+
+	if (error) {
+		bp->b_flags |= XBF_ASYNC;
+		xfs_buf_ioend_fail(bp);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		return error;
+	}
+
+	if (!clcount)
+		return -EAGAIN;
+
+	XFS_STATS_INC(mp, xs_icluster_flushcnt);
+	XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
+	return 0;
+
 }
 
 /* Release an inode. */
···
 	if (!lsn)
 		return 0;
 	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
+}
+
+/*
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding.  The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
+ */
+static int
+xfs_iolock_two_inodes_and_break_layout(
+	struct inode		*src,
+	struct inode		*dest)
+{
+	int			error;
+
+	if (src > dest)
+		swap(src, dest);
+
+retry:
+	/* Wait to break both inodes' layouts before we start locking. */
+	error = break_layout(src, true);
+	if (error)
+		return error;
+	if (src != dest) {
+		error = break_layout(dest, true);
+		if (error)
+			return error;
+	}
+
+	/* Lock one inode and make sure nobody got in and leased it. */
+	inode_lock(src);
+	error = break_layout(src, false);
+	if (error) {
+		inode_unlock(src);
+		if (error == -EWOULDBLOCK)
+			goto retry;
+		return error;
+	}
+
+	if (src == dest)
+		return 0;
+
+	/* Lock the other inode and make sure nobody got in and leased it. */
+	inode_lock_nested(dest, I_MUTEX_NONDIR2);
+	error = break_layout(dest, false);
+	if (error) {
+		inode_unlock(src);
+		inode_unlock(dest);
+		if (error == -EWOULDBLOCK)
+			goto retry;
+		return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
+ * mmap activity.
+ */
+int
+xfs_ilock2_io_mmap(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	int			ret;
+
+	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
+	if (ret)
+		return ret;
+	if (ip1 == ip2)
+		xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
+	else
+		xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
+				    ip2, XFS_MMAPLOCK_EXCL);
+	return 0;
+}
+
+/* Unlock both inodes to allow IO and mmap activity. */
+void
+xfs_iunlock2_io_mmap(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	bool			same_inode = (ip1 == ip2);
+
+	xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+	if (!same_inode)
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+	inode_unlock(VFS_I(ip2));
+	if (!same_inode)
+		inode_unlock(VFS_I(ip1));
 }

fs/xfs/xfs_inode.h

···
 void		xfs_iunpin_wait(xfs_inode_t *);
 #define xfs_ipincount(ip)	((unsigned int) atomic_read(&ip->i_pincount))
 
-int		xfs_iflush(struct xfs_inode *, struct xfs_buf **);
+int		xfs_iflush_cluster(struct xfs_buf *);
 void		xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode,
 				struct xfs_inode *ip1, uint ip1_mode);
 
···
 void xfs_iunlink_destroy(struct xfs_perag *pag);
 
 void xfs_end_io(struct work_struct *work);
+
+int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
+void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
 
 #endif	/* __XFS_INODE_H__ */

fs/xfs/xfs_inode_item.c

···
 	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(lip->li_buf);
 
 	trace_xfs_inode_pin(ip, _RET_IP_);
 	atomic_inc(&ip->i_pincount);
···
  * item which was previously pinned with a call to xfs_inode_item_pin().
  *
  * Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
+ *
+ * Note that unpin can race with inode cluster buffer freeing marking the buffer
+ * stale. In that case, flush completions are run from the buffer unpin call,
+ * which may happen before the inode is unpinned. If we lose the race, there
+ * will be no buffer attached to the log item, but the inode will be marked
+ * XFS_ISTALE.
  */
 STATIC void
 xfs_inode_item_unpin(
···
 	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;
 
 	trace_xfs_inode_unpin(ip, _RET_IP_);
+	ASSERT(lip->li_buf || xfs_iflags_test(ip, XFS_ISTALE));
 	ASSERT(atomic_read(&ip->i_pincount) > 0);
 	if (atomic_dec_and_test(&ip->i_pincount))
 		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
-}
-
-/*
- * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer
- * have been failed during writeback
- *
- * This informs the AIL that the inode is already flush locked on the next push,
- * and acquires a hold on the buffer to ensure that it isn't reclaimed before
- * dirty data makes it to disk.
- */
-STATIC void
-xfs_inode_item_error(
-	struct xfs_log_item	*lip,
-	struct xfs_buf		*bp)
-{
-	ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode));
-	xfs_set_li_failed(lip, bp);
 }
 
 STATIC uint
···
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
-	if (xfs_ipincount(ip) > 0)
+	ASSERT(iip->ili_item.li_buf);
+
+	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp) ||
+	    (ip->i_flags & XFS_ISTALE))
 		return XFS_ITEM_PINNED;
 
-	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
+	/* If the inode is already flush locked, we're already flushing. */
+	if (xfs_isiflocked(ip))
+		return XFS_ITEM_FLUSHING;
+
+	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
-
-	/*
-	 * Re-check the pincount now that we stabilized the value by
-	 * taking the ilock.
-	 */
-	if (xfs_ipincount(ip) > 0) {
-		rval = XFS_ITEM_PINNED;
-		goto out_unlock;
-	}
-
-	/*
-	 * Stale inode items should force out the iclog.
-	 */
-	if (ip->i_flags & XFS_ISTALE) {
-		rval = XFS_ITEM_PINNED;
-		goto out_unlock;
-	}
-
-	/*
-	 * Someone else is already flushing the inode.  Nothing we can do
-	 * here but wait for the flush to finish and remove the item from
-	 * the AIL.
-	 */
-	if (!xfs_iflock_nowait(ip)) {
-		rval = XFS_ITEM_FLUSHING;
-		goto out_unlock;
-	}
-
-	ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
-	ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
 
 	spin_unlock(&lip->li_ailp->ail_lock);
 
-	error = xfs_iflush(ip, &bp);
+	/*
+	 * We need to hold a reference for flushing the cluster buffer as it may
+	 * fail the buffer without IO submission. In which case, we better get a
+	 * reference for that completion because otherwise we don't get a
+	 * reference for IO until we queue the buffer for delwri submission.
+	 */
+	xfs_buf_hold(bp);
+	error = xfs_iflush_cluster(bp);
 	if (!error) {
 		if (!xfs_buf_delwri_queue(bp, buffer_list))
 			rval = XFS_ITEM_FLUSHING;
 		xfs_buf_relse(bp);
-	} else if (error == -EAGAIN)
+	} else {
+		/*
+		 * Release the buffer if we were unable to flush anything. On
+		 * any other error, the buffer has already been released.
+		 */
+		if (error == -EAGAIN)
+			xfs_buf_relse(bp);
 		rval = XFS_ITEM_LOCKED;
+	}
 
 	spin_lock(&lip->li_ailp->ail_lock);
-out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	return rval;
 }
 
···
 	.iop_committed	= xfs_inode_item_committed,
 	.iop_push	= xfs_inode_item_push,
 	.iop_committing	= xfs_inode_item_committing,
-	.iop_error	= xfs_inode_item_error
 };
 
 
···
 	struct xfs_inode_log_item *iip;
 
 	ASSERT(ip->i_itemp == NULL);
-	iip = ip->i_itemp = kmem_zone_zalloc(xfs_ili_zone, 0);
+	iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_zone,
+					      GFP_KERNEL | __GFP_NOFAIL);
 
 	iip->ili_inode = ip;
+	spin_lock_init(&iip->ili_lock);
 	xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE,
 						&xfs_inode_item_ops);
 }
···
  */
 void
 xfs_inode_item_destroy(
-	xfs_inode_t	*ip)
+	struct xfs_inode	*ip)
 {
-	kmem_free(ip->i_itemp->ili_item.li_lv_shadow);
-	kmem_cache_free(xfs_ili_zone, ip->i_itemp);
+	struct xfs_inode_log_item *iip = ip->i_itemp;
+
+	ASSERT(iip->ili_item.li_buf == NULL);
+
+	ip->i_itemp = NULL;
+	kmem_free(iip->ili_item.li_lv_shadow);
+	kmem_cache_free(xfs_ili_zone, iip);
 }
 
 
 /*
- * This is the inode flushing I/O completion routine.  It is called
- * from interrupt level when the buffer containing the inode is
- * flushed to disk.  It is responsible for removing the inode item
- * from the AIL if it has not been re-logged, and unlocking the inode's
- * flush lock.
- *
- * To reduce AIL lock traffic as much as possible, we scan the buffer log item
- * list for other inodes that will run this function. We remove them from the
- * buffer list so we can process all the inode IO completions in one AIL lock
- * traversal.
+ * We only want to pull the item from the AIL if it is actually there
+ * and its location in the log has not changed since we started the
+ * flush.  Thus, we only bother if the inode's lsn has not changed.
+ */
+static void
+xfs_iflush_ail_updates(
+	struct xfs_ail		*ailp,
+	struct list_head	*list)
+{
+	struct xfs_log_item	*lip;
+	xfs_lsn_t		tail_lsn = 0;
+
+	/* this is an opencoded batch version of xfs_trans_ail_delete */
+	spin_lock(&ailp->ail_lock);
+	list_for_each_entry(lip, list, li_bio_list) {
+		xfs_lsn_t	lsn;
+
+		clear_bit(XFS_LI_FAILED, &lip->li_flags);
+		if (INODE_ITEM(lip)->ili_flush_lsn != lip->li_lsn)
+			continue;
+
+		lsn = xfs_ail_delete_one(ailp, lip);
+		if (!tail_lsn && lsn)
+			tail_lsn = lsn;
+	}
+	xfs_ail_update_finish(ailp, tail_lsn);
+}
+
+/*
+ * Walk the list of inodes that have completed their IOs. If they are clean
+ * remove them from the list and dissociate them from the buffer. Buffers that
+ * are still dirty remain linked to the buffer and on the list. Caller must
+ * handle them appropriately.
+ */
+static void
+xfs_iflush_finish(
+	struct xfs_buf		*bp,
+	struct list_head	*list)
+{
+	struct xfs_log_item	*lip, *n;
+
+	list_for_each_entry_safe(lip, n, list, li_bio_list) {
+		struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+		bool	drop_buffer = false;
+
+		spin_lock(&iip->ili_lock);
+
+		/*
+		 * Remove the reference to the cluster buffer if the inode is
+		 * clean in memory and drop the buffer reference once we've
+		 * dropped the locks we hold.
+		 */
+		ASSERT(iip->ili_item.li_buf == bp);
+		if (!iip->ili_fields) {
+			iip->ili_item.li_buf = NULL;
+			list_del_init(&lip->li_bio_list);
+			drop_buffer = true;
+		}
+		iip->ili_last_fields = 0;
+		iip->ili_flush_lsn = 0;
+		spin_unlock(&iip->ili_lock);
+		xfs_ifunlock(iip->ili_inode);
+		if (drop_buffer)
+			xfs_buf_rele(bp);
+	}
+}
+
+/*
+ * Inode buffer IO completion routine.  It is responsible for removing inodes
+ * attached to the buffer from the AIL if they have not been re-logged, as well
+ * as completing the flush and unlocking the inode.
  */
 void
 xfs_iflush_done(
-	struct xfs_buf		*bp,
-	struct xfs_log_item	*lip)
+	struct xfs_buf		*bp)
 {
-	struct xfs_inode_log_item *iip;
-	struct xfs_log_item	*blip, *n;
-	struct xfs_ail		*ailp = lip->li_ailp;
-	int			need_ail = 0;
-	LIST_HEAD(tmp);
+	struct xfs_log_item	*lip, *n;
+	LIST_HEAD(flushed_inodes);
+	LIST_HEAD(ail_updates);
 
 	/*
-	 * Scan the buffer IO completions for other inodes being completed and
-	 * attach them to the current inode log item.
+	 * Pull the attached inodes from the buffer one at a time and take the
+	 * appropriate action on them.
 	 */
+	list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
+		struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 
-	list_add_tail(&lip->li_bio_list, &tmp);
-
-	list_for_each_entry_safe(blip, n, &bp->b_li_list, li_bio_list) {
-		if (lip->li_cb != xfs_iflush_done)
+		if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) {
+			xfs_iflush_abort(iip->ili_inode);
+			continue;
+		}
+		if (!iip->ili_last_fields)
 			continue;
 
-		list_move_tail(&blip->li_bio_list, &tmp);
-		/*
-		 * while we have the item, do the unlocked check for needing
-		 * the AIL lock.
-		 */
-		iip = INODE_ITEM(blip);
-		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
-		    test_bit(XFS_LI_FAILED, &blip->li_flags))
-			need_ail++;
+		/* Do an unlocked check for needing the AIL lock. */
+		if (iip->ili_flush_lsn == lip->li_lsn ||
+		    test_bit(XFS_LI_FAILED, &lip->li_flags))
+			list_move_tail(&lip->li_bio_list, &ail_updates);
+		else
+			list_move_tail(&lip->li_bio_list, &flushed_inodes);
 	}
 
-	/* make sure we capture the state of the initial inode. */
-	iip = INODE_ITEM(lip);
-	if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) ||
-	    test_bit(XFS_LI_FAILED, &lip->li_flags))
-		need_ail++;
-
-	/*
-	 * We only want to pull the item from the AIL if it is
-	 * actually there and its location in the log has not
-	 * changed since we started the flush.  Thus, we only bother
-	 * if the ili_logged flag is set and the inode's lsn has not
-	 * changed.  First we check the lsn outside
-	 * the lock since it's cheaper, and then we recheck while
-	 * holding the lock before removing the inode from the AIL.
-	 */
-	if (need_ail) {
-		xfs_lsn_t	tail_lsn = 0;
-
-		/* this is an opencoded batch version of xfs_trans_ail_delete */
-		spin_lock(&ailp->ail_lock);
-		list_for_each_entry(blip, &tmp, li_bio_list) {
-			if (INODE_ITEM(blip)->ili_logged &&
-			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) {
-				/*
-				 * xfs_ail_update_finish() only cares about the
-				 * lsn of the first tail item removed, any
-				 * others will be at the same or higher lsn so
-				 * we just ignore them.
-				 */
-				xfs_lsn_t lsn = xfs_ail_delete_one(ailp, blip);
-				if (!tail_lsn && lsn)
-					tail_lsn = lsn;
-			} else {
-				xfs_clear_li_failed(blip);
-			}
-		}
-		xfs_ail_update_finish(ailp, tail_lsn);
+	if (!list_empty(&ail_updates)) {
+		xfs_iflush_ail_updates(bp->b_mount->m_ail, &ail_updates);
+		list_splice_tail(&ail_updates, &flushed_inodes);
 	}
 
-	/*
-	 * clean up and unlock the flush lock now we are done. We can clear the
-	 * ili_last_fields bits now that we know that the data corresponding to
-	 * them is safely on disk.
-	 */
-	list_for_each_entry_safe(blip, n, &tmp, li_bio_list) {
-		list_del_init(&blip->li_bio_list);
-		iip = INODE_ITEM(blip);
-		iip->ili_logged = 0;
-		iip->ili_last_fields = 0;
-		xfs_ifunlock(iip->ili_inode);
-	}
-	list_del(&tmp);
+	xfs_iflush_finish(bp, &flushed_inodes);
+	if (!list_empty(&flushed_inodes))
+		list_splice_tail(&flushed_inodes, &bp->b_li_list);
 }
 
 /*
···
  */
 void
 xfs_iflush_abort(
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	struct xfs_inode_log_item	*iip = ip->i_itemp;
+	struct xfs_inode_log_item *iip = ip->i_itemp;
+	struct xfs_buf		*bp = NULL;
 
 	if (iip) {
-		xfs_trans_ail_delete(&iip->ili_item, 0);
-		iip->ili_logged = 0;
 		/*
-		 * Clear the ili_last_fields bits now that we know that the
-		 * data corresponding to them is safely on disk.
+		 * Clear the failed bit before removing the item from the AIL so
+		 * xfs_trans_ail_delete() doesn't try to clear and release the
+		 * buffer attached to the log item before we are done with it.
 		 */
-		iip->ili_last_fields = 0;
+		clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags);
+		xfs_trans_ail_delete(&iip->ili_item, 0);
+
 		/*
 		 * Clear the inode logging fields so no more flushes are
 		 * attempted.
 		 */
+		spin_lock(&iip->ili_lock);
+		iip->ili_last_fields = 0;
 		iip->ili_fields = 0;
 		iip->ili_fsync_fields = 0;
+		iip->ili_flush_lsn = 0;
+		bp = iip->ili_item.li_buf;
+		iip->ili_item.li_buf = NULL;
+		list_del_init(&iip->ili_item.li_bio_list);
+		spin_unlock(&iip->ili_lock);
 	}
-	/*
-	 * Release the inode's flush lock since we're done with it.
-	 */
 	xfs_ifunlock(ip);
-}
-
-void
-xfs_istale_done(
-	struct xfs_buf		*bp,
-	struct xfs_log_item	*lip)
-{
-	xfs_iflush_abort(INODE_ITEM(lip)->ili_inode);
+	if (bp)
+		xfs_buf_rele(bp);
 }
 
 /*

fs/xfs/xfs_inode_item.h

···
 struct xfs_inode_log_item {
 	struct xfs_log_item	ili_item;	   /* common portion */
 	struct xfs_inode	*ili_inode;	   /* inode ptr */
-	xfs_lsn_t		ili_flush_lsn;	   /* lsn at last flush */
-	xfs_lsn_t		ili_last_lsn;	   /* lsn at last transaction */
-	unsigned short		ili_lock_flags;	   /* lock flags */
-	unsigned short		ili_logged;	   /* flushed logged data */
+	unsigned short		ili_lock_flags;	   /* inode lock flags */
+	/*
+	 * The ili_lock protects the interactions between the dirty state and
+	 * the flush state of the inode log item. This allows us to do atomic
+	 * modifications of multiple state fields without having to hold a
+	 * specific inode lock to serialise them.
+	 *
+	 * We need atomic changes between inode dirtying, inode flushing and
+	 * inode completion, but these all hold different combinations of
+	 * ILOCK and iflock and hence we need some other method of serialising
+	 * updates to the flush state.
+	 */
+	spinlock_t		ili_lock;	   /* flush state lock */
 	unsigned int		ili_last_fields;   /* fields when flushed */
 	unsigned int		ili_fields;	   /* fields to be logged */
 	unsigned int		ili_fsync_fields;  /* logged since last fsync */
+	xfs_lsn_t		ili_flush_lsn;	   /* lsn at last flush */
+	xfs_lsn_t		ili_last_lsn;	   /* lsn at last transaction */
 };
 
-static inline int xfs_inode_clean(xfs_inode_t *ip)
+static inline int xfs_inode_clean(struct xfs_inode *ip)
 {
 	return !ip->i_itemp || !(ip->i_itemp->ili_fields & XFS_ILOG_ALL);
 }
 
 extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);
 extern void xfs_inode_item_destroy(struct xfs_inode *);
-extern void xfs_iflush_done(struct xfs_buf *, struct xfs_log_item *);
-extern void xfs_istale_done(struct xfs_buf *, struct xfs_log_item *);
+extern void xfs_iflush_done(struct xfs_buf *);
 extern void xfs_iflush_abort(struct xfs_inode *);
 extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
 					 struct xfs_inode_log_format *);

fs/xfs/xfs_inode_item_recover.c

···
 	xfs_dinode_calc_crc(log->l_mp, dip);
 
 	ASSERT(bp->b_mount == mp);
-	bp->b_iodone = xlog_recover_iodone;
+	bp->b_flags |= _XBF_LOGRECOVERY;
 	xfs_buf_delwri_queue(bp, buffer_list);
 
 out_release:

fs/xfs/xfs_ioctl.c

···
 		xflags |= FS_XFLAG_NODUMP;
 	else
 		xflags &= ~FS_XFLAG_NODUMP;
+	if (flags & FS_DAX_FL)
+		xflags |= FS_XFLAG_DAX;
+	else
+		xflags &= ~FS_XFLAG_DAX;
 
 	return xflags;
 }
 
 STATIC unsigned int
 xfs_di2lxflags(
-	uint16_t	di_flags)
+	uint16_t	di_flags,
+	uint64_t	di_flags2)
 {
 	unsigned int	flags = 0;
 
···
 		flags |= FS_NOATIME_FL;
 	if (di_flags & XFS_DIFLAG_NODUMP)
 		flags |= FS_NODUMP_FL;
+	if (di_flags2 & XFS_DIFLAG2_DAX) {
+		flags |= FS_DAX_FL;
+	}
 	return flags;
 }
 
···
 {
 	unsigned int		flags;
 
-	flags = xfs_di2lxflags(ip->i_d.di_flags);
+	flags = xfs_di2lxflags(ip->i_d.di_flags, ip->i_d.di_flags2);
 	if (copy_to_user(arg, &flags, sizeof(flags)))
 		return -EFAULT;
 	return 0;
···
 
 	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
 		      FS_NOATIME_FL | FS_NODUMP_FL | \
-		      FS_SYNC_FL))
+		      FS_SYNC_FL | FS_DAX_FL))
 		return -EOPNOTSUPP;
 
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));

fs/xfs/xfs_iomap.c

···
 
 STATIC bool
 xfs_quota_need_throttle(
-	struct xfs_inode *ip,
-	int type,
-	xfs_fsblock_t alloc_blocks)
+	struct xfs_inode	*ip,
+	xfs_dqtype_t		type,
+	xfs_fsblock_t		alloc_blocks)
 {
-	struct xfs_dquot *dq = xfs_inode_dquot(ip, type);
+	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);
 
 	if (!dq || !xfs_this_quota_on(ip->i_mount, type))
 		return false;
···
 		return false;
 
 	/* under the lo watermark, no throttle */
-	if (dq->q_res_bcount + alloc_blocks < dq->q_prealloc_lo_wmark)
+	if (dq->q_blk.reserved + alloc_blocks < dq->q_prealloc_lo_wmark)
 		return false;
 
 	return true;
···
 
 STATIC void
 xfs_quota_calc_throttle(
-	struct xfs_inode *ip,
-	int type,
-	xfs_fsblock_t *qblocks,
-	int *qshift,
-	int64_t	*qfreesp)
+	struct xfs_inode	*ip,
+	xfs_dqtype_t		type,
+	xfs_fsblock_t		*qblocks,
+	int			*qshift,
+	int64_t			*qfreesp)
 {
-	int64_t freesp;
-	int shift = 0;
-	struct xfs_dquot *dq = xfs_inode_dquot(ip, type);
+	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);
+	int64_t			freesp;
+	int			shift = 0;
 
 	/* no dq, or over hi wmark, squash the prealloc completely */
-	if (!dq || dq->q_res_bcount >= dq->q_prealloc_hi_wmark) {
+	if (!dq || dq->q_blk.reserved >= dq->q_prealloc_hi_wmark) {
 		*qblocks = 0;
 		*qfreesp = 0;
 		return;
 	}
 
-	freesp = dq->q_prealloc_hi_wmark - dq->q_res_bcount;
+	freesp = dq->q_prealloc_hi_wmark - dq->q_blk.reserved;
 	if (freesp < dq->q_low_space[XFS_QLOWSP_5_PCNT]) {
 		shift = 2;
 		if (freesp < dq->q_low_space[XFS_QLOWSP_3_PCNT])
···
 	 * Check each quota to cap the prealloc size, provide a shift value to
 	 * throttle with and adjust amount of available space.
 	 */
-	if (xfs_quota_need_throttle(ip, XFS_DQ_USER, alloc_blocks))
-		xfs_quota_calc_throttle(ip, XFS_DQ_USER, &qblocks, &qshift,
+	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_USER, alloc_blocks))
+		xfs_quota_calc_throttle(ip, XFS_DQTYPE_USER, &qblocks, &qshift,
 					&freesp);
-	if (xfs_quota_need_throttle(ip, XFS_DQ_GROUP, alloc_blocks))
-		xfs_quota_calc_throttle(ip, XFS_DQ_GROUP, &qblocks, &qshift,
+	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_GROUP, alloc_blocks))
+		xfs_quota_calc_throttle(ip, XFS_DQTYPE_GROUP, &qblocks, &qshift,
 					&freesp);
-	if (xfs_quota_need_throttle(ip, XFS_DQ_PROJ, alloc_blocks))
-		xfs_quota_calc_throttle(ip, XFS_DQ_PROJ, &qblocks, &qshift,
+	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_PROJ, alloc_blocks))
+		xfs_quota_calc_throttle(ip, XFS_DQTYPE_PROJ, &qblocks, &qshift,
 					&freesp);
 
 	/*

fs/xfs/xfs_linux.h

···
 #define xfs_cowb_secs		xfs_params.cowb_timer.val
 
 #define current_cpu()		(raw_smp_processor_id())
-#define current_pid()		(current->pid)
-#define current_test_flags(f)	(current->flags & (f))
 #define current_set_flags_nested(sp, f)		\
 		(*(sp) = current->flags, current->flags |= (f))
-#define current_clear_flags_nested(sp, f)	\
-		(*(sp) = current->flags, current->flags &= ~(f))
 #define current_restore_flags_nested(sp, f)	\
 		(current->flags = ((current->flags & ~(f)) | (*(sp) & (f))))
 

fs/xfs/xfs_log.c

···
 	XFS_STATS_INC(mp, xs_try_logspace);
 
 	ASSERT(*ticp == NULL);
-	tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent, 0);
+	tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent);
 	*ticp = tic;
 
 	xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt
···
 	int			unit_bytes,
 	int			cnt,
 	char			client,
-	bool			permanent,
-	xfs_km_flags_t		alloc_flags)
+	bool			permanent)
 {
 	struct xlog_ticket	*tic;
 	int			unit_res;
 
-	tic = kmem_zone_zalloc(xfs_log_ticket_zone, alloc_flags);
-	if (!tic)
-		return NULL;
+	tic = kmem_cache_zalloc(xfs_log_ticket_zone, GFP_NOFS | __GFP_NOFAIL);
 
 	unit_res = xfs_log_calc_unit_res(log->l_mp, unit_bytes);
 

fs/xfs/xfs_log_cil.c

···
 {
 	struct xlog_ticket *tic;
 
-	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0,
-				KM_NOFS);
+	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0);
 
 	/*
 	 * set the current reservation to zero so we know to steal the basic

fs/xfs/xfs_log_priv.h

···
 	int		unit_bytes,
 	int		count,
 	char		client,
-	bool		permanent,
-	xfs_km_flags_t	alloc_flags);
-
+	bool		permanent);
 
 static inline void
 xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)

fs/xfs/xfs_log_recover.c

···
 	if (bp->b_log_item)
 		xfs_buf_item_relse(bp);
 	ASSERT(bp->b_log_item == NULL);
-
-	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp);
+	bp->b_flags &= ~_XBF_LOGRECOVERY;
+	xfs_buf_ioend_finish(bp);
 }
 
 /*

fs/xfs/xfs_mount.c

···
 		ASSERT(atomic_read(&pag->pag_ref) == 0);
 		xfs_iunlink_destroy(pag);
 		xfs_buf_hash_destroy(pag);
-		mutex_destroy(&pag->pag_ici_reclaim_lock);
 		call_rcu(&pag->rcu_head, __xfs_free_perag);
 	}
 }
···
 		pag->pag_agno = index;
 		pag->pag_mount = mp;
 		spin_lock_init(&pag->pag_ici_lock);
-		mutex_init(&pag->pag_ici_reclaim_lock);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 		if (xfs_buf_hash_init(pag))
 			goto out_free_pag;
···
 out_hash_destroy:
 	xfs_buf_hash_destroy(pag);
 out_free_pag:
-	mutex_destroy(&pag->pag_ici_reclaim_lock);
 	kmem_free(pag);
 out_unwind_new_pags:
 	/* unwind any prior newly initialized pags */
···
 			break;
 		xfs_buf_hash_destroy(pag);
 		xfs_iunlink_destroy(pag);
-		mutex_destroy(&pag->pag_ici_reclaim_lock);
 		kmem_free(pag);
 	}
 	return error;
···
 	 * quota inodes.
 	 */
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	xfs_reclaim_inodes(mp);
 	xfs_health_unmount(mp);
  out_log_dealloc:
 	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
···
 	xfs_ail_push_all_sync(mp->m_ail);
 
 	/*
-	 * And reclaim all inodes.  At this point there should be no dirty
-	 * inodes and none should be pinned or locked, but use synchronous
-	 * reclaim just to be sure. We can stop background inode reclaim
-	 * here as well if it is still running.
+	 * Reclaim all inodes. At this point there should be no dirty inodes and
+	 * none should be pinned or locked. Stop background inode reclaim here
+	 * if it is still running.
 	 */
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	xfs_reclaim_inodes(mp);
 	xfs_health_unmount(mp);
 
 	xfs_qm_unmount(mp);

fs/xfs/xfs_mount.h

···
 	spinlock_t	pag_ici_lock;	/* incore inode cache lock */
 	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
-	struct mutex	pag_ici_reclaim_lock;	/* serialisation point */
 	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */
 
 	/* buffer cache index */

fs/xfs/xfs_qm.c

···
 STATIC int
 xfs_qm_dquot_walk(
 	struct xfs_mount	*mp,
-	int			type,
+	xfs_dqtype_t		type,
 	int			(*execute)(struct xfs_dquot *dqp, void *data),
 	void			*data)
 {
···
 		for (i = 0; i < nr_found; i++) {
 			struct xfs_dquot *dqp = batch[i];
 
-			next_index = be32_to_cpu(dqp->q_core.d_id) + 1;
+			next_index = dqp->q_id + 1;
 
 			error = execute(batch[i], data);
 			if (error == -EAGAIN) {
···
 	int			error = -EAGAIN;
 
 	xfs_dqlock(dqp);
-	if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0)
+	if ((dqp->q_flags & XFS_DQFLAG_FREEING) || dqp->q_nrefs != 0)
 		goto out_unlock;
 
-	dqp->dq_flags |= XFS_DQ_FREEING;
+	dqp->q_flags |= XFS_DQFLAG_FREEING;
 
 	xfs_dqflock(dqp);
 
···
 			error = xfs_bwrite(bp);
 			xfs_buf_relse(bp);
 		} else if (error == -EAGAIN) {
+			dqp->q_flags &= ~XFS_DQFLAG_FREEING;
 			goto out_unlock;
 		}
 		xfs_dqflock(dqp);
···
 	xfs_dqfunlock(dqp);
 	xfs_dqunlock(dqp);
 
-	radix_tree_delete(xfs_dquot_tree(qi, dqp->q_core.d_flags),
-			  be32_to_cpu(dqp->q_core.d_id));
+	radix_tree_delete(xfs_dquot_tree(qi, xfs_dquot_type(dqp)), dqp->q_id);
 	qi->qi_dquots--;
 
 	/*
···
 	uint			flags)
 {
 	if (flags & XFS_QMOPT_UQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
+		xfs_qm_dquot_walk(mp, XFS_DQTYPE_USER, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_GQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
+		xfs_qm_dquot_walk(mp, XFS_DQTYPE_GROUP, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_PQUOTA)
-		xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge, NULL);
+		xfs_qm_dquot_walk(mp, XFS_DQTYPE_PROJ, xfs_qm_dqpurge, NULL);
 }
 
 /*
···
 xfs_qm_dqattach_one(
 	struct xfs_inode	*ip,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	bool			doalloc,
 	struct xfs_dquot	**IO_idqpp)
 {
···
 
 	if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
 		error = xfs_qm_dqattach_one(ip, i_uid_read(VFS_I(ip)),
-				XFS_DQ_USER, doalloc, &ip->i_udquot);
+				XFS_DQTYPE_USER, doalloc, &ip->i_udquot);
 		if (error)
 			goto done;
 		ASSERT(ip->i_udquot);
···
 
 	if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
 		error = xfs_qm_dqattach_one(ip, i_gid_read(VFS_I(ip)),
-				XFS_DQ_GROUP, doalloc, &ip->i_gdquot);
+				XFS_DQTYPE_GROUP, doalloc, &ip->i_gdquot);
 		if (error)
 			goto done;
 		ASSERT(ip->i_gdquot);
 	}
 
 	if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
-		error = xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQ_PROJ,
+		error = xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQTYPE_PROJ,
 				doalloc, &ip->i_pdquot);
 		if (error)
 			goto done;
···
 	/*
 	 * Prevent lookups now that we are past the point of no return.
 	 */
-	dqp->dq_flags |= XFS_DQ_FREEING;
+	dqp->q_flags |= XFS_DQFLAG_FREEING;
 	xfs_dqunlock(dqp);
 
 	ASSERT(dqp->q_nrefs == 0);
···
 STATIC void
 xfs_qm_set_defquota(
 	struct xfs_mount	*mp,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct xfs_quotainfo	*qinf)
 {
 	struct xfs_dquot	*dqp;
 	struct xfs_def_quota	*defq;
-	struct xfs_disk_dquot	*ddqp;
 	int			error;
 
 	error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
 	if (error)
 		return;
 
-	ddqp = &dqp->q_core;
 	defq = xfs_get_defquota(qinf, xfs_dquot_type(dqp));
 
 	/*
 	 * Timers and warnings have been already set, let's just set the
 	 * default limits for this quota type
 	 */
-	defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
-	defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
-	defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
-	defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
-	defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
-	defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+	defq->blk.hard = dqp->q_blk.hardlimit;
+	defq->blk.soft = dqp->q_blk.softlimit;
+	defq->ino.hard = dqp->q_ino.hardlimit;
+	defq->ino.soft = dqp->q_ino.softlimit;
+	defq->rtb.hard = dqp->q_rtb.hardlimit;
+	defq->rtb.soft = dqp->q_rtb.softlimit;
 	xfs_qm_dqdestroy(dqp);
 }
 
···
 static void
 xfs_qm_init_timelimits(
 	struct xfs_mount	*mp,
-	uint			type)
+	xfs_dqtype_t		type)
 {
 	struct xfs_quotainfo	*qinf = mp->m_quotainfo;
 	struct xfs_def_quota	*defq;
-	struct xfs_disk_dquot	*ddqp;
 	struct xfs_dquot	*dqp;
 	int			error;
 
 	defq = xfs_get_defquota(qinf, type);
 
-	defq->btimelimit = XFS_QM_BTIMELIMIT;
-	defq->itimelimit = XFS_QM_ITIMELIMIT;
-	defq->rtbtimelimit = XFS_QM_RTBTIMELIMIT;
-	defq->bwarnlimit = XFS_QM_BWARNLIMIT;
-	defq->iwarnlimit = XFS_QM_IWARNLIMIT;
-	defq->rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
+	defq->blk.time = XFS_QM_BTIMELIMIT;
+	defq->ino.time = XFS_QM_ITIMELIMIT;
+	defq->rtb.time = XFS_QM_RTBTIMELIMIT;
+	defq->blk.warn = XFS_QM_BWARNLIMIT;
+	defq->ino.warn = XFS_QM_IWARNLIMIT;
+	defq->rtb.warn = XFS_QM_RTBWARNLIMIT;
 
 	/*
 	 * We try to get the limits from the superuser's limits fields.
···
 	if (error)
 		return;
 
-	ddqp = &dqp->q_core;
-
 	/*
 	 * The warnings and timers set the grace period given to
 	 * a user or group before he or she can not perform any
 	 * more writing. If it is zero, a default is used.
 	 */
-	if (ddqp->d_btimer)
-		defq->btimelimit = be32_to_cpu(ddqp->d_btimer);
-	if (ddqp->d_itimer)
-		defq->itimelimit = be32_to_cpu(ddqp->d_itimer);
-	if (ddqp->d_rtbtimer)
-		defq->rtbtimelimit = be32_to_cpu(ddqp->d_rtbtimer);
-	if (ddqp->d_bwarns)
-		defq->bwarnlimit = be16_to_cpu(ddqp->d_bwarns);
-	if (ddqp->d_iwarns)
-		defq->iwarnlimit = be16_to_cpu(ddqp->d_iwarns);
-	if (ddqp->d_rtbwarns)
-		defq->rtbwarnlimit = be16_to_cpu(ddqp->d_rtbwarns);
+	if (dqp->q_blk.timer)
+		defq->blk.time = dqp->q_blk.timer;
+	if (dqp->q_ino.timer)
+		defq->ino.time = dqp->q_ino.timer;
+	if (dqp->q_rtb.timer)
+		defq->rtb.time = dqp->q_rtb.timer;
+	if (dqp->q_blk.warnings)
+		defq->blk.warn = dqp->q_blk.warnings;
+	if (dqp->q_ino.warnings)
+		defq->ino.warn = dqp->q_ino.warnings;
+	if (dqp->q_rtb.warnings)
+		defq->rtb.warn = dqp->q_rtb.warnings;
 
 	xfs_qm_dqdestroy(dqp);
 }
···
 
 	mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
 
-	xfs_qm_init_timelimits(mp, XFS_DQ_USER);
-	xfs_qm_init_timelimits(mp, XFS_DQ_GROUP);
-	xfs_qm_init_timelimits(mp, XFS_DQ_PROJ);
+	xfs_qm_init_timelimits(mp, XFS_DQTYPE_USER);
+	xfs_qm_init_timelimits(mp, XFS_DQTYPE_GROUP);
+	xfs_qm_init_timelimits(mp, XFS_DQTYPE_PROJ);
 
 	if (XFS_IS_UQUOTA_RUNNING(mp))
-		xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
+		xfs_qm_set_defquota(mp, XFS_DQTYPE_USER, qinf);
 	if (XFS_IS_GQUOTA_RUNNING(mp))
-		xfs_qm_set_defquota(mp, XFS_DQ_GROUP, qinf);
+		xfs_qm_set_defquota(mp, XFS_DQTYPE_GROUP, qinf);
 	if (XFS_IS_PQUOTA_RUNNING(mp))
-		xfs_qm_set_defquota(mp, XFS_DQ_PROJ, qinf);
+		xfs_qm_set_defquota(mp, XFS_DQTYPE_PROJ, qinf);
 
 	qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
 	qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
···
 
 STATIC void
 xfs_qm_reset_dqcounts(
-	xfs_mount_t	*mp,
-	xfs_buf_t	*bp,
-	xfs_dqid_t	id,
-	uint		type)
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	xfs_dqid_t		id,
+	xfs_dqtype_t		type)
 {
 	struct xfs_dqblk	*dqb;
 	int			j;
-	xfs_failaddr_t		fa;
 
 	trace_xfs_reset_dqcounts(bp, _RET_IP_);
 
···
 		 * find uninitialised dquot blks. See comment in
 		 * xfs_dquot_verify.
 		 */
-		fa = xfs_dqblk_verify(mp, &dqb[j], id + j, type);
-		if (fa)
+		if (xfs_dqblk_verify(mp, &dqb[j], id + j) ||
+		    (dqb[j].dd_diskdq.d_type & XFS_DQTYPE_REC_MASK) != type)
 			xfs_dqblk_repair(mp, &dqb[j], id + j, type);
 
 		/*
 		 * Reset type in case we are reusing group quota file for
 		 * project quotas or vice versa
 		 */
-		ddq->d_flags = type;
+		ddq->d_type = type;
 		ddq->d_bcount = 0;
 		ddq->d_icount = 0;
 		ddq->d_rtbcount = 0;
···
 	xfs_dqid_t		firstid,
 	xfs_fsblock_t		bno,
 	xfs_filblks_t		blkcnt,
-	uint			flags,
+	xfs_dqtype_t		type,
 	struct list_head	*buffer_list)
 {
 	struct xfs_buf		*bp;
-	int			error;
-	int			type;
+	int			error = 0;
 
 	ASSERT(blkcnt > 0);
-	type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER :
-		(flags & XFS_QMOPT_PQUOTA ? XFS_DQ_PROJ : XFS_DQ_GROUP);
-	error = 0;
 
 	/*
 	 * Blkcnt arg can be a very big number, and might even be
···
 xfs_qm_reset_dqcounts_buf(
 	struct xfs_mount	*mp,
 	struct xfs_inode	*qip,
-	uint			flags,
+	xfs_dqtype_t		type,
 	struct list_head	*buffer_list)
 {
 	struct xfs_bmbt_irec	*map;
···
 			error = xfs_qm_reset_dqcounts_all(mp, firstid,
 						   map[i].br_startblock,
 						   map[i].br_blockcount,
-						   flags, buffer_list);
+						   type, buffer_list);
 			if (error)
 				goto out;
 		}
···
 STATIC int
 xfs_qm_quotacheck_dqadjust(
 	struct xfs_inode	*ip,
-	uint			type,
+	xfs_dqtype_t		type,
 	xfs_qcnt_t		nblks,
 	xfs_qcnt_t		rtblks)
 {
···
 	 * Adjust the inode count and the block count to reflect this inode's
 	 * resource usage.
 	 */
-	be64_add_cpu(&dqp->q_core.d_icount, 1);
-	dqp->q_res_icount++;
+	dqp->q_ino.count++;
+	dqp->q_ino.reserved++;
 	if (nblks) {
-		be64_add_cpu(&dqp->q_core.d_bcount, nblks);
-		dqp->q_res_bcount += nblks;
+		dqp->q_blk.count += nblks;
+		dqp->q_blk.reserved += nblks;
 	}
 	if (rtblks) {
-		be64_add_cpu(&dqp->q_core.d_rtbcount, rtblks);
-		dqp->q_res_rtbcount += rtblks;
+		dqp->q_rtb.count += rtblks;
+		dqp->q_rtb.reserved += rtblks;
 	}
 
 	/*
···
 	 *
 	 * There are no timers for the default values set in the root dquot.
 	 */
-	if (dqp->q_core.d_id) {
-		xfs_qm_adjust_dqlimits(mp, dqp);
-		xfs_qm_adjust_dqtimers(mp, dqp);
+	if (dqp->q_id) {
+		xfs_qm_adjust_dqlimits(dqp);
+		xfs_qm_adjust_dqtimers(dqp);
 	}
 
-	dqp->dq_flags |= XFS_DQ_DIRTY;
+	dqp->q_flags |= XFS_DQFLAG_DIRTY;
 	xfs_qm_dqput(dqp);
 	return 0;
 }
···
 	 * and quotaoffs don't race. (Quotachecks happen at mount time only).
 	 */
 	if (XFS_IS_UQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_USER, nblks,
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQTYPE_USER, nblks,
 				rtblks);
 		if (error)
 			goto error0;
 	}
 
 	if (XFS_IS_GQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_GROUP, nblks,
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQTYPE_GROUP, nblks,
 				rtblks);
 		if (error)
 			goto error0;
 	}
 
 	if (XFS_IS_PQUOTA_ON(mp)) {
-		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_PROJ, nblks,
+		error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQTYPE_PROJ, nblks,
 				rtblks);
 		if (error)
 			goto error0;
···
 	int			error = 0;
 
 	xfs_dqlock(dqp);
-	if (dqp->dq_flags & XFS_DQ_FREEING)
+	if (dqp->q_flags & XFS_DQFLAG_FREEING)
 		goto out_unlock;
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
···
 	 * We don't log our changes till later.
 	 */
 	if (uip) {
-		error = xfs_qm_reset_dqcounts_buf(mp, uip, XFS_QMOPT_UQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, uip, XFS_DQTYPE_USER,
 					 &buffer_list);
 		if (error)
 			goto error_return;
···
 	}
 
 	if (gip) {
-		error = xfs_qm_reset_dqcounts_buf(mp, gip, XFS_QMOPT_GQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, gip, XFS_DQTYPE_GROUP,
 					 &buffer_list);
 		if (error)
 			goto error_return;
···
 	}
 
 	if (pip) {
-		error = xfs_qm_reset_dqcounts_buf(mp, pip, XFS_QMOPT_PQUOTA,
+		error = xfs_qm_reset_dqcounts_buf(mp, pip, XFS_DQTYPE_PROJ,
 					 &buffer_list);
 		if (error)
 			goto error_return;
···
 	 * down to disk buffers if everything was updated successfully.
 	 */
 	if (XFS_IS_UQUOTA_ON(mp)) {
-		error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one,
+		error = xfs_qm_dquot_walk(mp, XFS_DQTYPE_USER, xfs_qm_flush_one,
 					  &buffer_list);
 	}
 	if (XFS_IS_GQUOTA_ON(mp)) {
-		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one,
+		error2 = xfs_qm_dquot_walk(mp, XFS_DQTYPE_GROUP, xfs_qm_flush_one,
 					   &buffer_list);
 		if (!error)
 			error = error2;
 	}
 	if (XFS_IS_PQUOTA_ON(mp)) {
-		error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one,
+		error2 = xfs_qm_dquot_walk(mp, XFS_DQTYPE_PROJ, xfs_qm_flush_one,
 					   &buffer_list);
 		if (!error)
 			error = error2;
···
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 
 	mutex_lock(&qi->qi_tree_lock);
-	radix_tree_delete(xfs_dquot_tree(qi, dqp->q_core.d_flags),
-			  be32_to_cpu(dqp->q_core.d_id));
+	radix_tree_delete(xfs_dquot_tree(qi, xfs_dquot_type(dqp)), dqp->q_id);
 
 	qi->qi_dquots--;
 	mutex_unlock(&qi->qi_tree_lock);
···
 			 */
 			xfs_iunlock(ip, lockflags);
 			error = xfs_qm_dqget(mp, from_kuid(user_ns, uid),
-					XFS_DQ_USER, true, &uq);
+					XFS_DQTYPE_USER, true, &uq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				return error;
···
 		if (!gid_eq(inode->i_gid, gid)) {
 			xfs_iunlock(ip, lockflags);
 			error = xfs_qm_dqget(mp, from_kgid(user_ns, gid),
-					XFS_DQ_GROUP, true, &gq);
+					XFS_DQTYPE_GROUP, true, &gq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				goto error_rele;
···
 	if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
 		if (ip->i_d.di_projid != prid) {
 			xfs_iunlock(ip, lockflags);
-			error = xfs_qm_dqget(mp, (xfs_dqid_t)prid, XFS_DQ_PROJ,
-					true, &pq);
+			error = xfs_qm_dqget(mp, (xfs_dqid_t)prid,
+					XFS_DQTYPE_PROJ, true, &pq);
 			if (error) {
 				ASSERT(error != -ENOENT);
 				goto error_rele;
···
 			XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS;
 
 	if (XFS_IS_UQUOTA_ON(mp) && udqp &&
-	    i_uid_read(VFS_I(ip)) != be32_to_cpu(udqp->q_core.d_id)) {
+	    i_uid_read(VFS_I(ip)) != udqp->q_id) {
 		udq_delblks = udqp;
 		/*
 		 * If there are delayed allocation blocks, then we have to
···
 		}
 	}
 	if (XFS_IS_GQUOTA_ON(ip->i_mount) && gdqp &&
-	    i_gid_read(VFS_I(ip)) != be32_to_cpu(gdqp->q_core.d_id)) {
+	    i_gid_read(VFS_I(ip)) != gdqp->q_id) {
 		gdq_delblks = gdqp;
 		if (delblks) {
 			ASSERT(ip->i_gdquot);
···
 	}
 
 	if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp &&
-	    ip->i_d.di_projid != be32_to_cpu(pdqp->q_core.d_id)) {
+	    ip->i_d.di_projid != pdqp->q_id) {
 		pdq_delblks = pdqp;
 		if (delblks) {
 			ASSERT(ip->i_pdquot);
···
 
 	if (udqp && XFS_IS_UQUOTA_ON(mp)) {
 		ASSERT(ip->i_udquot == NULL);
-		ASSERT(i_uid_read(VFS_I(ip)) == be32_to_cpu(udqp->q_core.d_id));
+		ASSERT(i_uid_read(VFS_I(ip)) == udqp->q_id);
 
 		ip->i_udquot = xfs_qm_dqhold(udqp);
 		xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
 	if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
 		ASSERT(ip->i_gdquot == NULL);
-		ASSERT(i_gid_read(VFS_I(ip)) == be32_to_cpu(gdqp->q_core.d_id));
+		ASSERT(i_gid_read(VFS_I(ip)) == gdqp->q_id);
 
 		ip->i_gdquot = xfs_qm_dqhold(gdqp);
 		xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
 	if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(ip->i_pdquot == NULL);
-		ASSERT(ip->i_d.di_projid == be32_to_cpu(pdqp->q_core.d_id));
+		ASSERT(ip->i_d.di_projid == pdqp->q_id);
 
 		ip->i_pdquot = xfs_qm_dqhold(pdqp);
 		xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1);

fs/xfs/xfs_qm.h

···
 #define XFS_DQITER_MAP_SIZE	10
 
 #define XFS_IS_DQUOT_UNINITIALIZED(dqp) ( \
-	!dqp->q_core.d_blk_hardlimit && \
-	!dqp->q_core.d_blk_softlimit && \
-	!dqp->q_core.d_rtb_hardlimit && \
-	!dqp->q_core.d_rtb_softlimit && \
-	!dqp->q_core.d_ino_hardlimit && \
-	!dqp->q_core.d_ino_softlimit && \
-	!dqp->q_core.d_bcount && \
-	!dqp->q_core.d_rtbcount && \
-	!dqp->q_core.d_icount)
+	!dqp->q_blk.hardlimit && \
+	!dqp->q_blk.softlimit && \
+	!dqp->q_rtb.hardlimit && \
+	!dqp->q_rtb.softlimit && \
+	!dqp->q_ino.hardlimit && \
+	!dqp->q_ino.softlimit && \
+	!dqp->q_blk.count && \
+	!dqp->q_rtb.count && \
+	!dqp->q_ino.count)
 
-/*
- * This defines the unit of allocation of dquots.
- * Currently, it is just one file system block, and a 4K blk contains 30
- * (136 * 30 = 4080) dquots. It's probably not worth trying to make
- * this more dynamic.
- * XXXsup However, if this number is changed, we have to make sure that we don't
- * implicitly assume that we do allocations in chunks of a single filesystem
- * block in the dquot/xqm code.
- */
-#define XFS_DQUOT_CLUSTER_SIZE_FSB	(xfs_filblks_t)1
+struct xfs_quota_limits {
+	xfs_qcnt_t		hard;	/* default hard limit */
+	xfs_qcnt_t		soft;	/* default soft limit */
+	time64_t		time;	/* limit for timers */
+	xfs_qwarncnt_t		warn;	/* limit for warnings */
+};
 
 /* Defaults for each quota type: time limits, warn limits, usage limits */
 struct xfs_def_quota {
-	time64_t	btimelimit;	/* limit for blks timer */
-	time64_t	itimelimit;	/* limit for inodes timer */
-	time64_t	rtbtimelimit;	/* limit for rt blks timer */
-	xfs_qwarncnt_t	bwarnlimit;	/* limit for blks warnings */
-	xfs_qwarncnt_t	iwarnlimit;	/* limit for inodes warnings */
-	xfs_qwarncnt_t	rtbwarnlimit;	/* limit for rt blks warnings */
-	xfs_qcnt_t	bhardlimit;	/* default data blk hard limit */
-	xfs_qcnt_t	bsoftlimit;	/* default data blk soft limit */
-	xfs_qcnt_t	ihardlimit;	/* default inode count hard limit */
-	xfs_qcnt_t	isoftlimit;	/* default inode count soft limit */
-	xfs_qcnt_t	rtbhardlimit;	/* default realtime blk hard limit */
-	xfs_qcnt_t	rtbsoftlimit;	/* default realtime blk soft limit */
+	struct xfs_quota_limits	blk;
+	struct xfs_quota_limits	ino;
+	struct xfs_quota_limits	rtb;
 };
 
 /*
···
 static inline struct radix_tree_root *
 xfs_dquot_tree(
 	struct xfs_quotainfo	*qi,
-	int			type)
+	xfs_dqtype_t		type)
 {
 	switch (type) {
-	case XFS_DQ_USER:
+	case XFS_DQTYPE_USER:
 		return &qi->qi_uquota_tree;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return &qi->qi_gquota_tree;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return &qi->qi_pquota_tree;
 	default:
 		ASSERT(0);
···
 }
 
 static inline struct xfs_inode *
-xfs_quota_inode(xfs_mount_t *mp, uint dq_flags)
+xfs_quota_inode(struct xfs_mount *mp, xfs_dqtype_t type)
 {
-	switch (dq_flags & XFS_DQ_ALLTYPES) {
-	case XFS_DQ_USER:
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return mp->m_quotainfo->qi_uquotaip;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return mp->m_quotainfo->qi_gquotaip;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return mp->m_quotainfo->qi_pquotaip;
 	default:
 		ASSERT(0);
 	}
 	return NULL;
-}
-
-static inline int
-xfs_dquot_type(struct xfs_dquot *dqp)
-{
-	if (XFS_QM_ISUDQ(dqp))
-		return XFS_DQ_USER;
-	if (XFS_QM_ISGDQ(dqp))
-		return XFS_DQ_GROUP;
-	ASSERT(XFS_QM_ISPDQ(dqp));
-	return XFS_DQ_PROJ;
 }
 
 extern void	xfs_trans_mod_dquot(struct xfs_trans *tp, struct xfs_dquot *dqp,
···
 
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
-extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct qc_dqblk *);
-extern int		xfs_qm_scall_getquota_next(struct xfs_mount *,
-					xfs_dqid_t *, uint, struct qc_dqblk *);
-extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
-					struct qc_dqblk *);
+extern int		xfs_qm_scall_getquota(struct xfs_mount *mp,
+					xfs_dqid_t id,
+					xfs_dqtype_t type,
+					struct qc_dqblk *dst);
+extern int		xfs_qm_scall_getquota_next(struct xfs_mount *mp,
+					xfs_dqid_t *id,
+					xfs_dqtype_t type,
+					struct qc_dqblk *dst);
+extern int		xfs_qm_scall_setqlim(struct xfs_mount *mp,
+					xfs_dqid_t id,
+					xfs_dqtype_t type,
+					struct qc_dqblk *newlim);
 extern int		xfs_qm_scall_quotaon(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_quotaoff(struct xfs_mount *, uint);
 
 static inline struct xfs_def_quota *
-xfs_get_defquota(struct xfs_quotainfo *qi, int type)
+xfs_get_defquota(struct xfs_quotainfo *qi, xfs_dqtype_t type)
 {
 	switch (type) {
-	case XFS_DQ_USER:
+	case XFS_DQTYPE_USER:
 		return &qi->qi_usr_default;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return &qi->qi_grp_default;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return &qi->qi_prj_default;
 	default:
 		ASSERT(0);

fs/xfs/xfs_qm_bhv.c

···
 {
 	uint64_t		limit;
 
-	limit = dqp->q_core.d_blk_softlimit ?
-		be64_to_cpu(dqp->q_core.d_blk_softlimit) :
-		be64_to_cpu(dqp->q_core.d_blk_hardlimit);
+	limit = dqp->q_blk.softlimit ?
+		dqp->q_blk.softlimit :
+		dqp->q_blk.hardlimit;
 	if (limit && statp->f_blocks > limit) {
 		statp->f_blocks = limit;
 		statp->f_bfree = statp->f_bavail =
-			(statp->f_blocks > dqp->q_res_bcount) ?
-			 (statp->f_blocks - dqp->q_res_bcount) : 0;
+			(statp->f_blocks > dqp->q_blk.reserved) ?
+			 (statp->f_blocks - dqp->q_blk.reserved) : 0;
 	}
 
-	limit = dqp->q_core.d_ino_softlimit ?
-		be64_to_cpu(dqp->q_core.d_ino_softlimit) :
-		be64_to_cpu(dqp->q_core.d_ino_hardlimit);
+	limit = dqp->q_ino.softlimit ?
+		dqp->q_ino.softlimit :
+		dqp->q_ino.hardlimit;
 	if (limit && statp->f_files > limit) {
 		statp->f_files = limit;
 		statp->f_ffree =
-			(statp->f_files > dqp->q_res_icount) ?
-			 (statp->f_files - dqp->q_res_icount) : 0;
+			(statp->f_files > dqp->q_ino.reserved) ?
+			 (statp->f_files - dqp->q_ino.reserved) : 0;
 	}
 }
 
···
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_dquot	*dqp;
 
-	if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQ_PROJ, false, &dqp)) {
+	if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
 		xfs_fill_statvfs_from_dquot(statp, dqp);
 		xfs_qm_dqput(dqp);
 	}

fs/xfs/xfs_qm_syscalls.c

···
 	int		error = -EINVAL;
 
 	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0 ||
-	    (flags & ~XFS_DQ_ALLTYPES)) {
+	    (flags & ~XFS_QMOPT_QUOTALL)) {
 		xfs_debug(mp, "%s: flags=%x m_qflags=%x",
 			__func__, flags, mp->m_qflags);
 		return -EINVAL;
 	}
 
-	if (flags & XFS_DQ_USER) {
+	if (flags & XFS_QMOPT_UQUOTA) {
 		error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_uquotino);
 		if (error)
 			return error;
 	}
-	if (flags & XFS_DQ_GROUP) {
+	if (flags & XFS_QMOPT_GQUOTA) {
 		error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_gquotino);
 		if (error)
 			return error;
 	}
-	if (flags & XFS_DQ_PROJ)
+	if (flags & XFS_QMOPT_PQUOTA)
 		error = xfs_qm_scall_trunc_qfile(mp, mp->m_sb.sb_pquotino);
 
 	return error;
···
 	(QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK)
 
 /*
+ * Adjust limits of this quota, and the defaults if passed in.  Returns true
+ * if the new limits made sense and were applied, false otherwise.
+ */
+static inline bool
+xfs_setqlim_limits(
+	struct xfs_mount	*mp,
+	struct xfs_dquot_res	*res,
+	struct xfs_quota_limits	*qlim,
+	xfs_qcnt_t		hard,
+	xfs_qcnt_t		soft,
+	const char		*tag)
+{
+	/* The hard limit can't be less than the soft limit. */
+	if (hard != 0 && hard < soft) {
+		xfs_debug(mp, "%shard %lld < %ssoft %lld", tag, hard, tag,
+				soft);
+		return false;
+	}
+
+	res->hardlimit = hard;
+	res->softlimit = soft;
+	if (qlim) {
+		qlim->hard = hard;
+		qlim->soft = soft;
+	}
+
+	return true;
+}
+
+static inline void
+xfs_setqlim_warns(
+	struct xfs_dquot_res	*res,
+	struct xfs_quota_limits	*qlim,
+	int			warns)
+{
+	res->warnings = warns;
+	if (qlim)
+		qlim->warn = warns;
+}
+
+static inline void
+xfs_setqlim_timer(
+	struct xfs_dquot_res	*res,
+	struct xfs_quota_limits	*qlim,
+	s64			timer)
+{
+	res->timer = timer;
+	if (qlim)
+		qlim->time = timer;
+}
+
+/*
  * Adjust quota limits, and start/stop timers accordingly.
  */
 int
 xfs_qm_scall_setqlim(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct qc_dqblk		*newlim)
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
-	struct xfs_disk_dquot	*ddq;
 	struct xfs_dquot	*dqp;
 	struct xfs_trans	*tp;
 	struct xfs_def_quota	*defq;
+	struct xfs_dquot_res	*res;
+	struct xfs_quota_limits	*qlim;
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
···
 
 	xfs_dqlock(dqp);
 	xfs_trans_dqjoin(tp, dqp);
-	ddq = &dqp->q_core;
 
 	/*
+	 * Update quota limits, warnings, and timers, and the defaults
+	 * if we're touching id == 0.
+	 *
 	 * Make sure that hardlimits are >= soft limits before changing.
-	 */
-	hard = (newlim->d_fieldmask & QC_SPC_HARD) ?
-		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) :
-			be64_to_cpu(ddq->d_blk_hardlimit);
-	soft = (newlim->d_fieldmask & QC_SPC_SOFT) ?
-		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) :
-			be64_to_cpu(ddq->d_blk_softlimit);
-	if (hard == 0 || hard >= soft) {
-		ddq->d_blk_hardlimit = cpu_to_be64(hard);
-		ddq->d_blk_softlimit = cpu_to_be64(soft);
-		xfs_dquot_set_prealloc_limits(dqp);
-		if (id == 0) {
-			defq->bhardlimit = hard;
-			defq->bsoftlimit = soft;
-		}
-	} else {
-		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
-	}
-	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
-		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) :
-			be64_to_cpu(ddq->d_rtb_hardlimit);
-	soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ?
-		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) :
-			be64_to_cpu(ddq->d_rtb_softlimit);
-	if (hard == 0 || hard >= soft) {
-		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
-		ddq->d_rtb_softlimit = cpu_to_be64(soft);
-		if (id == 0) {
-			defq->rtbhardlimit = hard;
-			defq->rtbsoftlimit = soft;
-		}
-	} else {
-		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
-	}
-
-	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
-		(xfs_qcnt_t) newlim->d_ino_hardlimit :
-			be64_to_cpu(ddq->d_ino_hardlimit);
-	soft = (newlim->d_fieldmask & QC_INO_SOFT) ?
-		(xfs_qcnt_t) newlim->d_ino_softlimit :
-			be64_to_cpu(ddq->d_ino_softlimit);
-	if (hard == 0 || hard >= soft) {
-		ddq->d_ino_hardlimit = cpu_to_be64(hard);
-		ddq->d_ino_softlimit = cpu_to_be64(soft);
-		if (id == 0) {
-			defq->ihardlimit = hard;
-			defq->isoftlimit = soft;
-		}
-	} else {
-		xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft);
-	}
-
-	/*
-	 * Update warnings counter(s) if requested
-	 */
-	if (newlim->d_fieldmask & QC_SPC_WARNS)
-		ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns);
-	if (newlim->d_fieldmask & QC_INO_WARNS)
-		ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns);
-	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
-		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns);
-
-	if (id == 0) {
-		if (newlim->d_fieldmask & QC_SPC_WARNS)
-			defq->bwarnlimit = newlim->d_spc_warns;
-		if (newlim->d_fieldmask & QC_INO_WARNS)
-			defq->iwarnlimit = newlim->d_ino_warns;
-		if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
-			defq->rtbwarnlimit = newlim->d_rt_spc_warns;
-	}
-
-	/*
+	 *
+	 * Update warnings counter(s) if requested.
+	 *
 	 * Timelimits for the super user set the relative time the other users
 	 * can be over quota for this file system. If it is zero a default is
 	 * used.  Ditto for the default soft and hard limit values (already
···
 	 * For other IDs, userspace can bump out the grace period if over
 	 * the soft limit.
 	 */
-	if (newlim->d_fieldmask & QC_SPC_TIMER)
-		ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer);
-	if (newlim->d_fieldmask & QC_INO_TIMER)
-		ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer);
-	if (newlim->d_fieldmask & QC_RT_SPC_TIMER)
-		ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer);
 
-	if (id == 0) {
-		if (newlim->d_fieldmask & QC_SPC_TIMER)
-			defq->btimelimit = newlim->d_spc_timer;
-		if (newlim->d_fieldmask & QC_INO_TIMER)
-			defq->itimelimit = newlim->d_ino_timer;
-		if (newlim->d_fieldmask & QC_RT_SPC_TIMER)
-			defq->rtbtimelimit = newlim->d_rt_spc_timer;
-	}
+	/* Blocks on the data device. */
+	hard = (newlim->d_fieldmask & QC_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) :
+			dqp->q_blk.hardlimit;
+	soft = (newlim->d_fieldmask & QC_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) :
+			dqp->q_blk.softlimit;
+	res = &dqp->q_blk;
+	qlim = id == 0 ? &defq->blk : NULL;
+
+	if (xfs_setqlim_limits(mp, res, qlim, hard, soft, "blk"))
+		xfs_dquot_set_prealloc_limits(dqp);
+	if (newlim->d_fieldmask & QC_SPC_WARNS)
+		xfs_setqlim_warns(res, qlim, newlim->d_spc_warns);
+	if (newlim->d_fieldmask & QC_SPC_TIMER)
+		xfs_setqlim_timer(res, qlim, newlim->d_spc_timer);
+
+	/* Blocks on the realtime device. */
+	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) :
+			dqp->q_rtb.hardlimit;
+	soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) :
+			dqp->q_rtb.softlimit;
+	res = &dqp->q_rtb;
+	qlim = id == 0 ? &defq->rtb : NULL;
+
+	xfs_setqlim_limits(mp, res, qlim, hard, soft, "rtb");
+	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+		xfs_setqlim_warns(res, qlim, newlim->d_rt_spc_warns);
+	if (newlim->d_fieldmask & QC_RT_SPC_TIMER)
+		xfs_setqlim_timer(res, qlim, newlim->d_rt_spc_timer);
+
+	/* Inodes */
+	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
+		(xfs_qcnt_t) newlim->d_ino_hardlimit :
+			dqp->q_ino.hardlimit;
+	soft = (newlim->d_fieldmask & QC_INO_SOFT) ?
+		(xfs_qcnt_t) newlim->d_ino_softlimit :
+			dqp->q_ino.softlimit;
+	res = &dqp->q_ino;
+	qlim = id == 0 ? &defq->ino : NULL;
+
+	xfs_setqlim_limits(mp, res, qlim, hard, soft, "ino");
+	if (newlim->d_fieldmask & QC_INO_WARNS)
+		xfs_setqlim_warns(res, qlim, newlim->d_ino_warns);
+	if (newlim->d_fieldmask & QC_INO_TIMER)
+		xfs_setqlim_timer(res, qlim, newlim->d_ino_timer);
 
 	if (id != 0) {
 		/*
···
 		 * is on or off. We don't really want to bother with iterating
 		 * over all ondisk dquots and turning the timers on/off.
 		 */
-		xfs_qm_adjust_dqtimers(mp, dqp);
+		xfs_qm_adjust_dqtimers(dqp);
 	}
-	dqp->dq_flags |= XFS_DQ_DIRTY;
+	dqp->q_flags |= XFS_DQFLAG_DIRTY;
 	xfs_trans_log_dquot(tp, dqp);
 
 	error = xfs_trans_commit(tp);
···
 static void
 xfs_qm_scall_getquota_fill_qc(
 	struct xfs_mount	*mp,
-	uint			type,
+	xfs_dqtype_t		type,
 	const struct xfs_dquot	*dqp,
 	struct qc_dqblk		*dst)
 {
 	memset(dst, 0, sizeof(*dst));
-	dst->d_spc_hardlimit =
-		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
-	dst->d_spc_softlimit =
-		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
-	dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
-	dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
-	dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount);
-	dst->d_ino_count = dqp->q_res_icount;
-	dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer);
-	dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer);
-	dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns);
-	dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns);
-	dst->d_rt_spc_hardlimit =
-		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
-	dst->d_rt_spc_softlimit =
-		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
-	dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount);
-	dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
-	dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
+	dst->d_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_blk.hardlimit);
+	dst->d_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_blk.softlimit);
+	dst->d_ino_hardlimit = dqp->q_ino.hardlimit;
+	dst->d_ino_softlimit = dqp->q_ino.softlimit;
+	dst->d_space = XFS_FSB_TO_B(mp, dqp->q_blk.reserved);
+	dst->d_ino_count = dqp->q_ino.reserved;
+	dst->d_spc_timer = dqp->q_blk.timer;
+	dst->d_ino_timer = dqp->q_ino.timer;
+	dst->d_ino_warns = dqp->q_ino.warnings;
+	dst->d_spc_warns = dqp->q_blk.warnings;
+	dst->d_rt_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.hardlimit);
+	dst->d_rt_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.softlimit);
+	dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_rtb.reserved);
+	dst->d_rt_spc_timer = dqp->q_rtb.timer;
+	dst->d_rt_spc_warns = dqp->q_rtb.warnings;
 
 	/*
 	 * Internally, we don't reset all the timers when quota enforcement
 	 * gets turned off. No need to confuse the user level code,
 	 * so return zeroes in that case.
 	 */
-	if ((!XFS_IS_UQUOTA_ENFORCED(mp) &&
-	     dqp->q_core.d_flags == XFS_DQ_USER) ||
-	    (!XFS_IS_GQUOTA_ENFORCED(mp) &&
-	     dqp->q_core.d_flags == XFS_DQ_GROUP) ||
-	    (!XFS_IS_PQUOTA_ENFORCED(mp) &&
-	     dqp->q_core.d_flags == XFS_DQ_PROJ)) {
+	if (!xfs_dquot_is_enforced(dqp)) {
 		dst->d_spc_timer = 0;
 		dst->d_ino_timer = 0;
 		dst->d_rt_spc_timer = 0;
 	}
 
 #ifdef DEBUG
-	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
-	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
-	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
-	    dqp->q_core.d_id != 0) {
+	if (xfs_dquot_is_enforced(dqp) && dqp->q_id != 0) {
 		if ((dst->d_space > dst->d_spc_softlimit) &&
 		    (dst->d_spc_softlimit > 0)) {
 			ASSERT(dst->d_spc_timer != 0);
 		}
-		if ((dst->d_ino_count > dst->d_ino_softlimit) &&
-		    (dst->d_ino_softlimit > 0)) {
+		if ((dst->d_ino_count > dqp->q_ino.softlimit) &&
+		    (dqp->q_ino.softlimit > 0)) {
 			ASSERT(dst->d_ino_timer != 0);
 		}
 	}
···
 xfs_qm_scall_getquota(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct qc_dqblk		*dst)
 {
 	struct xfs_dquot	*dqp;
···
 xfs_qm_scall_getquota_next(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		*id,
-	uint			type,
+	xfs_dqtype_t		type,
 	struct qc_dqblk		*dst)
 {
 	struct xfs_dquot	*dqp;
···
 		return error;
 
 	/* Fill in the ID we actually read from disk */
-	*id = be32_to_cpu(dqp->q_core.d_id);
+	*id = dqp->q_id;
 
 	xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst);
 

fs/xfs/xfs_quota.h

···
  */
 
 struct xfs_trans;
+struct xfs_buf;
 
 /*
  * This check is done typically without holding the inode lock;
···
 
 static inline uint
 xfs_quota_chkd_flag(
-	uint		dqtype)
+	xfs_dqtype_t		type)
 {
-	switch (dqtype) {
-	case XFS_DQ_USER:
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return XFS_UQUOTA_CHKD;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return XFS_GQUOTA_CHKD;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return XFS_PQUOTA_CHKD;
 	default:
 		return 0;
···
 extern void xfs_qm_unmount(struct xfs_mount *);
 extern void xfs_qm_unmount_quotas(struct xfs_mount *);
 
+void		xfs_dquot_done(struct xfs_buf *);
+
 #else
 static inline int
 xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
···
 #define xfs_qm_mount_quotas(mp)
 #define xfs_qm_unmount(mp)
 #define xfs_qm_unmount_quotas(mp)
+
+static inline void xfs_dquot_done(struct xfs_buf *bp)
+{
+	return;
+}
+
 #endif /* CONFIG_XFS_QUOTA */
 
 #define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \

fs/xfs/xfs_quotaops.c

···
 	tstate->flags |= QCI_SYSFILE;
 	tstate->blocks = ip->i_d.di_nblocks;
 	tstate->nextents = ip->i_df.if_nextents;
-	tstate->spc_timelimit = (u32)defq->btimelimit;
-	tstate->ino_timelimit = (u32)defq->itimelimit;
-	tstate->rt_spc_timelimit = (u32)defq->rtbtimelimit;
-	tstate->spc_warnlimit = defq->bwarnlimit;
-	tstate->ino_warnlimit = defq->iwarnlimit;
-	tstate->rt_spc_warnlimit = defq->rtbwarnlimit;
+	tstate->spc_timelimit = (u32)defq->blk.time;
+	tstate->ino_timelimit = (u32)defq->ino.time;
+	tstate->rt_spc_timelimit = (u32)defq->rtb.time;
+	tstate->spc_warnlimit = defq->blk.warn;
+	tstate->ino_warnlimit = defq->ino.warn;
+	tstate->rt_spc_warnlimit = defq->rtb.warn;
 	if (tempqip)
 		xfs_irele(ip);
 }
···
 	return 0;
 }
 
-STATIC int
+STATIC xfs_dqtype_t
 xfs_quota_type(int type)
 {
 	switch (type) {
 	case USRQUOTA:
-		return XFS_DQ_USER;
+		return XFS_DQTYPE_USER;
 	case GRPQUOTA:
-		return XFS_DQ_GROUP;
+		return XFS_DQTYPE_GROUP;
 	default:
-		return XFS_DQ_PROJ;
+		return XFS_DQTYPE_PROJ;
 	}
 }
 
···
 		return -EINVAL;
 
 	if (uflags & FS_USER_QUOTA)
-		flags |= XFS_DQ_USER;
+		flags |= XFS_QMOPT_UQUOTA;
 	if (uflags & FS_GROUP_QUOTA)
-		flags |= XFS_DQ_GROUP;
+		flags |= XFS_QMOPT_GQUOTA;
 	if (uflags & FS_PROJ_QUOTA)
-		flags |= XFS_DQ_PROJ;
+		flags |= XFS_QMOPT_PQUOTA;
 
 	return xfs_qm_scall_trunc_qfiles(mp, flags);
 }

fs/xfs/xfs_refcount_item.c

···
 		cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents),
 				0);
 	else
-		cuip = kmem_zone_zalloc(xfs_cui_zone, 0);
+		cuip = kmem_cache_zalloc(xfs_cui_zone,
+					 GFP_KERNEL | __GFP_NOFAIL);
 
 	xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops);
 	cuip->cui_format.cui_nextents = nextents;
···
 {
 	struct xfs_cud_log_item		*cudp;
 
-	cudp = kmem_zone_zalloc(xfs_cud_zone, 0);
+	cudp = kmem_cache_zalloc(xfs_cud_zone, GFP_KERNEL | __GFP_NOFAIL);
 	xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
 			  &xfs_cud_item_ops);
 	cudp->cud_cuip = cuip;

fs/xfs/xfs_reflink.c

···
 	int			error = 0;
 
 	/* Holes, unwritten, and delalloc extents cannot be shared */
-	if (!xfs_is_cow_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
+	if (!xfs_is_cow_inode(ip) || !xfs_bmap_is_written_extent(irec)) {
 		*shared = false;
 		return 0;
 	}
···
 	 * preallocations can leak into the range we are called upon, and we
 	 * need to skip them.
 	 */
-	if (!xfs_bmap_is_real_extent(&got)) {
+	if (!xfs_bmap_is_written_extent(&got)) {
 		*end_fsb = del.br_startoff;
 		goto out_cancel;
 	}
···
 }
 
 /*
- * Unmap a range of blocks from a file, then map other blocks into the hole.
- * The range to unmap is (destoff : destoff + srcioff + irec->br_blockcount).
- * The extent irec is mapped into dest at irec->br_startoff.
+ * Remap the given extent into the file.  The dmap blockcount will be set to
+ * the number of blocks that were actually remapped.
  */
 STATIC int
 xfs_reflink_remap_extent(
 	struct xfs_inode	*ip,
-	struct xfs_bmbt_irec	*irec,
-	xfs_fileoff_t		destoff,
+	struct xfs_bmbt_irec	*dmap,
 	xfs_off_t		new_isize)
 {
+	struct xfs_bmbt_irec	smap;
 	struct xfs_mount	*mp = ip->i_mount;
-	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
-	unsigned int		resblks;
-	struct xfs_bmbt_irec	uirec;
-	xfs_filblks_t		rlen;
-	xfs_filblks_t		unmap_len;
 	xfs_off_t		newlen;
+	int64_t			qres, qdelta;
+	unsigned int		resblks;
+	bool			smap_real;
+	bool			dmap_written = xfs_bmap_is_written_extent(dmap);
+	int			nimaps;
 	int			error;
 
-	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
-	trace_xfs_reflink_punch_range(ip, destoff, unmap_len);
-
-	/* No reflinking if we're low on space */
-	if (real_extent) {
-		error = xfs_reflink_ag_has_free_space(mp,
-				XFS_FSB_TO_AGNO(mp, irec->br_startblock));
-		if (error)
-			goto out;
-	}
-
 	/* Start a rolling transaction to switch the mappings */
-	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
+	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out;
···
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* If we're not just clearing space, then do we have enough quota? */
-	if (real_extent) {
-		error = xfs_trans_reserve_quota_nblks(tp, ip,
-				irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
+	/*
+	 * Read what's currently mapped in the destination file into smap.
+	 * If smap isn't a hole, we will have to remove it before we can add
+	 * dmap to the destination file.
+	 */
+	nimaps = 1;
+	error = xfs_bmapi_read(ip, dmap->br_startoff, dmap->br_blockcount,
+			&smap, &nimaps, 0);
+	if (error)
+		goto out_cancel;
+	ASSERT(nimaps == 1 && smap.br_startoff == dmap->br_startoff);
+	smap_real = xfs_bmap_is_real_extent(&smap);
+
+	/*
+	 * We can only remap as many blocks as the smaller of the two extent
+	 * maps, because we can only remap one extent at a time.
+	 */
+	dmap->br_blockcount = min(dmap->br_blockcount, smap.br_blockcount);
+	ASSERT(dmap->br_blockcount == smap.br_blockcount);
+
+	trace_xfs_reflink_remap_extent_dest(ip, &smap);
+
+	/*
+	 * Two extents mapped to the same physical block must not have
+	 * different states; that's filesystem corruption.  Move on to the next
+	 * extent if they're both holes or both the same physical extent.
+	 */
+	if (dmap->br_startblock == smap.br_startblock) {
+		if (dmap->br_state != smap.br_state)
+			error = -EFSCORRUPTED;
+		goto out_cancel;
+	}
+
+	/* If both extents are unwritten, leave them alone. */
+	if (dmap->br_state == XFS_EXT_UNWRITTEN &&
+	    smap.br_state == XFS_EXT_UNWRITTEN)
+		goto out_cancel;
+
+	/* No reflinking if the AG of the dest mapping is low on space. */
+	if (dmap_written) {
+		error = xfs_reflink_ag_has_free_space(mp,
+				XFS_FSB_TO_AGNO(mp, dmap->br_startblock));
 		if (error)
 			goto out_cancel;
 	}
 
-	trace_xfs_reflink_remap(ip, irec->br_startoff,
-				irec->br_blockcount, irec->br_startblock);
-
-	/* Unmap the old blocks in the data fork. */
-	rlen = unmap_len;
-	while (rlen) {
-		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
+	/*
+	 * Compute quota reservation if we think the quota block counter for
+	 * this file could increase.
+	 *
+	 * Adding a written extent to the extent map can cause a bmbt split,
+	 * and removing a mapped extent from the extent can cause a bmbt split.
+	 * The two operations cannot both cause a split since they operate on
+	 * the same index in the bmap btree, so we only need a reservation for
+	 * one bmbt split if either thing is happening.
+	 *
+	 * If we are mapping a written extent into the file, we need to have
+	 * enough quota block count reservation to handle the blocks in that
+	 * extent.  We log only the delta to the quota block counts, so if the
+	 * extent we're unmapping also has blocks allocated to it, we don't
+	 * need a quota reservation for the extent itself.
+	 *
+	 * Note that if we're replacing a delalloc reservation with a written
+	 * extent, we have to take the full quota reservation because removing
+	 * the delalloc reservation gives the block count back to the quota
+	 * count.  This is suboptimal, but the VFS flushed the dest range
+	 * before we started.  That should have removed all the delalloc
+	 * reservations, but we code defensively.
+	 */
+	qres = qdelta = 0;
+	if (smap_real || dmap_written)
+		qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	if (!smap_real && dmap_written)
+		qres += dmap->br_blockcount;
+	if (qres > 0) {
+		error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0,
+				XFS_QMOPT_RES_REGBLKS);
 		if (error)
 			goto out_cancel;
+	}
+
+	if (smap_real) {
+		/*
+		 * If the extent we're unmapping is backed by storage (written
+		 * or not), unmap the extent and drop its refcount.
+		 */
+		xfs_bmap_unmap_extent(tp, ip, &smap);
+		xfs_refcount_decrease_extent(tp, &smap);
+		qdelta -= smap.br_blockcount;
+	} else if (smap.br_startblock == DELAYSTARTBLOCK) {
+		xfs_filblks_t	len = smap.br_blockcount;
 
 		/*
-		 * Trim the extent to whatever got unmapped.
-		 * Remember, bunmapi works backwards.
+		 * If the extent we're unmapping is a delalloc reservation,
+		 * we can use the regular bunmapi function to release the
+		 * incore state.  Dropping the delalloc reservation takes care
+		 * of the quota reservation for us.
 		 */
-		uirec.br_startblock = irec->br_startblock + rlen;
-		uirec.br_startoff = irec->br_startoff + rlen;
-		uirec.br_blockcount = unmap_len - rlen;
-		uirec.br_state = irec->br_state;
-		unmap_len = rlen;
-
-		/* If this isn't a real mapping, we're done. */
-		if (!real_extent || uirec.br_blockcount == 0)
-			goto next_extent;
-
-		trace_xfs_reflink_remap(ip, uirec.br_startoff,
-				uirec.br_blockcount, uirec.br_startblock);
-
-		/* Update the refcount tree */
-		xfs_refcount_increase_extent(tp, &uirec);
-
-		/* Map the new blocks into the data fork. */
-		xfs_bmap_map_extent(tp, ip, &uirec);
-
-		/* Update quota accounting. */
-		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
-				uirec.br_blockcount);
-
-		/* Update dest isize if needed. */
-		newlen = XFS_FSB_TO_B(mp,
-				uirec.br_startoff + uirec.br_blockcount);
-		newlen = min_t(xfs_off_t, newlen, new_isize);
-		if (newlen > i_size_read(VFS_I(ip))) {
-			trace_xfs_reflink_update_inode_size(ip, newlen);
-			i_size_write(VFS_I(ip), newlen);
-			ip->i_d.di_size = newlen;
-			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		}
-
-next_extent:
-		/* Process all the deferred stuff. */
-		error = xfs_defer_finish(&tp);
+		error = __xfs_bunmapi(NULL, ip, smap.br_startoff, &len, 0, 1);
 		if (error)
 			goto out_cancel;
+		ASSERT(len == 0);
 	}
 
+	/*
+	 * If the extent we're sharing is backed by written storage, increase
+	 * its refcount and map it into the file.
+	 */
+	if (dmap_written) {
+		xfs_refcount_increase_extent(tp, dmap);
+		xfs_bmap_map_extent(tp, ip, dmap);
+		qdelta += dmap->br_blockcount;
+	}
+
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, qdelta);
+
+	/* Update dest isize if needed. */
+	newlen = XFS_FSB_TO_B(mp, dmap->br_startoff + dmap->br_blockcount);
+	newlen = min_t(xfs_off_t, newlen, new_isize);
+	if (newlen > i_size_read(VFS_I(ip))) {
+		trace_xfs_reflink_update_inode_size(ip, newlen);
+		i_size_write(VFS_I(ip), newlen);
+		ip->i_d.di_size = newlen;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	}
+
+	/* Commit everything and unlock. */
 	error = xfs_trans_commit(tp);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		goto out;
-	return 0;
+	goto out_unlock;
 
 out_cancel:
 	xfs_trans_cancel(tp);
+out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
-	trace_xfs_reflink_remap_extent_error(ip, error, _RET_IP_);
+	if (error)
+		trace_xfs_reflink_remap_extent_error(ip, error, _RET_IP_);
 	return error;
 }
 
-/*
- * Iteratively remap one file's extents (and holes) to another's.
- */
+/* Remap a range of one file to the other. */
 int
 xfs_reflink_remap_blocks(
 	struct xfs_inode	*src,
···
 	loff_t			*remapped)
 {
 	struct xfs_bmbt_irec	imap;
-	xfs_fileoff_t		srcoff;
-	xfs_fileoff_t		destoff;
+	struct xfs_mount	*mp = src->i_mount;
+	xfs_fileoff_t		srcoff = XFS_B_TO_FSBT(mp, pos_in);
+	xfs_fileoff_t		destoff = XFS_B_TO_FSBT(mp, pos_out);
 	xfs_filblks_t		len;
-	xfs_filblks_t		range_len;
 	xfs_filblks_t		remapped_len = 0;
 	xfs_off_t		new_isize = pos_out + remap_len;
 	int			nimaps;
 	int			error = 0;
 
-	destoff = XFS_B_TO_FSBT(src->i_mount, pos_out);
-	srcoff = XFS_B_TO_FSBT(src->i_mount, pos_in);
-	len = XFS_B_TO_FSB(src->i_mount, remap_len);
+	len = min_t(xfs_filblks_t, XFS_B_TO_FSB(mp, remap_len),
+			XFS_MAX_FILEOFF);
 
-	/* drange = (destoff, destoff + len); srange = (srcoff, srcoff + len) */
-	while (len) {
-		uint		lock_mode;
+	trace_xfs_reflink_remap_blocks(src, srcoff, len, dest, destoff);
 
-		trace_xfs_reflink_remap_blocks_loop(src, srcoff, len,
-				dest, destoff);
+	while (len > 0) {
+		unsigned int	lock_mode;
 
 		/* Read extent from the source file */
 		nimaps = 1;
···
 		xfs_iunlock(src, lock_mode);
 		if (error)
 			break;
-		ASSERT(nimaps == 1);
+		/*
+		 * The caller supposedly flushed all dirty pages in the source
+		 * file range, which means that writeback should have allocated
+		 * or deleted all delalloc reservations in that range.  If we
+		 * find one, that's a good sign that something is seriously
+		 * wrong here.
+		 */
+		ASSERT(nimaps == 1 && imap.br_startoff == srcoff);
+		if (imap.br_startblock == DELAYSTARTBLOCK) {
+			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+			error = -EFSCORRUPTED;
+			break;
+		}
 
-		trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_DATA_FORK,
-				&imap);
+		trace_xfs_reflink_remap_extent_src(src, &imap);
 
-		/* Translate imap into the destination file. */
-		range_len = imap.br_startoff + imap.br_blockcount - srcoff;
-		imap.br_startoff += destoff - srcoff;
-
-		/* Clear dest from destoff to the end of imap and map it in. */
-		error = xfs_reflink_remap_extent(dest, &imap, destoff,
-				new_isize);
+		/* Remap into the destination file at the given offset. */
+		imap.br_startoff = destoff;
+		error = xfs_reflink_remap_extent(dest, &imap, new_isize);
 		if (error)
 			break;
 
···
 		}
 
 		/* Advance drange/srange */
-		srcoff += range_len;
-		destoff += range_len;
-		len -= range_len;
-		remapped_len += range_len;
+		srcoff += imap.br_blockcount;
+		destoff += imap.br_blockcount;
+		len -= imap.br_blockcount;
+		remapped_len += imap.br_blockcount;
 	}
 
 	if (error)
···
 	*remapped = min_t(loff_t, remap_len,
 			  XFS_FSB_TO_B(src->i_mount, remapped_len));
 	return error;
-}
-
-/*
- * Grab the exclusive iolock for a data copy from src to dest, making sure to
- * abide vfs locking order (lowest pointer value goes first) and breaking the
- * layout leases before proceeding.  The loop is needed because we cannot call
- * the blocking break_layout() with the iolocks held, and therefore have to
- * back out both locks.
- */
-static int
-xfs_iolock_two_inodes_and_break_layout(
-	struct inode		*src,
-	struct inode		*dest)
-{
-	int			error;
-
-	if (src > dest)
-		swap(src, dest);
-
-retry:
-	/* Wait to break both inodes' layouts before we start locking. */
-	error = break_layout(src, true);
-	if (error)
-		return error;
-	if (src != dest) {
-		error = break_layout(dest, true);
-		if (error)
-			return error;
-	}
-
-	/* Lock one inode and make sure nobody got in and leased it. */
-	inode_lock(src);
-	error = break_layout(src, false);
-	if (error) {
-		inode_unlock(src);
-		if (error == -EWOULDBLOCK)
-			goto retry;
-		return error;
-	}
-
-	if (src == dest)
-		return 0;
-
-	/* Lock the other inode and make sure nobody got in and leased it. */
-	inode_lock_nested(dest, I_MUTEX_NONDIR2);
-	error = break_layout(dest, false);
-	if (error) {
-		inode_unlock(src);
-		inode_unlock(dest);
-		if (error == -EWOULDBLOCK)
-			goto retry;
-		return error;
-	}
-
-	return 0;
-}
-
-/* Unlock both inodes after they've been prepped for a range clone. */
-void
-xfs_reflink_remap_unlock(
-	struct file		*file_in,
-	struct file		*file_out)
-{
-	struct inode		*inode_in = file_inode(file_in);
-	struct xfs_inode	*src = XFS_I(inode_in);
-	struct inode		*inode_out = file_inode(file_out);
-	struct xfs_inode	*dest = XFS_I(inode_out);
-	bool			same_inode = (inode_in == inode_out);
-
-	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
-	if (!same_inode)
-		xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
-	inode_unlock(inode_out);
-	if (!same_inode)
-		inode_unlock(inode_in);
 }
 
 /*
···
 	struct xfs_inode	*src = XFS_I(inode_in);
 	struct inode		*inode_out = file_inode(file_out);
 	struct xfs_inode	*dest = XFS_I(inode_out);
-	bool			same_inode = (inode_in == inode_out);
-	ssize_t			ret;
+	int			ret;
 
 	/* Lock both files against IO */
-	ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
+	ret = xfs_ilock2_io_mmap(src, dest);
 	if (ret)
 		return ret;
-	if (same_inode)
-		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
-	else
-		xfs_lock_two_inodes(src, XFS_MMAPLOCK_EXCL, dest,
-				XFS_MMAPLOCK_EXCL);
 
 	/* Check file eligibility and prepare for block sharing. */
 	ret = -EINVAL;
···
 
 	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
 			len, remap_flags);
-	if (ret < 0 || *len == 0)
+	if (ret || *len == 0)
 		goto out_unlock;
 
 	/* Attach dquots to dest inode before changing block map */
···
 	if (ret)
 		goto out_unlock;
 
-	return 1;
+	return 0;
 out_unlock:
-	xfs_reflink_remap_unlock(file_in, file_out);
+	xfs_iunlock2_io_mmap(src, dest);
 	return ret;
 }
 

fs/xfs/xfs_reflink.h

···
 		loff_t *remapped);
 extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen,
 		xfs_extlen_t cowextsize, unsigned int remap_flags);
-extern void xfs_reflink_remap_unlock(struct file *file_in,
-		struct file *file_out);
 
 #endif /* __XFS_REFLINK_H */

fs/xfs/xfs_rmap_item.c

···
 	if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
 		ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0);
 	else
-		ruip = kmem_zone_zalloc(xfs_rui_zone, 0);
+		ruip = kmem_cache_zalloc(xfs_rui_zone,
+					 GFP_KERNEL | __GFP_NOFAIL);
 
 	xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
 	ruip->rui_format.rui_nextents = nextents;
···
 {
 	struct xfs_rud_log_item		*rudp;
 
-	rudp = kmem_zone_zalloc(xfs_rud_zone, 0);
+	rudp = kmem_cache_zalloc(xfs_rud_zone, GFP_KERNEL | __GFP_NOFAIL);
 	xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
 			  &xfs_rud_item_ops);
 	rudp->rud_ruip = ruip;

fs/xfs/xfs_super.c

···
 	/* force the log to unpin objects from the now complete transactions */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
-	/* reclaim inodes to do any IO before the freeze completes */
-	xfs_reclaim_inodes(mp, 0);
-	xfs_reclaim_inodes(mp, SYNC_WAIT);
 
 	/* Push the superblock and write an unmount record */
 	error = xfs_log_sbcount(mp);
···
 	struct super_block	*sb)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
+	unsigned int		flags;
+	int			ret;
 
+	/*
+	 * The filesystem is now frozen far enough that memory reclaim
+	 * cannot safely operate on the filesystem. Hence we need to
+	 * set a GFP_NOFS context here to avoid recursion deadlocks.
+	 */
+	flags = memalloc_nofs_save();
 	xfs_stop_block_reaping(mp);
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
-	return xfs_sync_sb(mp, true);
+	ret = xfs_sync_sb(mp, true);
+	memalloc_nofs_restore(flags);
+	return ret;
 }
 
 STATIC int
···
 	xfs_sb_t		*sbp = &mp->m_sb;
 	int			flags = fc->sb_flags;
 	int			error;
+
+	/* version 5 superblocks always support version counters. */
+	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+		fc->sb_flags |= SB_I_VERSION;
 
 	error = xfs_fc_validate_params(new_mp);
 	if (error)

fs/xfs/xfs_trace.h

···
 struct xfs_trans_res;
 struct xfs_inobt_rec_incore;
 union xfs_btree_ptr;
+struct xfs_dqtrx;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
···
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(u32, id)
+		__field(xfs_dqtype_t, type)
 		__field(unsigned, flags)
 		__field(unsigned, nrefs)
 		__field(unsigned long long, res_bcount)
+		__field(unsigned long long, res_rtbcount)
+		__field(unsigned long long, res_icount)
+
 		__field(unsigned long long, bcount)
+		__field(unsigned long long, rtbcount)
 		__field(unsigned long long, icount)
+
 		__field(unsigned long long, blk_hardlimit)
 		__field(unsigned long long, blk_softlimit)
+		__field(unsigned long long, rtb_hardlimit)
+		__field(unsigned long long, rtb_softlimit)
 		__field(unsigned long long, ino_hardlimit)
 		__field(unsigned long long, ino_softlimit)
-	), \
+	),
 	TP_fast_assign(
 		__entry->dev = dqp->q_mount->m_super->s_dev;
-		__entry->id = be32_to_cpu(dqp->q_core.d_id);
-		__entry->flags = dqp->dq_flags;
+		__entry->id = dqp->q_id;
+		__entry->type = dqp->q_type;
+		__entry->flags = dqp->q_flags;
 		__entry->nrefs = dqp->q_nrefs;
-		__entry->res_bcount = dqp->q_res_bcount;
-		__entry->bcount = be64_to_cpu(dqp->q_core.d_bcount);
-		__entry->icount = be64_to_cpu(dqp->q_core.d_icount);
-		__entry->blk_hardlimit =
-			be64_to_cpu(dqp->q_core.d_blk_hardlimit);
-		__entry->blk_softlimit =
-			be64_to_cpu(dqp->q_core.d_blk_softlimit);
-		__entry->ino_hardlimit =
-			be64_to_cpu(dqp->q_core.d_ino_hardlimit);
-		__entry->ino_softlimit =
-			be64_to_cpu(dqp->q_core.d_ino_softlimit);
+
+		__entry->res_bcount = dqp->q_blk.reserved;
+		__entry->res_rtbcount = dqp->q_rtb.reserved;
+		__entry->res_icount = dqp->q_ino.reserved;
+
+		__entry->bcount = dqp->q_blk.count;
+		__entry->rtbcount = dqp->q_rtb.count;
+		__entry->icount = dqp->q_ino.count;
+
+		__entry->blk_hardlimit = dqp->q_blk.hardlimit;
+		__entry->blk_softlimit = dqp->q_blk.softlimit;
+		__entry->rtb_hardlimit = dqp->q_rtb.hardlimit;
+		__entry->rtb_softlimit = dqp->q_rtb.softlimit;
+		__entry->ino_hardlimit = dqp->q_ino.hardlimit;
+		__entry->ino_softlimit = dqp->q_ino.softlimit;
 	),
-	TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx "
+	TP_printk("dev %d:%d id 0x%x type %s flags %s nrefs %u "
+		  "res_bc 0x%llx res_rtbc 0x%llx res_ic 0x%llx "
 		  "bcnt 0x%llx bhardlimit 0x%llx bsoftlimit 0x%llx "
+		  "rtbcnt 0x%llx rtbhardlimit 0x%llx rtbsoftlimit 0x%llx "
 		  "icnt 0x%llx ihardlimit 0x%llx isoftlimit 0x%llx]",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->id,
-		  __print_flags(__entry->flags, "|", XFS_DQ_FLAGS),
+		  __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS),
 		  __entry->nrefs,
 		  __entry->res_bcount,
+		  __entry->res_rtbcount,
+		  __entry->res_icount,
 		  __entry->bcount,
 		  __entry->blk_hardlimit,
 		  __entry->blk_softlimit,
+		  __entry->rtbcount,
+		  __entry->rtb_hardlimit,
+		  __entry->rtb_softlimit,
 		  __entry->icount,
 		  __entry->ino_hardlimit,
 		  __entry->ino_softlimit)
···
 DEFINE_DQUOT_EVENT(xfs_dqflush);
 DEFINE_DQUOT_EVENT(xfs_dqflush_force);
 DEFINE_DQUOT_EVENT(xfs_dqflush_done);
+DEFINE_DQUOT_EVENT(xfs_trans_apply_dquot_deltas_before);
+DEFINE_DQUOT_EVENT(xfs_trans_apply_dquot_deltas_after);
+
+#define XFS_QMOPT_FLAGS \
+	{ XFS_QMOPT_UQUOTA,		"UQUOTA" }, \
+	{ XFS_QMOPT_PQUOTA,		"PQUOTA" }, \
+	{ XFS_QMOPT_FORCE_RES,		"FORCE_RES" }, \
+	{ XFS_QMOPT_SBVERSION,		"SBVERSION" }, \
+	{ XFS_QMOPT_GQUOTA,		"GQUOTA" }, \
+	{ XFS_QMOPT_INHERIT,		"INHERIT" }, \
+	{ XFS_QMOPT_RES_REGBLKS,	"RES_REGBLKS" }, \
+	{ XFS_QMOPT_RES_RTBLKS,		"RES_RTBLKS" }, \
+	{ XFS_QMOPT_BCOUNT,		"BCOUNT" }, \
+	{ XFS_QMOPT_ICOUNT,		"ICOUNT" }, \
+	{ XFS_QMOPT_RTBCOUNT,		"RTBCOUNT" }, \
+	{ XFS_QMOPT_DELBCOUNT,		"DELBCOUNT" }, \
+	{ XFS_QMOPT_DELRTBCOUNT,	"DELRTBCOUNT" }, \
+	{ XFS_QMOPT_RES_INOS,		"RES_INOS" }
+
+TRACE_EVENT(xfs_trans_mod_dquot,
+	TP_PROTO(struct xfs_trans *tp, struct xfs_dquot *dqp,
+		 unsigned int field, int64_t delta),
+	TP_ARGS(tp, dqp, field, delta),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_dqtype_t, type)
+		__field(unsigned int, flags)
+		__field(unsigned int, dqid)
+		__field(unsigned int, field)
+		__field(int64_t, delta)
+	),
+	TP_fast_assign(
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->type = dqp->q_type;
+		__entry->flags = dqp->q_flags;
+		__entry->dqid = dqp->q_id;
+		__entry->field = field;
+		__entry->delta = delta;
+	),
+	TP_printk("dev %d:%d dquot id 0x%x type %s flags %s field %s delta %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dqid,
+		  __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS),
+		  __print_flags(__entry->field, "|", XFS_QMOPT_FLAGS),
+		  __entry->delta)
+);
+
+DECLARE_EVENT_CLASS(xfs_dqtrx_class,
+	TP_PROTO(struct xfs_dqtrx *qtrx),
+	TP_ARGS(qtrx),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_dqtype_t, type)
+		__field(unsigned int, flags)
+		__field(u32, dqid)
+
+		__field(uint64_t, blk_res)
+		__field(int64_t,  bcount_delta)
+		__field(int64_t,  delbcnt_delta)
+
+		__field(uint64_t, rtblk_res)
+		__field(uint64_t, rtblk_res_used)
+		__field(int64_t,  rtbcount_delta)
+		__field(int64_t,  delrtb_delta)
+
+		__field(uint64_t, ino_res)
+		__field(uint64_t, ino_res_used)
+		__field(int64_t,  icount_delta)
+	),
+	TP_fast_assign(
+		__entry->dev = qtrx->qt_dquot->q_mount->m_super->s_dev;
+		__entry->type = qtrx->qt_dquot->q_type;
+		__entry->flags = qtrx->qt_dquot->q_flags;
+		__entry->dqid = qtrx->qt_dquot->q_id;
+
+		__entry->blk_res = qtrx->qt_blk_res;
+		__entry->bcount_delta = qtrx->qt_bcount_delta;
+		__entry->delbcnt_delta = qtrx->qt_delbcnt_delta;
+
+		__entry->rtblk_res = qtrx->qt_rtblk_res;
+		__entry->rtblk_res_used = qtrx->qt_rtblk_res_used;
+		__entry->rtbcount_delta = qtrx->qt_rtbcount_delta;
+		__entry->delrtb_delta = qtrx->qt_delrtb_delta;
+
+		__entry->ino_res = qtrx->qt_ino_res;
+		__entry->ino_res_used = qtrx->qt_ino_res_used;
+		__entry->icount_delta = qtrx->qt_icount_delta;
+	),
+	TP_printk("dev %d:%d dquot id 0x%x type %s flags %s"
+		  "blk_res %llu bcount_delta %lld delbcnt_delta %lld "
+		  "rtblk_res %llu rtblk_res_used %llu rtbcount_delta %lld delrtb_delta %lld "
+		  "ino_res %llu ino_res_used %llu icount_delta %lld",
+		MAJOR(__entry->dev), MINOR(__entry->dev),
+		__entry->dqid,
+		  __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS),
+
+		__entry->blk_res,
+		__entry->bcount_delta,
+		__entry->delbcnt_delta,
+
+		__entry->rtblk_res,
+		__entry->rtblk_res_used,
+		__entry->rtbcount_delta,
+		__entry->delrtb_delta,
+
+		__entry->ino_res,
+		__entry->ino_res_used,
+		__entry->icount_delta)
+)
+
+#define DEFINE_DQTRX_EVENT(name) \
+DEFINE_EVENT(xfs_dqtrx_class, name, \
+	TP_PROTO(struct xfs_dqtrx *qtrx), \
+	TP_ARGS(qtrx))
+DEFINE_DQTRX_EVENT(xfs_trans_apply_dquot_deltas);
+DEFINE_DQTRX_EVENT(xfs_trans_mod_dquot_before);
+DEFINE_DQTRX_EVENT(xfs_trans_mod_dquot_after);
 
 DECLARE_EVENT_CLASS(xfs_loggrant_class,
 	TP_PROTO(struct xlog *log, struct xlog_ticket *tic),
···
 DEFINE_INODE_EVENT(xfs_reflink_set_inode_flag);
 DEFINE_INODE_EVENT(xfs_reflink_unset_inode_flag);
 DEFINE_ITRUNC_EVENT(xfs_reflink_update_inode_size);
-DEFINE_IMAP_EVENT(xfs_reflink_remap_imap);
-TRACE_EVENT(xfs_reflink_remap_blocks_loop,
+TRACE_EVENT(xfs_reflink_remap_blocks,
 	TP_PROTO(struct xfs_inode *src, xfs_fileoff_t soffset,
 		 xfs_filblks_t len, struct xfs_inode *dest,
 		 xfs_fileoff_t doffset),
···
 		  __entry->dest_ino,
 		  __entry->dest_lblk)
 );
-TRACE_EVENT(xfs_reflink_punch_range,
-	TP_PROTO(struct xfs_inode *ip, xfs_fileoff_t lblk,
-		 xfs_extlen_t len),
-	TP_ARGS(ip, lblk, len),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(xfs_fileoff_t, lblk)
-		__field(xfs_extlen_t, len)
-	),
-	TP_fast_assign(
-		__entry->dev = VFS_I(ip)->i_sb->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->lblk = lblk;
-		__entry->len = len;
-	),
-	TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->lblk,
-		  __entry->len)
-);
-TRACE_EVENT(xfs_reflink_remap,
-	TP_PROTO(struct xfs_inode *ip, xfs_fileoff_t lblk,
-		 xfs_extlen_t len, xfs_fsblock_t new_pblk),
-	TP_ARGS(ip, lblk, len, new_pblk),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(xfs_fileoff_t, lblk)
-		__field(xfs_extlen_t, len)
-		__field(xfs_fsblock_t, new_pblk)
-	),
-	TP_fast_assign(
-		__entry->dev = VFS_I(ip)->i_sb->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->lblk = lblk;
-		__entry->len = len;
-		__entry->new_pblk = new_pblk;
-	),
-	TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x new_pblk %llu",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->lblk,
-		  __entry->len,
-		  __entry->new_pblk)
-);
 DEFINE_DOUBLE_IO_EVENT(xfs_reflink_remap_range);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_set_inode_flag_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_update_inode_size_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_blocks_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_extent_error);
+DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_src);
+DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_dest);
 
 /* dedupe tracepoints */
 DEFINE_DOUBLE_IO_EVENT(xfs_reflink_compare_extents);
···
 DEFINE_KMEM_EVENT(kmem_alloc_io);
 DEFINE_KMEM_EVENT(kmem_alloc_large);
 DEFINE_KMEM_EVENT(kmem_realloc);
-DEFINE_KMEM_EVENT(kmem_zone_alloc);
 
 TRACE_EVENT(xfs_check_new_dalign,
 	TP_PROTO(struct xfs_mount *mp, int new_dalign, xfs_ino_t calc_rootino),

fs/xfs/xfs_trans.c

···
 
 	trace_xfs_trans_dup(tp, _RET_IP_);
 
-	ntp = kmem_zone_zalloc(xfs_trans_zone, 0);
+	ntp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
 
 	/*
 	 * Initialize the new transaction structure.
···
 
 	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
 		       (tp->t_flags & XFS_TRANS_RESERVE) |
-		       (tp->t_flags & XFS_TRANS_NO_WRITECOUNT);
+		       (tp->t_flags & XFS_TRANS_NO_WRITECOUNT) |
+		       (tp->t_flags & XFS_TRANS_RES_FDBLKS);
 	/* We gave our writer reference to the new transaction */
 	tp->t_flags |= XFS_TRANS_NO_WRITECOUNT;
 	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
···
 	 * GFP_NOFS allocation context so that we avoid lockdep false positives
 	 * by doing GFP_KERNEL allocations inside sb_start_intwrite().
 	 */
-	tp = kmem_zone_zalloc(xfs_trans_zone, 0);
+	tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
 
···
 	 */
 	WARN_ON(resp->tr_logres > 0 &&
 		mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+	ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) ||
+	       xfs_sb_version_haslazysbcount(&mp->m_sb));
 
 	tp->t_magic = XFS_TRANS_HEADER_MAGIC;
 	tp->t_flags = flags;
···
 			tp->t_blk_res_used += (uint)-delta;
 			if (tp->t_blk_res_used > tp->t_blk_res)
 				xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		} else if (delta > 0 && (tp->t_flags & XFS_TRANS_RES_FDBLKS)) {
+			int64_t	blkres_delta;
+
+			/*
+			 * Return freed blocks directly to the reservation
+			 * instead of the global pool, being careful not to
+			 * overflow the trans counter. This is used to preserve
+			 * reservation across chains of transaction rolls that
+			 * repeatedly free and allocate blocks.
+			 */
+			blkres_delta = min_t(int64_t, delta,
+					     UINT_MAX - tp->t_blk_res);
+			tp->t_blk_res += blkres_delta;
+			delta -= blkres_delta;
 		}
 		tp->t_fdblocks_delta += delta;
 		if (xfs_sb_version_haslazysbcount(&mp->m_sb))

fs/xfs/xfs_trans.h

···
 	unsigned long			li_flags;	/* misc flags */
 	struct xfs_buf			*li_buf;	/* real buffer pointer */
 	struct list_head		li_bio_list;	/* buffer item list */
-	void				(*li_cb)(struct xfs_buf *,
-						 struct xfs_log_item *);
-							/* buffer item iodone */
-							/* callback func */
 	const struct xfs_item_ops	*li_ops;	/* function list */
 
 	/* delayed logging */
···
 	void (*iop_committing)(struct xfs_log_item *, xfs_lsn_t commit_lsn);
 	void (*iop_release)(struct xfs_log_item *);
 	xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t);
-	void (*iop_error)(struct xfs_log_item *, xfs_buf_t *);
 	int (*iop_recover)(struct xfs_log_item *lip, struct xfs_trans *tp);
 	bool (*iop_match)(struct xfs_log_item *item, uint64_t id);
 };

fs/xfs/xfs_trans_ail.c

···
 	}
 
 	/* protected by ail_lock */
-	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
-		xfs_clear_li_failed(lip);
+	list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
+		if (bp->b_flags & _XBF_INODES)
+			clear_bit(XFS_LI_FAILED, &lip->li_flags);
+		else
+			xfs_clear_li_failed(lip);
+	}
 
 	xfs_buf_unlock(bp);
 	return XFS_ITEM_SUCCESS;
···
 	target = ailp->ail_target;
 	ailp->ail_target_prev = target;
 
+	/* we're done if the AIL is empty or our push has reached the end */
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->ail_last_pushed_lsn);
-	if (!lip) {
-		/*
-		 * If the AIL is empty or our push has reached the end we are
-		 * done now.
-		 */
-		xfs_trans_ail_cursor_done(&cur);
-		spin_unlock(&ailp->ail_lock);
+	if (!lip)
 		goto out_done;
-	}
 
 	XFS_STATS_INC(mp, xs_push_ail);
 
···
 			break;
 		lsn = lip->li_lsn;
 	}
+
+out_done:
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
 
···
 		ailp->ail_log_flush++;
 
 	if (!count || XFS_LSN_CMP(lsn, target) >= 0) {
-out_done:
 		/*
 		 * We reached the target or the AIL is empty, so wait a bit
 		 * longer for I/O to complete and remove pushed items from the
···
 		 */
 		smp_rmb();
 		if (!xfs_ail_min(ailp) &&
-		    ailp->ail_target == ailp->ail_target_prev) {
+		    ailp->ail_target == ailp->ail_target_prev &&
+		    list_empty(&ailp->ail_buf_list)) {
 			spin_unlock(&ailp->ail_lock);
 			freezable_schedule();
 			tout = 0;
···
 
 	trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
 	xfs_ail_delete(ailp, lip);
-	xfs_clear_li_failed(lip);
 	clear_bit(XFS_LI_IN_AIL, &lip->li_flags);
 	lip->li_lsn = 0;
 
···
 	}
 
 	/* xfs_ail_update_finish() drops the AIL lock */
+	xfs_clear_li_failed(lip);
 	tail_lsn = xfs_ail_delete_one(ailp, lip);
 	xfs_ail_update_finish(ailp, tail_lsn);
 }

fs/xfs/xfs_trans_buf.c

···
 
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
-	ASSERT(bp->b_iodone == NULL ||
-	       bp->b_iodone == xfs_buf_iodone_callbacks);
 
 	/*
 	 * Mark the buffer as needing to be written out eventually,
 	 * and set its iodone function to remove the buffer's buf log
 	 * item from the AIL and free it when the buffer is flushed
-	 * to disk.  See xfs_buf_attach_iodone() for more details
-	 * on li_cb and xfs_buf_iodone_callbacks().
-	 * If we end up aborting this transaction, we trap this buffer
-	 * inside the b_bdstrat callback so that this won't get written to
-	 * disk.
+	 * to disk.
 	 */
 	bp->b_flags |= XBF_DONE;
 
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	bp->b_iodone = xfs_buf_iodone_callbacks;
-	bip->bli_item.li_cb = xfs_buf_iodone;
 
 	/*
 	 * If we invalidated the buffer within this transaction, then
···
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
 	bip->bli_flags |= XFS_BLI_INODE_BUF;
+	bp->b_flags |= _XBF_INODES;
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
 }
 
···
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
 	bip->bli_flags |= XFS_BLI_STALE_INODE;
-	bip->bli_item.li_cb = xfs_buf_iodone;
+	bp->b_flags |= _XBF_INODES;
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
 }
 
···
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
 	bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
+	bp->b_flags |= _XBF_INODES;
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
 }
 
···
 		break;
 	}
 
+	bp->b_flags |= _XBF_DQUOTS;
 	xfs_trans_buf_set_type(tp, bp, type);
 }

fs/xfs/xfs_trans_dquot.c

···
 #include "xfs_trans_priv.h"
 #include "xfs_quota.h"
 #include "xfs_qm.h"
+#include "xfs_trace.h"
 
 STATIC void	xfs_trans_alloc_dqinfo(xfs_trans_t *);
 
···
 	int			i;
 	struct xfs_dqtrx	*qa;
 
-	if (XFS_QM_ISUDQ(dqp))
+	switch (xfs_dquot_type(dqp)) {
+	case XFS_DQTYPE_USER:
 		qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_USR];
-	else if (XFS_QM_ISGDQ(dqp))
+		break;
+	case XFS_DQTYPE_GROUP:
 		qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_GRP];
-	else if (XFS_QM_ISPDQ(dqp))
+		break;
+	case XFS_DQTYPE_PROJ:
 		qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_PRJ];
-	else
+		break;
+	default:
 		return NULL;
+	}
 
 	for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) {
 		if (qa[i].qt_dquot == NULL ||
···
 	ASSERT(qtrx);
 	if (qtrx->qt_dquot == NULL)
 		qtrx->qt_dquot = dqp;
+
+	if (delta) {
+		trace_xfs_trans_mod_dquot_before(qtrx);
+		trace_xfs_trans_mod_dquot(tp, dqp, field, delta);
+	}
 
 	switch (field) {
 
···
 	      default:
 		ASSERT(0);
 	}
+
+	if (delta)
+		trace_xfs_trans_mod_dquot_after(qtrx);
+
 	tp->t_flags |= XFS_TRANS_DQ_DIRTY;
 }
 
···
 	}
 }
 
+/* Apply dqtrx changes to the quota reservation counters. */
+static inline void
+xfs_apply_quota_reservation_deltas(
+	struct xfs_dquot_res	*res,
+	uint64_t		reserved,
+	int64_t			res_used,
+	int64_t			count_delta)
+{
+	if (reserved != 0) {
+		/*
+		 * Subtle math here: If reserved > res_used (the normal case),
+		 * we're simply subtracting the unused transaction quota
+		 * reservation from the dquot reservation.
+		 *
+		 * If, however, res_used > reserved, then we have allocated
+		 * more quota blocks than were reserved for the transaction.
+		 * We must add that excess to the dquot reservation since it
+		 * tracks (usage + resv) and by definition we didn't reserve
+		 * that excess.
+		 */
+		res->reserved -= abs(reserved - res_used);
+	} else if (count_delta != 0) {
+		/*
+		 * These blks were never reserved, either inside a transaction
+		 * or outside one (in a delayed allocation). Also, this isn't
+		 * always a negative number since we sometimes deliberately
+		 * skip quota reservations.
+		 */
+		res->reserved += count_delta;
+	}
+}
 
 /*
  * Called by xfs_trans_commit() and similar in spirit to
···
 	int			i, j;
 	struct xfs_dquot	*dqp;
 	struct xfs_dqtrx	*qtrx, *qa;
-	struct xfs_disk_dquot	*d;
 	int64_t			totalbdelta;
 	int64_t			totalrtbdelta;
 
···
 		xfs_trans_dqlockedjoin(tp, qa);
 
 		for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) {
+			uint64_t	blk_res_used;
+
 			qtrx = &qa[i];
 			/*
 			 * The array of dquots is filled
···
 			/*
 			 * adjust the actual number of blocks used
 			 */
-			d = &dqp->q_core;
 
 			/*
 			 * The issue here is - sometimes we don't make a blkquota
···
 				qtrx->qt_delbcnt_delta;
 			totalrtbdelta = qtrx->qt_rtbcount_delta +
 				qtrx->qt_delrtb_delta;
+
+			if (totalbdelta != 0 || totalrtbdelta != 0 ||
+			    qtrx->qt_icount_delta != 0) {
+				trace_xfs_trans_apply_dquot_deltas_before(dqp);
+				trace_xfs_trans_apply_dquot_deltas(qtrx);
+			}
+
 #ifdef DEBUG
 			if (totalbdelta < 0)
-				ASSERT(be64_to_cpu(d->d_bcount) >=
-				       -totalbdelta);
+				ASSERT(dqp->q_blk.count >= -totalbdelta);
 
 			if (totalrtbdelta < 0)
-				ASSERT(be64_to_cpu(d->d_rtbcount) >=
-				       -totalrtbdelta);
+				ASSERT(dqp->q_rtb.count >= -totalrtbdelta);
 
 			if (qtrx->qt_icount_delta < 0)
-				ASSERT(be64_to_cpu(d->d_icount) >=
-				       -qtrx->qt_icount_delta);
+				ASSERT(dqp->q_ino.count >= -qtrx->qt_icount_delta);
 #endif
 			if (totalbdelta)
-				be64_add_cpu(&d->d_bcount, (xfs_qcnt_t)totalbdelta);
+				dqp->q_blk.count += totalbdelta;
 
 			if (qtrx->qt_icount_delta)
-				be64_add_cpu(&d->d_icount, (xfs_qcnt_t)qtrx->qt_icount_delta);
+				dqp->q_ino.count += qtrx->qt_icount_delta;
 
 			if (totalrtbdelta)
-				be64_add_cpu(&d->d_rtbcount, (xfs_qcnt_t)totalrtbdelta);
+				dqp->q_rtb.count += totalrtbdelta;
+
+			if (totalbdelta != 0 || totalrtbdelta != 0 ||
+			    qtrx->qt_icount_delta != 0)
+				trace_xfs_trans_apply_dquot_deltas_after(dqp);
 
 			/*
 			 * Get any default limits in use.
 			 * Start/reset the timer(s) if needed.
 			 */
-			if (d->d_id) {
-				xfs_qm_adjust_dqlimits(tp->t_mountp, dqp);
-				xfs_qm_adjust_dqtimers(tp->t_mountp, dqp);
+			if (dqp->q_id) {
+				xfs_qm_adjust_dqlimits(dqp);
+				xfs_qm_adjust_dqtimers(dqp);
 			}
 
-			dqp->dq_flags |= XFS_DQ_DIRTY;
+			dqp->q_flags |= XFS_DQFLAG_DIRTY;
 			/*
 			 * add this to the list of items to get logged
 			 */
···
 			 * In case of delayed allocations, there's no
 			 * reservation that a transaction structure knows of.
 			 */
-			if (qtrx->qt_blk_res != 0) {
-				uint64_t	blk_res_used = 0;
+			blk_res_used = max_t(int64_t, 0, qtrx->qt_bcount_delta);
+			xfs_apply_quota_reservation_deltas(&dqp->q_blk,
+					qtrx->qt_blk_res, blk_res_used,
+					qtrx->qt_bcount_delta);
 
-				if (qtrx->qt_bcount_delta > 0)
-					blk_res_used = qtrx->qt_bcount_delta;
-
-				if (qtrx->qt_blk_res != blk_res_used) {
-					if (qtrx->qt_blk_res > blk_res_used)
-						dqp->q_res_bcount -= (xfs_qcnt_t)
-							(qtrx->qt_blk_res -
-							 blk_res_used);
-					else
-						dqp->q_res_bcount -= (xfs_qcnt_t)
-							(blk_res_used -
-							 qtrx->qt_blk_res);
-				}
-			} else {
-				/*
-				 * These blks were never reserved, either inside
-				 * a transaction or outside one (in a delayed
-				 * allocation). Also, this isn't always a
-				 * negative number since we sometimes
-				 * deliberately skip quota reservations.
-				 */
-				if (qtrx->qt_bcount_delta) {
-					dqp->q_res_bcount +=
-					      (xfs_qcnt_t)qtrx->qt_bcount_delta;
-				}
-			}
 			/*
 			 * Adjust the RT reservation.
 			 */
-			if (qtrx->qt_rtblk_res != 0) {
-				if (qtrx->qt_rtblk_res != qtrx->qt_rtblk_res_used) {
-					if (qtrx->qt_rtblk_res >
-					    qtrx->qt_rtblk_res_used)
-					       dqp->q_res_rtbcount -= (xfs_qcnt_t)
-						       (qtrx->qt_rtblk_res -
-							qtrx->qt_rtblk_res_used);
-					else
-					       dqp->q_res_rtbcount -= (xfs_qcnt_t)
-						       (qtrx->qt_rtblk_res_used -
-							qtrx->qt_rtblk_res);
-				}
-			} else {
-				if (qtrx->qt_rtbcount_delta)
-					dqp->q_res_rtbcount +=
-					    (xfs_qcnt_t)qtrx->qt_rtbcount_delta;
-			}
+			xfs_apply_quota_reservation_deltas(&dqp->q_rtb,
+					qtrx->qt_rtblk_res,
+					qtrx->qt_rtblk_res_used,
+					qtrx->qt_rtbcount_delta);
 
 			/*
 			 * Adjust the inode reservation.
 			 */
-			if (qtrx->qt_ino_res != 0) {
-				ASSERT(qtrx->qt_ino_res >=
-				       qtrx->qt_ino_res_used);
-				if (qtrx->qt_ino_res > qtrx->qt_ino_res_used)
-					dqp->q_res_icount -= (xfs_qcnt_t)
-						(qtrx->qt_ino_res -
-						 qtrx->qt_ino_res_used);
-			} else {
-				if (qtrx->qt_icount_delta)
-					dqp->q_res_icount +=
-					    (xfs_qcnt_t)qtrx->qt_icount_delta;
-			}
+			ASSERT(qtrx->qt_ino_res >= qtrx->qt_ino_res_used);
+			xfs_apply_quota_reservation_deltas(&dqp->q_ino,
+					qtrx->qt_ino_res,
+					qtrx->qt_ino_res_used,
+					qtrx->qt_icount_delta);
 
-			ASSERT(dqp->q_res_bcount >=
-				be64_to_cpu(dqp->q_core.d_bcount));
-			ASSERT(dqp->q_res_icount >=
-				be64_to_cpu(dqp->q_core.d_icount));
-			ASSERT(dqp->q_res_rtbcount >=
-				be64_to_cpu(dqp->q_core.d_rtbcount));
+			ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count);
+			ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count);
+			ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count);
 		}
 	}
 }
···
 			if (qtrx->qt_blk_res) {
 				xfs_dqlock(dqp);
 				locked = true;
-				dqp->q_res_bcount -=
+				dqp->q_blk.reserved -=
 					(xfs_qcnt_t)qtrx->qt_blk_res;
 			}
 			if (qtrx->qt_ino_res) {
···
 					xfs_dqlock(dqp);
 					locked = true;
 				}
-				dqp->q_res_icount -=
+				dqp->q_ino.reserved -=
 					(xfs_qcnt_t)qtrx->qt_ino_res;
 			}
 
···
 					xfs_dqlock(dqp);
 					locked = true;
 				}
-				dqp->q_res_rtbcount -=
+				dqp->q_rtb.reserved -=
 					(xfs_qcnt_t)qtrx->qt_rtblk_res;
 			}
 			if (locked)
···
 	struct xfs_dquot	*dqp,
 	int			type)
 {
-	enum quota_type qtype;
+	enum quota_type		qtype;
 
-	if (dqp->dq_flags & XFS_DQ_PROJ)
+	switch (xfs_dquot_type(dqp)) {
+	case XFS_DQTYPE_PROJ:
 		qtype = PRJQUOTA;
-	else if (dqp->dq_flags & XFS_DQ_USER)
+		break;
+	case XFS_DQTYPE_USER:
 		qtype = USRQUOTA;
-	else
+		break;
+	case XFS_DQTYPE_GROUP:
 		qtype = GRPQUOTA;
+		break;
+	default:
+		return;
+	}
 
-	quota_send_warning(make_kqid(&init_user_ns, qtype,
-				     be32_to_cpu(dqp->q_core.d_id)),
+	quota_send_warning(make_kqid(&init_user_ns, qtype, dqp->q_id),
 			   mp->m_super->s_dev, type);
+}
+
+/*
+ * Decide if we can make an additional reservation against a quota resource.
+ * Returns an inode QUOTA_NL_ warning code and whether or not it's fatal.
+ *
+ * Note that we assume that the numeric difference between the inode and block
+ * warning codes will always be 3 since it's userspace ABI now, and will never
+ * decrease the quota reservation, so the *BELOW messages are irrelevant.
+ */
+static inline int
+xfs_dqresv_check(
+	struct xfs_dquot_res	*res,
+	struct xfs_quota_limits	*qlim,
+	int64_t			delta,
+	bool			*fatal)
+{
+	xfs_qcnt_t		hardlimit = res->hardlimit;
+	xfs_qcnt_t		softlimit = res->softlimit;
+	xfs_qcnt_t		total_count = res->reserved + delta;
+
+	BUILD_BUG_ON(QUOTA_NL_BHARDWARN     != QUOTA_NL_IHARDWARN + 3);
+	BUILD_BUG_ON(QUOTA_NL_BSOFTLONGWARN != QUOTA_NL_ISOFTLONGWARN + 3);
+	BUILD_BUG_ON(QUOTA_NL_BSOFTWARN     != QUOTA_NL_ISOFTWARN + 3);
+
+	*fatal = false;
+	if (delta <= 0)
+		return QUOTA_NL_NOWARN;
+
+	if (!hardlimit)
+		hardlimit = qlim->hard;
+	if (!softlimit)
+		softlimit = qlim->soft;
+
+	if (hardlimit && total_count > hardlimit) {
+		*fatal = true;
+		return QUOTA_NL_IHARDWARN;
+	}
+
+	if (softlimit && total_count > softlimit) {
+		time64_t	now = ktime_get_real_seconds();
+
+		if ((res->timer != 0 && now > res->timer) ||
+		    (res->warnings != 0 && res->warnings >= qlim->warn)) {
+			*fatal = true;
+			return QUOTA_NL_ISOFTLONGWARN;
+		}
+
+		res->warnings++;
+		return QUOTA_NL_ISOFTWARN;
+	}
+
+	return QUOTA_NL_NOWARN;
 }
 
 /*
···
 	long			ninos,
 	uint			flags)
 {
-	xfs_qcnt_t		hardlimit;
-	xfs_qcnt_t		softlimit;
-	time64_t		timer;
-	xfs_qwarncnt_t		warns;
-	xfs_qwarncnt_t		warnlimit;
-	xfs_qcnt_t		total_count;
-	xfs_qcnt_t		*resbcountp;
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_def_quota	*defq;
-
+	struct xfs_dquot_res	*blkres;
+	struct xfs_quota_limits	*qlim;
 
 	xfs_dqlock(dqp);
 
 	defq = xfs_get_defquota(q, xfs_dquot_type(dqp));
 
 	if (flags & XFS_TRANS_DQ_RES_BLKS) {
-		hardlimit = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
-		if (!hardlimit)
-			hardlimit = defq->bhardlimit;
-		softlimit = be64_to_cpu(dqp->q_core.d_blk_softlimit);
-		if (!softlimit)
-			softlimit = defq->bsoftlimit;
-		timer = be32_to_cpu(dqp->q_core.d_btimer);
-		warns = be16_to_cpu(dqp->q_core.d_bwarns);
-		warnlimit = defq->bwarnlimit;
-		resbcountp = &dqp->q_res_bcount;
+		blkres = &dqp->q_blk;
+		qlim = &defq->blk;
 	} else {
-		ASSERT(flags & XFS_TRANS_DQ_RES_RTBLKS);
-		hardlimit = be64_to_cpu(dqp->q_core.d_rtb_hardlimit);
-		if (!hardlimit)
-			hardlimit = defq->rtbhardlimit;
-		softlimit = be64_to_cpu(dqp->q_core.d_rtb_softlimit);
-		if (!softlimit)
-			softlimit = defq->rtbsoftlimit;
-		timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
-		warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
-		warnlimit = defq->rtbwarnlimit;
-		resbcountp = &dqp->q_res_rtbcount;
+		blkres = &dqp->q_rtb;
+		qlim = &defq->rtb;
 	}
 
-	if ((flags & XFS_QMOPT_FORCE_RES) == 0 &&
-	    dqp->q_core.d_id &&
-	    ((XFS_IS_UQUOTA_ENFORCED(dqp->q_mount) && XFS_QM_ISUDQ(dqp)) ||
-	     (XFS_IS_GQUOTA_ENFORCED(dqp->q_mount) && XFS_QM_ISGDQ(dqp)) ||
-	     (XFS_IS_PQUOTA_ENFORCED(dqp->q_mount) && XFS_QM_ISPDQ(dqp)))) {
-		if (nblks > 0) {
+	if ((flags & XFS_QMOPT_FORCE_RES) == 0 && dqp->q_id &&
+	    xfs_dquot_is_enforced(dqp)) {
+		int		quota_nl;
+		bool		fatal;
+
+		/*
+		 * dquot is locked already. See if we'd go over the hardlimit
+		 * or exceed the timelimit if we'd reserve resources.
+		 */
+		quota_nl = xfs_dqresv_check(blkres, qlim, nblks, &fatal);
+		if (quota_nl != QUOTA_NL_NOWARN) {
 			/*
-			 * dquot is locked already. See if we'd go over the
-			 * hardlimit or exceed the timelimit if we allocate
-			 * nblks.
+			 * Quota block warning codes are 3 more than the inode
+			 * codes, which we check above.
 			 */
-			total_count = *resbcountp + nblks;
-			if (hardlimit && total_count > hardlimit) {
-				xfs_quota_warn(mp, dqp, QUOTA_NL_BHARDWARN);
+			xfs_quota_warn(mp, dqp, quota_nl + 3);
+			if (fatal)
 				goto error_return;
-			}
-			if (softlimit && total_count > softlimit) {
-				if ((timer != 0 &&
-				     ktime_get_real_seconds() > timer) ||
-				    (warns != 0 && warns >= warnlimit)) {
-					xfs_quota_warn(mp, dqp,
-						       QUOTA_NL_BSOFTLONGWARN);
-					goto error_return;
-				}
-
-				xfs_quota_warn(mp, dqp, QUOTA_NL_BSOFTWARN);
-			}
 		}
-		if (ninos > 0) {
-			total_count = be64_to_cpu(dqp->q_core.d_icount) + ninos;
-			timer = be32_to_cpu(dqp->q_core.d_itimer);
-			warns = be16_to_cpu(dqp->q_core.d_iwarns);
-			warnlimit = defq->iwarnlimit;
-			hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
-			if (!hardlimit)
-				hardlimit = defq->ihardlimit;
-			softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
-			if (!softlimit)
-				softlimit = defq->isoftlimit;
 
-			if (hardlimit && total_count > hardlimit) {
-				xfs_quota_warn(mp, dqp, QUOTA_NL_IHARDWARN);
+		quota_nl = xfs_dqresv_check(&dqp->q_ino, &defq->ino, ninos,
+				&fatal);
+		if (quota_nl != QUOTA_NL_NOWARN) {
+			xfs_quota_warn(mp, dqp, quota_nl);
+			if (fatal)
 				goto error_return;
-			}
-			if (softlimit && total_count > softlimit) {
-				if  ((timer != 0 &&
-				      ktime_get_real_seconds() > timer) ||
-				     (warns != 0 && warns >= warnlimit)) {
-					xfs_quota_warn(mp, dqp,
-						       QUOTA_NL_ISOFTLONGWARN);
-					goto error_return;
-				}
-				xfs_quota_warn(mp, dqp, QUOTA_NL_ISOFTWARN);
-			}
 		}
 	}
 
 	/*
 	 * Change the reservation, but not the actual usage.
-	 * Note that q_res_bcount = q_core.d_bcount + resv
+	 * Note that q_blk.reserved = q_blk.count + resv
 	 */
-	(*resbcountp) += (xfs_qcnt_t)nblks;
-	if (ninos != 0)
-		dqp->q_res_icount += (xfs_qcnt_t)ninos;
+	blkres->reserved += (xfs_qcnt_t)nblks;
+	dqp->q_ino.reserved += (xfs_qcnt_t)ninos;
 
 	/*
 	 * note the reservation amt in the trans struct too,
···
 					    XFS_TRANS_DQ_RES_INOS,
 					    ninos);
 	}
-	ASSERT(dqp->q_res_bcount >= be64_to_cpu(dqp->q_core.d_bcount));
-	ASSERT(dqp->q_res_rtbcount >= be64_to_cpu(dqp->q_core.d_rtbcount));
-	ASSERT(dqp->q_res_icount >= be64_to_cpu(dqp->q_core.d_icount));
+	ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count);
+	ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count);
+	ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count);
 
 	xfs_dqunlock(dqp);
 	return 0;
 
 error_return:
 	xfs_dqunlock(dqp);
-	if (XFS_QM_ISPDQ(dqp))
+	if (xfs_dquot_type(dqp) == XFS_DQTYPE_PROJ)
 		return -ENOSPC;
 	return -EDQUOT;
 }
···
 xfs_trans_alloc_dqinfo(
 	xfs_trans_t	*tp)
 {
-	tp->t_dqinfo = kmem_zone_zalloc(xfs_qm_dqtrxzone, 0);
+	tp->t_dqinfo = kmem_cache_zalloc(xfs_qm_dqtrxzone,
+					 GFP_KERNEL | __GFP_NOFAIL);
 }
 
 void