Merge tag 'xfs-5.10-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:
 "The second large pile of new stuff for 5.10, with changes even more
  monumental than last week!

  We are formally announcing the deprecation of the V4 filesystem format
  in 2030. All users must upgrade to the V5 format, which contains
  design improvements that greatly strengthen metadata validation,
  supports reflink and online fsck, and is the intended vehicle for
  handling timestamps past 2038. We're also deprecating the old Irix
  behavioral tweaks in September 2025.

  Coming along for the ride are two design changes to the deferred
  metadata ops subsystem. One of the improvements is to retain correct
  logical ordering of tasks and subtasks, which is a more logical design
  for upper layers of XFS and will become necessary when we add atomic
  file range swaps and commits. The second improvement to deferred ops
  improves the scalability of the log by helping the log tail to move
  forward during long-running operations. This reduces log contention
  when there are a large number of threads trying to run transactions.

  In addition to that, this fixes numerous small bugs in log recovery;
  refactors logical intent log item recovery to remove the last
  remaining place in XFS where we could have nested transactions; fixes
  a couple of ways that intent log item recovery could fail in ways that
  wouldn't have happened in the regular commit paths; fixes a deadlock
  vector in the GETFSMAP implementation (which improves its performance
  by 20%); and fixes serious bugs in the realtime growfs, fallocate, and
  bitmap handling code.

  Summary:

   - Deprecate the V4 filesystem format, some disused mount options, and
     some legacy sysctl knobs now that we can support dates into the
     25th century. Note that removal of V4 support will not happen until
     the early 2030s.

   - Fix some probles with inode realtime flag propagation.

   - Fix some buffer handling issues when growing a rt filesystem.

   - Fix a problem where a BMAP_REMAP unmap call would free rt extents
     even though the purpose of BMAP_REMAP is to avoid freeing the
     blocks.

   - Strengthen the dabtree online scrubber to check hash values on
     child dabtree blocks.

   - Actually log new intent items created as part of recovering log
     intent items.

   - Fix a bug where quotas weren't attached to an inode undergoing bmap
     intent item recovery.

   - Fix a buffer overrun problem with specially crafted log buffer
     headers.

   - Various cleanups to type usage and slightly inaccurate comments.

   - More cleanups to the xattr, log, and quota code.

   - Don't run the (slower) shared-rmap operations on attr fork
     mappings.

   - Fix a bug where we failed to check the LSN of finobt blocks during
     replay and could therefore overwrite newer data with older data.

   - Clean up the ugly nested transaction mess that log recovery uses to
     stage intent item recovery in the correct order by creating a
     proper data structure to capture recovered chains.

   - Use the capture structure to resume intent item chains with the
     same log space and block reservations as when they were captured.

   - Fix a UAF bug in bmap intent item recovery where we failed to
     maintain our reference to the incore inode if the bmap operation
     needed to relog itself to continue.

   - Rearrange the defer ops mechanism to finish newly created subtasks
     of a parent task before moving on to the next parent task.

   - Automatically relog intent items in deferred ops chains if doing so
     would help us avoid pinning the log tail. This will help fix some
     log scaling problems now and will facilitate atomic file updates
     later.

   - Fix a deadlock in the GETFSMAP implementation by using an internal
     memory buffer to reduce indirect calls and copies to userspace,
     thereby improving its performance by ~20%.

   - Fix various problems when calling growfs on a realtime volume would
     not fully update the filesystem metadata.

   - Fix broken Kconfig asking about deprecated XFS when XFS is
     disabled"

* tag 'xfs-5.10-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (48 commits)
  xfs: fix Kconfig asking about XFS_SUPPORT_V4 when XFS_FS=n
  xfs: fix high key handling in the rt allocator's query_range function
  xfs: annotate grabbing the realtime bitmap/summary locks in growfs
  xfs: make xfs_growfs_rt update secondary superblocks
  xfs: fix realtime bitmap/summary file truncation when growing rt volume
  xfs: fix the indent in xfs_trans_mod_dquot
  xfs: do the ASSERT for the arguments O_{u,g,p}dqpp
  xfs: fix deadlock and streamline xfs_getfsmap performance
  xfs: limit entries returned when counting fsmap records
  xfs: only relog deferred intent items if free space in the log gets low
  xfs: expose the log push threshold
  xfs: periodically relog deferred intent items
  xfs: change the order in which child and parent defer ops are finished
  xfs: fix an incore inode UAF in xfs_bui_recover
  xfs: clean up xfs_bui_item_recover iget/trans_alloc/ilock ordering
  xfs: clean up bmap intent item recovery checking
  xfs: xfs_defer_capture should absorb remaining transaction reservation
  xfs: xfs_defer_capture should absorb remaining block reservations
  xfs: proper replay of deferred ops queued during log recovery
  xfs: remove XFS_LI_RECOVERED
  ...

36 files changed, 992 insertions, 508 deletions

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index e685299eb3d2..9fac5ea8d0e4 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -22,6 +22,31 @@ config XFS_FS
 	  system of your root partition is compiled as a module, you'll need
 	  to use an initial ramdisk (initrd) to boot.
 
+config XFS_SUPPORT_V4
+	bool "Support deprecated V4 (crc=0) format"
+	depends on XFS_FS
+	default y
+	help
+	  The V4 filesystem format lacks certain features that are supported
+	  by the V5 format, such as metadata checksumming, strengthened
+	  metadata verification, and the ability to store timestamps past the
+	  year 2038.  Because of this, the V4 format is deprecated.  All users
+	  should upgrade by backing up their files, reformatting, and restoring
+	  from the backup.
+
+	  Administrators and users can detect a V4 filesystem by running
+	  xfs_info against a filesystem mountpoint and checking for a string
+	  beginning with "crc=".  If the string "crc=0" is found, the
+	  filesystem is a V4 filesystem.  If no such string is found, please
+	  upgrade xfsprogs to the latest version and try again.
+
+	  This option will become default N in September 2025.  Support for the
+	  V4 format will be removed entirely in September 2030.  Distributors
+	  can say N here to withdraw support earlier.
+
+	  To continue supporting the old V4 format (crc=0), say Y.
+	  To close off an attack surface, say N.
+
 config XFS_QUOTA
 	bool "XFS Quota support"
 	depends on XFS_FS
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 3f80cede7406..48d8e9caf86f 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -96,8 +96,6 @@ xfs_attr3_rmt_verify(
 {
 	struct xfs_attr3_rmt_hdr *rmt = ptr;
 
-	if (!xfs_sb_version_hascrc(&mp->m_sb))
-		return __this_address;
 	if (!xfs_verify_magic(bp, rmt->rm_magic))
 		return __this_address;
 	if (!uuid_equal(&rmt->rm_uuid, &mp->m_sb.sb_meta_uuid))
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 1b0a01b06a05..d9a692484eae 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5046,20 +5046,25 @@ xfs_bmap_del_extent_real(
 
 	flags = XFS_ILOG_CORE;
 	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
-		xfs_fsblock_t	bno;
 		xfs_filblks_t	len;
 		xfs_extlen_t	mod;
 
-		bno = div_u64_rem(del->br_startblock, mp->m_sb.sb_rextsize,
-				  &mod);
-		ASSERT(mod == 0);
 		len = div_u64_rem(del->br_blockcount, mp->m_sb.sb_rextsize,
 				  &mod);
 		ASSERT(mod == 0);
 
-		error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len);
-		if (error)
-			goto done;
+		if (!(bflags & XFS_BMAPI_REMAP)) {
+			xfs_fsblock_t	bno;
+
+			bno = div_u64_rem(del->br_startblock,
+					mp->m_sb.sb_rextsize, &mod);
+			ASSERT(mod == 0);
+
+			error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len);
+			if (error)
+				goto done;
+		}
+
 		do_fx = 0;
 		nblks = len * mp->m_sb.sb_rextsize;
 		qfield = XFS_TRANS_DQ_RTBCOUNT;
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index b40a4e80f5ee..b876b44c0204 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -15,8 +15,8 @@
  */
 #define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
 #define XFS_ATTR_LEAF_MAGIC	0xfbee	/* magic number: attribute leaf blks */
-#define	XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
+#define XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
+#define XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
 
 typedef struct xfs_da_blkinfo {
 	__be32		forw;			/* previous block in list */
@@ -35,8 +35,8 @@ typedef struct xfs_da_blkinfo {
  */
 #define XFS_DA3_NODE_MAGIC	0x3ebe	/* magic number: non-leaf blocks */
 #define XFS_ATTR3_LEAF_MAGIC	0x3bee	/* magic number: attribute leaf blks */
-#define	XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v2 dirlf multi blks */
+#define XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v3 dirlf single blks */
+#define XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v3 dirlf multi blks */
 
 struct xfs_da3_blkinfo {
 	/*
@@ -61,7 +61,7 @@ struct xfs_da3_blkinfo {
  * Since we have duplicate keys, use a binary search but always follow
  * all match in the block, not just the first match found.
  */
-#define	XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
+#define XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
 
 typedef struct xfs_da_node_hdr {
 	struct xfs_da_blkinfo	info;	/* block type, links, etc. */
@@ -746,14 +746,14 @@ xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
  */
 static inline int xfs_attr_leaf_entsize_remote(int nlen)
 {
-	return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+	return round_up(sizeof(struct xfs_attr_leaf_name_remote) - 1 +
+			nlen, XFS_ATTR_LEAF_NAME_ALIGN);
 }
 
 static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
 {
-	return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+	return round_up(sizeof(struct xfs_attr_leaf_name_local) - 1 +
+			nlen + vlen, XFS_ATTR_LEAF_NAME_ALIGN);
 }
 
 static inline int xfs_attr_leaf_entsize_local_max(int bsize)
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index d8f586256add..eff4a127188e 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -16,6 +16,8 @@
 #include "xfs_inode.h"
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
+#include "xfs_log.h"
 
 /*
  * Deferred Operations in XFS
@@ -186,8 +188,9 @@ xfs_defer_create_intent(
 {
 	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 
-	dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work,
-			dfp->dfp_count, sort);
+	if (!dfp->dfp_intent)
+		dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work,
+						     dfp->dfp_count, sort);
 }
 
 /*
@@ -312,22 +315,6 @@ xfs_defer_trans_roll(
 }
 
 /*
- * Reset an already used dfops after finish.
- */
-static void
-xfs_defer_reset(
-	struct xfs_trans	*tp)
-{
-	ASSERT(list_empty(&tp->t_dfops));
-
-	/*
-	 * Low mode state transfers across transaction rolls to mirror dfops
-	 * lifetime. Clear it now that dfops is reset.
-	 */
-	tp->t_flags &= ~XFS_TRANS_LOWMODE;
-}
-
-/*
  * Free up any items left in the list.
  */
 static void
@@ -360,6 +347,58 @@ xfs_defer_cancel_list(
 }
 
 /*
+ * Prevent a log intent item from pinning the tail of the log by logging a
+ * done item to release the intent item; and then log a new intent item.
+ * The caller should provide a fresh transaction and roll it after we're done.
+ */
+static int
+xfs_defer_relog(
+	struct xfs_trans		**tpp,
+	struct list_head		*dfops)
+{
+	struct xlog			*log = (*tpp)->t_mountp->m_log;
+	struct xfs_defer_pending	*dfp;
+	xfs_lsn_t			threshold_lsn = NULLCOMMITLSN;
+
+
+	ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	list_for_each_entry(dfp, dfops, dfp_list) {
+		/*
+		 * If the log intent item for this deferred op is not a part of
+		 * the current log checkpoint, relog the intent item to keep
+		 * the log tail moving forward.  We're ok with this being racy
+		 * because an incorrect decision means we'll be a little slower
+		 * at pushing the tail.
+		 */
+		if (dfp->dfp_intent == NULL ||
+		    xfs_log_item_in_current_chkpt(dfp->dfp_intent))
+			continue;
+
+		/*
+		 * Figure out where we need the tail to be in order to maintain
+		 * the minimum required free space in the log.  Only sample
+		 * the log threshold once per call.
+		 */
+		if (threshold_lsn == NULLCOMMITLSN) {
+			threshold_lsn = xlog_grant_push_threshold(log, 0);
+			if (threshold_lsn == NULLCOMMITLSN)
+				break;
+		}
+		if (XFS_LSN_CMP(dfp->dfp_intent->li_lsn, threshold_lsn) >= 0)
+			continue;
+
+		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
+		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
+		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp);
+	}
+
+	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
+		return xfs_defer_trans_roll(tpp);
+	return 0;
+}
+
+/*
  * Log an intent-done item for the first pending intent, and finish the work
  * items.
  */
@@ -390,6 +429,7 @@ xfs_defer_finish_one(
 			list_add(li, &dfp->dfp_work);
 			dfp->dfp_count++;
 			dfp->dfp_done = NULL;
+			dfp->dfp_intent = NULL;
 			xfs_defer_create_intent(tp, dfp, false);
 		}
 
@@ -428,13 +468,27 @@ xfs_defer_finish_noroll(
 
 	/* Until we run out of pending work to finish... */
 	while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) {
+		/*
+		 * Deferred items that are created in the process of finishing
+		 * other deferred work items should be queued at the head of
+		 * the pending list, which puts them ahead of the deferred work
+		 * that was created by the caller.  This keeps the number of
+		 * pending work items to a minimum, which decreases the amount
+		 * of time that any one intent item can stick around in memory,
+		 * pinning the log tail.
+		 */
 		xfs_defer_create_intents(*tp);
-		list_splice_tail_init(&(*tp)->t_dfops, &dop_pending);
+		list_splice_init(&(*tp)->t_dfops, &dop_pending);
 
 		error = xfs_defer_trans_roll(tp);
 		if (error)
 			goto out_shutdown;
 
+		/* Possibly relog intent items to keep the log moving. */
+		error = xfs_defer_relog(tp, &dop_pending);
+		if (error)
+			goto out_shutdown;
+
 		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
 				       dfp_list);
 		error = xfs_defer_finish_one(*tp, dfp);
@@ -475,7 +529,10 @@ xfs_defer_finish(
 			return error;
 		}
 	}
-	xfs_defer_reset(*tp);
+
+	/* Reset LOWMODE now that we've finished all the dfops. */
+	ASSERT(list_empty(&(*tp)->t_dfops));
+	(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
 	return 0;
 }
 
@@ -549,6 +606,139 @@ xfs_defer_move(
 	 * that behavior.
 	 */
 	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
+	stp->t_flags &= ~XFS_TRANS_LOWMODE;
+}
+
+/*
+ * Prepare a chain of fresh deferred ops work items to be completed later.  Log
+ * recovery requires the ability to put off until later the actual finishing
+ * work so that it can process unfinished items recovered from the log in
+ * correct order.
+ *
+ * Create and log intent items for all the work that we're capturing so that we
+ * can be assured that the items will get replayed if the system goes down
+ * before log recovery gets a chance to finish the work it put off.  The entire
+ * deferred ops state is transferred to the capture structure and the
+ * transaction is then ready for the caller to commit it.  If there are no
+ * intent items to capture, this function returns NULL.
+ *
+ * If capture_ip is not NULL, the capture structure will obtain an extra
+ * reference to the inode.
+ */
+static struct xfs_defer_capture *
+xfs_defer_ops_capture(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*capture_ip)
+{
+	struct xfs_defer_capture	*dfc;
+
+	if (list_empty(&tp->t_dfops))
+		return NULL;
+
+	/* Create an object to capture the defer ops. */
+	dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS);
+	INIT_LIST_HEAD(&dfc->dfc_list);
+	INIT_LIST_HEAD(&dfc->dfc_dfops);
+
+	xfs_defer_create_intents(tp);
+
+	/* Move the dfops chain and transaction state to the capture struct. */
+	list_splice_init(&tp->t_dfops, &dfc->dfc_dfops);
+	dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE;
+	tp->t_flags &= ~XFS_TRANS_LOWMODE;
+
+	/* Capture the remaining block reservations along with the dfops. */
+	dfc->dfc_blkres = tp->t_blk_res - tp->t_blk_res_used;
+	dfc->dfc_rtxres = tp->t_rtx_res - tp->t_rtx_res_used;
+
+	/* Preserve the log reservation size. */
+	dfc->dfc_logres = tp->t_log_res;
+
+	/*
+	 * Grab an extra reference to this inode and attach it to the capture
+	 * structure.
+	 */
+	if (capture_ip) {
+		ihold(VFS_I(capture_ip));
+		dfc->dfc_capture_ip = capture_ip;
+	}
+
+	return dfc;
+}
+
+/* Release all resources that we used to capture deferred ops. */
+void
+xfs_defer_ops_release(
+	struct xfs_mount		*mp,
+	struct xfs_defer_capture	*dfc)
+{
+	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
+	if (dfc->dfc_capture_ip)
+		xfs_irele(dfc->dfc_capture_ip);
+	kmem_free(dfc);
+}
+
+/*
+ * Capture any deferred ops and commit the transaction.  This is the last step
+ * needed to finish a log intent item that we recovered from the log.  If any
+ * of the deferred ops operate on an inode, the caller must pass in that inode
+ * so that the reference can be transferred to the capture structure.  The
+ * caller must hold ILOCK_EXCL on the inode, and must unlock it before calling
+ * xfs_defer_ops_continue.
+ */
+int
+xfs_defer_ops_capture_and_commit(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*capture_ip,
+	struct list_head		*capture_list)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_defer_capture	*dfc;
+	int				error;
+
+	ASSERT(!capture_ip || xfs_isilocked(capture_ip, XFS_ILOCK_EXCL));
+
+	/* If we don't capture anything, commit transaction and exit. */
+	dfc = xfs_defer_ops_capture(tp, capture_ip);
+	if (!dfc)
+		return xfs_trans_commit(tp);
+
+	/* Commit the transaction and add the capture structure to the list. */
+	error = xfs_trans_commit(tp);
+	if (error) {
+		xfs_defer_ops_release(mp, dfc);
+		return error;
+	}
+
+	list_add_tail(&dfc->dfc_list, capture_list);
+	return 0;
+}
+
+/*
+ * Attach a chain of captured deferred ops to a new transaction and free the
+ * capture structure.  If an inode was captured, it will be passed back to the
+ * caller with ILOCK_EXCL held and joined to the transaction with lockflags==0.
+ * The caller now owns the inode reference.
+ */
+void
+xfs_defer_ops_continue(
+	struct xfs_defer_capture	*dfc,
+	struct xfs_trans		*tp,
+	struct xfs_inode		**captured_ipp)
+{
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+	ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
+
+	/* Lock and join the captured inode to the new transaction. */
+	if (dfc->dfc_capture_ip) {
+		xfs_ilock(dfc->dfc_capture_ip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, dfc->dfc_capture_ip, 0);
+	}
+	*captured_ipp = dfc->dfc_capture_ip;
+
+	/* Move captured dfops chain and state to the transaction. */
+	list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
+	tp->t_flags |= dfc->dfc_tpflags;
 
-	xfs_defer_reset(stp);
+	kmem_free(dfc);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 6b2ca580f2b0..05472f71fffe 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -8,6 +8,7 @@
 
 struct xfs_btree_cur;
 struct xfs_defer_op_type;
+struct xfs_defer_capture;
 
 /*
  * Header for deferred operation list.
@@ -63,4 +64,40 @@ extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
 extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
 
+/*
+ * This structure enables a dfops user to detach the chain of deferred
+ * operations from a transaction so that they can be continued later.
+ */
+struct xfs_defer_capture {
+	/* List of other capture structures. */
+	struct list_head	dfc_list;
+
+	/* Deferred ops state saved from the transaction. */
+	struct list_head	dfc_dfops;
+	unsigned int		dfc_tpflags;
+
+	/* Block reservations for the data and rt devices. */
+	unsigned int		dfc_blkres;
+	unsigned int		dfc_rtxres;
+
+	/* Log reservation saved from the transaction. */
+	unsigned int		dfc_logres;
+
+	/*
+	 * An inode reference that must be maintained to complete the deferred
+	 * work.
+	 */
+	struct xfs_inode	*dfc_capture_ip;
+};
+
+/*
+ * Functions to capture a chain of deferred operations and continue them later.
+ * This doesn't normally happen except log recovery.
+ */
+int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
+		struct xfs_inode *capture_ip, struct list_head *capture_list);
+void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
+		struct xfs_inode **captured_ipp);
+void xfs_defer_ops_release(struct xfs_mount *mp, struct xfs_defer_capture *d);
+
 #endif /* __XFS_DEFER_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 536666143fe7..ef5eaf33d146 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -17,7 +17,7 @@ struct xfs_dinode;
  */
 struct xfs_icdinode {
 	uint16_t	di_flushiter;	/* incremented on flush */
-	uint32_t	di_projid;	/* owner's project id */
+	prid_t		di_projid;	/* owner's project id */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 27c39268c31f..340c83f76c80 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2505,12 +2505,15 @@ xfs_rmap_map_extent(
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
+	enum xfs_rmap_intent_type type = XFS_RMAP_MAP;
+
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return;
 
-	__xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
-			XFS_RMAP_MAP_SHARED : XFS_RMAP_MAP, ip->i_ino,
-			whichfork, PREV);
+	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
+		type = XFS_RMAP_MAP_SHARED;
+
+	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
 }
 
 /* Unmap an extent out of a file. */
@@ -2521,12 +2524,15 @@ xfs_rmap_unmap_extent(
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
+	enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP;
+
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return;
 
-	__xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
-			XFS_RMAP_UNMAP_SHARED : XFS_RMAP_UNMAP, ip->i_ino,
-			whichfork, PREV);
+	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
+		type = XFS_RMAP_UNMAP_SHARED;
+
+	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
 }
 
 /*
@@ -2543,12 +2549,15 @@ xfs_rmap_convert_extent(
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
+	enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT;
+
 	if (!xfs_rmap_update_is_needed(mp, whichfork))
 		return;
 
-	__xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
-			XFS_RMAP_CONVERT_SHARED : XFS_RMAP_CONVERT, ip->i_ino,
-			whichfork, PREV);
+	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
+		type = XFS_RMAP_CONVERT_SHARED;
+
+	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
 }
 
 /* Schedule the creation of an rmap for non-file data. */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 1d9fa8a300f1..6c1aba16113c 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1018,7 +1018,6 @@ xfs_rtalloc_query_range(
 	struct xfs_mount		*mp = tp->t_mountp;
 	xfs_rtblock_t			rtstart;
 	xfs_rtblock_t			rtend;
-	xfs_rtblock_t			rem;
 	int				is_free;
 	int				error = 0;
 
@@ -1027,13 +1026,12 @@ xfs_rtalloc_query_range(
 	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
 	    low_rec->ar_startext == high_rec->ar_startext)
 		return 0;
-	if (high_rec->ar_startext > mp->m_sb.sb_rextents)
-		high_rec->ar_startext = mp->m_sb.sb_rextents;
+	high_rec->ar_startext = min(high_rec->ar_startext,
+			mp->m_sb.sb_rextents - 1);
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	rtstart = low_rec->ar_startext;
-	rem = high_rec->ar_startext - rtstart;
-	while (rem) {
+	while (rtstart <= high_rec->ar_startext) {
 		/* Is the first block free? */
 		error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend,
 				&is_free);
@@ -1042,7 +1040,7 @@ xfs_rtalloc_query_range(
 
 		/* How long does the extent go for? */
 		error = xfs_rtfind_forw(mp, tp, rtstart,
-				high_rec->ar_startext - 1, &rtend);
+				high_rec->ar_startext, &rtend);
 		if (error)
 			break;
 
@@ -1055,7 +1053,6 @@ xfs_rtalloc_query_range(
 				break;
 		}
 
-		rem -= rtend - rtstart + 1;
 		rtstart = rtend + 1;
 	}
 
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index e56786f0a13c..653f3280e1c1 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -441,6 +441,20 @@ xchk_da_btree_block(
 		goto out_freebp;
 	}
 
+	/*
+	 * If we've been handed a block that is below the dabtree root, does
+	 * its hashval match what the parent block expected to see?
+	 */
+	if (level > 0) {
+		struct xfs_da_node_entry	*key;
+
+		key = xchk_da_btree_node_entry(ds, level - 1);
+		if (be32_to_cpu(key->hashval) != blk->hashval) {
+			xchk_da_set_corrupt(ds, level);
+			goto out_freebp;
+		}
+	}
+
 out:
 	return error;
 out_freebp:
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index ec3691372e7c..9e16a4d0f97c 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -24,6 +24,7 @@
 #include "xfs_error.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_quota.h"
 
 kmem_zone_t	*xfs_bui_zone;
 kmem_zone_t	*xfs_bud_zone;
@@ -423,30 +424,26 @@ const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
 STATIC int
 xfs_bui_item_recover(
 	struct xfs_log_item		*lip,
-	struct xfs_trans		*parent_tp)
+	struct list_head		*capture_list)
 {
 	struct xfs_bmbt_irec		irec;
 	struct xfs_bui_log_item		*buip = BUI_ITEM(lip);
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
-	struct xfs_mount		*mp = parent_tp->t_mountp;
+	struct xfs_mount		*mp = lip->li_mountp;
 	struct xfs_map_extent		*bmap;
 	struct xfs_bud_log_item		*budp;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			inode_fsb;
 	xfs_filblks_t			count;
 	xfs_exntst_t			state;
-	enum xfs_bmap_intent_type	type;
-	bool				op_ok;
 	unsigned int			bui_type;
 	int				whichfork;
 	int				error = 0;
 
 	/* Only one mapping operation per BUI... */
-	if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
-		xfs_bui_release(buip);
+	if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS)
 		return -EFSCORRUPTED;
-	}
 
 	/*
 	 * First check the validity of the extent described by the
@@ -457,76 +454,58 @@ xfs_bui_item_recover(
 			   XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
 	inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
 			XFS_INO_TO_FSB(mp, bmap->me_owner)));
-	switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
+	state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
+			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+	whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
+			XFS_ATTR_FORK : XFS_DATA_FORK;
+	bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
+	switch (bui_type) {
 	case XFS_BMAP_MAP:
 	case XFS_BMAP_UNMAP:
-		op_ok = true;
 		break;
 	default:
-		op_ok = false;
-		break;
+		return -EFSCORRUPTED;
 	}
-	if (!op_ok || startblock_fsb == 0 ||
+	if (startblock_fsb == 0 ||
 	    bmap->me_len == 0 ||
 	    inode_fsb == 0 ||
 	    startblock_fsb >= mp->m_sb.sb_dblocks ||
 	    bmap->me_len >= mp->m_sb.sb_agblocks ||
 	    inode_fsb >= mp->m_sb.sb_dblocks ||
-	    (bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
-		/*
-		 * This will pull the BUI from the AIL and
-		 * free the memory associated with it.
-		 */
-		xfs_bui_release(buip);
+	    (bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS))
 		return -EFSCORRUPTED;
-	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
-			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
+	/* Grab the inode. */
+	error = xfs_iget(mp, NULL, bmap->me_owner, 0, 0, &ip);
 	if (error)
 		return error;
-	/*
-	 * Recovery stashes all deferred ops during intent processing and
-	 * finishes them on completion. Transfer current dfops state to this
-	 * transaction and transfer the result back before we return.
-	 */
-	xfs_defer_move(tp, parent_tp);
-	budp = xfs_trans_get_bud(tp, buip);
 
-	/* Grab the inode. */
-	error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
+	error = xfs_qm_dqattach(ip);
 	if (error)
-		goto err_inode;
+		goto err_rele;
 
 	if (VFS_I(ip)->i_nlink == 0)
 		xfs_iflags_set(ip, XFS_IRECOVERY);
 
-	/* Process deferred bmap item. */
-	state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
-			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-	whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
-			XFS_ATTR_FORK : XFS_DATA_FORK;
-	bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
-	switch (bui_type) {
-	case XFS_BMAP_MAP:
-	case XFS_BMAP_UNMAP:
-		type = bui_type;
-		break;
-	default:
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
-		error = -EFSCORRUPTED;
-		goto err_inode;
-	}
+	/* Allocate transaction and do the work. */
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
+			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
+	if (error)
+		goto err_rele;
+
+	budp = xfs_trans_get_bud(tp, buip);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
 	count = bmap->me_len;
-	error = xfs_trans_log_finish_bmap_update(tp, budp, type, ip, whichfork,
-			bmap->me_startoff, bmap->me_startblock, &count, state);
+	error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip,
+			whichfork, bmap->me_startoff, bmap->me_startblock,
+			&count, state);
 	if (error)
-		goto err_inode;
+		goto err_cancel;
 
 	if (count > 0) {
-		ASSERT(type == XFS_BMAP_UNMAP);
+		ASSERT(bui_type == XFS_BMAP_UNMAP);
 		irec.br_startblock = bmap->me_startblock;
 		irec.br_blockcount = count;
 		irec.br_startoff = bmap->me_startoff;
@@ -534,20 +513,24 @@ xfs_bui_item_recover(
 		xfs_bmap_unmap_extent(tp, ip, &irec);
 	}
 
-	xfs_defer_move(parent_tp, tp);
-	error = xfs_trans_commit(tp);
+	/*
+	 * Commit transaction, which frees the transaction and saves the inode
+	 * for later replay activities.
+	 */
+	error = xfs_defer_ops_capture_and_commit(tp, ip, capture_list);
+	if (error)
+		goto err_unlock;
+
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_irele(ip);
+	return 0;
 
-	return error;
-
-err_inode:
-	xfs_defer_move(parent_tp, tp);
+err_cancel:
 	xfs_trans_cancel(tp);
-	if (ip) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_irele(ip);
-	}
+err_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+err_rele:
+	xfs_irele(ip);
 	return error;
 }
 
@@ -559,6 +542,32 @@ xfs_bui_item_match(
 	return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_bui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_bud_log_item		*budp;
+	struct xfs_bui_log_item		*buip;
+	struct xfs_map_extent		*extp;
+	unsigned int			count;
+
+	count = BUI_ITEM(intent)->bui_format.bui_nextents;
+	extp = BUI_ITEM(intent)->bui_format.bui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	budp = xfs_trans_get_bud(tp, BUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
+
+	buip = xfs_bui_init(tp->t_mountp);
+	memcpy(buip->bui_format.bui_extents, extp, count * sizeof(*extp));
+	atomic_set(&buip->bui_next_extent, count);
+	xfs_trans_add_item(tp, &buip->bui_item);
+	set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
+	return &buip->bui_item;
+}
+
 static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_size	= xfs_bui_item_size,
 	.iop_format	= xfs_bui_item_format,
@@ -566,6 +575,7 @@ static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_release	= xfs_bui_item_release,
 	.iop_recover	= xfs_bui_item_recover,
 	.iop_match	= xfs_bui_item_match,
+	.iop_relog	= xfs_bui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index 24c7a8d11e1a..d44e8b4a3391 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -719,6 +719,8 @@ xlog_recover_get_buf_lsn(
 	case XFS_ABTC_MAGIC:
 	case XFS_RMAP_CRC_MAGIC:
 	case XFS_REFC_CRC_MAGIC:
+	case XFS_FIBT_CRC_MAGIC:
+	case XFS_FIBT_MAGIC:
 	case XFS_IBT_CRC_MAGIC:
 	case XFS_IBT_MAGIC: {
 		struct xfs_btree_block *btb = blk;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 3072814e407d..1d95ed387d66 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -831,8 +831,8 @@ xfs_qm_dqget_checks(
 }
 
 /*
- * Given the file system, id, and type (UDQUOT/GDQUOT), return a locked
- * dquot, doing an allocation (if requested) as needed.
+ * Given the file system, id, and type (UDQUOT/GDQUOT/PDQUOT), return a
+ * locked dquot, doing an allocation (if requested) as needed.
  */
 int
 xfs_qm_dqget(
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 6cb8cd11072a..6c11bfc3d452 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -585,10 +585,10 @@ const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
 STATIC int
 xfs_efi_item_recover(
 	struct xfs_log_item		*lip,
-	struct xfs_trans		*parent_tp)
+	struct list_head		*capture_list)
 {
 	struct xfs_efi_log_item		*efip = EFI_ITEM(lip);
-	struct xfs_mount		*mp = parent_tp->t_mountp;
+	struct xfs_mount		*mp = lip->li_mountp;
 	struct xfs_efd_log_item		*efdp;
 	struct xfs_trans		*tp;
 	struct xfs_extent		*extp;
@@ -608,14 +608,8 @@ xfs_efi_item_recover(
 		if (startblock_fsb == 0 ||
 		    extp->ext_len == 0 ||
 		    startblock_fsb >= mp->m_sb.sb_dblocks ||
-		    extp->ext_len >= mp->m_sb.sb_agblocks) {
-			/*
-			 * This will pull the EFI from the AIL and
-			 * free the memory associated with it.
-			 */
-			xfs_efi_release(efip);
+		    extp->ext_len >= mp->m_sb.sb_agblocks)
 			return -EFSCORRUPTED;
-		}
 	}
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
@@ -633,8 +627,7 @@ xfs_efi_item_recover(
 
 	}
 
-	error = xfs_trans_commit(tp);
-	return error;
+	return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
 
 abort_error:
 	xfs_trans_cancel(tp);
@@ -649,6 +642,34 @@ xfs_efi_item_match(
 	return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_efi_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_efd_log_item		*efdp;
+	struct xfs_efi_log_item		*efip;
+	struct xfs_extent		*extp;
+	unsigned int			count;
+
+	count = EFI_ITEM(intent)->efi_format.efi_nextents;
+	extp = EFI_ITEM(intent)->efi_format.efi_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	efdp = xfs_trans_get_efd(tp, EFI_ITEM(intent), count);
+	efdp->efd_next_extent = count;
+	memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp));
+	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
+
+	efip = xfs_efi_init(tp->t_mountp, count);
+	memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp));
+	atomic_set(&efip->efi_next_extent, count);
+	xfs_trans_add_item(tp, &efip->efi_item);
+	set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
+	return &efip->efi_item;
+}
+
 static const struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_size	= xfs_efi_item_size,
 	.iop_format	= xfs_efi_item_format,
@@ -656,6 +677,7 @@ static const struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_release	= xfs_efi_item_release,
 	.iop_recover	= xfs_efi_item_recover,
 	.iop_match	= xfs_efi_item_match,
+	.iop_relog	= xfs_efi_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 1a88025e68a3..db23e455eb91 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -33,39 +33,7 @@ enum xfs_fstrm_alloc {
 /*
  * Allocation group filestream associations are tracked with per-ag atomic
  * counters.  These counters allow xfs_filestream_pick_ag() to tell whether a
- * particular AG already has active filestreams associated with it. The mount
- * point's m_peraglock is used to protect these counters from per-ag array
- * re-allocation during a growfs operation.  When xfs_growfs_data_private() is
- * about to reallocate the array, it calls xfs_filestream_flush() with the
- * m_peraglock held in write mode.
- *
- * Since xfs_mru_cache_flush() guarantees that all the free functions for all
- * the cache elements have finished executing before it returns, it's safe for
- * the free functions to use the atomic counters without m_peraglock protection.
- * This allows the implementation of xfs_fstrm_free_func() to be agnostic about
- * whether it was called with the m_peraglock held in read mode, write mode or
- * not held at all.  The race condition this addresses is the following:
- *
- *  - The work queue scheduler fires and pulls a filestream directory cache
- *    element off the LRU end of the cache for deletion, then gets pre-empted.
- *  - A growfs operation grabs the m_peraglock in write mode, flushes all the
- *    remaining items from the cache and reallocates the mount point's per-ag
- *    array, resetting all the counters to zero.
- *  - The work queue thread resumes and calls the free function for the element
- *    it started cleaning up earlier.  In the process it decrements the
- *    filestreams counter for an AG that now has no references.
- *
- * With a shrinkfs feature, the above scenario could panic the system.
- *
- * All other uses of the following macros should be protected by either the
- * m_peraglock held in read mode, or the cache's internal locking exposed by the
- * interval between a call to xfs_mru_cache_lookup() and a call to
- * xfs_mru_cache_done().  In addition, the m_peraglock must be held in read mode
- * when new elements are added to the cache.
- *
- * Combined, these locking rules ensure that no associations will ever exist in
- * the cache that reference per-ag array elements that have since been
- * reallocated.
+ * particular AG already has active filestreams associated with it.
  */
 int
 xfs_filestream_peek_ag(
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 4eebcec4aae6..9ce5e7d5bf8f 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -26,7 +26,7 @@
 #include "xfs_rtalloc.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
-void
+static void
 xfs_fsmap_from_internal(
 	struct fsmap		*dest,
 	struct xfs_fsmap	*src)
@@ -155,8 +155,7 @@ xfs_fsmap_owner_from_rmap(
 /* getfsmap query state */
 struct xfs_getfsmap_info {
 	struct xfs_fsmap_head	*head;
-	xfs_fsmap_format_t	formatter;	/* formatting fn */
-	void			*format_arg;	/* format buffer */
+	struct fsmap		*fsmap_recs;	/* mapping records */
 	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
 	u64			missing_owner;	/* owner of holes */
@@ -224,6 +223,20 @@ xfs_getfsmap_is_shared(
 	return 0;
 }
 
+static inline void
+xfs_getfsmap_format(
+	struct xfs_mount		*mp,
+	struct xfs_fsmap		*xfm,
+	struct xfs_getfsmap_info	*info)
+{
+	struct fsmap			*rec;
+
+	trace_xfs_getfsmap_mapping(mp, xfm);
+
+	rec = &info->fsmap_recs[info->head->fmh_entries++];
+	xfs_fsmap_from_internal(rec, xfm);
+}
+
 /*
  * Format a reverse mapping for getfsmap, having translated rm_startblock
  * into the appropriate daddr units.
@@ -256,6 +269,9 @@ xfs_getfsmap_helper(
 
 	/* Are we just counting mappings? */
 	if (info->head->fmh_count == 0) {
+		if (info->head->fmh_entries == UINT_MAX)
+			return -ECANCELED;
+
 		if (rec_daddr > info->next_daddr)
 			info->head->fmh_entries++;
 
@@ -285,10 +301,7 @@ xfs_getfsmap_helper(
 		fmr.fmr_offset = 0;
 		fmr.fmr_length = rec_daddr - info->next_daddr;
 		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
-		error = info->formatter(&fmr, info->format_arg);
-		if (error)
-			return error;
-		info->head->fmh_entries++;
+		xfs_getfsmap_format(mp, &fmr, info);
 	}
 
 	if (info->last)
@@ -320,11 +333,8 @@ xfs_getfsmap_helper(
 		if (shared)
 			fmr.fmr_flags |= FMR_OF_SHARED;
 	}
-	error = info->formatter(&fmr, info->format_arg);
-	if (error)
-		return error;
-	info->head->fmh_entries++;
 
+	xfs_getfsmap_format(mp, &fmr, info);
 out:
 	rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
 	if (info->next_daddr < rec_daddr)
@@ -792,11 +802,11 @@ xfs_getfsmap_check_keys(
 #endif /* CONFIG_XFS_RT */
 
 /*
- * Get filesystem's extents as described in head, and format for
- * output.  Calls formatter to fill the user's buffer until all
- * extents are mapped, until the passed-in head->fmh_count slots have
- * been filled, or until the formatter short-circuits the loop, if it
- * is tracking filled-in extents on its own.
+ * Get filesystem's extents as described in head, and format for output. Fills
+ * in the supplied records array until there are no more reverse mappings to
+ * return or head.fmh_entries == head.fmh_count.  In the second case, this
+ * function returns -ECANCELED to indicate that more records would have been
+ * returned.
  *
  * Key to Confusion
  * ----------------
@@ -816,8 +826,7 @@ int
 xfs_getfsmap(
 	struct xfs_mount		*mp,
 	struct xfs_fsmap_head		*head,
-	xfs_fsmap_format_t		formatter,
-	void				*arg)
+	struct fsmap			*fsmap_recs)
 {
 	struct xfs_trans		*tp = NULL;
 	struct xfs_fsmap		dkeys[2];	/* per-dev keys */
@@ -892,8 +901,7 @@ xfs_getfsmap(
 
 	info.next_daddr = head->fmh_keys[0].fmr_physical +
 			  head->fmh_keys[0].fmr_length;
-	info.formatter = formatter;
-	info.format_arg = arg;
+	info.fsmap_recs = fsmap_recs;
 	info.head = head;
 
 	/*
diff --git a/fs/xfs/xfs_fsmap.h b/fs/xfs/xfs_fsmap.h
index c6c57739b862..a0775788e7b1 100644
--- a/fs/xfs/xfs_fsmap.h
+++ b/fs/xfs/xfs_fsmap.h
@@ -27,13 +27,9 @@ struct xfs_fsmap_head {
 	struct xfs_fsmap fmh_keys[2];	/* low and high keys */
 };
 
-void xfs_fsmap_from_internal(struct fsmap *dest, struct xfs_fsmap *src);
 void xfs_fsmap_to_internal(struct xfs_fsmap *dest, struct fsmap *src);
 
-/* fsmap to userspace formatter - copy to user & advance pointer */
-typedef int (*xfs_fsmap_format_t)(struct xfs_fsmap *, void *);
-
 int xfs_getfsmap(struct xfs_mount *mp, struct xfs_fsmap_head *head,
-		xfs_fsmap_format_t formatter, void *arg);
+		struct fsmap *out_recs);
 
 #endif /* __XFS_FSMAP_H__ */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 49624973eecc..2bfbcf28b1bd 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -698,6 +698,68 @@ out_unlock:
 	return error;
 }
 
+/* Propagate di_flags from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags(
+	struct xfs_inode	*ip,
+	const struct xfs_inode	*pip)
+{
+	unsigned int		di_flags = 0;
+	umode_t			mode = VFS_I(ip)->i_mode;
+
+	if (S_ISDIR(mode)) {
+		if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
+			di_flags |= XFS_DIFLAG_RTINHERIT;
+		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+			ip->i_d.di_extsize = pip->i_d.di_extsize;
+		}
+		if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+			di_flags |= XFS_DIFLAG_PROJINHERIT;
+	} else if (S_ISREG(mode)) {
+		if ((pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) &&
+		    xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
+			di_flags |= XFS_DIFLAG_REALTIME;
+		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+			di_flags |= XFS_DIFLAG_EXTSIZE;
+			ip->i_d.di_extsize = pip->i_d.di_extsize;
+		}
+	}
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
+	    xfs_inherit_noatime)
+		di_flags |= XFS_DIFLAG_NOATIME;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
+	    xfs_inherit_nodump)
+		di_flags |= XFS_DIFLAG_NODUMP;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
+	    xfs_inherit_sync)
+		di_flags |= XFS_DIFLAG_SYNC;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
+	    xfs_inherit_nosymlinks)
+		di_flags |= XFS_DIFLAG_NOSYMLINKS;
+	if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
+	    xfs_inherit_nodefrag)
+		di_flags |= XFS_DIFLAG_NODEFRAG;
+	if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
+		di_flags |= XFS_DIFLAG_FILESTREAM;
+
+	ip->i_d.di_flags |= di_flags;
+}
+
+/* Propagate di_flags2 from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags2(
+	struct xfs_inode	*ip,
+	const struct xfs_inode	*pip)
+{
+	if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
+		ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+		ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+	}
+	if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+		ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
+}
+
 /*
  * Allocate an inode on disk and return a copy of its in-core version.
  * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
@@ -841,54 +903,10 @@ xfs_ialloc(
 		break;
 	case S_IFREG:
 	case S_IFDIR:
-		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint		di_flags = 0;
-
-			if (S_ISDIR(mode)) {
-				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
-					di_flags |= XFS_DIFLAG_RTINHERIT;
-				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
-					di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-					ip->i_d.di_extsize = pip->i_d.di_extsize;
-				}
-				if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-					di_flags |= XFS_DIFLAG_PROJINHERIT;
-			} else if (S_ISREG(mode)) {
-				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
-					di_flags |= XFS_DIFLAG_REALTIME;
-				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
-					di_flags |= XFS_DIFLAG_EXTSIZE;
-					ip->i_d.di_extsize = pip->i_d.di_extsize;
-				}
-			}
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
-			    xfs_inherit_noatime)
-				di_flags |= XFS_DIFLAG_NOATIME;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
-			    xfs_inherit_nodump)
-				di_flags |= XFS_DIFLAG_NODUMP;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
-			    xfs_inherit_sync)
-				di_flags |= XFS_DIFLAG_SYNC;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
-			    xfs_inherit_nosymlinks)
-				di_flags |= XFS_DIFLAG_NOSYMLINKS;
-			if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
-			    xfs_inherit_nodefrag)
-				di_flags |= XFS_DIFLAG_NODEFRAG;
-			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
-				di_flags |= XFS_DIFLAG_FILESTREAM;
-
-			ip->i_d.di_flags |= di_flags;
-		}
-		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) {
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
-				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
-			}
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
-		}
+		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY))
+			xfs_inode_inherit_flags(ip, pip);
+		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY))
+			xfs_inode_inherit_flags2(ip, pip);
 		/* FALLTHROUGH */
 	case S_IFLNK:
 		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
@@ -1516,17 +1534,10 @@ xfs_itruncate_extents_flags(
 		if (error)
 			goto out;
 
-		/*
-		 * Duplicate the transaction that has the permanent
-		 * reservation and commit the old transaction.
-		 */
+		/* free the just unmapped extents */
 		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out;
-
-		error = xfs_trans_roll_inode(&tp, ip);
-		if (error)
-			goto out;
 	}
 
 	if (whichfork == XFS_DATA_FORK) {
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bca7659fb5c6..3fbd98f61ea5 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1716,39 +1716,17 @@ out_free_buf:
 	return error;
 }
 
-struct getfsmap_info {
-	struct xfs_mount	*mp;
-	struct fsmap_head __user *data;
-	unsigned int		idx;
-	__u32			last_flags;
-};
-
-STATIC int
-xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv)
-{
-	struct getfsmap_info	*info = priv;
-	struct fsmap		fm;
-
-	trace_xfs_getfsmap_mapping(info->mp, xfm);
-
-	info->last_flags = xfm->fmr_flags;
-	xfs_fsmap_from_internal(&fm, xfm);
-	if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm,
-			sizeof(struct fsmap)))
-		return -EFAULT;
-
-	return 0;
-}
-
 STATIC int
 xfs_ioc_getfsmap(
 	struct xfs_inode	*ip,
 	struct fsmap_head	__user *arg)
 {
-	struct getfsmap_info	info = { NULL };
 	struct xfs_fsmap_head	xhead = {0};
 	struct fsmap_head	head;
-	bool			aborted = false;
+	struct fsmap		*recs;
+	unsigned int		count;
+	__u32			last_flags = 0;
+	bool			done = false;
 	int			error;
 
 	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
@@ -1760,38 +1738,112 @@ xfs_ioc_getfsmap(
 		       sizeof(head.fmh_keys[1].fmr_reserved)))
 		return -EINVAL;
 
+	/*
+	 * Use an internal memory buffer so that we don't have to copy fsmap
+	 * data to userspace while holding locks.  Start by trying to allocate
+	 * up to 128k for the buffer, but fall back to a single page if needed.
+	 */
+	count = min_t(unsigned int, head.fmh_count,
+			131072 / sizeof(struct fsmap));
+	recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL);
+	if (!recs) {
+		count = min_t(unsigned int, head.fmh_count,
+				PAGE_SIZE / sizeof(struct fsmap));
+		recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL);
+		if (!recs)
+			return -ENOMEM;
+	}
+
 	xhead.fmh_iflags = head.fmh_iflags;
-	xhead.fmh_count = head.fmh_count;
 	xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
 	xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);
 
 	trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
 	trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);
 
-	info.mp = ip->i_mount;
-	info.data = arg;
-	error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info);
-	if (error == -ECANCELED) {
-		error = 0;
-		aborted = true;
-	} else if (error)
-		return error;
+	head.fmh_entries = 0;
+	do {
+		struct fsmap __user	*user_recs;
+		struct fsmap		*last_rec;
+
+		user_recs = &arg->fmh_recs[head.fmh_entries];
+		xhead.fmh_entries = 0;
+		xhead.fmh_count = min_t(unsigned int, count,
+					head.fmh_count - head.fmh_entries);
+
+		/* Run query, record how many entries we got. */
+		error = xfs_getfsmap(ip->i_mount, &xhead, recs);
+		switch (error) {
+		case 0:
+			/*
+			 * There are no more records in the result set.  Copy
+			 * whatever we got to userspace and break out.
+			 */
+			done = true;
+			break;
+		case -ECANCELED:
+			/*
+			 * The internal memory buffer is full.  Copy whatever
+			 * records we got to userspace and go again if we have
+			 * not yet filled the userspace buffer.
+			 */
+			error = 0;
+			break;
+		default:
+			goto out_free;
+		}
+		head.fmh_entries += xhead.fmh_entries;
+		head.fmh_oflags = xhead.fmh_oflags;
 
-	/* If we didn't abort, set the "last" flag in the last fmx */
-	if (!aborted && info.idx) {
-		info.last_flags |= FMR_OF_LAST;
-		if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags,
-				&info.last_flags, sizeof(info.last_flags)))
-			return -EFAULT;
+		/*
+		 * If the caller wanted a record count or there aren't any
+		 * new records to return, we're done.
+		 */
+		if (head.fmh_count == 0 || xhead.fmh_entries == 0)
+			break;
+
+		/* Copy all the records we got out to userspace. */
+		if (copy_to_user(user_recs, recs,
+				 xhead.fmh_entries * sizeof(struct fsmap))) {
+			error = -EFAULT;
+			goto out_free;
+		}
+
+		/* Remember the last record flags we copied to userspace. */
+		last_rec = &recs[xhead.fmh_entries - 1];
+		last_flags = last_rec->fmr_flags;
+
+		/* Set up the low key for the next iteration. */
+		xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec);
+		trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
+	} while (!done && head.fmh_entries < head.fmh_count);
+
+	/*
+	 * If there are no more records in the query result set and we're not
+	 * in counting mode, mark the last record returned with the LAST flag.
+	 */
+	if (done && head.fmh_count > 0 && head.fmh_entries > 0) {
+		struct fsmap __user	*user_rec;
+
+		last_flags |= FMR_OF_LAST;
+		user_rec = &arg->fmh_recs[head.fmh_entries - 1];
+
+		if (copy_to_user(&user_rec->fmr_flags, &last_flags,
+					sizeof(last_flags))) {
+			error = -EFAULT;
+			goto out_free;
+		}
 	}
 
 	/* copy back header */
-	head.fmh_entries = xhead.fmh_entries;
-	head.fmh_oflags = xhead.fmh_oflags;
-	if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
-		return -EFAULT;
+	if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) {
+		error = -EFAULT;
+		goto out_free;
+	}
 
-	return 0;
+out_free:
+	kmem_free(recs);
+	return error;
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 80a13c8561d8..5e165456da68 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -237,7 +237,7 @@ xfs_vn_create(
 	umode_t		mode,
 	bool		flags)
 {
-	return xfs_vn_mknod(dir, dentry, mode, 0);
+	return xfs_generic_create(dir, dentry, mode, 0, false);
 }
 
 STATIC int
@@ -246,7 +246,7 @@ xfs_vn_mkdir(
 	struct dentry	*dentry,
 	umode_t		mode)
 {
-	return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
+	return xfs_generic_create(dir, dentry, mode | S_IFDIR, 0, false);
 }
 
 STATIC struct dentry *
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index ab737fed7b12..ad1009778d33 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -123,7 +123,6 @@ typedef __u32			xfs_nlink_t;
 #define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
 
-#define SYNCHRONIZE()	barrier()
 #define __return_address __builtin_return_address(0)
 
 /*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ad0c69ee8947..fa2d05e65ff1 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1475,14 +1475,14 @@ xlog_commit_record(
 }
 
 /*
- * Push on the buffer cache code if we ever use more than 75% of the on-disk
- * log space.  This code pushes on the lsn which would supposedly free up
- * the 25% which we want to leave free.  We may need to adopt a policy which
- * pushes on an lsn which is further along in the log once we reach the high
- * water mark.  In this manner, we would be creating a low water mark.
+ * Compute the LSN that we'd need to push the log tail towards in order to have
+ * (a) enough on-disk log space to log the number of bytes specified, (b) at
+ * least 25% of the log space free, and (c) at least 256 blocks free.  If the
+ * log free space already meets all three thresholds, this function returns
+ * NULLCOMMITLSN.
  */
-STATIC void
-xlog_grant_push_ail(
+xfs_lsn_t
+xlog_grant_push_threshold(
 	struct xlog	*log,
 	int		need_bytes)
 {
@@ -1508,7 +1508,7 @@ xlog_grant_push_ail(
 	free_threshold = max(free_threshold, (log->l_logBBsize >> 2));
 	free_threshold = max(free_threshold, 256);
 	if (free_blocks >= free_threshold)
-		return;
+		return NULLCOMMITLSN;
 
 	xlog_crack_atomic_lsn(&log->l_tail_lsn, &threshold_cycle,
 						&threshold_block);
@@ -1528,13 +1528,33 @@ xlog_grant_push_ail(
 	if (XFS_LSN_CMP(threshold_lsn, last_sync_lsn) > 0)
 		threshold_lsn = last_sync_lsn;
 
+	return threshold_lsn;
+}
+
+/*
+ * Push the tail of the log if we need to do so to maintain the free log space
+ * thresholds set out by xlog_grant_push_threshold.  We may need to adopt a
+ * policy which pushes on an lsn which is further along in the log once we
+ * reach the high water mark.  In this manner, we would be creating a low water
+ * mark.
+ */
+STATIC void
+xlog_grant_push_ail(
+	struct xlog	*log,
+	int		need_bytes)
+{
+	xfs_lsn_t	threshold_lsn;
+
+	threshold_lsn = xlog_grant_push_threshold(log, need_bytes);
+	if (threshold_lsn == NULLCOMMITLSN || XLOG_FORCED_SHUTDOWN(log))
+		return;
+
 	/*
 	 * Get the transaction layer to kick the dirty buffers out to
 	 * disk asynchronously. No point in trying to do this if
 	 * the filesystem is shutting down.
 	 */
-	if (!XLOG_FORCED_SHUTDOWN(log))
-		xfs_ail_push(log->l_ailp, threshold_lsn);
+	xfs_ail_push(log->l_ailp, threshold_lsn);
 }
 
 /*
@@ -1604,9 +1624,7 @@ xlog_cksum(
 		int		i;
 		int		xheads;
 
-		xheads = size / XLOG_HEADER_CYCLE_SIZE;
-		if (size % XLOG_HEADER_CYCLE_SIZE)
-			xheads++;
+		xheads = DIV_ROUND_UP(size, XLOG_HEADER_CYCLE_SIZE);
 
 		for (i = 1; i < xheads; i++) {
 			crc = crc32c(crc, &xhdr[i].hic_xheader,
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 1412d6993f1e..58c3fcbec94a 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -141,4 +141,6 @@ void	xfs_log_quiesce(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 bool	xfs_log_in_recovery(struct xfs_mount *);
 
+xfs_lsn_t xlog_grant_push_threshold(struct xlog *log, int need_bytes);
+
 #endif	/* __XFS_LOG_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a17d788921d6..a8289adc1b29 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -371,6 +371,19 @@ out:
 	return error;
 }
 
+static inline int
+xlog_logrec_hblks(struct xlog *log, struct xlog_rec_header *rh)
+{
+	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+		int	h_size = be32_to_cpu(rh->h_size);
+
+		if ((be32_to_cpu(rh->h_version) & XLOG_VERSION_2) &&
+		    h_size > XLOG_HEADER_CYCLE_SIZE)
+			return DIV_ROUND_UP(h_size, XLOG_HEADER_CYCLE_SIZE);
+	}
+	return 1;
+}
+
 /*
  * Potentially backup over partial log record write.
  *
@@ -463,15 +476,7 @@ xlog_find_verify_log_record(
 	 * reset last_blk.  Only when last_blk points in the middle of a log
 	 * record do we update last_blk.
 	 */
-	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		uint	h_size = be32_to_cpu(head->h_size);
-
-		xhdrs = h_size / XLOG_HEADER_CYCLE_SIZE;
-		if (h_size % XLOG_HEADER_CYCLE_SIZE)
-			xhdrs++;
-	} else {
-		xhdrs = 1;
-	}
+	xhdrs = xlog_logrec_hblks(log, head);
 
 	if (*last_blk - i + extra_bblks !=
 	    BTOBB(be32_to_cpu(head->h_len)) + xhdrs)
@@ -1158,22 +1163,7 @@ xlog_check_unmount_rec(
 	 * below. We won't want to clear the unmount record if there is one, so
 	 * we pass the lsn of the unmount record rather than the block after it.
 	 */
-	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		int	h_size = be32_to_cpu(rhead->h_size);
-		int	h_version = be32_to_cpu(rhead->h_version);
-
-		if ((h_version & XLOG_VERSION_2) &&
-		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
-			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
-			if (h_size % XLOG_HEADER_CYCLE_SIZE)
-				hblks++;
-		} else {
-			hblks = 1;
-		}
-	} else {
-		hblks = 1;
-	}
-
+	hblks = xlog_logrec_hblks(log, rhead);
 	after_umount_blk = xlog_wrap_logbno(log,
 			rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)));
 
@@ -2444,44 +2434,66 @@ xlog_recover_process_data(
 /* Take all the collected deferred ops and finish them in order. */
 static int
 xlog_finish_defer_ops(
-	struct xfs_trans	*parent_tp)
+	struct xfs_mount	*mp,
+	struct list_head	*capture_list)
 {
-	struct xfs_mount	*mp = parent_tp->t_mountp;
+	struct xfs_defer_capture *dfc, *next;
 	struct xfs_trans	*tp;
-	int64_t			freeblks;
-	uint			resblks;
-	int			error;
+	struct xfs_inode	*ip;
+	int			error = 0;
 
-	/*
-	 * We're finishing the defer_ops that accumulated as a result of
-	 * recovering unfinished intent items during log recovery.  We
-	 * reserve an itruncate transaction because it is the largest
-	 * permanent transaction type.  Since we're the only user of the fs
-	 * right now, take 93% (15/16) of the available free blocks.  Use
-	 * weird math to avoid a 64-bit division.
-	 */
-	freeblks = percpu_counter_sum(&mp->m_fdblocks);
-	if (freeblks <= 0)
-		return -ENOSPC;
-	resblks = min_t(int64_t, UINT_MAX, freeblks);
-	resblks = (resblks * 15) >> 4;
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks,
-			0, XFS_TRANS_RESERVE, &tp);
-	if (error)
-		return error;
-	/* transfer all collected dfops to this transaction */
-	xfs_defer_move(tp, parent_tp);
+	list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
+		struct xfs_trans_res	resv;
+
+		/*
+		 * Create a new transaction reservation from the captured
+		 * information.  Set logcount to 1 to force the new transaction
+		 * to regrant every roll so that we can make forward progress
+		 * in recovery no matter how full the log might be.
+		 */
+		resv.tr_logres = dfc->dfc_logres;
+		resv.tr_logcount = 1;
+		resv.tr_logflags = XFS_TRANS_PERM_LOG_RES;
+
+		error = xfs_trans_alloc(mp, &resv, dfc->dfc_blkres,
+				dfc->dfc_rtxres, XFS_TRANS_RESERVE, &tp);
+		if (error)
+			return error;
 
-	return xfs_trans_commit(tp);
+		/*
+		 * Transfer to this new transaction all the dfops we captured
+		 * from recovering a single intent item.
+		 */
+		list_del_init(&dfc->dfc_list);
+		xfs_defer_ops_continue(dfc, tp, &ip);
+
+		error = xfs_trans_commit(tp);
+		if (ip) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			xfs_irele(ip);
+		}
+		if (error)
+			return error;
+	}
+
+	ASSERT(list_empty(capture_list));
+	return 0;
 }
 
-/* Is this log item a deferred action intent? */
-static inline bool xlog_item_is_intent(struct xfs_log_item *lip)
+/* Release all the captured defer ops and capture structures in this list. */
+static void
+xlog_abort_defer_ops(
+	struct xfs_mount		*mp,
+	struct list_head		*capture_list)
 {
-	return lip->li_ops->iop_recover != NULL &&
-	       lip->li_ops->iop_match != NULL;
-}
+	struct xfs_defer_capture	*dfc;
+	struct xfs_defer_capture	*next;
 
+	list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
+		list_del_init(&dfc->dfc_list);
+		xfs_defer_ops_release(mp, dfc);
+	}
+}
 /*
  * When this is called, all of the log intent items which did not have
  * corresponding log done items should be in the AIL.  What we do now
@@ -2502,35 +2514,23 @@ STATIC int
 xlog_recover_process_intents(
 	struct xlog		*log)
 {
-	struct xfs_trans	*parent_tp;
+	LIST_HEAD(capture_list);
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	struct xfs_ail		*ailp;
-	int			error;
+	int			error = 0;
 #if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
 #endif
 
-	/*
-	 * The intent recovery handlers commit transactions to complete recovery
-	 * for individual intents, but any new deferred operations that are
-	 * queued during that process are held off until the very end. The
-	 * purpose of this transaction is to serve as a container for deferred
-	 * operations. Each intent recovery handler must transfer dfops here
-	 * before its local transaction commits, and we'll finish the entire
-	 * list below.
-	 */
-	error = xfs_trans_alloc_empty(log->l_mp, &parent_tp);
-	if (error)
-		return error;
-
 	ailp = log->l_ailp;
 	spin_lock(&ailp->ail_lock);
-	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	while (lip != NULL) {
+	for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
+	     lip != NULL;
+	     lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
 		/*
 		 * We're done when we see something other than an intent.
 		 * There should be no intents left in the AIL now.
@@ -2552,26 +2552,29 @@ xlog_recover_process_intents(
 
 		/*
 		 * NOTE: If your intent processing routine can create more
-		 * deferred ops, you /must/ attach them to the transaction in
-		 * this routine or else those subsequent intents will get
+		 * deferred ops, you /must/ attach them to the capture list in
+		 * the recover routine or else those subsequent intents will be
 		 * replayed in the wrong order!
 		 */
-		if (!test_and_set_bit(XFS_LI_RECOVERED, &lip->li_flags)) {
-			spin_unlock(&ailp->ail_lock);
-			error = lip->li_ops->iop_recover(lip, parent_tp);
-			spin_lock(&ailp->ail_lock);
-		}
+		spin_unlock(&ailp->ail_lock);
+		error = lip->li_ops->iop_recover(lip, &capture_list);
+		spin_lock(&ailp->ail_lock);
 		if (error)
-			goto out;
-		lip = xfs_trans_ail_cursor_next(ailp, &cur);
+			break;
 	}
-out:
+
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
-	if (!error)
-		error = xlog_finish_defer_ops(parent_tp);
-	xfs_trans_cancel(parent_tp);
+	if (error)
+		goto err;
+
+	error = xlog_finish_defer_ops(log->l_mp, &capture_list);
+	if (error)
+		goto err;
 
+	return 0;
+err:
+	xlog_abort_defer_ops(log->l_mp, &capture_list);
 	return error;
 }
 
@@ -2878,7 +2881,8 @@ STATIC int
 xlog_valid_rec_header(
 	struct xlog		*log,
 	struct xlog_rec_header	*rhead,
-	xfs_daddr_t		blkno)
+	xfs_daddr_t		blkno,
+	int			bufsize)
 {
 	int			hlen;
 
@@ -2894,10 +2898,14 @@ xlog_valid_rec_header(
 		return -EFSCORRUPTED;
 	}
 
-	/* LR body must have data or it wouldn't have been written */
+	/*
+	 * LR body must have data (or it wouldn't have been written)
+	 * and h_len must not be greater than LR buffer size.
+	 */
 	hlen = be32_to_cpu(rhead->h_len);
-	if (XFS_IS_CORRUPT(log->l_mp, hlen <= 0 || hlen > INT_MAX))
+	if (XFS_IS_CORRUPT(log->l_mp, hlen <= 0 || hlen > bufsize))
 		return -EFSCORRUPTED;
+
 	if (XFS_IS_CORRUPT(log->l_mp,
 			   blkno > log->l_logBBsize || blkno > INT_MAX))
 		return -EFSCORRUPTED;
@@ -2958,9 +2966,6 @@ xlog_do_recovery_pass(
 			goto bread_err1;
 
 		rhead = (xlog_rec_header_t *)offset;
-		error = xlog_valid_rec_header(log, rhead, tail_blk);
-		if (error)
-			goto bread_err1;
 
 		/*
 		 * xfsprogs has a bug where record length is based on lsunit but
@@ -2975,30 +2980,22 @@ xlog_do_recovery_pass(
 		 */
 		h_size = be32_to_cpu(rhead->h_size);
 		h_len = be32_to_cpu(rhead->h_len);
-		if (h_len > h_size) {
-			if (h_len <= log->l_mp->m_logbsize &&
-			    be32_to_cpu(rhead->h_num_logops) == 1) {
-				xfs_warn(log->l_mp,
+		if (h_len > h_size && h_len <= log->l_mp->m_logbsize &&
+		    rhead->h_num_logops == cpu_to_be32(1)) {
+			xfs_warn(log->l_mp,
 		"invalid iclog size (%d bytes), using lsunit (%d bytes)",
-					 h_size, log->l_mp->m_logbsize);
-				h_size = log->l_mp->m_logbsize;
-			} else {
-				XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW,
-						log->l_mp);
-				error = -EFSCORRUPTED;
-				goto bread_err1;
-			}
+				 h_size, log->l_mp->m_logbsize);
+			h_size = log->l_mp->m_logbsize;
 		}
 
-		if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) &&
-		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
-			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
-			if (h_size % XLOG_HEADER_CYCLE_SIZE)
-				hblks++;
+		error = xlog_valid_rec_header(log, rhead, tail_blk, h_size);
+		if (error)
+			goto bread_err1;
+
+		hblks = xlog_logrec_hblks(log, rhead);
+		if (hblks != 1) {
 			kmem_free(hbp);
 			hbp = xlog_alloc_buffer(log, hblks);
-		} else {
-			hblks = 1;
 		}
 	} else {
 		ASSERT(log->l_sectBBsize == 1);
@@ -3070,7 +3067,7 @@ xlog_do_recovery_pass(
 			}
 			rhead = (xlog_rec_header_t *)offset;
 			error = xlog_valid_rec_header(log, rhead,
-						split_hblks ? blk_no : 0);
+					split_hblks ? blk_no : 0, h_size);
 			if (error)
 				goto bread_err2;
 
@@ -3151,7 +3148,7 @@ xlog_do_recovery_pass(
 			goto bread_err2;
 
 		rhead = (xlog_rec_header_t *)offset;
-		error = xlog_valid_rec_header(log, rhead, blk_no);
+		error = xlog_valid_rec_header(log, rhead, blk_no, h_size);
 		if (error)
 			goto bread_err2;
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 3f82e0c92c2d..b2a9abee8b2b 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -249,7 +249,6 @@ xfs_qm_unmount_quotas(
 STATIC int
 xfs_qm_dqattach_one(
 	struct xfs_inode	*ip,
-	xfs_dqid_t		id,
 	xfs_dqtype_t		type,
 	bool			doalloc,
 	struct xfs_dquot	**IO_idqpp)
@@ -330,23 +329,23 @@ xfs_qm_dqattach_locked(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
-		error = xfs_qm_dqattach_one(ip, i_uid_read(VFS_I(ip)),
-				XFS_DQTYPE_USER, doalloc, &ip->i_udquot);
+		error = xfs_qm_dqattach_one(ip, 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_DQTYPE_GROUP, doalloc, &ip->i_gdquot);
+		error = xfs_qm_dqattach_one(ip, 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_DQTYPE_PROJ,
+		error = xfs_qm_dqattach_one(ip, XFS_DQTYPE_PROJ,
 				doalloc, &ip->i_pdquot);
 		if (error)
 			goto done;
@@ -1663,6 +1662,7 @@ xfs_qm_vop_dqalloc(
 	}
 
 	if ((flags & XFS_QMOPT_UQUOTA) && XFS_IS_UQUOTA_ON(mp)) {
+		ASSERT(O_udqpp);
 		if (!uid_eq(inode->i_uid, uid)) {
 			/*
 			 * What we need is the dquot that has this uid, and
@@ -1696,6 +1696,7 @@ xfs_qm_vop_dqalloc(
 		}
 	}
 	if ((flags & XFS_QMOPT_GQUOTA) && XFS_IS_GQUOTA_ON(mp)) {
+		ASSERT(O_gdqpp);
 		if (!gid_eq(inode->i_gid, gid)) {
 			xfs_iunlock(ip, lockflags);
 			error = xfs_qm_dqget(mp, from_kgid(user_ns, gid),
@@ -1713,9 +1714,10 @@ xfs_qm_vop_dqalloc(
 		}
 	}
 	if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
+		ASSERT(O_pdqpp);
 		if (ip->i_d.di_projid != prid) {
 			xfs_iunlock(ip, lockflags);
-			error = xfs_qm_dqget(mp, (xfs_dqid_t)prid,
+			error = xfs_qm_dqget(mp, prid,
 					XFS_DQTYPE_PROJ, true, &pq);
 			if (error) {
 				ASSERT(error != -ENOENT);
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index ca93b6488377..7529eb63ce94 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -424,7 +424,7 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
 STATIC int
 xfs_cui_item_recover(
 	struct xfs_log_item		*lip,
-	struct xfs_trans		*parent_tp)
+	struct list_head		*capture_list)
 {
 	struct xfs_bmbt_irec		irec;
 	struct xfs_cui_log_item		*cuip = CUI_ITEM(lip);
@@ -432,7 +432,7 @@ xfs_cui_item_recover(
 	struct xfs_cud_log_item		*cudp;
 	struct xfs_trans		*tp;
 	struct xfs_btree_cur		*rcur = NULL;
-	struct xfs_mount		*mp = parent_tp->t_mountp;
+	struct xfs_mount		*mp = lip->li_mountp;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			new_fsb;
 	xfs_extlen_t			new_len;
@@ -467,14 +467,8 @@ xfs_cui_item_recover(
 		    refc->pe_len == 0 ||
 		    startblock_fsb >= mp->m_sb.sb_dblocks ||
 		    refc->pe_len >= mp->m_sb.sb_agblocks ||
-		    (refc->pe_flags & ~XFS_REFCOUNT_EXTENT_FLAGS)) {
-			/*
-			 * This will pull the CUI from the AIL and
-			 * free the memory associated with it.
-			 */
-			xfs_cui_release(cuip);
+		    (refc->pe_flags & ~XFS_REFCOUNT_EXTENT_FLAGS))
 			return -EFSCORRUPTED;
-		}
 	}
 
 	/*
@@ -493,12 +487,7 @@ xfs_cui_item_recover(
 			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-	/*
-	 * Recovery stashes all deferred ops during intent processing and
-	 * finishes them on completion. Transfer current dfops state to this
-	 * transaction and transfer the result back before we return.
-	 */
-	xfs_defer_move(tp, parent_tp);
+
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -555,13 +544,10 @@ xfs_cui_item_recover(
 	}
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
-	xfs_defer_move(parent_tp, tp);
-	error = xfs_trans_commit(tp);
-	return error;
+	return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
-	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -574,6 +560,32 @@ xfs_cui_item_match(
 	return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_cui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_cud_log_item		*cudp;
+	struct xfs_cui_log_item		*cuip;
+	struct xfs_phys_extent		*extp;
+	unsigned int			count;
+
+	count = CUI_ITEM(intent)->cui_format.cui_nextents;
+	extp = CUI_ITEM(intent)->cui_format.cui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	cudp = xfs_trans_get_cud(tp, CUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
+
+	cuip = xfs_cui_init(tp->t_mountp, count);
+	memcpy(cuip->cui_format.cui_extents, extp, count * sizeof(*extp));
+	atomic_set(&cuip->cui_next_extent, count);
+	xfs_trans_add_item(tp, &cuip->cui_item);
+	set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
+	return &cuip->cui_item;
+}
+
 static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_size	= xfs_cui_item_size,
 	.iop_format	= xfs_cui_item_format,
@@ -581,6 +593,7 @@ static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_release	= xfs_cui_item_release,
 	.iop_recover	= xfs_cui_item_recover,
 	.iop_match	= xfs_cui_item_match,
+	.iop_relog	= xfs_cui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index dc5b0753cd51..7adc996ca6e3 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -467,14 +467,14 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
 STATIC int
 xfs_rui_item_recover(
 	struct xfs_log_item		*lip,
-	struct xfs_trans		*parent_tp)
+	struct list_head		*capture_list)
 {
 	struct xfs_rui_log_item		*ruip = RUI_ITEM(lip);
 	struct xfs_map_extent		*rmap;
 	struct xfs_rud_log_item		*rudp;
 	struct xfs_trans		*tp;
 	struct xfs_btree_cur		*rcur = NULL;
-	struct xfs_mount		*mp = parent_tp->t_mountp;
+	struct xfs_mount		*mp = lip->li_mountp;
 	xfs_fsblock_t			startblock_fsb;
 	enum xfs_rmap_intent_type	type;
 	xfs_exntst_t			state;
@@ -511,14 +511,8 @@ xfs_rui_item_recover(
 		    rmap->me_len == 0 ||
 		    startblock_fsb >= mp->m_sb.sb_dblocks ||
 		    rmap->me_len >= mp->m_sb.sb_agblocks ||
-		    (rmap->me_flags & ~XFS_RMAP_EXTENT_FLAGS)) {
-			/*
-			 * This will pull the RUI from the AIL and
-			 * free the memory associated with it.
-			 */
-			xfs_rui_release(ruip);
+		    (rmap->me_flags & ~XFS_RMAP_EXTENT_FLAGS))
 			return -EFSCORRUPTED;
-		}
 	}
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
@@ -573,8 +567,7 @@ xfs_rui_item_recover(
 	}
 
 	xfs_rmap_finish_one_cleanup(tp, rcur, error);
-	error = xfs_trans_commit(tp);
-	return error;
+	return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
 
 abort_error:
 	xfs_rmap_finish_one_cleanup(tp, rcur, error);
@@ -590,6 +583,32 @@ xfs_rui_item_match(
 	return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_rui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_rud_log_item		*rudp;
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_map_extent		*extp;
+	unsigned int			count;
+
+	count = RUI_ITEM(intent)->rui_format.rui_nextents;
+	extp = RUI_ITEM(intent)->rui_format.rui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
+
+	ruip = xfs_rui_init(tp->t_mountp, count);
+	memcpy(ruip->rui_format.rui_extents, extp, count * sizeof(*extp));
+	atomic_set(&ruip->rui_next_extent, count);
+	xfs_trans_add_item(tp, &ruip->rui_item);
+	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
+	return &ruip->rui_item;
+}
+
 static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_size	= xfs_rui_item_size,
 	.iop_format	= xfs_rui_item_format,
@@ -597,6 +616,7 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_release	= xfs_rui_item_release,
 	.iop_recover	= xfs_rui_item_recover,
 	.iop_match	= xfs_rui_item_match,
+	.iop_relog	= xfs_rui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 5b89c12f1566..ede1baf31413 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -18,7 +18,7 @@
 #include "xfs_trans_space.h"
 #include "xfs_icache.h"
 #include "xfs_rtalloc.h"
-
+#include "xfs_sb.h"
 
 /*
  * Read and return the summary information for a given extent size,
@@ -778,8 +778,14 @@ xfs_growfs_rt_alloc(
 	struct xfs_bmbt_irec	map;		/* block map output */
 	int			nmap;		/* number of block maps */
 	int			resblks;	/* space reservation */
+	enum xfs_blft		buf_type;
 	struct xfs_trans	*tp;
 
+	if (ip == mp->m_rsumip)
+		buf_type = XFS_BLFT_RTSUMMARY_BUF;
+	else
+		buf_type = XFS_BLFT_RTBITMAP_BUF;
+
 	/*
 	 * Allocate space to the file, as necessary.
 	 */
@@ -841,6 +847,9 @@ xfs_growfs_rt_alloc(
 					mp->m_bsize, 0, &bp);
 			if (error)
 				goto out_trans_cancel;
+
+			xfs_trans_buf_set_type(tp, bp, buf_type);
+			bp->b_ops = &xfs_rtbuf_ops;
 			memset(bp->b_addr, 0, mp->m_sb.sb_blocksize);
 			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
 			/*
@@ -1015,23 +1024,29 @@ xfs_growfs_rt(
 		/*
 		 * Lock out other callers by grabbing the bitmap inode lock.
 		 */
-		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
 		xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
 		/*
-		 * Update the bitmap inode's size.
+		 * Update the bitmap inode's size ondisk and incore.  We need
+		 * to update the incore size so that inode inactivation won't
+		 * punch what it thinks are "posteof" blocks.
 		 */
 		mp->m_rbmip->i_d.di_size =
 			nsbp->sb_rbmblocks * nsbp->sb_blocksize;
+		i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_d.di_size);
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 		/*
 		 * Get the summary inode into the transaction.
 		 */
-		xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL);
+		xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
 		xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
 		/*
-		 * Update the summary inode's size.
+		 * Update the summary inode's size.  We need to update the
+		 * incore size so that inode inactivation won't punch what it
+		 * thinks are "posteof" blocks.
 		 */
 		mp->m_rsumip->i_d.di_size = nmp->m_rsumsize;
+		i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_d.di_size);
 		xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE);
 		/*
 		 * Copy summary data from old to new sizes.
@@ -1087,7 +1102,13 @@ error_cancel:
 		if (error)
 			break;
 	}
+	if (error)
+		goto out_free;
+
+	/* Update secondary superblocks now the physical grow has completed */
+	error = xfs_update_secondary_sbs(mp);
 
+out_free:
 	/*
 	 * Free the fake mp structure.
 	 */
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index f70f1255220b..20e0534a772c 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -23,6 +23,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 	uint64_t	xs_xstrat_bytes = 0;
 	uint64_t	xs_write_bytes = 0;
 	uint64_t	xs_read_bytes = 0;
+	uint64_t	defer_relog = 0;
 
 	static const struct xstats_entry {
 		char	*desc;
@@ -70,10 +71,13 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		xs_xstrat_bytes += per_cpu_ptr(stats, i)->s.xs_xstrat_bytes;
 		xs_write_bytes += per_cpu_ptr(stats, i)->s.xs_write_bytes;
 		xs_read_bytes += per_cpu_ptr(stats, i)->s.xs_read_bytes;
+		defer_relog += per_cpu_ptr(stats, i)->s.defer_relog;
 	}
 
 	len += scnprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n",
 			xs_xstrat_bytes, xs_write_bytes, xs_read_bytes);
+	len += scnprintf(buf + len, PATH_MAX-len, "defer_relog %llu\n",
+			defer_relog);
 	len += scnprintf(buf + len, PATH_MAX-len, "debug %u\n",
 #if defined(DEBUG)
 		1);
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 34d704f703d2..43ffba74f045 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -137,6 +137,7 @@ struct __xfsstats {
 	uint64_t		xs_xstrat_bytes;
 	uint64_t		xs_write_bytes;
 	uint64_t		xs_read_bytes;
+	uint64_t		defer_relog;
 };
 
 #define	xfsstats_offset(f)	(offsetof(struct __xfsstats, f)/sizeof(uint32_t))
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index baf5de30eebb..d1b5f2d2a245 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1234,25 +1234,12 @@ xfs_fc_parse_param(
 	case Opt_nouuid:
 		mp->m_flags |= XFS_MOUNT_NOUUID;
 		return 0;
-	case Opt_ikeep:
-		mp->m_flags |= XFS_MOUNT_IKEEP;
-		return 0;
-	case Opt_noikeep:
-		mp->m_flags &= ~XFS_MOUNT_IKEEP;
-		return 0;
 	case Opt_largeio:
 		mp->m_flags |= XFS_MOUNT_LARGEIO;
 		return 0;
 	case Opt_nolargeio:
 		mp->m_flags &= ~XFS_MOUNT_LARGEIO;
 		return 0;
-	case Opt_attr2:
-		mp->m_flags |= XFS_MOUNT_ATTR2;
-		return 0;
-	case Opt_noattr2:
-		mp->m_flags &= ~XFS_MOUNT_ATTR2;
-		mp->m_flags |= XFS_MOUNT_NOATTR2;
-		return 0;
 	case Opt_filestreams:
 		mp->m_flags |= XFS_MOUNT_FILESTREAMS;
 		return 0;
@@ -1304,6 +1291,24 @@ xfs_fc_parse_param(
 		xfs_mount_set_dax_mode(mp, result.uint_32);
 		return 0;
 #endif
+	/* Following mount options will be removed in September 2025 */
+	case Opt_ikeep:
+		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		mp->m_flags |= XFS_MOUNT_IKEEP;
+		return 0;
+	case Opt_noikeep:
+		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		mp->m_flags &= ~XFS_MOUNT_IKEEP;
+		return 0;
+	case Opt_attr2:
+		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		mp->m_flags |= XFS_MOUNT_ATTR2;
+		return 0;
+	case Opt_noattr2:
+		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		mp->m_flags &= ~XFS_MOUNT_ATTR2;
+		mp->m_flags |= XFS_MOUNT_NOATTR2;
+		return 0;
 	default:
 		xfs_warn(mp, "unknown mount option [%s].", param->key);
 		return -EINVAL;
@@ -1450,6 +1455,19 @@ xfs_fc_fill_super(
 	if (error)
 		goto out_free_sb;
 
+	/* V4 support is undergoing deprecation. */
+	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
+#ifdef CONFIG_XFS_SUPPORT_V4
+		xfs_warn_once(mp,
+	"Deprecated V4 format (crc=0) will not be supported after September 2030.");
+#else
+		xfs_warn(mp,
+	"Deprecated V4 format (crc=0) not supported by kernel.");
+		error = -EINVAL;
+		goto out_free_sb;
+#endif
+	}
+
 	/*
 	 * XFS block mappings use 54 bits to store the logical block offset.
 	 * This should suffice to handle the maximum file size that the VFS
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 021ef96d0542..fac9de7ee6d0 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -50,13 +50,45 @@ xfs_panic_mask_proc_handler(
 }
 #endif /* CONFIG_PROC_FS */
 
+STATIC int
+xfs_deprecate_irix_sgid_inherit_proc_handler(
+	struct ctl_table	*ctl,
+	int			write,
+	void			*buffer,
+	size_t			*lenp,
+	loff_t			*ppos)
+{
+	if (write) {
+		printk_once(KERN_WARNING
+				"XFS: " "%s sysctl option is deprecated.\n",
+				ctl->procname);
+	}
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
+STATIC int
+xfs_deprecate_irix_symlink_mode_proc_handler(
+	struct ctl_table	*ctl,
+	int			write,
+	void			*buffer,
+	size_t			*lenp,
+	loff_t			*ppos)
+{
+	if (write) {
+		printk_once(KERN_WARNING
+				"XFS: " "%s sysctl option is deprecated.\n",
+				ctl->procname);
+	}
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
 static struct ctl_table xfs_table[] = {
 	{
 		.procname	= "irix_sgid_inherit",
 		.data		= &xfs_params.sgid_inherit.val,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= xfs_deprecate_irix_sgid_inherit_proc_handler,
 		.extra1		= &xfs_params.sgid_inherit.min,
 		.extra2		= &xfs_params.sgid_inherit.max
 	},
@@ -65,7 +97,7 @@ static struct ctl_table xfs_table[] = {
 		.data		= &xfs_params.symlink_mode.val,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= xfs_deprecate_irix_symlink_mode_proc_handler,
 		.extra1		= &xfs_params.symlink_mode.min,
 		.extra2		= &xfs_params.symlink_mode.max
 	},
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index dcdcf99cfa5d..86951652d3ed 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2533,6 +2533,7 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent);
 
 #define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index ca18a040336a..c94e71f741b6 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -959,7 +959,7 @@ xfs_trans_cancel(
 		struct xfs_log_item *lip;
 
 		list_for_each_entry(lip, &tp->t_items, li_trans)
-			ASSERT(!(lip->li_type == XFS_LI_EFD));
+			ASSERT(!xlog_item_is_intent_done(lip));
 	}
 #endif
 	xfs_trans_unreserve_and_mod_sb(tp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f46534b75236..084658946cc8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -55,14 +55,12 @@ struct xfs_log_item {
 #define	XFS_LI_ABORTED	1
 #define	XFS_LI_FAILED	2
 #define	XFS_LI_DIRTY	3	/* log item dirty in transaction */
-#define	XFS_LI_RECOVERED 4	/* log intent item has been recovered */
 
 #define XFS_LI_FLAGS \
 	{ (1 << XFS_LI_IN_AIL),		"IN_AIL" }, \
 	{ (1 << XFS_LI_ABORTED),	"ABORTED" }, \
 	{ (1 << XFS_LI_FAILED),		"FAILED" }, \
-	{ (1 << XFS_LI_DIRTY),		"DIRTY" }, \
-	{ (1 << XFS_LI_RECOVERED),	"RECOVERED" }
+	{ (1 << XFS_LI_DIRTY),		"DIRTY" }
 
 struct xfs_item_ops {
 	unsigned flags;
@@ -74,10 +72,29 @@ struct xfs_item_ops {
 	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);
-	int (*iop_recover)(struct xfs_log_item *lip, struct xfs_trans *tp);
+	int (*iop_recover)(struct xfs_log_item *lip,
+			   struct list_head *capture_list);
 	bool (*iop_match)(struct xfs_log_item *item, uint64_t id);
+	struct xfs_log_item *(*iop_relog)(struct xfs_log_item *intent,
+			struct xfs_trans *tp);
 };
 
+/* Is this log item a deferred action intent? */
+static inline bool
+xlog_item_is_intent(struct xfs_log_item *lip)
+{
+	return lip->li_ops->iop_recover != NULL &&
+	       lip->li_ops->iop_match != NULL;
+}
+
+/* Is this a log intent-done item? */
+static inline bool
+xlog_item_is_intent_done(struct xfs_log_item *lip)
+{
+	return lip->li_ops->iop_unpin == NULL &&
+	       lip->li_ops->iop_push == NULL;
+}
+
 /*
  * Release the log item as soon as committed.  This is for items just logging
  * intents that never need to be written back in place.
@@ -243,4 +260,12 @@ void		xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
 
 extern kmem_zone_t	*xfs_trans_zone;
 
+static inline struct xfs_log_item *
+xfs_trans_item_relog(
+	struct xfs_log_item	*lip,
+	struct xfs_trans	*tp)
+{
+	return lip->li_ops->iop_relog(lip, tp);
+}
+
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 133fc6fc3edd..fe45b0c3970c 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -221,36 +221,27 @@ xfs_trans_mod_dquot(
 	}
 
 	switch (field) {
-
-		/*
-		 * regular disk blk reservation
-		 */
-	      case XFS_TRANS_DQ_RES_BLKS:
+	/* regular disk blk reservation */
+	case XFS_TRANS_DQ_RES_BLKS:
 		qtrx->qt_blk_res += delta;
 		break;
 
-		/*
-		 * inode reservation
-		 */
-	      case XFS_TRANS_DQ_RES_INOS:
+	/* inode reservation */
+	case XFS_TRANS_DQ_RES_INOS:
 		qtrx->qt_ino_res += delta;
 		break;
 
-		/*
-		 * disk blocks used.
-		 */
-	      case XFS_TRANS_DQ_BCOUNT:
+	/* disk blocks used. */
+	case XFS_TRANS_DQ_BCOUNT:
 		qtrx->qt_bcount_delta += delta;
 		break;
 
-	      case XFS_TRANS_DQ_DELBCOUNT:
+	case XFS_TRANS_DQ_DELBCOUNT:
 		qtrx->qt_delbcnt_delta += delta;
 		break;
 
-		/*
-		 * Inode Count
-		 */
-	      case XFS_TRANS_DQ_ICOUNT:
+	/* Inode Count */
+	case XFS_TRANS_DQ_ICOUNT:
 		if (qtrx->qt_ino_res && delta > 0) {
 			qtrx->qt_ino_res_used += delta;
 			ASSERT(qtrx->qt_ino_res >= qtrx->qt_ino_res_used);
@@ -258,17 +249,13 @@ xfs_trans_mod_dquot(
 		qtrx->qt_icount_delta += delta;
 		break;
 
-		/*
-		 * rtblk reservation
-		 */
-	      case XFS_TRANS_DQ_RES_RTBLKS:
+	/* rtblk reservation */
+	case XFS_TRANS_DQ_RES_RTBLKS:
 		qtrx->qt_rtblk_res += delta;
 		break;
 
-		/*
-		 * rtblk count
-		 */
-	      case XFS_TRANS_DQ_RTBCOUNT:
+	/* rtblk count */
+	case XFS_TRANS_DQ_RTBCOUNT:
 		if (qtrx->qt_rtblk_res && delta > 0) {
 			qtrx->qt_rtblk_res_used += delta;
 			ASSERT(qtrx->qt_rtblk_res >= qtrx->qt_rtblk_res_used);
@@ -276,11 +263,11 @@ xfs_trans_mod_dquot(
 		qtrx->qt_rtbcount_delta += delta;
 		break;
 
-	      case XFS_TRANS_DQ_DELRTBCOUNT:
+	case XFS_TRANS_DQ_DELRTBCOUNT:
 		qtrx->qt_delrtb_delta += delta;
 		break;
 
-	      default:
+	default:
 		ASSERT(0);
 	}