Merge tag 'xfs-6.5-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:

 - Fix some ordering problems with log items during log recovery

 - Don't deadlock the system by trying to flush busy freed extents while
   holding on to busy freed extents

 - Improve validation of log geometry parameters when reading the
   primary superblock

 - Validate the length field in the AGF header

 - Fix recordset filtering bugs when re-calling GETFSMAP to return more
   results when the resultset didn't previously fit in the caller's
   buffer

 - Fix integer overflows in GETFSMAP when working with rt volumes larger
   than 2^32 fsblocks

 - Fix GETFSMAP reporting the undefined space beyond the last rtextent

 - Fix filtering bugs in GETFSMAP's log device backend if the log ever
   becomes longer than 2^32 fsblocks

 - Improve validation of file offsets in the GETFSMAP range parameters

 - Fix an off by one bug in the pmem media failure notification
   computation

 - Validate the length field in the AGI header too

* tag 'xfs-6.5-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: Remove unneeded semicolon
  xfs: AGI length should be bounds checked
  xfs: fix the calculation for "end" and "length"
  xfs: fix xfs_btree_query_range callers to initialize btree rec fully
  xfs: validate fsmap offsets specified in the query keys
  xfs: fix logdev fsmap query result filtering
  xfs: clean up the rtbitmap fsmap backend
  xfs: fix getfsmap reporting past the last rt extent
  xfs: fix integer overflows in the fsmap rtbitmap and logdev backends
  xfs: fix interval filtering in multi-step fsmap queries
  xfs: fix bounds check in xfs_defer_agfl_block()
  xfs: AGF length has never been bounds checked
  xfs: journal geometry is not properly bounds checked
  xfs: don't block in busy flushing when freeing extents
  xfs: allow extent free intents to be retried
  xfs: pass alloc flags through to xfs_extent_busy_flush()
  xfs: use deferred frees for btree block freeing
  xfs: don't reverse order of items in bulk AIL insertion
  xfs: remove redundant initializations of pointers drop_leaf and save_leaf

21 files changed, 586 insertions, 331 deletions

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index ee84835ebc66..e9cc481b4ddf 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -985,7 +985,7 @@ xfs_ag_shrink_space(
 			goto resv_err;
 
 		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
-				true);
+				XFS_AG_RESV_NONE, true);
 		if (err2)
 			goto resv_err;
 
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index c20fe99405d8..3069194527dd 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1536,7 +1536,8 @@ xfs_alloc_ag_vextent_lastblock(
  */
 STATIC int
 xfs_alloc_ag_vextent_near(
-	struct xfs_alloc_arg	*args)
+	struct xfs_alloc_arg	*args,
+	uint32_t		alloc_flags)
 {
 	struct xfs_alloc_cur	acur = {};
 	int			error;		/* error code */
@@ -1555,6 +1556,8 @@ xfs_alloc_ag_vextent_near(
 	if (args->agbno > args->max_agbno)
 		args->agbno = args->max_agbno;
 
+	/* Retry once quickly if we find busy extents before blocking. */
+	alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
 restart:
 	len = 0;
 
@@ -1610,9 +1613,20 @@ restart:
 	 */
 	if (!acur.len) {
 		if (acur.busy) {
+			/*
+			 * Our only valid extents must have been busy. Flush and
+			 * retry the allocation again. If we get an -EAGAIN
+			 * error, we're being told that a deadlock was avoided
+			 * and the current transaction needs committing before
+			 * the allocation can be retried.
+			 */
 			trace_xfs_alloc_near_busy(args);
-			xfs_extent_busy_flush(args->mp, args->pag,
-					      acur.busy_gen);
+			error = xfs_extent_busy_flush(args->tp, args->pag,
+					acur.busy_gen, alloc_flags);
+			if (error)
+				goto out;
+
+			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
 			goto restart;
 		}
 		trace_xfs_alloc_size_neither(args);
@@ -1635,22 +1649,25 @@ out:
  * and of the form k * prod + mod unless there's nothing that large.
  * Return the starting a.g. block, or NULLAGBLOCK if we can't do it.
  */
-STATIC int				/* error */
+static int
 xfs_alloc_ag_vextent_size(
-	xfs_alloc_arg_t	*args)		/* allocation argument structure */
+	struct xfs_alloc_arg	*args,
+	uint32_t		alloc_flags)
 {
-	struct xfs_agf	*agf = args->agbp->b_addr;
-	struct xfs_btree_cur *bno_cur;	/* cursor for bno btree */
-	struct xfs_btree_cur *cnt_cur;	/* cursor for cnt btree */
-	int		error;		/* error result */
-	xfs_agblock_t	fbno;		/* start of found freespace */
-	xfs_extlen_t	flen;		/* length of found freespace */
-	int		i;		/* temp status variable */
-	xfs_agblock_t	rbno;		/* returned block number */
-	xfs_extlen_t	rlen;		/* length of returned extent */
-	bool		busy;
-	unsigned	busy_gen;
+	struct xfs_agf		*agf = args->agbp->b_addr;
+	struct xfs_btree_cur	*bno_cur;
+	struct xfs_btree_cur	*cnt_cur;
+	xfs_agblock_t		fbno;		/* start of found freespace */
+	xfs_extlen_t		flen;		/* length of found freespace */
+	xfs_agblock_t		rbno;		/* returned block number */
+	xfs_extlen_t		rlen;		/* length of returned extent */
+	bool			busy;
+	unsigned		busy_gen;
+	int			error;
+	int			i;
 
+	/* Retry once quickly if we find busy extents before blocking. */
+	alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
 restart:
 	/*
 	 * Allocate and initialize a cursor for the by-size btree.
@@ -1708,19 +1725,25 @@ restart:
 			error = xfs_btree_increment(cnt_cur, 0, &i);
 			if (error)
 				goto error0;
-			if (i == 0) {
-				/*
-				 * Our only valid extents must have been busy.
-				 * Make it unbusy by forcing the log out and
-				 * retrying.
-				 */
-				xfs_btree_del_cursor(cnt_cur,
-						     XFS_BTREE_NOERROR);
-				trace_xfs_alloc_size_busy(args);
-				xfs_extent_busy_flush(args->mp,
-							args->pag, busy_gen);
-				goto restart;
-			}
+			if (i)
+				continue;
+
+			/*
+			 * Our only valid extents must have been busy. Flush and
+			 * retry the allocation again. If we get an -EAGAIN
+			 * error, we're being told that a deadlock was avoided
+			 * and the current transaction needs committing before
+			 * the allocation can be retried.
+			 */
+			trace_xfs_alloc_size_busy(args);
+			error = xfs_extent_busy_flush(args->tp, args->pag,
+					busy_gen, alloc_flags);
+			if (error)
+				goto error0;
+
+			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
+			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+			goto restart;
 		}
 	}
 
@@ -1800,9 +1823,21 @@ restart:
 	args->len = rlen;
 	if (rlen < args->minlen) {
 		if (busy) {
-			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+			/*
+			 * Our only valid extents must have been busy. Flush and
+			 * retry the allocation again. If we get an -EAGAIN
+			 * error, we're being told that a deadlock was avoided
+			 * and the current transaction needs committing before
+			 * the allocation can be retried.
+			 */
 			trace_xfs_alloc_size_busy(args);
-			xfs_extent_busy_flush(args->mp, args->pag, busy_gen);
+			error = xfs_extent_busy_flush(args->tp, args->pag,
+					busy_gen, alloc_flags);
+			if (error)
+				goto error0;
+
+			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
+			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 			goto restart;
 		}
 		goto out_nominleft;
@@ -2435,23 +2470,25 @@ static int
 xfs_defer_agfl_block(
 	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
-	xfs_fsblock_t			agbno,
+	xfs_agblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_extent_free_item	*xefi;
+	xfs_fsblock_t			fsbno = XFS_AGB_TO_FSB(mp, agno, agbno);
 
 	ASSERT(xfs_extfree_item_cache != NULL);
 	ASSERT(oinfo != NULL);
 
+	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno)))
+		return -EFSCORRUPTED;
+
 	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
 			       GFP_KERNEL | __GFP_NOFAIL);
-	xefi->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
+	xefi->xefi_startblock = fsbno;
 	xefi->xefi_blockcount = 1;
 	xefi->xefi_owner = oinfo->oi_owner;
-
-	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock)))
-		return -EFSCORRUPTED;
+	xefi->xefi_agresv = XFS_AG_RESV_AGFL;
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
@@ -2470,6 +2507,7 @@ __xfs_free_extent_later(
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type,
 	bool				skip_discard)
 {
 	struct xfs_extent_free_item	*xefi;
@@ -2490,6 +2528,7 @@ __xfs_free_extent_later(
 	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
 #endif
 	ASSERT(xfs_extfree_item_cache != NULL);
+	ASSERT(type != XFS_AG_RESV_AGFL);
 
 	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
 		return -EFSCORRUPTED;
@@ -2498,6 +2537,7 @@ __xfs_free_extent_later(
 			       GFP_KERNEL | __GFP_NOFAIL);
 	xefi->xefi_startblock = bno;
 	xefi->xefi_blockcount = (xfs_extlen_t)len;
+	xefi->xefi_agresv = type;
 	if (skip_discard)
 		xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
 	if (oinfo) {
@@ -2568,7 +2608,7 @@ out:
 int			/* error */
 xfs_alloc_fix_freelist(
 	struct xfs_alloc_arg	*args,	/* allocation argument structure */
-	int			flags)	/* XFS_ALLOC_FLAG_... */
+	uint32_t		alloc_flags)
 {
 	struct xfs_mount	*mp = args->mp;
 	struct xfs_perag	*pag = args->pag;
@@ -2584,7 +2624,7 @@ xfs_alloc_fix_freelist(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	if (!xfs_perag_initialised_agf(pag)) {
-		error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
+		error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
 		if (error) {
 			/* Couldn't lock the AGF so skip this AG. */
 			if (error == -EAGAIN)
@@ -2600,13 +2640,13 @@ xfs_alloc_fix_freelist(
 	 */
 	if (xfs_perag_prefers_metadata(pag) &&
 	    (args->datatype & XFS_ALLOC_USERDATA) &&
-	    (flags & XFS_ALLOC_FLAG_TRYLOCK)) {
-		ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
+	    (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) {
+		ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING));
 		goto out_agbp_relse;
 	}
 
 	need = xfs_alloc_min_freelist(mp, pag);
-	if (!xfs_alloc_space_available(args, need, flags |
+	if (!xfs_alloc_space_available(args, need, alloc_flags |
 			XFS_ALLOC_FLAG_CHECK))
 		goto out_agbp_relse;
 
@@ -2615,7 +2655,7 @@ xfs_alloc_fix_freelist(
 	 * Can fail if we're not blocking on locks, and it's held.
 	 */
 	if (!agbp) {
-		error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
+		error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
 		if (error) {
 			/* Couldn't lock the AGF so skip this AG. */
 			if (error == -EAGAIN)
@@ -2630,7 +2670,7 @@ xfs_alloc_fix_freelist(
 
 	/* If there isn't enough total space or single-extent, reject it. */
 	need = xfs_alloc_min_freelist(mp, pag);
-	if (!xfs_alloc_space_available(args, need, flags))
+	if (!xfs_alloc_space_available(args, need, alloc_flags))
 		goto out_agbp_relse;
 
 #ifdef DEBUG
@@ -2668,11 +2708,12 @@ xfs_alloc_fix_freelist(
 	 */
 	memset(&targs, 0, sizeof(targs));
 	/* struct copy below */
-	if (flags & XFS_ALLOC_FLAG_NORMAP)
+	if (alloc_flags & XFS_ALLOC_FLAG_NORMAP)
 		targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
 	else
 		targs.oinfo = XFS_RMAP_OINFO_AG;
-	while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) {
+	while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) &&
+			pag->pagf_flcount > need) {
 		error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0);
 		if (error)
 			goto out_agbp_relse;
@@ -2700,7 +2741,7 @@ xfs_alloc_fix_freelist(
 		targs.resv = XFS_AG_RESV_AGFL;
 
 		/* Allocate as many blocks as possible at once. */
-		error = xfs_alloc_ag_vextent_size(&targs);
+		error = xfs_alloc_ag_vextent_size(&targs, alloc_flags);
 		if (error)
 			goto out_agflbp_relse;
 
@@ -2710,7 +2751,7 @@ xfs_alloc_fix_freelist(
 		 * on a completely full ag.
 		 */
 		if (targs.agbno == NULLAGBLOCK) {
-			if (flags & XFS_ALLOC_FLAG_FREEING)
+			if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
 				break;
 			goto out_agflbp_relse;
 		}
@@ -2916,6 +2957,47 @@ xfs_alloc_put_freelist(
 }
 
 /*
+ * Check that this AGF/AGI header's sequence number and length matches the AG
+ * number and size in fsblocks.
+ */
+xfs_failaddr_t
+xfs_validate_ag_length(
+	struct xfs_buf		*bp,
+	uint32_t		seqno,
+	uint32_t		length)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	/*
+	 * During growfs operations, the perag is not fully initialised,
+	 * so we can't use it for any useful checking. growfs ensures we can't
+	 * use it by using uncached buffers that don't have the perag attached
+	 * so we can detect and avoid this problem.
+	 */
+	if (bp->b_pag && seqno != bp->b_pag->pag_agno)
+		return __this_address;
+
+	/*
+	 * Only the last AG in the filesystem is allowed to be shorter
+	 * than the AG size recorded in the superblock.
+	 */
+	if (length != mp->m_sb.sb_agblocks) {
+		/*
+		 * During growfs, the new last AG can get here before we
+		 * have updated the superblock. Give it a pass on the seqno
+		 * check.
+		 */
+		if (bp->b_pag && seqno != mp->m_sb.sb_agcount - 1)
+			return __this_address;
+		if (length < XFS_MIN_AG_BLOCKS)
+			return __this_address;
+		if (length > mp->m_sb.sb_agblocks)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
+/*
  * Verify the AGF is consistent.
  *
  * We do not verify the AGFL indexes in the AGF are fully consistent here
@@ -2934,6 +3016,9 @@ xfs_agf_verify(
 {
 	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_agf		*agf = bp->b_addr;
+	xfs_failaddr_t		fa;
+	uint32_t		agf_seqno = be32_to_cpu(agf->agf_seqno);
+	uint32_t		agf_length = be32_to_cpu(agf->agf_length);
 
 	if (xfs_has_crc(mp)) {
 		if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid))
@@ -2945,18 +3030,26 @@ xfs_agf_verify(
 	if (!xfs_verify_magic(bp, agf->agf_magicnum))
 		return __this_address;
 
-	if (!(XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
-	      be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
-	      be32_to_cpu(agf->agf_flfirst) < xfs_agfl_size(mp) &&
-	      be32_to_cpu(agf->agf_fllast) < xfs_agfl_size(mp) &&
-	      be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)))
+	if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)))
 		return __this_address;
 
-	if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks)
+	/*
+	 * Both agf_seqno and agf_length need to validated before anything else
+	 * block number related in the AGF or AGFL can be checked.
+	 */
+	fa = xfs_validate_ag_length(bp, agf_seqno, agf_length);
+	if (fa)
+		return fa;
+
+	if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp))
+		return __this_address;
+	if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp))
+		return __this_address;
+	if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp))
 		return __this_address;
 
 	if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
-	    be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))
+	    be32_to_cpu(agf->agf_freeblks) > agf_length)
 		return __this_address;
 
 	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
@@ -2967,38 +3060,28 @@ xfs_agf_verify(
 						mp->m_alloc_maxlevels)
 		return __this_address;
 
-	if (xfs_has_rmapbt(mp) &&
-	    (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
-	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
-						mp->m_rmap_maxlevels))
-		return __this_address;
-
-	if (xfs_has_rmapbt(mp) &&
-	    be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length))
+	if (xfs_has_lazysbcount(mp) &&
+	    be32_to_cpu(agf->agf_btreeblks) > agf_length)
 		return __this_address;
 
-	/*
-	 * during growfs operations, the perag is not fully initialised,
-	 * so we can't use it for any useful checking. growfs ensures we can't
-	 * use it by using uncached buffers that don't have the perag attached
-	 * so we can detect and avoid this problem.
-	 */
-	if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno)
-		return __this_address;
+	if (xfs_has_rmapbt(mp)) {
+		if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length)
+			return __this_address;
 
-	if (xfs_has_lazysbcount(mp) &&
-	    be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length))
-		return __this_address;
+		if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
+		    be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
+							mp->m_rmap_maxlevels)
+			return __this_address;
+	}
 
-	if (xfs_has_reflink(mp) &&
-	    be32_to_cpu(agf->agf_refcount_blocks) >
-	    be32_to_cpu(agf->agf_length))
-		return __this_address;
+	if (xfs_has_reflink(mp)) {
+		if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length)
+			return __this_address;
 
-	if (xfs_has_reflink(mp) &&
-	    (be32_to_cpu(agf->agf_refcount_level) < 1 ||
-	     be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels))
-		return __this_address;
+		if (be32_to_cpu(agf->agf_refcount_level) < 1 ||
+		    be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels)
+			return __this_address;
+	}
 
 	return NULL;
 }
@@ -3226,7 +3309,7 @@ xfs_alloc_vextent_check_args(
 static int
 xfs_alloc_vextent_prepare_ag(
 	struct xfs_alloc_arg	*args,
-	uint32_t		flags)
+	uint32_t		alloc_flags)
 {
 	bool			need_pag = !args->pag;
 	int			error;
@@ -3235,7 +3318,7 @@ xfs_alloc_vextent_prepare_ag(
 		args->pag = xfs_perag_get(args->mp, args->agno);
 
 	args->agbp = NULL;
-	error = xfs_alloc_fix_freelist(args, flags);
+	error = xfs_alloc_fix_freelist(args, alloc_flags);
 	if (error) {
 		trace_xfs_alloc_vextent_nofix(args);
 		if (need_pag)
@@ -3357,6 +3440,7 @@ xfs_alloc_vextent_this_ag(
 {
 	struct xfs_mount	*mp = args->mp;
 	xfs_agnumber_t		minimum_agno;
+	uint32_t		alloc_flags = 0;
 	int			error;
 
 	ASSERT(args->pag != NULL);
@@ -3375,9 +3459,9 @@ xfs_alloc_vextent_this_ag(
 		return error;
 	}
 
-	error = xfs_alloc_vextent_prepare_ag(args, 0);
+	error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
 	if (!error && args->agbp)
-		error = xfs_alloc_ag_vextent_size(args);
+		error = xfs_alloc_ag_vextent_size(args, alloc_flags);
 
 	return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
 }
@@ -3406,20 +3490,20 @@ xfs_alloc_vextent_iterate_ags(
 	xfs_agnumber_t		minimum_agno,
 	xfs_agnumber_t		start_agno,
 	xfs_agblock_t		target_agbno,
-	uint32_t		flags)
+	uint32_t		alloc_flags)
 {
 	struct xfs_mount	*mp = args->mp;
 	xfs_agnumber_t		restart_agno = minimum_agno;
 	xfs_agnumber_t		agno;
 	int			error = 0;
 
-	if (flags & XFS_ALLOC_FLAG_TRYLOCK)
+	if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)
 		restart_agno = 0;
 restart:
 	for_each_perag_wrap_range(mp, start_agno, restart_agno,
 			mp->m_sb.sb_agcount, agno, args->pag) {
 		args->agno = agno;
-		error = xfs_alloc_vextent_prepare_ag(args, flags);
+		error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
 		if (error)
 			break;
 		if (!args->agbp) {
@@ -3433,10 +3517,10 @@ restart:
 		 */
 		if (args->agno == start_agno && target_agbno) {
 			args->agbno = target_agbno;
-			error = xfs_alloc_ag_vextent_near(args);
+			error = xfs_alloc_ag_vextent_near(args, alloc_flags);
 		} else {
 			args->agbno = 0;
-			error = xfs_alloc_ag_vextent_size(args);
+			error = xfs_alloc_ag_vextent_size(args, alloc_flags);
 		}
 		break;
 	}
@@ -3453,8 +3537,8 @@ restart:
 	 * constraining flags by the caller, drop them and retry the allocation
 	 * without any constraints being set.
 	 */
-	if (flags) {
-		flags = 0;
+	if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) {
+		alloc_flags &= ~XFS_ALLOC_FLAG_TRYLOCK;
 		restart_agno = minimum_agno;
 		goto restart;
 	}
@@ -3482,6 +3566,7 @@ xfs_alloc_vextent_start_ag(
 	xfs_agnumber_t		start_agno;
 	xfs_agnumber_t		rotorstep = xfs_rotorstep;
 	bool			bump_rotor = false;
+	uint32_t		alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
 	int			error;
 
 	ASSERT(args->pag == NULL);
@@ -3508,7 +3593,7 @@ xfs_alloc_vextent_start_ag(
 
 	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
 	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
-			XFS_FSB_TO_AGBNO(mp, target), XFS_ALLOC_FLAG_TRYLOCK);
+			XFS_FSB_TO_AGBNO(mp, target), alloc_flags);
 
 	if (bump_rotor) {
 		if (args->agno == start_agno)
@@ -3535,6 +3620,7 @@ xfs_alloc_vextent_first_ag(
 	struct xfs_mount	*mp = args->mp;
 	xfs_agnumber_t		minimum_agno;
 	xfs_agnumber_t		start_agno;
+	uint32_t		alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
 	int			error;
 
 	ASSERT(args->pag == NULL);
@@ -3553,7 +3639,7 @@ xfs_alloc_vextent_first_ag(
 
 	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
 	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
-			XFS_FSB_TO_AGBNO(mp, target), 0);
+			XFS_FSB_TO_AGBNO(mp, target), alloc_flags);
 	return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
 }
 
@@ -3606,6 +3692,7 @@ xfs_alloc_vextent_near_bno(
 	struct xfs_mount	*mp = args->mp;
 	xfs_agnumber_t		minimum_agno;
 	bool			needs_perag = args->pag == NULL;
+	uint32_t		alloc_flags = 0;
 	int			error;
 
 	if (!needs_perag)
@@ -3626,9 +3713,9 @@ xfs_alloc_vextent_near_bno(
 	if (needs_perag)
 		args->pag = xfs_perag_grab(mp, args->agno);
 
-	error = xfs_alloc_vextent_prepare_ag(args, 0);
+	error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
 	if (!error && args->agbp)
-		error = xfs_alloc_ag_vextent_near(args);
+		error = xfs_alloc_ag_vextent_near(args, alloc_flags);
 
 	return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag);
 }
@@ -3756,15 +3843,11 @@ xfs_alloc_query_range(
 	xfs_alloc_query_range_fn		fn,
 	void					*priv)
 {
-	union xfs_btree_irec			low_brec;
-	union xfs_btree_irec			high_brec;
-	struct xfs_alloc_query_range_info	query;
+	union xfs_btree_irec			low_brec = { .a = *low_rec };
+	union xfs_btree_irec			high_brec = { .a = *high_rec };
+	struct xfs_alloc_query_range_info	query = { .priv = priv, .fn = fn };
 
 	ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
-	low_brec.a = *low_rec;
-	high_brec.a = *high_rec;
-	query.priv = priv;
-	query.fn = fn;
 	return xfs_btree_query_range(cur, &low_brec, &high_brec,
 			xfs_alloc_query_range_helper, &query);
 }
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 85ac470be0da..6bb8d295c321 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -19,11 +19,12 @@ unsigned int xfs_agfl_size(struct xfs_mount *mp);
 /*
  * Flags for xfs_alloc_fix_freelist.
  */
-#define	XFS_ALLOC_FLAG_TRYLOCK	0x00000001  /* use trylock for buffer locking */
-#define	XFS_ALLOC_FLAG_FREEING	0x00000002  /* indicate caller is freeing extents*/
-#define	XFS_ALLOC_FLAG_NORMAP	0x00000004  /* don't modify the rmapbt */
-#define	XFS_ALLOC_FLAG_NOSHRINK	0x00000008  /* don't shrink the freelist */
-#define	XFS_ALLOC_FLAG_CHECK	0x00000010  /* test only, don't modify args */
+#define	XFS_ALLOC_FLAG_TRYLOCK	(1U << 0)  /* use trylock for buffer locking */
+#define	XFS_ALLOC_FLAG_FREEING	(1U << 1)  /* indicate caller is freeing extents*/
+#define	XFS_ALLOC_FLAG_NORMAP	(1U << 2)  /* don't modify the rmapbt */
+#define	XFS_ALLOC_FLAG_NOSHRINK	(1U << 3)  /* don't shrink the freelist */
+#define	XFS_ALLOC_FLAG_CHECK	(1U << 4)  /* test only, don't modify args */
+#define	XFS_ALLOC_FLAG_TRYFLUSH	(1U << 5)  /* don't wait in busy extent flush */
 
 /*
  * Argument structure for xfs_alloc routines.
@@ -195,7 +196,7 @@ int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp,
 		struct xfs_buf **bpp);
 int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
 			struct xfs_buf *, struct xfs_owner_info *);
-int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
+int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags);
 int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag,
 		struct xfs_buf **agbp);
 
@@ -232,7 +233,7 @@ xfs_buf_to_agfl_bno(
 
 int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
-		bool skip_discard);
+		enum xfs_ag_resv_type type, bool skip_discard);
 
 /*
  * List of extents to be free "later".
@@ -245,6 +246,7 @@ struct xfs_extent_free_item {
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
 	struct xfs_perag	*xefi_pag;
 	unsigned int		xefi_flags;
+	enum xfs_ag_resv_type	xefi_agresv;
 };
 
 void xfs_extent_free_get_group(struct xfs_mount *mp,
@@ -259,9 +261,10 @@ xfs_free_extent_later(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
-	const struct xfs_owner_info	*oinfo)
+	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type)
 {
-	return __xfs_free_extent_later(tp, bno, len, oinfo, false);
+	return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
 }
 
 
@@ -270,4 +273,7 @@ extern struct kmem_cache	*xfs_extfree_item_cache;
 int __init xfs_extfree_intent_init_cache(void);
 void xfs_extfree_intent_destroy_cache(void);
 
+xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno,
+		uint32_t length);
+
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index beee51ad75ce..2580ae47209a 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -2293,8 +2293,6 @@ xfs_attr3_leaf_unbalance(
 
 	trace_xfs_attr_leaf_unbalance(state->args);
 
-	drop_leaf = drop_blk->bp->b_addr;
-	save_leaf = save_blk->bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf);
 	xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf);
 	entry = xfs_attr3_leaf_entryp(drop_leaf);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index fef35696adb7..30c931b38853 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -574,7 +574,8 @@ xfs_bmap_btree_to_extents(
 		return error;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
+	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
+			XFS_AG_RESV_NONE);
 	if (error)
 		return error;
 
@@ -5236,8 +5237,9 @@ xfs_bmap_del_extent_real(
 		} else {
 			error = __xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
-					(bflags & XFS_BMAPI_NODISCARD) ||
-					del->br_state == XFS_EXT_UNWRITTEN);
+					XFS_AG_RESV_NONE,
+					((bflags & XFS_BMAPI_NODISCARD) ||
+					del->br_state == XFS_EXT_UNWRITTEN));
 			if (error)
 				goto done;
 		}
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 36564ae3084f..bf3f1b36fdd2 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -271,7 +271,8 @@ xfs_bmbt_free_block(
 	int			error;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
-	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
+	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
+			XFS_AG_RESV_NONE);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 34600f94c2f4..b83e54c70906 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1853,8 +1853,8 @@ xfs_difree_inode_chunk(
 		/* not sparse, calculate extent info directly */
 		return xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, sagbno),
-				M_IGEO(mp)->ialloc_blks,
-				&XFS_RMAP_OINFO_INODES);
+				M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
+				XFS_AG_RESV_NONE);
 	}
 
 	/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1899,8 +1899,8 @@ xfs_difree_inode_chunk(
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
 		error = xfs_free_extent_later(tp,
-				XFS_AGB_TO_FSB(mp, agno, agbno),
-				contigblk, &XFS_RMAP_OINFO_INODES);
+				XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
+				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
 		if (error)
 			return error;
 
@@ -2486,11 +2486,14 @@ xfs_ialloc_log_agi(
 
 static xfs_failaddr_t
 xfs_agi_verify(
-	struct xfs_buf	*bp)
+	struct xfs_buf		*bp)
 {
-	struct xfs_mount *mp = bp->b_mount;
-	struct xfs_agi	*agi = bp->b_addr;
-	int		i;
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_agi		*agi = bp->b_addr;
+	xfs_failaddr_t		fa;
+	uint32_t		agi_seqno = be32_to_cpu(agi->agi_seqno);
+	uint32_t		agi_length = be32_to_cpu(agi->agi_length);
+	int			i;
 
 	if (xfs_has_crc(mp)) {
 		if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid))
@@ -2507,6 +2510,10 @@ xfs_agi_verify(
 	if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)))
 		return __this_address;
 
+	fa = xfs_validate_ag_length(bp, agi_seqno, agi_length);
+	if (fa)
+		return fa;
+
 	if (be32_to_cpu(agi->agi_level) < 1 ||
 	    be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
 		return __this_address;
@@ -2516,15 +2523,6 @@ xfs_agi_verify(
 	     be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
 		return __this_address;
 
-	/*
-	 * during growfs operations, the perag is not fully initialised,
-	 * so we can't use it for any useful checking. growfs ensures we can't
-	 * use it by using uncached buffers that don't have the perag attached
-	 * so we can detect and avoid this problem.
-	 */
-	if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno)
-		return __this_address;
-
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
 		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
 			continue;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 5a945ae21b5d..9258f01c0015 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -160,8 +160,7 @@ __xfs_inobt_free_block(
 
 	xfs_inobt_mod_blockcount(cur, -1);
 	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
-	return xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
 			&XFS_RMAP_OINFO_INOBT, resv);
 }
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index b6e21433925c..646b3fa362ad 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1152,7 +1152,8 @@ xfs_refcount_adjust_extents(
 						cur->bc_ag.pag->pag_agno,
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
-						  tmp.rc_blockcount, NULL);
+						  tmp.rc_blockcount, NULL,
+						  XFS_AG_RESV_NONE);
 				if (error)
 					goto out_error;
 			}
@@ -1213,7 +1214,8 @@ xfs_refcount_adjust_extents(
 					cur->bc_ag.pag->pag_agno,
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
-					ext.rc_blockcount, NULL);
+					ext.rc_blockcount, NULL,
+					XFS_AG_RESV_NONE);
 			if (error)
 				goto out_error;
 		}
@@ -1919,8 +1921,13 @@ xfs_refcount_recover_cow_leftovers(
 	struct xfs_buf			*agbp;
 	struct xfs_refcount_recovery	*rr, *n;
 	struct list_head		debris;
-	union xfs_btree_irec		low;
-	union xfs_btree_irec		high;
+	union xfs_btree_irec		low = {
+		.rc.rc_domain		= XFS_REFC_DOMAIN_COW,
+	};
+	union xfs_btree_irec		high = {
+		.rc.rc_domain		= XFS_REFC_DOMAIN_COW,
+		.rc.rc_startblock	= -1U,
+	};
 	xfs_fsblock_t			fsb;
 	int				error;
 
@@ -1951,10 +1958,6 @@ xfs_refcount_recover_cow_leftovers(
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
 
 	/* Find all the leftover CoW staging extents. */
-	memset(&low, 0, sizeof(low));
-	memset(&high, 0, sizeof(high));
-	low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW;
-	high.rc.rc_startblock = -1U;
 	error = xfs_btree_query_range(cur, &low, &high,
 			xfs_refcount_recover_extent, &debris);
 	xfs_btree_del_cursor(cur, error);
@@ -1981,7 +1984,8 @@ xfs_refcount_recover_cow_leftovers(
 
 		/* Free the block. */
 		error = xfs_free_extent_later(tp, fsb,
-				rr->rr_rrec.rc_blockcount, NULL);
+				rr->rr_rrec.rc_blockcount, NULL,
+				XFS_AG_RESV_NONE);
 		if (error)
 			goto out_trans;
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index d4afc5f4e6a5..5c3987d8dc24 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -106,19 +106,13 @@ xfs_refcountbt_free_block(
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
-	int			error;
 
 	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
-	error = xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
 			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
-	if (error)
-		return error;
-
-	return error;
 }
 
 STATIC int
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index f4dc23b3b837..fbb0b2637463 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2389,14 +2389,10 @@ xfs_rmap_query_range(
 	xfs_rmap_query_range_fn			fn,
 	void					*priv)
 {
-	union xfs_btree_irec			low_brec;
-	union xfs_btree_irec			high_brec;
-	struct xfs_rmap_query_range_info	query;
+	union xfs_btree_irec			low_brec = { .r = *low_rec };
+	union xfs_btree_irec			high_brec = { .r = *high_rec };
+	struct xfs_rmap_query_range_info	query = { .priv = priv, .fn = fn };
 
-	low_brec.r = *low_rec;
-	high_brec.r = *high_rec;
-	query.priv = priv;
-	query.fn = fn;
 	return xfs_btree_query_range(cur, &low_brec, &high_brec,
 			xfs_rmap_query_range_helper, &query);
 }
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index ba0f17bc1dc0..5e174685a77c 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -412,7 +412,6 @@ xfs_validate_sb_common(
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
 	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
 	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
-	    sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE			||
 	    sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
 	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES	||
 	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES	||
@@ -430,6 +429,61 @@ xfs_validate_sb_common(
 		return -EFSCORRUPTED;
 	}
 
+	/*
+	 * Logs that are too large are not supported at all. Reject them
+	 * outright. Logs that are too small are tolerated on v4 filesystems,
+	 * but we can only check that when mounting the log. Hence we skip
+	 * those checks here.
+	 */
+	if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) {
+		xfs_notice(mp,
+		"Log size 0x%x blocks too large, maximum size is 0x%llx blocks",
+			 sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS);
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) {
+		xfs_warn(mp,
+		"log size 0x%llx bytes too large, maximum size is 0x%llx bytes",
+			 XFS_FSB_TO_B(mp, sbp->sb_logblocks),
+			 XFS_MAX_LOG_BYTES);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Do not allow filesystems with corrupted log sector or stripe units to
+	 * be mounted. We cannot safely size the iclogs or write to the log if
+	 * the log stripe unit is not valid.
+	 */
+	if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) {
+		if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) {
+			xfs_notice(mp,
+			"log sector size in bytes/log2 (0x%x/0x%x) must match",
+				sbp->sb_logsectsize, 1U << sbp->sb_logsectlog);
+			return -EFSCORRUPTED;
+		}
+	} else if (sbp->sb_logsectsize || sbp->sb_logsectlog) {
+		xfs_notice(mp,
+		"log sector size in bytes/log2 (0x%x/0x%x) are not zero",
+			sbp->sb_logsectsize, sbp->sb_logsectlog);
+		return -EFSCORRUPTED;
+	}
+
+	if (sbp->sb_logsunit > 1) {
+		if (sbp->sb_logsunit % sbp->sb_blocksize) {
+			xfs_notice(mp,
+		"log stripe unit 0x%x bytes must be a multiple of block size",
+				sbp->sb_logsunit);
+			return -EFSCORRUPTED;
+		}
+		if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) {
+			xfs_notice(mp,
+		"log stripe unit 0x%x bytes over maximum size (0x%x bytes)",
+				sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE);
+			return -EFSCORRUPTED;
+		}
+	}
+
 	/* Validate the realtime geometry; stolen from xfs_repair */
 	if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
 	    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) {
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index f3d328e4a440..7c2fdc71e42d 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -566,20 +566,45 @@ xfs_extent_busy_clear(
 
 /*
  * Flush out all busy extents for this AG.
+ *
+ * If the current transaction is holding busy extents, the caller may not want
+ * to wait for committed busy extents to resolve. If we are being told just to
+ * try a flush or progress has been made since we last skipped a busy extent,
+ * return immediately to allow the caller to try again.
+ *
+ * If we are freeing extents, we might actually be holding the only free extents
+ * in the transaction busy list and the log force won't resolve that situation.
+ * In this case, we must return -EAGAIN to avoid a deadlock by informing the
+ * caller it needs to commit the busy extents it holds before retrying the
+ * extent free operation.
  */
-void
+int
 xfs_extent_busy_flush(
-	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
-	unsigned		busy_gen)
+	unsigned		busy_gen,
+	uint32_t		alloc_flags)
 {
 	DEFINE_WAIT		(wait);
 	int			error;
 
-	error = xfs_log_force(mp, XFS_LOG_SYNC);
+	error = xfs_log_force(tp->t_mountp, XFS_LOG_SYNC);
 	if (error)
-		return;
+		return error;
+
+	/* Avoid deadlocks on uncommitted busy extents. */
+	if (!list_empty(&tp->t_busy)) {
+		if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH)
+			return 0;
+
+		if (busy_gen != READ_ONCE(pag->pagb_gen))
+			return 0;
+
+		if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
+			return -EAGAIN;
+	}
 
+	/* Wait for committed busy extents to resolve. */
 	do {
 		prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
 		if  (busy_gen != READ_ONCE(pag->pagb_gen))
@@ -588,6 +613,7 @@ xfs_extent_busy_flush(
 	} while (1);
 
 	finish_wait(&pag->pagb_wait, &wait);
+	return 0;
 }
 
 void
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 4a118131059f..c37bf87e6781 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -51,9 +51,9 @@ bool
 xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
 		xfs_extlen_t *len, unsigned *busy_gen);
 
-void
-xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag,
-	unsigned busy_gen);
+int
+xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag,
+		unsigned busy_gen, uint32_t alloc_flags);
 
 void
 xfs_extent_busy_wait_all(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index f9e36b810663..f1a5ecf099aa 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -337,6 +337,34 @@ xfs_trans_get_efd(
 }
 
 /*
+ * Fill the EFD with all extents from the EFI when we need to roll the
+ * transaction and continue with a new EFI.
+ *
+ * This simply copies all the extents in the EFI to the EFD rather than make
+ * assumptions about which extents in the EFI have already been processed. We
+ * currently keep the xefi list in the same order as the EFI extent list, but
+ * that may not always be the case. Copying everything avoids leaving a landmine
+ * were we fail to cancel all the extents in an EFI if the xefi list is
+ * processed in a different order to the extents in the EFI.
+ */
+static void
+xfs_efd_from_efi(
+	struct xfs_efd_log_item	*efdp)
+{
+	struct xfs_efi_log_item *efip = efdp->efd_efip;
+	uint                    i;
+
+	ASSERT(efip->efi_format.efi_nextents > 0);
+	ASSERT(efdp->efd_next_extent < efip->efi_format.efi_nextents);
+
+	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
+	       efdp->efd_format.efd_extents[i] =
+		       efip->efi_format.efi_extents[i];
+	}
+	efdp->efd_next_extent = efip->efi_format.efi_nextents;
+}
+
+/*
  * Free an extent and log it to the EFD. Note that the transaction is marked
  * dirty regardless of whether the extent free succeeds or fails to support the
  * EFI/EFD lifecycle rules.
@@ -365,7 +393,7 @@ xfs_trans_free_extent(
 			agbno, xefi->xefi_blockcount);
 
 	error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
-			xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE,
+			xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
 			xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
 
 	/*
@@ -378,6 +406,17 @@ xfs_trans_free_extent(
 	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
 	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
 
+	/*
+	 * If we need a new transaction to make progress, the caller will log a
+	 * new EFI with the current contents. It will also log an EFD to cancel
+	 * the existing EFI, and so we need to copy all the unprocessed extents
+	 * in this EFI to the EFD so this works correctly.
+	 */
+	if (error == -EAGAIN) {
+		xfs_efd_from_efi(efdp);
+		return error;
+	}
+
 	next_extent = efdp->efd_next_extent;
 	ASSERT(next_extent < efdp->efd_format.efd_nextents);
 	extp = &(efdp->efd_format.efd_extents[next_extent]);
@@ -495,6 +534,13 @@ xfs_extent_free_finish_item(
 
 	error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi);
 
+	/*
+	 * Don't free the XEFI if we need a new transaction to complete
+	 * processing of it.
+	 */
+	if (error == -EAGAIN)
+		return error;
+
 	xfs_extent_free_put_group(xefi);
 	kmem_cache_free(xfs_extfree_item_cache, xefi);
 	return error;
@@ -620,6 +666,7 @@ xfs_efi_item_recover(
 	struct xfs_trans		*tp;
 	int				i;
 	int				error = 0;
+	bool				requeue_only = false;
 
 	/*
 	 * First check the validity of the extents described by the
@@ -644,6 +691,7 @@ xfs_efi_item_recover(
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
 		struct xfs_extent_free_item	fake = {
 			.xefi_owner		= XFS_RMAP_OWN_UNKNOWN,
+			.xefi_agresv		= XFS_AG_RESV_NONE,
 		};
 		struct xfs_extent		*extp;
 
@@ -652,9 +700,28 @@ xfs_efi_item_recover(
 		fake.xefi_startblock = extp->ext_start;
 		fake.xefi_blockcount = extp->ext_len;
 
-		xfs_extent_free_get_group(mp, &fake);
-		error = xfs_trans_free_extent(tp, efdp, &fake);
-		xfs_extent_free_put_group(&fake);
+		if (!requeue_only) {
+			xfs_extent_free_get_group(mp, &fake);
+			error = xfs_trans_free_extent(tp, efdp, &fake);
+			xfs_extent_free_put_group(&fake);
+		}
+
+		/*
+		 * If we can't free the extent without potentially deadlocking,
+		 * requeue the rest of the extents to a new so that they get
+		 * run again later with a new transaction context.
+		 */
+		if (error == -EAGAIN || requeue_only) {
+			error = xfs_free_extent_later(tp, fake.xefi_startblock,
+					fake.xefi_blockcount,
+					&XFS_RMAP_OINFO_ANY_OWNER,
+					fake.xefi_agresv);
+			if (!error) {
+				requeue_only = true;
+				continue;
+			}
+		}
+
 		if (error == -EFSCORRUPTED)
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					extp, sizeof(*extp));
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 59e7d1a14b67..10403ba9b58f 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -160,9 +160,18 @@ struct xfs_getfsmap_info {
 	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
 	struct xfs_perag	*pag;		/* AG info, if applicable */
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
+	/* daddr of low fsmap key when we're using the rtbitmap */
+	xfs_daddr_t		low_daddr;
 	u64			missing_owner;	/* owner of holes */
 	u32			dev;		/* device id */
-	struct xfs_rmap_irec	low;		/* low rmap key */
+	/*
+	 * Low rmap key for the query.  If low.rm_blockcount is nonzero, this
+	 * is the second (or later) call to retrieve the recordset in pieces.
+	 * xfs_getfsmap_rec_before_start will compare all records retrieved
+	 * by the rmapbt query to filter out any records that start before
+	 * the last record.
+	 */
+	struct xfs_rmap_irec	low;
 	struct xfs_rmap_irec	high;		/* high rmap key */
 	bool			last;		/* last extent? */
 };
@@ -237,16 +246,31 @@ xfs_getfsmap_format(
 	xfs_fsmap_from_internal(rec, xfm);
 }
 
+static inline bool
+xfs_getfsmap_rec_before_start(
+	struct xfs_getfsmap_info	*info,
+	const struct xfs_rmap_irec	*rec,
+	xfs_daddr_t			rec_daddr)
+{
+	if (info->low_daddr != -1ULL)
+		return rec_daddr < info->low_daddr;
+	if (info->low.rm_blockcount)
+		return xfs_rmap_compare(rec, &info->low) < 0;
+	return false;
+}
+
 /*
  * Format a reverse mapping for getfsmap, having translated rm_startblock
- * into the appropriate daddr units.
+ * into the appropriate daddr units.  Pass in a nonzero @len_daddr if the
+ * length could be larger than rm_blockcount in struct xfs_rmap_irec.
  */
 STATIC int
 xfs_getfsmap_helper(
 	struct xfs_trans		*tp,
 	struct xfs_getfsmap_info	*info,
 	const struct xfs_rmap_irec	*rec,
-	xfs_daddr_t			rec_daddr)
+	xfs_daddr_t			rec_daddr,
+	xfs_daddr_t			len_daddr)
 {
 	struct xfs_fsmap		fmr;
 	struct xfs_mount		*mp = tp->t_mountp;
@@ -256,12 +280,15 @@ xfs_getfsmap_helper(
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
+	if (len_daddr == 0)
+		len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+
 	/*
 	 * Filter out records that start before our startpoint, if the
 	 * caller requested that.
 	 */
-	if (xfs_rmap_compare(rec, &info->low) < 0) {
-		rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+	if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) {
+		rec_daddr += len_daddr;
 		if (info->next_daddr < rec_daddr)
 			info->next_daddr = rec_daddr;
 		return 0;
@@ -280,7 +307,7 @@ xfs_getfsmap_helper(
 
 		info->head->fmh_entries++;
 
-		rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+		rec_daddr += len_daddr;
 		if (info->next_daddr < rec_daddr)
 			info->next_daddr = rec_daddr;
 		return 0;
@@ -320,7 +347,7 @@ xfs_getfsmap_helper(
 	if (error)
 		return error;
 	fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset);
-	fmr.fmr_length = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+	fmr.fmr_length = len_daddr;
 	if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
 		fmr.fmr_flags |= FMR_OF_PREALLOC;
 	if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
@@ -337,7 +364,7 @@ xfs_getfsmap_helper(
 
 	xfs_getfsmap_format(mp, &fmr, info);
 out:
-	rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+	rec_daddr += len_daddr;
 	if (info->next_daddr < rec_daddr)
 		info->next_daddr = rec_daddr;
 	return 0;
@@ -358,7 +385,7 @@ xfs_getfsmap_datadev_helper(
 	fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock);
 	rec_daddr = XFS_FSB_TO_DADDR(mp, fsb);
 
-	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr);
+	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0);
 }
 
 /* Transform a bnobt irec into a fsmap */
@@ -382,7 +409,7 @@ xfs_getfsmap_datadev_bnobt_helper(
 	irec.rm_offset = 0;
 	irec.rm_flags = 0;
 
-	return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr);
+	return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0);
 }
 
 /* Set rmap flags based on the getfsmap flags */
@@ -409,31 +436,25 @@ xfs_getfsmap_logdev(
 {
 	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_rmap_irec		rmap;
-	int				error;
+	xfs_daddr_t			rec_daddr, len_daddr;
+	xfs_fsblock_t			start_fsb, end_fsb;
+	uint64_t			eofs;
 
-	/* Set up search keys */
-	info->low.rm_startblock = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
-	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
-	error = xfs_fsmap_owner_to_rmap(&info->low, keys);
-	if (error)
-		return error;
-	info->low.rm_blockcount = 0;
-	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	start_fsb = XFS_BB_TO_FSBT(mp,
+				keys[0].fmr_physical + keys[0].fmr_length);
+	end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
 
-	error = xfs_fsmap_owner_to_rmap(&info->high, keys + 1);
-	if (error)
-		return error;
-	info->high.rm_startblock = -1U;
-	info->high.rm_owner = ULLONG_MAX;
-	info->high.rm_offset = ULLONG_MAX;
-	info->high.rm_blockcount = 0;
-	info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
-	info->missing_owner = XFS_FMR_OWN_FREE;
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (keys[0].fmr_length > 0)
+		info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);
 
-	trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low);
-	trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high);
+	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
+	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);
 
-	if (keys[0].fmr_physical > 0)
+	if (start_fsb > 0)
 		return 0;
 
 	/* Fabricate an rmap entry for the external log device. */
@@ -443,7 +464,9 @@ xfs_getfsmap_logdev(
 	rmap.rm_offset = 0;
 	rmap.rm_flags = 0;
 
-	return xfs_getfsmap_helper(tp, info, &rmap, 0);
+	rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
+	len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
+	return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
 }
 
 #ifdef CONFIG_XFS_RT
@@ -457,72 +480,58 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 {
 	struct xfs_getfsmap_info	*info = priv;
 	struct xfs_rmap_irec		irec;
-	xfs_daddr_t			rec_daddr;
+	xfs_rtblock_t			rtbno;
+	xfs_daddr_t			rec_daddr, len_daddr;
+
+	rtbno = rec->ar_startext * mp->m_sb.sb_rextsize;
+	rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	irec.rm_startblock = rtbno;
+
+	rtbno = rec->ar_extcount * mp->m_sb.sb_rextsize;
+	len_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	irec.rm_blockcount = rtbno;
 
-	irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize;
-	rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock);
-	irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize;
 	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
 	irec.rm_offset = 0;
 	irec.rm_flags = 0;
 
-	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
+	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
 }
 
-/* Execute a getfsmap query against the realtime device. */
+/* Execute a getfsmap query against the realtime device rtbitmap. */
 STATIC int
-__xfs_getfsmap_rtdev(
+xfs_getfsmap_rtdev_rtbitmap(
 	struct xfs_trans		*tp,
 	const struct xfs_fsmap		*keys,
-	int				(*query_fn)(struct xfs_trans *,
-						    struct xfs_getfsmap_info *),
 	struct xfs_getfsmap_info	*info)
 {
+
+	struct xfs_rtalloc_rec		alow = { 0 };
+	struct xfs_rtalloc_rec		ahigh = { 0 };
 	struct xfs_mount		*mp = tp->t_mountp;
-	xfs_fsblock_t			start_fsb;
-	xfs_fsblock_t			end_fsb;
+	xfs_rtblock_t			start_rtb;
+	xfs_rtblock_t			end_rtb;
 	uint64_t			eofs;
-	int				error = 0;
+	int				error;
 
-	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rextents * mp->m_sb.sb_rextsize);
 	if (keys[0].fmr_physical >= eofs)
 		return 0;
-	start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
-	end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
+	start_rtb = XFS_BB_TO_FSBT(mp,
+				keys[0].fmr_physical + keys[0].fmr_length);
+	end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
 
-	/* Set up search keys */
-	info->low.rm_startblock = start_fsb;
-	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
-	if (error)
-		return error;
-	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
-	info->low.rm_blockcount = 0;
-	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
-
-	info->high.rm_startblock = end_fsb;
-	error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
-	if (error)
-		return error;
-	info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset);
-	info->high.rm_blockcount = 0;
-	xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
-
-	trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low);
-	trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high);
+	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
 
-	return query_fn(tp, info);
-}
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (keys[0].fmr_length > 0) {
+		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+		if (info->low_daddr >= eofs)
+			return 0;
+	}
 
-/* Actually query the realtime bitmap. */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap_query(
-	struct xfs_trans		*tp,
-	struct xfs_getfsmap_info	*info)
-{
-	struct xfs_rtalloc_rec		alow = { 0 };
-	struct xfs_rtalloc_rec		ahigh = { 0 };
-	struct xfs_mount		*mp = tp->t_mountp;
-	int				error;
+	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
+	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);
 
 	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 
@@ -530,8 +539,8 @@ xfs_getfsmap_rtdev_rtbitmap_query(
 	 * Set up query parameters to return free rtextents covering the range
 	 * we want.
 	 */
-	alow.ar_startext = info->low.rm_startblock;
-	ahigh.ar_startext = info->high.rm_startblock;
+	alow.ar_startext = start_rtb;
+	ahigh.ar_startext = end_rtb;
 	do_div(alow.ar_startext, mp->m_sb.sb_rextsize);
 	if (do_div(ahigh.ar_startext, mp->m_sb.sb_rextsize))
 		ahigh.ar_startext++;
@@ -554,18 +563,6 @@ err:
 	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	return error;
 }
-
-/* Execute a getfsmap query against the realtime device rtbitmap. */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap(
-	struct xfs_trans		*tp,
-	const struct xfs_fsmap		*keys,
-	struct xfs_getfsmap_info	*info)
-{
-	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
-	return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query,
-			info);
-}
 #endif /* CONFIG_XFS_RT */
 
 /* Execute a getfsmap query against the regular data device. */
@@ -606,9 +603,27 @@ __xfs_getfsmap_datadev(
 	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
 	if (error)
 		return error;
-	info->low.rm_blockcount = 0;
+	info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
 	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
 
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (info->low.rm_blockcount == 0) {
+		/* empty */
+	} else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) ||
+		   (info->low.rm_flags & (XFS_RMAP_ATTR_FORK |
+					  XFS_RMAP_BMBT_BLOCK |
+					  XFS_RMAP_UNWRITTEN))) {
+		info->low.rm_startblock += info->low.rm_blockcount;
+		info->low.rm_owner = 0;
+		info->low.rm_offset = 0;
+
+		start_fsb += info->low.rm_blockcount;
+		if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs)
+			return 0;
+	} else {
+		info->low.rm_offset += info->low.rm_blockcount;
+	}
+
 	info->high.rm_startblock = -1U;
 	info->high.rm_owner = ULLONG_MAX;
 	info->high.rm_offset = ULLONG_MAX;
@@ -659,12 +674,8 @@ __xfs_getfsmap_datadev(
 		 * Set the AG low key to the start of the AG prior to
 		 * moving on to the next AG.
 		 */
-		if (pag->pag_agno == start_ag) {
-			info->low.rm_startblock = 0;
-			info->low.rm_owner = 0;
-			info->low.rm_offset = 0;
-			info->low.rm_flags = 0;
-		}
+		if (pag->pag_agno == start_ag)
+			memset(&info->low, 0, sizeof(info->low));
 
 		/*
 		 * If this is the last AG, report any gap at the end of it
@@ -791,6 +802,19 @@ xfs_getfsmap_check_keys(
 	struct xfs_fsmap		*low_key,
 	struct xfs_fsmap		*high_key)
 {
+	if (low_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
+		if (low_key->fmr_offset)
+			return false;
+	}
+	if (high_key->fmr_flags != -1U &&
+	    (high_key->fmr_flags & (FMR_OF_SPECIAL_OWNER |
+				    FMR_OF_EXTENT_MAP))) {
+		if (high_key->fmr_offset && high_key->fmr_offset != -1ULL)
+			return false;
+	}
+	if (high_key->fmr_length && high_key->fmr_length != -1ULL)
+		return false;
+
 	if (low_key->fmr_device > high_key->fmr_device)
 		return false;
 	if (low_key->fmr_device < high_key->fmr_device)
@@ -834,15 +858,15 @@ xfs_getfsmap_check_keys(
  * ----------------
  * There are multiple levels of keys and counters at work here:
  * xfs_fsmap_head.fmh_keys	-- low and high fsmap keys passed in;
- * 				   these reflect fs-wide sector addrs.
+ *				   these reflect fs-wide sector addrs.
  * dkeys			-- fmh_keys used to query each device;
- * 				   these are fmh_keys but w/ the low key
- * 				   bumped up by fmr_length.
+ *				   these are fmh_keys but w/ the low key
+ *				   bumped up by fmr_length.
  * xfs_getfsmap_info.next_daddr	-- next disk addr we expect to see; this
  *				   is how we detect gaps in the fsmap
 				   records and report them.
  * xfs_getfsmap_info.low/high	-- per-AG low/high keys computed from
- * 				   dkeys; used to query the metadata.
+ *				   dkeys; used to query the metadata.
  */
 int
 xfs_getfsmap(
@@ -863,6 +887,8 @@ xfs_getfsmap(
 	if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) ||
 	    !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1]))
 		return -EINVAL;
+	if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1]))
+		return -EINVAL;
 
 	use_rmap = xfs_has_rmapbt(mp) &&
 		   has_capability_noaudit(current, CAP_SYS_ADMIN);
@@ -901,26 +927,15 @@ xfs_getfsmap(
 	 * blocks could be mapped to several other files/offsets.
 	 * According to rmapbt record ordering, the minimal next
 	 * possible record for the block range is the next starting
-	 * offset in the same inode. Therefore, bump the file offset to
-	 * continue the search appropriately.  For all other low key
-	 * mapping types (attr blocks, metadata), bump the physical
-	 * offset as there can be no other mapping for the same physical
-	 * block range.
+	 * offset in the same inode. Therefore, each fsmap backend bumps
+	 * the file offset to continue the search appropriately.  For
+	 * all other low key mapping types (attr blocks, metadata), each
+	 * fsmap backend bumps the physical offset as there can be no
+	 * other mapping for the same physical block range.
 	 */
 	dkeys[0] = head->fmh_keys[0];
-	if (dkeys[0].fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
-		dkeys[0].fmr_physical += dkeys[0].fmr_length;
-		dkeys[0].fmr_owner = 0;
-		if (dkeys[0].fmr_offset)
-			return -EINVAL;
-	} else
-		dkeys[0].fmr_offset += dkeys[0].fmr_length;
-	dkeys[0].fmr_length = 0;
 	memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap));
 
-	if (!xfs_getfsmap_check_keys(dkeys, &head->fmh_keys[1]))
-		return -EINVAL;
-
 	info.next_daddr = head->fmh_keys[0].fmr_physical +
 			  head->fmh_keys[0].fmr_length;
 	info.fsmap_recs = fsmap_recs;
@@ -960,6 +975,8 @@ xfs_getfsmap(
 		info.dev = handlers[i].dev;
 		info.last = false;
 		info.pag = NULL;
+		info.low_daddr = -1ULL;
+		info.low.rm_blockcount = 0;
 		error = handlers[i].fn(tp, dkeys, &info);
 		if (error)
 			break;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index fc61cc024023..79004d193e54 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -639,7 +639,6 @@ xfs_log_mount(
 	int		num_bblks)
 {
 	struct xlog	*log;
-	bool		fatal = xfs_has_crc(mp);
 	int		error = 0;
 	int		min_logfsbs;
 
@@ -663,53 +662,37 @@ xfs_log_mount(
 	mp->m_log = log;
 
 	/*
-	 * Validate the given log space and drop a critical message via syslog
-	 * if the log size is too small that would lead to some unexpected
-	 * situations in transaction log space reservation stage.
+	 * Now that we have set up the log and it's internal geometry
+	 * parameters, we can validate the given log space and drop a critical
+	 * message via syslog if the log size is too small. A log that is too
+	 * small can lead to unexpected situations in transaction log space
+	 * reservation stage. The superblock verifier has already validated all
+	 * the other log geometry constraints, so we don't have to check those
+	 * here.
 	 *
-	 * Note: we can't just reject the mount if the validation fails.  This
-	 * would mean that people would have to downgrade their kernel just to
-	 * remedy the situation as there is no way to grow the log (short of
-	 * black magic surgery with xfs_db).
+	 * Note: For v4 filesystems, we can't just reject the mount if the
+	 * validation fails.  This would mean that people would have to
+	 * downgrade their kernel just to remedy the situation as there is no
+	 * way to grow the log (short of black magic surgery with xfs_db).
 	 *
-	 * We can, however, reject mounts for CRC format filesystems, as the
+	 * We can, however, reject mounts for V5 format filesystems, as the
 	 * mkfs binary being used to make the filesystem should never create a
 	 * filesystem with a log that is too small.
 	 */
 	min_logfsbs = xfs_log_calc_minimum_size(mp);
-
 	if (mp->m_sb.sb_logblocks < min_logfsbs) {
 		xfs_warn(mp,
 		"Log size %d blocks too small, minimum size is %d blocks",
 			 mp->m_sb.sb_logblocks, min_logfsbs);
-		error = -EINVAL;
-	} else if (mp->m_sb.sb_logblocks > XFS_MAX_LOG_BLOCKS) {
-		xfs_warn(mp,
-		"Log size %d blocks too large, maximum size is %lld blocks",
-			 mp->m_sb.sb_logblocks, XFS_MAX_LOG_BLOCKS);
-		error = -EINVAL;
-	} else if (XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks) > XFS_MAX_LOG_BYTES) {
-		xfs_warn(mp,
-		"log size %lld bytes too large, maximum size is %lld bytes",
-			 XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks),
-			 XFS_MAX_LOG_BYTES);
-		error = -EINVAL;
-	} else if (mp->m_sb.sb_logsunit > 1 &&
-		   mp->m_sb.sb_logsunit % mp->m_sb.sb_blocksize) {
-		xfs_warn(mp,
-		"log stripe unit %u bytes must be a multiple of block size",
-			 mp->m_sb.sb_logsunit);
-		error = -EINVAL;
-		fatal = true;
-	}
-	if (error) {
+
 		/*
 		 * Log check errors are always fatal on v5; or whenever bad
 		 * metadata leads to a crash.
 		 */
-		if (fatal) {
+		if (xfs_has_crc(mp)) {
 			xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!");
 			ASSERT(0);
+			error = -EINVAL;
 			goto out_free_log;
 		}
 		xfs_crit(mp, "Log size out of supported range.");
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index c4078d0ec108..4a9bbd3fe120 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -114,7 +114,8 @@ xfs_dax_notify_ddev_failure(
 	int			error = 0;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
-	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen);
+	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
+							     daddr + bblen - 1);
 	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
 
 	error = xfs_trans_alloc_empty(mp, &tp);
@@ -210,7 +211,7 @@ xfs_dax_notify_failure(
 	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
 
 	/* Ignore the range out of filesystem area */
-	if (offset + len < ddev_start)
+	if (offset + len - 1 < ddev_start)
 		return -ENXIO;
 	if (offset > ddev_end)
 		return -ENXIO;
@@ -222,8 +223,8 @@ xfs_dax_notify_failure(
 		len -= ddev_start - offset;
 		offset = 0;
 	}
-	if (offset + len > ddev_end)
-		len -= ddev_end - offset;
+	if (offset + len - 1 > ddev_end)
+		len = ddev_end - offset + 1;
 
 	return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
 			mf_flags);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index abcc559f3c64..eb9102453aff 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -617,7 +617,8 @@ xfs_reflink_cancel_cow_blocks(
 					del.br_blockcount);
 
 			error = xfs_free_extent_later(*tpp, del.br_startblock,
-					  del.br_blockcount, NULL);
+					del.br_blockcount, NULL,
+					XFS_AG_RESV_NONE);
 			if (error)
 				break;
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 4db669203149..f3cc204bb4bf 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3623,6 +3623,31 @@ DEFINE_FSMAP_EVENT(xfs_fsmap_low_key);
 DEFINE_FSMAP_EVENT(xfs_fsmap_high_key);
 DEFINE_FSMAP_EVENT(xfs_fsmap_mapping);
 
+DECLARE_EVENT_CLASS(xfs_fsmap_linear_class,
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno),
+	TP_ARGS(mp, keydev, bno),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, keydev)
+		__field(xfs_fsblock_t, bno)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->keydev = new_decode_dev(keydev);
+		__entry->bno = bno;
+	),
+	TP_printk("dev %d:%d keydev %d:%d bno 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
+		  __entry->bno)
+)
+#define DEFINE_FSMAP_LINEAR_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_linear_class, name, \
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \
+	TP_ARGS(mp, keydev, bno))
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear);
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear);
+
 DECLARE_EVENT_CLASS(xfs_getfsmap_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap),
 	TP_ARGS(mp, fsmap),
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 7d4109af193e..1098452e7f95 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -823,7 +823,7 @@ xfs_trans_ail_update_bulk(
 			trace_xfs_ail_insert(lip, 0, lsn);
 		}
 		lip->li_lsn = lsn;
-		list_add(&lip->li_ail, &tmp);
+		list_add_tail(&lip->li_ail, &tmp);
 	}
 
 	if (!list_empty(&tmp))