Merge tag 'xfs-6.1-fixes-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:
 "Dave and I had thought that this would be a very quiet cycle, but we
  thought wrong.

  At first there were the usual trickle of minor bugfixes, but then
  Zorro pulled -rc1 and noticed complaints about the stronger memcpy
  checks w.r.t. flex arrays.

  Analyzing how to fix that revealed a bunch of validation gaps in
  validating ondisk log items during recovery, and then a customer hit
  an infinite loop in the refcounting code on a corrupt filesystem.

  So. This largeish batch of fixes addresses all those problems, I hope.

  Summary:

   - Fix a UAF bug during log recovery

   - Fix memory leaks when mount fails

   - Detect corrupt bestfree information in a directory block

   - Fix incorrect return value type for the dax page fault handlers

   - Fix fortify complaints about memcpy of xfs log item objects

   - Strengthen inadequate validation of recovered log items

   - Fix incorrectly declared flex array in EFI log item structs

   - Log corrupt log items for debugging purposes

   - Fix infinite loop problems in the refcount code if the refcount
     btree node block keys are corrupt

   - Fix infinite loop problems in the refcount code if the refcount
     btree records suffer MSB bitflips

   - Add more sanity checking to continued defer ops to prevent
     overflows from one AG to the next or off EOFS"

* tag 'xfs-6.1-fixes-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (28 commits)
  xfs: rename XFS_REFC_COW_START to _COWFLAG
  xfs: fix uninitialized list head in struct xfs_refcount_recovery
  xfs: fix agblocks check in the cow leftover recovery function
  xfs: check record domain when accessing refcount records
  xfs: remove XFS_FIND_RCEXT_SHARED and _COW
  xfs: refactor domain and refcount checking
  xfs: report refcount domain in tracepoints
  xfs: track cow/shared record domains explicitly in xfs_refcount_irec
  xfs: refactor refcount record usage in xchk_refcountbt_rec
  xfs: dump corrupt recovered log intent items to dmesg consistently
  xfs: move _irec structs to xfs_types.h
  xfs: actually abort log recovery on corrupt intent-done log items
  xfs: check deferred refcount op continuation parameters
  xfs: refactor all the EFI/EFD log item sizeof logic
  xfs: create a predicate to verify per-AG extents
  xfs: fix memcpy fortify errors in EFI log format copying
  xfs: make sure aglen never goes negative in xfs_refcount_adjust_extents
  xfs: fix memcpy fortify errors in RUI log format copying
  xfs: fix memcpy fortify errors in CUI log format copying
  xfs: fix memcpy fortify errors in BUI log format copying
  ...

fs/xfs/libxfs/xfs_ag.h

@@ -133,6 +133,21 @@ xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
 	return true;
 }
 
+static inline bool
+xfs_verify_agbext(
+	struct xfs_perag	*pag,
+	xfs_agblock_t		agbno,
+	xfs_agblock_t		len)
+{
+	if (agbno + len <= agbno)
+		return false;
+
+	if (!xfs_verify_agbno(pag, agbno))
+		return false;
+
+	return xfs_verify_agbno(pag, agbno + len - 1);
+}
+
 /*
  * Verify that an AG inode number pointer neither points outside the AG
  * nor points at static metadata.

fs/xfs/libxfs/xfs_alloc.c

@@ -263,11 +263,7 @@ xfs_alloc_get_rec(
 		goto out_bad_rec;
 
 	/* check for valid extent range, including overflow */
-	if (!xfs_verify_agbno(pag, *bno))
-		goto out_bad_rec;
-	if (*bno > *bno + *len)
-		goto out_bad_rec;
-	if (!xfs_verify_agbno(pag, *bno + *len - 1))
+	if (!xfs_verify_agbext(pag, *bno, *len))
 		goto out_bad_rec;
 
 	return 0;

fs/xfs/libxfs/xfs_dir2_leaf.c

@@ -146,6 +146,8 @@ xfs_dir3_leaf_check_int(
 	xfs_dir2_leaf_tail_t		*ltp;
 	int				stale;
 	int				i;
+	bool				isleaf1 = (hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
+						   hdr->magic == XFS_DIR3_LEAF1_MAGIC);
 
 	ltp = xfs_dir2_leaf_tail_p(geo, leaf);
 
@@ -158,8 +160,7 @@ xfs_dir3_leaf_check_int(
 		return __this_address;
 
 	/* Leaves and bests don't overlap in leaf format. */
-	if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
-	     hdr->magic == XFS_DIR3_LEAF1_MAGIC) &&
+	if (isleaf1 &&
 	    (char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
 		return __this_address;
 
@@ -175,6 +176,10 @@ xfs_dir3_leaf_check_int(
 		}
 		if (hdr->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 			stale++;
+		if (isleaf1 && xfs_dir2_dataptr_to_db(geo,
+				be32_to_cpu(hdr->ents[i].address)) >=
+				be32_to_cpu(ltp->bestcount))
+			return __this_address;
 	}
 	if (hdr->stale != stale)
 		return __this_address;

fs/xfs/libxfs/xfs_format.h

@@ -1564,20 +1564,6 @@ struct xfs_rmap_rec {
 #define RMAPBT_UNUSED_OFFSET_BITLEN	7
 #define RMAPBT_OFFSET_BITLEN		54
 
-#define XFS_RMAP_ATTR_FORK		(1 << 0)
-#define XFS_RMAP_BMBT_BLOCK		(1 << 1)
-#define XFS_RMAP_UNWRITTEN		(1 << 2)
-#define XFS_RMAP_KEY_FLAGS		(XFS_RMAP_ATTR_FORK | \
-					 XFS_RMAP_BMBT_BLOCK)
-#define XFS_RMAP_REC_FLAGS		(XFS_RMAP_UNWRITTEN)
-struct xfs_rmap_irec {
-	xfs_agblock_t	rm_startblock;	/* extent start block */
-	xfs_extlen_t	rm_blockcount;	/* extent length */
-	uint64_t	rm_owner;	/* extent owner */
-	uint64_t	rm_offset;	/* offset within the owner */
-	unsigned int	rm_flags;	/* state flags */
-};
-
 /*
  * Key structure
  *
@@ -1626,7 +1612,7 @@ unsigned int xfs_refc_block(struct xfs_mount *mp);
  * on the startblock.  This speeds up mount time deletion of stale
  * staging extents because they're all at the right side of the tree.
  */
-#define XFS_REFC_COW_START		((xfs_agblock_t)(1U << 31))
+#define XFS_REFC_COWFLAG		(1U << 31)
 #define REFCNTBT_COWFLAG_BITLEN		1
 #define REFCNTBT_AGBLOCK_BITLEN		31
 
@@ -1640,12 +1626,6 @@ struct xfs_refcount_key {
 	__be32		rc_startblock;	/* starting block number */
 };
 
-struct xfs_refcount_irec {
-	xfs_agblock_t	rc_startblock;	/* starting block number */
-	xfs_extlen_t	rc_blockcount;	/* count of free blocks */
-	xfs_nlink_t	rc_refcount;	/* number of inodes linked here */
-};
-
 #define MAXREFCOUNT	((xfs_nlink_t)~0U)
 #define MAXREFCEXTLEN	((xfs_extlen_t)~0U)
 

fs/xfs/libxfs/xfs_log_format.h

@@ -613,25 +613,49 @@ typedef struct xfs_efi_log_format {
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_t		efi_extents[];	/* array of extents to free */
 } xfs_efi_log_format_t;
 
+static inline size_t
+xfs_efi_log_format_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efi_log_format) +
+			nr * sizeof(struct xfs_extent);
+}
+
 typedef struct xfs_efi_log_format_32 {
 	uint16_t		efi_type;	/* efi log item type */
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_32_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_32_t		efi_extents[];	/* array of extents to free */
 } __attribute__((packed)) xfs_efi_log_format_32_t;
 
+static inline size_t
+xfs_efi_log_format32_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efi_log_format_32) +
+			nr * sizeof(struct xfs_extent_32);
+}
+
 typedef struct xfs_efi_log_format_64 {
 	uint16_t		efi_type;	/* efi log item type */
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_64_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_64_t		efi_extents[];	/* array of extents to free */
 } xfs_efi_log_format_64_t;
 
+static inline size_t
+xfs_efi_log_format64_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efi_log_format_64) +
+			nr * sizeof(struct xfs_extent_64);
+}
+
 /*
  * This is the structure used to lay out an efd log item in the
  * log.  The efd_extents array is a variable size array whose
@@ -642,25 +666,49 @@ typedef struct xfs_efd_log_format {
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_t		efd_extents[];	/* array of extents freed */
 } xfs_efd_log_format_t;
 
+static inline size_t
+xfs_efd_log_format_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efd_log_format) +
+			nr * sizeof(struct xfs_extent);
+}
+
 typedef struct xfs_efd_log_format_32 {
 	uint16_t		efd_type;	/* efd log item type */
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_32_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_32_t		efd_extents[];	/* array of extents freed */
 } __attribute__((packed)) xfs_efd_log_format_32_t;
 
+static inline size_t
+xfs_efd_log_format32_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efd_log_format_32) +
+			nr * sizeof(struct xfs_extent_32);
+}
+
 typedef struct xfs_efd_log_format_64 {
 	uint16_t		efd_type;	/* efd log item type */
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_64_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_64_t		efd_extents[];	/* array of extents freed */
 } xfs_efd_log_format_64_t;
 
+static inline size_t
+xfs_efd_log_format64_sizeof(
+	unsigned int		nr)
+{
+	return sizeof(struct xfs_efd_log_format_64) +
+			nr * sizeof(struct xfs_extent_64);
+}
+
 /*
  * RUI/RUD (reverse mapping) log format definitions
  */

fs/xfs/libxfs/xfs_refcount.c

@@ -46,13 +46,16 @@ STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
 int
 xfs_refcount_lookup_le(
 	struct xfs_btree_cur	*cur,
+	enum xfs_refc_domain	domain,
 	xfs_agblock_t		bno,
 	int			*stat)
 {
-	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+			xfs_refcount_encode_startblock(bno, domain),
 			XFS_LOOKUP_LE);
 	cur->bc_rec.rc.rc_startblock = bno;
 	cur->bc_rec.rc.rc_blockcount = 0;
+	cur->bc_rec.rc.rc_domain = domain;
 	return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
 }
 
@@ -63,13 +66,16 @@ xfs_refcount_lookup_le(
 int
 xfs_refcount_lookup_ge(
 	struct xfs_btree_cur	*cur,
+	enum xfs_refc_domain	domain,
 	xfs_agblock_t		bno,
 	int			*stat)
 {
-	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+			xfs_refcount_encode_startblock(bno, domain),
 			XFS_LOOKUP_GE);
 	cur->bc_rec.rc.rc_startblock = bno;
 	cur->bc_rec.rc.rc_blockcount = 0;
+	cur->bc_rec.rc.rc_domain = domain;
 	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
 }
 
@@ -80,13 +86,16 @@ xfs_refcount_lookup_ge(
 int
 xfs_refcount_lookup_eq(
 	struct xfs_btree_cur	*cur,
+	enum xfs_refc_domain	domain,
 	xfs_agblock_t		bno,
 	int			*stat)
 {
-	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+			xfs_refcount_encode_startblock(bno, domain),
 			XFS_LOOKUP_LE);
 	cur->bc_rec.rc.rc_startblock = bno;
 	cur->bc_rec.rc.rc_blockcount = 0;
+	cur->bc_rec.rc.rc_domain = domain;
 	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
 }
 
@@ -96,7 +105,17 @@ xfs_refcount_btrec_to_irec(
 	const union xfs_btree_rec	*rec,
 	struct xfs_refcount_irec	*irec)
 {
-	irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock);
+	uint32_t			start;
+
+	start = be32_to_cpu(rec->refc.rc_startblock);
+	if (start & XFS_REFC_COWFLAG) {
+		start &= ~XFS_REFC_COWFLAG;
+		irec->rc_domain = XFS_REFC_DOMAIN_COW;
+	} else {
+		irec->rc_domain = XFS_REFC_DOMAIN_SHARED;
+	}
+
+	irec->rc_startblock = start;
 	irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount);
 	irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount);
 }
@@ -114,7 +133,6 @@ xfs_refcount_get_rec(
 	struct xfs_perag		*pag = cur->bc_ag.pag;
 	union xfs_btree_rec		*rec;
 	int				error;
-	xfs_agblock_t			realstart;
 
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !*stat)
@@ -124,22 +142,11 @@ xfs_refcount_get_rec(
 	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
 		goto out_bad_rec;
 
-	/* handle special COW-staging state */
-	realstart = irec->rc_startblock;
-	if (realstart & XFS_REFC_COW_START) {
-		if (irec->rc_refcount != 1)
-			goto out_bad_rec;
-		realstart &= ~XFS_REFC_COW_START;
-	} else if (irec->rc_refcount < 2) {
+	if (!xfs_refcount_check_domain(irec))
 		goto out_bad_rec;
-	}
 
 	/* check for valid extent range, including overflow */
-	if (!xfs_verify_agbno(pag, realstart))
-		goto out_bad_rec;
-	if (realstart > realstart + irec->rc_blockcount)
-		goto out_bad_rec;
-	if (!xfs_verify_agbno(pag, realstart + irec->rc_blockcount - 1))
+	if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount))
 		goto out_bad_rec;
 
 	if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
@@ -169,12 +176,17 @@ xfs_refcount_update(
 	struct xfs_refcount_irec	*irec)
 {
 	union xfs_btree_rec	rec;
+	uint32_t		start;
 	int			error;
 
 	trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
-	rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock);
+
+	start = xfs_refcount_encode_startblock(irec->rc_startblock,
+			irec->rc_domain);
+	rec.refc.rc_startblock = cpu_to_be32(start);
 	rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount);
 	rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount);
+
 	error = xfs_btree_update(cur, &rec);
 	if (error)
 		trace_xfs_refcount_update_error(cur->bc_mp,
@@ -196,9 +208,12 @@ xfs_refcount_insert(
 	int				error;
 
 	trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+
 	cur->bc_rec.rc.rc_startblock = irec->rc_startblock;
 	cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
 	cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
+	cur->bc_rec.rc.rc_domain = irec->rc_domain;
+
 	error = xfs_btree_insert(cur, i);
 	if (error)
 		goto out_error;
@@ -244,7 +259,8 @@ xfs_refcount_delete(
 	}
 	if (error)
 		goto out_error;
-	error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec);
+	error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock,
+			&found_rec);
 out_error:
 	if (error)
 		trace_xfs_refcount_delete_error(cur->bc_mp,
@@ -343,6 +359,7 @@ xfs_refc_next(
 STATIC int
 xfs_refcount_split_extent(
 	struct xfs_btree_cur		*cur,
+	enum xfs_refc_domain		domain,
 	xfs_agblock_t			agbno,
 	bool				*shape_changed)
 {
@@ -351,7 +368,7 @@ xfs_refcount_split_extent(
 	int				error;
 
 	*shape_changed = false;
-	error = xfs_refcount_lookup_le(cur, agbno, &found_rec);
+	error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec);
 	if (error)
 		goto out_error;
 	if (!found_rec)
@@ -364,6 +381,8 @@ xfs_refcount_split_extent(
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
+	if (rcext.rc_domain != domain)
+		return 0;
 	if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno)
 		return 0;
 
@@ -415,6 +434,9 @@ xfs_refcount_merge_center_extents(
 	trace_xfs_refcount_merge_center_extents(cur->bc_mp,
 			cur->bc_ag.pag->pag_agno, left, center, right);
 
+	ASSERT(left->rc_domain == center->rc_domain);
+	ASSERT(right->rc_domain == center->rc_domain);
+
 	/*
 	 * Make sure the center and right extents are not in the btree.
 	 * If the center extent was synthesized, the first delete call
@@ -423,8 +445,8 @@ xfs_refcount_merge_center_extents(
 	 * call removes the center and the second one removes the right
 	 * extent.
 	 */
-	error = xfs_refcount_lookup_ge(cur, center->rc_startblock,
-			&found_rec);
+	error = xfs_refcount_lookup_ge(cur, center->rc_domain,
+			center->rc_startblock, &found_rec);
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -451,8 +473,8 @@ xfs_refcount_merge_center_extents(
 	}
 
 	/* Enlarge the left extent. */
-	error = xfs_refcount_lookup_le(cur, left->rc_startblock,
-			&found_rec);
+	error = xfs_refcount_lookup_le(cur, left->rc_domain,
+			left->rc_startblock, &found_rec);
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -491,10 +513,12 @@ xfs_refcount_merge_left_extent(
 	trace_xfs_refcount_merge_left_extent(cur->bc_mp,
 			cur->bc_ag.pag->pag_agno, left, cleft);
 
+	ASSERT(left->rc_domain == cleft->rc_domain);
+
 	/* If the extent at agbno (cleft) wasn't synthesized, remove it. */
 	if (cleft->rc_refcount > 1) {
-		error = xfs_refcount_lookup_le(cur, cleft->rc_startblock,
-				&found_rec);
+		error = xfs_refcount_lookup_le(cur, cleft->rc_domain,
+				cleft->rc_startblock, &found_rec);
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -512,8 +536,8 @@ xfs_refcount_merge_left_extent(
 	}
 
 	/* Enlarge the left extent. */
-	error = xfs_refcount_lookup_le(cur, left->rc_startblock,
-			&found_rec);
+	error = xfs_refcount_lookup_le(cur, left->rc_domain,
+			left->rc_startblock, &found_rec);
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -552,13 +576,15 @@ xfs_refcount_merge_right_extent(
 	trace_xfs_refcount_merge_right_extent(cur->bc_mp,
 			cur->bc_ag.pag->pag_agno, cright, right);
 
+	ASSERT(right->rc_domain == cright->rc_domain);
+
 	/*
 	 * If the extent ending at agbno+aglen (cright) wasn't synthesized,
 	 * remove it.
 	 */
 	if (cright->rc_refcount > 1) {
-		error = xfs_refcount_lookup_le(cur, cright->rc_startblock,
-			&found_rec);
+		error = xfs_refcount_lookup_le(cur, cright->rc_domain,
+				cright->rc_startblock, &found_rec);
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -576,8 +602,8 @@ xfs_refcount_merge_right_extent(
 	}
 
 	/* Enlarge the right extent. */
-	error = xfs_refcount_lookup_le(cur, right->rc_startblock,
-			&found_rec);
+	error = xfs_refcount_lookup_le(cur, right->rc_domain,
+			right->rc_startblock, &found_rec);
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -600,8 +626,6 @@ xfs_refcount_merge_right_extent(
 	return error;
 }
 
-#define XFS_FIND_RCEXT_SHARED	1
-#define XFS_FIND_RCEXT_COW	2
 /*
  * Find the left extent and the one after it (cleft).  This function assumes
  * that we've already split any extent crossing agbno.
@@ -611,16 +635,16 @@ xfs_refcount_find_left_extents(
 	struct xfs_btree_cur		*cur,
 	struct xfs_refcount_irec	*left,
 	struct xfs_refcount_irec	*cleft,
+	enum xfs_refc_domain		domain,
 	xfs_agblock_t			agbno,
-	xfs_extlen_t			aglen,
-	int				flags)
+	xfs_extlen_t			aglen)
 {
 	struct xfs_refcount_irec	tmp;
 	int				error;
 	int				found_rec;
 
 	left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK;
-	error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec);
+	error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec);
 	if (error)
 		goto out_error;
 	if (!found_rec)
@@ -634,11 +658,9 @@ xfs_refcount_find_left_extents(
 		goto out_error;
 	}
 
-	if (xfs_refc_next(&tmp) != agbno)
-		return 0;
-	if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+	if (tmp.rc_domain != domain)
 		return 0;
-	if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+	if (xfs_refc_next(&tmp) != agbno)
 		return 0;
 	/* We have a left extent; retrieve (or invent) the next right one */
 	*left = tmp;
@@ -655,6 +677,9 @@ xfs_refcount_find_left_extents(
 			goto out_error;
 		}
 
+		if (tmp.rc_domain != domain)
+			goto not_found;
+
 		/* if tmp starts at the end of our range, just use that */
 		if (tmp.rc_startblock == agbno)
 			*cleft = tmp;
@@ -671,8 +696,10 @@ xfs_refcount_find_left_extents(
 			cleft->rc_blockcount = min(aglen,
 					tmp.rc_startblock - agbno);
 			cleft->rc_refcount = 1;
+			cleft->rc_domain = domain;
 		}
 	} else {
+not_found:
 		/*
 		 * No extents, so pretend that there's one covering the whole
 		 * range.
@@ -680,6 +707,7 @@ xfs_refcount_find_left_extents(
 		cleft->rc_startblock = agbno;
 		cleft->rc_blockcount = aglen;
 		cleft->rc_refcount = 1;
+		cleft->rc_domain = domain;
 	}
 	trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			left, cleft, agbno);
@@ -700,16 +728,16 @@ xfs_refcount_find_right_extents(
 	struct xfs_btree_cur		*cur,
 	struct xfs_refcount_irec	*right,
 	struct xfs_refcount_irec	*cright,
+	enum xfs_refc_domain		domain,
 	xfs_agblock_t			agbno,
-	xfs_extlen_t			aglen,
-	int				flags)
+	xfs_extlen_t			aglen)
 {
 	struct xfs_refcount_irec	tmp;
 	int				error;
 	int				found_rec;
 
 	right->rc_startblock = cright->rc_startblock = NULLAGBLOCK;
-	error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec);
+	error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec);
 	if (error)
 		goto out_error;
 	if (!found_rec)
@@ -723,11 +751,9 @@ xfs_refcount_find_right_extents(
 		goto out_error;
 	}
 
-	if (tmp.rc_startblock != agbno + aglen)
-		return 0;
-	if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+	if (tmp.rc_domain != domain)
 		return 0;
-	if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+	if (tmp.rc_startblock != agbno + aglen)
 		return 0;
 	/* We have a right extent; retrieve (or invent) the next left one */
 	*right = tmp;
@@ -744,6 +770,9 @@ xfs_refcount_find_right_extents(
 			goto out_error;
 		}
 
+		if (tmp.rc_domain != domain)
+			goto not_found;
+
 		/* if tmp ends at the end of our range, just use that */
 		if (xfs_refc_next(&tmp) == agbno + aglen)
 			*cright = tmp;
@@ -760,8 +789,10 @@ xfs_refcount_find_right_extents(
 			cright->rc_blockcount = right->rc_startblock -
 					cright->rc_startblock;
 			cright->rc_refcount = 1;
+			cright->rc_domain = domain;
 		}
 	} else {
+not_found:
 		/*
 		 * No extents, so pretend that there's one covering the whole
 		 * range.
@@ -769,6 +800,7 @@ xfs_refcount_find_right_extents(
 		cright->rc_startblock = agbno;
 		cright->rc_blockcount = aglen;
 		cright->rc_refcount = 1;
+		cright->rc_domain = domain;
 	}
 	trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			cright, right, agbno + aglen);
@@ -794,10 +826,10 @@ xfs_refc_valid(
 STATIC int
 xfs_refcount_merge_extents(
 	struct xfs_btree_cur	*cur,
+	enum xfs_refc_domain	domain,
 	xfs_agblock_t		*agbno,
 	xfs_extlen_t		*aglen,
 	enum xfs_refc_adjust_op adjust,
-	int			flags,
 	bool			*shape_changed)
 {
 	struct xfs_refcount_irec	left = {0}, cleft = {0};
@@ -812,12 +844,12 @@ xfs_refcount_merge_extents(
 	 * just below (agbno + aglen) [cright], and just above (agbno + aglen)
 	 * [right].
 	 */
-	error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno,
-			*aglen, flags);
+	error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain,
+			*agbno, *aglen);
 	if (error)
 		return error;
-	error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno,
-			*aglen, flags);
+	error = xfs_refcount_find_right_extents(cur, &right, &cright, domain,
+			*agbno, *aglen);
 	if (error)
 		return error;
 
@@ -870,7 +902,7 @@ xfs_refcount_merge_extents(
 				aglen);
 	}
 
-	return error;
+	return 0;
 }
 
 /*
@@ -933,7 +965,8 @@ xfs_refcount_adjust_extents(
 	if (*aglen == 0)
 		return 0;
 
-	error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec);
+	error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno,
+			&found_rec);
 	if (error)
 		goto out_error;
 
@@ -941,10 +974,11 @@ xfs_refcount_adjust_extents(
 		error = xfs_refcount_get_rec(cur, &ext, &found_rec);
 		if (error)
 			goto out_error;
-		if (!found_rec) {
+		if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) {
 			ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
 			ext.rc_blockcount = 0;
 			ext.rc_refcount = 0;
+			ext.rc_domain = XFS_REFC_DOMAIN_SHARED;
 		}
 
 		/*
@@ -957,6 +991,8 @@ xfs_refcount_adjust_extents(
 			tmp.rc_blockcount = min(*aglen,
 					ext.rc_startblock - *agbno);
 			tmp.rc_refcount = 1 + adj;
+			tmp.rc_domain = XFS_REFC_DOMAIN_SHARED;
+
 			trace_xfs_refcount_modify_extent(cur->bc_mp,
 					cur->bc_ag.pag->pag_agno, &tmp);
 
@@ -986,15 +1022,30 @@ xfs_refcount_adjust_extents(
 			(*agbno) += tmp.rc_blockcount;
 			(*aglen) -= tmp.rc_blockcount;
 
-			error = xfs_refcount_lookup_ge(cur, *agbno,
+			/* Stop if there's nothing left to modify */
+			if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
+				break;
+
+			/* Move the cursor to the start of ext. */
+			error = xfs_refcount_lookup_ge(cur,
+					XFS_REFC_DOMAIN_SHARED, *agbno,
 					&found_rec);
 			if (error)
 				goto out_error;
 		}
 
-		/* Stop if there's nothing left to modify */
-		if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
-			break;
+		/*
+		 * A previous step trimmed agbno/aglen such that the end of the
+		 * range would not be in the middle of the record.  If this is
+		 * no longer the case, something is seriously wrong with the
+		 * btree.  Make sure we never feed the synthesized record into
+		 * the processing loop below.
+		 */
+		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
+		    XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+			error = -EFSCORRUPTED;
+			goto out_error;
+		}
 
 		/*
 		 * Adjust the reference count and either update the tree
@@ -1070,13 +1121,15 @@ xfs_refcount_adjust(
 	/*
 	 * Ensure that no rcextents cross the boundary of the adjustment range.
 	 */
-	error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+	error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+			agbno, &shape_changed);
 	if (error)
 		goto out_error;
 	if (shape_changed)
 		shape_changes++;
 
-	error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+	error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+			agbno + aglen, &shape_changed);
 	if (error)
 		goto out_error;
 	if (shape_changed)
@@ -1085,8 +1138,8 @@ xfs_refcount_adjust(
 	/*
 	 * Try to merge with the left or right extents of the range.
 	 */
-	error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj,
-			XFS_FIND_RCEXT_SHARED, &shape_changed);
+	error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED,
+			new_agbno, new_aglen, adj, &shape_changed);
 	if (error)
 		goto out_error;
 	if (shape_changed)
@@ -1124,6 +1177,32 @@ xfs_refcount_finish_one_cleanup(
 		xfs_trans_brelse(tp, agbp);
 }
 
+/*
+ * Set up a continuation a deferred refcount operation by updating the intent.
+ * Checks to make sure we're not going to run off the end of the AG.
+ */
+static inline int
+xfs_refcount_continue_op(
+	struct xfs_btree_cur		*cur,
+	xfs_fsblock_t			startblock,
+	xfs_agblock_t			new_agbno,
+	xfs_extlen_t			new_len,
+	xfs_fsblock_t			*new_fsbno)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_perag		*pag = cur->bc_ag.pag;
+
+	if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len)))
+		return -EFSCORRUPTED;
+
+	*new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+
+	ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len));
+	ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno));
+
+	return 0;
+}
+
 /*
  * Process one of the deferred refcount operations.  We pass back the
  * btree cursor to maintain our lock on the btree between calls.
@@ -1191,12 +1270,20 @@ xfs_refcount_finish_one(
 	case XFS_REFCOUNT_INCREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
 				new_len, XFS_REFCOUNT_ADJUST_INCREASE);
-		*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+		if (error)
+			goto out_drop;
+		if (*new_len > 0)
+			error = xfs_refcount_continue_op(rcur, startblock,
+					new_agbno, *new_len, new_fsb);
 		break;
 	case XFS_REFCOUNT_DECREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
 				new_len, XFS_REFCOUNT_ADJUST_DECREASE);
-		*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+		if (error)
+			goto out_drop;
+		if (*new_len > 0)
+			error = xfs_refcount_continue_op(rcur, startblock,
+					new_agbno, *new_len, new_fsb);
 		break;
 	case XFS_REFCOUNT_ALLOC_COW:
 		*new_fsb = startblock + blockcount;
@@ -1307,7 +1394,8 @@ xfs_refcount_find_shared(
 	*flen = 0;
 
 	/* Try to find a refcount extent that crosses the start */
-	error = xfs_refcount_lookup_le(cur, agbno, &have);
+	error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno,
+			&have);
 	if (error)
 		goto out_error;
 	if (!have) {
@@ -1325,6 +1413,8 @@ xfs_refcount_find_shared(
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
+	if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+		goto done;
 
 	/* If the extent ends before the start, look at the next one */
 	if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) {
@@ -1340,6 +1430,8 @@ xfs_refcount_find_shared(
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
+		if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+			goto done;
 	}
 
 	/* If the extent starts after the range we want, bail out */
@@ -1371,7 +1463,8 @@ xfs_refcount_find_shared(
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
-		if (tmp.rc_startblock >= agbno + aglen ||
+		if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED ||
+		    tmp.rc_startblock >= agbno + aglen ||
 		    tmp.rc_startblock != *fbno + *flen)
 			break;
 		*flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno);
@@ -1455,17 +1548,23 @@ xfs_refcount_adjust_cow_extents(
 		return 0;
 
 	/* Find any overlapping refcount records */
-	error = xfs_refcount_lookup_ge(cur, agbno, &found_rec);
+	error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno,
+			&found_rec);
 	if (error)
 		goto out_error;
 	error = xfs_refcount_get_rec(cur, &ext, &found_rec);
 	if (error)
 		goto out_error;
+	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
+				ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		error = -EFSCORRUPTED;
+		goto out_error;
+	}
 	if (!found_rec) {
-		ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks +
-				XFS_REFC_COW_START;
+		ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
 		ext.rc_blockcount = 0;
 		ext.rc_refcount = 0;
+		ext.rc_domain = XFS_REFC_DOMAIN_COW;
 	}
 
 	switch (adj) {
@@ -1480,6 +1579,8 @@ xfs_refcount_adjust_cow_extents(
 		tmp.rc_startblock = agbno;
 		tmp.rc_blockcount = aglen;
 		tmp.rc_refcount = 1;
+		tmp.rc_domain = XFS_REFC_DOMAIN_COW;
+
 		trace_xfs_refcount_modify_extent(cur->bc_mp,
 				cur->bc_ag.pag->pag_agno, &tmp);
 
@@ -1542,24 +1643,24 @@ xfs_refcount_adjust_cow(
 	bool			shape_changed;
 	int			error;
 
-	agbno += XFS_REFC_COW_START;
-
 	/*
 	 * Ensure that no rcextents cross the boundary of the adjustment range.
 	 */
-	error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+	error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+			agbno, &shape_changed);
 	if (error)
 		goto out_error;
 
-	error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+	error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+			agbno + aglen, &shape_changed);
 	if (error)
 		goto out_error;
 
 	/*
 	 * Try to merge with the left or right extents of the range.
 	 */
-	error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj,
-			XFS_FIND_RCEXT_COW, &shape_changed);
+	error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno,
+			&aglen, adj, &shape_changed);
 	if (error)
 		goto out_error;
 
@@ -1666,10 +1767,18 @@ xfs_refcount_recover_extent(
 			   be32_to_cpu(rec->refc.rc_refcount) != 1))
 		return -EFSCORRUPTED;
 
-	rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0);
+	rr = kmalloc(sizeof(struct xfs_refcount_recovery),
+			GFP_KERNEL | __GFP_NOFAIL);
+	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
-	list_add_tail(&rr->rr_list, debris);
 
+	if (XFS_IS_CORRUPT(cur->bc_mp,
+			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		kfree(rr);
+		return -EFSCORRUPTED;
+	}
+
+	list_add_tail(&rr->rr_list, debris);
 	return 0;
 }
 
@@ -1687,10 +1796,11 @@ xfs_refcount_recover_cow_leftovers(
 	union xfs_btree_irec		low;
 	union xfs_btree_irec		high;
 	xfs_fsblock_t			fsb;
-	xfs_agblock_t			agbno;
 	int				error;
 
-	if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
+	/* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */
+	BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG);
+	if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS)
 		return -EOPNOTSUPP;
 
 	INIT_LIST_HEAD(&debris);
@@ -1717,7 +1827,7 @@ xfs_refcount_recover_cow_leftovers(
 	/* Find all the leftover CoW staging extents. */
 	memset(&low, 0, sizeof(low));
 	memset(&high, 0, sizeof(high));
-	low.rc.rc_startblock = XFS_REFC_COW_START;
+	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);
@@ -1738,8 +1848,8 @@ xfs_refcount_recover_cow_leftovers(
 				&rr->rr_rrec);
 
 		/* Free the orphan record */
-		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
-		fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno);
+		fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
+				rr->rr_rrec.rc_startblock);
 		xfs_refcount_free_cow_extent(tp, fsb,
 				rr->rr_rrec.rc_blockcount);
 
@@ -1751,7 +1861,7 @@ xfs_refcount_recover_cow_leftovers(
 			goto out_free;
 
 		list_del(&rr->rr_list);
-		kmem_free(rr);
+		kfree(rr);
 	}
 
 	return error;
@@ -1761,7 +1871,7 @@ xfs_refcount_recover_cow_leftovers(
 	/* Free the leftover list */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
 		list_del(&rr->rr_list);
-		kmem_free(rr);
+		kfree(rr);
 	}
 	return error;
 }
@@ -1770,6 +1880,7 @@ xfs_refcount_recover_cow_leftovers(
 int
 xfs_refcount_has_record(
 	struct xfs_btree_cur	*cur,
+	enum xfs_refc_domain	domain,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
 	bool			*exists)
@@ -1781,6 +1892,7 @@ xfs_refcount_has_record(
 	low.rc.rc_startblock = bno;
 	memset(&high, 0xFF, sizeof(high));
 	high.rc.rc_startblock = bno + len - 1;
+	low.rc.rc_domain = high.rc.rc_domain = domain;
 
 	return xfs_btree_has_record(cur, &low, &high, exists);
 }

fs/xfs/libxfs/xfs_refcount.h

@@ -14,14 +14,33 @@ struct xfs_bmbt_irec;
 struct xfs_refcount_irec;
 
 extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur,
-		xfs_agblock_t bno, int *stat);
+		enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
 extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur,
-		xfs_agblock_t bno, int *stat);
+		enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
 extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur,
-		xfs_agblock_t bno, int *stat);
+		enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
 extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);
 
+static inline uint32_t
+xfs_refcount_encode_startblock(
+	xfs_agblock_t		startblock,
+	enum xfs_refc_domain	domain)
+{
+	uint32_t		start;
+
+	/*
+	 * low level btree operations need to handle the generic btree range
+	 * query functions (which set rc_domain == -1U), so we check that the
+	 * domain is /not/ shared.
+	 */
+	start = startblock & ~XFS_REFC_COWFLAG;
+	if (domain != XFS_REFC_DOMAIN_SHARED)
+		start |= XFS_REFC_COWFLAG;
+
+	return start;
+}
+
 enum xfs_refcount_intent_type {
 	XFS_REFCOUNT_INCREASE = 1,
 	XFS_REFCOUNT_DECREASE,
@@ -36,6 +55,18 @@ struct xfs_refcount_intent {
 	xfs_fsblock_t				ri_startblock;
 };
 
+/* Check that the refcount is appropriate for the record domain. */
+static inline bool
+xfs_refcount_check_domain(
+	const struct xfs_refcount_irec	*irec)
+{
+	if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1)
+		return false;
+	if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2)
+		return false;
+	return true;
+}
+
 void xfs_refcount_increase_extent(struct xfs_trans *tp,
 		struct xfs_bmbt_irec *irec);
 void xfs_refcount_decrease_extent(struct xfs_trans *tp,
@@ -79,7 +110,8 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 #define XFS_REFCOUNT_ITEM_OVERHEAD	32
 
 extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
-		xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+		enum xfs_refc_domain domain, xfs_agblock_t bno,
+		xfs_extlen_t len, bool *exists);
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);

fs/xfs/libxfs/xfs_refcount_btree.c

@@ -13,6 +13,7 @@
 #include "xfs_btree.h"
 #include "xfs_btree_staging.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_refcount.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
@@ -160,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec)
 {
-	rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock);
+	const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+	uint32_t		start;
+
+	start = xfs_refcount_encode_startblock(irec->rc_startblock,
+			irec->rc_domain);
+	rec->refc.rc_startblock = cpu_to_be32(start);
 	rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount);
 	rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount);
 }
@@ -182,10 +188,13 @@ xfs_refcountbt_key_diff(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_key	*key)
 {
-	struct xfs_refcount_irec	*rec = &cur->bc_rec.rc;
 	const struct xfs_refcount_key	*kp = &key->refc;
+	const struct xfs_refcount_irec	*irec = &cur->bc_rec.rc;
+	uint32_t			start;
 
-	return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+	start = xfs_refcount_encode_startblock(irec->rc_startblock,
+			irec->rc_domain);
+	return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
 }
 
 STATIC int64_t

fs/xfs/libxfs/xfs_rmap.c

@@ -235,13 +235,8 @@ xfs_rmap_get_rec(
 			goto out_bad_rec;
 	} else {
 		/* check for valid extent range, including overflow */
-		if (!xfs_verify_agbno(pag, irec->rm_startblock))
-			goto out_bad_rec;
-		if (irec->rm_startblock >
-				irec->rm_startblock + irec->rm_blockcount)
-			goto out_bad_rec;
-		if (!xfs_verify_agbno(pag,
-				irec->rm_startblock + irec->rm_blockcount - 1))
+		if (!xfs_verify_agbext(pag, irec->rm_startblock,
+					    irec->rm_blockcount))
 			goto out_bad_rec;
 	}
 

fs/xfs/libxfs/xfs_trans_resv.c

@@ -422,7 +422,7 @@ xfs_calc_itruncate_reservation_minlogsize(
 
 /*
  * In renaming a files we can modify:
- *    the four inodes involved: 4 * inode size
+ *    the five inodes involved: 5 * inode size
  *    the two directory btrees: 2 * (max depth + v2) * dir block size
  *    the two directory bmap btrees: 2 * max depth * block size
  * And the bmap_finish transaction can free dir and bmap blocks (two sets
@@ -437,7 +437,7 @@ xfs_calc_rename_reservation(
 	struct xfs_mount	*mp)
 {
 	return XFS_DQUOT_LOGRES(mp) +
-		max((xfs_calc_inode_res(mp, 4) +
+		max((xfs_calc_inode_res(mp, 5) +
 		     xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
 				      XFS_FSB_TO_B(mp, 1))),
 		    (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +

fs/xfs/libxfs/xfs_types.h

@@ -166,6 +166,36 @@ typedef struct xfs_bmbt_irec
 	xfs_exntst_t	br_state;	/* extent state */
 } xfs_bmbt_irec_t;
 
+enum xfs_refc_domain {
+	XFS_REFC_DOMAIN_SHARED = 0,
+	XFS_REFC_DOMAIN_COW,
+};
+
+#define XFS_REFC_DOMAIN_STRINGS \
+	{ XFS_REFC_DOMAIN_SHARED,	"shared" }, \
+	{ XFS_REFC_DOMAIN_COW,		"cow" }
+
+struct xfs_refcount_irec {
+	xfs_agblock_t	rc_startblock;	/* starting block number */
+	xfs_extlen_t	rc_blockcount;	/* count of free blocks */
+	xfs_nlink_t	rc_refcount;	/* number of inodes linked here */
+	enum xfs_refc_domain	rc_domain; /* shared or cow staging extent? */
+};
+
+#define XFS_RMAP_ATTR_FORK		(1 << 0)
+#define XFS_RMAP_BMBT_BLOCK		(1 << 1)
+#define XFS_RMAP_UNWRITTEN		(1 << 2)
+#define XFS_RMAP_KEY_FLAGS		(XFS_RMAP_ATTR_FORK | \
+					 XFS_RMAP_BMBT_BLOCK)
+#define XFS_RMAP_REC_FLAGS		(XFS_RMAP_UNWRITTEN)
+struct xfs_rmap_irec {
+	xfs_agblock_t	rm_startblock;	/* extent start block */
+	xfs_extlen_t	rm_blockcount;	/* extent length */
+	uint64_t	rm_owner;	/* extent owner */
+	uint64_t	rm_offset;	/* offset within the owner */
+	unsigned int	rm_flags;	/* state flags */
+};
+
 /* per-AG block reservation types */
 enum xfs_ag_resv_type {
 	XFS_AG_RESV_NONE = 0,

fs/xfs/scrub/alloc.c

@@ -100,9 +100,7 @@ xchk_allocbt_rec(
 	bno = be32_to_cpu(rec->alloc.ar_startblock);
 	len = be32_to_cpu(rec->alloc.ar_blockcount);
 
-	if (bno + len <= bno ||
-	    !xfs_verify_agbno(pag, bno) ||
-	    !xfs_verify_agbno(pag, bno + len - 1))
+	if (!xfs_verify_agbext(pag, bno, len))
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	xchk_allocbt_xref(bs->sc, bno, len);

fs/xfs/scrub/ialloc.c

@@ -108,9 +108,8 @@ xchk_iallocbt_chunk(
 	xfs_agblock_t			bno;
 
 	bno = XFS_AGINO_TO_AGBNO(mp, agino);
-	if (bno + len <= bno ||
-	    !xfs_verify_agbno(pag, bno) ||
-	    !xfs_verify_agbno(pag, bno + len - 1))
+
+	if (!xfs_verify_agbext(pag, bno, len))
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);

fs/xfs/scrub/refcount.c

@@ -269,15 +269,13 @@ xchk_refcountbt_process_rmap_fragments(
 STATIC void
 xchk_refcountbt_xref_rmap(
 	struct xfs_scrub		*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	xfs_nlink_t			refcount)
+	const struct xfs_refcount_irec	*irec)
 {
 	struct xchk_refcnt_check	refchk = {
-		.sc = sc,
-		.bno = bno,
-		.len = len,
-		.refcount = refcount,
+		.sc			= sc,
+		.bno			= irec->rc_startblock,
+		.len			= irec->rc_blockcount,
+		.refcount		= irec->rc_refcount,
 		.seen = 0,
 	};
 	struct xfs_rmap_irec		low;
@@ -291,9 +289,9 @@ xchk_refcountbt_xref_rmap(
 
 	/* Cross-reference with the rmapbt to confirm the refcount. */
 	memset(&low, 0, sizeof(low));
-	low.rm_startblock = bno;
+	low.rm_startblock = irec->rc_startblock;
 	memset(&high, 0xFF, sizeof(high));
-	high.rm_startblock = bno + len - 1;
+	high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1;
 
 	INIT_LIST_HEAD(&refchk.fragments);
 	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
@@ -302,7 +300,7 @@ xchk_refcountbt_xref_rmap(
 		goto out_free;
 
 	xchk_refcountbt_process_rmap_fragments(&refchk);
-	if (refcount != refchk.seen)
+	if (irec->rc_refcount != refchk.seen)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 out_free:
@@ -315,17 +313,16 @@ xchk_refcountbt_xref_rmap(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_refcountbt_xref(
-	struct xfs_scrub	*sc,
-	xfs_agblock_t		agbno,
-	xfs_extlen_t		len,
-	xfs_nlink_t		refcount)
+	struct xfs_scrub		*sc,
+	const struct xfs_refcount_irec	*irec)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xchk_xref_is_used_space(sc, agbno, len);
-	xchk_xref_is_not_inode_chunk(sc, agbno, len);
-	xchk_refcountbt_xref_rmap(sc, agbno, len, refcount);
+	xchk_xref_is_used_space(sc, irec->rc_startblock, irec->rc_blockcount);
+	xchk_xref_is_not_inode_chunk(sc, irec->rc_startblock,
+			irec->rc_blockcount);
+	xchk_refcountbt_xref_rmap(sc, irec);
 }
 
 /* Scrub a refcountbt record. */
@@ -334,35 +331,27 @@ xchk_refcountbt_rec(
 	struct xchk_btree	*bs,
 	const union xfs_btree_rec *rec)
 {
+	struct xfs_refcount_irec irec;
 	xfs_agblock_t		*cow_blocks = bs->private;
 	struct xfs_perag	*pag = bs->cur->bc_ag.pag;
-	xfs_agblock_t		bno;
-	xfs_extlen_t		len;
-	xfs_nlink_t		refcount;
-	bool			has_cowflag;
 
-	bno = be32_to_cpu(rec->refc.rc_startblock);
-	len = be32_to_cpu(rec->refc.rc_blockcount);
-	refcount = be32_to_cpu(rec->refc.rc_refcount);
+	xfs_refcount_btrec_to_irec(rec, &irec);
 
-	/* Only CoW records can have refcount == 1. */
-	has_cowflag = (bno & XFS_REFC_COW_START);
-	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
+	/* Check the domain and refcount are not incompatible. */
+	if (!xfs_refcount_check_domain(&irec))
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
-	if (has_cowflag)
-		(*cow_blocks) += len;
+
+	if (irec.rc_domain == XFS_REFC_DOMAIN_COW)
+		(*cow_blocks) += irec.rc_blockcount;
 
 	/* Check the extent. */
-	bno &= ~XFS_REFC_COW_START;
-	if (bno + len <= bno ||
-	    !xfs_verify_agbno(pag, bno) ||
-	    !xfs_verify_agbno(pag, bno + len - 1))
+	if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount))
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	if (refcount == 0)
+	if (irec.rc_refcount == 0)
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xchk_refcountbt_xref(bs->sc, bno, len, refcount);
+	xchk_refcountbt_xref(bs->sc, &irec);
 
 	return 0;
 }
@@ -426,7 +415,6 @@ xchk_xref_is_cow_staging(
 	xfs_extlen_t			len)
 {
 	struct xfs_refcount_irec	rc;
-	bool				has_cowflag;
 	int				has_refcount;
 	int				error;
 
@@ -434,8 +422,8 @@ xchk_xref_is_cow_staging(
 		return;
 
 	/* Find the CoW staging extent. */
-	error = xfs_refcount_lookup_le(sc->sa.refc_cur,
-			agbno + XFS_REFC_COW_START, &has_refcount);
+	error = xfs_refcount_lookup_le(sc->sa.refc_cur, XFS_REFC_DOMAIN_COW,
+			agbno, &has_refcount);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
@@ -451,9 +439,8 @@ xchk_xref_is_cow_staging(
 		return;
 	}
 
-	/* CoW flag must be set, refcount must be 1. */
-	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
-	if (!has_cowflag || rc.rc_refcount != 1)
+	/* CoW lookup returned a shared extent record? */
+	if (rc.rc_domain != XFS_REFC_DOMAIN_COW)
 		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 
 	/* Must be at least as long as what was passed in */
@@ -477,7 +464,8 @@ xchk_xref_is_not_shared(
 	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
-	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
+	error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED,
+			agbno, len, &shared);
 	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (shared)

fs/xfs/xfs_attr_item.c

@@ -245,28 +245,6 @@ xfs_attri_init(
 	return attrip;
 }
 
-/*
- * Copy an attr format buffer from the given buf, and into the destination attr
- * format structure.
- */
-STATIC int
-xfs_attri_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_attri_log_format	*dst_attr_fmt)
-{
-	struct xfs_attri_log_format	*src_attr_fmt = buf->i_addr;
-	size_t				len;
-
-	len = sizeof(struct xfs_attri_log_format);
-	if (buf->i_len != len) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-		return -EFSCORRUPTED;
-	}
-
-	memcpy((char *)dst_attr_fmt, (char *)src_attr_fmt, len);
-	return 0;
-}
-
 static inline struct xfs_attrd_log_item *ATTRD_ITEM(struct xfs_log_item *lip)
 {
 	return container_of(lip, struct xfs_attrd_log_item, attrd_item);
@@ -731,24 +709,50 @@ xlog_recover_attri_commit_pass2(
 	struct xfs_attri_log_nameval	*nv;
 	const void			*attr_value = NULL;
 	const void			*attr_name;
-	int                             error;
+	size_t				len;
 
 	attri_formatp = item->ri_buf[0].i_addr;
 	attr_name = item->ri_buf[1].i_addr;
 
 	/* Validate xfs_attri_log_format before the large memory allocation */
+	len = sizeof(struct xfs_attri_log_format);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
 	if (!xfs_attri_validate(mp, attri_formatp)) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	/* Validate the attr name */
+	if (item->ri_buf[1].i_len !=
+			xlog_calc_iovec_len(attri_formatp->alfi_name_len)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
 		return -EFSCORRUPTED;
 	}
 
 	if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[1].i_addr, item->ri_buf[1].i_len);
 		return -EFSCORRUPTED;
 	}
 
-	if (attri_formatp->alfi_value_len)
+	/* Validate the attr value, if present */
+	if (attri_formatp->alfi_value_len != 0) {
+		if (item->ri_buf[2].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					item->ri_buf[0].i_addr,
+					item->ri_buf[0].i_len);
+			return -EFSCORRUPTED;
+		}
+
 		attr_value = item->ri_buf[2].i_addr;
+	}
 
 	/*
 	 * Memory alloc failure will cause replay to abort.  We attach the
@@ -760,9 +764,7 @@ xlog_recover_attri_commit_pass2(
 			attri_formatp->alfi_value_len);
 
 	attrip = xfs_attri_init(mp, nv);
-	error = xfs_attri_copy_format(&item->ri_buf[0], &attrip->attri_format);
-	if (error)
-		goto out;
+	memcpy(&attrip->attri_format, attri_formatp, len);
 
 	/*
 	 * The ATTRI has two references. One for the ATTRD and one for ATTRI to
@@ -774,10 +776,6 @@ xlog_recover_attri_commit_pass2(
 	xfs_attri_release(attrip);
 	xfs_attri_log_nameval_put(nv);
 	return 0;
-out:
-	xfs_attri_item_free(attrip);
-	xfs_attri_log_nameval_put(nv);
-	return error;
 }
 
 /*
@@ -842,7 +840,8 @@ xlog_recover_attrd_commit_pass2(
 
 	attrd_formatp = item->ri_buf[0].i_addr;
 	if (item->ri_buf[0].i_len != sizeof(struct xfs_attrd_log_format)) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
 		return -EFSCORRUPTED;
 	}
 

fs/xfs/xfs_bmap_item.c

@@ -608,28 +608,18 @@ static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_relog	= xfs_bui_item_relog,
 };
 
-/*
- * Copy an BUI format buffer from the given buf, and into the destination
- * BUI format structure.  The BUI/BUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
 xfs_bui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_bui_log_format	*dst_bui_fmt)
+	struct xfs_bui_log_format	*dst,
+	const struct xfs_bui_log_format	*src)
 {
-	struct xfs_bui_log_format	*src_bui_fmt;
-	uint				len;
+	unsigned int			i;
 
-	src_bui_fmt = buf->i_addr;
-	len = xfs_bui_log_format_sizeof(src_bui_fmt->bui_nextents);
+	memcpy(dst, src, offsetof(struct xfs_bui_log_format, bui_extents));
 
-	if (buf->i_len == len) {
-		memcpy(dst_bui_fmt, src_bui_fmt, len);
-		return 0;
-	}
-	XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-	return -EFSCORRUPTED;
+	for (i = 0; i < src->bui_nextents; i++)
+		memcpy(&dst->bui_extents[i], &src->bui_extents[i],
+				sizeof(struct xfs_map_extent));
 }
 
 /*
@@ -646,23 +636,34 @@ xlog_recover_bui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_bui_log_item		*buip;
 	struct xfs_bui_log_format	*bui_formatp;
+	size_t				len;
 
 	bui_formatp = item->ri_buf[0].i_addr;
 
+	if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
 	if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
 		return -EFSCORRUPTED;
 	}
-	buip = xfs_bui_init(mp);
-	error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format);
-	if (error) {
-		xfs_bui_item_free(buip);
-		return error;
+
+	len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
 	}
+
+	buip = xfs_bui_init(mp);
+	xfs_bui_copy_format(&buip->bui_format, bui_formatp);
 	atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so
@@ -696,7 +697,8 @@ xlog_recover_bud_commit_pass2(
 
 	bud_formatp = item->ri_buf[0].i_addr;
 	if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
 		return -EFSCORRUPTED;
 	}
 

fs/xfs/xfs_error.c

@@ -234,13 +234,18 @@ int
 xfs_errortag_init(
 	struct xfs_mount	*mp)
 {
+	int ret;
+
 	mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX,
 			KM_MAYFAIL);
 	if (!mp->m_errortag)
 		return -ENOMEM;
 
-	return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
-			       &mp->m_kobj, "errortag");
+	ret = xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
+				&mp->m_kobj, "errortag");
+	if (ret)
+		kmem_free(mp->m_errortag);
+	return ret;
 }
 
 void

fs/xfs/xfs_extfree_item.c

@@ -66,27 +66,16 @@ xfs_efi_release(
 	xfs_efi_item_free(efip);
 }
 
-/*
- * This returns the number of iovecs needed to log the given efi item.
- * We only need 1 iovec for an efi item.  It just logs the efi_log_format
- * structure.
- */
-static inline int
-xfs_efi_item_sizeof(
-	struct xfs_efi_log_item *efip)
-{
-	return sizeof(struct xfs_efi_log_format) +
-	       (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t);
-}
-
 STATIC void
 xfs_efi_item_size(
 	struct xfs_log_item	*lip,
 	int			*nvecs,
 	int			*nbytes)
 {
+	struct xfs_efi_log_item	*efip = EFI_ITEM(lip);
+
 	*nvecs += 1;
-	*nbytes += xfs_efi_item_sizeof(EFI_ITEM(lip));
+	*nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents);
 }
 
 /*
@@ -112,7 +101,7 @@ xfs_efi_item_format(
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT,
 			&efip->efi_format,
-			xfs_efi_item_sizeof(efip));
+			xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents));
 }
 
 
@@ -155,13 +144,11 @@ xfs_efi_init(
 
 {
 	struct xfs_efi_log_item	*efip;
-	uint			size;
 
 	ASSERT(nextents > 0);
 	if (nextents > XFS_EFI_MAX_FAST_EXTENTS) {
-		size = (uint)(sizeof(struct xfs_efi_log_item) +
-			((nextents - 1) * sizeof(xfs_extent_t)));
-		efip = kmem_zalloc(size, 0);
+		efip = kzalloc(xfs_efi_log_item_sizeof(nextents),
+				GFP_KERNEL | __GFP_NOFAIL);
 	} else {
 		efip = kmem_cache_zalloc(xfs_efi_cache,
 					 GFP_KERNEL | __GFP_NOFAIL);
@@ -188,15 +175,17 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
 {
 	xfs_efi_log_format_t *src_efi_fmt = buf->i_addr;
 	uint i;
-	uint len = sizeof(xfs_efi_log_format_t) +
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t);
-	uint len32 = sizeof(xfs_efi_log_format_32_t) +
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t);
-	uint len64 = sizeof(xfs_efi_log_format_64_t) +
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t);
+	uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents);
+	uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents);
+	uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents);
 
 	if (buf->i_len == len) {
-		memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len);
+		memcpy(dst_efi_fmt, src_efi_fmt,
+		       offsetof(struct xfs_efi_log_format, efi_extents));
+		for (i = 0; i < src_efi_fmt->efi_nextents; i++)
+			memcpy(&dst_efi_fmt->efi_extents[i],
+			       &src_efi_fmt->efi_extents[i],
+			       sizeof(struct xfs_extent));
 		return 0;
 	} else if (buf->i_len == len32) {
 		xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr;
@@ -227,7 +216,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
 		}
 		return 0;
 	}
-	XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+	XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr,
+			buf->i_len);
 	return -EFSCORRUPTED;
 }
 
@@ -246,27 +236,16 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp)
 		kmem_cache_free(xfs_efd_cache, efdp);
 }
 
-/*
- * This returns the number of iovecs needed to log the given efd item.
- * We only need 1 iovec for an efd item.  It just logs the efd_log_format
- * structure.
- */
-static inline int
-xfs_efd_item_sizeof(
-	struct xfs_efd_log_item *efdp)
-{
-	return sizeof(xfs_efd_log_format_t) +
-	       (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t);
-}
-
 STATIC void
 xfs_efd_item_size(
 	struct xfs_log_item	*lip,
 	int			*nvecs,
 	int			*nbytes)
 {
+	struct xfs_efd_log_item	*efdp = EFD_ITEM(lip);
+
 	*nvecs += 1;
-	*nbytes += xfs_efd_item_sizeof(EFD_ITEM(lip));
+	*nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents);
 }
 
 /*
@@ -291,7 +270,7 @@ xfs_efd_item_format(
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT,
 			&efdp->efd_format,
-			xfs_efd_item_sizeof(efdp));
+			xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents));
 }
 
 /*
@@ -340,9 +319,8 @@ xfs_trans_get_efd(
 	ASSERT(nextents > 0);
 
 	if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
-		efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) +
-				(nextents - 1) * sizeof(struct xfs_extent),
-				0);
+		efdp = kzalloc(xfs_efd_log_item_sizeof(nextents),
+				GFP_KERNEL | __GFP_NOFAIL);
 	} else {
 		efdp = kmem_cache_zalloc(xfs_efd_cache,
 					GFP_KERNEL | __GFP_NOFAIL);
@@ -733,6 +711,12 @@ xlog_recover_efi_commit_pass2(
 
 	efi_formatp = item->ri_buf[0].i_addr;
 
+	if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
 	efip = xfs_efi_init(mp, efi_formatp->efi_nextents);
 	error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format);
 	if (error) {
@@ -769,12 +753,24 @@ xlog_recover_efd_commit_pass2(
 	xfs_lsn_t			lsn)
 {
 	struct xfs_efd_log_format	*efd_formatp;
+	int				buflen = item->ri_buf[0].i_len;
 
 	efd_formatp = item->ri_buf[0].i_addr;
-	ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) +
-		((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) ||
-	       (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) +
-		((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t)))));
+
+	if (buflen < sizeof(struct xfs_efd_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				efd_formatp, buflen);
+		return -EFSCORRUPTED;
+	}
+
+	if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof(
+						efd_formatp->efd_nextents) &&
+	    item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof(
+						efd_formatp->efd_nextents)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				efd_formatp, buflen);
+		return -EFSCORRUPTED;
+	}
 
 	xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id);
 	return 0;

fs/xfs/xfs_extfree_item.h

@@ -52,6 +52,14 @@ struct xfs_efi_log_item {
 	xfs_efi_log_format_t	efi_format;
 };
 
+static inline size_t
+xfs_efi_log_item_sizeof(
+	unsigned int		nr)
+{
+	return offsetof(struct xfs_efi_log_item, efi_format) +
+			xfs_efi_log_format_sizeof(nr);
+}
+
 /*
  * This is the "extent free done" log item.  It is used to log
  * the fact that some extents earlier mentioned in an efi item
@@ -64,6 +72,14 @@ struct xfs_efd_log_item {
 	xfs_efd_log_format_t	efd_format;
 };
 
+static inline size_t
+xfs_efd_log_item_sizeof(
+	unsigned int		nr)
+{
+	return offsetof(struct xfs_efd_log_item, efd_format) +
+			xfs_efd_log_format_sizeof(nr);
+}
+
 /*
  * Max number of extents in fast allocation path.
  */

fs/xfs/xfs_file.c

@@ -1261,7 +1261,7 @@ xfs_file_llseek(
 }
 
 #ifdef CONFIG_FS_DAX
-static int
+static inline vm_fault_t
 xfs_dax_fault(
 	struct vm_fault		*vmf,
 	enum page_entry_size	pe_size,
@@ -1274,14 +1274,15 @@ xfs_dax_fault(
 				&xfs_read_iomap_ops);
 }
 #else
-static int
+static inline vm_fault_t
 xfs_dax_fault(
 	struct vm_fault		*vmf,
 	enum page_entry_size	pe_size,
 	bool			write_fault,
 	pfn_t			*pfn)
 {
-	return 0;
+	ASSERT(0);
+	return VM_FAULT_SIGBUS;
 }
 #endif
 

fs/xfs/xfs_inode.c

@@ -2818,7 +2818,7 @@ xfs_rename(
 	 * Lock all the participating inodes. Depending upon whether
 	 * the target_name exists in the target directory, and
 	 * whether the target directory is the same as the source
-	 * directory, we can lock from 2 to 4 inodes.
+	 * directory, we can lock from 2 to 5 inodes.
 	 */
 	xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL);
 

fs/xfs/xfs_log_recover.c

@@ -2552,6 +2552,8 @@ xlog_recover_process_intents(
 	for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 	     lip != NULL;
 	     lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
+		const struct xfs_item_ops	*ops;
+
 		if (!xlog_item_is_intent(lip))
 			break;
 
@@ -2567,13 +2569,17 @@ xlog_recover_process_intents(
 		 * 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!
+		 *
+		 * The recovery function can free the log item, so we must not
+		 * access lip after it returns.
 		 */
 		spin_unlock(&ailp->ail_lock);
-		error = lip->li_ops->iop_recover(lip, &capture_list);
+		ops = lip->li_ops;
+		error = ops->iop_recover(lip, &capture_list);
 		spin_lock(&ailp->ail_lock);
 		if (error) {
 			trace_xlog_intent_recovery_failed(log->l_mp, error,
-					lip->li_ops->iop_recover);
+					ops->iop_recover);
 			break;
 		}
 	}

fs/xfs/xfs_ondisk.h

@@ -118,10 +118,10 @@ xfs_check_ondisk_structs(void)
 	/* log structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	28);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32,		12);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
@@ -134,6 +134,21 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format,	40);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent,		16);
+
+	XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents,	16);
 
 	/*
 	 * The v5 superblock format extended several v4 header structures with

fs/xfs/xfs_refcount_item.c

@@ -523,7 +523,9 @@ xfs_cui_item_recover(
 			type = refc_type;
 			break;
 		default:
-			XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					&cuip->cui_format,
+					sizeof(cuip->cui_format));
 			error = -EFSCORRUPTED;
 			goto abort_error;
 		}
@@ -536,7 +538,8 @@ xfs_cui_item_recover(
 				&new_fsb, &new_len, &rcur);
 		if (error == -EFSCORRUPTED)
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					refc, sizeof(*refc));
+					&cuip->cui_format,
+					sizeof(cuip->cui_format));
 		if (error)
 			goto abort_error;
 
@@ -622,28 +625,18 @@ static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_relog	= xfs_cui_item_relog,
 };
 
-/*
- * Copy an CUI format buffer from the given buf, and into the destination
- * CUI format structure.  The CUI/CUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
 xfs_cui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_cui_log_format	*dst_cui_fmt)
+	struct xfs_cui_log_format	*dst,
+	const struct xfs_cui_log_format	*src)
 {
-	struct xfs_cui_log_format	*src_cui_fmt;
-	uint				len;
+	unsigned int			i;
 
-	src_cui_fmt = buf->i_addr;
-	len = xfs_cui_log_format_sizeof(src_cui_fmt->cui_nextents);
+	memcpy(dst, src, offsetof(struct xfs_cui_log_format, cui_extents));
 
-	if (buf->i_len == len) {
-		memcpy(dst_cui_fmt, src_cui_fmt, len);
-		return 0;
-	}
-	XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-	return -EFSCORRUPTED;
+	for (i = 0; i < src->cui_nextents; i++)
+		memcpy(&dst->cui_extents[i], &src->cui_extents[i],
+				sizeof(struct xfs_phys_extent));
 }
 
 /*
@@ -660,19 +653,28 @@ xlog_recover_cui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_cui_log_item		*cuip;
 	struct xfs_cui_log_format	*cui_formatp;
+	size_t				len;
 
 	cui_formatp = item->ri_buf[0].i_addr;
 
-	cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
-	error = xfs_cui_copy_format(&item->ri_buf[0], &cuip->cui_format);
-	if (error) {
-		xfs_cui_item_free(cuip);
-		return error;
+	if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
 	}
+
+	len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
+	xfs_cui_copy_format(&cuip->cui_format, cui_formatp);
 	atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so
@@ -706,7 +708,8 @@ xlog_recover_cud_commit_pass2(
 
 	cud_formatp = item->ri_buf[0].i_addr;
 	if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
 		return -EFSCORRUPTED;
 	}
 

fs/xfs/xfs_rmap_item.c

@@ -155,31 +155,6 @@ xfs_rui_init(
 	return ruip;
 }
 
-/*
- * Copy an RUI format buffer from the given buf, and into the destination
- * RUI format structure.  The RUI/RUD items were designed not to need any
- * special alignment handling.
- */
-STATIC int
-xfs_rui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_rui_log_format	*dst_rui_fmt)
-{
-	struct xfs_rui_log_format	*src_rui_fmt;
-	uint				len;
-
-	src_rui_fmt = buf->i_addr;
-	len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents);
-
-	if (buf->i_len != len) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-		return -EFSCORRUPTED;
-	}
-
-	memcpy(dst_rui_fmt, src_rui_fmt, len);
-	return 0;
-}
-
 static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip)
 {
 	return container_of(lip, struct xfs_rud_log_item, rud_item);
@@ -582,7 +557,9 @@ xfs_rui_item_recover(
 			type = XFS_RMAP_FREE;
 			break;
 		default:
-			XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					&ruip->rui_format,
+					sizeof(ruip->rui_format));
 			error = -EFSCORRUPTED;
 			goto abort_error;
 		}
@@ -652,6 +629,20 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_relog	= xfs_rui_item_relog,
 };
 
+static inline void
+xfs_rui_copy_format(
+	struct xfs_rui_log_format	*dst,
+	const struct xfs_rui_log_format	*src)
+{
+	unsigned int			i;
+
+	memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents));
+
+	for (i = 0; i < src->rui_nextents; i++)
+		memcpy(&dst->rui_extents[i], &src->rui_extents[i],
+				sizeof(struct xfs_map_extent));
+}
+
 /*
  * This routine is called to create an in-core extent rmap update
  * item from the rui format structure which was logged on disk.
@@ -666,19 +657,28 @@ xlog_recover_rui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_rui_log_item		*ruip;
 	struct xfs_rui_log_format	*rui_formatp;
+	size_t				len;
 
 	rui_formatp = item->ri_buf[0].i_addr;
 
-	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
-	error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format);
-	if (error) {
-		xfs_rui_item_free(ruip);
-		return error;
+	if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
 	}
+
+	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
+	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
 	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so
@@ -711,7 +711,11 @@ xlog_recover_rud_commit_pass2(
 	struct xfs_rud_log_format	*rud_formatp;
 
 	rud_formatp = item->ri_buf[0].i_addr;
-	ASSERT(item->ri_buf[0].i_len == sizeof(struct xfs_rud_log_format));
+	if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				rud_formatp, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
 
 	xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id);
 	return 0;

fs/xfs/xfs_super.c

@@ -2028,18 +2028,14 @@ xfs_init_caches(void)
 		goto out_destroy_trans_cache;
 
 	xfs_efd_cache = kmem_cache_create("xfs_efd_item",
-					(sizeof(struct xfs_efd_log_item) +
-					(XFS_EFD_MAX_FAST_EXTENTS - 1) *
-					sizeof(struct xfs_extent)),
-					0, 0, NULL);
+			xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS),
+			0, 0, NULL);
 	if (!xfs_efd_cache)
 		goto out_destroy_buf_item_cache;
 
 	xfs_efi_cache = kmem_cache_create("xfs_efi_item",
-					 (sizeof(struct xfs_efi_log_item) +
-					 (XFS_EFI_MAX_FAST_EXTENTS - 1) *
-					 sizeof(struct xfs_extent)),
-					 0, 0, NULL);
+			xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS),
+			0, 0, NULL);
 	if (!xfs_efi_cache)
 		goto out_destroy_efd_cache;
 

fs/xfs/xfs_sysfs.h

@@ -33,10 +33,15 @@ xfs_sysfs_init(
 	const char		*name)
 {
 	struct kobject		*parent;
+	int err;
 
 	parent = parent_kobj ? &parent_kobj->kobject : NULL;
 	init_completion(&kobj->complete);
-	return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name);
+	err = kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name);
+	if (err)
+		kobject_put(&kobj->kobject);
+
+	return err;
 }
 
 static inline void

fs/xfs/xfs_trace.h

@@ -799,6 +799,9 @@ TRACE_DEFINE_ENUM(PE_SIZE_PTE);
 TRACE_DEFINE_ENUM(PE_SIZE_PMD);
 TRACE_DEFINE_ENUM(PE_SIZE_PUD);
 
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
+
 TRACE_EVENT(xfs_filemap_fault,
 	TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size,
 		 bool write_fault),
@@ -2925,6 +2928,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
 		__field(xfs_nlink_t, refcount)
@@ -2932,13 +2936,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
 		__entry->refcount = irec->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount)
@@ -2958,6 +2964,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
 		__field(xfs_nlink_t, refcount)
@@ -2966,14 +2973,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
 		__entry->refcount = irec->rc_refcount;
 		__entry->agbno = agbno;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount,
@@ -2994,9 +3003,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
@@ -3004,20 +3015,24 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount)
@@ -3038,9 +3053,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
@@ -3049,21 +3066,25 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
 		__entry->agbno = agbno;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount,
@@ -3086,12 +3107,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
+		__field(enum xfs_refc_domain, i3_domain)
 		__field(xfs_agblock_t, i3_startblock)
 		__field(xfs_extlen_t, i3_blockcount)
 		__field(xfs_nlink_t, i3_refcount)
@@ -3099,27 +3123,33 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
+		__entry->i3_domain = i3->rc_domain;
 		__entry->i3_startblock = i3->rc_startblock;
 		__entry->i3_blockcount = i3->rc_blockcount;
 		__entry->i3_refcount = i3->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount,
+		  __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i3_startblock,
 		  __entry->i3_blockcount,
 		  __entry->i3_refcount)

fs/xfs/xfs_trans_ail.c

@@ -730,11 +730,10 @@ void
 xfs_ail_push_all_sync(
 	struct xfs_ail  *ailp)
 {
-	struct xfs_log_item	*lip;
 	DEFINE_WAIT(wait);
 
 	spin_lock(&ailp->ail_lock);
-	while ((lip = xfs_ail_max(ailp)) != NULL) {
+	while (xfs_ail_max(ailp) != NULL) {
 		prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE);
 		wake_up_process(ailp->ail_task);
 		spin_unlock(&ailp->ail_lock);