From 95f0b95e2b686ceaa3f465e9fa079f22e0fe7665 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Mon, 9 Aug 2021 12:05:22 +0530
Subject: xfs: Define max extent length based on on-disk format definition

The maximum extent length depends on maximum block count that can be stored in
a BMBT record. Hence this commit defines MAXEXTLEN based on
BMBT_BLOCKCOUNT_BITLEN.

While at it, the commit also renames MAXEXTLEN to XFS_MAX_BMBT_EXTLEN.

Suggested-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 57 ++++++++++++++++++++++++------------------------
 1 file changed, 29 insertions(+), 28 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 74198dd82b03..00b8e6e1c404 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1452,7 +1452,7 @@ xfs_bmap_add_extent_delay_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -1470,13 +1470,13 @@ xfs_bmap_add_extent_delay_real(
 	    new_endoff == RIGHT.br_startoff &&
 	    new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
 	    new->br_state == RIGHT.br_state &&
-	    new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
+	    new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING)) !=
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= MAXEXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -2000,7 +2000,7 @@ xfs_bmap_add_extent_unwritten_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -2018,13 +2018,13 @@ xfs_bmap_add_extent_unwritten_real(
 	    new_endoff == RIGHT.br_startoff &&
 	    new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
 	    new->br_state == RIGHT.br_state &&
-	    new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
+	    new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING)) !=
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= MAXEXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2510,15 +2510,15 @@ xfs_bmap_add_extent_hole_delay(
 	 */
 	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
-	    left.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
 	    new->br_startoff + new->br_blockcount == right.br_startoff &&
-	    new->br_blockcount + right.br_blockcount <= MAXEXTLEN &&
+	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     (left.br_blockcount + new->br_blockcount +
-	      right.br_blockcount <= MAXEXTLEN)))
+	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2661,17 +2661,17 @@ xfs_bmap_add_extent_hole_real(
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
 	    left.br_startblock + left.br_blockcount == new->br_startblock &&
 	    left.br_state == new->br_state &&
-	    left.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
 	    new->br_startoff + new->br_blockcount == right.br_startoff &&
 	    new->br_startblock + new->br_blockcount == right.br_startblock &&
 	    new->br_state == right.br_state &&
-	    new->br_blockcount + right.br_blockcount <= MAXEXTLEN &&
+	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     left.br_blockcount + new->br_blockcount +
-	     right.br_blockcount <= MAXEXTLEN))
+	     right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -2906,15 +2906,15 @@ xfs_bmap_extsize_align(
 
 	/*
 	 * For large extent hint sizes, the aligned extent might be larger than
-	 * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
-	 * the length back under MAXEXTLEN. The outer allocation loops handle
-	 * short allocation just fine, so it is safe to do this. We only want to
-	 * do it when we are forced to, though, because it means more allocation
-	 * operations are required.
+	 * XFS_BMBT_MAX_EXTLEN. In that case, reduce the size by an extsz so
+	 * that it pulls the length back under XFS_BMBT_MAX_EXTLEN. The outer
+	 * allocation loops handle short allocation just fine, so it is safe to
+	 * do this. We only want to do it when we are forced to, though, because
+	 * it means more allocation operations are required.
 	 */
-	while (align_alen > MAXEXTLEN)
+	while (align_alen > XFS_MAX_BMBT_EXTLEN)
 		align_alen -= extsz;
-	ASSERT(align_alen <= MAXEXTLEN);
+	ASSERT(align_alen <= XFS_MAX_BMBT_EXTLEN);
 
 	/*
 	 * If the previous block overlaps with this proposed allocation
@@ -3004,9 +3004,9 @@ xfs_bmap_extsize_align(
 			return -EINVAL;
 	} else {
 		ASSERT(orig_off >= align_off);
-		/* see MAXEXTLEN handling above */
+		/* see XFS_BMBT_MAX_EXTLEN handling above */
 		ASSERT(orig_end <= align_off + align_alen ||
-		       align_alen + extsz > MAXEXTLEN);
+		       align_alen + extsz > XFS_MAX_BMBT_EXTLEN);
 	}
 
 #ifdef DEBUG
@@ -3971,7 +3971,7 @@ xfs_bmapi_reserve_delalloc(
 	 * Cap the alloc length. Keep track of prealloc so we know whether to
 	 * tag the inode before we return.
 	 */
-	alen = XFS_FILBLKS_MIN(len + prealloc, MAXEXTLEN);
+	alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
 	if (!eof)
 		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
 	if (prealloc && alen >= len)
@@ -4104,7 +4104,7 @@ xfs_bmapi_allocate(
 		if (!xfs_iext_peek_prev_extent(ifp, &bma->icur, &bma->prev))
 			bma->prev.br_startoff = NULLFILEOFF;
 	} else {
-		bma->length = XFS_FILBLKS_MIN(bma->length, MAXEXTLEN);
+		bma->length = XFS_FILBLKS_MIN(bma->length, XFS_MAX_BMBT_EXTLEN);
 		if (!bma->eof)
 			bma->length = XFS_FILBLKS_MIN(bma->length,
 					bma->got.br_startoff - bma->offset);
@@ -4424,8 +4424,8 @@ xfs_bmapi_write(
 			 * xfs_extlen_t and therefore 32 bits. Hence we have to
 			 * check for 32-bit overflows and handle them here.
 			 */
-			if (len > (xfs_filblks_t)MAXEXTLEN)
-				bma.length = MAXEXTLEN;
+			if (len > (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN)
+				bma.length = XFS_MAX_BMBT_EXTLEN;
 			else
 				bma.length = len;
 
@@ -4560,7 +4560,8 @@ xfs_bmapi_convert_delalloc(
 	bma.ip = ip;
 	bma.wasdel = true;
 	bma.offset = bma.got.br_startoff;
-	bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount, MAXEXTLEN);
+	bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount,
+			XFS_MAX_BMBT_EXTLEN);
 	bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
 
 	/*
@@ -4641,7 +4642,7 @@ xfs_bmapi_remap(
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(len > 0);
-	ASSERT(len <= (xfs_filblks_t)MAXEXTLEN);
+	ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC |
 			   XFS_BMAPI_NORMAP)));
@@ -5641,7 +5642,7 @@ xfs_bmse_can_merge(
 	if ((left->br_startoff + left->br_blockcount != startoff) ||
 	    (left->br_startblock + left->br_blockcount != got->br_startblock) ||
 	    (left->br_state != got->br_state) ||
-	    (left->br_blockcount + got->br_blockcount > MAXEXTLEN))
+	    (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN))
 		return false;
 
 	return true;
-- 
cgit v1.2.3


From 9feb8f19665c8ba051c6a81aa7897149e7748e1e Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Thu, 27 Aug 2020 15:09:10 +0530
Subject: xfs: Introduce xfs_iext_max_nextents() helper

xfs_iext_max_nextents() returns the maximum number of extents possible for one
of data, cow or attribute fork. This helper will be extended further in a
future commit when maximum extent counts associated with data/attribute forks
are increased.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 9 ++++-----
 fs/xfs/libxfs/xfs_inode_buf.c  | 8 +++-----
 fs/xfs/libxfs/xfs_inode_fork.c | 2 +-
 fs/xfs/libxfs/xfs_inode_fork.h | 8 ++++++++
 4 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 00b8e6e1c404..a713bc7242a4 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -74,13 +74,12 @@ xfs_bmap_compute_maxlevels(
 	 * ATTR2 we have to assume the worst case scenario of a minimum size
 	 * available.
 	 */
-	if (whichfork == XFS_DATA_FORK) {
-		maxleafents = MAXEXTNUM;
+	maxleafents = xfs_iext_max_nextents(whichfork);
+	if (whichfork == XFS_DATA_FORK)
 		sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
-	} else {
-		maxleafents = MAXAEXTNUM;
+	else
 		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
-	}
+
 	maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
 	minnoderecs = mp->m_bmap_dmnr[1];
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 87781a5d5a45..b1c37a82ddce 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -337,6 +337,7 @@ xfs_dinode_verify_fork(
 	int			whichfork)
 {
 	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+	xfs_extnum_t		max_extents;
 
 	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -358,12 +359,9 @@ xfs_dinode_verify_fork(
 			return __this_address;
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		if (whichfork == XFS_ATTR_FORK) {
-			if (di_nextents > MAXAEXTNUM)
-				return __this_address;
-		} else if (di_nextents > MAXEXTNUM) {
+		max_extents = xfs_iext_max_nextents(whichfork);
+		if (di_nextents > max_extents)
 			return __this_address;
-		}
 		break;
 	default:
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 9149f4f796fc..e136c29a0ec1 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -744,7 +744,7 @@ xfs_iext_count_may_overflow(
 	if (whichfork == XFS_COW_FORK)
 		return 0;
 
-	max_exts = (whichfork == XFS_ATTR_FORK) ? MAXAEXTNUM : MAXEXTNUM;
+	max_exts = xfs_iext_max_nextents(whichfork);
 
 	if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
 		max_exts = 10;
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 3d64a3acb0ed..2605f7ff8fc1 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -133,6 +133,14 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
 	return ifp->if_format;
 }
 
+static inline xfs_extnum_t xfs_iext_max_nextents(int whichfork)
+{
+	if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK)
+		return MAXEXTNUM;
+
+	return MAXAEXTNUM;
+}
+
 struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format,
 				xfs_extnum_t nextents);
 struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
-- 
cgit v1.2.3


From bb1d50494cbdd9c5991ddc7feeeb14982872b2a8 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Fri, 26 Feb 2021 11:24:31 +0530
Subject: xfs: Use xfs_extnum_t instead of basic data types

xfs_extnum_t is the type to use to declare variables which have values
obtained from xfs_dinode->di_[a]nextents. This commit replaces basic
types (e.g. uint32_t) with xfs_extnum_t for such variables.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 2 +-
 fs/xfs/libxfs/xfs_inode_buf.c  | 2 +-
 fs/xfs/libxfs/xfs_inode_fork.c | 2 +-
 fs/xfs/scrub/inode.c           | 2 +-
 fs/xfs/xfs_trace.h             | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a713bc7242a4..cc15981b1793 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -54,7 +54,7 @@ xfs_bmap_compute_maxlevels(
 {
 	int		level;		/* btree level */
 	uint		maxblocks;	/* max blocks at this level */
-	uint		maxleafents;	/* max leaf entries possible */
+	xfs_extnum_t	maxleafents;	/* max leaf entries possible */
 	int		maxrootrecs;	/* max records in root block */
 	int		minleafrecs;	/* min records in leaf block */
 	int		minnoderecs;	/* min records in node block */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index b1c37a82ddce..7cad307840b3 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -336,7 +336,7 @@ xfs_dinode_verify_fork(
 	struct xfs_mount	*mp,
 	int			whichfork)
 {
-	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+	xfs_extnum_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
 	xfs_extnum_t		max_extents;
 
 	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index e136c29a0ec1..a17c4d87520a 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -105,7 +105,7 @@ xfs_iformat_extents(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	int			state = xfs_bmap_fork_to_state(whichfork);
-	int			nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+	xfs_extnum_t		nex = XFS_DFORK_NEXTENTS(dip, whichfork);
 	int			size = nex * sizeof(xfs_bmbt_rec_t);
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_rec	*dp;
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index eac15af7b08c..87925761e174 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -232,7 +232,7 @@ xchk_dinode(
 	size_t			fork_recs;
 	unsigned long long	isize;
 	uint64_t		flags2;
-	uint32_t		nextents;
+	xfs_extnum_t		nextents;
 	prid_t			prid;
 	uint16_t		flags;
 	uint16_t		mode;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b141ef78c755..16a91b4f97bd 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2169,7 +2169,7 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 		__field(int, which)
 		__field(xfs_ino_t, ino)
 		__field(int, format)
-		__field(int, nex)
+		__field(xfs_extnum_t, nex)
 		__field(int, broot_size)
 		__field(int, fork_off)
 	),
-- 
cgit v1.2.3


From 755c38ffe1a5937d8fa03419018f49f3a23fa9a7 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Tue, 16 Nov 2021 07:28:40 +0000
Subject: xfs: Promote xfs_extnum_t and xfs_aextnum_t to 64 and 32-bits
 respectively

A future commit will introduce a 64-bit on-disk data extent counter and a
32-bit on-disk attr extent counter. This commit promotes xfs_extnum_t and
xfs_aextnum_t to 64 and 32-bits in order to correctly handle in-core versions
of these quantities.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 4 ++--
 fs/xfs/libxfs/xfs_inode_fork.c | 4 ++--
 fs/xfs/libxfs/xfs_inode_fork.h | 2 +-
 fs/xfs/libxfs/xfs_types.h      | 4 ++--
 fs/xfs/xfs_inode.c             | 4 ++--
 fs/xfs/xfs_trace.h             | 2 +-
 6 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index cc15981b1793..9f38e33d6ce2 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -83,7 +83,7 @@ xfs_bmap_compute_maxlevels(
 	maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
 	minnoderecs = mp->m_bmap_dmnr[1];
-	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
+	maxblocks = howmany_64(maxleafents, minleafrecs);
 	for (level = 1; maxblocks > 1; level++) {
 		if (maxblocks <= maxrootrecs)
 			maxblocks = 1;
@@ -467,7 +467,7 @@ error0:
 	if (bp_release)
 		xfs_trans_brelse(NULL, bp);
 error_norelse:
-	xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
+	xfs_warn(mp, "%s: BAD after btree leaves for %llu extents",
 		__func__, i);
 	xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 1cf48cee45e3..004b205d87b8 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -117,8 +117,8 @@ xfs_iformat_extents(
 	 * we just bail out rather than crash in kmem_alloc() or memcpy() below.
 	 */
 	if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
-		xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
-			(unsigned long long) ip->i_ino, nex);
+		xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).",
+			ip->i_ino, nex);
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_extents(1)", dip, sizeof(*dip),
 				__this_address);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 7ed2ecb51bca..4a8b77d425df 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -21,9 +21,9 @@ struct xfs_ifork {
 		void		*if_root;	/* extent tree root */
 		char		*if_data;	/* inline file data */
 	} if_u1;
+	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	int8_t			if_format;	/* format of this fork */
-	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 794a54cbd0de..373f64a492a4 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -12,8 +12,8 @@ typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
 typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
-typedef int32_t		xfs_extnum_t;	/* # of extents in a file */
-typedef int16_t		xfs_aextnum_t;	/* # extents in an attribute fork */
+typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
+typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
 typedef int64_t		xfs_fsize_t;	/* bytes in a file */
 typedef uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9de6205fe134..adc1355ce853 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3515,8 +3515,8 @@ xfs_iflush(
 	if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) >
 				ip->i_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-			"%s: detected corrupt incore inode %Lu, "
-			"total extents = %d, nblocks = %Ld, ptr "PTR_FMT,
+			"%s: detected corrupt incore inode %llu, "
+			"total extents = %llu nblocks = %lld, ptr "PTR_FMT,
 			__func__, ip->i_ino,
 			ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp),
 			ip->i_nblocks, ip);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 16a91b4f97bd..fe6cb2951233 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2182,7 +2182,7 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 		__entry->broot_size = ip->i_df.if_broot_bytes;
 		__entry->fork_off = XFS_IFORK_BOFF(ip);
 	),
-	TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %d, "
+	TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %llu, "
 		  "broot size %d, forkoff 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
-- 
cgit v1.2.3


From 0c35e7ba18508e9344a1f27b412924bc8b34eba8 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Tue, 16 Nov 2021 09:20:01 +0000
Subject: xfs: Use uint64_t to count maximum blocks that can be used by BMBT

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 9f38e33d6ce2..b317226fb4ba 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -52,9 +52,9 @@ xfs_bmap_compute_maxlevels(
 	xfs_mount_t	*mp,		/* file system mount structure */
 	int		whichfork)	/* data or attr fork */
 {
-	int		level;		/* btree level */
-	uint		maxblocks;	/* max blocks at this level */
+	uint64_t	maxblocks;	/* max blocks at this level */
 	xfs_extnum_t	maxleafents;	/* max leaf entries possible */
+	int		level;		/* btree level */
 	int		maxrootrecs;	/* max records in root block */
 	int		minleafrecs;	/* min records in leaf block */
 	int		minnoderecs;	/* min records in node block */
@@ -88,7 +88,7 @@ xfs_bmap_compute_maxlevels(
 		if (maxblocks <= maxrootrecs)
 			maxblocks = 1;
 		else
-			maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
+			maxblocks = howmany_64(maxblocks, minnoderecs);
 	}
 	mp->m_bm_maxlevels[whichfork] = level;
 	ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk());
-- 
cgit v1.2.3


From df9ad5cc7a524048ea7ff983d6feeb6d8c47a761 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Tue, 16 Nov 2021 09:54:37 +0000
Subject: xfs: Introduce macros to represent new maximum extent counts for
 data/attr forks

This commit defines new macros to represent maximum extent counts allowed by
filesystems which have support for large per-inode extent counters.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       |  9 ++++-----
 fs/xfs/libxfs/xfs_bmap_btree.c |  9 +++++++--
 fs/xfs/libxfs/xfs_format.h     | 24 ++++++++++++++++++++++--
 fs/xfs/libxfs/xfs_inode_buf.c  |  4 +++-
 fs/xfs/libxfs/xfs_inode_fork.c |  3 ++-
 fs/xfs/libxfs/xfs_inode_fork.h | 21 +++++++++++++++++----
 6 files changed, 55 insertions(+), 15 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b317226fb4ba..1254d4d4821e 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -61,10 +61,8 @@ xfs_bmap_compute_maxlevels(
 	int		sz;		/* root block size */
 
 	/*
-	 * The maximum number of extents in a file, hence the maximum number of
-	 * leaf entries, is controlled by the size of the on-disk extent count,
-	 * either a signed 32-bit number for the data fork, or a signed 16-bit
-	 * number for the attr fork.
+	 * The maximum number of extents in a fork, hence the maximum number of
+	 * leaf entries, is controlled by the size of the on-disk extent count.
 	 *
 	 * Note that we can no longer assume that if we are in ATTR1 that the
 	 * fork offset of all the inodes will be
@@ -74,7 +72,8 @@ xfs_bmap_compute_maxlevels(
 	 * ATTR2 we have to assume the worst case scenario of a minimum size
 	 * available.
 	 */
-	maxleafents = xfs_iext_max_nextents(whichfork);
+	maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp),
+				whichfork);
 	if (whichfork == XFS_DATA_FORK)
 		sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 	else
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 453309fc85f2..2b77d45c215f 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -597,7 +597,11 @@ xfs_bmbt_maxrecs(
 	return xfs_bmbt_block_maxrecs(blocklen, leaf);
 }
 
-/* Compute the max possible height for block mapping btrees. */
+/*
+ * Calculate the maximum possible height of the btree that the on-disk format
+ * supports. This is used for sizing structures large enough to support every
+ * possible configuration of a filesystem that might get mounted.
+ */
 unsigned int
 xfs_bmbt_maxlevels_ondisk(void)
 {
@@ -611,7 +615,8 @@ xfs_bmbt_maxlevels_ondisk(void)
 	minrecs[1] = xfs_bmbt_block_maxrecs(blocklen, false) / 2;
 
 	/* One extra level for the inode root. */
-	return xfs_btree_compute_maxlevels(minrecs, MAXEXTNUM) + 1;
+	return xfs_btree_compute_maxlevels(minrecs,
+			XFS_MAX_EXTCNT_DATA_FORK_LARGE) + 1;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 57b24744a7c2..eb85bc9b229b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -872,9 +872,29 @@ enum xfs_dinode_fmt {
 
 /*
  * Max values for extnum and aextnum.
+ *
+ * The original on-disk extent counts were held in signed fields, resulting in
+ * maximum extent counts of 2^31 and 2^15 for the data and attr forks
+ * respectively. Similarly the maximum extent length is limited to 2^21 blocks
+ * by the 21-bit wide blockcount field of a BMBT extent record.
+ *
+ * The newly introduced data fork extent counter can hold a 64-bit value,
+ * however the maximum number of extents in a file is also limited to 2^54
+ * extents by the 54-bit wide startoff field of a BMBT extent record.
+ *
+ * It is further limited by the maximum supported file size of 2^63
+ * *bytes*. This leads to a maximum extent count for maximally sized filesystem
+ * blocks (64kB) of:
+ *
+ * 2^63 bytes / 2^16 bytes per block = 2^47 blocks
+ *
+ * Rounding up 47 to the nearest multiple of bits-per-byte results in 48. Hence
+ * 2^48 was chosen as the maximum data fork extent count.
  */
-#define	MAXEXTNUM	((xfs_extnum_t)0x7fffffff)	/* signed int */
-#define	MAXAEXTNUM	((xfs_aextnum_t)0x7fff)		/* signed short */
+#define XFS_MAX_EXTCNT_DATA_FORK_LARGE	((xfs_extnum_t)((1ULL << 48) - 1))
+#define XFS_MAX_EXTCNT_ATTR_FORK_LARGE	((xfs_extnum_t)((1ULL << 32) - 1))
+#define XFS_MAX_EXTCNT_DATA_FORK_SMALL	((xfs_extnum_t)((1ULL << 31) - 1))
+#define XFS_MAX_EXTCNT_ATTR_FORK_SMALL	((xfs_extnum_t)((1ULL << 15) - 1))
 
 /*
  * Inode minimum and maximum sizes.
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index f0e063835318..e0d3140c3622 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -361,7 +361,9 @@ xfs_dinode_verify_fork(
 			return __this_address;
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		max_extents = xfs_iext_max_nextents(whichfork);
+		max_extents = xfs_iext_max_nextents(
+					xfs_dinode_has_large_extent_counts(dip),
+					whichfork);
 		if (di_nextents > max_extents)
 			return __this_address;
 		break;
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 004b205d87b8..bb5d841aac58 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -744,7 +744,8 @@ xfs_iext_count_may_overflow(
 	if (whichfork == XFS_COW_FORK)
 		return 0;
 
-	max_exts = xfs_iext_max_nextents(whichfork);
+	max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip),
+				whichfork);
 
 	if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
 		max_exts = 10;
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 4a8b77d425df..967837a88860 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -133,12 +133,25 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
 	return ifp->if_format;
 }
 
-static inline xfs_extnum_t xfs_iext_max_nextents(int whichfork)
+static inline xfs_extnum_t xfs_iext_max_nextents(bool has_large_extent_counts,
+				int whichfork)
 {
-	if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK)
-		return MAXEXTNUM;
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+	case XFS_COW_FORK:
+		if (has_large_extent_counts)
+			return XFS_MAX_EXTCNT_DATA_FORK_LARGE;
+		return XFS_MAX_EXTCNT_DATA_FORK_SMALL;
+
+	case XFS_ATTR_FORK:
+		if (has_large_extent_counts)
+			return XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+		return XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
 
-	return MAXAEXTNUM;
+	default:
+		ASSERT(0);
+		return 0;
+	}
 }
 
 static inline xfs_extnum_t
-- 
cgit v1.2.3


From 83a21c18441f75aec64548692b52d34582b98a6a Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Tue, 29 Mar 2022 06:14:00 +0000
Subject: xfs: Directory's data fork extent counter can never overflow

The maximum file size that can be represented by the data fork extent counter
in the worst case occurs when all extents are 1 block in length and each block
is 1KB in size.

With XFS_MAX_EXTCNT_DATA_FORK_SMALL representing maximum extent count and with
1KB sized blocks, a file can reach upto,
(2^31) * 1KB = 2TB

This is much larger than the theoretical maximum size of a directory
i.e. XFS_DIR2_SPACE_SIZE * 3 = ~96GB.

Since a directory's inode can never overflow its data fork extent counter,
this commit removes all the overflow checks associated with
it. xfs_dinode_verify() now performs a rough check to verify if a diretory's
data fork is larger than 96GB.

Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 20 ---------------
 fs/xfs/libxfs/xfs_da_btree.h   |  1 +
 fs/xfs/libxfs/xfs_da_format.h  |  1 +
 fs/xfs/libxfs/xfs_dir2.c       |  8 ++++++
 fs/xfs/libxfs/xfs_format.h     | 13 ++++++++++
 fs/xfs/libxfs/xfs_inode_buf.c  |  3 +++
 fs/xfs/libxfs/xfs_inode_fork.h | 13 ----------
 fs/xfs/xfs_inode.c             | 55 ++----------------------------------------
 fs/xfs/xfs_symlink.c           |  5 ----
 9 files changed, 28 insertions(+), 91 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 1254d4d4821e..4fab0c92ab70 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5147,26 +5147,6 @@ xfs_bmap_del_extent_real(
 		 * Deleting the middle of the extent.
 		 */
 
-		/*
-		 * For directories, -ENOSPC is returned since a directory entry
-		 * remove operation must not fail due to low extent count
-		 * availability. -ENOSPC will be handled by higher layers of XFS
-		 * by letting the corresponding empty Data/Free blocks to linger
-		 * until a future remove operation. Dabtree blocks would be
-		 * swapped with the last block in the leaf space and then the
-		 * new last block will be unmapped.
-		 *
-		 * The above logic also applies to the source directory entry of
-		 * a rename operation.
-		 */
-		error = xfs_iext_count_may_overflow(ip, whichfork, 1);
-		if (error) {
-			ASSERT(S_ISDIR(VFS_I(ip)->i_mode) &&
-				whichfork == XFS_DATA_FORK);
-			error = -ENOSPC;
-			goto done;
-		}
-
 		old = got;
 
 		got.br_blockcount = del->br_startoff - got.br_startoff;
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 0faf7d9ac241..7f08f6de48bf 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -30,6 +30,7 @@ struct xfs_da_geometry {
 	unsigned int	free_hdr_size;	/* dir2 free header size */
 	unsigned int	free_max_bests;	/* # of bests entries in dir2 free */
 	xfs_dablk_t	freeblk;	/* blockno of free data v2 */
+	xfs_extnum_t	max_extents;	/* Max. extents in corresponding fork */
 
 	xfs_dir2_data_aoff_t data_first_offset;
 	size_t		data_entry_offset;
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 5a49caa5c9df..95354b7ab7f5 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -277,6 +277,7 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
  * Directory address space divided into sections,
  * spaces separated by 32GB.
  */
+#define	XFS_DIR2_MAX_SPACES	3
 #define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
 #define	XFS_DIR2_DATA_SPACE	0
 #define	XFS_DIR2_DATA_OFFSET	(XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 5f1e4799e8fa..3cd51fa3837b 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -150,6 +150,8 @@ xfs_da_mount(
 	dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
 	dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
+	dageo->max_extents = (XFS_DIR2_MAX_SPACES * XFS_DIR2_SPACE_SIZE) >>
+					mp->m_sb.sb_blocklog;
 	dageo->magicpct = (dageo->blksize * 37) / 100;
 
 	/* set up attribute geometry - single fsb only */
@@ -161,6 +163,12 @@ xfs_da_mount(
 	dageo->node_hdr_size = mp->m_dir_geo->node_hdr_size;
 	dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
+
+	if (xfs_has_large_extent_counts(mp))
+		dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+	else
+		dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
+
 	dageo->magicpct = (dageo->blksize * 37) / 100;
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 82b404c99b80..43de892d0305 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -915,6 +915,19 @@ enum xfs_dinode_fmt {
  *
  * Rounding up 47 to the nearest multiple of bits-per-byte results in 48. Hence
  * 2^48 was chosen as the maximum data fork extent count.
+ *
+ * The maximum file size that can be represented by the data fork extent counter
+ * in the worst case occurs when all extents are 1 block in length and each
+ * block is 1KB in size.
+ *
+ * With XFS_MAX_EXTCNT_DATA_FORK_SMALL representing maximum extent count and
+ * with 1KB sized blocks, a file can reach upto,
+ * 1KB * (2^31) = 2TB
+ *
+ * This is much larger than the theoretical maximum size of a directory
+ * i.e. XFS_DIR2_SPACE_SIZE * XFS_DIR2_MAX_SPACES = ~96GB.
+ *
+ * Hence, a directory inode can never overflow its data fork extent counter.
  */
 #define XFS_MAX_EXTCNT_DATA_FORK_LARGE	((xfs_extnum_t)((1ULL << 48) - 1))
 #define XFS_MAX_EXTCNT_ATTR_FORK_LARGE	((xfs_extnum_t)((1ULL << 32) - 1))
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ee8d4eb7d048..74b82ec80f8e 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -491,6 +491,9 @@ xfs_dinode_verify(
 	if (mode && nextents + naextents > nblocks)
 		return __this_address;
 
+	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
+		return __this_address;
+
 	if (mode && XFS_DFORK_BOFF(dip) > mp->m_sb.sb_inodesize)
 		return __this_address;
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index fd5c3c2d77e0..6f9d69f8896e 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -39,19 +39,6 @@ struct xfs_ifork {
  */
 #define XFS_IEXT_PUNCH_HOLE_CNT		(1)
 
-/*
- * Directory entry addition can cause the following,
- * 1. Data block can be added/removed.
- *    A new extent can cause extent count to increase by 1.
- * 2. Free disk block can be added/removed.
- *    Same behaviour as described above for Data block.
- * 3. Dabtree blocks.
- *    XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new
- *    extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH.
- */
-#define XFS_IEXT_DIR_MANIP_CNT(mp) \
-	((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount)
-
 /*
  * Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to
  * be added. One extra extent for dabtree in case a local attr is
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index adc1355ce853..20f15a0393e1 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1024,11 +1024,6 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK,
-			XFS_IEXT_DIR_MANIP_CNT(mp));
-	if (error)
-		goto out_trans_cancel;
-
 	/*
 	 * A newly created regular or special file just has one directory
 	 * entry pointing to them, but a directory also the "." entry
@@ -1242,11 +1237,6 @@ xfs_link(
 	if (error)
 		goto std_return;
 
-	error = xfs_iext_count_may_overflow(tdp, XFS_DATA_FORK,
-			XFS_IEXT_DIR_MANIP_CNT(mp));
-	if (error)
-		goto error_return;
-
 	/*
 	 * If we are using project inheritance, we only allow hard link
 	 * creation in our tree when the project IDs are the same; else
@@ -3210,35 +3200,6 @@ retry:
 	/*
 	 * Check for expected errors before we dirty the transaction
 	 * so we can return an error without a transaction abort.
-	 *
-	 * Extent count overflow check:
-	 *
-	 * From the perspective of src_dp, a rename operation is essentially a
-	 * directory entry remove operation. Hence the only place where we check
-	 * for extent count overflow for src_dp is in
-	 * xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns
-	 * -ENOSPC when it detects a possible extent count overflow and in
-	 * response, the higher layers of directory handling code do the
-	 * following:
-	 * 1. Data/Free blocks: XFS lets these blocks linger until a
-	 *    future remove operation removes them.
-	 * 2. Dabtree blocks: XFS swaps the blocks with the last block in the
-	 *    Leaf space and unmaps the last block.
-	 *
-	 * For target_dp, there are two cases depending on whether the
-	 * destination directory entry exists or not.
-	 *
-	 * When destination directory entry does not exist (i.e. target_ip ==
-	 * NULL), extent count overflow check is performed only when transaction
-	 * has a non-zero sized space reservation associated with it.  With a
-	 * zero-sized space reservation, XFS allows a rename operation to
-	 * continue only when the directory has sufficient free space in its
-	 * data/leaf/free space blocks to hold the new entry.
-	 *
-	 * When destination directory entry exists (i.e. target_ip != NULL), all
-	 * we need to do is change the inode number associated with the already
-	 * existing entry. Hence there is no need to perform an extent count
-	 * overflow check.
 	 */
 	if (target_ip == NULL) {
 		/*
@@ -3249,12 +3210,6 @@ retry:
 			error = xfs_dir_canenter(tp, target_dp, target_name);
 			if (error)
 				goto out_trans_cancel;
-		} else {
-			error = xfs_iext_count_may_overflow(target_dp,
-					XFS_DATA_FORK,
-					XFS_IEXT_DIR_MANIP_CNT(mp));
-			if (error)
-				goto out_trans_cancel;
 		}
 	} else {
 		/*
@@ -3422,18 +3377,12 @@ retry:
 	 * inode number of the whiteout inode rather than removing it
 	 * altogether.
 	 */
-	if (wip) {
+	if (wip)
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
 					spaceres);
-	} else {
-		/*
-		 * NOTE: We don't need to check for extent count overflow here
-		 * because the dir remove name code will leave the dir block in
-		 * place if the extent count would overflow.
-		 */
+	else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
 					   spaceres);
-	}
 
 	if (error)
 		goto out_trans_cancel;
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index affbedf78160..4145ba872547 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -226,11 +226,6 @@ xfs_symlink(
 		goto out_trans_cancel;
 	}
 
-	error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK,
-			XFS_IEXT_DIR_MANIP_CNT(mp));
-	if (error)
-		goto out_trans_cancel;
-
 	/*
 	 * Allocate an inode for the symlink.
 	 */
-- 
cgit v1.2.3


From 4f86bb4b66c999ad9ddcfd49fec93992eeba2715 Mon Sep 17 00:00:00 2001
From: Chandan Babu R <chandan.babu@oracle.com>
Date: Wed, 9 Mar 2022 07:49:36 +0000
Subject: xfs: Conditionally upgrade existing inodes to use large extent
 counters

This commit enables upgrading existing inodes to use large extent counters
provided that underlying filesystem's superblock has large extent counter
feature enabled.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c       |  3 +++
 fs/xfs/libxfs/xfs_bmap.c       |  6 ++++--
 fs/xfs/libxfs/xfs_format.h     | 11 +++++++++++
 fs/xfs/libxfs/xfs_inode_fork.c | 24 ++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_fork.h |  2 ++
 fs/xfs/xfs_bmap_item.c         |  2 ++
 fs/xfs/xfs_bmap_util.c         | 13 +++++++++++++
 fs/xfs/xfs_dquot.c             |  3 +++
 fs/xfs/xfs_iomap.c             |  5 +++++
 fs/xfs/xfs_reflink.c           |  5 +++++
 fs/xfs/xfs_rtalloc.c           |  3 +++
 11 files changed, 75 insertions(+), 2 deletions(-)

(limited to 'fs/xfs/libxfs/xfs_bmap.c')

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 23523b802539..2815cfbbae70 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -776,6 +776,9 @@ xfs_attr_set(
 	if (args->value || xfs_inode_hasattr(dp)) {
 		error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK,
 				XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
+		if (error == -EFBIG)
+			error = xfs_iext_count_upgrade(args->trans, dp,
+					XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
 		if (error)
 			goto out_trans_cancel;
 	}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4fab0c92ab70..82d5467ddf2c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4524,14 +4524,16 @@ xfs_bmapi_convert_delalloc(
 		return error;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
 
 	error = xfs_iext_count_may_overflow(ip, whichfork,
 			XFS_IEXT_ADD_NOSPLIT_CNT);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip,
+				XFS_IEXT_ADD_NOSPLIT_CNT);
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_trans_ijoin(tp, ip, 0);
-
 	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) ||
 	    bma.got.br_startoff > offset_fsb) {
 		/*
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 43de892d0305..3beaa819b790 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -934,6 +934,17 @@ enum xfs_dinode_fmt {
 #define XFS_MAX_EXTCNT_DATA_FORK_SMALL	((xfs_extnum_t)((1ULL << 31) - 1))
 #define XFS_MAX_EXTCNT_ATTR_FORK_SMALL	((xfs_extnum_t)((1ULL << 15) - 1))
 
+/*
+ * When we upgrade an inode to the large extent counts, the maximum value by
+ * which the extent count can increase is bound by the change in size of the
+ * on-disk field. No upgrade operation should ever be adding more than a few
+ * tens of extents, so if we get a really large value it is a sign of a code bug
+ * or corruption.
+ */
+#define XFS_MAX_EXTCNT_UPGRADE_NR	\
+	min(XFS_MAX_EXTCNT_ATTR_FORK_LARGE - XFS_MAX_EXTCNT_ATTR_FORK_SMALL,	\
+	    XFS_MAX_EXTCNT_DATA_FORK_LARGE - XFS_MAX_EXTCNT_DATA_FORK_SMALL)
+
 /*
  * Inode minimum and maximum sizes.
  */
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index bb5d841aac58..9aee4a1e2fe9 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -756,3 +756,27 @@ xfs_iext_count_may_overflow(
 
 	return 0;
 }
+
+/*
+ * Upgrade this inode's extent counter fields to be able to handle a potential
+ * increase in the extent count by nr_to_add.  Normally this is the same
+ * quantity that caused xfs_iext_count_may_overflow() to return -EFBIG.
+ */
+int
+xfs_iext_count_upgrade(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	uint			nr_to_add)
+{
+	ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
+
+	if (!xfs_has_large_extent_counts(ip->i_mount) ||
+	    xfs_inode_has_large_extent_counts(ip) ||
+	    XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
+		return -EFBIG;
+
+	ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 6f9d69f8896e..4f68c1f20beb 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -275,6 +275,8 @@ int xfs_ifork_verify_local_data(struct xfs_inode *ip);
 int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
 int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
+int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
+		uint nr_to_add);
 
 /* returns true if the fork has extents but they are not read in yet. */
 static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp)
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 761dde155099..593ac29cffc7 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -506,6 +506,8 @@ xfs_bui_item_recover(
 		iext_delta = XFS_IEXT_PUNCH_HOLE_CNT;
 
 	error = xfs_iext_count_may_overflow(ip, whichfork, iext_delta);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip, iext_delta);
 	if (error)
 		goto err_cancel;
 
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 18c1b99311a8..52be58372c63 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -859,6 +859,9 @@ xfs_alloc_file_space(
 
 		error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 				XFS_IEXT_ADD_NOSPLIT_CNT);
+		if (error == -EFBIG)
+			error = xfs_iext_count_upgrade(tp, ip,
+					XFS_IEXT_ADD_NOSPLIT_CNT);
 		if (error)
 			goto error;
 
@@ -914,6 +917,8 @@ xfs_unmap_extent(
 
 	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 			XFS_IEXT_PUNCH_HOLE_CNT);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip, XFS_IEXT_PUNCH_HOLE_CNT);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1195,6 +1200,8 @@ xfs_insert_file_space(
 
 	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 			XFS_IEXT_PUNCH_HOLE_CNT);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip, XFS_IEXT_PUNCH_HOLE_CNT);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1423,6 +1430,9 @@ xfs_swap_extent_rmap(
 				error = xfs_iext_count_may_overflow(ip,
 						XFS_DATA_FORK,
 						XFS_IEXT_SWAP_RMAP_CNT);
+				if (error == -EFBIG)
+					error = xfs_iext_count_upgrade(tp, ip,
+							XFS_IEXT_SWAP_RMAP_CNT);
 				if (error)
 					goto out;
 			}
@@ -1431,6 +1441,9 @@ xfs_swap_extent_rmap(
 				error = xfs_iext_count_may_overflow(tip,
 						XFS_DATA_FORK,
 						XFS_IEXT_SWAP_RMAP_CNT);
+				if (error == -EFBIG)
+					error = xfs_iext_count_upgrade(tp, ip,
+							XFS_IEXT_SWAP_RMAP_CNT);
 				if (error)
 					goto out;
 			}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 5afedcbc78c7..eb211e0ede5d 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -322,6 +322,9 @@ xfs_dquot_disk_alloc(
 
 	error = xfs_iext_count_may_overflow(quotip, XFS_DATA_FORK,
 			XFS_IEXT_ADD_NOSPLIT_CNT);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, quotip,
+				XFS_IEXT_ADD_NOSPLIT_CNT);
 	if (error)
 		goto err_cancel;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 87e1cf5060bd..5a393259a3a3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -251,6 +251,8 @@ xfs_iomap_write_direct(
 		return error;
 
 	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, nr_exts);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip, nr_exts);
 	if (error)
 		goto out_trans_cancel;
 
@@ -555,6 +557,9 @@ xfs_iomap_write_unwritten(
 
 		error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 				XFS_IEXT_WRITE_UNWRITTEN_CNT);
+		if (error == -EFBIG)
+			error = xfs_iext_count_upgrade(tp, ip,
+					XFS_IEXT_WRITE_UNWRITTEN_CNT);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 54e68e5693fd..1ae6d3434ad2 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -620,6 +620,9 @@ xfs_reflink_end_cow_extent(
 
 	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 			XFS_IEXT_REFLINK_END_COW_CNT);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip,
+				XFS_IEXT_REFLINK_END_COW_CNT);
 	if (error)
 		goto out_cancel;
 
@@ -1121,6 +1124,8 @@ xfs_reflink_remap_extent(
 		++iext_delta;
 
 	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, iext_delta);
+	if (error == -EFBIG)
+		error = xfs_iext_count_upgrade(tp, ip, iext_delta);
 	if (error)
 		goto out_cancel;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index b8c79ee791af..3e587e85d5bf 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -806,6 +806,9 @@ xfs_growfs_rt_alloc(
 
 		error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
 				XFS_IEXT_ADD_NOSPLIT_CNT);
+		if (error == -EFBIG)
+			error = xfs_iext_count_upgrade(tp, ip,
+					XFS_IEXT_ADD_NOSPLIT_CNT);
 		if (error)
 			goto out_trans_cancel;
 
-- 
cgit v1.2.3