[PATCH 6.6 024/124] xfs: fix error returns from xfs_bmapi_write

[PATCH 6.6 024/124] xfs: fix error returns from xfs_bmapi_write

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <hch@lst.de>

commit 6773da870ab89123d1b513da63ed59e32a29cb77 upstream.

[backport: resolve conflicts due to missing quota_repair.c,
rtbitmap_repair.c, xfs_bmap_mark_sick()]

xfs_bmapi_write can return 0 without actually returning a mapping in
mval in two different cases:

 1) when there is absolutely no space available to do an allocation
 2) when converting delalloc space, and the allocation is so small
    that it only covers parts of the delalloc extent before the
    range requested by the caller

Callers at best can handle one of these cases, but in many cases can't
cope with either one.  Switch xfs_bmapi_write to always return a
mapping or return an error code instead.  For case 1) above ENOSPC is
the obvious choice which is very much what the callers expect anyway.
For case 2) there is no really good error code, so pick a funky one
from the SysV streams portfolio.

This fixes the reproducer here:

    https://lore.kernel.org/linux-xfs/CAEJPjCvT3Uag-pMTYuigEjWZHn1sGMZ0GCjVVCv29tNHK76Cgg@mail.gmail.com0/

which uses reserved blocks to create file systems that are gravely
out of space and thus cause at least xfs_file_alloc_space to hang
and trigger the lack of ENOSPC handling in xfs_dquot_disk_alloc.

Note that this patch does not actually make any caller but
xfs_alloc_file_space deal intelligently with case 2) above.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: 刘通 <lyutoon@gmail.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_attr_remote.c |    1 
 fs/xfs/libxfs/xfs_bmap.c        |   46 ++++++++++++++++++++++++++++++++--------
 fs/xfs/libxfs/xfs_da_btree.c    |   20 ++++-------------
 fs/xfs/xfs_bmap_util.c          |   31 +++++++++++++-------------
 fs/xfs/xfs_dquot.c              |    1 
 fs/xfs/xfs_iomap.c              |    8 ------
 fs/xfs/xfs_reflink.c            |   14 ------------
 fs/xfs/xfs_rtalloc.c            |    2 -
 8 files changed, 57 insertions(+), 66 deletions(-)

--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -619,7 +619,6 @@ xfs_attr_rmtval_set_blk(
 	if (error)
 		return error;
 
-	ASSERT(nmap == 1);
 	ASSERT((map->br_startblock != DELAYSTARTBLOCK) &&
 	       (map->br_startblock != HOLESTARTBLOCK));
 
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4128,8 +4128,10 @@ xfs_bmapi_allocate(
 	} else {
 		error = xfs_bmap_alloc_userdata(bma);
 	}
-	if (error || bma->blkno == NULLFSBLOCK)
+	if (error)
 		return error;
+	if (bma->blkno == NULLFSBLOCK)
+		return -ENOSPC;
 
 	if (bma->flags & XFS_BMAPI_ZERO) {
 		error = xfs_zero_extent(bma->ip, bma->blkno, bma->length);
@@ -4309,6 +4311,15 @@ xfs_bmapi_finish(
  * extent state if necessary.  Details behaviour is controlled by the flags
  * parameter.  Only allocates blocks from a single allocation group, to avoid
  * locking problems.
+ *
+ * Returns 0 on success and places the extent mappings in mval.  nmaps is used
+ * as an input/output parameter where the caller specifies the maximum number
+ * of mappings that may be returned and xfs_bmapi_write passes back the number
+ * of mappings (including existing mappings) it found.
+ *
+ * Returns a negative error code on failure, including -ENOSPC when it could not
+ * allocate any blocks and -ENOSR when it did allocate blocks to convert a
+ * delalloc range, but those blocks were before the passed in range.
  */
 int
 xfs_bmapi_write(
@@ -4436,10 +4447,16 @@ xfs_bmapi_write(
 			ASSERT(len > 0);
 			ASSERT(bma.length > 0);
 			error = xfs_bmapi_allocate(&bma);
-			if (error)
+			if (error) {
+				/*
+				 * If we already allocated space in a previous
+				 * iteration return what we go so far when
+				 * running out of space.
+				 */
+				if (error == -ENOSPC && bma.nallocs)
+					break;
 				goto error0;
-			if (bma.blkno == NULLFSBLOCK)
-				break;
+			}
 
 			/*
 			 * If this is a CoW allocation, record the data in
@@ -4477,7 +4494,6 @@ xfs_bmapi_write(
 		if (!xfs_iext_next_extent(ifp, &bma.icur, &bma.got))
 			eof = true;
 	}
-	*nmap = n;
 
 	error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags,
 			whichfork);
@@ -4488,7 +4504,22 @@ xfs_bmapi_write(
 	       ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork));
 	xfs_bmapi_finish(&bma, whichfork, 0);
 	xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval,
-		orig_nmap, *nmap);
+		orig_nmap, n);
+
+	/*
+	 * When converting delayed allocations, xfs_bmapi_allocate ignores
+	 * the passed in bno and always converts from the start of the found
+	 * delalloc extent.
+	 *
+	 * To avoid a successful return with *nmap set to 0, return the magic
+	 * -ENOSR error code for this particular case so that the caller can
+	 * handle it.
+	 */
+	if (!n) {
+		ASSERT(bma.nallocs >= *nmap);
+		return -ENOSR;
+	}
+	*nmap = n;
 	return 0;
 error0:
 	xfs_bmapi_finish(&bma, whichfork, error);
@@ -4595,9 +4626,6 @@ xfs_bmapi_convert_delalloc(
 	if (error)
 		goto out_finish;
 
-	error = -ENOSPC;
-	if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK))
-		goto out_finish;
 	error = -EFSCORRUPTED;
 	if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock)))
 		goto out_finish;
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2158,8 +2158,8 @@ xfs_da_grow_inode_int(
 	struct xfs_inode	*dp = args->dp;
 	int			w = args->whichfork;
 	xfs_rfsblock_t		nblks = dp->i_nblocks;
-	struct xfs_bmbt_irec	map, *mapp;
-	int			nmap, error, got, i, mapi;
+	struct xfs_bmbt_irec	map, *mapp = &map;
+	int			nmap, error, got, i, mapi = 1;
 
 	/*
 	 * Find a spot in the file space to put the new block.
@@ -2175,14 +2175,7 @@ xfs_da_grow_inode_int(
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
 			args->total, &map, &nmap);
-	if (error)
-		return error;
-
-	ASSERT(nmap <= 1);
-	if (nmap == 1) {
-		mapp = &map;
-		mapi = 1;
-	} else if (nmap == 0 && count > 1) {
+	if (error == -ENOSPC && count > 1) {
 		xfs_fileoff_t		b;
 		int			c;
 
@@ -2199,16 +2192,13 @@ xfs_da_grow_inode_int(
 					args->total, &mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
-			if (nmap < 1)
-				break;
 			mapi += nmap;
 			b = mapp[mapi - 1].br_startoff +
 			    mapp[mapi - 1].br_blockcount;
 		}
-	} else {
-		mapi = 0;
-		mapp = NULL;
 	}
+	if (error)
+		goto out_free_map;
 
 	/*
 	 * Count the blocks we got, make sure it matches the total.
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -868,33 +868,32 @@ xfs_alloc_file_space(
 		if (error)
 			goto error;
 
-		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
-				&nimaps);
-		if (error)
-			goto error;
-
-		ip->i_diflags |= XFS_DIFLAG_PREALLOC;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-		error = xfs_trans_commit(tp);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (error)
-			break;
-
 		/*
 		 * If the allocator cannot find a single free extent large
 		 * enough to cover the start block of the requested range,
-		 * xfs_bmapi_write will return 0 but leave *nimaps set to 0.
+		 * xfs_bmapi_write will return -ENOSR.
 		 *
 		 * In that case we simply need to keep looping with the same
 		 * startoffset_fsb so that one of the following allocations
 		 * will eventually reach the requested range.
 		 */
-		if (nimaps) {
+		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
+				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
+				&nimaps);
+		if (error) {
+			if (error != -ENOSR)
+				goto error;
+			error = 0;
+		} else {
 			startoffset_fsb += imapp->br_blockcount;
 			allocatesize_fsb -= imapp->br_blockcount;
 		}
+
+		ip->i_diflags |= XFS_DIFLAG_PREALLOC;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+		error = xfs_trans_commit(tp);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	}
 
 	return error;
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -333,7 +333,6 @@ xfs_dquot_disk_alloc(
 		goto err_cancel;
 
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
-	ASSERT(nmaps == 1);
 	ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
 	       (map.br_startblock != HOLESTARTBLOCK));
 
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -317,14 +317,6 @@ xfs_iomap_write_direct(
 	if (error)
 		goto out_unlock;
 
-	/*
-	 * Copy any maps to caller's array and return any error.
-	 */
-	if (nimaps == 0) {
-		error = -ENOSPC;
-		goto out_unlock;
-	}
-
 	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock)))
 		error = xfs_alert_fsblock_zero(ip, imap);
 
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -429,13 +429,6 @@ xfs_reflink_fill_cow_hole(
 	if (error)
 		return error;
 
-	/*
-	 * Allocation succeeded but the requested range was not even partially
-	 * satisfied?  Bail out!
-	 */
-	if (nimaps == 0)
-		return -ENOSPC;
-
 convert:
 	return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now);
 
@@ -498,13 +491,6 @@ xfs_reflink_fill_delalloc(
 		error = xfs_trans_commit(tp);
 		if (error)
 			return error;
-
-		/*
-		 * Allocation succeeded but the requested range was not even
-		 * partially satisfied?  Bail out!
-		 */
-		if (nimaps == 0)
-			return -ENOSPC;
 	} while (cmap->br_startoff + cmap->br_blockcount <= imap->br_startoff);
 
 	return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now);
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -840,8 +840,6 @@ xfs_growfs_rt_alloc(
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
 					XFS_BMAPI_METADATA, 0, &map, &nmap);
-		if (!error && nmap < 1)
-			error = -ENOSPC;
 		if (error)
 			goto out_trans_cancel;
 		/*

[PATCH 6.6 025/124] xfs: fix xfs_bmap_add_extent_delay_real for partial conversions

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <hch@lst.de>

commit d69bee6a35d3c5e4873b9e164dd1a9711351a97c upstream.

[backport: resolve conflict due to xfs_mod_freecounter refactor]

xfs_bmap_add_extent_delay_real takes parts or all of a delalloc extent
and converts them to a real extent.  It is written to deal with any
potential overlap of the to be converted range with the delalloc extent,
but it turns out that currently only converting the entire extents, or a
part starting at the beginning is actually exercised, as the only caller
always tries to convert the entire delalloc extent, and either succeeds
or at least progresses partially from the start.

If it only converts a tiny part of a delalloc extent, the indirect block
calculation for the new delalloc extent (da_new) might be equivalent to that
of the existing delalloc extent (da_old).  If this extent conversion now
requires allocating an indirect block that gets accounted into da_new,
leading to the assert that da_new must be smaller or equal to da_new
unless we split the extent to trigger.

Except for the assert that case is actually handled by just trying to
allocate more space, as that already handled for the split case (which
currently can't be reached at all), so just reusing it should be fine.
Except that without dipping into the reserved block pool that would make
it a bit too easy to trigger a fs shutdown due to ENOSPC.  So in addition
to adjusting the assert, also dip into the reserved block pool.

Note that I could only reproduce the assert with a change to only convert
the actually asked range instead of the full delalloc extent from
xfs_bmapi_write.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1549,6 +1549,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 		}
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG:
@@ -1578,6 +1579,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 		}
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
@@ -1611,6 +1613,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 		}
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING:
@@ -1643,6 +1646,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			}
 		}
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG:
@@ -1680,6 +1684,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 		}
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_LEFT_FILLING:
@@ -1767,6 +1772,7 @@ xfs_bmap_add_extent_delay_real(
 		xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);
 		xfs_iext_next(ifp, &bma->icur);
 		xfs_iext_update_extent(bma->ip, state, &bma->icur, &RIGHT);
+		ASSERT(da_new <= da_old);
 		break;
 
 	case BMAP_RIGHT_FILLING:
@@ -1814,6 +1820,7 @@ xfs_bmap_add_extent_delay_real(
 		PREV.br_blockcount = temp;
 		xfs_iext_insert(bma->ip, &bma->icur, &PREV, state);
 		xfs_iext_next(ifp, &bma->icur);
+		ASSERT(da_new <= da_old);
 		break;
 
 	case 0:
@@ -1934,11 +1941,9 @@ xfs_bmap_add_extent_delay_real(
 	}
 
 	/* adjust for changes in reserved delayed indirect blocks */
-	if (da_new != da_old) {
-		ASSERT(state == 0 || da_new < da_old);
+	if (da_new != da_old)
 		error = xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new),
-				false);
-	}
+				true);
 
 	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork);
 done:

[PATCH 6.6 026/124] xfs: remove a racy if_bytes check in xfs_reflink_end_cow_extent

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <hch@lst.de>

commit 86de848403abda05bf9c16dcdb6bef65a8d88c41 upstream.

Accessing if_bytes without the ilock is racy.  Remove the initial
if_bytes == 0 check in xfs_reflink_end_cow_extent and let
ext_iext_lookup_extent fail for this case after we've taken the ilock.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_reflink.c |    6 ------
 1 file changed, 6 deletions(-)

--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -716,12 +716,6 @@ xfs_reflink_end_cow_extent(
 	int			nmaps;
 	int			error;
 
-	/* No COW extents?  That's easy! */
-	if (ifp->if_bytes == 0) {
-		*offset_fsb = end_fsb;
-		return 0;
-	}
-
 	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
 			XFS_TRANS_RESERVE, &tp);

[PATCH 6.6 027/124] xfs: require XFS_SB_FEAT_INCOMPAT_LOG_XATTRS for attr log intent item recovery

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 8ef1d96a985e4dc07ffbd71bd7fc5604a80cc644 upstream.

The XFS_SB_FEAT_INCOMPAT_LOG_XATTRS feature bit protects a filesystem
from old kernels that do not know how to recover extended attribute log
intent items.  Make this check mandatory instead of a debugging assert.

Fixes: fd920008784ea ("xfs: Set up infrastructure for log attribute replay")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_attr_item.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -510,6 +510,9 @@ xfs_attri_validate(
 	unsigned int			op = attrp->alfi_op_flags &
 					     XFS_ATTRI_OP_FLAGS_TYPE_MASK;
 
+	if (!xfs_sb_version_haslogxattrs(&mp->m_sb))
+		return false;
+
 	if (attrp->__pad != 0)
 		return false;
 
@@ -602,8 +605,6 @@ xfs_attri_item_recover(
 	args->op_flags = XFS_DA_OP_RECOVERY | XFS_DA_OP_OKNOENT |
 			 XFS_DA_OP_LOGGED;
 
-	ASSERT(xfs_sb_version_haslogxattrs(&mp->m_sb));
-
 	switch (attr->xattri_op_flags) {
 	case XFS_ATTRI_OP_FLAGS_SET:
 	case XFS_ATTRI_OP_FLAGS_REPLACE:

[PATCH 6.6 028/124] xfs: check opcode and iovec count match in xlog_recover_attri_commit_pass2

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit ad206ae50eca62836c5460ab5bbf2a6c59a268e7 upstream.

Check that the number of recovered log iovecs is what is expected for
the xattri opcode is expecting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_attr_item.c |   27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -719,6 +719,7 @@ xlog_recover_attri_commit_pass2(
 	const void			*attr_value = NULL;
 	const void			*attr_name;
 	size_t				len;
+	unsigned int			op;
 
 	attri_formatp = item->ri_buf[0].i_addr;
 	attr_name = item->ri_buf[1].i_addr;
@@ -737,6 +738,32 @@ xlog_recover_attri_commit_pass2(
 		return -EFSCORRUPTED;
 	}
 
+	/* Check the number of log iovecs makes sense for the op code. */
+	op = attri_formatp->alfi_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK;
+	switch (op) {
+	case XFS_ATTRI_OP_FLAGS_SET:
+	case XFS_ATTRI_OP_FLAGS_REPLACE:
+		/* Log item, attr name, attr value */
+		if (item->ri_total != 3) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					     attri_formatp, len);
+			return -EFSCORRUPTED;
+		}
+		break;
+	case XFS_ATTRI_OP_FLAGS_REMOVE:
+		/* Log item, attr name */
+		if (item->ri_total != 2) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					     attri_formatp, len);
+			return -EFSCORRUPTED;
+		}
+		break;
+	default:
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				     attri_formatp, len);
+		return -EFSCORRUPTED;
+	}
+
 	/* Validate the attr name */
 	if (item->ri_buf[1].i_len !=
 			xlog_calc_iovec_len(attri_formatp->alfi_name_len)) {

[PATCH 6.6 029/124] xfs: fix missing check for invalid attr flags

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit f660ec8eaeb50d0317c29601aacabdb15e5f2203 upstream.

[backport: fix build errors in xchk_xattr_listent]

The xattr scrubber doesn't check for undefined flags in shortform attr
entries.  Therefore, define a mask XFS_ATTR_ONDISK_MASK that has all
possible XFS_ATTR_* flags in it, and use that to check for unknown bits
in xchk_xattr_actor.

Refactor the check in the dabtree scanner function to use the new mask
as well.  The redundant checks need to be in place because the dabtree
check examines the hash mappings and therefore needs to decode the attr
leaf entries to compute the namehash.  This happens before the walk of
the xattr entries themselves.

Fixes: ae0506eba78fd ("xfs: check used space of shortform xattr structures")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_da_format.h |    5 +++++
 fs/xfs/scrub/attr.c           |   13 +++++++++----
 2 files changed, 14 insertions(+), 4 deletions(-)

--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -703,8 +703,13 @@ struct xfs_attr3_leafblock {
 #define XFS_ATTR_ROOT		(1u << XFS_ATTR_ROOT_BIT)
 #define XFS_ATTR_SECURE		(1u << XFS_ATTR_SECURE_BIT)
 #define XFS_ATTR_INCOMPLETE	(1u << XFS_ATTR_INCOMPLETE_BIT)
+
 #define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
 
+#define XFS_ATTR_ONDISK_MASK	(XFS_ATTR_NSP_ONDISK_MASK | \
+				 XFS_ATTR_LOCAL | \
+				 XFS_ATTR_INCOMPLETE)
+
 /*
  * Alignment for namelist and valuelist entries (since they are mixed
  * there can be only one alignment value)
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -182,6 +182,11 @@ xchk_xattr_listent(
 		return;
 	}
 
+	if (flags & ~XFS_ATTR_ONDISK_MASK) {
+		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
+		goto fail_xref;
+	}
+
 	if (flags & XFS_ATTR_INCOMPLETE) {
 		/* Incomplete attr key, just mark the inode for preening. */
 		xchk_ino_set_preen(sx->sc, context->dp->i_ino);
@@ -463,7 +468,6 @@ xchk_xattr_rec(
 	xfs_dahash_t			hash;
 	int				nameidx;
 	int				hdrsize;
-	unsigned int			badflags;
 	int				error;
 
 	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -493,10 +497,11 @@ xchk_xattr_rec(
 
 	/* Retrieve the entry and check it. */
 	hash = be32_to_cpu(ent->hashval);
-	badflags = ~(XFS_ATTR_LOCAL | XFS_ATTR_ROOT | XFS_ATTR_SECURE |
-			XFS_ATTR_INCOMPLETE);
-	if ((ent->flags & badflags) != 0)
+	if (ent->flags & ~XFS_ATTR_ONDISK_MASK) {
 		xchk_da_set_corrupt(ds, level);
+		return 0;
+	}
+
 	if (ent->flags & XFS_ATTR_LOCAL) {
 		lentry = (struct xfs_attr_leaf_name_local *)
 				(((char *)bp->b_addr) + nameidx);

[PATCH 6.6 030/124] xfs: check shortform attr entry flags specifically

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 309dc9cbbb4379241bcc9b5a6a42c04279a0e5a7 upstream.

While reviewing flag checking in the attr scrub functions, we noticed
that the shortform attr scanner didn't catch entries that have the LOCAL
or INCOMPLETE bits set.  Neither of these flags can ever be set on a
shortform attr, so we need to check this narrower set of valid flags.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/scrub/attr.c |    9 +++++++++
 1 file changed, 9 insertions(+)

--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -566,6 +566,15 @@ xchk_xattr_check_sf(
 			break;
 		}
 
+		/*
+		 * Shortform entries do not set LOCAL or INCOMPLETE, so the
+		 * only valid flag bits here are for namespaces.
+		 */
+		if (sfe->flags & ~XFS_ATTR_NSP_ONDISK_MASK) {
+			xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0);
+			break;
+		}
+
 		if (!xchk_xattr_set_map(sc, ab->usedmap,
 				(char *)sfe - (char *)sf,
 				sizeof(struct xfs_attr_sf_entry))) {

[PATCH 6.6 031/124] xfs: validate recovered name buffers when recovering xattr items

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 1c7f09d210aba2f2bb206e2e8c97c9f11a3fd880 upstream.

Strengthen the xattri log item recovery code by checking that we
actually have the required name and newname buffers for whatever
operation we're replaying.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_attr_item.c |   58 +++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 47 insertions(+), 11 deletions(-)

--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -719,22 +719,20 @@ xlog_recover_attri_commit_pass2(
 	const void			*attr_value = NULL;
 	const void			*attr_name;
 	size_t				len;
-	unsigned int			op;
-
-	attri_formatp = item->ri_buf[0].i_addr;
-	attr_name = item->ri_buf[1].i_addr;
+	unsigned int			op, i = 0;
 
 	/* 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) {
+	if (item->ri_buf[i].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;
 	}
 
+	attri_formatp = item->ri_buf[i].i_addr;
 	if (!xfs_attri_validate(mp, attri_formatp)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+				attri_formatp, len);
 		return -EFSCORRUPTED;
 	}
 
@@ -763,31 +761,69 @@ xlog_recover_attri_commit_pass2(
 				     attri_formatp, len);
 		return -EFSCORRUPTED;
 	}
+	i++;
 
 	/* Validate the attr name */
-	if (item->ri_buf[1].i_len !=
+	if (item->ri_buf[i].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);
+				attri_formatp, len);
 		return -EFSCORRUPTED;
 	}
 
+	attr_name = item->ri_buf[i].i_addr;
 	if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-				item->ri_buf[1].i_addr, item->ri_buf[1].i_len);
+				attri_formatp, len);
 		return -EFSCORRUPTED;
 	}
+	i++;
 
 	/* 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)) {
+		if (item->ri_buf[i].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;
+		attr_value = item->ri_buf[i].i_addr;
+		i++;
+	}
+
+	/*
+	 * Make sure we got the correct number of buffers for the operation
+	 * that we just loaded.
+	 */
+	if (i != item->ri_total) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				attri_formatp, len);
+		return -EFSCORRUPTED;
+	}
+
+	switch (op) {
+	case XFS_ATTRI_OP_FLAGS_REMOVE:
+		/* Regular remove operations operate only on names. */
+		if (attr_value != NULL || attri_formatp->alfi_value_len != 0) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					     attri_formatp, len);
+			return -EFSCORRUPTED;
+		}
+		fallthrough;
+	case XFS_ATTRI_OP_FLAGS_SET:
+	case XFS_ATTRI_OP_FLAGS_REPLACE:
+		/*
+		 * Regular xattr set/remove/replace operations require a name
+		 * and do not take a newname.  Values are optional for set and
+		 * replace.
+		 */
+		if (attr_name == NULL || attri_formatp->alfi_name_len == 0) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					     attri_formatp, len);
+			return -EFSCORRUPTED;
+		}
+		break;
 	}
 
 	/*

[PATCH 6.6 032/124] xfs: enforce one namespace per attribute

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit ea0b3e814741fb64e7785b564ea619578058e0b0 upstream.

[backport: fix conflicts due to various xattr refactoring]

Create a standardized helper function to enforce one namespace bit per
extended attribute, and refactor all the open-coded hweight logic.  This
function is not a static inline to avoid porting hassles in userspace.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_attr.c      |   11 +++++++++++
 fs/xfs/libxfs/xfs_attr.h      |    4 +++-
 fs/xfs/libxfs/xfs_attr_leaf.c |    6 +++++-
 fs/xfs/scrub/attr.c           |   12 +++++-------
 fs/xfs/xfs_attr_item.c        |   10 ++++++++--
 fs/xfs/xfs_attr_list.c        |   11 +++++++----
 6 files changed, 39 insertions(+), 15 deletions(-)

--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1565,12 +1565,23 @@ out_release:
 	return error;
 }
 
+/* Enforce that there is at most one namespace bit per attr. */
+inline bool xfs_attr_check_namespace(unsigned int attr_flags)
+{
+	return hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) < 2;
+}
+
 /* Returns true if the attribute entry name is valid. */
 bool
 xfs_attr_namecheck(
+	unsigned int	attr_flags,
 	const void	*name,
 	size_t		length)
 {
+	/* Only one namespace bit allowed. */
+	if (!xfs_attr_check_namespace(attr_flags))
+		return false;
+
 	/*
 	 * MAXNAMELEN includes the trailing null, but (name/length) leave it
 	 * out, so use >= for the length check.
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -547,7 +547,9 @@ int xfs_attr_get(struct xfs_da_args *arg
 int xfs_attr_set(struct xfs_da_args *args);
 int xfs_attr_set_iter(struct xfs_attr_intent *attr);
 int xfs_attr_remove_iter(struct xfs_attr_intent *attr);
-bool xfs_attr_namecheck(const void *name, size_t length);
+bool xfs_attr_check_namespace(unsigned int attr_flags);
+bool xfs_attr_namecheck(unsigned int attr_flags, const void *name,
+		size_t length);
 int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
 void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres,
 			 unsigned int *total);
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -984,6 +984,10 @@ xfs_attr_shortform_to_leaf(
 		nargs.hashval = xfs_da_hashname(sfe->nameval,
 						sfe->namelen);
 		nargs.attr_filter = sfe->flags & XFS_ATTR_NSP_ONDISK_MASK;
+		if (!xfs_attr_check_namespace(sfe->flags)) {
+			error = -EFSCORRUPTED;
+			goto out;
+		}
 		error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */
 		ASSERT(error == -ENOATTR);
 		error = xfs_attr3_leaf_add(bp, &nargs);
@@ -1105,7 +1109,7 @@ xfs_attr_shortform_verify(
 		 * one namespace flag per xattr, so we can just count the
 		 * bits (i.e. hweight) here.
 		 */
-		if (hweight8(sfep->flags & XFS_ATTR_NSP_ONDISK_MASK) > 1)
+		if (!xfs_attr_check_namespace(sfep->flags))
 			return __this_address;
 
 		sfep = next_sfep;
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -193,14 +193,8 @@ xchk_xattr_listent(
 		return;
 	}
 
-	/* Only one namespace bit allowed. */
-	if (hweight32(flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
-		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
-		goto fail_xref;
-	}
-
 	/* Does this name make sense? */
-	if (!xfs_attr_namecheck(name, namelen)) {
+	if (!xfs_attr_namecheck(flags, name, namelen)) {
 		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
 		goto fail_xref;
 	}
@@ -501,6 +495,10 @@ xchk_xattr_rec(
 		xchk_da_set_corrupt(ds, level);
 		return 0;
 	}
+	if (!xfs_attr_check_namespace(ent->flags)) {
+		xchk_da_set_corrupt(ds, level);
+		return 0;
+	}
 
 	if (ent->flags & XFS_ATTR_LOCAL) {
 		lentry = (struct xfs_attr_leaf_name_local *)
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -522,6 +522,10 @@ xfs_attri_validate(
 	if (attrp->alfi_attr_filter & ~XFS_ATTRI_FILTER_MASK)
 		return false;
 
+	if (!xfs_attr_check_namespace(attrp->alfi_attr_filter &
+				      XFS_ATTR_NSP_ONDISK_MASK))
+		return false;
+
 	/* alfi_op_flags should be either a set or remove */
 	switch (op) {
 	case XFS_ATTRI_OP_FLAGS_SET:
@@ -572,7 +576,8 @@ xfs_attri_item_recover(
 	 */
 	attrp = &attrip->attri_format;
 	if (!xfs_attri_validate(mp, attrp) ||
-	    !xfs_attr_namecheck(nv->name.i_addr, nv->name.i_len))
+	    !xfs_attr_namecheck(attrp->alfi_attr_filter, nv->name.i_addr,
+				nv->name.i_len))
 		return -EFSCORRUPTED;
 
 	error = xlog_recover_iget(mp,  attrp->alfi_ino, &ip);
@@ -772,7 +777,8 @@ xlog_recover_attri_commit_pass2(
 	}
 
 	attr_name = item->ri_buf[i].i_addr;
-	if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) {
+	if (!xfs_attr_namecheck(attri_formatp->alfi_attr_filter, attr_name,
+				attri_formatp->alfi_name_len)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 				attri_formatp, len);
 		return -EFSCORRUPTED;
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -82,7 +82,8 @@ xfs_attr_shortform_list(
 	     (dp->i_af.if_bytes + sf->hdr.count * 16) < context->bufsize)) {
 		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 			if (XFS_IS_CORRUPT(context->dp->i_mount,
-					   !xfs_attr_namecheck(sfe->nameval,
+					   !xfs_attr_namecheck(sfe->flags,
+							       sfe->nameval,
 							       sfe->namelen)))
 				return -EFSCORRUPTED;
 			context->put_listent(context,
@@ -120,7 +121,8 @@ xfs_attr_shortform_list(
 	for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 		if (unlikely(
 		    ((char *)sfe < (char *)sf) ||
-		    ((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)))) {
+		    ((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)) ||
+		    !xfs_attr_check_namespace(sfe->flags))) {
 			XFS_CORRUPTION_ERROR("xfs_attr_shortform_list",
 					     XFS_ERRLEVEL_LOW,
 					     context->dp->i_mount, sfe,
@@ -174,7 +176,7 @@ xfs_attr_shortform_list(
 			cursor->offset = 0;
 		}
 		if (XFS_IS_CORRUPT(context->dp->i_mount,
-				   !xfs_attr_namecheck(sbp->name,
+				   !xfs_attr_namecheck(sbp->flags, sbp->name,
 						       sbp->namelen))) {
 			error = -EFSCORRUPTED;
 			goto out;
@@ -465,7 +467,8 @@ xfs_attr3_leaf_list_int(
 		}
 
 		if (XFS_IS_CORRUPT(context->dp->i_mount,
-				   !xfs_attr_namecheck(name, namelen)))
+				   !xfs_attr_namecheck(entry->flags, name,
+						       namelen)))
 			return -EFSCORRUPTED;
 		context->put_listent(context, entry->flags,
 					      name, namelen, valuelen);

[PATCH 6.6 033/124] xfs: revert commit 44af6c7e59b12

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 2a009397eb5ae178670cbd7101e9635cf6412b35 upstream.

[backport: resolve conflicts due to new xattr walk helper]

In my haste to fix what I thought was a performance problem in the attr
scrub code, I neglected to notice that the xfs_attr_get_ilocked also had
the effect of checking that attributes can actually be looked up through
the attr dabtree.  Fix this.

Fixes: 44af6c7e59b12 ("xfs: don't load local xattr values during scrub")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/scrub/attr.c |   13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -200,14 +200,6 @@ xchk_xattr_listent(
 	}
 
 	/*
-	 * Local xattr values are stored in the attr leaf block, so we don't
-	 * need to retrieve the value from a remote block to detect corruption
-	 * problems.
-	 */
-	if (flags & XFS_ATTR_LOCAL)
-		goto fail_xref;
-
-	/*
 	 * Try to allocate enough memory to extrat the attr value.  If that
 	 * doesn't work, we overload the seen_enough variable to convey
 	 * the error message back to the main scrub function.
@@ -222,6 +214,11 @@ xchk_xattr_listent(
 
 	args.value = ab->value;
 
+	/*
+	 * Get the attr value to ensure that lookup can find this attribute
+	 * through the dabtree indexing and that remote value retrieval also
+	 * works correctly.
+	 */
 	error = xfs_attr_get_ilocked(&args);
 	/* ENODATA means the hash lookup failed and the attr is bad */
 	if (error == -ENODATA)

[PATCH 6.6 034/124] xfs: use dontcache for grabbing inodes during scrub

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit b27ce0da60a523fc32e3795f96b2de5490642235 upstream.

[backport: resolve conflict due to missing iscan.c]

Back when I wrote commit a03297a0ca9f2, I had thought that we'd be doing
users a favor by only marking inodes dontcache at the end of a scrub
operation, and only if there's only one reference to that inode.  This
was more or less true back when I_DONTCACHE was an XFS iflag and the
only thing it did was change the outcome of xfs_fs_drop_inode to 1.

Note: If there are dentries pointing to the inode when scrub finishes,
the inode will have positive i_count and stay around in cache until
dentry reclaim.

But now we have d_mark_dontcache, which cause the inode *and* the
dentries attached to it all to be marked I_DONTCACHE, which means that
we drop the dentries ASAP, which drops the inode ASAP.

This is bad if scrub found problems with the inode, because now they can
be scheduled for inactivation, which can cause inodegc to trip on it and
shut down the filesystem.

Even if the inode isn't bad, this is still suboptimal because phases 3-7
each initiate inode scans.  Dropping the inode immediately during phase
3 is silly because phase 5 will reload it and drop it immediately, etc.
It's fine to mark the inodes dontcache, but if there have been accesses
to the file that set up dentries, we should keep them.

I validated this by setting up ftrace to capture xfs_iget_recycle*
tracepoints and ran xfs/285 for 30 seconds.  With current djwong-wtf I
saw ~30,000 recycle events.  I then dropped the d_mark_dontcache calls
and set XFS_IGET_DONTCACHE, and the recycle events dropped to ~5,000 per
30 seconds.

Therefore, grab the inode with XFS_IGET_DONTCACHE, which only has the
effect of setting I_DONTCACHE for cache misses.  Remove the
d_mark_dontcache call that can happen in xchk_irele.

Fixes: a03297a0ca9f2 ("xfs: manage inode DONTCACHE status at irele time")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/scrub/common.c |   12 +++---------
 fs/xfs/scrub/scrub.h  |    7 +++++++
 2 files changed, 10 insertions(+), 9 deletions(-)

--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -735,7 +735,7 @@ xchk_iget(
 {
 	ASSERT(sc->tp != NULL);
 
-	return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp);
+	return xfs_iget(sc->mp, sc->tp, inum, XCHK_IGET_FLAGS, 0, ipp);
 }
 
 /*
@@ -786,8 +786,8 @@ again:
 	if (error)
 		return error;
 
-	error = xfs_iget(mp, tp, inum,
-			XFS_IGET_NORETRY | XFS_IGET_UNTRUSTED, 0, ipp);
+	error = xfs_iget(mp, tp, inum, XFS_IGET_NORETRY | XCHK_IGET_FLAGS, 0,
+			ipp);
 	if (error == -EAGAIN) {
 		/*
 		 * The inode may be in core but temporarily unavailable and may
@@ -994,12 +994,6 @@ xchk_irele(
 		spin_lock(&VFS_I(ip)->i_lock);
 		VFS_I(ip)->i_state &= ~I_DONTCACHE;
 		spin_unlock(&VFS_I(ip)->i_lock);
-	} else if (atomic_read(&VFS_I(ip)->i_count) == 1) {
-		/*
-		 * If this is the last reference to the inode and the caller
-		 * permits it, set DONTCACHE to avoid thrashing.
-		 */
-		d_mark_dontcache(VFS_I(ip));
 	}
 
 	xfs_irele(ip);
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -17,6 +17,13 @@ struct xfs_scrub;
 #define XCHK_GFP_FLAGS	((__force gfp_t)(GFP_KERNEL | __GFP_NOWARN | \
 					 __GFP_RETRY_MAYFAIL))
 
+/*
+ * For opening files by handle for fsck operations, we don't trust the inumber
+ * or the allocation state; therefore, perform an untrusted lookup.  We don't
+ * want these inodes to pollute the cache, so mark them for immediate removal.
+ */
+#define XCHK_IGET_FLAGS	(XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE)
+
 /* Type info and names for the scrub types. */
 enum xchk_type {
 	ST_NONE = 1,	/* disabled */

[PATCH 6.6 035/124] xfs: match lock mode in xfs_buffered_write_iomap_begin()

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Zhang Yi <yi.zhang@huawei.com>

commit bb712842a85d595525e72f0e378c143e620b3ea2 upstream.

Commit 1aa91d9c9933 ("xfs: Add async buffered write support") replace
xfs_ilock(XFS_ILOCK_EXCL) with xfs_ilock_for_iomap() when locking the
writing inode, and a new variable lockmode is used to indicate the lock
mode. Although the lockmode should always be XFS_ILOCK_EXCL, it's still
better to use this variable instead of useing XFS_ILOCK_EXCL directly
when unlocking the inode.

Fixes: 1aa91d9c9933 ("xfs: Add async buffered write support")
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_iomap.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1141,13 +1141,13 @@ retry:
 	 * them out if the write happens to fail.
 	 */
 	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_NEW);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, lockmode);
 	trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
 	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW, seq);
 
 found_imap:
 	seq = xfs_iomap_inode_sequence(ip, 0);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, lockmode);
 	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq);
 
 found_cow:
@@ -1157,17 +1157,17 @@ found_cow:
 		if (error)
 			goto out_unlock;
 		seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xfs_iunlock(ip, lockmode);
 		return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
 					 IOMAP_F_SHARED, seq);
 	}
 
 	xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, lockmode);
 	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0, seq);
 
 out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, lockmode);
 	return error;
 }
 

[PATCH 6.6 036/124] xfs: make the seq argument to xfs_bmapi_convert_delalloc() optional

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Zhang Yi <yi.zhang@huawei.com>

commit fc8d0ba0ff5fe4700fa02008b7751ec6b84b7677 upstream.

Allow callers to pass a NULLL seq argument if they don't care about
the fork sequence number.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_bmap.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4595,7 +4595,8 @@ xfs_bmapi_convert_delalloc(
 	if (!isnullstartblock(bma.got.br_startblock)) {
 		xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
 				xfs_iomap_inode_sequence(ip, flags));
-		*seq = READ_ONCE(ifp->if_seq);
+		if (seq)
+			*seq = READ_ONCE(ifp->if_seq);
 		goto out_trans_cancel;
 	}
 
@@ -4641,7 +4642,8 @@ xfs_bmapi_convert_delalloc(
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
 	xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags,
 				xfs_iomap_inode_sequence(ip, flags));
-	*seq = READ_ONCE(ifp->if_seq);
+	if (seq)
+		*seq = READ_ONCE(ifp->if_seq);
 
 	if (whichfork == XFS_COW_FORK)
 		xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length);

[PATCH 6.6 037/124] xfs: make xfs_bmapi_convert_delalloc() to allocate the target offset

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Zhang Yi <yi.zhang@huawei.com>

commit 2e08371a83f1c06fd85eea8cd37c87a224cc4cc4 upstream.

Since xfs_bmapi_convert_delalloc() only attempts to allocate the entire
delalloc extent and require multiple invocations to allocate the target
offset. So xfs_convert_blocks() add a loop to do this job and we call it
in the write back path, but xfs_convert_blocks() isn't a common helper.
Let's do it in xfs_bmapi_convert_delalloc() and drop
xfs_convert_blocks(), preparing for the post EOF delalloc blocks
converting in the buffered write begin path.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   34 +++++++++++++++++++++++++++--
 fs/xfs/xfs_aops.c        |   54 ++++++++++++-----------------------------------
 2 files changed, 46 insertions(+), 42 deletions(-)

--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4537,8 +4537,8 @@ error0:
  * invocations to allocate the target offset if a large enough physical extent
  * is not available.
  */
-int
-xfs_bmapi_convert_delalloc(
+static int
+xfs_bmapi_convert_one_delalloc(
 	struct xfs_inode	*ip,
 	int			whichfork,
 	xfs_off_t		offset,
@@ -4666,6 +4666,36 @@ out_trans_cancel:
 	return error;
 }
 
+/*
+ * Pass in a dellalloc extent and convert it to real extents, return the real
+ * extent that maps offset_fsb in iomap.
+ */
+int
+xfs_bmapi_convert_delalloc(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	loff_t			offset,
+	struct iomap		*iomap,
+	unsigned int		*seq)
+{
+	int			error;
+
+	/*
+	 * Attempt to allocate whatever delalloc extent currently backs offset
+	 * and put the result into iomap.  Allocate in a loop because it may
+	 * take several attempts to allocate real blocks for a contiguous
+	 * delalloc extent if free space is sufficiently fragmented.
+	 */
+	do {
+		error = xfs_bmapi_convert_one_delalloc(ip, whichfork, offset,
+					iomap, seq);
+		if (error)
+			return error;
+	} while (iomap->offset + iomap->length <= offset);
+
+	return 0;
+}
+
 int
 xfs_bmapi_remap(
 	struct xfs_trans	*tp,
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -233,45 +233,6 @@ xfs_imap_valid(
 	return true;
 }
 
-/*
- * Pass in a dellalloc extent and convert it to real extents, return the real
- * extent that maps offset_fsb in wpc->iomap.
- *
- * The current page is held locked so nothing could have removed the block
- * backing offset_fsb, although it could have moved from the COW to the data
- * fork by another thread.
- */
-static int
-xfs_convert_blocks(
-	struct iomap_writepage_ctx *wpc,
-	struct xfs_inode	*ip,
-	int			whichfork,
-	loff_t			offset)
-{
-	int			error;
-	unsigned		*seq;
-
-	if (whichfork == XFS_COW_FORK)
-		seq = &XFS_WPC(wpc)->cow_seq;
-	else
-		seq = &XFS_WPC(wpc)->data_seq;
-
-	/*
-	 * Attempt to allocate whatever delalloc extent currently backs offset
-	 * and put the result into wpc->iomap.  Allocate in a loop because it
-	 * may take several attempts to allocate real blocks for a contiguous
-	 * delalloc extent if free space is sufficiently fragmented.
-	 */
-	do {
-		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
-				&wpc->iomap, seq);
-		if (error)
-			return error;
-	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
-
-	return 0;
-}
-
 static int
 xfs_map_blocks(
 	struct iomap_writepage_ctx *wpc,
@@ -289,6 +250,7 @@ xfs_map_blocks(
 	struct xfs_iext_cursor	icur;
 	int			retries = 0;
 	int			error = 0;
+	unsigned int		*seq;
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
@@ -386,7 +348,19 @@ retry:
 	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
+	/*
+	 * Convert a dellalloc extent to a real one. The current page is held
+	 * locked so nothing could have removed the block backing offset_fsb,
+	 * although it could have moved from the COW to the data fork by another
+	 * thread.
+	 */
+	if (whichfork == XFS_COW_FORK)
+		seq = &XFS_WPC(wpc)->cow_seq;
+	else
+		seq = &XFS_WPC(wpc)->data_seq;
+
+	error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
+				&wpc->iomap, seq);
 	if (error) {
 		/*
 		 * If we failed to find the extent in the COW fork we might have

[PATCH 6.6 038/124] xfs: convert delayed extents to unwritten when zeroing post eof blocks

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Zhang Yi <yi.zhang@huawei.com>

commit 5ce5674187c345dc31534d2024c09ad8ef29b7ba upstream.

Current clone operation could be non-atomic if the destination of a file
is beyond EOF, user could get a file with corrupted (zeroed) data on
crash.

The problem is about preallocations. If you write some data into a file:

	[A...B)

and XFS decides to preallocate some post-eof blocks, then it can create
a delayed allocation reservation:

	[A.........D)

The writeback path tries to convert delayed extents to real ones by
allocating blocks. If there aren't enough contiguous free space, we can
end up with two extents, the first real and the second still delalloc:

	[A....C)[C.D)

After that, both the in-memory and the on-disk file sizes are still B.
If we clone into the range [E...F) from another file:

	[A....C)[C.D)      [E...F)

then xfs_reflink_zero_posteof() calls iomap_zero_range() to zero out the
range [B, E) beyond EOF and flush it. Since [C, D) is still a delalloc
extent, its pagecache will be zeroed and both the in-memory and on-disk
size will be updated to D after flushing but before cloning. This is
wrong, because the user can see the size change and read the zeroes
while the clone operation is ongoing.

We need to keep the in-memory and on-disk size before the clone
operation starts, so instead of writing zeroes through the page cache
for delayed ranges beyond EOF, we convert these ranges to unwritten and
invalidate any cached data over that range beyond EOF.

Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_iomap.c |   29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1006,6 +1006,24 @@ xfs_buffered_write_iomap_begin(
 	}
 
 	/*
+	 * For zeroing, trim a delalloc extent that extends beyond the EOF
+	 * block.  If it starts beyond the EOF block, convert it to an
+	 * unwritten extent.
+	 */
+	if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb &&
+	    isnullstartblock(imap.br_startblock)) {
+		xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
+
+		if (offset_fsb >= eof_fsb)
+			goto convert_delay;
+		if (end_fsb > eof_fsb) {
+			end_fsb = eof_fsb;
+			xfs_trim_extent(&imap, offset_fsb,
+					end_fsb - offset_fsb);
+		}
+	}
+
+	/*
 	 * Search the COW fork extent list even if we did not find a data fork
 	 * extent.  This serves two purposes: first this implements the
 	 * speculative preallocation using cowextsize, so that we also unshare
@@ -1150,6 +1168,17 @@ found_imap:
 	xfs_iunlock(ip, lockmode);
 	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq);
 
+convert_delay:
+	xfs_iunlock(ip, lockmode);
+	truncate_pagecache(inode, offset);
+	error = xfs_bmapi_convert_delalloc(ip, XFS_DATA_FORK, offset,
+					   iomap, NULL);
+	if (error)
+		return error;
+
+	trace_xfs_iomap_alloc(ip, offset, count, XFS_DATA_FORK, &imap);
+	return 0;
+
 found_cow:
 	seq = xfs_iomap_inode_sequence(ip, 0);
 	if (imap.br_startoff <= offset_fsb) {

[PATCH 6.6 039/124] xfs: allow symlinks with short remote targets

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 38de567906d95c397d87f292b892686b7ec6fbc3 upstream.

An internal user complained about log recovery failing on a symlink
("Bad dinode after recovery") with the following (excerpted) format:

core.magic = 0x494e
core.mode = 0120777
core.version = 3
core.format = 2 (extents)
core.nlinkv2 = 1
core.nextents = 1
core.size = 297
core.nblocks = 1
core.naextents = 0
core.forkoff = 0
core.aformat = 2 (extents)
u3.bmx[0] = [startoff,startblock,blockcount,extentflag]
0:[0,12,1,0]

This is a symbolic link with a 297-byte target stored in a disk block,
which is to say this is a symlink with a remote target.  The forkoff is
0, which is to say that there's 512 - 176 == 336 bytes in the inode core
to store the data fork.

Eventually, testing of generic/388 failed with the same inode corruption
message during inode recovery.  In writing a debugging patch to call
xfs_dinode_verify on dirty inode log items when we're committing
transactions, I observed that xfs/298 can reproduce the problem quite
quickly.

xfs/298 creates a symbolic link, adds some extended attributes, then
deletes them all.  The test failure occurs when the final removexattr
also deletes the attr fork because that does not convert the remote
symlink back into a shortform symlink.  That is how we trip this test.
The only reason why xfs/298 only triggers with the debug patch added is
that it deletes the symlink, so the final iflush shows the inode as
free.

I wrote a quick fstest to emulate the behavior of xfs/298, except that
it leaves the symlinks on the filesystem after inducing the "corrupt"
state.  Kernels going back at least as far as 4.18 have written out
symlink inodes in this manner and prior to 1eb70f54c445f they did not
object to reading them back in.

Because we've been writing out inodes this way for quite some time, the
only way to fix this is to relax the check for symbolic links.
Directories don't have this problem because di_size is bumped to
blocksize during the sf->data conversion.

Fixes: 1eb70f54c445f ("xfs: validate inode fork size against fork format")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c |   28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -366,17 +366,37 @@ xfs_dinode_verify_fork(
 	/*
 	 * For fork types that can contain local data, check that the fork
 	 * format matches the size of local data contained within the fork.
-	 *
-	 * For all types, check that when the size says the should be in extent
-	 * or btree format, the inode isn't claiming it is in local format.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
-		if (S_ISDIR(mode) || S_ISLNK(mode)) {
+		/*
+		 * A directory small enough to fit in the inode must be stored
+		 * in local format.  The directory sf <-> extents conversion
+		 * code updates the directory size accordingly.
+		 */
+		if (S_ISDIR(mode)) {
 			if (be64_to_cpu(dip->di_size) <= fork_size &&
 			    fork_format != XFS_DINODE_FMT_LOCAL)
 				return __this_address;
 		}
 
+		/*
+		 * A symlink with a target small enough to fit in the inode can
+		 * be stored in extents format if xattrs were added (thus
+		 * converting the data fork from shortform to remote format)
+		 * and then removed.
+		 */
+		if (S_ISLNK(mode)) {
+			if (be64_to_cpu(dip->di_size) <= fork_size &&
+			    fork_format != XFS_DINODE_FMT_EXTENTS &&
+			    fork_format != XFS_DINODE_FMT_LOCAL)
+				return __this_address;
+		}
+
+		/*
+		 * For all types, check that when the size says the fork should
+		 * be in extent or btree format, the inode isn't claiming to be
+		 * in local format.
+		 */
 		if (be64_to_cpu(dip->di_size) > fork_size &&
 		    fork_format == XFS_DINODE_FMT_LOCAL)
 			return __this_address;

[PATCH 6.6 040/124] xfs: make sure sb_fdblocks is non-negative

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Wengang Wang <wen.gang.wang@oracle.com>

commit 58f880711f2ba53fd5e959875aff5b3bf6d5c32e upstream.

A user with a completely full filesystem experienced an unexpected
shutdown when the filesystem tried to write the superblock during
runtime.
kernel shows the following dmesg:

[    8.176281] XFS (dm-4): Metadata corruption detected at xfs_sb_write_verify+0x60/0x120 [xfs], xfs_sb block 0x0
[    8.177417] XFS (dm-4): Unmount and run xfs_repair
[    8.178016] XFS (dm-4): First 128 bytes of corrupted metadata buffer:
[    8.178703] 00000000: 58 46 53 42 00 00 10 00 00 00 00 00 01 90 00 00  XFSB............
[    8.179487] 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[    8.180312] 00000020: cf 12 dc 89 ca 26 45 29 92 e6 e3 8d 3b b8 a2 c3  .....&E)....;...
[    8.181150] 00000030: 00 00 00 00 01 00 00 06 00 00 00 00 00 00 00 80  ................
[    8.182003] 00000040: 00 00 00 00 00 00 00 81 00 00 00 00 00 00 00 82  ................
[    8.182004] 00000050: 00 00 00 01 00 64 00 00 00 00 00 04 00 00 00 00  .....d..........
[    8.182004] 00000060: 00 00 64 00 b4 a5 02 00 02 00 00 08 00 00 00 00  ..d.............
[    8.182005] 00000070: 00 00 00 00 00 00 00 00 0c 09 09 03 17 00 00 19  ................
[    8.182008] XFS (dm-4): Corruption of in-memory data detected.  Shutting down filesystem
[    8.182010] XFS (dm-4): Please unmount the filesystem and rectify the problem(s)

When xfs_log_sb writes super block to disk, b_fdblocks is fetched from
m_fdblocks without any lock. As m_fdblocks can experience a positive ->
negative -> positive changing when the FS reaches fullness (see
xfs_mod_fdblocks). So there is a chance that sb_fdblocks is negative, and
because sb_fdblocks is type of unsigned long long, it reads super big.
And sb_fdblocks being bigger than sb_dblocks is a problem during log
recovery, xfs_validate_sb_write() complains.

Fix:
As sb_fdblocks will be re-calculated during mount when lazysbcount is
enabled, We just need to make xfs_validate_sb_write() happy -- make sure
sb_fdblocks is not nenative. This patch also takes care of other percpu
counters in xfs_log_sb.

Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_sb.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1031,11 +1031,12 @@ xfs_log_sb(
 	 * and hence we don't need have to update it here.
 	 */
 	if (xfs_has_lazysbcount(mp)) {
-		mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+		mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount);
 		mp->m_sb.sb_ifree = min_t(uint64_t,
-				percpu_counter_sum(&mp->m_ifree),
+				percpu_counter_sum_positive(&mp->m_ifree),
 				mp->m_sb.sb_icount);
-		mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+		mp->m_sb.sb_fdblocks =
+				percpu_counter_sum_positive(&mp->m_fdblocks);
 	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);

[PATCH 6.6 041/124] xfs: fix unlink vs cluster buffer instantiation race

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dave Chinner <dchinner@redhat.com>

commit 348a1983cf4cf5099fc398438a968443af4c9f65 upstream.

Luis has been reporting an assert failure when freeing an inode
cluster during inode inactivation for a while. The assert looks
like:

 XFS: Assertion failed: bp->b_flags & XBF_DONE, file: fs/xfs/xfs_trans_buf.c, line: 241
 ------------[ cut here ]------------
 kernel BUG at fs/xfs/xfs_message.c:102!
 Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
 CPU: 4 PID: 73 Comm: kworker/4:1 Not tainted 6.10.0-rc1 #4
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
 Workqueue: xfs-inodegc/loop5 xfs_inodegc_worker [xfs]
 RIP: 0010:assfail (fs/xfs/xfs_message.c:102) xfs
 RSP: 0018:ffff88810188f7f0 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff88816e748250 RCX: 1ffffffff844b0e7
 RDX: 0000000000000004 RSI: ffff88810188f558 RDI: ffffffffc2431fa0
 RBP: 1ffff11020311f01 R08: 0000000042431f9f R09: ffffed1020311e9b
 R10: ffff88810188f4df R11: ffffffffac725d70 R12: ffff88817a3f4000
 R13: ffff88812182f000 R14: ffff88810188f998 R15: ffffffffc2423f80
 FS:  0000000000000000(0000) GS:ffff8881c8400000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000055fe9d0f109c CR3: 000000014426c002 CR4: 0000000000770ef0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  <TASK>
 xfs_trans_read_buf_map (fs/xfs/xfs_trans_buf.c:241 (discriminator 1)) xfs
 xfs_imap_to_bp (fs/xfs/xfs_trans.h:210 fs/xfs/libxfs/xfs_inode_buf.c:138) xfs
 xfs_inode_item_precommit (fs/xfs/xfs_inode_item.c:145) xfs
 xfs_trans_run_precommits (fs/xfs/xfs_trans.c:931) xfs
 __xfs_trans_commit (fs/xfs/xfs_trans.c:966) xfs
 xfs_inactive_ifree (fs/xfs/xfs_inode.c:1811) xfs
 xfs_inactive (fs/xfs/xfs_inode.c:2013) xfs
 xfs_inodegc_worker (fs/xfs/xfs_icache.c:1841 fs/xfs/xfs_icache.c:1886) xfs
 process_one_work (kernel/workqueue.c:3231)
 worker_thread (kernel/workqueue.c:3306 (discriminator 2) kernel/workqueue.c:3393 (discriminator 2))
 kthread (kernel/kthread.c:389)
 ret_from_fork (arch/x86/kernel/process.c:147)
 ret_from_fork_asm (arch/x86/entry/entry_64.S:257)
  </TASK>

And occurs when the the inode precommit handlers is attempt to look
up the inode cluster buffer to attach the inode for writeback.

The trail of logic that I can reconstruct is as follows.

	1. the inode is clean when inodegc runs, so it is not
	   attached to a cluster buffer when precommit runs.

	2. #1 implies the inode cluster buffer may be clean and not
	   pinned by dirty inodes when inodegc runs.

	3. #2 implies that the inode cluster buffer can be reclaimed
	   by memory pressure at any time.

	4. The assert failure implies that the cluster buffer was
	   attached to the transaction, but not marked done. It had
	   been accessed earlier in the transaction, but not marked
	   done.

	5. #4 implies the cluster buffer has been invalidated (i.e.
	   marked stale).

	6. #5 implies that the inode cluster buffer was instantiated
	   uninitialised in the transaction in xfs_ifree_cluster(),
	   which only instantiates the buffers to invalidate them
	   and never marks them as done.

Given factors 1-3, this issue is highly dependent on timing and
environmental factors. Hence the issue can be very difficult to
reproduce in some situations, but highly reliable in others. Luis
has an environment where it can be reproduced easily by g/531 but,
OTOH, I've reproduced it only once in ~2000 cycles of g/531.

I think the fix is to have xfs_ifree_cluster() set the XBF_DONE flag
on the cluster buffers, even though they may not be initialised. The
reasons why I think this is safe are:

	1. A buffer cache lookup hit on a XBF_STALE buffer will
	   clear the XBF_DONE flag. Hence all future users of the
	   buffer know they have to re-initialise the contents
	   before use and mark it done themselves.

	2. xfs_trans_binval() sets the XFS_BLI_STALE flag, which
	   means the buffer remains locked until the journal commit
	   completes and the buffer is unpinned. Hence once marked
	   XBF_STALE/XFS_BLI_STALE by xfs_ifree_cluster(), the only
	   context that can access the freed buffer is the currently
	   running transaction.

	3. #2 implies that future buffer lookups in the currently
	   running transaction will hit the transaction match code
	   and not the buffer cache. Hence XBF_STALE and
	   XFS_BLI_STALE will not be cleared unless the transaction
	   initialises and logs the buffer with valid contents
	   again. At which point, the buffer will be marked marked
	   XBF_DONE again, so having XBF_DONE already set on the
	   stale buffer is a moot point.

	4. #2 also implies that any concurrent access to that
	   cluster buffer will block waiting on the buffer lock
	   until the inode cluster has been fully freed and is no
	   longer an active inode cluster buffer.

	5. #4 + #1 means that any future user of the disk range of
	   that buffer will always see the range of disk blocks
	   covered by the cluster buffer as not done, and hence must
	   initialise the contents themselves.

	6. Setting XBF_DONE in xfs_ifree_cluster() then means the
	   unlinked inode precommit code will see a XBF_DONE buffer
	   from the transaction match as it expects. It can then
	   attach the stale but newly dirtied inode to the stale
	   but newly dirtied cluster buffer without unexpected
	   failures. The stale buffer will then sail through the
	   journal and do the right thing with the attached stale
	   inode during unpin.

Hence the fix is just one line of extra code. The explanation of
why we have to set XBF_DONE in xfs_ifree_cluster, OTOH, is long and
complex....

Fixes: 82842fee6e59 ("xfs: fix AGF vs inode cluster buffer deadlock")
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Tested-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_inode.c |   23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2329,11 +2329,26 @@ xfs_ifree_cluster(
 		 * This buffer may not have been correctly initialised as we
 		 * didn't read it from disk. That's not important because we are
 		 * only using to mark the buffer as stale in the log, and to
-		 * attach stale cached inodes on it. That means it will never be
-		 * dispatched for IO. If it is, we want to know about it, and we
-		 * want it to fail. We can acheive this by adding a write
-		 * verifier to the buffer.
+		 * attach stale cached inodes on it.
+		 *
+		 * For the inode that triggered the cluster freeing, this
+		 * attachment may occur in xfs_inode_item_precommit() after we
+		 * have marked this buffer stale.  If this buffer was not in
+		 * memory before xfs_ifree_cluster() started, it will not be
+		 * marked XBF_DONE and this will cause problems later in
+		 * xfs_inode_item_precommit() when we trip over a (stale, !done)
+		 * buffer to attached to the transaction.
+		 *
+		 * Hence we have to mark the buffer as XFS_DONE here. This is
+		 * safe because we are also marking the buffer as XBF_STALE and
+		 * XFS_BLI_STALE. That means it will never be dispatched for
+		 * IO and it won't be unlocked until the cluster freeing has
+		 * been committed to the journal and the buffer unpinned. If it
+		 * is written, we want to know about it, and we want it to
+		 * fail. We can acheive this by adding a write verifier to the
+		 * buffer.
 		 */
+		bp->b_flags |= XBF_DONE;
 		bp->b_ops = &xfs_inode_buf_ops;
 
 		/*

[PATCH 6.6 042/124] xfs: fix freeing speculative preallocations for preallocated files

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <hch@lst.de>

commit 610b29161b0aa9feb59b78dc867553274f17fb01 upstream.

xfs_can_free_eofblocks returns false for files that have persistent
preallocations unless the force flag is passed and there are delayed
blocks.  This means it won't free delalloc reservations for files
with persistent preallocations unless the force flag is set, and it
will also free the persistent preallocations if the force flag is
set and the file happens to have delayed allocations.

Both of these are bad, so do away with the force flag and always free
only post-EOF delayed allocations for files with the XFS_DIFLAG_PREALLOC
or APPEND flags set.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/xfs_bmap_util.c |   30 ++++++++++++++++++++++--------
 fs/xfs/xfs_bmap_util.h |    2 +-
 fs/xfs/xfs_icache.c    |    2 +-
 fs/xfs/xfs_inode.c     |   14 ++++----------
 4 files changed, 28 insertions(+), 20 deletions(-)

--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -636,13 +636,11 @@ out_unlock:
 
 /*
  * Test whether it is appropriate to check an inode for and free post EOF
- * blocks. The 'force' parameter determines whether we should also consider
- * regular files that are marked preallocated or append-only.
+ * blocks.
  */
 bool
 xfs_can_free_eofblocks(
-	struct xfs_inode	*ip,
-	bool			force)
+	struct xfs_inode	*ip)
 {
 	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -676,11 +674,11 @@ xfs_can_free_eofblocks(
 		return false;
 
 	/*
-	 * Do not free real preallocated or append-only files unless the file
-	 * has delalloc blocks and we are forced to remove them.
+	 * Only free real extents for inodes with persistent preallocations or
+	 * the append-only flag.
 	 */
 	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
-		if (!force || ip->i_delayed_blks == 0)
+		if (ip->i_delayed_blks == 0)
 			return false;
 
 	/*
@@ -734,6 +732,22 @@ xfs_free_eofblocks(
 	/* Wait on dio to ensure i_size has settled. */
 	inode_dio_wait(VFS_I(ip));
 
+	/*
+	 * For preallocated files only free delayed allocations.
+	 *
+	 * Note that this means we also leave speculative preallocations in
+	 * place for preallocated files.
+	 */
+	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {
+		if (ip->i_delayed_blks) {
+			xfs_bmap_punch_delalloc_range(ip,
+				round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
+				LLONG_MAX);
+		}
+		xfs_inode_clear_eofblocks_tag(ip);
+		return 0;
+	}
+
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
 	if (error) {
 		ASSERT(xfs_is_shutdown(mp));
@@ -1048,7 +1062,7 @@ xfs_prepare_shift(
 	 * Trim eofblocks to avoid shifting uninitialized post-eof preallocation
 	 * into the accessible region of the file.
 	 */
-	if (xfs_can_free_eofblocks(ip, true)) {
+	if (xfs_can_free_eofblocks(ip)) {
 		error = xfs_free_eofblocks(ip);
 		if (error)
 			return error;
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -63,7 +63,7 @@ int	xfs_insert_file_space(struct xfs_ino
 				xfs_off_t len);
 
 /* EOF block manipulation functions */
-bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
+bool	xfs_can_free_eofblocks(struct xfs_inode *ip);
 int	xfs_free_eofblocks(struct xfs_inode *ip);
 
 int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1149,7 +1149,7 @@ xfs_inode_free_eofblocks(
 	}
 	*lockflags |= XFS_IOLOCK_EXCL;
 
-	if (xfs_can_free_eofblocks(ip, false))
+	if (xfs_can_free_eofblocks(ip))
 		return xfs_free_eofblocks(ip);
 
 	/* inode could be preallocated or append-only */
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1469,7 +1469,7 @@ xfs_release(
 	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
 		return 0;
 
-	if (xfs_can_free_eofblocks(ip, false)) {
+	if (xfs_can_free_eofblocks(ip)) {
 		/*
 		 * Check if the inode is being opened, written and closed
 		 * frequently and we have delayed allocation blocks outstanding
@@ -1685,15 +1685,13 @@ xfs_inode_needs_inactive(
 
 	/*
 	 * This file isn't being freed, so check if there are post-eof blocks
-	 * to free.  @force is true because we are evicting an inode from the
-	 * cache.  Post-eof blocks must be freed, lest we end up with broken
-	 * free space accounting.
+	 * to free.
 	 *
 	 * Note: don't bother with iolock here since lockdep complains about
 	 * acquiring it in reclaim context. We have the only reference to the
 	 * inode at this point anyways.
 	 */
-	return xfs_can_free_eofblocks(ip, true);
+	return xfs_can_free_eofblocks(ip);
 }
 
 /*
@@ -1741,15 +1739,11 @@ xfs_inactive(
 
 	if (VFS_I(ip)->i_nlink != 0) {
 		/*
-		 * force is true because we are evicting an inode from the
-		 * cache. Post-eof blocks must be freed, lest we end up with
-		 * broken free space accounting.
-		 *
 		 * Note: don't bother with iolock here since lockdep complains
 		 * about acquiring it in reclaim context. We have the only
 		 * reference to the inode at this point anyways.
 		 */
-		if (xfs_can_free_eofblocks(ip, true))
+		if (xfs_can_free_eofblocks(ip))
 			error = xfs_free_eofblocks(ip);
 
 		goto out;

[PATCH 6.6 043/124] xfs: allow unlinked symlinks and dirs with zero size

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 1ec9307fc066dd8a140d5430f8a7576aa9d78cd3 upstream.

For a very very long time, inode inactivation has set the inode size to
zero before unmapping the extents associated with the data fork.
Unfortunately, commit 3c6f46eacd876 changed the inode verifier to
prohibit zero-length symlinks and directories.  If an inode happens to
get logged in this state and the system crashes before freeing the
inode, log recovery will also fail on the broken inode.

Therefore, allow zero-size symlinks and directories as long as the link
count is zero; nobody will be able to open these files by handle so
there isn't any risk of data exposure.

Fixes: 3c6f46eacd876 ("xfs: sanity check directory inode di_size")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c |   23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -371,10 +371,13 @@ xfs_dinode_verify_fork(
 		/*
 		 * A directory small enough to fit in the inode must be stored
 		 * in local format.  The directory sf <-> extents conversion
-		 * code updates the directory size accordingly.
+		 * code updates the directory size accordingly.  Directories
+		 * being truncated have zero size and are not subject to this
+		 * check.
 		 */
 		if (S_ISDIR(mode)) {
-			if (be64_to_cpu(dip->di_size) <= fork_size &&
+			if (dip->di_size &&
+			    be64_to_cpu(dip->di_size) <= fork_size &&
 			    fork_format != XFS_DINODE_FMT_LOCAL)
 				return __this_address;
 		}
@@ -512,9 +515,19 @@ xfs_dinode_verify(
 	if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
 		return __this_address;
 
-	/* No zero-length symlinks/dirs. */
-	if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
-		return __this_address;
+	/*
+	 * No zero-length symlinks/dirs unless they're unlinked and hence being
+	 * inactivated.
+	 */
+	if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) {
+		if (dip->di_version > 1) {
+			if (dip->di_nlink)
+				return __this_address;
+		} else {
+			if (dip->di_onlink)
+				return __this_address;
+		}
+	}
 
 	fa = xfs_dinode_verify_nrext64(mp, dip);
 	if (fa)

[PATCH 6.6 044/124] xfs: restrict when we try to align cow fork delalloc to cowextsz hints

[Greg Kroah-Hartman]

6.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <djwong@kernel.org>

commit 288e1f693f04e66be99f27e7cbe4a45936a66745 upstream.

xfs/205 produces the following failure when always_cow is enabled:

#  --- a/tests/xfs/205.out	2024-02-28 16:20:24.437887970 -0800
#  +++ b/tests/xfs/205.out.bad	2024-06-03 21:13:40.584000000 -0700
#  @@ -1,4 +1,5 @@
#   QA output created by 205
#   *** one file
#  +   !!! disk full (expected)
#   *** one file, a few bytes at a time
#   *** done

This is the result of overly aggressive attempts to align cow fork
delalloc reservations to the CoW extent size hint.  Looking at the trace
data, we're trying to append a single fsblock to the "fred" file.
Trying to create a speculative post-eof reservation fails because
there's not enough space.

We then set @prealloc_blocks to zero and try again, but the cowextsz
alignment code triggers, which expands our request for a 1-fsblock
reservation into a 39-block reservation.  There's not enough space for
that, so the whole write fails with ENOSPC even though there's
sufficient space in the filesystem to allocate the single block that we
need to land the write.

There are two things wrong here -- first, we shouldn't be attempting
speculative preallocations beyond what was requested when we're low on
space.  Second, if we've already computed a posteof preallocation, we
shouldn't bother trying to align that to the cowextsize hint.

Fix both of these problems by adding a flag that only enables the
expansion of the delalloc reservation to the cowextsize if we're doing a
non-extending write, and only if we're not doing an ENOSPC retry.  This
requires us to move the ENOSPC retry logic to xfs_bmapi_reserve_delalloc.

I probably should have caught this six years ago when 6ca30729c206d was
being reviewed, but oh well.  Update the comments to reflect what the
code does now.

Fixes: 6ca30729c206d ("xfs: bmap code cleanup")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   31 +++++++++++++++++++++++++++----
 fs/xfs/xfs_iomap.c       |   34 ++++++++++++----------------------
 2 files changed, 39 insertions(+), 26 deletions(-)

--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3974,20 +3974,32 @@ xfs_bmapi_reserve_delalloc(
 	xfs_extlen_t		alen;
 	xfs_extlen_t		indlen;
 	int			error;
-	xfs_fileoff_t		aoff = off;
+	xfs_fileoff_t		aoff;
+	bool			use_cowextszhint =
+					whichfork == XFS_COW_FORK && !prealloc;
 
+retry:
 	/*
 	 * Cap the alloc length. Keep track of prealloc so we know whether to
 	 * tag the inode before we return.
 	 */
+	aoff = off;
 	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)
 		prealloc = alen - len;
 
-	/* Figure out the extent size, adjust alen */
-	if (whichfork == XFS_COW_FORK) {
+	/*
+	 * If we're targetting the COW fork but aren't creating a speculative
+	 * posteof preallocation, try to expand the reservation to align with
+	 * the COW extent size hint if there's sufficient free space.
+	 *
+	 * Unlike the data fork, the CoW cancellation functions will free all
+	 * the reservations at inactivation, so we don't require that every
+	 * delalloc reservation have a dirty pagecache.
+	 */
+	if (use_cowextszhint) {
 		struct xfs_bmbt_irec	prev;
 		xfs_extlen_t		extsz = xfs_get_cowextsz_hint(ip);
 
@@ -4006,7 +4018,7 @@ xfs_bmapi_reserve_delalloc(
 	 */
 	error = xfs_quota_reserve_blkres(ip, alen);
 	if (error)
-		return error;
+		goto out;
 
 	/*
 	 * Split changing sb for alen and indlen since they could be coming
@@ -4051,6 +4063,17 @@ out_unreserve_blocks:
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
 		xfs_quota_unreserve_blkres(ip, alen);
+out:
+	if (error == -ENOSPC || error == -EDQUOT) {
+		trace_xfs_delalloc_enospc(ip, off, len);
+
+		if (prealloc || use_cowextszhint) {
+			/* retry without any preallocation */
+			use_cowextszhint = false;
+			prealloc = 0;
+			goto retry;
+		}
+	}
 	return error;
 }
 
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1127,33 +1127,23 @@ xfs_buffered_write_iomap_begin(
 		}
 	}
 
-retry:
-	error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
-			end_fsb - offset_fsb, prealloc_blocks,
-			allocfork == XFS_DATA_FORK ? &imap : &cmap,
-			allocfork == XFS_DATA_FORK ? &icur : &ccur,
-			allocfork == XFS_DATA_FORK ? eof : cow_eof);
-	switch (error) {
-	case 0:
-		break;
-	case -ENOSPC:
-	case -EDQUOT:
-		/* retry without any preallocation */
-		trace_xfs_delalloc_enospc(ip, offset, count);
-		if (prealloc_blocks) {
-			prealloc_blocks = 0;
-			goto retry;
-		}
-		fallthrough;
-	default:
-		goto out_unlock;
-	}
-
 	if (allocfork == XFS_COW_FORK) {
+		error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
+				end_fsb - offset_fsb, prealloc_blocks, &cmap,
+				&ccur, cow_eof);
+		if (error)
+			goto out_unlock;
+
 		trace_xfs_iomap_alloc(ip, offset, count, allocfork, &cmap);
 		goto found_cow;
 	}
 
+	error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
+			end_fsb - offset_fsb, prealloc_blocks, &imap, &icur,
+			eof);
+	if (error)
+		goto out_unlock;
+
 	/*
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.