Merge tag 'large-extent-counters-v9' of https://github.com/chandanr/linux into xfs-5.19-for-next

xfs: Large extent counters

The commit xfs: fix inode fork extent count overflow
(3f8a4f1d876d3e3e49e50b0396eaffcc4ba71b08) mentions that 10 billion
data fork extents should be possible to create. However the
corresponding on-disk field has a signed 32-bit type. Hence this
patchset extends the per-inode data fork extent counter to 64 bits
(out of which 48 bits are used to store the extent count).

Also, XFS has an attribute fork extent counter which is 16 bits
wide. A workload that,
1. Creates 1 million 255-byte sized xattrs,
2. Deletes 50% of these xattrs in an alternating manner,
3. Tries to insert 400,000 new 255-byte sized xattrs
   causes the xattr extent counter to overflow.

Dave tells me that there are instances where a single file has more
than 100 million hardlinks. With parent pointers being stored in
xattrs, we will overflow the signed 16-bits wide attribute extent
counter when large number of hardlinks are created. Hence this
patchset extends the on-disk field to 32-bits.

The following changes are made to accomplish this,
1. A 64-bit inode field is carved out of existing di_pad and
   di_flushiter fields to hold the 64-bit data fork extent counter.
2. The existing 32-bit inode data fork extent counter will be used to
   hold the attribute fork extent counter.
3. A new incompat superblock flag to prevent older kernels from mounting
   the filesystem.

Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

1 files changed, 32 insertions, 7 deletions

diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 9149f4f796fc..9aee4a1e2fe9 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;
@@ -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);
@@ -230,7 +230,7 @@ xfs_iformat_data_fork(
 	 * depend on it.
 	 */
 	ip->i_df.if_format = dip->di_format;
-	ip->i_df.if_nextents = be32_to_cpu(dip->di_nextents);
+	ip->i_df.if_nextents = xfs_dfork_data_extents(dip);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFIFO:
@@ -295,14 +295,14 @@ xfs_iformat_attr_fork(
 	struct xfs_inode	*ip,
 	struct xfs_dinode	*dip)
 {
+	xfs_extnum_t		naextents = xfs_dfork_attr_extents(dip);
 	int			error = 0;
 
 	/*
 	 * Initialize the extent count early, as the per-format routines may
 	 * depend on it.
 	 */
-	ip->i_afp = xfs_ifork_alloc(dip->di_aformat,
-				be16_to_cpu(dip->di_anextents));
+	ip->i_afp = xfs_ifork_alloc(dip->di_aformat, naextents);
 
 	switch (ip->i_afp->if_format) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -744,7 +744,8 @@ 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(xfs_inode_has_large_extent_counts(ip),
+				whichfork);
 
 	if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
 		max_exts = 10;
@@ -755,3 +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;
+}