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, 67 insertions, 16 deletions

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index cae9708c8587..74b82ec80f8e 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -279,6 +279,25 @@ xfs_inode_to_disk_ts(
 	return ts;
 }
 
+static inline void
+xfs_inode_to_disk_iext_counters(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*to)
+{
+	if (xfs_inode_has_large_extent_counts(ip)) {
+		to->di_big_nextents = cpu_to_be64(xfs_ifork_nextents(&ip->i_df));
+		to->di_big_anextents = cpu_to_be32(xfs_ifork_nextents(ip->i_afp));
+		/*
+		 * We might be upgrading the inode to use larger extent counters
+		 * than was previously used. Hence zero the unused field.
+		 */
+		to->di_nrext64_pad = cpu_to_be16(0);
+	} else {
+		to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
+		to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
+	}
+}
+
 void
 xfs_inode_to_disk(
 	struct xfs_inode	*ip,
@@ -296,7 +315,6 @@ xfs_inode_to_disk(
 	to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff);
 	to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16);
 
-	memset(to->di_pad, 0, sizeof(to->di_pad));
 	to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
 	to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime);
 	to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime);
@@ -307,8 +325,6 @@ xfs_inode_to_disk(
 	to->di_size = cpu_to_be64(ip->i_disk_size);
 	to->di_nblocks = cpu_to_be64(ip->i_nblocks);
 	to->di_extsize = cpu_to_be32(ip->i_extsize);
-	to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
-	to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
 	to->di_forkoff = ip->i_forkoff;
 	to->di_aformat = xfs_ifork_format(ip->i_afp);
 	to->di_flags = cpu_to_be16(ip->i_diflags);
@@ -323,11 +339,14 @@ xfs_inode_to_disk(
 		to->di_lsn = cpu_to_be64(lsn);
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
-		to->di_flushiter = 0;
+		to->di_v3_pad = 0;
 	} else {
 		to->di_version = 2;
 		to->di_flushiter = cpu_to_be16(ip->i_flushiter);
+		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
 	}
+
+	xfs_inode_to_disk_iext_counters(ip, to);
 }
 
 static xfs_failaddr_t
@@ -336,7 +355,10 @@ 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_extnum_t		max_extents;
+
+	di_nextents = xfs_dfork_nextents(dip, whichfork);
 
 	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -358,12 +380,11 @@ 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(
+					xfs_dinode_has_large_extent_counts(dip),
+					whichfork);
+		if (di_nextents > max_extents)
 			return __this_address;
-		}
 		break;
 	default:
 		return __this_address;
@@ -396,6 +417,24 @@ xfs_dinode_verify_forkoff(
 	return NULL;
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_nrext64(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	*dip)
+{
+	if (xfs_dinode_has_large_extent_counts(dip)) {
+		if (!xfs_has_large_extent_counts(mp))
+			return __this_address;
+		if (dip->di_nrext64_pad != 0)
+			return __this_address;
+	} else if (dip->di_version >= 3) {
+		if (dip->di_v3_pad != 0)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -407,6 +446,9 @@ xfs_dinode_verify(
 	uint16_t		flags;
 	uint64_t		flags2;
 	uint64_t		di_size;
+	xfs_extnum_t		nextents;
+	xfs_extnum_t		naextents;
+	xfs_filblks_t		nblocks;
 
 	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
 		return __this_address;
@@ -437,10 +479,19 @@ xfs_dinode_verify(
 	if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
 		return __this_address;
 
+	fa = xfs_dinode_verify_nrext64(mp, dip);
+	if (fa)
+		return fa;
+
+	nextents = xfs_dfork_data_extents(dip);
+	naextents = xfs_dfork_attr_extents(dip);
+	nblocks = be64_to_cpu(dip->di_nblocks);
+
 	/* Fork checks carried over from xfs_iformat_fork */
-	if (mode &&
-	    be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
-			be64_to_cpu(dip->di_nblocks))
+	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)
@@ -497,7 +548,7 @@ xfs_dinode_verify(
 		default:
 			return __this_address;
 		}
-		if (dip->di_anextents)
+		if (naextents)
 			return __this_address;
 	}
 
@@ -639,7 +690,7 @@ xfs_inode_validate_extsize(
 	if (extsize_bytes % blocksize_bytes)
 		return __this_address;
 
-	if (extsize > MAXEXTLEN)
+	if (extsize > XFS_MAX_BMBT_EXTLEN)
 		return __this_address;
 
 	if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
@@ -696,7 +747,7 @@ xfs_inode_validate_cowextsize(
 	if (cowextsize_bytes % mp->m_sb.sb_blocksize)
 		return __this_address;
 
-	if (cowextsize > MAXEXTLEN)
+	if (cowextsize > XFS_MAX_BMBT_EXTLEN)
 		return __this_address;
 
 	if (cowextsize > mp->m_sb.sb_agblocks / 2)