xfs: Introduce per-inode 64-bit extent counters

This commit introduces new fields in the on-disk inode format to support
64-bit data fork extent counters and 32-bit attribute fork extent
counters. The new fields will be used only when an inode has
XFS_DIFLAG2_NREXT64 flag set. Otherwise we continue to use the regular 32-bit
data fork extent counters and 16-bit attribute fork extent counters.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
Suggested-by: Dave Chinner <dchinner@redhat.com>

Author: Chandan Babu R

fs/xfs/libxfs/xfs_format.h

@@ -792,16 +792,41 @@ struct xfs_dinode {
 	__be32		di_nlink;	/* number of links to file */
 	__be16		di_projid_lo;	/* lower part of owner's project id */
 	__be16		di_projid_hi;	/* higher part owner's project id */
-	__u8		di_pad[6];	/* unused, zeroed space */
-	__be16		di_flushiter;	/* incremented on flush */
+	union {
+		/* Number of data fork extents if NREXT64 is set */
+		__be64	di_big_nextents;
+
+		/* Padding for V3 inodes without NREXT64 set. */
+		__be64	di_v3_pad;
+
+		/* Padding and inode flush counter for V2 inodes. */
+		struct {
+			__u8	di_v2_pad[6];
+			__be16	di_flushiter;
+		};
+	};
 	xfs_timestamp_t	di_atime;	/* time last accessed */
 	xfs_timestamp_t	di_mtime;	/* time last modified */
 	xfs_timestamp_t	di_ctime;	/* time created/inode modified */
 	__be64		di_size;	/* number of bytes in file */
 	__be64		di_nblocks;	/* # of direct & btree blocks used */
 	__be32		di_extsize;	/* basic/minimum extent size for file */
-	__be32		di_nextents;	/* number of extents in data fork */
-	__be16		di_anextents;	/* number of extents in attribute fork*/
+	union {
+		/*
+		 * For V2 inodes and V3 inodes without NREXT64 set, this
+		 * is the number of data and attr fork extents.
+		 */
+		struct {
+			__be32	di_nextents;
+			__be16	di_anextents;
+		} __packed;
+
+		/* Number of attr fork extents if NREXT64 is set. */
+		struct {
+			__be32	di_big_anextents;
+			__be16	di_nrext64_pad;
+		} __packed;
+	} __packed;
 	__u8		di_forkoff;	/* attr fork offs, <<3 for 64b align */
 	__s8		di_aformat;	/* format of attr fork's data */
 	__be32		di_dmevmask;	/* DMIG event mask */

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
@@ -398,6 +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,
@@ -442,6 +479,10 @@ 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);

fs/xfs/libxfs/xfs_inode_fork.h

@@ -158,13 +158,19 @@ static inline xfs_extnum_t
 xfs_dfork_data_extents(
 	struct xfs_dinode	*dip)
 {
+	if (xfs_dinode_has_large_extent_counts(dip))
+		return be64_to_cpu(dip->di_big_nextents);
+
 	return be32_to_cpu(dip->di_nextents);
 }
 
 static inline xfs_extnum_t
 xfs_dfork_attr_extents(
 	struct xfs_dinode	*dip)
 {
+	if (xfs_dinode_has_large_extent_counts(dip))
+		return be32_to_cpu(dip->di_big_anextents);
+
 	return be16_to_cpu(dip->di_anextents);
 }
 

fs/xfs/libxfs/xfs_log_format.h

@@ -388,16 +388,41 @@ struct xfs_log_dinode {
 	uint32_t	di_nlink;	/* number of links to file */
 	uint16_t	di_projid_lo;	/* lower part of owner's project id */
 	uint16_t	di_projid_hi;	/* higher part of owner's project id */
-	uint8_t		di_pad[6];	/* unused, zeroed space */
-	uint16_t	di_flushiter;	/* incremented on flush */
+	union {
+		/* Number of data fork extents if NREXT64 is set */
+		uint64_t	di_big_nextents;
+
+		/* Padding for V3 inodes without NREXT64 set. */
+		uint64_t	di_v3_pad;
+
+		/* Padding and inode flush counter for V2 inodes. */
+		struct {
+			uint8_t	di_v2_pad[6];	/* V2 inode zeroed space */
+			uint16_t di_flushiter;	/* V2 inode incremented on flush */
+		};
+	};
 	xfs_log_timestamp_t di_atime;	/* time last accessed */
 	xfs_log_timestamp_t di_mtime;	/* time last modified */
 	xfs_log_timestamp_t di_ctime;	/* time created/inode modified */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
-	uint32_t	di_nextents;	/* number of extents in data fork */
-	uint16_t	di_anextents;	/* number of extents in attribute fork*/
+	union {
+		/*
+		 * For V2 inodes and V3 inodes without NREXT64 set, this
+		 * is the number of data and attr fork extents.
+		 */
+		struct {
+			uint32_t  di_nextents;
+			uint16_t  di_anextents;
+		} __packed;
+
+		/* Number of attr fork extents if NREXT64 is set. */
+		struct {
+			uint32_t  di_big_anextents;
+			uint16_t  di_nrext64_pad;
+		} __packed;
+	} __packed;
 	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
 	int8_t		di_aformat;	/* format of attr fork's data */
 	uint32_t	di_dmevmask;	/* DMIG event mask */

fs/xfs/xfs_inode_item.c

@@ -359,6 +359,21 @@ xfs_copy_dm_fields_to_log_dinode(
 	}
 }
 
+static inline void
+xfs_inode_to_log_dinode_iext_counters(
+	struct xfs_inode	*ip,
+	struct xfs_log_dinode	*to)
+{
+	if (xfs_inode_has_large_extent_counts(ip)) {
+		to->di_big_nextents = xfs_ifork_nextents(&ip->i_df);
+		to->di_big_anextents = xfs_ifork_nextents(ip->i_afp);
+		to->di_nrext64_pad = 0;
+	} else {
+		to->di_nextents = xfs_ifork_nextents(&ip->i_df);
+		to->di_anextents = xfs_ifork_nextents(ip->i_afp);
+	}
+}
+
 static void
 xfs_inode_to_log_dinode(
 	struct xfs_inode	*ip,
@@ -374,7 +389,6 @@ xfs_inode_to_log_dinode(
 	to->di_projid_lo = ip->i_projid & 0xffff;
 	to->di_projid_hi = ip->i_projid >> 16;
 
-	memset(to->di_pad, 0, sizeof(to->di_pad));
 	memset(to->di_pad3, 0, sizeof(to->di_pad3));
 	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime);
 	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime);
@@ -386,8 +400,6 @@ xfs_inode_to_log_dinode(
 	to->di_size = ip->i_disk_size;
 	to->di_nblocks = ip->i_nblocks;
 	to->di_extsize = ip->i_extsize;
-	to->di_nextents = xfs_ifork_nextents(&ip->i_df);
-	to->di_anextents = xfs_ifork_nextents(ip->i_afp);
 	to->di_forkoff = ip->i_forkoff;
 	to->di_aformat = xfs_ifork_format(ip->i_afp);
 	to->di_flags = ip->i_diflags;
@@ -407,11 +419,14 @@ xfs_inode_to_log_dinode(
 		to->di_lsn = 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 = ip->i_flushiter;
+		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
 	}
+
+	xfs_inode_to_log_dinode_iext_counters(ip, to);
 }
 
 /*

fs/xfs/xfs_inode_item_recover.c

@@ -149,6 +149,22 @@ static inline bool xfs_log_dinode_has_large_extent_counts(
 	       (ld->di_flags2 & XFS_DIFLAG2_NREXT64);
 }
 
+static inline void
+xfs_log_dinode_to_disk_iext_counters(
+	struct xfs_log_dinode	*from,
+	struct xfs_dinode	*to)
+{
+	if (xfs_log_dinode_has_large_extent_counts(from)) {
+		to->di_big_nextents = cpu_to_be64(from->di_big_nextents);
+		to->di_big_anextents = cpu_to_be32(from->di_big_anextents);
+		to->di_nrext64_pad = cpu_to_be16(from->di_nrext64_pad);
+	} else {
+		to->di_nextents = cpu_to_be32(from->di_nextents);
+		to->di_anextents = cpu_to_be16(from->di_anextents);
+	}
+
+}
+
 STATIC void
 xfs_log_dinode_to_disk(
 	struct xfs_log_dinode	*from,
@@ -165,7 +181,6 @@ xfs_log_dinode_to_disk(
 	to->di_nlink = cpu_to_be32(from->di_nlink);
 	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
 	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
-	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 
 	to->di_atime = xfs_log_dinode_to_disk_ts(from, from->di_atime);
 	to->di_mtime = xfs_log_dinode_to_disk_ts(from, from->di_mtime);
@@ -174,8 +189,6 @@ xfs_log_dinode_to_disk(
 	to->di_size = cpu_to_be64(from->di_size);
 	to->di_nblocks = cpu_to_be64(from->di_nblocks);
 	to->di_extsize = cpu_to_be32(from->di_extsize);
-	to->di_nextents = cpu_to_be32(from->di_nextents);
-	to->di_anextents = cpu_to_be16(from->di_anextents);
 	to->di_forkoff = from->di_forkoff;
 	to->di_aformat = from->di_aformat;
 	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
@@ -191,12 +204,66 @@ xfs_log_dinode_to_disk(
 		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(from->di_ino);
 		to->di_lsn = cpu_to_be64(lsn);
-		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &from->di_uuid);
-		to->di_flushiter = 0;
+		to->di_v3_pad = 0;
 	} else {
 		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
+	}
+
+	xfs_log_dinode_to_disk_iext_counters(from, to);
+}
+
+STATIC int
+xlog_dinode_verify_extent_counts(
+	struct xfs_mount	*mp,
+	struct xfs_log_dinode	*ldip)
+{
+	xfs_extnum_t		nextents;
+	xfs_aextnum_t		anextents;
+
+	if (xfs_log_dinode_has_large_extent_counts(ldip)) {
+		if (!xfs_has_large_extent_counts(mp) ||
+		    (ldip->di_nrext64_pad != 0)) {
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode large extent count format",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+			xfs_alert(mp,
+				"Bad inode 0x%llx, large extent counts %d, padding 0x%x",
+				ldip->di_ino, xfs_has_large_extent_counts(mp),
+				ldip->di_nrext64_pad);
+			return -EFSCORRUPTED;
+		}
+
+		nextents = ldip->di_big_nextents;
+		anextents = ldip->di_big_anextents;
+	} else {
+		if (ldip->di_version == 3 && ldip->di_v3_pad != 0) {
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode di_v3_pad",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+			xfs_alert(mp,
+				"Bad inode 0x%llx, di_v3_pad 0x%llx",
+				ldip->di_ino, ldip->di_v3_pad);
+			return -EFSCORRUPTED;
+		}
+
+		nextents = ldip->di_nextents;
+		anextents = ldip->di_anextents;
+	}
+
+	if (unlikely(nextents + anextents > ldip->di_nblocks)) {
+		XFS_CORRUPTION_ERROR("Bad log dinode extent counts",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+		xfs_alert(mp,
+			"Bad inode 0x%llx, large extent counts %d, nextents 0x%llx, anextents 0x%x, nblocks 0x%llx",
+			ldip->di_ino, xfs_has_large_extent_counts(mp), nextents,
+			anextents, ldip->di_nblocks);
+		return -EFSCORRUPTED;
 	}
+
+	return 0;
 }
 
 STATIC int
@@ -347,16 +414,11 @@ xlog_recover_inode_commit_pass2(
 			goto out_release;
 		}
 	}
-	if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){
-		XFS_CORRUPTION_ERROR("Bad log dinode extent counts",
-				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
-		xfs_alert(mp,
-			"Bad inode 0x%llx, nextents 0x%x, anextents 0x%x, nblocks 0x%llx",
-			in_f->ilf_ino, ldip->di_nextents, ldip->di_anextents,
-			ldip->di_nblocks);
-		error = -EFSCORRUPTED;
+
+	error = xlog_dinode_verify_extent_counts(mp, ldip);
+	if (error)
 		goto out_release;
-	}
+
 	if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) {
 		XFS_CORRUPTION_ERROR("Bad log dinode fork offset",
 				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));