1 files changed, 209 insertions, 24 deletions

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d0dcce462bf4..aa13fc00afd7 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -19,6 +19,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
 #include "xfs_health.h"
+#include "xfs_metafile.h"
 
 #include <linux/iversion.h>
 
@@ -136,7 +137,7 @@ xfs_imap_to_bp(
 	int			error;
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+			imap->im_len, 0, bpp, &xfs_inode_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
 				XFS_SICK_AG_INODES);
@@ -209,12 +210,15 @@ xfs_inode_from_disk(
 	 * They will also be unconditionally written back to disk as v2 inodes.
 	 */
 	if (unlikely(from->di_version == 1)) {
-		set_nlink(inode, be16_to_cpu(from->di_onlink));
+		/* di_metatype used to be di_onlink */
+		set_nlink(inode, be16_to_cpu(from->di_metatype));
 		ip->i_projid = 0;
 	} else {
 		set_nlink(inode, be32_to_cpu(from->di_nlink));
 		ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
 					be16_to_cpu(from->di_projid_lo);
+		if (xfs_dinode_is_metadir(from))
+			ip->i_metatype = be16_to_cpu(from->di_metatype);
 	}
 
 	i_uid_write(inode, be32_to_cpu(from->di_uid));
@@ -248,7 +252,10 @@ xfs_inode_from_disk(
 					   be64_to_cpu(from->di_changecount));
 		ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
 		ip->i_diflags2 = be64_to_cpu(from->di_flags2);
+		/* also covers the di_used_blocks union arm: */
 		ip->i_cowextsize = be32_to_cpu(from->di_cowextsize);
+		BUILD_BUG_ON(sizeof(from->di_cowextsize) !=
+			     sizeof(from->di_used_blocks));
 	}
 
 	error = xfs_iformat_data_fork(ip, from);
@@ -315,7 +322,10 @@ xfs_inode_to_disk(
 	struct inode		*inode = VFS_I(ip);
 
 	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
-	to->di_onlink = 0;
+	if (xfs_is_metadir_inode(ip))
+		to->di_metatype = cpu_to_be16(ip->i_metatype);
+	else
+		to->di_metatype = 0;
 
 	to->di_format = xfs_ifork_format(&ip->i_df);
 	to->di_uid = cpu_to_be32(i_uid_read(inode));
@@ -342,6 +352,7 @@ xfs_inode_to_disk(
 		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
 		to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime);
 		to->di_flags2 = cpu_to_be64(ip->i_diflags2);
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = cpu_to_be32(ip->i_cowextsize);
 		to->di_ino = cpu_to_be64(ip->i_ino);
 		to->di_lsn = cpu_to_be64(lsn);
@@ -374,17 +385,40 @@ 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.  Directories
+		 * being truncated have zero size and are not subject to this
+		 * check.
+		 */
+		if (S_ISDIR(mode)) {
+			if (dip->di_size &&
+			    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;
@@ -411,6 +445,30 @@ xfs_dinode_verify_fork(
 		if (di_nextents > max_extents)
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (!xfs_has_metadir(mp))
+			return __this_address;
+		if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA)))
+			return __this_address;
+		switch (be16_to_cpu(dip->di_metatype)) {
+		case XFS_METAFILE_RTRMAP:
+			/*
+			 * growfs must create the rtrmap inodes before adding a
+			 * realtime volume to the filesystem, so we cannot use
+			 * the rtrmapbt predicate here.
+			 */
+			if (!xfs_has_rmapbt(mp))
+				return __this_address;
+			break;
+		case XFS_METAFILE_RTREFCOUNT:
+			/* same comment about growfs and rmap inodes applies */
+			if (!xfs_has_reflink(mp))
+				return __this_address;
+			break;
+		default:
+			return __this_address;
+		}
+		break;
 	default:
 		return __this_address;
 	}
@@ -430,6 +488,10 @@ xfs_dinode_verify_forkoff(
 		if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (!xfs_has_metadir(mp) || !xfs_has_parent(mp))
+			return __this_address;
+		fallthrough;
 	case XFS_DINODE_FMT_LOCAL:	/* fall through ... */
 	case XFS_DINODE_FMT_EXTENTS:    /* fall through ... */
 	case XFS_DINODE_FMT_BTREE:
@@ -460,6 +522,69 @@ xfs_dinode_verify_nrext64(
 	return NULL;
 }
 
+/*
+ * Validate all the picky requirements we have for a file that claims to be
+ * filesystem metadata.
+ */
+xfs_failaddr_t
+xfs_dinode_verify_metadir(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	*dip,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
+{
+	if (!xfs_has_metadir(mp))
+		return __this_address;
+
+	/* V5 filesystem only */
+	if (dip->di_version < 3)
+		return __this_address;
+
+	if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
+		return __this_address;
+
+	/* V3 inode fields that are always zero */
+	if ((flags2 & XFS_DIFLAG2_NREXT64) && dip->di_nrext64_pad)
+		return __this_address;
+	if (!(flags2 & XFS_DIFLAG2_NREXT64) && dip->di_flushiter)
+		return __this_address;
+
+	/* Metadata files can only be directories or regular files */
+	if (!S_ISDIR(mode) && !S_ISREG(mode))
+		return __this_address;
+
+	/* They must have zero access permissions */
+	if (mode & 0777)
+		return __this_address;
+
+	/* DMAPI event and state masks are zero */
+	if (dip->di_dmevmask || dip->di_dmstate)
+		return __this_address;
+
+	/*
+	 * User and group IDs must be zero.  The project ID is used for
+	 * grouping inodes.  Metadata inodes are never accounted to quotas.
+	 */
+	if (dip->di_uid || dip->di_gid)
+		return __this_address;
+
+	/* Mandatory inode flags must be set */
+	if (S_ISDIR(mode)) {
+		if ((flags & XFS_METADIR_DIFLAGS) != XFS_METADIR_DIFLAGS)
+			return __this_address;
+	} else {
+		if ((flags & XFS_METAFILE_DIFLAGS) != XFS_METAFILE_DIFLAGS)
+			return __this_address;
+	}
+
+	/* dax flags2 must not be set */
+	if (flags2 & XFS_DIFLAG2_DAX)
+		return __this_address;
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -491,6 +616,23 @@ xfs_dinode_verify(
 			return __this_address;
 	}
 
+	/*
+	 * Historical note: xfsprogs in the 3.2 era set up its incore inodes to
+	 * have di_nlink track the link count, even if the actual filesystem
+	 * only supported V1 inodes (i.e. di_onlink).  When writing out the
+	 * ondisk inode, it would set both the ondisk di_nlink and di_onlink to
+	 * the the incore di_nlink value, which is why we cannot check for
+	 * di_nlink==0 on a V1 inode.  V2/3 inodes would get written out with
+	 * di_onlink==0, so we can check that.
+	 */
+	if (dip->di_version == 2) {
+		if (dip->di_metatype)
+			return __this_address;
+	} else if (dip->di_version >= 3) {
+		if (!xfs_dinode_is_metadir(dip) && dip->di_metatype)
+			return __this_address;
+	}
+
 	/* don't allow invalid i_size */
 	di_size = be64_to_cpu(dip->di_size);
 	if (di_size & (1ULL << 63))
@@ -500,9 +642,20 @@ 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 {
+			/* di_metatype used to be di_onlink */
+			if (dip->di_metatype)
+				return __this_address;
+		}
+	}
 
 	fa = xfs_dinode_verify_nrext64(mp, dip);
 	if (fa)
@@ -516,9 +669,6 @@ xfs_dinode_verify(
 	if (mode && nextents + naextents > nblocks)
 		return __this_address;
 
-	if (nextents + naextents == 0 && nblocks != 0)
-		return __this_address;
-
 	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
 		return __this_address;
 
@@ -602,20 +752,40 @@ xfs_dinode_verify(
 		return __this_address;
 
 	/* don't let reflink and realtime mix */
-	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME))
+	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME) &&
+	    !xfs_has_rtreflink(mp))
 		return __this_address;
 
-	/* COW extent size hint validation */
-	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
-			mode, flags, flags2);
-	if (fa)
-		return fa;
+	if (xfs_has_zoned(mp) &&
+	    dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) {
+		if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents)
+			return __this_address;
+	} else {
+		/* COW extent size hint validation */
+		fa = xfs_inode_validate_cowextsize(mp,
+				be32_to_cpu(dip->di_cowextsize),
+				mode, flags, flags2);
+		if (fa)
+			return fa;
+	}
 
 	/* bigtime iflag can only happen on bigtime filesystems */
 	if (xfs_dinode_has_bigtime(dip) &&
 	    !xfs_has_bigtime(mp))
 		return __this_address;
 
+	if (flags2 & XFS_DIFLAG2_METADATA) {
+		fa = xfs_dinode_verify_metadir(mp, dip, mode, flags, flags2);
+		if (fa)
+			return fa;
+	}
+
+	/* metadata inodes containing btrees always have zero extent count */
+	if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) {
+		if (nextents + naextents == 0 && nblocks != 0)
+			return __this_address;
+	}
+
 	return NULL;
 }
 
@@ -751,11 +921,29 @@ xfs_inode_validate_cowextsize(
 	bool				rt_flag;
 	bool				hint_flag;
 	uint32_t			cowextsize_bytes;
+	uint32_t			blocksize_bytes;
 
 	rt_flag = (flags & XFS_DIFLAG_REALTIME);
 	hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE);
 	cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize);
 
+	/*
+	 * Similar to extent size hints, a directory can be configured to
+	 * propagate realtime status and a CoW extent size hint to newly
+	 * created files even if there is no realtime device, and the hints on
+	 * disk can become misaligned if the sysadmin changes the rt extent
+	 * size while adding the realtime device.
+	 *
+	 * Therefore, we can only enforce the rextsize alignment check against
+	 * regular realtime files, and rely on callers to decide when alignment
+	 * checks are appropriate, and fix things up as needed.
+	 */
+
+	if (rt_flag)
+		blocksize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
+	else
+		blocksize_bytes = mp->m_sb.sb_blocksize;
+
 	if (hint_flag && !xfs_has_reflink(mp))
 		return __this_address;
 
@@ -769,16 +957,13 @@ xfs_inode_validate_cowextsize(
 	if (mode && !hint_flag && cowextsize != 0)
 		return __this_address;
 
-	if (hint_flag && rt_flag)
-		return __this_address;
-
-	if (cowextsize_bytes % mp->m_sb.sb_blocksize)
+	if (cowextsize_bytes % blocksize_bytes)
 		return __this_address;
 
 	if (cowextsize > XFS_MAX_BMBT_EXTLEN)
 		return __this_address;
 
-	if (cowextsize > mp->m_sb.sb_agblocks / 2)
+	if (!rt_flag && cowextsize > mp->m_sb.sb_agblocks / 2)
 		return __this_address;
 
 	return NULL;