[PATCH v22 0/4] xfs: online repair of inodes and extent maps

[PATCH v22 0/4] xfs: online repair of inodes and extent maps

[Darrick J. Wong]

Hi all,

In the second part of the twenty-second revision of the online repair
patchset, we implement repairing of inode records, inode forks, and
inode block maps.  We also implement a meager symbolic link repair
ability.

If you're going to start using this mess, you probably ought to just
pull from my git trees, which are linked below.

This is an extraordinary way to destroy everything.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-inodes

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-inodes

[PATCH 1/4] xfs: repair inode records

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Try to reinitialize corrupt inodes, or clear the reflink flag
if it's not needed.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/Makefile             |    1 
 fs/xfs/libxfs/xfs_format.h  |    3 
 fs/xfs/scrub/inode_repair.c |  662 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h       |    2 
 fs/xfs/scrub/scrub.c        |    2 
 5 files changed, 668 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/scrub/inode_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7506dc7092e2..a66b75625940 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -163,6 +163,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   array.o \
 				   bitmap.o \
 				   ialloc_repair.o \
+				   inode_repair.o \
 				   refcount_repair.o \
 				   repair.o \
 				   xfile.o \
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1b7dcbae051c..7f1616199d79 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -979,7 +979,8 @@ enum xfs_dinode_fmt {
 #define XFS_DFORK_APTR(dip)	\
 	(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
 #define XFS_DFORK_PTR(dip,w)	\
-	((w) == XFS_DATA_FORK ? XFS_DFORK_DPTR(dip) : XFS_DFORK_APTR(dip))
+	((void *)((w) == XFS_DATA_FORK ? XFS_DFORK_DPTR(dip) : \
+					 XFS_DFORK_APTR(dip)))
 
 #define XFS_DFORK_FORMAT(dip,w) \
 	((w) == XFS_DATA_FORK ? \
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
new file mode 100644
index 000000000000..268803d23177
--- /dev/null
+++ b/fs/xfs/scrub/inode_repair.c
@@ -0,0 +1,662 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_inode_buf.h"
+#include "xfs_inode_fork.h"
+#include "xfs_ialloc.h"
+#include "xfs_da_format.h"
+#include "xfs_reflink.h"
+#include "xfs_rmap.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_quota_defs.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Inode Repair
+ *
+ * Roughly speaking, inode problems can be classified based on whether or not
+ * they trip the dinode verifiers.  If those trip, then we won't be able to
+ * _iget ourselves the inode.
+ *
+ * Therefore, the xrep_dinode_* functions fix anything that will cause the
+ * inode buffer verifier or the dinode verifier.  The xrep_inode_* functions
+ * fix things on live incore inodes.
+ */
+
+/* Make sure this buffer can pass the inode buffer verifier. */
+STATIC void
+xrep_dinode_buf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_trans	*tp = sc->tp;
+	struct xfs_dinode	*dip;
+	xfs_agnumber_t		agno;
+	xfs_agino_t		agino;
+	int			ioff;
+	int			i;
+	int			ni;
+	bool			crc_ok;
+	bool			magic_ok;
+	bool			unlinked_ok;
+
+	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+	agno = xfs_daddr_to_agno(mp, XFS_BUF_ADDR(bp));
+	for (i = 0; i < ni; i++) {
+		ioff = i << mp->m_sb.sb_inodelog;
+		dip = xfs_buf_offset(bp, ioff);
+		agino = be32_to_cpu(dip->di_next_unlinked);
+
+		unlinked_ok = magic_ok = crc_ok = false;
+
+		if (xfs_verify_agino_or_null(sc->mp, agno, agino))
+			unlinked_ok = true;
+
+		if (dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+		    xfs_dinode_good_version(mp, dip->di_version))
+			magic_ok = true;
+
+		if (xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+				XFS_DINODE_CRC_OFF))
+			crc_ok = true;
+
+		if (magic_ok && unlinked_ok && crc_ok)
+			continue;
+
+		if (!magic_ok) {
+			dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+			dip->di_version = 3;
+		}
+		if (!unlinked_ok)
+			dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
+		xfs_dinode_calc_crc(mp, dip);
+		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
+		xfs_trans_log_buf(tp, bp, ioff, ioff + sizeof(*dip) - 1);
+	}
+}
+
+/* Reinitialize things that never change in an inode. */
+STATIC void
+xrep_dinode_header(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
+{
+	dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+	if (!xfs_dinode_good_version(sc->mp, dip->di_version))
+		dip->di_version = 3;
+	dip->di_ino = cpu_to_be64(sc->sm->sm_ino);
+	uuid_copy(&dip->di_uuid, &sc->mp->m_sb.sb_meta_uuid);
+	dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
+}
+
+/*
+ * Turn di_mode into /something/ recognizable.
+ *
+ * XXX: Ideally we'd try to read data block 0 to see if it's a directory.
+ */
+STATIC void
+xrep_dinode_mode(
+	struct xfs_dinode	*dip)
+{
+	uint16_t		mode;
+
+	mode = be16_to_cpu(dip->di_mode);
+	if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
+		return;
+
+	/* bad mode, so we set it to a file that only root can read */
+	mode = S_IFREG;
+	dip->di_mode = cpu_to_be16(mode);
+	dip->di_uid = 0;
+	dip->di_gid = 0;
+}
+
+/* Fix any conflicting flags that the verifiers complain about. */
+STATIC void
+xrep_dinode_flags(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_mount	*mp = sc->mp;
+	uint64_t		flags2;
+	uint16_t		mode;
+	uint16_t		flags;
+
+	mode = be16_to_cpu(dip->di_mode);
+	flags = be16_to_cpu(dip->di_flags);
+	flags2 = be64_to_cpu(dip->di_flags2);
+
+	if (xfs_sb_version_hasreflink(&mp->m_sb) && S_ISREG(mode))
+		flags2 |= XFS_DIFLAG2_REFLINK;
+	else
+		flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE);
+	if (flags & XFS_DIFLAG_REALTIME)
+		flags2 &= ~XFS_DIFLAG2_REFLINK;
+	if (flags2 & XFS_DIFLAG2_REFLINK)
+		flags2 &= ~XFS_DIFLAG2_DAX;
+	dip->di_flags = cpu_to_be16(flags);
+	dip->di_flags2 = cpu_to_be64(flags2);
+}
+
+/*
+ * Blow out symlink; now it points to the current dir.  We don't have to worry
+ * about incore state because this inode is failing the verifiers.
+ */
+STATIC void
+xrep_dinode_zap_symlink(
+	struct xfs_dinode	*dip)
+{
+	char			*p;
+
+	dip->di_format = XFS_DINODE_FMT_LOCAL;
+	dip->di_size = cpu_to_be64(1);
+	p = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	*p = '.';
+}
+
+/*
+ * Blow out dir, make it point to the root.  In the future repair will
+ * reconstruct this directory for us.  Note that there's no in-core directory
+ * inode because the sf verifier tripped, so we don't have to worry about the
+ * dentry cache.
+ */
+STATIC void
+xrep_dinode_zap_dir(
+	struct xfs_mount		*mp,
+	struct xfs_dinode		*dip)
+{
+	struct xfs_dir2_sf_hdr		*sfp;
+	int				i8count;
+
+	dip->di_format = XFS_DINODE_FMT_LOCAL;
+	i8count = mp->m_sb.sb_rootino > XFS_DIR2_MAX_SHORT_INUM;
+	sfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	sfp->count = 0;
+	sfp->i8count = i8count;
+	xfs_dir2_sf_put_parent_ino(sfp, mp->m_sb.sb_rootino);
+	dip->di_size = cpu_to_be64(xfs_dir2_sf_hdr_size(i8count));
+}
+
+/* Make sure we don't have a garbage file size. */
+STATIC void
+xrep_dinode_size(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	*dip)
+{
+	uint64_t		size;
+	uint16_t		mode;
+
+	mode = be16_to_cpu(dip->di_mode);
+	size = be64_to_cpu(dip->di_size);
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		/* di_size can't be nonzero for special files */
+		dip->di_size = 0;
+		break;
+	case S_IFREG:
+		/* Regular files can't be larger than 2^63-1 bytes. */
+		dip->di_size = cpu_to_be64(size & ~(1ULL << 63));
+		break;
+	case S_IFLNK:
+		/*
+		 * Truncate ridiculously oversized symlinks.  If the size is
+		 * zero, reset it to point to the current directory.  Both of
+		 * these conditions trigger dinode verifier errors, so there
+		 * is no in-core state to reset.
+		 */
+		if (size > XFS_SYMLINK_MAXLEN)
+			dip->di_size = cpu_to_be64(XFS_SYMLINK_MAXLEN);
+		else if (size == 0)
+			xrep_dinode_zap_symlink(dip);
+		break;
+	case S_IFDIR:
+		/*
+		 * Directories can't have a size larger than 32G.  If the size
+		 * is zero, reset it to an empty directory.  Both of these
+		 * conditions trigger dinode verifier errors, so there is no
+		 * in-core state to reset.
+		 */
+		if (size > XFS_DIR2_SPACE_SIZE)
+			dip->di_size = cpu_to_be64(XFS_DIR2_SPACE_SIZE);
+		else if (size == 0)
+			xrep_dinode_zap_dir(mp, dip);
+		break;
+	}
+}
+
+/* Fix extent size hints. */
+STATIC void
+xrep_dinode_extsize_hints(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_mount	*mp = sc->mp;
+	uint64_t		flags2;
+	uint16_t		flags;
+	uint16_t		mode;
+	xfs_failaddr_t		fa;
+
+	mode = be16_to_cpu(dip->di_mode);
+	flags = be16_to_cpu(dip->di_flags);
+	flags2 = be64_to_cpu(dip->di_flags2);
+
+	fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
+			mode, flags);
+	if (fa) {
+		dip->di_extsize = 0;
+		dip->di_flags &= ~cpu_to_be16(XFS_DIFLAG_EXTSIZE |
+					      XFS_DIFLAG_EXTSZINHERIT);
+	}
+
+	if (dip->di_version < 3)
+		return;
+
+	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
+			mode, flags, flags2);
+	if (fa) {
+		dip->di_cowextsize = 0;
+		dip->di_flags2 &= ~cpu_to_be64(XFS_DIFLAG2_COWEXTSIZE);
+	}
+}
+
+/* Inode didn't pass verifiers, so fix the raw buffer and retry iget. */
+STATIC int
+xrep_dinode_core(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_imap		imap;
+	struct xfs_buf		*bp;
+	struct xfs_dinode	*dip;
+	xfs_ino_t		ino;
+	bool			inuse;
+	int			error;
+
+	/* Map & read inode. */
+	ino = sc->sm->sm_ino;
+	error = xfs_imap(sc->mp, sc->tp, ino, &imap, XFS_IGET_UNTRUSTED);
+	if (error)
+		return error;
+
+	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+			imap.im_blkno, imap.im_len, XBF_UNMAPPED, &bp, NULL);
+	if (error)
+		return error;
+
+	/* Make absolutely sure this inode isn't in core. */
+	error = xfs_icache_inode_is_allocated(sc->mp, sc->tp, ino, &inuse);
+	if (error == 0) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	/* Make sure we can pass the inode buffer verifier. */
+	xrep_dinode_buf(sc, bp);
+	bp->b_ops = &xfs_inode_buf_ops;
+
+	/* Fix everything the verifier will complain about. */
+	dip = xfs_buf_offset(bp, imap.im_boffset);
+	xrep_dinode_header(sc, dip);
+	xrep_dinode_mode(dip);
+	xrep_dinode_flags(sc, dip);
+	xrep_dinode_size(sc->mp, dip);
+	xrep_dinode_extsize_hints(sc, dip);
+
+	/* Write out the inode... */
+	xfs_dinode_calc_crc(sc->mp, dip);
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_DINO_BUF);
+	xfs_trans_log_buf(sc->tp, bp, imap.im_boffset,
+			imap.im_boffset + sc->mp->m_sb.sb_inodesize - 1);
+	error = xfs_trans_commit(sc->tp);
+	if (error)
+		return error;
+	sc->tp = NULL;
+
+	/* ...and reload it? */
+	error = xfs_iget(sc->mp, sc->tp, ino,
+			XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, &sc->ip);
+	if (error)
+		return error;
+	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+	xfs_ilock(sc->ip, sc->ilock_flags);
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+	sc->ilock_flags |= XFS_ILOCK_EXCL;
+	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
+
+	return 0;
+}
+
+/* Fix everything xfs_dinode_verify cares about. */
+STATIC int
+xrep_dinode_problems(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	error = xrep_dinode_core(sc);
+	if (error)
+		return error;
+
+	/* We had to fix a totally busted inode, schedule quotacheck. */
+	if (XFS_IS_UQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQ_USER);
+	if (XFS_IS_GQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQ_GROUP);
+	if (XFS_IS_PQUOTA_ON(sc->mp))
+		xrep_force_quotacheck(sc, XFS_DQ_PROJ);
+
+	return 0;
+}
+
+/*
+ * Fix problems that the verifiers don't care about.  In general these are
+ * errors that don't cause problems elsewhere in the kernel that we can easily
+ * detect, so we don't check them all that rigorously.
+ */
+
+/* Make sure block and extent counts are ok. */
+STATIC int
+xrep_inode_blockcounts(
+	struct xfs_scrub	*sc)
+{
+	xfs_filblks_t		count;
+	xfs_filblks_t		acount;
+	xfs_extnum_t		nextents;
+	int			error;
+
+	/* Set data fork counters from the data fork mappings. */
+	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
+			&nextents, &count);
+	if (error)
+		return error;
+	if (XFS_IS_REALTIME_INODE(sc->ip)) {
+		if (count >= sc->mp->m_sb.sb_rblocks)
+			return -EFSCORRUPTED;
+	} else if (!xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+		if (count >= sc->mp->m_sb.sb_dblocks)
+			return -EFSCORRUPTED;
+	}
+	sc->ip->i_d.di_nextents = nextents;
+
+	/* Set attr fork counters from the attr fork mappings. */
+	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
+			&nextents, &acount);
+	if (error)
+		return error;
+	if (count >= sc->mp->m_sb.sb_dblocks)
+		return -EFSCORRUPTED;
+	if (nextents >= (uint16_t)-1U)
+		return -EFSCORRUPTED;
+	sc->ip->i_d.di_anextents = nextents;
+
+	sc->ip->i_d.di_nblocks = count + acount;
+
+	/*
+	 * If we found attr fork extents but no attr fork root, zero the
+	 * attr fork extent count so that the attr fork repair will run.
+	 */
+	if (sc->ip->i_d.di_anextents != 0 && sc->ip->i_d.di_forkoff == 0)
+		sc->ip->i_d.di_anextents = 0;
+
+	return 0;
+}
+
+/* Check for invalid uid/gid.  Note that a -1U projid is allowed. */
+STATIC void
+xrep_inode_ids(
+	struct xfs_scrub	*sc)
+{
+	if (sc->ip->i_d.di_uid == -1U) {
+		sc->ip->i_d.di_uid = 0;
+		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
+		if (XFS_IS_UQUOTA_ON(sc->mp))
+			xrep_force_quotacheck(sc, XFS_DQ_USER);
+	}
+
+	if (sc->ip->i_d.di_gid == -1U) {
+		sc->ip->i_d.di_gid = 0;
+		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
+		if (XFS_IS_GQUOTA_ON(sc->mp))
+			xrep_force_quotacheck(sc, XFS_DQ_GROUP);
+	}
+}
+
+static inline void
+xrep_clamp_nsec(
+	struct timespec64	*ts)
+{
+	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
+}
+
+/* Nanosecond counters can't have more than 1 billion. */
+STATIC void
+xrep_inode_timestamps(
+	struct xfs_inode	*ip)
+{
+	xrep_clamp_nsec(&VFS_I(ip)->i_atime);
+	xrep_clamp_nsec(&VFS_I(ip)->i_mtime);
+	xrep_clamp_nsec(&VFS_I(ip)->i_ctime);
+
+	if (ip->i_d.di_version > 2)
+		xrep_clamp_nsec(&ip->i_d.di_crtime);
+}
+
+/* Fix inode flags that don't make sense together. */
+STATIC void
+xrep_inode_flags(
+	struct xfs_scrub	*sc)
+{
+	uint16_t		mode;
+
+	mode = VFS_I(sc->ip)->i_mode;
+
+	/* Clear junk flags */
+	if (sc->ip->i_d.di_flags & ~XFS_DIFLAG_ANY)
+		sc->ip->i_d.di_flags &= ~XFS_DIFLAG_ANY;
+
+	/* NEWRTBM only applies to realtime bitmaps */
+	if (sc->ip->i_ino == sc->mp->m_sb.sb_rbmino)
+		sc->ip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+	else
+		sc->ip->i_d.di_flags &= ~XFS_DIFLAG_NEWRTBM;
+
+	/* These only make sense for directories. */
+	if (!S_ISDIR(mode))
+		sc->ip->i_d.di_flags &= ~(XFS_DIFLAG_RTINHERIT |
+					  XFS_DIFLAG_EXTSZINHERIT |
+					  XFS_DIFLAG_PROJINHERIT |
+					  XFS_DIFLAG_NOSYMLINKS);
+
+	/* These only make sense for files. */
+	if (!S_ISREG(mode))
+		sc->ip->i_d.di_flags &= ~(XFS_DIFLAG_REALTIME |
+					  XFS_DIFLAG_EXTSIZE);
+
+	/* These only make sense for non-rt files. */
+	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME)
+		sc->ip->i_d.di_flags &= ~XFS_DIFLAG_FILESTREAM;
+
+	/* Immutable and append only?  Drop the append. */
+	if ((sc->ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE) &&
+	    (sc->ip->i_d.di_flags & XFS_DIFLAG_APPEND))
+		sc->ip->i_d.di_flags &= ~XFS_DIFLAG_APPEND;
+
+	if (sc->ip->i_d.di_version < 3)
+		return;
+
+	/* Clear junk flags. */
+	if (sc->ip->i_d.di_flags2 & ~XFS_DIFLAG2_ANY)
+		sc->ip->i_d.di_flags2 &= ~XFS_DIFLAG2_ANY;
+
+	/* No reflink flag unless we support it and it's a file. */
+	if (!xfs_sb_version_hasreflink(&sc->mp->m_sb) ||
+	    !S_ISREG(mode))
+		sc->ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+
+	/* DAX only applies to files and dirs. */
+	if (!(S_ISREG(mode) || S_ISDIR(mode)))
+		sc->ip->i_d.di_flags2 &= ~XFS_DIFLAG2_DAX;
+
+	/* No reflink files on the realtime device. */
+	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME)
+		sc->ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+
+	/* No mixing reflink and DAX yet. */
+	if (sc->ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)
+		sc->ip->i_d.di_flags2 &= ~XFS_DIFLAG2_DAX;
+}
+
+/*
+ * Fix size problems with block/node format directories.  If we fail to find
+ * the extent list, just bail out and let the bmapbtd repair functions clean
+ * up that mess.
+ */
+STATIC void
+xrep_inode_blockdir_size(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		off;
+	int			error;
+
+	/* Find the last block before 32G; this is the dir size. */
+	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
+		if (error)
+			return;
+	}
+
+	off = XFS_B_TO_FSB(sc->mp, XFS_DIR2_SPACE_SIZE);
+	if (!xfs_iext_lookup_extent_before(sc->ip, ifp, &off, &icur, &got)) {
+		/* zero-extents directory? */
+		return;
+	}
+
+	off = got.br_startoff + got.br_blockcount;
+	sc->ip->i_d.di_size = min_t(loff_t, XFS_DIR2_SPACE_SIZE,
+			XFS_FSB_TO_B(sc->mp, off));
+}
+
+/* Fix size problems with short format directories. */
+STATIC void
+xrep_inode_sfdir_size(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_ifork	*ifp;
+
+	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+	sc->ip->i_d.di_size = ifp->if_bytes;
+}
+
+/*
+ * Fix any irregularities in an inode's size now that we can iterate extent
+ * maps and access other regular inode data.
+ */
+STATIC void
+xrep_inode_size(
+	struct xfs_scrub	*sc)
+{
+	/*
+	 * Currently we only support fixing size on extents or btree format
+	 * directories.  Files can be any size and sizes for the other inode
+	 * special types are fixed by xrep_dinode_size.
+	 */
+	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
+		return;
+	switch (XFS_IFORK_FORMAT(sc->ip, XFS_DATA_FORK)) {
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
+		xrep_inode_blockdir_size(sc);
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+		xrep_inode_sfdir_size(sc);
+		break;
+	}
+}
+
+/* Fix any irregularities in an inode that the verifiers don't catch. */
+STATIC int
+xrep_inode_problems(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	error = xrep_inode_blockcounts(sc);
+	if (error)
+		return error;
+	xrep_inode_timestamps(sc->ip);
+	xrep_inode_flags(sc);
+	xrep_inode_ids(sc);
+	xrep_inode_size(sc);
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
+/* Repair an inode's fields. */
+int
+xrep_inode(
+	struct xfs_scrub	*sc)
+{
+	int			error = 0;
+
+	/*
+	 * No inode?  That means we failed the _iget verifiers.  Repair all
+	 * the things that the inode verifiers care about, then retry _iget.
+	 */
+	if (!sc->ip) {
+		error = xrep_dinode_problems(sc);
+		if (error)
+			goto out;
+	}
+
+	/* By this point we had better have a working incore inode. */
+	ASSERT(sc->ip);
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* If we found corruption of any kind, try to fix it. */
+	if ((sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) ||
+	    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT)) {
+		error = xrep_inode_problems(sc);
+		if (error)
+			goto out;
+	}
+
+	/* See if we can clear the reflink flag. */
+	if (xfs_is_reflink_inode(sc->ip))
+		return xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+
+out:
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index c0769aaae9a4..dfb4fe77fae8 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -71,6 +71,7 @@ int xrep_agi(struct xfs_scrub *sc);
 int xrep_allocbt(struct xfs_scrub *sc);
 int xrep_iallocbt(struct xfs_scrub *sc);
 int xrep_refcountbt(struct xfs_scrub *sc);
+int xrep_inode(struct xfs_scrub *sc);
 
 struct xrep_newbt_resv {
 	/* Link to list of extents that we've reserved. */
@@ -169,6 +170,7 @@ xrep_reset_perag_resv(
 #define xrep_allocbt			xrep_notsupported
 #define xrep_iallocbt			xrep_notsupported
 #define xrep_refcountbt			xrep_notsupported
+#define xrep_inode			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 7a036a8e4189..ee2b77b4350b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -261,7 +261,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode,
 		.scrub	= xchk_inode,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_inode,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,

[PATCH 2/4] xfs: zap broken inode forks

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Determine if inode fork damage is responsible for the inode being unable
to pass the ifork verifiers in xfs_iget and zap the fork contents if
this is true.  Once this is done the fork will be empty but we'll be
able to construct an in-core inode, and a subsequent call to the inode
fork repair ioctl will search the rmapbt to rebuild the records that
were in the fork.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c |   32 ++-
 fs/xfs/libxfs/xfs_attr_leaf.h |    2 
 fs/xfs/libxfs/xfs_bmap.c      |   21 ++
 fs/xfs/libxfs/xfs_bmap.h      |    2 
 fs/xfs/scrub/inode_repair.c   |  402 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 440 insertions(+), 19 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 08d4b10ae2d5..7d14589ba8d1 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -977,23 +977,16 @@ xfs_attr_shortform_allfit(
 	return xfs_attr_shortform_bytesfit(dp, bytes);
 }
 
-/* Verify the consistency of an inline attribute fork. */
+/* Verify the consistency of a raw inline attribute fork. */
 xfs_failaddr_t
-xfs_attr_shortform_verify(
-	struct xfs_inode		*ip)
+xfs_attr_shortform_verify_struct(
+	struct xfs_attr_shortform	*sfp,
+	size_t				size)
 {
-	struct xfs_attr_shortform	*sfp;
 	struct xfs_attr_sf_entry	*sfep;
 	struct xfs_attr_sf_entry	*next_sfep;
 	char				*endp;
-	struct xfs_ifork		*ifp;
 	int				i;
-	int64_t				size;
-
-	ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL);
-	ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
-	sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	size = ifp->if_bytes;
 
 	/*
 	 * Give up if the attribute is way too short.
@@ -1051,6 +1044,23 @@ xfs_attr_shortform_verify(
 	return NULL;
 }
 
+/* Verify the consistency of an inline attribute fork. */
+xfs_failaddr_t
+xfs_attr_shortform_verify(
+	struct xfs_inode		*ip)
+{
+	struct xfs_attr_shortform	*sfp;
+	struct xfs_ifork		*ifp;
+	int64_t				size;
+
+	ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL);
+	ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
+	sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
+	size = ifp->if_bytes;
+
+	return xfs_attr_shortform_verify_struct(sfp, size);
+}
+
 /*
  * Convert a leaf attribute list to shortform attribute list
  */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index f4a188e28b7b..d2476535c8c3 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -64,6 +64,8 @@ int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args,
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
+xfs_failaddr_t xfs_attr_shortform_verify_struct(struct xfs_attr_shortform *sfp,
+		size_t size);
 xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);
 void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4584bb7da5a2..84ddd4654975 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6287,18 +6287,16 @@ xfs_bmap_finish_one(
 	return error;
 }
 
-/* Check that an inode's extent does not have invalid flags or bad ranges. */
+/* Check that an extent does not have invalid flags or bad ranges. */
 xfs_failaddr_t
-xfs_bmap_validate_extent(
-	struct xfs_inode	*ip,
+xfs_bmap_validate_extent_raw(
+	struct xfs_mount	*mp,
+	bool			isrt,
 	int			whichfork,
 	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fsblock_t		endfsb;
-	bool			isrt;
 
-	isrt = XFS_IS_REALTIME_INODE(ip);
 	endfsb = irec->br_startblock + irec->br_blockcount - 1;
 	if (isrt) {
 		if (!xfs_verify_rtbno(mp, irec->br_startblock))
@@ -6318,3 +6316,14 @@ xfs_bmap_validate_extent(
 		return __this_address;
 	return NULL;
 }
+
+/* Check that an inode's extent does not have invalid flags or bad ranges. */
+xfs_failaddr_t
+xfs_bmap_validate_extent(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*irec)
+{
+	return xfs_bmap_validate_extent_raw(ip->i_mount,
+			XFS_IS_REALTIME_INODE(ip), whichfork, irec);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 14d25e0b7d9c..07c9726d40c2 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -278,6 +278,8 @@ static inline int xfs_bmap_fork_to_state(int whichfork)
 	}
 }
 
+xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool isrt,
+		int whichfork, struct xfs_bmbt_irec *irec);
 xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *irec);
 
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 268803d23177..1569b720ee91 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -22,12 +22,16 @@
 #include "xfs_ialloc.h"
 #include "xfs_da_format.h"
 #include "xfs_reflink.h"
+#include "xfs_alloc.h"
 #include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
 #include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_bmap_util.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_quota_defs.h"
+#include "xfs_attr_leaf.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -140,7 +144,8 @@ xrep_dinode_mode(
 STATIC void
 xrep_dinode_flags(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode	*dip)
+	struct xfs_dinode	*dip,
+	bool			is_rt_file)
 {
 	struct xfs_mount	*mp = sc->mp;
 	uint64_t		flags2;
@@ -151,6 +156,11 @@ xrep_dinode_flags(
 	flags = be16_to_cpu(dip->di_flags);
 	flags2 = be64_to_cpu(dip->di_flags2);
 
+	if (is_rt_file)
+		flags |= XFS_DIFLAG_REALTIME;
+	else
+		flags &= ~XFS_DIFLAG_REALTIME;
+
 	if (xfs_sb_version_hasreflink(&mp->m_sb) && S_ISREG(mode))
 		flags2 |= XFS_DIFLAG2_REFLINK;
 	else
@@ -287,11 +297,393 @@ xrep_dinode_extsize_hints(
 	}
 }
 
+/* Blocks and extents associated with an inode, according to rmap records. */
+struct xrep_dinode_stats {
+	struct xfs_scrub	*sc;
+
+	/* Blocks in use on the data device by data extents or bmbt blocks. */
+	xfs_rfsblock_t		data_blocks;
+
+	/* Blocks in use on the rt device. */
+	xfs_rfsblock_t		rt_blocks;
+
+	/* Blocks in use by the attr fork. */
+	xfs_rfsblock_t		attr_blocks;
+
+	/* Number of data device extents for the data fork. */
+	xfs_extnum_t		data_extents;
+
+	/*
+	 * Number of realtime device extents for the data fork.  If
+	 * data_extents and rt_extents indicate that the data fork has extents
+	 * on both devices, we'll just back away slowly.
+	 */
+	xfs_extnum_t		rt_extents;
+
+	/* Number of (data device) extents for the attr fork. */
+	xfs_aextnum_t		attr_extents;
+};
+
+/* Count extents and blocks for an inode given an rmap. */
+STATIC int
+xrep_dinode_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
+{
+	struct xrep_dinode_stats	*dis = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(dis->sc, &error))
+		return error;
+
+	/* Is this even the right fork? */
+	if (rec->rm_owner != dis->sc->sm->sm_ino)
+		return 0;
+	if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
+		dis->attr_blocks += rec->rm_blockcount;
+		if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+			dis->attr_extents++;
+	} else {
+		dis->data_blocks += rec->rm_blockcount;
+		if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+			dis->data_extents++;
+	}
+	return 0;
+}
+
+/* Count extents and blocks for an inode from all AG rmap data. */
+STATIC int
+xrep_dinode_count_ag_rmaps(
+	struct xrep_dinode_stats	*dis,
+	xfs_agnumber_t			agno)
+{
+	struct xfs_btree_cur		*cur;
+	struct xfs_buf			*agf;
+	int				error;
+
+	error = xfs_alloc_read_agf(dis->sc->mp, dis->sc->tp, agno, 0, &agf);
+	if (error)
+		return error;
+
+	cur = xfs_rmapbt_init_cursor(dis->sc->mp, dis->sc->tp, agf, agno);
+	if (!cur) {
+		error = -ENOMEM;
+		goto out_agf;
+	}
+
+	error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, dis);
+	xfs_btree_del_cursor(cur, error);
+out_agf:
+	xfs_trans_brelse(dis->sc->tp, agf);
+	return error;
+}
+
+/* Count extents and blocks for a given inode from all rmap data. */
+STATIC int
+xrep_dinode_count_rmaps(
+	struct xrep_dinode_stats	*dis)
+{
+	xfs_agnumber_t			agno;
+	int				error;
+
+	if (!xfs_sb_version_hasrmapbt(&dis->sc->mp->m_sb) ||
+	    xfs_sb_version_hasrealtime(&dis->sc->mp->m_sb))
+		return -EOPNOTSUPP;
+
+	/* XXX: find rt blocks too */
+	if (dis->rt_extents != 0) {
+		ASSERT(0);
+		return -EOPNOTSUPP;
+	}
+
+	for (agno = 0; agno < dis->sc->mp->m_sb.sb_agcount; agno++) {
+		error = xrep_dinode_count_ag_rmaps(dis, agno);
+		if (error)
+			return error;
+	}
+
+	/* Can't have extents on both the rt and the data device. */
+	if (dis->data_extents && dis->rt_extents)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Return true if this extents-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_extents_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	int			dfork_size,
+	int			whichfork)
+{
+	struct xfs_bmbt_irec	new;
+	struct xfs_bmbt_rec	*dp;
+	bool			isrt;
+	int			i;
+	int			nex;
+	int			fork_size;
+
+	nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+	fork_size = nex * sizeof(struct xfs_bmbt_rec);
+	if (fork_size < 0 || fork_size > dfork_size)
+		return true;
+	if (whichfork == XFS_ATTR_FORK && nex > ((uint16_t)-1U))
+		return true;
+	dp = XFS_DFORK_PTR(dip, whichfork);
+
+	isrt = dip->di_flags & cpu_to_be16(XFS_DIFLAG_REALTIME);
+	for (i = 0; i < nex; i++, dp++) {
+		xfs_failaddr_t	fa;
+
+		xfs_bmbt_disk_get_all(dp, &new);
+		fa = xfs_bmap_validate_extent_raw(sc->mp, isrt, whichfork,
+				&new);
+		if (fa)
+			return true;
+	}
+
+	return false;
+}
+
+/* Return true if this btree-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_btree_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	int			dfork_size,
+	int			whichfork)
+{
+	struct xfs_bmdr_block	*dfp;
+	int			nrecs;
+	int			level;
+
+	if (XFS_DFORK_NEXTENTS(dip, whichfork) <=
+			dfork_size / sizeof(struct xfs_bmbt_rec))
+		return true;
+
+	dfp = XFS_DFORK_PTR(dip, whichfork);
+	nrecs = be16_to_cpu(dfp->bb_numrecs);
+	level = be16_to_cpu(dfp->bb_level);
+
+	if (nrecs == 0 || XFS_BMDR_SPACE_CALC(nrecs) > dfork_size)
+		return true;
+	if (level == 0 || level > XFS_BTREE_MAXLEVELS)
+		return true;
+	return false;
+}
+
+/*
+ * Check the data fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_dfork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	uint16_t		mode)
+{
+	uint64_t		size;
+	unsigned int		fmt;
+	int			dfork_size;
+
+	fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
+	size = be64_to_cpu(dip->di_size);
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		if (fmt != XFS_DINODE_FMT_DEV)
+			return true;
+		break;
+	case S_IFREG:
+		if (fmt == XFS_DINODE_FMT_LOCAL)
+			return true;
+		/* fall through */
+	case S_IFLNK:
+	case S_IFDIR:
+		switch (fmt) {
+		case XFS_DINODE_FMT_LOCAL:
+		case XFS_DINODE_FMT_EXTENTS:
+		case XFS_DINODE_FMT_BTREE:
+			break;
+		default:
+			return true;
+		}
+		break;
+	default:
+		return true;
+	}
+	dfork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_DATA_FORK);
+	switch (fmt) {
+	case XFS_DINODE_FMT_DEV:
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+		if (size > dfork_size)
+			return true;
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (xrep_dinode_bad_extents_fork(sc, dip, dfork_size,
+				XFS_DATA_FORK))
+			return true;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (xrep_dinode_bad_btree_fork(sc, dip, dfork_size,
+				XFS_DATA_FORK))
+			return true;
+		break;
+	default:
+		return true;
+	}
+
+	return false;
+}
+
+/* Reset the data fork to something sane. */
+STATIC void
+xrep_dinode_zap_dfork(
+	struct xfs_scrub		*sc,
+	struct xfs_dinode		*dip,
+	uint16_t			mode,
+	struct xrep_dinode_stats	*dis)
+{
+	/* Special files always get reset to DEV */
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFSOCK:
+		dip->di_format = XFS_DINODE_FMT_DEV;
+		dip->di_size = 0;
+		return;
+	}
+
+	/*
+	 * If we have data extents, reset to an empty map and hope the user
+	 * will run the bmapbtd checker next.
+	 */
+	if (dis->data_extents || dis->rt_extents || S_ISREG(mode)) {
+		dip->di_format = XFS_DINODE_FMT_EXTENTS;
+		dip->di_nextents = 0;
+		return;
+	}
+
+	/* Otherwise, reset the local format to the minimum. */
+	switch (mode & S_IFMT) {
+	case S_IFLNK:
+		xrep_dinode_zap_symlink(dip);
+		break;
+	case S_IFDIR:
+		xrep_dinode_zap_dir(sc->mp, dip);
+		break;
+	}
+}
+
+/*
+ * Check the attr fork for things that will fail the ifork verifiers or the
+ * ifork formatters.
+ */
+STATIC bool
+xrep_dinode_check_afork(
+	struct xfs_scrub		*sc,
+	struct xfs_dinode		*dip)
+{
+	struct xfs_attr_shortform	*sfp;
+	int				size;
+
+	if (XFS_DFORK_BOFF(dip) == 0)
+		return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
+		       dip->di_anextents != 0;
+
+	size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
+	switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
+	case XFS_DINODE_FMT_LOCAL:
+		sfp = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
+		return xfs_attr_shortform_verify_struct(sfp, size) != NULL;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (xrep_dinode_bad_extents_fork(sc, dip, size, XFS_ATTR_FORK))
+			return true;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (xrep_dinode_bad_btree_fork(sc, dip, size, XFS_ATTR_FORK))
+			return true;
+		break;
+	default:
+		return true;
+	}
+
+	return false;
+}
+
+/* Reset the attr fork to something sane. */
+STATIC void
+xrep_dinode_zap_afork(
+	struct xfs_scrub		*sc,
+	struct xfs_dinode		*dip,
+	struct xrep_dinode_stats	*dis)
+{
+	dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
+	dip->di_anextents = 0;
+	/*
+	 * We leave a nonzero forkoff so that the bmap scrub will look for
+	 * attr rmaps.
+	 */
+	dip->di_forkoff = dis->attr_extents ? 1 : 0;
+}
+
+/*
+ * Zap the data/attr forks if we spot anything that isn't going to pass the
+ * ifork verifiers or the ifork formatters, because we need to get the inode
+ * into good enough shape that the higher level repair functions can run.
+ */
+STATIC void
+xrep_dinode_zap_forks(
+	struct xfs_scrub		*sc,
+	struct xfs_dinode		*dip,
+	struct xrep_dinode_stats	*dis)
+{
+	uint16_t			mode;
+	bool				zap_datafork = false;
+	bool				zap_attrfork = false;
+
+	mode = be16_to_cpu(dip->di_mode);
+
+	/* Inode counters don't make sense? */
+	if (be32_to_cpu(dip->di_nextents) > be64_to_cpu(dip->di_nblocks))
+		zap_datafork = true;
+	if (be16_to_cpu(dip->di_anextents) > be64_to_cpu(dip->di_nblocks))
+		zap_attrfork = true;
+	if (be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
+			be64_to_cpu(dip->di_nblocks))
+		zap_datafork = zap_attrfork = true;
+
+	if (!zap_datafork)
+		zap_datafork = xrep_dinode_check_dfork(sc, dip, mode);
+	if (!zap_attrfork)
+		zap_attrfork = xrep_dinode_check_afork(sc, dip);
+
+	/* Zap whatever's bad. */
+	if (zap_attrfork)
+		xrep_dinode_zap_afork(sc, dip, dis);
+	if (zap_datafork)
+		xrep_dinode_zap_dfork(sc, dip, mode, dis);
+	dip->di_nblocks = 0;
+	if (!zap_attrfork)
+		be64_add_cpu(&dip->di_nblocks, dis->attr_blocks);
+	if (!zap_datafork) {
+		be64_add_cpu(&dip->di_nblocks, dis->data_blocks);
+		be64_add_cpu(&dip->di_nblocks, dis->rt_blocks);
+	}
+}
+
 /* Inode didn't pass verifiers, so fix the raw buffer and retry iget. */
 STATIC int
 xrep_dinode_core(
 	struct xfs_scrub	*sc)
 {
+	struct xrep_dinode_stats	dis = { .sc = sc };
 	struct xfs_imap		imap;
 	struct xfs_buf		*bp;
 	struct xfs_dinode	*dip;
@@ -299,6 +691,11 @@ xrep_dinode_core(
 	bool			inuse;
 	int			error;
 
+	/* Figure out what this inode had mapped in both forks. */
+	error = xrep_dinode_count_rmaps(&dis);
+	if (error)
+		return error;
+
 	/* Map & read inode. */
 	ino = sc->sm->sm_ino;
 	error = xfs_imap(sc->mp, sc->tp, ino, &imap, XFS_IGET_UNTRUSTED);
@@ -325,9 +722,10 @@ xrep_dinode_core(
 	dip = xfs_buf_offset(bp, imap.im_boffset);
 	xrep_dinode_header(sc, dip);
 	xrep_dinode_mode(dip);
-	xrep_dinode_flags(sc, dip);
+	xrep_dinode_flags(sc, dip, dis.rt_extents > 0);
 	xrep_dinode_size(sc->mp, dip);
 	xrep_dinode_extsize_hints(sc, dip);
+	xrep_dinode_zap_forks(sc, dip, &dis);
 
 	/* Write out the inode... */
 	xfs_dinode_calc_crc(sc->mp, dip);

[PATCH 3/4] xfs: repair inode block maps

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Use the reverse-mapping btree information to rebuild an inode block map.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/Makefile                |    1 
 fs/xfs/libxfs/xfs_bmap_btree.c |  113 +++++++-
 fs/xfs/libxfs/xfs_bmap_btree.h |    8 +
 fs/xfs/libxfs/xfs_iext_tree.c  |   23 +-
 fs/xfs/libxfs/xfs_inode_fork.c |   23 +-
 fs/xfs/libxfs/xfs_inode_fork.h |    4 
 fs/xfs/scrub/bmap.c            |   22 ++
 fs/xfs/scrub/bmap_repair.c     |  560 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h          |    4 
 fs/xfs/scrub/scrub.c           |    4 
 fs/xfs/scrub/trace.h           |   34 ++
 fs/xfs/xfs_trans.c             |   54 ++++
 fs/xfs/xfs_trans.h             |    2 
 13 files changed, 816 insertions(+), 36 deletions(-)
 create mode 100644 fs/xfs/scrub/bmap_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index a66b75625940..933ba41396b0 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -162,6 +162,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   alloc_repair.o \
 				   array.o \
 				   bitmap.o \
+				   bmap_repair.o \
 				   ialloc_repair.o \
 				   inode_repair.o \
 				   refcount_repair.o \
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index ffe608d2a2d9..e9c1e2862df5 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -58,7 +58,7 @@ xfs_bmdr_to_bmbt(
 
 void
 xfs_bmbt_disk_get_all(
-	struct xfs_bmbt_rec	*rec,
+	const struct xfs_bmbt_rec *rec,
 	struct xfs_bmbt_irec	*irec)
 {
 	uint64_t		l0 = get_unaligned_be64(&rec->l0);
@@ -300,10 +300,7 @@ xfs_bmbt_get_minrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
-				    cur->bc_private.b.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0) / 2;
@@ -318,10 +315,7 @@ xfs_bmbt_get_maxrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
-				    cur->bc_private.b.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0);
@@ -541,40 +535,123 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 /*
  * Allocate a new bmap btree cursor.
  */
-struct xfs_btree_cur *				/* new bmap btree cursor */
-xfs_bmbt_init_cursor(
+static struct xfs_btree_cur *			/* new bmap btree cursor */
+xfs_bmbt_init_common(
 	struct xfs_mount	*mp,		/* file system mount point */
 	struct xfs_trans	*tp,		/* transaction pointer */
-	struct xfs_inode	*ip,		/* inode owning the btree */
-	int			whichfork)	/* data or attr fork */
+	struct xfs_inode	*ip)		/* inode owning the btree */
 {
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	struct xfs_btree_cur	*cur;
-	ASSERT(whichfork != XFS_COW_FORK);
 
 	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
-	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 	cur->bc_btnum = XFS_BTNUM_BMAP;
 	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
-	cur->bc_ops = &xfs_bmbt_ops;
 	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
 	if (xfs_sb_version_hascrc(&mp->m_sb))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
-	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.ip = ip;
 	cur->bc_private.b.allocated = 0;
 	cur->bc_private.b.flags = 0;
+	cur->bc_ops = &xfs_bmbt_ops;
+
+	return cur;
+}
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *				/* new bmap btree cursor */
+xfs_bmbt_init_cursor(
+	struct xfs_mount	*mp,		/* file system mount point */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* inode owning the btree */
+	int			whichfork)	/* data or attr fork */
+{
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_btree_cur	*cur;
+	ASSERT(whichfork != XFS_COW_FORK);
+
+	cur = xfs_bmbt_init_common(mp, tp, ip);
+
+	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.whichfork = whichfork;
 
 	return cur;
 }
 
+/*
+ * Allocate a new bmap btree cursor for reloading an inode block mapping data
+ * structure.  Note that callers can use the staged cursor to reload extents
+ * format inode forks if they rebuild the iext tree and commit the staged
+ * cursor immediately.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_stage_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xbtree_ifakeroot	*ifake)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_btree_ops	*ops;
+
+	cur = xfs_bmbt_init_common(mp, tp, ip);
+	cur->bc_nlevels = ifake->if_levels;
+	cur->bc_private.b.forksize = ifake->if_fork_size;
+	cur->bc_private.b.whichfork = -1;
+	xfs_btree_stage_ifakeroot(cur, ifake, &ops);
+	ops->update_cursor = NULL;
+	return cur;
+}
+
+/*
+ * Swap in the new inode fork root.  Once we pass this point the newly rebuilt
+ * mappings are in place and we have to kill off any old btree blocks.
+ */
+void
+xfs_bmbt_commit_staged_btree(
+	struct xfs_btree_cur	*cur,
+	int			whichfork)
+{
+	struct xbtree_ifakeroot	*ifake = cur->bc_private.b.ifake;
+	struct xfs_ifork	*ifp;
+	static const short	brootflag[2] =
+		{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
+	static const short	extflag[2] =
+		{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
+	int			flags = XFS_ILOG_CORE;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+	ASSERT(whichfork != XFS_COW_FORK);
+
+	ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, whichfork);
+	xfs_ifork_reset(ifp);
+	memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork));
+
+	XFS_IFORK_FMT_SET(cur->bc_private.b.ip, whichfork, ifake->if_format);
+	XFS_IFORK_NEXT_SET(cur->bc_private.b.ip, whichfork, ifake->if_extents);
+	switch (ifake->if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		flags |= extflag[whichfork];
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		flags |= brootflag[whichfork];
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+	xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip, flags);
+	xfs_btree_commit_ifakeroot(cur, whichfork, &xfs_bmbt_ops);
+}
+
 /*
  * Calculate number of records in a bmap btree block.
  */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 29b407d053b4..0b20736808a3 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -11,6 +11,7 @@ struct xfs_btree_block;
 struct xfs_mount;
 struct xfs_inode;
 struct xfs_trans;
+struct xbtree_ifakeroot;
 
 /*
  * Btree block header size depends on a superblock flag.
@@ -90,7 +91,8 @@ extern void xfs_bmdr_to_bmbt(struct xfs_inode *, xfs_bmdr_block_t *, int,
 void xfs_bmbt_disk_set_all(struct xfs_bmbt_rec *r, struct xfs_bmbt_irec *s);
 extern xfs_filblks_t xfs_bmbt_disk_get_blockcount(xfs_bmbt_rec_t *r);
 extern xfs_fileoff_t xfs_bmbt_disk_get_startoff(xfs_bmbt_rec_t *r);
-extern void xfs_bmbt_disk_get_all(xfs_bmbt_rec_t *r, xfs_bmbt_irec_t *s);
+extern void xfs_bmbt_disk_get_all(const struct xfs_bmbt_rec *r,
+		struct xfs_bmbt_irec *s);
 
 extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int,
 			xfs_bmdr_block_t *, int);
@@ -105,6 +107,10 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
+struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
+		struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xbtree_ifakeroot *ifake);
+void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur, int whichfork);
 
 extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index 52451809c478..ad56a69c735a 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -622,13 +622,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
 }
 
 void
-xfs_iext_insert(
-	struct xfs_inode	*ip,
+xfs_iext_insert_raw(
+	struct xfs_ifork	*ifp,
 	struct xfs_iext_cursor	*cur,
-	struct xfs_bmbt_irec	*irec,
-	int			state)
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 	xfs_fileoff_t		offset = irec->br_startoff;
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
@@ -662,12 +660,23 @@ xfs_iext_insert(
 	xfs_iext_set(cur_rec(cur), irec);
 	ifp->if_bytes += sizeof(struct xfs_iext_rec);
 
-	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
 	if (new)
 		xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
 }
 
+void
+xfs_iext_insert(
+	struct xfs_inode	*ip,
+	struct xfs_iext_cursor	*cur,
+	struct xfs_bmbt_irec	*irec,
+	int			state)
+{
+	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
+
+	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+	xfs_iext_insert_raw(ifp, cur, irec);
+}
+
 static struct xfs_iext_node *
 xfs_iext_rebalance_node(
 	struct xfs_iext_node	*parent,
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index ad2b9c313fd2..e8ed4d8551ec 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -502,14 +502,11 @@ xfs_idata_realloc(
 	ifp->if_bytes = new_size;
 }
 
+/* Free all memory and reset a fork back to its initial state. */
 void
-xfs_idestroy_fork(
-	xfs_inode_t	*ip,
-	int		whichfork)
+xfs_ifork_reset(
+	struct xfs_ifork	*ifp)
 {
-	struct xfs_ifork	*ifp;
-
-	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (ifp->if_broot != NULL) {
 		kmem_free(ifp->if_broot);
 		ifp->if_broot = NULL;
@@ -521,7 +518,7 @@ xfs_idestroy_fork(
 	 * not local then we may or may not have an extents list,
 	 * so check and free it up if we do.
 	 */
-	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
+	if (ifp->if_flags & XFS_IFINLINE) {
 		if (ifp->if_u1.if_data != NULL) {
 			kmem_free(ifp->if_u1.if_data);
 			ifp->if_u1.if_data = NULL;
@@ -529,6 +526,18 @@ xfs_idestroy_fork(
 	} else if ((ifp->if_flags & XFS_IFEXTENTS) && ifp->if_height) {
 		xfs_iext_destroy(ifp);
 	}
+	ifp->if_flags = 0;
+}
+
+void
+xfs_idestroy_fork(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp;
+
+	ifp = XFS_IFORK_PTR(ip, whichfork);
+	xfs_ifork_reset(ifp);
 
 	if (whichfork == XFS_ATTR_FORK) {
 		kmem_cache_free(xfs_ifork_zone, ip->i_afp);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 500333d0101e..370ac0b099f0 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -96,6 +96,7 @@ struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
 int		xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
 void		xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
 				struct xfs_inode_log_item *, int);
+void		xfs_ifork_reset(struct xfs_ifork *ifp);
 void		xfs_idestroy_fork(struct xfs_inode *, int);
 void		xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
 				int whichfork);
@@ -107,6 +108,9 @@ void		xfs_init_local_fork(struct xfs_inode *ip, int whichfork,
 				const void *data, int64_t size);
 
 xfs_extnum_t	xfs_iext_count(struct xfs_ifork *ifp);
+void		xfs_iext_insert_raw(struct xfs_ifork *ifp,
+			struct xfs_iext_cursor *cur,
+			struct xfs_bmbt_irec *irec);
 void		xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
 			struct xfs_bmbt_irec *, int);
 void		xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index fa6ea6407992..d8214f156f03 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -29,6 +29,7 @@ xchk_setup_inode_bmap(
 	struct xfs_scrub	*sc,
 	struct xfs_inode	*ip)
 {
+	bool			is_repair = false;
 	int			error;
 
 	error = xchk_get_inode(sc, ip);
@@ -38,6 +39,10 @@ xchk_setup_inode_bmap(
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
 
+#ifdef CONFIG_XFS_REPAIR
+	is_repair = (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR);
+#endif
+
 	/*
 	 * We don't want any ephemeral data fork updates sitting around
 	 * while we inspect block mappings, so wait for directio to finish
@@ -45,10 +50,27 @@ xchk_setup_inode_bmap(
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
 	    sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) {
+		/* Break all our leases, we're going to mess with things. */
+		if (is_repair) {
+			error = xfs_break_layouts(VFS_I(sc->ip),
+					&sc->ilock_flags, BREAK_UNMAP);
+			if (error)
+				goto out;
+		}
+
 		inode_dio_wait(VFS_I(sc->ip));
 		error = filemap_write_and_wait(VFS_I(sc->ip)->i_mapping);
 		if (error)
 			goto out;
+
+		/* Drop the page cache if we're repairing block mappings. */
+		if (is_repair) {
+			error = invalidate_inode_pages2(
+					VFS_I(sc->ip)->i_mapping);
+			if (error)
+				goto out;
+		}
+
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c
new file mode 100644
index 000000000000..187858f0c119
--- /dev/null
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -0,0 +1,560 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_alloc.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_quota.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/array.h"
+
+/*
+ * Inode Fork Block Mapping (BMBT) Repair
+ * ======================================
+ *
+ * Gather all the rmap records for the inode and fork we're fixing, reset the
+ * incore fork, then recreate the btree.
+ */
+struct xrep_bmap {
+	/* Old bmbt blocks */
+	struct xbitmap		old_bmbt_blocks;
+
+	/* New fork. */
+	struct xrep_newbt	new_fork_info;
+	struct xfs_btree_bload	bmap_bload;
+
+	/* List of new bmap records. */
+	struct xfbma		*bmap_records;
+
+	struct xfs_scrub	*sc;
+
+	/* How many blocks did we find allocated to this file? */
+	xfs_rfsblock_t		nblocks;
+
+	/* How many bmbt blocks did we find for this fork? */
+	xfs_rfsblock_t		old_bmbt_block_count;
+
+	/* get_data()'s position in the free space record array. */
+	uint64_t		iter;
+
+	/* Which fork are we fixing? */
+	int			whichfork;
+};
+
+/* Record extents that belong to this inode's fork. */
+STATIC int
+xrep_bmap_walk_rmap(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rec,
+	void			*priv)
+{
+	struct xrep_bmap	*rb = priv;
+	struct xfs_bmbt_rec	rbe;
+	struct xfs_bmbt_irec	irec;
+	struct xfs_mount	*mp = cur->bc_mp;
+	xfs_fsblock_t		fsbno;
+	int			error = 0;
+
+	if (xchk_should_terminate(rb->sc, &error))
+		return error;
+
+	/* Skip extents which are not owned by this inode and fork. */
+	if (rec->rm_owner != rb->sc->ip->i_ino)
+		return 0;
+
+	rb->nblocks += rec->rm_blockcount;
+
+	/* If this rmap isn't for the fork we want, we're done. */
+	if (rb->whichfork == XFS_DATA_FORK &&
+	    (rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+	if (rb->whichfork == XFS_ATTR_FORK &&
+	    !(rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+
+	/* Remember any old bmbt blocks we find so we can delete them later. */
+	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
+		fsbno = XFS_AGB_TO_FSB(mp, cur->bc_private.a.agno,
+				rec->rm_startblock);
+		rb->old_bmbt_block_count += rec->rm_blockcount;
+		return xbitmap_set(&rb->old_bmbt_blocks, fsbno,
+				rec->rm_blockcount);
+	}
+
+	/* Remember this rmap as a series of bmap records. */
+	irec.br_startoff = rec->rm_offset;
+	irec.br_startblock = XFS_AGB_TO_FSB(mp, cur->bc_private.a.agno,
+					rec->rm_startblock);
+	if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
+		irec.br_state = XFS_EXT_UNWRITTEN;
+	else
+		irec.br_state = XFS_EXT_NORM;
+
+	do {
+		xfs_extlen_t len = min_t(xfs_filblks_t, rec->rm_blockcount,
+					 MAXEXTLEN);
+
+		irec.br_blockcount = len;
+		xfs_bmbt_disk_set_all(&rbe, &irec);
+
+		trace_xrep_bmap_found(rb->sc->ip, rb->whichfork, &irec);
+
+		if (xchk_should_terminate(rb->sc, &error))
+			break;
+
+		error = xfbma_append(rb->bmap_records, &rbe);
+		if (error)
+			break;
+
+		irec.br_startblock += len;
+		irec.br_startoff += len;
+		rec->rm_blockcount -= len;
+	} while (rec->rm_blockcount > 0);
+
+	return error;
+}
+
+/* Compare two bmap extents. */
+static int
+xrep_bmap_extent_cmp(
+	const void			*a,
+	const void			*b)
+{
+	xfs_fileoff_t			ao;
+	xfs_fileoff_t			bo;
+
+	ao = xfs_bmbt_disk_get_startoff((struct xfs_bmbt_rec *)a);
+	bo = xfs_bmbt_disk_get_startoff((struct xfs_bmbt_rec *)b);
+
+	if (ao > bo)
+		return 1;
+	else if (ao < bo)
+		return -1;
+	return 0;
+}
+
+/* Scan one AG for reverse mappings that we can turn into extent maps. */
+STATIC int
+xrep_bmap_scan_ag(
+	struct xrep_bmap	*rb,
+	xfs_agnumber_t		agno)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agf_bp = NULL;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, agno);
+	error = xfs_rmap_query_all(cur, xrep_bmap_walk_rmap, rb);
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(sc->tp, agf_bp);
+	return error;
+}
+
+/*
+ * Collect block mappings for this fork of this inode and decide if we have
+ * enough space to rebuild.  Caller is responsible for cleaning up the list if
+ * anything goes wrong.
+ */
+STATIC int
+xrep_bmap_find_mappings(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	xfs_agnumber_t		agno;
+	int			error = 0;
+
+	/* Iterate the rmaps for extents. */
+	for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) {
+		error = xrep_bmap_scan_ag(rb, agno);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Retrieve bmap data for bulk load. */
+STATIC int
+xrep_bmap_get_data(
+	struct xfs_btree_cur	*cur,
+	void			*priv)
+{
+	struct xfs_bmbt_rec	rec;
+	struct xfs_bmbt_irec	*irec = &cur->bc_rec.b;
+	struct xrep_bmap	*rb = priv;
+	int			error;
+
+	error = xfbma_get_data(rb->bmap_records, &rb->iter, &rec);
+	if (error)
+		return error;
+
+	xfs_bmbt_disk_get_all(&rec, irec);
+	return 0;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_bmap_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_bmap        *rb = priv;
+
+	return xrep_newbt_claim_block(cur, &rb->new_fork_info, ptr);
+}
+
+/* Figure out how much space we need to create the incore btree root block. */
+STATIC size_t
+xrep_bmap_iroot_size(
+	struct xfs_btree_cur	*cur,
+	unsigned int		nr_this_level,
+	void			*priv)
+{
+	return XFS_BMAP_BROOT_SPACE_CALC(cur->bc_mp, nr_this_level);
+}
+
+/* Update the inode counters. */
+STATIC int
+xrep_bmap_reset_counters(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	int64_t			delta;
+	int			error;
+
+	/*
+	 * Update the inode block counts to reflect the extents we found in the
+	 * rmapbt.
+	 */
+	delta = ifake->if_blocks - rb->old_bmbt_block_count;
+	sc->ip->i_d.di_nblocks = rb->nblocks + delta;
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+
+	/*
+	 * Adjust the quota counts by the difference in size between the old
+	 * and new bmbt.
+	 */
+	if (delta == 0 || !XFS_IS_QUOTA_ON(sc->mp))
+		return 0;
+
+	error = xrep_ino_dqattach(sc);
+	if (error)
+		return error;
+
+	xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, delta);
+	return 0;
+}
+
+/* Create a new iext tree and load it with block mappings. */
+STATIC int
+xrep_bmap_extents_load(
+	struct xrep_bmap	*rb,
+	struct xfs_btree_cur	*bmap_cur)
+{
+	struct xfs_iext_cursor	icur;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	struct xfs_ifork	*ifp = ifake->if_fork;
+	unsigned int		i;
+	int			error;
+
+	ASSERT(ifp->if_bytes == 0);
+
+	/* Add all the records to the incore extent tree. */
+	rb->iter = 0;
+	xfs_iext_first(ifp, &icur);
+	for (i = 0; i < ifake->if_extents; i++) {
+		error = xrep_bmap_get_data(bmap_cur, rb);
+		if (error)
+			return error;
+		xfs_iext_insert_raw(ifp, &icur, &bmap_cur->bc_rec.b);
+		xfs_iext_next(ifp, &icur);
+	}
+	ifp->if_flags = XFS_IFEXTENTS;
+
+	return 0;
+}
+
+/* Reserve new btree blocks and bulk load all the bmap records. */
+STATIC int
+xrep_bmap_btree_load(
+	struct xrep_bmap	*rb,
+	struct xfs_btree_cur	**bmap_curp)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	int			error;
+
+	rb->bmap_bload.get_data = xrep_bmap_get_data;
+	rb->bmap_bload.alloc_block = xrep_bmap_alloc_block;
+	rb->bmap_bload.iroot_size = xrep_bmap_iroot_size;
+	xrep_bload_estimate_slack(sc, &rb->bmap_bload);
+
+	/* Compute how many blocks we'll need. */
+	error = xfs_btree_bload_compute_geometry(*bmap_curp, &rb->bmap_bload,
+			ifake->if_extents);
+	if (error)
+		return error;
+	xfs_btree_del_cursor(*bmap_curp, error);
+	*bmap_curp = NULL;
+
+	/*
+	 * Guess how many blocks we're going to need to rebuild an entire bmap
+	 * from the number of extents we found, and pump up our transaction to
+	 * have sufficient block reservation.
+	 */
+	error = xfs_trans_reserve_more(sc->tp, rb->bmap_bload.nr_blocks, 0);
+	if (error)
+		return error;
+
+	/*
+	 * Reserve the space we'll need for the new btree.  Drop the cursor
+	 * while we do this because that can roll the transaction and cursors
+	 * can't handle that.
+	 */
+	error = xrep_newbt_alloc_blocks(&rb->new_fork_info,
+			rb->bmap_bload.nr_blocks);
+	if (error)
+		return error;
+
+	/* Add all observed bmap records. */
+	rb->iter = 0;
+	*bmap_curp = xfs_bmbt_stage_cursor(sc->mp, sc->tp, sc->ip, ifake);
+	return xfs_btree_bload(*bmap_curp, &rb->bmap_bload, rb);
+}
+
+/*
+ * Use the collected bmap information to stage a new bmap fork.  If this is
+ * successful we'll return with the new fork information logged to the repair
+ * transaction but not yet committed.
+ */
+STATIC int
+xrep_bmap_build_new_fork(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_btree_cur	*bmap_cur;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	int			error;
+
+	/*
+	 * Sort the bmap extents by startblock to avoid btree splits when we
+	 * rebuild the bmbt btree.
+	 */
+	error = xfbma_sort(rb->bmap_records, xrep_bmap_extent_cmp);
+	if (error)
+		return error;
+
+	/*
+	 * Prepare to construct the new fork by initializing the new btree
+	 * structure and creating a fake ifork in the ifakeroot structure.
+	 */
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+	xrep_newbt_init_inode(&rb->new_fork_info, sc, rb->whichfork, &oinfo);
+	bmap_cur = xfs_bmbt_stage_cursor(sc->mp, sc->tp, sc->ip, ifake);
+
+	/*
+	 * Figure out the size and format of the new fork, then fill it with
+	 * all the bmap records we've found.  Join the inode to the transaction
+	 * so that we can roll the transaction while holding the inode locked.
+	 */
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+	ifake->if_extents = xfbma_length(rb->bmap_records);
+	if (XFS_BMDR_SPACE_CALC(ifake->if_extents) <=
+	    XFS_DFORK_SIZE(&sc->ip->i_d, sc->mp, rb->whichfork)) {
+		ifake->if_format = XFS_DINODE_FMT_EXTENTS;
+		error = xrep_bmap_extents_load(rb, bmap_cur);
+	} else {
+		ifake->if_format = XFS_DINODE_FMT_BTREE;
+		error = xrep_bmap_btree_load(rb, &bmap_cur);
+	}
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Install the new fork in the inode.  After this point the old mapping
+	 * data are no longer accessible and the new tree is live.  We delete
+	 * the cursor immediately after committing the staged root because the
+	 * staged fork might be in extents format.
+	 */
+	xfs_bmbt_commit_staged_btree(bmap_cur, rb->whichfork);
+	xfs_btree_del_cursor(bmap_cur, 0);
+
+	/* Reset the inode counters now that we've changed the fork. */
+	error = xrep_bmap_reset_counters(rb);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting information. */
+	xrep_newbt_destroy(&rb->new_fork_info, error);
+
+	return xfs_trans_roll_inode(&sc->tp, sc->ip);
+err_cur:
+	if (bmap_cur)
+		xfs_btree_del_cursor(bmap_cur, error);
+err_newbt:
+	xrep_newbt_destroy(&rb->new_fork_info, error);
+	return error;
+}
+
+/*
+ * Now that we've logged the new inode btree, invalidate all of the old blocks
+ * and free them, if there were any.
+ */
+STATIC int
+xrep_bmap_remove_old_tree(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	struct xfs_owner_info	oinfo;
+
+	/* Free the old bmbt blocks if they're not in use. */
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+	return xrep_reap_extents(sc, &rb->old_bmbt_blocks, &oinfo,
+			XFS_AG_RESV_NONE);
+}
+
+/* Check for garbage inputs. */
+STATIC int
+xrep_bmap_check_inputs(
+	struct xfs_scrub	*sc,
+	int			whichfork)
+{
+	ASSERT(whichfork == XFS_DATA_FORK || whichfork == XFS_ATTR_FORK);
+
+	/* Don't know how to repair the other fork formats. */
+	if (XFS_IFORK_FORMAT(sc->ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+	    XFS_IFORK_FORMAT(sc->ip, whichfork) != XFS_DINODE_FMT_BTREE)
+		return -EOPNOTSUPP;
+
+	/*
+	 * If there's no attr fork area in the inode, there's no attr fork to
+	 * rebuild.
+	 */
+	if (whichfork == XFS_ATTR_FORK) {
+		if (!XFS_IFORK_Q(sc->ip))
+			return -ENOENT;
+		return 0;
+	}
+
+	/* Only files, symlinks, and directories get to have data forks. */
+	switch (VFS_I(sc->ip)->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		/* ok */
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* If we somehow have delalloc extents, forget it. */
+	if (sc->ip->i_delayed_blks)
+		return -EBUSY;
+
+	/* Don't know how to rebuild realtime data forks. */
+	if (XFS_IS_REALTIME_INODE(sc->ip))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/* Repair an inode fork. */
+STATIC int
+xrep_bmap(
+	struct xfs_scrub	*sc,
+	int			whichfork)
+{
+	struct xrep_bmap	*rb;
+	int			error = 0;
+
+	error = xrep_bmap_check_inputs(sc, whichfork);
+	if (error)
+		return error;
+
+	rb = kmem_zalloc(sizeof(struct xrep_bmap), KM_NOFS | KM_MAYFAIL);
+	if (!rb)
+		return -ENOMEM;
+	rb->sc = sc;
+	rb->whichfork = whichfork;
+
+	/* Set up some storage */
+	rb->bmap_records = xfbma_init(sizeof(struct xfs_bmbt_rec));
+	if (IS_ERR(rb->bmap_records)) {
+		error = PTR_ERR(rb->bmap_records);
+		goto out_rb;
+	}
+
+	/* Collect all reverse mappings for this fork's extents. */
+	xbitmap_init(&rb->old_bmbt_blocks);
+	error = xrep_bmap_find_mappings(rb);
+	if (error)
+		goto out_bitmap;
+
+	/* Rebuild the bmap information. */
+	error = xrep_bmap_build_new_fork(rb);
+	if (error)
+		goto out_bitmap;
+
+	/* Kill the old tree. */
+	error = xrep_bmap_remove_old_tree(rb);
+
+out_bitmap:
+	xbitmap_destroy(&rb->old_bmbt_blocks);
+	xfbma_destroy(rb->bmap_records);
+out_rb:
+	kmem_free(rb);
+	return error;
+}
+
+/* Repair an inode's data fork. */
+int
+xrep_bmap_data(
+	struct xfs_scrub	*sc)
+{
+	return xrep_bmap(sc, XFS_DATA_FORK);
+}
+
+/* Repair an inode's attr fork. */
+int
+xrep_bmap_attr(
+	struct xfs_scrub	*sc)
+{
+	return xrep_bmap(sc, XFS_ATTR_FORK);
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index dfb4fe77fae8..84ea16f410bb 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -72,6 +72,8 @@ int xrep_allocbt(struct xfs_scrub *sc);
 int xrep_iallocbt(struct xfs_scrub *sc);
 int xrep_refcountbt(struct xfs_scrub *sc);
 int xrep_inode(struct xfs_scrub *sc);
+int xrep_bmap_data(struct xfs_scrub *sc);
+int xrep_bmap_attr(struct xfs_scrub *sc);
 
 struct xrep_newbt_resv {
 	/* Link to list of extents that we've reserved. */
@@ -171,6 +173,8 @@ xrep_reset_perag_resv(
 #define xrep_iallocbt			xrep_notsupported
 #define xrep_refcountbt			xrep_notsupported
 #define xrep_inode			xrep_notsupported
+#define xrep_bmap_data			xrep_notsupported
+#define xrep_bmap_attr			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index ee2b77b4350b..f5b6184f609b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -267,13 +267,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_data,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_bmap_data,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_attr,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_bmap_attr,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index ed9484de80fe..592f9512115c 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -724,7 +724,7 @@ DEFINE_EVENT(xrep_rmap_class, name, \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
 DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
 DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
 
 TRACE_EVENT(xrep_abt_found,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
@@ -809,6 +809,38 @@ TRACE_EVENT(xrep_refc_found,
 		  __entry->refcount)
 )
 
+TRACE_EVENT(xrep_bmap_found,
+	TP_PROTO(struct xfs_inode *ip, int whichfork,
+		 struct xfs_bmbt_irec *irec),
+	TP_ARGS(ip, whichfork, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, lblk)
+		__field(xfs_extlen_t, len)
+		__field(xfs_fsblock_t, pblk)
+		__field(int, state)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->whichfork = whichfork;
+		__entry->lblk = irec->br_startoff;
+		__entry->len = irec->br_blockcount;
+		__entry->pblk = irec->br_startblock;
+		__entry->state = irec->br_state;
+	),
+	TP_printk("dev %d:%d ino 0x%llx whichfork %s lblk 0x%llx len 0x%x pblk %llu st %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->whichfork == XFS_ATTR_FORK ? "attr" : "data",
+		  __entry->lblk,
+		  __entry->len,
+		  __entry->pblk,
+		  __entry->state)
+);
+
 TRACE_EVENT(xrep_init_btblock,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 xfs_btnum_t btnum),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 3b208f9a865c..3a0e0a6d1a0d 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -129,6 +129,60 @@ xfs_trans_dup(
 	return ntp;
 }
 
+/*
+ * Try to reserve more blocks for a transaction.  The single use case we
+ * support is for online repair -- use a transaction to gather data without
+ * fear of btree cycle deadlocks; calculate how many blocks we really need
+ * from that data; and only then start modifying data.  This can fail due to
+ * ENOSPC, so we have to be able to cancel the transaction.
+ */
+int
+xfs_trans_reserve_more(
+	struct xfs_trans	*tp,
+	uint			blocks,
+	uint			rtextents)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
+	int			error = 0;
+
+	ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
+
+	/*
+	 * Attempt to reserve the needed disk blocks by decrementing
+	 * the number needed from the number available.  This will
+	 * fail if the count would go below zero.
+	 */
+	if (blocks > 0) {
+		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
+		if (error)
+			return -ENOSPC;
+		tp->t_blk_res += blocks;
+	}
+
+	/*
+	 * Attempt to reserve the needed realtime extents by decrementing
+	 * the number needed from the number available.  This will
+	 * fail if the count would go below zero.
+	 */
+	if (rtextents > 0) {
+		error = xfs_mod_frextents(mp, -((int64_t)rtextents));
+		if (error) {
+			error = -ENOSPC;
+			goto out_blocks;
+		}
+		tp->t_rtx_res += rtextents;
+	}
+
+	return 0;
+out_blocks:
+	if (blocks > 0) {
+		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
+		tp->t_blk_res -= blocks;
+	}
+	return error;
+}
+
 /*
  * This is called to reserve free disk blocks and log space for the
  * given transaction.  This must be done before allocating any resources
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 64d7f171ebd3..982d53eb2853 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -165,6 +165,8 @@ typedef struct xfs_trans {
 int		xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
 			uint blocks, uint rtextents, uint flags,
 			struct xfs_trans **tpp);
+int		xfs_trans_reserve_more(struct xfs_trans *tp, uint blocks,
+			uint rtextents);
 int		xfs_trans_alloc_empty(struct xfs_mount *mp,
 			struct xfs_trans **tpp);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);

[PATCH 4/4] xfs: repair damaged symlinks

[Darrick J. Wong]

From: Darrick J. Wong <darrick.wong@oracle.com>

Repair inconsistent symbolic link data.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/Makefile               |    1 
 fs/xfs/scrub/repair.h         |    2 
 fs/xfs/scrub/scrub.c          |    2 
 fs/xfs/scrub/symlink.c        |    5 +
 fs/xfs/scrub/symlink_repair.c |  243 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_symlink.c          |  150 ++++++++++++++-----------
 fs/xfs/xfs_symlink.h          |    3 +
 7 files changed, 338 insertions(+), 68 deletions(-)
 create mode 100644 fs/xfs/scrub/symlink_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 933ba41396b0..f746ba679948 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -167,6 +167,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   inode_repair.o \
 				   refcount_repair.o \
 				   repair.o \
+				   symlink_repair.o \
 				   xfile.o \
 				   )
 endif
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 84ea16f410bb..4ff872b7b8cd 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -74,6 +74,7 @@ int xrep_refcountbt(struct xfs_scrub *sc);
 int xrep_inode(struct xfs_scrub *sc);
 int xrep_bmap_data(struct xfs_scrub *sc);
 int xrep_bmap_attr(struct xfs_scrub *sc);
+int xrep_symlink(struct xfs_scrub *sc);
 
 struct xrep_newbt_resv {
 	/* Link to list of extents that we've reserved. */
@@ -175,6 +176,7 @@ xrep_reset_perag_resv(
 #define xrep_inode			xrep_notsupported
 #define xrep_bmap_data			xrep_notsupported
 #define xrep_bmap_attr			xrep_notsupported
+#define xrep_symlink			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index f5b6184f609b..ff06bc5031ae 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -297,7 +297,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_symlink,
 		.scrub	= xchk_symlink,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_symlink,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 5641ae512c9e..1709c2d90752 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -21,12 +21,15 @@ xchk_setup_symlink(
 	struct xfs_scrub	*sc,
 	struct xfs_inode	*ip)
 {
+	uint			resblks;
+
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kmem_zalloc_large(XFS_SYMLINK_MAXLEN + 1, 0);
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xchk_setup_inode_contents(sc, ip, 0);
+	resblks = xfs_symlink_blocks(sc->mp, XFS_SYMLINK_MAXLEN);
+	return xchk_setup_inode_contents(sc, ip, resblks);
 }
 
 /* Symbolic links. */
diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c
new file mode 100644
index 000000000000..8adb3e34d1c1
--- /dev/null
+++ b/fs/xfs/scrub/symlink_repair.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_symlink.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Symbolic Link Repair
+ * ====================
+ *
+ * There's not much we can do to repair symbolic links -- we truncate them to
+ * the first NULL byte and reinitialize the target.  Zero-length symlinks are
+ * turned into links to the current dir.
+ */
+
+/* Try to salvage the pathname from rmt blocks. */
+STATIC int
+xrep_symlink_salvage_remote(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_buf		*bp;
+	char			*target_buf = sc->buf;
+	xfs_failaddr_t		fa;
+	xfs_filblks_t		fsblocks;
+	xfs_daddr_t		d;
+	loff_t			len;
+	loff_t			offset;
+	unsigned int		byte_cnt;
+	bool			magic_ok;
+	bool			hdr_ok;
+	int			n;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			error;
+
+	/* We'll only read until the buffer is full. */
+	len = max_t(loff_t, ip->i_d.di_size, XFS_SYMLINK_MAXLEN);
+	fsblocks = xfs_symlink_blocks(sc->mp, len);
+	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+	if (error)
+		return error;
+
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		struct xfs_dsymlink_hdr	*dsl;
+
+		d = XFS_FSB_TO_DADDR(sc->mp, mval[n].br_startblock);
+
+		/* Read the rmt block.  We'll run the verifiers manually. */
+		error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+				d, XFS_FSB_TO_BB(sc->mp, mval[n].br_blockcount),
+				0, &bp, NULL);
+		if (error)
+			return error;
+		bp->b_ops = &xfs_symlink_buf_ops;
+
+		/* How many bytes do we expect to get out of this buffer? */
+		byte_cnt = XFS_FSB_TO_B(sc->mp, mval[n].br_blockcount);
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(sc->mp, byte_cnt);
+		byte_cnt = min_t(unsigned int, byte_cnt, len);
+
+		/*
+		 * See if the verifiers accept this block.  We're willing to
+		 * salvage if the if the offset/byte/ino are ok and either the
+		 * verifier passed or the magic is ok.  Anything else and we
+		 * stop dead in our tracks.
+		 */
+		fa = bp->b_ops->verify_struct(bp);
+		dsl = bp->b_addr;
+		magic_ok = dsl->sl_magic == cpu_to_be32(XFS_SYMLINK_MAGIC);
+		hdr_ok = xfs_symlink_hdr_ok(ip->i_ino, offset, byte_cnt, bp);
+		if (!hdr_ok || (fa != NULL && !magic_ok))
+			break;
+
+		memcpy(target_buf + offset, dsl + 1, byte_cnt);
+
+		len -= byte_cnt;
+		offset += byte_cnt;
+	}
+
+	/* Ensure we have a zero at the end, and /some/ contents. */
+	if (offset == 0)
+		sprintf(target_buf, ".");
+	else
+		target_buf[offset] = 0;
+	return 0;
+}
+
+/*
+ * Try to salvage an inline symlink's contents.  Empty symlinks become a link
+ * to the current directory.
+ */
+STATIC void
+xrep_symlink_salvage_inline(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	if (ifp->if_u1.if_data)
+		strncpy(sc->buf, ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip));
+	if (strlen(sc->buf) == 0)
+		sprintf(sc->buf, ".");
+}
+
+/* Reset an inline symlink to its fresh configuration. */
+STATIC void
+xrep_symlink_truncate_inline(
+	struct xfs_inode	*ip)
+{
+	xfs_idestroy_fork(ip, XFS_DATA_FORK);
+	ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
+	ip->i_d.di_nextents = 0;
+	memset(&ip->i_df, 0, sizeof(struct xfs_ifork));
+	ip->i_df.if_flags |= XFS_IFEXTENTS;
+}
+
+/*
+ * Salvage an inline symlink's contents and reset data fork.
+ * Returns with the inode joined to the transaction.
+ */
+STATIC int
+xrep_symlink_inline(
+	struct xfs_scrub	*sc)
+{
+	/* Salvage whatever link target information we can find. */
+	xrep_symlink_salvage_inline(sc);
+
+	/* Truncate the symlink. */
+	xrep_symlink_truncate_inline(sc->ip);
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+	return 0;
+}
+
+/*
+ * Salvage an inline symlink's contents and reset data fork.
+ * Returns with the inode joined to the transaction.
+ */
+STATIC int
+xrep_symlink_remote(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	/* Salvage whatever link target information we can find. */
+	error = xrep_symlink_salvage_remote(sc);
+	if (error)
+		return error;
+
+	/* Truncate the symlink. */
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+	return xfs_itruncate_extents(&sc->tp, sc->ip, XFS_DATA_FORK, 0);
+}
+
+/*
+ * Reinitialize a link target.  Caller must ensure the inode is joined to
+ * the transaction.
+ */
+STATIC int
+xrep_symlink_reinitialize(
+	struct xfs_scrub	*sc)
+{
+	xfs_fsblock_t		fs_blocks;
+	unsigned int		target_len;
+	uint			resblks;
+	int			error;
+
+	/* How many blocks do we need? */
+	target_len = strlen(sc->buf);
+	ASSERT(target_len != 0);
+	if (target_len == 0 || target_len > XFS_SYMLINK_MAXLEN)
+		return -EFSCORRUPTED;
+
+	/* Set up to reinitialize the target. */
+	fs_blocks = xfs_symlink_blocks(sc->mp, target_len);
+	resblks = XFS_SYMLINK_SPACE_RES(sc->mp, target_len, fs_blocks);
+	error = xfs_trans_reserve_quota_nblks(sc->tp, sc->ip, resblks, 0,
+			XFS_QMOPT_RES_REGBLKS);
+
+	/* Try to write the new target back out. */
+	error = xfs_symlink_write_target(sc->tp, sc->ip, sc->buf, target_len,
+			fs_blocks, resblks);
+	if (error)
+		return error;
+
+	/* Finish up any block mapping activities. */
+	return xfs_defer_finish(&sc->tp);
+}
+
+/* Repair a symbolic link. */
+int
+xrep_symlink(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_ifork	*ifp;
+	int			error;
+
+	error = xfs_qm_dqattach_locked(sc->ip, false);
+	if (error)
+		return error;
+
+	/* Salvage whatever we can of the target. */
+	*((char *)sc->buf) = 0;
+	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+	if (ifp->if_flags & XFS_IFINLINE)
+		error = xrep_symlink_inline(sc);
+	else
+		error = xrep_symlink_remote(sc);
+	if (error)
+		return error;
+
+	/* Now reset the target. */
+	return xrep_symlink_reinitialize(sc);
+}
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index a25502bc2071..bedd9a8be75f 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -142,6 +142,86 @@ xfs_readlink(
 	return error;
 }
 
+/* Write the symlink target into the inode. */
+int
+xfs_symlink_write_target(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	const char		*target_path,
+	int			pathlen,
+	xfs_fsblock_t		fs_blocks,
+	uint			resblks)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_mount	*mp = tp->t_mountp;
+	const char		*cur_chunk;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	int			byte_cnt;
+	int			nmaps;
+	int			offset;
+	int			n;
+	int			error;
+
+	/*
+	 * If the symlink will fit into the inode, write it inline.
+	 */
+	if (pathlen <= XFS_IFORK_DSIZE(ip)) {
+		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
+
+		ip->i_d.di_size = pathlen;
+		ip->i_d.di_format = XFS_DINODE_FMT_LOCAL;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+
+		return 0;
+	}
+
+	/* Write target to remote blocks. */
+	nmaps = XFS_SYMLINK_MAPS;
+	error = xfs_bmapi_write(tp, ip, 0, fs_blocks, XFS_BMAPI_METADATA,
+			resblks, mval, &nmaps);
+	if (error)
+		return error;
+
+	if (resblks)
+		resblks -= fs_blocks;
+	ip->i_d.di_size = pathlen;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	cur_chunk = target_path;
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		char	*buf;
+
+		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
+				BTOBB(byte_cnt), 0);
+		if (!bp)
+			return -ENOMEM;
+		bp->b_ops = &xfs_symlink_buf_ops;
+
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+		byte_cnt = min(byte_cnt, pathlen);
+
+		buf = bp->b_addr;
+		buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
+					   byte_cnt, bp);
+
+		memcpy(buf, cur_chunk, byte_cnt);
+
+		cur_chunk += byte_cnt;
+		pathlen -= byte_cnt;
+		offset += byte_cnt;
+
+		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+		xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
+						(char *)bp->b_addr);
+	}
+	ASSERT(pathlen == 0);
+	return 0;
+}
+
 int
 xfs_symlink(
 	struct xfs_inode	*dp,
@@ -156,15 +236,7 @@ xfs_symlink(
 	int			error = 0;
 	int			pathlen;
 	bool                    unlock_dp_on_error = false;
-	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
-	int			nmaps;
-	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
-	xfs_daddr_t		d;
-	const char		*cur_chunk;
-	int			byte_cnt;
-	int			n;
-	xfs_buf_t		*bp;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
 	struct xfs_dquot	*gdqp = NULL;
@@ -258,65 +330,11 @@ xfs_symlink(
 
 	if (resblks)
 		resblks -= XFS_IALLOC_SPACE_RES(mp);
-	/*
-	 * If the symlink will fit into the inode, write it inline.
-	 */
-	if (pathlen <= XFS_IFORK_DSIZE(ip)) {
-		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
-
-		ip->i_d.di_size = pathlen;
-		ip->i_d.di_format = XFS_DINODE_FMT_LOCAL;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
-	} else {
-		int	offset;
-
-		first_fsb = 0;
-		nmaps = XFS_SYMLINK_MAPS;
-
-		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
-		if (error)
-			goto out_trans_cancel;
-
-		if (resblks)
-			resblks -= fs_blocks;
-		ip->i_d.di_size = pathlen;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-		cur_chunk = target_path;
-		offset = 0;
-		for (n = 0; n < nmaps; n++) {
-			char	*buf;
-
-			d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
-			byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
-			bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
-					       BTOBB(byte_cnt), 0);
-			if (!bp) {
-				error = -ENOMEM;
-				goto out_trans_cancel;
-			}
-			bp->b_ops = &xfs_symlink_buf_ops;
-
-			byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
-			byte_cnt = min(byte_cnt, pathlen);
-
-			buf = bp->b_addr;
-			buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
-						   byte_cnt, bp);
-
-			memcpy(buf, cur_chunk, byte_cnt);
 
-			cur_chunk += byte_cnt;
-			pathlen -= byte_cnt;
-			offset += byte_cnt;
-
-			xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
-			xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
-							(char *)bp->b_addr);
-		}
-		ASSERT(pathlen == 0);
-	}
+	error = xfs_symlink_write_target(tp, ip, target_path, pathlen,
+			fs_blocks, resblks);
+	if (error)
+		goto out_trans_cancel;
 
 	/*
 	 * Create the directory entry for the symlink.
diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h
index b1fa091427e6..51f1b53d3f79 100644
--- a/fs/xfs/xfs_symlink.h
+++ b/fs/xfs/xfs_symlink.h
@@ -12,5 +12,8 @@ int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
 int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link);
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_inactive_symlink(struct xfs_inode *ip);
+int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
+		uint resblks);
 
 #endif /* __XFS_SYMLINK_H */