From: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Fix anything that causes the quota verifiers to fail.
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
---
fs/xfs/Makefile | 1
fs/xfs/scrub/attr_repair.c | 2
fs/xfs/scrub/common.h | 8 +
fs/xfs/scrub/quota.c | 2
fs/xfs/scrub/quota_repair.c | 365 +++++++++++++++++++++++++++++++++++++++++++
fs/xfs/scrub/repair.c | 58 +++++++
fs/xfs/scrub/repair.h | 8 +
fs/xfs/scrub/scrub.c | 11 +
fs/xfs/scrub/scrub.h | 1
9 files changed, 448 insertions(+), 8 deletions(-)
create mode 100644 fs/xfs/scrub/quota_repair.c
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 24d8b19a837b..0392bca6f5fe 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -174,5 +174,6 @@ xfs-y += $(addprefix scrub/, \
rmap_repair.o \
symlink_repair.o \
)
+xfs-$(CONFIG_XFS_QUOTA) += scrub/quota_repair.o
endif
endif
diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c
index 5f2e4dad92b7..aba5ac671a28 100644
--- a/fs/xfs/scrub/attr_repair.c
+++ b/fs/xfs/scrub/attr_repair.c
@@ -355,7 +355,7 @@ xfs_repair_xattr_recover(
}
/* Free all the attribute fork blocks and delete the fork. */
-STATIC int
+int
xfs_repair_xattr_reset_btree(
struct xfs_scrub_context *sc)
{
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index e8c4e41139ca..b0cca36de2de 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -138,6 +138,14 @@ static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
XFS_SCRUB_OFLAG_XCORRUPT);
}
+/* Do we need to invoke the repair tool? */
+static inline bool xfs_scrub_needs_repair(struct xfs_scrub_metadata *sm)
+{
+ return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT |
+ XFS_SCRUB_OFLAG_PREEN);
+}
+
int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
void xfs_scrub_iput(struct xfs_scrub_context *sc, struct xfs_inode *ip);
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ff906aa0a3b..ab0f0f7fde2d 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -29,7 +29,7 @@
#include "scrub/trace.h"
/* Convert a scrub type code to a DQ flag, or return 0 if error. */
-static inline uint
+uint
xfs_scrub_quota_to_dqtype(
struct xfs_scrub_context *sc)
{
diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c
new file mode 100644
index 000000000000..4e7af44a2ba1
--- /dev/null
+++ b/fs/xfs/scrub/quota_repair.c
@@ -0,0 +1,365 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
+ */
+#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_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_dquot.h"
+#include "xfs_dquot_item.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Quota Repair
+ * ============
+ *
+ * Quota repairs are fairly simplistic; we fix everything that the dquot
+ * verifiers complain about, cap any counters or limits that make no sense,
+ * and schedule a quotacheck if we had to fix anything. We also repair any
+ * data fork extent records that don't apply to metadata files.
+ */
+
+struct xfs_repair_quota_info {
+ struct xfs_scrub_context *sc;
+ bool need_quotacheck;
+};
+
+/* Scrub the fields in an individual quota item. */
+STATIC int
+xfs_repair_quota_item(
+ struct xfs_dquot *dq,
+ uint dqtype,
+ void *priv)
+{
+ struct xfs_repair_quota_info *rqi = priv;
+ struct xfs_scrub_context *sc = rqi->sc;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_disk_dquot *d = &dq->q_core;
+ unsigned long long bsoft;
+ unsigned long long isoft;
+ unsigned long long rsoft;
+ unsigned long long bhard;
+ unsigned long long ihard;
+ unsigned long long rhard;
+ unsigned long long bcount;
+ unsigned long long icount;
+ unsigned long long rcount;
+ xfs_ino_t fs_icount;
+ bool dirty = false;
+ int error;
+
+ /* Did we get the dquot type we wanted? */
+ if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES)) {
+ d->d_flags = dqtype;
+ dirty = true;
+ }
+
+ if (d->d_pad0 || d->d_pad) {
+ d->d_pad0 = 0;
+ d->d_pad = 0;
+ dirty = true;
+ }
+
+ /* Check the limits. */
+ bhard = be64_to_cpu(d->d_blk_hardlimit);
+ ihard = be64_to_cpu(d->d_ino_hardlimit);
+ rhard = be64_to_cpu(d->d_rtb_hardlimit);
+
+ bsoft = be64_to_cpu(d->d_blk_softlimit);
+ isoft = be64_to_cpu(d->d_ino_softlimit);
+ rsoft = be64_to_cpu(d->d_rtb_softlimit);
+
+ if (bsoft > bhard) {
+ d->d_blk_softlimit = d->d_blk_hardlimit;
+ dirty = true;
+ }
+
+ if (isoft > ihard) {
+ d->d_ino_softlimit = d->d_ino_hardlimit;
+ dirty = true;
+ }
+
+ if (rsoft > rhard) {
+ d->d_rtb_softlimit = d->d_rtb_hardlimit;
+ dirty = true;
+ }
+
+ /* Check the resource counts. */
+ bcount = be64_to_cpu(d->d_bcount);
+ icount = be64_to_cpu(d->d_icount);
+ rcount = be64_to_cpu(d->d_rtbcount);
+ fs_icount = percpu_counter_sum(&mp->m_icount);
+
+ /*
+ * Check that usage doesn't exceed physical limits. However, on
+ * a reflink filesystem we're allowed to exceed physical space
+ * if there are no quota limits. We don't know what the real number
+ * is, but we can make quotacheck find out for us.
+ */
+ if (!xfs_sb_version_hasreflink(&mp->m_sb) &&
+ mp->m_sb.sb_dblocks < bcount) {
+ dq->q_res_bcount -= be64_to_cpu(dq->q_core.d_bcount);
+ dq->q_res_bcount += mp->m_sb.sb_dblocks;
+ d->d_bcount = cpu_to_be64(mp->m_sb.sb_dblocks);
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+ if (icount > fs_icount) {
+ dq->q_res_icount -= be64_to_cpu(dq->q_core.d_icount);
+ dq->q_res_icount += fs_icount;
+ d->d_icount = cpu_to_be64(fs_icount);
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+ if (rcount > mp->m_sb.sb_rblocks) {
+ dq->q_res_rtbcount -= be64_to_cpu(dq->q_core.d_rtbcount);
+ dq->q_res_rtbcount += mp->m_sb.sb_rblocks;
+ d->d_rtbcount = cpu_to_be64(mp->m_sb.sb_rblocks);
+ rqi->need_quotacheck = true;
+ dirty = true;
+ }
+
+ if (!dirty)
+ return 0;
+
+ dq->dq_flags |= XFS_DQ_DIRTY;
+ xfs_trans_dqjoin(sc->tp, dq);
+ xfs_trans_log_dquot(sc->tp, dq);
+ error = xfs_trans_roll(&sc->tp);
+ xfs_dqlock(dq);
+ return error;
+}
+
+/* Fix a quota timer so that we can pass the verifier. */
+STATIC void
+xfs_repair_quota_fix_timer(
+ __be64 softlimit,
+ __be64 countnow,
+ __be32 *timer,
+ time_t timelimit)
+{
+ uint64_t soft = be64_to_cpu(softlimit);
+ uint64_t count = be64_to_cpu(countnow);
+
+ if (soft && count > soft && *timer == 0)
+ *timer = cpu_to_be32(get_seconds() + timelimit);
+}
+
+/* Fix anything the verifiers complain about. */
+STATIC int
+xfs_repair_quota_block(
+ struct xfs_scrub_context *sc,
+ struct xfs_buf *bp,
+ uint dqtype,
+ xfs_dqid_t id)
+{
+ struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr;
+ struct xfs_disk_dquot *ddq;
+ struct xfs_quotainfo *qi = sc->mp->m_quotainfo;
+ enum xfs_blft buftype = 0;
+ int i;
+
+ bp->b_ops = &xfs_dquot_buf_ops;
+ for (i = 0; i < qi->qi_dqperchunk; i++) {
+ ddq = &d[i].dd_diskdq;
+
+ ddq->d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+ ddq->d_version = XFS_DQUOT_VERSION;
+ ddq->d_flags = dqtype;
+ ddq->d_id = cpu_to_be32(id + i);
+
+ xfs_repair_quota_fix_timer(ddq->d_blk_softlimit,
+ ddq->d_bcount, &ddq->d_btimer,
+ qi->qi_btimelimit);
+ xfs_repair_quota_fix_timer(ddq->d_ino_softlimit,
+ ddq->d_icount, &ddq->d_itimer,
+ qi->qi_itimelimit);
+ xfs_repair_quota_fix_timer(ddq->d_rtb_softlimit,
+ ddq->d_rtbcount, &ddq->d_rtbtimer,
+ qi->qi_rtbtimelimit);
+
+ if (xfs_sb_version_hascrc(&sc->mp->m_sb)) {
+ uuid_copy(&d->dd_uuid, &sc->mp->m_sb.sb_meta_uuid);
+ xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
+ XFS_DQUOT_CRC_OFF);
+ } else {
+ memset(&d->dd_uuid, 0, sizeof(d->dd_uuid));
+ d->dd_lsn = 0;
+ d->dd_crc = 0;
+ }
+ }
+ switch (dqtype) {
+ case XFS_DQ_USER:
+ buftype = XFS_BLFT_UDQUOT_BUF;
+ break;
+ case XFS_DQ_GROUP:
+ buftype = XFS_BLFT_GDQUOT_BUF;
+ break;
+ case XFS_DQ_PROJ:
+ buftype = XFS_BLFT_PDQUOT_BUF;
+ break;
+ }
+ xfs_trans_buf_set_type(sc->tp, bp, buftype);
+ xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
+ return xfs_trans_roll(&sc->tp);
+}
+
+/* Repair quota's data fork. */
+STATIC int
+xfs_repair_quota_data_fork(
+ struct xfs_scrub_context *sc,
+ uint dqtype)
+{
+ struct xfs_bmbt_irec irec = { 0 };
+ struct xfs_iext_cursor icur;
+ struct xfs_quotainfo *qi = sc->mp->m_quotainfo;
+ struct xfs_ifork *ifp;
+ struct xfs_buf *bp;
+ struct xfs_dqblk *d;
+ xfs_dqid_t id;
+ xfs_fileoff_t max_dqid_off;
+ xfs_fileoff_t off;
+ xfs_fsblock_t fsbno;
+ bool truncate = false;
+ int error = 0;
+
+ error = xfs_repair_metadata_inode_forks(sc);
+ if (error)
+ goto out;
+
+ /* Check for data fork problems that apply only to quota files. */
+ max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
+ ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ if (isnullstartblock(irec.br_startblock)) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ if (irec.br_startoff > max_dqid_off ||
+ irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
+ truncate = true;
+ break;
+ }
+ }
+ if (truncate) {
+ error = xfs_itruncate_extents(&sc->tp, sc->ip, XFS_DATA_FORK,
+ max_dqid_off * sc->mp->m_sb.sb_blocksize);
+ if (error)
+ goto out;
+ }
+
+ /* Now go fix anything that fails the verifiers. */
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ for (fsbno = irec.br_startblock, off = irec.br_startoff;
+ fsbno < irec.br_startblock + irec.br_blockcount;
+ fsbno += XFS_DQUOT_CLUSTER_SIZE_FSB,
+ off += XFS_DQUOT_CLUSTER_SIZE_FSB) {
+ id = off * qi->qi_dqperchunk;
+ error = xfs_trans_read_buf(sc->mp, sc->tp,
+ sc->mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(sc->mp, fsbno),
+ qi->qi_dqchunklen,
+ 0, &bp, &xfs_dquot_buf_ops);
+ if (error == 0) {
+ d = (struct xfs_dqblk *)bp->b_addr;
+ if (id == be32_to_cpu(d->dd_diskdq.d_id))
+ continue;
+ error = -EFSCORRUPTED;
+ }
+ if (error != -EFSBADCRC && error != -EFSCORRUPTED)
+ goto out;
+
+ /* Failed verifier, try again. */
+ error = xfs_trans_read_buf(sc->mp, sc->tp,
+ sc->mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(sc->mp, fsbno),
+ qi->qi_dqchunklen,
+ 0, &bp, NULL);
+ if (error)
+ goto out;
+ error = xfs_repair_quota_block(sc, bp, dqtype, id);
+ }
+ }
+
+ /*
+ * Roll the transaction so that we unlock all of the buffers we
+ * touched while doing raw dquot buffer checks. Subsequent parts of
+ * quota repair will use the regular dquot APIs, which re-read the
+ * dquot buffers to construct in-core dquots without a transaction.
+ * This causes deadlocks if we haven't released the dquot buffers.
+ */
+ error = xfs_trans_roll(&sc->tp);
+out:
+ return error;
+}
+
+/*
+ * Go fix anything in the quota items that we could have been mad about. Now
+ * that we've checked the quota inode data fork we have to drop ILOCK_EXCL to
+ * use the regular dquot functions.
+ */
+STATIC int
+xfs_repair_quota_problems(
+ struct xfs_scrub_context *sc,
+ uint dqtype)
+{
+ struct xfs_repair_quota_info rqi;
+ int error;
+
+ rqi.sc = sc;
+ rqi.need_quotacheck = false;
+ error = xfs_qm_dqiterate(sc->mp, dqtype, xfs_repair_quota_item, &rqi);
+ if (error)
+ return error;
+
+ /* Make a quotacheck happen. */
+ if (rqi.need_quotacheck)
+ xfs_repair_force_quotacheck(sc, dqtype);
+ return 0;
+}
+
+/* Repair all of a quota type's items. */
+int
+xfs_repair_quota(
+ struct xfs_scrub_context *sc)
+{
+ uint dqtype;
+ int error;
+
+ dqtype = xfs_scrub_quota_to_dqtype(sc);
+
+ /* Fix problematic data fork mappings. */
+ error = xfs_repair_quota_data_fork(sc, dqtype);
+ if (error)
+ goto out;
+
+ /* Unlock quota inode; we play only with dquots from now on. */
+ xfs_iunlock(sc->ip, sc->ilock_flags);
+ sc->ilock_flags = 0;
+
+ /* Fix anything the dquot verifiers complain about. */
+ error = xfs_repair_quota_problems(sc, dqtype);
+out:
+ return error;
+}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 85ec872093e6..399a98e1d8f7 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -29,6 +29,8 @@
#include "xfs_ag_resv.h"
#include "xfs_trans_space.h"
#include "xfs_quota.h"
+#include "xfs_attr.h"
+#include "xfs_reflink.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -1182,3 +1184,59 @@ xfs_repair_grab_all_ag_headers(
return error;
}
+
+/*
+ * Repair the attr/data forks of a metadata inode. The metadata inode must be
+ * pointed to by sc->ip and the ILOCK must be held.
+ */
+int
+xfs_repair_metadata_inode_forks(
+ struct xfs_scrub_context *sc)
+{
+ __u32 smtype;
+ __u32 smflags;
+ int error;
+
+ smtype = sc->sm->sm_type;
+ smflags = sc->sm->sm_flags;
+
+ /* Let's see if the forks need repair. */
+ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ error = xfs_scrub_metadata_inode_forks(sc);
+ if (error || !xfs_scrub_needs_repair(sc->sm))
+ goto out;
+
+ xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+ /* Clear the reflink flag & attr forks that we shouldn't have. */
+ if (xfs_is_reflink_inode(sc->ip)) {
+ error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
+ if (error)
+ goto out;
+ }
+
+ if (xfs_inode_hasattr(sc->ip)) {
+ error = xfs_repair_xattr_reset_btree(sc);
+ if (error)
+ goto out;
+ }
+
+ /* Repair the data fork. */
+ sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
+ error = xfs_repair_bmap_data(sc);
+ sc->sm->sm_type = smtype;
+ if (error)
+ goto out;
+
+ /* Bail out if we still need repairs. */
+ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ error = xfs_scrub_metadata_inode_forks(sc);
+ if (error)
+ goto out;
+ if (xfs_scrub_needs_repair(sc->sm))
+ error = -EFSCORRUPTED;
+out:
+ sc->sm->sm_type = smtype;
+ sc->sm->sm_flags = smflags;
+ return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 05a63fcc2364..083ab63624eb 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -97,6 +97,8 @@ void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
int xfs_repair_grab_all_ag_headers(struct xfs_scrub_context *sc);
int xfs_repair_rmapbt_setup(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xfs_repair_xattr_reset_btree(struct xfs_scrub_context *sc);
+int xfs_repair_metadata_inode_forks(struct xfs_scrub_context *sc);
/* Metadata repairers */
@@ -114,6 +116,11 @@ int xfs_repair_bmap_data(struct xfs_scrub_context *sc);
int xfs_repair_bmap_attr(struct xfs_scrub_context *sc);
int xfs_repair_symlink(struct xfs_scrub_context *sc);
int xfs_repair_xattr(struct xfs_scrub_context *sc);
+#ifdef CONFIG_XFS_QUOTA
+int xfs_repair_quota(struct xfs_scrub_context *sc);
+#else
+# define xfs_repair_quota xfs_repair_notsupported
+#endif /* CONFIG_XFS_QUOTA */
#else
@@ -157,6 +164,7 @@ static inline int xfs_repair_rmapbt_setup(
#define xfs_repair_bmap_attr xfs_repair_notsupported
#define xfs_repair_symlink xfs_repair_notsupported
#define xfs_repair_xattr xfs_repair_notsupported
+#define xfs_repair_quota xfs_repair_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 857197c89729..f57ec412a617 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -355,19 +355,19 @@ static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
- .repair = xfs_repair_notsupported,
+ .repair = xfs_repair_quota,
},
[XFS_SCRUB_TYPE_GQUOTA] = { /* group quota */
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
- .repair = xfs_repair_notsupported,
+ .repair = xfs_repair_quota,
},
[XFS_SCRUB_TYPE_PQUOTA] = { /* project quota */
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
- .repair = xfs_repair_notsupported,
+ .repair = xfs_repair_quota,
},
};
@@ -562,9 +562,8 @@ xfs_scrub_metadata(
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
sc.sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
- needs_fix = (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
- XFS_SCRUB_OFLAG_XCORRUPT |
- XFS_SCRUB_OFLAG_PREEN));
+ needs_fix = xfs_scrub_needs_repair(sc.sm);
+
/*
* If userspace asked for a repair but it wasn't necessary,
* report that back to userspace.
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 270098bb3225..43c4189ea549 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -157,5 +157,6 @@ void xfs_scrub_xref_is_used_rt_space(struct xfs_scrub_context *sc,
bool xfs_scrub_xattr_set_map(struct xfs_scrub_context *sc, unsigned long *map,
unsigned int start, unsigned int len);
+uint xfs_scrub_quota_to_dqtype(struct xfs_scrub_context *sc);
#endif /* __XFS_SCRUB_SCRUB_H__ */
--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
