summaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/scrub.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/scrub/scrub.c')
-rw-r--r--fs/xfs/scrub/scrub.c421
1 files changed, 378 insertions, 43 deletions
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4849efcaa33a..5c266d2842db 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -14,9 +14,14 @@
#include "xfs_inode.h"
#include "xfs_quota.h"
#include "xfs_qm.h"
-#include "xfs_errortag.h"
-#include "xfs_error.h"
#include "xfs_scrub.h"
+#include "xfs_buf_mem.h"
+#include "xfs_rmap.h"
+#include "xfs_exchrange.h"
+#include "xfs_exchmaps.h"
+#include "xfs_dir2.h"
+#include "xfs_parent.h"
+#include "xfs_icache.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -24,6 +29,8 @@
#include "scrub/health.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
+#include "scrub/tempfile.h"
+#include "scrub/orphanage.h"
/*
* Online Scrub and Repair
@@ -142,6 +149,18 @@ xchk_probe(
if (xchk_should_terminate(sc, &error))
return error;
+ /*
+ * If the caller is probing to see if repair works but repair isn't
+ * built into the kernel, return EOPNOTSUPP because that's the signal
+ * that userspace expects. If online repair is built in, set the
+ * CORRUPT flag (without any of the usual tracing/logging) to force us
+ * into xrep_probe.
+ */
+ if (xchk_could_repair(sc)) {
+ if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR))
+ return -EOPNOTSUPP;
+ sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ }
return 0;
}
@@ -159,9 +178,51 @@ xchk_fsgates_disable(
if (sc->flags & XCHK_FSGATES_DRAIN)
xfs_drain_wait_disable();
+ if (sc->flags & XCHK_FSGATES_QUOTA)
+ xfs_dqtrx_hook_disable();
+
+ if (sc->flags & XCHK_FSGATES_DIRENTS)
+ xfs_dir_hook_disable();
+
+ if (sc->flags & XCHK_FSGATES_RMAP)
+ xfs_rmap_hook_disable();
+
sc->flags &= ~XCHK_FSGATES_ALL;
}
+/* Free the resources associated with a scrub subtype. */
+void
+xchk_scrub_free_subord(
+ struct xfs_scrub_subord *sub)
+{
+ struct xfs_scrub *sc = sub->parent_sc;
+
+ ASSERT(sc->ip == sub->sc.ip);
+ ASSERT(sc->orphanage == sub->sc.orphanage);
+ ASSERT(sc->tempip == sub->sc.tempip);
+
+ sc->sm->sm_type = sub->old_smtype;
+ sc->sm->sm_flags = sub->old_smflags |
+ (sc->sm->sm_flags & XFS_SCRUB_FLAGS_OUT);
+ sc->tp = sub->sc.tp;
+
+ if (sub->sc.buf) {
+ if (sub->sc.buf_cleanup)
+ sub->sc.buf_cleanup(sub->sc.buf);
+ kvfree(sub->sc.buf);
+ }
+ if (sub->sc.xmbtp)
+ xmbuf_free(sub->sc.xmbtp);
+ if (sub->sc.xfile)
+ xfile_destroy(sub->sc.xfile);
+
+ sc->ilock_flags = sub->sc.ilock_flags;
+ sc->orphanage_ilock_flags = sub->sc.orphanage_ilock_flags;
+ sc->temp_ilock_flags = sub->sc.temp_ilock_flags;
+
+ kfree(sub);
+}
+
/* Free all the resources and finish the transactions. */
STATIC int
xchk_teardown(
@@ -186,6 +247,10 @@ xchk_teardown(
sc->flags &= ~XCHK_HAVE_FREEZE_PROT;
mnt_drop_write_file(sc->file);
}
+ if (sc->xmbtp) {
+ xmbuf_free(sc->xmbtp);
+ sc->xmbtp = NULL;
+ }
if (sc->xfile) {
xfile_destroy(sc->xfile);
sc->xfile = NULL;
@@ -198,6 +263,8 @@ xchk_teardown(
sc->buf = NULL;
}
+ xrep_tempfile_rele(sc);
+ xrep_orphanage_rele(sc);
xchk_fsgates_disable(sc);
return error;
}
@@ -238,127 +305,154 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
[XFS_SCRUB_TYPE_BNOBT] = { /* bnobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_allocbt,
- .scrub = xchk_bnobt,
- .repair = xrep_notsupported,
+ .scrub = xchk_allocbt,
+ .repair = xrep_allocbt,
+ .repair_eval = xrep_revalidate_allocbt,
},
[XFS_SCRUB_TYPE_CNTBT] = { /* cntbt */
.type = ST_PERAG,
.setup = xchk_setup_ag_allocbt,
- .scrub = xchk_cntbt,
- .repair = xrep_notsupported,
+ .scrub = xchk_allocbt,
+ .repair = xrep_allocbt,
+ .repair_eval = xrep_revalidate_allocbt,
},
[XFS_SCRUB_TYPE_INOBT] = { /* inobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_iallocbt,
- .scrub = xchk_inobt,
- .repair = xrep_notsupported,
+ .scrub = xchk_iallocbt,
+ .repair = xrep_iallocbt,
+ .repair_eval = xrep_revalidate_iallocbt,
},
[XFS_SCRUB_TYPE_FINOBT] = { /* finobt */
.type = ST_PERAG,
.setup = xchk_setup_ag_iallocbt,
- .scrub = xchk_finobt,
+ .scrub = xchk_iallocbt,
.has = xfs_has_finobt,
- .repair = xrep_notsupported,
+ .repair = xrep_iallocbt,
+ .repair_eval = xrep_revalidate_iallocbt,
},
[XFS_SCRUB_TYPE_RMAPBT] = { /* rmapbt */
.type = ST_PERAG,
.setup = xchk_setup_ag_rmapbt,
.scrub = xchk_rmapbt,
.has = xfs_has_rmapbt,
- .repair = xrep_notsupported,
+ .repair = xrep_rmapbt,
},
[XFS_SCRUB_TYPE_REFCNTBT] = { /* refcountbt */
.type = ST_PERAG,
.setup = xchk_setup_ag_refcountbt,
.scrub = xchk_refcountbt,
.has = xfs_has_reflink,
- .repair = xrep_notsupported,
+ .repair = xrep_refcountbt,
},
[XFS_SCRUB_TYPE_INODE] = { /* inode record */
.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,
.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,
.setup = xchk_setup_inode_bmap,
.scrub = xchk_bmap_cow,
- .repair = xrep_notsupported,
+ .repair = xrep_bmap_cow,
},
[XFS_SCRUB_TYPE_DIR] = { /* directory */
.type = ST_INODE,
.setup = xchk_setup_directory,
.scrub = xchk_directory,
- .repair = xrep_notsupported,
+ .repair = xrep_directory,
},
[XFS_SCRUB_TYPE_XATTR] = { /* extended attributes */
.type = ST_INODE,
.setup = xchk_setup_xattr,
.scrub = xchk_xattr,
- .repair = xrep_notsupported,
+ .repair = xrep_xattr,
},
[XFS_SCRUB_TYPE_SYMLINK] = { /* symbolic link */
.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,
.setup = xchk_setup_parent,
.scrub = xchk_parent,
- .repair = xrep_notsupported,
+ .repair = xrep_parent,
},
[XFS_SCRUB_TYPE_RTBITMAP] = { /* realtime bitmap */
.type = ST_FS,
.setup = xchk_setup_rtbitmap,
.scrub = xchk_rtbitmap,
- .has = xfs_has_realtime,
- .repair = xrep_notsupported,
+ .repair = xrep_rtbitmap,
},
[XFS_SCRUB_TYPE_RTSUM] = { /* realtime summary */
.type = ST_FS,
.setup = xchk_setup_rtsummary,
.scrub = xchk_rtsummary,
- .has = xfs_has_realtime,
- .repair = xrep_notsupported,
+ .repair = xrep_rtsummary,
},
[XFS_SCRUB_TYPE_UQUOTA] = { /* user quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_GQUOTA] = { /* group quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_PQUOTA] = { /* project quota */
.type = ST_FS,
.setup = xchk_setup_quota,
.scrub = xchk_quota,
- .repair = xrep_notsupported,
+ .repair = xrep_quota,
},
[XFS_SCRUB_TYPE_FSCOUNTERS] = { /* fs summary counters */
.type = ST_FS,
.setup = xchk_setup_fscounters,
.scrub = xchk_fscounters,
- .repair = xrep_notsupported,
+ .repair = xrep_fscounters,
+ },
+ [XFS_SCRUB_TYPE_QUOTACHECK] = { /* quota counters */
+ .type = ST_FS,
+ .setup = xchk_setup_quotacheck,
+ .scrub = xchk_quotacheck,
+ .repair = xrep_quotacheck,
+ },
+ [XFS_SCRUB_TYPE_NLINKS] = { /* inode link counts */
+ .type = ST_FS,
+ .setup = xchk_setup_nlinks,
+ .scrub = xchk_nlinks,
+ .repair = xrep_nlinks,
+ },
+ [XFS_SCRUB_TYPE_HEALTHY] = { /* fs healthy; clean all reminders */
+ .type = ST_FS,
+ .setup = xchk_setup_fs,
+ .scrub = xchk_health_record,
+ .repair = xrep_notsupported,
+ },
+ [XFS_SCRUB_TYPE_DIRTREE] = { /* directory tree structure */
+ .type = ST_INODE,
+ .setup = xchk_setup_dirtree,
+ .scrub = xchk_dirtree,
+ .has = xfs_has_parent,
+ .repair = xrep_dirtree,
},
};
@@ -464,8 +558,38 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
}
#endif /* CONFIG_XFS_ONLINE_REPAIR */
+/*
+ * Create a new scrub context from an existing one, but with a different scrub
+ * type.
+ */
+struct xfs_scrub_subord *
+xchk_scrub_create_subord(
+ struct xfs_scrub *sc,
+ unsigned int subtype)
+{
+ struct xfs_scrub_subord *sub;
+
+ sub = kzalloc(sizeof(*sub), XCHK_GFP_FLAGS);
+ if (!sub)
+ return ERR_PTR(-ENOMEM);
+
+ sub->old_smtype = sc->sm->sm_type;
+ sub->old_smflags = sc->sm->sm_flags;
+ sub->parent_sc = sc;
+ memcpy(&sub->sc, sc, sizeof(struct xfs_scrub));
+ sub->sc.ops = &meta_scrub_ops[subtype];
+ sub->sc.sm->sm_type = subtype;
+ sub->sc.sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ sub->sc.buf = NULL;
+ sub->sc.buf_cleanup = NULL;
+ sub->sc.xfile = NULL;
+ sub->sc.xmbtp = NULL;
+
+ return sub;
+}
+
/* Dispatch metadata scrubbing. */
-int
+STATIC int
xfs_scrub_metadata(
struct file *file,
struct xfs_scrub_metadata *sm)
@@ -507,6 +631,7 @@ xfs_scrub_metadata(
sc->sm = sm;
sc->ops = &meta_scrub_ops[sm->sm_type];
sc->sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
+ sc->relax = INIT_XCHK_RELAX;
retry_op:
/*
* When repairs are allowed, prevent freezing or readonly remount while
@@ -531,7 +656,10 @@ retry_op:
/* Scrub for errors. */
check_start = xchk_stats_now();
- error = sc->ops->scrub(sc);
+ if ((sc->flags & XREP_ALREADY_FIXED) && sc->ops->repair_eval != NULL)
+ error = sc->ops->repair_eval(sc);
+ else
+ error = sc->ops->scrub(sc);
run.scrub_ns += xchk_stats_elapsed_ns(check_start);
if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER))
goto try_harder;
@@ -542,23 +670,12 @@ retry_op:
xchk_update_health(sc);
- if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
- !(sc->flags & XREP_ALREADY_FIXED)) {
- bool needs_fix = xchk_needs_repair(sc->sm);
-
- /* Userspace asked us to rebuild the structure regardless. */
- if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD)
- needs_fix = true;
-
- /* Let debug users force us into the repair routines. */
- if (XFS_TEST_ERROR(needs_fix, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
- needs_fix = true;
-
+ if (xchk_could_repair(sc)) {
/*
* If userspace asked for a repair but it wasn't necessary,
* report that back to userspace.
*/
- if (!needs_fix) {
+ if (!xrep_will_attempt(sc)) {
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
goto out_nofix;
}
@@ -618,3 +735,221 @@ try_harder:
run.retries++;
goto retry_op;
}
+
+/* Scrub one aspect of one piece of metadata. */
+int
+xfs_ioc_scrub_metadata(
+ struct file *file,
+ void __user *arg)
+{
+ struct xfs_scrub_metadata scrub;
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&scrub, arg, sizeof(scrub)))
+ return -EFAULT;
+
+ error = xfs_scrub_metadata(file, &scrub);
+ if (error)
+ return error;
+
+ if (copy_to_user(arg, &scrub, sizeof(scrub)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/* Decide if there have been any scrub failures up to this point. */
+static inline int
+xfs_scrubv_check_barrier(
+ struct xfs_mount *mp,
+ const struct xfs_scrub_vec *vectors,
+ const struct xfs_scrub_vec *stop_vec)
+{
+ const struct xfs_scrub_vec *v;
+ __u32 failmask;
+
+ failmask = stop_vec->sv_flags & XFS_SCRUB_FLAGS_OUT;
+
+ for (v = vectors; v < stop_vec; v++) {
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER)
+ continue;
+
+ /*
+ * Runtime errors count as a previous failure, except the ones
+ * used to ask userspace to retry.
+ */
+ switch (v->sv_ret) {
+ case -EBUSY:
+ case -ENOENT:
+ case -EUSERS:
+ case 0:
+ break;
+ default:
+ return -ECANCELED;
+ }
+
+ /*
+ * If any of the out-flags on the scrub vector match the mask
+ * that was set on the barrier vector, that's a previous fail.
+ */
+ if (v->sv_flags & failmask)
+ return -ECANCELED;
+ }
+
+ return 0;
+}
+
+/*
+ * If the caller provided us with a nonzero inode number that isn't the ioctl
+ * file, try to grab a reference to it to eliminate all further untrusted inode
+ * lookups. If we can't get the inode, let each scrub function try again.
+ */
+STATIC struct xfs_inode *
+xchk_scrubv_open_by_handle(
+ struct xfs_mount *mp,
+ const struct xfs_scrub_vec_head *head)
+{
+ struct xfs_trans *tp;
+ struct xfs_inode *ip;
+ int error;
+
+ error = xfs_trans_alloc_empty(mp, &tp);
+ if (error)
+ return NULL;
+
+ error = xfs_iget(mp, tp, head->svh_ino, XCHK_IGET_FLAGS, 0, &ip);
+ xfs_trans_cancel(tp);
+ if (error)
+ return NULL;
+
+ if (VFS_I(ip)->i_generation != head->svh_gen) {
+ xfs_irele(ip);
+ return NULL;
+ }
+
+ return ip;
+}
+
+/* Vectored scrub implementation to reduce ioctl calls. */
+int
+xfs_ioc_scrubv_metadata(
+ struct file *file,
+ void __user *arg)
+{
+ struct xfs_scrub_vec_head head;
+ struct xfs_scrub_vec_head __user *uhead = arg;
+ struct xfs_scrub_vec *vectors;
+ struct xfs_scrub_vec __user *uvectors;
+ struct xfs_inode *ip_in = XFS_I(file_inode(file));
+ struct xfs_mount *mp = ip_in->i_mount;
+ struct xfs_inode *handle_ip = NULL;
+ struct xfs_scrub_vec *v;
+ size_t vec_bytes;
+ unsigned int i;
+ int error = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&head, uhead, sizeof(head)))
+ return -EFAULT;
+
+ if (head.svh_reserved)
+ return -EINVAL;
+ if (head.svh_flags & ~XFS_SCRUB_VEC_FLAGS_ALL)
+ return -EINVAL;
+ if (head.svh_nr == 0)
+ return 0;
+
+ vec_bytes = array_size(head.svh_nr, sizeof(struct xfs_scrub_vec));
+ if (vec_bytes > PAGE_SIZE)
+ return -ENOMEM;
+
+ uvectors = u64_to_user_ptr(head.svh_vectors);
+ vectors = memdup_user(uvectors, vec_bytes);
+ if (IS_ERR(vectors))
+ return PTR_ERR(vectors);
+
+ trace_xchk_scrubv_start(ip_in, &head);
+
+ for (i = 0, v = vectors; i < head.svh_nr; i++, v++) {
+ if (v->sv_reserved) {
+ error = -EINVAL;
+ goto out_free;
+ }
+
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER &&
+ (v->sv_flags & ~XFS_SCRUB_FLAGS_OUT)) {
+ error = -EINVAL;
+ goto out_free;
+ }
+
+ trace_xchk_scrubv_item(mp, &head, i, v);
+ }
+
+ /*
+ * If the caller wants us to do a scrub-by-handle and the file used to
+ * call the ioctl is not the same file, load the incore inode and pin
+ * it across all the scrubv actions to avoid repeated UNTRUSTED
+ * lookups. The reference is not passed to deeper layers of scrub
+ * because each scrubber gets to decide its own strategy and return
+ * values for getting an inode.
+ */
+ if (head.svh_ino && head.svh_ino != ip_in->i_ino)
+ handle_ip = xchk_scrubv_open_by_handle(mp, &head);
+
+ /* Run all the scrubbers. */
+ for (i = 0, v = vectors; i < head.svh_nr; i++, v++) {
+ struct xfs_scrub_metadata sm = {
+ .sm_type = v->sv_type,
+ .sm_flags = v->sv_flags,
+ .sm_ino = head.svh_ino,
+ .sm_gen = head.svh_gen,
+ .sm_agno = head.svh_agno,
+ };
+
+ if (v->sv_type == XFS_SCRUB_TYPE_BARRIER) {
+ v->sv_ret = xfs_scrubv_check_barrier(mp, vectors, v);
+ if (v->sv_ret) {
+ trace_xchk_scrubv_barrier_fail(mp, &head, i, v);
+ break;
+ }
+
+ continue;
+ }
+
+ v->sv_ret = xfs_scrub_metadata(file, &sm);
+ v->sv_flags = sm.sm_flags;
+
+ trace_xchk_scrubv_outcome(mp, &head, i, v);
+
+ if (head.svh_rest_us) {
+ ktime_t expires;
+
+ expires = ktime_add_ns(ktime_get(),
+ head.svh_rest_us * 1000);
+ set_current_state(TASK_KILLABLE);
+ schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+ }
+
+ if (fatal_signal_pending(current)) {
+ error = -EINTR;
+ goto out_free;
+ }
+ }
+
+ if (copy_to_user(uvectors, vectors, vec_bytes) ||
+ copy_to_user(uhead, &head, sizeof(head))) {
+ error = -EFAULT;
+ goto out_free;
+ }
+
+out_free:
+ if (handle_ip)
+ xfs_irele(handle_ip);
+ kfree(vectors);
+ return error;
+}
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-30 06:52:43 +0300