[21/41] xfs_scrub: re-run metafile scrubbers during phase 5

Commit Message

Darrick J. Wong Dec. 23, 2024, 9:51 p.m. UTC

From: Darrick J. Wong <[e-mail]>

For metadata files on a metadir filesystem, re-run the scrubbers during
phase 5 to ensure that the metadata files are still connected.

Signed-off-by: "Darrick J. Wong" <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
---
 scrub/phase5.c |   97 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 scrub/scrub.h  |    7 ++++
 2 files changed, 103 insertions(+), 1 deletion(-)

Patch

diff --git a/scrub/phase5.c b/scrub/phase5.c
index 69b1cae5c5e2c0..4d0a76a529b55d 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -745,6 +745,87 @@  run_kernel_fs_scan_scrubbers(
 	return ret;
 }
 
+/* Queue one metapath scrubber. */
+static int
+queue_metapath_scan(
+	struct workqueue	*wq,
+	bool			*abortedp,
+	uint64_t		type)
+{
+	struct fs_scan_item	*item;
+	struct scrub_ctx	*ctx = wq->wq_ctx;
+	int			ret;
+
+	item = malloc(sizeof(struct fs_scan_item));
+	if (!item) {
+		ret = ENOMEM;
+		str_liberror(ctx, ret, _("setting up metapath scan"));
+		return ret;
+	}
+	scrub_item_init_metapath(&item->sri, type);
+	scrub_item_schedule(&item->sri, XFS_SCRUB_TYPE_METAPATH);
+	item->abortedp = abortedp;
+
+	ret = -workqueue_add(wq, fs_scan_worker, 0, item);
+	if (ret)
+		str_liberror(ctx, ret, _("queuing metapath scan work"));
+
+	return ret;
+}
+
+/*
+ * Scrub metadata directory file paths to ensure that fs metadata are still
+ * connected where the fs needs to find them.
+ */
+static int
+run_kernel_metadir_path_scrubbers(
+	struct scrub_ctx	*ctx)
+{
+	struct workqueue	wq;
+	const struct xfrog_scrub_descr	*sc;
+	uint64_t		type;
+	unsigned int		nr_threads = scrub_nproc_workqueue(ctx);
+	bool			aborted = false;
+	int			ret, ret2;
+
+	ret = -workqueue_create(&wq, (struct xfs_mount *)ctx, nr_threads);
+	if (ret) {
+		str_liberror(ctx, ret, _("setting up metapath scan workqueue"));
+		return ret;
+	}
+
+	/*
+	 * Scan all the metadata files in parallel if metadata directories
+	 * are enabled, because the phase 3 scrubbers might have taken out
+	 * parts of the metadir tree.
+	 */
+	for (type = 0; type < XFS_SCRUB_METAPATH_NR; type++) {
+		sc = &xfrog_metapaths[type];
+		if (sc->group != XFROG_SCRUB_GROUP_FS)
+			continue;
+
+		ret = queue_metapath_scan(&wq, &aborted, type);
+		if (ret) {
+			str_liberror(ctx, ret,
+ _("queueing metapath scrub work"));
+			goto wait;
+		}
+	}
+
+wait:
+	ret2 = -workqueue_terminate(&wq);
+	if (ret2) {
+		str_liberror(ctx, ret2, _("joining metapath scan workqueue"));
+		if (!ret)
+			ret = ret2;
+	}
+	if (aborted && !ret)
+		ret = ECANCELED;
+
+	workqueue_destroy(&wq);
+	return ret;
+}
+
 /* Check directory connectivity. */
 int
 phase5_func(
@@ -753,6 +834,16 @@  phase5_func(
 	struct ncheck_state	ncs = { .ctx = ctx };
 	int			ret;
 
+	/*
+	 * Make sure metadata files are still connected to the metadata
+	 * directory tree now that phase 3 pruned all corrupt directory tree
+	 * links.
+	 */
+	if (ctx->mnt.fsgeom.flags & XFS_FSOP_GEOM_FLAGS_METADIR) {
+		ret = run_kernel_metadir_path_scrubbers(ctx);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * Check and fix anything that requires a full filesystem scan.  We do
@@ -805,8 +896,12 @@  phase5_estimate(
 	unsigned int		*nr_threads,
 	int			*rshift)
 {
+	unsigned int		scans = 2;
+
 	*items = scrub_estimate_iscan_work(ctx);
-	*nr_threads = scrub_nproc(ctx) * 2;
+	if (ctx->mnt.fsgeom.flags & XFS_FSOP_GEOM_FLAGS_METADIR)
+		scans++;
+	*nr_threads = scrub_nproc(ctx) * scans;
 	*rshift = 0;
 	return 0;
 }
diff --git a/scrub/scrub.h b/scrub/scrub.h
index c3eed1b261d511..3bb3ea1d07bf40 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -108,6 +108,13 @@  scrub_item_init_file(struct scrub_item *sri, const struct xfs_bulkstat *bstat)
 	sri->sri_gen = bstat->bs_gen;
 }
 
+static inline void
+scrub_item_init_metapath(struct scrub_item *sri, uint64_t metapath)
+{
+	memset(sri, 0, sizeof(*sri));
+	sri->sri_ino = metapath;
+}
+
 void scrub_item_dump(struct scrub_item *sri, unsigned int group_mask,
 		const char *tag);