xfs: hook live realtime rmap operations during a repair operation

Hook the regular realtime rmap code when an rtrmapbt repair operation is
running so that we can unlock the AGF buffer to scan the filesystem and
keep the in-memory btree up to date during the scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index 709b31137153eadab3b921c0e34d0f5db490f4d2..e05e1d63622b832cfd3dd5faa9a9be85c57919ea 100644 (file)
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -1587,7 +1587,7 @@ xrep_rmapbt_live_update(
        if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo))
                goto out_unlock;
 
-       trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p);
+       trace_xrep_rmap_live_update(&rr->sc->sa.pag->pag_group, action, p);
 
        error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
        if (error)

diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c
index 49f39fba60b757a36b824f025be6c19388f880f5..22f2a5fe5786c679e954634b1d60b39cf686f8d1 100644 (file)
--- a/fs/xfs/scrub/rtrmap_repair.c
+++ b/fs/xfs/scrub/rtrmap_repair.c
@@ -71,6 +71,9 @@ struct xrep_rtrmap {
        /* new rtrmapbt information */
        struct xrep_newbt       new_btree;
 
+       /* lock for the xfbtree and xfile */
+       struct mutex            lock;
+
        /* rmap records generated from primary metadata */
        struct xfbtree          rtrmap_btree;
 
@@ -79,6 +82,9 @@ struct xrep_rtrmap {
        /* bitmap of old rtrmapbt blocks */
        struct xfsb_bitmap      old_rtrmapbt_blocks;
 
+       /* Hooks into rtrmap update code. */
+       struct xfs_rmap_hook    rhook;
+
        /* inode scan cursor */
        struct xchk_iscan       iscan;
 
@@ -98,6 +104,8 @@ xrep_setup_rtrmapbt(
        char                    *descr;
        int                     error;
 
+       xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP);
+
        descr = xchk_xfile_rtgroup_descr(sc, "reverse mapping records");
        error = xrep_setup_xfbtree(sc, descr);
        kfree(descr);
@@ -151,19 +159,31 @@ xrep_rtrmap_stash(
        if (xchk_should_terminate(sc, &error))
                return error;
 
+       if (xchk_iscan_aborted(&rr->iscan))
+               return -EFSCORRUPTED;
+
        trace_xrep_rtrmap_found(sc->mp, &rmap);
 
        /* Add entry to in-memory btree. */
+       mutex_lock(&rr->lock);
        mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, sc->tp, &rr->rtrmap_btree);
        error = xfs_rmap_map_raw(mcur, &rmap);
        xfs_btree_del_cursor(mcur, error);
        if (error)
                goto out_cancel;
 
-       return xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp);
+       error = xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp);
+       if (error)
+               goto out_abort;
+
+       mutex_unlock(&rr->lock);
+       return 0;
 
 out_cancel:
        xfbtree_trans_cancel(&rr->rtrmap_btree, sc->tp);
+out_abort:
+       xchk_iscan_abort(&rr->iscan);
+       mutex_unlock(&rr->lock);
        return error;
 }
 
@@ -486,6 +506,13 @@ xrep_rtrmap_find_rmaps(
        if (error)
                return error;
 
+       /*
+        * If a hook failed to update the in-memory btree, we lack the data to
+        * continue the repair.
+        */
+       if (xchk_iscan_aborted(&rr->iscan))
+               return -EFSCORRUPTED;
+
        /* Scan for old rtrmap blocks. */
        while ((pag = xfs_perag_next(sc->mp, pag))) {
                error = xrep_rtrmap_scan_ag(rr, pag);
@@ -704,6 +731,83 @@ xrep_rtrmap_remove_old_tree(
        return xrep_reset_metafile_resv(rr->sc);
 }
 
+static inline bool
+xrep_rtrmapbt_want_live_update(
+       struct xchk_iscan               *iscan,
+       const struct xfs_owner_info     *oi)
+{
+       if (xchk_iscan_aborted(iscan))
+               return false;
+
+       /*
+        * We scanned the CoW staging extents before we started the iscan, so
+        * we need all the updates.
+        */
+       if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner))
+               return true;
+
+       /* Ignore updates to files that the scanner hasn't visited yet. */
+       return xchk_iscan_want_live_update(iscan, oi->oi_owner);
+}
+
+/*
+ * Apply a rtrmapbt update from the regular filesystem into our shadow btree.
+ * We're running from the thread that owns the rtrmap ILOCK and is generating
+ * the update, so we must be careful about which parts of the struct
+ * xrep_rtrmap that we change.
+ */
+static int
+xrep_rtrmapbt_live_update(
+       struct notifier_block           *nb,
+       unsigned long                   action,
+       void                            *data)
+{
+       struct xfs_rmap_update_params   *p = data;
+       struct xrep_rtrmap              *rr;
+       struct xfs_mount                *mp;
+       struct xfs_btree_cur            *mcur;
+       struct xfs_trans                *tp;
+       void                            *txcookie;
+       int                             error;
+
+       rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb);
+       mp = rr->sc->mp;
+
+       if (!xrep_rtrmapbt_want_live_update(&rr->iscan, &p->oinfo))
+               goto out_unlock;
+
+       trace_xrep_rmap_live_update(&rr->sc->sr.rtg->rtg_group, action, p);
+
+       error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
+       if (error)
+               goto out_abort;
+
+       mutex_lock(&rr->lock);
+       mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree);
+       error = __xfs_rmap_finish_intent(mcur, action, p->startblock,
+                       p->blockcount, &p->oinfo, p->unwritten);
+       xfs_btree_del_cursor(mcur, error);
+       if (error)
+               goto out_cancel;
+
+       error = xfbtree_trans_commit(&rr->rtrmap_btree, tp);
+       if (error)
+               goto out_cancel;
+
+       xrep_trans_cancel_hook_dummy(&txcookie, tp);
+       mutex_unlock(&rr->lock);
+       return NOTIFY_DONE;
+
+out_cancel:
+       xfbtree_trans_cancel(&rr->rtrmap_btree, tp);
+       xrep_trans_cancel_hook_dummy(&txcookie, tp);
+out_abort:
+       xchk_iscan_abort(&rr->iscan);
+       mutex_unlock(&rr->lock);
+out_unlock:
+       return NOTIFY_DONE;
+}
+
 /* Set up the filesystem scan components. */
 STATIC int
 xrep_rtrmap_setup_scan(
@@ -712,6 +816,7 @@ xrep_rtrmap_setup_scan(
        struct xfs_scrub        *sc = rr->sc;
        int                     error;
 
+       mutex_init(&rr->lock);
        xfsb_bitmap_init(&rr->old_rtrmapbt_blocks);
 
        /* Set up some storage */
@@ -722,10 +827,26 @@ xrep_rtrmap_setup_scan(
 
        /* Retry iget every tenth of a second for up to 30 seconds. */
        xchk_iscan_start(sc, 30000, 100, &rr->iscan);
+
+       /*
+        * Hook into live rtrmap operations so that we can update our in-memory
+        * btree to reflect live changes on the filesystem.  Since we drop the
+        * rtrmap ILOCK to scan all the inodes, we need this piece to avoid
+        * installing a stale btree.
+        */
+       ASSERT(sc->flags & XCHK_FSGATES_RMAP);
+       xfs_rmap_hook_setup(&rr->rhook, xrep_rtrmapbt_live_update);
+       error = xfs_rmap_hook_add(&sc->sr.rtg->rtg_group, &rr->rhook);
+       if (error)
+               goto out_iscan;
        return 0;
 
+out_iscan:
+       xchk_iscan_teardown(&rr->iscan);
+       xfbtree_destroy(&rr->rtrmap_btree);
 out_bitmap:
        xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks);
+       mutex_destroy(&rr->lock);
        return error;
 }
 
@@ -734,9 +855,14 @@ STATIC void
 xrep_rtrmap_teardown(
        struct xrep_rtrmap      *rr)
 {
+       struct xfs_scrub        *sc = rr->sc;
+
+       xchk_iscan_abort(&rr->iscan);
+       xfs_rmap_hook_del(&sc->sr.rtg->rtg_group, &rr->rhook);
        xchk_iscan_teardown(&rr->iscan);
        xfbtree_destroy(&rr->rtrmap_btree);
        xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks);
+       mutex_destroy(&rr->lock);
 }
 
 /* Repair the realtime rmap btree. */
@@ -747,9 +873,6 @@ xrep_rtrmapbt(
        struct xrep_rtrmap      *rr = sc->buf;
        int                     error;
 
-       /* Functionality is not yet complete. */
-       return xrep_notsupported(sc);
-
        /* Make sure any problems with the fork are fixed. */
        error = xrep_metadata_inode_forks(sc);
        if (error)

diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 3f2a8695ef5cb5b39a763e555d8272e56b6ffa97..d1eb3bedd257931f226b07891ab7db4c85d25c67 100644 (file)
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -41,6 +41,9 @@ struct xchk_dirtree_outcomes;
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
 
+TRACE_DEFINE_ENUM(XG_TYPE_AG);
+TRACE_DEFINE_ENUM(XG_TYPE_RTG);
+
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF);
@@ -2709,11 +2712,12 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode);
 DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode);
 
 TRACE_EVENT(xrep_rmap_live_update,
-       TP_PROTO(const struct xfs_perag *pag, unsigned int op,
+       TP_PROTO(const struct xfs_group *xg, unsigned int op,
                 const struct xfs_rmap_update_params *p),
-       TP_ARGS(pag, op, p),
+       TP_ARGS(xg, op, p),
        TP_STRUCT__entry(
                __field(dev_t, dev)
+               __field(enum xfs_group_type, type)
                __field(xfs_agnumber_t, agno)
                __field(unsigned int, op)
                __field(xfs_agblock_t, agbno)
@@ -2723,8 +2727,9 @@ TRACE_EVENT(xrep_rmap_live_update,
                __field(unsigned int, flags)
        ),
        TP_fast_assign(
-               __entry->dev = pag_mount(pag)->m_super->s_dev;
-               __entry->agno = pag_agno(pag);
+               __entry->dev = xg->xg_mount->m_super->s_dev;
+               __entry->type = xg->xg_type;
+               __entry->agno = xg->xg_index;
                __entry->op = op;
                __entry->agbno = p->startblock;
                __entry->len = p->blockcount;
@@ -2733,10 +2738,12 @@ TRACE_EVENT(xrep_rmap_live_update,
                if (p->unwritten)
                        __entry->flags |= XFS_RMAP_UNWRITTEN;
        ),
-       TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+       TP_printk("dev %d:%d %sno 0x%x op %d %sbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                 __print_symbolic(__entry->type, XG_TYPE_STRINGS),
                  __entry->agno,
                  __entry->op,
+                 __print_symbolic(__entry->type, XG_TYPE_STRINGS),
                  __entry->agbno,
                  __entry->len,
                  __entry->owner,