Merge tag 'repair-rmap-btree-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.9-mergeC

xfs: online repair of rmap btrees

We have now constructed the four tools that we need to scan the
filesystem looking for reverse mappings: an inode scanner, hooks to
receive live updates from other writer threads, the ability to construct
btrees in memory, and a btree bulk loader.

This series glues those three together, enabling us to scan the
filesystem for mappings and keep it up to date while other writers run,
and then commit the new btree to disk atomically.

To reduce the size of each patch, the functionality is left disabled
until the end of the series and broken up into three patches: one to
create the mechanics of scanning the filesystem, a second to transition
to in-memory btrees, and a third to set up the live hooks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

* tag 'repair-rmap-btree-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: hook live rmap operations during a repair operation
  xfs: create a shadow rmap btree during rmap repair
  xfs: repair the rmapbt
  xfs: create agblock bitmap helper to count the number of set regions
  xfs: create a helper to decide if a file mapping targets the rt volume

Author: Chandan Babu R

fs/xfs/Makefile

@@ -201,6 +201,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
+				   rmap_repair.o \
 				   )
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \

fs/xfs/libxfs/xfs_ag.c

@@ -417,6 +417,7 @@ xfs_initialize_perag(
 		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
+		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
 
 		error = xfs_buf_cache_init(&pag->pag_bcache);

fs/xfs/libxfs/xfs_ag.h

@@ -90,6 +90,7 @@ struct xfs_perag {
 	uint8_t		pagf_repair_bno_level;
 	uint8_t		pagf_repair_cnt_level;
 	uint8_t		pagf_repair_refcount_level;
+	uint8_t		pagf_repair_rmap_level;
 #endif
 
 	spinlock_t	pag_state_lock;
@@ -119,6 +120,9 @@ struct xfs_perag {
 	 * inconsistencies.
 	 */
 	struct xfs_defer_drain	pag_intents_drain;
+
+	/* Hook to feed rmapbt updates to an active online repair. */
+	struct xfs_hooks	pag_rmap_update_hooks;
 #endif /* __KERNEL__ */
 };
 

fs/xfs/libxfs/xfs_bmap.c

@@ -4913,7 +4913,7 @@ xfs_bmap_del_extent_delay(
 
 	XFS_STATS_INC(mp, xs_del_exlist);
 
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	del_endoff = del->br_startoff + del->br_blockcount;
 	got_endoff = got->br_startoff + got->br_blockcount;
 	da_old = startblockval(got->br_startblock);
@@ -5149,7 +5149,7 @@ xfs_bmap_del_extent_real(
 		return -ENOSPC;
 
 	*logflagsp = XFS_ILOG_CORE;
-	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
+	if (xfs_ifork_is_realtime(ip, whichfork)) {
 		if (!(bflags & XFS_BMAPI_REMAP)) {
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);
@@ -5396,7 +5396,7 @@ __xfs_bunmapi(
 		return 0;
 	}
 	XFS_STATS_INC(mp, xs_blk_unmap);
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	end = start + len;
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) {
@@ -6379,3 +6379,46 @@ xfs_bunmapi_range(
 out:
 	return error;
 }
+
+struct xfs_bmap_query_range {
+	xfs_bmap_query_range_fn	fn;
+	void			*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_bmap_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	*query = priv;
+	struct xfs_bmbt_irec		irec;
+	xfs_failaddr_t			fa;
+
+	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
+	fa = xfs_bmap_validate_extent(cur->bc_ino.ip, cur->bc_ino.whichfork,
+			&irec);
+	if (fa) {
+		xfs_btree_mark_sick(cur);
+		return xfs_bmap_complain_bad_rec(cur->bc_ino.ip,
+				cur->bc_ino.whichfork, fa, &irec);
+	}
+
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all bmaps. */
+int
+xfs_bmap_query_all(
+	struct xfs_btree_cur		*cur,
+	xfs_bmap_query_range_fn		fn,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	query = {
+		.priv			= priv,
+		.fn			= fn,
+	};
+
+	return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
+}

fs/xfs/libxfs/xfs_bmap.h

@@ -280,4 +280,12 @@ extern struct kmem_cache	*xfs_bmap_intent_cache;
 int __init xfs_bmap_intent_init_cache(void);
 void xfs_bmap_intent_destroy_cache(void);
 
+typedef int (*xfs_bmap_query_range_fn)(
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*rec,
+	void			*priv);
+
+int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
+		void *priv);
+
 #endif	/* __XFS_BMAP_H__ */

fs/xfs/libxfs/xfs_inode_fork.c

@@ -813,3 +813,12 @@ xfs_iext_count_upgrade(
 
 	return 0;
 }
+
+/* Decide if a file mapping is on the realtime device or not. */
+bool
+xfs_ifork_is_realtime(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	return XFS_IS_REALTIME_INODE(ip) && whichfork != XFS_ATTR_FORK;
+}

fs/xfs/libxfs/xfs_inode_fork.h

@@ -260,6 +260,7 @@ int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
 int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
 		uint nr_to_add);
+bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork);
 
 /* returns true if the fork has extents but they are not read in yet. */
 static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp)