[PATCH] f2fs: handle nat.blkaddr corruption in f2fs_get_node_info()

[Chao Yu]

F2FS-fs (dm-55): access invalid blkaddr:972878540
Call trace:
 dump_backtrace+0xec/0x128
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0x88
 dump_stack+0x18/0x24
 __f2fs_is_valid_blkaddr+0x360/0x3b4
 f2fs_is_valid_blkaddr+0x10/0x20
 f2fs_get_node_info+0x21c/0x60c
 __write_node_page+0x15c/0x734
 f2fs_sync_node_pages+0x4f8/0x700
 f2fs_write_checkpoint+0x4a8/0x99c
 __checkpoint_and_complete_reqs+0x7c/0x20c
 issue_checkpoint_thread+0x4c/0xd8
 kthread+0x11c/0x1b0
 ret_from_fork+0x10/0x20

If nat.blkaddr is corrupted, during checkpoint, f2fs_sync_node_pages()
will loop to flush node page w/ corrupted nat.blkaddr.

Although, it tags SBI_NEED_FSCK, checkpoint can not persist it due
to deadloop.

Let's call f2fs_handle_error(, ERROR_INCONSISTENT_NAT) to record such
error into superblock, it expects fsck can detect the error and repair
inconsistent nat.blkaddr after device reboot.

Note that, let's add sanity check in f2fs_get_node_info() to detect
in-memory nat.blkaddr inconsistency, but only if CONFIG_F2FS_CHECK_FS
is enabled.

Signed-off-by: Chao Yu <chao@xxxxxxxxxx>
---
 fs/f2fs/node.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 8b5cd764226a..519c4c114607 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -555,8 +555,8 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	struct f2fs_nat_entry ne;
 	struct nat_entry *e;
 	pgoff_t index;
-	block_t blkaddr;
 	int i;
+	bool need_cache = true;
 
 	ni->flag = 0;
 	ni->nid = nid;
@@ -569,6 +569,10 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
 		f2fs_up_read(&nm_i->nat_tree_lock);
+		if (IS_ENABLED(CONFIG_F2FS_CHECK_FS)) {
+			need_cache = false;
+			goto sanity_check;
+		}
 		return 0;
 	}
 
@@ -594,7 +598,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	up_read(&curseg->journal_rwsem);
 	if (i >= 0) {
 		f2fs_up_read(&nm_i->nat_tree_lock);
-		goto cache;
+		goto sanity_check;
 	}
 
 	/* Fill node_info from nat page */
@@ -609,14 +613,23 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	ne = nat_blk->entries[nid - start_nid];
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_folio_put(folio, true);
-cache:
-	blkaddr = le32_to_cpu(ne.block_addr);
-	if (__is_valid_data_blkaddr(blkaddr) &&
-		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE))
-		return -EFAULT;
+sanity_check:
+	if (__is_valid_data_blkaddr(ni->blk_addr) &&
+		!f2fs_is_valid_blkaddr(sbi, ni->blk_addr,
+					DATA_GENERIC_ENHANCE)) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_err_ratelimited(sbi,
+			"f2fs_get_node_info of %pS: inconsistent nat entry, "
+			"ino:%u, nid:%u, blkaddr:%u, ver:%u, flag:%u",
+			__builtin_return_address(0),
+			ni->ino, ni->nid, ni->blk_addr, ni->version, ni->flag);
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT);
+		return -EFSCORRUPTED;
+	}
 
 	/* cache nat entry */
-	cache_nat_entry(sbi, nid, &ne);
+	if (need_cache)
+		cache_nat_entry(sbi, nid, &ne);
 	return 0;
 }
 
-- 
2.49.0