1 files changed, 80 insertions, 106 deletions

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index dedba481b66d..7c2787829369 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -20,7 +20,7 @@
 #include "iostat.h"
 #include <trace/events/f2fs.h>
 
-#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
+#define on_f2fs_build_free_nids(nm_i) mutex_is_locked(&(nm_i)->build_lock)
 
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
@@ -123,7 +123,7 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 static void clear_node_page_dirty(struct page *page)
 {
 	if (PageDirty(page)) {
-		f2fs_clear_page_cache_dirty_tag(page);
+		f2fs_clear_page_cache_dirty_tag(page_folio(page));
 		clear_page_dirty_for_io(page);
 		dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
 	}
@@ -633,7 +633,7 @@ static void f2fs_ra_node_pages(struct page *parent, int start, int n)
 
 	/* Then, try readahead for siblings of the desired node */
 	end = start + n;
-	end = min(end, NIDS_PER_BLOCK);
+	end = min(end, (int)NIDS_PER_BLOCK);
 	for (i = start; i < end; i++) {
 		nid = get_nid(parent, i, false);
 		f2fs_ra_node_page(sbi, nid);
@@ -799,6 +799,16 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	for (i = 1; i <= level; i++) {
 		bool done = false;
 
+		if (nids[i] && nids[i] == dn->inode->i_ino) {
+			err = -EFSCORRUPTED;
+			f2fs_err_ratelimited(sbi,
+				"inode mapping table is corrupted, run fsck to fix it, "
+				"ino:%lu, nid:%u, level:%d, offset:%d",
+				dn->inode->i_ino, nids[i], level, offset[level]);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			goto release_pages;
+		}
+
 		if (!nids[i] && mode == ALLOC_NODE) {
 			/* alloc new node */
 			if (!f2fs_alloc_nid(sbi, &(nids[i]))) {
@@ -929,7 +939,7 @@ static int truncate_node(struct dnode_of_data *dn)
 	clear_node_page_dirty(dn->node_page);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
-	index = dn->node_page->index;
+	index = page_folio(dn->node_page)->index;
 	f2fs_put_page(dn->node_page, 1);
 
 	invalidate_mapping_pages(NODE_MAPPING(sbi),
@@ -1134,7 +1144,14 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
 	level = get_node_path(inode, from, offset, noffset);
-	if (level < 0) {
+	if (level <= 0) {
+		if (!level) {
+			level = -EFSCORRUPTED;
+			f2fs_err(sbi, "%s: inode ino=%lx has corrupted node block, from:%lu addrs:%u",
+					__func__, inode->i_ino,
+					from, ADDRS_PER_INODE(inode));
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		}
 		trace_f2fs_truncate_inode_blocks_exit(inode, level);
 		return level;
 	}
@@ -1197,7 +1214,17 @@ skip_partial:
 		default:
 			BUG();
 		}
-		if (err < 0 && err != -ENOENT)
+		if (err == -ENOENT) {
+			set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+			f2fs_err_ratelimited(sbi,
+				"truncate node fail, ino:%lu, nid:%u, "
+				"offset[0]:%d, offset[1]:%d, nofs:%d",
+				inode->i_ino, dn.nid, offset[0],
+				offset[1], nofs);
+			err = 0;
+		}
+		if (err < 0)
 			goto fail;
 		if (offset[1] == 0 &&
 				ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
@@ -1374,6 +1401,7 @@ fail:
  */
 static int read_node_page(struct page *page, blk_opf_t op_flags)
 {
+	struct folio *folio = page_folio(page);
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
 	struct f2fs_io_info fio = {
@@ -1386,21 +1414,21 @@ static int read_node_page(struct page *page, blk_opf_t op_flags)
 	};
 	int err;
 
-	if (PageUptodate(page)) {
+	if (folio_test_uptodate(folio)) {
 		if (!f2fs_inode_chksum_verify(sbi, page)) {
-			ClearPageUptodate(page);
+			folio_clear_uptodate(folio);
 			return -EFSBADCRC;
 		}
 		return LOCKED_PAGE;
 	}
 
-	err = f2fs_get_node_info(sbi, page->index, &ni, false);
+	err = f2fs_get_node_info(sbi, folio->index, &ni, false);
 	if (err)
 		return err;
 
 	/* NEW_ADDR can be seen, after cp_error drops some dirty node pages */
 	if (unlikely(ni.blk_addr == NULL_ADDR || ni.blk_addr == NEW_ADDR)) {
-		ClearPageUptodate(page);
+		folio_clear_uptodate(folio);
 		return -ENOENT;
 	}
 
@@ -1497,7 +1525,7 @@ out_err:
 out_put_err:
 	/* ENOENT comes from read_node_page which is not an error. */
 	if (err != -ENOENT)
-		f2fs_handle_page_eio(sbi, page->index, NODE);
+		f2fs_handle_page_eio(sbi, page_folio(page), NODE);
 	f2fs_put_page(page, 1);
 	return ERR_PTR(err);
 }
@@ -1540,7 +1568,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 	if (!clear_page_dirty_for_io(page))
 		goto page_out;
 
-	ret = f2fs_write_inline_data(inode, page);
+	ret = f2fs_write_inline_data(inode, page_folio(page));
 	inode_dec_dirty_pages(inode);
 	f2fs_remove_dirty_inode(inode);
 	if (ret)
@@ -1613,6 +1641,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 				enum iostat_type io_type, unsigned int *seq_id)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	struct folio *folio = page_folio(page);
 	nid_t nid;
 	struct node_info ni;
 	struct f2fs_io_info fio = {
@@ -1629,15 +1658,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	};
 	unsigned int seq;
 
-	trace_f2fs_writepage(page, NODE);
+	trace_f2fs_writepage(folio, NODE);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		/* keep node pages in remount-ro mode */
 		if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
 			goto redirty_out;
-		ClearPageUptodate(page);
+		folio_clear_uptodate(folio);
 		dec_page_count(sbi, F2FS_DIRTY_NODES);
-		unlock_page(page);
+		folio_unlock(folio);
 		return 0;
 	}
 
@@ -1651,7 +1680,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
-	f2fs_bug_on(sbi, page->index != nid);
+	f2fs_bug_on(sbi, folio->index != nid);
 
 	if (f2fs_get_node_info(sbi, nid, &ni, !do_balance))
 		goto redirty_out;
@@ -1665,10 +1694,10 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 
 	/* This page is already truncated */
 	if (unlikely(ni.blk_addr == NULL_ADDR)) {
-		ClearPageUptodate(page);
+		folio_clear_uptodate(folio);
 		dec_page_count(sbi, F2FS_DIRTY_NODES);
 		f2fs_up_read(&sbi->node_write);
-		unlock_page(page);
+		folio_unlock(folio);
 		return 0;
 	}
 
@@ -1679,7 +1708,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		goto redirty_out;
 	}
 
-	if (atomic && !test_opt(sbi, NOBARRIER) && !f2fs_sb_has_blkzoned(sbi))
+	if (atomic && !test_opt(sbi, NOBARRIER))
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 
 	/* should add to global list before clearing PAGECACHE status */
@@ -1689,7 +1718,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 			*seq_id = seq;
 	}
 
-	set_page_writeback(page);
+	folio_start_writeback(folio);
 
 	fio.old_blkaddr = ni.blk_addr;
 	f2fs_do_write_node_page(nid, &fio);
@@ -1702,7 +1731,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		submitted = NULL;
 	}
 
-	unlock_page(page);
+	folio_unlock(folio);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_submit_merged_write(sbi, NODE);
@@ -1716,7 +1745,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	return 0;
 
 redirty_out:
-	redirty_page_for_writepage(wbc, page);
+	folio_redirty_for_writepage(wbc, folio);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -1748,7 +1777,7 @@ int f2fs_move_node_page(struct page *node_page, int gc_type)
 		goto release_page;
 	} else {
 		/* set page dirty and write it */
-		if (!PageWriteback(node_page))
+		if (!folio_test_writeback(page_folio(node_page)))
 			set_page_dirty(node_page);
 	}
 out_page:
@@ -1872,7 +1901,7 @@ continue_unlock:
 	}
 	if (!ret && atomic && !marked) {
 		f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx",
-			   ino, last_page->index);
+			   ino, page_folio(last_page)->index);
 		lock_page(last_page);
 		f2fs_wait_on_page_writeback(last_page, NODE, true, true);
 		set_page_dirty(last_page);
@@ -1942,7 +1971,7 @@ void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
 		for (i = 0; i < nr_folios; i++) {
 			struct page *page = &fbatch.folios[i]->page;
 
-			if (!IS_DNODE(page))
+			if (!IS_INODE(page))
 				continue;
 
 			lock_page(page);
@@ -2176,7 +2205,7 @@ skip_write:
 static bool f2fs_dirty_node_folio(struct address_space *mapping,
 		struct folio *folio)
 {
-	trace_f2fs_set_page_dirty(&folio->page, NODE);
+	trace_f2fs_set_page_dirty(folio, NODE);
 
 	if (!folio_test_uptodate(folio))
 		folio_mark_uptodate(folio);
@@ -2258,24 +2287,6 @@ static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i,
 	}
 }
 
-bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned int i;
-	bool ret = true;
-
-	f2fs_down_read(&nm_i->nat_tree_lock);
-	for (i = 0; i < nm_i->nat_blocks; i++) {
-		if (!test_bit_le(i, nm_i->nat_block_bitmap)) {
-			ret = false;
-			break;
-		}
-	}
-	f2fs_up_read(&nm_i->nat_tree_lock);
-
-	return ret;
-}
-
 static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
 							bool set, bool build)
 {
@@ -2954,23 +2965,7 @@ add_out:
 	list_add_tail(&nes->set_list, head);
 }
 
-static void __update_nat_bits(struct f2fs_nm_info *nm_i, unsigned int nat_ofs,
-							unsigned int valid)
-{
-	if (valid == 0) {
-		__set_bit_le(nat_ofs, nm_i->empty_nat_bits);
-		__clear_bit_le(nat_ofs, nm_i->full_nat_bits);
-		return;
-	}
-
-	__clear_bit_le(nat_ofs, nm_i->empty_nat_bits);
-	if (valid == NAT_ENTRY_PER_BLOCK)
-		__set_bit_le(nat_ofs, nm_i->full_nat_bits);
-	else
-		__clear_bit_le(nat_ofs, nm_i->full_nat_bits);
-}
-
-static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 						struct page *page)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2979,7 +2974,7 @@ static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 	int valid = 0;
 	int i = 0;
 
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+	if (!enabled_nat_bits(sbi, NULL))
 		return;
 
 	if (nat_index == 0) {
@@ -2990,36 +2985,17 @@ static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 		if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR)
 			valid++;
 	}
-
-	__update_nat_bits(nm_i, nat_index, valid);
-}
-
-void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned int nat_ofs;
-
-	f2fs_down_read(&nm_i->nat_tree_lock);
-
-	for (nat_ofs = 0; nat_ofs < nm_i->nat_blocks; nat_ofs++) {
-		unsigned int valid = 0, nid_ofs = 0;
-
-		/* handle nid zero due to it should never be used */
-		if (unlikely(nat_ofs == 0)) {
-			valid = 1;
-			nid_ofs = 1;
-		}
-
-		for (; nid_ofs < NAT_ENTRY_PER_BLOCK; nid_ofs++) {
-			if (!test_bit_le(nid_ofs,
-					nm_i->free_nid_bitmap[nat_ofs]))
-				valid++;
-		}
-
-		__update_nat_bits(nm_i, nat_ofs, valid);
+	if (valid == 0) {
+		__set_bit_le(nat_index, nm_i->empty_nat_bits);
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
+		return;
 	}
 
-	f2fs_up_read(&nm_i->nat_tree_lock);
+	__clear_bit_le(nat_index, nm_i->empty_nat_bits);
+	if (valid == NAT_ENTRY_PER_BLOCK)
+		__set_bit_le(nat_index, nm_i->full_nat_bits);
+	else
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
 }
 
 static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
@@ -3038,7 +3014,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if ((cpc->reason & CP_UMOUNT) ||
+	if (enabled_nat_bits(sbi, cpc) ||
 		!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
@@ -3085,7 +3061,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	if (to_journal) {
 		up_write(&curseg->journal_rwsem);
 	} else {
-		update_nat_bits(sbi, start_nid, page);
+		__update_nat_bits(sbi, start_nid, page);
 		f2fs_put_page(page, 1);
 	}
 
@@ -3116,7 +3092,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * during unmount, let's flush nat_bits before checking
 	 * nat_cnt[DIRTY_NAT].
 	 */
-	if (cpc->reason & CP_UMOUNT) {
+	if (enabled_nat_bits(sbi, cpc)) {
 		f2fs_down_write(&nm_i->nat_tree_lock);
 		remove_nats_in_journal(sbi);
 		f2fs_up_write(&nm_i->nat_tree_lock);
@@ -3132,7 +3108,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (cpc->reason & CP_UMOUNT ||
+	if (enabled_nat_bits(sbi, cpc) ||
 		!__has_cursum_space(journal,
 			nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
@@ -3169,18 +3145,15 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 	__u64 cp_ver = cur_cp_version(ckpt);
 	block_t nat_bits_addr;
 
+	if (!enabled_nat_bits(sbi, NULL))
+		return 0;
+
 	nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
 	nm_i->nat_bits = f2fs_kvzalloc(sbi,
-			nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
+			F2FS_BLK_TO_BYTES(nm_i->nat_bits_blocks), GFP_KERNEL);
 	if (!nm_i->nat_bits)
 		return -ENOMEM;
 
-	nm_i->full_nat_bits = nm_i->nat_bits + 8;
-	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
-
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
-		return 0;
-
 	nat_bits_addr = __start_cp_addr(sbi) + BLKS_PER_SEG(sbi) -
 						nm_i->nat_bits_blocks;
 	for (i = 0; i < nm_i->nat_bits_blocks; i++) {
@@ -3190,19 +3163,20 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
-		memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+		memcpy(nm_i->nat_bits + F2FS_BLK_TO_BYTES(i),
 					page_address(page), F2FS_BLKSIZE);
 		f2fs_put_page(page, 1);
 	}
 
 	cp_ver |= (cur_cp_crc(ckpt) << 32);
 	if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
-		clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
-		f2fs_notice(sbi, "Disable nat_bits due to incorrect cp_ver (%llu, %llu)",
-			cp_ver, le64_to_cpu(*(__le64 *)nm_i->nat_bits));
+		disable_nat_bits(sbi, true);
 		return 0;
 	}
 
+	nm_i->full_nat_bits = nm_i->nat_bits + 8;
+	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
+
 	f2fs_notice(sbi, "Found nat_bits in checkpoint");
 	return 0;
 }
@@ -3213,7 +3187,7 @@ static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
 	unsigned int i = 0;
 	nid_t nid, last_nid;
 
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+	if (!enabled_nat_bits(sbi, NULL))
 		return;
 
 	for (i = 0; i < nm_i->nat_blocks; i++) {