Merge tag 'f2fs-for-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "Another round of various bug fixes came in. Damien improved SMR drive
  support a bit, and Chao replaced BUG_ON() with reporting errors to
  user since we've not hit from users but did hit from crafted images.
  We've found a disk layout bug in large_nat_bits feature which supports
  very large NAT entries enabled at mkfs. If the feature is enabled, it
  will give a notice to run fsck to correct the on-disk layout.

  Enhancements:
   - reduce memory consumption for SMR drive
   - better discard handling for multiple partitions
   - tracepoints for f2fs_file_write_iter/f2fs_filemap_fault
   - allow to change CP_CHKSUM_OFFSET
   - detect wrong layout of large_nat_bitmap feature
   - enhance checking valid data indices

  Bug fixes:
   - Multiple partition support for SMR drive
   - deadlock problem in f2fs_balance_fs_bg
   - add boundary checks to fix abnormal behaviors on fuzzed images
   - inline_xattr space calculations
   - replace f2fs_bug_on with errors

  In addition, this series contains various memory boundary check and
  sanity check of on-disk consistency"

* tag 'f2fs-for-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: fix to avoid accessing xattr across the boundary
  f2fs: fix to avoid potential race on sbi->unusable_block_count access/update
  f2fs: add tracepoint for f2fs_filemap_fault()
  f2fs: introduce DATA_GENERIC_ENHANCE
  f2fs: fix to handle error in f2fs_disable_checkpoint()
  f2fs: remove redundant check in f2fs_file_write_iter()
  f2fs: fix to be aware of readonly device in write_checkpoint()
  f2fs: fix to skip recovery on readonly device
  f2fs: fix to consider multiple device for readonly check
  f2fs: relocate chksum_offset for large_nat_bitmap feature
  f2fs: allow unfixed f2fs_checkpoint.checksum_offset
  f2fs: Replace spaces with tab
  f2fs: insert space before the open parenthesis '('
  f2fs: allow address pointer number of dnode aligning to specified size
  f2fs: introduce f2fs_read_single_page() for cleanup
  f2fs: mark is_extension_exist() inline
  f2fs: fix to set FI_UPDATE_WRITE correctly
  f2fs: fix to avoid panic in f2fs_inplace_write_data()
  f2fs: fix to do sanity check on valid block count of segment
  f2fs: fix to do sanity check on valid node/block count
  ...

1 files changed, 54 insertions, 16 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4c55d2ea9df3..6b959bbb336a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1019,7 +1019,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		blkdev_put(FDEV(i).bdev, FMODE_EXCL);
 #ifdef CONFIG_BLK_DEV_ZONED
-		kvfree(FDEV(i).blkz_type);
+		kvfree(FDEV(i).blkz_seq);
 #endif
 	}
 	kvfree(sbi->devs);
@@ -1221,10 +1221,13 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = total_count - start_count;
 	buf->f_bfree = user_block_count - valid_user_blocks(sbi) -
 						sbi->current_reserved_blocks;
+
+	spin_lock(&sbi->stat_lock);
 	if (unlikely(buf->f_bfree <= sbi->unusable_block_count))
 		buf->f_bfree = 0;
 	else
 		buf->f_bfree -= sbi->unusable_block_count;
+	spin_unlock(&sbi->stat_lock);
 
 	if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks)
 		buf->f_bavail = buf->f_bfree -
@@ -1499,9 +1502,15 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 	mutex_lock(&sbi->gc_mutex);
 	cpc.reason = CP_PAUSE;
 	set_sbi_flag(sbi, SBI_CP_DISABLED);
-	f2fs_write_checkpoint(sbi, &cpc);
+	err = f2fs_write_checkpoint(sbi, &cpc);
+	if (err)
+		goto out_unlock;
 
+	spin_lock(&sbi->stat_lock);
 	sbi->unusable_block_count = 0;
+	spin_unlock(&sbi->stat_lock);
+
+out_unlock:
 	mutex_unlock(&sbi->gc_mutex);
 restore_flag:
 	sbi->sb->s_flags = s_flags;	/* Restore MS_RDONLY status */
@@ -2271,7 +2280,7 @@ static const struct export_operations f2fs_export_ops = {
 static loff_t max_file_blocks(void)
 {
 	loff_t result = 0;
-	loff_t leaf_count = ADDRS_PER_BLOCK;
+	loff_t leaf_count = DEF_ADDRS_PER_BLOCK;
 
 	/*
 	 * note: previously, result is equal to (DEF_ADDRS_PER_INODE -
@@ -2449,7 +2458,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	/* Currently, support only 4KB page cache size */
 	if (F2FS_BLKSIZE != PAGE_SIZE) {
 		f2fs_msg(sb, KERN_INFO,
-			"Invalid page_cache_size (%lu), supports only 4KB\n",
+			"Invalid page_cache_size (%lu), supports only 4KB",
 			PAGE_SIZE);
 		return 1;
 	}
@@ -2458,7 +2467,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
 	if (blocksize != F2FS_BLKSIZE) {
 		f2fs_msg(sb, KERN_INFO,
-			"Invalid blocksize (%u), supports only 4KB\n",
+			"Invalid blocksize (%u), supports only 4KB",
 			blocksize);
 		return 1;
 	}
@@ -2466,7 +2475,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	/* check log blocks per segment */
 	if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
 		f2fs_msg(sb, KERN_INFO,
-			"Invalid log blocks per segment (%u)\n",
+			"Invalid log blocks per segment (%u)",
 			le32_to_cpu(raw_super->log_blocks_per_seg));
 		return 1;
 	}
@@ -2587,7 +2596,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int log_blocks_per_seg;
 	unsigned int segment_count_main;
 	unsigned int cp_pack_start_sum, cp_payload;
-	block_t user_block_count;
+	block_t user_block_count, valid_user_blocks;
+	block_t avail_node_count, valid_node_count;
 	int i, j;
 
 	total = le32_to_cpu(raw_super->segment_count);
@@ -2622,6 +2632,24 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}
 
+	valid_user_blocks = le64_to_cpu(ckpt->valid_block_count);
+	if (valid_user_blocks > user_block_count) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong valid_user_blocks: %u, user_block_count: %u",
+			valid_user_blocks, user_block_count);
+		return 1;
+	}
+
+	valid_node_count = le32_to_cpu(ckpt->valid_node_count);
+	avail_node_count = sbi->total_node_count - sbi->nquota_files -
+						F2FS_RESERVED_NODE_NUM;
+	if (valid_node_count > avail_node_count) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong valid_node_count: %u, avail_node_count: %u",
+			valid_node_count, avail_node_count);
+		return 1;
+	}
+
 	main_segs = le32_to_cpu(raw_super->segment_count_main);
 	blocks_per_seg = sbi->blocks_per_seg;
 
@@ -2793,9 +2821,11 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 	if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
 		FDEV(devi).nr_blkz++;
 
-	FDEV(devi).blkz_type = f2fs_kmalloc(sbi, FDEV(devi).nr_blkz,
-								GFP_KERNEL);
-	if (!FDEV(devi).blkz_type)
+	FDEV(devi).blkz_seq = f2fs_kzalloc(sbi,
+					BITS_TO_LONGS(FDEV(devi).nr_blkz)
+					* sizeof(unsigned long),
+					GFP_KERNEL);
+	if (!FDEV(devi).blkz_seq)
 		return -ENOMEM;
 
 #define F2FS_REPORT_NR_ZONES   4096
@@ -2822,7 +2852,8 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 		}
 
 		for (i = 0; i < nr_zones; i++) {
-			FDEV(devi).blkz_type[n] = zones[i].type;
+			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
+				set_bit(n, FDEV(devi).blkz_seq);
 			sector += zones[i].len;
 			n++;
 		}
@@ -3105,7 +3136,7 @@ try_onemore:
 #ifndef CONFIG_BLK_DEV_ZONED
 	if (f2fs_sb_has_blkzoned(sbi)) {
 		f2fs_msg(sb, KERN_ERR,
-			 "Zoned block device support is not enabled\n");
+			 "Zoned block device support is not enabled");
 		err = -EOPNOTSUPP;
 		goto free_sb_buf;
 	}
@@ -3350,10 +3381,17 @@ try_onemore:
 		 * mount should be failed, when device has readonly mode, and
 		 * previous checkpoint was not done by clean system shutdown.
 		 */
-		if (bdev_read_only(sb->s_bdev) &&
-				!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
-			err = -EROFS;
-			goto free_meta;
+		if (f2fs_hw_is_readonly(sbi)) {
+			if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+				err = -EROFS;
+				f2fs_msg(sb, KERN_ERR,
+					"Need to recover fsync data, but "
+					"write access unavailable");
+				goto free_meta;
+			}
+			f2fs_msg(sbi->sb, KERN_INFO, "write access "
+				"unavailable, skipping recovery");
+			goto reset_checkpoint;
 		}
 
 		if (need_fsck)