Merge tag 'f2fs-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've introduced native swap file support which can
  exploit DIO, enhanced existing checkpoint=disable feature with
  additional mount option to tune the triggering condition, and allowed
  user to preallocate physical blocks in a pinned file which will be
  useful to avoid f2fs fragmentation in append-only workloads. In
  addition, we've fixed subtle quota corruption issue.

  Enhancements:
   - add swap file support which uses DIO
   - allocate blocks for pinned file
   - allow SSR and mount option to enhance checkpoint=disable
   - enhance IPU IOs
   - add more sanity checks such as memory boundary access

  Bug fixes:
   - quota corruption in very corner case of error-injected SPO case
   - fix root_reserved on remount and some wrong counts
   - add missing fsck flag

  Some patches were also introduced to clean up ambiguous i_flags and
  debugging messages codes"

* tag 'f2fs-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (33 commits)
  f2fs: improve print log in f2fs_sanity_check_ckpt()
  f2fs: avoid out-of-range memory access
  f2fs: fix to avoid long latency during umount
  f2fs: allow all the users to pin a file
  f2fs: support swap file w/ DIO
  f2fs: allocate blocks for pinned file
  f2fs: fix is_idle() check for discard type
  f2fs: add a rw_sem to cover quota flag changes
  f2fs: set SBI_NEED_FSCK for xattr corruption case
  f2fs: use generic EFSBADCRC/EFSCORRUPTED
  f2fs: Use DIV_ROUND_UP() instead of open-coding
  f2fs: print kernel message if filesystem is inconsistent
  f2fs: introduce f2fs_<level> macros to wrap f2fs_printk()
  f2fs: avoid get_valid_blocks() for cleanup
  f2fs: ioctl for removing a range from F2FS
  f2fs: only set project inherit bit for directory
  f2fs: separate f2fs i_flags from fs_flags and ext4 i_flags
  f2fs: replace ktype default_attrs with default_groups
  f2fs: Add option to limit required GC for checkpoint=disable
  f2fs: Fix accounting for unusable blocks
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -243,3 +243,11 @@ Description:
 		 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
 		 - [h] means add/del hot file extension
 		 - [c] means add/del cold file extension
+
+What:		/sys/fs/f2fs/<disk>/unusable
+Date		April 2019
+Contact:	"Daniel Rosenberg" <drosen@google.com>
+Description:
+		If checkpoint=disable, it displays the number of blocks that are unusable.
+                If checkpoint=enable it displays the enumber of blocks that would be unusable
+                if checkpoint=disable were to be set.

Documentation/filesystems/f2fs.txt

@@ -214,11 +214,22 @@ fsync_mode=%s          Control the policy of fsync. Currently supports "posix",
                        non-atomic files likewise "nobarrier" mount option.
 test_dummy_encryption  Enable dummy encryption, which provides a fake fscrypt
                        context. The fake fscrypt context is used by xfstests.
-checkpoint=%s          Set to "disable" to turn off checkpointing. Set to "enable"
+checkpoint=%s[:%u[%]]     Set to "disable" to turn off checkpointing. Set to "enable"
                        to reenable checkpointing. Is enabled by default. While
                        disabled, any unmounting or unexpected shutdowns will cause
                        the filesystem contents to appear as they did when the
                        filesystem was mounted with that option.
+                       While mounting with checkpoint=disabled, the filesystem must
+                       run garbage collection to ensure that all available space can
+                       be used. If this takes too much time, the mount may return
+                       EAGAIN. You may optionally add a value to indicate how much
+                       of the disk you would be willing to temporarily give up to
+                       avoid additional garbage collection. This can be given as a
+                       number of blocks, or as a percent. For instance, mounting
+                       with checkpoint=disable:100% would always succeed, but it may
+                       hide up to all remaining free space. The actual space that
+                       would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable
+                       This space is reclaimed once checkpoint=enable.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -246,11 +257,14 @@ Files in /sys/fs/f2fs/<devname>
 ..............................................................................
  File                         Content
 
- gc_max_sleep_time            This tuning parameter controls the maximum sleep
+ gc_urgent_sleep_time         This parameter controls sleep time for gc_urgent.
+                              500 ms is set by default. See above gc_urgent.
+
+ gc_min_sleep_time            This tuning parameter controls the minimum sleep
                               time for the garbage collection thread. Time is
                               in milliseconds.
 
- gc_min_sleep_time            This tuning parameter controls the minimum sleep
+ gc_max_sleep_time            This tuning parameter controls the maximum sleep
                               time for the garbage collection thread. Time is
                               in milliseconds.
 
@@ -270,9 +284,6 @@ Files in /sys/fs/f2fs/<devname>
                               to 1, background thread starts to do GC by given
                               gc_urgent_sleep_time interval.
 
- gc_urgent_sleep_time         This parameter controls sleep time for gc_urgent.
-                              500 ms is set by default. See above gc_urgent.
-
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
 			      segments is larger than the number of segments
@@ -287,7 +298,16 @@ Files in /sys/fs/f2fs/<devname>
 			      checkpoint is triggered, and issued during the
 			      checkpoint. By default, it is disabled with 0.
 
- trim_sections                This parameter controls the number of sections
+ discard_granularity	      This parameter controls the granularity of discard
+			      command size. It will issue discard commands iif
+			      the size is larger than given granularity. Its
+			      unit size is 4KB, and 4 (=16KB) is set by default.
+			      The maximum value is 128 (=512KB).
+
+ reserved_blocks	      This parameter indicates the number of blocks that
+			      f2fs reserves internally for root.
+
+ batched_trim_sections	      This parameter controls the number of sections
                               to be trimmed out in batch mode when FITRIM
                               conducts. 32 sections is set by default.
 
@@ -309,11 +329,35 @@ Files in /sys/fs/f2fs/<devname>
 			      the number is less than this value, it triggers
 			      in-place-updates.
 
+ min_seq_blocks		      This parameter controls the threshold to serialize
+			      write IOs issued by multiple threads in parallel.
+
+ min_hot_blocks		      This parameter controls the threshold to allocate
+			      a hot data log for pending data blocks to write.
+
+ min_ssr_sections	      This parameter adds the threshold when deciding
+			      SSR block allocation. If this is large, SSR mode
+			      will be enabled early.
+
+ ram_thresh                   This parameter controls the memory footprint used
+			      by free nids and cached nat entries. By default,
+			      10 is set, which indicates 10 MB / 1 GB RAM.
+
+ ra_nid_pages		      When building free nids, F2FS reads NAT blocks
+			      ahead for speed up. Default is 0.
+
+ dirty_nats_ratio	      Given dirty ratio of cached nat entries, F2FS
+			      determines flushing them in background.
+
  max_victim_search	      This parameter controls the number of trials to
 			      find a victim segment when conducting SSR and
 			      cleaning operations. The default value is 4096
 			      which covers 8GB block address range.
 
+ migration_granularity	      For large-sized sections, F2FS can stop GC given
+			      this granularity instead of reclaiming entire
+			      section.
+
  dir_level                    This parameter controls the directory level to
 			      support large directory. If a directory has a
 			      number of files, it can reduce the file lookup
@@ -321,9 +365,53 @@ Files in /sys/fs/f2fs/<devname>
 			      Otherwise, it needs to decrease this value to
 			      reduce the space overhead. The default value is 0.
 
- ram_thresh                   This parameter controls the memory footprint used
-			      by free nids and cached nat entries. By default,
-			      10 is set, which indicates 10 MB / 1 GB RAM.
+ cp_interval		      F2FS tries to do checkpoint periodically, 60 secs
+			      by default.
+
+ idle_interval		      F2FS detects system is idle, if there's no F2FS
+			      operations during given interval, 5 secs by
+			      default.
+
+ discard_idle_interval	      F2FS detects the discard thread is idle, given
+			      time interval. Default is 5 secs.
+
+ gc_idle_interval	      F2FS detects the GC thread is idle, given time
+			      interval. Default is 5 secs.
+
+ umount_discard_timeout       When unmounting the disk, F2FS waits for finishing
+			      queued discard commands which can take huge time.
+			      This gives time out for it, 5 secs by default.
+
+ iostat_enable		      This controls to enable/disable iostat in F2FS.
+
+ readdir_ra		      This enables/disabled readahead of inode blocks
+			      in readdir, and default is enabled.
+
+ gc_pin_file_thresh	      This indicates how many GC can be failed for the
+			      pinned file. If it exceeds this, F2FS doesn't
+			      guarantee its pinning state. 2048 trials is set
+			      by default.
+
+ extension_list		      This enables to change extension_list for hot/cold
+			      files in runtime.
+
+ inject_rate		      This controls injection rate of arbitrary faults.
+
+ inject_type		      This controls injection type of arbitrary faults.
+
+ dirty_segments 	      This shows # of dirty segments.
+
+ lifetime_write_kbytes	      This shows # of data written to the disk.
+
+ features		      This shows current features enabled on F2FS.
+
+ current_reserved_blocks      This shows # of blocks currently reserved.
+
+ unusable                     If checkpoint=disable, this shows the number of
+                              blocks that are unusable.
+                              If checkpoint=enable it shows the number of blocks
+                              that would be unusable if checkpoint=disable were
+                              to be set.
 
 ================================================================================
 USAGE
@@ -716,3 +804,28 @@ WRITE_LIFE_NOT_SET    WARM_DATA                WRITE_LIFE_NOT_SET
 WRITE_LIFE_NONE       "                        WRITE_LIFE_NONE
 WRITE_LIFE_MEDIUM     "                        WRITE_LIFE_MEDIUM
 WRITE_LIFE_LONG       "                        WRITE_LIFE_LONG
+
+Fallocate(2) Policy
+-------------------
+
+The default policy follows the below posix rule.
+
+Allocating disk space
+    The default operation (i.e., mode is zero) of fallocate() allocates
+    the disk space within the range specified by offset and len.  The
+    file size (as reported by stat(2)) will be changed if offset+len is
+    greater than the file size.  Any subregion within the range specified
+    by offset and len that did not contain data before the call will be
+    initialized to zero.  This default behavior closely resembles the
+    behavior of the posix_fallocate(3) library function, and is intended
+    as a method of optimally implementing that function.
+
+However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to
+fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having
+zero or random data, which is useful to the below scenario where:
+ 1. create(fd)
+ 2. ioctl(fd, F2FS_IOC_SET_PIN_FILE)
+ 3. fallocate(fd, 0, 0, size)
+ 4. address = fibmap(fd, offset)
+ 5. open(blkdev)
+ 6. write(blkdev, address)

fs/f2fs/checkpoint.c

@@ -146,8 +146,8 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 
 	exist = f2fs_test_bit(offset, se->cur_valid_map);
 	if (!exist && type == DATA_GENERIC_ENHANCE) {
-		f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
-			"blkaddr:%u, sit bitmap:%d", blkaddr, exist);
+		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
+			 blkaddr, exist);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		WARN_ON(1);
 	}
@@ -184,8 +184,8 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 	case DATA_GENERIC_ENHANCE_READ:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 				blkaddr < MAIN_BLKADDR(sbi))) {
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"access invalid blkaddr:%u", blkaddr);
+			f2fs_warn(sbi, "access invalid blkaddr:%u",
+				  blkaddr);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			WARN_ON(1);
 			return false;
@@ -657,8 +657,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 
 err_out:
 	set_sbi_flag(sbi, SBI_NEED_FSCK);
-	f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: orphan failed (ino=%x), run fsck to fix.",
+	f2fs_warn(sbi, "%s: orphan failed (ino=%x), run fsck to fix.",
 		  __func__, ino);
 	return err;
 }
@@ -676,13 +675,12 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		return 0;
 
 	if (bdev_read_only(sbi->sb->s_bdev)) {
-		f2fs_msg(sbi->sb, KERN_INFO, "write access "
-			"unavailable, skipping orphan cleanup");
+		f2fs_info(sbi, "write access unavailable, skipping orphan cleanup");
 		return 0;
 	}
 
 	if (s_flags & SB_RDONLY) {
-		f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
+		f2fs_info(sbi, "orphan cleanup on readonly fs");
 		sbi->sb->s_flags &= ~SB_RDONLY;
 	}
 
@@ -827,26 +825,14 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 	if (crc_offset < CP_MIN_CHKSUM_OFFSET ||
 			crc_offset > CP_CHKSUM_OFFSET) {
 		f2fs_put_page(*cp_page, 1);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"invalid crc_offset: %zu", crc_offset);
+		f2fs_warn(sbi, "invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;
 	}
 
-	if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) {
-		if (crc_offset != CP_MIN_CHKSUM_OFFSET) {
-			f2fs_put_page(*cp_page, 1);
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"layout of large_nat_bitmap is deprecated, "
-				"run fsck to repair, chksum_offset: %zu",
-				crc_offset);
-			return -EINVAL;
-		}
-	}
-
 	crc = f2fs_checkpoint_chksum(sbi, *cp_block);
 	if (crc != cur_cp_crc(*cp_block)) {
 		f2fs_put_page(*cp_page, 1);
-		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+		f2fs_warn(sbi, "invalid crc value");
 		return -EINVAL;
 	}
 
@@ -869,8 +855,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 
 	if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
 					sbi->blocks_per_seg) {
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"invalid cp_pack_total_block_count:%u",
+		f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u",
 			  le32_to_cpu(cp_block->cp_pack_total_block_count));
 		goto invalid_cp;
 	}
@@ -905,6 +890,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	unsigned int cp_blks = 1 + __cp_payload(sbi);
 	block_t cp_blk_no;
 	int i;
+	int err;
 
 	sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
 				 GFP_KERNEL);
@@ -932,6 +918,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	} else if (cp2) {
 		cur_page = cp2;
 	} else {
+		err = -EFSCORRUPTED;
 		goto fail_no_cp;
 	}
 
@@ -944,8 +931,10 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 		sbi->cur_cp_pack = 2;
 
 	/* Sanity checking of checkpoint */
-	if (f2fs_sanity_check_ckpt(sbi))
+	if (f2fs_sanity_check_ckpt(sbi)) {
+		err = -EFSCORRUPTED;
 		goto free_fail_no_cp;
+	}
 
 	if (cp_blks <= 1)
 		goto done;
@@ -959,8 +948,10 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 		unsigned char *ckpt = (unsigned char *)sbi->ckpt;
 
 		cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
-		if (IS_ERR(cur_page))
+		if (IS_ERR(cur_page)) {
+			err = PTR_ERR(cur_page);
 			goto free_fail_no_cp;
+		}
 		sit_bitmap_ptr = page_address(cur_page);
 		memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
 		f2fs_put_page(cur_page, 1);
@@ -975,7 +966,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	f2fs_put_page(cp2, 1);
 fail_no_cp:
 	kvfree(sbi->ckpt);
-	return -EINVAL;
+	return err;
 }
 
 static void __add_dirty_inode(struct inode *inode, enum inode_type type)
@@ -1142,17 +1133,24 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi)
 
 static bool __need_flush_quota(struct f2fs_sb_info *sbi)
 {
+	bool ret = false;
+
 	if (!is_journalled_quota(sbi))
 		return false;
-	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
-		return false;
-	if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
-		return false;
-	if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH))
-		return true;
-	if (get_pages(sbi, F2FS_DIRTY_QDATA))
-		return true;
-	return false;
+
+	down_write(&sbi->quota_sem);
+	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) {
+		ret = false;
+	} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) {
+		ret = false;
+	} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) {
+		clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
+		ret = true;
+	} else if (get_pages(sbi, F2FS_DIRTY_QDATA)) {
+		ret = true;
+	}
+	up_write(&sbi->quota_sem);
+	return ret;
 }
 
 /*
@@ -1171,26 +1169,22 @@ static int block_operations(struct f2fs_sb_info *sbi)
 	blk_start_plug(&plug);
 
 retry_flush_quotas:
+	f2fs_lock_all(sbi);
 	if (__need_flush_quota(sbi)) {
 		int locked;
 
 		if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
 			set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
-			f2fs_lock_all(sbi);
+			set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
 			goto retry_flush_dents;
 		}
-		clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
+		f2fs_unlock_all(sbi);
 
 		/* only failed during mount/umount/freeze/quotactl */
 		locked = down_read_trylock(&sbi->sb->s_umount);
 		f2fs_quota_sync(sbi->sb, -1);
 		if (locked)
 			up_read(&sbi->sb->s_umount);
-	}
-
-	f2fs_lock_all(sbi);
-	if (__need_flush_quota(sbi)) {
-		f2fs_unlock_all(sbi);
 		cond_resched();
 		goto retry_flush_quotas;
 	}
@@ -1212,12 +1206,6 @@ static int block_operations(struct f2fs_sb_info *sbi)
 	 */
 	down_write(&sbi->node_change);
 
-	if (__need_flush_quota(sbi)) {
-		up_write(&sbi->node_change);
-		f2fs_unlock_all(sbi);
-		goto retry_flush_quotas;
-	}
-
 	if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
 		up_write(&sbi->node_change);
 		f2fs_unlock_all(sbi);
@@ -1313,7 +1301,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	else
 		__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
-	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
+		is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
 		__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
 	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
@@ -1328,10 +1317,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
 		__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
-	/*
-	 * TODO: we count on fsck.f2fs to clear this flag until we figure out
-	 * missing cases which clear it incorrectly.
-	 */
+	else
+		__clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
 
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
 		__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
@@ -1571,8 +1558,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 		if (cpc->reason != CP_PAUSE)
 			return 0;
-		f2fs_msg(sbi->sb, KERN_WARNING,
-				"Start checkpoint disabled!");
+		f2fs_warn(sbi, "Start checkpoint disabled!");
 	}
 	mutex_lock(&sbi->cp_mutex);
 
@@ -1638,8 +1624,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	stat_inc_cp_count(sbi->stat_info);
 
 	if (cpc->reason & CP_RECOVERY)
-		f2fs_msg(sbi->sb, KERN_NOTICE,
-			"checkpoint: version = %llx", ckpt_ver);
+		f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver);
 
 	/* do checkpoint periodically */
 	f2fs_update_time(sbi, CP_TIME);

fs/f2fs/debug.c

@@ -27,8 +27,15 @@ static DEFINE_MUTEX(f2fs_stat_mutex);
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	int i;
 
+	/* these will be changed if online resize is done */
+	si->main_area_segs = le32_to_cpu(raw_super->segment_count_main);
+	si->main_area_sections = le32_to_cpu(raw_super->section_count);
+	si->main_area_zones = si->main_area_sections /
+				le32_to_cpu(raw_super->secs_per_zone);
+
 	/* validation check of the segment numbers */
 	si->hit_largest = atomic64_read(&sbi->read_hit_largest);
 	si->hit_cached = atomic64_read(&sbi->read_hit_cached);

fs/f2fs/dir.c

@@ -218,8 +218,7 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 
 	max_depth = F2FS_I(dir)->i_current_depth;
 	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
-		f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
-				"Corrupted max_depth of %lu: %u",
+		f2fs_warn(F2FS_I_SB(dir), "Corrupted max_depth of %lu: %u",
 			  dir->i_ino, max_depth);
 		max_depth = MAX_DIR_HASH_DEPTH;
 		f2fs_i_depth_write(dir, max_depth);
@@ -816,11 +815,10 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 		if (unlikely(bit_pos > d->max ||
 				le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) {
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"%s: corrupted namelen=%d, run fsck to fix.",
+			f2fs_warn(sbi, "%s: corrupted namelen=%d, run fsck to fix.",
 				  __func__, le16_to_cpu(de->name_len));
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			err = -EINVAL;
+			err = -EFSCORRUPTED;
 			goto out;
 		}
 
@@ -828,8 +826,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			int save_len = fstr->len;
 
 			err = fscrypt_fname_disk_to_usr(d->inode,
-						(u32)de->hash_code, 0,
-						&de_name, fstr);
+						(u32)le32_to_cpu(de->hash_code),
+						0, &de_name, fstr);
 			if (err)
 				goto out;
 

fs/f2fs/extent_cache.c

@@ -184,8 +184,7 @@ bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
 		next_re = rb_entry(next, struct rb_entry, rb_node);
 
 		if (cur_re->ofs + cur_re->len > next_re->ofs) {
-			f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, "
-				"cur(%u, %u) next(%u, %u)",
+			f2fs_info(sbi, "inconsistent rbtree, cur(%u, %u) next(%u, %u)",
 				  cur_re->ofs, cur_re->len,
 				  next_re->ofs, next_re->len);
 			return false;

fs/f2fs/gc.c

@@ -311,10 +311,11 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	struct sit_info *sm = SIT_I(sbi);
 	struct victim_sel_policy p;
 	unsigned int secno, last_victim;
-	unsigned int last_segment = MAIN_SEGS(sbi);
+	unsigned int last_segment;
 	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
+	last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec;
 
 	p.alloc_mode = alloc_mode;
 	select_policy(sbi, gc_type, type, &p);
@@ -387,7 +388,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 			goto next;
 		/* Don't touch checkpointed data */
 		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
-					get_ckpt_valid_blocks(sbi, segno)))
+					get_ckpt_valid_blocks(sbi, segno) &&
+					p.alloc_mode != SSR))
 			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
 			goto next;
@@ -404,7 +406,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 				sm->last_victim[p.gc_mode] = last_victim + 1;
 			else
 				sm->last_victim[p.gc_mode] = segno + 1;
-			sm->last_victim[p.gc_mode] %= MAIN_SEGS(sbi);
+			sm->last_victim[p.gc_mode] %=
+				(MAIN_SECS(sbi) * sbi->segs_per_sec);
 			break;
 		}
 	}
@@ -615,8 +618,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	}
 
 	if (sum->version != dni->version) {
-		f2fs_msg(sbi->sb, KERN_WARNING,
-				"%s: valid data with mismatched node version.",
+		f2fs_warn(sbi, "%s: valid data with mismatched node version.",
 			  __func__);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 	}
@@ -658,7 +660,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
 		dn.data_blkaddr = ei.blk + index - ei.fofs;
 		if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
 						DATA_GENERIC_ENHANCE_READ))) {
-			err = -EFAULT;
+			err = -EFSCORRUPTED;
 			goto put_page;
 		}
 		goto got_it;
@@ -676,7 +678,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
 	}
 	if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
 						DATA_GENERIC_ENHANCE))) {
-		err = -EFAULT;
+		err = -EFSCORRUPTED;
 		goto put_page;
 	}
 got_it:
@@ -1180,8 +1182,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 
 		sum = page_address(sum_page);
 		if (type != GET_SUM_TYPE((&sum->footer))) {
-			f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent segment (%u) "
-				"type [%d, %d] in SSA and SIT",
+			f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT",
 				 segno, type, GET_SUM_TYPE((&sum->footer)));
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			f2fs_stop_checkpoint(sbi, false);
@@ -1360,3 +1361,176 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
 		SIT_I(sbi)->last_victim[ALLOC_NEXT] =
 				GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
 }
+
+static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
+							unsigned int end)
+{
+	int type;
+	unsigned int segno, next_inuse;
+	int err = 0;
+
+	/* Move out cursegs from the target range */
+	for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++)
+		allocate_segment_for_resize(sbi, type, start, end);
+
+	/* do GC to move out valid blocks in the range */
+	for (segno = start; segno <= end; segno += sbi->segs_per_sec) {
+		struct gc_inode_list gc_list = {
+			.ilist = LIST_HEAD_INIT(gc_list.ilist),
+			.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
+		};
+
+		mutex_lock(&sbi->gc_mutex);
+		do_garbage_collect(sbi, segno, &gc_list, FG_GC);
+		mutex_unlock(&sbi->gc_mutex);
+		put_gc_inode(&gc_list);
+
+		if (get_valid_blocks(sbi, segno, true))
+			return -EAGAIN;
+	}
+
+	err = f2fs_sync_fs(sbi->sb, 1);
+	if (err)
+		return err;
+
+	next_inuse = find_next_inuse(FREE_I(sbi), end + 1, start);
+	if (next_inuse <= end) {
+		f2fs_err(sbi, "segno %u should be free but still inuse!",
+			 next_inuse);
+		f2fs_bug_on(sbi, 1);
+	}
+	return err;
+}
+
+static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
+{
+	struct f2fs_super_block *raw_sb = F2FS_RAW_SUPER(sbi);
+	int section_count = le32_to_cpu(raw_sb->section_count);
+	int segment_count = le32_to_cpu(raw_sb->segment_count);
+	int segment_count_main = le32_to_cpu(raw_sb->segment_count_main);
+	long long block_count = le64_to_cpu(raw_sb->block_count);
+	int segs = secs * sbi->segs_per_sec;
+
+	raw_sb->section_count = cpu_to_le32(section_count + secs);
+	raw_sb->segment_count = cpu_to_le32(segment_count + segs);
+	raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs);
+	raw_sb->block_count = cpu_to_le64(block_count +
+					(long long)segs * sbi->blocks_per_seg);
+}
+
+static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
+{
+	int segs = secs * sbi->segs_per_sec;
+	long long user_block_count =
+				le64_to_cpu(F2FS_CKPT(sbi)->user_block_count);
+
+	SM_I(sbi)->segment_count = (int)SM_I(sbi)->segment_count + segs;
+	MAIN_SEGS(sbi) = (int)MAIN_SEGS(sbi) + segs;
+	FREE_I(sbi)->free_sections = (int)FREE_I(sbi)->free_sections + secs;
+	FREE_I(sbi)->free_segments = (int)FREE_I(sbi)->free_segments + segs;
+	F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count +
+					(long long)segs * sbi->blocks_per_seg);
+}
+
+int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
+{
+	__u64 old_block_count, shrunk_blocks;
+	unsigned int secs;
+	int gc_mode, gc_type;
+	int err = 0;
+	__u32 rem;
+
+	old_block_count = le64_to_cpu(F2FS_RAW_SUPER(sbi)->block_count);
+	if (block_count > old_block_count)
+		return -EINVAL;
+
+	/* new fs size should align to section size */
+	div_u64_rem(block_count, BLKS_PER_SEC(sbi), &rem);
+	if (rem)
+		return -EINVAL;
+
+	if (block_count == old_block_count)
+		return 0;
+
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
+		f2fs_err(sbi, "Should run fsck to repair first.");
+		return -EFSCORRUPTED;
+	}
+
+	if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+		f2fs_err(sbi, "Checkpoint should be enabled.");
+		return -EINVAL;
+	}
+
+	freeze_bdev(sbi->sb->s_bdev);
+
+	shrunk_blocks = old_block_count - block_count;
+	secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi));
+	spin_lock(&sbi->stat_lock);
+	if (shrunk_blocks + valid_user_blocks(sbi) +
+		sbi->current_reserved_blocks + sbi->unusable_block_count +
+		F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count)
+		err = -ENOSPC;
+	else
+		sbi->user_block_count -= shrunk_blocks;
+	spin_unlock(&sbi->stat_lock);
+	if (err) {
+		thaw_bdev(sbi->sb->s_bdev, sbi->sb);
+		return err;
+	}
+
+	mutex_lock(&sbi->resize_mutex);
+	set_sbi_flag(sbi, SBI_IS_RESIZEFS);
+
+	mutex_lock(&DIRTY_I(sbi)->seglist_lock);
+
+	MAIN_SECS(sbi) -= secs;
+
+	for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++)
+		if (SIT_I(sbi)->last_victim[gc_mode] >=
+					MAIN_SECS(sbi) * sbi->segs_per_sec)
+			SIT_I(sbi)->last_victim[gc_mode] = 0;
+
+	for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++)
+		if (sbi->next_victim_seg[gc_type] >=
+					MAIN_SECS(sbi) * sbi->segs_per_sec)
+			sbi->next_victim_seg[gc_type] = NULL_SEGNO;
+
+	mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
+
+	err = free_segment_range(sbi, MAIN_SECS(sbi) * sbi->segs_per_sec,
+			MAIN_SEGS(sbi) - 1);
+	if (err)
+		goto out;
+
+	update_sb_metadata(sbi, -secs);
+
+	err = f2fs_commit_super(sbi, false);
+	if (err) {
+		update_sb_metadata(sbi, secs);
+		goto out;
+	}
+
+	update_fs_metadata(sbi, -secs);
+	clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
+	err = f2fs_sync_fs(sbi->sb, 1);
+	if (err) {
+		update_fs_metadata(sbi, secs);
+		update_sb_metadata(sbi, secs);
+		f2fs_commit_super(sbi, false);
+	}
+out:
+	if (err) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_err(sbi, "resize_fs failed, should run fsck to repair!");
+
+		MAIN_SECS(sbi) += secs;
+		spin_lock(&sbi->stat_lock);
+		sbi->user_block_count += shrunk_blocks;
+		spin_unlock(&sbi->stat_lock);
+	}
+	clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
+	mutex_unlock(&sbi->resize_mutex);
+	thaw_bdev(sbi->sb->s_bdev, sbi->sb);
+	return err;
+}

fs/f2fs/inline.c

@@ -140,11 +140,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
 		f2fs_put_dnode(dn);
 		set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
-		f2fs_msg(fio.sbi->sb, KERN_WARNING,
-			"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
-			"run fsck to fix.",
+		f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.",
 			  __func__, dn->inode->i_ino, dn->data_blkaddr);
-		return -EINVAL;
+		return -EFSCORRUPTED;
 	}
 
 	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
@@ -383,11 +381,9 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 	if (unlikely(dn.data_blkaddr != NEW_ADDR)) {
 		f2fs_put_dnode(&dn);
 		set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
-		f2fs_msg(F2FS_P_SB(page)->sb, KERN_WARNING,
-			"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
-			"run fsck to fix.",
+		f2fs_warn(F2FS_P_SB(page), "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.",
 			  __func__, dir->i_ino, dn.data_blkaddr);
-		err = -EINVAL;
+		err = -EFSCORRUPTED;
 		goto out;
 	}
 

fs/f2fs/inode.c

@@ -74,7 +74,7 @@ static int __written_first_block(struct f2fs_sb_info *sbi,
 	if (!__is_valid_data_blkaddr(addr))
 		return 1;
 	if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE))
-		return -EFAULT;
+		return -EFSCORRUPTED;
 	return 0;
 }
 
@@ -176,8 +176,7 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
 	calculated = f2fs_inode_chksum(sbi, page);
 
 	if (provided != calculated)
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x",
+		f2fs_warn(sbi, "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x",
 			  page->index, ino_of_node(page), provided, calculated);
 
 	return provided == calculated;
@@ -202,18 +201,14 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 	iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
 	if (!iblocks) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
-			"run fsck to fix.",
+		f2fs_warn(sbi, "%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, run fsck to fix.",
 			  __func__, inode->i_ino, iblocks);
 		return false;
 	}
 
 	if (ino_of_node(node_page) != nid_of_node(node_page)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: corrupted inode footer i_ino=%lx, ino,nid: "
-			"[%u, %u] run fsck to fix.",
+		f2fs_warn(sbi, "%s: corrupted inode footer i_ino=%lx, ino,nid: [%u, %u] run fsck to fix.",
 			  __func__, inode->i_ino,
 			  ino_of_node(node_page), nid_of_node(node_page));
 		return false;
@@ -222,8 +217,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 	if (f2fs_sb_has_flexible_inline_xattr(sbi)
 			&& !f2fs_has_extra_attr(inode)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: corrupted inode ino=%lx, run fsck to fix.",
+		f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.",
 			  __func__, inode->i_ino);
 		return false;
 	}
@@ -231,9 +225,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 	if (f2fs_has_extra_attr(inode) &&
 			!f2fs_sb_has_extra_attr(sbi)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: inode (ino=%lx) is with extra_attr, "
-			"but extra_attr feature is off",
+		f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off",
 			  __func__, inode->i_ino);
 		return false;
 	}
@@ -241,9 +233,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 	if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE ||
 			fi->i_extra_isize % sizeof(__le32)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: inode (ino=%lx) has corrupted i_extra_isize: %d, "
-			"max: %zu",
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, max: %zu",
 			  __func__, inode->i_ino, fi->i_extra_isize,
 			  F2FS_TOTAL_EXTRA_ATTR_SIZE);
 		return false;
@@ -255,9 +245,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		(!fi->i_inline_xattr_size ||
 		fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: inode (ino=%lx) has corrupted "
-			"i_inline_xattr_size: %d, max: %zu",
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %zu",
 			  __func__, inode->i_ino, fi->i_inline_xattr_size,
 			  MAX_INLINE_XATTR_SIZE);
 		return false;
@@ -272,9 +260,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 			!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
 						DATA_GENERIC_ENHANCE))) {
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"%s: inode (ino=%lx) extent info [%u, %u, %u] "
-				"is incorrect, run fsck to fix",
+			f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
 				  __func__, inode->i_ino,
 				  ei->blk, ei->fofs, ei->len);
 			return false;
@@ -284,18 +270,14 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 	if (f2fs_has_inline_data(inode) &&
 			(!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: inode (ino=%lx, mode=%u) should not have "
-			"inline_data, run fsck to fix",
+		f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
 			  __func__, inode->i_ino, inode->i_mode);
 		return false;
 	}
 
 	if (f2fs_has_inline_dentry(inode) && !S_ISDIR(inode->i_mode)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: inode (ino=%lx, mode=%u) should not have "
-			"inline_dentry, run fsck to fix",
+		f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_dentry, run fsck to fix",
 			  __func__, inode->i_ino, inode->i_mode);
 		return false;
 	}
@@ -343,6 +325,8 @@ static int do_read_inode(struct inode *inode)
 					le16_to_cpu(ri->i_gc_failures);
 	fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
 	fi->i_flags = le32_to_cpu(ri->i_flags);
+	if (S_ISREG(inode->i_mode))
+		fi->i_flags &= ~F2FS_PROJINHERIT_FL;
 	fi->flags = 0;
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
@@ -374,7 +358,7 @@ static int do_read_inode(struct inode *inode)
 
 	if (!sanity_check_inode(inode, node_page)) {
 		f2fs_put_page(node_page, 1);
-		return -EINVAL;
+		return -EFSCORRUPTED;
 	}
 
 	/* check data exist */
@@ -783,8 +767,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
 	err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
 	if (err) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"May loss orphan inode, run fsck to fix.");
+		f2fs_warn(sbi, "May loss orphan inode, run fsck to fix.");
 		goto out;
 	}
 
@@ -792,8 +775,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
 		err = f2fs_acquire_orphan_inode(sbi);
 		if (err) {
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"Too many orphan inodes, run fsck to fix.");
+			f2fs_warn(sbi, "Too many orphan inodes, run fsck to fix.");
 		} else {
 			f2fs_add_orphan_inode(inode);
 		}

fs/f2fs/namei.c

@@ -385,9 +385,8 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	int err = 0;
 
 	if (f2fs_readonly(sbi->sb)) {
-		f2fs_msg(sbi->sb, KERN_INFO,
-			"skip recovering inline_dots inode (ino:%lu, pino:%u) "
-			"in readonly mountpoint", dir->i_ino, pino);
+		f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint",
+			  dir->i_ino, pino);
 		return 0;
 	}
 
@@ -484,8 +483,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ENCRYPTED(dir) &&
 	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 	    !fscrypt_has_permitted_context(dir, inode)) {
-		f2fs_msg(inode->i_sb, KERN_WARNING,
-			 "Inconsistent encryption contexts: %lu/%lu",
+		f2fs_warn(F2FS_I_SB(inode), "Inconsistent encryption contexts: %lu/%lu",
 			  dir->i_ino, inode->i_ino);
 		err = -EPERM;
 		goto out_iput;

fs/f2fs/node.c

@@ -34,10 +34,9 @@ int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		f2fs_msg(sbi->sb, KERN_WARNING,
-				"%s: out-of-range nid=%x, run fsck to fix.",
+		f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.",
 			  __func__, nid);
-		return -EINVAL;
+		return -EFSCORRUPTED;
 	}
 	return 0;
 }
@@ -1189,10 +1188,8 @@ int f2fs_remove_inode_page(struct inode *inode)
 	}
 
 	if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) {
-		f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
-			"Inconsistent i_blocks, ino:%lu, iblocks:%llu",
-			inode->i_ino,
-			(unsigned long long)inode->i_blocks);
+		f2fs_warn(F2FS_I_SB(inode), "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
+			  inode->i_ino, (unsigned long long)inode->i_blocks);
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
 	}
 
@@ -1291,7 +1288,7 @@ static int read_node_page(struct page *page, int op_flags)
 	if (PageUptodate(page)) {
 		if (!f2fs_inode_chksum_verify(sbi, page)) {
 			ClearPageUptodate(page);
-			return -EBADMSG;
+			return -EFSBADCRC;
 		}
 		return LOCKED_PAGE;
 	}
@@ -1375,13 +1372,12 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 	}
 
 	if (!f2fs_inode_chksum_verify(sbi, page)) {
-		err = -EBADMSG;
+		err = -EFSBADCRC;
 		goto out_err;
 	}
 page_hit:
 	if(unlikely(nid != nid_of_node(page))) {
-		f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, "
-			"nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+		f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
 			  nid, nid_of_node(page), ino_of_node(page),
 			  ofs_of_node(page), cpver_of_node(page),
 			  next_blkaddr_of_node(page));
@@ -1752,8 +1748,7 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			break;
 	}
 	if (!ret && atomic && !marked) {
-		f2fs_msg(sbi->sb, KERN_DEBUG,
-			"Retry to write fsync mark: ino=%u, idx=%lx",
+		f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx",
 			   ino, last_page->index);
 		lock_page(last_page);
 		f2fs_wait_on_page_writeback(last_page, NODE, true, true);
@@ -2304,8 +2299,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 			if (ret) {
 				up_read(&nm_i->nat_tree_lock);
 				f2fs_bug_on(sbi, !mount);
-				f2fs_msg(sbi->sb, KERN_ERR,
-					"NAT is corrupt, run fsck to fix it");
+				f2fs_err(sbi, "NAT is corrupt, run fsck to fix it");
 				return ret;
 			}
 		}
@@ -2725,7 +2719,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
 		i = 1;
 	}
 	for (; i < NAT_ENTRY_PER_BLOCK; i++) {
-		if (nat_blk->entries[i].block_addr != NULL_ADDR)
+		if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR)
 			valid++;
 	}
 	if (valid == 0) {
@@ -2915,7 +2909,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 	nm_i->full_nat_bits = nm_i->nat_bits + 8;
 	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
 
-	f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint");
+	f2fs_notice(sbi, "Found nat_bits in checkpoint");
 	return 0;
 }
 

fs/f2fs/recovery.c

@@ -188,8 +188,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
 		name = "<encrypted>";
 	else
 		name = raw_inode->i_name;
-	f2fs_msg(inode->i_sb, KERN_NOTICE,
-			"%s: ino = %x, name = %s, dir = %lx, err = %d",
+	f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %s, dir = %lx, err = %d",
 		    __func__, ino_of_node(ipage), name,
 		    IS_ERR(dir) ? 0 : dir->i_ino, err);
 	return err;
@@ -292,8 +291,7 @@ static int recover_inode(struct inode *inode, struct page *page)
 	else
 		name = F2FS_INODE(page)->i_name;
 
-	f2fs_msg(inode->i_sb, KERN_NOTICE,
-		"recover_inode: ino = %x, name = %s, inline = %x",
+	f2fs_notice(F2FS_I_SB(inode), "recover_inode: ino = %x, name = %s, inline = %x",
 		    ino_of_node(page), name, raw->i_inline);
 	return 0;
 }
@@ -371,10 +369,9 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
 		/* sanity check in order to detect looped node chain */
 		if (++loop_cnt >= free_blocks ||
 			blkaddr == next_blkaddr_of_node(page)) {
-			f2fs_msg(sbi->sb, KERN_NOTICE,
-				"%s: detect looped node chain, "
-				"blkaddr:%u, next:%u",
-				__func__, blkaddr, next_blkaddr_of_node(page));
+			f2fs_notice(sbi, "%s: detect looped node chain, blkaddr:%u, next:%u",
+				    __func__, blkaddr,
+				    next_blkaddr_of_node(page));
 			f2fs_put_page(page, 1);
 			err = -EINVAL;
 			break;
@@ -553,11 +550,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
 
 	if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
-		f2fs_msg(sbi->sb, KERN_WARNING,
-			"Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
+		f2fs_warn(sbi, "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
 			  inode->i_ino, ofs_of_node(dn.node_page),
 			  ofs_of_node(page));
-		err = -EFAULT;
+		err = -EFSCORRUPTED;
 		goto err;
 	}
 
@@ -569,13 +565,13 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 		if (__is_valid_data_blkaddr(src) &&
 			!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
-			err = -EFAULT;
+			err = -EFSCORRUPTED;
 			goto err;
 		}
 
 		if (__is_valid_data_blkaddr(dest) &&
 			!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
-			err = -EFAULT;
+			err = -EFSCORRUPTED;
 			goto err;
 		}
 
@@ -642,10 +638,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 err:
 	f2fs_put_dnode(&dn);
 out:
-	f2fs_msg(sbi->sb, KERN_NOTICE,
-		"recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
-		inode->i_ino,
-		file_keep_isize(inode) ? "keep" : "recover",
+	f2fs_notice(sbi, "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
+		    inode->i_ino, file_keep_isize(inode) ? "keep" : "recover",
 		    recovered, err);
 	return err;
 }
@@ -734,8 +728,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 #endif
 
 	if (s_flags & SB_RDONLY) {
-		f2fs_msg(sbi->sb, KERN_INFO,
-				"recover fsync data on readonly fs");
+		f2fs_info(sbi, "recover fsync data on readonly fs");
 		sbi->sb->s_flags &= ~SB_RDONLY;
 	}
 

fs/f2fs/segment.h

@@ -109,7 +109,7 @@
 #define	START_SEGNO(segno)		\
 	(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
 #define SIT_BLK_CNT(sbi)			\
-	((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
+	DIV_ROUND_UP(MAIN_SEGS(sbi), SIT_ENTRY_PER_BLOCK)
 #define f2fs_bitmap_size(nr)			\
 	(BITS_TO_LONGS(nr) * sizeof(unsigned long))
 
@@ -693,21 +693,19 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 	} while (cur_pos < sbi->blocks_per_seg);
 
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
-		f2fs_msg(sbi->sb, KERN_ERR,
-				"Mismatch valid blocks %d vs. %d",
+		f2fs_err(sbi, "Mismatch valid blocks %d vs. %d",
 			 GET_SIT_VBLOCKS(raw_sit), valid_blocks);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return -EINVAL;
+		return -EFSCORRUPTED;
 	}
 
 	/* check segment usage, and check boundary of a given segment number */
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
 					|| segno > TOTAL_SEGS(sbi) - 1)) {
-		f2fs_msg(sbi->sb, KERN_ERR,
-				"Wrong valid blocks %d or segno %u",
+		f2fs_err(sbi, "Wrong valid blocks %d or segno %u",
 			 GET_SIT_VBLOCKS(raw_sit), segno);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return -EINVAL;
+		return -EFSCORRUPTED;
 	}
 	return 0;
 }

fs/f2fs/sysfs.c

@@ -68,6 +68,20 @@ static ssize_t dirty_segments_show(struct f2fs_attr *a,
 		(unsigned long long)(dirty_segments(sbi)));
 }
 
+static ssize_t unusable_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	block_t unusable;
+
+	if (test_opt(sbi, DISABLE_CHECKPOINT))
+		unusable = sbi->unusable_block_count;
+	else
+		unusable = f2fs_get_unusable_blocks(sbi);
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)unusable);
+}
+
+
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -440,6 +454,7 @@ F2FS_GENERAL_RO_ATTR(dirty_segments);
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 F2FS_GENERAL_RO_ATTR(features);
 F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
+F2FS_GENERAL_RO_ATTR(unusable);
 
 #ifdef CONFIG_FS_ENCRYPTION
 F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@@ -495,6 +510,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(inject_type),
 #endif
 	ATTR_LIST(dirty_segments),
+	ATTR_LIST(unusable),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(features),
 	ATTR_LIST(reserved_blocks),
@@ -568,8 +584,7 @@ static int __maybe_unused segment_info_seq_show(struct seq_file *seq,
 
 		if ((i % 10) == 0)
 			seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u", se->type,
-					get_valid_blocks(sbi, i, false));
+		seq_printf(seq, "%d|%-3u", se->type, se->valid_blocks);
 		if ((i % 10) == 9 || i == (total_segs - 1))
 			seq_putc(seq, '\n');
 		else
@@ -595,8 +610,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
 		struct seg_entry *se = get_seg_entry(sbi, i);
 
 		seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u|", se->type,
-					get_valid_blocks(sbi, i, false));
+		seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks);
 		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
 			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
 		seq_putc(seq, '\n');

fs/f2fs/xattr.c

@@ -346,7 +346,10 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 
 	*xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name);
 	if (!*xe) {
-		err = -EFAULT;
+		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+								inode->i_ino);
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+		err = -EFSCORRUPTED;
 		goto out;
 	}
 check:
@@ -622,7 +625,10 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, last_base_addr, index, len, name);
 	if (!here) {
-		error = -EFAULT;
+		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+								inode->i_ino);
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+		error = -EFSCORRUPTED;
 		goto exit;
 	}
 

include/trace/events/f2fs.h

@@ -1019,8 +1019,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= page->mapping->host->i_sb->s_dev;
-		__entry->ino		= page->mapping->host->i_ino;
+		__entry->dev		= page_file_mapping(page)->host->i_sb->s_dev;
+		__entry->ino		= page_file_mapping(page)->host->i_ino;
 		__entry->index		= page->index;
 		__entry->old_blkaddr	= fio->old_blkaddr;
 		__entry->new_blkaddr	= fio->new_blkaddr;
@@ -1207,10 +1207,11 @@ DECLARE_EVENT_CLASS(f2fs__page,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= page->mapping->host->i_sb->s_dev;
-		__entry->ino	= page->mapping->host->i_ino;
+		__entry->dev	= page_file_mapping(page)->host->i_sb->s_dev;
+		__entry->ino	= page_file_mapping(page)->host->i_ino;
 		__entry->type	= type;
-		__entry->dir	= S_ISDIR(page->mapping->host->i_mode);
+		__entry->dir	=
+			S_ISDIR(page_file_mapping(page)->host->i_mode);
 		__entry->index	= page->index;
 		__entry->dirty	= PageDirty(page);
 		__entry->uptodate = PageUptodate(page);