Merge tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've made more work into per-file compression support.

  For example, F2FS_IOC_GET | SET_COMPRESS_OPTION provides a way to
  change the algorithm or cluster size per file. F2FS_IOC_COMPRESS |
  DECOMPRESS_FILE provides a way to compress and decompress the existing
  normal files manually.

  There is also a new mount option, compress_mode=fs|user, which can
  control who compresses the data.

  Chao also added a checksum feature with a mount option so that
  we are able to detect any corrupted cluster.

  In addition, Daniel contributed casefolding with encryption patch,
  which will be used for Android devices.

  Summary:

  Enhancements:
   - add ioctls and mount option to manage per-file compression feature
   - support casefolding with encryption
   - support checksum for compressed cluster
   - avoid IO starvation by replacing mutex with rwsem
   - add sysfs, max_io_bytes, to control max bio size

  Bug fixes:
   - fix use-after-free issue when compression and fsverity are enabled
   - fix consistency corruption during fault injection test
   - fix data offset for lseek
   - get rid of buffer_head which has 32bits limit in fiemap
   - fix some bugs in multi-partitions support
   - fix nat entry count calculation in shrinker
   - fix some stat information

  And, we've refactored some logics and fix minor bugs as well"

* tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (36 commits)
  f2fs: compress: fix compression chksum
  f2fs: fix shift-out-of-bounds in sanity_check_raw_super()
  f2fs: fix race of pending_pages in decompression
  f2fs: fix to account inline xattr correctly during recovery
  f2fs: inline: fix wrong inline inode stat
  f2fs: inline: correct comment in f2fs_recover_inline_data
  f2fs: don't check PAGE_SIZE again in sanity_check_raw_super()
  f2fs: convert to F2FS_*_INO macro
  f2fs: introduce max_io_bytes, a sysfs entry, to limit bio size
  f2fs: don't allow any writes on readonly mount
  f2fs: avoid race condition for shrinker count
  f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE
  f2fs: add compress_mode mount option
  f2fs: Remove unnecessary unlikely()
  f2fs: init dirty_secmap incorrectly
  f2fs: remove buffer_head which has 32bits limit
  f2fs: fix wrong block count instead of bytes
  f2fs: use new conversion functions between blks and bytes
  f2fs: rename logical_to_blk and blk_to_logical
  f2fs: fix kbytes written stat for multi-device case
  ...

1 files changed, 29 insertions, 8 deletions

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 54a1905af052..897edb7c951a 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -37,7 +37,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	struct page *page = NULL;
+	struct page *page;
 repeat:
 	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
@@ -348,13 +348,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 		goto skip_write;
 
 	/* if locked failed, cp will flush dirty pages instead */
-	if (!mutex_trylock(&sbi->cp_mutex))
+	if (!down_write_trylock(&sbi->cp_global_sem))
 		goto skip_write;
 
 	trace_f2fs_writepages(mapping->host, wbc, META);
 	diff = nr_pages_to_write(sbi, META, wbc);
 	written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
-	mutex_unlock(&sbi->cp_mutex);
+	up_write(&sbi->cp_global_sem);
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
 	return 0;
 
@@ -1385,6 +1385,26 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi,
 	f2fs_submit_merged_write(sbi, META_FLUSH);
 }
 
+static inline u64 get_sectors_written(struct block_device *bdev)
+{
+	return (u64)part_stat_read(bdev, sectors[STAT_WRITE]);
+}
+
+u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_is_multi_device(sbi)) {
+		u64 sectors = 0;
+		int i;
+
+		for (i = 0; i < sbi->s_ndevs; i++)
+			sectors += get_sectors_written(FDEV(i).bdev);
+
+		return sectors;
+	}
+
+	return get_sectors_written(sbi->sb->s_bdev);
+}
+
 static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -1488,8 +1508,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	start_blk += data_sum_blocks;
 
 	/* Record write statistics in the hot node summary */
-	kbytes_written = sbi->kbytes_written + BD_PART_WRITTEN(sbi);
-
+	kbytes_written = sbi->kbytes_written;
+	kbytes_written += (f2fs_get_sectors_written(sbi) -
+				sbi->sectors_written_start) >> 1;
 	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
 
 	if (__remain_node_summaries(cpc->reason)) {
@@ -1569,7 +1590,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		f2fs_warn(sbi, "Start checkpoint disabled!");
 	}
 	if (cpc->reason != CP_RESIZE)
-		mutex_lock(&sbi->cp_mutex);
+		down_write(&sbi->cp_global_sem);
 
 	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
 		((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
@@ -1597,7 +1618,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			goto out;
 		}
 
-		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+		if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 &&
 				SIT_I(sbi)->dirty_sentries == 0 &&
 				prefree_segments(sbi) == 0) {
 			f2fs_flush_sit_entries(sbi, cpc);
@@ -1644,7 +1665,7 @@ stop:
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 out:
 	if (cpc->reason != CP_RESIZE)
-		mutex_unlock(&sbi->cp_mutex);
+		up_write(&sbi->cp_global_sem);
 	return err;
 }