Merge tag 'f2fs-for-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we added a new mount option, "checkpoint_merge", which
  introduces a kernel thread dealing with the f2fs checkpoints. Once we
  start to manage the IO priority along with blk-cgroup, the checkpoint
  operation can be processed in a lower priority under the process
  context. Since the checkpoint holds all the filesystem operations, we
  give a higher priority to the checkpoint thread all the time.

  Enhancements:
   - introduce gc_merge mount option to introduce a checkpoint thread
   - improve to run discard thread efficiently
   - allow modular compression algorithms
   - expose # of overprivision segments to sysfs
   - expose runtime compression stat to sysfs

  Bug fixes:
   - fix OOB memory access by the node id lookup
   - avoid touching checkpointed data in the checkpoint-disabled mode
   - fix the resizing flow to avoid kernel panic and race conditions
   - fix block allocation issues on pinned files
   - address some swapfile issues
   - fix hugtask problem and kernel panic during atomic write operations
   - don't start checkpoint thread in RO

  And, we've cleaned up some kernel coding style and build warnings. In
  addition, we fixed some minor race conditions and error handling
  routines"

* tag 'f2fs-for-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (48 commits)
  f2fs: drop inplace IO if fs status is abnormal
  f2fs: compress: remove unneed check condition
  f2fs: clean up left deprecated IO trace codes
  f2fs: avoid using native allocate_segment_by_default()
  f2fs: remove unnecessary struct declaration
  f2fs: fix to avoid NULL pointer dereference
  f2fs: avoid duplicated codes for cleanup
  f2fs: document: add description about compressed space handling
  f2fs: clean up build warnings
  f2fs: fix the periodic wakeups of discard thread
  f2fs: fix to avoid accessing invalid fio in f2fs_allocate_data_block()
  f2fs: fix to avoid GC/mmap race with f2fs_truncate()
  f2fs: set checkpoint_merge by default
  f2fs: Fix a hungtask problem in atomic write
  f2fs: fix to restrict mount condition on readonly block device
  f2fs: introduce gc_merge mount option
  f2fs: fix to cover __allocate_new_section() with curseg_lock
  f2fs: fix wrong alloc_type in f2fs_do_replace_block
  f2fs: delete empty compress.h
  f2fs: fix a typo in inode.c
  ...

1 files changed, 75 insertions, 27 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 82592b19b4e0..7d325bfaf65a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -151,6 +151,8 @@ enum {
 	Opt_compress_chksum,
 	Opt_compress_mode,
 	Opt_atgc,
+	Opt_gc_merge,
+	Opt_nogc_merge,
 	Opt_err,
 };
 
@@ -223,6 +225,8 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_chksum, "compress_chksum"},
 	{Opt_compress_mode, "compress_mode=%s"},
 	{Opt_atgc, "atgc"},
+	{Opt_gc_merge, "gc_merge"},
+	{Opt_nogc_merge, "nogc_merge"},
 	{Opt_err, NULL},
 };
 
@@ -555,6 +559,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 		/*
@@ -1073,6 +1078,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 		case Opt_atgc:
 			set_opt(sbi, ATGC);
 			break;
+		case Opt_gc_merge:
+			set_opt(sbi, GC_MERGE);
+			break;
+		case Opt_nogc_merge:
+			clear_opt(sbi, GC_MERGE);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1616,6 +1627,7 @@ static inline void f2fs_show_quota_options(struct seq_file *seq,
 #endif
 }
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 static inline void f2fs_show_compress_options(struct seq_file *seq,
 							struct super_block *sb)
 {
@@ -1661,6 +1673,7 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 	else if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER)
 		seq_printf(seq, ",compress_mode=%s", "user");
 }
+#endif
 
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
@@ -1673,6 +1686,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF)
 		seq_printf(seq, ",background_gc=%s", "off");
 
+	if (test_opt(sbi, GC_MERGE))
+		seq_puts(seq, ",gc_merge");
+
 	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
 		seq_puts(seq, ",disable_roll_forward");
 	if (test_opt(sbi, NORECOVERY))
@@ -1824,6 +1840,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, EXTENT_CACHE);
 	set_opt(sbi, NOHEAP);
 	clear_opt(sbi, DISABLE_CHECKPOINT);
+	set_opt(sbi, MERGE_CHECKPOINT);
 	F2FS_OPTION(sbi).unusable_cap = 0;
 	sbi->sb->s_flags |= SB_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
@@ -1865,7 +1882,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 
 	while (!f2fs_time_over(sbi, DISABLE_TIME)) {
 		down_write(&sbi->gc_lock);
-		err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+		err = f2fs_gc(sbi, true, false, false, NULL_SEGNO);
 		if (err == -ENODATA) {
 			err = 0;
 			break;
@@ -1876,7 +1893,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 
 	ret = sync_filesystem(sbi->sb);
 	if (ret || err) {
-		err = ret ? ret: err;
+		err = ret ? ret : err;
 		goto restore_flag;
 	}
 
@@ -1925,8 +1942,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	struct f2fs_mount_info org_mount_opt;
 	unsigned long old_sb_flags;
 	int err;
-	bool need_restart_gc = false;
-	bool need_stop_gc = false;
+	bool need_restart_gc = false, need_stop_gc = false;
+	bool need_restart_ckpt = false, need_stop_ckpt = false;
+	bool need_restart_flush = false, need_stop_flush = false;
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 	bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
 	bool no_io_align = !F2FS_IO_ALIGNED(sbi);
@@ -2035,7 +2053,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * option. Also sync the filesystem.
 	 */
 	if ((*flags & SB_RDONLY) ||
-			F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) {
+			(F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF &&
+			!test_opt(sbi, GC_MERGE))) {
 		if (sbi->gc_thread) {
 			f2fs_stop_gc_thread(sbi);
 			need_restart_gc = true;
@@ -2057,18 +2076,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		clear_sbi_flag(sbi, SBI_IS_CLOSE);
 	}
 
-	if (checkpoint_changed) {
-		if (test_opt(sbi, DISABLE_CHECKPOINT)) {
-			err = f2fs_disable_checkpoint(sbi);
-			if (err)
-				goto restore_gc;
-		} else {
-			f2fs_enable_checkpoint(sbi);
-		}
-	}
-
-	if (!test_opt(sbi, DISABLE_CHECKPOINT) &&
-			test_opt(sbi, MERGE_CHECKPOINT)) {
+	if ((*flags & SB_RDONLY) || test_opt(sbi, DISABLE_CHECKPOINT) ||
+			!test_opt(sbi, MERGE_CHECKPOINT)) {
+		f2fs_stop_ckpt_thread(sbi);
+		need_restart_ckpt = true;
+	} else {
 		err = f2fs_start_ckpt_thread(sbi);
 		if (err) {
 			f2fs_err(sbi,
@@ -2076,8 +2088,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			    err);
 			goto restore_gc;
 		}
-	} else {
-		f2fs_stop_ckpt_thread(sbi);
+		need_stop_ckpt = true;
 	}
 
 	/*
@@ -2087,11 +2098,24 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if ((*flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
 		clear_opt(sbi, FLUSH_MERGE);
 		f2fs_destroy_flush_cmd_control(sbi, false);
+		need_restart_flush = true;
 	} else {
 		err = f2fs_create_flush_cmd_control(sbi);
 		if (err)
-			goto restore_gc;
+			goto restore_ckpt;
+		need_stop_flush = true;
 	}
+
+	if (checkpoint_changed) {
+		if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+			err = f2fs_disable_checkpoint(sbi);
+			if (err)
+				goto restore_flush;
+		} else {
+			f2fs_enable_checkpoint(sbi);
+		}
+	}
+
 skip:
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
@@ -2106,6 +2130,21 @@ skip:
 	adjust_unusable_cap_perc(sbi);
 	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	return 0;
+restore_flush:
+	if (need_restart_flush) {
+		if (f2fs_create_flush_cmd_control(sbi))
+			f2fs_warn(sbi, "background flush thread has stopped");
+	} else if (need_stop_flush) {
+		clear_opt(sbi, FLUSH_MERGE);
+		f2fs_destroy_flush_cmd_control(sbi, false);
+	}
+restore_ckpt:
+	if (need_restart_ckpt) {
+		if (f2fs_start_ckpt_thread(sbi))
+			f2fs_warn(sbi, "background ckpt thread has stopped");
+	} else if (need_stop_ckpt) {
+		f2fs_stop_ckpt_thread(sbi);
+	}
 restore_gc:
 	if (need_restart_gc) {
 		if (f2fs_start_gc_thread(sbi))
@@ -3719,7 +3758,7 @@ try_onemore:
 	sbi->iostat_period_ms = DEFAULT_IOSTAT_PERIOD_MS;
 
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		int n = (i == META) ? 1: NR_TEMP_TYPE;
+		int n = (i == META) ? 1 : NR_TEMP_TYPE;
 		int j;
 
 		sbi->write_io[i] =
@@ -3833,7 +3872,7 @@ try_onemore:
 
 	/* setup checkpoint request control and start checkpoint issue thread */
 	f2fs_init_ckpt_req_control(sbi);
-	if (!test_opt(sbi, DISABLE_CHECKPOINT) &&
+	if (!f2fs_readonly(sb) && !test_opt(sbi, DISABLE_CHECKPOINT) &&
 			test_opt(sbi, MERGE_CHECKPOINT)) {
 		err = f2fs_start_ckpt_thread(sbi);
 		if (err) {
@@ -3929,10 +3968,18 @@ try_onemore:
 		 * previous checkpoint was not done by clean system shutdown.
 		 */
 		if (f2fs_hw_is_readonly(sbi)) {
-			if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))
-				f2fs_err(sbi, "Need to recover fsync data, but write access unavailable");
-			else
-				f2fs_info(sbi, "write access unavailable, skipping recovery");
+			if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+				err = f2fs_recover_fsync_data(sbi, true);
+				if (err > 0) {
+					err = -EROFS;
+					f2fs_err(sbi, "Need to recover fsync data, but "
+						"write access unavailable, please try "
+						"mount w/ disable_roll_forward or norecovery");
+				}
+				if (err < 0)
+					goto free_meta;
+			}
+			f2fs_info(sbi, "write access unavailable, skipping recovery");
 			goto reset_checkpoint;
 		}
 
@@ -3989,7 +4036,8 @@ reset_checkpoint:
 	 * If filesystem is not mounted as read-only then
 	 * do start the gc_thread.
 	 */
-	if (F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF && !f2fs_readonly(sb)) {
+	if ((F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF ||
+		test_opt(sbi, GC_MERGE)) && !f2fs_readonly(sb)) {
 		/* After POR, we can run background GC thread.*/
 		err = f2fs_start_gc_thread(sbi);
 		if (err)