Merge tag 'f2fs-for-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "The main changes include converting major IO paths to use folio, and
  adding various knobs to control GC more flexibly for Zoned devices.

  In addition, there are several patches to address corner cases of
  atomic file operations and better support for file pinning on zoned
  device.

  Enhancement:
   - add knobs to tune foreground/background GCs for Zoned devices
   - convert IO paths to use folio
   - reduce expensive checkpoint trigger frequency
   - allow F2FS_IPU_NOCACHE for pinned file
   - forcibly migrate to secure space for zoned device file pinning
   - get rid of buffer_head use
   - add write priority option based on zone UFS
   - get rid of online repair on corrupted directory

  Bug fixes:
   - fix to don't panic system for no free segment fault injection
   - fix to don't set SB_RDONLY in f2fs_handle_critical_error()
   - avoid unused block when dio write in LFS mode
   - compress: don't redirty sparse cluster during {,de}compress
   - check discard support for conventional zones
   - atomic: prevent atomic file from being dirtied before commit
   - atomic: fix to check atomic_file in f2fs ioctl interfaces
   - atomic: fix to forbid dio in atomic_file
   - atomic: fix to truncate pagecache before on-disk metadata truncation
   - atomic: create COW inode from parent dentry
   - atomic: fix to avoid racing w/ GC
   - atomic: require FMODE_WRITE for atomic write ioctls
   - fix to wait page writeback before setting gcing flag
   - fix to avoid racing in between read and OPU dio write, dio completion
   - fix several potential integer overflows in file offsets and dir_block_index
   - fix to avoid use-after-free in f2fs_stop_gc_thread()

  As usual, there are several code clean-ups and refactorings"

* tag 'f2fs-for-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (60 commits)
  f2fs: allow F2FS_IPU_NOCACHE for pinned file
  f2fs: forcibly migrate to secure space for zoned device file pinning
  f2fs: remove unused parameters
  f2fs: fix to don't panic system for no free segment fault injection
  f2fs: fix to don't set SB_RDONLY in f2fs_handle_critical_error()
  f2fs: add valid block ratio not to do excessive GC for one time GC
  f2fs: create gc_no_zoned_gc_percent and gc_boost_zoned_gc_percent
  f2fs: do FG_GC when GC boosting is required for zoned devices
  f2fs: increase BG GC migration window granularity when boosted for zoned devices
  f2fs: add reserved_segments sysfs node
  f2fs: introduce migration_window_granularity
  f2fs: make BG GC more aggressive for zoned devices
  f2fs: avoid unused block when dio write in LFS mode
  f2fs: fix to check atomic_file in f2fs ioctl interfaces
  f2fs: get rid of online repaire on corrupted directory
  f2fs: prevent atomic file from being dirtied before commit
  f2fs: get rid of page->index
  f2fs: convert read_node_page() to use folio
  f2fs: convert __write_node_page() to use folio
  f2fs: convert f2fs_write_data_page() to use folio
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -579,6 +579,12 @@ Description:	When ATGC is on, it controls age threshold to bypass GCing young
 		candidates whose age is not beyond the threshold, by default it was
 		initialized as 604800 seconds (equals to 7 days).
 
+What:		/sys/fs/f2fs/<disk>/atgc_enabled
+Date:		Feb 2024
+Contact:	"Jinbao Liu" <liujinbao1@xiaomi.com>
+Description:	It represents whether ATGC is on or off. The value is 1 which
+               indicates that ATGC is on, and 0 indicates that it is off.
+
 What:		/sys/fs/f2fs/<disk>/gc_reclaimed_segments
 Date:		July 2021
 Contact:	"Daeho Jeong" <daehojeong@google.com>
@@ -763,3 +769,53 @@ Date:		November 2023
 Contact:	"Chao Yu" <chao@kernel.org>
 Description:	It controls to enable/disable IO aware feature for background discard.
 		By default, the value is 1 which indicates IO aware is on.
+
+What:		/sys/fs/f2fs/<disk>/blkzone_alloc_policy
+Date:		July 2024
+Contact:	"Yuanhong Liao" <liaoyuanhong@vivo.com>
+Description:	The zone UFS we are currently using consists of two parts:
+		conventional zones and sequential zones. It can be used to control which part
+		to prioritize for writes, with a default value of 0.
+
+		========================  =========================================
+		value					  description
+		blkzone_alloc_policy = 0  Prioritize writing to sequential zones
+		blkzone_alloc_policy = 1  Only allow writing to sequential zones
+		blkzone_alloc_policy = 2  Prioritize writing to conventional zones
+		========================  =========================================
+
+What:		/sys/fs/f2fs/<disk>/migration_window_granularity
+Date:		September 2024
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	Controls migration window granularity of garbage collection on large
+		section. it can control the scanning window granularity for GC migration
+		in a unit of segment, while migration_granularity controls the number
+		of segments which can be migrated at the same turn.
+
+What:		/sys/fs/f2fs/<disk>/reserved_segments
+Date:		September 2024
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	In order to fine tune GC behavior, we can control the number of
+		reserved segments.
+
+What:		/sys/fs/f2fs/<disk>/gc_no_zoned_gc_percent
+Date:		September 2024
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	If the percentage of free sections over total sections is above this
+		number, F2FS do not garbage collection for zoned devices through the
+		background GC thread. the default number is "60".
+
+What:		/sys/fs/f2fs/<disk>/gc_boost_zoned_gc_percent
+Date:		September 2024
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	If the percentage of free sections over total sections is under this
+		number, F2FS boosts garbage collection for zoned devices through the
+		background GC thread. the default number is "25".
+
+What:		/sys/fs/f2fs/<disk>/gc_valid_thresh_ratio
+Date:		September 2024
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	It controls the valid block ratio threshold not to trigger excessive GC
+		for zoned deivces. The initial value of it is 95(%). F2FS will stop the
+		background GC thread from intiating GC for sections having valid blocks
+		exceeding the ratio.

fs/f2fs/checkpoint.c

@@ -99,7 +99,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 	}
 
 	if (unlikely(!PageUptodate(page))) {
-		f2fs_handle_page_eio(sbi, page->index, META);
+		f2fs_handle_page_eio(sbi, page_folio(page), META);
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
@@ -345,30 +345,31 @@ static int __f2fs_write_meta_page(struct page *page,
 				enum iostat_type io_type)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	struct folio *folio = page_folio(page);
 
-	trace_f2fs_writepage(page_folio(page), META);
+	trace_f2fs_writepage(folio, META);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
-			ClearPageUptodate(page);
+			folio_clear_uptodate(folio);
 			dec_page_count(sbi, F2FS_DIRTY_META);
-			unlock_page(page);
+			folio_unlock(folio);
 			return 0;
 		}
 		goto redirty_out;
 	}
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
-	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
+	if (wbc->for_reclaim && folio->index < GET_SUM_BLOCK(sbi, 0))
 		goto redirty_out;
 
-	f2fs_do_write_meta_page(sbi, page, io_type);
+	f2fs_do_write_meta_page(sbi, folio, io_type);
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
 		f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
 
-	unlock_page(page);
+	folio_unlock(folio);
 
 	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_write(sbi, META);
@@ -1551,7 +1552,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		blk = start_blk + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks;
 		for (i = 0; i < nm_i->nat_bits_blocks; i++)
 			f2fs_update_meta_page(sbi, nm_i->nat_bits +
-					(i << F2FS_BLKSIZE_BITS), blk + i);
+					F2FS_BLK_TO_BYTES(i), blk + i);
 	}
 
 	/* write out checkpoint buffer at block 0 */

fs/f2fs/compress.c

@@ -90,11 +90,13 @@ bool f2fs_is_compressed_page(struct page *page)
 static void f2fs_set_compressed_page(struct page *page,
 		struct inode *inode, pgoff_t index, void *data)
 {
-	attach_page_private(page, (void *)data);
+	struct folio *folio = page_folio(page);
+
+	folio_attach_private(folio, (void *)data);
 
 	/* i_crypto_info and iv index */
-	page->index = index;
-	page->mapping = inode->i_mapping;
+	folio->index = index;
+	folio->mapping = inode->i_mapping;
 }
 
 static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock)
@@ -160,17 +162,17 @@ void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse)
 		cc->cluster_idx = NULL_CLUSTER;
 }
 
-void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page)
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio)
 {
 	unsigned int cluster_ofs;
 
-	if (!f2fs_cluster_can_merge_page(cc, page->index))
+	if (!f2fs_cluster_can_merge_page(cc, folio->index))
 		f2fs_bug_on(F2FS_I_SB(cc->inode), 1);
 
-	cluster_ofs = offset_in_cluster(cc, page->index);
-	cc->rpages[cluster_ofs] = page;
+	cluster_ofs = offset_in_cluster(cc, folio->index);
+	cc->rpages[cluster_ofs] = folio_page(folio, 0);
 	cc->nr_rpages++;
-	cc->cluster_idx = cluster_idx(cc, page->index);
+	cc->cluster_idx = cluster_idx(cc, folio->index);
 }
 
 #ifdef CONFIG_F2FS_FS_LZO
@@ -879,7 +881,7 @@ static bool cluster_has_invalid_data(struct compress_ctx *cc)
 		f2fs_bug_on(F2FS_I_SB(cc->inode), !page);
 
 		/* beyond EOF */
-		if (page->index >= nr_pages)
+		if (page_folio(page)->index >= nr_pages)
 			return true;
 	}
 	return false;
@@ -945,7 +947,7 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
 	unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
 	int count, i;
 
-	for (i = 1, count = 1; i < cluster_size; i++) {
+	for (i = 0, count = 0; i < cluster_size; i++) {
 		block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
 							dn->ofs_in_node + i);
 
@@ -956,8 +958,8 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
 	return count;
 }
 
-static int __f2fs_cluster_blocks(struct inode *inode,
-				unsigned int cluster_idx, bool compr_blks)
+static int __f2fs_cluster_blocks(struct inode *inode, unsigned int cluster_idx,
+				enum cluster_check_type type)
 {
 	struct dnode_of_data dn;
 	unsigned int start_idx = cluster_idx <<
@@ -978,10 +980,12 @@ static int __f2fs_cluster_blocks(struct inode *inode,
 	}
 
 	if (dn.data_blkaddr == COMPRESS_ADDR) {
-		if (compr_blks)
-			ret = __f2fs_get_cluster_blocks(inode, &dn);
-		else
+		if (type == CLUSTER_COMPR_BLKS)
+			ret = 1 + __f2fs_get_cluster_blocks(inode, &dn);
+		else if (type == CLUSTER_IS_COMPR)
 			ret = 1;
+	} else if (type == CLUSTER_RAW_BLKS) {
+		ret = __f2fs_get_cluster_blocks(inode, &dn);
 	}
 fail:
 	f2fs_put_dnode(&dn);
@@ -991,7 +995,16 @@ static int __f2fs_cluster_blocks(struct inode *inode,
 /* return # of compressed blocks in compressed cluster */
 static int f2fs_compressed_blocks(struct compress_ctx *cc)
 {
-	return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx, true);
+	return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx,
+		CLUSTER_COMPR_BLKS);
+}
+
+/* return # of raw blocks in non-compressed cluster */
+static int f2fs_decompressed_blocks(struct inode *inode,
+				unsigned int cluster_idx)
+{
+	return __f2fs_cluster_blocks(inode, cluster_idx,
+		CLUSTER_RAW_BLKS);
 }
 
 /* return whether cluster is compressed one or not */
@@ -999,7 +1012,16 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
 {
 	return __f2fs_cluster_blocks(inode,
 		index >> F2FS_I(inode)->i_log_cluster_size,
-		false);
+		CLUSTER_IS_COMPR);
+}
+
+/* return whether cluster contains non raw blocks or not */
+bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index)
+{
+	unsigned int cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size;
+
+	return f2fs_decompressed_blocks(inode, cluster_idx) !=
+		F2FS_I(inode)->i_cluster_size;
 }
 
 static bool cluster_may_compress(struct compress_ctx *cc)
@@ -1093,7 +1115,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 		if (PageUptodate(page))
 			f2fs_put_page(page, 1);
 		else
-			f2fs_compress_ctx_add_page(cc, page);
+			f2fs_compress_ctx_add_page(cc, page_folio(page));
 	}
 
 	if (!f2fs_cluster_is_empty(cc)) {
@@ -1123,7 +1145,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 		}
 
 		f2fs_wait_on_page_writeback(page, DATA, true, true);
-		f2fs_compress_ctx_add_page(cc, page);
+		f2fs_compress_ctx_add_page(cc, page_folio(page));
 
 		if (!PageUptodate(page)) {
 release_and_retry:
@@ -1523,7 +1545,8 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 		if (!clear_page_dirty_for_io(cc->rpages[i]))
 			goto continue_unlock;
 
-		ret = f2fs_write_single_data_page(cc->rpages[i], &submitted,
+		ret = f2fs_write_single_data_page(page_folio(cc->rpages[i]),
+						&submitted,
 						NULL, NULL, wbc, io_type,
 						compr_blocks, false);
 		if (ret) {

fs/f2fs/debug.c

@@ -275,7 +275,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	/* build nm */
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
-	si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+	si->base_mem += F2FS_BLK_TO_BYTES(NM_I(sbi)->nat_bits_blocks);
 	si->base_mem += NM_I(sbi)->nat_blocks *
 				f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
 	si->base_mem += NM_I(sbi)->nat_blocks / 8;

fs/f2fs/dir.c

@@ -166,7 +166,8 @@ static unsigned long dir_block_index(unsigned int level,
 	unsigned long bidx = 0;
 
 	for (i = 0; i < level; i++)
-		bidx += dir_buckets(i, dir_level) * bucket_blocks(i);
+		bidx += mul_u32_u32(dir_buckets(i, dir_level),
+				    bucket_blocks(i));
 	bidx += idx * bucket_blocks(level);
 	return bidx;
 }
@@ -841,6 +842,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	struct	f2fs_dentry_block *dentry_blk;
 	unsigned int bit_pos;
 	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+	pgoff_t index = page_folio(page)->index;
 	int i;
 
 	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
@@ -866,8 +868,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	set_page_dirty(page);
 
 	if (bit_pos == NR_DENTRY_IN_BLOCK &&
-		!f2fs_truncate_hole(dir, page->index, page->index + 1)) {
-		f2fs_clear_page_cache_dirty_tag(page);
+		!f2fs_truncate_hole(dir, index, index + 1)) {
+		f2fs_clear_page_cache_dirty_tag(page_folio(page));
 		clear_page_dirty_for_io(page);
 		ClearPageUptodate(page);
 		clear_page_private_all(page);

fs/f2fs/extent_cache.c

@@ -366,7 +366,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 static void __drop_largest_extent(struct extent_tree *et,
 					pgoff_t fofs, unsigned int len)
 {
-	if (fofs < et->largest.fofs + et->largest.len &&
+	if (fofs < (pgoff_t)et->largest.fofs + et->largest.len &&
 			fofs + len > et->largest.fofs) {
 		et->largest.len = 0;
 		et->largest_updated = true;
@@ -456,7 +456,7 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 
 	if (type == EX_READ &&
 			et->largest.fofs <= pgofs &&
-			et->largest.fofs + et->largest.len > pgofs) {
+			(pgoff_t)et->largest.fofs + et->largest.len > pgofs) {
 		*ei = et->largest;
 		ret = true;
 		stat_inc_largest_node_hit(sbi);

fs/f2fs/gc.c

@@ -81,6 +81,8 @@ static int gc_thread_func(void *data)
 			continue;
 		}
 
+		gc_control.one_time = false;
+
 		/*
 		 * [GC triggering condition]
 		 * 0. GC is not conducted currently.
@@ -116,15 +118,30 @@ static int gc_thread_func(void *data)
 			goto next;
 		}
 
-		if (has_enough_invalid_blocks(sbi))
+		if (f2fs_sb_has_blkzoned(sbi)) {
+			if (has_enough_free_blocks(sbi,
+				gc_th->no_zoned_gc_percent)) {
+				wait_ms = gc_th->no_gc_sleep_time;
+				f2fs_up_write(&sbi->gc_lock);
+				goto next;
+			}
+			if (wait_ms == gc_th->no_gc_sleep_time)
+				wait_ms = gc_th->max_sleep_time;
+		}
+
+		if (need_to_boost_gc(sbi)) {
 			decrease_sleep_time(gc_th, &wait_ms);
-		else
+			if (f2fs_sb_has_blkzoned(sbi))
+				gc_control.one_time = true;
+		} else {
 			increase_sleep_time(gc_th, &wait_ms);
+		}
 do_gc:
 		stat_inc_gc_call_count(sbi, foreground ?
 					FOREGROUND : BACKGROUND);
 
-		sync_mode = F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC;
+		sync_mode = (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) ||
+				gc_control.one_time;
 
 		/* foreground GC was been triggered via f2fs_balance_fs() */
 		if (foreground)
@@ -179,9 +196,21 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
+	gc_th->valid_thresh_ratio = DEF_GC_THREAD_VALID_THRESH_RATIO;
+
+	if (f2fs_sb_has_blkzoned(sbi)) {
+		gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED;
+		gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED;
+		gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED;
+		gc_th->no_zoned_gc_percent = LIMIT_NO_ZONED_GC;
+		gc_th->boost_zoned_gc_percent = LIMIT_BOOST_ZONED_GC;
+	} else {
 		gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
 		gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
 		gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
+		gc_th->no_zoned_gc_percent = 0;
+		gc_th->boost_zoned_gc_percent = 0;
+	}
 
 	gc_th->gc_wake = false;
 
@@ -339,7 +368,7 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned char age = 0;
 	unsigned char u;
 	unsigned int i;
-	unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi, segno);
+	unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi);
 
 	for (i = 0; i < usable_segs_per_sec; i++)
 		mtime += get_seg_entry(sbi, start + i)->mtime;
@@ -368,6 +397,11 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 	if (p->alloc_mode == SSR)
 		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 
+	if (p->one_time_gc && (get_valid_blocks(sbi, segno, true) >=
+		CAP_BLKS_PER_SEC(sbi) * sbi->gc_thread->valid_thresh_ratio /
+		100))
+		return UINT_MAX;
+
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
 		return get_valid_blocks(sbi, segno, true);
@@ -742,7 +776,7 @@ static int f2fs_gc_pinned_control(struct inode *inode, int gc_type,
  */
 int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
 			int gc_type, int type, char alloc_mode,
-			unsigned long long age)
+			unsigned long long age, bool one_time)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct sit_info *sm = SIT_I(sbi);
@@ -759,6 +793,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
 	p.alloc_mode = alloc_mode;
 	p.age = age;
 	p.age_threshold = sbi->am.age_threshold;
+	p.one_time_gc = one_time;
 
 retry:
 	select_policy(sbi, gc_type, type, &p);
@@ -1670,13 +1705,14 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
-			int gc_type)
+			int gc_type, bool one_time)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	int ret;
 
 	down_write(&sit_i->sentry_lock);
-	ret = f2fs_get_victim(sbi, victim, gc_type, NO_CHECK_TYPE, LFS, 0);
+	ret = f2fs_get_victim(sbi, victim, gc_type, NO_CHECK_TYPE,
+			LFS, 0, one_time);
 	up_write(&sit_i->sentry_lock);
 	return ret;
 }
@@ -1684,30 +1720,49 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 static int do_garbage_collect(struct f2fs_sb_info *sbi,
 				unsigned int start_segno,
 				struct gc_inode_list *gc_list, int gc_type,
-				bool force_migrate)
+				bool force_migrate, bool one_time)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
 	struct blk_plug plug;
 	unsigned int segno = start_segno;
 	unsigned int end_segno = start_segno + SEGS_PER_SEC(sbi);
+	unsigned int sec_end_segno;
 	int seg_freed = 0, migrated = 0;
 	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
 						SUM_TYPE_DATA : SUM_TYPE_NODE;
 	unsigned char data_type = (type == SUM_TYPE_DATA) ? DATA : NODE;
 	int submitted = 0;
 
-	if (__is_large_section(sbi))
-		end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi));
+	if (__is_large_section(sbi)) {
+		sec_end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi));
 
 		/*
 		 * zone-capacity can be less than zone-size in zoned devices,
 		 * resulting in less than expected usable segments in the zone,
-	 * calculate the end segno in the zone which can be garbage collected
+		 * calculate the end segno in the zone which can be garbage
+		 * collected
 		 */
 		if (f2fs_sb_has_blkzoned(sbi))
-		end_segno -= SEGS_PER_SEC(sbi) -
-					f2fs_usable_segs_in_sec(sbi, segno);
+			sec_end_segno -= SEGS_PER_SEC(sbi) -
+					f2fs_usable_segs_in_sec(sbi);
+
+		if (gc_type == BG_GC || one_time) {
+			unsigned int window_granularity =
+				sbi->migration_window_granularity;
+
+			if (f2fs_sb_has_blkzoned(sbi) &&
+					!has_enough_free_blocks(sbi,
+					sbi->gc_thread->boost_zoned_gc_percent))
+				window_granularity *=
+					BOOST_GC_MULTIPLE;
+
+			end_segno = start_segno + window_granularity;
+		}
+
+		if (end_segno > sec_end_segno)
+			end_segno = sec_end_segno;
+	}
 
 	sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type);
 
@@ -1786,7 +1841,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 
 		if (__is_large_section(sbi))
 			sbi->next_victim_seg[gc_type] =
-				(segno + 1 < end_segno) ? segno + 1 : NULL_SEGNO;
+				(segno + 1 < sec_end_segno) ?
+					segno + 1 : NULL_SEGNO;
 skip:
 		f2fs_put_page(sum_page, 0);
 	}
@@ -1863,7 +1919,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
 		goto stop;
 	}
 retry:
-	ret = __get_victim(sbi, &segno, gc_type);
+	ret = __get_victim(sbi, &segno, gc_type, gc_control->one_time);
 	if (ret) {
 		/* allow to search victim from sections has pinned data */
 		if (ret == -ENODATA && gc_type == FG_GC &&
@@ -1875,17 +1931,21 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
 	}
 
 	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type,
-				gc_control->should_migrate_blocks);
+				gc_control->should_migrate_blocks,
+				gc_control->one_time);
 	if (seg_freed < 0)
 		goto stop;
 
 	total_freed += seg_freed;
 
-	if (seg_freed == f2fs_usable_segs_in_sec(sbi, segno)) {
+	if (seg_freed == f2fs_usable_segs_in_sec(sbi)) {
 		sec_freed++;
 		total_sec_freed++;
 	}
 
+	if (gc_control->one_time)
+		goto stop;
+
 	if (gc_type == FG_GC) {
 		sbi->cur_victim_sec = NULL_SEGNO;
 
@@ -2010,8 +2070,7 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi,
 			.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
 		};
 
-		do_garbage_collect(sbi, segno, &gc_list, FG_GC,
-						dry_run_sections == 0);
+		do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false);
 		put_gc_inode(&gc_list);
 
 		if (!dry_run && get_valid_blocks(sbi, segno, true))

fs/f2fs/gc.h

@@ -15,16 +15,27 @@
 #define DEF_GC_THREAD_MAX_SLEEP_TIME	60000
 #define DEF_GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
 
+/* GC sleep parameters for zoned deivces */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED	10
+#define DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED	20
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED	60000
+
 /* choose candidates from sections which has age of more than 7 days */
 #define DEF_GC_THREAD_AGE_THRESHOLD		(60 * 60 * 24 * 7)
 #define DEF_GC_THREAD_CANDIDATE_RATIO		20	/* select 20% oldest sections as candidates */
 #define DEF_GC_THREAD_MAX_CANDIDATE_COUNT	10	/* select at most 10 sections as candidates */
 #define DEF_GC_THREAD_AGE_WEIGHT		60	/* age weight */
+#define DEF_GC_THREAD_VALID_THRESH_RATIO	95	/* do not GC over 95% valid block ratio for one time GC */
 #define DEFAULT_ACCURACY_CLASS			10000	/* accuracy class */
 
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
+#define LIMIT_NO_ZONED_GC	60 /* percentage over total user space of no gc for zoned devices */
+#define LIMIT_BOOST_ZONED_GC	25 /* percentage over total user space of boosted gc for zoned devices */
+#define DEF_MIGRATION_WINDOW_GRANULARITY_ZONED	3
+#define BOOST_GC_MULTIPLE	5
+
 #define DEF_GC_FAILED_PINNED_FILES	2048
 #define MAX_GC_FAILED_PINNED_FILES	USHRT_MAX
 
@@ -51,6 +62,11 @@ struct f2fs_gc_kthread {
 						 * caller of f2fs_balance_fs()
 						 * will wait on this wait queue.
 						 */
+
+	/* for gc control for zoned devices */
+	unsigned int no_zoned_gc_percent;
+	unsigned int boost_zoned_gc_percent;
+	unsigned int valid_thresh_ratio;
 };
 
 struct gc_inode_list {
@@ -152,6 +168,12 @@ static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
 		*wait -= min_time;
 }
 
+static inline bool has_enough_free_blocks(struct f2fs_sb_info *sbi,
+						unsigned int limit_perc)
+{
+	return free_sections(sbi) > ((sbi->total_sections * limit_perc) / 100);
+}
+
 static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
 {
 	block_t user_block_count = sbi->user_block_count;
@@ -167,3 +189,10 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
 		free_user_blocks(sbi) <
 			limit_free_user_blocks(invalid_user_blocks));
 }
+
+static inline bool need_to_boost_gc(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return !has_enough_free_blocks(sbi, LIMIT_BOOST_ZONED_GC);
+	return has_enough_invalid_blocks(sbi);
+}

fs/f2fs/inline.c

@@ -260,35 +260,34 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	return err;
 }
 
-int f2fs_write_inline_data(struct inode *inode, struct page *page)
+int f2fs_write_inline_data(struct inode *inode, struct folio *folio)
 {
-	struct dnode_of_data dn;
-	int err;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct page *ipage;
 
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
-	if (err)
-		return err;
+	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage))
+		return PTR_ERR(ipage);
 
 	if (!f2fs_has_inline_data(inode)) {
-		f2fs_put_dnode(&dn);
+		f2fs_put_page(ipage, 1);
 		return -EAGAIN;
 	}
 
-	f2fs_bug_on(F2FS_I_SB(inode), page->index);
+	f2fs_bug_on(F2FS_I_SB(inode), folio->index);
 
-	f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true);
-	memcpy_from_page(inline_data_addr(inode, dn.inode_page),
-			 page, 0, MAX_INLINE_DATA(inode));
-	set_page_dirty(dn.inode_page);
+	f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+	memcpy_from_folio(inline_data_addr(inode, ipage),
+			 folio, 0, MAX_INLINE_DATA(inode));
+	set_page_dirty(ipage);
 
-	f2fs_clear_page_cache_dirty_tag(page);
+	f2fs_clear_page_cache_dirty_tag(folio);
 
 	set_inode_flag(inode, FI_APPEND_WRITE);
 	set_inode_flag(inode, FI_DATA_EXIST);
 
-	clear_page_private_inline(dn.inode_page);
-	f2fs_put_dnode(&dn);
+	clear_page_private_inline(ipage);
+	f2fs_put_page(ipage, 1);
 	return 0;
 }
 

fs/f2fs/inode.c

@@ -7,7 +7,6 @@
  */
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
-#include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/sched/mm.h>
 #include <linux/lz4.h>
@@ -35,6 +34,11 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 	if (f2fs_inode_dirtied(inode, sync))
 		return;
 
+	if (f2fs_is_atomic_file(inode)) {
+		set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+		return;
+	}
+
 	mark_inode_dirty_sync(inode);
 }
 
@@ -175,7 +179,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
 
 	if (provided != calculated)
 		f2fs_warn(sbi, "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x",
-			  page->index, ino_of_node(page), provided, calculated);
+			  page_folio(page)->index, ino_of_node(page),
+			  provided, calculated);
 
 	return provided == calculated;
 }

fs/f2fs/namei.c

@@ -457,62 +457,6 @@ struct dentry *f2fs_get_parent(struct dentry *child)
 	return d_obtain_alias(f2fs_iget(child->d_sb, ino));
 }
 
-static int __recover_dot_dentries(struct inode *dir, nid_t pino)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
-	struct qstr dot = QSTR_INIT(".", 1);
-	struct f2fs_dir_entry *de;
-	struct page *page;
-	int err = 0;
-
-	if (f2fs_readonly(sbi->sb)) {
-		f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint",
-			  dir->i_ino, pino);
-		return 0;
-	}
-
-	if (!S_ISDIR(dir->i_mode)) {
-		f2fs_err(sbi, "inconsistent inode status, skip recovering inline_dots inode (ino:%lu, i_mode:%u, pino:%u)",
-			  dir->i_ino, dir->i_mode, pino);
-		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return -ENOTDIR;
-	}
-
-	err = f2fs_dquot_initialize(dir);
-	if (err)
-		return err;
-
-	f2fs_balance_fs(sbi, true);
-
-	f2fs_lock_op(sbi);
-
-	de = f2fs_find_entry(dir, &dot, &page);
-	if (de) {
-		f2fs_put_page(page, 0);
-	} else if (IS_ERR(page)) {
-		err = PTR_ERR(page);
-		goto out;
-	} else {
-		err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
-		if (err)
-			goto out;
-	}
-
-	de = f2fs_find_entry(dir, &dotdot_name, &page);
-	if (de)
-		f2fs_put_page(page, 0);
-	else if (IS_ERR(page))
-		err = PTR_ERR(page);
-	else
-		err = f2fs_do_add_link(dir, &dotdot_name, NULL, pino, S_IFDIR);
-out:
-	if (!err)
-		clear_inode_flag(dir, FI_INLINE_DOTS);
-
-	f2fs_unlock_op(sbi);
-	return err;
-}
-
 static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		unsigned int flags)
 {
@@ -522,7 +466,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct dentry *new;
 	nid_t ino = -1;
 	int err = 0;
-	unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
 	struct f2fs_filename fname;
 
 	trace_f2fs_lookup_start(dir, dentry, flags);
@@ -558,17 +501,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
-		err = __recover_dot_dentries(dir, root_ino);
-		if (err)
-			goto out_iput;
-	}
-
-	if (f2fs_has_inline_dots(inode)) {
-		err = __recover_dot_dentries(inode, dir->i_ino);
-		if (err)
-			goto out_iput;
-	}
 	if (IS_ENCRYPTED(dir) &&
 	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 	    !fscrypt_has_permitted_context(dir, inode)) {

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);
 	}
@@ -919,7 +919,7 @@ 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),
@@ -1369,6 +1369,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
  */
 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 = {
@@ -1381,21 +1382,21 @@ 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;
 	}
 
@@ -1492,7 +1493,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 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);
 }
@@ -1535,7 +1536,7 @@ 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)
@@ -1608,6 +1609,7 @@ 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 = {
@@ -1624,15 +1626,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	};
 	unsigned int seq;
 
-	trace_f2fs_writepage(page_folio(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;
 	}
 
@@ -1646,7 +1648,7 @@ 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;
@@ -1660,10 +1662,10 @@ 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;
 	}
 
@@ -1674,7 +1676,7 @@ 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 */
@@ -1684,7 +1686,7 @@ 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);
@@ -1697,7 +1699,7 @@ 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);
@@ -1711,7 +1713,7 @@ 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;
 }
 
@@ -1867,7 +1869,7 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 	}
 	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);
@@ -3166,7 +3168,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 
 	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;
 
@@ -3185,7 +3187,7 @@ 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);
 	}

fs/f2fs/segment.c

@@ -199,6 +199,10 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
 	clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
 	clear_inode_flag(inode, FI_ATOMIC_REPLACE);
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
+	if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
+		clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+		f2fs_mark_inode_dirty_sync(inode, true);
+	}
 	stat_dec_atomic_inode(inode);
 
 	F2FS_I(inode)->atomic_write_task = NULL;
@@ -366,6 +370,10 @@ static int __f2fs_commit_atomic_write(struct inode *inode)
 	} else {
 		sbi->committed_atomic_block += fi->atomic_write_cnt;
 		set_inode_flag(inode, FI_ATOMIC_COMMITTED);
+		if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
+			clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+			f2fs_mark_inode_dirty_sync(inode, true);
+		}
 	}
 
 	__complete_revoke_list(inode, &revoke_list, ret ? true : false);
@@ -1282,6 +1290,13 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 						wait_list, issued);
 			return 0;
 		}
+
+		/*
+		 * Issue discard for conventional zones only if the device
+		 * supports discard.
+		 */
+		if (!bdev_max_discard_sectors(bdev))
+			return -EOPNOTSUPP;
 	}
 #endif
 
@@ -2686,22 +2701,47 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
 			goto got_it;
 	}
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * If we format f2fs on zoned storage, let's try to get pinned sections
 	 * from beginning of the storage, which should be a conventional one.
 	 */
 	if (f2fs_sb_has_blkzoned(sbi)) {
-		segno = pinning ? 0 : max(first_zoned_segno(sbi), *newseg);
+		/* Prioritize writing to conventional zones */
+		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning)
+			segno = 0;
+		else
+			segno = max(first_zoned_segno(sbi), *newseg);
 		hint = GET_SEC_FROM_SEG(sbi, segno);
 	}
+#endif
 
 find_other_zone:
 	secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) {
+		/* Write only to sequential zones */
+		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) {
+			hint = GET_SEC_FROM_SEG(sbi, first_zoned_segno(sbi));
+			secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
+		} else
+			secno = find_first_zero_bit(free_i->free_secmap,
+								MAIN_SECS(sbi));
+		if (secno >= MAIN_SECS(sbi)) {
+			ret = -ENOSPC;
+			f2fs_bug_on(sbi, 1);
+			goto out_unlock;
+		}
+	}
+#endif
+
 	if (secno >= MAIN_SECS(sbi)) {
 		secno = find_first_zero_bit(free_i->free_secmap,
 							MAIN_SECS(sbi));
 		if (secno >= MAIN_SECS(sbi)) {
 			ret = -ENOSPC;
+			f2fs_bug_on(sbi, 1);
 			goto out_unlock;
 		}
 	}
@@ -2743,10 +2783,8 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
 out_unlock:
 	spin_unlock(&free_i->segmap_lock);
 
-	if (ret == -ENOSPC) {
+	if (ret == -ENOSPC)
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
-		f2fs_bug_on(sbi, 1);
-	}
 	return ret;
 }
 
@@ -3052,7 +3090,8 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
 	sanity_check_seg_type(sbi, seg_type);
 
 	/* f2fs_need_SSR() already forces to do this */
-	if (!f2fs_get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) {
+	if (!f2fs_get_victim(sbi, &segno, BG_GC, seg_type,
+				alloc_mode, age, false)) {
 		curseg->next_segno = segno;
 		return 1;
 	}
@@ -3079,7 +3118,8 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
 	for (; cnt-- > 0; reversed ? i-- : i++) {
 		if (i == seg_type)
 			continue;
-		if (!f2fs_get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) {
+		if (!f2fs_get_victim(sbi, &segno, BG_GC, i,
+					alloc_mode, age, false)) {
 			curseg->next_segno = segno;
 			return 1;
 		}
@@ -3522,7 +3562,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		if (file_is_cold(inode) || f2fs_need_compress_data(inode))
 			return CURSEG_COLD_DATA;
 
-		type = __get_age_segment_type(inode, fio->page->index);
+		type = __get_age_segment_type(inode,
+				page_folio(fio->page)->index);
 		if (type != NO_CHECK_TYPE)
 			return type;
 
@@ -3781,7 +3822,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 		f2fs_up_read(&fio->sbi->io_order_lock);
 }
 
-void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio,
 					enum iostat_type io_type)
 {
 	struct f2fs_io_info fio = {
@@ -3790,20 +3831,20 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
 		.temp = HOT,
 		.op = REQ_OP_WRITE,
 		.op_flags = REQ_SYNC | REQ_META | REQ_PRIO,
-		.old_blkaddr = page->index,
-		.new_blkaddr = page->index,
-		.page = page,
+		.old_blkaddr = folio->index,
+		.new_blkaddr = folio->index,
+		.page = folio_page(folio, 0),
 		.encrypted_page = NULL,
 		.in_list = 0,
 	};
 
-	if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
+	if (unlikely(folio->index >= MAIN_BLKADDR(sbi)))
 		fio.op_flags &= ~REQ_META;
 
-	set_page_writeback(page);
+	folio_start_writeback(folio);
 	f2fs_submit_page_write(&fio);
 
-	stat_inc_meta_count(sbi, page->index);
+	stat_inc_meta_count(sbi, folio->index);
 	f2fs_update_iostat(sbi, NULL, io_type, F2FS_BLKSIZE);
 }
 
@@ -5381,8 +5422,7 @@ unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
 	return BLKS_PER_SEG(sbi);
 }
 
-unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
-					unsigned int segno)
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi)
 {
 	if (f2fs_sb_has_blkzoned(sbi))
 		return CAP_SEGS_PER_SEC(sbi);

fs/f2fs/segment.h

@@ -188,6 +188,7 @@ struct victim_sel_policy {
 	unsigned int min_segno;		/* segment # having min. cost */
 	unsigned long long age;		/* mtime of GCed section*/
 	unsigned long long age_threshold;/* age threshold */
+	bool one_time_gc;		/* one time GC */
 };
 
 struct seg_entry {
@@ -430,7 +431,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
-	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
 
 	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
@@ -464,7 +465,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
-	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
 
 	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {

fs/f2fs/super.c

@@ -11,7 +11,6 @@
 #include <linux/fs_context.h>
 #include <linux/sched/mm.h>
 #include <linux/statfs.h>
-#include <linux/buffer_head.h>
 #include <linux/kthread.h>
 #include <linux/parser.h>
 #include <linux/mount.h>
@@ -707,6 +706,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			if (!strcmp(name, "on")) {
 				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
 			} else if (!strcmp(name, "off")) {
+				if (f2fs_sb_has_blkzoned(sbi)) {
+					f2fs_warn(sbi, "zoned devices need bggc");
+					kfree(name);
+					return -EINVAL;
+				}
 				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_OFF;
 			} else if (!strcmp(name, "sync")) {
 				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC;
@@ -2561,7 +2565,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 
 static void f2fs_shutdown(struct super_block *sb)
 {
-	f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false);
+	f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false, false);
 }
 
 #ifdef CONFIG_QUOTA
@@ -3318,29 +3322,47 @@ loff_t max_file_blocks(struct inode *inode)
 	 * fit within U32_MAX + 1 data units.
 	 */
 
-	result = min(result, (((loff_t)U32_MAX + 1) * 4096) >> F2FS_BLKSIZE_BITS);
+	result = min(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096));
 
 	return result;
 }
 
-static int __f2fs_commit_super(struct buffer_head *bh,
-			struct f2fs_super_block *super)
+static int __f2fs_commit_super(struct f2fs_sb_info *sbi, struct folio *folio,
+						pgoff_t index, bool update)
 {
-	lock_buffer(bh);
-	if (super)
-		memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
-	set_buffer_dirty(bh);
-	unlock_buffer(bh);
-
+	struct bio *bio;
 	/* it's rare case, we can do fua all the time */
-	return __sync_dirty_buffer(bh, REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA;
+	int ret;
+
+	folio_lock(folio);
+	folio_wait_writeback(folio);
+	if (update)
+		memcpy(F2FS_SUPER_BLOCK(folio, index), F2FS_RAW_SUPER(sbi),
+					sizeof(struct f2fs_super_block));
+	folio_mark_dirty(folio);
+	folio_clear_dirty_for_io(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+
+	bio = bio_alloc(sbi->sb->s_bdev, 1, opf, GFP_NOFS);
+
+	/* it doesn't need to set crypto context for superblock update */
+	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(folio_index(folio));
+
+	if (!bio_add_folio(bio, folio, folio_size(folio), 0))
+		f2fs_bug_on(sbi, 1);
+
+	ret = submit_bio_wait(bio);
+	folio_end_writeback(folio);
+
+	return ret;
 }
 
 static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
-					struct buffer_head *bh)
+					struct folio *folio, pgoff_t index)
 {
-	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
-					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index);
 	struct super_block *sb = sbi->sb;
 	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
@@ -3356,9 +3378,9 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 	u32 segment_count = le32_to_cpu(raw_super->segment_count);
 	u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
 	u64 main_end_blkaddr = main_blkaddr +
-				(segment_count_main << log_blocks_per_seg);
+				((u64)segment_count_main << log_blocks_per_seg);
 	u64 seg_end_blkaddr = segment0_blkaddr +
-				(segment_count << log_blocks_per_seg);
+				((u64)segment_count << log_blocks_per_seg);
 
 	if (segment0_blkaddr != cp_blkaddr) {
 		f2fs_info(sbi, "Mismatch start address, segment0(%u) cp_blkaddr(%u)",
@@ -3415,7 +3437,7 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 			set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 			res = "internally";
 		} else {
-			err = __f2fs_commit_super(bh, NULL);
+			err = __f2fs_commit_super(sbi, folio, index, false);
 			res = err ? "failed" : "done";
 		}
 		f2fs_info(sbi, "Fix alignment : %s, start(%u) end(%llu) block(%u)",
@@ -3428,12 +3450,11 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 }
 
 static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
-				struct buffer_head *bh)
+					struct folio *folio, pgoff_t index)
 {
 	block_t segment_count, segs_per_sec, secs_per_zone, segment_count_main;
 	block_t total_sections, blocks_per_seg;
-	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
-					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index);
 	size_t crc_offset = 0;
 	__u32 crc = 0;
 
@@ -3591,7 +3612,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	}
 
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
-	if (sanity_check_area_boundary(sbi, bh))
+	if (sanity_check_area_boundary(sbi, folio, index))
 		return -EFSCORRUPTED;
 
 	return 0;
@@ -3786,6 +3807,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
 	sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
 	sbi->migration_granularity = SEGS_PER_SEC(sbi);
+	sbi->migration_window_granularity = f2fs_sb_has_blkzoned(sbi) ?
+		DEF_MIGRATION_WINDOW_GRANULARITY_ZONED : SEGS_PER_SEC(sbi);
 	sbi->seq_file_ra_mul = MIN_RA_MUL;
 	sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
 	sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
@@ -3938,7 +3961,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
 {
 	struct super_block *sb = sbi->sb;
 	int block;
-	struct buffer_head *bh;
+	struct folio *folio;
 	struct f2fs_super_block *super;
 	int err = 0;
 
@@ -3947,32 +3970,32 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
 		return -ENOMEM;
 
 	for (block = 0; block < 2; block++) {
-		bh = sb_bread(sb, block);
-		if (!bh) {
+		folio = read_mapping_folio(sb->s_bdev->bd_mapping, block, NULL);
+		if (IS_ERR(folio)) {
 			f2fs_err(sbi, "Unable to read %dth superblock",
 				 block + 1);
-			err = -EIO;
+			err = PTR_ERR(folio);
 			*recovery = 1;
 			continue;
 		}
 
 		/* sanity checking of raw super */
-		err = sanity_check_raw_super(sbi, bh);
+		err = sanity_check_raw_super(sbi, folio, block);
 		if (err) {
 			f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock",
 				 block + 1);
-			brelse(bh);
+			folio_put(folio);
 			*recovery = 1;
 			continue;
 		}
 
 		if (!*raw_super) {
-			memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+			memcpy(super, F2FS_SUPER_BLOCK(folio, block),
 							sizeof(*super));
 			*valid_super_block = block;
 			*raw_super = super;
 		}
-		brelse(bh);
+		folio_put(folio);
 	}
 
 	/* No valid superblock */
@@ -3986,7 +4009,8 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
 
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 {
-	struct buffer_head *bh;
+	struct folio *folio;
+	pgoff_t index;
 	__u32 crc = 0;
 	int err;
 
@@ -4004,22 +4028,24 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	}
 
 	/* write back-up superblock first */
-	bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1);
-	if (!bh)
-		return -EIO;
-	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
-	brelse(bh);
+	index = sbi->valid_super_block ? 0 : 1;
+	folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	err = __f2fs_commit_super(sbi, folio, index, true);
+	folio_put(folio);
 
 	/* if we are in recovery path, skip writing valid superblock */
 	if (recover || err)
 		return err;
 
 	/* write current valid superblock */
-	bh = sb_bread(sbi->sb, sbi->valid_super_block);
-	if (!bh)
-		return -EIO;
-	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
-	brelse(bh);
+	index = sbi->valid_super_block;
+	folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	err = __f2fs_commit_super(sbi, folio, index, true);
+	folio_put(folio);
 	return err;
 }
 
@@ -4173,12 +4199,14 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
 	}
 
 	f2fs_warn(sbi, "Remounting filesystem read-only");
+
 	/*
-	 * Make sure updated value of ->s_mount_flags will be visible before
-	 * ->s_flags update
+	 * We have already set CP_ERROR_FLAG flag to stop all updates
+	 * to filesystem, so it doesn't need to set SB_RDONLY flag here
+	 * because the flag should be set covered w/ sb->s_umount semaphore
+	 * via remount procedure, otherwise, it will confuse code like
+	 * freeze_super() which will lead to deadlocks and other problems.
 	 */
-	smp_wmb();
-	sb->s_flags |= SB_RDONLY;
 }
 
 static void f2fs_record_error_work(struct work_struct *work)
@@ -4219,6 +4247,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 	sbi->aligned_blksize = true;
 #ifdef CONFIG_BLK_DEV_ZONED
 	sbi->max_open_zones = UINT_MAX;
+	sbi->blkzone_alloc_policy = BLKZONE_ALLOC_PRIOR_SEQ;
 #endif
 
 	for (i = 0; i < max_devices; i++) {

fs/f2fs/sysfs.c

@@ -170,6 +170,12 @@ static ssize_t undiscard_blks_show(struct f2fs_attr *a,
 				SM_I(sbi)->dcc_info->undiscard_blks);
 }
 
+static ssize_t atgc_enabled_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", sbi->am.atgc_enabled ? 1 : 0);
+}
+
 static ssize_t gc_mode_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -182,50 +188,50 @@ static ssize_t features_show(struct f2fs_attr *a,
 	int len = 0;
 
 	if (f2fs_sb_has_encrypt(sbi))
-		len += scnprintf(buf, PAGE_SIZE - len, "%s",
+		len += sysfs_emit_at(buf, len, "%s",
 						"encryption");
 	if (f2fs_sb_has_blkzoned(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "blkzoned");
 	if (f2fs_sb_has_extra_attr(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "extra_attr");
 	if (f2fs_sb_has_project_quota(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "projquota");
 	if (f2fs_sb_has_inode_chksum(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "inode_checksum");
 	if (f2fs_sb_has_flexible_inline_xattr(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "flexible_inline_xattr");
 	if (f2fs_sb_has_quota_ino(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "quota_ino");
 	if (f2fs_sb_has_inode_crtime(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "inode_crtime");
 	if (f2fs_sb_has_lost_found(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "lost_found");
 	if (f2fs_sb_has_verity(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "verity");
 	if (f2fs_sb_has_sb_chksum(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "sb_checksum");
 	if (f2fs_sb_has_casefold(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "casefold");
 	if (f2fs_sb_has_readonly(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "readonly");
 	if (f2fs_sb_has_compression(sbi))
-		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "compression");
-	len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+	len += sysfs_emit_at(buf, len, "%s%s",
 				len ? ", " : "", "pin_file");
-	len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+	len += sysfs_emit_at(buf, len, "\n");
 	return len;
 }
 
@@ -323,17 +329,14 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 		int hot_count = sbi->raw_super->hot_ext_count;
 		int len = 0, i;
 
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-						"cold file extension:\n");
+		len += sysfs_emit_at(buf, len, "cold file extension:\n");
 		for (i = 0; i < cold_count; i++)
-			len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
-								extlist[i]);
+			len += sysfs_emit_at(buf, len, "%s\n", extlist[i]);
 
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-						"hot file extension:\n");
+		len += sysfs_emit_at(buf, len, "hot file extension:\n");
 		for (i = cold_count; i < cold_count + hot_count; i++)
-			len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
-								extlist[i]);
+			len += sysfs_emit_at(buf, len, "%s\n", extlist[i]);
+
 		return len;
 	}
 
@@ -561,6 +564,11 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 			return -EINVAL;
 	}
 
+	if (!strcmp(a->attr.name, "migration_window_granularity")) {
+		if (t == 0 || t > SEGS_PER_SEC(sbi))
+			return -EINVAL;
+	}
+
 	if (!strcmp(a->attr.name, "gc_urgent")) {
 		if (t == 0) {
 			sbi->gc_mode = GC_NORMAL;
@@ -627,6 +635,15 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 	}
 #endif
 
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (!strcmp(a->attr.name, "blkzone_alloc_policy")) {
+		if (t < BLKZONE_ALLOC_PRIOR_SEQ || t > BLKZONE_ALLOC_PRIOR_CONV)
+			return -EINVAL;
+		sbi->blkzone_alloc_policy = t;
+		return count;
+	}
+#endif
+
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (!strcmp(a->attr.name, "compr_written_block") ||
 		!strcmp(a->attr.name, "compr_saved_block")) {
@@ -775,7 +792,8 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 	if (!strcmp(a->attr.name, "ipu_policy")) {
 		if (t >= BIT(F2FS_IPU_MAX))
 			return -EINVAL;
-		if (t && f2fs_lfs_mode(sbi))
+		/* allow F2FS_IPU_NOCACHE only for IPU in the pinned file */
+		if (f2fs_lfs_mode(sbi) && (t & ~BIT(F2FS_IPU_NOCACHE)))
 			return -EINVAL;
 		SM_I(sbi)->ipu_policy = (unsigned int)t;
 		return count;
@@ -960,6 +978,9 @@ GC_THREAD_RW_ATTR(gc_urgent_sleep_time, urgent_sleep_time);
 GC_THREAD_RW_ATTR(gc_min_sleep_time, min_sleep_time);
 GC_THREAD_RW_ATTR(gc_max_sleep_time, max_sleep_time);
 GC_THREAD_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time);
+GC_THREAD_RW_ATTR(gc_no_zoned_gc_percent, no_zoned_gc_percent);
+GC_THREAD_RW_ATTR(gc_boost_zoned_gc_percent, boost_zoned_gc_percent);
+GC_THREAD_RW_ATTR(gc_valid_thresh_ratio, valid_thresh_ratio);
 
 /* SM_INFO ATTR */
 SM_INFO_RW_ATTR(reclaim_segments, rec_prefree_segments);
@@ -969,6 +990,7 @@ SM_INFO_GENERAL_RW_ATTR(min_fsync_blocks);
 SM_INFO_GENERAL_RW_ATTR(min_seq_blocks);
 SM_INFO_GENERAL_RW_ATTR(min_hot_blocks);
 SM_INFO_GENERAL_RW_ATTR(min_ssr_sections);
+SM_INFO_GENERAL_RW_ATTR(reserved_segments);
 
 /* DCC_INFO ATTR */
 DCC_INFO_RW_ATTR(max_small_discards, max_discards);
@@ -1001,6 +1023,7 @@ F2FS_SBI_RW_ATTR(gc_pin_file_thresh, gc_pin_file_threshold);
 F2FS_SBI_RW_ATTR(gc_reclaimed_segments, gc_reclaimed_segs);
 F2FS_SBI_GENERAL_RW_ATTR(max_victim_search);
 F2FS_SBI_GENERAL_RW_ATTR(migration_granularity);
+F2FS_SBI_GENERAL_RW_ATTR(migration_window_granularity);
 F2FS_SBI_GENERAL_RW_ATTR(dir_level);
 #ifdef CONFIG_F2FS_IOSTAT
 F2FS_SBI_GENERAL_RW_ATTR(iostat_enable);
@@ -1033,6 +1056,7 @@ F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold);
 F2FS_SBI_GENERAL_RW_ATTR(last_age_weight);
 #ifdef CONFIG_BLK_DEV_ZONED
 F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
+F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
 #endif
 
 /* STAT_INFO ATTR */
@@ -1072,6 +1096,7 @@ F2FS_GENERAL_RO_ATTR(encoding);
 F2FS_GENERAL_RO_ATTR(mounted_time_sec);
 F2FS_GENERAL_RO_ATTR(main_blkaddr);
 F2FS_GENERAL_RO_ATTR(pending_discard);
+F2FS_GENERAL_RO_ATTR(atgc_enabled);
 F2FS_GENERAL_RO_ATTR(gc_mode);
 #ifdef CONFIG_F2FS_STAT_FS
 F2FS_GENERAL_RO_ATTR(moved_blocks_background);
@@ -1116,6 +1141,9 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(gc_min_sleep_time),
 	ATTR_LIST(gc_max_sleep_time),
 	ATTR_LIST(gc_no_gc_sleep_time),
+	ATTR_LIST(gc_no_zoned_gc_percent),
+	ATTR_LIST(gc_boost_zoned_gc_percent),
+	ATTR_LIST(gc_valid_thresh_ratio),
 	ATTR_LIST(gc_idle),
 	ATTR_LIST(gc_urgent),
 	ATTR_LIST(reclaim_segments),
@@ -1138,8 +1166,10 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(min_seq_blocks),
 	ATTR_LIST(min_hot_blocks),
 	ATTR_LIST(min_ssr_sections),
+	ATTR_LIST(reserved_segments),
 	ATTR_LIST(max_victim_search),
 	ATTR_LIST(migration_granularity),
+	ATTR_LIST(migration_window_granularity),
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),
 	ATTR_LIST(ra_nid_pages),
@@ -1187,6 +1217,7 @@ static struct attribute *f2fs_attrs[] = {
 #endif
 #ifdef CONFIG_BLK_DEV_ZONED
 	ATTR_LIST(unusable_blocks_per_sec),
+	ATTR_LIST(blkzone_alloc_policy),
 #endif
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	ATTR_LIST(compr_written_block),
@@ -1200,6 +1231,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(atgc_candidate_count),
 	ATTR_LIST(atgc_age_weight),
 	ATTR_LIST(atgc_age_threshold),
+	ATTR_LIST(atgc_enabled),
 	ATTR_LIST(seq_file_ra_mul),
 	ATTR_LIST(gc_segment_mode),
 	ATTR_LIST(gc_reclaimed_segments),

fs/f2fs/verity.c

@@ -74,7 +74,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
 
-	if (pos + count > inode->i_sb->s_maxbytes)
+	if (pos + count > F2FS_BLK_TO_BYTES(max_file_blocks(inode)))
 		return -EFBIG;
 
 	while (count) {
@@ -237,7 +237,8 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
 	pos = le64_to_cpu(dloc.pos);
 
 	/* Get the descriptor */
-	if (pos + size < pos || pos + size > inode->i_sb->s_maxbytes ||
+	if (pos + size < pos ||
+	    pos + size > F2FS_BLK_TO_BYTES(max_file_blocks(inode)) ||
 	    pos < f2fs_verity_metadata_pos(inode) || size > INT_MAX) {
 		f2fs_warn(F2FS_I_SB(inode), "invalid verity xattr");
 		f2fs_handle_error(F2FS_I_SB(inode),

fs/f2fs/xattr.c

@@ -629,6 +629,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr, *last_base_addr;
 	int found, newsize;
@@ -772,9 +773,18 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
 			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
 		f2fs_set_encrypted_inode(inode);
-	if (S_ISDIR(inode->i_mode))
-		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
 
+	if (!S_ISDIR(inode->i_mode))
+		goto same;
+	/*
+	 * In restrict mode, fsync() always try to trigger checkpoint for all
+	 * metadata consistency, in other mode, it triggers checkpoint when
+	 * parent's xattr metadata was updated.
+	 */
+	if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
+		set_sbi_flag(sbi, SBI_NEED_CP);
+	else
+		f2fs_add_ino_entry(sbi, inode->i_ino, XATTR_DIR_INO);
 same:
 	if (is_inode_flag_set(inode, FI_ACL_MODE)) {
 		inode->i_mode = F2FS_I(inode)->i_acl_mode;

include/linux/f2fs_fs.h

@@ -19,7 +19,6 @@
 #define F2FS_BLKSIZE_BITS		PAGE_SHIFT /* bits for F2FS_BLKSIZE */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
 #define F2FS_EXTENSION_LEN		8	/* max size of extension */
-#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
@@ -28,6 +27,7 @@
 #define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_END_BYTES(blk)		(F2FS_BLK_TO_BYTES(blk + 1) - 1)
+#define F2FS_BLK_ALIGN(x)			(F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1))
 
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3
@@ -278,7 +278,7 @@ struct node_footer {
 #define F2FS_INLINE_DATA	0x02	/* file inline data flag */
 #define F2FS_INLINE_DENTRY	0x04	/* file inline dentry flag */
 #define F2FS_DATA_EXIST		0x08	/* file inline data exist flag */
-#define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries */
+#define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries (obsolete) */
 #define F2FS_EXTRA_ATTR		0x20	/* file having extra attribute */
 #define F2FS_PIN_FILE		0x40	/* file should not be gced */
 #define F2FS_COMPRESS_RELEASED	0x80	/* file released compressed blocks */

include/trace/events/f2fs.h

@@ -139,7 +139,8 @@ TRACE_DEFINE_ENUM(EX_BLOCK_AGE);
 		{ CP_NODE_NEED_CP,	"node needs cp" },		\
 		{ CP_FASTBOOT_MODE,	"fastboot mode" },		\
 		{ CP_SPEC_LOG_NUM,	"log type is 2" },		\
-		{ CP_RECOVER_DIR,	"dir needs recovery" })
+		{ CP_RECOVER_DIR,	"dir needs recovery" },		\
+		{ CP_XATTR_DIR,		"dir's xattr updated" })
 
 #define show_shutdown_mode(type)					\
 	__print_symbolic(type,						\