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
  ...

Author: torvalds

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);
@@ -991,15 +995,33 @@ 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 */
 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) {