1 files changed, 327 insertions, 181 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b72fa103b963..875aef2fc520 100644
--- a/fs/f2fs/super.c
+++ b/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>
@@ -44,24 +43,26 @@ static struct kmem_cache *f2fs_inode_cachep;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 
 const char *f2fs_fault_name[FAULT_MAX] = {
-	[FAULT_KMALLOC]		= "kmalloc",
-	[FAULT_KVMALLOC]	= "kvmalloc",
-	[FAULT_PAGE_ALLOC]	= "page alloc",
-	[FAULT_PAGE_GET]	= "page get",
-	[FAULT_ALLOC_NID]	= "alloc nid",
-	[FAULT_ORPHAN]		= "orphan",
-	[FAULT_BLOCK]		= "no more block",
-	[FAULT_DIR_DEPTH]	= "too big dir depth",
-	[FAULT_EVICT_INODE]	= "evict_inode fail",
-	[FAULT_TRUNCATE]	= "truncate fail",
-	[FAULT_READ_IO]		= "read IO error",
-	[FAULT_CHECKPOINT]	= "checkpoint error",
-	[FAULT_DISCARD]		= "discard error",
-	[FAULT_WRITE_IO]	= "write IO error",
-	[FAULT_SLAB_ALLOC]	= "slab alloc",
-	[FAULT_DQUOT_INIT]	= "dquot initialize",
-	[FAULT_LOCK_OP]		= "lock_op",
-	[FAULT_BLKADDR]		= "invalid blkaddr",
+	[FAULT_KMALLOC]			= "kmalloc",
+	[FAULT_KVMALLOC]		= "kvmalloc",
+	[FAULT_PAGE_ALLOC]		= "page alloc",
+	[FAULT_PAGE_GET]		= "page get",
+	[FAULT_ALLOC_NID]		= "alloc nid",
+	[FAULT_ORPHAN]			= "orphan",
+	[FAULT_BLOCK]			= "no more block",
+	[FAULT_DIR_DEPTH]		= "too big dir depth",
+	[FAULT_EVICT_INODE]		= "evict_inode fail",
+	[FAULT_TRUNCATE]		= "truncate fail",
+	[FAULT_READ_IO]			= "read IO error",
+	[FAULT_CHECKPOINT]		= "checkpoint error",
+	[FAULT_DISCARD]			= "discard error",
+	[FAULT_WRITE_IO]		= "write IO error",
+	[FAULT_SLAB_ALLOC]		= "slab alloc",
+	[FAULT_DQUOT_INIT]		= "dquot initialize",
+	[FAULT_LOCK_OP]			= "lock_op",
+	[FAULT_BLKADDR_VALIDITY]	= "invalid blkaddr",
+	[FAULT_BLKADDR_CONSISTENCE]	= "inconsistent blkaddr",
+	[FAULT_NO_SEGMENT]		= "no free segment",
 };
 
 int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
@@ -93,11 +94,26 @@ int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
 #endif
 
 /* f2fs-wide shrinker description */
-static struct shrinker f2fs_shrinker_info = {
-	.scan_objects = f2fs_shrink_scan,
-	.count_objects = f2fs_shrink_count,
-	.seeks = DEFAULT_SEEKS,
-};
+static struct shrinker *f2fs_shrinker_info;
+
+static int __init f2fs_init_shrinker(void)
+{
+	f2fs_shrinker_info = shrinker_alloc(0, "f2fs-shrinker");
+	if (!f2fs_shrinker_info)
+		return -ENOMEM;
+
+	f2fs_shrinker_info->count_objects = f2fs_shrink_count;
+	f2fs_shrinker_info->scan_objects = f2fs_shrink_scan;
+
+	shrinker_register(f2fs_shrinker_info);
+
+	return 0;
+}
+
+static void f2fs_exit_shrinker(void)
+{
+	shrinker_free(f2fs_shrinker_info);
+}
 
 enum {
 	Opt_gc_background,
@@ -304,7 +320,7 @@ struct kmem_cache *f2fs_cf_name_slab;
 static int __init f2fs_create_casefold_cache(void)
 {
 	f2fs_cf_name_slab = f2fs_kmem_cache_create("f2fs_casefolded_name",
-							F2FS_NAME_LEN);
+						   F2FS_NAME_LEN);
 	return f2fs_cf_name_slab ? 0 : -ENOMEM;
 }
 
@@ -694,6 +710,11 @@ 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;
@@ -1309,13 +1330,13 @@ default_check:
 		return -EINVAL;
 	}
 #endif
-#if !IS_ENABLED(CONFIG_UNICODE)
-	if (f2fs_sb_has_casefold(sbi)) {
+
+	if (!IS_ENABLED(CONFIG_UNICODE) && f2fs_sb_has_casefold(sbi)) {
 		f2fs_err(sbi,
 			"Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE");
 		return -EINVAL;
 	}
-#endif
+
 	/*
 	 * The BLKZONED feature indicates that the drive was formatted with
 	 * zone alignment optimization. This is optional for host-aware
@@ -1371,11 +1392,6 @@ default_check:
 		}
 	}
 
-	if (test_opt(sbi, DISABLE_CHECKPOINT) && f2fs_lfs_mode(sbi)) {
-		f2fs_err(sbi, "LFS is not compatible with checkpoint=disable");
-		return -EINVAL;
-	}
-
 	if (test_opt(sbi, ATGC) && f2fs_lfs_mode(sbi)) {
 		f2fs_err(sbi, "LFS is not compatible with ATGC");
 		return -EINVAL;
@@ -1499,6 +1515,12 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync)
 		inc_page_count(sbi, F2FS_DIRTY_IMETA);
 	}
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
+
+	/* if atomic write is not committed, set inode w/ atomic dirty */
+	if (!ret && f2fs_is_atomic_file(inode) &&
+			!is_inode_flag_set(inode, FI_ATOMIC_COMMITTED))
+		set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+
 	return ret;
 }
 
@@ -1559,7 +1581,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		if (i > 0)
-			blkdev_put(FDEV(i).bdev, sbi->sb);
+			bdev_fput(FDEV(i).bdev_file);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -1666,12 +1688,10 @@ static void f2fs_put_super(struct super_block *sb)
 
 	kvfree(sbi->ckpt);
 
-	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 
-	destroy_device_list(sbi);
 	f2fs_destroy_page_array_cache(sbi);
 	f2fs_destroy_xattr_caches(sbi);
 #ifdef CONFIG_QUOTA
@@ -1686,7 +1706,6 @@ static void f2fs_put_super(struct super_block *sb)
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
 #endif
-	kfree(sbi);
 }
 
 int f2fs_sync_fs(struct super_block *sb, int sync)
@@ -1768,26 +1787,32 @@ static int f2fs_statfs_project(struct super_block *sb,
 
 	limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
 					dquot->dq_dqb.dqb_bhardlimit);
-	if (limit)
-		limit >>= sb->s_blocksize_bits;
+	limit >>= sb->s_blocksize_bits;
+
+	if (limit) {
+		uint64_t remaining = 0;
 
-	if (limit && buf->f_blocks > limit) {
 		curblock = (dquot->dq_dqb.dqb_curspace +
 			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
-		buf->f_blocks = limit;
-		buf->f_bfree = buf->f_bavail =
-			(buf->f_blocks > curblock) ?
-			 (buf->f_blocks - curblock) : 0;
+		if (limit > curblock)
+			remaining = limit - curblock;
+
+		buf->f_blocks = min(buf->f_blocks, limit);
+		buf->f_bfree = min(buf->f_bfree, remaining);
+		buf->f_bavail = min(buf->f_bavail, remaining);
 	}
 
 	limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
 					dquot->dq_dqb.dqb_ihardlimit);
 
-	if (limit && buf->f_files > limit) {
-		buf->f_files = limit;
-		buf->f_ffree =
-			(buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
-			 (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+	if (limit) {
+		uint64_t remaining = 0;
+
+		if (limit > dquot->dq_dqb.dqb_curinodes)
+			remaining = limit - dquot->dq_dqb.dqb_curinodes;
+
+		buf->f_files = min(buf->f_files, limit);
+		buf->f_ffree = min(buf->f_ffree, remaining);
 	}
 
 	spin_unlock(&dquot->dq_dqb_lock);
@@ -1845,9 +1870,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid    = u64_to_fsid(id);
 
 #ifdef CONFIG_QUOTA
-	if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
+	if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) &&
 			sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
-		f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf);
+		f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf);
 	}
 #endif
 	return 0;
@@ -2205,6 +2230,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 			.init_gc_type = FG_GC,
 			.should_migrate_blocks = false,
 			.err_gc_skipped = true,
+			.no_bg_gc = true,
 			.nr_free_secs = 1 };
 
 		f2fs_down_write(&sbi->gc_lock);
@@ -2284,9 +2310,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	unsigned long old_sb_flags;
 	int err;
 	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 need_restart_discard = false, need_stop_discard = false;
+	bool need_enable_checkpoint = false, need_disable_checkpoint = false;
 	bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE);
 	bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE);
 	bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT);
@@ -2339,6 +2365,17 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if (err)
 		goto restore_opts;
 
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_has_blkzoned(sbi) &&
+		sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) {
+		f2fs_err(sbi,
+			"zoned: max open zones %u is too small, need at least %u open zones",
+				 sbi->max_open_zones, F2FS_OPTION(sbi).active_logs);
+		err = -EINVAL;
+		goto restore_opts;
+	}
+#endif
+
 	/* flush outstanding errors before changing fs state */
 	flush_work(&sbi->s_error_work);
 
@@ -2443,24 +2480,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		clear_sbi_flag(sbi, SBI_IS_CLOSE);
 	}
 
-	if ((*flags & SB_RDONLY) || test_opt(sbi, DISABLE_CHECKPOINT) ||
-			!test_opt(sbi, MERGE_CHECKPOINT)) {
-		f2fs_stop_ckpt_thread(sbi);
-		need_restart_ckpt = true;
-	} else {
-		/* Flush if the prevous checkpoint, if exists. */
-		f2fs_flush_ckpt_thread(sbi);
-
-		err = f2fs_start_ckpt_thread(sbi);
-		if (err) {
-			f2fs_err(sbi,
-			    "Failed to start F2FS issue_checkpoint_thread (%d)",
-			    err);
-			goto restore_gc;
-		}
-		need_stop_ckpt = true;
-	}
-
 	/*
 	 * We stop issue flush thread if FS is mounted as RO
 	 * or if flush_merge is not passed in mount option.
@@ -2472,7 +2491,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	} else {
 		err = f2fs_create_flush_cmd_control(sbi);
 		if (err)
-			goto restore_ckpt;
+			goto restore_gc;
 		need_stop_flush = true;
 	}
 
@@ -2494,8 +2513,31 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			err = f2fs_disable_checkpoint(sbi);
 			if (err)
 				goto restore_discard;
+			need_enable_checkpoint = true;
 		} else {
 			f2fs_enable_checkpoint(sbi);
+			need_disable_checkpoint = true;
+		}
+	}
+
+	/*
+	 * Place this routine at the end, since a new checkpoint would be
+	 * triggered while remount and we need to take care of it before
+	 * returning from remount.
+	 */
+	if ((*flags & SB_RDONLY) || test_opt(sbi, DISABLE_CHECKPOINT) ||
+			!test_opt(sbi, MERGE_CHECKPOINT)) {
+		f2fs_stop_ckpt_thread(sbi);
+	} else {
+		/* Flush if the prevous checkpoint, if exists. */
+		f2fs_flush_ckpt_thread(sbi);
+
+		err = f2fs_start_ckpt_thread(sbi);
+		if (err) {
+			f2fs_err(sbi,
+			    "Failed to start F2FS issue_checkpoint_thread (%d)",
+			    err);
+			goto restore_checkpoint;
 		}
 	}
 
@@ -2513,6 +2555,13 @@ skip:
 	adjust_unusable_cap_perc(sbi);
 	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	return 0;
+restore_checkpoint:
+	if (need_enable_checkpoint) {
+		f2fs_enable_checkpoint(sbi);
+	} else if (need_disable_checkpoint) {
+		if (f2fs_disable_checkpoint(sbi))
+			f2fs_warn(sbi, "checkpoint has not been disabled");
+	}
 restore_discard:
 	if (need_restart_discard) {
 		if (f2fs_start_discard_thread(sbi))
@@ -2528,13 +2577,6 @@ restore_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))
@@ -2673,7 +2715,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	int offset = off & (sb->s_blocksize - 1);
 	size_t towrite = len;
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	int err = 0;
 	int tocopy;
@@ -2683,7 +2725,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 								towrite);
 retry:
 		err = a_ops->write_begin(NULL, mapping, off, tocopy,
-							&page, &fsdata);
+							&folio, &fsdata);
 		if (unlikely(err)) {
 			if (err == -ENOMEM) {
 				f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
@@ -2693,10 +2735,10 @@ retry:
 			break;
 		}
 
-		memcpy_to_page(page, offset, data, tocopy);
+		memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy);
 
 		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
-						page, fsdata);
+						folio, fsdata);
 		offset = 0;
 		towrite -= tocopy;
 		off += tocopy;
@@ -2706,7 +2748,7 @@ retry:
 
 	if (len == towrite)
 		return err;
-	inode->i_mtime = inode_set_ctime_current(inode);
+	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	f2fs_mark_inode_dirty_sync(inode, false);
 	return len - towrite;
 }
@@ -3200,13 +3242,6 @@ static bool f2fs_has_stable_inodes(struct super_block *sb)
 	return true;
 }
 
-static void f2fs_get_ino_and_lblk_bits(struct super_block *sb,
-				       int *ino_bits_ret, int *lblk_bits_ret)
-{
-	*ino_bits_ret = 8 * sizeof(nid_t);
-	*lblk_bits_ret = 8 * sizeof(block_t);
-}
-
 static struct block_device **f2fs_get_devices(struct super_block *sb,
 					      unsigned int *num_devs)
 {
@@ -3228,13 +3263,15 @@ static struct block_device **f2fs_get_devices(struct super_block *sb,
 }
 
 static const struct fscrypt_operations f2fs_cryptops = {
-	.key_prefix		= "f2fs:",
+	.needs_bounce_pages	= 1,
+	.has_32bit_inodes	= 1,
+	.supports_subblock_data_units = 1,
+	.legacy_key_prefix	= "f2fs:",
 	.get_context		= f2fs_get_context,
 	.set_context		= f2fs_set_context,
 	.get_dummy_policy	= f2fs_get_dummy_policy,
 	.empty_dir		= f2fs_empty_dir,
 	.has_stable_inodes	= f2fs_has_stable_inodes,
-	.get_ino_and_lblk_bits	= f2fs_get_ino_and_lblk_bits,
 	.get_devices		= f2fs_get_devices,
 };
 #endif
@@ -3279,6 +3316,7 @@ static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid,
 }
 
 static const struct export_operations f2fs_export_ops = {
+	.encode_fh = generic_encode_ino32_fh,
 	.fh_to_dentry = f2fs_fh_to_dentry,
 	.fh_to_parent = f2fs_fh_to_parent,
 	.get_parent = f2fs_get_parent,
@@ -3312,27 +3350,54 @@ loff_t max_file_blocks(struct inode *inode)
 	leaf_count *= NIDS_PER_BLOCK;
 	result += leaf_count;
 
+	/*
+	 * For compatibility with FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{64,32} with
+	 * a 4K crypto data unit, we must restrict the max filesize to what can
+	 * fit within U32_MAX + 1 data units.
+	 */
+
+	result = umin(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);
+	bio_put(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);
@@ -3407,7 +3472,7 @@ 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)",
@@ -3420,12 +3485,11 @@ 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;
 
@@ -3451,7 +3515,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		}
 	}
 
-	/* Currently, support only 4KB block size */
+	/* only support block_size equals to PAGE_SIZE */
 	if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) {
 		f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u",
 			  le32_to_cpu(raw_super->log_blocksize),
@@ -3466,7 +3530,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		return -EFSCORRUPTED;
 	}
 
-	/* Currently, support 512/1024/2048/4096 bytes sector size */
+	/* Currently, support 512/1024/2048/4096/16K bytes sector size */
 	if (le32_to_cpu(raw_super->log_sectorsize) >
 				F2FS_MAX_LOG_SECTOR_SIZE ||
 		le32_to_cpu(raw_super->log_sectorsize) <
@@ -3583,7 +3647,7 @@ 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;
@@ -3604,6 +3668,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	block_t user_block_count, valid_user_blocks;
 	block_t avail_node_count, valid_node_count;
 	unsigned int nat_blocks, nat_bits_bytes, nat_bits_blocks;
+	unsigned int sit_blk_cnt;
 	int i, j;
 
 	total = le32_to_cpu(raw_super->segment_count);
@@ -3715,6 +3780,13 @@ skip_cross:
 		return 1;
 	}
 
+	sit_blk_cnt = DIV_ROUND_UP(main_segs, SIT_ENTRY_PER_BLOCK);
+	if (sit_bitmap_size * 8 < sit_blk_cnt) {
+		f2fs_err(sbi, "Wrong bitmap size: sit: %u, sit_blk_cnt:%u",
+			 sit_bitmap_size, sit_blk_cnt);
+		return 1;
+	}
+
 	cp_pack_start_sum = __start_sum_addr(sbi);
 	cp_payload = __cp_payload(sbi);
 	if (cp_pack_start_sum < cp_payload + 1 ||
@@ -3766,9 +3838,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
 	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
 	sbi->total_sections = le32_to_cpu(raw_super->section_count);
-	sbi->total_node_count =
-		((le32_to_cpu(raw_super->segment_count_nat) / 2) *
-		NAT_ENTRY_PER_BLOCK) << sbi->log_blocks_per_seg;
+	sbi->total_node_count = SEGS_TO_BLKS(sbi,
+			((le32_to_cpu(raw_super->segment_count_nat) / 2) *
+			NAT_ENTRY_PER_BLOCK));
 	F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino);
 	F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino);
 	F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino);
@@ -3778,6 +3850,8 @@ 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;
@@ -3872,11 +3946,24 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 	sector_t nr_sectors = bdev_nr_sectors(bdev);
 	struct f2fs_report_zones_args rep_zone_arg;
 	u64 zone_sectors;
+	unsigned int max_open_zones;
 	int ret;
 
 	if (!f2fs_sb_has_blkzoned(sbi))
 		return 0;
 
+	if (bdev_is_zoned(FDEV(devi).bdev)) {
+		max_open_zones = bdev_max_open_zones(bdev);
+		if (max_open_zones && (max_open_zones < sbi->max_open_zones))
+			sbi->max_open_zones = max_open_zones;
+		if (sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) {
+			f2fs_err(sbi,
+				"zoned: max open zones %u is too small, need at least %u open zones",
+				sbi->max_open_zones, F2FS_OPTION(sbi).active_logs);
+			return -EINVAL;
+		}
+	}
+
 	zone_sectors = bdev_zone_sectors(bdev);
 	if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
 				SECTOR_TO_BLOCK(zone_sectors))
@@ -3917,7 +4004,7 @@ 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;
 
@@ -3926,32 +4013,32 @@ 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 */
@@ -3965,7 +4052,8 @@ 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;
 
@@ -3983,22 +4071,24 @@ 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;
 }
 
@@ -4033,7 +4123,9 @@ static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi)
 
 	f2fs_up_write(&sbi->sb_lock);
 	if (err)
-		f2fs_err(sbi, "f2fs_commit_super fails to record err:%d", err);
+		f2fs_err_ratelimited(sbi,
+			"f2fs_commit_super fails to record stop_reason, err:%d",
+			err);
 }
 
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag)
@@ -4076,8 +4168,9 @@ static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error)
 
 	err = f2fs_commit_super(sbi, false);
 	if (err)
-		f2fs_err(sbi, "f2fs_commit_super fails to record errors:%u, err:%d",
-								error, err);
+		f2fs_err_ratelimited(sbi,
+			"f2fs_commit_super fails to record errors:%u, err:%d",
+			error, err);
 out_unlock:
 	f2fs_up_write(&sbi->sb_lock);
 }
@@ -4168,6 +4261,37 @@ static void f2fs_record_error_work(struct work_struct *work)
 	f2fs_record_stop_reason(sbi);
 }
 
+static inline unsigned int get_first_seq_zone_segno(struct f2fs_sb_info *sbi)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+	unsigned int zoneno, total_zones;
+	int devi;
+
+	if (!f2fs_sb_has_blkzoned(sbi))
+		return NULL_SEGNO;
+
+	for (devi = 0; devi < sbi->s_ndevs; devi++) {
+		if (!bdev_is_zoned(FDEV(devi).bdev))
+			continue;
+
+		total_zones = GET_ZONE_FROM_SEG(sbi, FDEV(devi).total_segments);
+
+		for (zoneno = 0; zoneno < total_zones; zoneno++) {
+			unsigned int segs, blks;
+
+			if (!f2fs_zone_is_seq(sbi, devi, zoneno))
+				continue;
+
+			segs = GET_SEG_FROM_SEC(sbi,
+					zoneno * sbi->secs_per_zone);
+			blks = SEGS_TO_BLKS(sbi, segs);
+			return GET_SEGNO(sbi, FDEV(devi).start_blk + blks);
+		}
+	}
+#endif
+	return NULL_SEGNO;
+}
+
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -4196,10 +4320,22 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 
 	logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
 	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++) {
+		if (max_devices == 1) {
+			FDEV(i).total_segments =
+				le32_to_cpu(raw_super->segment_count_main);
+			FDEV(i).start_blk = 0;
+			FDEV(i).end_blk = FDEV(i).total_segments *
+						BLKS_PER_SEG(sbi);
+		}
+
 		if (i == 0)
-			FDEV(0).bdev = sbi->sb->s_bdev;
+			FDEV(0).bdev_file = sbi->sb->s_bdev_file;
 		else if (!RDEV(i).path[0])
 			break;
 
@@ -4211,21 +4347,22 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			if (i == 0) {
 				FDEV(i).start_blk = 0;
 				FDEV(i).end_blk = FDEV(i).start_blk +
-				    (FDEV(i).total_segments <<
-				    sbi->log_blocks_per_seg) - 1 +
-				    le32_to_cpu(raw_super->segment0_blkaddr);
+					SEGS_TO_BLKS(sbi,
+					FDEV(i).total_segments) - 1 +
+					le32_to_cpu(raw_super->segment0_blkaddr);
 			} else {
 				FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
 				FDEV(i).end_blk = FDEV(i).start_blk +
-					(FDEV(i).total_segments <<
-					sbi->log_blocks_per_seg) - 1;
-				FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
-					mode, sbi->sb, NULL);
+						SEGS_TO_BLKS(sbi,
+						FDEV(i).total_segments) - 1;
+				FDEV(i).bdev_file = bdev_file_open_by_path(
+					FDEV(i).path, mode, sbi->sb, NULL);
 			}
 		}
-		if (IS_ERR(FDEV(i).bdev))
-			return PTR_ERR(FDEV(i).bdev);
+		if (IS_ERR(FDEV(i).bdev_file))
+			return PTR_ERR(FDEV(i).bdev_file);
 
+		FDEV(i).bdev = file_bdev(FDEV(i).bdev_file);
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
@@ -4233,24 +4370,21 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			sbi->aligned_blksize = false;
 
 #ifdef CONFIG_BLK_DEV_ZONED
-		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
-				!f2fs_sb_has_blkzoned(sbi)) {
-			f2fs_err(sbi, "Zoned block device feature not enabled");
-			return -EINVAL;
-		}
-		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+		if (bdev_is_zoned(FDEV(i).bdev)) {
+			if (!f2fs_sb_has_blkzoned(sbi)) {
+				f2fs_err(sbi, "Zoned block device feature not enabled");
+				return -EINVAL;
+			}
 			if (init_blkz_info(sbi, i)) {
 				f2fs_err(sbi, "Failed to initialize F2FS blkzone information");
 				return -EINVAL;
 			}
 			if (max_devices == 1)
 				break;
-			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: Host-managed)",
 				  i, FDEV(i).path,
 				  FDEV(i).total_segments,
-				  FDEV(i).start_blk, FDEV(i).end_blk,
-				  bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
-				  "Host-aware" : "Host-managed");
+				  FDEV(i).start_blk, FDEV(i).end_blk);
 			continue;
 		}
 #endif
@@ -4448,7 +4582,8 @@ try_onemore:
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
-	memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+	super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
+	super_set_sysfs_name_bdev(sb);
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	/* init f2fs-specific super block info */
@@ -4565,6 +4700,9 @@ try_onemore:
 	/* For write statistics */
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 
+	/* get segno of first zoned block device */
+	sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi);
+
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
 	if (__exist_node_summaries(sbi))
@@ -4599,6 +4737,7 @@ try_onemore:
 		goto free_node_inode;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root); /* allocate root dentry */
 	if (!sb->s_root) {
 		err = -ENOMEM;
@@ -4682,19 +4821,25 @@ try_onemore:
 #ifdef CONFIG_QUOTA
 	f2fs_recover_quota_end(sbi, quota_enabled);
 #endif
-
+reset_checkpoint:
 	/*
 	 * If the f2fs is not readonly and fsync data recovery succeeds,
 	 * check zoned block devices' write pointer consistency.
 	 */
-	if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
-		err = f2fs_check_write_pointer(sbi);
-		if (err)
-			goto free_meta;
+	if (f2fs_sb_has_blkzoned(sbi) && !f2fs_readonly(sb)) {
+		int err2;
+
+		f2fs_notice(sbi, "Checking entire write pointers");
+		err2 = f2fs_check_write_pointer(sbi);
+		if (err2)
+			err = err2;
 	}
+	if (err)
+		goto free_meta;
 
-reset_checkpoint:
-	f2fs_init_inmem_curseg(sbi);
+	err = f2fs_init_inmem_curseg(sbi);
+	if (err)
+		goto sync_free_meta;
 
 	/* f2fs_recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -4818,6 +4963,7 @@ free_sbi:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
+	sb->s_fs_info = NULL;
 
 	/* give only one another chance */
 	if (retry_cnt > 0 && skip_recovery) {
@@ -4836,9 +4982,9 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 
 static void kill_f2fs_super(struct super_block *sb)
 {
-	if (sb->s_root) {
-		struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
+	if (sb->s_root) {
 		set_sbi_flag(sbi, SBI_IS_CLOSE);
 		f2fs_stop_gc_thread(sbi);
 		f2fs_stop_discard_thread(sbi);
@@ -4865,6 +5011,12 @@ static void kill_f2fs_super(struct super_block *sb)
 			sb->s_flags &= ~SB_RDONLY;
 	}
 	kill_block_super(sb);
+	/* Release block devices last, after fscrypt_destroy_keyring(). */
+	if (sbi) {
+		destroy_device_list(sbi);
+		kfree(sbi);
+		sb->s_fs_info = NULL;
+	}
 }
 
 static struct file_system_type f2fs_fs_type = {
@@ -4898,12 +5050,6 @@ static int __init init_f2fs_fs(void)
 {
 	int err;
 
-	if (PAGE_SIZE != F2FS_BLKSIZE) {
-		printk("F2FS not supported on PAGE_SIZE(%lu) != %d\n",
-				PAGE_SIZE, F2FS_BLKSIZE);
-		return -EINVAL;
-	}
-
 	err = init_inodecache();
 	if (err)
 		goto fail;
@@ -4928,12 +5074,9 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_init_sysfs();
 	if (err)
 		goto free_garbage_collection_cache;
-	err = register_shrinker(&f2fs_shrinker_info, "f2fs-shrinker");
+	err = f2fs_init_shrinker();
 	if (err)
 		goto free_sysfs;
-	err = register_filesystem(&f2fs_fs_type);
-	if (err)
-		goto free_shrinker;
 	f2fs_create_root_stats();
 	err = f2fs_init_post_read_processing();
 	if (err)
@@ -4956,7 +5099,12 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_create_casefold_cache();
 	if (err)
 		goto free_compress_cache;
+	err = register_filesystem(&f2fs_fs_type);
+	if (err)
+		goto free_casefold_cache;
 	return 0;
+free_casefold_cache:
+	f2fs_destroy_casefold_cache();
 free_compress_cache:
 	f2fs_destroy_compress_cache();
 free_compress_mempool:
@@ -4971,9 +5119,7 @@ free_post_read:
 	f2fs_destroy_post_read_processing();
 free_root_stats:
 	f2fs_destroy_root_stats();
-	unregister_filesystem(&f2fs_fs_type);
-free_shrinker:
-	unregister_shrinker(&f2fs_shrinker_info);
+	f2fs_exit_shrinker();
 free_sysfs:
 	f2fs_exit_sysfs();
 free_garbage_collection_cache:
@@ -4996,6 +5142,7 @@ fail:
 
 static void __exit exit_f2fs_fs(void)
 {
+	unregister_filesystem(&f2fs_fs_type);
 	f2fs_destroy_casefold_cache();
 	f2fs_destroy_compress_cache();
 	f2fs_destroy_compress_mempool();
@@ -5004,8 +5151,7 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_iostat_processing();
 	f2fs_destroy_post_read_processing();
 	f2fs_destroy_root_stats();
-	unregister_filesystem(&f2fs_fs_type);
-	unregister_shrinker(&f2fs_shrinker_info);
+	f2fs_exit_shrinker();
 	f2fs_exit_sysfs();
 	f2fs_destroy_garbage_collection_cache();
 	f2fs_destroy_extent_cache();