Merge tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "A pretty small update including mostly minor bug fixes in zoned
  storage along with the large section support.

  Enhancements:
   - add support for FS_IOC_GETFSSYSFSPATH
   - enable atgc dynamically if conditions are met
   - use new ioprio Macro to get ckpt thread ioprio level
   - remove unreachable lazytime mount option parsing

  Bug fixes:
   - fix null reference error when checking end of zone
   - fix start segno of large section
   - fix to cover read extent cache access with lock
   - don't dirty inode for readonly filesystem
   - allocate a new section if curseg is not the first seg in its zone
   - only fragment segment in the same section
   - truncate preallocated blocks in f2fs_file_open()
   - fix to avoid use SSR allocate when do defragment
   - fix to force buffered IO on inline_data inode

  And some minor code clean-ups and sanity checks"

* tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (26 commits)
  f2fs: clean up addrs_per_{inode,block}()
  f2fs: clean up F2FS_I()
  f2fs: use meta inode for GC of COW file
  f2fs: use meta inode for GC of atomic file
  f2fs: only fragment segment in the same section
  f2fs: fix to update user block counts in block_operations()
  f2fs: remove unreachable lazytime mount option parsing
  f2fs: fix null reference error when checking end of zone
  f2fs: fix start segno of large section
  f2fs: remove redundant sanity check in sanity_check_inode()
  f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid
  f2fs: fix to use mnt_{want,drop}_write_file replace file_{start,end}_wrtie
  f2fs: clean up set REQ_RAHEAD given rac
  f2fs: enable atgc dynamically if conditions are met
  f2fs: fix to truncate preallocated blocks in f2fs_file_open()
  f2fs: fix to cover read extent cache access with lock
  f2fs: fix return value of f2fs_convert_inline_inode()
  f2fs: use new ioprio Macro to get ckpt thread ioprio level
  f2fs: fix to don't dirty inode for readonly filesystem
  f2fs: fix to avoid use SSR allocate when do defragment
  ...

fs/f2fs/checkpoint.c

@@ -1186,6 +1186,11 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi)
 	ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
 	ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
 	ckpt->next_free_nid = cpu_to_le32(last_nid);
+
+	/* update user_block_counts */
+	sbi->last_valid_block_count = sbi->total_valid_block_count;
+	percpu_counter_set(&sbi->alloc_valid_block_count, 0);
+	percpu_counter_set(&sbi->rf_node_block_count, 0);
 }
 
 static bool __need_flush_quota(struct f2fs_sb_info *sbi)
@@ -1575,11 +1580,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		start_blk += NR_CURSEG_NODE_TYPE;
 	}
 
-	/* update user_block_counts */
-	sbi->last_valid_block_count = sbi->total_valid_block_count;
-	percpu_counter_set(&sbi->alloc_valid_block_count, 0);
-	percpu_counter_set(&sbi->rf_node_block_count, 0);
-
 	/* Here, we have one bio having CP pack except cp pack 2 page */
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
 	/* Wait for all dirty meta pages to be submitted for IO */
@@ -1718,6 +1718,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	}
 
 	f2fs_restore_inmem_curseg(sbi);
+	f2fs_reinit_atgc_curseg(sbi);
 	stat_inc_cp_count(sbi);
 stop:
 	unblock_operations(sbi);

fs/f2fs/compress.c

@@ -1100,7 +1100,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 		struct bio *bio = NULL;
 
 		ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size,
-					&last_block_in_bio, false, true);
+					&last_block_in_bio, NULL, true);
 		f2fs_put_rpages(cc);
 		f2fs_destroy_compress_ctx(cc, true);
 		if (ret)

fs/f2fs/data.c

@@ -925,6 +925,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 #ifdef CONFIG_BLK_DEV_ZONED
 static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
+	struct block_device *bdev = sbi->sb->s_bdev;
 	int devi = 0;
 
 	if (f2fs_is_multi_device(sbi)) {
@@ -935,8 +936,9 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
 			return false;
 		}
 		blkaddr -= FDEV(devi).start_blk;
+		bdev = FDEV(devi).bdev;
 	}
-	return bdev_is_zoned(FDEV(devi).bdev) &&
+	return bdev_is_zoned(bdev) &&
 		f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
 		(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
 }
@@ -2067,12 +2069,17 @@ static inline loff_t f2fs_readpage_limit(struct inode *inode)
 	return i_size_read(inode);
 }
 
+static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac)
+{
+	return rac ? REQ_RAHEAD : 0;
+}
+
 static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 					unsigned nr_pages,
 					struct f2fs_map_blocks *map,
 					struct bio **bio_ret,
 					sector_t *last_block_in_bio,
-					bool is_readahead)
+					struct readahead_control *rac)
 {
 	struct bio *bio = *bio_ret;
 	const unsigned blocksize = blks_to_bytes(inode, 1);
@@ -2148,7 +2155,7 @@ static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 	}
 	if (bio == NULL) {
 		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
-				is_readahead ? REQ_RAHEAD : 0, index,
+				f2fs_ra_op_flags(rac), index,
 				false);
 		if (IS_ERR(bio)) {
 			ret = PTR_ERR(bio);
@@ -2178,7 +2185,7 @@ static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 				unsigned nr_pages, sector_t *last_block_in_bio,
-				bool is_readahead, bool for_write)
+				struct readahead_control *rac, bool for_write)
 {
 	struct dnode_of_data dn;
 	struct inode *inode = cc->inode;
@@ -2301,7 +2308,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 
 		if (!bio) {
 			bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
-					is_readahead ? REQ_RAHEAD : 0,
+					f2fs_ra_op_flags(rac),
 					page->index, for_write);
 			if (IS_ERR(bio)) {
 				ret = PTR_ERR(bio);
@@ -2399,7 +2406,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
 			ret = f2fs_read_multi_pages(&cc, &bio,
 						max_nr_pages,
 						&last_block_in_bio,
-						rac != NULL, false);
+						rac, false);
 			f2fs_destroy_compress_ctx(&cc, false);
 			if (ret)
 				goto set_error_page;
@@ -2449,7 +2456,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
 				ret = f2fs_read_multi_pages(&cc, &bio,
 							max_nr_pages,
 							&last_block_in_bio,
-							rac != NULL, false);
+							rac, false);
 				f2fs_destroy_compress_ctx(&cc, false);
 			}
 		}
@@ -2601,7 +2608,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
 		return true;
 	if (IS_NOQUOTA(inode))
 		return true;
-	if (f2fs_is_atomic_file(inode))
+	if (f2fs_used_in_atomic_write(inode))
 		return true;
 	/* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */
 	if (f2fs_compressed_file(inode) &&
@@ -2688,7 +2695,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 	}
 
 	/* wait for GCed page writeback via META_MAPPING */
-	if (fio->post_read)
+	if (fio->meta_gc)
 		f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
 
 	/*
@@ -2783,7 +2790,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 		.submitted = 0,
 		.compr_blocks = compr_blocks,
 		.need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
-		.post_read = f2fs_post_read_required(inode) ? 1 : 0,
+		.meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
 		.io_type = io_type,
 		.io_wbc = wbc,
 		.bio = bio,

fs/f2fs/extent_cache.c

@@ -19,33 +19,23 @@
 #include "node.h"
 #include <trace/events/f2fs.h>
 
-bool sanity_check_extent_cache(struct inode *inode)
+bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct extent_tree *et = fi->extent_tree[EX_READ];
-	struct extent_info *ei;
-
-	if (!et)
-		return true;
+	struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
+	struct extent_info ei;
 
-	ei = &et->largest;
-	if (!ei->len)
-		return true;
+	get_read_extent_info(&ei, i_ext);
 
-	/* Let's drop, if checkpoint got corrupted. */
-	if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) {
-		ei->len = 0;
-		et->largest_updated = true;
+	if (!ei.len)
 		return true;
-	}
 
-	if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) ||
-	    !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+	if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) ||
+	    !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1,
 					DATA_GENERIC_ENHANCE)) {
 		f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
 			  __func__, inode->i_ino,
-			  ei->blk, ei->fofs, ei->len);
+			  ei.blk, ei.fofs, ei.len);
 		return false;
 	}
 	return true;
@@ -394,24 +384,22 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 
 	if (!__may_extent_tree(inode, EX_READ)) {
 		/* drop largest read extent */
-		if (i_ext && i_ext->len) {
+		if (i_ext->len) {
 			f2fs_wait_on_page_writeback(ipage, NODE, true, true);
 			i_ext->len = 0;
 			set_page_dirty(ipage);
 		}
-		goto out;
+		set_inode_flag(inode, FI_NO_EXTENT);
+		return;
 	}
 
 	et = __grab_extent_tree(inode, EX_READ);
 
-	if (!i_ext || !i_ext->len)
-		goto out;
-
 	get_read_extent_info(&ei, i_ext);
 
 	write_lock(&et->lock);
-	if (atomic_read(&et->node_cnt))
-		goto unlock_out;
+	if (atomic_read(&et->node_cnt) || !ei.len)
+		goto skip;
 
 	en = __attach_extent_node(sbi, et, &ei, NULL,
 				&et->root.rb_root.rb_node, true);
@@ -423,11 +411,13 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 		list_add_tail(&en->list, &eti->extent_list);
 		spin_unlock(&eti->extent_lock);
 	}
-unlock_out:
+skip:
+	/* Let's drop, if checkpoint got corrupted. */
+	if (f2fs_cp_error(sbi)) {
+		et->largest.len = 0;
+		et->largest_updated = true;
+	}
 	write_unlock(&et->lock);
-out:
-	if (!F2FS_I(inode)->extent_tree[EX_READ])
-		set_inode_flag(inode, FI_NO_EXTENT);
 }
 
 void f2fs_init_age_extent_tree(struct inode *inode)

fs/f2fs/f2fs.h

@@ -803,6 +803,7 @@ enum {
 	FI_COW_FILE,		/* indicate COW file */
 	FI_ATOMIC_COMMITTED,	/* indicate atomic commit completed except disk sync */
 	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
+	FI_OPENED_FILE,		/* indicate file has been opened */
 	FI_MAX,			/* max flag, never be used */
 };
 
@@ -842,7 +843,11 @@ struct f2fs_inode_info {
 	struct task_struct *atomic_write_task;	/* store atomic write task */
 	struct extent_tree *extent_tree[NR_EXTENT_CACHES];
 					/* cached extent_tree entry */
+	union {
 		struct inode *cow_inode;	/* copy-on-write inode for atomic write */
+		struct inode *atomic_inode;
+					/* point to atomic_inode, available only for cow_inode */
+	};
 
 	/* avoid racing between foreground op and gc */
 	struct f2fs_rwsem i_gc_rwsem[2];
@@ -1210,7 +1215,7 @@ struct f2fs_io_info {
 	unsigned int in_list:1;		/* indicate fio is in io_list */
 	unsigned int is_por:1;		/* indicate IO is from recovery or not */
 	unsigned int encrypted:1;	/* indicate file is encrypted */
-	unsigned int post_read:1;	/* require post read */
+	unsigned int meta_gc:1;		/* require meta inode GC */
 	enum iostat_type io_type;	/* io type */
 	struct writeback_control *io_wbc; /* writeback control */
 	struct bio **bio;		/* bio for ipu */
@@ -3222,21 +3227,15 @@ static inline bool f2fs_need_compress_data(struct inode *inode)
 	return false;
 }
 
-static inline unsigned int addrs_per_inode(struct inode *inode)
+static inline unsigned int addrs_per_page(struct inode *inode,
+							bool is_inode)
 {
-	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
-				get_inline_xattr_addrs(inode);
+	unsigned int addrs = is_inode ? (CUR_ADDRS_PER_INODE(inode) -
+			get_inline_xattr_addrs(inode)) : DEF_ADDRS_PER_BLOCK;
 
-	if (!f2fs_compressed_file(inode))
-		return addrs;
+	if (f2fs_compressed_file(inode))
 		return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
-}
-
-static inline unsigned int addrs_per_block(struct inode *inode)
-{
-	if (!f2fs_compressed_file(inode))
-		return DEF_ADDRS_PER_BLOCK;
-	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
+	return addrs;
 }
 
 static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
@@ -3706,6 +3705,7 @@ void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
 int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
 bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno);
 int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi);
 void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
 void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
 int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
@@ -4163,7 +4163,7 @@ extern struct kmem_cache *f2fs_inode_entry_slab;
  * inline.c
  */
 bool f2fs_may_inline_data(struct inode *inode);
-bool f2fs_sanity_check_inline_data(struct inode *inode);
+bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage);
 bool f2fs_may_inline_dentry(struct inode *inode);
 void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage);
 void f2fs_truncate_inline_inode(struct inode *inode,
@@ -4204,7 +4204,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
 /*
  * extent_cache.c
  */
-bool sanity_check_extent_cache(struct inode *inode);
+bool sanity_check_extent_cache(struct inode *inode, struct page *ipage);
 void f2fs_init_extent_tree(struct inode *inode);
 void f2fs_drop_extent_tree(struct inode *inode);
 void f2fs_destroy_extent_node(struct inode *inode);
@@ -4275,6 +4275,16 @@ static inline bool f2fs_post_read_required(struct inode *inode)
 		f2fs_compressed_file(inode);
 }
 
+static inline bool f2fs_used_in_atomic_write(struct inode *inode)
+{
+	return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode);
+}
+
+static inline bool f2fs_meta_inode_gc_required(struct inode *inode)
+{
+	return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode);
+}
+
 /*
  * compress.c
  */
@@ -4310,7 +4320,7 @@ void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
 				unsigned int llen, unsigned int c_len);
 int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 				unsigned nr_pages, sector_t *last_block_in_bio,
-				bool is_readahead, bool for_write);
+				struct readahead_control *rac, bool for_write);
 struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
 void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed,
 				bool in_task);
@@ -4401,22 +4411,18 @@ static inline int set_compress_context(struct inode *inode)
 {
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 
-	F2FS_I(inode)->i_compress_algorithm =
-			F2FS_OPTION(sbi).compress_algorithm;
-	F2FS_I(inode)->i_log_cluster_size =
-			F2FS_OPTION(sbi).compress_log_size;
-	F2FS_I(inode)->i_compress_flag =
-			F2FS_OPTION(sbi).compress_chksum ?
+	fi->i_compress_algorithm = F2FS_OPTION(sbi).compress_algorithm;
+	fi->i_log_cluster_size = F2FS_OPTION(sbi).compress_log_size;
+	fi->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ?
 					BIT(COMPRESS_CHKSUM) : 0;
-	F2FS_I(inode)->i_cluster_size =
-			BIT(F2FS_I(inode)->i_log_cluster_size);
-	if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 ||
-		F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) &&
+	fi->i_cluster_size = BIT(fi->i_log_cluster_size);
+	if ((fi->i_compress_algorithm == COMPRESS_LZ4 ||
+		fi->i_compress_algorithm == COMPRESS_ZSTD) &&
 			F2FS_OPTION(sbi).compress_level)
-		F2FS_I(inode)->i_compress_level =
-				F2FS_OPTION(sbi).compress_level;
-	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
+		fi->i_compress_level = F2FS_OPTION(sbi).compress_level;
+	fi->i_flags |= F2FS_COMPR_FL;
 	set_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_inc_compr_inode(inode);
 	inc_compr_inode_stat(inode);
@@ -4431,15 +4437,15 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
-	f2fs_down_write(&F2FS_I(inode)->i_sem);
+	f2fs_down_write(&fi->i_sem);
 
 	if (!f2fs_compressed_file(inode)) {
-		f2fs_up_write(&F2FS_I(inode)->i_sem);
+		f2fs_up_write(&fi->i_sem);
 		return true;
 	}
 	if (f2fs_is_mmap_file(inode) ||
 		(S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) {
-		f2fs_up_write(&F2FS_I(inode)->i_sem);
+		f2fs_up_write(&fi->i_sem);
 		return false;
 	}
 
@@ -4448,7 +4454,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode)
 	clear_inode_flag(inode, FI_COMPRESSED_FILE);
 	f2fs_mark_inode_dirty_sync(inode, true);
 
-	f2fs_up_write(&F2FS_I(inode)->i_sem);
+	f2fs_up_write(&fi->i_sem);
 	return true;
 }
 

fs/f2fs/file.c

@@ -554,6 +554,42 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+static int finish_preallocate_blocks(struct inode *inode)
+{
+	int ret;
+
+	inode_lock(inode);
+	if (is_inode_flag_set(inode, FI_OPENED_FILE)) {
+		inode_unlock(inode);
+		return 0;
+	}
+
+	if (!file_should_truncate(inode)) {
+		set_inode_flag(inode, FI_OPENED_FILE);
+		inode_unlock(inode);
+		return 0;
+	}
+
+	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	filemap_invalidate_lock(inode->i_mapping);
+
+	truncate_setsize(inode, i_size_read(inode));
+	ret = f2fs_truncate(inode);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+
+	if (!ret)
+		set_inode_flag(inode, FI_OPENED_FILE);
+
+	inode_unlock(inode);
+	if (ret)
+		return ret;
+
+	file_dont_truncate(inode);
+	return 0;
+}
+
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
 	int err = fscrypt_file_open(inode, filp);
@@ -571,7 +607,11 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 	filp->f_mode |= FMODE_NOWAIT;
 	filp->f_mode |= FMODE_CAN_ODIRECT;
 
-	return dquot_file_open(inode, filp);
+	err = dquot_file_open(inode, filp);
+	if (err)
+		return err;
+
+	return finish_preallocate_blocks(inode);
 }
 
 void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -825,6 +865,8 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
 		return true;
 	if (f2fs_compressed_file(inode))
 		return true;
+	if (f2fs_has_inline_data(inode))
+		return true;
 
 	/* disallow direct IO if any of devices has unaligned blksize */
 	if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
@@ -937,6 +979,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int err;
 
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
@@ -955,7 +998,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			return -EOPNOTSUPP;
 		if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) &&
 			!IS_ALIGNED(attr->ia_size,
-			F2FS_BLK_TO_BYTES(F2FS_I(inode)->i_cluster_size)))
+			F2FS_BLK_TO_BYTES(fi->i_cluster_size)))
 			return -EINVAL;
 	}
 
@@ -1009,7 +1052,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 				return err;
 		}
 
-		f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+		f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 		filemap_invalidate_lock(inode->i_mapping);
 
 		truncate_setsize(inode, attr->ia_size);
@@ -1021,14 +1064,14 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * larger than i_size.
 		 */
 		filemap_invalidate_unlock(inode->i_mapping);
-		f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+		f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
 		if (err)
 			return err;
 
-		spin_lock(&F2FS_I(inode)->i_size_lock);
+		spin_lock(&fi->i_size_lock);
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
-		F2FS_I(inode)->last_disk_size = i_size_read(inode);
-		spin_unlock(&F2FS_I(inode)->i_size_lock);
+		fi->last_disk_size = i_size_read(inode);
+		spin_unlock(&fi->i_size_lock);
 	}
 
 	__setattr_copy(idmap, inode, attr);
@@ -1038,7 +1081,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 
 		if (is_inode_flag_set(inode, FI_ACL_MODE)) {
 			if (!err)
-				inode->i_mode = F2FS_I(inode)->i_acl_mode;
+				inode->i_mode = fi->i_acl_mode;
 			clear_inode_flag(inode, FI_ACL_MODE);
 		}
 	}
@@ -1946,15 +1989,15 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 			if (err)
 				return err;
 
-			f2fs_down_write(&F2FS_I(inode)->i_sem);
+			f2fs_down_write(&fi->i_sem);
 			if (!f2fs_may_compress(inode) ||
 					(S_ISREG(inode->i_mode) &&
 					F2FS_HAS_BLOCKS(inode))) {
-				f2fs_up_write(&F2FS_I(inode)->i_sem);
+				f2fs_up_write(&fi->i_sem);
 				return -EINVAL;
 			}
 			err = set_compress_context(inode);
-			f2fs_up_write(&F2FS_I(inode)->i_sem);
+			f2fs_up_write(&fi->i_sem);
 
 			if (err)
 				return err;
@@ -2139,6 +2182,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 
 		set_inode_flag(fi->cow_inode, FI_COW_FILE);
 		clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
+
+		/* Set the COW inode's atomic_inode to the atomic inode */
+		F2FS_I(fi->cow_inode)->atomic_inode = inode;
 	} else {
 		/* Reuse the already created COW inode */
 		ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
@@ -3541,6 +3587,7 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
 static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	pgoff_t page_idx = 0, last_idx;
 	unsigned int released_blocks = 0;
@@ -3578,7 +3625,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret)
 		goto out;
 
-	if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+	if (!atomic_read(&fi->i_compr_blocks)) {
 		ret = -EPERM;
 		goto out;
 	}
@@ -3587,7 +3634,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	inode_set_ctime_current(inode);
 	f2fs_mark_inode_dirty_sync(inode, true);
 
-	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3613,7 +3660,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 
 		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
-		count = round_up(count, F2FS_I(inode)->i_cluster_size);
+		count = round_up(count, fi->i_cluster_size);
 
 		ret = release_compress_blocks(&dn, count);
 
@@ -3629,7 +3676,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	}
 
 	filemap_invalidate_unlock(inode->i_mapping);
-	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
 out:
 	if (released_blocks)
 		f2fs_update_time(sbi, REQ_TIME);
@@ -3640,14 +3687,14 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret >= 0) {
 		ret = put_user(released_blocks, (u64 __user *)arg);
 	} else if (released_blocks &&
-			atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+			atomic_read(&fi->i_compr_blocks)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
 			"iblocks=%llu, released=%u, compr_blocks=%u, "
 			"run fsck to fix.",
 			__func__, inode->i_ino, inode->i_blocks,
 			released_blocks,
-			atomic_read(&F2FS_I(inode)->i_compr_blocks));
+			atomic_read(&fi->i_compr_blocks));
 	}
 
 	return ret;
@@ -3736,6 +3783,7 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count,
 static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	pgoff_t page_idx = 0, last_idx;
 	unsigned int reserved_blocks = 0;
@@ -3761,10 +3809,10 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 		goto unlock_inode;
 	}
 
-	if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
+	if (atomic_read(&fi->i_compr_blocks))
 		goto unlock_inode;
 
-	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3790,7 +3838,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 
 		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
-		count = round_up(count, F2FS_I(inode)->i_cluster_size);
+		count = round_up(count, fi->i_cluster_size);
 
 		ret = reserve_compress_blocks(&dn, count, &reserved_blocks);
 
@@ -3805,7 +3853,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	}
 
 	filemap_invalidate_unlock(inode->i_mapping);
-	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
 
 	if (!ret) {
 		clear_inode_flag(inode, FI_COMPRESS_RELEASED);
@@ -3821,14 +3869,14 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	if (!ret) {
 		ret = put_user(reserved_blocks, (u64 __user *)arg);
 	} else if (reserved_blocks &&
-			atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+			atomic_read(&fi->i_compr_blocks)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: partial blocks were reserved i_ino=%lx "
 			"iblocks=%llu, reserved=%u, compr_blocks=%u, "
 			"run fsck to fix.",
 			__func__, inode->i_ino, inode->i_blocks,
 			reserved_blocks,
-			atomic_read(&F2FS_I(inode)->i_compr_blocks));
+			atomic_read(&fi->i_compr_blocks));
 	}
 
 	return ret;
@@ -3891,7 +3939,9 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 			 IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
 		return -EOPNOTSUPP;
 
-	file_start_write(filp);
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
 	inode_lock(inode);
 
 	if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
@@ -4017,7 +4067,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 err:
 	inode_unlock(inode);
-	file_end_write(filp);
+	mnt_drop_write_file(filp);
 
 	return ret;
 }
@@ -4052,6 +4102,7 @@ static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg)
 static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_comp_option option;
 	int ret = 0;
@@ -4071,7 +4122,9 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
 		option.algorithm >= COMPRESS_MAX)
 		return -EINVAL;
 
-	file_start_write(filp);
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
 	inode_lock(inode);
 
 	f2fs_down_write(&F2FS_I(inode)->i_sem);
@@ -4090,27 +4143,27 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	F2FS_I(inode)->i_compress_algorithm = option.algorithm;
-	F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size;
-	F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size);
+	fi->i_compress_algorithm = option.algorithm;
+	fi->i_log_cluster_size = option.log_cluster_size;
+	fi->i_cluster_size = BIT(option.log_cluster_size);
 	/* Set default level */
-	if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD)
-		F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL;
+	if (fi->i_compress_algorithm == COMPRESS_ZSTD)
+		fi->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL;
 	else
-		F2FS_I(inode)->i_compress_level = 0;
+		fi->i_compress_level = 0;
 	/* Adjust mount option level */
 	if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm &&
 	    F2FS_OPTION(sbi).compress_level)
-		F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level;
+		fi->i_compress_level = F2FS_OPTION(sbi).compress_level;
 	f2fs_mark_inode_dirty_sync(inode, true);
 
 	if (!f2fs_is_compress_backend_ready(inode))
 		f2fs_warn(sbi, "compression algorithm is successfully set, "
 			"but current kernel doesn't support this algorithm.");
 out:
-	f2fs_up_write(&F2FS_I(inode)->i_sem);
+	f2fs_up_write(&fi->i_sem);
 	inode_unlock(inode);
-	file_end_write(filp);
+	mnt_drop_write_file(filp);
 
 	return ret;
 }
@@ -4167,7 +4220,9 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 
 	f2fs_balance_fs(sbi, true);
 
-	file_start_write(filp);
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
 	inode_lock(inode);
 
 	if (!f2fs_is_compress_backend_ready(inode)) {
@@ -4222,7 +4277,7 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 	inode_unlock(inode);
-	file_end_write(filp);
+	mnt_drop_write_file(filp);
 
 	return ret;
 }
@@ -4244,7 +4299,9 @@ static int f2fs_ioc_compress_file(struct file *filp)
 
 	f2fs_balance_fs(sbi, true);
 
-	file_start_write(filp);
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
 	inode_lock(inode);
 
 	if (!f2fs_is_compress_backend_ready(inode)) {
@@ -4300,7 +4357,7 @@ static int f2fs_ioc_compress_file(struct file *filp)
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 	inode_unlock(inode);
-	file_end_write(filp);
+	mnt_drop_write_file(filp);
 
 	return ret;
 }

fs/f2fs/gc.c

@@ -1171,7 +1171,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 static int ra_data_block(struct inode *inode, pgoff_t index)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct address_space *mapping = inode->i_mapping;
+	struct address_space *mapping = f2fs_is_cow_file(inode) ?
+				F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
 	struct dnode_of_data dn;
 	struct page *page;
 	struct f2fs_io_info fio = {
@@ -1260,6 +1261,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
 static int move_data_block(struct inode *inode, block_t bidx,
 				int gc_type, unsigned int segno, int off)
 {
+	struct address_space *mapping = f2fs_is_cow_file(inode) ?
+				F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.ino = inode->i_ino,
@@ -1282,7 +1285,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 				CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA;
 
 	/* do not read out */
-	page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
+	page = f2fs_grab_cache_page(mapping, bidx, false);
 	if (!page)
 		return -ENOMEM;
 
@@ -1563,6 +1566,16 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				continue;
 			}
 
+			if (f2fs_has_inline_data(inode)) {
+				iput(inode);
+				set_sbi_flag(sbi, SBI_NEED_FSCK);
+				f2fs_err_ratelimited(sbi,
+					"inode %lx has both inline_data flag and "
+					"data block, nid=%u, ofs_in_node=%u",
+					inode->i_ino, dni.nid, ofs_in_node);
+				continue;
+			}
+
 			err = f2fs_gc_pinned_control(inode, gc_type, segno);
 			if (err == -EAGAIN) {
 				iput(inode);
@@ -1579,7 +1592,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 			start_bidx = f2fs_start_bidx_of_node(nofs, inode) +
 								ofs_in_node;
 
-			if (f2fs_post_read_required(inode)) {
+			if (f2fs_meta_inode_gc_required(inode)) {
 				int err = ra_data_block(inode, start_bidx);
 
 				f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -1630,7 +1643,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 			start_bidx = f2fs_start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
-			if (f2fs_post_read_required(inode))
+			if (f2fs_meta_inode_gc_required(inode))
 				err = move_data_block(inode, start_bidx,
 							gc_type, segno, off);
 			else
@@ -1638,7 +1651,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 								segno, off);
 
 			if (!err && (gc_type == FG_GC ||
-					f2fs_post_read_required(inode)))
+					f2fs_meta_inode_gc_required(inode)))
 				submitted++;
 
 			if (locked) {
@@ -1742,7 +1755,6 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 		if (type != GET_SUM_TYPE((&sum->footer))) {
 			f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT",
 				 segno, type, GET_SUM_TYPE((&sum->footer)));
-			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			f2fs_stop_checkpoint(sbi, false,
 				STOP_CP_REASON_CORRUPTED_SUMMARY);
 			goto skip;

fs/f2fs/inline.c

@@ -16,7 +16,7 @@
 
 static bool support_inline_data(struct inode *inode)
 {
-	if (f2fs_is_atomic_file(inode))
+	if (f2fs_used_in_atomic_write(inode))
 		return false;
 	if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
 		return false;
@@ -33,11 +33,29 @@ bool f2fs_may_inline_data(struct inode *inode)
 	return !f2fs_post_read_required(inode);
 }
 
-bool f2fs_sanity_check_inline_data(struct inode *inode)
+static bool inode_has_blocks(struct inode *inode, struct page *ipage)
+{
+	struct f2fs_inode *ri = F2FS_INODE(ipage);
+	int i;
+
+	if (F2FS_HAS_BLOCKS(inode))
+		return true;
+
+	for (i = 0; i < DEF_NIDS_PER_INODE; i++) {
+		if (ri->i_nid[i])
+			return true;
+	}
+	return false;
+}
+
+bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage)
 {
 	if (!f2fs_has_inline_data(inode))
 		return false;
 
+	if (inode_has_blocks(inode, ipage))
+		return false;
+
 	if (!support_inline_data(inode))
 		return true;
 
@@ -203,8 +221,10 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	struct page *ipage, *page;
 	int err = 0;
 
-	if (!f2fs_has_inline_data(inode) ||
-			f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
+	if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	if (!f2fs_has_inline_data(inode))
 		return 0;
 
 	err = f2fs_dquot_initialize(inode);

fs/f2fs/inode.c

@@ -29,6 +29,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 	if (is_inode_flag_set(inode, FI_NEW_INODE))
 		return;
 
+	if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+		return;
+
 	if (f2fs_inode_dirtied(inode, sync))
 		return;
 
@@ -310,10 +313,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 			if (!sanity_check_compress_inode(inode, ri))
 				return false;
 		}
-	} else if (f2fs_sb_has_flexible_inline_xattr(sbi)) {
-		f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.",
-			  __func__, inode->i_ino);
-		return false;
 	}
 
 	if (!f2fs_sb_has_extra_attr(sbi)) {
@@ -344,7 +343,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		}
 	}
 
-	if (f2fs_sanity_check_inline_data(inode)) {
+	if (f2fs_sanity_check_inline_data(inode, node_page)) {
 		f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
 			  __func__, inode->i_ino, inode->i_mode);
 		return false;
@@ -508,16 +507,16 @@ static int do_read_inode(struct inode *inode)
 
 	init_idisk_time(inode);
 
-	/* Need all the flag bits */
-	f2fs_init_read_extent_tree(inode, node_page);
-	f2fs_init_age_extent_tree(inode);
-
-	if (!sanity_check_extent_cache(inode)) {
+	if (!sanity_check_extent_cache(inode, node_page)) {
 		f2fs_put_page(node_page, 1);
 		f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
 		return -EFSCORRUPTED;
 	}
 
+	/* Need all the flag bits */
+	f2fs_init_read_extent_tree(inode, node_page);
+	f2fs_init_age_extent_tree(inode);
+
 	f2fs_put_page(node_page, 1);
 
 	stat_inc_inline_xattr(inode);
@@ -610,14 +609,6 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 	}
 	f2fs_set_inode_flags(inode);
 
-	if (file_should_truncate(inode) &&
-			!is_sbi_flag_set(sbi, SBI_POR_DOING)) {
-		ret = f2fs_truncate(inode);
-		if (ret)
-			goto bad_inode;
-		file_dont_truncate(inode);
-	}
-
 	unlock_new_inode(inode);
 	trace_f2fs_iget(inode);
 	return inode;
@@ -645,8 +636,9 @@ struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
 
 void f2fs_update_inode(struct inode *inode, struct page *node_page)
 {
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_inode *ri;
-	struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
+	struct extent_tree *et = fi->extent_tree[EX_READ];
 
 	f2fs_wait_on_page_writeback(node_page, NODE, true, true);
 	set_page_dirty(node_page);
@@ -656,7 +648,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 	ri = F2FS_INODE(node_page);
 
 	ri->i_mode = cpu_to_le16(inode->i_mode);
-	ri->i_advise = F2FS_I(inode)->i_advise;
+	ri->i_advise = fi->i_advise;
 	ri->i_uid = cpu_to_le32(i_uid_read(inode));
 	ri->i_gid = cpu_to_le32(i_gid_read(inode));
 	ri->i_links = cpu_to_le32(inode->i_nlink);
@@ -682,58 +674,49 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 	ri->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
 	ri->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode));
 	if (S_ISDIR(inode->i_mode))
-		ri->i_current_depth =
-			cpu_to_le32(F2FS_I(inode)->i_current_depth);
+		ri->i_current_depth = cpu_to_le32(fi->i_current_depth);
 	else if (S_ISREG(inode->i_mode))
-		ri->i_gc_failures = cpu_to_le16(F2FS_I(inode)->i_gc_failures);
-	ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
-	ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
-	ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
+		ri->i_gc_failures = cpu_to_le16(fi->i_gc_failures);
+	ri->i_xattr_nid = cpu_to_le32(fi->i_xattr_nid);
+	ri->i_flags = cpu_to_le32(fi->i_flags);
+	ri->i_pino = cpu_to_le32(fi->i_pino);
 	ri->i_generation = cpu_to_le32(inode->i_generation);
-	ri->i_dir_level = F2FS_I(inode)->i_dir_level;
+	ri->i_dir_level = fi->i_dir_level;
 
 	if (f2fs_has_extra_attr(inode)) {
-		ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
+		ri->i_extra_isize = cpu_to_le16(fi->i_extra_isize);
 
 		if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)))
 			ri->i_inline_xattr_size =
-				cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
+				cpu_to_le16(fi->i_inline_xattr_size);
 
 		if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
-			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
-								i_projid)) {
+			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) {
 			projid_t i_projid;
 
-			i_projid = from_kprojid(&init_user_ns,
-						F2FS_I(inode)->i_projid);
+			i_projid = from_kprojid(&init_user_ns, fi->i_projid);
 			ri->i_projid = cpu_to_le32(i_projid);
 		}
 
 		if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
-			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
-								i_crtime)) {
-			ri->i_crtime =
-				cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
-			ri->i_crtime_nsec =
-				cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
+			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
+			ri->i_crtime = cpu_to_le64(fi->i_crtime.tv_sec);
+			ri->i_crtime_nsec = cpu_to_le32(fi->i_crtime.tv_nsec);
 		}
 
 		if (f2fs_sb_has_compression(F2FS_I_SB(inode)) &&
-			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 							i_compress_flag)) {
 			unsigned short compress_flag;
 
-			ri->i_compr_blocks =
-				cpu_to_le64(atomic_read(
-					&F2FS_I(inode)->i_compr_blocks));
-			ri->i_compress_algorithm =
-				F2FS_I(inode)->i_compress_algorithm;
-			compress_flag = F2FS_I(inode)->i_compress_flag |
-				F2FS_I(inode)->i_compress_level <<
+			ri->i_compr_blocks = cpu_to_le64(
+					atomic_read(&fi->i_compr_blocks));
+			ri->i_compress_algorithm = fi->i_compress_algorithm;
+			compress_flag = fi->i_compress_flag |
+						fi->i_compress_level <<
 						COMPRESS_LEVEL_OFFSET;
 			ri->i_compress_flag = cpu_to_le16(compress_flag);
-			ri->i_log_cluster_size =
-				F2FS_I(inode)->i_log_cluster_size;
+			ri->i_log_cluster_size = fi->i_log_cluster_size;
 		}
 	}
 
@@ -813,8 +796,9 @@ void f2fs_evict_inode(struct inode *inode)
 
 	f2fs_abort_atomic_write(inode, true);
 
-	if (fi->cow_inode) {
+	if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) {
 		clear_inode_flag(fi->cow_inode, FI_COW_FILE);
+		F2FS_I(fi->cow_inode)->atomic_inode = NULL;
 		iput(fi->cow_inode);
 		fi->cow_inode = NULL;
 	}

fs/f2fs/namei.c

@@ -221,6 +221,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 						const char *name)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct f2fs_inode_info *fi;
 	nid_t ino;
 	struct inode *inode;
 	bool nid_free = false;
@@ -241,14 +242,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 
 	inode_init_owner(idmap, inode, dir, mode);
 
+	fi = F2FS_I(inode);
 	inode->i_ino = ino;
 	inode->i_blocks = 0;
 	simple_inode_init_ts(inode);
-	F2FS_I(inode)->i_crtime = inode_get_mtime(inode);
+	fi->i_crtime = inode_get_mtime(inode);
 	inode->i_generation = get_random_u32();
 
 	if (S_ISDIR(inode->i_mode))
-		F2FS_I(inode)->i_current_depth = 1;
+		fi->i_current_depth = 1;
 
 	err = insert_inode_locked(inode);
 	if (err) {
@@ -258,9 +260,9 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 
 	if (f2fs_sb_has_project_quota(sbi) &&
 		(F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL))
-		F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
+		fi->i_projid = F2FS_I(dir)->i_projid;
 	else
-		F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
+		fi->i_projid = make_kprojid(&init_user_ns,
 							F2FS_DEF_PROJID);
 
 	err = fscrypt_prepare_new_inode(dir, inode, &encrypt);
@@ -278,7 +280,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 
 	if (f2fs_sb_has_extra_attr(sbi)) {
 		set_inode_flag(inode, FI_EXTRA_ATTR);
-		F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
+		fi->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
 	}
 
 	if (test_opt(sbi, INLINE_XATTR))
@@ -296,15 +298,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 				f2fs_has_inline_dentry(inode)) {
 		xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
 	}
-	F2FS_I(inode)->i_inline_xattr_size = xattr_size;
+	fi->i_inline_xattr_size = xattr_size;
 
-	F2FS_I(inode)->i_flags =
+	fi->i_flags =
 		f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
 
 	if (S_ISDIR(inode->i_mode))
-		F2FS_I(inode)->i_flags |= F2FS_INDEX_FL;
+		fi->i_flags |= F2FS_INDEX_FL;
 
-	if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
+	if (fi->i_flags & F2FS_PROJINHERIT_FL)
 		set_inode_flag(inode, FI_PROJ_INHERIT);
 
 	/* Check compression first. */

fs/f2fs/recovery.c

@@ -280,6 +280,7 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
 static int recover_inode(struct inode *inode, struct page *page)
 {
 	struct f2fs_inode *raw = F2FS_INODE(page);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	char *name;
 	int err;
 
@@ -302,12 +303,12 @@ static int recover_inode(struct inode *inode, struct page *page)
 			i_projid = (projid_t)le32_to_cpu(raw->i_projid);
 			kprojid = make_kprojid(&init_user_ns, i_projid);
 
-			if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) {
+			if (!projid_eq(kprojid, fi->i_projid)) {
 				err = f2fs_transfer_project_quota(inode,
 								kprojid);
 				if (err)
 					return err;
-				F2FS_I(inode)->i_projid = kprojid;
+				fi->i_projid = kprojid;
 			}
 		}
 	}
@@ -320,10 +321,10 @@ static int recover_inode(struct inode *inode, struct page *page)
 	inode_set_mtime(inode, le64_to_cpu(raw->i_mtime),
 			le32_to_cpu(raw->i_mtime_nsec));
 
-	F2FS_I(inode)->i_advise = raw->i_advise;
-	F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
+	fi->i_advise = raw->i_advise;
+	fi->i_flags = le32_to_cpu(raw->i_flags);
 	f2fs_set_inode_flags(inode);
-	F2FS_I(inode)->i_gc_failures = le16_to_cpu(raw->i_gc_failures);
+	fi->i_gc_failures = le16_to_cpu(raw->i_gc_failures);
 
 	recover_inline_flags(inode, raw);
 

fs/f2fs/segment.c

@@ -2784,11 +2784,19 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	unsigned short seg_type = curseg->seg_type;
 
 	sanity_check_seg_type(sbi, seg_type);
-	if (f2fs_need_rand_seg(sbi))
-		return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
+	if (__is_large_section(sbi)) {
+		if (f2fs_need_rand_seg(sbi)) {
+			unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno);
 
-	if (__is_large_section(sbi))
+			if (GET_SEC_FROM_SEG(sbi, curseg->segno + 1) != hint)
+				return curseg->segno;
+			return get_random_u32_inclusive(curseg->segno + 1,
+					GET_SEG_FROM_SEC(sbi, hint + 1) - 1);
+		}
 		return curseg->segno;
+	} else if (f2fs_need_rand_seg(sbi)) {
+		return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
+	}
 
 	/* inmem log may not locate on any segment after mount */
 	if (!curseg->inited)
@@ -2931,12 +2939,12 @@ static int get_atssr_segment(struct f2fs_sb_info *sbi, int type,
 	return ret;
 }
 
-static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
+static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi, bool force)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC);
 	int ret = 0;
 
-	if (!sbi->am.atgc_enabled)
+	if (!sbi->am.atgc_enabled && !force)
 		return 0;
 
 	f2fs_down_read(&SM_I(sbi)->curseg_lock);
@@ -2953,9 +2961,30 @@ static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
 	f2fs_up_read(&SM_I(sbi)->curseg_lock);
 	return ret;
 }
+
 int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
 {
-	return __f2fs_init_atgc_curseg(sbi);
+	return __f2fs_init_atgc_curseg(sbi, false);
+}
+
+int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi)
+{
+	int ret;
+
+	if (!test_opt(sbi, ATGC))
+		return 0;
+	if (sbi->am.atgc_enabled)
+		return 0;
+	if (le64_to_cpu(F2FS_CKPT(sbi)->elapsed_time) <
+			sbi->am.age_threshold)
+		return 0;
+
+	ret = __f2fs_init_atgc_curseg(sbi, true);
+	if (!ret) {
+		sbi->am.atgc_enabled = true;
+		f2fs_info(sbi, "reenabled age threshold GC");
+	}
+	return ret;
 }
 
 static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
@@ -3483,7 +3512,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		if (page_private_gcing(fio->page)) {
 			if (fio->sbi->am.atgc_enabled &&
 				(fio->io_type == FS_DATA_IO) &&
-				(fio->sbi->gc_mode != GC_URGENT_HIGH))
+				(fio->sbi->gc_mode != GC_URGENT_HIGH) &&
+				__is_valid_data_blkaddr(fio->old_blkaddr) &&
+				!is_inode_flag_set(inode, FI_OPU_WRITE))
 				return CURSEG_ALL_DATA_ATGC;
 			else
 				return CURSEG_COLD_DATA;
@@ -3828,7 +3859,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 		goto drop_bio;
 	}
 
-	if (fio->post_read)
+	if (fio->meta_gc)
 		f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1);
 
 	stat_inc_inplace_blocks(fio->sbi);
@@ -3998,7 +4029,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *cpage;
 
-	if (!f2fs_post_read_required(inode))
+	if (!f2fs_meta_inode_gc_required(inode))
 		return;
 
 	if (!__is_valid_data_blkaddr(blkaddr))
@@ -4017,7 +4048,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	block_t i;
 
-	if (!f2fs_post_read_required(inode))
+	if (!f2fs_meta_inode_gc_required(inode))
 		return;
 
 	for (i = 0; i < len; i++)
@@ -5187,7 +5218,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 	}
 
 	/* Allocate a new section if it's not new. */
-	if (cs->next_blkoff) {
+	if (cs->next_blkoff ||
+	    cs->segno != GET_SEG_FROM_SEC(sbi, GET_ZONE_FROM_SEC(sbi, cs_section))) {
 		unsigned int old_segno = cs->segno, old_blkoff = cs->next_blkoff;
 
 		f2fs_allocate_new_section(sbi, type, true);

fs/f2fs/segment.h

@@ -347,7 +347,8 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
 				unsigned int segno, bool use_section)
 {
 	if (use_section && __is_large_section(sbi)) {
-		unsigned int start_segno = START_SEGNO(segno);
+		unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+		unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 		unsigned int blocks = 0;
 		int i;
 

fs/f2fs/super.c

@@ -151,8 +151,6 @@ enum {
 	Opt_mode,
 	Opt_fault_injection,
 	Opt_fault_type,
-	Opt_lazytime,
-	Opt_nolazytime,
 	Opt_quota,
 	Opt_noquota,
 	Opt_usrquota,
@@ -229,8 +227,6 @@ static match_table_t f2fs_tokens = {
 	{Opt_mode, "mode=%s"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_fault_type, "fault_type=%u"},
-	{Opt_lazytime, "lazytime"},
-	{Opt_nolazytime, "nolazytime"},
 	{Opt_quota, "quota"},
 	{Opt_noquota, "noquota"},
 	{Opt_usrquota, "usrquota"},
@@ -918,12 +914,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			f2fs_info(sbi, "fault_type options not supported");
 			break;
 #endif
-		case Opt_lazytime:
-			sb->s_flags |= SB_LAZYTIME;
-			break;
-		case Opt_nolazytime:
-			sb->s_flags &= ~SB_LAZYTIME;
-			break;
 #ifdef CONFIG_QUOTA
 		case Opt_quota:
 		case Opt_usrquota:
@@ -4481,6 +4471,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
 	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 */

fs/f2fs/sysfs.c

@@ -340,13 +340,13 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 	if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) {
 		struct ckpt_req_control *cprc = &sbi->cprc_info;
 		int class = IOPRIO_PRIO_CLASS(cprc->ckpt_thread_ioprio);
-		int data = IOPRIO_PRIO_DATA(cprc->ckpt_thread_ioprio);
+		int level = IOPRIO_PRIO_LEVEL(cprc->ckpt_thread_ioprio);
 
 		if (class != IOPRIO_CLASS_RT && class != IOPRIO_CLASS_BE)
 			return -EINVAL;
 
 		return sysfs_emit(buf, "%s,%d\n",
-			class == IOPRIO_CLASS_RT ? "rt" : "be", data);
+			class == IOPRIO_CLASS_RT ? "rt" : "be", level);
 	}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -450,7 +450,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 		const char *name = strim((char *)buf);
 		struct ckpt_req_control *cprc = &sbi->cprc_info;
 		int class;
-		long data;
+		long level;
 		int ret;
 
 		if (!strncmp(name, "rt,", 3))
@@ -461,13 +461,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 			return -EINVAL;
 
 		name += 3;
-		ret = kstrtol(name, 10, &data);
+		ret = kstrtol(name, 10, &level);
 		if (ret)
 			return ret;
-		if (data >= IOPRIO_NR_LEVELS || data < 0)
+		if (level >= IOPRIO_NR_LEVELS || level < 0)
 			return -EINVAL;
 
-		cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data);
+		cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, level);
 		if (test_opt(sbi, MERGE_CHECKPOINT)) {
 			ret = set_task_ioprio(cprc->f2fs_issue_ckpt,
 					cprc->ckpt_thread_ioprio);

include/linux/f2fs_fs.h

@@ -259,15 +259,14 @@ struct node_footer {
 #define CUR_ADDRS_PER_INODE(inode)	(DEF_ADDRS_PER_INODE - \
 					get_extra_isize(inode))
 #define DEF_NIDS_PER_INODE	5	/* Node IDs in an Inode */
-#define ADDRS_PER_INODE(inode)	addrs_per_inode(inode)
+#define ADDRS_PER_INODE(inode)	addrs_per_page(inode, true)
 /* Address Pointers in a Direct Block */
 #define DEF_ADDRS_PER_BLOCK	((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
-#define ADDRS_PER_BLOCK(inode)	addrs_per_block(inode)
+#define ADDRS_PER_BLOCK(inode)	addrs_per_page(inode, false)
 /* Node IDs in an Indirect Block */
 #define NIDS_PER_BLOCK		((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
 
-#define ADDRS_PER_PAGE(page, inode)	\
-	(IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode))
+#define ADDRS_PER_PAGE(page, inode)	(addrs_per_page(inode, IS_INODE(page)))
 
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)