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

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

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

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

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

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

24 files changed, 615 insertions, 219 deletions

diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 62e638a49bbf..7669de7b49ce 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -7,6 +7,13 @@ config F2FS_FS
 	select CRYPTO_CRC32
 	select F2FS_FS_XATTR if FS_ENCRYPTION
 	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+	select LZ4_COMPRESS if F2FS_FS_LZ4
+	select LZ4_DECOMPRESS if F2FS_FS_LZ4
+	select LZ4HC_COMPRESS if F2FS_FS_LZ4HC
+	select LZO_COMPRESS if F2FS_FS_LZO
+	select LZO_DECOMPRESS if F2FS_FS_LZO
+	select ZSTD_COMPRESS if F2FS_FS_ZSTD
+	select ZSTD_DECOMPRESS if F2FS_FS_ZSTD
 	help
 	  F2FS is based on Log-structured File System (LFS), which supports
 	  versatile "flash-friendly" features. The design has been focused on
@@ -94,8 +101,6 @@ config F2FS_FS_COMPRESSION
 config F2FS_FS_LZO
 	bool "LZO compression support"
 	depends on F2FS_FS_COMPRESSION
-	select LZO_COMPRESS
-	select LZO_DECOMPRESS
 	default y
 	help
 	  Support LZO compress algorithm, if unsure, say Y.
@@ -103,8 +108,6 @@ config F2FS_FS_LZO
 config F2FS_FS_LZ4
 	bool "LZ4 compression support"
 	depends on F2FS_FS_COMPRESSION
-	select LZ4_COMPRESS
-	select LZ4_DECOMPRESS
 	default y
 	help
 	  Support LZ4 compress algorithm, if unsure, say Y.
@@ -113,7 +116,6 @@ config F2FS_FS_LZ4HC
 	bool "LZ4HC compression support"
 	depends on F2FS_FS_COMPRESSION
 	depends on F2FS_FS_LZ4
-	select LZ4HC_COMPRESS
 	default y
 	help
 	  Support LZ4HC compress algorithm, LZ4HC has compatible on-disk
@@ -122,8 +124,6 @@ config F2FS_FS_LZ4HC
 config F2FS_FS_ZSTD
 	bool "ZSTD compression support"
 	depends on F2FS_FS_COMPRESSION
-	select ZSTD_COMPRESS
-	select ZSTD_DECOMPRESS
 	default y
 	help
 	  Support ZSTD compress algorithm, if unsure, say Y.
@@ -132,8 +132,6 @@ config F2FS_FS_LZORLE
 	bool "LZO-RLE compression support"
 	depends on F2FS_FS_COMPRESSION
 	depends on F2FS_FS_LZO
-	select LZO_COMPRESS
-	select LZO_DECOMPRESS
 	default y
 	help
 	  Support LZO-RLE compress algorithm, if unsure, say Y.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 965037a9c205..239ad9453b99 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -29,6 +29,7 @@ static inline size_t f2fs_acl_size(int count)
 static inline int f2fs_acl_count(size_t size)
 {
 	ssize_t s;
+
 	size -= sizeof(struct f2fs_acl_header);
 	s = size - 4 * sizeof(struct f2fs_acl_entry_short);
 	if (s < 0) {
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index be5415a0dbbc..f795049e63d5 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -719,6 +719,7 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
 		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
 			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
+
 			err = recover_orphan_inode(sbi, ino);
 			if (err) {
 				f2fs_put_page(page, 1);
@@ -1456,7 +1457,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			orphan_blocks);
 
 	if (__remain_node_summaries(cpc->reason))
-		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
+		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks + NR_CURSEG_NODE_TYPE);
 	else
@@ -1818,7 +1819,11 @@ int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi)
 	llist_add(&req.llnode, &cprc->issue_list);
 	atomic_inc(&cprc->queued_ckpt);
 
-	/* update issue_list before we wake up issue_checkpoint thread */
+	/*
+	 * update issue_list before we wake up issue_checkpoint thread,
+	 * this smp_mb() pairs with another barrier in ___wait_event(),
+	 * see more details in comments of waitqueue_active().
+	 */
 	smp_mb();
 
 	if (waitqueue_active(&cprc->ckpt_wait_queue))
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 77fa342de38f..53b13787eb2c 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -76,12 +76,6 @@ bool f2fs_is_compressed_page(struct page *page)
 		return false;
 	if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page))
 		return false;
-	/*
-	 * page->private may be set with pid.
-	 * pid_max is enough to check if it is traced.
-	 */
-	if (IS_IO_TRACED_PAGE(page))
-		return false;
 
 	f2fs_bug_on(F2FS_M_SB(page->mapping),
 		*((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC);
@@ -896,7 +890,6 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
 
 static bool __cluster_may_compress(struct compress_ctx *cc)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
 	loff_t i_size = i_size_read(cc->inode);
 	unsigned nr_pages = DIV_ROUND_UP(i_size, PAGE_SIZE);
 	int i;
@@ -904,12 +897,7 @@ static bool __cluster_may_compress(struct compress_ctx *cc)
 	for (i = 0; i < cc->cluster_size; i++) {
 		struct page *page = cc->rpages[i];
 
-		f2fs_bug_on(sbi, !page);
-
-		if (unlikely(f2fs_cp_error(sbi)))
-			return false;
-		if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-			return false;
+		f2fs_bug_on(F2FS_I_SB(cc->inode), !page);
 
 		/* beyond EOF */
 		if (page->index >= nr_pages)
@@ -1353,6 +1341,7 @@ unlock_continue:
 	if (fio.compr_blocks)
 		f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false);
 	f2fs_i_compr_blocks_update(inode, cc->nr_cpages, true);
+	add_compr_block_stat(inode, cc->nr_cpages);
 
 	set_inode_flag(cc->inode, FI_APPEND_WRITE);
 	if (cc->cluster_idx == 0)
diff --git a/fs/f2fs/compress.h b/fs/f2fs/compress.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/fs/f2fs/compress.h
+++ /dev/null
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 4e5257c763d0..96f1a354f89f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1086,6 +1086,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 
 	for (; count > 0; dn->ofs_in_node++) {
 		block_t blkaddr = f2fs_data_blkaddr(dn);
+
 		if (blkaddr == NULL_ADDR) {
 			dn->data_blkaddr = NEW_ADDR;
 			__set_data_blkaddr(dn);
@@ -1722,7 +1723,7 @@ static int get_data_block_dio_write(struct inode *inode, sector_t iblock,
 	return __get_data_block(inode, iblock, bh_result, create,
 				F2FS_GET_BLOCK_DIO, NULL,
 				f2fs_rw_hint_to_seg_type(inode->i_write_hint),
-				IS_SWAPFILE(inode) ? false : true);
+				true);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
@@ -1837,6 +1838,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	int ret = 0;
 	bool compr_cluster = false;
 	unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
+	loff_t maxbytes;
 
 	if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
 		ret = f2fs_precache_extents(inode);
@@ -1850,6 +1852,15 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	inode_lock(inode);
 
+	maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
+	if (start > maxbytes) {
+		ret = -EFBIG;
+		goto out;
+	}
+
+	if (len > maxbytes || (maxbytes - len) < start)
+		len = maxbytes - start;
+
 	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
 		ret = f2fs_xattr_fiemap(inode, fieinfo);
 		goto out;
@@ -3755,6 +3766,7 @@ int f2fs_migrate_page(struct address_space *mapping,
 
 	if (atomic_written) {
 		struct inmem_pages *cur;
+
 		list_for_each_entry(cur, &fi->inmem_pages, list)
 			if (cur->page == page) {
 				cur->page = newpage;
@@ -3780,11 +3792,64 @@ int f2fs_migrate_page(struct address_space *mapping,
 #endif
 
 #ifdef CONFIG_SWAP
+static int f2fs_is_file_aligned(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	block_t main_blkaddr = SM_I(sbi)->main_blkaddr;
+	block_t cur_lblock;
+	block_t last_lblock;
+	block_t pblock;
+	unsigned long nr_pblocks;
+	unsigned int blocks_per_sec = BLKS_PER_SEC(sbi);
+	int ret = 0;
+
+	cur_lblock = 0;
+	last_lblock = bytes_to_blks(inode, i_size_read(inode));
+
+	while (cur_lblock < last_lblock) {
+		struct f2fs_map_blocks map;
+
+		memset(&map, 0, sizeof(map));
+		map.m_lblk = cur_lblock;
+		map.m_len = last_lblock - cur_lblock;
+		map.m_next_pgofs = NULL;
+		map.m_next_extent = NULL;
+		map.m_seg_type = NO_CHECK_TYPE;
+		map.m_may_create = false;
+
+		ret = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_FIEMAP);
+		if (ret)
+			goto out;
+
+		/* hole */
+		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+			f2fs_err(sbi, "Swapfile has holes\n");
+			ret = -ENOENT;
+			goto out;
+		}
+
+		pblock = map.m_pblk;
+		nr_pblocks = map.m_len;
+
+		if ((pblock - main_blkaddr) & (blocks_per_sec - 1) ||
+			nr_pblocks & (blocks_per_sec - 1)) {
+			f2fs_err(sbi, "Swapfile does not align to section");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		cur_lblock += nr_pblocks;
+	}
+out:
+	return ret;
+}
+
 static int check_swap_activate_fast(struct swap_info_struct *sis,
 				struct file *swap_file, sector_t *span)
 {
 	struct address_space *mapping = swap_file->f_mapping;
 	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	sector_t cur_lblock;
 	sector_t last_lblock;
 	sector_t pblock;
@@ -3792,8 +3857,8 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 	sector_t highest_pblock = 0;
 	int nr_extents = 0;
 	unsigned long nr_pblocks;
-	u64 len;
-	int ret;
+	unsigned int blocks_per_sec = BLKS_PER_SEC(sbi);
+	int ret = 0;
 
 	/*
 	 * Map all the blocks into the extent list.  This code doesn't try
@@ -3801,31 +3866,41 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 	 */
 	cur_lblock = 0;
 	last_lblock = bytes_to_blks(inode, i_size_read(inode));
-	len = i_size_read(inode);
 
-	while (cur_lblock <= last_lblock && cur_lblock < sis->max) {
+	while (cur_lblock < last_lblock && cur_lblock < sis->max) {
 		struct f2fs_map_blocks map;
-		pgoff_t next_pgofs;
 
 		cond_resched();
 
 		memset(&map, 0, sizeof(map));
 		map.m_lblk = cur_lblock;
-		map.m_len = bytes_to_blks(inode, len) - cur_lblock;
-		map.m_next_pgofs = &next_pgofs;
+		map.m_len = last_lblock - cur_lblock;
+		map.m_next_pgofs = NULL;
+		map.m_next_extent = NULL;
 		map.m_seg_type = NO_CHECK_TYPE;
+		map.m_may_create = false;
 
 		ret = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_FIEMAP);
 		if (ret)
-			goto err_out;
+			goto out;
 
 		/* hole */
-		if (!(map.m_flags & F2FS_MAP_FLAGS))
-			goto err_out;
+		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+			f2fs_err(sbi, "Swapfile has holes\n");
+			ret = -ENOENT;
+			goto out;
+		}
 
 		pblock = map.m_pblk;
 		nr_pblocks = map.m_len;
 
+		if ((pblock - SM_I(sbi)->main_blkaddr) & (blocks_per_sec - 1) ||
+				nr_pblocks & (blocks_per_sec - 1)) {
+			f2fs_err(sbi, "Swapfile does not align to section");
+			ret = -EINVAL;
+			goto out;
+		}
+
 		if (cur_lblock + nr_pblocks >= sis->max)
 			nr_pblocks = sis->max - cur_lblock;
 
@@ -3854,9 +3929,6 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 	sis->highest_bit = cur_lblock - 1;
 out:
 	return ret;
-err_out:
-	pr_err("swapon: swapfile has holes\n");
-	return -EINVAL;
 }
 
 /* Copied from generic_swapfile_activate() to check any holes */
@@ -3865,6 +3937,7 @@ static int check_swap_activate(struct swap_info_struct *sis,
 {
 	struct address_space *mapping = swap_file->f_mapping;
 	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	unsigned blocks_per_page;
 	unsigned long page_no;
 	sector_t probe_block;
@@ -3872,11 +3945,15 @@ static int check_swap_activate(struct swap_info_struct *sis,
 	sector_t lowest_block = -1;
 	sector_t highest_block = 0;
 	int nr_extents = 0;
-	int ret;
+	int ret = 0;
 
 	if (PAGE_SIZE == F2FS_BLKSIZE)
 		return check_swap_activate_fast(sis, swap_file, span);
 
+	ret = f2fs_is_file_aligned(inode);
+	if (ret)
+		goto out;
+
 	blocks_per_page = bytes_to_blks(inode, PAGE_SIZE);
 
 	/*
@@ -3891,13 +3968,14 @@ static int check_swap_activate(struct swap_info_struct *sis,
 		unsigned block_in_page;
 		sector_t first_block;
 		sector_t block = 0;
-		int	 err = 0;
 
 		cond_resched();
 
 		block = probe_block;
-		err = bmap(inode, &block);
-		if (err || !block)
+		ret = bmap(inode, &block);
+		if (ret)
+			goto out;
+		if (!block)
 			goto bad_bmap;
 		first_block = block;
 
@@ -3913,9 +3991,10 @@ static int check_swap_activate(struct swap_info_struct *sis,
 					block_in_page++) {
 
 			block = probe_block + block_in_page;
-			err = bmap(inode, &block);
-
-			if (err || !block)
+			ret = bmap(inode, &block);
+			if (ret)
+				goto out;
+			if (!block)
 				goto bad_bmap;
 
 			if (block != first_block + block_in_page) {
@@ -3955,8 +4034,8 @@ reprobe:
 out:
 	return ret;
 bad_bmap:
-	pr_err("swapon: swapfile has holes\n");
-	return -EINVAL;
+	f2fs_err(sbi, "Swapfile has holes\n");
+	return -ENOENT;
 }
 
 static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 91855d5721cd..c03949a7ccff 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -173,6 +173,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->util_invalid = 50 - si->util_free - si->util_valid;
 	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
+
 		si->curseg[i] = curseg->segno;
 		si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
 		si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
@@ -300,10 +301,12 @@ get_cache:
 	si->page_mem = 0;
 	if (sbi->node_inode) {
 		unsigned npages = NODE_MAPPING(sbi)->nrpages;
+
 		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	}
 	if (sbi->meta_inode) {
 		unsigned npages = META_MAPPING(sbi)->nrpages;
+
 		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	}
 }
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index e211a1b6b013..dc7ce79672b8 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -471,6 +471,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 		struct page *page, struct inode *inode)
 {
 	enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
+
 	lock_page(page);
 	f2fs_wait_on_page_writeback(page, type, true, true);
 	de->ino = cpu_to_le32(inode->i_ino);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 11a20dc505aa..044878866ca3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -97,6 +97,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_NORECOVERY		0x04000000
 #define F2FS_MOUNT_ATGC			0x08000000
 #define F2FS_MOUNT_MERGE_CHECKPOINT	0x10000000
+#define	F2FS_MOUNT_GC_MERGE		0x20000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -637,21 +638,26 @@ enum {
 #define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)
 
 #define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
-#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
 #define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
-#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
 #define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
+
+#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
 #define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
+
 #define file_is_encrypt(inode)	is_file(inode, FADVISE_ENCRYPT_BIT)
 #define file_set_encrypt(inode)	set_file(inode, FADVISE_ENCRYPT_BIT)
-#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
+
 #define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
 #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+
 #define file_keep_isize(inode)	is_file(inode, FADVISE_KEEP_SIZE_BIT)
 #define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
+
 #define file_is_hot(inode)	is_file(inode, FADVISE_HOT_BIT)
 #define file_set_hot(inode)	set_file(inode, FADVISE_HOT_BIT)
 #define file_clear_hot(inode)	clear_file(inode, FADVISE_HOT_BIT)
+
 #define file_is_verity(inode)	is_file(inode, FADVISE_VERITY_BIT)
 #define file_set_verity(inode)	set_file(inode, FADVISE_VERITY_BIT)
 
@@ -860,7 +866,7 @@ struct f2fs_nm_info {
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
 	struct radix_tree_root nat_set_root;/* root of the nat set cache */
-	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
+	struct rw_semaphore nat_tree_lock;	/* protect nat entry tree */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	spinlock_t nat_list_lock;	/* protect clean nat entry list */
 	unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
@@ -1297,14 +1303,6 @@ enum {
 #define IS_DUMMY_WRITTEN_PAGE(page)			\
 		(page_private(page) == DUMMY_WRITTEN_PAGE)
 
-#ifdef CONFIG_F2FS_IO_TRACE
-#define IS_IO_TRACED_PAGE(page)			\
-		(page_private(page) > 0 &&		\
-		 page_private(page) < (unsigned long)PID_MAX_LIMIT)
-#else
-#define IS_IO_TRACED_PAGE(page) (0)
-#endif
-
 /* For compression */
 enum compress_algorithm_type {
 	COMPRESS_LZO,
@@ -1623,6 +1621,11 @@ struct f2fs_sb_info {
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	struct kmem_cache *page_array_slab;	/* page array entry */
 	unsigned int page_array_slab_size;	/* default page array slab size */
+
+	/* For runtime compression statistics */
+	u64 compr_written_block;
+	u64 compr_saved_block;
+	u32 compr_new_inode;
 #endif
 };
 
@@ -2215,6 +2218,7 @@ static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
 static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	void *tmp_ptr = &ckpt->sit_nat_version_bitmap;
 	int offset;
 
 	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
@@ -2224,7 +2228,7 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 		 * if large_nat_bitmap feature is enabled, leave checksum
 		 * protection for all nat/sit bitmaps.
 		 */
-		return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32);
+		return tmp_ptr + offset + sizeof(__le32);
 	}
 
 	if (__cp_payload(sbi) > 0) {
@@ -2235,7 +2239,7 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 	} else {
 		offset = (flag == NAT_BITMAP) ?
 			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
-		return &ckpt->sit_nat_version_bitmap + offset;
+		return tmp_ptr + offset;
 	}
 }
 
@@ -3302,7 +3306,6 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);
 /*
  * node.c
  */
-struct dnode_of_data;
 struct node_info;
 
 int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
@@ -3379,6 +3382,7 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
 int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
 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);
 void f2fs_init_inmem_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);
@@ -3386,7 +3390,7 @@ void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
 			unsigned int *newseg, bool new_sec, int dir);
 void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
 					unsigned int start, unsigned int end);
-void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force);
 void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
 bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
@@ -3550,7 +3554,7 @@ void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
 int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
 void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
 block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, bool force,
 			unsigned int segno);
 void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
 int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
@@ -3958,6 +3962,18 @@ int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi);
 void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
 int __init f2fs_init_compress_cache(void);
 void f2fs_destroy_compress_cache(void);
+#define inc_compr_inode_stat(inode)					\
+	do {								\
+		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);		\
+		sbi->compr_new_inode++;					\
+	} while (0)
+#define add_compr_block_stat(inode, blocks)				\
+	do {								\
+		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);		\
+		int diff = F2FS_I(inode)->i_cluster_size - blocks;	\
+		sbi->compr_written_block += blocks;			\
+		sbi->compr_saved_block += diff;				\
+	} while (0)
 #else
 static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
 static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
@@ -3986,6 +4002,7 @@ static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return
 static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
 static inline int __init f2fs_init_compress_cache(void) { return 0; }
 static inline void f2fs_destroy_compress_cache(void) { }
+#define inc_compr_inode_stat(inode)		do { } while (0)
 #endif
 
 static inline void set_compress_context(struct inode *inode)
@@ -4009,6 +4026,7 @@ static inline void set_compress_context(struct inode *inode)
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
 	set_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_inc_compr_inode(inode);
+	inc_compr_inode_stat(inode);
 	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
@@ -4179,8 +4197,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 		if (F2FS_IO_ALIGNED(sbi))
 			return true;
 	}
-	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
-					!IS_SWAPFILE(inode))
+	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED))
 		return true;
 
 	return false;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 8a56acbcee4c..44a4650aea7b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1622,9 +1622,10 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	struct f2fs_map_blocks map = { .m_next_pgofs = NULL,
 			.m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE,
 			.m_may_create = true };
-	pgoff_t pg_end;
+	pgoff_t pg_start, pg_end;
 	loff_t new_size = i_size_read(inode);
 	loff_t off_end;
+	block_t expanded = 0;
 	int err;
 
 	err = inode_newsize_ok(inode, (len + offset));
@@ -1637,11 +1638,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 
 	f2fs_balance_fs(sbi, true);
 
+	pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
 	pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
 	off_end = (offset + len) & (PAGE_SIZE - 1);
 
-	map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
-	map.m_len = pg_end - map.m_lblk;
+	map.m_lblk = pg_start;
+	map.m_len = pg_end - pg_start;
 	if (off_end)
 		map.m_len++;
 
@@ -1649,19 +1651,15 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		return 0;
 
 	if (f2fs_is_pinned_file(inode)) {
-		block_t len = (map.m_len >> sbi->log_blocks_per_seg) <<
-					sbi->log_blocks_per_seg;
-		block_t done = 0;
+		block_t sec_blks = BLKS_PER_SEC(sbi);
+		block_t sec_len = roundup(map.m_len, sec_blks);
 
-		if (map.m_len % sbi->blocks_per_seg)
-			len += sbi->blocks_per_seg;
-
-		map.m_len = sbi->blocks_per_seg;
+		map.m_len = sec_blks;
 next_alloc:
 		if (has_not_enough_free_secs(sbi, 0,
 			GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
 			down_write(&sbi->gc_lock);
-			err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+			err = f2fs_gc(sbi, true, false, false, NULL_SEGNO);
 			if (err && err != -ENODATA && err != -EAGAIN)
 				goto out_err;
 		}
@@ -1669,7 +1667,7 @@ next_alloc:
 		down_write(&sbi->pin_sem);
 
 		f2fs_lock_op(sbi);
-		f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA_PINNED);
+		f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
 		f2fs_unlock_op(sbi);
 
 		map.m_seg_type = CURSEG_COLD_DATA_PINNED;
@@ -1677,24 +1675,25 @@ next_alloc:
 
 		up_write(&sbi->pin_sem);
 
-		done += map.m_len;
-		len -= map.m_len;
+		expanded += map.m_len;
+		sec_len -= map.m_len;
 		map.m_lblk += map.m_len;
-		if (!err && len)
+		if (!err && sec_len)
 			goto next_alloc;
 
-		map.m_len = done;
+		map.m_len = expanded;
 	} else {
 		err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+		expanded = map.m_len;
 	}
 out_err:
 	if (err) {
 		pgoff_t last_off;
 
-		if (!map.m_len)
+		if (!expanded)
 			return err;
 
-		last_off = map.m_lblk + map.m_len - 1;
+		last_off = pg_start + expanded - 1;
 
 		/* update new size to the failed position */
 		new_size = (last_off == pg_end) ? offset + len :
@@ -2434,7 +2433,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 		down_write(&sbi->gc_lock);
 	}
 
-	ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
+	ret = f2fs_gc(sbi, sync, true, false, NULL_SEGNO);
 out:
 	mnt_drop_write_file(filp);
 	return ret;
@@ -2470,7 +2469,8 @@ do_more:
 		down_write(&sbi->gc_lock);
 	}
 
-	ret = f2fs_gc(sbi, range->sync, true, GET_SEGNO(sbi, range->start));
+	ret = f2fs_gc(sbi, range->sync, true, false,
+				GET_SEGNO(sbi, range->start));
 	if (ret) {
 		if (ret == -EBUSY)
 			ret = -EAGAIN;
@@ -2527,7 +2527,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_map_blocks map = { .m_next_extent = NULL,
-					.m_seg_type = NO_CHECK_TYPE ,
+					.m_seg_type = NO_CHECK_TYPE,
 					.m_may_create = false };
 	struct extent_info ei = {0, 0, 0};
 	pgoff_t pg_start, pg_end, next_pgofs;
@@ -2923,7 +2923,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
 		sm->last_victim[GC_CB] = end_segno + 1;
 		sm->last_victim[GC_GREEDY] = end_segno + 1;
 		sm->last_victim[ALLOC_NEXT] = end_segno + 1;
-		ret = f2fs_gc(sbi, true, true, start_segno);
+		ret = f2fs_gc(sbi, true, true, true, start_segno);
 		if (ret == -EAGAIN)
 			ret = 0;
 		else if (ret < 0)
@@ -4311,8 +4311,13 @@ write:
 		clear_inode_flag(inode, FI_NO_PREALLOC);
 
 		/* if we couldn't write data, we should deallocate blocks. */
-		if (preallocated && i_size_read(inode) < target_size)
+		if (preallocated && i_size_read(inode) < target_size) {
+			down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			f2fs_truncate(inode);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
+			up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+		}
 
 		if (ret > 0)
 			f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 39330ad3c44e..8d1f17ab94d8 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -31,19 +31,24 @@ static int gc_thread_func(void *data)
 	struct f2fs_sb_info *sbi = data;
 	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
 	wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
+	wait_queue_head_t *fggc_wq = &sbi->gc_thread->fggc_wq;
 	unsigned int wait_ms;
 
 	wait_ms = gc_th->min_sleep_time;
 
 	set_freezable();
 	do {
-		bool sync_mode;
+		bool sync_mode, foreground = false;
 
 		wait_event_interruptible_timeout(*wq,
 				kthread_should_stop() || freezing(current) ||
+				waitqueue_active(fggc_wq) ||
 				gc_th->gc_wake,
 				msecs_to_jiffies(wait_ms));
 
+		if (test_opt(sbi, GC_MERGE) && waitqueue_active(fggc_wq))
+			foreground = true;
+
 		/* give it a try one time */
 		if (gc_th->gc_wake)
 			gc_th->gc_wake = 0;
@@ -90,7 +95,10 @@ static int gc_thread_func(void *data)
 			goto do_gc;
 		}
 
-		if (!down_write_trylock(&sbi->gc_lock)) {
+		if (foreground) {
+			down_write(&sbi->gc_lock);
+			goto do_gc;
+		} else if (!down_write_trylock(&sbi->gc_lock)) {
 			stat_other_skip_bggc_count(sbi);
 			goto next;
 		}
@@ -107,14 +115,22 @@ static int gc_thread_func(void *data)
 		else
 			increase_sleep_time(gc_th, &wait_ms);
 do_gc:
-		stat_inc_bggc_count(sbi->stat_info);
+		if (!foreground)
+			stat_inc_bggc_count(sbi->stat_info);
 
 		sync_mode = F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC;
 
+		/* foreground GC was been triggered via f2fs_balance_fs() */
+		if (foreground)
+			sync_mode = false;
+
 		/* if return value is not zero, no victim was selected */
-		if (f2fs_gc(sbi, sync_mode, true, NULL_SEGNO))
+		if (f2fs_gc(sbi, sync_mode, !foreground, false, NULL_SEGNO))
 			wait_ms = gc_th->no_gc_sleep_time;
 
+		if (foreground)
+			wake_up_all(&gc_th->fggc_wq);
+
 		trace_f2fs_background_gc(sbi->sb, wait_ms,
 				prefree_segments(sbi), free_segments(sbi));
 
@@ -144,10 +160,11 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 	gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
 	gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
 
-	gc_th->gc_wake= 0;
+	gc_th->gc_wake = 0;
 
 	sbi->gc_thread = gc_th;
 	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
+	init_waitqueue_head(&sbi->gc_thread->fggc_wq);
 	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
 			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(gc_th->f2fs_gc_task)) {
@@ -162,9 +179,11 @@ out:
 void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
+
 	if (!gc_th)
 		return;
 	kthread_stop(gc_th->f2fs_gc_task);
+	wake_up_all(&gc_th->fggc_wq);
 	kfree(gc_th);
 	sbi->gc_thread = NULL;
 }
@@ -392,10 +411,6 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
 		if (p->gc_mode == GC_AT &&
 			get_valid_blocks(sbi, segno, true) == 0)
 			return;
-
-		if (p->alloc_mode == AT_SSR &&
-			get_seg_entry(sbi, segno)->ckpt_valid_blocks == 0)
-			return;
 	}
 
 	for (i = 0; i < sbi->segs_per_sec; i++)
@@ -728,11 +743,27 @@ retry:
 
 		if (sec_usage_check(sbi, secno))
 			goto next;
+
 		/* Don't touch checkpointed data */
-		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
-					get_ckpt_valid_blocks(sbi, segno) &&
-					p.alloc_mode == LFS))
-			goto next;
+		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+			if (p.alloc_mode == LFS) {
+				/*
+				 * LFS is set to find source section during GC.
+				 * The victim should have no checkpointed data.
+				 */
+				if (get_ckpt_valid_blocks(sbi, segno, true))
+					goto next;
+			} else {
+				/*
+				 * SSR | AT_SSR are set to find target segment
+				 * for writes which can be full by checkpointed
+				 * and newly written blocks.
+				 */
+				if (!f2fs_segment_has_free_slot(sbi, segno))
+					goto next;
+			}
+		}
+
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
 			goto next;
 
@@ -828,6 +859,7 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 static void put_gc_inode(struct gc_inode_list *gc_list)
 {
 	struct inode_entry *ie, *next_ie;
+
 	list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) {
 		radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
 		iput(ie->inode);
@@ -952,9 +984,11 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
 		bidx = node_ofs - 1;
 	} else if (node_ofs <= indirect_blks) {
 		int dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1);
+
 		bidx = node_ofs - 2 - dec;
 	} else {
 		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
+
 		bidx = node_ofs - 5 - dec;
 	}
 	return bidx * ADDRS_PER_BLOCK(inode) + ADDRS_PER_INODE(inode);
@@ -1120,7 +1154,8 @@ static int move_data_block(struct inode *inode, block_t bidx,
 	block_t newaddr;
 	int err = 0;
 	bool lfs_mode = f2fs_lfs_mode(fio.sbi);
-	int type = fio.sbi->am.atgc_enabled ?
+	int type = fio.sbi->am.atgc_enabled && (gc_type == BG_GC) &&
+				(fio.sbi->gc_mode != GC_URGENT_HIGH) ?
 				CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA;
 
 	/* do not read out */
@@ -1354,7 +1389,8 @@ out:
  * the victim data block is ignored.
  */
 static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
-		struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
+		struct gc_inode_list *gc_list, unsigned int segno, int gc_type,
+		bool force_migrate)
 {
 	struct super_block *sb = sbi->sb;
 	struct f2fs_summary *entry;
@@ -1383,8 +1419,8 @@ next_step:
 		 * race condition along with SSR block allocation.
 		 */
 		if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) ||
-				get_valid_blocks(sbi, segno, true) ==
-							BLKS_PER_SEC(sbi))
+			(!force_migrate && get_valid_blocks(sbi, segno, true) ==
+							BLKS_PER_SEC(sbi)))
 			return submitted;
 
 		if (check_valid_map(sbi, segno, off) == 0)
@@ -1519,7 +1555,8 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 
 static int do_garbage_collect(struct f2fs_sb_info *sbi,
 				unsigned int start_segno,
-				struct gc_inode_list *gc_list, int gc_type)
+				struct gc_inode_list *gc_list, int gc_type,
+				bool force_migrate)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
@@ -1606,7 +1643,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 								gc_type);
 		else
 			submitted += gc_data_segment(sbi, sum->entries, gc_list,
-							segno, gc_type);
+							segno, gc_type,
+							force_migrate);
 
 		stat_inc_seg_count(sbi, type, gc_type);
 		migrated++;
@@ -1634,7 +1672,7 @@ skip:
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
-			bool background, unsigned int segno)
+			bool background, bool force, unsigned int segno)
 {
 	int gc_type = sync ? FG_GC : BG_GC;
 	int sec_freed = 0, seg_freed = 0, total_freed = 0;
@@ -1696,7 +1734,7 @@ gc_more:
 	if (ret)
 		goto stop;
 
-	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
+	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type, force);
 	if (gc_type == FG_GC &&
 		seg_freed == f2fs_usable_segs_in_sec(sbi, segno))
 		sec_freed++;
@@ -1835,7 +1873,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi,
 			.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
 		};
 
-		do_garbage_collect(sbi, segno, &gc_list, FG_GC);
+		do_garbage_collect(sbi, segno, &gc_list, FG_GC, true);
 		put_gc_inode(&gc_list);
 
 		if (!gc_only && get_valid_blocks(sbi, segno, true)) {
@@ -1974,7 +2012,20 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
 
 	/* stop CP to protect MAIN_SEC in free_segment_range */
 	f2fs_lock_op(sbi);
+
+	spin_lock(&sbi->stat_lock);
+	if (shrunk_blocks + valid_user_blocks(sbi) +
+		sbi->current_reserved_blocks + sbi->unusable_block_count +
+		F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count)
+		err = -ENOSPC;
+	spin_unlock(&sbi->stat_lock);
+
+	if (err)
+		goto out_unlock;
+
 	err = free_segment_range(sbi, secs, true);
+
+out_unlock:
 	f2fs_unlock_op(sbi);
 	up_write(&sbi->gc_lock);
 	if (err)
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 0c8dae12dc51..3fe145e8e594 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -42,6 +42,12 @@ struct f2fs_gc_kthread {
 
 	/* for changing gc mode */
 	unsigned int gc_wake;
+
+	/* for GC_MERGE mount option */
+	wait_queue_head_t fggc_wq;		/*
+						 * caller of f2fs_balance_fs()
+						 * will wait on this wait queue.
+						 */
 };
 
 struct gc_inode_list {
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 993caefcd2bb..92652ca7a7c8 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -219,7 +219,8 @@ out:
 
 	f2fs_put_page(page, 1);
 
-	f2fs_balance_fs(sbi, dn.node_changed);
+	if (!err)
+		f2fs_balance_fs(sbi, dn.node_changed);
 
 	return err;
 }
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 349d9cb933ee..b401f08569f7 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -666,6 +666,7 @@ retry:
 	node_page = f2fs_get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
 		int err = PTR_ERR(node_page);
+
 		if (err == -ENOMEM) {
 			cond_resched();
 			goto retry;
@@ -698,7 +699,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	/*
 	 * We need to balance fs here to prevent from producing dirty node pages
-	 * during the urgent cleaning time when runing out of free sections.
+	 * during the urgent cleaning time when running out of free sections.
 	 */
 	f2fs_update_inode_page(inode);
 	if (wbc && wbc->nr_to_write)
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 377c6b161b23..a9cd9cf97229 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -418,6 +418,7 @@ struct dentry *f2fs_get_parent(struct dentry *child)
 {
 	struct page *page;
 	unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot_name, &page);
+
 	if (!ino) {
 		if (IS_ERR(page))
 			return ERR_CAST(page);
@@ -627,6 +628,7 @@ static const char *f2fs_get_link(struct dentry *dentry,
 				 struct delayed_call *done)
 {
 	const char *link = page_get_link(dentry, inode, done);
+
 	if (!IS_ERR(link) && !*link) {
 		/* this is broken symlink case */
 		do_delayed_call(done);
@@ -765,6 +767,7 @@ out_fail:
 static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
+
 	if (f2fs_empty_dir(inode))
 		return f2fs_unlink(dir, dentry);
 	return -ENOTEMPTY;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 4b0e2e3c2c88..e67ce5f13b98 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -43,11 +43,15 @@ int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct sysinfo val;
 	unsigned long avail_ram;
 	unsigned long mem_size = 0;
 	bool res = false;
 
+	if (!nm_i)
+		return true;
+
 	si_meminfo(&val);
 
 	/* only uses low memory */
@@ -89,6 +93,10 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 		/* it allows 20% / total_ram for inmemory pages */
 		mem_size = get_pages(sbi, F2FS_INMEM_PAGES);
 		res = mem_size < (val.totalram / 5);
+	} else if (type == DISCARD_CACHE) {
+		mem_size = (atomic_read(&dcc->discard_cmd_cnt) *
+				sizeof(struct discard_cmd)) >> PAGE_SHIFT;
+		res = mem_size < (avail_ram * nm_i->ram_thresh / 100);
 	} else {
 		if (!sbi->sb->s_bdi->wb.dirty_exceeded)
 			return true;
@@ -462,6 +470,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	/* increment version no as node is removed */
 	if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
 		unsigned char version = nat_get_version(e);
+
 		nat_set_version(e, inc_node_version(version));
 	}
 
@@ -1383,7 +1392,7 @@ repeat:
 		goto out_err;
 	}
 page_hit:
-	if(unlikely(nid != nid_of_node(page))) {
+	if (unlikely(nid != nid_of_node(page))) {
 		f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
 			  nid, nid_of_node(page), ino_of_node(page),
 			  ofs_of_node(page), cpver_of_node(page),
@@ -1775,7 +1784,7 @@ continue_unlock:
 out:
 	if (nwritten)
 		f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE);
-	return ret ? -EIO: 0;
+	return ret ? -EIO : 0;
 }
 
 static int f2fs_match_ino(struct inode *inode, unsigned long ino, void *data)
@@ -2117,8 +2126,8 @@ static int __insert_free_nid(struct f2fs_sb_info *sbi,
 				struct free_nid *i)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-
 	int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i);
+
 	if (err)
 		return err;
 
@@ -2785,6 +2794,9 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 		struct f2fs_nat_entry raw_ne;
 		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
+		if (f2fs_check_nid_range(sbi, nid))
+			continue;
+
 		raw_ne = nat_in_journal(journal, i);
 
 		ne = __lookup_nat_cache(nm_i, nid);
@@ -2980,6 +2992,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	while ((found = __gang_lookup_nat_set(nm_i,
 					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
+
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
 			__adjust_nat_entry_set(setvec[idx], &sets,
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index f84541b57acb..7a45c0f10629 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -147,6 +147,7 @@ enum mem_type {
 	INO_ENTRIES,	/* indicates inode entries */
 	EXTENT_CACHE,	/* indicates extent cache */
 	INMEM_PAGES,	/* indicates inmemory pages */
+	DISCARD_CACHE,	/* indicates memory of cached discard cmds */
 	BASE_CHECK,	/* check kernel status */
 };
 
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index da75d5d52f0a..422146c6d866 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -458,6 +458,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	/* Get the previous summary */
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
+
 		if (curseg->segno == segno) {
 			sum = curseg->sum_blk->entries[blkoff];
 			goto got_it;
@@ -875,5 +876,5 @@ out:
 #endif
 	sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
 
-	return ret ? ret: err;
+	return ret ? ret : err;
 }
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index c2866561263e..c605415840b5 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -186,7 +186,10 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page)
 {
 	struct inmem_pages *new;
 
-	f2fs_set_page_private(page, ATOMIC_WRITTEN_PAGE);
+	if (PagePrivate(page))
+		set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
+	else
+		f2fs_set_page_private(page, ATOMIC_WRITTEN_PAGE);
 
 	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
 
@@ -324,23 +327,27 @@ void f2fs_drop_inmem_pages(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
-	while (!list_empty(&fi->inmem_pages)) {
+	do {
 		mutex_lock(&fi->inmem_lock);
+		if (list_empty(&fi->inmem_pages)) {
+			fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
+
+			spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+			if (!list_empty(&fi->inmem_ilist))
+				list_del_init(&fi->inmem_ilist);
+			if (f2fs_is_atomic_file(inode)) {
+				clear_inode_flag(inode, FI_ATOMIC_FILE);
+				sbi->atomic_files--;
+			}
+			spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+
+			mutex_unlock(&fi->inmem_lock);
+			break;
+		}
 		__revoke_inmem_pages(inode, &fi->inmem_pages,
 						true, false, true);
 		mutex_unlock(&fi->inmem_lock);
-	}
-
-	fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
-
-	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
-	if (!list_empty(&fi->inmem_ilist))
-		list_del_init(&fi->inmem_ilist);
-	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(inode, FI_ATOMIC_FILE);
-		sbi->atomic_files--;
-	}
-	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+	} while (1);
 }
 
 void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
@@ -503,8 +510,19 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 * dir/node pages without enough free segments.
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
-		down_write(&sbi->gc_lock);
-		f2fs_gc(sbi, false, false, NULL_SEGNO);
+		if (test_opt(sbi, GC_MERGE) && sbi->gc_thread &&
+					sbi->gc_thread->f2fs_gc_task) {
+			DEFINE_WAIT(wait);
+
+			prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait,
+						TASK_UNINTERRUPTIBLE);
+			wake_up(&sbi->gc_thread->gc_wait_queue_head);
+			io_schedule();
+			finish_wait(&sbi->gc_thread->fggc_wq, &wait);
+		} else {
+			down_write(&sbi->gc_lock);
+			f2fs_gc(sbi, false, false, false, NULL_SEGNO);
+		}
 	}
 }
 
@@ -653,7 +671,11 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
 
 	llist_add(&cmd.llnode, &fcc->issue_list);
 
-	/* update issue_list before we wake up issue_flush thread */
+	/*
+	 * update issue_list before we wake up issue_flush thread, this
+	 * smp_mb() pairs with another barrier in ___wait_event(), see
+	 * more details in comments of waitqueue_active().
+	 */
 	smp_mb();
 
 	if (waitqueue_active(&fcc->flush_wait_queue))
@@ -861,7 +883,7 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	mutex_lock(&dirty_i->seglist_lock);
 
 	valid_blocks = get_valid_blocks(sbi, segno, false);
-	ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);
+	ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno, false);
 
 	if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
 		ckpt_valid_blocks == usable_blocks)) {
@@ -946,7 +968,7 @@ static unsigned int get_free_segment(struct f2fs_sb_info *sbi)
 	for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
 		if (get_valid_blocks(sbi, segno, false))
 			continue;
-		if (get_ckpt_valid_blocks(sbi, segno))
+		if (get_ckpt_valid_blocks(sbi, segno, false))
 			continue;
 		mutex_unlock(&dirty_i->seglist_lock);
 		return segno;
@@ -1095,6 +1117,8 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 				struct discard_policy *dpolicy,
 				int discard_type, unsigned int granularity)
 {
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
 	/* common policy */
 	dpolicy->type = discard_type;
 	dpolicy->sync = true;
@@ -1114,7 +1138,9 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 		dpolicy->ordered = true;
 		if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
 			dpolicy->granularity = 1;
-			dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+			if (atomic_read(&dcc->discard_cmd_cnt))
+				dpolicy->max_interval =
+					DEF_MIN_DISCARD_ISSUE_TIME;
 		}
 	} else if (discard_type == DPOLICY_FORCE) {
 		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
@@ -1730,8 +1756,15 @@ static int issue_discard_thread(void *data)
 	set_freezable();
 
 	do {
-		__init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
-					dcc->discard_granularity);
+		if (sbi->gc_mode == GC_URGENT_HIGH ||
+			!f2fs_available_free_memory(sbi, DISCARD_CACHE))
+			__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
+		else
+			__init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
+						dcc->discard_granularity);
+
+		if (!atomic_read(&dcc->discard_cmd_cnt))
+		       wait_ms = dpolicy.max_interval;
 
 		wait_event_interruptible_timeout(*q,
 				kthread_should_stop() || freezing(current) ||
@@ -1755,9 +1788,8 @@ static int issue_discard_thread(void *data)
 			wait_ms = dpolicy.max_interval;
 			continue;
 		}
-
-		if (sbi->gc_mode == GC_URGENT_HIGH)
-			__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
+		if (!atomic_read(&dcc->discard_cmd_cnt))
+			continue;
 
 		sb_start_intwrite(sbi->sb);
 
@@ -1765,7 +1797,7 @@ static int issue_discard_thread(void *data)
 		if (issued > 0) {
 			__wait_all_discard_cmd(sbi, &dpolicy);
 			wait_ms = dpolicy.min_interval;
-		} else if (issued == -1){
+		} else if (issued == -1) {
 			wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME);
 			if (!wait_ms)
 				wait_ms = dpolicy.mid_interval;
@@ -2142,6 +2174,7 @@ static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
 					unsigned int segno, int modified)
 {
 	struct seg_entry *se = get_seg_entry(sbi, segno);
+
 	se->type = type;
 	if (modified)
 		__mark_sit_entry_dirty(sbi, segno);
@@ -2333,6 +2366,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	void *addr = curseg->sum_blk;
+
 	addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
 	memcpy(addr, sum, sizeof(struct f2fs_summary));
 }
@@ -2604,22 +2638,20 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 	curseg->alloc_type = LFS;
 }
 
-static void __next_free_blkoff(struct f2fs_sb_info *sbi,
-			struct curseg_info *seg, block_t start)
+static int __next_free_blkoff(struct f2fs_sb_info *sbi,
+					int segno, block_t start)
 {
-	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
+	struct seg_entry *se = get_seg_entry(sbi, segno);
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
 	unsigned long *target_map = SIT_I(sbi)->tmp_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
-	int i, pos;
+	int i;
 
 	for (i = 0; i < entries; i++)
 		target_map[i] = ckpt_map[i] | cur_map[i];
 
-	pos = __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);
-
-	seg->next_blkoff = pos;
+	return __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);
 }
 
 /*
@@ -2631,11 +2663,18 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
 				struct curseg_info *seg)
 {
 	if (seg->alloc_type == SSR)
-		__next_free_blkoff(sbi, seg, seg->next_blkoff + 1);
+		seg->next_blkoff =
+			__next_free_blkoff(sbi, seg->segno,
+						seg->next_blkoff + 1);
 	else
 		seg->next_blkoff++;
 }
 
+bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
+{
+	return __next_free_blkoff(sbi, segno, 0) < sbi->blocks_per_seg;
+}
+
 /*
  * This function always allocates a used segment(from dirty seglist) by SSR
  * manner, so it should recover the existing segment information of valid blocks
@@ -2661,7 +2700,7 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool flush)
 
 	reset_curseg(sbi, type, 1);
 	curseg->alloc_type = SSR;
-	__next_free_blkoff(sbi, curseg, 0);
+	curseg->next_blkoff = __next_free_blkoff(sbi, curseg->segno, 0);
 
 	sum_page = f2fs_get_sum_page(sbi, new_segno);
 	if (IS_ERR(sum_page)) {
@@ -2893,7 +2932,8 @@ unlock:
 	up_read(&SM_I(sbi)->curseg_lock);
 }
 
-static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type)
+static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type,
+						bool new_sec, bool force)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	unsigned int old_segno;
@@ -2901,32 +2941,43 @@ static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type)
 	if (!curseg->inited)
 		goto alloc;
 
-	if (!curseg->next_blkoff &&
-		!get_valid_blocks(sbi, curseg->segno, false) &&
-		!get_ckpt_valid_blocks(sbi, curseg->segno))
-		return;
+	if (force || curseg->next_blkoff ||
+		get_valid_blocks(sbi, curseg->segno, new_sec))
+		goto alloc;
 
+	if (!get_ckpt_valid_blocks(sbi, curseg->segno, new_sec))
+		return;
 alloc:
 	old_segno = curseg->segno;
 	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
 	locate_dirty_segment(sbi, old_segno);
 }
 
-void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type)
+static void __allocate_new_section(struct f2fs_sb_info *sbi,
+						int type, bool force)
+{
+	__allocate_new_segment(sbi, type, true, force);
+}
+
+void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force)
 {
+	down_read(&SM_I(sbi)->curseg_lock);
 	down_write(&SIT_I(sbi)->sentry_lock);
-	__allocate_new_segment(sbi, type);
+	__allocate_new_section(sbi, type, force);
 	up_write(&SIT_I(sbi)->sentry_lock);
+	up_read(&SM_I(sbi)->curseg_lock);
 }
 
 void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
 {
 	int i;
 
+	down_read(&SM_I(sbi)->curseg_lock);
 	down_write(&SIT_I(sbi)->sentry_lock);
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
-		__allocate_new_segment(sbi, i);
+		__allocate_new_segment(sbi, i, false, false);
 	up_write(&SIT_I(sbi)->sentry_lock);
+	up_read(&SM_I(sbi)->curseg_lock);
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -3239,7 +3290,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		struct inode *inode = fio->page->mapping->host;
 
 		if (is_cold_data(fio->page)) {
-			if (fio->sbi->am.atgc_enabled)
+			if (fio->sbi->am.atgc_enabled &&
+				(fio->io_type == FS_DATA_IO) &&
+				(fio->sbi->gc_mode != GC_URGENT_HIGH))
 				return CURSEG_ALL_DATA_ATGC;
 			else
 				return CURSEG_COLD_DATA;
@@ -3365,12 +3418,12 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		f2fs_inode_chksum_set(sbi, page);
 	}
 
-	if (F2FS_IO_ALIGNED(sbi))
-		fio->retry = false;
-
 	if (fio) {
 		struct f2fs_bio_info *io;
 
+		if (F2FS_IO_ALIGNED(sbi))
+			fio->retry = false;
+
 		INIT_LIST_HEAD(&fio->list);
 		fio->in_list = true;
 		io = sbi->write_io[fio->type] + fio->temp;
@@ -3499,7 +3552,13 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.",
 			  __func__, segno);
-		return -EFSCORRUPTED;
+		err = -EFSCORRUPTED;
+		goto drop_bio;
+	}
+
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) || f2fs_cp_error(sbi)) {
+		err = -EIO;
+		goto drop_bio;
 	}
 
 	stat_inc_inplace_blocks(fio->sbi);
@@ -3514,6 +3573,15 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 	}
 
 	return err;
+drop_bio:
+	if (fio->bio) {
+		struct bio *bio = *(fio->bio);
+
+		bio->bi_status = BLK_STS_IOERR;
+		bio_endio(bio);
+		fio->bio = NULL;
+	}
+	return err;
 }
 
 static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
@@ -3539,6 +3607,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	struct seg_entry *se;
 	int type;
 	unsigned short old_blkoff;
+	unsigned char old_alloc_type;
 
 	segno = GET_SEGNO(sbi, new_blkaddr);
 	se = get_seg_entry(sbi, segno);
@@ -3572,6 +3641,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 	old_cursegno = curseg->segno;
 	old_blkoff = curseg->next_blkoff;
+	old_alloc_type = curseg->alloc_type;
 
 	/* change the current segment */
 	if (segno != curseg->segno) {
@@ -3606,6 +3676,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 			change_curseg(sbi, type, true);
 		}
 		curseg->next_blkoff = old_blkoff;
+		curseg->alloc_type = old_alloc_type;
 	}
 
 	up_write(&sit_i->sentry_lock);
@@ -3717,6 +3788,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 
 		for (j = 0; j < blk_off; j++) {
 			struct f2fs_summary *s;
+
 			s = (struct f2fs_summary *)(kaddr + offset);
 			seg_i->sum_blk->entries[j] = *s;
 			offset += SUMMARY_SIZE;
@@ -3779,6 +3851,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		if (__exist_node_summaries(sbi)) {
 			struct f2fs_summary *ns = &sum->entries[0];
 			int i;
+
 			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
 				ns->version = 0;
 				ns->ofs_in_node = 0;
@@ -3880,6 +3953,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 	/* Step 3: write summary entries */
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		unsigned short blkoff;
+
 		seg_i = CURSEG_I(sbi, i);
 		if (sbi->ckpt->alloc_type[i] == SSR)
 			blkoff = sbi->blocks_per_seg;
@@ -3916,6 +3990,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
 	int i, end;
+
 	if (IS_DATASEG(type))
 		end = type + NR_CURSEG_DATA_TYPE;
 	else
@@ -4499,6 +4574,7 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 	/* set use the current segments */
 	for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) {
 		struct curseg_info *curseg_t = CURSEG_I(sbi, type);
+
 		__set_test_and_inuse(sbi, curseg_t->segno);
 	}
 }
@@ -4731,7 +4807,8 @@ static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
 }
 
 static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
-			      void *data) {
+			      void *data)
+{
 	memcpy(data, zone, sizeof(struct blk_zone));
 	return 0;
 }
@@ -4783,7 +4860,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 
 	f2fs_notice(sbi, "Assign new section to curseg[%d]: "
 		    "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff);
-	allocate_segment_by_default(sbi, type, true);
+
+	f2fs_allocate_new_section(sbi, type, true);
 
 	/* check consistency of the zone curseg pointed to */
 	if (check_zone_write_pointer(sbi, zbd, &zone))
@@ -4847,8 +4925,10 @@ struct check_zone_write_pointer_args {
 };
 
 static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
-				      void *data) {
+				      void *data)
+{
 	struct check_zone_write_pointer_args *args;
+
 	args = (struct check_zone_write_pointer_args *)data;
 
 	return check_zone_write_pointer(args->sbi, args->fdev, zone);
@@ -5127,6 +5207,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
 static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
 	kvfree(dirty_i->victim_secmap);
 }
 
@@ -5171,6 +5252,7 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 static void destroy_free_segmap(struct f2fs_sb_info *sbi)
 {
 	struct free_segmap_info *free_i = SM_I(sbi)->free_info;
+
 	if (!free_i)
 		return;
 	SM_I(sbi)->free_info = NULL;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index e9a7a637d688..050230c70a53 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -172,12 +172,10 @@ enum {
 /*
  * BG_GC means the background cleaning job.
  * FG_GC means the on-demand cleaning job.
- * FORCE_FG_GC means on-demand cleaning job in background.
  */
 enum {
 	BG_GC = 0,
 	FG_GC,
-	FORCE_FG_GC,
 };
 
 /* for a function parameter to select a victim segment */
@@ -361,8 +359,20 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
 }
 
 static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
-				unsigned int segno)
+				unsigned int segno, bool use_section)
 {
+	if (use_section && __is_large_section(sbi)) {
+		unsigned int start_segno = START_SEGNO(segno);
+		unsigned int blocks = 0;
+		int i;
+
+		for (i = 0; i < sbi->segs_per_sec; i++, start_segno++) {
+			struct seg_entry *se = get_seg_entry(sbi, start_segno);
+
+			blocks += se->ckpt_valid_blocks;
+		}
+		return blocks;
+	}
 	return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 }
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 82592b19b4e0..7d325bfaf65a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -151,6 +151,8 @@ enum {
 	Opt_compress_chksum,
 	Opt_compress_mode,
 	Opt_atgc,
+	Opt_gc_merge,
+	Opt_nogc_merge,
 	Opt_err,
 };
 
@@ -223,6 +225,8 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_chksum, "compress_chksum"},
 	{Opt_compress_mode, "compress_mode=%s"},
 	{Opt_atgc, "atgc"},
+	{Opt_gc_merge, "gc_merge"},
+	{Opt_nogc_merge, "nogc_merge"},
 	{Opt_err, NULL},
 };
 
@@ -555,6 +559,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 		/*
@@ -1073,6 +1078,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 		case Opt_atgc:
 			set_opt(sbi, ATGC);
 			break;
+		case Opt_gc_merge:
+			set_opt(sbi, GC_MERGE);
+			break;
+		case Opt_nogc_merge:
+			clear_opt(sbi, GC_MERGE);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1616,6 +1627,7 @@ static inline void f2fs_show_quota_options(struct seq_file *seq,
 #endif
 }
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 static inline void f2fs_show_compress_options(struct seq_file *seq,
 							struct super_block *sb)
 {
@@ -1661,6 +1673,7 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 	else if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER)
 		seq_printf(seq, ",compress_mode=%s", "user");
 }
+#endif
 
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
@@ -1673,6 +1686,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF)
 		seq_printf(seq, ",background_gc=%s", "off");
 
+	if (test_opt(sbi, GC_MERGE))
+		seq_puts(seq, ",gc_merge");
+
 	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
 		seq_puts(seq, ",disable_roll_forward");
 	if (test_opt(sbi, NORECOVERY))
@@ -1824,6 +1840,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, EXTENT_CACHE);
 	set_opt(sbi, NOHEAP);
 	clear_opt(sbi, DISABLE_CHECKPOINT);
+	set_opt(sbi, MERGE_CHECKPOINT);
 	F2FS_OPTION(sbi).unusable_cap = 0;
 	sbi->sb->s_flags |= SB_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
@@ -1865,7 +1882,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 
 	while (!f2fs_time_over(sbi, DISABLE_TIME)) {
 		down_write(&sbi->gc_lock);
-		err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+		err = f2fs_gc(sbi, true, false, false, NULL_SEGNO);
 		if (err == -ENODATA) {
 			err = 0;
 			break;
@@ -1876,7 +1893,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 
 	ret = sync_filesystem(sbi->sb);
 	if (ret || err) {
-		err = ret ? ret: err;
+		err = ret ? ret : err;
 		goto restore_flag;
 	}
 
@@ -1925,8 +1942,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	struct f2fs_mount_info org_mount_opt;
 	unsigned long old_sb_flags;
 	int err;
-	bool need_restart_gc = false;
-	bool need_stop_gc = false;
+	bool need_restart_gc = false, need_stop_gc = false;
+	bool need_restart_ckpt = false, need_stop_ckpt = false;
+	bool need_restart_flush = false, need_stop_flush = false;
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 	bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
 	bool no_io_align = !F2FS_IO_ALIGNED(sbi);
@@ -2035,7 +2053,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * option. Also sync the filesystem.
 	 */
 	if ((*flags & SB_RDONLY) ||
-			F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) {
+			(F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF &&
+			!test_opt(sbi, GC_MERGE))) {
 		if (sbi->gc_thread) {
 			f2fs_stop_gc_thread(sbi);
 			need_restart_gc = true;
@@ -2057,18 +2076,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		clear_sbi_flag(sbi, SBI_IS_CLOSE);
 	}
 
-	if (checkpoint_changed) {
-		if (test_opt(sbi, DISABLE_CHECKPOINT)) {
-			err = f2fs_disable_checkpoint(sbi);
-			if (err)
-				goto restore_gc;
-		} else {
-			f2fs_enable_checkpoint(sbi);
-		}
-	}
-
-	if (!test_opt(sbi, DISABLE_CHECKPOINT) &&
-			test_opt(sbi, MERGE_CHECKPOINT)) {
+	if ((*flags & SB_RDONLY) || test_opt(sbi, DISABLE_CHECKPOINT) ||
+			!test_opt(sbi, MERGE_CHECKPOINT)) {
+		f2fs_stop_ckpt_thread(sbi);
+		need_restart_ckpt = true;
+	} else {
 		err = f2fs_start_ckpt_thread(sbi);
 		if (err) {
 			f2fs_err(sbi,
@@ -2076,8 +2088,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			    err);
 			goto restore_gc;
 		}
-	} else {
-		f2fs_stop_ckpt_thread(sbi);
+		need_stop_ckpt = true;
 	}
 
 	/*
@@ -2087,11 +2098,24 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if ((*flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
 		clear_opt(sbi, FLUSH_MERGE);
 		f2fs_destroy_flush_cmd_control(sbi, false);
+		need_restart_flush = true;
 	} else {
 		err = f2fs_create_flush_cmd_control(sbi);
 		if (err)
-			goto restore_gc;
+			goto restore_ckpt;
+		need_stop_flush = true;
 	}
+
+	if (checkpoint_changed) {
+		if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+			err = f2fs_disable_checkpoint(sbi);
+			if (err)
+				goto restore_flush;
+		} else {
+			f2fs_enable_checkpoint(sbi);
+		}
+	}
+
 skip:
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
@@ -2106,6 +2130,21 @@ skip:
 	adjust_unusable_cap_perc(sbi);
 	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	return 0;
+restore_flush:
+	if (need_restart_flush) {
+		if (f2fs_create_flush_cmd_control(sbi))
+			f2fs_warn(sbi, "background flush thread has stopped");
+	} else if (need_stop_flush) {
+		clear_opt(sbi, FLUSH_MERGE);
+		f2fs_destroy_flush_cmd_control(sbi, false);
+	}
+restore_ckpt:
+	if (need_restart_ckpt) {
+		if (f2fs_start_ckpt_thread(sbi))
+			f2fs_warn(sbi, "background ckpt thread has stopped");
+	} else if (need_stop_ckpt) {
+		f2fs_stop_ckpt_thread(sbi);
+	}
 restore_gc:
 	if (need_restart_gc) {
 		if (f2fs_start_gc_thread(sbi))
@@ -3719,7 +3758,7 @@ try_onemore:
 	sbi->iostat_period_ms = DEFAULT_IOSTAT_PERIOD_MS;
 
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		int n = (i == META) ? 1: NR_TEMP_TYPE;
+		int n = (i == META) ? 1 : NR_TEMP_TYPE;
 		int j;
 
 		sbi->write_io[i] =
@@ -3833,7 +3872,7 @@ try_onemore:
 
 	/* setup checkpoint request control and start checkpoint issue thread */
 	f2fs_init_ckpt_req_control(sbi);
-	if (!test_opt(sbi, DISABLE_CHECKPOINT) &&
+	if (!f2fs_readonly(sb) && !test_opt(sbi, DISABLE_CHECKPOINT) &&
 			test_opt(sbi, MERGE_CHECKPOINT)) {
 		err = f2fs_start_ckpt_thread(sbi);
 		if (err) {
@@ -3929,10 +3968,18 @@ try_onemore:
 		 * previous checkpoint was not done by clean system shutdown.
 		 */
 		if (f2fs_hw_is_readonly(sbi)) {
-			if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))
-				f2fs_err(sbi, "Need to recover fsync data, but write access unavailable");
-			else
-				f2fs_info(sbi, "write access unavailable, skipping recovery");
+			if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+				err = f2fs_recover_fsync_data(sbi, true);
+				if (err > 0) {
+					err = -EROFS;
+					f2fs_err(sbi, "Need to recover fsync data, but "
+						"write access unavailable, please try "
+						"mount w/ disable_roll_forward or norecovery");
+				}
+				if (err < 0)
+					goto free_meta;
+			}
+			f2fs_info(sbi, "write access unavailable, skipping recovery");
 			goto reset_checkpoint;
 		}
 
@@ -3989,7 +4036,8 @@ reset_checkpoint:
 	 * If filesystem is not mounted as read-only then
 	 * do start the gc_thread.
 	 */
-	if (F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF && !f2fs_readonly(sb)) {
+	if ((F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF ||
+		test_opt(sbi, GC_MERGE)) && !f2fs_readonly(sb)) {
 		/* After POR, we can run background GC thread.*/
 		err = f2fs_start_gc_thread(sbi);
 		if (err)
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index e38a7f6921dd..39b522ec73e7 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/unicode.h>
 #include <linux/ioprio.h>
+#include <linux/sysfs.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -91,6 +92,13 @@ static ssize_t free_segments_show(struct f2fs_attr *a,
 			(unsigned long long)(free_segments(sbi)));
 }
 
+static ssize_t ovp_segments_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	return sprintf(buf, "%llu\n",
+			(unsigned long long)(overprovision_segments(sbi)));
+}
+
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -282,6 +290,17 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 		return len;
 	}
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (!strcmp(a->attr.name, "compr_written_block"))
+		return sysfs_emit(buf, "%llu\n", sbi->compr_written_block);
+
+	if (!strcmp(a->attr.name, "compr_saved_block"))
+		return sysfs_emit(buf, "%llu\n", sbi->compr_saved_block);
+
+	if (!strcmp(a->attr.name, "compr_new_inode"))
+		return sysfs_emit(buf, "%u\n", sbi->compr_new_inode);
+#endif
+
 	ui = (unsigned int *)(ptr + a->offset);
 
 	return sprintf(buf, "%u\n", *ui);
@@ -458,6 +477,24 @@ out:
 		return count;
 	}
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (!strcmp(a->attr.name, "compr_written_block") ||
+		!strcmp(a->attr.name, "compr_saved_block")) {
+		if (t != 0)
+			return -EINVAL;
+		sbi->compr_written_block = 0;
+		sbi->compr_saved_block = 0;
+		return count;
+	}
+
+	if (!strcmp(a->attr.name, "compr_new_inode")) {
+		if (t != 0)
+			return -EINVAL;
+		sbi->compr_new_inode = 0;
+		return count;
+	}
+#endif
+
 	*ui = (unsigned int)t;
 
 	return count;
@@ -629,6 +666,7 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag);
 F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, ckpt_thread_ioprio, ckpt_thread_ioprio);
 F2FS_GENERAL_RO_ATTR(dirty_segments);
 F2FS_GENERAL_RO_ATTR(free_segments);
+F2FS_GENERAL_RO_ATTR(ovp_segments);
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 F2FS_GENERAL_RO_ATTR(features);
 F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
@@ -668,6 +706,9 @@ F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
 F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_written_block, compr_written_block);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_saved_block, compr_saved_block);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_new_inode, compr_new_inode);
 #endif
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
@@ -715,6 +756,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(ckpt_thread_ioprio),
 	ATTR_LIST(dirty_segments),
 	ATTR_LIST(free_segments),
+	ATTR_LIST(ovp_segments),
 	ATTR_LIST(unusable),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(features),
@@ -731,6 +773,11 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(moved_blocks_background),
 	ATTR_LIST(avg_vblocks),
 #endif
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	ATTR_LIST(compr_written_block),
+	ATTR_LIST(compr_saved_block),
+	ATTR_LIST(compr_new_inode),
+#endif
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index a7beff28a3c5..03549b5ba204 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -152,40 +152,73 @@ static int f2fs_end_enable_verity(struct file *filp, const void *desc,
 				  size_t desc_size, u64 merkle_tree_size)
 {
 	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size;
 	struct fsverity_descriptor_location dloc = {
 		.version = cpu_to_le32(F2FS_VERIFY_VER),
 		.size = cpu_to_le32(desc_size),
 		.pos = cpu_to_le64(desc_pos),
 	};
-	int err = 0;
+	int err = 0, err2 = 0;
 
-	if (desc != NULL) {
-		/* Succeeded; write the verity descriptor. */
-		err = pagecache_write(inode, desc, desc_size, desc_pos);
+	/*
+	 * If an error already occurred (which fs/verity/ signals by passing
+	 * desc == NULL), then only clean-up is needed.
+	 */
+	if (desc == NULL)
+		goto cleanup;
 
-		/* Write all pages before clearing FI_VERITY_IN_PROGRESS. */
-		if (!err)
-			err = filemap_write_and_wait(inode->i_mapping);
-	}
+	/* Append the verity descriptor. */
+	err = pagecache_write(inode, desc, desc_size, desc_pos);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Write all pages (both data and verity metadata).  Note that this must
+	 * happen before clearing FI_VERITY_IN_PROGRESS; otherwise pages beyond
+	 * i_size won't be written properly.  For crash consistency, this also
+	 * must happen before the verity inode flag gets persisted.
+	 */
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto cleanup;
+
+	/* Set the verity xattr. */
+	err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_VERITY,
+			    F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc),
+			    NULL, XATTR_CREATE);
+	if (err)
+		goto cleanup;
 
-	/* If we failed, truncate anything we wrote past i_size. */
-	if (desc == NULL || err)
-		f2fs_truncate(inode);
+	/* Finally, set the verity inode flag. */
+	file_set_verity(inode);
+	f2fs_set_inode_flags(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 
 	clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+	return 0;
 
-	if (desc != NULL && !err) {
-		err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_VERITY,
-				    F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc),
-				    NULL, XATTR_CREATE);
-		if (!err) {
-			file_set_verity(inode);
-			f2fs_set_inode_flags(inode);
-			f2fs_mark_inode_dirty_sync(inode, true);
-		}
+cleanup:
+	/*
+	 * Verity failed to be enabled, so clean up by truncating any verity
+	 * metadata that was written beyond i_size (both from cache and from
+	 * disk) and clearing FI_VERITY_IN_PROGRESS.
+	 *
+	 * Taking i_gc_rwsem[WRITE] is needed to stop f2fs garbage collection
+	 * from re-instantiating cached pages we are truncating (since unlike
+	 * normal file accesses, garbage collection isn't limited by i_size).
+	 */
+	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	err2 = f2fs_truncate(inode);
+	if (err2) {
+		f2fs_err(sbi, "Truncating verity metadata failed (errno=%d)",
+			 err2);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 	}
-	return err;
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+	return err ?: err2;
 }
 
 static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 490f843ec3bf..c8f34decbf8e 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -488,6 +488,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 		f2fs_wait_on_page_writeback(xpage, NODE, true, true);
 	} else {
 		struct dnode_of_data dn;
+
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
 		xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
 		if (IS_ERR(xpage)) {