Merge remote-tracking branch 'aosp/upstream-f2fs-stable-linux-5.10.y' into android12-5.10

* aosp/upstream-f2fs-stable-linux-5.10.y:
  Revert "f2fs: avoid attaching SB_ACTIVE flag during mount/remount"
  f2fs: remove false alarm on iget failure during GC
  f2fs: enable extent cache for compression files in read-only
  f2fs: fix to avoid adding tab before doc section
  f2fs: introduce f2fs_casefolded_name slab cache
  f2fs: swap: support migrating swapfile in aligned write mode
  f2fs: swap: remove dead codes
  f2fs: compress: add compress_inode to cache compressed blocks
  f2fs: clean up /sys/fs/f2fs/<disk>/features
  f2fs: add pin_file in feature list
  f2fs: Advertise encrypted casefolding in sysfs
  f2fs: Show casefolding support only when supported
  f2fs: support RO feature
  f2fs: logging neatening

Bug: 186107892
Bug: 190759634
Bug: 190517210
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
Change-Id: I8eb93d8a43304b98166676da52a9c2434b15b942

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -203,7 +203,34 @@ Description:	Shows total written kbytes issued to disk.
 What:		/sys/fs/f2fs/<disk>/features
 Date:		July 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:	Shows all enabled features in current device.
+Description:	<deprecated: should use /sys/fs/f2fs/<disk>/feature_list/
+		Shows all enabled features in current device.
+		Supported features:
+		encryption, blkzoned, extra_attr, projquota, inode_checksum,
+		flexible_inline_xattr, quota_ino, inode_crtime, lost_found,
+		verity, sb_checksum, casefold, readonly, compression, pin_file.
+
+What:		/sys/fs/f2fs/<disk>/feature_list/
+Date:		June 2021
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Expand /sys/fs/f2fs/<disk>/features to meet sysfs rule.
+		Supported on-disk features:
+		encryption, block_zoned (aka blkzoned), extra_attr,
+		project_quota (aka projquota), inode_checksum,
+		flexible_inline_xattr, quota_ino, inode_crtime, lost_found,
+		verity, sb_checksum, casefold, readonly, compression.
+		Note that, pin_file is moved into /sys/fs/f2fs/features/.
+
+What:		/sys/fs/f2fs/features/
+Date:		July 2017
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Shows all enabled kernel features.
+		Supported features:
+		encryption, block_zoned, extra_attr, project_quota,
+		inode_checksum, flexible_inline_xattr, quota_ino,
+		inode_crtime, lost_found, verity, sb_checksum,
+		casefold, readonly, compression, test_dummy_encryption_v2,
+		atomic_write, pin_file, encrypted_casefold.
 
 What:		/sys/fs/f2fs/<disk>/inject_rate
 Date:		May 2016

Documentation/filesystems/f2fs.rst

@@ -289,6 +289,9 @@ compress_mode=%s	 Control file compression mode. This supports "fs" and "user"
 			 choosing the target file and the timing. The user can do manual
 			 compression/decompression on the compression enabled files using
 			 ioctls.
+compress_cache		 Support to use address space of a filesystem managed inode to
+			 cache compressed block, in order to improve cache hit ratio of
+			 random read.
 inlinecrypt		 When possible, encrypt/decrypt the contents of encrypted
 			 files using the blk-crypto framework rather than
 			 filesystem-layer encryption. This allows the use of
@@ -717,10 +720,10 @@ users.
 ===================== ======================== ===================
 User                  F2FS                     Block
 ===================== ======================== ===================
-                      META                     WRITE_LIFE_NOT_SET
+N/A                   META                     WRITE_LIFE_NOT_SET
-                      HOT_NODE                 "
+N/A                   HOT_NODE                 "
-                      WARM_NODE                "
+N/A                   WARM_NODE                "
-                      COLD_NODE                "
+N/A                   COLD_NODE                "
 ioctl(COLD)           COLD_DATA                WRITE_LIFE_EXTREME
 extension list        "                        "
 
@@ -746,10 +749,10 @@ WRITE_LIFE_LONG       "                        WRITE_LIFE_LONG
 ===================== ======================== ===================
 User                  F2FS                     Block
 ===================== ======================== ===================
-                      META                     WRITE_LIFE_MEDIUM;
+N/A                   META                     WRITE_LIFE_MEDIUM;
-                      HOT_NODE                 WRITE_LIFE_NOT_SET
+N/A                   HOT_NODE                 WRITE_LIFE_NOT_SET
-                      WARM_NODE                "
+N/A                   WARM_NODE                "
-                      COLD_NODE                WRITE_LIFE_NONE
+N/A                   COLD_NODE                WRITE_LIFE_NONE
 ioctl(COLD)           COLD_DATA                WRITE_LIFE_EXTREME
 extension list        "                        "
 

fs/f2fs/checkpoint.c

@@ -691,6 +691,9 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 
 #ifdef CONFIG_QUOTA
+	/* Needed for iput() to work correctly and not trash data */
+	sbi->sb->s_flags |= SB_ACTIVE;
+
 	/*
 	 * Turn on quotas which were not enabled for read-only mounts if
 	 * filesystem has quota feature, so that they are updated correctly.

fs/f2fs/compress.c

@@ -12,9 +12,11 @@
 #include <linux/lzo.h>
 #include <linux/lz4.h>
 #include <linux/zstd.h>
+#include <linux/pagevec.h>
 
 #include "f2fs.h"
 #include "node.h"
+#include "segment.h"
 #include <trace/events/f2fs.h>
 
 static struct kmem_cache *cic_entry_slab;
@@ -736,7 +738,7 @@ out:
 	return ret;
 }
 
-static void f2fs_decompress_cluster(struct decompress_io_ctx *dic)
+void f2fs_decompress_cluster(struct decompress_io_ctx *dic)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode);
 	struct f2fs_inode_info *fi = F2FS_I(dic->inode);
@@ -835,7 +837,8 @@ out_end_io:
  * page being waited on in the cluster, and if so, it decompresses the cluster
  * (or in the case of a failure, cleans up without actually decompressing).
  */
-void f2fs_end_read_compressed_page(struct page *page, bool failed)
+void f2fs_end_read_compressed_page(struct page *page, bool failed,
+						block_t blkaddr)
 {
 	struct decompress_io_ctx *dic =
 			(struct decompress_io_ctx *)page_private(page);
@@ -845,6 +848,9 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed)
 
 	if (failed)
 		WRITE_ONCE(dic->failed, true);
+	else if (blkaddr)
+		f2fs_cache_compressed_page(sbi, page,
+					dic->inode->i_ino, blkaddr);
 
 	if (atomic_dec_and_test(&dic->remaining_pages))
 		f2fs_decompress_cluster(dic);
@@ -1660,6 +1666,164 @@ void f2fs_put_page_dic(struct page *page)
 	f2fs_put_dic(dic);
 }
 
+const struct address_space_operations f2fs_compress_aops = {
+	.releasepage = f2fs_release_page,
+	.invalidatepage = f2fs_invalidate_page,
+};
+
+struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi)
+{
+	return sbi->compress_inode->i_mapping;
+}
+
+void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	if (!sbi->compress_inode)
+		return;
+	invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr);
+}
+
+void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+						nid_t ino, block_t blkaddr)
+{
+	struct page *cpage;
+	int ret;
+
+	if (!test_opt(sbi, COMPRESS_CACHE))
+		return;
+
+	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ))
+		return;
+
+	if (!f2fs_available_free_memory(sbi, COMPRESS_PAGE))
+		return;
+
+	cpage = find_get_page(COMPRESS_MAPPING(sbi), blkaddr);
+	if (cpage) {
+		f2fs_put_page(cpage, 0);
+		return;
+	}
+
+	cpage = alloc_page(__GFP_NOWARN | __GFP_IO);
+	if (!cpage)
+		return;
+
+	ret = add_to_page_cache_lru(cpage, COMPRESS_MAPPING(sbi),
+						blkaddr, GFP_NOFS);
+	if (ret) {
+		f2fs_put_page(cpage, 0);
+		return;
+	}
+
+	set_page_private_data(cpage, ino);
+
+	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ))
+		goto out;
+
+	memcpy(page_address(cpage), page_address(page), PAGE_SIZE);
+	SetPageUptodate(cpage);
+out:
+	f2fs_put_page(cpage, 1);
+}
+
+bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+								block_t blkaddr)
+{
+	struct page *cpage;
+	bool hitted = false;
+
+	if (!test_opt(sbi, COMPRESS_CACHE))
+		return false;
+
+	cpage = f2fs_pagecache_get_page(COMPRESS_MAPPING(sbi),
+				blkaddr, FGP_LOCK | FGP_NOWAIT, GFP_NOFS);
+	if (cpage) {
+		if (PageUptodate(cpage)) {
+			atomic_inc(&sbi->compress_page_hit);
+			memcpy(page_address(page),
+				page_address(cpage), PAGE_SIZE);
+			hitted = true;
+		}
+		f2fs_put_page(cpage, 1);
+	}
+
+	return hitted;
+}
+
+void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct address_space *mapping = sbi->compress_inode->i_mapping;
+	struct pagevec pvec;
+	pgoff_t index = 0;
+	pgoff_t end = MAX_BLKADDR(sbi);
+
+	if (!mapping->nrpages)
+		return;
+
+	pagevec_init(&pvec);
+
+	do {
+		unsigned int nr_pages;
+		int i;
+
+		nr_pages = pagevec_lookup_range(&pvec, mapping,
+						&index, end - 1);
+		if (!nr_pages)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			if (page->index > end)
+				break;
+
+			lock_page(page);
+			if (page->mapping != mapping) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (ino != get_page_private_data(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			generic_error_remove_page(mapping, page);
+			unlock_page(page);
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	} while (index < end);
+}
+
+int f2fs_init_compress_inode(struct f2fs_sb_info *sbi)
+{
+	struct inode *inode;
+
+	if (!test_opt(sbi, COMPRESS_CACHE))
+		return 0;
+
+	inode = f2fs_iget(sbi->sb, F2FS_COMPRESS_INO(sbi));
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+	sbi->compress_inode = inode;
+
+	sbi->compress_percent = COMPRESS_PERCENT;
+	sbi->compress_watermark = COMPRESS_WATERMARK;
+
+	atomic_set(&sbi->compress_page_hit, 0);
+
+	return 0;
+}
+
+void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi)
+{
+	if (!sbi->compress_inode)
+		return;
+	iput(sbi->compress_inode);
+	sbi->compress_inode = NULL;
+}
+
 int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi)
 {
 	dev_t dev = sbi->sb->s_bdev->bd_dev;

fs/f2fs/data.c

@@ -133,7 +133,7 @@ static void f2fs_finish_read_bio(struct bio *bio)
 
 		if (f2fs_is_compressed_page(page)) {
 			if (bio->bi_status)
-				f2fs_end_read_compressed_page(page, true);
+				f2fs_end_read_compressed_page(page, true, 0);
 			f2fs_put_page_dic(page);
 			continue;
 		}
@@ -229,15 +229,19 @@ static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx)
 	struct bio_vec *bv;
 	struct bvec_iter_all iter_all;
 	bool all_compressed = true;
+	block_t blkaddr = SECTOR_TO_BLOCK(ctx->bio->bi_iter.bi_sector);
 
 	bio_for_each_segment_all(bv, ctx->bio, iter_all) {
 		struct page *page = bv->bv_page;
 
 		/* PG_error was set if decryption failed. */
 		if (f2fs_is_compressed_page(page))
-			f2fs_end_read_compressed_page(page, PageError(page));
+			f2fs_end_read_compressed_page(page, PageError(page),
+						blkaddr);
 		else
 			all_compressed = false;
+
+		blkaddr++;
 	}
 
 	/*
@@ -1368,9 +1372,11 @@ alloc:
 	old_blkaddr = dn->data_blkaddr;
 	f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
 				&sum, seg_type, NULL);
-	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
+		f2fs_invalidate_compress_page(sbi, old_blkaddr);
+	}
 	f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
 
 	/*
@@ -2190,7 +2196,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 		goto out_put_dnode;
 	}
 
-	for (i = 0; i < dic->nr_cpages; i++) {
+	for (i = 0; i < cc->nr_cpages; i++) {
 		struct page *page = dic->cpages[i];
 		block_t blkaddr;
 		struct bio_post_read_ctx *ctx;
@@ -2198,6 +2204,14 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 		blkaddr = data_blkaddr(dn.inode, dn.node_page,
 						dn.ofs_in_node + i + 1);
 
+		f2fs_wait_on_block_writeback(inode, blkaddr);
+
+		if (f2fs_load_compressed_page(sbi, page, blkaddr)) {
+			if (atomic_dec_and_test(&dic->remaining_pages))
+				f2fs_decompress_cluster(dic);
+			continue;
+		}
+
 		if (bio && (!page_is_mergeable(sbi, bio,
 					*last_block_in_bio, blkaddr) ||
 		    !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
@@ -2219,8 +2233,6 @@ submit_and_realloc:
 			}
 		}
 
-		f2fs_wait_on_block_writeback(inode, blkaddr);
-
 		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
 			goto submit_and_realloc;
 
@@ -2476,6 +2488,10 @@ static inline bool check_inplace_update_policy(struct inode *inode,
 
 bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
 {
+	/* swap file is migrating in aligned write mode */
+	if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
+		return false;
+
 	if (f2fs_is_pinned_file(inode))
 		return true;
 
@@ -2498,6 +2514,11 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
 		return true;
 	if (f2fs_is_atomic_file(inode))
 		return true;
+
+	/* swap file is migrating in aligned write mode */
+	if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
+		return true;
+
 	if (fio) {
 		if (page_private_gcing(fio->page))
 			return true;
@@ -3675,6 +3696,13 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 
 	clear_page_private_gcing(page);
 
+	if (test_opt(sbi, COMPRESS_CACHE)) {
+		if (f2fs_compressed_file(inode))
+			f2fs_invalidate_compress_pages(sbi, inode->i_ino);
+		if (inode->i_ino == F2FS_COMPRESS_INO(sbi))
+			clear_page_private_data(page);
+	}
+
 	if (page_private_atomic(page))
 		return f2fs_drop_inmem_page(inode, page);
 
@@ -3692,6 +3720,16 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	if (page_private_atomic(page))
 		return 0;
 
+	if (test_opt(F2FS_P_SB(page), COMPRESS_CACHE)) {
+		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+		struct inode *inode = page->mapping->host;
+
+		if (f2fs_compressed_file(inode))
+			f2fs_invalidate_compress_pages(sbi, inode->i_ino);
+		if (inode->i_ino == F2FS_COMPRESS_INO(sbi))
+			clear_page_private_data(page);
+	}
+
 	clear_page_private_gcing(page);
 
 	detach_page_private(page);
@@ -3858,67 +3896,66 @@ int f2fs_migrate_page(struct address_space *mapping,
 #endif
 
 #ifdef CONFIG_SWAP
-static int f2fs_is_file_aligned(struct inode *inode)
+static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
+							unsigned int blkcnt)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	block_t main_blkaddr = SM_I(sbi)->main_blkaddr;
+	unsigned int blkofs;
-	block_t cur_lblock;
+	unsigned int blk_per_sec = BLKS_PER_SEC(sbi);
-	block_t last_lblock;
+	unsigned int secidx = start_blk / blk_per_sec;
-	block_t pblock;
+	unsigned int end_sec = secidx + blkcnt / blk_per_sec;
-	unsigned long nr_pblocks;
-	unsigned int blocks_per_sec = BLKS_PER_SEC(sbi);
-	unsigned int not_aligned = 0;
 	int ret = 0;
 
-	cur_lblock = 0;
+	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	last_lblock = bytes_to_blks(inode, i_size_read(inode));
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 
-	while (cur_lblock < last_lblock) {
+	set_inode_flag(inode, FI_ALIGNED_WRITE);
-		struct f2fs_map_blocks map;
 
-		memset(&map, 0, sizeof(map));
+	for (; secidx < end_sec; secidx++) {
-		map.m_lblk = cur_lblock;
+		down_write(&sbi->pin_sem);
-		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);
+		f2fs_lock_op(sbi);
-		if (ret)
+		f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
-			goto out;
+		f2fs_unlock_op(sbi);
 
-		/* hole */
+		set_inode_flag(inode, FI_DO_DEFRAG);
-		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
-			f2fs_err(sbi, "Swapfile has holes\n");
-			ret = -ENOENT;
-			goto out;
-		}
 
-		pblock = map.m_pblk;
+		for (blkofs = 0; blkofs < blk_per_sec; blkofs++) {
-		nr_pblocks = map.m_len;
+			struct page *page;
+			unsigned int blkidx = secidx * blk_per_sec + blkofs;
 
-		if ((pblock - main_blkaddr) & (blocks_per_sec - 1) ||
+			page = f2fs_get_lock_data_page(inode, blkidx, true);
-			nr_pblocks & (blocks_per_sec - 1)) {
+			if (IS_ERR(page)) {
-			if (f2fs_is_pinned_file(inode)) {
+				up_write(&sbi->pin_sem);
-				f2fs_err(sbi, "Swapfile does not align to section");
+				ret = PTR_ERR(page);
-				ret = -EINVAL;
+				goto done;
-				goto out;
 			}
-			not_aligned++;
+
+			set_page_dirty(page);
+			f2fs_put_page(page, 1);
 		}
 
-		cur_lblock += nr_pblocks;
+		clear_inode_flag(inode, FI_DO_DEFRAG);
+
+		ret = filemap_fdatawrite(inode->i_mapping);
+
+		up_write(&sbi->pin_sem);
+
+		if (ret)
+			break;
 	}
-	if (not_aligned)
+
-		f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n"
+done:
-			"\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()",
+	clear_inode_flag(inode, FI_DO_DEFRAG);
-			not_aligned);
+	clear_inode_flag(inode, FI_ALIGNED_WRITE);
-out:
+
+	up_write(&F2FS_I(inode)->i_mmap_sem);
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+
 	return ret;
 }
 
-static int check_swap_activate_fast(struct swap_info_struct *sis,
+static int check_swap_activate(struct swap_info_struct *sis,
 				struct file *swap_file, sector_t *span)
 {
 	struct address_space *mapping = swap_file->f_mapping;
@@ -3931,7 +3968,8 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 	sector_t highest_pblock = 0;
 	int nr_extents = 0;
 	unsigned long nr_pblocks;
-	unsigned int blocks_per_sec = BLKS_PER_SEC(sbi);
+	unsigned int blks_per_sec = BLKS_PER_SEC(sbi);
+	unsigned int sec_blks_mask = BLKS_PER_SEC(sbi) - 1;
 	unsigned int not_aligned = 0;
 	int ret = 0;
 
@@ -3944,7 +3982,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 
 	while (cur_lblock < last_lblock && cur_lblock < sis->max) {
 		struct f2fs_map_blocks map;
-
+retry:
 		cond_resched();
 
 		memset(&map, 0, sizeof(map));
@@ -3961,7 +3999,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 
 		/* hole */
 		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
-			f2fs_err(sbi, "Swapfile has holes\n");
+			f2fs_err(sbi, "Swapfile has holes");
 			ret = -EINVAL;
 			goto out;
 		}
@@ -3969,16 +4007,28 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 		pblock = map.m_pblk;
 		nr_pblocks = map.m_len;
 
-		if ((pblock - SM_I(sbi)->main_blkaddr) & (blocks_per_sec - 1) ||
+		if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask ||
-				nr_pblocks & (blocks_per_sec - 1)) {
+				nr_pblocks & sec_blks_mask) {
-			if (f2fs_is_pinned_file(inode)) {
-				f2fs_err(sbi, "Swapfile does not align to section");
-				ret = -EINVAL;
-				goto out;
-			}
 			not_aligned++;
-		}
 
+			nr_pblocks = roundup(nr_pblocks, blks_per_sec);
+			if (cur_lblock + nr_pblocks > sis->max)
+				nr_pblocks -= blks_per_sec;
+
+			if (!nr_pblocks) {
+				/* this extent is last one */
+				nr_pblocks = map.m_len;
+				f2fs_warn(sbi, "Swapfile: last extent is not aligned to section");
+				goto next;
+			}
+
+			ret = f2fs_migrate_blocks(inode, cur_lblock,
+							nr_pblocks);
+			if (ret)
+				goto out;
+			goto retry;
+		}
+next:
 		if (cur_lblock + nr_pblocks >= sis->max)
 			nr_pblocks = sis->max - cur_lblock;
 
@@ -4005,122 +4055,13 @@ static int check_swap_activate_fast(struct swap_info_struct *sis,
 	sis->max = cur_lblock;
 	sis->pages = cur_lblock - 1;
 	sis->highest_bit = cur_lblock - 1;
-
+out:
 	if (not_aligned)
-		f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n"
+		f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%u * N)",
-			"\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()",
+			  not_aligned, blks_per_sec * F2FS_BLKSIZE);
-			not_aligned);
-out:
 	return ret;
 }
 
-/* Copied from generic_swapfile_activate() to check any holes */
-static int check_swap_activate(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);
-	unsigned blocks_per_page;
-	unsigned long page_no;
-	sector_t probe_block;
-	sector_t last_block;
-	sector_t lowest_block = -1;
-	sector_t highest_block = 0;
-	int nr_extents = 0;
-	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);
-
-	/*
-	 * Map all the blocks into the extent list.  This code doesn't try
-	 * to be very smart.
-	 */
-	probe_block = 0;
-	page_no = 0;
-	last_block = bytes_to_blks(inode, i_size_read(inode));
-	while ((probe_block + blocks_per_page) <= last_block &&
-			page_no < sis->max) {
-		unsigned block_in_page;
-		sector_t first_block;
-		sector_t block = 0;
-
-		cond_resched();
-
-		block = probe_block;
-		ret = bmap(inode, &block);
-		if (ret)
-			goto out;
-		if (!block)
-			goto bad_bmap;
-		first_block = block;
-
-		/*
-		 * It must be PAGE_SIZE aligned on-disk
-		 */
-		if (first_block & (blocks_per_page - 1)) {
-			probe_block++;
-			goto reprobe;
-		}
-
-		for (block_in_page = 1; block_in_page < blocks_per_page;
-					block_in_page++) {
-
-			block = probe_block + block_in_page;
-			ret = bmap(inode, &block);
-			if (ret)
-				goto out;
-			if (!block)
-				goto bad_bmap;
-
-			if (block != first_block + block_in_page) {
-				/* Discontiguity */
-				probe_block++;
-				goto reprobe;
-			}
-		}
-
-		first_block >>= (PAGE_SHIFT - inode->i_blkbits);
-		if (page_no) {	/* exclude the header page */
-			if (first_block < lowest_block)
-				lowest_block = first_block;
-			if (first_block > highest_block)
-				highest_block = first_block;
-		}
-
-		/*
-		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
-		 */
-		ret = add_swap_extent(sis, page_no, 1, first_block);
-		if (ret < 0)
-			goto out;
-		nr_extents += ret;
-		page_no++;
-		probe_block += blocks_per_page;
-reprobe:
-		continue;
-	}
-	ret = nr_extents;
-	*span = 1 + highest_block - lowest_block;
-	if (page_no == 0)
-		page_no = 1;	/* force Empty message */
-	sis->max = page_no;
-	sis->pages = page_no - 1;
-	sis->highest_bit = page_no - 1;
-out:
-	return ret;
-bad_bmap:
-	f2fs_err(sbi, "Swapfile has holes\n");
-	return -EINVAL;
-}
-
 static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
 				sector_t *span)
 {

fs/f2fs/debug.c

@@ -152,6 +152,12 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	if (sbi->meta_inode)
 		si->meta_pages = META_MAPPING(sbi)->nrpages;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (sbi->compress_inode) {
+		si->compress_pages = COMPRESS_MAPPING(sbi)->nrpages;
+		si->compress_page_hit = atomic_read(&sbi->compress_page_hit);
+	}
+#endif
 	si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT];
 	si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT];
 	si->sits = MAIN_SEGS(sbi);
@@ -309,6 +315,12 @@ get_cache:
 
 		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (sbi->compress_inode) {
+		unsigned npages = COMPRESS_MAPPING(sbi)->nrpages;
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
+#endif
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -476,6 +488,7 @@ static int stat_show(struct seq_file *s, void *v)
 			"volatile IO: %4d (Max. %4d)\n",
 			   si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
 			   si->vw_cnt, si->max_vw_cnt);
+		seq_printf(s, "  - compress: %4d, hit:%8d\n", si->compress_pages, si->compress_page_hit);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",

fs/f2fs/dir.c

@@ -16,6 +16,10 @@
 #include "xattr.h"
 #include <trace/events/f2fs.h>
 
+#ifdef CONFIG_UNICODE
+extern struct kmem_cache *f2fs_cf_name_slab;
+#endif
+
 static unsigned long dir_blocks(struct inode *inode)
 {
 	return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
@@ -77,11 +81,10 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 {
 #ifdef CONFIG_UNICODE
 	struct super_block *sb = dir->i_sb;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (IS_CASEFOLDED(dir)) {
-		fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
+		fname->cf_name.name = kmem_cache_alloc(f2fs_cf_name_slab,
-						   GFP_NOFS);
+								GFP_NOFS);
 		if (!fname->cf_name.name)
 			return -ENOMEM;
 		fname->cf_name.len = utf8_casefold(sb->s_encoding,
@@ -89,7 +92,7 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 						   fname->cf_name.name,
 						   F2FS_NAME_LEN);
 		if ((int)fname->cf_name.len <= 0) {
-			kfree(fname->cf_name.name);
+			kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
 			fname->cf_name.name = NULL;
 			if (sb_has_strict_encoding(sb))
 				return -EINVAL;
@@ -172,8 +175,10 @@ void f2fs_free_filename(struct f2fs_filename *fname)
 	fname->crypto_buf.name = NULL;
 #endif
 #ifdef CONFIG_UNICODE
-	kfree(fname->cf_name.name);
+	if (fname->cf_name.name) {
-	fname->cf_name.name = NULL;
+		kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
+		fname->cf_name.name = NULL;
+	}
 #endif
 }
 

fs/f2fs/f2fs.h

@@ -98,6 +98,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_ATGC			0x08000000
 #define F2FS_MOUNT_MERGE_CHECKPOINT	0x10000000
 #define	F2FS_MOUNT_GC_MERGE		0x20000000
+#define F2FS_MOUNT_COMPRESS_CACHE	0x40000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -168,6 +169,7 @@ struct f2fs_mount_info {
 #define F2FS_FEATURE_SB_CHKSUM		0x0800
 #define F2FS_FEATURE_CASEFOLD		0x1000
 #define F2FS_FEATURE_COMPRESSION	0x2000
+#define F2FS_FEATURE_RO			0x4000
 
 #define __F2FS_HAS_FEATURE(raw_super, mask)				\
 	((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -707,6 +709,7 @@ enum {
 	FI_MMAP_FILE,		/* indicate file was mmapped */
 	FI_ENABLE_COMPRESS,	/* enable compression in "user" compression mode */
 	FI_COMPRESS_RELEASED,	/* compressed blocks were released */
+	FI_ALIGNED_WRITE,	/* enable aligned write */
 	FI_MAX,			/* max flag, never be used */
 };
 
@@ -940,6 +943,7 @@ static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
 #define	NR_CURSEG_DATA_TYPE	(3)
 #define NR_CURSEG_NODE_TYPE	(3)
 #define NR_CURSEG_INMEM_TYPE	(2)
+#define NR_CURSEG_RO_TYPE	(2)
 #define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
 #define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
 
@@ -1372,6 +1376,37 @@ PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
 PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
 PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE);
 
+static inline unsigned long get_page_private_data(struct page *page)
+{
+	unsigned long data = page_private(page);
+
+	if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
+		return 0;
+	return data >> PAGE_PRIVATE_MAX;
+}
+
+static inline void set_page_private_data(struct page *page, unsigned long data)
+{
+	if (!PagePrivate(page)) {
+		get_page(page);
+		SetPagePrivate(page);
+	}
+	set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page));
+	page_private(page) |= data << PAGE_PRIVATE_MAX;
+}
+
+static inline void clear_page_private_data(struct page *page)
+{
+	page_private(page) &= (1 << PAGE_PRIVATE_MAX) - 1;
+	if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) {
+		set_page_private(page, 0);
+		if (PagePrivate(page)) {
+			ClearPagePrivate(page);
+			put_page(page);
+		}
+	}
+}
+
 /* For compression */
 enum compress_algorithm_type {
 	COMPRESS_LZO,
@@ -1386,6 +1421,9 @@ enum compress_flag {
 	COMPRESS_MAX_FLAG,
 };
 
+#define	COMPRESS_WATERMARK			20
+#define	COMPRESS_PERCENT			20
+
 #define COMPRESS_DATA_RESERVED_SIZE		4
 struct compress_data {
 	__le32 clen;			/* compressed data size */
@@ -1663,6 +1701,9 @@ struct f2fs_sb_info {
 	struct kobject s_stat_kobj;		/* /sys/fs/f2fs/<devname>/stat */
 	struct completion s_stat_kobj_unregister;
 
+	struct kobject s_feature_list_kobj;		/* /sys/fs/f2fs/<devname>/feature_list */
+	struct completion s_feature_list_kobj_unregister;
+
 	/* For shrinker support */
 	struct list_head s_list;
 	int s_ndevs;				/* number of devices */
@@ -1695,6 +1736,12 @@ struct f2fs_sb_info {
 	u64 compr_written_block;
 	u64 compr_saved_block;
 	u32 compr_new_inode;
+
+	/* For compressed block cache */
+	struct inode *compress_inode;		/* cache compressed blocks */
+	unsigned int compress_percent;		/* cache page percentage */
+	unsigned int compress_watermark;	/* cache page watermark */
+	atomic_t compress_page_hit;		/* cache hit count */
 #endif
 };
 
@@ -3101,25 +3148,6 @@ static inline bool is_dot_dotdot(const u8 *name, size_t len)
 	return false;
 }
 
-static inline bool f2fs_may_extent_tree(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
-	if (!test_opt(sbi, EXTENT_CACHE) ||
-			is_inode_flag_set(inode, FI_NO_EXTENT) ||
-			is_inode_flag_set(inode, FI_COMPRESSED_FILE))
-		return false;
-
-	/*
-	 * for recovered files during mount do not create extents
-	 * if shrinker is not registered.
-	 */
-	if (list_empty(&sbi->s_list))
-		return false;
-
-	return S_ISREG(inode->i_mode);
-}
-
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
@@ -3662,7 +3690,8 @@ struct f2fs_stat_info {
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
 	int rsvd_segs, overp_segs;
-	int dirty_count, node_pages, meta_pages;
+	int dirty_count, node_pages, meta_pages, compress_pages;
+	int compress_page_hit;
 	int prefree_count, call_count, cp_count, bg_cp_count;
 	int tot_segs, node_segs, data_segs, free_segs, free_secs;
 	int bg_node_segs, bg_data_segs;
@@ -3998,7 +4027,9 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
 bool f2fs_is_compress_backend_ready(struct inode *inode);
 int f2fs_init_compress_mempool(void);
 void f2fs_destroy_compress_mempool(void);
-void f2fs_end_read_compressed_page(struct page *page, bool failed);
+void f2fs_decompress_cluster(struct decompress_io_ctx *dic);
+void f2fs_end_read_compressed_page(struct page *page, bool failed,
+							block_t blkaddr);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
 void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
@@ -4016,10 +4047,19 @@ void f2fs_put_page_dic(struct page *page);
 int f2fs_init_compress_ctx(struct compress_ctx *cc);
 void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
 void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
+int f2fs_init_compress_inode(struct f2fs_sb_info *sbi);
+void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi);
 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);
+struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi);
+void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+						nid_t ino, block_t blkaddr);
+bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+								block_t blkaddr);
+void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino);
 #define inc_compr_inode_stat(inode)					\
 	do {								\
 		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);		\
@@ -4048,7 +4088,9 @@ static inline struct page *f2fs_compress_control_page(struct page *page)
 }
 static inline int f2fs_init_compress_mempool(void) { return 0; }
 static inline void f2fs_destroy_compress_mempool(void) { }
-static inline void f2fs_end_read_compressed_page(struct page *page, bool failed)
+static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic) { }
+static inline void f2fs_end_read_compressed_page(struct page *page,
+						bool failed, block_t blkaddr)
 {
 	WARN_ON_ONCE(1);
 }
@@ -4056,10 +4098,20 @@ static inline void f2fs_put_page_dic(struct page *page)
 {
 	WARN_ON_ONCE(1);
 }
+static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { }
 static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
 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) { }
+static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi,
+				block_t blkaddr) { }
+static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
+				struct page *page, nid_t ino, block_t blkaddr) { }
+static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
+				struct page *page, block_t blkaddr) { return false; }
+static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
+							nid_t ino) { }
 #define inc_compr_inode_stat(inode)		do { } while (0)
 #endif
 
@@ -4124,6 +4176,27 @@ F2FS_FEATURE_FUNCS(verity, VERITY);
 F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
 F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
 F2FS_FEATURE_FUNCS(compression, COMPRESSION);
+F2FS_FEATURE_FUNCS(readonly, RO);
+
+static inline bool f2fs_may_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (!test_opt(sbi, EXTENT_CACHE) ||
+			is_inode_flag_set(inode, FI_NO_EXTENT) ||
+			(is_inode_flag_set(inode, FI_COMPRESSED_FILE) &&
+			 !f2fs_sb_has_readonly(sbi)))
+		return false;
+
+	/*
+	 * for recovered files during mount do not create extents
+	 * if shrinker is not registered.
+	 */
+	if (list_empty(&sbi->s_list))
+		return false;
+
+	return S_ISREG(inode->i_mode);
+}
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,

fs/f2fs/file.c

@@ -3360,7 +3360,7 @@ static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg)
 
 	if (!f2fs_sb_has_verity(F2FS_I_SB(inode))) {
 		f2fs_warn(F2FS_I_SB(inode),
-			  "Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem.\n",
+			  "Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem",
 			  inode->i_ino);
 		return -EOPNOTSUPP;
 	}
@@ -4144,9 +4144,8 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg)
 							LLONG_MAX);
 
 	if (ret)
-		f2fs_warn(sbi, "%s: The file might be partially decompressed "
+		f2fs_warn(sbi, "%s: The file might be partially decompressed (errno=%d). Please delete the file.",
-				"(errno=%d). Please delete the file.\n",
+			  __func__, ret);
-				__func__, ret);
 out:
 	inode_unlock(inode);
 	file_end_write(filp);
@@ -4218,9 +4217,8 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg)
 	clear_inode_flag(inode, FI_ENABLE_COMPRESS);
 
 	if (ret)
-		f2fs_warn(sbi, "%s: The file might be partially compressed "
+		f2fs_warn(sbi, "%s: The file might be partially compressed (errno=%d). Please delete the file.",
-				"(errno=%d). Please delete the file.\n",
+			  __func__, ret);
-				__func__, ret);
 out:
 	inode_unlock(inode);
 	file_end_write(filp);

fs/f2fs/gc.c

@@ -1031,8 +1031,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 		if (unlikely(check_valid_map(sbi, segno, offset))) {
 			if (!test_and_set_bit(segno, SIT_I(sbi)->invalid_segmap)) {
-				f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u\n",
+				f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u",
-						blkaddr, source_blkaddr, segno);
+					 blkaddr, source_blkaddr, segno);
 				f2fs_bug_on(sbi, 1);
 			}
 		}
@@ -1261,6 +1261,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 	f2fs_put_page(mpage, 1);
 	invalidate_mapping_pages(META_MAPPING(fio.sbi),
 				fio.old_blkaddr, fio.old_blkaddr);
+	f2fs_invalidate_compress_page(fio.sbi, fio.old_blkaddr);
 
 	set_page_dirty(fio.encrypted_page);
 	if (clear_page_dirty_for_io(fio.encrypted_page))
@@ -1450,10 +1451,8 @@ next_step:
 
 		if (phase == 3) {
 			inode = f2fs_iget(sb, dni.ino);
-			if (IS_ERR(inode) || is_bad_inode(inode)) {
+			if (IS_ERR(inode) || is_bad_inode(inode))
-				set_sbi_flag(sbi, SBI_NEED_FSCK);
 				continue;
-			}
 
 			if (!down_write_trylock(
 				&F2FS_I(inode)->i_gc_rwsem[WRITE])) {

fs/f2fs/inode.c

@@ -18,6 +18,10 @@
 
 #include <trace/events/f2fs.h>
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+extern const struct address_space_operations f2fs_compress_aops;
+#endif
+
 void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 {
 	if (is_inode_flag_set(inode, FI_NEW_INODE))
@@ -494,6 +498,11 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 	if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
 		goto make_now;
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (ino == F2FS_COMPRESS_INO(sbi))
+		goto make_now;
+#endif
+
 	ret = do_read_inode(inode);
 	if (ret)
 		goto bad_inode;
@@ -504,6 +513,12 @@ make_now:
 	} else if (ino == F2FS_META_INO(sbi)) {
 		inode->i_mapping->a_ops = &f2fs_meta_aops;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	} else if (ino == F2FS_COMPRESS_INO(sbi)) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		inode->i_mapping->a_ops = &f2fs_compress_aops;
+#endif
+		mapping_set_gfp_mask(inode->i_mapping,
+			GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
 	} else if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &f2fs_file_inode_operations;
 		inode->i_fop = &f2fs_file_operations;
@@ -723,8 +738,12 @@ void f2fs_evict_inode(struct inode *inode)
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
 
+	if (test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
+		f2fs_invalidate_compress_pages(sbi, inode->i_ino);
+
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
-			inode->i_ino == F2FS_META_INO(sbi))
+			inode->i_ino == F2FS_META_INO(sbi) ||
+			inode->i_ino == F2FS_COMPRESS_INO(sbi))
 		goto out_clear;
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));

fs/f2fs/node.c

@@ -97,6 +97,20 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 		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 (type == COMPRESS_PAGE) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		unsigned long free_ram = val.freeram;
+
+		/*
+		 * free memory is lower than watermark or cached page count
+		 * exceed threshold, deny caching compress page.
+		 */
+		res = (free_ram > avail_ram * sbi->compress_watermark / 100) &&
+			(COMPRESS_MAPPING(sbi)->nrpages <
+			 free_ram * sbi->compress_percent / 100);
+#else
+		res = false;
+#endif
 	} else {
 		if (!sbi->sb->s_bdi->wb.dirty_exceeded)
 			return true;

fs/f2fs/node.h

@@ -38,6 +38,9 @@
 /* return value for read_node_page */
 #define LOCKED_PAGE	1
 
+/* check pinned file's alignment status of physical blocks */
+#define FILE_NOT_ALIGNED	1
+
 /* For flag in struct node_info */
 enum {
 	IS_CHECKPOINTED,	/* is it checkpointed before? */
@@ -148,6 +151,7 @@ enum mem_type {
 	EXTENT_CACHE,	/* indicates extent cache */
 	INMEM_PAGES,	/* indicates inmemory pages */
 	DISCARD_CACHE,	/* indicates memory of cached discard cmds */
+	COMPRESS_PAGE,	/* indicates memory of cached compressed pages */
 	BASE_CHECK,	/* check kernel status */
 };
 

fs/f2fs/recovery.c

@@ -45,6 +45,10 @@
 
 static struct kmem_cache *fsync_entry_slab;
 
+#ifdef CONFIG_UNICODE
+extern struct kmem_cache *f2fs_cf_name_slab;
+#endif
+
 bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
 {
 	s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
@@ -145,7 +149,7 @@ static int init_recovered_filename(const struct inode *dir,
 		f2fs_hash_filename(dir, fname);
 #ifdef CONFIG_UNICODE
 		/* Case-sensitive match is fine for recovery */
-		kfree(fname->cf_name.name);
+		kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
 		fname->cf_name.name = NULL;
 #endif
 	} else {
@@ -782,6 +786,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	}
 
 #ifdef CONFIG_QUOTA
+	/* Needed for iput() to work correctly and not trash data */
+	sbi->sb->s_flags |= SB_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
 	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
 #endif
@@ -809,8 +815,10 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
-	else
+	else {
-		f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE);
+		/* restore s_flags to let iput() trash data */
+		sbi->sb->s_flags = s_flags;
+	}
 skip:
 	fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
 

fs/f2fs/segment.c

@@ -2322,6 +2322,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 		return;
 
 	invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
+	f2fs_invalidate_compress_page(sbi, addr);
 
 	/* add it into sit main buffer */
 	down_write(&sit_i->sentry_lock);
@@ -3290,6 +3291,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	if (fio->type == DATA) {
 		struct inode *inode = fio->page->mapping->host;
 
+		if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
+			return CURSEG_COLD_DATA_PINNED;
+
 		if (page_private_gcing(fio->page)) {
 			if (fio->sbi->am.atgc_enabled &&
 				(fio->io_type == FS_DATA_IO) &&
@@ -3469,9 +3473,11 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 reallocate:
 	f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 			&fio->new_blkaddr, sum, type, fio);
-	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
+	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) {
 		invalidate_mapping_pages(META_MAPPING(fio->sbi),
 					fio->old_blkaddr, fio->old_blkaddr);
+		f2fs_invalidate_compress_page(fio->sbi, fio->old_blkaddr);
+	}
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_write(fio);
@@ -3661,6 +3667,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
+		f2fs_invalidate_compress_page(sbi, old_blkaddr);
 		if (!from_gc)
 			update_segment_mtime(sbi, old_blkaddr, 0);
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -3920,7 +3927,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 	/* sanity check for summary blocks */
 	if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
 			sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) {
-		f2fs_err(sbi, "invalid journal entries nats %u sits %u\n",
+		f2fs_err(sbi, "invalid journal entries nats %u sits %u",
 			 nats_in_cursum(nat_j), sits_in_cursum(sit_j));
 		return -EINVAL;
 	}
@@ -4683,6 +4690,10 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi)
 		struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
 		unsigned int blkofs = curseg->next_blkoff;
 
+		if (f2fs_sb_has_readonly(sbi) &&
+			i != CURSEG_HOT_DATA && i != CURSEG_HOT_NODE)
+			continue;
+
 		sanity_check_seg_type(sbi, curseg->seg_type);
 
 		if (f2fs_test_bit(blkofs, se->cur_valid_map))

fs/f2fs/super.c

@@ -150,6 +150,7 @@ enum {
 	Opt_compress_extension,
 	Opt_compress_chksum,
 	Opt_compress_mode,
+	Opt_compress_cache,
 	Opt_atgc,
 	Opt_gc_merge,
 	Opt_nogc_merge,
@@ -224,6 +225,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_extension, "compress_extension=%s"},
 	{Opt_compress_chksum, "compress_chksum"},
 	{Opt_compress_mode, "compress_mode=%s"},
+	{Opt_compress_cache, "compress_cache"},
 	{Opt_atgc, "atgc"},
 	{Opt_gc_merge, "gc_merge"},
 	{Opt_nogc_merge, "nogc_merge"},
@@ -275,6 +277,24 @@ static int f2fs_sb_read_encoding(const struct f2fs_super_block *sb,
 
 	return 0;
 }
+
+struct kmem_cache *f2fs_cf_name_slab;
+static int __init f2fs_create_casefold_cache(void)
+{
+	f2fs_cf_name_slab = f2fs_kmem_cache_create("f2fs_casefolded_name",
+							F2FS_NAME_LEN);
+	if (!f2fs_cf_name_slab)
+		return -ENOMEM;
+	return 0;
+}
+
+static void f2fs_destroy_casefold_cache(void)
+{
+	kmem_cache_destroy(f2fs_cf_name_slab);
+}
+#else
+static int __init f2fs_create_casefold_cache(void) { return 0; }
+static void f2fs_destroy_casefold_cache(void) { }
 #endif
 
 static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
@@ -555,7 +575,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 	int ret;
 
 	if (!options)
-		return 0;
+		goto default_check;
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
@@ -1066,12 +1086,16 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			}
 			kfree(name);
 			break;
+		case Opt_compress_cache:
+			set_opt(sbi, COMPRESS_CACHE);
+			break;
 #else
 		case Opt_compress_algorithm:
 		case Opt_compress_log_size:
 		case Opt_compress_extension:
 		case Opt_compress_chksum:
 		case Opt_compress_mode:
+		case Opt_compress_cache:
 			f2fs_info(sbi, "compression options not supported");
 			break;
 #endif
@@ -1090,6 +1114,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			return -EINVAL;
 		}
 	}
+default_check:
 #ifdef CONFIG_QUOTA
 	if (f2fs_check_quota_options(sbi))
 		return -EINVAL;
@@ -1153,7 +1178,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 	}
 
 	if (test_opt(sbi, DISABLE_CHECKPOINT) && f2fs_lfs_mode(sbi)) {
-		f2fs_err(sbi, "LFS not compatible with checkpoint=disable\n");
+		f2fs_err(sbi, "LFS not compatible with checkpoint=disable");
 		return -EINVAL;
 	}
 
@@ -1162,6 +1187,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 	 */
 	if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE)
 		F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
+
+	if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
+		f2fs_err(sbi, "Allow to mount readonly mode only");
+		return -EROFS;
+	}
 	return 0;
 }
 
@@ -1406,6 +1436,8 @@ static void f2fs_put_super(struct super_block *sb)
 
 	f2fs_bug_on(sbi, sbi->fsync_node_num);
 
+	f2fs_destroy_compress_inode(sbi);
+
 	iput(sbi->node_inode);
 	sbi->node_inode = NULL;
 
@@ -1675,6 +1707,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 		seq_printf(seq, ",compress_mode=%s", "fs");
 	else if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER)
 		seq_printf(seq, ",compress_mode=%s", "user");
+
+	if (test_opt(sbi, COMPRESS_CACHE))
+		seq_puts(seq, ",compress_cache");
 }
 #endif
 
@@ -1822,7 +1857,11 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 static void default_options(struct f2fs_sb_info *sbi)
 {
 	/* init some FS parameters */
-	F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE;
+	if (f2fs_sb_has_readonly(sbi))
+		F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE;
+	else
+		F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE;
+
 	F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
 	F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
 	F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
@@ -1869,15 +1908,17 @@ static int f2fs_enable_quotas(struct super_block *sb);
 
 static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 {
+	unsigned int s_flags = sbi->sb->s_flags;
 	struct cp_control cpc;
 	int err = 0;
 	int ret;
 	block_t unusable;
 
-	if (sbi->sb->s_flags & SB_RDONLY) {
+	if (s_flags & SB_RDONLY) {
 		f2fs_err(sbi, "checkpoint=disable on readonly fs");
 		return -EINVAL;
 	}
+	sbi->sb->s_flags |= SB_ACTIVE;
 
 	f2fs_update_time(sbi, DISABLE_TIME);
 
@@ -1895,13 +1936,13 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 	ret = sync_filesystem(sbi->sb);
 	if (ret || err) {
 		err = ret ? ret : err;
-		goto out;
+		goto restore_flag;
 	}
 
 	unusable = f2fs_get_unusable_blocks(sbi);
 	if (f2fs_disable_cp_again(sbi, unusable)) {
 		err = -EAGAIN;
-		goto out;
+		goto restore_flag;
 	}
 
 	down_write(&sbi->gc_lock);
@@ -1917,7 +1958,8 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 
 out_unlock:
 	up_write(&sbi->gc_lock);
-out:
+restore_flag:
+	sbi->sb->s_flags = s_flags;	/* Restore SB_RDONLY status */
 	return err;
 }
 
@@ -1949,6 +1991,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
 	bool no_io_align = !F2FS_IO_ALIGNED(sbi);
 	bool no_atgc = !test_opt(sbi, ATGC);
+	bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
 	bool checkpoint_changed;
 #ifdef CONFIG_QUOTA
 	int i, j;
@@ -2004,6 +2047,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if (f2fs_readonly(sb) && (*flags & SB_RDONLY))
 		goto skip;
 
+	if (f2fs_sb_has_readonly(sbi) && !(*flags & SB_RDONLY)) {
+		err = -EROFS;
+		goto restore_opts;
+	}
+
 #ifdef CONFIG_QUOTA
 	if (!f2fs_readonly(sb) && (*flags & SB_RDONLY)) {
 		err = dquot_suspend(sb, -1);
@@ -2041,6 +2089,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
+	if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) {
+		err = -EINVAL;
+		f2fs_warn(sbi, "switch compress_cache option is not allowed");
+		goto restore_opts;
+	}
+
 	if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) {
 		err = -EINVAL;
 		f2fs_warn(sbi, "disabling checkpoint not compatible with read-only");
@@ -3137,14 +3191,15 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
 	reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
 
-	if (unlikely(fsmeta < F2FS_MIN_META_SEGMENTS ||
+	if (!f2fs_sb_has_readonly(sbi) &&
+			unlikely(fsmeta < F2FS_MIN_META_SEGMENTS ||
 			ovp_segments == 0 || reserved_segments == 0)) {
 		f2fs_err(sbi, "Wrong layout: check mkfs.f2fs version");
 		return 1;
 	}
-
 	user_block_count = le64_to_cpu(ckpt->user_block_count);
-	segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	segment_count_main = le32_to_cpu(raw_super->segment_count_main) +
+			(f2fs_sb_has_readonly(sbi) ? 1 : 0);
 	log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
 	if (!user_block_count || user_block_count >=
 			segment_count_main << log_blocks_per_seg) {
@@ -3175,6 +3230,10 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
 			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
 			return 1;
+
+		if (f2fs_sb_has_readonly(sbi))
+			goto check_data;
+
 		for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) {
 			if (le32_to_cpu(ckpt->cur_node_segno[i]) ==
 				le32_to_cpu(ckpt->cur_node_segno[j])) {
@@ -3185,10 +3244,15 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 			}
 		}
 	}
+check_data:
 	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
 		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
 			le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
 			return 1;
+
+		if (f2fs_sb_has_readonly(sbi))
+			goto skip_cross;
+
 		for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) {
 			if (le32_to_cpu(ckpt->cur_data_segno[i]) ==
 				le32_to_cpu(ckpt->cur_data_segno[j])) {
@@ -3210,7 +3274,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 			}
 		}
 	}
-
+skip_cross:
 	sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
 	nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
 
@@ -3555,7 +3619,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 #ifdef CONFIG_BLK_DEV_ZONED
 		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
 				!f2fs_sb_has_blkzoned(sbi)) {
-			f2fs_err(sbi, "Zoned block device feature not enabled\n");
+			f2fs_err(sbi, "Zoned block device feature not enabled");
 			return -EINVAL;
 		}
 		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
@@ -3940,10 +4004,14 @@ try_onemore:
 		goto free_node_inode;
 	}
 
-	err = f2fs_register_sysfs(sbi);
+	err = f2fs_init_compress_inode(sbi);
 	if (err)
 		goto free_root_inode;
 
+	err = f2fs_register_sysfs(sbi);
+	if (err)
+		goto free_compress_inode;
+
 #ifdef CONFIG_QUOTA
 	/* Enable quota usage during mount */
 	if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) {
@@ -4084,6 +4152,8 @@ free_meta:
 	/* evict some inodes being cached by GC */
 	evict_inodes(sb);
 	f2fs_unregister_sysfs(sbi);
+free_compress_inode:
+	f2fs_destroy_compress_inode(sbi);
 free_root_inode:
 	dput(sb->s_root);
 	sb->s_root = NULL;
@@ -4162,6 +4232,15 @@ static void kill_f2fs_super(struct super_block *sb)
 		f2fs_stop_gc_thread(sbi);
 		f2fs_stop_discard_thread(sbi);
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		/*
+		 * latter evict_inode() can bypass checking and invalidating
+		 * compress inode cache.
+		 */
+		if (test_opt(sbi, COMPRESS_CACHE))
+			truncate_inode_pages_final(COMPRESS_MAPPING(sbi));
+#endif
+
 		if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
 				!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
 			struct cp_control cpc = {
@@ -4261,7 +4340,12 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_init_compress_cache();
 	if (err)
 		goto free_compress_mempool;
+	err = f2fs_create_casefold_cache();
+	if (err)
+		goto free_compress_cache;
 	return 0;
+free_compress_cache:
+	f2fs_destroy_compress_cache();
 free_compress_mempool:
 	f2fs_destroy_compress_mempool();
 free_bioset:
@@ -4297,6 +4381,7 @@ fail:
 
 static void __exit exit_f2fs_fs(void)
 {
+	f2fs_destroy_casefold_cache();
 	f2fs_destroy_compress_cache();
 	f2fs_destroy_compress_mempool();
 	f2fs_destroy_bioset();

fs/f2fs/sysfs.c

@@ -158,6 +158,9 @@ static ssize_t features_show(struct f2fs_attr *a,
 	if (f2fs_sb_has_casefold(sbi))
 		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "casefold");
+	if (f2fs_sb_has_readonly(sbi))
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+				len ? ", " : "", "readonly");
 	if (f2fs_sb_has_compression(sbi))
 		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "compression");
@@ -563,46 +566,49 @@ static void f2fs_sb_release(struct kobject *kobj)
 	complete(&sbi->s_kobj_unregister);
 }
 
-enum feat_id {
+/*
-	FEAT_CRYPTO = 0,
+ * Note that there are three feature list entries:
-	FEAT_BLKZONED,
+ * 1) /sys/fs/f2fs/features
-	FEAT_ATOMIC_WRITE,
+ *   : shows runtime features supported by in-kernel f2fs along with Kconfig.
-	FEAT_EXTRA_ATTR,
+ *     - ref. F2FS_FEATURE_RO_ATTR()
-	FEAT_PROJECT_QUOTA,
+ *
-	FEAT_INODE_CHECKSUM,
+ * 2) /sys/fs/f2fs/$s_id/features <deprecated>
-	FEAT_FLEXIBLE_INLINE_XATTR,
+ *   : shows on-disk features enabled by mkfs.f2fs, used for old kernels. This
-	FEAT_QUOTA_INO,
+ *     won't add new feature anymore, and thus, users should check entries in 3)
-	FEAT_INODE_CRTIME,
+ *     instead of this 2).
-	FEAT_LOST_FOUND,
+ *
-	FEAT_VERITY,
+ * 3) /sys/fs/f2fs/$s_id/feature_list
-	FEAT_SB_CHECKSUM,
+ *   : shows on-disk features enabled by mkfs.f2fs per instance, which follows
-	FEAT_CASEFOLD,
+ *     sysfs entry rule where each entry should expose single value.
-	FEAT_COMPRESSION,
+ *     This list covers old feature list provided by 2) and beyond. Therefore,
-	FEAT_TEST_DUMMY_ENCRYPTION_V2,
+ *     please add new on-disk feature in this list only.
-};
+ *     - ref. F2FS_SB_FEATURE_RO_ATTR()
-
+ */
 static ssize_t f2fs_feature_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
-	switch (a->id) {
+	return sprintf(buf, "supported\n");
-	case FEAT_CRYPTO:
+}
-	case FEAT_BLKZONED:
+
-	case FEAT_ATOMIC_WRITE:
+#define F2FS_FEATURE_RO_ATTR(_name)				\
-	case FEAT_EXTRA_ATTR:
+static struct f2fs_attr f2fs_attr_##_name = {			\
-	case FEAT_PROJECT_QUOTA:
+	.attr = {.name = __stringify(_name), .mode = 0444 },	\
-	case FEAT_INODE_CHECKSUM:
+	.show	= f2fs_feature_show,				\
-	case FEAT_FLEXIBLE_INLINE_XATTR:
+}
-	case FEAT_QUOTA_INO:
+
-	case FEAT_INODE_CRTIME:
+static ssize_t f2fs_sb_feature_show(struct f2fs_attr *a,
-	case FEAT_LOST_FOUND:
+		struct f2fs_sb_info *sbi, char *buf)
-	case FEAT_VERITY:
+{
-	case FEAT_SB_CHECKSUM:
+	if (F2FS_HAS_FEATURE(sbi, a->id))
-	case FEAT_CASEFOLD:
-	case FEAT_COMPRESSION:
-	case FEAT_TEST_DUMMY_ENCRYPTION_V2:
 		return sprintf(buf, "supported\n");
-	}
+	return sprintf(buf, "unsupported\n");
-	return 0;
+}
+
+#define F2FS_SB_FEATURE_RO_ATTR(_name, _feat)			\
+static struct f2fs_attr f2fs_attr_sb_##_name = {		\
+	.attr = {.name = __stringify(_name), .mode = 0444 },	\
+	.show	= f2fs_sb_feature_show,				\
+	.id	= F2FS_FEATURE_##_feat,				\
 }
 
 #define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
@@ -622,13 +628,6 @@ static struct f2fs_attr f2fs_attr_##_name = {			\
 #define F2FS_GENERAL_RO_ATTR(name) \
 static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
 
-#define F2FS_FEATURE_RO_ATTR(_name, _id)			\
-static struct f2fs_attr f2fs_attr_##_name = {			\
-	.attr = {.name = __stringify(_name), .mode = 0444 },	\
-	.show	= f2fs_feature_show,				\
-	.id	= _id,						\
-}
-
 #define F2FS_STAT_ATTR(_struct_type, _struct_name, _name, _elname)	\
 static struct f2fs_attr f2fs_attr_##_name = {			\
 	.attr = {.name = __stringify(_name), .mode = 0444 },	\
@@ -702,31 +701,39 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks);
 #endif
 
 #ifdef CONFIG_FS_ENCRYPTION
-F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
+F2FS_FEATURE_RO_ATTR(encryption);
-F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2, FEAT_TEST_DUMMY_ENCRYPTION_V2);
+F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2);
+#ifdef CONFIG_UNICODE
+F2FS_FEATURE_RO_ATTR(encrypted_casefold);
 #endif
+#endif /* CONFIG_FS_ENCRYPTION */
 #ifdef CONFIG_BLK_DEV_ZONED
-F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED);
+F2FS_FEATURE_RO_ATTR(block_zoned);
 #endif
-F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE);
+F2FS_FEATURE_RO_ATTR(atomic_write);
-F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR);
+F2FS_FEATURE_RO_ATTR(extra_attr);
-F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA);
+F2FS_FEATURE_RO_ATTR(project_quota);
-F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM);
+F2FS_FEATURE_RO_ATTR(inode_checksum);
-F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR);
+F2FS_FEATURE_RO_ATTR(flexible_inline_xattr);
-F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO);
+F2FS_FEATURE_RO_ATTR(quota_ino);
-F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME);
+F2FS_FEATURE_RO_ATTR(inode_crtime);
-F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND);
+F2FS_FEATURE_RO_ATTR(lost_found);
 #ifdef CONFIG_FS_VERITY
-F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY);
+F2FS_FEATURE_RO_ATTR(verity);
 #endif
-F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
+F2FS_FEATURE_RO_ATTR(sb_checksum);
-F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
+#ifdef CONFIG_UNICODE
+F2FS_FEATURE_RO_ATTR(casefold);
+#endif
+F2FS_FEATURE_RO_ATTR(readonly);
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION);
+F2FS_FEATURE_RO_ATTR(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
+F2FS_FEATURE_RO_ATTR(pin_file);
+
 /* For ATGC */
 F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_candidate_ratio, candidate_ratio);
 F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_candidate_count, max_candidate_count);
@@ -813,7 +820,10 @@ static struct attribute *f2fs_feat_attrs[] = {
 #ifdef CONFIG_FS_ENCRYPTION
 	ATTR_LIST(encryption),
 	ATTR_LIST(test_dummy_encryption_v2),
+#ifdef CONFIG_UNICODE
+	ATTR_LIST(encrypted_casefold),
 #endif
+#endif /* CONFIG_FS_ENCRYPTION */
 #ifdef CONFIG_BLK_DEV_ZONED
 	ATTR_LIST(block_zoned),
 #endif
@@ -829,10 +839,14 @@ static struct attribute *f2fs_feat_attrs[] = {
 	ATTR_LIST(verity),
 #endif
 	ATTR_LIST(sb_checksum),
+#ifdef CONFIG_UNICODE
 	ATTR_LIST(casefold),
+#endif
+	ATTR_LIST(readonly),
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	ATTR_LIST(compression),
 #endif
+	ATTR_LIST(pin_file),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs_feat);
@@ -844,6 +858,40 @@ static struct attribute *f2fs_stat_attrs[] = {
 };
 ATTRIBUTE_GROUPS(f2fs_stat);
 
+F2FS_SB_FEATURE_RO_ATTR(encryption, ENCRYPT);
+F2FS_SB_FEATURE_RO_ATTR(block_zoned, BLKZONED);
+F2FS_SB_FEATURE_RO_ATTR(extra_attr, EXTRA_ATTR);
+F2FS_SB_FEATURE_RO_ATTR(project_quota, PRJQUOTA);
+F2FS_SB_FEATURE_RO_ATTR(inode_checksum, INODE_CHKSUM);
+F2FS_SB_FEATURE_RO_ATTR(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR);
+F2FS_SB_FEATURE_RO_ATTR(quota_ino, QUOTA_INO);
+F2FS_SB_FEATURE_RO_ATTR(inode_crtime, INODE_CRTIME);
+F2FS_SB_FEATURE_RO_ATTR(lost_found, LOST_FOUND);
+F2FS_SB_FEATURE_RO_ATTR(verity, VERITY);
+F2FS_SB_FEATURE_RO_ATTR(sb_checksum, SB_CHKSUM);
+F2FS_SB_FEATURE_RO_ATTR(casefold, CASEFOLD);
+F2FS_SB_FEATURE_RO_ATTR(compression, COMPRESSION);
+F2FS_SB_FEATURE_RO_ATTR(readonly, RO);
+
+static struct attribute *f2fs_sb_feat_attrs[] = {
+	ATTR_LIST(sb_encryption),
+	ATTR_LIST(sb_block_zoned),
+	ATTR_LIST(sb_extra_attr),
+	ATTR_LIST(sb_project_quota),
+	ATTR_LIST(sb_inode_checksum),
+	ATTR_LIST(sb_flexible_inline_xattr),
+	ATTR_LIST(sb_quota_ino),
+	ATTR_LIST(sb_inode_crtime),
+	ATTR_LIST(sb_lost_found),
+	ATTR_LIST(sb_verity),
+	ATTR_LIST(sb_sb_checksum),
+	ATTR_LIST(sb_casefold),
+	ATTR_LIST(sb_compression),
+	ATTR_LIST(sb_readonly),
+	NULL,
+};
+ATTRIBUTE_GROUPS(f2fs_sb_feat);
+
 static const struct sysfs_ops f2fs_attr_ops = {
 	.show	= f2fs_attr_show,
 	.store	= f2fs_attr_store,
@@ -910,6 +958,33 @@ static struct kobj_type f2fs_stat_ktype = {
 	.release	= f2fs_stat_kobj_release,
 };
 
+static ssize_t f2fs_sb_feat_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+							s_feature_list_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static void f2fs_feature_list_kobj_release(struct kobject *kobj)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+							s_feature_list_kobj);
+	complete(&sbi->s_feature_list_kobj_unregister);
+}
+
+static const struct sysfs_ops f2fs_feature_list_attr_ops = {
+	.show	= f2fs_sb_feat_attr_show,
+};
+
+static struct kobj_type f2fs_feature_list_ktype = {
+	.default_groups = f2fs_sb_feat_groups,
+	.sysfs_ops	= &f2fs_feature_list_attr_ops,
+	.release	= f2fs_feature_list_kobj_release,
+};
+
 static int __maybe_unused segment_info_seq_show(struct seq_file *seq,
 						void *offset)
 {
@@ -1126,6 +1201,14 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 	if (err)
 		goto put_stat_kobj;
 
+	sbi->s_feature_list_kobj.kset = &f2fs_kset;
+	init_completion(&sbi->s_feature_list_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_feature_list_kobj,
+					&f2fs_feature_list_ktype,
+					&sbi->s_kobj, "feature_list");
+	if (err)
+		goto put_feature_list_kobj;
+
 	if (f2fs_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
 
@@ -1140,6 +1223,9 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 				victim_bits_seq_show, sb);
 	}
 	return 0;
+put_feature_list_kobj:
+	kobject_put(&sbi->s_feature_list_kobj);
+	wait_for_completion(&sbi->s_feature_list_kobj_unregister);
 put_stat_kobj:
 	kobject_put(&sbi->s_stat_kobj);
 	wait_for_completion(&sbi->s_stat_kobj_unregister);
@@ -1162,6 +1248,9 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
 	kobject_del(&sbi->s_stat_kobj);
 	kobject_put(&sbi->s_stat_kobj);
 	wait_for_completion(&sbi->s_stat_kobj_unregister);
+	kobject_del(&sbi->s_feature_list_kobj);
+	kobject_put(&sbi->s_feature_list_kobj);
+	wait_for_completion(&sbi->s_feature_list_kobj_unregister);
 
 	kobject_del(&sbi->s_kobj);
 	kobject_put(&sbi->s_kobj);

include/linux/f2fs_fs.h

@@ -34,6 +34,7 @@
 #define F2FS_ROOT_INO(sbi)	((sbi)->root_ino_num)
 #define F2FS_NODE_INO(sbi)	((sbi)->node_ino_num)
 #define F2FS_META_INO(sbi)	((sbi)->meta_ino_num)
+#define F2FS_COMPRESS_INO(sbi)	(NM_I(sbi)->max_nid)
 
 #define F2FS_MAX_QUOTAS		3