Merge tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've made more work into per-file compression support.

  For example, F2FS_IOC_GET | SET_COMPRESS_OPTION provides a way to
  change the algorithm or cluster size per file. F2FS_IOC_COMPRESS |
  DECOMPRESS_FILE provides a way to compress and decompress the existing
  normal files manually.

  There is also a new mount option, compress_mode=fs|user, which can
  control who compresses the data.

  Chao also added a checksum feature with a mount option so that
  we are able to detect any corrupted cluster.

  In addition, Daniel contributed casefolding with encryption patch,
  which will be used for Android devices.

  Summary:

  Enhancements:
   - add ioctls and mount option to manage per-file compression feature
   - support casefolding with encryption
   - support checksum for compressed cluster
   - avoid IO starvation by replacing mutex with rwsem
   - add sysfs, max_io_bytes, to control max bio size

  Bug fixes:
   - fix use-after-free issue when compression and fsverity are enabled
   - fix consistency corruption during fault injection test
   - fix data offset for lseek
   - get rid of buffer_head which has 32bits limit in fiemap
   - fix some bugs in multi-partitions support
   - fix nat entry count calculation in shrinker
   - fix some stat information

  And, we've refactored some logics and fix minor bugs as well"

* tag 'f2fs-for-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (36 commits)
  f2fs: compress: fix compression chksum
  f2fs: fix shift-out-of-bounds in sanity_check_raw_super()
  f2fs: fix race of pending_pages in decompression
  f2fs: fix to account inline xattr correctly during recovery
  f2fs: inline: fix wrong inline inode stat
  f2fs: inline: correct comment in f2fs_recover_inline_data
  f2fs: don't check PAGE_SIZE again in sanity_check_raw_super()
  f2fs: convert to F2FS_*_INO macro
  f2fs: introduce max_io_bytes, a sysfs entry, to limit bio size
  f2fs: don't allow any writes on readonly mount
  f2fs: avoid race condition for shrinker count
  f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE
  f2fs: add compress_mode mount option
  f2fs: Remove unnecessary unlikely()
  f2fs: init dirty_secmap incorrectly
  f2fs: remove buffer_head which has 32bits limit
  f2fs: fix wrong block count instead of bytes
  f2fs: use new conversion functions between blks and bytes
  f2fs: rename logical_to_blk and blk_to_logical
  f2fs: fix kbytes written stat for multi-device case
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -370,3 +370,10 @@ Date:		April 2020
 Contact:	"Daeho Jeong" <daehojeong@google.com>
 Description:	Give a way to change iostat_period time. 3secs by default.
 		The new iostat trace gives stats gap given the period.
+What:		/sys/fs/f2fs/<disk>/max_io_bytes
+Date:		December 2020
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	This gives a control to limit the bio size in f2fs.
+		Default is zero, which will follow underlying block layer limit,
+		whereas, if it has a certain bytes value, f2fs won't submit a
+		bio larger than that size.

Documentation/filesystems/f2fs.rst

@@ -260,6 +260,14 @@ compress_extension=%s	 Support adding specified extension, so that f2fs can enab
 			 For other files, we can still enable compression via ioctl.
 			 Note that, there is one reserved special extension '*', it
 			 can be set to enable compression for all files.
+compress_chksum		 Support verifying chksum of raw data in compressed cluster.
+compress_mode=%s	 Control file compression mode. This supports "fs" and "user"
+			 modes. In "fs" mode (default), f2fs does automatic compression
+			 on the compression enabled files. In "user" mode, f2fs disables
+			 the automaic compression and gives the user discretion of
+			 choosing the target file and the timing. The user can do manual
+			 compression/decompression on the compression enabled files using
+			 ioctls.
 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
@@ -810,6 +818,34 @@ Compress metadata layout::
 	| data length | data chksum | reserved |      compressed data       |
 	+-------------+-------------+----------+----------------------------+
 
+Compression mode
+--------------------------
+
+f2fs supports "fs" and "user" compression modes with "compression_mode" mount option.
+With this option, f2fs provides a choice to select the way how to compress the
+compression enabled files (refer to "Compression implementation" section for how to
+enable compression on a regular inode).
+
+1) compress_mode=fs
+This is the default option. f2fs does automatic compression in the writeback of the
+compression enabled files.
+
+2) compress_mode=user
+This disables the automaic compression and gives the user discretion of choosing the
+target file and the timing. The user can do manual compression/decompression on the
+compression enabled files using F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE
+ioctls like the below.
+
+To decompress a file,
+
+fd = open(filename, O_WRONLY, 0);
+ret = ioctl(fd, F2FS_IOC_DECOMPRESS_FILE);
+
+To compress a file,
+
+fd = open(filename, O_WRONLY, 0);
+ret = ioctl(fd, F2FS_IOC_COMPRESS_FILE);
+
 NVMe Zoned Namespace devices
 ----------------------------
 

MAINTAINERS

@@ -6746,6 +6746,7 @@ F:	Documentation/filesystems/f2fs.rst
 F:	fs/f2fs/
 F:	include/linux/f2fs_fs.h
 F:	include/trace/events/f2fs.h
+F:	include/uapi/linux/f2fs.h
 
 F71805F HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>

fs/crypto/fname.c

@@ -574,7 +574,3 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return valid;
 }
 EXPORT_SYMBOL_GPL(fscrypt_d_revalidate);
-
-const struct dentry_operations fscrypt_d_ops = {
-	.d_revalidate = fscrypt_d_revalidate,
-};

fs/crypto/fscrypt_private.h

@@ -297,7 +297,6 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
 				  u32 orig_len, u32 max_len,
 				  u32 *encrypted_len_ret);
-extern const struct dentry_operations fscrypt_d_ops;
 
 /* hkdf.c */
 

fs/crypto/hooks.c

@@ -108,7 +108,6 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags |= DCACHE_NOKEY_NAME;
 		spin_unlock(&dentry->d_lock);
-		d_set_d_op(dentry, &fscrypt_d_ops);
 	}
 	return err;
 }

fs/ext4/dir.c

@@ -657,10 +657,3 @@ const struct file_operations ext4_dir_operations = {
 	.fsync		= ext4_sync_file,
 	.release	= ext4_release_dir,
 };
-
-#ifdef CONFIG_UNICODE
-const struct dentry_operations ext4_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
-};
-#endif

fs/ext4/ext4.h

@@ -3381,10 +3381,6 @@ static inline void ext4_unlock_group(struct super_block *sb,
 /* dir.c */
 extern const struct file_operations ext4_dir_operations;
 
-#ifdef CONFIG_UNICODE
-extern const struct dentry_operations ext4_dentry_ops;
-#endif
-
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;

fs/ext4/namei.c

@@ -1608,6 +1608,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
 	struct buffer_head *bh;
 
 	err = ext4_fname_prepare_lookup(dir, dentry, &fname);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return NULL;
 	if (err)

fs/ext4/super.c

@@ -4963,11 +4963,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount4;
 	}
 
-#ifdef CONFIG_UNICODE
-	if (sb->s_encoding)
-		sb->s_d_op = &ext4_dentry_ops;
-#endif
-
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");

fs/f2fs/acl.c

@@ -384,7 +384,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 							struct page *dpage)
 {
 	struct posix_acl *default_acl = NULL, *acl = NULL;
-	int error = 0;
+	int error;
 
 	error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage);
 	if (error)

fs/f2fs/checkpoint.c

@@ -37,7 +37,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	struct page *page = NULL;
+	struct page *page;
 repeat:
 	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
@@ -348,13 +348,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 		goto skip_write;
 
 	/* if locked failed, cp will flush dirty pages instead */
-	if (!mutex_trylock(&sbi->cp_mutex))
+	if (!down_write_trylock(&sbi->cp_global_sem))
 		goto skip_write;
 
 	trace_f2fs_writepages(mapping->host, wbc, META);
 	diff = nr_pages_to_write(sbi, META, wbc);
 	written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
-	mutex_unlock(&sbi->cp_mutex);
+	up_write(&sbi->cp_global_sem);
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
 	return 0;
 
@@ -1385,6 +1385,26 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi,
 	f2fs_submit_merged_write(sbi, META_FLUSH);
 }
 
+static inline u64 get_sectors_written(struct block_device *bdev)
+{
+	return (u64)part_stat_read(bdev, sectors[STAT_WRITE]);
+}
+
+u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_is_multi_device(sbi)) {
+		u64 sectors = 0;
+		int i;
+
+		for (i = 0; i < sbi->s_ndevs; i++)
+			sectors += get_sectors_written(FDEV(i).bdev);
+
+		return sectors;
+	}
+
+	return get_sectors_written(sbi->sb->s_bdev);
+}
+
 static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -1488,8 +1508,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	start_blk += data_sum_blocks;
 
 	/* Record write statistics in the hot node summary */
-	kbytes_written = sbi->kbytes_written + BD_PART_WRITTEN(sbi);
-
+	kbytes_written = sbi->kbytes_written;
+	kbytes_written += (f2fs_get_sectors_written(sbi) -
+				sbi->sectors_written_start) >> 1;
 	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
 
 	if (__remain_node_summaries(cpc->reason)) {
@@ -1569,7 +1590,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		f2fs_warn(sbi, "Start checkpoint disabled!");
 	}
 	if (cpc->reason != CP_RESIZE)
-		mutex_lock(&sbi->cp_mutex);
+		down_write(&sbi->cp_global_sem);
 
 	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
 		((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
@@ -1597,7 +1618,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			goto out;
 		}
 
-		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+		if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 &&
 				SIT_I(sbi)->dirty_sentries == 0 &&
 				prefree_segments(sbi) == 0) {
 			f2fs_flush_sit_entries(sbi, cpc);
@@ -1644,7 +1665,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 out:
 	if (cpc->reason != CP_RESIZE)
-		mutex_unlock(&sbi->cp_mutex);
+		up_write(&sbi->cp_global_sem);
 	return err;
 }
 

fs/f2fs/compress.c

@@ -602,6 +602,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 				f2fs_cops[fi->i_compress_algorithm];
 	unsigned int max_len, new_nr_cpages;
 	struct page **new_cpages;
+	u32 chksum = 0;
 	int i, ret;
 
 	trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
@@ -655,6 +656,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
 
+	if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)
+		chksum = f2fs_crc32(F2FS_I_SB(cc->inode),
+					cc->cbuf->cdata, cc->clen);
+	cc->cbuf->chksum = cpu_to_le32(chksum);
+
 	for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
 		cc->cbuf->reserved[i] = cpu_to_le32(0);
 
@@ -790,6 +796,22 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 
 	ret = cops->decompress_pages(dic);
 
+	if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) {
+		u32 provided = le32_to_cpu(dic->cbuf->chksum);
+		u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen);
+
+		if (provided != calculated) {
+			if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) {
+				set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT);
+				printk_ratelimited(
+					"%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x",
+					KERN_INFO, sbi->sb->s_id, dic->inode->i_ino,
+					provided, calculated);
+			}
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		}
+	}
+
 out_vunmap_cbuf:
 	vm_unmap_ram(dic->cbuf, dic->nr_cpages);
 out_vunmap_rbuf:
@@ -798,8 +820,6 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 	if (cops->destroy_decompress_ctx)
 		cops->destroy_decompress_ctx(dic);
 out_free_dic:
-	if (verity)
-		atomic_set(&dic->pending_pages, dic->nr_cpages);
 	if (!verity)
 		f2fs_decompress_end_io(dic->rpages, dic->cluster_size,
 								ret, false);
@@ -921,7 +941,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
 
 static bool cluster_may_compress(struct compress_ctx *cc)
 {
-	if (!f2fs_compressed_file(cc->inode))
+	if (!f2fs_need_compress_data(cc->inode))
 		return false;
 	if (f2fs_is_atomic_file(cc->inode))
 		return false;

fs/f2fs/debug.c

@@ -145,8 +145,8 @@ 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;
-	si->nats = NM_I(sbi)->nat_cnt;
-	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT];
+	si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT];
 	si->sits = MAIN_SEGS(sbi);
 	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
@@ -278,9 +278,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
 				NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
 				sizeof(struct free_nid);
-	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
-	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
-					sizeof(struct nat_entry_set);
+	si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] *
+				sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] *
+				sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
 	for (i = 0; i < MAX_INO_ENTRY; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);

fs/f2fs/dir.c

@@ -5,6 +5,7 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com/
  */
+#include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/sched/signal.h>
@@ -206,30 +207,55 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 /*
  * Test whether a case-insensitive directory entry matches the filename
  * being searched for.
+ *
+ * Returns 1 for a match, 0 for no match, and -errno on an error.
  */
-static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
+static int f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
 	const struct super_block *sb = dir->i_sb;
 	const struct unicode_map *um = sb->s_encoding;
+	struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
+	if (IS_ENCRYPTED(dir)) {
+		const struct fscrypt_str encrypted_name =
+			FSTR_INIT((u8 *)de_name, de_name_len);
+
+		if (WARN_ON_ONCE(!fscrypt_has_encryption_key(dir)))
+			return -EINVAL;
+
+		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
+		if (!decrypted_name.name)
+			return -ENOMEM;
+		res = fscrypt_fname_disk_to_usr(dir, 0, 0, &encrypted_name,
+						&decrypted_name);
+		if (res < 0)
+			goto out;
+		entry.name = decrypted_name.name;
+		entry.len = decrypted_name.len;
+	}
+
 	res = utf8_strncasecmp_folded(um, name, &entry);
-	if (res < 0) {
-		/*
-		 * In strict mode, ignore invalid names.  In non-strict mode,
-		 * fall back to treating them as opaque byte sequences.
-		 */
-		if (sb_has_strict_encoding(sb) || name->len != entry.len)
-			return false;
-		return !memcmp(name->name, entry.name, name->len);
+	/*
+	 * In strict mode, ignore invalid names.  In non-strict mode,
+	 * fall back to treating them as opaque byte sequences.
+	 */
+	if (res < 0 && !sb_has_strict_encoding(sb)) {
+		res = name->len == entry.len &&
+				memcmp(name->name, entry.name, name->len) == 0;
+	} else {
+		/* utf8_strncasecmp_folded returns 0 on match */
+		res = (res == 0);
 	}
-	return res == 0;
+out:
+	kfree(decrypted_name.name);
+	return res;
 }
 #endif /* CONFIG_UNICODE */
 
-static inline bool f2fs_match_name(const struct inode *dir,
+static inline int f2fs_match_name(const struct inode *dir,
 				   const struct f2fs_filename *fname,
 				   const u8 *de_name, u32 de_name_len)
 {
@@ -256,6 +282,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
+	int res = 0;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -273,10 +300,15 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
 			continue;
 		}
 
-		if (de->hash_code == fname->hash &&
-		    f2fs_match_name(d->inode, fname, d->filename[bit_pos],
-				    le16_to_cpu(de->name_len)))
-			goto found;
+		if (de->hash_code == fname->hash) {
+			res = f2fs_match_name(d->inode, fname,
+					      d->filename[bit_pos],
+					      le16_to_cpu(de->name_len));
+			if (res < 0)
+				return ERR_PTR(res);
+			if (res)
+				goto found;
+		}
 
 		if (max_slots && max_len > *max_slots)
 			*max_slots = max_len;
@@ -326,7 +358,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		}
 
 		de = find_in_block(dir, dentry_page, fname, &max_slots);
-		if (de) {
+		if (IS_ERR(de)) {
+			*res_page = ERR_CAST(de);
+			de = NULL;
+			break;
+		} else if (de) {
 			*res_page = dentry_page;
 			break;
 		}
@@ -448,17 +484,39 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_put_page(page, 1);
 }
 
-static void init_dent_inode(const struct f2fs_filename *fname,
+static void init_dent_inode(struct inode *dir, struct inode *inode,
+			    const struct f2fs_filename *fname,
 			    struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
+	if (!fname) /* tmpfile case? */
+		return;
+
 	f2fs_wait_on_page_writeback(ipage, NODE, true, true);
 
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
 	ri->i_namelen = cpu_to_le32(fname->disk_name.len);
 	memcpy(ri->i_name, fname->disk_name.name, fname->disk_name.len);
+	if (IS_ENCRYPTED(dir)) {
+		file_set_enc_name(inode);
+		/*
+		 * Roll-forward recovery doesn't have encryption keys available,
+		 * so it can't compute the dirhash for encrypted+casefolded
+		 * filenames.  Append it to i_name if possible.  Else, disable
+		 * roll-forward recovery of the dentry (i.e., make fsync'ing the
+		 * file force a checkpoint) by setting LOST_PINO.
+		 */
+		if (IS_CASEFOLDED(dir)) {
+			if (fname->disk_name.len + sizeof(f2fs_hash_t) <=
+			    F2FS_NAME_LEN)
+				put_unaligned(fname->hash, (f2fs_hash_t *)
+					&ri->i_name[fname->disk_name.len]);
+			else
+				file_lost_pino(inode);
+		}
+	}
 	set_page_dirty(ipage);
 }
 
@@ -541,11 +599,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
 			return page;
 	}
 
-	if (fname) {
-		init_dent_inode(fname, page);
-		if (IS_ENCRYPTED(dir))
-			file_set_enc_name(inode);
-	}
+	init_dent_inode(dir, inode, fname, page);
 
 	/*
 	 * This file should be checkpointed during fsync.
@@ -1091,10 +1145,3 @@ const struct file_operations f2fs_dir_operations = {
 	.compat_ioctl   = f2fs_compat_ioctl,
 #endif
 };
-
-#ifdef CONFIG_UNICODE
-const struct dentry_operations f2fs_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
-};
-#endif

fs/f2fs/gc.c

@@ -1986,7 +1986,7 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
 
 	freeze_super(sbi->sb);
 	down_write(&sbi->gc_lock);
-	mutex_lock(&sbi->cp_mutex);
+	down_write(&sbi->cp_global_sem);
 
 	spin_lock(&sbi->stat_lock);
 	if (shrunk_blocks + valid_user_blocks(sbi) +
@@ -2031,7 +2031,7 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
 		spin_unlock(&sbi->stat_lock);
 	}
 out_err:
-	mutex_unlock(&sbi->cp_mutex);
+	up_write(&sbi->cp_global_sem);
 	up_write(&sbi->gc_lock);
 	thaw_super(sbi->sb);
 	clear_sbi_flag(sbi, SBI_IS_RESIZEFS);

fs/f2fs/hash.c

@@ -111,7 +111,9 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 		 * If the casefolded name is provided, hash it instead of the
 		 * on-disk name.  If the casefolded name is *not* provided, that
 		 * should only be because the name wasn't valid Unicode, so fall
-		 * back to treating the name as an opaque byte sequence.
+		 * back to treating the name as an opaque byte sequence.  Note
+		 * that to handle encrypted directories, the fallback must use
+		 * usr_fname (plaintext) rather than disk_name (ciphertext).
 		 */
 		WARN_ON_ONCE(!fname->usr_fname->name);
 		if (fname->cf_name.name) {
@@ -121,6 +123,13 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 			name = fname->usr_fname->name;
 			len = fname->usr_fname->len;
 		}
+		if (IS_ENCRYPTED(dir)) {
+			struct qstr tmp = QSTR_INIT(name, len);
+
+			fname->hash =
+				cpu_to_le32(fscrypt_fname_siphash(dir, &tmp));
+			return;
+		}
 	}
 #endif
 	fname->hash = cpu_to_le32(TEA_hash_name(name, len));

fs/f2fs/inline.c

@@ -188,7 +188,8 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	struct page *ipage, *page;
 	int err = 0;
 
-	if (!f2fs_has_inline_data(inode))
+	if (!f2fs_has_inline_data(inode) ||
+			f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
 		return 0;
 
 	page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
@@ -266,7 +267,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
 	 * [prev.] [next] of inline_data flag
 	 *    o       o  -> recover inline_data
 	 *    o       x  -> remove inline_data, and then recover data blocks
-	 *    x       o  -> remove inline_data, and then recover inline_data
+	 *    x       o  -> remove data blocks, and then recover inline_data
 	 *    x       x  -> recover data blocks
 	 */
 	if (IS_INODE(npage))
@@ -298,6 +299,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
 		if (IS_ERR(ipage))
 			return PTR_ERR(ipage);
 		f2fs_truncate_inline_inode(inode, ipage, 0);
+		stat_dec_inline_inode(inode);
 		clear_inode_flag(inode, FI_INLINE_DATA);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
@@ -306,6 +308,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
 		ret = f2fs_truncate_blocks(inode, 0, false);
 		if (ret)
 			return ret;
+		stat_inc_inline_inode(inode);
 		goto process_inline;
 	}
 	return 0;
@@ -332,6 +335,10 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
 	make_dentry_ptr_inline(dir, &d, inline_dentry);
 	de = f2fs_find_target_dentry(&d, fname, NULL);
 	unlock_page(ipage);
+	if (IS_ERR(de)) {
+		*res_page = ERR_CAST(de);
+		de = NULL;
+	}
 	if (de)
 		*res_page = ipage;
 	else

fs/f2fs/inode.c

@@ -456,6 +456,7 @@ static int do_read_inode(struct inode *inode)
 					le64_to_cpu(ri->i_compr_blocks));
 			fi->i_compress_algorithm = ri->i_compress_algorithm;
 			fi->i_log_cluster_size = ri->i_log_cluster_size;
+			fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag);
 			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
 			set_inode_flag(inode, FI_COMPRESSED_FILE);
 		}
@@ -634,6 +635,8 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 					&F2FS_I(inode)->i_compr_blocks));
 			ri->i_compress_algorithm =
 				F2FS_I(inode)->i_compress_algorithm;
+			ri->i_compress_flag =
+				cpu_to_le16(F2FS_I(inode)->i_compress_flag);
 			ri->i_log_cluster_size =
 				F2FS_I(inode)->i_log_cluster_size;
 		}

fs/f2fs/namei.c

@@ -497,6 +497,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = f2fs_prepare_lookup(dir, dentry, &fname);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		goto out_splice;
 	if (err)

fs/f2fs/node.c

@@ -62,8 +62,8 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct free_nid)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == NAT_ENTRIES) {
-		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
-							PAGE_SHIFT;
+		mem_size = (nm_i->nat_cnt[TOTAL_NAT] *
+				sizeof(struct nat_entry)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 		if (excess_cached_nats(sbi))
 			res = false;
@@ -109,7 +109,7 @@ static void clear_node_page_dirty(struct page *page)
 
 static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	return f2fs_get_meta_page(sbi, current_nat_addr(sbi, nid));
+	return f2fs_get_meta_page_retry(sbi, current_nat_addr(sbi, nid));
 }
 
 static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
@@ -177,7 +177,8 @@ static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
 	list_add_tail(&ne->list, &nm_i->nat_entries);
 	spin_unlock(&nm_i->nat_list_lock);
 
-	nm_i->nat_cnt++;
+	nm_i->nat_cnt[TOTAL_NAT]++;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]++;
 	return ne;
 }
 
@@ -207,7 +208,8 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
 static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
 {
 	radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
-	nm_i->nat_cnt--;
+	nm_i->nat_cnt[TOTAL_NAT]--;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]--;
 	__free_nat_entry(e);
 }
 
@@ -253,7 +255,8 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 	if (get_nat_flag(ne, IS_DIRTY))
 		goto refresh_list;
 
-	nm_i->dirty_nat_cnt++;
+	nm_i->nat_cnt[DIRTY_NAT]++;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]--;
 	set_nat_flag(ne, IS_DIRTY, true);
 refresh_list:
 	spin_lock(&nm_i->nat_list_lock);
@@ -273,7 +276,8 @@ static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 
 	set_nat_flag(ne, IS_DIRTY, false);
 	set->entry_cnt--;
-	nm_i->dirty_nat_cnt--;
+	nm_i->nat_cnt[DIRTY_NAT]--;
+	nm_i->nat_cnt[RECLAIMABLE_NAT]++;
 }
 
 static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -2590,9 +2594,15 @@ int f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
 
 	ri = F2FS_INODE(page);
 	if (ri->i_inline & F2FS_INLINE_XATTR) {
-		set_inode_flag(inode, FI_INLINE_XATTR);
+		if (!f2fs_has_inline_xattr(inode)) {
+			set_inode_flag(inode, FI_INLINE_XATTR);
+			stat_inc_inline_xattr(inode);
+		}
 	} else {
-		clear_inode_flag(inode, FI_INLINE_XATTR);
+		if (f2fs_has_inline_xattr(inode)) {
+			stat_dec_inline_xattr(inode);
+			clear_inode_flag(inode, FI_INLINE_XATTR);
+		}
 		goto update_inode;
 	}
 
@@ -2944,14 +2954,17 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	LIST_HEAD(sets);
 	int err = 0;
 
-	/* during unmount, let's flush nat_bits before checking dirty_nat_cnt */
+	/*
+	 * during unmount, let's flush nat_bits before checking
+	 * nat_cnt[DIRTY_NAT].
+	 */
 	if (enabled_nat_bits(sbi, cpc)) {
 		down_write(&nm_i->nat_tree_lock);
 		remove_nats_in_journal(sbi);
 		up_write(&nm_i->nat_tree_lock);
 	}
 
-	if (!nm_i->dirty_nat_cnt)
+	if (!nm_i->nat_cnt[DIRTY_NAT])
 		return 0;
 
 	down_write(&nm_i->nat_tree_lock);
@@ -2962,7 +2975,8 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * into nat entry set.
 	 */
 	if (enabled_nat_bits(sbi, cpc) ||
-		!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+		!__has_cursum_space(journal,
+			nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
@@ -3086,7 +3100,6 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 						F2FS_RESERVED_NODE_NUM;
 	nm_i->nid_cnt[FREE_NID] = 0;
 	nm_i->nid_cnt[PREALLOC_NID] = 0;
-	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
 	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
@@ -3220,7 +3233,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 			__del_from_nat_cache(nm_i, natvec[idx]);
 		}
 	}
-	f2fs_bug_on(sbi, nm_i->nat_cnt);
+	f2fs_bug_on(sbi, nm_i->nat_cnt[TOTAL_NAT]);
 
 	/* destroy nat set cache */
 	nid = 0;

fs/f2fs/node.h

@@ -126,13 +126,13 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
 
 static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
 {
-	return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+	return NM_I(sbi)->nat_cnt[DIRTY_NAT] >= NM_I(sbi)->max_nid *
 					NM_I(sbi)->dirty_nats_ratio / 100;
 }
 
 static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
 {
-	return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+	return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD;
 }
 
 static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)

fs/f2fs/recovery.c

@@ -5,6 +5,7 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com/
  */
+#include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include "f2fs.h"
@@ -128,7 +129,16 @@ static int init_recovered_filename(const struct inode *dir,
 	}
 
 	/* Compute the hash of the filename */
-	if (IS_CASEFOLDED(dir)) {
+	if (IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)) {
+		/*
+		 * In this case the hash isn't computable without the key, so it
+		 * was saved on-disk.
+		 */
+		if (fname->disk_name.len + sizeof(f2fs_hash_t) > F2FS_NAME_LEN)
+			return -EINVAL;
+		fname->hash = get_unaligned((f2fs_hash_t *)
+				&raw_inode->i_name[fname->disk_name.len]);
+	} else if (IS_CASEFOLDED(dir)) {
 		err = f2fs_init_casefolded_name(dir, fname);
 		if (err)
 			return err;
@@ -789,7 +799,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	INIT_LIST_HEAD(&dir_list);
 
 	/* prevent checkpoint */
-	mutex_lock(&sbi->cp_mutex);
+	down_write(&sbi->cp_global_sem);
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list, check_only);
@@ -840,7 +850,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	if (!err)
 		clear_sbi_flag(sbi, SBI_POR_DOING);
 
-	mutex_unlock(&sbi->cp_mutex);
+	up_write(&sbi->cp_global_sem);
 
 	/* let's drop all the directory inodes for clean checkpoint */
 	destroy_fsync_dnodes(&dir_list, err);

fs/f2fs/segment.c

@@ -529,31 +529,38 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 	else
 		f2fs_build_free_nids(sbi, false, false);
 
-	if (!is_idle(sbi, REQ_TIME) &&
-		(!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi)))
+	if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) ||
+		excess_prefree_segs(sbi))
+		goto do_sync;
+
+	/* there is background inflight IO or foreground operation recently */
+	if (is_inflight_io(sbi, REQ_TIME) ||
+		(!f2fs_time_over(sbi, REQ_TIME) && rwsem_is_locked(&sbi->cp_rwsem)))
 		return;
 
+	/* exceed periodical checkpoint timeout threshold */
+	if (f2fs_time_over(sbi, CP_TIME))
+		goto do_sync;
+
 	/* checkpoint is the only way to shrink partial cached entries */
-	if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
-			!f2fs_available_free_memory(sbi, INO_ENTRIES) ||
-			excess_prefree_segs(sbi) ||
-			excess_dirty_nats(sbi) ||
-			excess_dirty_nodes(sbi) ||
-			f2fs_time_over(sbi, CP_TIME)) {
-		if (test_opt(sbi, DATA_FLUSH) && from_bg) {
-			struct blk_plug plug;
-
-			mutex_lock(&sbi->flush_lock);
-
-			blk_start_plug(&plug);
-			f2fs_sync_dirty_inodes(sbi, FILE_INODE);
-			blk_finish_plug(&plug);
+	if (f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
+		f2fs_available_free_memory(sbi, INO_ENTRIES))
+		return;
 
-			mutex_unlock(&sbi->flush_lock);
-		}
-		f2fs_sync_fs(sbi->sb, true);
-		stat_inc_bg_cp_count(sbi->stat_info);
+do_sync:
+	if (test_opt(sbi, DATA_FLUSH) && from_bg) {
+		struct blk_plug plug;
+
+		mutex_lock(&sbi->flush_lock);
+
+		blk_start_plug(&plug);
+		f2fs_sync_dirty_inodes(sbi, FILE_INODE);
+		blk_finish_plug(&plug);
+
+		mutex_unlock(&sbi->flush_lock);
 	}
+	f2fs_sync_fs(sbi->sb, true);
+	stat_inc_bg_cp_count(sbi->stat_info);
 }
 
 static int __submit_flush_wait(struct f2fs_sb_info *sbi,
@@ -3254,7 +3261,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 			else
 				return CURSEG_COLD_DATA;
 		}
-		if (file_is_cold(inode) || f2fs_compressed_file(inode))
+		if (file_is_cold(inode) || f2fs_need_compress_data(inode))
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -4544,7 +4551,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 		return;
 
 	mutex_lock(&dirty_i->seglist_lock);
-	for (segno = 0; segno < MAIN_SECS(sbi); segno += blks_per_sec) {
+	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
 		valid_blocks = get_valid_blocks(sbi, segno, true);
 		secno = GET_SEC_FROM_SEG(sbi, segno);
 

fs/f2fs/shrinker.c

@@ -18,9 +18,7 @@ static unsigned int shrinker_run_no;
 
 static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 {
-	long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
-
-	return count > 0 ? count : 0;
+	return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT];
 }
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)

fs/f2fs/super.c

@@ -146,6 +146,8 @@ enum {
 	Opt_compress_algorithm,
 	Opt_compress_log_size,
 	Opt_compress_extension,
+	Opt_compress_chksum,
+	Opt_compress_mode,
 	Opt_atgc,
 	Opt_err,
 };
@@ -214,6 +216,8 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_algorithm, "compress_algorithm=%s"},
 	{Opt_compress_log_size, "compress_log_size=%u"},
 	{Opt_compress_extension, "compress_extension=%s"},
+	{Opt_compress_chksum, "compress_chksum"},
+	{Opt_compress_mode, "compress_mode=%s"},
 	{Opt_atgc, "atgc"},
 	{Opt_err, NULL},
 };
@@ -934,10 +938,29 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			F2FS_OPTION(sbi).compress_ext_cnt++;
 			kfree(name);
 			break;
+		case Opt_compress_chksum:
+			F2FS_OPTION(sbi).compress_chksum = true;
+			break;
+		case Opt_compress_mode:
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+			if (!strcmp(name, "fs")) {
+				F2FS_OPTION(sbi).compress_mode = COMPR_MODE_FS;
+			} else if (!strcmp(name, "user")) {
+				F2FS_OPTION(sbi).compress_mode = COMPR_MODE_USER;
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
 #else
 		case Opt_compress_algorithm:
 		case Opt_compress_log_size:
 		case Opt_compress_extension:
+		case Opt_compress_chksum:
+		case Opt_compress_mode:
 			f2fs_info(sbi, "compression options not supported");
 			break;
 #endif
@@ -1523,6 +1546,14 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 		seq_printf(seq, ",compress_extension=%s",
 			F2FS_OPTION(sbi).extensions[i]);
 	}
+
+	if (F2FS_OPTION(sbi).compress_chksum)
+		seq_puts(seq, ",compress_chksum");
+
+	if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_FS)
+		seq_printf(seq, ",compress_mode=%s", "fs");
+	else if (F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER)
+		seq_printf(seq, ",compress_mode=%s", "user");
 }
 
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
@@ -1672,6 +1703,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4;
 	F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE;
 	F2FS_OPTION(sbi).compress_ext_cnt = 0;
+	F2FS_OPTION(sbi).compress_mode = COMPR_MODE_FS;
 	F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
 
 	sbi->sb->s_flags &= ~SB_INLINECRYPT;
@@ -1904,7 +1936,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 
 	if (*flags & SB_RDONLY ||
 		F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) {
-		writeback_inodes_sb(sb, WB_REASON_SYNC);
 		sync_inodes_sb(sb);
 
 		set_sbi_flag(sbi, SBI_IS_DIRTY);
@@ -2744,7 +2775,6 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	block_t total_sections, blocks_per_seg;
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
-	unsigned int blocksize;
 	size_t crc_offset = 0;
 	__u32 crc = 0;
 
@@ -2770,18 +2800,11 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		}
 	}
 
-	/* Currently, support only 4KB page cache size */
-	if (F2FS_BLKSIZE != PAGE_SIZE) {
-		f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB",
-			  PAGE_SIZE);
-		return -EFSCORRUPTED;
-	}
-
 	/* Currently, support only 4KB block size */
-	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
-	if (blocksize != F2FS_BLKSIZE) {
-		f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB",
-			  blocksize);
+	if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) {
+		f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u",
+			  le32_to_cpu(raw_super->log_blocksize),
+			  F2FS_BLKSIZE_BITS);
 		return -EFSCORRUPTED;
 	}
 
@@ -3071,9 +3094,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->total_node_count =
 		(le32_to_cpu(raw_super->segment_count_nat) / 2)
 			* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
-	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
-	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
-	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
+	F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino);
+	F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino);
+	F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino);
 	sbi->cur_victim_sec = NULL_SECNO;
 	sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
 	sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
@@ -3399,12 +3422,6 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
 
-		if (f2fs_sb_has_encrypt(sbi)) {
-			f2fs_err(sbi,
-				"Can't mount with encoding and encryption");
-			return -EINVAL;
-		}
-
 		if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info,
 					  &encoding_flags)) {
 			f2fs_err(sbi,
@@ -3427,7 +3444,6 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 
 		sbi->sb->s_encoding = encoding;
 		sbi->sb->s_encoding_flags = encoding_flags;
-		sbi->sb->s_d_op = &f2fs_dentry_ops;
 	}
 #else
 	if (f2fs_sb_has_casefold(sbi)) {
@@ -3559,7 +3575,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->valid_super_block = valid_super_block;
 	init_rwsem(&sbi->gc_lock);
 	mutex_init(&sbi->writepages);
-	mutex_init(&sbi->cp_mutex);
+	init_rwsem(&sbi->cp_global_sem);
 	init_rwsem(&sbi->node_write);
 	init_rwsem(&sbi->node_change);
 
@@ -3700,8 +3716,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* For write statistics */
-	sbi->sectors_written_start =
-		(u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
+	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
@@ -3916,6 +3931,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 
 #ifdef CONFIG_UNICODE
 	utf8_unload(sb->s_encoding);
+	sb->s_encoding = NULL;
 #endif
 free_options:
 #ifdef CONFIG_QUOTA

fs/f2fs/sysfs.c

@@ -92,7 +92,8 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 {
 	return sprintf(buf, "%llu\n",
 			(unsigned long long)(sbi->kbytes_written +
-			BD_PART_WRITTEN(sbi)));
+			((f2fs_get_sectors_written(sbi) -
+				sbi->sectors_written_start) >> 1)));
 }
 
 static ssize_t features_show(struct f2fs_attr *a,
@@ -557,6 +558,7 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info,
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_period_ms, iostat_period_ms);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_io_bytes, max_io_bytes);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list);
 #ifdef CONFIG_F2FS_FAULT_INJECTION
@@ -641,6 +643,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(iostat_enable),
 	ATTR_LIST(iostat_period_ms),
 	ATTR_LIST(readdir_ra),
+	ATTR_LIST(max_io_bytes),
 	ATTR_LIST(gc_pin_file_thresh),
 	ATTR_LIST(extension_list),
 #ifdef CONFIG_F2FS_FAULT_INJECTION

fs/libfs.c

@@ -1451,4 +1451,74 @@ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 	return 0;
 }
 EXPORT_SYMBOL(generic_ci_d_hash);
+
+static const struct dentry_operations generic_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+};
+#endif
+
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct dentry_operations generic_encrypted_dentry_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+/**
+ * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
+ * @dentry:	dentry to set ops on
+ *
+ * Casefolded directories need d_hash and d_compare set, so that the dentries
+ * contained in them are handled case-insensitively.  Note that these operations
+ * are needed on the parent directory rather than on the dentries in it, and
+ * while the casefolding flag can be toggled on and off on an empty directory,
+ * dentry_operations can't be changed later.  As a result, if the filesystem has
+ * casefolding support enabled at all, we have to give all dentries the
+ * casefolding operations even if their inode doesn't have the casefolding flag
+ * currently (and thus the casefolding ops would be no-ops for now).
+ *
+ * Encryption works differently in that the only dentry operation it needs is
+ * d_revalidate, which it only needs on dentries that have the no-key name flag.
+ * The no-key flag can't be set "later", so we don't have to worry about that.
+ *
+ * Finally, to maximize compatibility with overlayfs (which isn't compatible
+ * with certain dentry operations) and to avoid taking an unnecessary
+ * performance hit, we use custom dentry_operations for each possible
+ * combination rather than always installing all operations.
+ */
+void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
+#endif
+#ifdef CONFIG_UNICODE
+	bool needs_ci_ops = dentry->d_sb->s_encoding;
+#endif
+#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+	if (needs_encrypt_ops && needs_ci_ops) {
+		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+		return;
+	}
 #endif
+#ifdef CONFIG_FS_ENCRYPTION
+	if (needs_encrypt_ops) {
+		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
+		return;
+	}
+#endif
+#ifdef CONFIG_UNICODE
+	if (needs_ci_ops) {
+		d_set_d_op(dentry, &generic_ci_dentry_ops);
+		return;
+	}
+#endif
+}
+EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);

fs/ubifs/dir.c

@@ -203,6 +203,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino);
 
 	err = fscrypt_prepare_lookup(dir, dentry, &nm);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return d_splice_alias(NULL, dentry);
 	if (err)

include/linux/f2fs_fs.h

@@ -273,7 +273,7 @@ struct f2fs_inode {
 			__le64 i_compr_blocks;	/* # of compressed blocks */
 			__u8 i_compress_algorithm;	/* compress algorithm */
 			__u8 i_log_cluster_size;	/* log of cluster size */
-			__le16 i_padding;		/* padding */
+			__le16 i_compress_flag;		/* compress flag */
 			__le32 i_extra_end[0];	/* for attribute size calculation */
 		} __packed;
 		__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */

include/linux/fs.h

@@ -3198,6 +3198,7 @@ extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
 extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 				const char *str, const struct qstr *name);
 #endif
+extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
 
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,

include/linux/fscrypt.h

@@ -757,8 +757,11 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
  * key is available, then the lookup is assumed to be by plaintext name;
  * otherwise, it is assumed to be by no-key name.
  *
- * This also installs a custom ->d_revalidate() method which will invalidate the
- * dentry if it was created without the key and the key is later added.
+ * This will set DCACHE_NOKEY_NAME on the dentry if the lookup is by no-key
+ * name.  In this case the filesystem must assign the dentry a dentry_operations
+ * which contains fscrypt_d_revalidate (or contains a d_revalidate method that
+ * calls fscrypt_d_revalidate), so that the dentry will be invalidated if the
+ * directory's encryption key is later added.
  *
  * Return: 0 on success; -ENOENT if the directory's key is unavailable but the
  * filename isn't a valid no-key name, so a negative dentry should be created;

include/trace/events/f2fs.h

@@ -6,6 +6,7 @@
 #define _TRACE_F2FS_H
 
 #include <linux/tracepoint.h>
+#include <uapi/linux/f2fs.h>
 
 #define show_dev(dev)		MAJOR(dev), MINOR(dev)
 #define show_dev_ino(entry)	show_dev(entry->dev), (unsigned long)entry->ino

include/uapi/linux/f2fs.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_F2FS_H
+#define _UAPI_LINUX_F2FS_H
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * f2fs-specific ioctl commands
+ */
+#define F2FS_IOCTL_MAGIC		0xf5
+#define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
+#define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
+#define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
+#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
+#define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
+#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
+						struct f2fs_defragment)
+#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
+						struct f2fs_move_range)
+#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
+						struct f2fs_flush_device)
+#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
+						struct f2fs_gc_range)
+#define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
+#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
+#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
+#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
+#define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
+#define F2FS_IOC_GET_COMPRESS_BLOCKS	_IOR(F2FS_IOCTL_MAGIC, 17, __u64)
+#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS				\
+					_IOR(F2FS_IOCTL_MAGIC, 18, __u64)
+#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS				\
+					_IOR(F2FS_IOCTL_MAGIC, 19, __u64)
+#define F2FS_IOC_SEC_TRIM_FILE		_IOW(F2FS_IOCTL_MAGIC, 20,	\
+						struct f2fs_sectrim_range)
+#define F2FS_IOC_GET_COMPRESS_OPTION	_IOR(F2FS_IOCTL_MAGIC, 21,	\
+						struct f2fs_comp_option)
+#define F2FS_IOC_SET_COMPRESS_OPTION	_IOW(F2FS_IOCTL_MAGIC, 22,	\
+						struct f2fs_comp_option)
+#define F2FS_IOC_DECOMPRESS_FILE	_IO(F2FS_IOCTL_MAGIC, 23)
+#define F2FS_IOC_COMPRESS_FILE		_IO(F2FS_IOCTL_MAGIC, 24)
+
+/*
+ * should be same as XFS_IOC_GOINGDOWN.
+ * Flags for going down operation used by FS_IOC_GOINGDOWN
+ */
+#define F2FS_IOC_SHUTDOWN	_IOR('X', 125, __u32)	/* Shutdown */
+#define F2FS_GOING_DOWN_FULLSYNC	0x0	/* going down with full sync */
+#define F2FS_GOING_DOWN_METASYNC	0x1	/* going down with metadata */
+#define F2FS_GOING_DOWN_NOSYNC		0x2	/* going down */
+#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
+#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
+
+/*
+ * Flags used by F2FS_IOC_SEC_TRIM_FILE
+ */
+#define F2FS_TRIM_FILE_DISCARD		0x1	/* send discard command */
+#define F2FS_TRIM_FILE_ZEROOUT		0x2	/* zero out */
+#define F2FS_TRIM_FILE_MASK		0x3
+
+struct f2fs_gc_range {
+	__u32 sync;
+	__u64 start;
+	__u64 len;
+};
+
+struct f2fs_defragment {
+	__u64 start;
+	__u64 len;
+};
+
+struct f2fs_move_range {
+	__u32 dst_fd;		/* destination fd */
+	__u64 pos_in;		/* start position in src_fd */
+	__u64 pos_out;		/* start position in dst_fd */
+	__u64 len;		/* size to move */
+};
+
+struct f2fs_flush_device {
+	__u32 dev_num;		/* device number to flush */
+	__u32 segments;		/* # of segments to flush */
+};
+
+struct f2fs_sectrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 flags;
+};
+
+struct f2fs_comp_option {
+	__u8 algorithm;
+	__u8 log_cluster_size;
+};
+
+#endif /* _UAPI_LINUX_F2FS_H */