Merge tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've added new features such as disk quota and statx,
  and modified internal bio management flow to merge more IOs depending
  on block types. We've also made internal threads freezeable for
  Android battery life. In addition to them, there are some patches to
  avoid lock contention as well as a couple of deadlock conditions.

  Enhancements:
   - support usrquota, grpquota, and statx
   - manage DATA/NODE typed bios separately to serialize more IOs
   - modify f2fs_lock_op/wio_mutex to avoid lock contention
   - prevent lock contention in migratepage

  Bug fixes:
   - fix missing load of written inode flag
   - fix worst case victim selection in GC
   - freezeable GC and discard threads for Android battery life
   - sanitize f2fs metadata to deal with security hole
   - clean up sysfs-related code and docs"

* tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (59 commits)
  f2fs: support plain user/group quota
  f2fs: avoid deadlock caused by lock order of page and lock_op
  f2fs: use spin_{,un}lock_irq{save,restore}
  f2fs: relax migratepage for atomic written page
  f2fs: don't count inode block in in-memory inode.i_blocks
  Revert "f2fs: fix to clean previous mount option when remount_fs"
  f2fs: do not set LOST_PINO for renamed dir
  f2fs: do not set LOST_PINO for newly created dir
  f2fs: skip ->writepages for {mete,node}_inode during recovery
  f2fs: introduce __check_sit_bitmap
  f2fs: stop gc/discard thread in prior during umount
  f2fs: introduce reserved_blocks in sysfs
  f2fs: avoid redundant f2fs_flush after remount
  f2fs: report # of free inodes more precisely
  f2fs: add ioctl to do gc with target block address
  f2fs: don't need to check encrypted inode for partial truncation
  f2fs: measure inode.i_blocks as generic filesystem
  f2fs: set CP_TRIMMED_FLAG correctly
  f2fs: require key for truncate(2) of encrypted file
  f2fs: move sysfs code from super.c to fs/f2fs/sysfs.c
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -75,7 +75,7 @@ Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
 Description:
 		 Controls the memory footprint used by f2fs.
 
-What:		/sys/fs/f2fs/<disk>/trim_sections
+What:		/sys/fs/f2fs/<disk>/batched_trim_sections
 Date:		February 2015
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
@@ -112,3 +112,21 @@ Date:		January 2016
 Contact:	"Shuoran Liu" <liushuoran@huawei.com>
 Description:
 		 Shows total written kbytes issued to disk.
+
+What:		/sys/fs/f2fs/<disk>/inject_rate
+Date:		May 2016
+Contact:	"Sheng Yong" <shengyong1@huawei.com>
+Description:
+		 Controls the injection rate.
+
+What:		/sys/fs/f2fs/<disk>/inject_type
+Date:		May 2016
+Contact:	"Sheng Yong" <shengyong1@huawei.com>
+Description:
+		 Controls the injection type.
+
+What:		/sys/fs/f2fs/<disk>/reserved_blocks
+Date:		June 2017
+Contact:	"Chao Yu" <yuchao0@huawei.com>
+Description:
+		 Controls current reserved blocks in system.

Documentation/filesystems/f2fs.txt

@@ -155,11 +155,15 @@ noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 data_flush             Enable data flushing before checkpoint in order to
                        persist data of regular and symlink.
+fault_injection=%d     Enable fault injection in all supported types with
+                       specified injection rate.
 mode=%s                Control block allocation mode which supports "adaptive"
                        and "lfs". In "lfs" mode, there should be no random
                        writes towards main area.
 io_bits=%u             Set the bit size of write IO requests. It should be set
                        with "mode=lfs".
+usrquota               Enable plain user disk quota accounting.
+grpquota               Enable plain group disk quota accounting.
 
 ================================================================================
 DEBUGFS ENTRIES

fs/f2fs/Makefile

@@ -2,7 +2,7 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o
 
 f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o inline.o
 f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
-f2fs-y		+= shrinker.o extent_cache.o
+f2fs-y		+= shrinker.o extent_cache.o sysfs.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o

fs/f2fs/acl.c

@@ -233,7 +233,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 		value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
 		if (IS_ERR(value)) {
 			clear_inode_flag(inode, FI_ACL_MODE);
-			return (int)PTR_ERR(value);
+			return PTR_ERR(value);
 		}
 	}
 

fs/f2fs/checkpoint.c

@@ -31,7 +31,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	sbi->sb->s_flags |= MS_RDONLY;
 	if (!end_io)
-		f2fs_flush_merged_bios(sbi);
+		f2fs_flush_merged_writes(sbi);
 }
 
 /*
@@ -162,6 +162,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.op = REQ_OP_READ,
 		.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 	struct blk_plug plug;
 
@@ -207,12 +208,10 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		}
 
 		fio.page = page;
-		fio.old_blkaddr = fio.new_blkaddr;
-		f2fs_submit_page_mbio(&fio);
+		f2fs_submit_page_bio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
-	f2fs_submit_merged_bio(sbi, META, READ);
 	blk_finish_plug(&plug);
 	return blkno - start;
 }
@@ -249,13 +248,13 @@ static int f2fs_write_meta_page(struct page *page,
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
-						0, page->index, META, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, META);
 
 	unlock_page(page);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, META, WRITE);
+		f2fs_submit_merged_write(sbi, META);
 
 	return 0;
 
@@ -270,6 +269,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff, written;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
@@ -358,7 +360,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 	}
 stop:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, type, WRITE);
+		f2fs_submit_merged_write(sbi, type);
 
 	blk_finish_plug(&plug);
 
@@ -906,7 +908,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 		 * We should submit bio, since it exists several
 		 * wribacking dentry pages in the freeing inode.
 		 */
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		f2fs_submit_merged_write(sbi, DATA);
 		cond_resched();
 	}
 	goto retry;
@@ -1051,8 +1053,9 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned long flags;
 
-	spin_lock(&sbi->cp_lock);
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 
 	if ((cpc->reason & CP_UMOUNT) &&
 			le32_to_cpu(ckpt->cp_pack_total_block_count) >
@@ -1083,14 +1086,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* set this flag to activate crc|cp_ver for recovery */
 	__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
 
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
+	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags;
 	block_t start_blk;
 	unsigned int data_sum_blocks, orphan_blocks;
 	__u32 crc32 = 0;
@@ -1132,12 +1135,12 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
 	data_sum_blocks = npages_for_summary_flush(sbi, false);
-	spin_lock(&sbi->cp_lock);
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
 		__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 
 	orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
@@ -1295,7 +1298,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	/* this is the case of multiple fstrims without any changes */
 	if (cpc->reason & CP_DISCARD) {

fs/f2fs/data.c

@@ -282,29 +282,32 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
 				nid_t ino, pgoff_t idx, enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	bool ret;
+	enum temp_type temp;
+	struct f2fs_bio_info *io;
+	bool ret = false;
+
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+		io = sbi->write_io[btype] + temp;
 
 		down_read(&io->io_rwsem);
 		ret = __has_merged_page(io, inode, ino, idx);
 		up_read(&io->io_rwsem);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (ret || btype == META)
+			break;
+	}
 	return ret;
 }
 
-static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
-				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw)
+static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
+				enum page_type type, enum temp_type temp)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io;
-
-	io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype];
+	struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
 
 	down_write(&io->io_rwsem);
 
-	if (!__has_merged_page(io, inode, ino, idx))
-		goto out;
-
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
@@ -314,29 +317,45 @@ static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 			io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 	}
 	__submit_merged_bio(io);
-out:
 	up_write(&io->io_rwsem);
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-									int rw)
+static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, bool force)
+{
+	enum temp_type temp;
+
+	if (!force && !has_merged_page(sbi, inode, ino, idx, type))
+		return;
+
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+
+		__f2fs_submit_merged_write(sbi, type, temp);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (type >= META)
+			break;
+	}
+}
+
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
 {
-	__f2fs_submit_merged_bio(sbi, NULL, 0, 0, type, rw);
+	__submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
 }
 
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw)
+				enum page_type type)
 {
-	if (has_merged_page(sbi, inode, ino, idx, type))
-		__f2fs_submit_merged_bio(sbi, inode, ino, idx, type, rw);
+	__submit_merged_write_cond(sbi, inode, ino, idx, type, false);
 }
 
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
 {
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_submit_merged_write(sbi, DATA);
+	f2fs_submit_merged_write(sbi, NODE);
+	f2fs_submit_merged_write(sbi, META);
 }
 
 /*
@@ -368,16 +387,29 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	return 0;
 }
 
-int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+int f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
-	struct f2fs_bio_info *io;
-	bool is_read = is_read_io(fio->op);
+	struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
 	struct page *bio_page;
 	int err = 0;
 
-	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
+	f2fs_bug_on(sbi, is_read_io(fio->op));
+
+	down_write(&io->io_rwsem);
+next:
+	if (fio->in_list) {
+		spin_lock(&io->io_lock);
+		if (list_empty(&io->io_list)) {
+			spin_unlock(&io->io_lock);
+			goto out_fail;
+		}
+		fio = list_first_entry(&io->io_list,
+						struct f2fs_io_info, list);
+		list_del(&fio->list);
+		spin_unlock(&io->io_lock);
+	}
 
 	if (fio->old_blkaddr != NEW_ADDR)
 		verify_block_addr(sbi, fio->old_blkaddr);
@@ -388,11 +420,8 @@ int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 	/* set submitted = 1 as a return value */
 	fio->submitted = 1;
 
-	if (!is_read)
 	inc_page_count(sbi, WB_DATA_TYPE(bio_page));
 
-	down_write(&io->io_rwsem);
-
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
 			!__same_bdev(sbi, fio->new_blkaddr, io->bio)))
@@ -402,26 +431,28 @@ int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 		if ((fio->type == DATA || fio->type == NODE) &&
 				fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
 			err = -EAGAIN;
-			if (!is_read)
 			dec_page_count(sbi, WB_DATA_TYPE(bio_page));
 			goto out_fail;
 		}
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						BIO_MAX_PAGES, is_read);
+						BIO_MAX_PAGES, false);
 		io->fio = *fio;
 	}
 
-	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
-							PAGE_SIZE) {
+	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
 
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
+
+	trace_f2fs_submit_page_write(fio->page, fio);
+
+	if (fio->in_list)
+		goto next;
 out_fail:
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(fio->page, fio);
 	return err;
 }
 
@@ -460,14 +491,15 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	int err;
 
 	if (!count)
 		return 0;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 	trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
 						dn->ofs_in_node, count);
@@ -718,6 +750,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct node_info ni;
 	pgoff_t fofs;
 	blkcnt_t count = 1;
+	int err;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
@@ -726,15 +759,15 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (dn->data_blkaddr == NEW_ADDR)
 		goto alloc;
 
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 alloc:
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-						&sum, CURSEG_WARM_DATA);
+					&sum, CURSEG_WARM_DATA, NULL, false);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -1321,7 +1354,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio)
 
 	/* flush pending IOs and wait for a while in the ENOMEM case */
 	if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
-		f2fs_flush_merged_bios(fio->sbi);
+		f2fs_flush_merged_writes(fio->sbi);
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		gfp_flags |= __GFP_NOFAIL;
 		goto retry_encrypt;
@@ -1368,13 +1401,14 @@ int do_write_data_page(struct f2fs_io_info *fio)
 
 		if (valid_ipu_blkaddr(fio)) {
 			ipu_force = true;
-			fio->need_lock = false;
+			fio->need_lock = LOCK_DONE;
 			goto got_it;
 		}
 	}
 
-	if (fio->need_lock)
-		f2fs_lock_op(fio->sbi);
+	/* Deadlock due to between page->lock and f2fs_lock_op */
+	if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
+		return -EAGAIN;
 
 	err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
 	if (err)
@@ -1388,19 +1422,18 @@ int do_write_data_page(struct f2fs_io_info *fio)
 		goto out_writepage;
 	}
 got_it:
-	err = encrypt_one_page(fio);
-	if (err)
-		goto out_writepage;
-
-	set_page_writeback(page);
-
 	/*
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
 	if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) {
+		err = encrypt_one_page(fio);
+		if (err)
+			goto out_writepage;
+
+		set_page_writeback(page);
 		f2fs_put_dnode(&dn);
-		if (fio->need_lock)
+		if (fio->need_lock == LOCK_REQ)
 			f2fs_unlock_op(fio->sbi);
 		err = rewrite_data_page(fio);
 		trace_f2fs_do_write_data_page(fio->page, IPU);
@@ -1408,6 +1441,20 @@ int do_write_data_page(struct f2fs_io_info *fio)
 		return err;
 	}
 
+	if (fio->need_lock == LOCK_RETRY) {
+		if (!f2fs_trylock_op(fio->sbi)) {
+			err = -EAGAIN;
+			goto out_writepage;
+		}
+		fio->need_lock = LOCK_REQ;
+	}
+
+	err = encrypt_one_page(fio);
+	if (err)
+		goto out_writepage;
+
+	set_page_writeback(page);
+
 	/* LFS mode write path */
 	write_data_page(&dn, fio);
 	trace_f2fs_do_write_data_page(page, OPU);
@@ -1417,7 +1464,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
 out_writepage:
 	f2fs_put_dnode(&dn);
 out:
-	if (fio->need_lock)
+	if (fio->need_lock == LOCK_REQ)
 		f2fs_unlock_op(fio->sbi);
 	return err;
 }
@@ -1443,11 +1490,14 @@ static int __write_data_page(struct page *page, bool *submitted,
 		.page = page,
 		.encrypted_page = NULL,
 		.submitted = false,
-		.need_lock = true,
+		.need_lock = LOCK_RETRY,
 	};
 
 	trace_f2fs_writepage(page, DATA);
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+
 	if (page->index < end_index)
 		goto write;
 
@@ -1461,8 +1511,6 @@ static int __write_data_page(struct page *page, bool *submitted,
 
 	zero_user_segment(page, offset, PAGE_SIZE);
 write:
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto redirty_out;
 	if (f2fs_is_drop_cache(inode))
 		goto out;
 	/* we should not write 0'th page having journal header */
@@ -1479,7 +1527,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
-		fio.need_lock = false;
+		fio.need_lock = LOCK_DONE;
 		err = do_write_data_page(&fio);
 		goto done;
 	}
@@ -1498,8 +1546,13 @@ static int __write_data_page(struct page *page, bool *submitted,
 			goto out;
 	}
 
-	if (err == -EAGAIN)
+	if (err == -EAGAIN) {
 		err = do_write_data_page(&fio);
+		if (err == -EAGAIN) {
+			fio.need_lock = LOCK_REQ;
+			err = do_write_data_page(&fio);
+		}
+	}
 	if (F2FS_I(inode)->last_disk_size < psize)
 		F2FS_I(inode)->last_disk_size = psize;
 
@@ -1513,8 +1566,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 		ClearPageUptodate(page);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index,
-						DATA, WRITE);
+		f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
 		clear_inode_flag(inode, FI_HOT_DATA);
 		remove_dirty_inode(inode);
 		submitted = NULL;
@@ -1525,7 +1577,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 		f2fs_balance_fs(sbi, need_balance_fs);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		f2fs_submit_merged_write(sbi, DATA);
 		submitted = NULL;
 	}
 
@@ -1618,7 +1670,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 			}
 
 			done_index = page->index;
-
+retry_write:
 			lock_page(page);
 
 			if (unlikely(page->mapping != mapping)) {
@@ -1654,6 +1706,15 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 					unlock_page(page);
 					ret = 0;
 					continue;
+				} else if (ret == -EAGAIN) {
+					ret = 0;
+					if (wbc->sync_mode == WB_SYNC_ALL) {
+						cond_resched();
+						congestion_wait(BLK_RW_ASYNC,
+									HZ/50);
+						goto retry_write;
+					}
+					continue;
 				}
 				done_index = page->index + 1;
 				done = 1;
@@ -1684,8 +1745,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 		mapping->writeback_index = done_index;
 
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
-						0, last_idx, DATA, WRITE);
+		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+						0, last_idx, DATA);
 
 	return ret;
 }
@@ -1706,6 +1767,10 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
 		return 0;
 
+	/* during POR, we don't need to trigger writepage at all. */
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
 			get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
 			available_free_memory(sbi, DIRTY_DENTS))
@@ -1715,10 +1780,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (is_inode_flag_set(inode, FI_DO_DEFRAG))
 		goto skip_write;
 
-	/* during POR, we don't need to trigger writepage at all. */
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto skip_write;
-
 	trace_f2fs_writepages(mapping->host, wbc, DATA);
 
 	/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
@@ -1753,8 +1814,10 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 	loff_t i_size = i_size_read(inode);
 
 	if (to > i_size) {
+		down_write(&F2FS_I(inode)->i_mmap_sem);
 		truncate_pagecache(inode, i_size);
 		truncate_blocks(inode, i_size, true);
+		up_write(&F2FS_I(inode)->i_mmap_sem);
 	}
 }
 
@@ -2152,8 +2215,12 @@ int f2fs_migrate_page(struct address_space *mapping,
 	BUG_ON(PageWriteback(page));
 
 	/* migrating an atomic written page is safe with the inmem_lock hold */
-	if (atomic_written && !mutex_trylock(&fi->inmem_lock))
+	if (atomic_written) {
+		if (mode != MIGRATE_SYNC)
+			return -EBUSY;
+		if (!mutex_trylock(&fi->inmem_lock))
 			return -EAGAIN;
+	}
 
 	/*
 	 * A reference is expected if PagePrivate set when move mapping,

fs/f2fs/dir.c

@@ -415,6 +415,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 	 * We lost i_pino from now on.
 	 */
 	if (is_inode_flag_set(inode, FI_INC_LINK)) {
+		if (!S_ISDIR(inode->i_mode))
 			file_lost_pino(inode);
 		/*
 		 * If link the tmpfile to alias through linkat path,

fs/f2fs/extent_cache.c

@@ -320,7 +320,7 @@ static void __drop_largest_extent(struct inode *inode,
 }
 
 /* return true, if inode page is changed */
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
@@ -358,6 +358,16 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 	return false;
 }
 
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+{
+	bool ret =  __f2fs_init_extent_tree(inode, i_ext);
+
+	if (!F2FS_I(inode)->extent_tree)
+		set_inode_flag(inode, FI_NO_EXTENT);
+
+	return ret;
+}
+
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {

fs/f2fs/f2fs.h

@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/quotaops.h>
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 #include <linux/fscrypt_supp.h>
 #else
@@ -88,6 +89,8 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
 #define F2FS_MOUNT_ADAPTIVE		0x00020000
 #define F2FS_MOUNT_LFS			0x00040000
+#define F2FS_MOUNT_USRQUOTA		0x00080000
+#define F2FS_MOUNT_GRPQUOTA		0x00100000
 
 #define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -303,6 +306,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 						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_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
@@ -327,6 +332,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
 #endif
 
+struct f2fs_gc_range {
+	u32 sync;
+	u64 start;
+	u64 len;
+};
+
 struct f2fs_defragment {
 	u64 start;
 	u64 len;
@@ -513,12 +524,19 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	loff_t	last_disk_size;		/* lastly written file size */
 
+#ifdef CONFIG_QUOTA
+	struct dquot *i_dquot[MAXQUOTAS];
+
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
 	struct list_head dirty_list;	/* dirty list for dirs and files */
 	struct list_head gdirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
 	struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
+	struct rw_semaphore i_mmap_sem;
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -792,17 +810,33 @@ enum page_type {
 	OPU,
 };
 
+enum temp_type {
+	HOT = 0,	/* must be zero for meta bio */
+	WARM,
+	COLD,
+	NR_TEMP_TYPE,
+};
+
+enum need_lock_type {
+	LOCK_REQ = 0,
+	LOCK_DONE,
+	LOCK_RETRY,
+};
+
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
+	enum temp_type temp;	/* contains HOT/WARM/COLD */
 	int op;			/* contains REQ_OP_ */
 	int op_flags;		/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	struct list_head list;		/* serialize IOs */
 	bool submitted;		/* indicate IO submission */
-	bool need_lock;		/* indicate we need to lock cp_rwsem */
+	int need_lock;		/* indicate we need to lock cp_rwsem */
+	bool in_list;		/* indicate fio is in io_list */
 };
 
 #define is_read_io(rw) ((rw) == READ)
@@ -812,6 +846,8 @@ struct f2fs_bio_info {
 	sector_t last_block_in_bio;	/* last block number */
 	struct f2fs_io_info fio;	/* store buffered io info. */
 	struct rw_semaphore io_rwsem;	/* blocking op for bio */
+	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
+	struct list_head io_list;	/* track fios */
 };
 
 #define FDEV(i)				(sbi->devs[i])
@@ -879,9 +915,9 @@ struct f2fs_sb_info {
 	struct f2fs_sm_info *sm_info;		/* segment manager */
 
 	/* for bio operations */
-	struct f2fs_bio_info read_io;			/* for read bios */
-	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
-	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
+	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
+	struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
+						/* bio ordering for NODE/DATA */
 	int write_io_size_bits;			/* Write IO size bits */
 	mempool_t *write_io_dummy;		/* Dummy pages */
 
@@ -939,6 +975,8 @@ struct f2fs_sb_info {
 	block_t total_valid_block_count;	/* # of valid blocks */
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
+	block_t reserved_blocks;		/* configurable reserved blocks */
+
 	u32 s_next_generation;			/* for NFS support */
 
 	/* # of pages, see count_type */
@@ -1228,9 +1266,11 @@ static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 
 static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__set_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
@@ -1244,22 +1284,26 @@ static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f
 
 static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
 {
+	unsigned long flags;
+
 	set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	if (lock)
-		spin_lock(&sbi->cp_lock);
+		spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
 	kfree(NM_I(sbi)->nat_bits);
 	NM_I(sbi)->nat_bits = NULL;
 	if (lock)
-		spin_unlock(&sbi->cp_lock);
+		spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
@@ -1275,6 +1319,11 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 	down_read(&sbi->cp_rwsem);
 }
 
+static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
+{
+	return down_read_trylock(&sbi->cp_rwsem);
+}
+
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
 	up_read(&sbi->cp_rwsem);
@@ -1324,17 +1373,14 @@ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 	return 0;
 }
 
-#define F2FS_DEFAULT_ALLOCATED_BLOCKS	1
-
 /*
  * Check whether the inode has blocks or not
  */
 static inline int F2FS_HAS_BLOCKS(struct inode *inode)
 {
-	if (F2FS_I(inode)->i_xattr_nid)
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1;
-	else
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS;
+	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;
+
+	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
 }
 
 static inline bool f2fs_has_xattr_block(unsigned int ofs)
@@ -1342,16 +1388,23 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 	return ofs == XATTR_NODE_OFFSET;
 }
 
-static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
-static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
+static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 				 struct inode *inode, blkcnt_t *count)
 {
-	blkcnt_t diff;
+	blkcnt_t diff = 0, release = 0;
+	block_t avail_user_block_count;
+	int ret;
+
+	ret = dquot_reserve_block(inode, *count);
+	if (ret)
+		return ret;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_BLOCK)) {
 		f2fs_show_injection_info(FAULT_BLOCK);
-		return false;
+		release = *count;
+		goto enospc;
 	}
 #endif
 	/*
@@ -1362,32 +1415,42 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	sbi->total_valid_block_count += (block_t)(*count);
-	if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
-		diff = sbi->total_valid_block_count - sbi->user_block_count;
+	avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks;
+	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
+		diff = sbi->total_valid_block_count - avail_user_block_count;
 		*count -= diff;
-		sbi->total_valid_block_count = sbi->user_block_count;
+		release = diff;
+		sbi->total_valid_block_count = avail_user_block_count;
 		if (!*count) {
 			spin_unlock(&sbi->stat_lock);
 			percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
-			return false;
+			goto enospc;
 		}
 	}
 	spin_unlock(&sbi->stat_lock);
 
-	f2fs_i_blocks_write(inode, *count, true);
-	return true;
+	if (release)
+		dquot_release_reservation_block(inode, release);
+	f2fs_i_blocks_write(inode, *count, true, true);
+	return 0;
+
+enospc:
+	dquot_release_reservation_block(inode, release);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 						struct inode *inode,
-						blkcnt_t count)
+						block_t count)
 {
+	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
+
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	f2fs_bug_on(sbi, inode->i_blocks < count);
+	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
-	f2fs_i_blocks_write(inode, count, false);
+	f2fs_i_blocks_write(inode, count, false, true);
 }
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1516,51 +1579,70 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
 }
 
-static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
+					struct inode *inode, bool is_inode)
 {
 	block_t	valid_block_count;
 	unsigned int valid_node_count;
+	bool quota = inode && !is_inode;
+
+	if (quota) {
+		int ret = dquot_reserve_block(inode, 1);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock(&sbi->stat_lock);
 
 	valid_block_count = sbi->total_valid_block_count + 1;
-	if (unlikely(valid_block_count > sbi->user_block_count)) {
+	if (unlikely(valid_block_count + sbi->reserved_blocks >
+						sbi->user_block_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
 	valid_node_count = sbi->total_valid_node_count + 1;
 	if (unlikely(valid_node_count > sbi->total_node_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
-	if (inode)
-		f2fs_i_blocks_write(inode, 1, true);
-
 	sbi->total_valid_node_count++;
 	sbi->total_valid_block_count++;
 	spin_unlock(&sbi->stat_lock);
 
+	if (inode) {
+		if (is_inode)
+			f2fs_mark_inode_dirty_sync(inode, true);
+		else
+			f2fs_i_blocks_write(inode, 1, true, true);
+	}
+
 	percpu_counter_inc(&sbi->alloc_valid_block_count);
-	return true;
+	return 0;
+
+enospc:
+	if (quota)
+		dquot_release_reservation_block(inode, 1);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+					struct inode *inode, bool is_inode)
 {
 	spin_lock(&sbi->stat_lock);
 
 	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
-	f2fs_bug_on(sbi, !inode->i_blocks);
+	f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
 
-	f2fs_i_blocks_write(inode, 1, false);
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
 
 	spin_unlock(&sbi->stat_lock);
+
+	if (!is_inode)
+		f2fs_i_blocks_write(inode, 1, false, true);
 }
 
 static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1835,13 +1917,21 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 }
 
 static inline void f2fs_i_blocks_write(struct inode *inode,
-					blkcnt_t diff, bool add)
+					block_t diff, bool add, bool claim)
 {
 	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
 	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
 
-	inode->i_blocks = add ? inode->i_blocks + diff :
-				inode->i_blocks - diff;
+	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
+	if (add) {
+		if (claim)
+			dquot_claim_block(inode, diff);
+		else
+			dquot_alloc_block_nofail(inode, diff);
+	} else {
+		dquot_free_block(inode, diff);
+	}
+
 	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);
@@ -2236,6 +2326,7 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
 void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void stop_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void release_discard_addrs(struct f2fs_sb_info *sbi);
@@ -2258,7 +2349,8 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 			bool recover_newaddr);
 void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
-			struct f2fs_summary *sum, int type);
+			struct f2fs_summary *sum, int type,
+			struct f2fs_io_info *fio, bool add_list);
 void f2fs_wait_on_page_writeback(struct page *page,
 			enum page_type type, bool ordered);
 void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
@@ -2308,14 +2400,13 @@ void destroy_checkpoint_caches(void);
 /*
  * data.c
  */
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-			int rw);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
+				enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
 int f2fs_submit_page_bio(struct f2fs_io_info *fio);
-int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
+int f2fs_submit_page_write(struct f2fs_io_info *fio);
 struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 			block_t blk_addr, struct bio *bio);
 int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
@@ -2632,6 +2723,14 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi);
 int __init create_extent_cache(void);
 void destroy_extent_cache(void);
 
+/*
+ * sysfs.c
+ */
+int __init f2fs_register_sysfs(void);
+void f2fs_unregister_sysfs(void);
+int f2fs_init_sysfs(struct f2fs_sb_info *sbi);
+void f2fs_exit_sysfs(struct f2fs_sb_info *sbi);
+
 /*
  * crypto support
  */

fs/f2fs/file.c

@@ -33,6 +33,18 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
+static int f2fs_filemap_fault(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	int err;
+
+	down_read(&F2FS_I(inode)->i_mmap_sem);
+	err = filemap_fault(vmf);
+	up_read(&F2FS_I(inode)->i_mmap_sem);
+
+	return err;
+}
+
 static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -59,13 +71,14 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	f2fs_balance_fs(sbi, dn.node_changed);
 
 	file_update_time(vmf->vma->vm_file);
+	down_read(&F2FS_I(inode)->i_mmap_sem);
 	lock_page(page);
 	if (unlikely(page->mapping != inode->i_mapping ||
 			page_offset(page) > i_size_read(inode) ||
 			!PageUptodate(page))) {
 		unlock_page(page);
 		err = -EFAULT;
-		goto out;
+		goto out_sem;
 	}
 
 	/*
@@ -94,6 +107,8 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
 
+out_sem:
+	up_read(&F2FS_I(inode)->i_mmap_sem);
 out:
 	sb_end_pagefault(inode->i_sb);
 	f2fs_update_time(sbi, REQ_TIME);
@@ -101,7 +116,7 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= f2fs_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
 };
@@ -415,14 +430,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	struct inode *inode = file_inode(file);
 	int err;
 
-	if (f2fs_encrypted_inode(inode)) {
-		err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return 0;
-		if (!f2fs_encrypted_inode(inode))
-			return -ENOKEY;
-	}
-
 	/* we don't need to use inline_data strictly */
 	err = f2fs_convert_inline_inode(inode);
 	if (err)
@@ -435,11 +442,10 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
-	int ret = generic_file_open(inode, filp);
 	struct dentry *dir;
 
-	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = fscrypt_get_encryption_info(inode);
+	if (f2fs_encrypted_inode(inode)) {
+		int ret = fscrypt_get_encryption_info(inode);
 		if (ret)
 			return -EACCES;
 		if (!fscrypt_has_encryption_key(inode))
@@ -452,7 +458,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 		return -EPERM;
 	}
 	dput(dir);
-	return ret;
+	return dquot_file_open(inode, filp);
 }
 
 int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -527,8 +533,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 truncate_out:
 	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, offset, PAGE_SIZE - offset);
-	if (!cache_only || !f2fs_encrypted_inode(inode) ||
-					!S_ISREG(inode->i_mode))
+
+	/* An encrypted inode should have a key and truncate the last page. */
+	f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode));
+	if (!cache_only)
 		set_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return 0;
@@ -633,11 +641,31 @@ int f2fs_truncate(struct inode *inode)
 }
 
 int f2fs_getattr(const struct path *path, struct kstat *stat,
-		 u32 request_mask, unsigned int flags)
+		 u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	unsigned int flags;
+
+	flags = fi->i_flags & FS_FL_USER_VISIBLE;
+	if (flags & FS_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (flags & FS_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (f2fs_encrypted_inode(inode))
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (flags & FS_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (flags & FS_NODUMP_FL)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
+
 	generic_fillattr(inode, stat);
-	stat->blocks <<= 3;
 	return 0;
 }
 
@@ -681,14 +709,34 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		return err;
 
+	if (is_quota_modification(inode, attr)) {
+		err = dquot_initialize(inode);
+		if (err)
+			return err;
+	}
+	if ((attr->ia_valid & ATTR_UID &&
+		!uid_eq(attr->ia_uid, inode->i_uid)) ||
+		(attr->ia_valid & ATTR_GID &&
+		!gid_eq(attr->ia_gid, inode->i_gid))) {
+		err = dquot_transfer(inode, attr);
+		if (err)
+			return err;
+	}
+
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (f2fs_encrypted_inode(inode) &&
-				fscrypt_get_encryption_info(inode))
-			return -EACCES;
+		if (f2fs_encrypted_inode(inode)) {
+			err = fscrypt_get_encryption_info(inode);
+			if (err)
+				return err;
+			if (!fscrypt_has_encryption_key(inode))
+				return -ENOKEY;
+		}
 
 		if (attr->ia_size <= i_size_read(inode)) {
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_setsize(inode, attr->ia_size);
 			err = f2fs_truncate(inode);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 			if (err)
 				return err;
 		} else {
@@ -696,7 +744,9 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			 * do not trim all blocks after i_size if target size is
 			 * larger than i_size.
 			 */
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_setsize(inode, attr->ia_size);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 
 			/* should convert inline inode here */
 			if (!f2fs_may_inline_data(inode)) {
@@ -839,12 +889,14 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 			blk_start = (loff_t)pg_start << PAGE_SHIFT;
 			blk_end = (loff_t)pg_end << PAGE_SHIFT;
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
 
 			f2fs_lock_op(sbi);
 			ret = truncate_hole(inode, pg_start, pg_end);
 			f2fs_unlock_op(sbi);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 		}
 	}
 
@@ -957,9 +1009,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 
 				if (do_replace[i]) {
 					f2fs_i_blocks_write(src_inode,
-								1, false);
+							1, false, false);
 					f2fs_i_blocks_write(dst_inode,
-								1, true);
+							1, true, false);
 					f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
 					blkaddr[i], ni.version, true, false);
 
@@ -1083,16 +1135,17 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	pg_start = offset >> PAGE_SHIFT;
 	pg_end = (offset + len) >> PAGE_SHIFT;
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	/* write out all dirty pages from offset */
 	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
 	if (ret)
-		return ret;
+		goto out;
 
 	truncate_pagecache(inode, offset);
 
 	ret = f2fs_do_collapse(inode, pg_start, pg_end);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* write out all moved pages, if possible */
 	filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -1105,6 +1158,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
 
+out:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
 }
 
@@ -1169,9 +1224,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	if (ret)
 		return ret;
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
 	if (ret)
-		return ret;
+		goto out_sem;
 
 	truncate_pagecache_range(inode, offset, offset + len - 1);
 
@@ -1185,7 +1241,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 		ret = fill_zero(inode, pg_start, off_start,
 						off_end - off_start);
 		if (ret)
-			return ret;
+			goto out_sem;
 
 		new_size = max_t(loff_t, new_size, offset + len);
 	} else {
@@ -1193,7 +1249,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 			ret = fill_zero(inode, pg_start++, off_start,
 						PAGE_SIZE - off_start);
 			if (ret)
-				return ret;
+				goto out_sem;
 
 			new_size = max_t(loff_t, new_size,
 					(loff_t)pg_start << PAGE_SHIFT);
@@ -1242,6 +1298,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 out:
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
 		f2fs_i_size_write(inode, new_size);
+out_sem:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 
 	return ret;
 }
@@ -1271,14 +1329,15 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	f2fs_balance_fs(sbi, true);
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	ret = truncate_blocks(inode, i_size_read(inode), true);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* write out all dirty pages from offset */
 	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
 	if (ret)
-		return ret;
+		goto out;
 
 	truncate_pagecache(inode, offset);
 
@@ -1307,6 +1366,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
+out:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
 }
 
@@ -1475,6 +1536,13 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 
 	inode_lock(inode);
 
+	/* Is it quota file? Do not allow user to mess with it */
+	if (IS_NOQUOTA(inode)) {
+		inode_unlock(inode);
+		ret = -EPERM;
+		goto unlock_out;
+	}
+
 	flags = f2fs_mask_flags(inode->i_mode, flags);
 
 	oldflags = fi->i_flags;
@@ -1493,7 +1561,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 
 	inode->i_ctime = current_time(inode);
 	f2fs_set_inode_flags(inode);
-
+	f2fs_mark_inode_dirty_sync(inode, false);
+unlock_out:
 	inode_unlock(inode);
 out:
 	mnt_drop_write_file(filp);
@@ -1862,6 +1931,50 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 	return ret;
 }
 
+static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_gc_range range;
+	u64 end;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
+							sizeof(range)))
+		return -EFAULT;
+
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	end = range.start + range.len;
+	if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi))
+		return -EINVAL;
+do_more:
+	if (!range.sync) {
+		if (!mutex_trylock(&sbi->gc_mutex)) {
+			ret = -EBUSY;
+			goto out;
+		}
+	} else {
+		mutex_lock(&sbi->gc_mutex);
+	}
+
+	ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+	range.start += sbi->blocks_per_seg;
+	if (range.start <= end)
+		goto do_more;
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -2306,6 +2419,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_get_encryption_pwsalt(filp, arg);
 	case F2FS_IOC_GARBAGE_COLLECT:
 		return f2fs_ioc_gc(filp, arg);
+	case F2FS_IOC_GARBAGE_COLLECT_RANGE:
+		return f2fs_ioc_gc_range(filp, arg);
 	case F2FS_IOC_WRITE_CHECKPOINT:
 		return f2fs_ioc_write_checkpoint(filp, arg);
 	case F2FS_IOC_DEFRAGMENT:
@@ -2326,11 +2441,6 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct blk_plug plug;
 	ssize_t ret;
 
-	if (f2fs_encrypted_inode(inode) &&
-				!fscrypt_has_encryption_key(inode) &&
-				fscrypt_get_encryption_info(inode))
-		return -EACCES;
-
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
@@ -2379,6 +2489,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_GET_ENCRYPTION_PWSALT:
 	case F2FS_IOC_GET_ENCRYPTION_POLICY:
 	case F2FS_IOC_GARBAGE_COLLECT:
+	case F2FS_IOC_GARBAGE_COLLECT_RANGE:
 	case F2FS_IOC_WRITE_CHECKPOINT:
 	case F2FS_IOC_DEFRAGMENT:
 	case F2FS_IOC_MOVE_RANGE:

fs/f2fs/gc.c

@@ -32,13 +32,14 @@ static int gc_thread_func(void *data)
 
 	wait_ms = gc_th->min_sleep_time;
 
+	set_freezable();
 	do {
-		if (try_to_freeze())
-			continue;
-		else
 		wait_event_interruptible_timeout(*wq,
-						kthread_should_stop(),
+				kthread_should_stop() || freezing(current),
 				msecs_to_jiffies(wait_ms));
+
+		if (try_to_freeze())
+			continue;
 		if (kthread_should_stop())
 			break;
 
@@ -258,11 +259,20 @@ static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
 				valid_blocks * 2 : valid_blocks;
 }
 
+static unsigned int get_ssr_cost(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct seg_entry *se = get_seg_entry(sbi, segno);
+
+	return se->ckpt_valid_blocks > se->valid_blocks ?
+				se->ckpt_valid_blocks : se->valid_blocks;
+}
+
 static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct victim_sel_policy *p)
 {
 	if (p->alloc_mode == SSR)
-		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+		return get_ssr_cost(sbi, segno);
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
@@ -586,9 +596,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
+		.temp = COLD,
 		.op = REQ_OP_READ,
 		.op_flags = 0,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 	struct dnode_of_data dn;
 	struct f2fs_summary sum;
@@ -632,7 +644,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 
 	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
-							&sum, CURSEG_COLD_DATA);
+					&sum, CURSEG_COLD_DATA, NULL, false);
 
 	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
 					FGP_LOCK | FGP_CREAT, GFP_NOFS);
@@ -670,7 +682,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	fio.op = REQ_OP_WRITE;
 	fio.op_flags = REQ_SYNC;
 	fio.new_blkaddr = newaddr;
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 
 	f2fs_update_data_blkaddr(&dn, newaddr);
 	set_inode_flag(inode, FI_APPEND_WRITE);
@@ -712,12 +724,13 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
 			.type = DATA,
+			.temp = COLD,
 			.op = REQ_OP_WRITE,
 			.op_flags = REQ_SYNC,
 			.old_blkaddr = NULL_ADDR,
 			.page = page,
 			.encrypted_page = NULL,
-			.need_lock = true,
+			.need_lock = LOCK_REQ,
 		};
 		bool is_dirty = PageDirty(page);
 		int err;
@@ -936,8 +949,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 	}
 
 	if (gc_type == FG_GC)
-		f2fs_submit_merged_bio(sbi,
-				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+		f2fs_submit_merged_write(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA);
 
 	blk_finish_plug(&plug);
 
@@ -955,7 +968,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 {
 	int gc_type = sync ? FG_GC : BG_GC;
 	int sec_freed = 0;
-	int ret = -EINVAL;
+	int ret;
 	struct cp_control cpc;
 	unsigned int init_segno = segno;
 	struct gc_inode_list gc_list = {
@@ -965,8 +978,10 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 
 	cpc.reason = __get_cp_reason(sbi);
 gc_more:
-	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
+	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) {
+		ret = -EINVAL;
 		goto stop;
+	}
 	if (unlikely(f2fs_cp_error(sbi))) {
 		ret = -EIO;
 		goto stop;
@@ -987,6 +1002,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 			gc_type = FG_GC;
 	}
 
+	ret = -EINVAL;
 	/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
 	if (gc_type == BG_GC && !background)
 		goto stop;

fs/f2fs/inline.c

@@ -316,12 +316,12 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 int make_empty_inline_dir(struct inode *inode, struct inode *parent,
 							struct page *ipage)
 {
-	struct f2fs_inline_dentry *dentry_blk;
+	struct f2fs_inline_dentry *inline_dentry;
 	struct f2fs_dentry_ptr d;
 
-	dentry_blk = inline_data_addr(ipage);
+	inline_dentry = inline_data_addr(ipage);
 
-	make_dentry_ptr_inline(NULL, &d, dentry_blk);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 	do_make_empty_dir(inode, parent, &d);
 
 	set_page_dirty(ipage);
@@ -500,7 +500,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 	struct page *ipage;
 	unsigned int bit_pos;
 	f2fs_hash_t name_hash;
-	struct f2fs_inline_dentry *dentry_blk = NULL;
+	struct f2fs_inline_dentry *inline_dentry = NULL;
 	struct f2fs_dentry_ptr d;
 	int slots = GET_DENTRY_SLOTS(new_name->len);
 	struct page *page = NULL;
@@ -510,11 +510,11 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
-	dentry_blk = inline_data_addr(ipage);
-	bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
+	inline_dentry = inline_data_addr(ipage);
+	bit_pos = room_for_filename(&inline_dentry->dentry_bitmap,
 						slots, NR_INLINE_DENTRY);
 	if (bit_pos >= NR_INLINE_DENTRY) {
-		err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
+		err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
 		if (err)
 			return err;
 		err = -EAGAIN;
@@ -534,7 +534,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	name_hash = f2fs_dentry_hash(new_name, NULL);
-	make_dentry_ptr_inline(NULL, &d, dentry_blk);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 	f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
 
 	set_page_dirty(ipage);
@@ -586,14 +586,14 @@ bool f2fs_empty_inline_dir(struct inode *dir)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct page *ipage;
 	unsigned int bit_pos = 2;
-	struct f2fs_inline_dentry *dentry_blk;
+	struct f2fs_inline_dentry *inline_dentry;
 
 	ipage = get_node_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage))
 		return false;
 
-	dentry_blk = inline_data_addr(ipage);
-	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+	inline_dentry = inline_data_addr(ipage);
+	bit_pos = find_next_bit_le(&inline_dentry->dentry_bitmap,
 					NR_INLINE_DENTRY,
 					bit_pos);
 

fs/f2fs/inode.c

@@ -16,6 +16,7 @@
 
 #include "f2fs.h"
 #include "node.h"
+#include "segment.h"
 
 #include <trace/events/f2fs.h>
 
@@ -44,7 +45,6 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
-	f2fs_mark_inode_dirty_sync(inode, false);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -130,7 +130,7 @@ static int do_read_inode(struct inode *inode)
 	i_gid_write(inode, le32_to_cpu(ri->i_gid));
 	set_nlink(inode, le32_to_cpu(ri->i_links));
 	inode->i_size = le64_to_cpu(ri->i_size);
-	inode->i_blocks = le64_to_cpu(ri->i_blocks);
+	inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1);
 
 	inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
 	inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
@@ -226,6 +226,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 		ret = -EIO;
 		goto bad_inode;
 	}
+	f2fs_set_inode_flags(inode);
 	unlock_new_inode(inode);
 	trace_f2fs_iget(inode);
 	return inode;
@@ -267,7 +268,7 @@ int update_inode(struct inode *inode, struct page *node_page)
 	ri->i_gid = cpu_to_le32(i_gid_read(inode));
 	ri->i_links = cpu_to_le32(inode->i_nlink);
 	ri->i_size = cpu_to_le64(i_size_read(inode));
-	ri->i_blocks = cpu_to_le64(inode->i_blocks);
+	ri->i_blocks = cpu_to_le64(SECTOR_TO_BLOCK(inode->i_blocks) + 1);
 
 	if (et) {
 		read_lock(&et->lock);
@@ -372,6 +373,8 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
+	dquot_initialize(inode);
+
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 
@@ -404,8 +407,11 @@ void f2fs_evict_inode(struct inode *inode)
 
 	if (err)
 		update_inode_page(inode);
+	dquot_free_inode(inode);
 	sb_end_intwrite(inode->i_sb);
 no_delete:
+	dquot_drop(inode);
+
 	stat_dec_inline_xattr(inode);
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
@@ -425,9 +431,10 @@ void f2fs_evict_inode(struct inode *inode)
 	if (is_inode_flag_set(inode, FI_FREE_NID)) {
 		alloc_nid_failed(sbi, inode->i_ino);
 		clear_inode_flag(inode, FI_FREE_NID);
-	}
+	} else {
 		f2fs_bug_on(sbi, err &&
 			!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
+	}
 out_clear:
 	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);

fs/f2fs/namei.c

@@ -15,6 +15,7 @@
 #include <linux/ctype.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
+#include <linux/quotaops.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -42,6 +43,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	}
 	f2fs_unlock_op(sbi);
 
+	nid_free = true;
+
 	inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino;
@@ -52,10 +55,17 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	err = insert_inode_locked(inode);
 	if (err) {
 		err = -EINVAL;
-		nid_free = true;
 		goto fail;
 	}
 
+	err = dquot_initialize(inode);
+	if (err)
+		goto fail_drop;
+
+	err = dquot_alloc_inode(inode);
+	if (err)
+		goto fail_drop;
+
 	/* If the directory encrypted, then we should encrypt the inode. */
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
@@ -85,6 +95,16 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 		set_inode_flag(inode, FI_FREE_NID);
 	iput(inode);
 	return ERR_PTR(err);
+fail_drop:
+	trace_f2fs_new_inode(inode, err);
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
+	if (nid_free)
+		set_inode_flag(inode, FI_FREE_NID);
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return ERR_PTR(err);
 }
 
 static int is_multimedia_file(const unsigned char *s, const char *sub)
@@ -136,6 +156,10 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -180,6 +204,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	f2fs_balance_fs(sbi, true);
 
 	inode->i_ctime = current_time(inode);
@@ -347,6 +375,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 
 	trace_f2fs_unlink_enter(dir, dentry);
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de) {
 		if (IS_ERR(page))
@@ -413,6 +445,10 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	if (disk_link.len > dir->i_sb->s_blocksize)
 		return -ENAMETOOLONG;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -500,6 +536,10 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -548,6 +588,10 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -583,6 +627,10 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -676,6 +724,14 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out;
 	}
 
+	err = dquot_initialize(old_dir);
+	if (err)
+		goto out;
+
+	err = dquot_initialize(new_dir);
+	if (err)
+		goto out;
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))
@@ -772,7 +828,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
+	if (!old_dir_entry || whiteout)
 		file_lost_pino(old_inode);
+	else
+		F2FS_I(old_inode)->i_pino = new_dir->i_ino;
 	up_write(&F2FS_I(old_inode)->i_sem);
 
 	old_inode->i_ctime = current_time(old_inode);
@@ -853,6 +912,14 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			 !fscrypt_has_permitted_context(old_dir, new_inode)))
 		return -EPERM;
 
+	err = dquot_initialize(old_dir);
+	if (err)
+		goto out;
+
+	err = dquot_initialize(new_dir);
+	if (err)
+		goto out;
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))

fs/f2fs/node.c

@@ -158,9 +158,6 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 	nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
 	struct nat_entry_set *head;
 
-	if (get_nat_flag(ne, IS_DIRTY))
-		return;
-
 	head = radix_tree_lookup(&nm_i->nat_set_root, set);
 	if (!head) {
 		head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS);
@@ -171,10 +168,18 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 		head->entry_cnt = 0;
 		f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
 	}
-	list_move_tail(&ne->list, &head->entry_list);
+
+	if (get_nat_flag(ne, IS_DIRTY))
+		goto refresh_list;
+
 	nm_i->dirty_nat_cnt++;
 	head->entry_cnt++;
 	set_nat_flag(ne, IS_DIRTY, true);
+refresh_list:
+	if (nat_get_blkaddr(ne) == NEW_ADDR)
+		list_del_init(&ne->list);
+	else
+		list_move_tail(&ne->list, &head->entry_list);
 }
 
 static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
@@ -673,15 +678,11 @@ static void truncate_node(struct dnode_of_data *dn)
 	struct node_info ni;
 
 	get_node_info(sbi, dn->nid, &ni);
-	if (dn->inode->i_blocks == 0) {
-		f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR);
-		goto invalidate;
-	}
 	f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
 
 	/* Deallocate node address */
 	invalidate_blocks(sbi, ni.blk_addr);
-	dec_valid_node_count(sbi, dn->inode);
+	dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
 	if (dn->nid == dn->inode->i_ino) {
@@ -689,7 +690,7 @@ static void truncate_node(struct dnode_of_data *dn)
 		dec_valid_inode_count(sbi);
 		f2fs_inode_synced(dn->inode);
 	}
-invalidate:
+
 	clear_node_page_dirty(dn->node_page);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
@@ -1006,7 +1007,7 @@ int remove_inode_page(struct inode *inode)
 
 	/* 0 is possible, after f2fs_new_inode() has failed */
 	f2fs_bug_on(F2FS_I_SB(inode),
-			inode->i_blocks != 0 && inode->i_blocks != 1);
+			inode->i_blocks != 0 && inode->i_blocks != 8);
 
 	/* will put inode & node pages */
 	truncate_node(&dn);
@@ -1039,10 +1040,9 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	if (unlikely(!inc_valid_node_count(sbi, dn->inode))) {
-		err = -ENOSPC;
+	if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs))))
 		goto fail;
-	}
+
 #ifdef CONFIG_F2FS_CHECK_FS
 	get_node_info(sbi, dn->nid, &new_ni);
 	f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
@@ -1152,6 +1152,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
 	} else if (err == LOCKED_PAGE) {
+		err = 0;
 		goto page_hit;
 	}
 
@@ -1165,15 +1166,22 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 		goto repeat;
 	}
 
-	if (unlikely(!PageUptodate(page)))
+	if (unlikely(!PageUptodate(page))) {
+		err = -EIO;
 		goto out_err;
+	}
 page_hit:
 	if(unlikely(nid != nid_of_node(page))) {
-		f2fs_bug_on(sbi, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, "
+			"nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+			nid, nid_of_node(page), ino_of_node(page),
+			ofs_of_node(page), cpver_of_node(page),
+			next_blkaddr_of_node(page));
 		ClearPageUptodate(page);
+		err = -EINVAL;
 out_err:
 		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
+		return ERR_PTR(err);
 	}
 	return page;
 }
@@ -1373,15 +1381,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	up_read(&sbi->node_write);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host, 0,
-						page->index, NODE, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0,
+						page->index, NODE);
 		submitted = NULL;
 	}
 
 	unlock_page(page);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		f2fs_submit_merged_write(sbi, NODE);
 		submitted = NULL;
 	}
 	if (submitted)
@@ -1518,8 +1526,7 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 	}
 out:
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx,
-							NODE, WRITE);
+		f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE);
 	return ret ? -EIO: 0;
 }
 
@@ -1625,7 +1632,7 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
 	}
 out:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		f2fs_submit_merged_write(sbi, NODE);
 	return ret;
 }
 
@@ -1675,6 +1682,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct blk_plug plug;
 	long diff;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -2192,14 +2202,14 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
 	get_node_info(sbi, prev_xnid, &ni);
 	f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
 	invalidate_blocks(sbi, ni.blk_addr);
-	dec_valid_node_count(sbi, inode);
+	dec_valid_node_count(sbi, inode, false);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
 recover_xnid:
 	/* 2: update xattr nid in inode */
 	remove_free_nid(sbi, new_xnid);
 	f2fs_i_xnid_write(inode, new_xnid);
-	if (unlikely(!inc_valid_node_count(sbi, inode)))
+	if (unlikely(inc_valid_node_count(sbi, inode, false)))
 		f2fs_bug_on(sbi, 1);
 	update_inode_page(inode);
 
@@ -2257,7 +2267,7 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	new_ni = old_ni;
 	new_ni.ino = ino;
 
-	if (unlikely(!inc_valid_node_count(sbi, NULL)))
+	if (unlikely(inc_valid_node_count(sbi, NULL, true)))
 		WARN_ON(1);
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 	inc_valid_inode_count(sbi);
@@ -2424,8 +2434,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 		nid_t nid = nat_get_nid(ne);
 		int offset;
 
-		if (nat_get_blkaddr(ne) == NEW_ADDR)
-			continue;
+		f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR);
 
 		if (to_journal) {
 			offset = lookup_journal_in_cursum(journal,
@@ -2553,7 +2562,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
-inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned int i = 0;

fs/f2fs/node.h

@@ -224,11 +224,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
 	block_addr -= nm_i->nat_blkaddr;
-	if ((block_addr >> sbi->log_blocks_per_seg) % 2)
-		block_addr -= sbi->blocks_per_seg;
-	else
-		block_addr += sbi->blocks_per_seg;
-
+	block_addr ^= 1 << sbi->log_blocks_per_seg;
 	return block_addr + nm_i->nat_blkaddr;
 }
 

fs/f2fs/segment.c

@@ -16,6 +16,7 @@
 #include <linux/kthread.h>
 #include <linux/swap.h>
 #include <linux/timer.h>
+#include <linux/freezer.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -312,7 +313,7 @@ static int __commit_inmem_pages(struct inode *inode,
 			fio.page = page;
 			fio.old_blkaddr = NULL_ADDR;
 			fio.encrypted_page = NULL;
-			fio.need_lock = false,
+			fio.need_lock = LOCK_DONE;
 			err = do_write_data_page(&fio);
 			if (err) {
 				unlock_page(page);
@@ -328,8 +329,7 @@ static int __commit_inmem_pages(struct inode *inode,
 	}
 
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(sbi, inode, 0, last_idx,
-							DATA, WRITE);
+		f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
 
 	if (!err)
 		__revoke_inmem_pages(inode, revoke_list, false, false);
@@ -555,6 +555,8 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 
 	if (SM_I(sbi)->fcc_info) {
 		fcc = SM_I(sbi)->fcc_info;
+		if (fcc->f2fs_issue_flush)
+			return err;
 		goto init_thread;
 	}
 
@@ -566,6 +568,9 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->fcc_info = fcc;
+	if (!test_opt(sbi, FLUSH_MERGE))
+		return err;
+
 init_thread:
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
@@ -736,12 +741,15 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 
+	f2fs_bug_on(sbi, dc->ref);
+
 	if (dc->error == -EOPNOTSUPP)
 		dc->error = 0;
 
 	if (dc->error)
 		f2fs_msg(sbi->sb, KERN_INFO,
-				"Issue discard failed, ret: %d", dc->error);
+			"Issue discard(%u, %u, %u) failed, ret: %d",
+			dc->lstart, dc->start, dc->len, dc->error);
 	__detach_discard_cmd(dcc, dc);
 }
 
@@ -751,10 +759,34 @@ static void f2fs_submit_discard_endio(struct bio *bio)
 
 	dc->error = blk_status_to_errno(bio->bi_status);
 	dc->state = D_DONE;
-	complete(&dc->wait);
+	complete_all(&dc->wait);
 	bio_put(bio);
 }
 
+void __check_sit_bitmap(struct f2fs_sb_info *sbi,
+				block_t start, block_t end)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+	struct seg_entry *sentry;
+	unsigned int segno;
+	block_t blk = start;
+	unsigned long offset, size, max_blocks = sbi->blocks_per_seg;
+	unsigned long *map;
+
+	while (blk < end) {
+		segno = GET_SEGNO(sbi, blk);
+		sentry = get_seg_entry(sbi, segno);
+		offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
+
+		size = min((unsigned long)(end - blk), max_blocks);
+		map = (unsigned long *)(sentry->cur_valid_map);
+		offset = __find_rev_next_bit(map, size, offset);
+		f2fs_bug_on(sbi, offset != size);
+		blk += size;
+	}
+#endif
+}
+
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
 static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
 				struct discard_cmd *dc)
@@ -782,6 +814,7 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
 			bio->bi_opf |= REQ_SYNC;
 			submit_bio(bio);
 			list_move_tail(&dc->list, &dcc->wait_list);
+			__check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
 		}
 	} else {
 		__remove_discard_cmd(sbi, dc);
@@ -838,7 +871,6 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
 		dc->len = blkaddr - dc->lstart;
 		dcc->undiscard_blks += dc->len;
 		__relocate_discard_cmd(dcc, dc);
-		f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
 		modified = true;
 	}
 
@@ -848,16 +880,12 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
 					di.start + blkaddr + 1 - di.lstart,
 					di.lstart + di.len - 1 - blkaddr,
 					NULL, NULL);
-			f2fs_bug_on(sbi,
-				!__check_rb_tree_consistence(sbi, &dcc->root));
 		} else {
 			dc->lstart++;
 			dc->len--;
 			dc->start++;
 			dcc->undiscard_blks += dc->len;
 			__relocate_discard_cmd(dcc, dc);
-			f2fs_bug_on(sbi,
-				!__check_rb_tree_consistence(sbi, &dcc->root));
 		}
 	}
 }
@@ -918,8 +946,6 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 			prev_dc->di.len += di.len;
 			dcc->undiscard_blks += di.len;
 			__relocate_discard_cmd(dcc, prev_dc);
-			f2fs_bug_on(sbi,
-				!__check_rb_tree_consistence(sbi, &dcc->root));
 			di = prev_dc->di;
 			tdc = prev_dc;
 			merged = true;
@@ -935,16 +961,12 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 			__relocate_discard_cmd(dcc, next_dc);
 			if (tdc)
 				__remove_discard_cmd(sbi, tdc);
-			f2fs_bug_on(sbi,
-				!__check_rb_tree_consistence(sbi, &dcc->root));
 			merged = true;
 		}
 
 		if (!merged) {
 			__insert_discard_tree(sbi, bdev, di.lstart, di.start,
 							di.len, NULL, NULL);
-			f2fs_bug_on(sbi,
-				!__check_rb_tree_consistence(sbi, &dcc->root));
 		}
  next:
 		prev_dc = next_dc;
@@ -983,6 +1005,8 @@ static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
 	int i, iter = 0;
 
 	mutex_lock(&dcc->cmd_lock);
+	f2fs_bug_on(sbi,
+		!__check_rb_tree_consistence(sbi, &dcc->root));
 	blk_start_plug(&plug);
 	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
 		pend_list = &dcc->pend_list[i];
@@ -1000,22 +1024,47 @@ static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
 	mutex_unlock(&dcc->cmd_lock);
 }
 
+static void __wait_one_discard_bio(struct f2fs_sb_info *sbi,
+							struct discard_cmd *dc)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	wait_for_completion_io(&dc->wait);
+	mutex_lock(&dcc->cmd_lock);
+	f2fs_bug_on(sbi, dc->state != D_DONE);
+	dc->ref--;
+	if (!dc->ref)
+		__remove_discard_cmd(sbi, dc);
+	mutex_unlock(&dcc->cmd_lock);
+}
+
 static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct list_head *wait_list = &(dcc->wait_list);
 	struct discard_cmd *dc, *tmp;
+	bool need_wait;
+
+next:
+	need_wait = false;
 
 	mutex_lock(&dcc->cmd_lock);
 	list_for_each_entry_safe(dc, tmp, wait_list, list) {
-		if (!wait_cond || dc->state == D_DONE) {
-			if (dc->ref)
-				continue;
+		if (!wait_cond || (dc->state == D_DONE && !dc->ref)) {
 			wait_for_completion_io(&dc->wait);
 			__remove_discard_cmd(sbi, dc);
+		} else {
+			dc->ref++;
+			need_wait = true;
+			break;
 		}
 	}
 	mutex_unlock(&dcc->cmd_lock);
+
+	if (need_wait) {
+		__wait_one_discard_bio(sbi, dc);
+		goto next;
+	}
 }
 
 /* This should be covered by global mutex, &sit_i->sentry_lock */
@@ -1037,14 +1086,19 @@ void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
 	}
 	mutex_unlock(&dcc->cmd_lock);
 
-	if (need_wait) {
-		wait_for_completion_io(&dc->wait);
-		mutex_lock(&dcc->cmd_lock);
-		f2fs_bug_on(sbi, dc->state != D_DONE);
-		dc->ref--;
-		if (!dc->ref)
-			__remove_discard_cmd(sbi, dc);
-		mutex_unlock(&dcc->cmd_lock);
+	if (need_wait)
+		__wait_one_discard_bio(sbi, dc);
+}
+
+void stop_discard_thread(struct f2fs_sb_info *sbi)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	if (dcc && dcc->f2fs_issue_discard) {
+		struct task_struct *discard_thread = dcc->f2fs_issue_discard;
+
+		dcc->f2fs_issue_discard = NULL;
+		kthread_stop(discard_thread);
 	}
 }
 
@@ -1060,7 +1114,15 @@ static int issue_discard_thread(void *data)
 	struct f2fs_sb_info *sbi = data;
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	wait_queue_head_t *q = &dcc->discard_wait_queue;
-repeat:
+
+	set_freezable();
+
+	do {
+		wait_event_interruptible(*q, kthread_should_stop() ||
+					freezing(current) ||
+					atomic_read(&dcc->discard_cmd_cnt));
+		if (try_to_freeze())
+			continue;
 		if (kthread_should_stop())
 			return 0;
 
@@ -1068,10 +1130,8 @@ static int issue_discard_thread(void *data)
 		__wait_discard_cmd(sbi, true);
 
 		congestion_wait(BLK_RW_SYNC, HZ/50);
-
-	wait_event_interruptible(*q, kthread_should_stop() ||
-				atomic_read(&dcc->discard_cmd_cnt));
-	goto repeat;
+	} while (!kthread_should_stop());
+	return 0;
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -1322,7 +1382,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 					sbi->blocks_per_seg, cur_pos);
 			len = next_pos - cur_pos;
 
-			if (force && len < cpc->trim_minlen)
+			if (f2fs_sb_mounted_blkzoned(sbi->sb) ||
+			    (force && len < cpc->trim_minlen))
 				goto skip;
 
 			f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
@@ -1398,12 +1459,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
 	if (!dcc)
 		return;
 
-	if (dcc->f2fs_issue_discard) {
-		struct task_struct *discard_thread = dcc->f2fs_issue_discard;
-
-		dcc->f2fs_issue_discard = NULL;
-		kthread_stop(discard_thread);
-	}
+	stop_discard_thread(sbi);
 
 	kfree(dcc);
 	SM_I(sbi)->dcc_info = NULL;
@@ -2040,66 +2096,80 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 	return false;
 }
 
-static int __get_segment_type_2(struct page *page, enum page_type p_type)
+static int __get_segment_type_2(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA)
+	if (fio->type == DATA)
 		return CURSEG_HOT_DATA;
 	else
 		return CURSEG_HOT_NODE;
 }
 
-static int __get_segment_type_4(struct page *page, enum page_type p_type)
+static int __get_segment_type_4(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA) {
-		struct inode *inode = page->mapping->host;
+	if (fio->type == DATA) {
+		struct inode *inode = fio->page->mapping->host;
 
 		if (S_ISDIR(inode->i_mode))
 			return CURSEG_HOT_DATA;
 		else
 			return CURSEG_COLD_DATA;
 	} else {
-		if (IS_DNODE(page) && is_cold_node(page))
+		if (IS_DNODE(fio->page) && is_cold_node(fio->page))
 			return CURSEG_WARM_NODE;
 		else
 			return CURSEG_COLD_NODE;
 	}
 }
 
-static int __get_segment_type_6(struct page *page, enum page_type p_type)
+static int __get_segment_type_6(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA) {
-		struct inode *inode = page->mapping->host;
+	if (fio->type == DATA) {
+		struct inode *inode = fio->page->mapping->host;
 
-		if (is_cold_data(page) || file_is_cold(inode))
+		if (is_cold_data(fio->page) || file_is_cold(inode))
 			return CURSEG_COLD_DATA;
 		if (is_inode_flag_set(inode, FI_HOT_DATA))
 			return CURSEG_HOT_DATA;
 		return CURSEG_WARM_DATA;
 	} else {
-		if (IS_DNODE(page))
-			return is_cold_node(page) ? CURSEG_WARM_NODE :
+		if (IS_DNODE(fio->page))
+			return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
 						CURSEG_HOT_NODE;
 		return CURSEG_COLD_NODE;
 	}
 }
 
-static int __get_segment_type(struct page *page, enum page_type p_type)
+static int __get_segment_type(struct f2fs_io_info *fio)
 {
-	switch (F2FS_P_SB(page)->active_logs) {
+	int type = 0;
+
+	switch (fio->sbi->active_logs) {
 	case 2:
-		return __get_segment_type_2(page, p_type);
+		type = __get_segment_type_2(fio);
+		break;
 	case 4:
-		return __get_segment_type_4(page, p_type);
+		type = __get_segment_type_4(fio);
+		break;
+	case 6:
+		type = __get_segment_type_6(fio);
+		break;
+	default:
+		f2fs_bug_on(fio->sbi, true);
 	}
-	/* NR_CURSEG_TYPE(6) logs by default */
-	f2fs_bug_on(F2FS_P_SB(page),
-		F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE);
-	return __get_segment_type_6(page, p_type);
+
+	if (IS_HOT(type))
+		fio->temp = HOT;
+	else if (IS_WARM(type))
+		fio->temp = WARM;
+	else
+		fio->temp = COLD;
+	return type;
 }
 
 void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		block_t old_blkaddr, block_t *new_blkaddr,
-		struct f2fs_summary *sum, int type)
+		struct f2fs_summary *sum, int type,
+		struct f2fs_io_info *fio, bool add_list)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -2135,29 +2205,35 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	if (page && IS_NODESEG(type))
 		fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
 
+	if (add_list) {
+		struct f2fs_bio_info *io;
+
+		INIT_LIST_HEAD(&fio->list);
+		fio->in_list = true;
+		io = sbi->write_io[fio->type] + fio->temp;
+		spin_lock(&io->io_lock);
+		list_add_tail(&fio->list, &io->io_list);
+		spin_unlock(&io->io_lock);
+	}
+
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
-	int type = __get_segment_type(fio->page, fio->type);
+	int type = __get_segment_type(fio);
 	int err;
 
-	if (fio->type == NODE || fio->type == DATA)
-		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
 reallocate:
 	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
-					&fio->new_blkaddr, sum, type);
+			&fio->new_blkaddr, sum, type, fio, true);
 
 	/* writeout dirty page into bdev */
-	err = f2fs_submit_page_mbio(fio);
+	err = f2fs_submit_page_write(fio);
 	if (err == -EAGAIN) {
 		fio->old_blkaddr = fio->new_blkaddr;
 		goto reallocate;
 	}
-
-	if (fio->type == NODE || fio->type == DATA)
-		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -2171,13 +2247,14 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 
 	if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
 		fio.op_flags &= ~REQ_META;
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 }
 
 void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -2296,8 +2373,8 @@ void f2fs_wait_on_page_writeback(struct page *page,
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
-						0, page->index, type, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, type);
 		if (ordered)
 			wait_on_page_writeback(page);
 		else
@@ -2455,6 +2532,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 
 static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 {
+	struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal;
+	struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal;
 	int type = CURSEG_HOT_DATA;
 	int err;
 
@@ -2481,6 +2560,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 			return err;
 	}
 
+	/* sanity check for summary blocks */
+	if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
+			sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -3203,7 +3287,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
-	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+	if (!f2fs_readonly(sbi->sb)) {
 		err = create_flush_cmd_control(sbi);
 		if (err)
 			return err;

fs/f2fs/segment.h

@@ -27,6 +27,10 @@
 #define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
 #define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE)
 
+#define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
+#define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
+#define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
+
 #define IS_CURSEG(sbi, seg)						\
 	(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\

fs/f2fs/super.c

@@ -22,6 +22,7 @@
 #include <linux/random.h>
 #include <linux/exportfs.h>
 #include <linux/blkdev.h>
+#include <linux/quotaops.h>
 #include <linux/f2fs_fs.h>
 #include <linux/sysfs.h>
 
@@ -35,9 +36,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
 
-static struct proc_dir_entry *f2fs_proc_root;
 static struct kmem_cache *f2fs_inode_cachep;
-static struct kset *f2fs_kset;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 
@@ -108,6 +107,8 @@ enum {
 	Opt_fault_injection,
 	Opt_lazytime,
 	Opt_nolazytime,
+	Opt_usrquota,
+	Opt_grpquota,
 	Opt_err,
 };
 
@@ -143,212 +144,11 @@ static match_table_t f2fs_tokens = {
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
+	{Opt_usrquota, "usrquota"},
+	{Opt_grpquota, "grpquota"},
 	{Opt_err, NULL},
 };
 
-/* Sysfs support for f2fs */
-enum {
-	GC_THREAD,	/* struct f2fs_gc_thread */
-	SM_INFO,	/* struct f2fs_sm_info */
-	DCC_INFO,	/* struct discard_cmd_control */
-	NM_INFO,	/* struct f2fs_nm_info */
-	F2FS_SBI,	/* struct f2fs_sb_info */
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
-	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
-#endif
-};
-
-struct f2fs_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
-	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
-			 const char *, size_t);
-	int struct_type;
-	int offset;
-};
-
-static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
-{
-	if (struct_type == GC_THREAD)
-		return (unsigned char *)sbi->gc_thread;
-	else if (struct_type == SM_INFO)
-		return (unsigned char *)SM_I(sbi);
-	else if (struct_type == DCC_INFO)
-		return (unsigned char *)SM_I(sbi)->dcc_info;
-	else if (struct_type == NM_INFO)
-		return (unsigned char *)NM_I(sbi);
-	else if (struct_type == F2FS_SBI)
-		return (unsigned char *)sbi;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	else if (struct_type == FAULT_INFO_RATE ||
-					struct_type == FAULT_INFO_TYPE)
-		return (unsigned char *)&sbi->fault_info;
-#endif
-	return NULL;
-}
-
-static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
-		struct f2fs_sb_info *sbi, char *buf)
-{
-	struct super_block *sb = sbi->sb;
-
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
-
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)(sbi->kbytes_written +
-			BD_PART_WRITTEN(sbi)));
-}
-
-static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
-			struct f2fs_sb_info *sbi, char *buf)
-{
-	unsigned char *ptr = NULL;
-	unsigned int *ui;
-
-	ptr = __struct_ptr(sbi, a->struct_type);
-	if (!ptr)
-		return -EINVAL;
-
-	ui = (unsigned int *)(ptr + a->offset);
-
-	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
-}
-
-static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
-			struct f2fs_sb_info *sbi,
-			const char *buf, size_t count)
-{
-	unsigned char *ptr;
-	unsigned long t;
-	unsigned int *ui;
-	ssize_t ret;
-
-	ptr = __struct_ptr(sbi, a->struct_type);
-	if (!ptr)
-		return -EINVAL;
-
-	ui = (unsigned int *)(ptr + a->offset);
-
-	ret = kstrtoul(skip_spaces(buf), 0, &t);
-	if (ret < 0)
-		return ret;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
-		return -EINVAL;
-#endif
-	*ui = t;
-	return count;
-}
-
-static ssize_t f2fs_attr_show(struct kobject *kobj,
-				struct attribute *attr, char *buf)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-								s_kobj);
-	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
-	return a->show ? a->show(a, sbi, buf) : 0;
-}
-
-static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
-						const char *buf, size_t len)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-									s_kobj);
-	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
-	return a->store ? a->store(a, sbi, buf, len) : 0;
-}
-
-static void f2fs_sb_release(struct kobject *kobj)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-								s_kobj);
-	complete(&sbi->s_kobj_unregister);
-}
-
-#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
-static struct f2fs_attr f2fs_attr_##_name = {			\
-	.attr = {.name = __stringify(_name), .mode = _mode },	\
-	.show	= _show,					\
-	.store	= _store,					\
-	.struct_type = _struct_type,				\
-	.offset = _offset					\
-}
-
-#define F2FS_RW_ATTR(struct_type, struct_name, name, elname)	\
-	F2FS_ATTR_OFFSET(struct_type, name, 0644,		\
-		f2fs_sbi_show, f2fs_sbi_store,			\
-		offsetof(struct struct_name, elname))
-
-#define F2FS_GENERAL_RO_ATTR(name) \
-static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
-
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
-F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
-#endif
-F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
-
-#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
-static struct attribute *f2fs_attrs[] = {
-	ATTR_LIST(gc_min_sleep_time),
-	ATTR_LIST(gc_max_sleep_time),
-	ATTR_LIST(gc_no_gc_sleep_time),
-	ATTR_LIST(gc_idle),
-	ATTR_LIST(reclaim_segments),
-	ATTR_LIST(max_small_discards),
-	ATTR_LIST(batched_trim_sections),
-	ATTR_LIST(ipu_policy),
-	ATTR_LIST(min_ipu_util),
-	ATTR_LIST(min_fsync_blocks),
-	ATTR_LIST(min_hot_blocks),
-	ATTR_LIST(max_victim_search),
-	ATTR_LIST(dir_level),
-	ATTR_LIST(ram_thresh),
-	ATTR_LIST(ra_nid_pages),
-	ATTR_LIST(dirty_nats_ratio),
-	ATTR_LIST(cp_interval),
-	ATTR_LIST(idle_interval),
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	ATTR_LIST(inject_rate),
-	ATTR_LIST(inject_type),
-#endif
-	ATTR_LIST(lifetime_write_kbytes),
-	NULL,
-};
-
-static const struct sysfs_ops f2fs_attr_ops = {
-	.show	= f2fs_attr_show,
-	.store	= f2fs_attr_store,
-};
-
-static struct kobj_type f2fs_ktype = {
-	.default_attrs	= f2fs_attrs,
-	.sysfs_ops	= &f2fs_attr_ops,
-	.release	= f2fs_sb_release,
-};
-
 void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -585,6 +385,20 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_nolazytime:
 			sb->s_flags &= ~MS_LAZYTIME;
 			break;
+#ifdef CONFIG_QUOTA
+		case Opt_usrquota:
+			set_opt(sbi, USRQUOTA);
+			break;
+		case Opt_grpquota:
+			set_opt(sbi, GRPQUOTA);
+			break;
+#else
+		case Opt_usrquota:
+		case Opt_grpquota:
+			f2fs_msg(sb, KERN_INFO,
+					"quota operations not supported");
+			break;
+#endif
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -624,7 +438,12 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	mutex_init(&fi->inmem_lock);
 	init_rwsem(&fi->dio_rwsem[READ]);
 	init_rwsem(&fi->dio_rwsem[WRITE]);
+	init_rwsem(&fi->i_mmap_sem);
 
+#ifdef CONFIG_QUOTA
+	memset(&fi->i_dquot, 0, sizeof(fi->i_dquot));
+	fi->i_reserved_quota = 0;
+#endif
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
 	return &fi->vfs_inode;
@@ -765,18 +584,13 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	kfree(sbi->devs);
 }
 
+static void f2fs_quota_off_umount(struct super_block *sb);
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	int i;
 
-	if (sbi->s_proc) {
-		remove_proc_entry("segment_info", sbi->s_proc);
-		remove_proc_entry("segment_bits", sbi->s_proc);
-		remove_proc_entry(sb->s_id, f2fs_proc_root);
-	}
-	kobject_del(&sbi->s_kobj);
-
-	stop_gc_thread(sbi);
+	f2fs_quota_off_umount(sb);
 
 	/* prevent remaining shrinker jobs */
 	mutex_lock(&sbi->umount_mutex);
@@ -797,7 +611,7 @@ static void f2fs_put_super(struct super_block *sb)
 	/* be sure to wait for any on-going discard commands */
 	f2fs_wait_discard_bios(sbi);
 
-	if (!sbi->discard_blks) {
+	if (f2fs_discard_en(sbi) && !sbi->discard_blks) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT | CP_TRIMMED,
 		};
@@ -817,7 +631,7 @@ static void f2fs_put_super(struct super_block *sb)
 	mutex_unlock(&sbi->umount_mutex);
 
 	/* our cp_error case, we can wait for any writeback page */
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
@@ -827,8 +641,8 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_segment_manager(sbi);
 
 	kfree(sbi->ckpt);
-	kobject_put(&sbi->s_kobj);
-	wait_for_completion(&sbi->s_kobj_unregister);
+
+	f2fs_exit_sysfs(sbi);
 
 	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
@@ -838,6 +652,8 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_device_list(sbi);
 	mempool_destroy(sbi->write_io_dummy);
 	destroy_percpu_info(sbi);
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	kfree(sbi);
 }
 
@@ -888,6 +704,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 	block_t total_count, user_block_count, start_count, ovp_count;
+	u64 avail_node_count;
 
 	total_count = le64_to_cpu(sbi->raw_super->block_count);
 	user_block_count = sbi->user_block_count;
@@ -898,11 +715,19 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_blocks = total_count - start_count;
 	buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
-	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
+	buf->f_bavail = user_block_count - valid_user_blocks(sbi) -
+						sbi->reserved_blocks;
 
-	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
-	buf->f_ffree = min(buf->f_files - valid_node_count(sbi),
+	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
+
+	if (avail_node_count > user_block_count) {
+		buf->f_files = user_block_count;
+		buf->f_ffree = buf->f_bavail;
+	} else {
+		buf->f_files = avail_node_count;
+		buf->f_ffree = min(avail_node_count - valid_node_count(sbi),
 					buf->f_bavail);
+	}
 
 	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
@@ -980,79 +805,19 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (test_opt(sbi, FAULT_INJECTION))
-		seq_puts(seq, ",fault_injection");
+		seq_printf(seq, ",fault_injection=%u",
+				sbi->fault_info.inject_rate);
+#endif
+#ifdef CONFIG_QUOTA
+	if (test_opt(sbi, USRQUOTA))
+		seq_puts(seq, ",usrquota");
+	if (test_opt(sbi, GRPQUOTA))
+		seq_puts(seq, ",grpquota");
 #endif
 
 	return 0;
 }
 
-static int segment_info_seq_show(struct seq_file *seq, void *offset)
-{
-	struct super_block *sb = seq->private;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	unsigned int total_segs =
-			le32_to_cpu(sbi->raw_super->segment_count_main);
-	int i;
-
-	seq_puts(seq, "format: segment_type|valid_blocks\n"
-		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
-	for (i = 0; i < total_segs; i++) {
-		struct seg_entry *se = get_seg_entry(sbi, i);
-
-		if ((i % 10) == 0)
-			seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u", se->type,
-					get_valid_blocks(sbi, i, false));
-		if ((i % 10) == 9 || i == (total_segs - 1))
-			seq_putc(seq, '\n');
-		else
-			seq_putc(seq, ' ');
-	}
-
-	return 0;
-}
-
-static int segment_bits_seq_show(struct seq_file *seq, void *offset)
-{
-	struct super_block *sb = seq->private;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	unsigned int total_segs =
-			le32_to_cpu(sbi->raw_super->segment_count_main);
-	int i, j;
-
-	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
-		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
-	for (i = 0; i < total_segs; i++) {
-		struct seg_entry *se = get_seg_entry(sbi, i);
-
-		seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u|", se->type,
-					get_valid_blocks(sbi, i, false));
-		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
-			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
-		seq_putc(seq, '\n');
-	}
-	return 0;
-}
-
-#define F2FS_PROC_FILE_DEF(_name)					\
-static int _name##_open_fs(struct inode *inode, struct file *file)	\
-{									\
-	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
-}									\
-									\
-static const struct file_operations f2fs_seq_##_name##_fops = {		\
-	.open = _name##_open_fs,					\
-	.read = seq_read,						\
-	.llseek = seq_lseek,						\
-	.release = single_release,					\
-};
-
-F2FS_PROC_FILE_DEF(segment_info);
-F2FS_PROC_FILE_DEF(segment_bits);
-
 static void default_options(struct f2fs_sb_info *sbi)
 {
 	/* init some FS parameters */
@@ -1089,6 +854,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct f2fs_mount_info org_mount_opt;
+	unsigned long old_sb_flags;
 	int err, active_logs;
 	bool need_restart_gc = false;
 	bool need_stop_gc = false;
@@ -1102,6 +868,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * need to restore them.
 	 */
 	org_mount_opt = sbi->mount_opt;
+	old_sb_flags = sb->s_flags;
 	active_logs = sbi->active_logs;
 
 	/* recover superblocks we couldn't write due to previous RO mount */
@@ -1113,7 +880,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 	}
 
-	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
 	/* parse mount options */
@@ -1128,6 +894,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
 		goto skip;
 
+	if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) {
+		err = dquot_suspend(sb, -1);
+		if (err < 0)
+			goto restore_opts;
+	} else {
+		/* dquot_resume needs RW */
+		sb->s_flags &= ~MS_RDONLY;
+		dquot_resume(sb, -1);
+	}
+
 	/* disallow enable/disable extent_cache dynamically */
 	if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
 		err = -EINVAL;
@@ -1192,12 +968,237 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 restore_opts:
 	sbi->mount_opt = org_mount_opt;
 	sbi->active_logs = active_logs;
+	sb->s_flags = old_sb_flags;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	sbi->fault_info = ffi;
 #endif
 	return err;
 }
 
+#ifdef CONFIG_QUOTA
+/* Read data from quotafile */
+static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
+			       size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	struct address_space *mapping = inode->i_mapping;
+	block_t blkidx = F2FS_BYTES_TO_BLK(off);
+	int offset = off & (sb->s_blocksize - 1);
+	int tocopy;
+	size_t toread;
+	loff_t i_size = i_size_read(inode);
+	struct page *page;
+	char *kaddr;
+
+	if (off > i_size)
+		return 0;
+
+	if (off + len > i_size)
+		len = i_size - off;
+	toread = len;
+	while (toread > 0) {
+		tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread);
+repeat:
+		page = read_mapping_page(mapping, blkidx, NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+
+		lock_page(page);
+
+		if (unlikely(page->mapping != mapping)) {
+			f2fs_put_page(page, 1);
+			goto repeat;
+		}
+		if (unlikely(!PageUptodate(page))) {
+			f2fs_put_page(page, 1);
+			return -EIO;
+		}
+
+		kaddr = kmap_atomic(page);
+		memcpy(data, kaddr + offset, tocopy);
+		kunmap_atomic(kaddr);
+		f2fs_put_page(page, 1);
+
+		offset = 0;
+		toread -= tocopy;
+		data += tocopy;
+		blkidx++;
+	}
+	return len;
+}
+
+/* Write to quotafile */
+static ssize_t f2fs_quota_write(struct super_block *sb, int type,
+				const char *data, size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	struct address_space *mapping = inode->i_mapping;
+	const struct address_space_operations *a_ops = mapping->a_ops;
+	int offset = off & (sb->s_blocksize - 1);
+	size_t towrite = len;
+	struct page *page;
+	char *kaddr;
+	int err = 0;
+	int tocopy;
+
+	while (towrite > 0) {
+		tocopy = min_t(unsigned long, sb->s_blocksize - offset,
+								towrite);
+
+		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
+							&page, NULL);
+		if (unlikely(err))
+			break;
+
+		kaddr = kmap_atomic(page);
+		memcpy(kaddr + offset, data, tocopy);
+		kunmap_atomic(kaddr);
+		flush_dcache_page(page);
+
+		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
+						page, NULL);
+		offset = 0;
+		towrite -= tocopy;
+		off += tocopy;
+		data += tocopy;
+		cond_resched();
+	}
+
+	if (len == towrite)
+		return err;
+	inode->i_version++;
+	inode->i_mtime = inode->i_ctime = current_time(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+	return len - towrite;
+}
+
+static struct dquot **f2fs_get_dquots(struct inode *inode)
+{
+	return F2FS_I(inode)->i_dquot;
+}
+
+static qsize_t *f2fs_get_reserved_space(struct inode *inode)
+{
+	return &F2FS_I(inode)->i_reserved_quota;
+}
+
+static int f2fs_quota_sync(struct super_block *sb, int type)
+{
+	struct quota_info *dqopt = sb_dqopt(sb);
+	int cnt;
+	int ret;
+
+	ret = dquot_writeback_dquots(sb, type);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now when everything is written we can discard the pagecache so
+	 * that userspace sees the changes.
+	 */
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+		if (type != -1 && cnt != type)
+			continue;
+		if (!sb_has_quota_active(sb, cnt))
+			continue;
+
+		ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping);
+		if (ret)
+			return ret;
+
+		inode_lock(dqopt->files[cnt]);
+		truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+		inode_unlock(dqopt->files[cnt]);
+	}
+	return 0;
+}
+
+static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
+							const struct path *path)
+{
+	struct inode *inode;
+	int err;
+
+	err = f2fs_quota_sync(sb, -1);
+	if (err)
+		return err;
+
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		return err;
+
+	inode = d_inode(path->dentry);
+
+	inode_lock(inode);
+	F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL;
+	inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+					S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+
+	return 0;
+}
+
+static int f2fs_quota_off(struct super_block *sb, int type)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	int err;
+
+	if (!inode || !igrab(inode))
+		return dquot_quota_off(sb, type);
+
+	f2fs_quota_sync(sb, -1);
+
+	err = dquot_quota_off(sb, type);
+	if (err)
+		goto out_put;
+
+	inode_lock(inode);
+	F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL);
+	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+out_put:
+	iput(inode);
+	return err;
+}
+
+static void f2fs_quota_off_umount(struct super_block *sb)
+{
+	int type;
+
+	for (type = 0; type < MAXQUOTAS; type++)
+		f2fs_quota_off(sb, type);
+}
+
+static const struct dquot_operations f2fs_quota_operations = {
+	.get_reserved_space = f2fs_get_reserved_space,
+	.write_dquot	= dquot_commit,
+	.acquire_dquot	= dquot_acquire,
+	.release_dquot	= dquot_release,
+	.mark_dirty	= dquot_mark_dquot_dirty,
+	.write_info	= dquot_commit_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
+};
+
+static const struct quotactl_ops f2fs_quotactl_ops = {
+	.quota_on	= f2fs_quota_on,
+	.quota_off	= f2fs_quota_off,
+	.quota_sync	= f2fs_quota_sync,
+	.get_state	= dquot_get_state,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
+};
+#else
+static inline void f2fs_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
 static struct super_operations f2fs_sops = {
 	.alloc_inode	= f2fs_alloc_inode,
 	.drop_inode	= f2fs_drop_inode,
@@ -1205,6 +1206,11 @@ static struct super_operations f2fs_sops = {
 	.write_inode	= f2fs_write_inode,
 	.dirty_inode	= f2fs_dirty_inode,
 	.show_options	= f2fs_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= f2fs_quota_read,
+	.quota_write	= f2fs_quota_write,
+	.get_dquots	= f2fs_get_dquots,
+#endif
 	.evict_inode	= f2fs_evict_inode,
 	.put_super	= f2fs_put_super,
 	.sync_fs	= f2fs_sync_fs,
@@ -1521,6 +1527,8 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned int ovp_segments, reserved_segments;
+	unsigned int main_segs, blocks_per_seg;
+	int i;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1542,6 +1550,20 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}
 
+	main_segs = le32_to_cpu(raw_super->segment_count_main);
+	blocks_per_seg = sbi->blocks_per_seg;
+
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+	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 (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -1552,7 +1574,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 static void init_sb_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = sbi->raw_super;
-	int i;
+	int i, j;
 
 	sbi->log_sectors_per_block =
 		le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1584,8 +1606,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
-	mutex_init(&sbi->wio_mutex[NODE]);
-	mutex_init(&sbi->wio_mutex[DATA]);
+	for (i = 0; i < NR_PAGE_TYPE - 1; i++)
+		for (j = HOT; j < NR_TEMP_TYPE; j++)
+			mutex_init(&sbi->wio_mutex[i][j]);
 	spin_lock_init(&sbi->cp_lock);
 }
 
@@ -1908,6 +1931,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (f2fs_sb_mounted_blkzoned(sb)) {
 		f2fs_msg(sb, KERN_ERR,
 			 "Zoned block device support is not enabled\n");
+		err = -EOPNOTSUPP;
 		goto free_sb_buf;
 	}
 #endif
@@ -1929,6 +1953,12 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_max_links = F2FS_LINK_MAX;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
+#ifdef CONFIG_QUOTA
+	sb->dq_op = &f2fs_quota_operations;
+	sb->s_qcop = &f2fs_quotactl_ops;
+	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+#endif
+
 	sb->s_op = &f2fs_sops;
 	sb->s_cop = &f2fs_cryptops;
 	sb->s_xattr = f2fs_xattr_handlers;
@@ -1950,13 +1980,24 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	set_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
-	init_rwsem(&sbi->read_io.io_rwsem);
-	sbi->read_io.sbi = sbi;
-	sbi->read_io.bio = NULL;
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		init_rwsem(&sbi->write_io[i].io_rwsem);
-		sbi->write_io[i].sbi = sbi;
-		sbi->write_io[i].bio = NULL;
+		int n = (i == META) ? 1: NR_TEMP_TYPE;
+		int j;
+
+		sbi->write_io[i] = kmalloc(n * sizeof(struct f2fs_bio_info),
+								GFP_KERNEL);
+		if (!sbi->write_io[i]) {
+			err = -ENOMEM;
+			goto free_options;
+		}
+
+		for (j = HOT; j < n; j++) {
+			init_rwsem(&sbi->write_io[i][j].io_rwsem);
+			sbi->write_io[i][j].sbi = sbi;
+			sbi->write_io[i][j].bio = NULL;
+			spin_lock_init(&sbi->write_io[i][j].io_lock);
+			INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
+		}
 	}
 
 	init_rwsem(&sbi->cp_rwsem);
@@ -1970,9 +2011,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (F2FS_IO_SIZE(sbi) > 1) {
 		sbi->write_io_dummy =
 			mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
-		if (!sbi->write_io_dummy)
+		if (!sbi->write_io_dummy) {
+			err = -ENOMEM;
 			goto free_options;
 		}
+	}
 
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
@@ -2003,6 +2046,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->total_valid_block_count =
 				le64_to_cpu(sbi->ckpt->valid_block_count);
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
+	sbi->reserved_blocks = 0;
 
 	for (i = 0; i < NR_INODE_TYPE; i++) {
 		INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -2078,22 +2122,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_root_inode;
 	}
 
-	if (f2fs_proc_root)
-		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
-
-	if (sbi->s_proc) {
-		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_info_fops, sb);
-		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_bits_fops, sb);
-	}
-
-	sbi->s_kobj.kset = f2fs_kset;
-	init_completion(&sbi->s_kobj_unregister);
-	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
-							"%s", sb->s_id);
+	err = f2fs_init_sysfs(sbi);
 	if (err)
-		goto free_proc;
+		goto free_root_inode;
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
@@ -2104,7 +2135,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		if (bdev_read_only(sb->s_bdev) &&
 				!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
 			err = -EROFS;
-			goto free_kobj;
+			goto free_sysfs;
 		}
 
 		if (need_fsck)
@@ -2118,7 +2149,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 			need_fsck = true;
 			f2fs_msg(sb, KERN_ERR,
 				"Cannot recover all fsync data errno=%d", err);
-			goto free_kobj;
+			goto free_sysfs;
 		}
 	} else {
 		err = recover_fsync_data(sbi, true);
@@ -2127,7 +2158,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 			err = -EINVAL;
 			f2fs_msg(sb, KERN_ERR,
 				"Need to recover fsync data");
-			goto free_kobj;
+			goto free_sysfs;
 		}
 	}
 skip_recovery:
@@ -2142,7 +2173,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		/* After POR, we can run background GC thread.*/
 		err = start_gc_thread(sbi);
 		if (err)
-			goto free_kobj;
+			goto free_sysfs;
 	}
 	kfree(options);
 
@@ -2160,17 +2191,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	f2fs_update_time(sbi, REQ_TIME);
 	return 0;
 
-free_kobj:
+free_sysfs:
 	f2fs_sync_inode_meta(sbi);
-	kobject_del(&sbi->s_kobj);
-	kobject_put(&sbi->s_kobj);
-	wait_for_completion(&sbi->s_kobj_unregister);
-free_proc:
-	if (sbi->s_proc) {
-		remove_proc_entry("segment_info", sbi->s_proc);
-		remove_proc_entry("segment_bits", sbi->s_proc);
-		remove_proc_entry(sb->s_id, f2fs_proc_root);
-	}
+	f2fs_exit_sysfs(sbi);
 free_root_inode:
 	dput(sb->s_root);
 	sb->s_root = NULL;
@@ -2202,6 +2225,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 free_io_dummy:
 	mempool_destroy(sbi->write_io_dummy);
 free_options:
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	destroy_percpu_info(sbi);
 	kfree(options);
 free_sb_buf:
@@ -2228,8 +2253,11 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 
 static void kill_f2fs_super(struct super_block *sb)
 {
-	if (sb->s_root)
+	if (sb->s_root) {
 		set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+		stop_gc_thread(F2FS_SB(sb));
+		stop_discard_thread(F2FS_SB(sb));
+	}
 	kill_block_super(sb);
 }
 
@@ -2283,30 +2311,26 @@ static int __init init_f2fs_fs(void)
 	err = create_extent_cache();
 	if (err)
 		goto free_checkpoint_caches;
-	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
-	if (!f2fs_kset) {
-		err = -ENOMEM;
+	err = f2fs_register_sysfs();
+	if (err)
 		goto free_extent_cache;
-	}
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
-		goto free_kset;
-
+		goto free_sysfs;
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
 		goto free_shrinker;
 	err = f2fs_create_root_stats();
 	if (err)
 		goto free_filesystem;
-	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
 	return 0;
 
 free_filesystem:
 	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
-free_kset:
-	kset_unregister(f2fs_kset);
+free_sysfs:
+	f2fs_unregister_sysfs();
 free_extent_cache:
 	destroy_extent_cache();
 free_checkpoint_caches:
@@ -2323,11 +2347,10 @@ static int __init init_f2fs_fs(void)
 
 static void __exit exit_f2fs_fs(void)
 {
-	remove_proc_entry("fs/f2fs", NULL);
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	unregister_shrinker(&f2fs_shrinker_info);
-	kset_unregister(f2fs_kset);
+	f2fs_unregister_sysfs();
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();

fs/f2fs/sysfs.c

+/*
+ * f2fs sysfs interface
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ * Copyright (c) 2017 Chao Yu <chao@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/proc_fs.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "segment.h"
+#include "gc.h"
+
+static struct proc_dir_entry *f2fs_proc_root;
+static struct kset *f2fs_kset;
+
+/* Sysfs support for f2fs */
+enum {
+	GC_THREAD,	/* struct f2fs_gc_thread */
+	SM_INFO,	/* struct f2fs_sm_info */
+	DCC_INFO,	/* struct discard_cmd_control */
+	NM_INFO,	/* struct f2fs_nm_info */
+	F2FS_SBI,	/* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
+	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
+#endif
+	RESERVED_BLOCKS,
+};
+
+struct f2fs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
+	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
+			 const char *, size_t);
+	int struct_type;
+	int offset;
+};
+
+static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
+{
+	if (struct_type == GC_THREAD)
+		return (unsigned char *)sbi->gc_thread;
+	else if (struct_type == SM_INFO)
+		return (unsigned char *)SM_I(sbi);
+	else if (struct_type == DCC_INFO)
+		return (unsigned char *)SM_I(sbi)->dcc_info;
+	else if (struct_type == NM_INFO)
+		return (unsigned char *)NM_I(sbi);
+	else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS)
+		return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	else if (struct_type == FAULT_INFO_RATE ||
+					struct_type == FAULT_INFO_TYPE)
+		return (unsigned char *)&sbi->fault_info;
+#endif
+	return NULL;
+}
+
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(sbi->kbytes_written +
+			BD_PART_WRITTEN(sbi)));
+}
+
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi, char *buf)
+{
+	unsigned char *ptr = NULL;
+	unsigned int *ui;
+
+	ptr = __struct_ptr(sbi, a->struct_type);
+	if (!ptr)
+		return -EINVAL;
+
+	ui = (unsigned int *)(ptr + a->offset);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi,
+			const char *buf, size_t count)
+{
+	unsigned char *ptr;
+	unsigned long t;
+	unsigned int *ui;
+	ssize_t ret;
+
+	ptr = __struct_ptr(sbi, a->struct_type);
+	if (!ptr)
+		return -EINVAL;
+
+	ui = (unsigned int *)(ptr + a->offset);
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret < 0)
+		return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+		return -EINVAL;
+#endif
+	if (a->struct_type == RESERVED_BLOCKS) {
+		spin_lock(&sbi->stat_lock);
+		if ((unsigned long)sbi->total_valid_block_count + t >
+				(unsigned long)sbi->user_block_count) {
+			spin_unlock(&sbi->stat_lock);
+			return -EINVAL;
+		}
+		*ui = t;
+		spin_unlock(&sbi->stat_lock);
+		return count;
+	}
+	*ui = t;
+	return count;
+}
+
+static ssize_t f2fs_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
+						const char *buf, size_t len)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+									s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void f2fs_sb_release(struct kobject *kobj)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	complete(&sbi->s_kobj_unregister);
+}
+
+#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
+static struct f2fs_attr f2fs_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.show	= _show,					\
+	.store	= _store,					\
+	.struct_type = _struct_type,				\
+	.offset = _offset					\
+}
+
+#define F2FS_RW_ATTR(struct_type, struct_name, name, elname)	\
+	F2FS_ATTR_OFFSET(struct_type, name, 0644,		\
+		f2fs_sbi_show, f2fs_sbi_store,			\
+		offsetof(struct struct_name, elname))
+
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
+F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
+
+#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
+static struct attribute *f2fs_attrs[] = {
+	ATTR_LIST(gc_min_sleep_time),
+	ATTR_LIST(gc_max_sleep_time),
+	ATTR_LIST(gc_no_gc_sleep_time),
+	ATTR_LIST(gc_idle),
+	ATTR_LIST(reclaim_segments),
+	ATTR_LIST(max_small_discards),
+	ATTR_LIST(batched_trim_sections),
+	ATTR_LIST(ipu_policy),
+	ATTR_LIST(min_ipu_util),
+	ATTR_LIST(min_fsync_blocks),
+	ATTR_LIST(min_hot_blocks),
+	ATTR_LIST(max_victim_search),
+	ATTR_LIST(dir_level),
+	ATTR_LIST(ram_thresh),
+	ATTR_LIST(ra_nid_pages),
+	ATTR_LIST(dirty_nats_ratio),
+	ATTR_LIST(cp_interval),
+	ATTR_LIST(idle_interval),
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	ATTR_LIST(inject_rate),
+	ATTR_LIST(inject_type),
+#endif
+	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(reserved_blocks),
+	NULL,
+};
+
+static const struct sysfs_ops f2fs_attr_ops = {
+	.show	= f2fs_attr_show,
+	.store	= f2fs_attr_store,
+};
+
+static struct kobj_type f2fs_ktype = {
+	.default_attrs	= f2fs_attrs,
+	.sysfs_ops	= &f2fs_attr_ops,
+	.release	= f2fs_sb_release,
+};
+
+static int segment_info_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs =
+			le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i;
+
+	seq_puts(seq, "format: segment_type|valid_blocks\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+	for (i = 0; i < total_segs; i++) {
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		if ((i % 10) == 0)
+			seq_printf(seq, "%-10d", i);
+		seq_printf(seq, "%d|%-3u", se->type,
+					get_valid_blocks(sbi, i, false));
+		if ((i % 10) == 9 || i == (total_segs - 1))
+			seq_putc(seq, '\n');
+		else
+			seq_putc(seq, ' ');
+	}
+
+	return 0;
+}
+
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs =
+			le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i, j;
+
+	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+	for (i = 0; i < total_segs; i++) {
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		seq_printf(seq, "%-10d", i);
+		seq_printf(seq, "%d|%-3u|", se->type,
+					get_valid_blocks(sbi, i, false));
+		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+		seq_putc(seq, '\n');
+	}
+	return 0;
+}
+
+#define F2FS_PROC_FILE_DEF(_name)					\
+static int _name##_open_fs(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
+}									\
+									\
+static const struct file_operations f2fs_seq_##_name##_fops = {		\
+	.open = _name##_open_fs,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+	.release = single_release,					\
+};
+
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
+int __init f2fs_register_sysfs(void)
+{
+	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+
+	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
+	if (!f2fs_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+void f2fs_unregister_sysfs(void)
+{
+	kset_unregister(f2fs_kset);
+	remove_proc_entry("fs/f2fs", NULL);
+}
+
+int f2fs_init_sysfs(struct f2fs_sb_info *sbi)
+{
+	struct super_block *sb = sbi->sb;
+	int err;
+
+	if (f2fs_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
+
+	if (sbi->s_proc) {
+		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_info_fops, sb);
+		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_bits_fops, sb);
+	}
+
+	sbi->s_kobj.kset = f2fs_kset;
+	init_completion(&sbi->s_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
+							"%s", sb->s_id);
+	if (err)
+		goto err_out;
+	return 0;
+err_out:
+	if (sbi->s_proc) {
+		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
+		remove_proc_entry(sb->s_id, f2fs_proc_root);
+	}
+	return err;
+}
+
+void f2fs_exit_sysfs(struct f2fs_sb_info *sbi)
+{
+	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
+
+	if (sbi->s_proc) {
+		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
+		remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
+	}
+}

include/trace/events/f2fs.h

@@ -19,6 +19,9 @@ TRACE_DEFINE_ENUM(INMEM_INVALIDATE);
 TRACE_DEFINE_ENUM(INMEM_REVOKE);
 TRACE_DEFINE_ENUM(IPU);
 TRACE_DEFINE_ENUM(OPU);
+TRACE_DEFINE_ENUM(HOT);
+TRACE_DEFINE_ENUM(WARM);
+TRACE_DEFINE_ENUM(COLD);
 TRACE_DEFINE_ENUM(CURSEG_HOT_DATA);
 TRACE_DEFINE_ENUM(CURSEG_WARM_DATA);
 TRACE_DEFINE_ENUM(CURSEG_COLD_DATA);
@@ -59,6 +62,12 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ IPU,		"IN-PLACE" },				\
 		{ OPU,		"OUT-OF-PLACE" })
 
+#define show_block_temp(temp)						\
+	__print_symbolic(temp,						\
+		{ HOT,		"HOT" },				\
+		{ WARM,		"WARM" },				\
+		{ COLD,		"COLD" })
+
 #define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_META | REQ_PRIO |	\
 			REQ_PREFLUSH | REQ_FUA)
 #define F2FS_BIO_FLAG_MASK(t)	(t & F2FS_OP_FLAGS)
@@ -757,6 +766,7 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__field(block_t, new_blkaddr)
 		__field(int, op)
 		__field(int, op_flags)
+		__field(int, temp)
 		__field(int, type)
 	),
 
@@ -768,16 +778,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__entry->new_blkaddr	= fio->new_blkaddr;
 		__entry->op		= fio->op;
 		__entry->op_flags	= fio->op_flags;
+		__entry->temp		= fio->temp;
 		__entry->type		= fio->type;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s",
+		"oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s_%s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
 		(unsigned long long)__entry->old_blkaddr,
 		(unsigned long long)__entry->new_blkaddr,
 		show_bio_type(__entry->op, __entry->op_flags),
+		show_block_temp(__entry->temp),
 		show_block_type(__entry->type))
 );
 
@@ -790,7 +802,7 @@ DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
 	TP_CONDITION(page->mapping)
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_write,
 
 	TP_PROTO(struct page *page, struct f2fs_io_info *fio),