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

…l/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" <[email protected]>
 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" <[email protected]>
 Description:
@@ -112,3 +112,21 @@ Date:		January 2016
 Contact:	"Shuoran Liu" <[email protected]>
 Description:
 		 Shows total written kbytes issued to disk.
+
+What:		/sys/fs/f2fs/<disk>/inject_rate
+Date:		May 2016
+Contact:	"Sheng Yong" <[email protected]>
+Description:
+		 Controls the injection rate.
+
+What:		/sys/fs/f2fs/<disk>/inject_type
+Date:		May 2016
+Contact:	"Sheng Yong" <[email protected]>
+Description:
+		 Controls the injection type.
+
+What:		/sys/fs/f2fs/<disk>/reserved_blocks
+Date:		June 2017
+Contact:	"Chao Yu" <[email protected]>
+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) {