Merge tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch series contains several performance tuning patches
  regarding to the IO submission flow, in addition to supporting new
  features such as a ZBC-base drive and multiple devices.

  It also includes some major bug fixes such as:
   - checkpoint version control
   - fdatasync-related roll-forward recovery routine
   - memory boundary or null-pointer access in corner cases
   - missing error cases

  It has various minor clean-up patches as well"

* tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (66 commits)
  f2fs: fix a missing size change in f2fs_setattr
  f2fs: fix to access nullified flush_cmd_control pointer
  f2fs: free meta pages if sanity check for ckpt is failed
  f2fs: detect wrong layout
  f2fs: call sync_fs when f2fs is idle
  Revert "f2fs: use percpu_counter for # of dirty pages in inode"
  f2fs: return AOP_WRITEPAGE_ACTIVATE for writepage
  f2fs: do not activate auto_recovery for fallocated i_size
  f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
  f2fs: fix 32-bit build
  f2fs: set ->owner for debugfs status file's file_operations
  f2fs: fix incorrect free inode count in ->statfs
  f2fs: drop duplicate header timer.h
  f2fs: fix wrong AUTO_RECOVER condition
  f2fs: do not recover i_size if it's valid
  f2fs: fix fdatasync
  f2fs: fix to account total free nid correctly
  f2fs: fix an infinite loop when flush nodes in cp
  f2fs: don't wait writeback for datas during checkpoint
  f2fs: fix wrong written_valid_blocks counting
  ...

1 files changed, 241 insertions, 40 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2cac6bb..702638e 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -412,14 +412,20 @@ static int parse_options(struct super_block *sb, char *options)
 			q = bdev_get_queue(sb->s_bdev);
 			if (blk_queue_discard(q)) {
 				set_opt(sbi, DISCARD);
-			} else {
+			} else if (!f2fs_sb_mounted_blkzoned(sb)) {
 				f2fs_msg(sb, KERN_WARNING,
 					"mounting with \"discard\" option, but "
 					"the device does not support discard");
 			}
 			break;
 		case Opt_nodiscard:
+			if (f2fs_sb_mounted_blkzoned(sb)) {
+				f2fs_msg(sb, KERN_WARNING,
+					"discard is required for zoned block devices");
+				return -EINVAL;
+			}
 			clear_opt(sbi, DISCARD);
+			break;
 		case Opt_noheap:
 			set_opt(sbi, NOHEAP);
 			break;
@@ -512,6 +518,13 @@ static int parse_options(struct super_block *sb, char *options)
 				return -ENOMEM;
 			if (strlen(name) == 8 &&
 					!strncmp(name, "adaptive", 8)) {
+				if (f2fs_sb_mounted_blkzoned(sb)) {
+					f2fs_msg(sb, KERN_WARNING,
+						 "adaptive mode is not allowed with "
+						 "zoned block device feature");
+					kfree(name);
+					return -EINVAL;
+				}
 				set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
 			} else if (strlen(name) == 3 &&
 					!strncmp(name, "lfs", 3)) {
@@ -558,13 +571,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	init_once((void *) fi);
 
-	if (percpu_counter_init(&fi->dirty_pages, 0, GFP_NOFS)) {
-		kmem_cache_free(f2fs_inode_cachep, fi);
-		return NULL;
-	}
-
 	/* Initialize f2fs-specific inode info */
 	fi->vfs_inode.i_version = 1;
+	atomic_set(&fi->dirty_pages, 0);
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
@@ -620,24 +629,25 @@ static int f2fs_drop_inode(struct inode *inode)
 	return generic_drop_inode(inode);
 }
 
-int f2fs_inode_dirtied(struct inode *inode)
+int f2fs_inode_dirtied(struct inode *inode, bool sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	int ret = 0;
 
 	spin_lock(&sbi->inode_lock[DIRTY_META]);
 	if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
-		spin_unlock(&sbi->inode_lock[DIRTY_META]);
-		return 1;
+		ret = 1;
+	} else {
+		set_inode_flag(inode, FI_DIRTY_INODE);
+		stat_inc_dirty_inode(sbi, DIRTY_META);
 	}
-
-	set_inode_flag(inode, FI_DIRTY_INODE);
-	list_add_tail(&F2FS_I(inode)->gdirty_list,
+	if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) {
+		list_add_tail(&F2FS_I(inode)->gdirty_list,
 				&sbi->inode_list[DIRTY_META]);
-	inc_page_count(sbi, F2FS_DIRTY_IMETA);
-	stat_inc_dirty_inode(sbi, DIRTY_META);
+		inc_page_count(sbi, F2FS_DIRTY_IMETA);
+	}
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
-
-	return 0;
+	return ret;
 }
 
 void f2fs_inode_synced(struct inode *inode)
@@ -649,10 +659,12 @@ void f2fs_inode_synced(struct inode *inode)
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
 		return;
 	}
-	list_del_init(&F2FS_I(inode)->gdirty_list);
+	if (!list_empty(&F2FS_I(inode)->gdirty_list)) {
+		list_del_init(&F2FS_I(inode)->gdirty_list);
+		dec_page_count(sbi, F2FS_DIRTY_IMETA);
+	}
 	clear_inode_flag(inode, FI_DIRTY_INODE);
 	clear_inode_flag(inode, FI_AUTO_RECOVER);
-	dec_page_count(sbi, F2FS_DIRTY_IMETA);
 	stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
 }
@@ -676,7 +688,7 @@ static void f2fs_dirty_inode(struct inode *inode, int flags)
 	if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
 		clear_inode_flag(inode, FI_AUTO_RECOVER);
 
-	f2fs_inode_dirtied(inode);
+	f2fs_inode_dirtied(inode, false);
 }
 
 static void f2fs_i_callback(struct rcu_head *head)
@@ -687,20 +699,28 @@ static void f2fs_i_callback(struct rcu_head *head)
 
 static void f2fs_destroy_inode(struct inode *inode)
 {
-	percpu_counter_destroy(&F2FS_I(inode)->dirty_pages);
 	call_rcu(&inode->i_rcu, f2fs_i_callback);
 }
 
 static void destroy_percpu_info(struct f2fs_sb_info *sbi)
 {
-	int i;
-
-	for (i = 0; i < NR_COUNT_TYPE; i++)
-		percpu_counter_destroy(&sbi->nr_pages[i]);
 	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	percpu_counter_destroy(&sbi->total_valid_inode_count);
 }
 
+static void destroy_device_list(struct f2fs_sb_info *sbi)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		blkdev_put(FDEV(i).bdev, FMODE_EXCL);
+#ifdef CONFIG_BLK_DEV_ZONED
+		kfree(FDEV(i).blkz_type);
+#endif
+	}
+	kfree(sbi->devs);
+}
+
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -738,7 +758,6 @@ static void f2fs_put_super(struct super_block *sb)
 	 * In addition, EIO will skip do checkpoint, we need this as well.
 	 */
 	release_ino_entry(sbi, true);
-	release_discard_addrs(sbi);
 
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
@@ -762,6 +781,8 @@ static void f2fs_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 
+	destroy_device_list(sbi);
+
 	destroy_percpu_info(sbi);
 	kfree(sbi);
 }
@@ -789,13 +810,17 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 
 static int f2fs_freeze(struct super_block *sb)
 {
-	int err;
-
 	if (f2fs_readonly(sb))
 		return 0;
 
-	err = f2fs_sync_fs(sb, 1);
-	return err;
+	/* IO error happened before */
+	if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+		return -EIO;
+
+	/* must be clean, since sync_filesystem() was already called */
+	if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+		return -EINVAL;
+	return 0;
 }
 
 static int f2fs_unfreeze(struct super_block *sb)
@@ -822,7 +847,8 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
 
 	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
-	buf->f_ffree = buf->f_files - valid_inode_count(sbi);
+	buf->f_ffree = min(buf->f_files - valid_node_count(sbi),
+							buf->f_bavail);
 
 	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
@@ -974,7 +1000,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, EXTENT_CACHE);
 	sbi->sb->s_flags |= MS_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
-	if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+	if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
 		set_opt_mode(sbi, F2FS_MOUNT_LFS);
 		set_opt(sbi, DISCARD);
 	} else {
@@ -1076,8 +1102,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * or if flush_merge is not passed in mount option.
 	 */
 	if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
-		destroy_flush_cmd_control(sbi);
-	} else if (!SM_I(sbi)->cmd_control_info) {
+		clear_opt(sbi, FLUSH_MERGE);
+		destroy_flush_cmd_control(sbi, false);
+	} else {
 		err = create_flush_cmd_control(sbi);
 		if (err)
 			goto restore_gc;
@@ -1426,6 +1453,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int ovp_segments, reserved_segments;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1437,6 +1465,16 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	if (unlikely(fsmeta >= total))
 		return 1;
 
+	ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+	reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+	if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+			ovp_segments == 0 || reserved_segments == 0)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong layout: check mkfs.f2fs version");
+		return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -1447,6 +1485,7 @@ 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;
 
 	sbi->log_sectors_per_block =
 		le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1471,6 +1510,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
 	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 
+	for (i = 0; i < NR_COUNT_TYPE; i++)
+		atomic_set(&sbi->nr_pages[i], 0);
+
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
 	mutex_init(&sbi->wio_mutex[NODE]);
@@ -1486,13 +1528,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 static int init_percpu_info(struct f2fs_sb_info *sbi)
 {
-	int i, err;
-
-	for (i = 0; i < NR_COUNT_TYPE; i++) {
-		err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
-		if (err)
-			return err;
-	}
+	int err;
 
 	err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
 	if (err)
@@ -1502,6 +1538,71 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 								GFP_KERNEL);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
+{
+	struct block_device *bdev = FDEV(devi).bdev;
+	sector_t nr_sectors = bdev->bd_part->nr_sects;
+	sector_t sector = 0;
+	struct blk_zone *zones;
+	unsigned int i, nr_zones;
+	unsigned int n = 0;
+	int err = -EIO;
+
+	if (!f2fs_sb_mounted_blkzoned(sbi->sb))
+		return 0;
+
+	if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
+				SECTOR_TO_BLOCK(bdev_zone_size(bdev)))
+		return -EINVAL;
+	sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev));
+	if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
+				__ilog2_u32(sbi->blocks_per_blkz))
+		return -EINVAL;
+	sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
+	FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
+					sbi->log_blocks_per_blkz;
+	if (nr_sectors & (bdev_zone_size(bdev) - 1))
+		FDEV(devi).nr_blkz++;
+
+	FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
+	if (!FDEV(devi).blkz_type)
+		return -ENOMEM;
+
+#define F2FS_REPORT_NR_ZONES   4096
+
+	zones = kcalloc(F2FS_REPORT_NR_ZONES, sizeof(struct blk_zone),
+			GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	/* Get block zones type */
+	while (zones && sector < nr_sectors) {
+
+		nr_zones = F2FS_REPORT_NR_ZONES;
+		err = blkdev_report_zones(bdev, sector,
+					  zones, &nr_zones,
+					  GFP_KERNEL);
+		if (err)
+			break;
+		if (!nr_zones) {
+			err = -EIO;
+			break;
+		}
+
+		for (i = 0; i < nr_zones; i++) {
+			FDEV(devi).blkz_type[n] = zones[i].type;
+			sector += zones[i].len;
+			n++;
+		}
+	}
+
+	kfree(zones);
+
+	return err;
+}
+#endif
+
 /*
  * Read f2fs raw super block.
  * Because we have two copies of super block, so read both of them
@@ -1594,6 +1695,77 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	return err;
 }
 
+static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	int i;
+
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (!RDEV(i).path[0])
+			return 0;
+
+		if (i == 0) {
+			sbi->devs = kzalloc(sizeof(struct f2fs_dev_info) *
+						MAX_DEVICES, GFP_KERNEL);
+			if (!sbi->devs)
+				return -ENOMEM;
+		}
+
+		memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+		FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments);
+		if (i == 0) {
+			FDEV(i).start_blk = 0;
+			FDEV(i).end_blk = FDEV(i).start_blk +
+				(FDEV(i).total_segments <<
+				sbi->log_blocks_per_seg) - 1 +
+				le32_to_cpu(raw_super->segment0_blkaddr);
+		} else {
+			FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+			FDEV(i).end_blk = FDEV(i).start_blk +
+				(FDEV(i).total_segments <<
+				sbi->log_blocks_per_seg) - 1;
+		}
+
+		FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+					sbi->sb->s_mode, sbi->sb->s_type);
+		if (IS_ERR(FDEV(i).bdev))
+			return PTR_ERR(FDEV(i).bdev);
+
+		/* to release errored devices */
+		sbi->s_ndevs = i + 1;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
+				!f2fs_sb_mounted_blkzoned(sbi->sb)) {
+			f2fs_msg(sbi->sb, KERN_ERR,
+				"Zoned block device feature not enabled\n");
+			return -EINVAL;
+		}
+		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+			if (init_blkz_info(sbi, i)) {
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"Failed to initialize F2FS blkzone information");
+				return -EINVAL;
+			}
+			f2fs_msg(sbi->sb, KERN_INFO,
+				"Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+				i, FDEV(i).path,
+				FDEV(i).total_segments,
+				FDEV(i).start_blk, FDEV(i).end_blk,
+				bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
+				"Host-aware" : "Host-managed");
+			continue;
+		}
+#endif
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"Mount Device [%2d]: %20s, %8u, %8x - %8x",
+				i, FDEV(i).path,
+				FDEV(i).total_segments,
+				FDEV(i).start_blk, FDEV(i).end_blk);
+	}
+	return 0;
+}
+
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct f2fs_sb_info *sbi;
@@ -1641,6 +1813,18 @@ try_onemore:
 	sb->s_fs_info = sbi;
 	sbi->raw_super = raw_super;
 
+	/*
+	 * The BLKZONED feature indicates that the drive was formatted with
+	 * zone alignment optimization. This is optional for host-aware
+	 * devices, but mandatory for host-managed zoned block devices.
+	 */
+#ifndef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_mounted_blkzoned(sb)) {
+		f2fs_msg(sb, KERN_ERR,
+			 "Zoned block device support is not enabled\n");
+		goto free_sb_buf;
+	}
+#endif
 	default_options(sbi);
 	/* parse mount options */
 	options = kstrdup((const char *)data, GFP_KERNEL);
@@ -1710,6 +1894,13 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
+	/* Initialize device list */
+	err = f2fs_scan_devices(sbi);
+	if (err) {
+		f2fs_msg(sb, KERN_ERR, "Failed to find devices");
+		goto free_devices;
+	}
+
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	percpu_counter_set(&sbi->total_valid_inode_count,
@@ -1893,12 +2084,21 @@ free_node_inode:
 	mutex_lock(&sbi->umount_mutex);
 	release_ino_entry(sbi, true);
 	f2fs_leave_shrinker(sbi);
+	/*
+	 * Some dirty meta pages can be produced by recover_orphan_inodes()
+	 * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+	 * followed by write_checkpoint() through f2fs_write_node_pages(), which
+	 * falls into an infinite loop in sync_meta_pages().
+	 */
+	truncate_inode_pages_final(META_MAPPING(sbi));
 	iput(sbi->node_inode);
 	mutex_unlock(&sbi->umount_mutex);
 free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
+free_devices:
+	destroy_device_list(sbi);
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
@@ -2044,3 +2244,4 @@ module_exit(exit_f2fs_fs)
 MODULE_AUTHOR("Samsung Electronics's Praesto Team");
 MODULE_DESCRIPTION("Flash Friendly File System");
 MODULE_LICENSE("GPL");
+