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, 173 insertions, 63 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f1b4a1775ebe..0738f48293cc 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -274,8 +274,10 @@ static int __commit_inmem_pages(struct inode *inode,
 
 			set_page_dirty(page);
 			f2fs_wait_on_page_writeback(page, DATA, true);
-			if (clear_page_dirty_for_io(page))
+			if (clear_page_dirty_for_io(page)) {
 				inode_dec_dirty_pages(inode);
+				remove_dirty_inode(inode);
+			}
 
 			fio.page = page;
 			err = do_write_data_page(&fio);
@@ -287,7 +289,6 @@ static int __commit_inmem_pages(struct inode *inode,
 			/* record old blkaddr for revoking */
 			cur->old_addr = fio.old_blkaddr;
 
-			clear_cold_data(page);
 			submit_bio = true;
 		}
 		unlock_page(page);
@@ -363,7 +364,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
 		mutex_lock(&sbi->gc_mutex);
-		f2fs_gc(sbi, false);
+		f2fs_gc(sbi, false, false);
 	}
 }
 
@@ -380,14 +381,17 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	if (!available_free_memory(sbi, FREE_NIDS))
 		try_to_free_nids(sbi, MAX_FREE_NIDS);
 	else
-		build_free_nids(sbi);
+		build_free_nids(sbi, false);
+
+	if (!is_idle(sbi))
+		return;
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
 			excess_prefree_segs(sbi) ||
 			excess_dirty_nats(sbi) ||
-			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+			f2fs_time_over(sbi, CP_TIME)) {
 		if (test_opt(sbi, DATA_FLUSH)) {
 			struct blk_plug plug;
 
@@ -400,6 +404,33 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	}
 }
 
+static int __submit_flush_wait(struct block_device *bdev)
+{
+	struct bio *bio = f2fs_bio_alloc(0);
+	int ret;
+
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_bdev = bdev;
+	ret = submit_bio_wait(bio);
+	bio_put(bio);
+	return ret;
+}
+
+static int submit_flush_wait(struct f2fs_sb_info *sbi)
+{
+	int ret = __submit_flush_wait(sbi->sb->s_bdev);
+	int i;
+
+	if (sbi->s_ndevs && !ret) {
+		for (i = 1; i < sbi->s_ndevs; i++) {
+			ret = __submit_flush_wait(FDEV(i).bdev);
+			if (ret)
+				break;
+		}
+	}
+	return ret;
+}
+
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -410,25 +441,18 @@ repeat:
 		return 0;
 
 	if (!llist_empty(&fcc->issue_list)) {
-		struct bio *bio;
 		struct flush_cmd *cmd, *next;
 		int ret;
 
-		bio = f2fs_bio_alloc(0);
-
 		fcc->dispatch_list = llist_del_all(&fcc->issue_list);
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
-		bio->bi_bdev = sbi->sb->s_bdev;
-		bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-		ret = submit_bio_wait(bio);
-
+		ret = submit_flush_wait(sbi);
 		llist_for_each_entry_safe(cmd, next,
 					  fcc->dispatch_list, llnode) {
 			cmd->ret = ret;
 			complete(&cmd->wait);
 		}
-		bio_put(bio);
 		fcc->dispatch_list = NULL;
 	}
 
@@ -449,15 +473,11 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 		return 0;
 
 	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
-		struct bio *bio = f2fs_bio_alloc(0);
 		int ret;
 
 		atomic_inc(&fcc->submit_flush);
-		bio->bi_bdev = sbi->sb->s_bdev;
-		bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-		ret = submit_bio_wait(bio);
+		ret = submit_flush_wait(sbi);
 		atomic_dec(&fcc->submit_flush);
-		bio_put(bio);
 		return ret;
 	}
 
@@ -469,8 +489,13 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 	if (!fcc->dispatch_list)
 		wake_up(&fcc->flush_wait_queue);
 
-	wait_for_completion(&cmd.wait);
-	atomic_dec(&fcc->submit_flush);
+	if (fcc->f2fs_issue_flush) {
+		wait_for_completion(&cmd.wait);
+		atomic_dec(&fcc->submit_flush);
+	} else {
+		llist_del_all(&fcc->issue_list);
+		atomic_set(&fcc->submit_flush, 0);
+	}
 
 	return cmd.ret;
 }
@@ -481,6 +506,11 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	struct flush_cmd_control *fcc;
 	int err = 0;
 
+	if (SM_I(sbi)->cmd_control_info) {
+		fcc = SM_I(sbi)->cmd_control_info;
+		goto init_thread;
+	}
+
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
@@ -488,6 +518,7 @@ 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)->cmd_control_info = fcc;
+init_thread:
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
@@ -500,14 +531,20 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	return err;
 }
 
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 {
 	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
 
-	if (fcc && fcc->f2fs_issue_flush)
-		kthread_stop(fcc->f2fs_issue_flush);
-	kfree(fcc);
-	SM_I(sbi)->cmd_control_info = NULL;
+	if (fcc && fcc->f2fs_issue_flush) {
+		struct task_struct *flush_thread = fcc->f2fs_issue_flush;
+
+		fcc->f2fs_issue_flush = NULL;
+		kthread_stop(flush_thread);
+	}
+	if (free) {
+		kfree(fcc);
+		SM_I(sbi)->cmd_control_info = NULL;
+	}
 }
 
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -633,15 +670,23 @@ static void f2fs_submit_bio_wait_endio(struct bio *bio)
 }
 
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
-int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+static int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
-	struct block_device *bdev = sbi->sb->s_bdev;
 	struct bio *bio = NULL;
 	int err;
 
-	err = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
-			&bio);
+	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+
+	if (sbi->s_ndevs) {
+		int devi = f2fs_target_device_index(sbi, blkstart);
+
+		blkstart -= FDEV(devi).start_blk;
+	}
+	err = __blkdev_issue_discard(bdev,
+				SECTOR_FROM_BLOCK(blkstart),
+				SECTOR_FROM_BLOCK(blklen),
+				GFP_NOFS, 0, &bio);
 	if (!err && bio) {
 		struct bio_entry *be = __add_bio_entry(sbi, bio);
 
@@ -654,24 +699,101 @@ int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi, sector_t sector,
 	return err;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+	sector_t nr_sects = SECTOR_FROM_BLOCK(blklen);
+	sector_t sector;
+	int devi = 0;
+
+	if (sbi->s_ndevs) {
+		devi = f2fs_target_device_index(sbi, blkstart);
+		blkstart -= FDEV(devi).start_blk;
+	}
+	sector = SECTOR_FROM_BLOCK(blkstart);
+
+	if (sector & (bdev_zone_size(bdev) - 1) ||
+				nr_sects != bdev_zone_size(bdev)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"(%d) %s: Unaligned discard attempted (block %x + %x)",
+			devi, sbi->s_ndevs ? FDEV(devi).path: "",
+			blkstart, blklen);
+		return -EIO;
+	}
+
+	/*
+	 * We need to know the type of the zone: for conventional zones,
+	 * use regular discard if the drive supports it. For sequential
+	 * zones, reset the zone write pointer.
+	 */
+	switch (get_blkz_type(sbi, bdev, blkstart)) {
+
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (!blk_queue_discard(bdev_get_queue(bdev)))
+			return 0;
+		return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		trace_f2fs_issue_reset_zone(sbi->sb, blkstart);
+		return blkdev_reset_zones(bdev, sector,
+					  nr_sects, GFP_NOFS);
+	default:
+		/* Unknown zone type: broken device ? */
+		return -EIO;
+	}
+}
+#endif
+
+static int __issue_discard_async(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
+				bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+		return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
+#endif
+	return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+}
+
 static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 				block_t blkstart, block_t blklen)
 {
-	sector_t start = SECTOR_FROM_BLOCK(blkstart);
-	sector_t len = SECTOR_FROM_BLOCK(blklen);
+	sector_t start = blkstart, len = 0;
+	struct block_device *bdev;
 	struct seg_entry *se;
 	unsigned int offset;
 	block_t i;
+	int err = 0;
+
+	bdev = f2fs_target_device(sbi, blkstart, NULL);
+
+	for (i = blkstart; i < blkstart + blklen; i++, len++) {
+		if (i != start) {
+			struct block_device *bdev2 =
+				f2fs_target_device(sbi, i, NULL);
+
+			if (bdev2 != bdev) {
+				err = __issue_discard_async(sbi, bdev,
+						start, len);
+				if (err)
+					return err;
+				bdev = bdev2;
+				start = i;
+				len = 0;
+			}
+		}
 
-	for (i = blkstart; i < blkstart + blklen; i++) {
 		se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
 		offset = GET_BLKOFF_FROM_SEG0(sbi, i);
 
 		if (!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
 	}
-	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
-	return __f2fs_issue_discard_async(sbi, start, len, GFP_NOFS, 0);
+
+	if (len)
+		err = __issue_discard_async(sbi, bdev, start, len);
+	return err;
 }
 
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
@@ -1296,25 +1418,21 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
-static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
-{
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	unsigned int old_segno;
-
-	old_segno = curseg->segno;
-	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
-	locate_dirty_segment(sbi, old_segno);
-}
-
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
+	struct curseg_info *curseg;
+	unsigned int old_segno;
 	int i;
 
 	if (test_opt(sbi, LFS))
 		return;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
-		__allocate_new_segments(sbi, i);
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		curseg = CURSEG_I(sbi, i);
+		old_segno = curseg->segno;
+		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+		locate_dirty_segment(sbi, old_segno);
+	}
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1448,21 +1566,11 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		struct f2fs_summary *sum, int type)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	struct curseg_info *curseg;
-	bool direct_io = (type == CURSEG_DIRECT_IO);
-
-	type = direct_io ? CURSEG_WARM_DATA : type;
-
-	curseg = CURSEG_I(sbi, type);
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
-	/* direct_io'ed data is aligned to the segment for better performance */
-	if (direct_io && curseg->next_blkoff &&
-				!has_not_enough_free_secs(sbi, 0, 0))
-		__allocate_new_segments(sbi, type);
-
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -2166,7 +2274,6 @@ out:
 static int build_sit_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
-	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct sit_info *sit_i;
 	unsigned int sit_segs, start;
 	char *src_bitmap, *dst_bitmap;
@@ -2233,7 +2340,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 
 	sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
 	sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
-	sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
+	sit_i->written_valid_blocks = 0;
 	sit_i->sit_bitmap = dst_bitmap;
 	sit_i->bitmap_size = bitmap_size;
 	sit_i->dirty_sentries = 0;
@@ -2315,10 +2422,10 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
 
 	do {
-		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
+		readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+							META_SIT, true);
 
 		start = start_blk * sit_i->sents_per_block;
 		end = (start_blk + readed) * sit_i->sents_per_block;
@@ -2387,6 +2494,9 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 		struct seg_entry *sentry = get_seg_entry(sbi, start);
 		if (!sentry->valid_blocks)
 			__set_free(sbi, start);
+		else
+			SIT_I(sbi)->written_valid_blocks +=
+						sentry->valid_blocks;
 	}
 
 	/* set use the current segments */
@@ -2645,7 +2755,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
 
 	if (!sm_info)
 		return;
-	destroy_flush_cmd_control(sbi);
+	destroy_flush_cmd_control(sbi, true);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);