f2fs: add async reset zone command support

This patch enables submit reset zone command asynchornously. It helps
decrease average latency of write IOs in high utilization scenario by
faster checkpointing.
Signed-off-by: Daejun Park <daejun7.park@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

fs/f2fs/f2fs.h

@@ -1176,6 +1176,7 @@ enum iostat_type {
 	/* other */
 	FS_DISCARD_IO,			/* discard */
 	FS_FLUSH_IO,			/* flush */
+	FS_ZONE_RESET_IO,		/* zone reset */
 	NR_IO_TYPE,
 };
 

fs/f2fs/iostat.c

@@ -80,6 +80,7 @@ int __maybe_unused iostat_info_seq_show(struct seq_file *seq, void *offset)
 	seq_puts(seq, "[OTHER]\n");
 	IOSTAT_INFO_SHOW("fs discard", FS_DISCARD_IO);
 	IOSTAT_INFO_SHOW("fs flush", FS_FLUSH_IO);
+	IOSTAT_INFO_SHOW("fs zone reset", FS_ZONE_RESET_IO);
 
 	return 0;
 }

fs/f2fs/segment.c

@@ -1196,6 +1196,45 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 				struct block_device *bdev, block_t lstart,
 				block_t start, block_t len);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static void __submit_zone_reset_cmd(struct f2fs_sb_info *sbi,
+				   struct discard_cmd *dc, blk_opf_t flag,
+				   struct list_head *wait_list,
+				   unsigned int *issued)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct block_device *bdev = dc->bdev;
+	struct bio *bio = bio_alloc(bdev, 0, REQ_OP_ZONE_RESET | flag, GFP_NOFS);
+	unsigned long flags;
+
+	trace_f2fs_issue_reset_zone(bdev, dc->di.start);
+
+	spin_lock_irqsave(&dc->lock, flags);
+	dc->state = D_SUBMIT;
+	dc->bio_ref++;
+	spin_unlock_irqrestore(&dc->lock, flags);
+
+	if (issued)
+		(*issued)++;
+
+	atomic_inc(&dcc->queued_discard);
+	dc->queued++;
+	list_move_tail(&dc->list, wait_list);
+
+	/* sanity check on discard range */
+	__check_sit_bitmap(sbi, dc->di.lstart, dc->di.lstart + dc->di.len);
+
+	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(dc->di.start);
+	bio->bi_private = dc;
+	bio->bi_end_io = f2fs_submit_discard_endio;
+	submit_bio(bio);
+
+	atomic_inc(&dcc->issued_discard);
+	f2fs_update_iostat(sbi, NULL, FS_ZONE_RESET_IO, dc->di.len * F2FS_BLKSIZE);
+}
+#endif
+
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
 static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 				struct discard_policy *dpolicy,
@@ -1217,6 +1256,13 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		return 0;
 
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) {
+		__submit_zone_reset_cmd(sbi, dc, flag, wait_list, issued);
+		return 0;
+	}
+#endif
+
 	trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len);
 
 	lstart = dc->di.lstart;
@@ -1461,6 +1507,19 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 	}
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static void __queue_zone_reset_cmd(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t lblkstart,
+		block_t blklen)
+{
+	trace_f2fs_queue_reset_zone(bdev, blkstart);
+
+	mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
+	__insert_discard_cmd(sbi, bdev, lblkstart, blkstart, blklen);
+	mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
+}
+#endif
+
 static void __queue_discard_cmd(struct f2fs_sb_info *sbi,
 		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
@@ -1724,6 +1783,19 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 	mutex_lock(&dcc->cmd_lock);
 	dc = __lookup_discard_cmd(sbi, blkaddr);
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (dc && f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(dc->bdev)) {
+		/* force submit zone reset */
+		if (dc->state == D_PREP)
+			__submit_zone_reset_cmd(sbi, dc, REQ_SYNC,
+						&dcc->wait_list, NULL);
+		dc->ref++;
+		mutex_unlock(&dcc->cmd_lock);
+		/* wait zone reset */
+		__wait_one_discard_bio(sbi, dc);
+		return;
+	}
+#endif
 	if (dc) {
 		if (dc->state == D_PREP) {
 			__punch_discard_cmd(sbi, dc, blkaddr);
@@ -1876,9 +1948,15 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 				 blkstart, blklen);
 			return -EIO;
 		}
-		trace_f2fs_issue_reset_zone(bdev, blkstart);
-		return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-					sector, nr_sects, GFP_NOFS);
+
+		if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) {
+			trace_f2fs_issue_reset_zone(bdev, blkstart);
+			return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+						sector, nr_sects, GFP_NOFS);
+		}
+
+		__queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen);
+		return 0;
 	}
 
 	/* For conventional zones, use regular discard if supported */

include/trace/events/f2fs.h

@@ -1512,7 +1512,7 @@ DEFINE_EVENT(f2fs_discard, f2fs_remove_discard,
 	TP_ARGS(dev, blkstart, blklen)
 );
 
-TRACE_EVENT(f2fs_issue_reset_zone,
+DECLARE_EVENT_CLASS(f2fs_reset_zone,
 
 	TP_PROTO(struct block_device *dev, block_t blkstart),
 
@@ -1528,11 +1528,25 @@ TRACE_EVENT(f2fs_issue_reset_zone,
 		__entry->blkstart = blkstart;
 	),
 
-	TP_printk("dev = (%d,%d), reset zone at block = 0x%llx",
+	TP_printk("dev = (%d,%d), zone at block = 0x%llx",
 		show_dev(__entry->dev),
 		(unsigned long long)__entry->blkstart)
 );
 
+DEFINE_EVENT(f2fs_reset_zone, f2fs_queue_reset_zone,
+
+	TP_PROTO(struct block_device *dev, block_t blkstart),
+
+	TP_ARGS(dev, blkstart)
+);
+
+DEFINE_EVENT(f2fs_reset_zone, f2fs_issue_reset_zone,
+
+	TP_PROTO(struct block_device *dev, block_t blkstart),
+
+	TP_ARGS(dev, blkstart)
+);
+
 TRACE_EVENT(f2fs_issue_flush,
 
 	TP_PROTO(struct block_device *dev, unsigned int nobarrier,
@@ -1979,6 +1993,7 @@ TRACE_EVENT(f2fs_iostat,
 		__field(unsigned long long,	fs_nrio)
 		__field(unsigned long long,	fs_mrio)
 		__field(unsigned long long,	fs_discard)
+		__field(unsigned long long,	fs_reset_zone)
 	),
 
 	TP_fast_assign(
@@ -2010,12 +2025,14 @@ TRACE_EVENT(f2fs_iostat,
 		__entry->fs_nrio	= iostat[FS_NODE_READ_IO];
 		__entry->fs_mrio	= iostat[FS_META_READ_IO];
 		__entry->fs_discard	= iostat[FS_DISCARD_IO];
+		__entry->fs_reset_zone	= iostat[FS_ZONE_RESET_IO];
 	),
 
 	TP_printk("dev = (%d,%d), "
 		"app [write=%llu (direct=%llu, buffered=%llu), mapped=%llu, "
 		"compr(buffered=%llu, mapped=%llu)], "
-		"fs [data=%llu, cdata=%llu, node=%llu, meta=%llu, discard=%llu], "
+		"fs [data=%llu, cdata=%llu, node=%llu, meta=%llu, discard=%llu, "
+		"reset_zone=%llu], "
 		"gc [data=%llu, node=%llu], "
 		"cp [data=%llu, node=%llu, meta=%llu], "
 		"app [read=%llu (direct=%llu, buffered=%llu), mapped=%llu], "
@@ -2026,6 +2043,7 @@ TRACE_EVENT(f2fs_iostat,
 		__entry->app_bio, __entry->app_mio, __entry->app_bcdio,
 		__entry->app_mcdio, __entry->fs_dio, __entry->fs_cdio,
 		__entry->fs_nio, __entry->fs_mio, __entry->fs_discard,
+		__entry->fs_reset_zone,
 		__entry->fs_gc_dio, __entry->fs_gc_nio, __entry->fs_cp_dio,
 		__entry->fs_cp_nio, __entry->fs_cp_mio,
 		__entry->app_rio, __entry->app_drio, __entry->app_brio,