1 files changed, 126 insertions, 36 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6db410f1bb8c..0457d620011f 100644
--- a/fs/f2fs/segment.c
+++ b/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 */
@@ -2115,7 +2193,7 @@ find_next:
 			len = next_pos - cur_pos;
 
 			if (f2fs_sb_has_blkzoned(sbi) ||
-			    (force && len < cpc->trim_minlen))
+					!force || len < cpc->trim_minlen)
 				goto skip;
 
 			f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
@@ -4768,17 +4846,17 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 {
 	unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno;
 	block_t zone_block, wp_block, last_valid_block;
-	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
 	int i, s, b, ret;
 	struct seg_entry *se;
 
 	if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
 		return 0;
 
-	wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block);
+	wp_block = fdev->start_blk + (zone->wp >> sbi->log_sectors_per_block);
 	wp_segno = GET_SEGNO(sbi, wp_block);
 	wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
-	zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block);
+	zone_block = fdev->start_blk + (zone->start >>
+						sbi->log_sectors_per_block);
 	zone_segno = GET_SEGNO(sbi, zone_block);
 	zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno);
 
@@ -4811,39 +4889,52 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 	}
 
 	/*
-	 * If last valid block is beyond the write pointer, report the
-	 * inconsistency. This inconsistency does not cause write error
-	 * because the zone will not be selected for write operation until
-	 * it get discarded. Just report it.
+	 * The write pointer matches with the valid blocks or
+	 * already points to the end of the zone.
 	 */
-	if (last_valid_block >= wp_block) {
-		f2fs_notice(sbi, "Valid block beyond write pointer: "
-			    "valid block[0x%x,0x%x] wp[0x%x,0x%x]",
-			    GET_SEGNO(sbi, last_valid_block),
-			    GET_BLKOFF_FROM_SEG0(sbi, last_valid_block),
-			    wp_segno, wp_blkoff);
+	if ((last_valid_block + 1 == wp_block) ||
+			(zone->wp == zone->start + zone->len))
 		return 0;
-	}
 
-	/*
-	 * If there is no valid block in the zone and if write pointer is
-	 * not at zone start, reset the write pointer.
-	 */
-	if (last_valid_block + 1 == zone_block && zone->wp != zone->start) {
+	if (last_valid_block + 1 == zone_block) {
+		/*
+		 * If there is no valid block in the zone and if write pointer
+		 * is not at zone start, reset the write pointer.
+		 */
 		f2fs_notice(sbi,
 			    "Zone without valid block has non-zero write "
 			    "pointer. Reset the write pointer: wp[0x%x,0x%x]",
 			    wp_segno, wp_blkoff);
 		ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block,
-					zone->len >> log_sectors_per_block);
-		if (ret) {
+				zone->len >> sbi->log_sectors_per_block);
+		if (ret)
 			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
 				 fdev->path, ret);
-			return ret;
-		}
+
+		return ret;
 	}
 
-	return 0;
+	/*
+	 * If there are valid blocks and the write pointer doesn't
+	 * match with them, we need to report the inconsistency and
+	 * fill the zone till the end to close the zone. This inconsistency
+	 * does not cause write error because the zone will not be selected
+	 * for write operation until it get discarded.
+	 */
+	f2fs_notice(sbi, "Valid blocks are not aligned with write pointer: "
+		    "valid block[0x%x,0x%x] wp[0x%x,0x%x]",
+		    GET_SEGNO(sbi, last_valid_block),
+		    GET_BLKOFF_FROM_SEG0(sbi, last_valid_block),
+		    wp_segno, wp_blkoff);
+
+	ret = blkdev_issue_zeroout(fdev->bdev, zone->wp,
+				zone->len - (zone->wp - zone->start),
+				GFP_NOFS, 0);
+	if (ret)
+		f2fs_err(sbi, "Fill up zone failed: %s (errno=%d)",
+			 fdev->path, ret);
+
+	return ret;
 }
 
 static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
@@ -4876,7 +4967,6 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 	struct blk_zone zone;
 	unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off;
 	block_t cs_zone_block, wp_block;
-	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
 	sector_t zone_sector;
 	int err;
 
@@ -4888,8 +4978,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 		return 0;
 
 	/* report zone for the sector the curseg points to */
-	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
-		<< log_sectors_per_block;
+	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) <<
+						sbi->log_sectors_per_block;
 	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
 				  report_one_zone_cb, &zone);
 	if (err != 1) {
@@ -4901,10 +4991,10 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 	if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
 		return 0;
 
-	wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block);
+	wp_block = zbd->start_blk + (zone.wp >> sbi->log_sectors_per_block);
 	wp_segno = GET_SEGNO(sbi, wp_block);
 	wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
-	wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0);
+	wp_sector_off = zone.wp & GENMASK(sbi->log_sectors_per_block - 1, 0);
 
 	if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff &&
 		wp_sector_off == 0)
@@ -4931,8 +5021,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 	if (!zbd)
 		return 0;
 
-	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
-		<< log_sectors_per_block;
+	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) <<
+						sbi->log_sectors_per_block;
 	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
 				  report_one_zone_cb, &zone);
 	if (err != 1) {
@@ -4950,7 +5040,7 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
 			    "Reset the zone: curseg[0x%x,0x%x]",
 			    type, cs->segno, cs->next_blkoff);
 		err = __f2fs_issue_discard_zone(sbi, zbd->bdev,	cs_zone_block,
-					zone.len >> log_sectors_per_block);
+					zone.len >> sbi->log_sectors_per_block);
 		if (err) {
 			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
 				 zbd->path, err);