1 files changed, 264 insertions, 7 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 56e81447e2f3..cf0eb002cfd4 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -334,7 +334,6 @@ void f2fs_drop_inmem_pages(struct inode *inode)
 	}
 
 	fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
-	stat_dec_atomic_write(inode);
 
 	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
 	if (!list_empty(&fi->inmem_ilist))
@@ -505,7 +504,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 * dir/node pages without enough free segments.
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 		f2fs_gc(sbi, false, false, NULL_SEGNO);
 	}
 }
@@ -2225,7 +2224,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 	struct sit_info *sit_i = SIT_I(sbi);
 
 	f2fs_bug_on(sbi, addr == NULL_ADDR);
-	if (addr == NEW_ADDR)
+	if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
 		return;
 
 	invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
@@ -2861,9 +2860,9 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	if (sbi->discard_blks == 0)
 		goto out;
 
-	mutex_lock(&sbi->gc_mutex);
+	down_write(&sbi->gc_lock);
 	err = f2fs_write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+	up_write(&sbi->gc_lock);
 	if (err)
 		goto out;
 
@@ -3036,7 +3035,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	if (fio->type == DATA) {
 		struct inode *inode = fio->page->mapping->host;
 
-		if (is_cold_data(fio->page) || file_is_cold(inode))
+		if (is_cold_data(fio->page) || file_is_cold(inode) ||
+				f2fs_compressed_file(inode))
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -3289,7 +3289,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 
 	stat_inc_inplace_blocks(fio->sbi);
 
-	if (fio->bio)
+	if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
 		err = f2fs_merge_page_bio(fio);
 	else
 		err = f2fs_submit_page_bio(fio);
@@ -4368,6 +4368,263 @@ out:
 	return 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+
+static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
+				    struct f2fs_dev_info *fdev,
+				    struct blk_zone *zone)
+{
+	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_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_segno = GET_SEGNO(sbi, zone_block);
+	zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno);
+
+	if (zone_segno >= MAIN_SEGS(sbi))
+		return 0;
+
+	/*
+	 * Skip check of zones cursegs point to, since
+	 * fix_curseg_write_pointer() checks them.
+	 */
+	for (i = 0; i < NO_CHECK_TYPE; i++)
+		if (zone_secno == GET_SEC_FROM_SEG(sbi,
+						   CURSEG_I(sbi, i)->segno))
+			return 0;
+
+	/*
+	 * Get last valid block of the zone.
+	 */
+	last_valid_block = zone_block - 1;
+	for (s = sbi->segs_per_sec - 1; s >= 0; s--) {
+		segno = zone_segno + s;
+		se = get_seg_entry(sbi, segno);
+		for (b = sbi->blocks_per_seg - 1; b >= 0; b--)
+			if (f2fs_test_bit(b, se->cur_valid_map)) {
+				last_valid_block = START_BLOCK(sbi, segno) + b;
+				break;
+			}
+		if (last_valid_block >= zone_block)
+			break;
+	}
+
+	/*
+	 * 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.
+	 */
+	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);
+		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) {
+		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) {
+			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+				 fdev->path, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
+						  block_t zone_blkaddr)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (!bdev_is_zoned(FDEV(i).bdev))
+			continue;
+		if (sbi->s_ndevs == 1 || (FDEV(i).start_blk <= zone_blkaddr &&
+				zone_blkaddr <= FDEV(i).end_blk))
+			return &FDEV(i);
+	}
+
+	return NULL;
+}
+
+static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
+			      void *data) {
+	memcpy(data, zone, sizeof(struct blk_zone));
+	return 0;
+}
+
+static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *cs = CURSEG_I(sbi, type);
+	struct f2fs_dev_info *zbd;
+	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;
+
+	cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+	cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+	zbd = get_target_zoned_dev(sbi, cs_zone_block);
+	if (!zbd)
+		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;
+	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+				  report_one_zone_cb, &zone);
+	if (err != 1) {
+		f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+			 zbd->path, err);
+		return err;
+	}
+
+	if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+		return 0;
+
+	wp_block = zbd->start_blk + (zone.wp >> 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);
+
+	if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff &&
+		wp_sector_off == 0)
+		return 0;
+
+	f2fs_notice(sbi, "Unaligned curseg[%d] with write pointer: "
+		    "curseg[0x%x,0x%x] wp[0x%x,0x%x]",
+		    type, cs->segno, cs->next_blkoff, wp_segno, wp_blkoff);
+
+	f2fs_notice(sbi, "Assign new section to curseg[%d]: "
+		    "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff);
+	allocate_segment_by_default(sbi, type, true);
+
+	/* check consistency of the zone curseg pointed to */
+	if (check_zone_write_pointer(sbi, zbd, &zone))
+		return -EIO;
+
+	/* check newly assigned zone */
+	cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+	cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+	zbd = get_target_zoned_dev(sbi, cs_zone_block);
+	if (!zbd)
+		return 0;
+
+	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
+		<< log_sectors_per_block;
+	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+				  report_one_zone_cb, &zone);
+	if (err != 1) {
+		f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+			 zbd->path, err);
+		return err;
+	}
+
+	if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+		return 0;
+
+	if (zone.wp != zone.start) {
+		f2fs_notice(sbi,
+			    "New zone for curseg[%d] is not yet discarded. "
+			    "Reset the zone: curseg[0x%x,0x%x]",
+			    type, cs->segno, cs->next_blkoff);
+		err = __f2fs_issue_discard_zone(sbi, zbd->bdev,
+				zone_sector >> log_sectors_per_block,
+				zone.len >> log_sectors_per_block);
+		if (err) {
+			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+				 zbd->path, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+	int i, ret;
+
+	for (i = 0; i < NO_CHECK_TYPE; i++) {
+		ret = fix_curseg_write_pointer(sbi, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct check_zone_write_pointer_args {
+	struct f2fs_sb_info *sbi;
+	struct f2fs_dev_info *fdev;
+};
+
+static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
+				      void *data) {
+	struct check_zone_write_pointer_args *args;
+	args = (struct check_zone_write_pointer_args *)data;
+
+	return check_zone_write_pointer(args->sbi, args->fdev, zone);
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+	int i, ret;
+	struct check_zone_write_pointer_args args;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (!bdev_is_zoned(FDEV(i).bdev))
+			continue;
+
+		args.sbi = sbi;
+		args.fdev = &FDEV(i);
+		ret = blkdev_report_zones(FDEV(i).bdev, 0, BLK_ALL_ZONES,
+					  check_zone_write_pointer_cb, &args);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+#else
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+	return 0;
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+	return 0;
+}
+#endif
+
 /*
  * Update min, max modified time for cost-benefit GC algorithm
  */