aboutsummaryrefslogtreecommitdiffstats
path: root/fs/f2fs
diff options
context:
space:
mode:
authorShin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>2019-12-09 19:44:45 +0900
committerJaegeuk Kim <jaegeuk@kernel.org>2020-01-15 13:43:48 -0800
commitd508c94e45fcd3421e64f556abb1cf145ccc0e8f (patch)
treefd694392563641e8b11e23eb17a3f29ceb9f3778 /fs/f2fs
parentf2fs: Check write pointer consistency of open zones (diff)
downloadlinux-dev-d508c94e45fcd3421e64f556abb1cf145ccc0e8f.tar.xz
linux-dev-d508c94e45fcd3421e64f556abb1cf145ccc0e8f.zip
f2fs: Check write pointer consistency of non-open zones
To catch f2fs bugs in write pointer handling code for zoned block devices, check write pointers of non-open zones that current segments do not point to. Do this check at mount time, after the fsync data recovery and current segments' write pointer consistency fix. Or when fsync data recovery is disabled by mount option, do the check when there is no fsync data. Check two items comparing write pointers with valid block maps in SIT. The first item is check for zones with no valid blocks. When there is no valid blocks in a zone, the write pointer should be at the start of the zone. If not, next write operation to the zone will cause unaligned write error. If write pointer is not at the zone start, reset the write pointer to place at the zone start. The second item is check between the write pointer position and the last valid block in the zone. It is unexpected that the last valid block position is beyond the write pointer. In such a case, report as a bug. Fix is not required for such zone, because the zone is not selected for next write operation until the zone get discarded. Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/f2fs.h1
-rw-r--r--fs/f2fs/segment.c126
-rw-r--r--fs/f2fs/super.c11
3 files changed, 138 insertions, 0 deletions
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 002c417b0a53..23a84d7f17b8 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3156,6 +3156,7 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 5c3018743a9f..3ec912bd5504 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -4370,6 +4370,90 @@ out:
#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)
{
@@ -4441,6 +4525,10 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
"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));
@@ -4492,11 +4580,49 @@ int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
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
/*
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 5111e1ffe58a..755ad57c795b 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3544,6 +3544,17 @@ try_onemore:
goto free_meta;
}
}
+
+ /*
+ * If the f2fs is not readonly and fsync data recovery succeeds,
+ * check zoned block devices' write pointer consistency.
+ */
+ if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
+ err = f2fs_check_write_pointer(sbi);
+ if (err)
+ goto free_meta;
+ }
+
reset_checkpoint:
/* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);