btrfs: don't rely on unchanging ->bi_bdev for zone append remaps

btrfs_record_physical_zoned relies on a bio->bi_bdev samples in the
bio_end_io handler to find the reverse map for remapping the zone append
write, but stacked block device drivers can and usually do change bi_bdev
when sending on the bio to a lower device.  This can happen e.g. with the
nvme-multipath driver when a NVMe SSD sets the shared namespace bit.

But there is no real need for the bdev in btrfs_record_physical_zoned,
as it is only passed to btrfs_rmap_block, which uses it to pick the
mapping to report if there are multiple reverse mappings.  As zone
writes can only do simple non-mirror writes right now, and anything
more complex will use the stripe tree there is no chance of the multiple
mappings case actually happening.

Instead open code the subset of btrfs_rmap_block in
btrfs_record_physical_zoned, which also removes a memory allocation and
remove the bdev field in the ordered extent.

Fixes: d8e3fb106f39 ("btrfs: zoned: use ZONE_APPEND write for zoned mode")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2fd518afc4f317baeaf5ce0c4e96a3a46c393423..44e9acc77a74828273c7fbc6aa62ef400311245e 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3162,8 +3162,8 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
                goto out;
        }
 
-       /* A valid bdev implies a write on a sequential zone */
-       if (ordered_extent->bdev) {
+       /* A valid ->physical implies a write on a sequential zone. */
+       if (ordered_extent->physical != (u64)-1) {
                btrfs_rewrite_logical_zoned(ordered_extent);
                btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
                                        ordered_extent->disk_num_bytes);

diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index ae3ed748acaf665a73c57f15f0021a994be28fbf..eb40cb39f842e6627f04ec174e06bb918d9af43b 100644 (file)
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -157,7 +157,6 @@ struct btrfs_ordered_extent {
         * command in a workqueue context
         */
        u64 physical;
-       struct block_device *bdev;
 };
 
 static inline void

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 442bb79ffd082ce479e86b2bfed512e0fa4ee91c..f95b2c94d6199a62194d785ffa3d427c0a3fa79b 100644 (file)
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1676,8 +1676,6 @@ void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
                return;
 
        ordered->physical = physical;
-       ordered->bdev = bbio->bio.bi_bdev;
-
        btrfs_put_ordered_extent(ordered);
 }
 
@@ -1689,43 +1687,46 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
        struct extent_map *em;
        struct btrfs_ordered_sum *sum;
        u64 orig_logical = ordered->disk_bytenr;
-       u64 *logical = NULL;
-       int nr, stripe_len;
+       struct map_lookup *map;
+       u64 physical = ordered->physical;
+       u64 chunk_start_phys;
+       u64 logical;
 
-       /* Zoned devices should not have partitions. So, we can assume it is 0 */
-       ASSERT(!bdev_is_partition(ordered->bdev));
-       if (WARN_ON(!ordered->bdev))
+       em = btrfs_get_chunk_map(fs_info, orig_logical, 1);
+       if (IS_ERR(em))
                return;
+       map = em->map_lookup;
+       chunk_start_phys = map->stripes[0].physical;
 
-       if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, ordered->bdev,
-                                    ordered->physical, &logical, &nr,
-                                    &stripe_len)))
-               goto out;
-
-       WARN_ON(nr != 1);
+       if (WARN_ON_ONCE(map->num_stripes > 1) ||
+           WARN_ON_ONCE((map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) ||
+           WARN_ON_ONCE(physical < chunk_start_phys) ||
+           WARN_ON_ONCE(physical > chunk_start_phys + em->orig_block_len)) {
+               free_extent_map(em);
+               return;
+       }
+       logical = em->start + (physical - map->stripes[0].physical);
+       free_extent_map(em);
 
-       if (orig_logical == *logical)
-               goto out;
+       if (orig_logical == logical)
+               return;
 
-       ordered->disk_bytenr = *logical;
+       ordered->disk_bytenr = logical;
 
        em_tree = &inode->extent_tree;
        write_lock(&em_tree->lock);
        em = search_extent_mapping(em_tree, ordered->file_offset,
                                   ordered->num_bytes);
-       em->block_start = *logical;
+       em->block_start = logical;
        free_extent_map(em);
        write_unlock(&em_tree->lock);
 
        list_for_each_entry(sum, &ordered->list, list) {
-               if (*logical < orig_logical)
-                       sum->bytenr -= orig_logical - *logical;
+               if (logical < orig_logical)
+                       sum->bytenr -= orig_logical - logical;
                else
-                       sum->bytenr += *logical - orig_logical;
+                       sum->bytenr += logical - orig_logical;
        }
-
-out:
-       kfree(logical);
 }
 
 bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,