atomic_t repair_count;
};
+/* Is this a data path I/O that needs storage layer checksum and repair? */
+static inline bool is_data_bbio(struct btrfs_bio *bbio)
+{
+ return bbio->inode && is_data_inode(&bbio->inode->vfs_inode);
+}
+
+static bool bbio_has_ordered_extent(struct btrfs_bio *bbio)
+{
+ return is_data_bbio(bbio) && btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE;
+}
+
/*
* Initialize a btrfs_bio structure. This skips the embedded bio itself as it
* is already initialized by the block layer.
return bbio;
}
-static blk_status_t btrfs_bio_extract_ordered_extent(struct btrfs_bio *bbio)
-{
- struct btrfs_ordered_extent *ordered;
- int ret;
-
- ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset);
- if (WARN_ON_ONCE(!ordered))
- return BLK_STS_IOERR;
- ret = btrfs_extract_ordered_extent(bbio, ordered);
- btrfs_put_ordered_extent(ordered);
-
- return errno_to_blk_status(ret);
-}
-
static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
struct btrfs_bio *orig_bbio,
u64 map_length, bool use_append)
btrfs_bio_init(bbio, fs_info, NULL, orig_bbio);
bbio->inode = orig_bbio->inode;
bbio->file_offset = orig_bbio->file_offset;
- if (!(orig_bbio->bio.bi_opf & REQ_BTRFS_ONE_ORDERED))
- orig_bbio->file_offset += map_length;
-
+ orig_bbio->file_offset += map_length;
+ if (bbio_has_ordered_extent(bbio)) {
+ refcount_inc(&orig_bbio->ordered->refs);
+ bbio->ordered = orig_bbio->ordered;
+ }
atomic_inc(&orig_bbio->pending_ios);
return bbio;
}
+/* Free a bio that was never submitted to the underlying device. */
+static void btrfs_cleanup_bio(struct btrfs_bio *bbio)
+{
+ if (bbio_has_ordered_extent(bbio))
+ btrfs_put_ordered_extent(bbio->ordered);
+ bio_put(&bbio->bio);
+}
+
+static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
+{
+ if (bbio_has_ordered_extent(bbio)) {
+ struct btrfs_ordered_extent *ordered = bbio->ordered;
+
+ bbio->end_io(bbio);
+ btrfs_put_ordered_extent(ordered);
+ } else {
+ bbio->end_io(bbio);
+ }
+}
+
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
+{
+ bbio->bio.bi_status = status;
+ __btrfs_bio_end_io(bbio);
+}
+
static void btrfs_orig_write_end_io(struct bio *bio);
static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
if (bbio->bio.bi_status)
btrfs_bbio_propagate_error(bbio, orig_bbio);
- bio_put(&bbio->bio);
+ btrfs_cleanup_bio(bbio);
bbio = orig_bbio;
}
if (atomic_dec_and_test(&bbio->pending_ios))
- bbio->end_io(bbio);
+ __btrfs_bio_end_io(bbio);
}
static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work);
/* Metadata reads are checked and repaired by the submitter. */
- if (bbio->inode && !(bbio->bio.bi_opf & REQ_META))
+ if (is_data_bbio(bbio))
btrfs_check_read_bio(bbio, bbio->bio.bi_private);
else
btrfs_orig_bbio_end_io(bbio);
INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
} else {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
btrfs_record_physical_zoned(bbio);
btrfs_orig_bbio_end_io(bbio);
}
btrfs_bio_counter_dec(bioc->fs_info);
bbio->mirror_num = bioc->mirror_num;
- if (bio_op(bio) == REQ_OP_READ && bbio->inode &&
- !(bbio->bio.bi_opf & REQ_META))
+ if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio))
btrfs_check_read_bio(bbio, NULL);
else
btrfs_orig_bbio_end_io(bbio);
static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
struct btrfs_io_stripe *smap, int mirror_num)
{
- /* Do not leak our private flag into the block layer. */
- bio->bi_opf &= ~REQ_BTRFS_ONE_ORDERED;
-
if (!bioc) {
/* Single mirror read/write fast path. */
btrfs_bio(bio)->mirror_num = mirror_num;
bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
+ if (bio_op(bio) != REQ_OP_READ)
+ btrfs_bio(bio)->orig_physical = smap->physical;
bio->bi_private = smap->dev;
bio->bi_end_io = btrfs_simple_end_io;
btrfs_submit_dev_bio(smap->dev, bio);
static bool should_async_write(struct btrfs_bio *bbio)
{
- /*
- * If the I/O is not issued by fsync and friends, (->sync_writers != 0),
- * then try to defer the submission to a workqueue to parallelize the
- * checksum calculation.
- */
- if (atomic_read(&bbio->inode->sync_writers))
+ /* Submit synchronously if the checksum implementation is fast. */
+ if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
return false;
/*
- * Submit metadata writes synchronously if the checksum implementation
- * is fast, or we are on a zoned device that wants I/O to be submitted
- * in order.
+ * Try to defer the submission to a workqueue to parallelize the
+ * checksum calculation unless the I/O is issued synchronously.
*/
- if (bbio->bio.bi_opf & REQ_META) {
- struct btrfs_fs_info *fs_info = bbio->fs_info;
+ if (op_is_sync(bbio->bio.bi_opf))
+ return false;
- if (btrfs_is_zoned(fs_info))
- return false;
- if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
- return false;
- }
+ /* Zoned devices require I/O to be submitted in order. */
+ if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(bbio->fs_info))
+ return false;
return true;
}
btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
run_one_async_free);
- if (op_is_sync(bbio->bio.bi_opf))
- btrfs_queue_work(fs_info->hipri_workers, &async->work);
- else
- btrfs_queue_work(fs_info->workers, &async->work);
+ btrfs_queue_work(fs_info->workers, &async->work);
return true;
}
struct btrfs_fs_info *fs_info = bbio->fs_info;
struct btrfs_bio *orig_bbio = bbio;
struct bio *bio = &bbio->bio;
- u64 logical = bio->bi_iter.bi_sector << 9;
+ u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
u64 length = bio->bi_iter.bi_size;
u64 map_length = length;
bool use_append = btrfs_use_zone_append(bbio);
int error;
btrfs_bio_counter_inc_blocked(fs_info);
- error = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
- &bioc, &smap, &mirror_num, 1);
+ error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
+ &bioc, &smap, &mirror_num, 1);
if (error) {
ret = errno_to_blk_status(error);
goto fail;
* Save the iter for the end_io handler and preload the checksums for
* data reads.
*/
- if (bio_op(bio) == REQ_OP_READ && inode && !(bio->bi_opf & REQ_META)) {
+ if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) {
bbio->saved_iter = bio->bi_iter;
ret = btrfs_lookup_bio_sums(bbio);
if (ret)
if (use_append) {
bio->bi_opf &= ~REQ_OP_WRITE;
bio->bi_opf |= REQ_OP_ZONE_APPEND;
- ret = btrfs_bio_extract_ordered_extent(bbio);
- if (ret)
- goto fail_put_bio;
}
/*
ret = btrfs_bio_csum(bbio);
if (ret)
goto fail_put_bio;
+ } else if (use_append) {
+ ret = btrfs_alloc_dummy_sum(bbio);
+ if (ret)
+ goto fail_put_bio;
}
}
fail_put_bio:
if (map_length < length)
- bio_put(bio);
+ btrfs_cleanup_bio(bbio);
fail:
btrfs_bio_counter_dec(fs_info);
btrfs_bio_end_io(orig_bbio, ret);
projects / linux-block.git / blobdiff