virtio_blk_submit_multireq() fuses adjacent in-zone writes into a single request. On a zoned backend, a merged zone append request that straddles a zone boundary is rejected by the device because each write must stay within a single zone.
Add a bail condition to the merge coalescer: if combining the candidate request into the current batch would cross a zone boundary, flush the current batch and start a new one. Signed-off-by: Sam Li <[email protected]> --- block/block-backend.c | 11 +++++++++++ hw/block/virtio-blk.c | 22 +++++++++++++++++++++- include/system/block-backend-io.h | 1 + 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/block/block-backend.c b/block/block-backend.c index 37ba7e9fc4..049e70ddcb 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -2326,6 +2326,17 @@ uint32_t blk_get_request_alignment(BlockBackend *blk) return bs ? bs->bl.request_alignment : BDRV_SECTOR_SIZE; } +/* + * Returns the zone size in bytes for a zoned backend, or 0 if @blk does + * not present zoned geometry. + */ +uint64_t blk_get_zone_size(BlockBackend *blk) +{ + BlockDriverState *bs = blk_bs(blk); + IO_CODE(); + return bs ? bs->bl.zone_size : 0; +} + /* Returns the optimal write zeroes alignment, in bytes; guaranteed nonzero */ uint32_t blk_get_pwrite_zeroes_alignment(BlockBackend *blk) { diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index 6b92066aff..39750fa1c0 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -294,6 +294,9 @@ static void virtio_blk_submit_multireq(VirtIOBlock *s, MultiReqBuffer *mrb) int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0; uint32_t max_transfer; int64_t sector_num = 0; + uint64_t zone_size = blk_get_zone_size(s->blk); + bool zone_cross; + int64_t zone_sector, end_sector; if (mrb->num_reqs == 1) { submit_requests(s, mrb, 0, 1, -1); @@ -309,17 +312,34 @@ static void virtio_blk_submit_multireq(VirtIOBlock *s, MultiReqBuffer *mrb) for (i = 0; i < mrb->num_reqs; i++) { VirtIOBlockReq *req = mrb->reqs[i]; if (num_reqs > 0) { + zone_cross = false; + + /* + * On zoned backends, a single backend write must not span a zone + * boundary. Bail out of merging if combining req into the current + * batch would straddle a zone. + */ + if (zone_size > 0) { + zone_sector = zone_size / BDRV_SECTOR_SIZE; + end_sector = req->sector_num + + req->qiov.size / BDRV_SECTOR_SIZE - 1; + zone_cross = (sector_num / zone_sector) != + (end_sector / zone_sector); + } + /* * NOTE: We cannot merge the requests in below situations: * 1. requests are not sequential * 2. merge would exceed maximum number of IOVs * 3. merge would exceed maximum transfer length of backend device + * 4. merge would cross a zone boundary on a zoned backend */ if (sector_num + nb_sectors != req->sector_num || niov > blk_get_max_iov(s->blk) - req->qiov.niov || req->qiov.size > max_transfer || nb_sectors > (max_transfer - - req->qiov.size) / BDRV_SECTOR_SIZE) { + req->qiov.size) / BDRV_SECTOR_SIZE || + zone_cross) { submit_requests(s, mrb, start, num_reqs, niov); num_reqs = 0; } diff --git a/include/system/block-backend-io.h b/include/system/block-backend-io.h index fd84723d9d..78d410b8df 100644 --- a/include/system/block-backend-io.h +++ b/include/system/block-backend-io.h @@ -121,6 +121,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk); uint32_t blk_get_pwrite_zeroes_alignment(BlockBackend *blk); uint32_t blk_get_max_transfer(BlockBackend *blk); uint64_t blk_get_max_hw_transfer(BlockBackend *blk); +uint64_t blk_get_zone_size(BlockBackend *blk); int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, BlockBackend *blk_out, int64_t off_out, -- 2.53.0
