diff options
| -rw-r--r-- | Documentation/block/ublk.rst | 77 | ||||
| -rw-r--r-- | block/blk-merge.c | 26 | ||||
| -rw-r--r-- | block/blk-zoned.c | 8 | ||||
| -rw-r--r-- | drivers/block/loop.c | 11 | ||||
| -rw-r--r-- | drivers/nvme/host/ioctl.c | 21 | ||||
| -rw-r--r-- | include/linux/bio.h | 2 | ||||
| -rw-r--r-- | include/linux/bvec.h | 7 |
7 files changed, 114 insertions, 38 deletions
diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst index c368e1081b41..8c4030bcabb6 100644 --- a/Documentation/block/ublk.rst +++ b/Documentation/block/ublk.rst @@ -352,6 +352,83 @@ For reaching best IO performance, ublk server should align its segment parameter of `struct ublk_param_segment` with backend for avoiding unnecessary IO split, which usually hurts io_uring performance. +Auto Buffer Registration +------------------------ + +The ``UBLK_F_AUTO_BUF_REG`` feature automatically handles buffer registration +and unregistration for I/O requests, which simplifies the buffer management +process and reduces overhead in the ublk server implementation. + +This is another feature flag for using zero copy, and it is compatible with +``UBLK_F_SUPPORT_ZERO_COPY``. + +Feature Overview +~~~~~~~~~~~~~~~~ + +This feature automatically registers request buffers to the io_uring context +before delivering I/O commands to the ublk server and unregisters them when +completing I/O commands. This eliminates the need for manual buffer +registration/unregistration via ``UBLK_IO_REGISTER_IO_BUF`` and +``UBLK_IO_UNREGISTER_IO_BUF`` commands, then IO handling in ublk server +can avoid dependency on the two uring_cmd operations. + +IOs can't be issued concurrently to io_uring if there is any dependency +among these IOs. So this way not only simplifies ublk server implementation, +but also makes concurrent IO handling becomes possible by removing the +dependency on buffer registration & unregistration commands. + +Usage Requirements +~~~~~~~~~~~~~~~~~~ + +1. The ublk server must create a sparse buffer table on the same ``io_ring_ctx`` + used for ``UBLK_IO_FETCH_REQ`` and ``UBLK_IO_COMMIT_AND_FETCH_REQ``. If + uring_cmd is issued on a different ``io_ring_ctx``, manual buffer + unregistration is required. + +2. Buffer registration data must be passed via uring_cmd's ``sqe->addr`` with the + following structure:: + + struct ublk_auto_buf_reg { + __u16 index; /* Buffer index for registration */ + __u8 flags; /* Registration flags */ + __u8 reserved0; /* Reserved for future use */ + __u32 reserved1; /* Reserved for future use */ + }; + + ublk_auto_buf_reg_to_sqe_addr() is for converting the above structure into + ``sqe->addr``. + +3. All reserved fields in ``ublk_auto_buf_reg`` must be zeroed. + +4. Optional flags can be passed via ``ublk_auto_buf_reg.flags``. + +Fallback Behavior +~~~~~~~~~~~~~~~~~ + +If auto buffer registration fails: + +1. When ``UBLK_AUTO_BUF_REG_FALLBACK`` is enabled: + + - The uring_cmd is completed + - ``UBLK_IO_F_NEED_REG_BUF`` is set in ``ublksrv_io_desc.op_flags`` + - The ublk server must manually deal with the failure, such as, register + the buffer manually, or using user copy feature for retrieving the data + for handling ublk IO + +2. If fallback is not enabled: + + - The ublk I/O request fails silently + - The uring_cmd won't be completed + +Limitations +~~~~~~~~~~~ + +- Requires same ``io_ring_ctx`` for all operations +- May require manual buffer management in fallback cases +- io_ring_ctx buffer table has a max size of 16K, which may not be enough + in case that too many ublk devices are handled by this single io_ring_ctx + and each one has very large queue depth + References ========== diff --git a/block/blk-merge.c b/block/blk-merge.c index 3af1d284add5..70d704615be5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -998,20 +998,20 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, if (!plug || rq_list_empty(&plug->mq_list)) return false; - rq_list_for_each(&plug->mq_list, rq) { - if (rq->q == q) { - if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == - BIO_MERGE_OK) - return true; - break; - } + rq = plug->mq_list.tail; + if (rq->q == q) + return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == + BIO_MERGE_OK; + else if (!plug->multiple_queues) + return false; - /* - * Only keep iterating plug list for merges if we have multiple - * queues - */ - if (!plug->multiple_queues) - break; + rq_list_for_each(&plug->mq_list, rq) { + if (rq->q != q) + continue; + if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == + BIO_MERGE_OK) + return true; + break; } return false; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 8f15d1aa6eb8..351d659280e1 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1225,6 +1225,7 @@ void blk_zone_write_plug_bio_endio(struct bio *bio) if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) { bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= REQ_OP_ZONE_APPEND; + bio_clear_flag(bio, BIO_EMULATES_ZONE_APPEND); } /* @@ -1306,7 +1307,6 @@ again: spin_unlock_irqrestore(&zwplug->lock, flags); bdev = bio->bi_bdev; - submit_bio_noacct_nocheck(bio); /* * blk-mq devices will reuse the extra reference on the request queue @@ -1314,8 +1314,12 @@ again: * path for BIO-based devices will not do that. So drop this extra * reference here. */ - if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) + if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) { + bdev->bd_disk->fops->submit_bio(bio); blk_queue_exit(bdev->bd_disk->queue); + } else { + blk_mq_submit_bio(bio); + } put_zwplug: /* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f8d136684109..500840e4a74e 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1248,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS; lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS); - if (size_changed) { - loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, - lo->lo_backing_file); - loop_set_size(lo, new_size); - } - /* update the direct I/O flag if lo_offset changed */ loop_update_dio(lo); @@ -1261,6 +1255,11 @@ out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue, memflags); if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); + if (!err && size_changed) { + loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, + lo->lo_backing_file); + loop_set_size(lo, new_size); + } out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 0b50da2f1175..6b3ac8ae3f34 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, pdu->result = le64_to_cpu(nvme_req(req)->result.u64); /* - * For iopoll, complete it directly. Note that using the uring_cmd - * helper for this is safe only because we check blk_rq_is_poll(). - * As that returns false if we're NOT on a polled queue, then it's - * safe to use the polled completion helper. - * - * Otherwise, move the completion to task work. + * IOPOLL could potentially complete this request directly, but + * if multiple rings are polling on the same queue, then it's possible + * for one ring to find completions for another ring. Punting the + * completion via task_work will always direct it to the right + * location, rather than potentially complete requests for ringA + * under iopoll invocations from ringB. */ - if (blk_rq_is_poll(req)) { - if (pdu->bio) - blk_rq_unmap_user(pdu->bio); - io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); - } else { - io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); - } - + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); return RQ_END_IO_FREE; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 9c37c66ef9ca..46ffac5caab7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -291,7 +291,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, fi->folio = page_folio(bvec->bv_page); fi->offset = bvec->bv_offset + - PAGE_SIZE * (bvec->bv_page - &fi->folio->page); + PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); fi->_next = folio_next(fi->folio); diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 204b22a99c4b..0a80e1f9aa20 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -57,9 +57,12 @@ static inline void bvec_set_page(struct bio_vec *bv, struct page *page, * @offset: offset into the folio */ static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio, - unsigned int len, unsigned int offset) + size_t len, size_t offset) { - bvec_set_page(bv, &folio->page, len, offset); + unsigned long nr = offset / PAGE_SIZE; + + WARN_ON_ONCE(len > UINT_MAX); + bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE); } /** |