From: Linus Torvalds Date: Tue, 10 Feb 2026 01:57:21 +0000 (-0800) Subject: Merge tag 'for-7.0/block-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git... X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=0c00ed308d0559fc216be0442a3df124e9e13533;p=thirdparty%2Fkernel%2Flinux.git Merge tag 'for-7.0/block-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux Pull block updates from Jens Axboe: - Support for batch request processing for ublk, improving the efficiency of the kernel/ublk server communication. This can yield nice 7-12% performance improvements - Support for integrity data for ublk - Various other ublk improvements and additions, including a ton of selftests additions and updated - Move the handling of blk-crypto software fallback from below the block layer to above it. This reduces the complexity of dealing with bio splitting - Series fixing a number of potential deadlocks in blk-mq related to the queue usage counter and writeback throttling and rq-qos debugfs handling - Add an async_depth queue attribute, to resolve a performance regression that's been around for a qhilw related to the scheduler depth handling - Only use task_work for IOPOLL completions on NVMe, if it is necessary to do so. An earlier fix for an issue resulted in all these completions being punted to task_work, to guarantee that completions were only run for a given io_uring ring when it was local to that ring. With the new changes, we can detect if it's necessary to use task_work or not, and avoid it if possible. - rnbd fixes: - Fix refcount underflow in device unmap path - Handle PREFLUSH and NOUNMAP flags properly in protocol - Fix server-side bi_size for special IOs - Zero response buffer before use - Fix trace format for flags - Add .release to rnbd_dev_ktype - MD pull requests via Yu Kuai - Fix raid5_run() to return error when log_init() fails - Fix IO hang with degraded array with llbitmap - Fix percpu_ref not resurrected on suspend timeout in llbitmap - Fix GPF in write_page caused by resize race - Fix NULL pointer dereference in process_metadata_update - Fix hang when stopping arrays with metadata through dm-raid - Fix any_working flag handling in raid10_sync_request - Refactor sync/recovery code path, improve error handling for badblocks, and remove unused recovery_disabled field - Consolidate mddev boolean fields into mddev_flags - Use mempool to allocate stripe_request_ctx and make sure max_sectors is not less than io_opt in raid5 - Fix return value of mddev_trylock - Fix memory leak in raid1_run() - Add Li Nan as mdraid reviewer - Move phys_vec definitions to the kernel types, mostly in preparation for some VFIO and RDMA changes - Improve the speed for secure erase for some devices - Various little rust updates - Various other minor fixes, improvements, and cleanups * tag 'for-7.0/block-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (162 commits) blk-mq: ABI/sysfs-block: fix docs build warnings selftests: ublk: organize test directories by test ID block: decouple secure erase size limit from discard size limit block: remove redundant kill_bdev() call in set_blocksize() blk-mq: add documentation for new queue attribute async_dpeth block, bfq: convert to use request_queue->async_depth mq-deadline: covert to use request_queue->async_depth kyber: covert to use request_queue->async_depth blk-mq: add a new queue sysfs attribute async_depth blk-mq: factor out a helper blk_mq_limit_depth() blk-mq-sched: unify elevators checking for async requests block: convert nr_requests to unsigned int block: don't use strcpy to copy blockdev name blk-mq-debugfs: warn about possible deadlock blk-mq-debugfs: add missing debugfs_mutex in blk_mq_debugfs_register_hctxs() blk-mq-debugfs: remove blk_mq_debugfs_unregister_rqos() blk-mq-debugfs: make blk_mq_debugfs_register_rqos() static blk-rq-qos: fix possible debugfs_mutex deadlock blk-mq-debugfs: factor out a helper to register debugfs for all rq_qos blk-wbt: fix possible deadlock to nest pcpu_alloc_mutex under q_usage_counter ... --- 0c00ed308d0559fc216be0442a3df124e9e13533 diff --cc drivers/nvme/host/pci.c index d86f2565a92ca,d87c56c62861e..80df992d1ae82 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@@ -822,36 -821,16 +822,34 @@@ static bool nvme_pci_prp_save_mapping(s { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + if (dma_use_iova(&iod->dma_state) || !dma_need_unmap(dma_dev)) + return true; + + if (!iod->nr_dma_vecs) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; + + iod->dma_vecs = mempool_alloc(nvmeq->dev->dmavec_mempool, + GFP_ATOMIC); + if (!iod->dma_vecs) { + iter->status = BLK_STS_RESOURCE; + return false; + } + } + + iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; + iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; + iod->nr_dma_vecs++; + return true; +} + +static bool nvme_pci_prp_iter_next(struct request *req, struct device *dma_dev, + struct blk_dma_iter *iter) +{ - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - if (iter->len) return true; - if (!blk_rq_dma_map_iter_next(req, dma_dev, &iod->dma_state, iter)) + if (!blk_rq_dma_map_iter_next(req, dma_dev, iter)) return false; - if (!dma_use_iova(&iod->dma_state) && dma_need_unmap(dma_dev)) { - iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; - iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; - iod->nr_dma_vecs++; - } - return true; + return nvme_pci_prp_save_mapping(req, dma_dev, iter); } static blk_status_t nvme_pci_setup_data_prp(struct request *req, diff --cc io_uring/rw.c index 3190c41bfdc95,ff3192f603f35..d10386f56d49e --- a/io_uring/rw.c +++ b/io_uring/rw.c @@@ -1323,11 -1315,17 +1323,17 @@@ static int io_uring_hybrid_poll(struct int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) { - struct io_wq_work_node *pos, *start, *prev; unsigned int poll_flags = 0; DEFINE_IO_COMP_BATCH(iob); + struct io_kiocb *req, *tmp; int nr_events = 0; + /* + * Store the polling io_ring_ctx so drivers can detect if they're + * completing a request in the same ring context that's polling. + */ + iob.poll_ctx = ctx; + /* * Only spin for completions if we don't have multiple devices hanging * off our complete list. diff --cc tools/testing/selftests/ublk/kublk.h index cae2e30f0cdd5,1faeccaaecae4..02f0c55d006b4 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@@ -223,10 -334,10 +334,10 @@@ static inline __u64 build_user_data(uns unsigned tgt_data, unsigned q_id, unsigned is_target_io) { /* we only have 7 bits to encode q_id */ - _Static_assert(UBLK_MAX_QUEUES_SHIFT <= 7); + _Static_assert(UBLK_MAX_QUEUES_SHIFT <= 7, "UBLK_MAX_QUEUES_SHIFT must be <= 7"); - assert(!(tag >> 16) && !(op >> 8) && !(tgt_data >> 16) && !(q_id >> 7)); + ublk_assert(!(tag >> 16) && !(op >> 8) && !(tgt_data >> 16) && !(q_id >> 7)); - return tag | (op << 16) | (tgt_data << 24) | + return tag | ((__u64)op << 16) | ((__u64)tgt_data << 24) | (__u64)q_id << 56 | (__u64)is_target_io << 63; }