From de671d6116b5210097cd6fbb877bac92536f265b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 21 Sep 2022 15:19:54 -0600 Subject: block: change request end_io handler to pass back a return value Everything is just converted to returning RQ_END_IO_NONE, and there should be no functional changes with this patch. In preparation for allowing the end_io handler to pass ownership back to the block layer, rather than retain ownership of the request. Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 6 ++++-- drivers/nvme/host/ioctl.c | 5 ++++- drivers/nvme/host/pci.c | 12 ++++++++---- drivers/nvme/target/passthru.c | 5 +++-- 4 files changed, 19 insertions(+), 9 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0f05b61a30fe..965a4c3e9d44 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1172,7 +1172,8 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2); } -static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) +static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, + blk_status_t status) { struct nvme_ctrl *ctrl = rq->end_io_data; unsigned long flags; @@ -1184,7 +1185,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) dev_err(ctrl->device, "failed nvme_keep_alive_end_io error=%d\n", status); - return; + return RQ_END_IO_NONE; } ctrl->comp_seen = false; @@ -1195,6 +1196,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) nvme_queue_keep_alive_work(ctrl); + return RQ_END_IO_NONE; } static void nvme_keep_alive_work(struct work_struct *work) diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 357791ff0623..2995789d5f9d 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -392,7 +392,8 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) io_uring_cmd_done(ioucmd, status, result); } -static void nvme_uring_cmd_end_io(struct request *req, blk_status_t err) +static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, + blk_status_t err) { struct io_uring_cmd *ioucmd = req->end_io_data; struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); @@ -411,6 +412,8 @@ static void nvme_uring_cmd_end_io(struct request *req, blk_status_t err) nvme_uring_task_cb(ioucmd); else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); + + return RQ_END_IO_NONE; } static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f9af99b7e672..7bbffd2a9beb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1268,7 +1268,7 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid) return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid); } -static void abort_endio(struct request *req, blk_status_t error) +static enum rq_end_io_ret abort_endio(struct request *req, blk_status_t error) { struct nvme_queue *nvmeq = req->mq_hctx->driver_data; @@ -1276,6 +1276,7 @@ static void abort_endio(struct request *req, blk_status_t error) "Abort status: 0x%x", nvme_req(req)->status); atomic_inc(&nvmeq->dev->ctrl.abort_limit); blk_mq_free_request(req); + return RQ_END_IO_NONE; } static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) @@ -2447,22 +2448,25 @@ out_unlock: return result; } -static void nvme_del_queue_end(struct request *req, blk_status_t error) +static enum rq_end_io_ret nvme_del_queue_end(struct request *req, + blk_status_t error) { struct nvme_queue *nvmeq = req->end_io_data; blk_mq_free_request(req); complete(&nvmeq->delete_done); + return RQ_END_IO_NONE; } -static void nvme_del_cq_end(struct request *req, blk_status_t error) +static enum rq_end_io_ret nvme_del_cq_end(struct request *req, + blk_status_t error) { struct nvme_queue *nvmeq = req->end_io_data; if (error) set_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags); - nvme_del_queue_end(req, error); + return nvme_del_queue_end(req, error); } static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 94d3153bae54..79af5140af8b 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -245,14 +245,15 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) nvme_passthru_end(ctrl, effects, req->cmd, status); } -static void nvmet_passthru_req_done(struct request *rq, - blk_status_t blk_status) +static enum rq_end_io_ret nvmet_passthru_req_done(struct request *rq, + blk_status_t blk_status) { struct nvmet_req *req = rq->end_io_data; req->cqe->result = nvme_req(rq)->result; nvmet_req_complete(req, nvme_req(rq)->status); blk_mq_free_request(rq); + return RQ_END_IO_NONE; } static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) -- cgit v1.2.3 From c0a7ba77e81b8440d10f38559a5e1d219ff7e87c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 21 Sep 2022 08:26:26 -0600 Subject: nvme: split out metadata vs non metadata end_io uring_cmd completions By splitting up the metadata and non-metadata end_io handling, we can remove any request dependencies on the normal non-metadata IO path. This is in preparation for enabling the normal IO passthrough path to pass the ownership of the request back to the block layer. Reviewed-by: Christoph Hellwig Reviewed-by: Anuj Gupta Reviewed-by: Sagi Grimberg Reviewed-by: Keith Busch Co-developed-by: Stefan Roesch Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 79 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 61 insertions(+), 18 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 2995789d5f9d..f9d1f7e4d6d1 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -356,9 +356,15 @@ struct nvme_uring_cmd_pdu { struct bio *bio; struct request *req; }; - void *meta; /* kernel-resident buffer */ - void __user *meta_buffer; u32 meta_len; + u32 nvme_status; + union { + struct { + void *meta; /* kernel-resident buffer */ + void __user *meta_buffer; + }; + u64 result; + } u; }; static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( @@ -367,11 +373,10 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; } -static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); struct request *req = pdu->req; - struct bio *bio = req->bio; int status; u64 result; @@ -382,27 +387,39 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) result = le64_to_cpu(nvme_req(req)->result.u64); - if (pdu->meta) - status = nvme_finish_user_metadata(req, pdu->meta_buffer, - pdu->meta, pdu->meta_len, status); - if (bio) - blk_rq_unmap_user(bio); + if (pdu->meta_len) + status = nvme_finish_user_metadata(req, pdu->u.meta_buffer, + pdu->u.meta, pdu->meta_len, status); + if (req->bio) + blk_rq_unmap_user(req->bio); blk_mq_free_request(req); io_uring_cmd_done(ioucmd, status, result); } +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + + if (pdu->bio) + blk_rq_unmap_user(pdu->bio); + + io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result); +} + static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, blk_status_t err) { struct io_uring_cmd *ioucmd = req->end_io_data; struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - /* extract bio before reusing the same field for request */ - struct bio *bio = pdu->bio; void *cookie = READ_ONCE(ioucmd->cookie); - pdu->req = req; - req->bio = bio; + req->bio = pdu->bio; + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + pdu->nvme_status = -EINTR; + else + pdu->nvme_status = nvme_req(req)->status; + pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64); /* * For iopoll, complete it directly. @@ -413,6 +430,29 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); + blk_mq_free_request(req); + return RQ_END_IO_NONE; +} + +static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, + blk_status_t err) +{ + struct io_uring_cmd *ioucmd = req->end_io_data; + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + void *cookie = READ_ONCE(ioucmd->cookie); + + req->bio = pdu->bio; + pdu->req = req; + + /* + * For iopoll, complete it directly. + * Otherwise, move the completion to task work. + */ + if (cookie != NULL && blk_rq_is_poll(req)) + nvme_uring_task_meta_cb(ioucmd); + else + io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb); + return RQ_END_IO_NONE; } @@ -474,8 +514,6 @@ retry: blk_flags); if (IS_ERR(req)) return PTR_ERR(req); - req->end_io = nvme_uring_cmd_end_io; - req->end_io_data = ioucmd; if (issue_flags & IO_URING_F_IOPOLL && rq_flags & REQ_POLLED) { if (unlikely(!req->bio)) { @@ -490,10 +528,15 @@ retry: } /* to free bio on completion, as req->bio will be null at that time */ pdu->bio = req->bio; - pdu->meta = meta; - pdu->meta_buffer = nvme_to_user_ptr(d.metadata); pdu->meta_len = d.metadata_len; - + req->end_io_data = ioucmd; + if (pdu->meta_len) { + pdu->u.meta = meta; + pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata); + req->end_io = nvme_uring_cmd_end_io_meta; + } else { + req->end_io = nvme_uring_cmd_end_io; + } blk_execute_rq_nowait(req, false); return -EIOCBQUEUED; } -- cgit v1.2.3 From 851eb780decb7180bcf09fad0035cba9aae669df Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Sep 2022 11:41:51 -0600 Subject: nvme: enable batched completions of passthrough IO Now that the normal passthrough end_io path doesn't need the request anymore, we can kill the explicit blk_mq_free_request() and just pass back RQ_END_IO_FREE instead. This enables the batched completion from freeing batches of requests at the time. This brings passthrough IO performance at least on par with bdev based O_DIRECT with io_uring. With this and batche allocations, peak performance goes from 110M IOPS to 122M IOPS. For IRQ based, passthrough is now also about 10% faster than previously, going from ~61M to ~67M IOPS. Reviewed-by: Anuj Gupta Reviewed-by: Sagi Grimberg Reviewed-by: Keith Busch Co-developed-by: Stefan Roesch Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index f9d1f7e4d6d1..914b142b6f2b 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -430,8 +430,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); - blk_mq_free_request(req); - return RQ_END_IO_NONE; + return RQ_END_IO_FREE; } static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, -- cgit v1.2.3 From 7f05635764390d5f811971af9f4c89b794032c80 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Fri, 30 Sep 2022 11:57:42 +0530 Subject: nvme: Use blk_rq_map_user_io helper User blk_rq_map_user_io instead of duplicating the same code at different places Signed-off-by: Anuj Gupta Link: https://lore.kernel.org/r/20220930062749.152261-6-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 914b142b6f2b..3746a02a88ef 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -88,22 +88,8 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, nvme_req(req)->flags |= NVME_REQ_USERCMD; if (ubuffer && bufflen) { - if (!vec) - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, - GFP_KERNEL); - else { - struct iovec fast_iov[UIO_FASTIOV]; - struct iovec *iov = fast_iov; - struct iov_iter iter; - - ret = import_iovec(rq_data_dir(req), ubuffer, bufflen, - UIO_FASTIOV, &iov, &iter); - if (ret < 0) - goto out; - ret = blk_rq_map_user_iov(q, req, NULL, &iter, - GFP_KERNEL); - kfree(iov); - } + ret = blk_rq_map_user_io(req, NULL, ubuffer, bufflen, + GFP_KERNEL, vec, 0, 0, rq_data_dir(req)); if (ret) goto out; bio = req->bio; -- cgit v1.2.3 From 38c0ddab7b93daa90c046d0b9064a34fb0e586e5 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 30 Sep 2022 11:57:43 +0530 Subject: nvme: refactor nvme_add_user_metadata Pass struct request rather than bio. It helps to kill a parameter, and some processing clean-up too. Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220930062749.152261-7-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 3746a02a88ef..bcaa6b3f97ca 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -20,19 +20,20 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval) return (void __user *)ptrval; } -static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf, - unsigned len, u32 seed, bool write) +static void *nvme_add_user_metadata(struct request *req, void __user *ubuf, + unsigned len, u32 seed) { struct bio_integrity_payload *bip; int ret = -ENOMEM; void *buf; + struct bio *bio = req->bio; buf = kmalloc(len, GFP_KERNEL); if (!buf) goto out; ret = -EFAULT; - if (write && copy_from_user(buf, ubuf, len)) + if ((req_op(req) == REQ_OP_DRV_OUT) && copy_from_user(buf, ubuf, len)) goto out_free_meta; bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); @@ -45,9 +46,13 @@ static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf, bip->bip_iter.bi_sector = seed; ret = bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)); - if (ret == len) - return buf; - ret = -ENOMEM; + if (ret != len) { + ret = -ENOMEM; + goto out_free_meta; + } + + req->cmd_flags |= REQ_INTEGRITY; + return buf; out_free_meta: kfree(buf); out: @@ -70,7 +75,6 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, u32 meta_seed, void **metap, unsigned timeout, bool vec, blk_opf_t rq_flags, blk_mq_req_flags_t blk_flags) { - bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; struct block_device *bdev = ns ? ns->disk->part0 : NULL; struct request *req; @@ -96,13 +100,12 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, if (bdev) bio_set_dev(bio, bdev); if (bdev && meta_buffer && meta_len) { - meta = nvme_add_user_metadata(bio, meta_buffer, meta_len, - meta_seed, write); + meta = nvme_add_user_metadata(req, meta_buffer, + meta_len, meta_seed); if (IS_ERR(meta)) { ret = PTR_ERR(meta); goto out_unmap; } - req->cmd_flags |= REQ_INTEGRITY; *metap = meta; } } -- cgit v1.2.3 From 470e900c8036ff1aafeb5f06f3cb7a375a081399 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 30 Sep 2022 11:57:44 +0530 Subject: nvme: refactor nvme_alloc_request nvme_alloc_request expects a large number of parameters. Split this out into two functions to reduce number of parameters. First one retains the name nvme_alloc_request, while second one is named nvme_map_user_request. Signed-off-by: Kanchan Joshi Signed-off-by: Anuj Gupta Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220930062749.152261-8-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 90 ++++++++++++++++++++++++++++------------------- 1 file changed, 53 insertions(+), 37 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index bcaa6b3f97ca..3f1e7af19716 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -70,54 +70,57 @@ static int nvme_finish_user_metadata(struct request *req, void __user *ubuf, } static struct request *nvme_alloc_user_request(struct request_queue *q, - struct nvme_command *cmd, void __user *ubuffer, - unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, void **metap, unsigned timeout, bool vec, - blk_opf_t rq_flags, blk_mq_req_flags_t blk_flags) + struct nvme_command *cmd, blk_opf_t rq_flags, + blk_mq_req_flags_t blk_flags) { - struct nvme_ns *ns = q->queuedata; - struct block_device *bdev = ns ? ns->disk->part0 : NULL; struct request *req; - struct bio *bio = NULL; - void *meta = NULL; - int ret; req = blk_mq_alloc_request(q, nvme_req_op(cmd) | rq_flags, blk_flags); if (IS_ERR(req)) return req; nvme_init_request(req, cmd); - - if (timeout) - req->timeout = timeout; nvme_req(req)->flags |= NVME_REQ_USERCMD; + return req; +} - if (ubuffer && bufflen) { - ret = blk_rq_map_user_io(req, NULL, ubuffer, bufflen, - GFP_KERNEL, vec, 0, 0, rq_data_dir(req)); - if (ret) - goto out; - bio = req->bio; - if (bdev) - bio_set_dev(bio, bdev); - if (bdev && meta_buffer && meta_len) { - meta = nvme_add_user_metadata(req, meta_buffer, - meta_len, meta_seed); - if (IS_ERR(meta)) { - ret = PTR_ERR(meta); - goto out_unmap; - } - *metap = meta; +static int nvme_map_user_request(struct request *req, void __user *ubuffer, + unsigned bufflen, void __user *meta_buffer, unsigned meta_len, + u32 meta_seed, void **metap, bool vec) +{ + struct request_queue *q = req->q; + struct nvme_ns *ns = q->queuedata; + struct block_device *bdev = ns ? ns->disk->part0 : NULL; + struct bio *bio = NULL; + void *meta = NULL; + int ret; + + ret = blk_rq_map_user_io(req, NULL, ubuffer, bufflen, GFP_KERNEL, vec, + 0, 0, rq_data_dir(req)); + + if (ret) + goto out; + bio = req->bio; + if (bdev) + bio_set_dev(bio, bdev); + + if (bdev && meta_buffer && meta_len) { + meta = nvme_add_user_metadata(req, meta_buffer, meta_len, + meta_seed); + if (IS_ERR(meta)) { + ret = PTR_ERR(meta); + goto out_unmap; } + *metap = meta; } - return req; + return ret; out_unmap: if (bio) blk_rq_unmap_user(bio); out: blk_mq_free_request(req); - return ERR_PTR(ret); + return ret; } static int nvme_submit_user_cmd(struct request_queue *q, @@ -132,11 +135,18 @@ static int nvme_submit_user_cmd(struct request_queue *q, u32 effects; int ret; - req = nvme_alloc_user_request(q, cmd, ubuffer, bufflen, meta_buffer, - meta_len, meta_seed, &meta, timeout, vec, 0, 0); + req = nvme_alloc_user_request(q, cmd, 0, 0); if (IS_ERR(req)) return PTR_ERR(req); + req->timeout = timeout; + if (ubuffer && bufflen) { + ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer, + meta_len, meta_seed, &meta, vec); + if (ret) + return ret; + } + bio = req->bio; ctrl = nvme_req(req)->ctrl; @@ -456,6 +466,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, blk_opf_t rq_flags = 0; blk_mq_req_flags_t blk_flags = 0; void *meta = NULL; + int ret; if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -495,13 +506,18 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, rq_flags |= REQ_POLLED; retry: - req = nvme_alloc_user_request(q, &c, nvme_to_user_ptr(d.addr), - d.data_len, nvme_to_user_ptr(d.metadata), - d.metadata_len, 0, &meta, d.timeout_ms ? - msecs_to_jiffies(d.timeout_ms) : 0, vec, rq_flags, - blk_flags); + req = nvme_alloc_user_request(q, &c, rq_flags, blk_flags); if (IS_ERR(req)) return PTR_ERR(req); + req->timeout = d.timeout_ms ? msecs_to_jiffies(d.timeout_ms) : 0; + + if (d.addr && d.data_len) { + ret = nvme_map_user_request(req, nvme_to_user_ptr(d.addr), + d.data_len, nvme_to_user_ptr(d.metadata), + d.metadata_len, 0, &meta, vec); + if (ret) + return ret; + } if (issue_flags & IO_URING_F_IOPOLL && rq_flags & REQ_POLLED) { if (unlikely(!req->bio)) { -- cgit v1.2.3 From 4d174486820e625fa85bac5d4235d4b4cb659866 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 30 Sep 2022 11:57:48 +0530 Subject: nvme: pass ubuffer as an integer This is a prep patch. Modify nvme_submit_user_cmd and nvme_map_user_request to take ubuffer as plain integer argument, and do away with nvme_to_user_ptr conversion in callers. Signed-off-by: Anuj Gupta Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220930062749.152261-12-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 3f1e7af19716..7a41caa9bfd2 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -83,9 +83,10 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, return req; } -static int nvme_map_user_request(struct request *req, void __user *ubuffer, +static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, void **metap, bool vec) + u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd, + bool vec) { struct request_queue *q = req->q; struct nvme_ns *ns = q->queuedata; @@ -94,8 +95,8 @@ static int nvme_map_user_request(struct request *req, void __user *ubuffer, void *meta = NULL; int ret; - ret = blk_rq_map_user_io(req, NULL, ubuffer, bufflen, GFP_KERNEL, vec, - 0, 0, rq_data_dir(req)); + ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer), bufflen, + GFP_KERNEL, vec, 0, 0, rq_data_dir(req)); if (ret) goto out; @@ -124,7 +125,7 @@ out: } static int nvme_submit_user_cmd(struct request_queue *q, - struct nvme_command *cmd, void __user *ubuffer, + struct nvme_command *cmd, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, u64 *result, unsigned timeout, bool vec) { @@ -142,7 +143,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, req->timeout = timeout; if (ubuffer && bufflen) { ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer, - meta_len, meta_seed, &meta, vec); + meta_len, meta_seed, &meta, NULL, vec); if (ret) return ret; } @@ -226,7 +227,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.appmask = cpu_to_le16(io.appmask); return nvme_submit_user_cmd(ns->queue, &c, - nvme_to_user_ptr(io.addr), length, + io.addr, length, metadata, meta_len, lower_32_bits(io.slba), NULL, 0, false); } @@ -280,7 +281,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, timeout = msecs_to_jiffies(cmd.timeout_ms); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - nvme_to_user_ptr(cmd.addr), cmd.data_len, + cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, 0, &result, timeout, false); @@ -326,7 +327,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, timeout = msecs_to_jiffies(cmd.timeout_ms); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - nvme_to_user_ptr(cmd.addr), cmd.data_len, + cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, 0, &cmd.result, timeout, vec); @@ -512,9 +513,9 @@ retry: req->timeout = d.timeout_ms ? msecs_to_jiffies(d.timeout_ms) : 0; if (d.addr && d.data_len) { - ret = nvme_map_user_request(req, nvme_to_user_ptr(d.addr), + ret = nvme_map_user_request(req, d.addr, d.data_len, nvme_to_user_ptr(d.metadata), - d.metadata_len, 0, &meta, vec); + d.metadata_len, 0, &meta, ioucmd, vec); if (ret) return ret; } -- cgit v1.2.3 From 23fd22e55b767be9c31fda57205afb2023cd6aad Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 30 Sep 2022 11:57:49 +0530 Subject: nvme: wire up fixed buffer support for nvme passthrough if io_uring sends passthrough command with IORING_URING_CMD_FIXED flag, use the pre-registered buffer for IO (non-vectored variant). Pass the buffer/length to io_uring and get the bvec iterator for the range. Next, pass this bvec to block-layer and obtain a bio/request for subsequent processing. Signed-off-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220930062749.152261-13-anuj20.g@samsung.com Signed-off-by: Jens Axboe --- drivers/nvme/host/ioctl.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 7a41caa9bfd2..81f5550b670d 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -95,8 +95,22 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, void *meta = NULL; int ret; - ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer), bufflen, - GFP_KERNEL, vec, 0, 0, rq_data_dir(req)); + if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) { + struct iov_iter iter; + + /* fixedbufs is only for non-vectored io */ + if (WARN_ON_ONCE(vec)) + return -EINVAL; + ret = io_uring_cmd_import_fixed(ubuffer, bufflen, + rq_data_dir(req), &iter, ioucmd); + if (ret < 0) + goto out; + ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL); + } else { + ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer), + bufflen, GFP_KERNEL, vec, 0, 0, + rq_data_dir(req)); + } if (ret) goto out; -- cgit v1.2.3