linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Kanchan Joshi <joshi.k@samsung.com>
To: axboe@kernel.dk, hch@lst.de
Cc: io-uring@vger.kernel.org, linux-nvme@lists.infradead.org,
	asml.silence@gmail.com, ming.lei@redhat.com, mcgrof@kernel.org,
	shr@fb.com, joshiiitr@gmail.com, anuj20.g@samsung.com,
	gost.dev@samsung.com
Subject: [PATCH v4 4/5] nvme: wire-up uring-cmd support for io-passthru on char-device.
Date: Thu,  5 May 2022 11:36:15 +0530	[thread overview]
Message-ID: <20220505060616.803816-5-joshi.k@samsung.com> (raw)
In-Reply-To: <20220505060616.803816-1-joshi.k@samsung.com>

Introduce handler for fops->uring_cmd(), implementing async passthru
on char device (/dev/ngX). The handler supports newly introduced
operation NVME_URING_CMD_IO. This operates on a new structure
nvme_uring_cmd, which is similar to struct nvme_passthru_cmd64 but
without the embedded 8b result field. This field is not needed since
uring-cmd allows to return additional result via big-CQE.

Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c        |   1 +
 drivers/nvme/host/ioctl.c       | 168 +++++++++++++++++++++++++++++++-
 drivers/nvme/host/multipath.c   |   1 +
 drivers/nvme/host/nvme.h        |   5 +
 include/uapi/linux/nvme_ioctl.h |  25 +++++
 5 files changed, 197 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e1846d04817f..682df98db341 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3699,6 +3699,7 @@ static const struct file_operations nvme_ns_chr_fops = {
 	.release	= nvme_ns_chr_release,
 	.unlocked_ioctl	= nvme_ns_chr_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
+	.uring_cmd	= nvme_ns_chr_uring_cmd,
 };
 
 static int nvme_add_ns_cdev(struct nvme_ns *ns)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 3531de8073a6..3687cb8d7428 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -26,6 +26,80 @@ static inline void *nvme_meta_from_bio(struct bio *bio)
 	return bip ? bvec_virt(bip->bip_vec) : NULL;
 }
 
+/*
+ * This overlays struct io_uring_cmd pdu.
+ * Expect build errors if this grows larger than that.
+ */
+struct nvme_uring_cmd_pdu {
+	union {
+		struct bio *bio;
+		struct request *req;
+	};
+	void *meta; /* kernel-resident buffer */
+	void __user *meta_buffer;
+	u32 meta_len;
+};
+
+static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
+		struct io_uring_cmd *ioucmd)
+{
+	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
+}
+
+static void nvme_uring_task_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;
+	bool write = req_op(req) == REQ_OP_DRV_OUT;
+	int status;
+	u64 result;
+
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+		status = -EINTR;
+	else
+		status = nvme_req(req)->status;
+
+	result = le64_to_cpu(nvme_req(req)->result.u64);
+	blk_mq_free_request(req);
+	if (bio)
+		blk_rq_unmap_user(bio);
+
+	if (pdu->meta && !status && !write) {
+		if (copy_to_user(pdu->meta_buffer, pdu->meta, pdu->meta_len))
+			status = -EFAULT;
+	}
+	kfree(pdu->meta);
+	io_uring_cmd_done(ioucmd, status, result);
+}
+
+static void nvme_end_async_pt(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;
+
+	pdu->req = req;
+	req->bio = bio;
+	/* this takes care of moving rest of completion-work to task context */
+	io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb);
+}
+
+static void nvme_setup_uring_cmd_data(struct request *rq,
+		struct io_uring_cmd *ioucmd, void __user *meta_buffer,
+		u32 meta_len)
+{
+	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
+
+	/* to free bio on completion, as req->bio will be null at that time */
+	pdu->bio = rq->bio;
+	pdu->meta = nvme_meta_from_bio(rq->bio);
+	pdu->meta_buffer = meta_buffer;
+	pdu->meta_len = meta_len;
+	rq->end_io_data = ioucmd;
+}
+
 static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
 		unsigned len, u32 seed, bool write)
 {
@@ -63,7 +137,8 @@ static void *nvme_add_user_metadata(struct bio *bio, 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, unsigned timeout, bool vec)
+		u32 meta_seed, unsigned timeout, bool vec, unsigned int rq_flags,
+		blk_mq_req_flags_t blk_flags)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -73,7 +148,7 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 	void *meta = NULL;
 	int ret;
 
-	req = blk_mq_alloc_request(q, nvme_req_op(cmd), 0);
+	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);
@@ -156,7 +231,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	struct request *req;
 
 	req = nvme_alloc_user_request(q, cmd, ubuffer, bufflen, meta_buffer,
-			meta_len, meta_seed, timeout, vec);
+			meta_len, meta_seed, timeout, vec, 0, 0);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	return nvme_execute_user_rq(req, meta_buffer, meta_len, result);
@@ -333,6 +408,55 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return status;
 }
 
+static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+		struct io_uring_cmd *ioucmd, unsigned int issue_flags)
+{
+	struct nvme_uring_cmd *cmd =
+		(struct nvme_uring_cmd *)ioucmd->cmd;
+	struct request_queue *q = ns ? ns->queue : ctrl->admin_q;
+	struct nvme_command c;
+	struct request *req;
+	unsigned int rq_flags = 0;
+	blk_mq_req_flags_t blk_flags = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (cmd->flags)
+		return -EINVAL;
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd->nsid))
+		return -EINVAL;
+
+	if (issue_flags & IO_URING_F_NONBLOCK) {
+		rq_flags = REQ_NOWAIT;
+		blk_flags = BLK_MQ_REQ_NOWAIT;
+	}
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = cmd->opcode;
+	c.common.flags = cmd->flags;
+	c.common.nsid = cpu_to_le32(cmd->nsid);
+	c.common.cdw2[0] = cpu_to_le32(cmd->cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cmd->cdw3);
+	c.common.cdw10 = cpu_to_le32(cmd->cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd->cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd->cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd->cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd->cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd->cdw15);
+
+	req = nvme_alloc_user_request(q, &c, nvme_to_user_ptr(cmd->addr),
+			cmd->data_len, nvme_to_user_ptr(cmd->metadata),
+			cmd->metadata_len, 0, cmd->timeout_ms ?
+			msecs_to_jiffies(cmd->timeout_ms) : 0, 0, rq_flags,
+			blk_flags);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	nvme_setup_uring_cmd_data(req, ioucmd, nvme_to_user_ptr(cmd->metadata),
+			cmd->metadata_len);
+	blk_execute_rq_nowait(req, 0, nvme_end_async_pt);
+	return -EIOCBQUEUED;
+}
+
 static bool is_ctrl_ioctl(unsigned int cmd)
 {
 	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
@@ -424,6 +548,32 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return __nvme_ioctl(ns, cmd, (void __user *)arg);
 }
 
+static void nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd,
+		unsigned int issue_flags)
+{
+	int ret;
+
+	BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu));
+
+	switch (ioucmd->cmd_op) {
+	case NVME_URING_CMD_IO:
+		ret = nvme_uring_cmd_io(ns->ctrl, ns, ioucmd, issue_flags);
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	if (ret != -EIOCBQUEUED)
+		io_uring_cmd_done(ioucmd, ret, 0);
+}
+
+void nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
+{
+	struct nvme_ns *ns = container_of(file_inode(ioucmd->file)->i_cdev,
+			struct nvme_ns, cdev);
+	nvme_ns_uring_cmd(ns, ioucmd, issue_flags);
+}
+
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
 		void __user *argp, struct nvme_ns_head *head, int srcu_idx)
@@ -490,6 +640,18 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
+void nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
+		unsigned int issue_flags)
+{
+	struct cdev *cdev = file_inode(ioucmd->file)->i_cdev;
+	struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev);
+	int srcu_idx = srcu_read_lock(&head->srcu);
+	struct nvme_ns *ns = nvme_find_path(head);
+
+	if (ns)
+		nvme_ns_uring_cmd(ns, ioucmd, issue_flags);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d464fdf978fb..d3e2440d8abb 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -437,6 +437,7 @@ static const struct file_operations nvme_ns_head_chr_fops = {
 	.release	= nvme_ns_head_chr_release,
 	.unlocked_ioctl	= nvme_ns_head_chr_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
+	.uring_cmd	= nvme_ns_head_chr_uring_cmd,
 };
 
 static int nvme_add_ns_head_cdev(struct nvme_ns_head *head)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a2b53ca63335..761ad6c629c4 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -16,6 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/t10-pi.h>
+#include <linux/io_uring.h>
 
 #include <trace/events/block.h>
 
@@ -782,6 +783,10 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
 		unsigned long arg);
 long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 		unsigned long arg);
+void nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd,
+		unsigned int issue_flags);
+void nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
+		unsigned int issue_flags);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index b2e43185e3b5..04e458c649ab 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 {
 	__u64	result;
 };
 
+/* same as struct nvme_passthru_cmd64, minus the 8b result field */
+struct nvme_uring_cmd {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u32   rsvd2;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -83,4 +105,7 @@ struct nvme_passthru_cmd64 {
 #define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 #define NVME_IOCTL_IO64_CMD_VEC	_IOWR('N', 0x49, struct nvme_passthru_cmd64)
 
+/* io_uring async commands: */
+#define NVME_URING_CMD_IO	_IOWR('N', 0x80, struct nvme_uring_cmd)
+
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */
-- 
2.25.1



  parent reply	other threads:[~2022-05-05  6:15 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20220505061142epcas5p2c943572766bfd5088138fe0f7873c96c@epcas5p2.samsung.com>
2022-05-05  6:06 ` [PATCH v4 0/5] io_uring passthrough for nvme Kanchan Joshi
     [not found]   ` <CGME20220505061144epcas5p3821a9516dad2b5eff5a25c56dbe164df@epcas5p3.samsung.com>
2022-05-05  6:06     ` [PATCH v4 1/5] fs,io_uring: add infrastructure for uring-cmd Kanchan Joshi
2022-05-05 12:52       ` Jens Axboe
2022-05-05 13:48         ` Ming Lei
2022-05-05 13:54           ` Jens Axboe
2022-05-05 13:29       ` Christoph Hellwig
2022-05-05 16:17       ` Jens Axboe
2022-05-05 17:04         ` Jens Axboe
2022-05-06  7:12         ` Kanchan Joshi
2022-05-10 14:23         ` Kanchan Joshi
2022-05-10 14:35           ` Jens Axboe
     [not found]   ` <CGME20220505061146epcas5p3919c48d58d353a62a5858ee10ad162a0@epcas5p3.samsung.com>
2022-05-05  6:06     ` [PATCH v4 2/5] block: wire-up support for passthrough plugging Kanchan Joshi
2022-05-05 14:21       ` Ming Lei
     [not found]   ` <CGME20220505061148epcas5p188618b5b15a95cbe48c8c1559a18c994@epcas5p1.samsung.com>
2022-05-05  6:06     ` [PATCH v4 3/5] nvme: refactor nvme_submit_user_cmd() Kanchan Joshi
2022-05-05 13:30       ` Christoph Hellwig
2022-05-05 18:37       ` Clay Mayers
2022-05-05 19:03         ` Jens Axboe
2022-05-05 19:11           ` Jens Axboe
2022-05-05 19:30             ` Clay Mayers
2022-05-05 19:31               ` Jens Axboe
2022-05-05 19:50                 ` hch
2022-05-05 20:44                   ` Jens Axboe
2022-05-06  5:56                     ` hch
     [not found]   ` <CGME20220505061150epcas5p2b60880c541a4b2f144c348834c7cbf0b@epcas5p2.samsung.com>
2022-05-05  6:06     ` Kanchan Joshi [this message]
2022-05-05 13:33       ` [PATCH v4 4/5] nvme: wire-up uring-cmd support for io-passthru on char-device Christoph Hellwig
2022-05-05 13:38       ` Jens Axboe
2022-05-05 13:42         ` Christoph Hellwig
2022-05-05 13:50           ` Jens Axboe
2022-05-05 17:23             ` Jens Axboe
2022-05-06  8:28               ` Christoph Hellwig
2022-05-06 13:37                 ` Jens Axboe
2022-05-06 14:50                   ` Christoph Hellwig
2022-05-06 14:57                     ` Jens Axboe
2022-05-07  5:03                       ` Christoph Hellwig
2022-05-07 12:53                         ` Jens Axboe
2022-05-09  6:00                           ` Christoph Hellwig
2022-05-09 12:52                             ` Jens Axboe
     [not found]   ` <CGME20220505061151epcas5p2523dc661a0daf3e6185dee771eade393@epcas5p2.samsung.com>
2022-05-05  6:06     ` [PATCH v4 5/5] nvme: add vectored-io support for uring-cmd Kanchan Joshi
2022-05-05 18:20   ` [PATCH v4 0/5] io_uring passthrough for nvme Jens Axboe
2022-05-05 18:29     ` Jens Axboe
2022-05-06  6:42       ` Kanchan Joshi
2022-05-06 13:14         ` Jens Axboe
2022-05-10  7:20     ` Christoph Hellwig
2022-05-10 12:29       ` Jens Axboe
2022-05-10 14:21         ` Kanchan Joshi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220505060616.803816-5-joshi.k@samsung.com \
    --to=joshi.k@samsung.com \
    --cc=anuj20.g@samsung.com \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=gost.dev@samsung.com \
    --cc=hch@lst.de \
    --cc=io-uring@vger.kernel.org \
    --cc=joshiiitr@gmail.com \
    --cc=linux-nvme@lists.infradead.org \
    --cc=mcgrof@kernel.org \
    --cc=ming.lei@redhat.com \
    --cc=shr@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).