public inbox for [email protected]
 help / color / mirror / Atom feed
From: Kanchan Joshi <[email protected]>
To: [email protected], [email protected]
Cc: [email protected], [email protected],
	[email protected], [email protected], [email protected],
	[email protected], [email protected], [email protected],
	[email protected]
Subject: [RFC 5/5] nvme: wire-up support for async-passthru on char-device.
Date: Fri,  1 Apr 2022 16:33:10 +0530	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Introduce handler for fops->async_cmd(), implementing async passthru
on char device (/dev/ngX). The handler supports NVME_IOCTL_IO64_CMD.

Signed-off-by: Kanchan Joshi <[email protected]>
Signed-off-by: Anuj Gupta <[email protected]>
---
 drivers/nvme/host/core.c      |   1 +
 drivers/nvme/host/ioctl.c     | 187 ++++++++++++++++++++++++++++------
 drivers/nvme/host/multipath.c |   1 +
 drivers/nvme/host/nvme.h      |   3 +
 4 files changed, 161 insertions(+), 31 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 961a5f8a44d2..38b9630c2cb7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3665,6 +3665,7 @@ 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,
+	.async_cmd	= nvme_ns_chr_async_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 22314962842d..1d15694d411c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -19,6 +19,81 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval)
 	return (void __user *)ptrval;
 }
 
+/*
+ * 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;
+} __packed;
+
+static 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_pt_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;
+
+	/* we can free request */
+	blk_mq_free_request(req);
+	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);
+
+	result = le64_to_cpu(nvme_req(req)->result.u64);
+	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_pt_task_cb);
+}
+
+static void nvme_setup_uring_cmd_data(struct request *rq,
+		struct io_uring_cmd *ioucmd, void *meta,
+		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 = meta;
+	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)
 {
@@ -56,7 +131,8 @@ static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u64 *result, unsigned timeout)
+		u32 meta_seed, u64 *result, unsigned timeout,
+		struct io_uring_cmd *ioucmd)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -93,6 +169,12 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 		}
 	}
 
+	if (ioucmd) { /* async dispatch */
+		nvme_setup_uring_cmd_data(req, ioucmd, meta, meta_buffer,
+				meta_len);
+		blk_execute_rq_nowait(req, 0, nvme_end_async_pt);
+		return -EIOCBQUEUED;
+	}
 	ret = nvme_execute_passthru_rq(req);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
@@ -170,7 +252,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	return nvme_submit_user_cmd(ns->queue, &c,
 			nvme_to_user_ptr(io.addr), length,
-			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
+			metadata, meta_len, lower_32_bits(io.slba), NULL, 0, NULL);
 }
 
 static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -224,7 +306,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			nvme_to_user_ptr(cmd.addr), cmd.data_len,
 			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &result, timeout);
+			0, &result, timeout, NULL);
 
 	if (status >= 0) {
 		if (put_user(result, &ucmd->result))
@@ -235,45 +317,51 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 }
 
 static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-			struct nvme_passthru_cmd64 __user *ucmd)
+			struct nvme_passthru_cmd64 __user *ucmd,
+			struct io_uring_cmd *ioucmd)
 {
-	struct nvme_passthru_cmd64 cmd;
+	struct nvme_passthru_cmd64 cmd, *cptr;
 	struct nvme_command c;
 	unsigned timeout = 0;
 	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
-		return -EFAULT;
-	if (cmd.flags)
+	if (!ioucmd) {
+		if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+			return -EFAULT;
+		cptr = &cmd;
+	} else {
+		cptr = (struct nvme_passthru_cmd64 *)ioucmd->cmd;
+	}
+	if (cptr->flags)
 		return -EINVAL;
-	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cptr->nsid))
 		return -EINVAL;
 
 	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);
-
-	if (cmd.timeout_ms)
-		timeout = msecs_to_jiffies(cmd.timeout_ms);
+	c.common.opcode = cptr->opcode;
+	c.common.flags = cptr->flags;
+	c.common.nsid = cpu_to_le32(cptr->nsid);
+	c.common.cdw2[0] = cpu_to_le32(cptr->cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cptr->cdw3);
+	c.common.cdw10 = cpu_to_le32(cptr->cdw10);
+	c.common.cdw11 = cpu_to_le32(cptr->cdw11);
+	c.common.cdw12 = cpu_to_le32(cptr->cdw12);
+	c.common.cdw13 = cpu_to_le32(cptr->cdw13);
+	c.common.cdw14 = cpu_to_le32(cptr->cdw14);
+	c.common.cdw15 = cpu_to_le32(cptr->cdw15);
+
+	if (cptr->timeout_ms)
+		timeout = msecs_to_jiffies(cptr->timeout_ms);
 
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			nvme_to_user_ptr(cmd.addr), cmd.data_len,
-			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
-			0, &cmd.result, timeout);
+			nvme_to_user_ptr(cptr->addr), cptr->data_len,
+			nvme_to_user_ptr(cptr->metadata), cptr->metadata_len,
+			0, &cptr->result, timeout, ioucmd);
 
-	if (status >= 0) {
-		if (put_user(cmd.result, &ucmd->result))
+	if (!ioucmd && status >= 0) {
+		if (put_user(cptr->result, &ucmd->result))
 			return -EFAULT;
 	}
 
@@ -296,7 +384,7 @@ static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd,
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
 	case NVME_IOCTL_ADMIN64_CMD:
-		return nvme_user_cmd64(ctrl, NULL, argp);
+		return nvme_user_cmd64(ctrl, NULL, argp, NULL);
 	default:
 		return sed_ioctl(ctrl->opal_dev, cmd, argp);
 	}
@@ -340,7 +428,7 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, argp);
 	case NVME_IOCTL_IO64_CMD:
-		return nvme_user_cmd64(ns->ctrl, ns, argp);
+		return nvme_user_cmd64(ns->ctrl, ns, argp, NULL);
 	default:
 		return -ENOTTY;
 	}
@@ -369,6 +457,29 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return __nvme_ioctl(ns, cmd, (void __user *)arg);
 }
 
+static int nvme_ns_async_ioctl(struct nvme_ns *ns, struct io_uring_cmd *ioucmd)
+{
+	int ret;
+
+	switch (ioucmd->cmd_op) {
+	case NVME_IOCTL_IO64_CMD:
+		ret = nvme_user_cmd64(ns->ctrl, ns, NULL, ioucmd);
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	return ret;
+}
+
+int nvme_ns_chr_async_cmd(struct io_uring_cmd *ioucmd)
+{
+	struct nvme_ns *ns = container_of(file_inode(ioucmd->file)->i_cdev,
+			struct nvme_ns, cdev);
+	return nvme_ns_async_ioctl(ns, ioucmd);
+}
+
+
 #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)
@@ -435,6 +546,20 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
+
+int nvme_ns_head_chr_async_cmd(struct io_uring_cmd *ioucmd)
+{
+	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);
+	int ret = -EWOULDBLOCK;
+
+	if (ns)
+		ret = nvme_ns_async_ioctl(ns, ioucmd);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
@@ -480,7 +605,7 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
 	case NVME_IOCTL_ADMIN64_CMD:
-		return nvme_user_cmd64(ctrl, NULL, argp);
+		return nvme_user_cmd64(ctrl, NULL, argp, NULL);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f8bf6606eb2f..1d798d09456f 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -459,6 +459,7 @@ 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,
+	.async_cmd	= nvme_ns_head_chr_async_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 a162f6c6da6e..7b801c241d26 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>
 
@@ -751,6 +752,8 @@ 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);
+int nvme_ns_chr_async_cmd(struct io_uring_cmd *ioucmd);
+int nvme_ns_head_chr_async_cmd(struct io_uring_cmd *ioucmd);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
-- 
2.25.1


  parent reply	other threads:[~2022-04-01 14:11 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20220401110829epcas5p39f3cf4d3f6eb8a5c59794787a2b72b15@epcas5p3.samsung.com>
2022-04-01 11:03 ` [RFC 0/5] big-cqe based uring-passthru Kanchan Joshi
     [not found]   ` <CGME20220401110831epcas5p403bacabe8f7e5262356fdc1a2e66df90@epcas5p4.samsung.com>
2022-04-01 11:03     ` [RFC 1/5] io_uring: add support for 128-byte SQEs Kanchan Joshi
     [not found]   ` <CGME20220401110833epcas5p18e828a307a646cef5b7aa429be4396e0@epcas5p1.samsung.com>
2022-04-01 11:03     ` [RFC 2/5] fs: add file_operations->async_cmd() Kanchan Joshi
2022-04-04  7:09       ` Christoph Hellwig
     [not found]   ` <CGME20220401110834epcas5p4d1e5e8d1beb1a6205d670bbcb932bf77@epcas5p4.samsung.com>
2022-04-01 11:03     ` [RFC 3/5] io_uring: add infra and support for IORING_OP_URING_CMD Kanchan Joshi
2022-04-04  7:16       ` Christoph Hellwig
2022-04-04  8:20         ` Pavel Begunkov
2022-04-05  5:58           ` Christoph Hellwig
2022-04-06  6:37             ` Kanchan Joshi
2022-04-04 15:14         ` Kanchan Joshi
2022-04-05  6:00           ` Christoph Hellwig
2022-04-05 16:27             ` Kanchan Joshi
     [not found]   ` <CGME20220401110836epcas5p37bd59ab5a48cf77ca3ac05052a164b0b@epcas5p3.samsung.com>
2022-04-01 11:03     ` [RFC 4/5] io_uring: add support for big-cqe Kanchan Joshi
2022-04-04  7:07       ` Christoph Hellwig
2022-04-04 14:04         ` Kanchan Joshi
     [not found]   ` <CGME20220401110838epcas5p2c1a2e776923dfe5bf65a3e7946820150@epcas5p2.samsung.com>
2022-04-01 11:03     ` Kanchan Joshi [this message]
2022-04-04  7:20       ` [RFC 5/5] nvme: wire-up support for async-passthru on char-device Christoph Hellwig
2022-04-04 14:25         ` Kanchan Joshi
2022-04-05  6:02           ` Christoph Hellwig
2022-04-05 15:40             ` Jens Axboe
2022-04-05 15:49             ` Kanchan Joshi
2022-04-06  5:20               ` Kanchan Joshi
2022-04-06  5:23                 ` Christoph Hellwig
2022-04-23 17:53                 ` Christoph Hellwig
2022-04-25 17:38                   ` Kanchan Joshi
2022-04-29 13:16                     ` Kanchan Joshi
2022-04-04  7:21   ` [RFC 0/5] big-cqe based uring-passthru Christoph Hellwig
2022-04-05 15:37     ` 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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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