From: Kanchan Joshi <[email protected]>
To: [email protected], [email protected],
[email protected]
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected], [email protected],
[email protected]
Subject: [RFC 12/13] nvme: allow user passthrough commands to poll
Date: Mon, 20 Dec 2021 19:47:33 +0530 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
From: Keith Busch <[email protected]>
The block layer knows how to deal with polled requests. Let the NVMe
driver use the previously reserved user "flags" fields to define an
option to allocate the request from the polled hardware contexts. If
polling is not enabled, then the block layer will automatically fallback
to a non-polled request.[1]
[1] https://lore.kernel.org/linux-block/[email protected]/
Signed-off-by: Keith Busch <[email protected]>
---
drivers/nvme/host/core.c | 10 ++++++----
drivers/nvme/host/ioctl.c | 33 +++++++++++++++++++--------------
drivers/nvme/host/nvme.h | 3 ++-
drivers/nvme/host/pci.c | 4 ++--
drivers/nvme/target/passthru.c | 2 +-
include/uapi/linux/nvme_ioctl.h | 4 ++++
6 files changed, 34 insertions(+), 22 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0c231946a310..5199adf7ae92 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -633,11 +633,13 @@ static inline void nvme_init_request(struct request *req,
}
struct request *nvme_alloc_request(struct request_queue *q,
- struct nvme_command *cmd, blk_mq_req_flags_t flags)
+ struct nvme_command *cmd, blk_mq_req_flags_t flags,
+ unsigned int rq_flags)
{
+ unsigned int cmd_flags = nvme_req_op(cmd) | rq_flags;
struct request *req;
- req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+ req = blk_mq_alloc_request(q, cmd_flags, flags);
if (!IS_ERR(req))
nvme_init_request(req, cmd);
return req;
@@ -1081,7 +1083,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
int ret;
if (qid == NVME_QID_ANY)
- req = nvme_alloc_request(q, cmd, flags);
+ req = nvme_alloc_request(q, cmd, flags, 0);
else
req = nvme_alloc_request_qid(q, cmd, flags, qid);
if (IS_ERR(req))
@@ -1277,7 +1279,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
}
rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
- BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+ BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, 0);
if (IS_ERR(rq)) {
/* allocation failure, reset the controller */
dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 013ff9baa78e..bdaf8f317aa8 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -142,7 +142,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
struct nvme_command *cmd, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
u32 meta_seed, u64 *result, unsigned timeout,
- struct io_uring_cmd *ioucmd)
+ struct io_uring_cmd *ioucmd, unsigned int rq_flags)
{
bool write = nvme_is_write(cmd);
struct nvme_ns *ns = q->queuedata;
@@ -152,7 +152,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
void *meta = NULL;
int ret;
- req = nvme_alloc_request(q, cmd, 0);
+ req = nvme_alloc_request(q, cmd, 0, rq_flags);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -212,11 +212,13 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
struct nvme_command c;
unsigned length, meta_len;
void __user *metadata;
+ unsigned int rq_flags = 0;
if (copy_from_user(&io, uio, sizeof(io)))
return -EFAULT;
- if (io.flags)
- return -EINVAL;
+
+ if (io.flags & NVME_HIPRI)
+ rq_flags |= REQ_POLLED;
switch (io.opcode) {
case nvme_cmd_write:
@@ -254,7 +256,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
memset(&c, 0, sizeof(c));
c.rw.opcode = io.opcode;
- c.rw.flags = io.flags;
+ c.rw.flags = 0;
c.rw.nsid = cpu_to_le32(ns->head->ns_id);
c.rw.slba = cpu_to_le64(io.slba);
c.rw.length = cpu_to_le16(io.nblocks);
@@ -266,7 +268,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
return nvme_submit_user_cmd(ns->queue, &c,
io.addr, length, metadata, meta_len,
- lower_32_bits(io.slba), NULL, 0, NULL);
+ lower_32_bits(io.slba), NULL, 0, NULL, rq_flags);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -288,6 +290,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
{
struct nvme_passthru_cmd cmd;
struct nvme_command c;
+ unsigned int rq_flags = 0;
unsigned timeout = 0;
u64 result;
int status;
@@ -296,14 +299,14 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return -EACCES;
if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
return -EFAULT;
- if (cmd.flags)
- return -EINVAL;
+ if (cmd.flags & NVME_HIPRI)
+ rq_flags |= REQ_POLLED;
if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
return -EINVAL;
memset(&c, 0, sizeof(c));
c.common.opcode = cmd.opcode;
- c.common.flags = cmd.flags;
+ c.common.flags = 0;
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);
@@ -319,7 +322,7 @@ 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,
cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
- cmd.metadata_len, 0, &result, timeout, NULL);
+ cmd.metadata_len, 0, &result, timeout, NULL, rq_flags);
if (status >= 0) {
if (put_user(result, &ucmd->result))
@@ -335,6 +338,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
{
struct nvme_passthru_cmd64 cmd;
struct nvme_command c;
+ unsigned int rq_flags = 0;
unsigned timeout = 0;
int status;
@@ -342,14 +346,15 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return -EACCES;
if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
return -EFAULT;
- if (cmd.flags)
- return -EINVAL;
+ if (cmd.flags & NVME_HIPRI)
+ rq_flags |= REQ_POLLED;
+
if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
return -EINVAL;
memset(&c, 0, sizeof(c));
c.common.opcode = cmd.opcode;
- c.common.flags = cmd.flags;
+ c.common.flags = 0;
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);
@@ -365,7 +370,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
- cmd.metadata_len, 0, &cmd.result, timeout, ioucmd);
+ cmd.metadata_len, 0, &cmd.result, timeout, ioucmd, rq_flags);
if (!ioucmd && status >= 0) {
if (put_user(cmd.result, &ucmd->result))
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6bbb8ed868eb..56a7cc8421fc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -696,7 +696,8 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
- struct nvme_command *cmd, blk_mq_req_flags_t flags);
+ struct nvme_command *cmd, blk_mq_req_flags_t flags,
+ unsigned int rq_flags);
void nvme_cleanup_cmd(struct request *req);
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 50deb8b69c40..3d013a88af9d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1429,7 +1429,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
req->tag, nvmeq->qid);
abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
- BLK_MQ_REQ_NOWAIT);
+ BLK_MQ_REQ_NOWAIT, 0);
if (IS_ERR(abort_req)) {
atomic_inc(&dev->ctrl.abort_limit);
return BLK_EH_RESET_TIMER;
@@ -2475,7 +2475,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
cmd.delete_queue.opcode = opcode;
cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
- req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
+ req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, 0);
if (IS_ERR(req))
return PTR_ERR(req);
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 9e5b89ae29df..2a9e2fd3b137 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -253,7 +253,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
timeout = nvmet_req_subsys(req)->admin_timeout;
}
- rq = nvme_alloc_request(q, req->cmd, 0);
+ rq = nvme_alloc_request(q, req->cmd, 0, 0);
if (IS_ERR(rq)) {
status = NVME_SC_INTERNAL;
goto out_put_ns;
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index d99b5a772698..df2c138c38d9 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -9,6 +9,10 @@
#include <linux/types.h>
+enum nvme_io_flags {
+ NVME_HIPRI = 1 << 0, /* use polling queue if available */
+};
+
struct nvme_user_io {
__u8 opcode;
__u8 flags;
--
2.25.1
next prev parent reply other threads:[~2021-12-21 2:57 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20211220142227epcas5p280851b0a62baa78379979eb81af7a096@epcas5p2.samsung.com>
2021-12-20 14:17 ` [RFC 00/13] uring-passthru for nvme Kanchan Joshi
[not found] ` <CGME20211220142228epcas5p2978d92d38f2015148d5f72913d6dbc3e@epcas5p2.samsung.com>
2021-12-20 14:17 ` [RFC 01/13] io_uring: add infra for uring_cmd completion in submitter-task Kanchan Joshi
2022-02-17 2:13 ` Luis Chamberlain
2022-02-17 15:39 ` Kanchan Joshi
2022-02-17 15:50 ` Jens Axboe
2022-02-17 17:56 ` Luis Chamberlain
2022-02-18 17:41 ` Kanchan Joshi
2022-02-17 18:46 ` Luis Chamberlain
2022-02-17 18:53 ` Jens Axboe
[not found] ` <CGME20211220142231epcas5p1482c78f91feabdbc3e62341790ab22e1@epcas5p1.samsung.com>
2021-12-20 14:17 ` [RFC 02/13] nvme: wire-up support for async-passthru on char-device Kanchan Joshi
[not found] ` <CGME20211220142233epcas5p3b54aa591fb7b81bfb58bc33b5f92a2d3@epcas5p3.samsung.com>
2021-12-20 14:17 ` [RFC 03/13] io_uring: mark iopoll not supported for uring-cmd Kanchan Joshi
2022-02-17 2:16 ` Luis Chamberlain
2022-02-17 2:52 ` Jens Axboe
[not found] ` <CGME20211220142235epcas5p3b8d56cd39d9710278ec3360be47f2cca@epcas5p3.samsung.com>
2021-12-20 14:17 ` [RFC 04/13] io_uring: modify unused field in io_uring_cmd to store flags Kanchan Joshi
[not found] ` <CGME20211220142237epcas5p48729a52293e4f7627e6ec53ca67b9c58@epcas5p4.samsung.com>
2021-12-20 14:17 ` [RFC 05/13] io_uring: add flag and helper for fixed-buffer uring-cmd Kanchan Joshi
[not found] ` <CGME20211220142239epcas5p3efc3c89bd536f3f5d728c81bc550e143@epcas5p3.samsung.com>
2021-12-20 14:17 ` [RFC 06/13] io_uring: add support for uring_cmd with fixed-buffer Kanchan Joshi
[not found] ` <CGME20211220142242epcas5p45dddab51a9f20a8ec3d8b8e4f1dda40a@epcas5p4.samsung.com>
2021-12-20 14:17 ` [RFC 07/13] nvme: enable passthrough " Kanchan Joshi
[not found] ` <CGME20211220142244epcas5p2f311ed168b8f31b9301bcc2002076db4@epcas5p2.samsung.com>
2021-12-20 14:17 ` [RFC 08/13] io_uring: plug for async bypass Kanchan Joshi
[not found] ` <CGME20211220142246epcas5p303c64b6b1b832c7fcd5ac31fc79c91d1@epcas5p3.samsung.com>
2021-12-20 14:17 ` [RFC 09/13] block: wire-up support for plugging Kanchan Joshi
[not found] ` <CGME20211220142248epcas5p1e5904e10396f8cdea54bbd8d7aeca9a6@epcas5p1.samsung.com>
2021-12-20 14:17 ` [RFC 10/13] block: factor out helper for bio allocation from cache Kanchan Joshi
[not found] ` <CGME20211220142250epcas5p34b9d93b1dd3388af6209a4223befe40f@epcas5p3.samsung.com>
2021-12-20 14:17 ` [RFC 11/13] nvme: enable bio-cache for fixed-buffer passthru Kanchan Joshi
[not found] ` <CGME20211220142252epcas5p4611297f9970acbc8ee3b0e325ca5ceec@epcas5p4.samsung.com>
2021-12-20 14:17 ` Kanchan Joshi [this message]
[not found] ` <CGME20211220142256epcas5p49e0804ff8b075e8063259f94ccc9ced0@epcas5p4.samsung.com>
2021-12-20 14:17 ` [RFC 13/13] nvme: Add async passthru polling support Kanchan Joshi
2021-12-21 3:45 ` [RFC 00/13] uring-passthru for nvme Jens Axboe
2021-12-21 14:36 ` 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] \
/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