[RFC 12/13] nvme: allow user passthrough commands to poll
Kanchan Joshi
joshi.k at samsung.com
Mon Dec 20 06:17:33 PST 2021
From: Keith Busch <kbusch at kernel.org>
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/20210517171443.GB2709391@dhcp-10-100-145-180.wdc.com/
Signed-off-by: Keith Busch <kbusch at kernel.org>
---
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
More information about the Linux-nvme
mailing list