From: Nilay Shroff <nilay@linux.ibm.com>
To: linux-nvme@lists.infradead.org
Cc: hare@suse.de, kbusch@kernel.org, hch@lst.de, sagi@grimberg.me,
dwagner@suse.de, kanie@linux.alibaba.com, jmeneghi@redhat.com,
randyj@purestorage.com, martin.petersen@oracle.com,
john.g.garry@oracle.com, gjoyce@linux.ibm.com,
Nilay Shroff <nilay@linux.ibm.com>
Subject: [PATCH v7 3/9] nvme-multipath: pass I/O type to nvme_find_path()
Date: Sun, 9 Aug 2026 15:37:58 +0530 [thread overview]
Message-ID: <20260809100825.2014133-4-nilay@linux.ibm.com> (raw)
In-Reply-To: <20260809100825.2014133-1-nilay@linux.ibm.com>
Currently, nvme_find_path() only accepts an nvme_ns_head argument.
However, the upcoming latency-aware I/O policy also needs to know
the I/O type (read/write/other) associated with the request in order
to make path selection decisions.
Update nvme_find_path() to accept an additional argument describing
the I/O type. This patch does not introduce any functional change and
only prepares the interface for subsequent latency-policy changes.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
drivers/nvme/host/ioctl.c | 38 +++++++++++++++++++++++++++++---
drivers/nvme/host/multipath.c | 9 ++++----
drivers/nvme/host/nvme.h | 41 ++++++++++++++++++++++++++++++++++-
drivers/nvme/host/pr.c | 6 +++--
drivers/nvme/host/sysfs.c | 2 +-
5 files changed, 85 insertions(+), 11 deletions(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 664216eece4a..8a8ed132fab2 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -708,18 +708,29 @@ static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode,
unsigned int cmd, unsigned long arg)
{
+ u8 opcode;
struct nvme_ns_head *head = bdev->bd_disk->private_data;
bool open_for_write = mode & BLK_OPEN_WRITE;
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret = -EWOULDBLOCK;
unsigned int flags = 0;
+ unsigned int op_type = NVME_STAT_OTHER;
if (bdev_is_partition(bdev))
flags |= NVME_IOCTL_PARTITION;
+ if (cmd == NVME_IOCTL_SUBMIT_IO) {
+ if (get_user(opcode, (u8 *)argp))
+ return -EFAULT;
+ if (opcode == nvme_cmd_write)
+ op_type = NVME_STAT_WRITE;
+ else if (opcode == nvme_cmd_read)
+ op_type = NVME_STAT_READ;
+ }
+
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, op_type);
if (!ns)
goto out_unlock;
@@ -741,6 +752,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode,
long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
+ u8 opcode;
bool open_for_write = file->f_mode & FMODE_WRITE;
struct cdev *cdev = file_inode(file)->i_cdev;
struct nvme_ns_head *head =
@@ -748,9 +760,19 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret = -EWOULDBLOCK;
+ unsigned int op_type = NVME_STAT_OTHER;
+
+ if (cmd == NVME_IOCTL_SUBMIT_IO) {
+ if (get_user(opcode, (u8 *)argp))
+ return -EFAULT;
+ if (opcode == nvme_cmd_write)
+ op_type = NVME_STAT_WRITE;
+ else if (opcode == nvme_cmd_read)
+ op_type = NVME_STAT_READ;
+ }
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, op_type);
if (!ns)
goto out_unlock;
@@ -770,9 +792,19 @@ int nvme_ns_head_chr_uring_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);
+ struct nvme_ns *ns;
int ret = -EINVAL;
+ const struct nvme_uring_cmd *cmd = io_uring_sqe128_cmd(ioucmd->sqe,
+ struct nvme_uring_cmd);
+ unsigned int op_type = NVME_STAT_OTHER;
+ __u8 opcode = READ_ONCE(cmd->opcode);
+
+ if (opcode == nvme_cmd_write)
+ op_type = NVME_STAT_WRITE;
+ else if (opcode == nvme_cmd_read)
+ op_type = NVME_STAT_READ;
+ ns = nvme_find_path(head, op_type);
if (ns)
ret = nvme_ns_uring_cmd(ns, ioucmd, issue_flags);
srcu_read_unlock(&head->srcu, srcu_idx);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 9b9a657fa330..8c20ff516e61 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -460,7 +460,8 @@ static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
return ns;
}
-inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head,
+ unsigned int op_type)
{
switch (READ_ONCE(head->subsys->iopolicy)) {
case NVME_IOPOLICY_QD:
@@ -522,7 +523,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
return;
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, __nvme_data_dir(bio_op(bio)));
if (likely(ns)) {
bio_set_dev(bio, ns->disk->part0);
/*
@@ -572,7 +573,7 @@ static int nvme_ns_head_get_unique_id(struct gendisk *disk, u8 id[16],
int srcu_idx, ret = -EWOULDBLOCK;
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, NVME_STAT_OTHER);
if (ns)
ret = nvme_ns_get_unique_id(ns, id, type);
srcu_read_unlock(&head->srcu, srcu_idx);
@@ -588,7 +589,7 @@ static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
int srcu_idx, ret = -EWOULDBLOCK;
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, NVME_STAT_OTHER);
if (ns)
ret = nvme_ns_report_zones(ns, sector, nr_zones, args);
srcu_read_unlock(&head->srcu, srcu_idx);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 824651cc898d..8a9ec502912d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -520,6 +520,13 @@ struct nvme_ns_ids {
u8 csi;
};
+enum nvme_stat_group {
+ NVME_STAT_READ,
+ NVME_STAT_WRITE,
+ NVME_STAT_OTHER,
+ NVME_NUM_STAT_GROUPS
+};
+
/*
* Anchor structure for namespaces. There is one for each namespace in a
* NVMe subsystem that any of our controllers can see, and the namespace
@@ -1032,7 +1039,39 @@ extern const struct attribute_group *nvme_dev_attr_groups[];
extern const struct block_device_operations nvme_bdev_ops;
void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
-struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
+struct nvme_ns *nvme_find_path(struct nvme_ns_head *head, unsigned int op_type);
+
+static inline int __nvme_data_dir(const enum req_op op)
+{
+ if (op == REQ_OP_READ)
+ return NVME_STAT_READ;
+ else if (op == REQ_OP_WRITE)
+ return NVME_STAT_WRITE;
+ else
+ return NVME_STAT_OTHER;
+}
+
+static inline int __nvme_data_dir_passthru(enum nvme_opcode op)
+{
+ if (op == nvme_cmd_read)
+ return NVME_STAT_READ;
+ else if (op == nvme_cmd_write)
+ return NVME_STAT_WRITE;
+ else
+ return NVME_STAT_OTHER;
+}
+
+static inline int nvme_data_dir(struct request *req)
+{
+ if (blk_rq_is_passthrough(req)) {
+ struct nvme_request *nr = nvme_req(req);
+
+ return __nvme_data_dir_passthru(nr->cmd->common.opcode);
+ }
+
+ return __nvme_data_dir(req_op(req));
+}
+
#ifdef CONFIG_NVME_MULTIPATH
static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
{
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index fe7dbe264815..80e106f151d2 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -53,10 +53,12 @@ static int nvme_send_ns_head_pr_command(struct block_device *bdev,
struct nvme_command *c, void *data, unsigned int data_len)
{
struct nvme_ns_head *head = bdev->bd_disk->private_data;
- int srcu_idx = srcu_read_lock(&head->srcu);
- struct nvme_ns *ns = nvme_find_path(head);
+ int srcu_idx;
+ struct nvme_ns *ns;
int ret = -EWOULDBLOCK;
+ srcu_idx = srcu_read_lock(&head->srcu);
+ ns = nvme_find_path(head, NVME_STAT_OTHER);
if (ns) {
c->common.nsid = cpu_to_le32(ns->head->ns_id);
ret = nvme_submit_sync_cmd(ns->queue, c, data, data_len);
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 75b2d69b5957..b2034e033ac3 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -195,7 +195,7 @@ static int ns_head_update_nuse(struct nvme_ns_head *head)
return 0;
srcu_idx = srcu_read_lock(&head->srcu);
- ns = nvme_find_path(head);
+ ns = nvme_find_path(head, NVME_STAT_OTHER);
if (!ns)
goto out_unlock;
--
2.53.0
next prev parent reply other threads:[~2026-08-09 10:09 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-09 10:07 [PATCH v7 0/9] nvme-multipath: introduce latency I/O policy Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 1/9] block: expose blk_stat_{enable,disable}_accounting() to drivers Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 2/9] block: record I/O request start time for passthru request Nilay Shroff
2026-08-09 10:07 ` Nilay Shroff [this message]
2026-08-09 10:07 ` [PATCH v7 4/9] nvme-multipath: add support for latency I/O policy Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 5/9] nvme: add generic debugfs support Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 6/9] nvme-multipath: add debugfs attribute latency_ewma_shift Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 7/9] nvme-multipath: add debugfs attribute latency_batch_timeout Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 8/9] nvme-multipath: add debugfs attribute latency_stat Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 9/9] nvme-multipath: add documentation for latency I/O policy Nilay Shroff
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=20260809100825.2014133-4-nilay@linux.ibm.com \
--to=nilay@linux.ibm.com \
--cc=dwagner@suse.de \
--cc=gjoyce@linux.ibm.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=jmeneghi@redhat.com \
--cc=john.g.garry@oracle.com \
--cc=kanie@linux.alibaba.com \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=martin.petersen@oracle.com \
--cc=randyj@purestorage.com \
--cc=sagi@grimberg.me \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.