From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Sasha Levin <sashal@kernel.org>, Sagi Grimberg <sagi@grimberg.me>,
Marta Rybczynska <mrybczyn@kalray.eu>,
linux-api@vger.kernel.org, linux-nvme@lists.infradead.org,
Marta Rybczynska <marta.rybczynska@kalray.eu>,
Keith Busch <kbusch@kernel.org>, Christoph Hellwig <hch@lst.de>
Subject: [PATCH AUTOSEL 5.3 24/68] nvme: allow 64-bit results in passthru commands
Date: Wed, 9 Oct 2019 13:05:03 -0400 [thread overview]
Message-ID: <20191009170547.32204-24-sashal@kernel.org> (raw)
In-Reply-To: <20191009170547.32204-1-sashal@kernel.org>
From: Marta Rybczynska <mrybczyn@kalray.eu>
[ Upstream commit 65e68edce0db433aa0c2b26d7dc14fbbbeb89fbb ]
It is not possible to get 64-bit results from the passthru commands,
what prevents from getting for the Capabilities (CAP) property value.
As a result, it is not possible to implement IOL's NVMe Conformance
test 4.3 Case 1 for Fabrics targets [1] (page 123).
This issue has been already discussed [2], but without a solution.
This patch solves the problem by adding new ioctls with a new
passthru structure, including 64-bit results. The older ioctls stay
unchanged.
[1] https://www.iol.unh.edu/sites/default/files/testsuites/nvme/UNH-IOL_NVMe_Conformance_Test_Suite_v11.0.pdf
[2] http://lists.infradead.org/pipermail/linux-nvme/2018-June/018791.html
Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/nvme/host/core.c | 108 +++++++++++++++++++++++++++-----
include/uapi/linux/nvme_ioctl.h | 23 +++++++
2 files changed, 115 insertions(+), 16 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3304e2c8a448a..36a5ed1eacbea 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -852,7 +852,7 @@ out:
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, u32 *result, unsigned timeout)
+ u32 meta_seed, u64 *result, unsigned timeout)
{
bool write = nvme_is_write(cmd);
struct nvme_ns *ns = q->queuedata;
@@ -893,7 +893,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
else
ret = nvme_req(req)->status;
if (result)
- *result = le32_to_cpu(nvme_req(req)->result.u32);
+ *result = le64_to_cpu(nvme_req(req)->result.u64);
if (meta && !ret && !write) {
if (copy_to_user(meta_buffer, meta, meta_len))
ret = -EFAULT;
@@ -1339,6 +1339,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_command c;
unsigned timeout = 0;
u32 effects;
+ u64 result;
+ int status;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+ return -EFAULT;
+ if (cmd.flags)
+ 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);
+
+ effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+ status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+ (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+ (void __user *)(uintptr_t)cmd.metadata,
+ cmd.metadata_len, 0, &result, timeout);
+ nvme_passthru_end(ctrl, effects);
+
+ if (status >= 0) {
+ if (put_user(result, &ucmd->result))
+ return -EFAULT;
+ }
+
+ return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+ struct nvme_passthru_cmd64 __user *ucmd)
+{
+ struct nvme_passthru_cmd64 cmd;
+ struct nvme_command c;
+ unsigned timeout = 0;
+ u32 effects;
int status;
if (!capable(CAP_SYS_ADMIN))
@@ -1409,6 +1457,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
srcu_read_unlock(&head->srcu, idx);
}
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+ if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+ return true;
+ if (is_sed_ioctl(cmd))
+ return true;
+ return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+ void __user *argp,
+ struct nvme_ns_head *head,
+ int srcu_idx)
+{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ int ret;
+
+ nvme_get_ctrl(ns->ctrl);
+ nvme_put_ns_from_disk(head, srcu_idx);
+
+ switch (cmd) {
+ case NVME_IOCTL_ADMIN_CMD:
+ ret = nvme_user_cmd(ctrl, NULL, argp);
+ break;
+ case NVME_IOCTL_ADMIN64_CMD:
+ ret = nvme_user_cmd64(ctrl, NULL, argp);
+ break;
+ default:
+ ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+ break;
+ }
+ nvme_put_ctrl(ctrl);
+ return ret;
+}
+
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
@@ -1426,20 +1509,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
* seperately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
- if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
- struct nvme_ctrl *ctrl = ns->ctrl;
-
- nvme_get_ctrl(ns->ctrl);
- nvme_put_ns_from_disk(head, srcu_idx);
-
- if (cmd == NVME_IOCTL_ADMIN_CMD)
- ret = nvme_user_cmd(ctrl, NULL, argp);
- else
- ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
- nvme_put_ctrl(ctrl);
- return ret;
- }
+ if (is_ctrl_ioctl(cmd))
+ return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
switch (cmd) {
case NVME_IOCTL_ID:
@@ -1452,6 +1523,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
case NVME_IOCTL_SUBMIT_IO:
ret = nvme_submit_io(ns, argp);
break;
+ case NVME_IOCTL_IO64_CMD:
+ ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+ break;
default:
if (ns->ndev)
ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2826,6 +2900,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
switch (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);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea1798e6..e168dc59e9a0d 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
__u32 result;
};
+struct nvme_passthru_cmd64 {
+ __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;
+ __u64 result;
+};
+
#define nvme_admin_cmd nvme_passthru_cmd
#define NVME_IOCTL_ID _IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
#define NVME_IOCTL_RESET _IO('N', 0x44)
#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45)
#define NVME_IOCTL_RESCAN _IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64)
#endif /* _UAPI_LINUX_NVME_IOCTL_H */
--
2.20.1
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
prev parent reply other threads:[~2019-10-09 17:25 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20191009170547.32204-1-sashal@kernel.org>
2019-10-09 17:04 ` [PATCH AUTOSEL 5.3 06/68] nvme-pci: Fix a race in controller removal Sasha Levin
2019-10-09 17:04 ` [PATCH AUTOSEL 5.3 18/68] nvme-tcp: fix wrong stop condition in io_work Sasha Levin
2019-10-09 17:04 ` [PATCH AUTOSEL 5.3 19/68] nvme-pci: Save PCI state before putting drive into deepest state Sasha Levin
2019-10-09 17:04 ` [PATCH AUTOSEL 5.3 20/68] nvme: fix an error code in nvme_init_subsystem() Sasha Levin
2019-10-09 17:05 ` [PATCH AUTOSEL 5.3 21/68] nvme-rdma: Fix max_hw_sectors calculation Sasha Levin
2019-10-09 17:05 ` [PATCH AUTOSEL 5.3 22/68] Added QUIRKs for ADATA XPG SX8200 Pro 512GB Sasha Levin
2019-10-09 17:05 ` [PATCH AUTOSEL 5.3 23/68] nvme: Add quirk for Kingston NVME SSD running FW E8FK11.T Sasha Levin
2019-10-09 17:05 ` Sasha Levin [this message]
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=20191009170547.32204-24-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=marta.rybczynska@kalray.eu \
--cc=mrybczyn@kalray.eu \
--cc=sagi@grimberg.me \
--cc=stable@vger.kernel.org \
/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).