linux-pci.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Damien Le Moal <dlemoal@kernel.org>
To: linux-nvme@lists.infradead.org, "Christoph Hellwig" <hch@lst.de>,
	"Keith Busch" <kbusch@kernel.org>,
	"Sagi Grimberg" <sagi@grimberg.me>,
	linux-pci@vger.kernel.org,
	"Manivannan Sadhasivam" <manivannan.sadhasivam@linaro.org>,
	"Krzysztof Wilczyński" <kw@linux.com>,
	"Kishon Vijay Abraham I" <kishon@kernel.org>,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	"Lorenzo Pieralisi" <lpieralisi@kernel.org>
Cc: Rick Wertenbroek <rick.wertenbroek@gmail.com>,
	Niklas Cassel <cassel@kernel.org>
Subject: [PATCH v5 11/18] nvmet: Do not require SGL for PCI target controller commands
Date: Sat, 14 Dec 2024 15:06:48 +0900	[thread overview]
Message-ID: <20241214060655.166325-12-dlemoal@kernel.org> (raw)
In-Reply-To: <20241214060655.166325-1-dlemoal@kernel.org>

Support for SGL is optional for the PCI transport. Modify
nvmet_req_init() to not require the NVME_CMD_SGL_METABUF command flag to
be set if the target controller transport type is NVMF_TRTYPE_PCI.
In addition to this, the NVMe base specification v2.1 mandate that all
admin commands use PRP, that is, have CDW0.PSDT cleared to 0. Modify
nvmet_parse_admin_cmd() to check this.

Finally, modify nvmet_check_transfer_len() and
nvmet_check_data_len_lte() to return the appropriate error status
depending on the command using SGL or PRP. Since for fabrics
nvmet_req_init() checks that a command uses SGL, always, this change
affects only PCI target controllers.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Rick Wertenbroek <rick.wertenbroek@gmail.com>
---
 drivers/nvme/target/admin-cmd.c |  5 +++++
 drivers/nvme/target/core.c      | 27 +++++++++++++++++++++------
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index c91864c185fc..0c5127a1d191 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1478,6 +1478,11 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 	if (unlikely(ret))
 		return ret;
 
+	/* For PCI controllers, admin commands shall not use SGL. */
+	if (nvmet_is_pci_ctrl(req->sq->ctrl) && !req->sq->qid &&
+	    cmd->common.flags & NVME_CMD_SGL_ALL)
+		return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+
 	if (nvmet_is_passthru_req(req))
 		return nvmet_parse_passthru_admin_cmd(req);
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 3a92e3a81b46..43c9888eea90 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1122,12 +1122,15 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	/*
 	 * For fabrics, PSDT field shall describe metadata pointer (MPTR) that
 	 * contains an address of a single contiguous physical buffer that is
-	 * byte aligned.
+	 * byte aligned. For PCI controllers, this is optional so not enforced.
 	 */
 	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
-		req->error_loc = offsetof(struct nvme_common_command, flags);
-		status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
-		goto fail;
+		if (!req->sq->ctrl || !nvmet_is_pci_ctrl(req->sq->ctrl)) {
+			req->error_loc =
+				offsetof(struct nvme_common_command, flags);
+			status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+			goto fail;
+		}
 	}
 
 	if (unlikely(!req->sq->ctrl))
@@ -1182,8 +1185,14 @@ EXPORT_SYMBOL_GPL(nvmet_req_transfer_len);
 bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len)
 {
 	if (unlikely(len != req->transfer_len)) {
+		u16 status;
+
 		req->error_loc = offsetof(struct nvme_common_command, dptr);
-		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR);
+		if (req->cmd->common.flags & NVME_CMD_SGL_ALL)
+			status = NVME_SC_SGL_INVALID_DATA;
+		else
+			status = NVME_SC_INVALID_FIELD;
+		nvmet_req_complete(req, status | NVME_STATUS_DNR);
 		return false;
 	}
 
@@ -1194,8 +1203,14 @@ EXPORT_SYMBOL_GPL(nvmet_check_transfer_len);
 bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len)
 {
 	if (unlikely(data_len > req->transfer_len)) {
+		u16 status;
+
 		req->error_loc = offsetof(struct nvme_common_command, dptr);
-		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR);
+		if (req->cmd->common.flags & NVME_CMD_SGL_ALL)
+			status = NVME_SC_SGL_INVALID_DATA;
+		else
+			status = NVME_SC_INVALID_FIELD;
+		nvmet_req_complete(req, status | NVME_STATUS_DNR);
 		return false;
 	}
 
-- 
2.47.1


  parent reply	other threads:[~2024-12-14  6:07 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-14  6:06 [PATCH v5 00/18] NVMe PCI endpoint target driver Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 01/18] nvme: Move opcode string helper functions declarations Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 02/18] nvmet: Add vendor_id and subsys_vendor_id subsystem attributes Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 03/18] nvmet: Export nvmet_update_cc() and nvmet_cc_xxx() helpers Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 04/18] nvmet: Introduce nvmet_get_cmd_effects_admin() Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 05/18] nvmet: Add drvdata field to struct nvmet_ctrl Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 06/18] nvme: Add PCI transport type Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 07/18] nvmet: Improve nvmet_alloc_ctrl() interface and implementation Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 08/18] nvmet: Introduce nvmet_req_transfer_len() Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 09/18] nvmet: Introduce nvmet_sq_create() and nvmet_cq_create() Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 10/18] nvmet: Add support for I/O queue management admin commands Damien Le Moal
2024-12-14  6:06 ` Damien Le Moal [this message]
2024-12-14  6:06 ` [PATCH v5 12/18] nvmet: Introduce get/set_feature controller operations Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 13/18] nvmet: Implement host identifier set feature support Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 14/18] nvmet: Implement interrupt coalescing " Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 15/18] nvmet: Implement interrupt config " Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 16/18] nvmet: Implement arbitration " Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 17/18] nvmet: New NVMe PCI endpoint target driver Damien Le Moal
2024-12-14  6:06 ` [PATCH v5 18/18] Documentation: Document the " Damien Le Moal

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=20241214060655.166325-12-dlemoal@kernel.org \
    --to=dlemoal@kernel.org \
    --cc=bhelgaas@google.com \
    --cc=cassel@kernel.org \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kishon@kernel.org \
    --cc=kw@linux.com \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=lpieralisi@kernel.org \
    --cc=manivannan.sadhasivam@linaro.org \
    --cc=rick.wertenbroek@gmail.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 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).