public inbox for io-uring@vger.kernel.org
 help / color / mirror / Atom feed
From: Yang Xiuwei <yangxiuwei@kylinos.cn>
To: linux-scsi@vger.kernel.org, linux-block@vger.kernel.org,
	io-uring@vger.kernel.org
Cc: fujita.tomonori@lab.ntt.co.jp, axboe@kernel.dk,
	James.Bottomley@HansenPartnership.com,
	martin.petersen@oracle.com, bvanassche@acm.org,
	Yang Xiuwei <yangxiuwei@kylinos.cn>
Subject: [RFC PATCH v4 3/3] bsg: implement SCSI BSG uring_cmd handler
Date: Thu, 22 Jan 2026 09:56:53 +0800	[thread overview]
Message-ID: <20260122015653.703188-4-yangxiuwei@kylinos.cn> (raw)
In-Reply-To: <20260122015653.703188-1-yangxiuwei@kylinos.cn>

Implement the SCSI-specific io_uring command handler for BSG. This
handler processes SCSI passthrough commands asynchronously via io_uring,
supporting both traditional user buffers and zero-copy fixed buffers.

Key features:
- Async command execution with proper completion handling
- Zero-copy support via io_uring fixed buffers
- Status information returned in CQE res2 field
- Non-blocking I/O support via IO_URING_F_NONBLOCK
- Proper error handling and validation

The implementation uses a PDU structure overlaying io_uring_cmd.pdu[32]
to store temporary state during command execution. Completion is handled
via task work to safely access user space.

This patch replaces the stub implementation from patch 2/3 with the full
implementation.

Signed-off-by: Yang Xiuwei <yangxiuwei@kylinos.cn>
---
 drivers/scsi/scsi_bsg.c | 202 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 201 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c
index 4d57e524e141..cfad019ec94d 100644
--- a/drivers/scsi/scsi_bsg.c
+++ b/drivers/scsi/scsi_bsg.c
@@ -10,10 +10,210 @@
 
 #define uptr64(val) ((void __user *)(uintptr_t)(val))
 
+/*
+ * BSG io_uring PDU structure overlaying io_uring_cmd.pdu[32].
+ * Stores temporary data needed during command execution.
+ */
+struct scsi_bsg_uring_cmd_pdu {
+	struct bio *bio;		/* mapped user buffer, unmap in task work */
+	struct request *req;		/* block request, freed in task work */
+	u64 response_addr;		/* user space response buffer address */
+	u32 resid_len;			/* residual transfer length */
+	/* Protocol-specific status fields using union for extensibility */
+	union {
+		struct {
+			u8 device_status;	/* SCSI device status (low 8 bits of result) */
+			u8 driver_status;	/* SCSI driver status (DRIVER_SENSE if check) */
+			u8 host_status;		/* SCSI host status (host_byte of result) */
+			u8 sense_len_wr;	/* actual sense data length written */
+		} scsi;
+		/* Future protocols can add their own status layouts here */
+	};
+};
+
+static inline struct scsi_bsg_uring_cmd_pdu *scsi_bsg_uring_cmd_pdu(
+	struct io_uring_cmd *ioucmd)
+{
+	return io_uring_cmd_to_pdu(ioucmd, struct scsi_bsg_uring_cmd_pdu);
+}
+
+/*
+ * Task work callback executed in process context.
+ * Builds res2 with status information and copies sense data to user space.
+ * res2 layout (64-bit):
+ *   0-7:   device_status
+ *   8-15:  driver_status
+ *   16-23: host_status
+ *   24-31: sense_len_wr
+ *   32-63: resid_len
+ */
+static void scsi_bsg_uring_task_cb(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	struct io_uring_cmd *ioucmd = io_uring_cmd_from_tw(tw_req);
+	struct scsi_bsg_uring_cmd_pdu *pdu = scsi_bsg_uring_cmd_pdu(ioucmd);
+	struct scsi_cmnd *scmd;
+	struct request *rq = pdu->req;
+	int ret = 0;
+	u64 res2;
+
+	scmd = blk_mq_rq_to_pdu(rq);
+
+	if (pdu->bio)
+		blk_rq_unmap_user(pdu->bio);
+
+	/* Build res2 with status information */
+	res2 = ((u64)pdu->resid_len << 32) |
+	       ((u64)(pdu->scsi.sense_len_wr & 0xff) << 24) |
+	       ((u64)(pdu->scsi.host_status & 0xff) << 16) |
+	       ((u64)(pdu->scsi.driver_status & 0xff) << 8) |
+	       (pdu->scsi.device_status & 0xff);
+
+	if (pdu->scsi.sense_len_wr && pdu->response_addr) {
+		if (copy_to_user(uptr64(pdu->response_addr), scmd->sense_buffer,
+				 pdu->scsi.sense_len_wr))
+			ret = -EFAULT;
+	}
+
+	blk_mq_free_request(rq);
+	io_uring_cmd_done32(ioucmd, ret, res2,
+			    IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);
+}
+
+/*
+ * Async completion callback executed in interrupt/atomic context.
+ * Saves SCSI status information and schedules task work for final completion.
+ */
+static enum rq_end_io_ret scsi_bsg_uring_cmd_done(struct request *req,
+						  blk_status_t status)
+{
+	struct io_uring_cmd *ioucmd = req->end_io_data;
+	struct scsi_bsg_uring_cmd_pdu *pdu = scsi_bsg_uring_cmd_pdu(ioucmd);
+	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
+
+	/* Pack SCSI status fields into union */
+	pdu->scsi.device_status = scmd->result & 0xff;
+	pdu->scsi.host_status = host_byte(scmd->result);
+	pdu->scsi.driver_status = 0;
+	pdu->scsi.sense_len_wr = 0;
+
+	if (scsi_status_is_check_condition(scmd->result)) {
+		pdu->scsi.driver_status = DRIVER_SENSE;
+		if (pdu->response_addr)
+			pdu->scsi.sense_len_wr = min_t(u8, scmd->sense_len, SCSI_SENSE_BUFFERSIZE);
+	}
+
+	pdu->resid_len = scmd->resid_len;
+
+	io_uring_cmd_do_in_task_lazy(ioucmd, scsi_bsg_uring_task_cb);
+	return RQ_END_IO_NONE;
+}
+
+static int scsi_bsg_map_user_buffer(struct request *req,
+				    struct io_uring_cmd *ioucmd,
+				    unsigned int issue_flags, gfp_t gfp_mask)
+{
+	const struct bsg_uring_cmd *cmd = io_uring_sqe_cmd(ioucmd->sqe);
+	struct iov_iter iter;
+	bool is_write = cmd->dout_xfer_len > 0;
+	u64 buf_addr = is_write ? cmd->dout_xferp : cmd->din_xferp;
+	unsigned long buf_len = is_write ? cmd->dout_xfer_len : cmd->din_xfer_len;
+	int ret;
+
+	if (ioucmd->flags & IORING_URING_CMD_FIXED) {
+		ret = io_uring_cmd_import_fixed(buf_addr, buf_len,
+						is_write ? WRITE : READ,
+						&iter, ioucmd, issue_flags);
+		if (ret < 0)
+			return ret;
+		ret = blk_rq_map_user_iov(req->q, req, NULL, &iter, gfp_mask);
+	} else {
+		ret = blk_rq_map_user(req->q, req, NULL, uptr64(buf_addr),
+				      buf_len, gfp_mask);
+	}
+
+	return ret;
+}
+
 static int scsi_bsg_uring_cmd(struct request_queue *q, struct io_uring_cmd *ioucmd,
 			       unsigned int issue_flags, bool open_for_write)
 {
-	return -EOPNOTSUPP;
+	struct scsi_bsg_uring_cmd_pdu *pdu = scsi_bsg_uring_cmd_pdu(ioucmd);
+	const struct bsg_uring_cmd *cmd = io_uring_sqe_cmd(ioucmd->sqe);
+	struct scsi_cmnd *scmd;
+	struct request *req;
+	blk_mq_req_flags_t blk_flags = 0;
+	gfp_t gfp_mask = GFP_KERNEL;
+	int ret = 0;
+
+	if (cmd->protocol != BSG_PROTOCOL_SCSI ||
+	    cmd->subprotocol != BSG_SUB_PROTOCOL_SCSI_CMD)
+		return -EINVAL;
+
+	if (!cmd->request || cmd->request_len == 0)
+		return -EINVAL;
+
+	if (cmd->dout_xfer_len && cmd->din_xfer_len) {
+		pr_warn_once("BIDI support in bsg has been removed.\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (cmd->dout_iovec_count > 0 || cmd->din_iovec_count > 0)
+		return -EOPNOTSUPP;
+
+	if (issue_flags & IO_URING_F_NONBLOCK) {
+		blk_flags = BLK_MQ_REQ_NOWAIT;
+		gfp_mask = GFP_NOWAIT;
+	}
+
+	req = scsi_alloc_request(q, cmd->dout_xfer_len ?
+				 REQ_OP_DRV_OUT : REQ_OP_DRV_IN, blk_flags);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	scmd = blk_mq_rq_to_pdu(req);
+	scmd->cmd_len = cmd->request_len;
+	if (scmd->cmd_len > sizeof(scmd->cmnd)) {
+		ret = -EINVAL;
+		goto out_free_req;
+	}
+	scmd->allowed = SG_DEFAULT_RETRIES;
+
+	if (copy_from_user(scmd->cmnd, uptr64(cmd->request), cmd->request_len)) {
+		ret = -EFAULT;
+		goto out_free_req;
+	}
+
+	if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) {
+		ret = -EPERM;
+		goto out_free_req;
+	}
+
+	pdu->response_addr = cmd->response;
+	scmd->sense_len = cmd->max_response_len ?
+		min(cmd->max_response_len, SCSI_SENSE_BUFFERSIZE) : SCSI_SENSE_BUFFERSIZE;
+
+	if (cmd->dout_xfer_len || cmd->din_xfer_len) {
+		ret = scsi_bsg_map_user_buffer(req, ioucmd, issue_flags, gfp_mask);
+		if (ret)
+			goto out_free_req;
+		pdu->bio = req->bio;
+	} else {
+		pdu->bio = NULL;
+	}
+
+	req->timeout = cmd->timeout_ms ?
+		msecs_to_jiffies(cmd->timeout_ms) : BLK_DEFAULT_SG_TIMEOUT;
+
+	req->end_io = scsi_bsg_uring_cmd_done;
+	req->end_io_data = ioucmd;
+	pdu->req = req;
+
+	blk_execute_rq_nowait(req, false);
+	return -EIOCBQUEUED;
+
+out_free_req:
+	blk_mq_free_request(req);
+	return ret;
 }
 
 static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
-- 
2.25.1


      parent reply	other threads:[~2026-01-22  1:57 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-22  1:56 [RFC PATCH v4 0/3] bsg: add io_uring command support for SCSI passthrough Yang Xiuwei
2026-01-22  1:56 ` [RFC PATCH v4 1/3] bsg: add bsg_uring_cmd uapi structure Yang Xiuwei
2026-01-22  1:56 ` [RFC PATCH v4 2/3] bsg: add uring_cmd support to BSG generic layer Yang Xiuwei
2026-01-22  1:56 ` Yang Xiuwei [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=20260122015653.703188-4-yangxiuwei@kylinos.cn \
    --to=yangxiuwei@kylinos.cn \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=fujita.tomonori@lab.ntt.co.jp \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    /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