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 --- drivers/scsi/scsi_bsg.c | 217 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 216 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 4399a25990fc..e1bc46884dc7 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -10,10 +10,225 @@ #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 sense_addr; /* user space response buffer address (SCSI: sense data) */ + 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->sense_addr) { + if (copy_to_user(uptr64(pdu->sense_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->sense_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; +} + +/* + * Validate bsg_uring_cmd structure parameters. + * Note: xfer_dir must match the actual SCSI command direction. + * The direction is determined by the CDB, and user space should + * set xfer_dir accordingly (0=READ, 1=WRITE). + */ +static int scsi_bsg_validate_uring_cmd(const struct bsg_uring_cmd *cmd) +{ + 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->xfer_dir > 1) + return -EINVAL; + + if (cmd->iovec_count > 0) + return -EOPNOTSUPP; + + return 0; +} + +/* + * Map user buffer to request, supporting both zero-copy (fixed buffers) + * and traditional mode. + */ +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; + int ret; + + if (ioucmd->flags & IORING_URING_CMD_FIXED) { + ret = io_uring_cmd_import_fixed(cmd->xfer_addr, cmd->xfer_len, + cmd->xfer_dir, &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(cmd->xfer_addr), cmd->xfer_len, + gfp_mask); + } + + return ret; +} + 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; + + ret = scsi_bsg_validate_uring_cmd(cmd); + if (ret) + return ret; + + if (issue_flags & IO_URING_F_NONBLOCK) { + blk_flags = BLK_MQ_REQ_NOWAIT; + gfp_mask = GFP_NOWAIT; + } + + req = scsi_alloc_request(q, cmd->xfer_dir ? + 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->sense_addr = cmd->response; + scmd->sense_len = cmd->max_response_len ? + min(cmd->max_response_len, SCSI_SENSE_BUFFERSIZE) : SCSI_SENSE_BUFFERSIZE; + + if (cmd->xfer_len > 0) { + 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