[SCSI] isci: atapi support

Based on original implementation from Jiangbi Liu and Maciej Trela.

ATAPI transfers happen in two-to-three stages.  The two stage atapi
commands are those that include a dma data transfer.  The data transfer
portion of these operations is handled by the hardware packet-dma
acceleration.  The three-stage commands do not have a data transfer and
are handled without hardware assistance in raw frame mode.

stage1: transmit host-to-device fis to notify the device of an incoming
atapi cdb.  Upon reception of the pio-setup-fis repost the task_context
to perform the dma transfer of the cdb+data (go to stage3), or repost
the task_context to transmit the cdb as a raw frame (go to stage 2).

stage2: wait for hardware notification of the cdb transmission and then
go to stage 3.

stage3: wait for the arrival of the terminating device-to-host fis and
terminate the command.

To keep the implementation simple we only support ATAPI packet-dma
protocol (for commands with data) to avoid needing to handle the data
transfer manually (like we do for SATA-PIO).  This may affect
compatibility for a small number of devices (see
ATA_HORKAGE_ATAPI_MOD16_DMA).

If the data-transfer underruns, or encounters an error the
device-to-host fis is expected to arrive in the unsolicited frame queue
to pass to libata for disposition.  However, in the DONE_UNEXP_FIS (data
underrun) case it appears we need to craft a response.  In the
DONE_REG_ERR case we do receive the UF and propagate it to libsas.

Signed-off-by: Maciej Trela <maciej.trela@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>

1 files changed, 315 insertions, 13 deletions

diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 225b196800a2..23a55043a923 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -481,7 +481,29 @@ static void sci_stp_optimized_request_construct(struct isci_request *ireq,
 	}
 }
 
+static void sci_atapi_construct(struct isci_request *ireq)
+{
+	struct host_to_dev_fis *h2d_fis = &ireq->stp.cmd;
+	struct sas_task *task;
+
+	/* To simplify the implementation we take advantage of the
+	 * silicon's partial acceleration of atapi protocol (dma data
+	 * transfers), so we promote all commands to dma protocol.  This
+	 * breaks compatibility with ATA_HORKAGE_ATAPI_MOD16_DMA drives.
+	 */
+	h2d_fis->features |= ATAPI_PKT_DMA;
+
+	scu_stp_raw_request_construct_task_context(ireq);
+
+	task = isci_request_access_task(ireq);
+	if (task->data_dir == DMA_NONE)
+		task->total_xfer_len = 0;
 
+	/* clear the response so we can detect arrivial of an
+	 * unsolicited h2d fis
+	 */
+	ireq->stp.rsp.fis_type = 0;
+}
 
 static enum sci_status
 sci_io_request_construct_sata(struct isci_request *ireq,
@@ -491,6 +513,7 @@ sci_io_request_construct_sata(struct isci_request *ireq,
 {
 	enum sci_status status = SCI_SUCCESS;
 	struct sas_task *task = isci_request_access_task(ireq);
+	struct domain_device *dev = ireq->target_device->domain_dev;
 
 	/* check for management protocols */
 	if (ireq->ttype == tmf_task) {
@@ -519,6 +542,13 @@ sci_io_request_construct_sata(struct isci_request *ireq,
 
 	}
 
+	/* ATAPI */
+	if (dev->sata_dev.command_set == ATAPI_COMMAND_SET &&
+	    task->ata_task.fis.command == ATA_CMD_PACKET) {
+		sci_atapi_construct(ireq);
+		return SCI_SUCCESS;
+	}
+
 	/* non data */
 	if (task->data_dir == DMA_NONE) {
 		scu_stp_raw_request_construct_task_context(ireq);
@@ -627,7 +657,7 @@ enum sci_status sci_task_request_construct_sata(struct isci_request *ireq)
 
 /**
  * sci_req_tx_bytes - bytes transferred when reply underruns request
- * @sci_req: request that was terminated early
+ * @ireq: request that was terminated early
  */
 #define SCU_TASK_CONTEXT_SRAM 0x200000
 static u32 sci_req_tx_bytes(struct isci_request *ireq)
@@ -729,6 +759,10 @@ sci_io_request_terminate(struct isci_request *ireq)
 	case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED:
 	case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG:
 	case SCI_REQ_STP_SOFT_RESET_WAIT_D2H:
+	case SCI_REQ_ATAPI_WAIT_H2D:
+	case SCI_REQ_ATAPI_WAIT_PIO_SETUP:
+	case SCI_REQ_ATAPI_WAIT_D2H:
+	case SCI_REQ_ATAPI_WAIT_TC_COMP:
 		sci_change_state(&ireq->sm, SCI_REQ_ABORTING);
 		return SCI_SUCCESS;
 	case SCI_REQ_TASK_WAIT_TC_RESP:
@@ -1194,8 +1228,8 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re
 {
 	struct isci_stp_request *stp_req = &ireq->stp.req;
 	struct scu_sgl_element_pair *sgl_pair;
+	enum sci_status status = SCI_SUCCESS;
 	struct scu_sgl_element *sgl;
-	enum sci_status status;
 	u32 offset;
 	u32 len = 0;
 
@@ -1249,7 +1283,7 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re
  */
 static enum sci_status
 sci_stp_request_pio_data_in_copy_data_buffer(struct isci_stp_request *stp_req,
-						  u8 *data_buf, u32 len)
+					     u8 *data_buf, u32 len)
 {
 	struct isci_request *ireq;
 	u8 *src_addr;
@@ -1423,6 +1457,128 @@ static enum sci_status sci_stp_request_udma_general_frame_handler(struct isci_re
 	return status;
 }
 
+static enum sci_status process_unsolicited_fis(struct isci_request *ireq,
+					       u32 frame_index)
+{
+	struct isci_host *ihost = ireq->owning_controller;
+	enum sci_status status;
+	struct dev_to_host_fis *frame_header;
+	u32 *frame_buffer;
+
+	status = sci_unsolicited_frame_control_get_header(&ihost->uf_control,
+							  frame_index,
+							  (void **)&frame_header);
+
+	if (status != SCI_SUCCESS)
+		return status;
+
+	if (frame_header->fis_type != FIS_REGD2H) {
+		dev_err(&ireq->isci_host->pdev->dev,
+			"%s ERROR: invalid fis type 0x%X\n",
+			__func__, frame_header->fis_type);
+		return SCI_FAILURE;
+	}
+
+	sci_unsolicited_frame_control_get_buffer(&ihost->uf_control,
+						 frame_index,
+						 (void **)&frame_buffer);
+
+	sci_controller_copy_sata_response(&ireq->stp.rsp,
+					  (u32 *)frame_header,
+					  frame_buffer);
+
+	/* Frame has been decoded return it to the controller */
+	sci_controller_release_frame(ihost, frame_index);
+
+	return status;
+}
+
+static enum sci_status atapi_d2h_reg_frame_handler(struct isci_request *ireq,
+						   u32 frame_index)
+{
+	struct sas_task *task = isci_request_access_task(ireq);
+	enum sci_status status;
+
+	status = process_unsolicited_fis(ireq, frame_index);
+
+	if (status == SCI_SUCCESS) {
+		if (ireq->stp.rsp.status & ATA_ERR)
+			status = SCI_IO_FAILURE_RESPONSE_VALID;
+	} else {
+		status = SCI_IO_FAILURE_RESPONSE_VALID;
+	}
+
+	if (status != SCI_SUCCESS) {
+		ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE;
+		ireq->sci_status = status;
+	} else {
+		ireq->scu_status = SCU_TASK_DONE_GOOD;
+		ireq->sci_status = SCI_SUCCESS;
+	}
+
+	/* the d2h ufi is the end of non-data commands */
+	if (task->data_dir == DMA_NONE)
+		sci_change_state(&ireq->sm, SCI_REQ_COMPLETED);
+
+	return status;
+}
+
+static void scu_atapi_reconstruct_raw_frame_task_context(struct isci_request *ireq)
+{
+	struct ata_device *dev = sas_to_ata_dev(ireq->target_device->domain_dev);
+	void *atapi_cdb = ireq->ttype_ptr.io_task_ptr->ata_task.atapi_packet;
+	struct scu_task_context *task_context = ireq->tc;
+
+	/* fill in the SCU Task Context for a DATA fis containing CDB in Raw Frame
+	 * type. The TC for previous Packet fis was already there, we only need to
+	 * change the H2D fis content.
+	 */
+	memset(&ireq->stp.cmd, 0, sizeof(struct host_to_dev_fis));
+	memcpy(((u8 *)&ireq->stp.cmd + sizeof(u32)), atapi_cdb, ATAPI_CDB_LEN);
+	memset(&(task_context->type.stp), 0, sizeof(struct stp_task_context));
+	task_context->type.stp.fis_type = FIS_DATA;
+	task_context->transfer_length_bytes = dev->cdb_len;
+}
+
+static void scu_atapi_construct_task_context(struct isci_request *ireq)
+{
+	struct ata_device *dev = sas_to_ata_dev(ireq->target_device->domain_dev);
+	struct sas_task *task = isci_request_access_task(ireq);
+	struct scu_task_context *task_context = ireq->tc;
+	int cdb_len = dev->cdb_len;
+
+	/* reference: SSTL 1.13.4.2
+	 * task_type, sata_direction
+	 */
+	if (task->data_dir == DMA_TO_DEVICE) {
+		task_context->task_type = SCU_TASK_TYPE_PACKET_DMA_OUT;
+		task_context->sata_direction = 0;
+	} else {
+		/* todo: for NO_DATA command, we need to send out raw frame. */
+		task_context->task_type = SCU_TASK_TYPE_PACKET_DMA_IN;
+		task_context->sata_direction = 1;
+	}
+
+	memset(&task_context->type.stp, 0, sizeof(task_context->type.stp));
+	task_context->type.stp.fis_type = FIS_DATA;
+
+	memset(&ireq->stp.cmd, 0, sizeof(ireq->stp.cmd));
+	memcpy(&ireq->stp.cmd.lbal, task->ata_task.atapi_packet, cdb_len);
+	task_context->ssp_command_iu_length = cdb_len / sizeof(u32);
+
+	/* task phase is set to TX_CMD */
+	task_context->task_phase = 0x1;
+
+	/* retry counter */
+	task_context->stp_retry_count = 0;
+
+	/* data transfer size. */
+	task_context->transfer_length_bytes = task->total_xfer_len;
+
+	/* setup sgl */
+	sci_request_build_sgl(ireq);
+}
+
 enum sci_status
 sci_io_request_frame_handler(struct isci_request *ireq,
 				  u32 frame_index)
@@ -1835,6 +1991,24 @@ sci_io_request_frame_handler(struct isci_request *ireq,
 
 		return status;
 	}
+	case SCI_REQ_ATAPI_WAIT_PIO_SETUP: {
+		struct sas_task *task = isci_request_access_task(ireq);
+
+		sci_controller_release_frame(ihost, frame_index);
+		ireq->target_device->working_request = ireq;
+		if (task->data_dir == DMA_NONE) {
+			sci_change_state(&ireq->sm, SCI_REQ_ATAPI_WAIT_TC_COMP);
+			scu_atapi_reconstruct_raw_frame_task_context(ireq);
+		} else {
+			sci_change_state(&ireq->sm, SCI_REQ_ATAPI_WAIT_D2H);
+			scu_atapi_construct_task_context(ireq);
+		}
+
+		sci_controller_continue_io(ireq);
+		return SCI_SUCCESS;
+	}
+	case SCI_REQ_ATAPI_WAIT_D2H:
+		return atapi_d2h_reg_frame_handler(ireq, frame_index);
 	case SCI_REQ_ABORTING:
 		/*
 		 * TODO: Is it even possible to get an unsolicited frame in the
@@ -1966,6 +2140,112 @@ stp_request_soft_reset_await_h2d_diagnostic_tc_event(struct isci_request *ireq,
 	return SCI_SUCCESS;
 }
 
+static enum sci_status atapi_raw_completion(struct isci_request *ireq, u32 completion_code,
+						  enum sci_base_request_states next)
+{
+	enum sci_status status = SCI_SUCCESS;
+
+	switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) {
+	case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD):
+		ireq->scu_status = SCU_TASK_DONE_GOOD;
+		ireq->sci_status = SCI_SUCCESS;
+		sci_change_state(&ireq->sm, next);
+		break;
+	default:
+		/* All other completion status cause the IO to be complete.
+		 * If a NAK was received, then it is up to the user to retry
+		 * the request.
+		 */
+		ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code);
+		ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR;
+
+		sci_change_state(&ireq->sm, SCI_REQ_COMPLETED);
+		break;
+	}
+
+	return status;
+}
+
+static enum sci_status atapi_data_tc_completion_handler(struct isci_request *ireq,
+							u32 completion_code)
+{
+	struct isci_remote_device *idev = ireq->target_device;
+	struct dev_to_host_fis *d2h = &ireq->stp.rsp;
+	enum sci_status status = SCI_SUCCESS;
+
+	switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) {
+	case (SCU_TASK_DONE_GOOD << SCU_COMPLETION_TL_STATUS_SHIFT):
+		sci_change_state(&ireq->sm, SCI_REQ_COMPLETED);
+		break;
+
+	case (SCU_TASK_DONE_UNEXP_FIS << SCU_COMPLETION_TL_STATUS_SHIFT): {
+		u16 len = sci_req_tx_bytes(ireq);
+
+		/* likely non-error data underrrun, workaround missing
+		 * d2h frame from the controller
+		 */
+		if (d2h->fis_type != FIS_REGD2H) {
+			d2h->fis_type = FIS_REGD2H;
+			d2h->flags = (1 << 6);
+			d2h->status = 0x50;
+			d2h->error = 0;
+			d2h->lbal = 0;
+			d2h->byte_count_low = len & 0xff;
+			d2h->byte_count_high = len >> 8;
+			d2h->device = 0xa0;
+			d2h->lbal_exp = 0;
+			d2h->lbam_exp = 0;
+			d2h->lbah_exp = 0;
+			d2h->_r_a = 0;
+			d2h->sector_count = 0x3;
+			d2h->sector_count_exp = 0;
+			d2h->_r_b = 0;
+			d2h->_r_c = 0;
+			d2h->_r_d = 0;
+		}
+
+		ireq->scu_status = SCU_TASK_DONE_GOOD;
+		ireq->sci_status = SCI_SUCCESS_IO_DONE_EARLY;
+		status = ireq->sci_status;
+
+		/* the hw will have suspended the rnc, so complete the
+		 * request upon pending resume
+		 */
+		sci_change_state(&idev->sm, SCI_STP_DEV_ATAPI_ERROR);
+		break;
+	}
+	case (SCU_TASK_DONE_EXCESS_DATA << SCU_COMPLETION_TL_STATUS_SHIFT):
+		/* In this case, there is no UF coming after.
+		 * compelte the IO now.
+		 */
+		ireq->scu_status = SCU_TASK_DONE_GOOD;
+		ireq->sci_status = SCI_SUCCESS;
+		sci_change_state(&ireq->sm, SCI_REQ_COMPLETED);
+		break;
+
+	default:
+		if (d2h->fis_type == FIS_REGD2H) {
+			/* UF received change the device state to ATAPI_ERROR */
+			status = ireq->sci_status;
+			sci_change_state(&idev->sm, SCI_STP_DEV_ATAPI_ERROR);
+		} else {
+			/* If receiving any non-sucess TC status, no UF
+			 * received yet, then an UF for the status fis
+			 * is coming after (XXX: suspect this is
+			 * actually a protocol error or a bug like the
+			 * DONE_UNEXP_FIS case)
+			 */
+			ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE;
+			ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID;
+
+			sci_change_state(&ireq->sm, SCI_REQ_ATAPI_WAIT_D2H);
+		}
+		break;
+	}
+
+	return status;
+}
+
 enum sci_status
 sci_io_request_tc_completion(struct isci_request *ireq,
 				  u32 completion_code)
@@ -2017,6 +2297,17 @@ sci_io_request_tc_completion(struct isci_request *ireq,
 		return request_aborting_state_tc_event(ireq,
 						       completion_code);
 
+	case SCI_REQ_ATAPI_WAIT_H2D:
+		return atapi_raw_completion(ireq, completion_code,
+					    SCI_REQ_ATAPI_WAIT_PIO_SETUP);
+
+	case SCI_REQ_ATAPI_WAIT_TC_COMP:
+		return atapi_raw_completion(ireq, completion_code,
+					    SCI_REQ_ATAPI_WAIT_D2H);
+
+	case SCI_REQ_ATAPI_WAIT_D2H:
+		return atapi_data_tc_completion_handler(ireq, completion_code);
+
 	default:
 		dev_warn(&ihost->pdev->dev,
 			 "%s: SCIC IO Request given task completion "
@@ -2423,6 +2714,8 @@ static void isci_process_stp_response(struct sas_task *task, struct dev_to_host_
 	 */
 	if (fis->status & ATA_DF)
 		ts->stat = SAS_PROTO_RESPONSE;
+	else if (fis->status & ATA_ERR)
+		ts->stat = SAM_STAT_CHECK_CONDITION;
 	else
 		ts->stat = SAM_STAT_GOOD;
 
@@ -2782,6 +3075,7 @@ static void sci_request_started_state_enter(struct sci_base_state_machine *sm)
 {
 	struct isci_request *ireq = container_of(sm, typeof(*ireq), sm);
 	struct domain_device *dev = ireq->target_device->domain_dev;
+	enum sci_base_request_states state;
 	struct sas_task *task;
 
 	/* XXX as hch said always creating an internal sas_task for tmf
@@ -2793,26 +3087,30 @@ static void sci_request_started_state_enter(struct sci_base_state_machine *sm)
 	 * substates
 	 */
 	if (!task && dev->dev_type == SAS_END_DEV) {
-		sci_change_state(sm, SCI_REQ_TASK_WAIT_TC_COMP);
+		state = SCI_REQ_TASK_WAIT_TC_COMP;
 	} else if (!task &&
 		   (isci_request_access_tmf(ireq)->tmf_code == isci_tmf_sata_srst_high ||
 		    isci_request_access_tmf(ireq)->tmf_code == isci_tmf_sata_srst_low)) {
-		sci_change_state(sm, SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED);
+		state = SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED;
 	} else if (task && task->task_proto == SAS_PROTOCOL_SMP) {
-		sci_change_state(sm, SCI_REQ_SMP_WAIT_RESP);
+		state = SCI_REQ_SMP_WAIT_RESP;
 	} else if (task && sas_protocol_ata(task->task_proto) &&
 		   !task->ata_task.use_ncq) {
-		u32 state;
-
-		if (task->data_dir == DMA_NONE)
+		if (dev->sata_dev.command_set == ATAPI_COMMAND_SET &&
+			task->ata_task.fis.command == ATA_CMD_PACKET) {
+			state = SCI_REQ_ATAPI_WAIT_H2D;
+		} else if (task->data_dir == DMA_NONE) {
 			state = SCI_REQ_STP_NON_DATA_WAIT_H2D;
-		else if (task->ata_task.dma_xfer)
+		} else if (task->ata_task.dma_xfer) {
 			state = SCI_REQ_STP_UDMA_WAIT_TC_COMP;
-		else /* PIO */
+		} else /* PIO */ {
 			state = SCI_REQ_STP_PIO_WAIT_H2D;
-
-		sci_change_state(sm, state);
+		}
+	} else {
+		/* SSP or NCQ are fully accelerated, no substates */
+		return;
 	}
+	sci_change_state(sm, state);
 }
 
 static void sci_request_completed_state_enter(struct sci_base_state_machine *sm)
@@ -2904,6 +3202,10 @@ static const struct sci_base_state sci_request_state_table[] = {
 	[SCI_REQ_TASK_WAIT_TC_RESP] = { },
 	[SCI_REQ_SMP_WAIT_RESP] = { },
 	[SCI_REQ_SMP_WAIT_TC_COMP] = { },
+	[SCI_REQ_ATAPI_WAIT_H2D] = { },
+	[SCI_REQ_ATAPI_WAIT_PIO_SETUP] = { },
+	[SCI_REQ_ATAPI_WAIT_D2H] = { },
+	[SCI_REQ_ATAPI_WAIT_TC_COMP] = { },
 	[SCI_REQ_COMPLETED] = {
 		.enter_state = sci_request_completed_state_enter,
 	},