Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   John Garry <john.garry@huawei.com>
To:     <jejb@linux.vnet.ibm.com>, <martin.petersen@oracle.com>
CC:     <linuxarm@huawei.com>, <linux-kernel@vger.kernel.org>,
        <linux-scsi@vger.kernel.org>,
        Xiang Chen <chenxiang66@hisilicon.com>,
        "John Garry" <john.garry@huawei.com>
Subject: [PATCH 1/6] scsi: hisi_sas: Add support for DIX feature for v3 hw
Date:   Wed, 6 Feb 2019 18:52:51 +0800
Message-ID: <1549450376-114929-2-git-send-email-john.garry@huawei.com>
In-Reply-To: <1549450376-114929-1-git-send-email-john.garry@huawei.com>
References: <1549450376-114929-1-git-send-email-john.garry@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Xiang Chen <chenxiang66@hisilicon.com>

This patch adds support for DIX to v3 hw driver.

For this, we build upon support for DIF, most significantly
is adding new DMA map and unmap paths.

Some pre-existing macro precedence issues are also tidied. They
were detected by checkpatch --strict.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h       | 40 ++++++++---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 96 +++++++++++++++++++++++---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 80 +++++++++++++++++----
 3 files changed, 184 insertions(+), 32 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 9b35f84b5029..df2a92a0e7a1 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -41,20 +41,25 @@
 #define HISI_SAS_COMMAND_TABLE_SZ (sizeof(union hisi_sas_command_table))
 
 #define hisi_sas_status_buf_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, status_buffer))
-#define hisi_sas_status_buf_addr_mem(slot) hisi_sas_status_buf_addr(slot->buf)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, status_buffer))
+#define hisi_sas_status_buf_addr_mem(slot) hisi_sas_status_buf_addr((slot)->buf)
 #define hisi_sas_status_buf_addr_dma(slot) \
-	hisi_sas_status_buf_addr(slot->buf_dma)
+	hisi_sas_status_buf_addr((slot)->buf_dma)
 
 #define hisi_sas_cmd_hdr_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, command_header))
-#define hisi_sas_cmd_hdr_addr_mem(slot) hisi_sas_cmd_hdr_addr(slot->buf)
-#define hisi_sas_cmd_hdr_addr_dma(slot) hisi_sas_cmd_hdr_addr(slot->buf_dma)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, command_header))
+#define hisi_sas_cmd_hdr_addr_mem(slot) hisi_sas_cmd_hdr_addr((slot)->buf)
+#define hisi_sas_cmd_hdr_addr_dma(slot) hisi_sas_cmd_hdr_addr((slot)->buf_dma)
 
 #define hisi_sas_sge_addr(buf) \
-	(buf + offsetof(struct hisi_sas_slot_buf_table, sge_page))
-#define hisi_sas_sge_addr_mem(slot) hisi_sas_sge_addr(slot->buf)
-#define hisi_sas_sge_addr_dma(slot) hisi_sas_sge_addr(slot->buf_dma)
+	((buf) + offsetof(struct hisi_sas_slot_buf_table, sge_page))
+#define hisi_sas_sge_addr_mem(slot) hisi_sas_sge_addr((slot)->buf)
+#define hisi_sas_sge_addr_dma(slot) hisi_sas_sge_addr((slot)->buf_dma)
+
+#define hisi_sas_sge_dif_addr(buf) \
+	((buf) + offsetof(struct hisi_sas_slot_dif_buf_table, sge_dif_page))
+#define hisi_sas_sge_dif_addr_mem(slot) hisi_sas_sge_dif_addr((slot)->buf)
+#define hisi_sas_sge_dif_addr_dma(slot) hisi_sas_sge_dif_addr((slot)->buf_dma)
 
 #define HISI_SAS_MAX_SSP_RESP_SZ (sizeof(struct ssp_frame_hdr) + 1024)
 #define HISI_SAS_MAX_SMP_RESP_SZ 1028
@@ -74,7 +79,11 @@
 				SHOST_DIF_TYPE2_PROTECTION | \
 				SHOST_DIF_TYPE3_PROTECTION)
 
-#define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK)
+#define HISI_SAS_DIX_PROT_MASK (SHOST_DIX_TYPE1_PROTECTION | \
+				SHOST_DIX_TYPE2_PROTECTION | \
+				SHOST_DIX_TYPE3_PROTECTION)
+
+#define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK | HISI_SAS_DIX_PROT_MASK)
 
 #define HISI_SAS_WAIT_PHYUP_TIMEOUT 20
 
@@ -201,6 +210,7 @@ struct hisi_sas_slot {
 	struct sas_task *task;
 	struct hisi_sas_port	*port;
 	u64	n_elem;
+	u64	n_elem_dif;
 	int	dlvry_queue;
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
@@ -464,6 +474,11 @@ struct hisi_sas_sge_page {
 	struct hisi_sas_sge sge[HISI_SAS_SGE_PAGE_CNT];
 }  __aligned(16);
 
+#define HISI_SAS_SGE_DIF_PAGE_CNT   SG_CHUNK_SIZE
+struct hisi_sas_sge_dif_page {
+	struct hisi_sas_sge sge[HISI_SAS_SGE_DIF_PAGE_CNT];
+}  __aligned(16);
+
 struct hisi_sas_command_table_ssp {
 	struct ssp_frame_hdr hdr;
 	union {
@@ -494,6 +509,11 @@ struct hisi_sas_slot_buf_table {
 	struct hisi_sas_sge_page sge_page;
 };
 
+struct hisi_sas_slot_dif_buf_table {
+	struct hisi_sas_slot_buf_table slot_buf;
+	struct hisi_sas_sge_dif_page sge_dif_page;
+};
+
 extern struct scsi_transport_template *hisi_sas_stt;
 
 extern bool hisi_sas_debugfs_enable;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 2d6b5fe90a9e..1a3d31d4258c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -252,11 +252,19 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 
 		task->lldd_task = NULL;
 
-		if (!sas_protocol_ata(task->task_proto))
+		if (!sas_protocol_ata(task->task_proto)) {
+			struct sas_ssp_task *ssp_task = &task->ssp_task;
+			struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+
 			if (slot->n_elem)
 				dma_unmap_sg(dev, task->scatter,
 					     task->num_scatter,
 					     task->data_dir);
+			if (slot->n_elem_dif)
+				dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+					     scsi_prot_sg_count(scsi_cmnd),
+					     task->data_dir);
+		}
 	}
 
 
@@ -380,6 +388,59 @@ static int hisi_sas_dma_map(struct hisi_hba *hisi_hba,
 	return rc;
 }
 
+static void hisi_sas_dif_dma_unmap(struct hisi_hba *hisi_hba,
+				   struct sas_task *task, int n_elem_dif)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (n_elem_dif) {
+		struct sas_ssp_task *ssp_task = &task->ssp_task;
+		struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+
+		dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+			     scsi_prot_sg_count(scsi_cmnd),
+			     task->data_dir);
+	}
+}
+
+static int hisi_sas_dif_dma_map(struct hisi_hba *hisi_hba,
+				int *n_elem_dif, struct sas_task *task)
+{
+	struct device *dev = hisi_hba->dev;
+	struct sas_ssp_task *ssp_task;
+	struct scsi_cmnd *scsi_cmnd;
+	int rc;
+
+	if (task->num_scatter) {
+		ssp_task = &task->ssp_task;
+		scsi_cmnd = ssp_task->cmd;
+
+		if (scsi_prot_sg_count(scsi_cmnd)) {
+			*n_elem_dif = dma_map_sg(dev,
+						 scsi_prot_sglist(scsi_cmnd),
+						 scsi_prot_sg_count(scsi_cmnd),
+						 task->data_dir);
+
+			if (!*n_elem_dif)
+				return -ENOMEM;
+
+			if (*n_elem_dif > HISI_SAS_SGE_DIF_PAGE_CNT) {
+				dev_err(dev, "task prep: n_elem_dif(%d) too large\n",
+					*n_elem_dif);
+				rc = -EINVAL;
+				goto err_out_dif_dma_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+err_out_dif_dma_unmap:
+	dma_unmap_sg(dev, scsi_prot_sglist(scsi_cmnd),
+		     scsi_prot_sg_count(scsi_cmnd), task->data_dir);
+	return rc;
+}
+
 static int hisi_sas_task_prep(struct sas_task *task,
 			      struct hisi_sas_dq **dq_pointer,
 			      bool is_tmf, struct hisi_sas_tmf_task *tmf,
@@ -394,7 +455,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	struct asd_sas_port *sas_port = device->port;
 	struct device *dev = hisi_hba->dev;
 	int dlvry_queue_slot, dlvry_queue, rc, slot_idx;
-	int n_elem = 0, n_elem_req = 0, n_elem_resp = 0;
+	int n_elem = 0, n_elem_dif = 0, n_elem_req = 0, n_elem_resp = 0;
 	struct hisi_sas_dq *dq;
 	unsigned long flags;
 	int wr_q_index;
@@ -427,6 +488,12 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	if (rc < 0)
 		goto prep_out;
 
+	if (!sas_protocol_ata(task->task_proto)) {
+		rc = hisi_sas_dif_dma_map(hisi_hba, &n_elem_dif, task);
+		if (rc < 0)
+			goto err_out_dma_unmap;
+	}
+
 	if (hisi_hba->hw->slot_index_alloc)
 		rc = hisi_hba->hw->slot_index_alloc(hisi_hba, device);
 	else {
@@ -445,7 +512,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		rc  = hisi_sas_slot_index_alloc(hisi_hba, scsi_cmnd);
 	}
 	if (rc < 0)
-		goto err_out_dma_unmap;
+		goto err_out_dif_dma_unmap;
 
 	slot_idx = rc;
 	slot = &hisi_hba->slot_info[slot_idx];
@@ -466,6 +533,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	dlvry_queue_slot = wr_q_index;
 
 	slot->n_elem = n_elem;
+	slot->n_elem_dif = n_elem_dif;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
 	cmd_hdr_base = hisi_hba->cmd_hdr[dlvry_queue];
@@ -509,6 +577,9 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 err_out_tag:
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
+err_out_dif_dma_unmap:
+	if (!sas_protocol_ata(task->task_proto))
+		hisi_sas_dif_dma_unmap(hisi_hba, task, n_elem_dif);
 err_out_dma_unmap:
 	hisi_sas_dma_unmap(hisi_hba, task, n_elem,
 			   n_elem_req, n_elem_resp);
@@ -2174,19 +2245,24 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba)
 
 	/* roundup to avoid overly large block size */
 	max_command_entries_ru = roundup(max_command_entries, 64);
-	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	if (hisi_hba->prot_mask & HISI_SAS_DIX_PROT_MASK)
+		sz_slot_buf_ru = sizeof(struct hisi_sas_slot_dif_buf_table);
+	else
+		sz_slot_buf_ru = sizeof(struct hisi_sas_slot_buf_table);
+	sz_slot_buf_ru = roundup(sz_slot_buf_ru, 64);
 	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
 	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
 	slots_per_blk = s / sz_slot_buf_ru;
+
 	for (i = 0; i < blk_cnt; i++) {
-		struct hisi_sas_slot_buf_table *buf;
-		dma_addr_t buf_dma;
 		int slot_index = i * slots_per_blk;
+		dma_addr_t buf_dma;
+		void *buf;
 
-		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		buf = dmam_alloc_coherent(dev, s, &buf_dma,
+					  GFP_KERNEL | __GFP_ZERO);
 		if (!buf)
 			goto err_out;
-		memset(buf, 0, s);
 
 		for (j = 0; j < slots_per_blk; j++, slot_index++) {
 			struct hisi_sas_slot *slot;
@@ -2196,8 +2272,8 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba)
 			slot->buf_dma = buf_dma;
 			slot->idx = slot_index;
 
-			buf++;
-			buf_dma += sizeof(*buf);
+			buf += sz_slot_buf_ru;
+			buf_dma += sz_slot_buf_ru;
 		}
 	}
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index eafcab088c0b..0455fba93daf 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -399,6 +399,8 @@ struct hisi_sas_err_record_v3 {
 #define USR_DATA_BLOCK_SZ_OFF	20
 #define USR_DATA_BLOCK_SZ_MSK	(0x3 << USR_DATA_BLOCK_SZ_OFF)
 #define T10_CHK_MSK_OFF	    16
+#define T10_CHK_REF_TAG_MSK (0xf0 << T10_CHK_MSK_OFF)
+#define T10_CHK_APP_TAG_MSK (0xc << T10_CHK_MSK_OFF)
 
 static bool hisi_sas_intr_conv;
 MODULE_PARM_DESC(intr_conv, "interrupt converge enable (0-1)");
@@ -969,19 +971,44 @@ static void prep_prd_sge_v3_hw(struct hisi_hba *hisi_hba,
 
 	hdr->prd_table_addr = cpu_to_le64(hisi_sas_sge_addr_dma(slot));
 
-	hdr->sg_len = cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
+	hdr->sg_len |= cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
+}
+
+static void prep_prd_sge_dif_v3_hw(struct hisi_hba *hisi_hba,
+				   struct hisi_sas_slot *slot,
+				   struct hisi_sas_cmd_hdr *hdr,
+				   struct scatterlist *scatter,
+				   int n_elem)
+{
+	struct hisi_sas_sge_dif_page *sge_dif_page;
+	struct scatterlist *sg;
+	int i;
+
+	sge_dif_page = hisi_sas_sge_dif_addr_mem(slot);
+
+	for_each_sg(scatter, sg, n_elem, i) {
+		struct hisi_sas_sge *entry = &sge_dif_page->sge[i];
+
+		entry->addr = cpu_to_le64(sg_dma_address(sg));
+		entry->page_ctrl_0 = 0;
+		entry->page_ctrl_1 = 0;
+		entry->data_len = cpu_to_le32(sg_dma_len(sg));
+		entry->data_off = 0;
+	}
+
+	hdr->dif_prd_table_addr =
+		cpu_to_le64(hisi_sas_sge_dif_addr_dma(slot));
+
+	hdr->sg_len |= cpu_to_le32(n_elem << CMD_HDR_DIF_SGL_LEN_OFF);
 }
 
 static u32 get_prot_chk_msk_v3_hw(struct scsi_cmnd *scsi_cmnd)
 {
 	unsigned char prot_flags = scsi_cmnd->prot_flags;
 
-	if (prot_flags & SCSI_PROT_TRANSFER_PI) {
-		if (prot_flags & SCSI_PROT_REF_CHECK)
-			return 0xc << 16;
-		return 0xfc << 16;
-	}
-	return 0;
+	if (prot_flags & SCSI_PROT_REF_CHECK)
+		return T10_CHK_APP_TAG_MSK;
+	return T10_CHK_REF_TAG_MSK | T10_CHK_APP_TAG_MSK;
 }
 
 static void fill_prot_v3_hw(struct scsi_cmnd *scsi_cmnd,
@@ -992,15 +1019,33 @@ static void fill_prot_v3_hw(struct scsi_cmnd *scsi_cmnd,
 	u32 lbrt_chk_val = t10_pi_ref_tag(scsi_cmnd->request);
 
 	switch (prot_op) {
+	case SCSI_PROT_READ_INSERT:
+		prot->dw0 |= T10_INSRT_EN_MSK;
+		prot->lbrtgv = lbrt_chk_val;
+		break;
 	case SCSI_PROT_READ_STRIP:
 		prot->dw0 |= (T10_RMV_EN_MSK | T10_CHK_EN_MSK);
 		prot->lbrtcv = lbrt_chk_val;
 		prot->dw4 |= get_prot_chk_msk_v3_hw(scsi_cmnd);
 		break;
+	case SCSI_PROT_READ_PASS:
+		prot->dw0 |= T10_CHK_EN_MSK;
+		prot->lbrtcv = lbrt_chk_val;
+		prot->dw4 |= get_prot_chk_msk_v3_hw(scsi_cmnd);
+		break;
 	case SCSI_PROT_WRITE_INSERT:
 		prot->dw0 |= T10_INSRT_EN_MSK;
 		prot->lbrtgv = lbrt_chk_val;
 		break;
+	case SCSI_PROT_WRITE_STRIP:
+		prot->dw0 |= (T10_RMV_EN_MSK | T10_CHK_EN_MSK);
+		prot->lbrtcv = lbrt_chk_val;
+		break;
+	case SCSI_PROT_WRITE_PASS:
+		prot->dw0 |= T10_CHK_EN_MSK;
+		prot->lbrtcv = lbrt_chk_val;
+		prot->dw4 |= get_prot_chk_msk_v3_hw(scsi_cmnd);
+		break;
 	default:
 		WARN(1, "prot_op(0x%x) is not valid\n", prot_op);
 		break;
@@ -1077,9 +1122,15 @@ static void prep_ssp_v3_hw(struct hisi_hba *hisi_hba,
 	hdr->dw2 = cpu_to_le32(dw2);
 	hdr->transfer_tags = cpu_to_le32(slot->idx);
 
-	if (has_data)
+	if (has_data) {
 		prep_prd_sge_v3_hw(hisi_hba, slot, hdr, task->scatter,
-					slot->n_elem);
+				   slot->n_elem);
+
+		if (scsi_prot_sg_count(scsi_cmnd))
+			prep_prd_sge_dif_v3_hw(hisi_hba, slot, hdr,
+					       scsi_prot_sglist(scsi_cmnd),
+					       slot->n_elem_dif);
+	}
 
 	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
 	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
@@ -1120,18 +1171,19 @@ static void prep_ssp_v3_hw(struct hisi_hba *hisi_hba,
 		fill_prot_v3_hw(scsi_cmnd, &prot);
 		memcpy(buf_cmd_prot, &prot,
 		       sizeof(struct hisi_sas_protect_iu_v3_hw));
-
 		/*
 		 * For READ, we need length of info read to memory, while for
 		 * WRITE we need length of data written to the disk.
 		 */
-		if (prot_op == SCSI_PROT_WRITE_INSERT) {
+		if (prot_op == SCSI_PROT_WRITE_INSERT ||
+		    prot_op == SCSI_PROT_READ_INSERT ||
+		    prot_op == SCSI_PROT_WRITE_PASS ||
+		    prot_op == SCSI_PROT_READ_PASS) {
 			unsigned int interval = scsi_prot_interval(scsi_cmnd);
 			unsigned int ilog2_interval = ilog2(interval);
 
 			len = (task->total_xfer_len >> ilog2_interval) * 8;
 		}
-
 	}
 
 	hdr->dw1 = cpu_to_le32(dw1);
@@ -2526,6 +2578,7 @@ static struct scsi_host_template sht_v3_hw = {
 	.bios_param		= sas_bios_param,
 	.this_id		= -1,
 	.sg_tablesize		= HISI_SAS_SGE_PAGE_CNT,
+	.sg_prot_tablesize	= HISI_SAS_SGE_PAGE_CNT,
 	.max_sectors		= SCSI_DEFAULT_MAX_SECTORS,
 	.eh_device_reset_handler = sas_eh_device_reset_handler,
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
@@ -2701,6 +2754,9 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_info(dev, "Registering for DIF/DIX prot_mask=0x%x\n",
 			 prot_mask);
 		scsi_host_set_prot(hisi_hba->shost, prot_mask);
+		if (hisi_hba->prot_mask & HISI_SAS_DIX_PROT_MASK)
+			scsi_host_set_guard(hisi_hba->shost,
+					    SHOST_DIX_GUARD_CRC);
 	}
 
 	rc = scsi_add_host(shost, dev);
-- 
2.17.1