diff mbox series

[net-next,4/7] net: hns3: Add enable and process common ecc errors

Message ID 20181019191532.10088-5-salil.mehta@huawei.com
State New
Headers show
Series Adds support of RAS Error Handling in HNS3 Driver | expand

Commit Message

Salil Mehta Oct. 19, 2018, 7:15 p.m. UTC 
From: Shiju Jose <shiju.jose@huawei.com>


This patch adds enable and processing of ecc errors from
common HNS blocks, CMDQ(Command Queue),
IMP(Integrated Management Processor) and TQP(Task Queue Pair).

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>

Signed-off-by: Salil Mehta <salil.mehta@huawei.com>

---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   3 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 285 +++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h |  30 +++
 3 files changed, 318 insertions(+)

-- 
2.7.4
diff mbox series

Patch

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 1ccde67..8525f18 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -209,6 +209,9 @@  enum hclge_opcode_type {
 
 	/* Led command */
 	HCLGE_OPC_LED_STATUS_CFG	= 0xB000,
+
+	/* Error INT commands */
+	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
 };
 
 #define HCLGE_TQP_REG_OFFSET		0x80000
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index d2640d1..8b37de4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -3,7 +3,292 @@ 
 
 #include "hclge_err.h"
 
+static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
+	{ .int_msk = BIT(0), .msg = "imp_itcm0_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err" },
+	{ .int_msk = BIT(2), .msg = "imp_itcm1_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "imp_itcm2_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "imp_itcm3_ecc_1bit_err" },
+	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err" },
+	{ .int_msk = BIT(8), .msg = "imp_dtcm0_mem0_ecc_1bit_err" },
+	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err" },
+	{ .int_msk = BIT(10), .msg = "imp_dtcm0_mem1_ecc_1bit_err" },
+	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err" },
+	{ .int_msk = BIT(12), .msg = "imp_dtcm1_mem0_ecc_1bit_err" },
+	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
+	{ .int_msk = BIT(14), .msg = "imp_dtcm1_mem1_ecc_1bit_err" },
+	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_imp_itcm4_ecc_int[] = {
+	{ .int_msk = BIT(0), .msg = "imp_itcm4_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "imp_itcm4_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
+	{ .int_msk = BIT(0), .msg = "cmdq_nic_rx_depth_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(2), .msg = "cmdq_nic_tx_depth_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "cmdq_nic_rx_tail_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "cmdq_nic_tx_tail_ecc_1bit_err" },
+	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(8), .msg = "cmdq_nic_rx_head_ecc_1bit_err" },
+	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(10), .msg = "cmdq_nic_tx_head_ecc_1bit_err" },
+	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(12), .msg = "cmdq_nic_rx_addr_ecc_1bit_err" },
+	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(14), .msg = "cmdq_nic_tx_addr_ecc_1bit_err" },
+	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_cmdq_rocee_mem_ecc_int[] = {
+	{ .int_msk = BIT(0), .msg = "cmdq_rocee_rx_depth_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(2), .msg = "cmdq_rocee_tx_depth_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "cmdq_rocee_rx_tail_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "cmdq_rocee_tx_tail_ecc_1bit_err" },
+	{ .int_msk = BIT(7), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(8), .msg = "cmdq_rocee_rx_head_ecc_1bit_err" },
+	{ .int_msk = BIT(9), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(10), .msg = "cmdq_rocee_tx_head_ecc_1bit_err" },
+	{ .int_msk = BIT(11), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(12), .msg = "cmdq_rocee_rx_addr_ecc_1bit_err" },
+	{ .int_msk = BIT(13), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(14), .msg = "cmdq_rocee_tx_addr_ecc_1bit_err" },
+	{ .int_msk = BIT(15), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
+	{ .int_msk = BIT(0), .msg = "tqp_int_cfg_even_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "tqp_int_cfg_odd_ecc_1bit_err" },
+	{ .int_msk = BIT(2), .msg = "tqp_int_ctrl_even_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "tqp_int_ctrl_odd_ecc_1bit_err" },
+	{ .int_msk = BIT(4), .msg = "tx_que_scan_int_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "rx_que_scan_int_ecc_1bit_err" },
+	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err" },
+	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err" },
+	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err" },
+	{ .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err" },
+	{ .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err" },
+	{ .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static void hclge_log_error(struct device *dev,
+			    const struct hclge_hw_error *err_list,
+			    u32 err_sts)
+{
+	const struct hclge_hw_error *err;
+	int i = 0;
+
+	while (err_list[i].msg) {
+		err = &err_list[i];
+		if (!(err->int_msk & err_sts)) {
+			i++;
+			continue;
+		}
+		dev_warn(dev, "%s [error status=0x%x] found\n",
+			 err->msg, err_sts);
+		i++;
+	}
+}
+
+/* hclge_cmd_query_error: read the error information
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @cmd:  command opcode
+ * @flag: flag for extended command structure
+ * @w_num: offset for setting the read interrupt type.
+ * @int_type: select which type of the interrupt for which the error
+ * info will be read(RAS-CE/RAS-NFE/RAS-FE etc).
+ *
+ * This function query the error info from hw register/s using command
+ */
+static int hclge_cmd_query_error(struct hclge_dev *hdev,
+				 struct hclge_desc *desc, u32 cmd,
+				 u16 flag, u8 w_num,
+				 enum hclge_err_int_type int_type)
+{
+	struct device *dev = &hdev->pdev->dev;
+	int num = 1;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
+	if (flag) {
+		desc[0].flag |= cpu_to_le16(flag);
+		hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
+		num = 2;
+	}
+	if (w_num)
+		desc[0].data[w_num] = cpu_to_le32(int_type);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "query error cmd failed (%d)\n", ret);
+
+	return ret;
+}
+
+/* hclge_cmd_clear_error: clear the error status
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @desc_src: prefilled descriptor from the previous command for reusing
+ * @cmd:  command opcode
+ * @flag: flag for extended command structure
+ *
+ * This function clear the error status in the hw register/s using command
+ */
+static int hclge_cmd_clear_error(struct hclge_dev *hdev,
+				 struct hclge_desc *desc,
+				 struct hclge_desc *desc_src,
+				 u32 cmd, u16 flag)
+{
+	struct device *dev = &hdev->pdev->dev;
+	int num = 1;
+	int ret, i;
+
+	if (cmd) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		if (flag) {
+			desc[0].flag |= cpu_to_le16(flag);
+			hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
+			num = 2;
+		}
+		if (desc_src) {
+			for (i = 0; i < 6; i++) {
+				desc[0].data[i] = desc_src[0].data[i];
+				if (flag)
+					desc[1].data[i] = desc_src[1].data[i];
+			}
+		}
+	} else {
+		hclge_cmd_reuse_desc(&desc[0], false);
+		if (flag) {
+			desc[0].flag |= cpu_to_le16(flag);
+			hclge_cmd_reuse_desc(&desc[1], false);
+			num = 2;
+		}
+	}
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "clear error cmd failed (%d)\n", ret);
+
+	return ret;
+}
+
+static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_COMMON_ECC_INT_CFG, false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_COMMON_ECC_INT_CFG, false);
+
+	if (en) {
+		/* enable COMMON error interrupts */
+		desc[0].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN);
+		desc[0].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN |
+					HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN);
+		desc[0].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN);
+		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN);
+		desc[0].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN);
+	} else {
+		/* disable COMMON error interrupts */
+		desc[0].data[0] = 0;
+		desc[0].data[2] = 0;
+		desc[0].data[3] = 0;
+		desc[0].data[4] = 0;
+		desc[0].data[5] = 0;
+	}
+	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK);
+	desc[1].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN_MASK |
+				HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN_MASK);
+	desc[1].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK);
+	desc[1].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN_MASK);
+	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
+	if (ret)
+		dev_err(dev,
+			"failed(%d) to enable/disable COMMON err interrupts\n",
+			ret);
+
+	return ret;
+}
+
+static void hclge_process_common_error(struct hclge_dev *hdev,
+				       enum hclge_err_int_type type)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	u32 err_sts;
+	int ret;
+
+	/* read err sts */
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_COMMON_ECC_INT_CFG,
+				    HCLGE_CMD_FLAG_NEXT, 0, 0);
+	if (ret) {
+		dev_err(dev,
+			"failed(=%d) to query COMMON error interrupt status\n",
+			ret);
+		return;
+	}
+
+	/* log err */
+	err_sts = (le32_to_cpu(desc[0].data[0])) & HCLGE_IMP_TCM_ECC_INT_MASK;
+	hclge_log_error(dev, &hclge_imp_tcm_ecc_int[0], err_sts);
+
+	err_sts = (le32_to_cpu(desc[0].data[1])) & HCLGE_CMDQ_ECC_INT_MASK;
+	hclge_log_error(dev, &hclge_cmdq_nic_mem_ecc_int[0], err_sts);
+
+	err_sts = (le32_to_cpu(desc[0].data[1]) >> HCLGE_CMDQ_ROC_ECC_INT_SHIFT)
+		   & HCLGE_CMDQ_ECC_INT_MASK;
+	hclge_log_error(dev, &hclge_cmdq_rocee_mem_ecc_int[0], err_sts);
+
+	if ((le32_to_cpu(desc[0].data[3])) & BIT(0))
+		dev_warn(dev, "imp_rd_data_poison_err found\n");
+
+	err_sts = (le32_to_cpu(desc[0].data[3]) >> HCLGE_TQP_ECC_INT_SHIFT) &
+		   HCLGE_TQP_ECC_INT_MASK;
+	hclge_log_error(dev, &hclge_tqp_int_ecc_int[0], err_sts);
+
+	err_sts = (le32_to_cpu(desc[0].data[5])) &
+		   HCLGE_IMP_ITCM4_ECC_INT_MASK;
+	hclge_log_error(dev, &hclge_imp_itcm4_ecc_int[0], err_sts);
+
+	/* clear error interrupts */
+	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_CLR_MASK);
+	desc[1].data[1] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_CLR_MASK |
+				HCLGE_CMDQ_ROCEE_ECC_CLR_MASK);
+	desc[1].data[3] = cpu_to_le32(HCLGE_TQP_IMP_ERR_CLR_MASK);
+	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_CLR_MASK);
+
+	ret = hclge_cmd_clear_error(hdev, &desc[0], NULL, 0,
+				    HCLGE_CMD_FLAG_NEXT);
+	if (ret)
+		dev_err(dev,
+			"failed(%d) to clear COMMON error interrupt status\n",
+			ret);
+}
+
 static const struct hclge_hw_blk hw_blk[] = {
+	{ .msk = BIT(5), .name = "COMMON",
+	  .enable_error = hclge_enable_common_error,
+	  .process_error = hclge_process_common_error, },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 373e9bf..b413141 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -11,6 +11,31 @@ 
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
 #define HCLGE_RAS_REG_NFE_SHIFT	8
 
+#define HCLGE_IMP_TCM_ECC_ERR_INT_EN	0xFFFF0000
+#define HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK	0xFFFF0000
+#define HCLGE_IMP_ITCM4_ECC_ERR_INT_EN	0x300
+#define HCLGE_IMP_ITCM4_ECC_ERR_INT_EN_MASK	0x300
+#define HCLGE_CMDQ_NIC_ECC_ERR_INT_EN	0xFFFF
+#define HCLGE_CMDQ_NIC_ECC_ERR_INT_EN_MASK	0xFFFF
+#define HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN	0xFFFF0000
+#define HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN_MASK	0xFFFF0000
+#define HCLGE_IMP_RD_POISON_ERR_INT_EN	0x0100
+#define HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK	0x0100
+#define HCLGE_TQP_ECC_ERR_INT_EN	0x0FFF
+#define HCLGE_TQP_ECC_ERR_INT_EN_MASK	0x0FFF
+
+#define HCLGE_IMP_TCM_ECC_INT_MASK	0xFFFF
+#define HCLGE_IMP_ITCM4_ECC_INT_MASK	0x3
+#define HCLGE_CMDQ_ECC_INT_MASK		0xFFFF
+#define HCLGE_CMDQ_ROC_ECC_INT_SHIFT	16
+#define HCLGE_TQP_ECC_INT_MASK		0xFFF
+#define HCLGE_TQP_ECC_INT_SHIFT		16
+#define HCLGE_IMP_TCM_ECC_CLR_MASK	0xFFFF
+#define HCLGE_IMP_ITCM4_ECC_CLR_MASK	0x3
+#define HCLGE_CMDQ_NIC_ECC_CLR_MASK	0xFFFF
+#define HCLGE_CMDQ_ROCEE_ECC_CLR_MASK	0xFFFF0000
+#define HCLGE_TQP_IMP_ERR_CLR_MASK	0x0FFF0001
+
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
@@ -26,6 +51,11 @@  struct hclge_hw_blk {
 			      enum hclge_err_int_type type);
 };
 
+struct hclge_hw_error {
+	u32 int_msk;
+	const char *msg;
+};
+
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
 pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev);
 #endif