[net-next,13/14] net: hns3: handle hw errors of SSU

Message ID	20181207210811.23844-14-salil.mehta@huawei.com
State	New
Headers	show Delivered-To: patch@linaro.org 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: Salil Mehta <salil.mehta@huawei.com> To: <davem@davemloft.net> CC: <salil.mehta@huawei.com>, <yisen.zhuang@huawei.com>, <lipeng321@huawei.com>, <mehta.salil@opnsrc.net>, <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>, <linuxarm@huawei.com>, Shiju Jose <shiju.jose@huawei.com> Subject: [PATCH net-next 13/14] net: hns3: handle hw errors of SSU Date: Fri, 7 Dec 2018 21:08:10 +0000 Message-ID: <20181207210811.23844-14-salil.mehta@huawei.com> In-Reply-To: <20181207210811.23844-1-salil.mehta@huawei.com> References: <20181207210811.23844-1-salil.mehta@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk
Series	net: hns3: Additions/optimizations related to HNS3 H/W err handling \| expand [net-next,00/14] net: hns3: Additions/optimizations related to HNS3 H/W err handling [net-next,01/14] net: hns3: remove existing process error functions and reorder hw_blk table [net-next,03/14] net: hns3: re-enable error interrupts on hw reset [net-next,04/14] net: hns3: deletes unnecessary settings of the descriptor data [net-next,05/14] net: hns3: rename process_hw_error function [net-next,07/14] net: hns3: add handling of hw ras errors using new set of commands [net-next,08/14] net: hns3: deleted logging 1 bit errors [net-next,09/14] net: hns3: add handling of hw errors reported through MSIX [net-next,10/14] net: hns3: add handling of hw errors of MAC [net-next,11/14] net: hns3: handle hw errors of PPP PF [net-next,12/14] net: hns3: handle hw errors of PPU(RCB) [net-next,13/14] net: hns3: handle hw errors of SSU [net-next,14/14] net: hns3: add handling of RDMA RAS errors

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 0223e83..eb91519 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -217,6 +217,8 @@ enum hclge_opcode_type { /* Error INT commands */ HCLGE_MAC_COMMON_INT_EN = 0x030E, HCLGE_TM_SCH_ECC_INT_EN = 0x0829, + HCLGE_SSU_ECC_INT_CMD = 0x0989, + HCLGE_SSU_COMMON_INT_CMD = 0x098C, HCLGE_PPU_MPF_ECC_INT_CMD = 0x0B40, HCLGE_PPU_MPF_OTHER_INT_CMD = 0x0B41, HCLGE_PPU_PF_OTHER_INT_CMD = 0x0B42, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 00086ce..660320d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -263,6 +263,80 @@ static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = { { /* sentinel */ } }; +static const struct hclge_hw_error hclge_ssu_com_err_int[] = { + { .int_msk = BIT(0), .msg = "buf_sum_err" }, + { .int_msk = BIT(1), .msg = "ppp_mb_num_err" }, + { .int_msk = BIT(2), .msg = "ppp_mbid_err" }, + { .int_msk = BIT(3), .msg = "ppp_rlt_mac_err" }, + { .int_msk = BIT(4), .msg = "ppp_rlt_host_err" }, + { .int_msk = BIT(5), .msg = "cks_edit_position_err" }, + { .int_msk = BIT(6), .msg = "cks_edit_condition_err" }, + { .int_msk = BIT(7), .msg = "vlan_edit_condition_err" }, + { .int_msk = BIT(8), .msg = "vlan_num_ot_err" }, + { .int_msk = BIT(9), .msg = "vlan_num_in_err" }, + { /* sentinel */ } +}; + +static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = { + { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" }, + { .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" }, + { .int_msk = BIT(2), .msg = "igu_pkt_without_key_port" }, + { .int_msk = BIT(3), .msg = "roc_eof_mis_match_port" }, + { .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port" }, + { .int_msk = BIT(5), .msg = "igu_eof_mis_match_port" }, + { .int_msk = BIT(6), .msg = "roc_sof_mis_match_port" }, + { .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port" }, + { .int_msk = BIT(8), .msg = "igu_sof_mis_match_port" }, + { .int_msk = BIT(11), .msg = "ets_rd_int_rx_port" }, + { .int_msk = BIT(12), .msg = "ets_wr_int_rx_port" }, + { .int_msk = BIT(13), .msg = "ets_rd_int_tx_port" }, + { .int_msk = BIT(14), .msg = "ets_wr_int_tx_port" }, + { /* sentinel */ } +}; + +static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = { + { .int_msk = BIT(0), .msg = "ig_mac_inf_int" }, + { .int_msk = BIT(1), .msg = "ig_host_inf_int" }, + { .int_msk = BIT(2), .msg = "ig_roc_buf_int" }, + { .int_msk = BIT(3), .msg = "ig_host_data_fifo_int" }, + { .int_msk = BIT(4), .msg = "ig_host_key_fifo_int" }, + { .int_msk = BIT(5), .msg = "tx_qcn_fifo_int" }, + { .int_msk = BIT(6), .msg = "rx_qcn_fifo_int" }, + { .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int" }, + { .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int" }, + { .int_msk = BIT(9), .msg = "qm_eof_fifo_int" }, + { .int_msk = BIT(10), .msg = "mb_rlt_fifo_int" }, + { .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int" }, + { .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int" }, + { .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int" }, + { .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int" }, + { .int_msk = BIT(15), .msg = "host_cmd_fifo_int" }, + { .int_msk = BIT(16), .msg = "mac_cmd_fifo_int" }, + { .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int" }, + { .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int" }, + { .int_msk = BIT(19), .msg = "dup_bitmap_empty_int" }, + { .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int" }, + { .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int" }, + { .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int" }, + { .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int" }, + { /* sentinel */ } +}; + +static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = { + { .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg" }, + { .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg" }, + { .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg" }, + { .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg" }, + { /* sentinel */ } +}; + +static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = { + { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" }, + { .int_msk = BIT(9), .msg = "low_water_line_err_port" }, + { .int_msk = BIT(10), .msg = "hi_water_line_err_port" }, + { /* sentinel */ } +}; + static void hclge_log_error(struct device *dev, char *reg, const struct hclge_hw_error *err, u32 err_sts) @@ -606,6 +680,63 @@ static int hclge_config_ppu_hw_err_int(struct hclge_dev *hdev, bool en) return ret; } +static int hclge_config_ssu_hw_err_int(struct hclge_dev *hdev, bool en) +{ + struct device *dev = &hdev->pdev->dev; + struct hclge_desc desc[2]; + int ret; + + /* configure SSU ecc error interrupts */ + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_ECC_INT_CMD, false); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_ECC_INT_CMD, false); + if (en) { + desc[0].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN); + desc[0].data[1] = + cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN); + desc[0].data[4] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN); + } + + desc[1].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK); + desc[1].data[1] = cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK); + desc[1].data[2] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK); + + ret = hclge_cmd_send(&hdev->hw, &desc[0], 2); + if (ret) { + dev_err(dev, + "fail(%d) to configure SSU ECC error interrupt\n", ret); + return ret; + } + + /* configure SSU common error interrupts */ + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_COMMON_INT_CMD, false); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_COMMON_INT_CMD, false); + + if (en) { + if (hdev->pdev->revision >= 0x21) + desc[0].data[0] = + cpu_to_le32(HCLGE_SSU_COMMON_INT_EN); + else + desc[0].data[0] = + cpu_to_le32(HCLGE_SSU_COMMON_INT_EN & ~BIT(5)); + desc[0].data[1] = cpu_to_le32(HCLGE_SSU_PORT_BASED_ERR_INT_EN); + desc[0].data[2] = + cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN); + } + + desc[1].data[0] = cpu_to_le32(HCLGE_SSU_COMMON_INT_EN_MASK | + HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK); + desc[1].data[1] = cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK); + + ret = hclge_cmd_send(&hdev->hw, &desc[0], 2); + if (ret) + dev_err(dev, + "fail(%d) to configure SSU COMMON error intr\n", ret); + + return ret; +} + #define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \ do { \ if (ae_dev->ops->set_default_reset_request) \ @@ -676,6 +807,27 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET); } + /* log SSU(Storage Switch Unit) errors */ + desc_data = (__le32 *)&desc[2]; + status = le32_to_cpu(*(desc_data + 2)); + if (status) { + dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_0 ssu_ecc_mbit_int[31:0]\n"); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET); + } + + status = le32_to_cpu(*(desc_data + 3)) & BIT(0); + if (status) { + dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_ecc_mbit_int[32]\n"); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET); + } + + status = le32_to_cpu(*(desc_data + 4)) & HCLGE_SSU_COMMON_ERR_INT_MASK; + if (status) { + hclge_log_error(dev, "SSU_COMMON_ERR_INT", + &hclge_ssu_com_err_int[0], status); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET); + } + /* log IGU(Ingress Unit) errors */ desc_data = (__le32 *)&desc[3]; status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK; @@ -775,6 +927,7 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev, struct hclge_desc *desc, int num) { + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; struct device *dev = &hdev->pdev->dev; __le32 *desc_data; u32 status; @@ -791,6 +944,28 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev, return ret; } + /* log SSU(Storage Switch Unit) errors */ + status = le32_to_cpu(desc[0].data[0]); + if (status) { + hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT", + &hclge_ssu_port_based_err_int[0], status); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET); + } + + status = le32_to_cpu(desc[0].data[1]); + if (status) { + hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT", + &hclge_ssu_fifo_overflow_int[0], status); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET); + } + + status = le32_to_cpu(desc[0].data[2]); + if (status) { + hclge_log_error(dev, "SSU_ETS_TCG_INT", + &hclge_ssu_ets_tcg_int[0], status); + HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET); + } + /* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */ desc_data = (__le32 *)&desc[1]; status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK; @@ -858,6 +1033,10 @@ static const struct hclge_hw_blk hw_blk[] = { .config_err_int = hclge_config_ppp_hw_err_int, }, { + .msk = BIT(2), .name = "SSU", + .config_err_int = hclge_config_ssu_hw_err_int, + }, + { .msk = BIT(3), .name = "PPU", .config_err_int = hclge_config_ppu_hw_err_int, }, @@ -1009,6 +1188,14 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev, goto msi_error; } + /* log SSU PF errors */ + status = le32_to_cpu(desc[0].data[0]) & HCLGE_SSU_PORT_INT_MSIX_MASK; + if (status) { + hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT", + &hclge_ssu_port_based_pf_int[0], status); + set_bit(HNAE3_GLOBAL_RESET, reset_requests); + } + /* read and log PPP PF errors */ desc_data = (__le32 *)&desc[2]; status = le32_to_cpu(*desc_data); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index 970d356..d2077f2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -58,7 +58,21 @@ #define HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK GENMASK(23, 16) #define HCLGE_PPU_PF_ABNORMAL_INT_EN GENMASK(5, 0) #define HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK GENMASK(5, 0) +#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN GENMASK(31, 0) +#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK GENMASK(31, 0) +#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN GENMASK(31, 0) +#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK GENMASK(31, 0) +#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN 0x0101 +#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK 0x0101 +#define HCLGE_SSU_COMMON_INT_EN GENMASK(9, 0) +#define HCLGE_SSU_COMMON_INT_EN_MASK GENMASK(9, 0) +#define HCLGE_SSU_PORT_BASED_ERR_INT_EN 0x0BFF +#define HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK 0x0BFF0000 +#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN GENMASK(23, 0) +#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK GENMASK(23, 0) +#define HCLGE_SSU_COMMON_ERR_INT_MASK GENMASK(9, 0) +#define HCLGE_SSU_PORT_INT_MSIX_MASK 0x7BFF #define HCLGE_IGU_INT_MASK GENMASK(3, 0) #define HCLGE_IGU_EGU_TNL_INT_MASK GENMASK(5, 0) #define HCLGE_PPP_MPF_INT_ST3_MASK GENMASK(5, 0)

[net-next,13/14] net: hns3: handle hw errors of SSU

Commit Message

Patch