driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6J5O7
----------------------------------------------------------------------
hns roce support 4 congestion control algorithms. Each algorihm involves multiple parameters. This patch add port sysfs directory for each algorithm, which allows users to modify the parameters of these algorithms.
Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Juan Zhou zhoujuan51@h-partners.com --- drivers/infiniband/hw/hns/Makefile | 2 +- drivers/infiniband/hw/hns/hns_roce_device.h | 27 ++ drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 63 ++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 132 ++++++++ drivers/infiniband/hw/hns/hns_roce_main.c | 3 + drivers/infiniband/hw/hns/hns_roce_sysfs.c | 346 ++++++++++++++++++++ 6 files changed, 572 insertions(+), 1 deletion(-) create mode 100644 drivers/infiniband/hw/hns/hns_roce_sysfs.c
diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index be1e1cdbcfa8..161615fda3ae 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -8,7 +8,7 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o \ - hns_roce_debugfs.o + hns_roce_debugfs.o hns_roce_sysfs.o
ifdef CONFIG_INFINIBAND_HNS_HIP08 hns-roce-hw-v2-objs := hns_roce_hw_v2.o $(hns-roce-objs) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index d8887b5d9882..d6c33bdf56d3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -710,6 +710,14 @@ struct hns_roce_eq_table { struct hns_roce_eq *eq; };
+enum hns_roce_scc_algo { + HNS_ROCE_SCC_ALGO_DCQCN = 0, + HNS_ROCE_SCC_ALGO_LDCP, + HNS_ROCE_SCC_ALGO_HC3, + HNS_ROCE_SCC_ALGO_DIP, + HNS_ROCE_SCC_ALGO_TOTAL, +}; + enum cong_type { CONG_TYPE_DCQCN, CONG_TYPE_LDCP, @@ -954,6 +962,20 @@ struct hns_roce_hw { u64 *stats, u32 port, int *hw_counters); const struct ib_device_ops *hns_roce_dev_ops; const struct ib_device_ops *hns_roce_dev_srq_ops; + int (*config_scc_param)(struct hns_roce_dev *hr_dev, + enum hns_roce_scc_algo algo); + int (*query_scc_param)(struct hns_roce_dev *hr_dev, + enum hns_roce_scc_algo alog); +}; + +#define HNS_ROCE_SCC_PARAM_SIZE 4 +struct hns_roce_scc_param { + __le32 param[HNS_ROCE_SCC_PARAM_SIZE]; + u32 lifespan; + unsigned long timestamp; + enum hns_roce_scc_algo algo_type; + struct delayed_work scc_cfg_dwork; + struct hns_roce_dev *hr_dev; };
struct hns_roce_dev { @@ -1019,6 +1041,7 @@ struct hns_roce_dev { u64 dwqe_page; struct hns_roce_dev_debugfs dbgfs; atomic64_t *dfx_cnt; + struct hns_roce_scc_param *scc_param; };
static inline struct hns_roce_dev *to_hr_dev(struct ib_device *ib_dev) @@ -1154,6 +1177,8 @@ static inline u8 get_tclass(const struct ib_global_route *grh) grh->traffic_class >> DSCP_SHIFT : grh->traffic_class; }
+extern const struct attribute_group *hns_attr_port_groups[]; + void hns_roce_init_uar_table(struct hns_roce_dev *dev); int hns_roce_uar_alloc(struct hns_roce_dev *dev, struct hns_roce_uar *uar);
@@ -1294,4 +1319,6 @@ struct hns_user_mmap_entry * hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address, size_t length, enum hns_roce_mmap_type mmap_type); +void hns_roce_register_sysfs(struct hns_roce_dev *hr_dev); +void hns_roce_unregister_sysfs(struct hns_roce_dev *hr_dev); #endif /* _HNS_ROCE_DEVICE_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 4d6a64df5a03..905040e9ccbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -6733,6 +6733,67 @@ static void hns_roce_v2_cleanup_eq_table(struct hns_roce_dev *hr_dev) kfree(eq_table->eq); }
+static const enum hns_roce_opcode_type scc_opcode[] = { + HNS_ROCE_OPC_CFG_DCQCN_PARAM, + HNS_ROCE_OPC_CFG_LDCP_PARAM, + HNS_ROCE_OPC_CFG_HC3_PARAM, + HNS_ROCE_OPC_CFG_DIP_PARAM, +}; + +static int hns_roce_v2_config_scc_param(struct hns_roce_dev *hr_dev, + enum hns_roce_scc_algo algo) +{ + struct hns_roce_scc_param *scc_param; + struct hns_roce_cmq_desc desc; + int ret; + + if (algo >= HNS_ROCE_SCC_ALGO_TOTAL) { + ibdev_err_ratelimited(&hr_dev->ib_dev, "invalid SCC algo.\n"); + return -EINVAL; + } + + hns_roce_cmq_setup_basic_desc(&desc, scc_opcode[algo], false); + scc_param = &hr_dev->scc_param[algo]; + memcpy(&desc.data, scc_param, sizeof(scc_param->param)); + + ret = hns_roce_cmq_send(hr_dev, &desc, 1); + if (ret) + ibdev_err_ratelimited(&hr_dev->ib_dev, + "failed to configure scc param, opcode: 0x%x, ret = %d.\n", + le16_to_cpu(desc.opcode), ret); + return ret; +} + +static int hns_roce_v2_query_scc_param(struct hns_roce_dev *hr_dev, + enum hns_roce_scc_algo algo) +{ + struct hns_roce_scc_param *scc_param; + struct hns_roce_cmq_desc desc; + int ret; + + if (hr_dev->pci_dev->revision <= PCI_REVISION_ID_HIP08 || hr_dev->is_vf) + return -EOPNOTSUPP; + + if (algo >= HNS_ROCE_SCC_ALGO_TOTAL) { + ibdev_err_ratelimited(&hr_dev->ib_dev, "invalid SCC algo.\n"); + return -EINVAL; + } + + hns_roce_cmq_setup_basic_desc(&desc, scc_opcode[algo], true); + ret = hns_roce_cmq_send(hr_dev, &desc, 1); + if (ret) { + ibdev_err_ratelimited(&hr_dev->ib_dev, + "failed to query scc param, opcode: 0x%x, ret = %d.\n", + le16_to_cpu(desc.opcode), ret); + return ret; + } + + scc_param = &hr_dev->scc_param[algo]; + memcpy(scc_param, &desc.data, sizeof(scc_param->param)); + + return 0; +} + static const struct ib_device_ops hns_roce_v2_dev_ops = { .destroy_qp = hns_roce_v2_destroy_qp, .modify_cq = hns_roce_v2_modify_cq, @@ -6782,6 +6843,8 @@ static const struct hns_roce_hw hns_roce_hw_v2 = { .query_hw_counter = hns_roce_hw_v2_query_counter, .hns_roce_dev_ops = &hns_roce_v2_dev_ops, .hns_roce_dev_srq_ops = &hns_roce_v2_dev_srq_ops, + .config_scc_param = hns_roce_v2_config_scc_param, + .query_scc_param = hns_roce_v2_query_scc_param, };
static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 3fe2d9467612..741be211ed7e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -195,6 +195,10 @@ enum { /* CMQ command */ enum hns_roce_opcode_type { HNS_QUERY_FW_VER = 0x0001, + HNS_ROCE_OPC_CFG_DCQCN_PARAM = 0x1A80, + HNS_ROCE_OPC_CFG_LDCP_PARAM = 0x1A81, + HNS_ROCE_OPC_CFG_HC3_PARAM = 0x1A82, + HNS_ROCE_OPC_CFG_DIP_PARAM = 0x1A83, HNS_ROCE_OPC_QUERY_HW_VER = 0x8000, HNS_ROCE_OPC_CFG_GLOBAL_PARAM = 0x8001, HNS_ROCE_OPC_ALLOC_PF_RES = 0x8004, @@ -1428,6 +1432,134 @@ struct hns_roce_wqe_atomic_seg { __le64 cmp_data; };
+#define HNS_ROCE_DCQCN_AI_OFS 0 +#define HNS_ROCE_DCQCN_AI_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_AI_MAX ((u16)(~0U)) +#define HNS_ROCE_DCQCN_F_OFS (HNS_ROCE_DCQCN_AI_OFS + HNS_ROCE_DCQCN_AI_SZ) +#define HNS_ROCE_DCQCN_F_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_F_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_TKP_OFS (HNS_ROCE_DCQCN_F_OFS + HNS_ROCE_DCQCN_F_SZ) +#define HNS_ROCE_DCQCN_TKP_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_TKP_MAX 15 +#define HNS_ROCE_DCQCN_TMP_OFS (HNS_ROCE_DCQCN_TKP_OFS + HNS_ROCE_DCQCN_TKP_SZ) +#define HNS_ROCE_DCQCN_TMP_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_TMP_MAX 15 +#define HNS_ROCE_DCQCN_ALP_OFS (HNS_ROCE_DCQCN_TMP_OFS + HNS_ROCE_DCQCN_TMP_SZ) +#define HNS_ROCE_DCQCN_ALP_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_ALP_MAX ((u16)(~0U)) +#define HNS_ROCE_DCQCN_MAX_SPEED_OFS (HNS_ROCE_DCQCN_ALP_OFS + \ + HNS_ROCE_DCQCN_ALP_SZ) +#define HNS_ROCE_DCQCN_MAX_SPEED_SZ sizeof(u32) +#define HNS_ROCE_DCQCN_MAX_SPEED_MAX ((u32)(~0U)) +#define HNS_ROCE_DCQCN_G_OFS (HNS_ROCE_DCQCN_MAX_SPEED_OFS + \ + HNS_ROCE_DCQCN_MAX_SPEED_SZ) +#define HNS_ROCE_DCQCN_G_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_G_MAX 15 +#define HNS_ROCE_DCQCN_AL_OFS (HNS_ROCE_DCQCN_G_OFS + HNS_ROCE_DCQCN_G_SZ) +#define HNS_ROCE_DCQCN_AL_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_AL_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_CNP_TIME_OFS (HNS_ROCE_DCQCN_AL_OFS + \ + HNS_ROCE_DCQCN_AL_SZ) +#define HNS_ROCE_DCQCN_CNP_TIME_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_CNP_TIME_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_ASHIFT_OFS (HNS_ROCE_DCQCN_CNP_TIME_OFS + \ + HNS_ROCE_DCQCN_CNP_TIME_SZ) +#define HNS_ROCE_DCQCN_ASHIFT_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_ASHIFT_MAX 15 +#define HNS_ROCE_DCQCN_LIFESPAN_OFS (HNS_ROCE_DCQCN_ASHIFT_OFS + \ + HNS_ROCE_DCQCN_ASHIFT_SZ) +#define HNS_ROCE_DCQCN_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_DCQCN_LIFESPAN_MAX 1000 + +#define HNS_ROCE_LDCP_CWD0_OFS 0 +#define HNS_ROCE_LDCP_CWD0_SZ sizeof(u32) +#define HNS_ROCE_LDCP_CWD0_MAX ((u32)(~0U)) +#define HNS_ROCE_LDCP_ALPHA_OFS (HNS_ROCE_LDCP_CWD0_OFS + HNS_ROCE_LDCP_CWD0_SZ) +#define HNS_ROCE_LDCP_ALPHA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_ALPHA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_GAMMA_OFS (HNS_ROCE_LDCP_ALPHA_OFS + \ + HNS_ROCE_LDCP_ALPHA_SZ) +#define HNS_ROCE_LDCP_GAMMA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_GAMMA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_BETA_OFS (HNS_ROCE_LDCP_GAMMA_OFS + \ + HNS_ROCE_LDCP_GAMMA_SZ) +#define HNS_ROCE_LDCP_BETA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_BETA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_ETA_OFS (HNS_ROCE_LDCP_BETA_OFS + HNS_ROCE_LDCP_BETA_SZ) +#define HNS_ROCE_LDCP_ETA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_ETA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_LIFESPAN_OFS (4 * sizeof(u32)) +#define HNS_ROCE_LDCP_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_LDCP_LIFESPAN_MAX 1000 + +#define HNS_ROCE_HC3_INITIAL_WINDOW_OFS 0 +#define HNS_ROCE_HC3_INITIAL_WINDOW_SZ sizeof(u32) +#define HNS_ROCE_HC3_INITIAL_WINDOW_MAX ((u32)(~0U)) +#define HNS_ROCE_HC3_BANDWIDTH_OFS (HNS_ROCE_HC3_INITIAL_WINDOW_OFS + \ + HNS_ROCE_HC3_INITIAL_WINDOW_SZ) +#define HNS_ROCE_HC3_BANDWIDTH_SZ sizeof(u32) +#define HNS_ROCE_HC3_BANDWIDTH_MAX ((u32)(~0U)) +#define HNS_ROCE_HC3_QLEN_SHIFT_OFS (HNS_ROCE_HC3_BANDWIDTH_OFS + \ + HNS_ROCE_HC3_BANDWIDTH_SZ) +#define HNS_ROCE_HC3_QLEN_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_QLEN_SHIFT_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_OFS (HNS_ROCE_HC3_QLEN_SHIFT_OFS + \ + HNS_ROCE_HC3_QLEN_SHIFT_SZ) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_OVER_PERIOD_OFS (HNS_ROCE_HC3_PORT_USAGE_SHIFT_OFS + \ + HNS_ROCE_HC3_PORT_USAGE_SHIFT_SZ) +#define HNS_ROCE_HC3_OVER_PERIOD_SZ sizeof(u8) +#define HNS_ROCE_HC3_OVER_PERIOD_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_MAX_STAGE_OFS (HNS_ROCE_HC3_OVER_PERIOD_OFS + \ + HNS_ROCE_HC3_OVER_PERIOD_SZ) +#define HNS_ROCE_HC3_MAX_STAGE_SZ sizeof(u8) +#define HNS_ROCE_HC3_MAX_STAGE_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_GAMMA_SHIFT_OFS (HNS_ROCE_HC3_MAX_STAGE_OFS + \ + HNS_ROCE_HC3_MAX_STAGE_SZ) +#define HNS_ROCE_HC3_GAMMA_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_GAMMA_SHIFT_MAX 15 +#define HNS_ROCE_HC3_LIFESPAN_OFS (4 * sizeof(u32)) +#define HNS_ROCE_HC3_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_HC3_LIFESPAN_MAX 1000 + +#define HNS_ROCE_DIP_AI_OFS 0 +#define HNS_ROCE_DIP_AI_SZ sizeof(u16) +#define HNS_ROCE_DIP_AI_MAX ((u16)(~0U)) +#define HNS_ROCE_DIP_F_OFS (HNS_ROCE_DIP_AI_OFS + HNS_ROCE_DIP_AI_SZ) +#define HNS_ROCE_DIP_F_SZ sizeof(u8) +#define HNS_ROCE_DIP_F_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_TKP_OFS (HNS_ROCE_DIP_F_OFS + HNS_ROCE_DIP_F_SZ) +#define HNS_ROCE_DIP_TKP_SZ sizeof(u8) +#define HNS_ROCE_DIP_TKP_MAX 15 +#define HNS_ROCE_DIP_TMP_OFS (HNS_ROCE_DIP_TKP_OFS + HNS_ROCE_DIP_TKP_SZ) +#define HNS_ROCE_DIP_TMP_SZ sizeof(u16) +#define HNS_ROCE_DIP_TMP_MAX 15 +#define HNS_ROCE_DIP_ALP_OFS (HNS_ROCE_DIP_TMP_OFS + HNS_ROCE_DIP_TMP_SZ) +#define HNS_ROCE_DIP_ALP_SZ sizeof(u16) +#define HNS_ROCE_DIP_ALP_MAX ((u16)(~0U)) +#define HNS_ROCE_DIP_MAX_SPEED_OFS (HNS_ROCE_DIP_ALP_OFS + HNS_ROCE_DIP_ALP_SZ) +#define HNS_ROCE_DIP_MAX_SPEED_SZ sizeof(u32) +#define HNS_ROCE_DIP_MAX_SPEED_MAX ((u32)(~0U)) +#define HNS_ROCE_DIP_G_OFS (HNS_ROCE_DIP_MAX_SPEED_OFS + \ + HNS_ROCE_DIP_MAX_SPEED_SZ) +#define HNS_ROCE_DIP_G_SZ sizeof(u8) +#define HNS_ROCE_DIP_G_MAX 15 +#define HNS_ROCE_DIP_AL_OFS (HNS_ROCE_DIP_G_OFS + HNS_ROCE_DIP_G_SZ) +#define HNS_ROCE_DIP_AL_SZ sizeof(u8) +#define HNS_ROCE_DIP_AL_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_CNP_TIME_OFS (HNS_ROCE_DIP_AL_OFS + HNS_ROCE_DIP_AL_SZ) +#define HNS_ROCE_DIP_CNP_TIME_SZ sizeof(u8) +#define HNS_ROCE_DIP_CNP_TIME_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_ASHIFT_OFS (HNS_ROCE_DIP_CNP_TIME_OFS + \ + HNS_ROCE_DIP_CNP_TIME_SZ) +#define HNS_ROCE_DIP_ASHIFT_SZ sizeof(u8) +#define HNS_ROCE_DIP_ASHIFT_MAX 15 +#define HNS_ROCE_DIP_LIFESPAN_OFS (HNS_ROCE_DIP_ASHIFT_OFS + \ + HNS_ROCE_DIP_ASHIFT_SZ) +#define HNS_ROCE_DIP_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_DIP_LIFESPAN_MAX 1000 + struct hns_roce_sccc_clr { __le32 qpn; __le32 rsv[5]; diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index b55fe6911f9f..18a346c5a6eb 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -633,6 +633,7 @@ static const struct ib_device_ops hns_roce_dev_ops = { .query_pkey = hns_roce_query_pkey, .query_port = hns_roce_query_port, .reg_user_mr = hns_roce_reg_user_mr, + .port_groups = hns_attr_port_groups,
INIT_RDMA_OBJ_SIZE(ib_ah, hns_roce_ah, ibah), INIT_RDMA_OBJ_SIZE(ib_cq, hns_roce_cq, ib_cq), @@ -1106,6 +1107,7 @@ int hns_roce_init(struct hns_roce_dev *hr_dev) if (ret) goto error_failed_register_device;
+ hns_roce_register_sysfs(hr_dev); hns_roce_register_debugfs(hr_dev);
return 0; @@ -1140,6 +1142,7 @@ int hns_roce_init(struct hns_roce_dev *hr_dev)
void hns_roce_exit(struct hns_roce_dev *hr_dev) { + hns_roce_unregister_sysfs(hr_dev); hns_roce_unregister_debugfs(hr_dev); hns_roce_unregister_device(hr_dev);
diff --git a/drivers/infiniband/hw/hns/hns_roce_sysfs.c b/drivers/infiniband/hw/hns/hns_roce_sysfs.c new file mode 100644 index 000000000000..63a50180c4f2 --- /dev/null +++ b/drivers/infiniband/hw/hns/hns_roce_sysfs.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright (c) 2023 Hisilicon Limited. + */ + +#include <rdma/ib_sysfs.h> + +#include "hnae3.h" +#include "hns_roce_device.h" +#include "hns_roce_hw_v2.h" + +static void scc_param_config_work(struct work_struct *work) +{ + struct hns_roce_scc_param *scc_param = container_of(work, + struct hns_roce_scc_param, scc_cfg_dwork.work); + struct hns_roce_dev *hr_dev = scc_param->hr_dev; + + hr_dev->hw->config_scc_param(hr_dev, scc_param->algo_type); +} + +static void get_default_scc_param(struct hns_roce_dev *hr_dev) +{ + int ret; + int i; + + for (i = 0; i < HNS_ROCE_SCC_ALGO_TOTAL; i++) { + hr_dev->scc_param[i].timestamp = jiffies; + ret = hr_dev->hw->query_scc_param(hr_dev, i); + if (ret && ret != -EOPNOTSUPP) + ibdev_warn_ratelimited(&hr_dev->ib_dev, + "failed to get default parameters of scc algo %d, ret = %d.\n", + i, ret); + } +} + +static int alloc_scc_param(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_scc_param *scc_param; + int i; + + scc_param = kvcalloc(HNS_ROCE_SCC_ALGO_TOTAL, sizeof(*scc_param), + GFP_KERNEL); + if (!scc_param) + return -ENOMEM; + + for (i = 0; i < HNS_ROCE_SCC_ALGO_TOTAL; i++) { + scc_param[i].algo_type = i; + scc_param[i].hr_dev = hr_dev; + INIT_DELAYED_WORK(&scc_param[i].scc_cfg_dwork, + scc_param_config_work); + } + + hr_dev->scc_param = scc_param; + + get_default_scc_param(hr_dev); + + return 0; +} + +struct hns_port_cc_attr { + struct ib_port_attribute port_attr; + enum hns_roce_scc_algo algo_type; + u32 offset; + u32 size; + u32 max; + u32 min; +}; + +static int scc_attr_check(struct hns_roce_dev *hr_dev, + struct hns_port_cc_attr *scc_attr, u32 port_num) +{ + if (port_num > hr_dev->caps.num_ports) + return -ENODEV; + + if (WARN_ON(scc_attr->size > sizeof(u32))) + return -EINVAL; + + if (WARN_ON(scc_attr->algo_type >= HNS_ROCE_SCC_ALGO_TOTAL)) + return -EINVAL; + + return 0; +} + +static ssize_t scc_attr_show(struct ib_device *ibdev, u32 port_num, + struct ib_port_attribute *attr, char *buf) +{ + struct hns_port_cc_attr *scc_attr = + container_of(attr, struct hns_port_cc_attr, port_attr); + struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + struct hns_roce_scc_param *scc_param; + __le32 val = 0; + int ret; + + ret = scc_attr_check(hr_dev, scc_attr, port_num); + if (ret) + return ret; + + scc_param = &hr_dev->scc_param[scc_attr->algo_type]; + + memcpy(&val, (void *)scc_param + scc_attr->offset, scc_attr->size); + + return sysfs_emit(buf, "%u\n", le32_to_cpu(val)); +} + +static ssize_t scc_attr_store(struct ib_device *ibdev, u32 port_num, + struct ib_port_attribute *attr, const char *buf, + size_t count) +{ + struct hns_port_cc_attr *scc_attr = + container_of(attr, struct hns_port_cc_attr, port_attr); + struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + struct hns_roce_scc_param *scc_param; + unsigned long lifespan_jiffies; + unsigned long exp_time; + __le32 attr_val; + u32 val; + int ret; + + ret = scc_attr_check(hr_dev, scc_attr, port_num); + if (ret) + return ret; + + if (kstrtou32(buf, 0, &val)) + return -EINVAL; + + if (val > scc_attr->max || val < scc_attr->min) + return -EINVAL; + + attr_val = cpu_to_le32(val); + scc_param = &hr_dev->scc_param[scc_attr->algo_type]; + memcpy((void *)scc_param + scc_attr->offset, &attr_val, + scc_attr->size); + + /* lifespan is only used for driver */ + if (scc_attr->offset >= offsetof(typeof(*scc_param), lifespan)) + return count; + + lifespan_jiffies = msecs_to_jiffies(scc_param->lifespan); + exp_time = scc_param->timestamp + lifespan_jiffies; + + if (time_is_before_eq_jiffies(exp_time)) { + scc_param->timestamp = jiffies; + queue_delayed_work(hr_dev->irq_workq, &scc_param->scc_cfg_dwork, + lifespan_jiffies); + } + + return count; +} + +static umode_t scc_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int i) +{ + struct ib_port_attribute *port_attr = + container_of(attr, struct ib_port_attribute, attr); + struct hns_port_cc_attr *scc_attr = + container_of(port_attr, struct hns_port_cc_attr, port_attr); + u32 port_num; + struct ib_device *ibdev = ib_port_sysfs_get_ibdev_kobj(kobj, &port_num); + struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + + if (hr_dev->is_vf || + !(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL)) + return 0; + + if (!(hr_dev->caps.cong_type & (1 << scc_attr->algo_type))) + return 0; + + return 0644; +} + +#define __HNS_SCC_ATTR(_name, _type, _offset, _size, _min, _max) { \ + .port_attr = __ATTR(_name, 0644, scc_attr_show, scc_attr_store), \ + .algo_type = _type, \ + .offset = _offset, \ + .size = _size, \ + .min = _min, \ + .max = _max, \ +} + +#define HNS_PORT_DCQCN_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_dcqcn_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_DCQCN, \ + HNS_ROCE_DCQCN_##NAME##_OFS, \ + HNS_ROCE_DCQCN_##NAME##_SZ, \ + 0, HNS_ROCE_DCQCN_##NAME##_MAX) + +HNS_PORT_DCQCN_CC_ATTR_RW(ai, AI); +HNS_PORT_DCQCN_CC_ATTR_RW(f, F); +HNS_PORT_DCQCN_CC_ATTR_RW(tkp, TKP); +HNS_PORT_DCQCN_CC_ATTR_RW(tmp, TMP); +HNS_PORT_DCQCN_CC_ATTR_RW(alp, ALP); +HNS_PORT_DCQCN_CC_ATTR_RW(max_speed, MAX_SPEED); +HNS_PORT_DCQCN_CC_ATTR_RW(g, G); +HNS_PORT_DCQCN_CC_ATTR_RW(al, AL); +HNS_PORT_DCQCN_CC_ATTR_RW(cnp_time, CNP_TIME); +HNS_PORT_DCQCN_CC_ATTR_RW(ashift, ASHIFT); +HNS_PORT_DCQCN_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *dcqcn_param_attrs[] = { + &hns_roce_port_attr_dcqcn_ai.port_attr.attr, + &hns_roce_port_attr_dcqcn_f.port_attr.attr, + &hns_roce_port_attr_dcqcn_tkp.port_attr.attr, + &hns_roce_port_attr_dcqcn_tmp.port_attr.attr, + &hns_roce_port_attr_dcqcn_alp.port_attr.attr, + &hns_roce_port_attr_dcqcn_max_speed.port_attr.attr, + &hns_roce_port_attr_dcqcn_g.port_attr.attr, + &hns_roce_port_attr_dcqcn_al.port_attr.attr, + &hns_roce_port_attr_dcqcn_cnp_time.port_attr.attr, + &hns_roce_port_attr_dcqcn_ashift.port_attr.attr, + &hns_roce_port_attr_dcqcn_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group dcqcn_cc_param_group = { + .name = "dcqcn_cc_param", + .attrs = dcqcn_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_LDCP_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_ldcp_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_LDCP, \ + HNS_ROCE_LDCP_##NAME##_OFS, \ + HNS_ROCE_LDCP_##NAME##_SZ, \ + 0, HNS_ROCE_LDCP_##NAME##_MAX) + +HNS_PORT_LDCP_CC_ATTR_RW(cwd0, CWD0); +HNS_PORT_LDCP_CC_ATTR_RW(alpha, ALPHA); +HNS_PORT_LDCP_CC_ATTR_RW(gamma, GAMMA); +HNS_PORT_LDCP_CC_ATTR_RW(beta, BETA); +HNS_PORT_LDCP_CC_ATTR_RW(eta, ETA); +HNS_PORT_LDCP_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *ldcp_param_attrs[] = { + &hns_roce_port_attr_ldcp_cwd0.port_attr.attr, + &hns_roce_port_attr_ldcp_alpha.port_attr.attr, + &hns_roce_port_attr_ldcp_gamma.port_attr.attr, + &hns_roce_port_attr_ldcp_beta.port_attr.attr, + &hns_roce_port_attr_ldcp_eta.port_attr.attr, + &hns_roce_port_attr_ldcp_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group ldcp_cc_param_group = { + .name = "ldcp_cc_param", + .attrs = ldcp_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_HC3_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_hc3_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_HC3, \ + HNS_ROCE_HC3_##NAME##_OFS, \ + HNS_ROCE_HC3_##NAME##_SZ, \ + 0, HNS_ROCE_HC3_##NAME##_MAX) + +HNS_PORT_HC3_CC_ATTR_RW(initial_window, INITIAL_WINDOW); +HNS_PORT_HC3_CC_ATTR_RW(bandwidth, BANDWIDTH); +HNS_PORT_HC3_CC_ATTR_RW(qlen_shift, QLEN_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(port_usage_shift, PORT_USAGE_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(over_period, OVER_PERIOD); +HNS_PORT_HC3_CC_ATTR_RW(max_stage, MAX_STAGE); +HNS_PORT_HC3_CC_ATTR_RW(gamma_shift, GAMMA_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *hc3_param_attrs[] = { + &hns_roce_port_attr_hc3_initial_window.port_attr.attr, + &hns_roce_port_attr_hc3_bandwidth.port_attr.attr, + &hns_roce_port_attr_hc3_qlen_shift.port_attr.attr, + &hns_roce_port_attr_hc3_port_usage_shift.port_attr.attr, + &hns_roce_port_attr_hc3_over_period.port_attr.attr, + &hns_roce_port_attr_hc3_max_stage.port_attr.attr, + &hns_roce_port_attr_hc3_gamma_shift.port_attr.attr, + &hns_roce_port_attr_hc3_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group hc3_cc_param_group = { + .name = "hc3_cc_param", + .attrs = hc3_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_DIP_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_dip_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_DIP, \ + HNS_ROCE_DIP_##NAME##_OFS, \ + HNS_ROCE_DIP_##NAME##_SZ, \ + 0, HNS_ROCE_DIP_##NAME##_MAX) + +HNS_PORT_DIP_CC_ATTR_RW(ai, AI); +HNS_PORT_DIP_CC_ATTR_RW(f, F); +HNS_PORT_DIP_CC_ATTR_RW(tkp, TKP); +HNS_PORT_DIP_CC_ATTR_RW(tmp, TMP); +HNS_PORT_DIP_CC_ATTR_RW(alp, ALP); +HNS_PORT_DIP_CC_ATTR_RW(max_speed, MAX_SPEED); +HNS_PORT_DIP_CC_ATTR_RW(g, G); +HNS_PORT_DIP_CC_ATTR_RW(al, AL); +HNS_PORT_DIP_CC_ATTR_RW(cnp_time, CNP_TIME); +HNS_PORT_DIP_CC_ATTR_RW(ashift, ASHIFT); +HNS_PORT_DIP_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *dip_param_attrs[] = { + &hns_roce_port_attr_dip_ai.port_attr.attr, + &hns_roce_port_attr_dip_f.port_attr.attr, + &hns_roce_port_attr_dip_tkp.port_attr.attr, + &hns_roce_port_attr_dip_tmp.port_attr.attr, + &hns_roce_port_attr_dip_alp.port_attr.attr, + &hns_roce_port_attr_dip_max_speed.port_attr.attr, + &hns_roce_port_attr_dip_g.port_attr.attr, + &hns_roce_port_attr_dip_al.port_attr.attr, + &hns_roce_port_attr_dip_cnp_time.port_attr.attr, + &hns_roce_port_attr_dip_ashift.port_attr.attr, + &hns_roce_port_attr_dip_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group dip_cc_param_group = { + .name = "dip_cc_param", + .attrs = dip_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +const struct attribute_group *hns_attr_port_groups[] = { + &dcqcn_cc_param_group, + &ldcp_cc_param_group, + &hc3_cc_param_group, + &dip_cc_param_group, + NULL, +}; + +void hns_roce_register_sysfs(struct hns_roce_dev *hr_dev) +{ + int ret; + + ret = alloc_scc_param(hr_dev); + if (ret) + dev_err(hr_dev->dev, "alloc scc param failed, ret = %d!\n", + ret); +} + +void hns_roce_unregister_sysfs(struct hns_roce_dev *hr_dev) +{ + if (hr_dev->scc_param) + kvfree(hr_dev->scc_param); +}
From: Lang Cheng chenglang@huawei.com
driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5Z2DS
----------------------------------------------------------------------
Driver can notify ulp with IB event when net link down/up.
Signed-off-by: Lang Cheng chenglang@huawei.com Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Juan Zhou zhoujuan51@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_device.h | 12 ++++++ drivers/infiniband/hw/hns/hns_roce_main.c | 43 +++++++++++++++------ 2 files changed, 44 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index d6c33bdf56d3..a443bf17e018 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -646,6 +646,7 @@ struct hns_roce_ib_iboe { struct net_device *netdevs[HNS_ROCE_MAX_PORTS]; struct notifier_block nb; u8 phy_port[HNS_ROCE_MAX_PORTS]; + enum ib_port_state port_state[HNS_ROCE_MAX_PORTS]; };
struct hns_roce_ceqe { @@ -1177,6 +1178,17 @@ static inline u8 get_tclass(const struct ib_global_route *grh) grh->traffic_class >> DSCP_SHIFT : grh->traffic_class; }
+static inline u8 to_rdma_port_num(u8 phy_port_num) +{ + return phy_port_num + 1; +} + +static inline enum ib_port_state get_port_state(struct net_device *net_dev) +{ + return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ? + IB_PORT_ACTIVE : IB_PORT_DOWN; +} + extern const struct attribute_group *hns_attr_port_groups[];
void hns_roce_init_uar_table(struct hns_roce_dev *dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 18a346c5a6eb..ff802fb6331e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -89,10 +89,13 @@ static int hns_roce_del_gid(const struct ib_gid_attr *attr, void **context) }
static int handle_en_event(struct hns_roce_dev *hr_dev, u32 port, - unsigned long event) + unsigned long dev_event) { struct device *dev = hr_dev->dev; + enum ib_port_state port_state; struct net_device *netdev; + struct ib_event event; + unsigned long flags; int ret = 0;
netdev = hr_dev->iboe.netdevs[port]; @@ -101,20 +104,38 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u32 port, return -ENODEV; }
- switch (event) { - case NETDEV_UP: - case NETDEV_CHANGE: + switch (dev_event) { case NETDEV_REGISTER: case NETDEV_CHANGEADDR: ret = hns_roce_set_mac(hr_dev, port, netdev->dev_addr); break; + case NETDEV_UP: + case NETDEV_CHANGE: + ret = hns_roce_set_mac(hr_dev, port, netdev->dev_addr); + if (ret) + return ret; + fallthrough; case NETDEV_DOWN: - /* - * In v1 engine, only support all ports closed together. - */ + port_state = get_port_state(netdev); + + spin_lock_irqsave(&hr_dev->iboe.lock, flags); + if (hr_dev->iboe.port_state[port] == port_state) { + spin_unlock_irqrestore(&hr_dev->iboe.lock, flags); + return NOTIFY_DONE; + } + hr_dev->iboe.port_state[port] = port_state; + spin_unlock_irqrestore(&hr_dev->iboe.lock, flags); + + event.device = &hr_dev->ib_dev; + event.event = (port_state == IB_PORT_ACTIVE) ? + IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR; + event.element.port_num = to_rdma_port_num(port); + ib_dispatch_event(&event); + break; + case NETDEV_UNREGISTER: break; default: - dev_dbg(dev, "NETDEV event = 0x%x!\n", (u32)(event)); + dev_dbg(dev, "NETDEV event = 0x%x!\n", (u32)(dev_event)); break; }
@@ -151,6 +172,8 @@ static int hns_roce_setup_mtu_mac(struct hns_roce_dev *hr_dev) u8 i;
for (i = 0; i < hr_dev->caps.num_ports; i++) { + hr_dev->iboe.port_state[i] = IB_PORT_DOWN; + ret = hns_roce_set_mac(hr_dev, i, hr_dev->iboe.netdevs[i]->dev_addr); if (ret) @@ -248,9 +271,7 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u32 port_num,
mtu = iboe_get_mtu(net_dev->mtu); props->active_mtu = mtu ? min(props->max_mtu, mtu) : IB_MTU_256; - props->state = netif_running(net_dev) && netif_carrier_ok(net_dev) ? - IB_PORT_ACTIVE : - IB_PORT_DOWN; + props->state = get_port_state(net_dev); props->phys_state = props->state == IB_PORT_ACTIVE ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED;
From: Lang Cheng chenglang@huawei.com
driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5Z2DS
----------------------------------------------------------------------
When the netdev port status changes, the roce driver sends a port down event by parsing the netdev event dispatched by IB_CORE, which takes about a few hundred milliseconds. But,it is not fast enough for ULP sometimes.
The HNS NIC driver can directly notify the ROCE driver send port event via callback function, this takes only a few milliseconds. This patch implements this callback function.
Signed-off-by: Lang Cheng chenglang@huawei.com Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Juan Zhou zhoujuan51@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 34 ++++++++++++++++++++++ 1 file changed, 34 insertions(+)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 905040e9ccbe..d99a9769cdbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -7110,9 +7110,43 @@ static int hns_roce_hw_v2_reset_notify(struct hnae3_handle *handle, return ret; }
+static void hns_roce_hw_v2_link_status_change(struct hnae3_handle *handle, + bool linkup) +{ + struct net_device *netdev = handle->rinfo.netdev; + struct hns_roce_dev *hr_dev = handle->priv; + struct ib_event event; + unsigned long flags; + u8 phy_port; + + if (linkup || !hr_dev) + return; + + for (phy_port = 0; phy_port < hr_dev->caps.num_ports; phy_port++) + if (netdev == hr_dev->iboe.netdevs[phy_port]) + break; + + if (phy_port == hr_dev->caps.num_ports) + return; + + spin_lock_irqsave(&hr_dev->iboe.lock, flags); + if (hr_dev->iboe.port_state[phy_port] == IB_PORT_DOWN) { + spin_unlock_irqrestore(&hr_dev->iboe.lock, flags); + return; + } + hr_dev->iboe.port_state[phy_port] = IB_PORT_DOWN; + spin_unlock_irqrestore(&hr_dev->iboe.lock, flags); + + event.device = &hr_dev->ib_dev; + event.element.port_num = to_rdma_port_num(phy_port); + event.event = IB_EVENT_PORT_ERR; + ib_dispatch_event(&event); +} + static const struct hnae3_client_ops hns_roce_hw_v2_ops = { .init_instance = hns_roce_hw_v2_init_instance, .uninit_instance = hns_roce_hw_v2_uninit_instance, + .link_status_change = hns_roce_hw_v2_link_status_change, .reset_notify = hns_roce_hw_v2_reset_notify, };
-
Chengchang Tang