diff options
Diffstat (limited to 'drivers/infiniband/core/nldev.c')
| -rw-r--r-- | drivers/infiniband/core/nldev.c | 800 |
1 files changed, 718 insertions, 82 deletions
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 69188cbbd99b..783e465e7c41 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -42,84 +42,105 @@ #include "cma_priv.h" #include "restrack.h" +/* + * Sort array elements by the netlink attribute name + */ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = { - [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, - .len = IB_DEVICE_NAME_MAX - 1}, - [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING, - .len = IB_FW_VERSION_NAME_MAX - 1}, - [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 }, - [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 }, - [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 }, - [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_RES_SUMMARY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME] = { .type = NLA_NUL_STRING, - .len = 16 }, - [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR] = { .type = NLA_U64 }, - [RDMA_NLDEV_ATTR_RES_QP] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_QP_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_LQPN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_RQPN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_RQ_PSN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_SQ_PSN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_RES_TYPE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_RES_STATE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_RES_PID] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_KERN_NAME] = { .type = NLA_NUL_STRING, - .len = TASK_COMM_LEN }, + [RDMA_NLDEV_ATTR_CHARDEV] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_CHARDEV_ABI] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_CHARDEV_NAME] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_CHARDEV_TYPE] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE }, + [RDMA_NLDEV_ATTR_DEV_DIM] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = IB_DEVICE_NAME_MAX }, + [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_DEV_PROTOCOL] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_DRIVER] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_DRIVER_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_DRIVER_STRING] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_DRIVER_S32] = { .type = NLA_S32 }, + [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 }, + [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_LINK_TYPE] = { .type = NLA_NUL_STRING, + .len = IFNAMSIZ }, + [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_NDEV_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_NDEV_NAME] = { .type = NLA_NUL_STRING, + .len = IFNAMSIZ }, + [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_CM_ID] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_CM_IDN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_PS] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = { - .len = sizeof(struct __kernel_sockaddr_storage) }, - [RDMA_NLDEV_ATTR_RES_DST_ADDR] = { - .len = sizeof(struct __kernel_sockaddr_storage) }, [RDMA_NLDEV_ATTR_RES_CQ] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CQE] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_USECNT] = { .type = NLA_U64 }, - [RDMA_NLDEV_ATTR_RES_POLL_CTX] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_RES_MR] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_RKEY] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_LKEY] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_CQN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_CTXN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_DST_ADDR] = { + .len = sizeof(struct __kernel_sockaddr_storage) }, [RDMA_NLDEV_ATTR_RES_IOVA] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_RES_KERN_NAME] = { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_RES_LKEY] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_LQPN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_MR] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_MRLEN] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_RES_MRN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_PD] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_PD_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_NDEV_INDEX] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_NDEV_NAME] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ }, - [RDMA_NLDEV_ATTR_DRIVER] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_DRIVER_ENTRY] = { .type = NLA_NESTED }, - [RDMA_NLDEV_ATTR_DRIVER_STRING] = { .type = NLA_NUL_STRING, - .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN }, - [RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_DRIVER_S32] = { .type = NLA_S32 }, - [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 }, - [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_RES_PDN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_CQN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_MRN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_CM_IDN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_RES_CTXN] = { .type = NLA_U32 }, - [RDMA_NLDEV_ATTR_LINK_TYPE] = { .type = NLA_NUL_STRING, - .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN }, - [RDMA_NLDEV_SYS_ATTR_NETNS_MODE] = { .type = NLA_U8 }, - [RDMA_NLDEV_ATTR_DEV_PROTOCOL] = { .type = NLA_NUL_STRING, - .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN }, + [RDMA_NLDEV_ATTR_RES_PD_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_PID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_POLL_CTX] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_RES_PS] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_QP] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_QP_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_RKEY] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_RQPN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_RQ_PSN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_SQ_PSN] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = { + .len = sizeof(struct __kernel_sockaddr_storage) }, + [RDMA_NLDEV_ATTR_RES_STATE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_RES_SUMMARY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]= { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME]= { .type = NLA_NUL_STRING, + .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, + [RDMA_NLDEV_ATTR_RES_TYPE] = { .type = NLA_U8 }, + [RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]= { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_RES_USECNT] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_STAT_MODE] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_STAT_RES] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_STAT_COUNTER] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_STAT_COUNTER_ID] = { .type = NLA_U32 }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTERS] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY] = { .type = NLA_NESTED }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] = { .type = NLA_NUL_STRING }, + [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 }, + [RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID] = { .type = NLA_U32 }, [RDMA_NLDEV_NET_NS_FD] = { .type = NLA_U32 }, + [RDMA_NLDEV_SYS_ATTR_NETNS_MODE] = { .type = NLA_U8 }, }; static int put_driver_name_print_type(struct sk_buff *msg, const char *name, @@ -232,6 +253,8 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type)) return -EMSGSIZE; + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, device->use_cq_dim)) + return -EMSGSIZE; /* * Link type is determined on first port and mlx4 device @@ -532,6 +555,9 @@ static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin, nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_POLL_CTX, cq->poll_ctx)) goto err; + if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, (cq->dim != NULL))) + goto err; + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQN, res->id)) goto err; if (!rdma_is_kernel_res(res) && @@ -623,6 +649,152 @@ static int fill_res_pd_entry(struct sk_buff *msg, bool has_cap_net_admin, err: return -EMSGSIZE; } +static int fill_stat_counter_mode(struct sk_buff *msg, + struct rdma_counter *counter) +{ + struct rdma_counter_mode *m = &counter->mode; + + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, m->mode)) + return -EMSGSIZE; + + if (m->mode == RDMA_COUNTER_MODE_AUTO) + if ((m->mask & RDMA_COUNTER_MASK_QP_TYPE) && + nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, m->param.qp_type)) + return -EMSGSIZE; + + return 0; +} + +static int fill_stat_counter_qp_entry(struct sk_buff *msg, u32 qpn) +{ + struct nlattr *entry_attr; + + entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP_ENTRY); + if (!entry_attr) + return -EMSGSIZE; + + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) + goto err; + + nla_nest_end(msg, entry_attr); + return 0; + +err: + nla_nest_cancel(msg, entry_attr); + return -EMSGSIZE; +} + +static int fill_stat_counter_qps(struct sk_buff *msg, + struct rdma_counter *counter) +{ + struct rdma_restrack_entry *res; + struct rdma_restrack_root *rt; + struct nlattr *table_attr; + struct ib_qp *qp = NULL; + unsigned long id = 0; + int ret = 0; + + table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP); + + rt = &counter->device->res[RDMA_RESTRACK_QP]; + xa_lock(&rt->xa); + xa_for_each(&rt->xa, id, res) { + if (!rdma_is_visible_in_pid_ns(res)) + continue; + + qp = container_of(res, struct ib_qp, res); + if (qp->qp_type == IB_QPT_RAW_PACKET && !capable(CAP_NET_RAW)) + continue; + + if (!qp->counter || (qp->counter->id != counter->id)) + continue; + + ret = fill_stat_counter_qp_entry(msg, qp->qp_num); + if (ret) + goto err; + } + + xa_unlock(&rt->xa); + nla_nest_end(msg, table_attr); + return 0; + +err: + xa_unlock(&rt->xa); + nla_nest_cancel(msg, table_attr); + return ret; +} + +static int fill_stat_hwcounter_entry(struct sk_buff *msg, + const char *name, u64 value) +{ + struct nlattr *entry_attr; + + entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY); + if (!entry_attr) + return -EMSGSIZE; + + if (nla_put_string(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME, + name)) + goto err; + if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE, + value, RDMA_NLDEV_ATTR_PAD)) + goto err; + + nla_nest_end(msg, entry_attr); + return 0; + +err: + nla_nest_cancel(msg, entry_attr); + return -EMSGSIZE; +} + +static int fill_stat_counter_hwcounters(struct sk_buff *msg, + struct rdma_counter *counter) +{ + struct rdma_hw_stats *st = counter->stats; + struct nlattr *table_attr; + int i; + + table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); + if (!table_attr) + return -EMSGSIZE; + + for (i = 0; i < st->num_counters; i++) + if (fill_stat_hwcounter_entry(msg, st->names[i], st->value[i])) + goto err; + + nla_nest_end(msg, table_attr); + return 0; + +err: + nla_nest_cancel(msg, table_attr); + return -EMSGSIZE; +} + +static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin, + struct rdma_restrack_entry *res, + uint32_t port) +{ + struct rdma_counter *counter = + container_of(res, struct rdma_counter, res); + + if (port && port != counter->port) + return 0; + + /* Dump it even query failed */ + rdma_counter_query_stats(counter); + + if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, counter->port) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, counter->id) || + fill_res_name_pid(msg, &counter->res) || + fill_stat_counter_mode(msg, counter) || + fill_stat_counter_qps(msg, counter) || + fill_stat_counter_hwcounters(msg, counter)) + return -EMSGSIZE; + + return 0; +} + static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -704,6 +876,14 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, goto put_done; } + if (tb[RDMA_NLDEV_ATTR_DEV_DIM]) { + u8 use_dim; + + use_dim = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_DIM]); + err = ib_device_set_dim(device, use_dim); + goto done; + } + done: ib_device_put(device); put_done: @@ -990,19 +1170,15 @@ static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = { .entry = RDMA_NLDEV_ATTR_RES_PD_ENTRY, .id = RDMA_NLDEV_ATTR_RES_PDN, }, + [RDMA_RESTRACK_COUNTER] = { + .fill_res_func = fill_res_counter_entry, + .nldev_cmd = RDMA_NLDEV_CMD_STAT_GET, + .nldev_attr = RDMA_NLDEV_ATTR_STAT_COUNTER, + .entry = RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY, + .id = RDMA_NLDEV_ATTR_STAT_COUNTER_ID, + }, }; -static bool is_visible_in_pid_ns(struct rdma_restrack_entry *res) -{ - /* - * 1. Kern resources should be visible in init name space only - * 2. Present only resources visible in the current namespace - */ - if (rdma_is_kernel_res(res)) - return task_active_pid_ns(current) == &init_pid_ns; - return task_active_pid_ns(current) == task_active_pid_ns(res->task); -} - static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, enum rdma_restrack_type res_type) @@ -1047,7 +1223,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, goto err; } - if (!is_visible_in_pid_ns(res)) { + if (!rdma_is_visible_in_pid_ns(res)) { ret = -ENOENT; goto err_get; } @@ -1159,7 +1335,7 @@ static int res_get_common_dumpit(struct sk_buff *skb, * objects. */ xa_for_each(&rt->xa, id, res) { - if (!is_visible_in_pid_ns(res)) + if (!rdma_is_visible_in_pid_ns(res)) continue; if (idx < start || !rdma_restrack_get(res)) @@ -1237,6 +1413,7 @@ RES_GET_FUNCS(cm_id, RDMA_RESTRACK_CM_ID); RES_GET_FUNCS(cq, RDMA_RESTRACK_CQ); RES_GET_FUNCS(pd, RDMA_RESTRACK_PD); RES_GET_FUNCS(mr, RDMA_RESTRACK_MR); +RES_GET_FUNCS(counter, RDMA_RESTRACK_COUNTER); static LIST_HEAD(link_ops); static DECLARE_RWSEM(link_ops_rwsem); @@ -1299,7 +1476,7 @@ static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, nla_strlcpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME], sizeof(ndev_name)); - ndev = dev_get_by_name(&init_net, ndev_name); + ndev = dev_get_by_name(sock_net(skb->sk), ndev_name); if (!ndev) return -ENODEV; @@ -1347,6 +1524,90 @@ static int nldev_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } +static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + char client_name[RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE]; + struct ib_client_nl_info data = {}; + struct ib_device *ibdev = NULL; + struct sk_buff *msg; + u32 index; + int err; + + err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, + extack); + if (err || !tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE]) + return -EINVAL; + + nla_strlcpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE], + sizeof(client_name)); + + if (tb[RDMA_NLDEV_ATTR_DEV_INDEX]) { + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + ibdev = ib_device_get_by_index(sock_net(skb->sk), index); + if (!ibdev) + return -EINVAL; + + if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { + data.port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(ibdev, data.port)) { + err = -EINVAL; + goto out_put; + } + } else { + data.port = -1; + } + } else if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { + return -EINVAL; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + err = -ENOMEM; + goto out_put; + } + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_GET_CHARDEV), + 0, 0); + + data.nl_msg = msg; + err = ib_get_client_nl_info(ibdev, client_name, &data); + if (err) + goto out_nlmsg; + + err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV, + huge_encode_dev(data.cdev->devt), + RDMA_NLDEV_ATTR_PAD); + if (err) + goto out_data; + err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV_ABI, data.abi, + RDMA_NLDEV_ATTR_PAD); + if (err) + goto out_data; + if (nla_put_string(msg, RDMA_NLDEV_ATTR_CHARDEV_NAME, + dev_name(data.cdev))) { + err = -EMSGSIZE; + goto out_data; + } + + nlmsg_end(msg, nlh); + put_device(data.cdev); + if (ibdev) + ib_device_put(ibdev); + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +out_data: + put_device(data.cdev); +out_nlmsg: + nlmsg_free(msg); +out_put: + if (ibdev) + ib_device_put(ibdev); + return err; +} + static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -1399,11 +1660,375 @@ static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } +static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + u32 index, port, mode, mask = 0, qpn, cntn = 0; + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + struct ib_device *device; + struct sk_buff *msg; + int ret; + + ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + /* Currently only counter for QP is supported */ + if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES] || + !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || + !tb[RDMA_NLDEV_ATTR_PORT_INDEX] || !tb[RDMA_NLDEV_ATTR_STAT_MODE]) + return -EINVAL; + + if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = ib_device_get_by_index(sock_net(skb->sk), index); + if (!device) + return -EINVAL; + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) { + ret = -EINVAL; + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_STAT_SET), + 0, 0); + + mode = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]); + if (mode == RDMA_COUNTER_MODE_AUTO) { + if (tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]) + mask = nla_get_u32( + tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]); + + ret = rdma_counter_set_auto_mode(device, port, + mask ? true : false, mask); + if (ret) + goto err_msg; + } else { + qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); + if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) { + cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); + ret = rdma_counter_bind_qpn(device, port, qpn, cntn); + } else { + ret = rdma_counter_bind_qpn_alloc(device, port, + qpn, &cntn); + } + if (ret) + goto err_msg; + + if (fill_nldev_handle(msg, device) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) { + ret = -EMSGSIZE; + goto err_fill; + } + } + + nlmsg_end(msg, nlh); + ib_device_put(device); + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_fill: + rdma_counter_unbind_qpn(device, port, qpn, cntn); +err_msg: + nlmsg_free(msg); +err: + ib_device_put(device); + return ret; +} + +static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + struct ib_device *device; + struct sk_buff *msg; + u32 index, port, qpn, cntn; + int ret; + + ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES] || + !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX] || + !tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID] || + !tb[RDMA_NLDEV_ATTR_RES_LQPN]) + return -EINVAL; + + if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = ib_device_get_by_index(sock_net(skb->sk), index); + if (!device) + return -EINVAL; + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) { + ret = -EINVAL; + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_STAT_SET), + 0, 0); + + cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); + qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); + ret = rdma_counter_unbind_qpn(device, port, qpn, cntn); + if (ret) + goto err_unbind; + + if (fill_nldev_handle(msg, device) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) { + ret = -EMSGSIZE; + goto err_fill; + } + + nlmsg_end(msg, nlh); + ib_device_put(device); + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_fill: + rdma_counter_bind_qpn(device, port, qpn, cntn); +err_unbind: + nlmsg_free(msg); +err: + ib_device_put(device); + return ret; +} + +static int stat_get_doit_default_counter(struct sk_buff *skb, + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, + struct nlattr *tb[]) +{ + struct rdma_hw_stats *stats; + struct nlattr *table_attr; + struct ib_device *device; + int ret, num_cnts, i; + struct sk_buff *msg; + u32 index, port; + u64 v; + + if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = ib_device_get_by_index(sock_net(skb->sk), index); + if (!device) + return -EINVAL; + + if (!device->ops.alloc_hw_stats || !device->ops.get_hw_stats) { + ret = -EINVAL; + goto err; + } + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) { + ret = -EINVAL; + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_STAT_GET), + 0, 0); + + if (fill_nldev_handle(msg, device) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) { + ret = -EMSGSIZE; + goto err_msg; + } + + stats = device->port_data ? device->port_data[port].hw_stats : NULL; + if (stats == NULL) { + ret = -EINVAL; + goto err_msg; + } + mutex_lock(&stats->lock); + + num_cnts = device->ops.get_hw_stats(device, stats, port, 0); + if (num_cnts < 0) { + ret = -EINVAL; + goto err_stats; + } + + table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); + if (!table_attr) { + ret = -EMSGSIZE; + goto err_stats; + } + for (i = 0; i < num_cnts; i++) { + v = stats->value[i] + + rdma_counter_get_hwstat_value(device, port, i); + if (fill_stat_hwcounter_entry(msg, stats->names[i], v)) { + ret = -EMSGSIZE; + goto err_table; + } + } + nla_nest_end(msg, table_attr); + + mutex_unlock(&stats->lock); + nlmsg_end(msg, nlh); + ib_device_put(device); + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_table: + nla_nest_cancel(msg, table_attr); +err_stats: + mutex_unlock(&stats->lock); +err_msg: + nlmsg_free(msg); +err: + ib_device_put(device); + return ret; +} + +static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, struct nlattr *tb[]) + +{ + static enum rdma_nl_counter_mode mode; + static enum rdma_nl_counter_mask mask; + struct ib_device *device; + struct sk_buff *msg; + u32 index, port; + int ret; + + if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) + return nldev_res_get_counter_doit(skb, nlh, extack); + + if (!tb[RDMA_NLDEV_ATTR_STAT_MODE] || + !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) + return -EINVAL; + + index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); + device = ib_device_get_by_index(sock_net(skb->sk), index); + if (!device) + return -EINVAL; + + port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); + if (!rdma_is_port_valid(device, port)) { + ret = -EINVAL; + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + + nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, + RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, + RDMA_NLDEV_CMD_STAT_GET), + 0, 0); + + ret = rdma_counter_get_mode(device, port, &mode, &mask); + if (ret) + goto err_msg; + + if (fill_nldev_handle(msg, device) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) + goto err_msg; + + if ((mode == RDMA_COUNTER_MODE_AUTO) && + nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) + goto err_msg; + + nlmsg_end(msg, nlh); + ib_device_put(device); + return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_msg: + nlmsg_free(msg); +err: + ib_device_put(device); + return ret; +} + +static int nldev_stat_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + int ret; + + ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, extack); + if (ret) + return -EINVAL; + + if (!tb[RDMA_NLDEV_ATTR_STAT_RES]) + return stat_get_doit_default_counter(skb, nlh, extack, tb); + + switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) { + case RDMA_NLDEV_ATTR_RES_QP: + ret = stat_get_doit_qp(skb, nlh, extack, tb); + break; + + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int nldev_stat_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; + int ret; + + ret = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, + nldev_policy, NULL); + if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES]) + return -EINVAL; + + switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) { + case RDMA_NLDEV_ATTR_RES_QP: + ret = nldev_res_get_counter_dumpit(skb, cb); + break; + + default: + ret = -EINVAL; + break; + } + + return ret; +} + static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { [RDMA_NLDEV_CMD_GET] = { .doit = nldev_get_doit, .dump = nldev_get_dumpit, }, + [RDMA_NLDEV_CMD_GET_CHARDEV] = { + .doit = nldev_get_chardev, + }, [RDMA_NLDEV_CMD_SET] = { .doit = nldev_set_doit, .flags = RDMA_NL_ADMIN_PERM, @@ -1449,6 +2074,17 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { }, [RDMA_NLDEV_CMD_SYS_SET] = { .doit = nldev_set_sys_set_doit, + }, + [RDMA_NLDEV_CMD_STAT_SET] = { + .doit = nldev_stat_set_doit, + .flags = RDMA_NL_ADMIN_PERM, + }, + [RDMA_NLDEV_CMD_STAT_GET] = { + .doit = nldev_stat_get_doit, + .dump = nldev_stat_get_dumpit, + }, + [RDMA_NLDEV_CMD_STAT_DEL] = { + .doit = nldev_stat_del_doit, .flags = RDMA_NL_ADMIN_PERM, }, }; |