diff options
74 files changed, 6725 insertions, 178 deletions
diff --git a/Documentation/scsi/scsi_transport_srp/Makefile b/Documentation/scsi/scsi_transport_srp/Makefile new file mode 100644 index 00000000000..5f6b567e955 --- /dev/null +++ b/Documentation/scsi/scsi_transport_srp/Makefile @@ -0,0 +1,7 @@ +all: rport_state_diagram.svg rport_state_diagram.png + +rport_state_diagram.svg: rport_state_diagram.dot + dot -Tsvg -o $@ $< + +rport_state_diagram.png: rport_state_diagram.dot + dot -Tpng -o $@ $< diff --git a/Documentation/scsi/scsi_transport_srp/rport_state_diagram.dot b/Documentation/scsi/scsi_transport_srp/rport_state_diagram.dot new file mode 100644 index 00000000000..75d610d6411 --- /dev/null +++ b/Documentation/scsi/scsi_transport_srp/rport_state_diagram.dot @@ -0,0 +1,26 @@ +digraph srp_initiator { + node [shape = doublecircle]; running lost; + node [shape = circle]; + + { + rank = min; + running_rta [ label = "running;\nreconnect\ntimer\nactive" ]; + }; + running [ label = "running;\nreconnect\ntimer\nstopped" ]; + blocked; + failfast [ label = "fail I/O\nfast" ]; + lost; + + running -> running_rta [ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nsrp_start_tl_fail_timers()" ]; + running_rta -> running [ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nreconnecting succeeded" ]; + running -> blocked [ label = "fast_io_fail_tmo >= 0 or\ndev_loss_tmo >= 0;\nsrp_start_tl_fail_timers()" ]; + running -> failfast [ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nreconnecting failed\n" ]; + blocked -> failfast [ label = "fast_io_fail_tmo\nexpired or\nreconnecting\nfailed" ]; + blocked -> lost [ label = "dev_loss_tmo\nexpired or\nsrp_stop_rport_timers()" ]; + failfast -> lost [ label = "dev_loss_tmo\nexpired or\nsrp_stop_rport_timers()" ]; + blocked -> running [ label = "reconnecting\nsucceeded" ]; + failfast -> failfast [ label = "reconnecting\nfailed" ]; + failfast -> running [ label = "reconnecting\nsucceeded" ]; + running -> lost [ label = "srp_stop_rport_timers()" ]; + running_rta -> lost [ label = "srp_stop_rport_timers()" ]; +} diff --git a/MAINTAINERS b/MAINTAINERS index 31a04621327..fc5908fcdc1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2158,6 +2158,11 @@ M: Nishank Trivedi <nistrive@cisco.com> S: Supported F: drivers/net/ethernet/cisco/enic/ +CISCO VIC LOW LATENCY NIC DRIVER +M: Upinder Malhi <umalhi@cisco.com> +S: Supported +F: drivers/infiniband/hw/usnic + CIRRUS LOGIC EP93XX ETHERNET DRIVER M: Hartley Sweeten <hsweeten@visionengravers.com> L: netdev@vger.kernel.org @@ -7468,7 +7473,7 @@ S: Maintained F: drivers/scsi/sr* SCSI RDMA PROTOCOL (SRP) INITIATOR -M: David Dillow <dillowda@ornl.gov> +M: Bart Van Assche <bvanassche@acm.org> L: linux-rdma@vger.kernel.org S: Supported W: http://www.openfabrics.org diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 3c101a07f17..77089399359 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -54,6 +54,7 @@ source "drivers/infiniband/hw/mlx4/Kconfig" source "drivers/infiniband/hw/mlx5/Kconfig" source "drivers/infiniband/hw/nes/Kconfig" source "drivers/infiniband/hw/ocrdma/Kconfig" +source "drivers/infiniband/hw/usnic/Kconfig" source "drivers/infiniband/ulp/ipoib/Kconfig" diff --git a/drivers/infiniband/Makefile b/drivers/infiniband/Makefile index 1fe69888515..bf508b5550c 100644 --- a/drivers/infiniband/Makefile +++ b/drivers/infiniband/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_MLX4_INFINIBAND) += hw/mlx4/ obj-$(CONFIG_MLX5_INFINIBAND) += hw/mlx5/ obj-$(CONFIG_INFINIBAND_NES) += hw/nes/ obj-$(CONFIG_INFINIBAND_OCRDMA) += hw/ocrdma/ +obj-$(CONFIG_INFINIBAND_USNIC) += hw/usnic/ obj-$(CONFIG_INFINIBAND_IPOIB) += ulp/ipoib/ obj-$(CONFIG_INFINIBAND_SRP) += ulp/srp/ obj-$(CONFIG_INFINIBAND_SRPT) += ulp/srpt/ diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 907f3d3f117..9b079a7ea29 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2527,8 +2527,11 @@ static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, return 0; sin6 = (struct sockaddr_in6 *) addr; - if ((ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && - !sin6->sin6_scope_id) + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) + return 0; + + if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 0717940ec3b..3d2e489ab73 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -334,7 +334,6 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; unsigned long flags; - int ret; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); /* @@ -350,7 +349,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) cm_id_priv->state = IW_CM_STATE_DESTROYING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); /* destroy the listening endpoint */ - ret = cm_id->device->iwcm->destroy_listen(cm_id); + cm_id->device->iwcm->destroy_listen(cm_id); spin_lock_irqsave(&cm_id_priv->lock, flags); break; case IW_CM_STATE_ESTABLISHED: diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index faad2caf22b..7d3292c7b4b 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -613,6 +613,7 @@ static ssize_t show_node_type(struct device *device, case RDMA_NODE_IB_CA: return sprintf(buf, "%d: CA\n", dev->node_type); case RDMA_NODE_RNIC: return sprintf(buf, "%d: RNIC\n", dev->node_type); case RDMA_NODE_USNIC: return sprintf(buf, "%d: usNIC\n", dev->node_type); + case RDMA_NODE_USNIC_UDP: return sprintf(buf, "%d: usNIC UDP\n", dev->node_type); case RDMA_NODE_IB_SWITCH: return sprintf(buf, "%d: switch\n", dev->node_type); case RDMA_NODE_IB_ROUTER: return sprintf(buf, "%d: router\n", dev->node_type); default: return sprintf(buf, "%d: <unknown>\n", dev->node_type); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index b3acfc03c74..3ac79511543 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -119,6 +119,8 @@ rdma_node_get_transport(enum rdma_node_type node_type) return RDMA_TRANSPORT_IWARP; case RDMA_NODE_USNIC: return RDMA_TRANSPORT_USNIC; + case RDMA_NODE_USNIC_UDP: + return RDMA_TRANSPORT_USNIC_UDP; default: BUG(); return 0; @@ -136,6 +138,7 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_ return IB_LINK_LAYER_INFINIBAND; case RDMA_TRANSPORT_IWARP: case RDMA_TRANSPORT_USNIC: + case RDMA_TRANSPORT_USNIC_UDP: return IB_LINK_LAYER_ETHERNET; default: return IB_LINK_LAYER_UNSPECIFIED; diff --git a/drivers/infiniband/hw/amso1100/c2_intr.c b/drivers/infiniband/hw/amso1100/c2_intr.c index 8951db4ae29..3a17d9b36db 100644 --- a/drivers/infiniband/hw/amso1100/c2_intr.c +++ b/drivers/infiniband/hw/amso1100/c2_intr.c @@ -169,7 +169,8 @@ static void handle_vq(struct c2_dev *c2dev, u32 mq_index) * We should never get here, as the adapter should * never send us a reply that we're not expecting. */ - vq_repbuf_free(c2dev, host_msg); + if (reply_msg != NULL) + vq_repbuf_free(c2dev, host_msg); pr_debug("handle_vq: UNEXPECTEDLY got NULL req\n"); return; } diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 84e45006451..41b11951a30 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -76,7 +76,7 @@ static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr, INIT_ULPTX_WR(req, wr_len, 0, 0); req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR) | (wait ? FW_WR_COMPL(1) : 0)); - req->wr.wr_lo = wait ? (__force __be64)&wr_wait : 0; + req->wr.wr_lo = wait ? (__force __be64)(unsigned long) &wr_wait : 0L; req->wr.wr_mid = cpu_to_be32(FW_WR_LEN16(DIV_ROUND_UP(wr_len, 16))); req->cmd = cpu_to_be32(ULPTX_CMD(ULP_TX_MEM_WRITE)); req->cmd |= cpu_to_be32(V_T5_ULP_MEMIO_ORDER(1)); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index bf218d9ec08..c2702f549f1 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -57,6 +57,7 @@ #define DRV_RELDATE "April 4, 2008" #define MLX4_IB_FLOW_MAX_PRIO 0xFFF +#define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver"); @@ -94,21 +95,27 @@ static union ib_gid zgid; static int check_flow_steering_support(struct mlx4_dev *dev) { + int eth_num_ports = 0; int ib_num_ports = 0; - int i; - - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) - ib_num_ports++; - if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { - if (ib_num_ports || mlx4_is_mfunc(dev)) { - pr_warn("Device managed flow steering is unavailable " - "for IB ports or in multifunction env.\n"); - return 0; + int dmfs = dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED; + + if (dmfs) { + int i; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) + eth_num_ports++; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + ib_num_ports++; + dmfs &= (!ib_num_ports || + (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB)) && + (!eth_num_ports || + (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN)); + if (ib_num_ports && mlx4_is_mfunc(dev)) { + pr_warn("Device managed flow steering is unavailable for IB port in multifunction env.\n"); + dmfs = 0; } - return 1; } - return 0; + return dmfs; } static int mlx4_ib_query_device(struct ib_device *ibdev, @@ -167,7 +174,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B; else props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A; - if (check_flow_steering_support(dev->dev)) + if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; } @@ -816,6 +823,7 @@ struct mlx4_ib_steering { }; static int parse_flow_attr(struct mlx4_dev *dev, + u32 qp_num, union ib_flow_spec *ib_spec, struct _rule_hw *mlx4_spec) { @@ -831,6 +839,14 @@ static int parse_flow_attr(struct mlx4_dev *dev, mlx4_spec->eth.vlan_tag = ib_spec->eth.val.vlan_tag; mlx4_spec->eth.vlan_tag_msk = ib_spec->eth.mask.vlan_tag; break; + case IB_FLOW_SPEC_IB: + type = MLX4_NET_TRANS_RULE_ID_IB; + mlx4_spec->ib.l3_qpn = + cpu_to_be32(qp_num); + mlx4_spec->ib.qpn_mask = + cpu_to_be32(MLX4_IB_FLOW_QPN_MASK); + break; + case IB_FLOW_SPEC_IPV4: type = MLX4_NET_TRANS_RULE_ID_IPV4; @@ -862,6 +878,115 @@ static int parse_flow_attr(struct mlx4_dev *dev, return mlx4_hw_rule_sz(dev, type); } +struct default_rules { + __u32 mandatory_fields[IB_FLOW_SPEC_SUPPORT_LAYERS]; + __u32 mandatory_not_fields[IB_FLOW_SPEC_SUPPORT_LAYERS]; + __u32 rules_create_list[IB_FLOW_SPEC_SUPPORT_LAYERS]; + __u8 link_layer; +}; +static const struct default_rules default_table[] = { + { + .mandatory_fields = {IB_FLOW_SPEC_IPV4}, + .mandatory_not_fields = {IB_FLOW_SPEC_ETH}, + .rules_create_list = {IB_FLOW_SPEC_IB}, + .link_layer = IB_LINK_LAYER_INFINIBAND + } +}; + +static int __mlx4_ib_default_rules_match(struct ib_qp *qp, + struct ib_flow_attr *flow_attr) +{ + int i, j, k; + void *ib_flow; + const struct default_rules *pdefault_rules = default_table; + u8 link_layer = rdma_port_get_link_layer(qp->device, flow_attr->port); + + for (i = 0; i < sizeof(default_table)/sizeof(default_table[0]); i++, + pdefault_rules++) { + __u32 field_types[IB_FLOW_SPEC_SUPPORT_LAYERS]; + memset(&field_types, 0, sizeof(field_types)); + + if (link_layer != pdefault_rules->link_layer) + continue; + + ib_flow = flow_attr + 1; + /* we assume the specs are sorted */ + for (j = 0, k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS && + j < flow_attr->num_of_specs; k++) { + union ib_flow_spec *current_flow = + (union ib_flow_spec *)ib_flow; + + /* same layer but different type */ + if (((current_flow->type & IB_FLOW_SPEC_LAYER_MASK) == + (pdefault_rules->mandatory_fields[k] & + IB_FLOW_SPEC_LAYER_MASK)) && + (current_flow->type != + pdefault_rules->mandatory_fields[k])) + goto out; + + /* same layer, try match next one */ + if (current_flow->type == + pdefault_rules->mandatory_fields[k]) { + j++; + ib_flow += + ((union ib_flow_spec *)ib_flow)->size; + } + } + + ib_flow = flow_attr + 1; + for (j = 0; j < flow_attr->num_of_specs; + j++, ib_flow += ((union ib_flow_spec *)ib_flow)->size) + for (k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS; k++) + /* same layer and same type */ + if (((union ib_flow_spec *)ib_flow)->type == + pdefault_rules->mandatory_not_fields[k]) + goto out; + + return i; + } +out: + return -1; +} + +static int __mlx4_ib_create_default_rules( + struct mlx4_ib_dev *mdev, + struct ib_qp *qp, + const struct default_rules *pdefault_rules, + struct _rule_hw *mlx4_spec) { + int size = 0; + int i; + + for (i = 0; i < sizeof(pdefault_rules->rules_create_list)/ + sizeof(pdefault_rules->rules_create_list[0]); i++) { + int ret; + union ib_flow_spec ib_spec; + switch (pdefault_rules->rules_create_list[i]) { + case 0: + /* no rule */ + continue; + case IB_FLOW_SPEC_IB: + ib_spec.type = IB_FLOW_SPEC_IB; + ib_spec.size = sizeof(struct ib_flow_spec_ib); + + break; + default: + /* invalid rule */ + return -EINVAL; + } + /* We must put empty rule, qpn is being ignored */ + ret = parse_flow_attr(mdev->dev, 0, &ib_spec, + mlx4_spec); + if (ret < 0) { + pr_info("invalid parsing\n"); + return -EINVAL; + } + + mlx4_spec = (void *)mlx4_spec + ret; + size += ret; + } + return size; +} + static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain, enum mlx4_net_trans_promisc_mode flow_type, @@ -873,6 +998,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att struct mlx4_ib_dev *mdev = to_mdev(qp->device); struct mlx4_cmd_mailbox *mailbox; struct mlx4_net_trans_rule_hw_ctrl *ctrl; + int default_flow; static const u16 __mlx4_domain[] = { [IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS, @@ -907,8 +1033,21 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att ib_flow = flow_attr + 1; |