diff options
43 files changed, 1090 insertions, 177 deletions
diff --git a/Documentation/scsi/scsi_transport_srp/Makefile b/Documentation/scsi/scsi_transport_srp/Makefile new file mode 100644 index 000000000000..5f6b567e955c --- /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 000000000000..75d610d6411a --- /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 9bc170ee9a2a..fc5908fcdc1f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7473,7 +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/core/cma.c b/drivers/infiniband/core/cma.c index 8e49db690f33..4173a2ad6d08 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2480,8 +2480,11 @@ 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 0717940ec3b5..3d2e489ab732 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/hw/amso1100/c2_intr.c b/drivers/infiniband/hw/amso1100/c2_intr.c index 8951db4ae29d..3a17d9b36dba 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 84e45006451c..41b11951a30a 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 1958c5ca792a..ea5844e89b2a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -55,6 +55,7 @@ #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"); @@ -92,21 +93,27 @@ 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, @@ -165,7 +172,7 @@ 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; } @@ -819,6 +826,7 @@ 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) { @@ -834,6 +842,14 @@ 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; @@ -865,6 +881,115 @@ 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, @@ -876,6 +1001,7 @@ 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, @@ -910,8 +1036,21 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att ib_flow = flow_attr + 1; size += sizeof(struct mlx4_net_trans_rule_hw_ctrl); + /* Add default flows */ + default_flow = __mlx4_ib_default_rules_match(qp, flow_attr); + if (default_flow >= 0) { + ret = __mlx4_ib_create_default_rules( + mdev, qp, default_table + default_flow, + mailbox->buf + size); + if (ret < 0) { + mlx4_free_cmd_mailbox(mdev->dev, mailbox); + return -EINVAL; + } + size += ret; + } for (i = 0; i < flow_attr->num_of_specs; i++) { - ret = parse_flow_attr(mdev->dev, ib_flow, mailbox->buf + size); + ret = parse_flow_attr(mdev->dev, qp->qp_num, ib_flow, + mailbox->buf + size); if (ret < 0) { mlx4_free_cmd_mailbox(mdev->dev, mailbox); return -EINVAL; @@ -1682,6 +1821,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) } if (check_flow_steering_support(dev)) { + ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED; ibdev->ib_dev.create_flow = mlx4_ib_create_flow; ibdev->ib_dev.destroy_flow = mlx4_ib_destroy_flow; @@ -1710,8 +1850,35 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) spin_lock_init(&ibdev->sm_lock); mutex_init(&ibdev->cap_mask_mutex); + if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) { + ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS; + err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count, + MLX4_IB_UC_STEER_QPN_ALIGN, + &ibdev->steer_qpn_base); + if (err) + goto err_counter; + + ibdev->ib_uc_qpns_bitmap = + kmalloc(BITS_TO_LONGS(ibdev->steer_qpn_count) * + sizeof(long), + GFP_KERNEL); + if (!ibdev->ib_uc_qpns_bitmap) { + dev_err(&dev->pdev->dev, "bit map alloc failed\n"); + goto err_steer_qp_release; + } + + bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count); + + err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE( + dev, ibdev->steer_qpn_base, + ibdev->steer_qpn_base + + ibdev->steer_qpn_count - 1); + if (err) + goto err_steer_free_bitmap; + } + if (ib_register_device(&ibdev->ib_dev, NULL)) - goto err_counter; + goto err_steer_free_bitmap; if (mlx4_ib_mad_init(ibdev)) goto err_reg; @@ -1762,6 +1929,13 @@ err_mad: err_reg: ib_unregister_device(&ibdev->ib_dev); +err_steer_free_bitmap: + kfree(ibdev->ib_uc_qpns_bitmap); + +err_steer_qp_release: + if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) + mlx4_qp_release_range(dev, ibdev->steer_qpn_base, + ibdev->steer_qpn_count); err_counter: for (; i; --i) if (ibdev->counters[i - 1] != -1) @@ -1782,6 +1956,69 @@ err_dealloc: return NULL; } +int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn) +{ + int offset; + + WARN_ON(!dev->ib_uc_qpns_bitmap); + + offset = bitmap_find_free_region(dev->ib_uc_qpns_bitmap, + dev->steer_qpn_count, + get_count_order(count)); + if (offset < 0) + return offset; + + *qpn = dev->steer_qpn_base + offset; + return 0; +} + +void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count) +{ + if (!qpn || + dev->steering_support != MLX4_STEERING_MODE_DEVICE_MANAGED) + return; + + BUG_ON(qpn < dev->steer_qpn_base); + + bitmap_release_region(dev->ib_uc_qpns_bitmap, + qpn - dev->steer_qpn_base, + get_count_order(count)); +} + +int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, + int is_attach) +{ + int err; + size_t flow_size; + struct ib_flow_attr *flow = NULL; + struct ib_flow_spec_ib *ib_spec; + + if (is_attach) { + flow_size = sizeof(struct ib_flow_attr) + + sizeof(struct ib_flow_spec_ib); + flow = kzalloc(flow_size, GFP_KERNEL); + if (!flow) + return -ENOMEM; + flow->port = mqp->port; + flow->num_of_specs = 1; + flow->size = flow_size; + ib_spec = (struct ib_flow_spec_ib *)(flow + 1); + ib_spec->type = IB_FLOW_SPEC_IB; + ib_spec->size = sizeof(struct ib_flow_spec_ib); + /* Add an empty rule for IB L2 */ + memset(&ib_spec->mask, 0, sizeof(ib_spec->mask)); + + err = __mlx4_ib_create_flow(&mqp->ibqp, flow, + IB_FLOW_DOMAIN_NIC, + MLX4_FS_REGULAR, + &mqp->reg_id); + } else { + err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id); + } + kfree(flow); + return err; +} + static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) { struct mlx4_ib_dev *ibdev = ibdev_ptr; @@ -1795,6 +2032,13 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) pr_warn("failure unregistering notifier\n"); ibdev->iboe.nb.notifier_call = NULL; } + + if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) { + mlx4_qp_release_range(dev, ibdev->steer_qpn_base, + ibdev->steer_qpn_count); + kfree(ibdev->ib_uc_qpns_bitmap); + } + iounmap(ibdev->uar_map); for (p = 0; p < ibdev->num_ports; ++p) if (ibdev->counters[p] != -1) diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 036b663dd26e..837f9aa3d2a2 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -68,6 +68,8 @@ enum { /*module param to indicate if SM assigns the alias_GUID*/ extern int mlx4_ib_sm_guid_assign; +#define MLX4_IB_UC_STEER_QPN_ALIGN 1 +#define MLX4_IB_UC_MAX_NUM_QPS 256 struct mlx4_ib_ucontext { struct ib_ucontext ibucontext; struct mlx4_uar uar; @@ -153,6 +155,7 @@ struct mlx4_ib_wq { enum mlx4_ib_qp_flags { MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO, MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, + MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP, MLX4_IB_SRIOV_TUNNEL_QP = 1 << 30, MLX4_IB_SRIOV_SQP = 1 << 31, }; @@ -270,6 +273,7 @@ struct mlx4_ib_qp { struct list_head gid_list; struct list_head steering_rules; struct mlx4_ib_buf *sqp_proxy_rcv; + u64 reg_id; }; @@ -494,6 +498,10 @@ struct mlx4_ib_dev { struct kobject *dev_ports_parent[MLX4_MFUNC_MAX]; struct mlx4_ib_iov_port iov_ports[MLX4_MAX_PORTS]; struct pkey_mgt pkeys; + unsigned long *ib_uc_qpns_bitmap; + int steer_qpn_count; + int steer_qpn_base; + int steering_support; }; struct ib_event_work { @@ -752,5 +760,9 @@ void mlx4_ib_device_unregister_sysfs(struct mlx4_ib_dev *device); __be64 mlx4_ib_gen_node_guid(void); +int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn); +void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count); +int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, + int is_attach); #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 4f10af2905b5..387fbf274151 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -716,6 +716,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO) qp->flags |= MLX4_IB_QP_LSO; + if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) { + if (dev->steering_support == + MLX4_STEERING_MODE_DEVICE_MANAGED) + qp->flags |= MLX4_IB_QP_NETIF; + else + goto err; + } + err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, qp); if (err) goto err; @@ -765,7 +773,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (init_attr->qp_type == IB_QPT_RAW_PACKET) err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn); else - err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn); + if (qp->flags & MLX4_IB_QP_NETIF) + err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn); + else + err = mlx4_qp_reserve_range(dev->dev, 1, 1, + &qpn); if (err) goto err_proxy; } @@ -790,8 +802,12 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, return 0; err_qpn: - if (!sqpn) - mlx4_qp_release_range(dev->dev, qpn, 1); + if (!sqpn) { + if (qp->flags & MLX4_IB_QP_NETIF) + mlx4_ib_steer_qp_free(dev, qpn, 1); + else + mlx4_qp_release_range(dev->dev, qpn, 1); + } err_proxy: if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI) free_proxy_bufs(pd->device, qp); @@ -932,8 +948,12 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, mlx4_qp_free(dev->dev, &qp->mqp); - if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) - mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1); + if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) { + if (qp->flags & MLX4_IB_QP_NETIF) + mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1); + else + mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1); + } mlx4_mtt_cleanup(dev->dev, &qp->mtt); @@ -987,9 +1007,16 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, */ if (init_attr->create_flags & ~(MLX4_IB_QP_LSO | MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK | - MLX4_IB_SRIOV_TUNNEL_QP | MLX4_IB_SRIOV_SQP)) + MLX4_IB_SRIOV_TUNNEL_QP | + MLX4_IB_SRIOV_SQP | + MLX4_IB_QP_NETIF)) return ERR_PTR(-EINVAL); + if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) { + if (init_attr->qp_type != IB_QPT_UD) + return ERR_PTR(-EINVAL); + } + if (init_attr->create_flags && (udata || ((init_attr->create_flags & ~MLX4_IB_SRIOV_SQP) && @@ -1235,6 +1262,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, struct mlx4_qp_context *context; enum mlx4_qp_optpar optpar = 0; int sqd_event; + int steer_qp = 0; int err = -EINVAL; context = kzalloc(sizeof *context, GFP_KERNEL); @@ -1319,6 +1347,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX; } else context->pri_path.counter_index = 0xff; + + if (qp->flags & MLX4_IB_QP_NETIF) { + mlx4_ib_steer_qp_reg(dev, qp, 1); + steer_qp = 1; + } } if (attr_mask & IB_QP_PKEY_INDEX) { @@ -1547,9 +1580,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, qp->sq_next_wqe = 0; if (qp->rq.wqe_cnt) *qp->db.db = 0; + + if (qp->flags & MLX4_IB_QP_NETIF) + mlx4_ib_steer_qp_reg(dev, qp, 0); } out: + if (err && steer_qp) + mlx4_ib_steer_qp_reg(dev, qp, 0); kfree(context); return err; } @@ -2762,6 +2800,9 @@ done: if (qp->flags & MLX4_IB_QP_LSO) qp_init_attr->create_flags |= IB_QP_CREATE_IPOIB_UD_LSO; + if (qp->flags & MLX4_IB_QP_NETIF) + qp_init_attr->create_flags |= IB_QP_CREATE_NETIF_QP; + qp_init_attr->sq_sig_type = qp->sq_signal_bits == cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE) ? IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR; diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c index 97516eb363b7..db2ea31df832 100644 --- a/drivers/infiniband/hw/mlx4/sysfs.c +++ b/drivers/infiniband/hw/mlx4/sysfs.c @@ -582,8 +582,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave) p->pkey_group.attrs = alloc_group_attrs(show_port_pkey, store_port_pkey, dev->dev->caps.pkey_table_len[port_num]); - if (!p->pkey_group.attrs) + if (!p->pkey_group.attrs) { + ret = -ENOMEM; goto err_alloc; + } ret = sysfs_create_group(&p->kobj, &p->pkey_group); if (ret) @@ -591,8 +593,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave) p->gid_group.name = "gid_idx"; p->gid_group.attrs = alloc_group_attrs(show_port_gid_idx, NULL, 1); - if (!p->gid_group.attrs) + if (!p->gid_group.attrs) { + ret = -ENOMEM; goto err_free_pkey; + } ret = sysfs_create_group(&p->kobj, &p->gid_group); if (ret) diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index b72627429745..b1705ce6eb88 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -73,14 +73,24 @@ static void *get_cqe(struct mlx5_ib_cq *cq, int n) return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz); } +static u8 sw_ownership_bit(int n, int nent) +{ + return (n & nent) ? 1 : 0; +} + static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n) { void *cqe = get_cqe(cq, n & cq->ibcq.cqe); struct mlx5_cqe64 *cqe64; cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64; - return ((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ - !!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe; + + if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) && + !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) { + return cqe; + } else { + return NULL; + } } static void *next_cqe_sw(struct mlx5_ib_cq *cq) @@ -351,6 +361,11 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64, qp->sq.last_poll = tail; } +static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf) +{ + mlx5_buf_free(&dev->mdev, &buf->buf); +} + static int mlx5_poll_one(struct mlx5_ib_cq *cq, struct mlx5_ib_qp **cur_qp, struct ib_wc *wc) @@ -366,6 +381,7 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq, void *cqe; int idx; +repoll: cqe = next_cqe_sw(cq); if (!cqe) return -EAGAIN; @@ -379,7 +395,18 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq, */ rmb(); - /* TBD: resize CQ */ + opcode = cqe64->op_own >> 4; + if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) { + if (likely(cq->resize_buf)) { + free_cq_buf(dev, &cq->buf); + cq->buf = *cq->resize_buf; + kfree(cq->resize_buf); + cq->resize_buf = NULL; + goto repoll; + } else { + mlx5_ib_warn(dev, "unexpected resize cqe\n"); + } + } qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff; if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) { @@ -398,7 +425,6 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq, } wc->qp = &(*cur_qp)->ibqp; - opcode = cqe64->op_own >> 4; switch (opcode) { case MLX5_CQE_REQ: wq = &(*cur_qp)->sq; @@ -503,15 +529,11 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf, return err; buf->cqe_size = cqe_size; + buf->nent = nent; return 0; } -static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf) -{ - mlx5_buf_free(&dev->mdev, &buf->buf); -} - static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, struct ib_ucontext *context, struct mlx5_ib_cq *cq, int entries, struct mlx5_create_cq_mbox_in **cqb, @@ -576,16 +598,16 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context) ib_umem_release(cq->buf.umem); } -static void init_cq_buf(struct mlx5_ib_cq *cq, int nent) +static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf) { int i; void *cqe; struct mlx5_cqe64 *cqe64; - for (i = 0; i < nent; i++) { - cqe = get_cqe(cq, i); - cqe64 = (cq->buf.cqe_size == 64) ? cqe : cqe + 64; - cqe64->op_own = 0xf1; + for (i = 0; i < buf->nent; i++) { + cqe = get_cqe_from_buf(buf, i, buf->cqe_size); + cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64; + cqe64->op_own = MLX5_CQE_INVALID << 4; } } @@ -610,7 +632,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (err) goto err_db; - init_cq_buf(cq, entries); + init_cq_buf(cq, &cq->buf); *inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * cq->buf.buf.npages; *cqb = mlx5_vzalloc(*inlen); @@ -818,12 +840,266 @@ void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq) int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period) { - return -ENOSYS; + struct mlx5_modify_cq_mbox_in *in; + struct mlx5_ib_dev *dev = to_mdev(cq->device); + struct mlx5_ib_cq *mcq = to_mcq(cq); + int err; + u32 fsel; + + if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_CQ_MODER)) + return -ENOSYS; + + in = kzalloc(sizeof(*in), GFP_KERNEL); + if (!in) + return -ENOMEM; + + in->cqn = cpu_to_be32(mcq->mcq.cqn); + fsel = (MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT); + in->ctx.cq_period = cpu_to_be16(cq_period); + in->ctx.cq_max_count = cpu_to_be16(cq_count); + in->field_select = cpu_to_be32(fsel); + err = mlx5_core_modify_cq(&dev->mdev, &mcq->mcq, in, sizeof(*in)); + kfree(in); + + if (err) + mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn); + + return err; +} + +static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, + int entries, struct ib_udata *udata, int *npas, + int *page_shift, int *cqe_size) +{ + struct mlx5_ib_resize_cq ucmd; + struct ib_umem *umem; + int err; + int npages; + struct ib_ucontext *context = cq->buf.umem->context; + + err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); + if (err) + return err; + + if (ucmd.reserved0 || ucmd.reserved1) + return -EINVAL; + + umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size, + IB_ACCESS_LOCAL_WRITE, 1); + if (IS_ERR(umem)) { + err = PTR_ERR(umem); + return err; + } + + mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift, + npas, NULL); + + cq->resize_umem = umem; + *cqe_size = ucmd.cqe_size; + + return 0; +} + +static void un_resize_user(struct mlx5_ib_cq *cq) +{ + ib_umem_release(cq->resize_umem); +} + +static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, + int entries, int cqe_size) +{ + int err; + + cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL); + if (!cq->resize_buf) + return -ENOMEM; + + err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size); + if (err) + goto ex; + + init_cq_buf(cq, cq->resize_buf); + + return 0; + +ex: + kfree(cq->resize_buf); + return err; +} + +static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq) +{ + free_cq_buf(dev, cq->resize_buf); + cq->resize_buf = NULL; +} + +static int copy_resize_cqes(struct mlx5_ib_cq *cq) +{ + struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device); + struct mlx5_cqe64 *scqe64; + struct mlx5_cqe64 *dcqe64; + void *start_cqe; + void *scqe; + void *dcqe; + int ssize; + int dsize; + int i; + u8 sw_own; + + ssize = cq->buf.cqe_size; + dsize = cq->resize_buf->cqe_size; + if (ssize != dsize) { + mlx5_ib_warn(dev, "resize from different cqe size is not supported\n"); + return -EINVAL; + } + + i = cq->mcq.cons_index; + scqe = get_sw_cqe(cq, i); + scqe64 = ssize == 64 ? scqe : scqe + 64; + start_cqe = scqe; + if (!scqe) { + mlx5_ib_warn(dev, "expected cqe in sw ownership\n"); + return -EINVAL; + } + + while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) { + dcqe = get_cqe_from_buf(cq->resize_buf, + (i + 1) & (cq->resize_buf->nent), + dsize); + dcqe64 = dsize == 64 ? dcqe : dcqe + 64; + sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent); + memcpy(dcqe, scqe, dsize); + dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own; + + ++i; + scqe = get_sw_cqe(cq, i); + scqe64 = ssize == 64 ? scqe : scqe + 64; + if (!scqe) { + mlx5_ib_warn(dev, "expected cqe in sw ownership\n"); + return -EINVAL; + } + + if (scqe == start_cqe) { + pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n", + cq->mcq.cqn); + return -ENOMEM; + } + } + ++cq->mcq.cons_index; + return 0; } int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) { - return -ENOSYS; + struct mlx5_ib_dev *dev = to_mdev(ibcq->device); + struct mlx5_ib_cq *cq = to_mcq(ibcq); + struct mlx5_modify_cq_mbox_in *in; + int err; + int npas; + int page_shift; + int inlen; + int uninitialized_var(cqe_size); + unsigned long flags; + + if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) { + pr_info("Firmware does not support resize CQ\n"); + return -ENOSYS; + } + + if (entries < 1) + return -EINVAL; + + entries = roundup_pow_of_two(entries + 1); + if (entries > dev->mdev.caps.max_cqes + 1) + return -EINVAL; + + if (entries == ibcq->cqe + 1) + return 0; + + mutex_lock(&cq->resize_mutex); + if (udata) { + err = resize_user(dev, cq, entries, udata, &npas, &page_shift, + &cqe_size); + } else { + cqe_size = 64; + err = resize_kernel(dev, cq, entries, cqe_size); + if (!err) { + npas = cq->resize_buf->buf.npages; + page_shift = cq->resize_buf->buf.page_shift; + } + } + + if (err) + goto ex; + + inlen = sizeof(*in) + npas * sizeof(in->pas[0]); + in = mlx5_vzalloc(inlen); + if (!in) { + err = -ENOMEM; + goto ex_resize; + } + + if (udata) + mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift, + in->pas, 0); + else + mlx5_fill_page_array(&cq->resize_buf->buf, in->pas); + + in->field_select = cpu_to_be32(MLX5_MODIFY_CQ_MASK_LOG_SIZE | + MLX5_MODIFY_CQ_MASK_PG_OFFSET | + MLX5_MODIFY_CQ_MASK_PG_SIZE); + in->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; + in->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5; + in->ctx.page_offset = 0; + in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(entries) << 24); + in->hdr.opmod = cpu_to_be16(MLX5_CQ_OPMOD_RESIZE); + in->cqn = cpu_to_be32(cq->mcq.cqn); + + err = mlx5_core_modify_cq(&dev->mdev, &cq->mcq, in, inlen); + if (err) + goto ex_alloc; + + if (udata) { + cq->ibcq.cqe = entries - 1; + ib_umem_release(cq->buf.umem); + cq->buf.umem = cq->resize_umem; + cq->resize_umem = NULL; + } else { + struct mlx5_ib_cq_buf tbuf; + int resized = 0; + + spin_lock_irqsave(&cq->lock, flags); + if (cq->resize_buf) { + err = copy_resize_cqes(cq); + if (!err) { + tbuf = cq->buf; + cq->buf = *cq->resize_buf; + kfree(cq->resize_buf); + cq->resize_buf = NULL; + resized = 1; + } + } + cq->ibcq.cqe = entries - 1; + spin_unlock_irqrestore(&cq->lock, flags); + if (resized) + free_cq_buf(dev, &tbuf); + } + mutex_unlock(&cq->resize_mutex); + + mlx5_vfree(in); + return 0; + +ex_alloc: + mlx5_vfree(in); + +ex_resize: + if (udata) + un_resize_user(cq); + else + un_resize_kernel(dev, cq); +ex: + mutex_unlock(&cq->resize_mutex); + return err; } int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 306534109627..9660d093f8cf 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -541,6 +541,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, struct mlx5_ib_ucontext *context; struct mlx5_uuar_info *uuari; struct mlx5_uar *uars; + int gross_uuars; int num_uars; int uuarn; int err; @@ -559,11 +560,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (req.total_num_uuars == 0) return ERR_PTR(-EINVAL); - req.total_num_uuars = ALIGN(req.total_num_uuars, MLX5_BF_REGS_PER_PAGE); + req.total_num_uuars = ALIGN(req.total_num_uuars, + MLX5_NON_FP_BF_REGS_PER_PAGE); if (req.num_low_latency_uuars > req.total_num_uuars - 1) return ERR_PTR(-EINVAL); - num_uars = req.total_num_uuars / MLX5_BF_REGS_PER_PAGE; + num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE; + gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE; resp.qp_tab_size = 1 << dev->mdev.caps.log_max_qp; resp.bf_reg_size = dev->mdev.caps.bf_reg_size; resp.cache_line_size = L1_CACHE_BYTES; @@ -585,7 +588,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, goto out_ctx; } - uuari->bitmap = kcalloc(BITS_TO_LONGS(req.total_num_uuars), + uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars), sizeof(*uuari->bitmap), GFP_KERNEL); if (!uuari->bitmap) { @@ -595,13 +598,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, /* * clear all fast path uuars */ - for (i = 0; i < req.total_num_uuars; i++) { + for (i = 0; i < gross_uuars; i++) { uuarn = i & 3; if (uuarn == 2 || uuarn == 3) set_bit(i, uuari->bitmap); } - uuari->count = kcalloc(req.total_num_uuars, sizeof(*uuari->count), GFP_KERNEL); + uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL); if (!uuari->count) { err = -ENOMEM; goto out_bitmap; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 4c134d93d4fc..389e31965773 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -195,6 +195,7 @@ struct mlx5_ib_cq_buf { struct mlx5_buf buf; struct ib_umem *umem; int cqe_size; + int nent; }; enum mlx5_ib_qp_flags { @@ -220,7 +221,7 @@ struct mlx5_ib_cq { /* protect resize cq */ struct mutex resize_mutex; - struct mlx5_ib_cq_resize *resize_buf; + struct mlx5_ib_cq_buf *resize_buf; struct ib_umem *resize_umem; int cqe_size; }; @@ -264,7 +265,6 @@ struct mlx5_ib_mr { enum ib_wc_status status; struct mlx5_ib_dev *dev; struct mlx5_create_mkey_mbox_out out; - unsigned long start; }; struct mlx5_ib_fast_reg_page_list { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 039c3e40fcb4..7c95ca1f0c25 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -146,7 +146,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) spin_lock_irq(&ent->lock); ent->pending++; spin_unlock_irq(&ent->lock); - mr->start = jiffies; err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in), reg_mr_callback, mr, &mr->out); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7c6b4ba49bec..70dd77085db6 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -340,14 +340,57 @@ static int qp_has_rq(struct ib_qp_init_attr *attr) return 1; } +static int first_med_uuar(void) +{ + return 1; +} + +static int next_uuar(int n) +{ + n++; + + while (((n % 4) & 2)) + n++; + + return n; +} + +static int num_med_uuar(struct mlx5_uuar_info *uuari) +{ + int n; + + n = uuari->num_uars * MLX5_NON_FP_BF_REGS_PER_PAGE - + uuari->num_low_latency_uuars - 1; + + return n >= 0 ? n : 0; +} + +static int max_uuari(struct mlx5_uuar_info *uuari) +{ + return uuari->num_uars * 4; +} + +static int first_hi_uuar(struct mlx5_uuar_info *uuari) +{ + int med; + int i; + int t; + + med = num_med_uuar(uuari); + for (t = 0, i = first_med_uuar();; i = next_uuar(i)) { + t++; + if (t == med) + return next_uuar(i); + } + + return 0; +} + static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari) { - int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE; - int start_uuar; int i; - start_uuar = nuuars - uuari->num_low_latency_uuars; - for (i = start_uuar; i < nuuars; i++) { + for (i = first_hi_uuar(uuari); i < max_uuari(uuari); i = next_uuar(i)) { if (!test_bit(i, uuari->bitmap)) { set_bit(i, uuari->bitmap); uuari->count[i]++; @@ -360,19 +403,10 @@ static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari) static int alloc_med_class_uuar(struct mlx5_uuar_info *uuari) { - int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE; - int minidx = 1; - int uuarn; - int end; + int minidx = first_med_uuar(); int i; - end = nuuars - uuari->num_low_latency_uuars; - - for (i = 1; i < end; i++) { - uuarn = i & 3; - if (uuarn == 2 || uuarn == 3) - continue; - + for (i = first_med_uuar(); i < first_hi_uuar(uuari); i = next_uuar(i)) { if (uuari->count[i] < uuari->count[minidx]) minidx = i; } @@ -489,12 +523,12 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, { struct mlx5_ib_ucontext *context; struct mlx5_ib_create_qp ucmd; - int page_shift; + int page_shift = 0; int uar_index; int npages; - u32 offset; + u32 offset = 0; int uuarn; - int ncont; + int ncont = 0; int err; err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); @@ -510,11 +544,16 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH); if (uuarn < 0) { mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n"); - mlx5_ib_dbg(dev, "reverting to high latency\n"); - uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW); + mlx5_ib_dbg(dev, "reverting to medium latency\n"); + uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM); if (uuarn < 0) { - mlx5_ib_dbg(dev, "uuar allocation failed\n"); - return uuarn; + mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n"); + mlx5_ib_dbg(dev, "reverting to high latency\n"); + uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW); + if (uuarn < 0) { + mlx5_ib_warn(dev, "uuar allocation failed\n"); + return uuarn; + } } } @@ -525,23 +564,29 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, if (err) goto err_uuar; - qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, - qp->buf_size, 0, 0); - if (IS_ERR(qp->umem)) { - mlx5_ib_dbg(dev, "umem_get failed\n"); - err = PTR_ERR(qp->umem); - goto err_uuar; + if (ucmd.buf_addr && qp->buf_size) { + qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, + qp->buf_size, 0, 0); + if (IS_ERR(qp->umem)) { + mlx5_ib_dbg(dev, "umem_get failed\n"); + err = PTR_ERR(qp->umem); + goto err_uuar; + } + } else { + qp->umem = NULL; } - mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift, - &ncont, NULL); - err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset); - if (err) { - mlx5_ib_warn(dev, "bad offset\n"); - goto err_umem; + if (qp->umem) { + mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift, + &ncont, NULL); + err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset); + if (err) { + mlx5_ib_warn(dev, "bad offset\n"); + goto err_umem; + } + mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n", + ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset); } - mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n", - ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset); *inlen = sizeof(**in) + sizeof(*(*in)->pas) * ncont; *in = mlx5_vzalloc(*inlen); @@ -549,7 +594,8 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, err = -ENOMEM; goto err_umem; } - mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0); + if (qp->umem) + mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0); (*in)->ctx.log_pg_sz_remote_qpn = cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24); (*in)->ctx.params2 = cpu_to_be32(offset << 6); @@ -580,7 +626,8 @@ err_free: mlx5_vfree(*in); err_umem: - ib_umem_release(qp->umem); + if (qp->umem) + ib_umem_release(qp->umem); err_uuar: free_uuar(&context->uuari, uuarn); @@ -593,7 +640,8 @@ static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp) context = to_mucontext(pd->uobject->context); mlx5_ib_db_unmap_user(context, &qp->db); - ib_umem_release(qp->umem); + if (qp->umem) + ib_umem_release(qp->umem); free_uuar(&context->uuari, qp->uuarn); } @@ -2212,6 +2260,10 @@ out: qp->db.db[MLX5_SND_DBR] = cpu_to_be32(qp->sq.cur_post); + /* Make sure doorbell record is visible to the HCA before + * we hit doorbell */ + wmb(); + if (bf->need_lock) spin_lock(&bf->lock); diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h index a886de3e593c..32a2a5dfc523 100644 --- a/drivers/infiniband/hw/mlx5/user.h +++ b/drivers/infiniband/hw/mlx5/user.h @@ -93,6 +93,9 @@ struct mlx5_ib_create_cq_resp { struct mlx5_ib_resize_cq { __u64 buf_addr; + __u16 cqe_size; + __u16 reserved0; + __u32 reserved1; }; struct mlx5_ib_create_srq { diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 6b29249aa85a..9c9f2f57e960 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -1354,8 +1354,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi neigh->ha, ntohl(rt->rt_gateway)); if (arpindex >= 0) { - if (!memcmp(nesadapter->arp_table[arpindex].mac_addr, - neigh->ha, ETH_ALEN)) { + if (ether_addr_equal(nesadapter->arp_table[arpindex].mac_addr, neigh->ha)) { /* Mac address same as in nes_arp_table */ goto out; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index ee499d942257..69da5dd1ca8a 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -84,6 +84,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, memcpy((u8 *)ah->av + eth_sz, &grh, sizeof(struct ocrdma_grh)); if (vlan_enabled) ah->av->valid |= OCRDMA_AV_VLAN_VALID; + ah->av->valid = cpu_to_le32(ah->av->valid); return status; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 9f9570ec3c2e..60d5ac23ea80 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -31,7 +31,7 @@ #define Bit(_b) (1 << (_b)) #define OCRDMA_GEN1_FAMILY 0xB -#define OCRDMA_GEN2_FAMILY 0x2 +#define OCRDMA_GEN2_FAMILY 0x0F #define OCRDMA_SUBSYS_ROCE 10 enum { @@ -1694,7 +1694,7 @@ struct ocrdma_grh { u16 rsvd; } __packed; -#define OCRDMA_AV_VALID Bit(0) +#define OCRDMA_AV_VALID Bit(7) #define OCRDMA_AV_VLAN_VALID Bit(1) struct ocrdma_av { diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index d6c7fe7f88d5..3ad651c3356c 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -57,13 +57,20 @@ static void qib_ud_loopback(struct qib_qp *sqp, struct qib_swqe *swqe) struct qib_sge *sge; struct ib_wc wc; u32 length; + enum ib_qp_type sqptype, dqptype; qp = qib_lookup_qpn(ibp, swqe->wr.wr.ud.remote_qpn); if (!qp) { ibp->n_pkt_drops++; return; } - if (qp->ibqp.qp_type != sqp->ibqp.qp_type || + + sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ? + IB_QPT_UD : sqp->ibqp.qp_type; + dqptype = qp->ibqp.qp_type == IB_QPT_GSI ? + IB_QPT_UD : qp->ibqp.qp_type; + + if (dqptype != sqptype || !(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) { ibp->n_pkt_drops++; goto drop; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index d64ed05fb082..5786a78ff8bc 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -104,6 +104,8 @@ int ipoib_open(struct net_device *dev) ipoib_dbg(priv, "bringing up interface\n"); + netif_carrier_off(dev); + set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_pkey_dev_delay_open(dev)) @@ -1366,8 +1368,6 @@ void ipoib_setup(struct net_device *dev) memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); - netif_carrier_off(dev); - priv->dev = dev; spin_lock_init(&priv->lock); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index 049a997caff3..c56d5d44c53b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -192,6 +192,9 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) if (priv->hca_caps & IB_DEVICE_BLOCK_MULTICAST_LOOPBACK) init_attr.create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK; + if (priv->hca_caps & IB_DEVICE_MANAGED_FLOW_STEERING) + init_attr.create_flags |= IB_QP_CREATE_NETIF_QP; + if (dev->features & NETIF_F_SG) init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index a88631918e85..529b6bcdca7a 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -660,6 +660,7 @@ static void srp_remove_target(struct srp_target_port *target) srp_rport_get(target->rport); srp_remove_host(target->scsi_host); scsi_remove_host(target->scsi_host); + srp_stop_rport_timers(target->rport); srp_disconnect_target(target); ib_destroy_cm_id(target->cm_id); srp_free_target_ib(target); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 1e9970d2f0f3..0d02fba94536 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1371,6 +1371,15 @@ static struct mlx4_cmd_info cmd_info[] = { .verify = NULL, .wrapper = mlx4_QP_FLOW_STEERING_DETACH_wrapper }, + { + .opcode = MLX4_FLOW_STEERING_IB_UC_QP_RANGE, + .has_inbox = false, + .has_outbox = false, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, + .wrapper = mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper + }, }; static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave, diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 194928214606..4bd2d80d065e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -513,6 +513,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68 #define QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET 0x70 +#define QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET 0x74 #define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76 #define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80 @@ -603,6 +604,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (field & 0x80) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN; dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f; + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); + if (field & 0x80) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_IPOIB; MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET); dev_cap->fs_max_num_qp_per_entry = field; MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET); @@ -860,6 +864,12 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET); } + + /* turn off ipoib managed steering for guests */ + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); + field &= ~0x80; + MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index acf9d5f1f922..34dffcf61bff 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -895,6 +895,23 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) } EXPORT_SYMBOL_GPL(mlx4_flow_detach); +int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, + u32 max_range_qpn) +{ + int err; + u64 in_param; + + in_param = ((u64) min_range_qpn) << 32; + in_param |= ((u64) max_range_qpn) & 0xFFFFFFFF; + + err = mlx4_cmd(dev, in_param, 0, 0, + MLX4_FLOW_STEERING_IB_UC_QP_RANGE, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); + + return err; +} +EXPORT_SYMBOL_GPL(mlx4_FLOW_STEERING_IB_UC_QP_RANGE); + int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot, enum mlx4_steer_type steer) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index e582a41a802b..59f67f9086dc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1236,6 +1236,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); int mlx4_get_mgm_entry_size(struct mlx4_dev *dev); int mlx4_get_qp_per_mgm(struct mlx4_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 2f3f2bc7f283..663510325c22 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3844,6 +3844,16 @@ int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave, return err; } +int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + return -EPERM; +} + + static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp) { struct res_gid *rgid; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index c2d660be6f76..43c5f4809526 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -201,10 +201,23 @@ EXPORT_SYMBOL(mlx5_core_query_cq); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - int type, struct mlx5_cq_modify_params *params) + struct mlx5_modify_cq_mbox_in *in, int in_sz) { - return -ENOSYS; + struct mlx5_modify_cq_mbox_out out; + int err; + + memset(&out, 0, sizeof(out)); + in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MODIFY_CQ); + err = mlx5_cmd_exec(dev, in, in_sz, &out, sizeof(out)); + if (err) + return err; + + if (out.hdr.status) + return mlx5_cmd_status_to_err(&out.hdr); + + return 0; } +EXPORT_SYMBOL(mlx5_core_modify_cq); int mlx5_init_cq_table(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 80f6d127257a..10e1f1a18255 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -275,7 +275,7 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) } static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, - int index) + int index, int *is_str) { struct mlx5_query_qp_mbox_out *out; struct mlx5_qp_context *ctx; @@ -293,19 +293,40 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, goto out; } + *is_str = 0; ctx = &out->ctx; switch (index) { case QP_PID: param = qp->pid; break; case QP_STATE: - param = be32_to_cpu(ctx->flags) >> 28; + param = (u64)mlx5_qp_state_str(be32_to_cpu(ctx->flags) >> 28); + *is_str = 1; break; case QP_XPORT: - param = (be32_to_cpu(ctx->flags) >> 16) & 0xff; + param = (u64)mlx5_qp_type_str((be32_to_cpu(ctx->flags) >> 16) & 0xff); + *is_str = 1; break; case QP_MTU: - param = ctx->mtu_msgmax >> 5; + switch (ctx->mtu_msgmax >> 5) { + case IB_MTU_256: + param = 256; + break; + case IB_MTU_512: + param = 512; + break; + case IB_MTU_1024: + param = 1024; + break; + case IB_MTU_2048: + param = 2048; + break; + case IB_MTU_4096: + param = 4096; + break; + default: + param = 0; + } break; case QP_N_RECV: param = 1 << ((ctx->rq_size_stride >> 3) & 0xf); @@ -414,6 +435,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count, struct mlx5_field_desc *desc; struct mlx5_rsc_debug *d; char tbuf[18]; + int is_str = 0; u64 field; int ret; @@ -424,7 +446,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count, d = (void *)(desc - desc->i) - sizeof(*d); switch (d->type) { case MLX5_DBG_RSC_QP: - field = qp_read_field(d->dev, d->object, desc->i); + field = qp_read_field(d->dev, d->object, desc->i, &is_str); break; case MLX5_DBG_RSC_EQ: @@ -440,7 +462,12 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count, return -EINVAL; } - ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field); + + if (is_str) + ret = snprintf(tbuf, sizeof(tbuf), "%s\n", (const char *)field); + else + ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field); + if (ret > 0) { if (copy_to_user(buf, tbuf, ret)) return -EFAULT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 40a9f5ed814d..a064f06e0cb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -460,7 +460,10 @@ disable_msix: err_stop_poll: mlx5_stop_health_poll(dev); - mlx5_cmd_teardown_hca(dev); + if (mlx5_cmd_teardown_hca(dev)) { + dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); + return err; + } err_pagealloc_stop: mlx5_pagealloc_stop(dev); @@ -503,7 +506,10 @@ void mlx5_dev_cleanup(struct mlx5_core_dev *dev) mlx5_eq_cleanup(dev); mlx5_disable_msix(dev); mlx5_stop_health_poll(dev); - mlx5_cmd_teardown_hca(dev); + if (mlx5_cmd_teardown_hca(dev)) { + dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); + return; + } mlx5_pagealloc_stop(dev); mlx5_reclaim_startup_pages(dev); mlx5_core_disable_hca(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 37b6ad1f9a1b..d59790a82bc3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -99,7 +99,7 @@ enum { enum { MLX5_MAX_RECLAIM_TIME_MILI = 5000, - MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / 4096, + MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, }; static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id) @@ -192,10 +192,8 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr) struct fw_page *fp; unsigned n; - if (list_empty(&dev->priv.free_list)) { + if (list_empty(&dev->priv.free_list)) return -ENOMEM; - mlx5_core_warn(dev, "\n"); - } fp = list_entry(dev->priv.free_list.next, struct fw_page, list); n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask)); @@ -208,7 +206,7 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr) if (!fp->free_count) list_del(&fp->list); - *addr = fp->addr + n * 4096; + *addr = fp->addr + n * MLX5_ADAPTER_PAGE_SIZE; return 0; } @@ -224,14 +222,15 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr) return; } - n = (addr & ~PAGE_MASK) % 4096; + n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT; fwp->free_count++; set_bit(n, &fwp->bitmask); if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) { rb_erase(&fwp->rb_node, &dev->priv.page_root); if (fwp->free_count != 1) list_del(&fwp->list); - dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE, + DMA_BIDIRECTIONAL); __free_page(fwp->page); kfree(fwp); } else if (fwp->free_count == 1) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index f6afe7b5a675..8c9ac870ecb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -57,7 +57,7 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, in->arg = cpu_to_be32(arg); in->register_id = cpu_to_be16(reg_num); err = mlx5_cmd_exec(dev, in, sizeof(*in) + size_in, out, - sizeof(out) + size_out); + sizeof(*out) + size_out); if (err) goto ex2; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 54faf8bfcaf4..510576213dd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -74,7 +74,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, struct mlx5_destroy_qp_mbox_out dout; int err; - memset(&dout, 0, sizeof(dout)); + memset(&out, 0, sizeof(out)); in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_QP); err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out)); @@ -84,7 +84,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, } if (out.hdr.status) { - pr_warn("current num of QPs 0x%x\n", atomic_read(&dev->num_qps)); + mlx5_core_warn(dev, "current num of QPs 0x%x\n", + atomic_read(&dev->num_qps)); return mlx5_cmd_status_to_err(&out.hdr); } diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index 2700a5a09bd4..d47ffc8d3e43 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -64,10 +64,14 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r) /** * srp_tmo_valid() - check timeout combination validity + * @reconnect_delay: Reconnect delay in seconds. + * @fast_io_fail_tmo: Fast I/O fail timeout in seconds. + * @dev_loss_tmo: Device loss timeout in seconds. * * The combination of the timeout parameters must be such that SCSI commands * are finished in a reasonable time. Hence do not allow the fast I/O fail - * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT. Furthermore, these + * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT nor allow dev_loss_tmo to + * exceed that limit if failing I/O fast has been disabled. Furthermore, these * parameters must be such that multipath can detect failed paths timely. * Hence do not allow all three parameters to be disabled simultaneously. */ @@ -79,6 +83,9 @@ int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo) return -EINVAL; if (fast_io_fail_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT) return -EINVAL; + if (fast_io_fail_tmo < 0 && + dev_loss_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT) + return -EINVAL; if (dev_loss_tmo >= LONG_MAX / HZ) return -EINVAL; if (fast_io_fail_tmo >= 0 && dev_loss_tmo >= 0 && @@ -368,6 +375,7 @@ invalid: /** * srp_reconnect_work() - reconnect and schedule a new attempt if necessary + * @work: Work structure used for scheduling this operation. */ static void srp_reconnect_work(struct work_struct *work) { @@ -408,6 +416,7 @@ static void __rport_fail_io_fast(struct srp_rport *rport) /** * rport_fast_io_fail_timedout() - fast I/O failure timeout handler + * @work: Work structure used for scheduling this operation. */ static void rport_fast_io_fail_timedout(struct work_struct *work) { @@ -426,6 +435,7 @@ static void rport_fast_io_fail_timedout(struct work_struct *work) /** * rport_dev_loss_timedout() - device loss timeout handler + * @work: Work structure used for scheduling this operation. */ static void rport_dev_loss_timedout(struct work_struct *work) { @@ -452,42 +462,35 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport) lockdep_assert_held(&rport->mutex); - if (!rport->deleted) { - delay = rport->reconnect_delay; - fast_io_fail_tmo = rport->fast_io_fail_tmo; - dev_loss_tmo = rport->dev_loss_tmo; - pr_debug("%s current state: %d\n", - dev_name(&shost->shost_gendev), rport->state); + delay = rport->reconnect_delay; + fast_io_fail_tmo = rport->fast_io_fail_tmo; + dev_loss_tmo = rport->dev_loss_tmo; + pr_debug("%s current state: %d\n", dev_name(&shost->shost_gendev), + rport->state); - if (delay > 0) - queue_delayed_work(system_long_wq, - &rport->reconnect_work, - 1UL * delay * HZ); - if (fast_io_fail_tmo >= 0 && - srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { - pr_debug("%s new state: %d\n", - dev_name(&shost->shost_gendev), - rport->state); - scsi_target_block(&shost->shost_gendev); + if (rport->state == SRP_RPORT_LOST) + return; + if (delay > 0) + queue_delayed_work(system_long_wq, &rport->reconnect_work, + 1UL * delay * HZ); + if (srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { + pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev), + rport->state); + scsi_target_block(&shost->shost_gendev); + if (fast_io_fail_tmo >= 0) queue_delayed_work(system_long_wq, &rport->fast_io_fail_work, 1UL * fast_io_fail_tmo * HZ); - } if (dev_loss_tmo >= 0) queue_delayed_work(system_long_wq, &rport->dev_loss_work, 1UL * dev_loss_tmo * HZ); - } else { - pr_debug("%s has already been deleted\n", - dev_name(&shost->shost_gendev)); - srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST); - scsi_target_unblock(&shost->shost_gendev, - SDEV_TRANSPORT_OFFLINE); } } /** * srp_start_tl_fail_timers() - start the transport layer failure timers + * @rport: SRP target port. * * Start the transport layer fast I/O failure and device loss timers. Do not * modify a timer that was already started. @@ -502,6 +505,7 @@ EXPORT_SYMBOL(srp_start_tl_fail_timers); /** * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn() + * @shost: SCSI host for which to count the number of scsi_request_fn() callers. */ static int scsi_request_fn_active(struct Scsi_Host *shost) { @@ -522,6 +526,7 @@ static int scsi_request_fn_active(struct Scsi_Host *shost) /** * srp_reconnect_rport() - reconnect to an SRP target port + * @rport: SRP target port. * * Blocks SCSI command queueing before invoking reconnect() such that * queuecommand() won't be invoked concurrently with reconnect() from outside @@ -556,7 +561,7 @@ int srp_reconnect_rport(struct srp_rport *rport) scsi_target_block(&shost->shost_gendev); while (scsi_request_fn_active(shost)) msleep(20); - res = i->f->reconnect(rport); + res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); if (res == 0) { @@ -578,9 +583,9 @@ int srp_reconnect_rport(struct srp_rport *rport) spin_unlock_irq(shost->host_lock); } else if (rport->state == SRP_RPORT_RUNNING) { /* - * srp_reconnect_rport() was invoked with fast_io_fail - * off. Mark the port as failed and start the TL failure - * timers if these had not yet been started. + * srp_reconnect_rport() has been invoked with fast_io_fail + * and dev_loss off. Mark the port as failed and start the TL + * failure timers if these had not yet been started. */ __rport_fail_io_fast(rport); scsi_target_unblock(&shost->shost_gendev, @@ -599,6 +604,7 @@ EXPORT_SYMBOL(srp_reconnect_rport); /** * srp_timed_out() - SRP transport intercept of the SCSI timeout EH + * @scmd: SCSI command. * * If a timeout occurs while an rport is in the blocked state, ask the SCSI * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core @@ -622,10 +628,6 @@ static void srp_rport_release(struct device *dev) { struct srp_rport *rport = dev_to_rport(dev); - cancel_delayed_work_sync(&rport->reconnect_work); - cancel_delayed_work_sync(&rport->fast_io_fail_work); - cancel_delayed_work_sync(&rport->dev_loss_work); - put_device(dev->parent); kfree(rport); } @@ -674,6 +676,7 @@ static int srp_host_match(struct attribute_container *cont, struct device *dev) /** * srp_rport_get() - increment rport reference count + * @rport: SRP target port. */ void srp_rport_get(struct srp_rport *rport) { @@ -683,6 +686,7 @@ EXPORT_SYMBOL(srp_rport_get); /** * srp_rport_put() - decrement rport reference count + * @rport: SRP target port. */ void srp_rport_put(struct srp_rport *rport) { @@ -780,12 +784,6 @@ void srp_rport_del(struct srp_rport *rport) device_del(dev); transport_destroy_device(dev); - mutex_lock(&rport->mutex); - if (rport->state == SRP_RPORT_BLOCKED) - __rport_fail_io_fast(rport); - rport->deleted = true; - mutex_unlock(&rport->mutex); - put_device(dev); } EXPORT_SYMBOL_GPL(srp_rport_del); @@ -810,6 +808,27 @@ void srp_remove_host(struct Scsi_Host *shost) } EXPORT_SYMBOL_GPL(srp_remove_host); +/** + * srp_stop_rport_timers - stop the transport layer recovery timers + * + * Must be called after srp_remove_host() and scsi_remove_host(). The caller + * must hold a reference on the rport (rport->dev) and on the SCSI host + * (rport->dev.parent). + */ +void srp_stop_rport_timers(struct srp_rport *rport) +{ + mutex_lock(&rport->mutex); + if (rport->state == SRP_RPORT_BLOCKED) + __rport_fail_io_fast(rport); + srp_rport_set_state(rport, SRP_RPORT_LOST); + mutex_unlock(&rport->mutex); + + cancel_delayed_work_sync(&rport->reconnect_work); + cancel_delayed_work_sync(&rport->fast_io_fail_work); + cancel_delayed_work_sync(&rport->dev_loss_work); +} +EXPORT_SYMBOL_GPL(srp_stop_rport_timers); + static int srp_tsk_mgmt_response(struct Scsi_Host *shost, u64 nexus, u64 tm_id, int result) { diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 8df61bc5da00..ff36620f88a7 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -157,6 +157,7 @@ enum { /* register/delete flow steering network rules */ MLX4_QP_FLOW_STEERING_ATTACH = 0x65, MLX4_QP_FLOW_STEERING_DETACH = 0x66, + MLX4_FLOW_STEERING_IB_UC_QP_RANGE = 0x64, }; enum { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7d3a523160ba..7de9fde3a9dd 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -160,7 +160,8 @@ enum { MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6, MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7, - MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8 + MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8, + MLX4_DEV_CAP_FLAG2_DMFS_IPOIB = 1LL << 9 }; enum { @@ -1144,6 +1145,9 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); +int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, + u32 max_range_qpn); + cycle_t mlx4_read_clock(struct mlx4_dev *dev); #endif /* MLX4_DEVICE_H */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 3db67f73d96d..2202c7f72b75 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -79,15 +79,23 @@ enum { MLX5_CQE_RESP_SEND = 2, MLX5_CQE_RESP_SEND_IMM = 3, MLX5_CQE_RESP_SEND_INV = 4, - MLX5_CQE_RESIZE_CQ = 0xff, /* TBD */ + MLX5_CQE_RESIZE_CQ = 5, MLX5_CQE_REQ_ERR = 13, MLX5_CQE_RESP_ERR = 14, + MLX5_CQE_INVALID = 15, }; enum { - MLX5_CQ_MODIFY_RESEIZE = 0, - MLX5_CQ_MODIFY_MODER = 1, - MLX5_CQ_MODIFY_MAPPING = 2, + MLX5_CQ_MODIFY_PERIOD = 1 << 0, + MLX5_CQ_MODIFY_COUNT = 1 << 1, + MLX5_CQ_MODIFY_OVERRUN = 1 << 2, +}; + +enum { + MLX5_CQ_OPMOD_RESIZE = 1, + MLX5_MODIFY_CQ_MASK_LOG_SIZE = 1 << 0, + MLX5_MODIFY_CQ_MASK_PG_OFFSET = 1 << 1, + MLX5_MODIFY_CQ_MASK_PG_SIZE = 1 << 2, }; struct mlx5_cq_modify_params { @@ -158,7 +166,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_query_cq_mbox_out *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - int type, struct mlx5_cq_modify_params *params); + struct mlx5_modify_cq_mbox_in *in, int in_sz); int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index da78875807fc..817a6fae6d2c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -104,9 +104,10 @@ enum { }; enum { - MLX5_BF_REGS_PER_PAGE = 4, - MLX5_MAX_UAR_PAGES = 1 << 8, - MLX5_MAX_UUARS = MLX5_MAX_UAR_PAGES * MLX5_BF_REGS_PER_PAGE, + MLX5_BF_REGS_PER_PAGE = 4, + MLX5_MAX_UAR_PAGES = 1 << 8, + MLX5_NON_FP_BF_REGS_PER_PAGE = 2, + MLX5_MAX_UUARS = MLX5_MAX_UAR_PAGES * MLX5_NON_FP_BF_REGS_PER_PAGE, }; enum { @@ -176,6 +177,8 @@ enum { MLX5_DEV_CAP_FLAG_APM = 1LL << 17, MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, + MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, + MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, MLX5_DEV_CAP_FLAG_RESIZE_SRQ = 1LL << 32, MLX5_DEV_CAP_FLAG_REMOTE_FENCE = 1LL << 38, MLX5_DEV_CAP_FLAG_TLP_HINTS = 1LL << 39, @@ -231,7 +234,8 @@ enum { }; enum { - MLX5_ADAPTER_PAGE_SHIFT = 12 + MLX5_ADAPTER_PAGE_SHIFT = 12, + MLX5_ADAPTER_PAGE_SIZE = 1 << MLX5_ADAPTER_PAGE_SHIFT, }; enum { @@ -697,6 +701,20 @@ struct mlx5_query_cq_mbox_out { __be64 pas[0]; }; +struct mlx5_modify_cq_mbox_in { + struct mlx5_inbox_hdr hdr; + __be32 cqn; + __be32 field_select; + struct mlx5_cq_context ctx; + u8 rsvd[192]; + __be64 pas[0]; +}; + +struct mlx5_modify_cq_mbox_out { + struct mlx5_outbox_hdr hdr; + u8 rsvd[8]; +}; + struct mlx5_enable_hca_mbox_in { struct mlx5_inbox_hdr hdr; u8 rsvd[8]; @@ -831,8 +849,8 @@ struct mlx5_create_mkey_mbox_in { struct mlx5_mkey_seg seg; u8 rsvd1[16]; __be32 xlat_oct_act_size; - __be32 bsf_coto_act_size; - u8 rsvd2[168]; + __be32 rsvd2; + u8 rsvd3[168]; __be64 pas[0]; }; @@ -871,6 +889,7 @@ struct mlx5_modify_mkey_mbox_in { struct mlx5_modify_mkey_mbox_out { struct mlx5_outbox_hdr hdr; + u8 rsvd[8]; }; struct mlx5_dump_mkey_mbox_in { diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index d9e3eacb3a7f..d51eff713549 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -464,4 +464,49 @@ void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev); int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); +static inline const char *mlx5_qp_type_str(int type) +{ + switch (type) { + case MLX5_QP_ST_RC: return "RC"; + case MLX5_QP_ST_UC: return "C"; + case MLX5_QP_ST_UD: return "UD"; + case MLX5_QP_ST_XRC: return "XRC"; + case MLX5_QP_ST_MLX: return "MLX"; + case MLX5_QP_ST_QP0: return "QP0"; + case MLX5_QP_ST_QP1: return "QP1"; + case MLX5_QP_ST_RAW_ETHERTYPE: return "RAW_ETHERTYPE"; + case MLX5_QP_ST_RAW_IPV6: return "RAW_IPV6"; + case MLX5_QP_ST_SNIFFER: return "SNIFFER"; + case MLX5_QP_ST_SYNC_UMR: return "SYNC_UMR"; + case MLX5_QP_ST_PTP_1588: return "PTP_1588"; + case MLX5_QP_ST_REG_UMR: return "REG_UMR"; + default: return "Invalid transport type"; + } +} + +static inline const char *mlx5_qp_state_str(int state) +{ + switch (state) { + case MLX5_QP_STATE_RST: + return "RST"; + case MLX5_QP_STATE_INIT: + return "INIT"; + case MLX5_QP_STATE_RTR: + return "RTR"; + case MLX5_QP_STATE_RTS: + return "RTS"; + case MLX5_QP_STATE_SQER: + return "SQER"; + case MLX5_QP_STATE_SQD: + return "SQD"; + case MLX5_QP_STATE_ERR: + return "ERR"; + case MLX5_QP_STATE_SQ_DRAINING: + return "SQ_DRAINING"; + case MLX5_QP_STATE_SUSPENDED: + return "SUSPENDED"; + default: return "Invalid QP state"; + } +} + #endif /* MLX5_QP_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 688511ed52f5..c6d343078617 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -635,6 +635,7 @@ enum ib_qp_type { enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = 1 << 1, + IB_QP_CREATE_NETIF_QP = 1 << 5, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, @@ -1101,13 +1102,14 @@ enum ib_flow_attr_type { enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, + IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41 }; - +#define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 4 /* Flow steering rule priority is set according to it's domain. @@ -1135,6 +1137,18 @@ struct ib_flow_spec_eth { struct ib_flow_eth_filter mask; }; +struct ib_flow_ib_filter { + __be16 dlid; + __u8 sl; +}; + +struct ib_flow_spec_ib { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_ib_filter val; + struct ib_flow_ib_filter mask; +}; + struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; @@ -1165,6 +1179,7 @@ union ib_flow_spec { u16 size; }; struct ib_flow_spec_eth eth; + struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; }; diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h index 4ebf6913b7b2..b11da5c1331e 100644 --- a/include/scsi/scsi_transport_srp.h +++ b/include/scsi/scsi_transport_srp.h @@ -19,7 +19,7 @@ struct srp_rport_identifiers { * @SRP_RPORT_BLOCKED: Transport layer not operational; fast I/O fail timer * is running and I/O has been blocked. * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast. - * @SRP_RPORT_LOST: Device loss timer has expired; port is being removed. + * @SRP_RPORT_LOST: Port is being removed. */ enum srp_rport_state { SRP_RPORT_RUNNING, @@ -29,10 +29,26 @@ enum srp_rport_state { }; /** - * struct srp_rport - * @lld_data: LLD private data. - * @mutex: Protects against concurrent rport reconnect / fast_io_fail / - * dev_loss_tmo activity. + * struct srp_rport - SRP initiator or target port + * + * Fields that are relevant for SRP initiator and SRP target drivers: + * @dev: Device associated with this rport. + * @port_id: 16-byte port identifier. + * @roles: Role of this port - initiator or target. + * + * Fields that are only relevant for SRP initiator drivers: + * @lld_data: LLD private data. + * @mutex: Protects against concurrent rport reconnect / + * fast_io_fail / dev_loss_tmo activity. + * @state: rport state. + * @deleted: Whether or not srp_rport_del() has already been invoked. + * @reconnect_delay: Reconnect delay in seconds. + * @failed_reconnects: Number of failed reconnect attempts. + * @reconnect_work: Work structure used for scheduling reconnect attempts. + * @fast_io_fail_tmo: Fast I/O fail timeout in seconds. + * @dev_loss_tmo: Device loss timeout in seconds. + * @fast_io_fail_work: Work structure used for scheduling fast I/O fail work. + * @dev_loss_work: Work structure used for scheduling device loss work. */ struct srp_rport { /* for initiator and target drivers */ @@ -48,7 +64,6 @@ struct srp_rport { struct mutex mutex; enum srp_rport_state state; - bool deleted; int reconnect_delay; int failed_reconnects; struct delayed_work reconnect_work; @@ -60,6 +75,8 @@ struct srp_rport { /** * struct srp_function_template + * + * Fields that are only relevant for SRP initiator drivers: * @has_rport_state: Whether or not to create the state, fast_io_fail_tmo and * dev_loss_tmo sysfs attribute for an rport. * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command @@ -71,6 +88,11 @@ struct srp_rport { * srp_reconnect_rport(). * @terminate_rport_io: Callback function for terminating all outstanding I/O * requests for an rport. + * @rport_delete: Callback function that deletes an rport. + * + * Fields that are only relevant for SRP target drivers: + * @tsk_mgmt_response: Callback function for sending a task management response. + * @it_nexus_response: Callback function for processing an IT nexus response. */ struct srp_function_template { /* for initiator drivers */ @@ -101,9 +123,11 @@ extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, extern int srp_reconnect_rport(struct srp_rport *rport); extern void srp_start_tl_fail_timers(struct srp_rport *rport); extern void srp_remove_host(struct Scsi_Host *); +extern void srp_stop_rport_timers(struct srp_rport *rport); /** * srp_chkready() - evaluate the transport layer state before I/O + * @rport: SRP target port pointer. * * Returns a SCSI result code that can be returned by the LLD queuecommand() * implementation. The role of this function is similar to that of |