From a3f5adaf491490089215f863a61b9422fae902f8 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 27 Sep 2010 17:51:10 -0700 Subject: IB/core: Add link layer property to ports This patch allows ports to have different link layers: IB_LINK_LAYER_INFINIBAND or IB_LINK_LAYER_ETHERNET. This is required for adding IBoE (InfiniBand-over-Ethernet, aka RoCE) support. For devices that do not provide an implementation for querying the link layer property of a port, we return a default value based on the transport: RMA_TRANSPORT_IB nodes will return IB_LINK_LAYER_INFINIBAND and RDMA_TRANSPORT_IWARP nodes will return IB_LINK_LAYER_ETHERNET. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- include/rdma/ib_verbs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 857b3b9cf120..e04c4888d1fd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -75,6 +75,12 @@ enum rdma_transport_type { enum rdma_transport_type rdma_node_get_transport(enum rdma_node_type node_type) __attribute_const__; +enum rdma_link_layer { + IB_LINK_LAYER_UNSPECIFIED, + IB_LINK_LAYER_INFINIBAND, + IB_LINK_LAYER_ETHERNET, +}; + enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = 1, IB_DEVICE_BAD_PKEY_CNTR = (1<<1), @@ -1010,6 +1016,8 @@ struct ib_device { int (*query_port)(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); + enum rdma_link_layer (*get_link_layer)(struct ib_device *device, + u8 port_num); int (*query_gid)(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); @@ -1222,6 +1230,9 @@ int ib_query_device(struct ib_device *device, int ib_query_port(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); +enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, + u8 port_num); + int ib_query_gid(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); -- cgit v1.3-14-g43fede From 5a0fd09428e47fb08d5a887515d92bb2447f4b65 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 7 Oct 2010 16:24:16 +0200 Subject: IB/mlx4: Limit size of fast registration WRs Fix the limit on the size of max fast registration WRs that can be posted to match hardware capabilities. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mlx4/mr.c | 2 +- include/linux/mlx4/device.h | 4 ++++ 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 4e94e360e43b..62e8cd6f0371 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -135,7 +135,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_srq = dev->dev->caps.num_srqs - dev->dev->caps.reserved_srqs; props->max_srq_wr = dev->dev->caps.max_srq_wqes - 1; props->max_srq_sge = dev->dev->caps.max_srq_sge; - props->max_fast_reg_page_list_len = PAGE_SIZE / sizeof (u64); + props->max_fast_reg_page_list_len = MLX4_MAX_FAST_REG_PAGES; props->local_ca_ack_delay = dev->dev->caps.local_ca_ack_delay; props->atomic_cap = dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_ATOMIC ? IB_ATOMIC_HCA : IB_ATOMIC_NONE; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 1d27b9a8e2d6..dca55b19a6f1 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -226,7 +226,7 @@ struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device struct mlx4_ib_fast_reg_page_list *mfrpl; int size = page_list_len * sizeof (u64); - if (size > PAGE_SIZE) + if (page_list_len > MLX4_MAX_FAST_REG_PAGES) return ERR_PTR(-EINVAL); mfrpl = kmalloc(sizeof *mfrpl, GFP_KERNEL); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7a7f9c1e679a..ada69389fb91 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -171,6 +171,10 @@ enum { MLX4_NUM_FEXCH = 64 * 1024, }; +enum { + MLX4_MAX_FAST_REG_PAGES = 511, +}; + static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor) { return (major << 32) | (minor << 16) | subminor; -- cgit v1.3-14-g43fede From 3c86aa70bf677a31b71c8292e349242e26cbc743 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 13 Oct 2010 21:26:51 +0200 Subject: RDMA/cm: Add RDMA CM support for IBoE devices Add support for IBoE device binding and IP --> GID resolution. Path resolving and multicast joining are implemented within cma.c by filling in the responses and running callbacks in the CMA work queue. IP --> GID resolution always yields IPv6 link local addresses; remote GIDs are derived from the destination MAC address of the remote port. Multicast GIDs are always mapped to multicast MACs as is done in IPv6. (IPv4 multicast is enabled by translating IPv4 multicast addresses to IPv6 multicast as described in .) Some helper functions are added to ib_addr.h. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/infiniband/core/cma.c | 309 ++++++++++++++++++++++++++++++++++--- drivers/infiniband/core/sa_query.c | 5 +- drivers/infiniband/core/ucma.c | 45 +++++- include/rdma/ib_addr.h | 99 +++++++++++- 4 files changed, 431 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index b930b8110a63..f61bc0738488 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -59,6 +59,7 @@ MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) +#define CMA_IBOE_PACKET_LIFETIME 18 static void cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device); @@ -157,6 +158,7 @@ struct cma_multicast { struct list_head list; void *context; struct sockaddr_storage addr; + struct kref mcref; }; struct cma_work { @@ -173,6 +175,12 @@ struct cma_ndev_work { struct rdma_cm_event event; }; +struct iboe_mcast_work { + struct work_struct work; + struct rdma_id_private *id; + struct cma_multicast *mc; +}; + union cma_ip_addr { struct in6_addr ip6; struct { @@ -281,6 +289,8 @@ static void cma_attach_to_dev(struct rdma_id_private *id_priv, atomic_inc(&cma_dev->refcount); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; + id_priv->id.route.addr.dev_addr.transport = + rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->list, &cma_dev->id_list); } @@ -290,6 +300,14 @@ static inline void cma_deref_dev(struct cma_device *cma_dev) complete(&cma_dev->comp); } +static inline void release_mc(struct kref *kref) +{ + struct cma_multicast *mc = container_of(kref, struct cma_multicast, mcref); + + kfree(mc->multicast.ib); + kfree(mc); +} + static void cma_detach_from_dev(struct rdma_id_private *id_priv) { list_del(&id_priv->list); @@ -323,22 +341,63 @@ static int cma_set_qkey(struct rdma_id_private *id_priv) return ret; } +static int find_gid_port(struct ib_device *device, union ib_gid *gid, u8 port_num) +{ + int i; + int err; + struct ib_port_attr props; + union ib_gid tmp; + + err = ib_query_port(device, port_num, &props); + if (err) + return 1; + + for (i = 0; i < props.gid_tbl_len; ++i) { + err = ib_query_gid(device, port_num, i, &tmp); + if (err) + return 1; + if (!memcmp(&tmp, gid, sizeof tmp)) + return 0; + } + + return -EAGAIN; +} + static int cma_acquire_dev(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct cma_device *cma_dev; - union ib_gid gid; + union ib_gid gid, iboe_gid; int ret = -ENODEV; + u8 port; + enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ? + IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET; - rdma_addr_get_sgid(dev_addr, &gid); + iboe_addr_get_sgid(dev_addr, &iboe_gid); + memcpy(&gid, dev_addr->src_dev_addr + + rdma_addr_gid_offset(dev_addr), sizeof gid); list_for_each_entry(cma_dev, &dev_list, list) { - ret = ib_find_cached_gid(cma_dev->device, &gid, - &id_priv->id.port_num, NULL); - if (!ret) { - cma_attach_to_dev(id_priv, cma_dev); - break; + for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) { + if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) { + if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB && + rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET) + ret = find_gid_port(cma_dev->device, &iboe_gid, port); + else + ret = find_gid_port(cma_dev->device, &gid, port); + + if (!ret) { + id_priv->id.port_num = port; + goto out; + } else if (ret == 1) + break; + } } } + +out: + if (!ret) + cma_attach_to_dev(id_priv, cma_dev); + return ret; } @@ -556,10 +615,16 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; + u16 pkey; + + if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) == + IB_LINK_LAYER_INFINIBAND) + pkey = ib_addr_get_pkey(dev_addr); + else + pkey = 0xffff; ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, - ib_addr_get_pkey(dev_addr), - &qp_attr->pkey_index); + pkey, &qp_attr->pkey_index); if (ret) return ret; @@ -737,8 +802,8 @@ static inline int cma_user_data_offset(enum rdma_port_space ps) static void cma_cancel_route(struct rdma_id_private *id_priv) { - switch (rdma_node_get_transport(id_priv->id.device->node_type)) { - case RDMA_TRANSPORT_IB: + switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) { + case IB_LINK_LAYER_INFINIBAND: if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); break; @@ -816,8 +881,17 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv) mc = container_of(id_priv->mc_list.next, struct cma_multicast, list); list_del(&mc->list); - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); + switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ib_sa_free_multicast(mc->multicast.ib); + kfree(mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_put(&mc->mcref, release_mc); + break; + default: + break; + } } } @@ -833,7 +907,7 @@ void rdma_destroy_id(struct rdma_cm_id *id) mutex_lock(&lock); if (id_priv->cma_dev) { mutex_unlock(&lock); - switch (rdma_node_get_transport(id->device->node_type)) { + switch (rdma_node_get_transport(id_priv->id.device->node_type)) { case RDMA_TRANSPORT_IB: if (id_priv->cm_id.ib && !IS_ERR(id_priv->cm_id.ib)) ib_destroy_cm_id(id_priv->cm_id.ib); @@ -1708,6 +1782,77 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms) return 0; } +static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) +{ + struct rdma_route *route = &id_priv->id.route; + struct rdma_addr *addr = &route->addr; + struct cma_work *work; + int ret; + struct sockaddr_in *src_addr = (struct sockaddr_in *)&route->addr.src_addr; + struct sockaddr_in *dst_addr = (struct sockaddr_in *)&route->addr.dst_addr; + struct net_device *ndev = NULL; + + if (src_addr->sin_family != dst_addr->sin_family) + return -EINVAL; + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + work->id = id_priv; + INIT_WORK(&work->work, cma_work_handler); + + route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); + if (!route->path_rec) { + ret = -ENOMEM; + goto err1; + } + + route->num_paths = 1; + + iboe_mac_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr); + iboe_mac_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr); + + route->path_rec->hop_limit = 1; + route->path_rec->reversible = 1; + route->path_rec->pkey = cpu_to_be16(0xffff); + route->path_rec->mtu_selector = IB_SA_EQ; + + if (addr->dev_addr.bound_dev_if) + ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); + if (!ndev) { + ret = -ENODEV; + goto err2; + } + + route->path_rec->mtu = iboe_get_mtu(ndev->mtu); + route->path_rec->rate_selector = IB_SA_EQ; + route->path_rec->rate = iboe_get_rate(ndev); + dev_put(ndev); + route->path_rec->packet_life_time_selector = IB_SA_EQ; + route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; + if (!route->path_rec->mtu) { + ret = -EINVAL; + goto err2; + } + + work->old_state = CMA_ROUTE_QUERY; + work->new_state = CMA_ROUTE_RESOLVED; + work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; + work->event.status = 0; + + queue_work(cma_wq, &work->work); + + return 0; + +err2: + kfree(route->path_rec); + route->path_rec = NULL; +err1: + kfree(work); + return ret; +} + int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms) { struct rdma_id_private *id_priv; @@ -1720,7 +1865,16 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms) atomic_inc(&id_priv->refcount); switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = cma_resolve_ib_route(id_priv, timeout_ms); + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ret = cma_resolve_ib_route(id_priv, timeout_ms); + break; + case IB_LINK_LAYER_ETHERNET: + ret = cma_resolve_iboe_route(id_priv); + break; + default: + ret = -ENOSYS; + } break; case RDMA_TRANSPORT_IWARP: ret = cma_resolve_iw_route(id_priv, timeout_ms); @@ -1773,7 +1927,7 @@ port_found: goto out; id_priv->id.route.addr.dev_addr.dev_type = - (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB) ? + (rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); @@ -2758,6 +2912,102 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, return 0; } +static void iboe_mcast_work_handler(struct work_struct *work) +{ + struct iboe_mcast_work *mw = container_of(work, struct iboe_mcast_work, work); + struct cma_multicast *mc = mw->mc; + struct ib_sa_multicast *m = mc->multicast.ib; + + mc->multicast.ib->context = mc; + cma_ib_mc_handler(0, m); + kref_put(&mc->mcref, release_mc); + kfree(mw); +} + +static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)addr; + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; + + if (cma_any_addr(addr)) { + memset(mgid, 0, sizeof *mgid); + } else if (addr->sa_family == AF_INET6) { + memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); + } else { + mgid->raw[0] = 0xff; + mgid->raw[1] = 0x0e; + mgid->raw[2] = 0; + mgid->raw[3] = 0; + mgid->raw[4] = 0; + mgid->raw[5] = 0; + mgid->raw[6] = 0; + mgid->raw[7] = 0; + mgid->raw[8] = 0; + mgid->raw[9] = 0; + mgid->raw[10] = 0xff; + mgid->raw[11] = 0xff; + *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; + } +} + +static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, + struct cma_multicast *mc) +{ + struct iboe_mcast_work *work; + struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; + int err; + struct sockaddr *addr = (struct sockaddr *)&mc->addr; + struct net_device *ndev = NULL; + + if (cma_zero_addr((struct sockaddr *)&mc->addr)) + return -EINVAL; + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + mc->multicast.ib = kzalloc(sizeof(struct ib_sa_multicast), GFP_KERNEL); + if (!mc->multicast.ib) { + err = -ENOMEM; + goto out1; + } + + cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid); + + mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff); + if (id_priv->id.ps == RDMA_PS_UDP) + mc->multicast.ib->rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); + + if (dev_addr->bound_dev_if) + ndev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); + if (!ndev) { + err = -ENODEV; + goto out2; + } + mc->multicast.ib->rec.rate = iboe_get_rate(ndev); + mc->multicast.ib->rec.hop_limit = 1; + mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu); + dev_put(ndev); + if (!mc->multicast.ib->rec.mtu) { + err = -EINVAL; + goto out2; + } + iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid); + work->id = id_priv; + work->mc = mc; + INIT_WORK(&work->work, iboe_mcast_work_handler); + kref_get(&mc->mcref); + queue_work(cma_wq, &work->work); + + return 0; + +out2: + kfree(mc->multicast.ib); +out1: + kfree(work); + return err; +} + int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, void *context) { @@ -2784,7 +3034,17 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = cma_join_ib_multicast(id_priv, mc); + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ret = cma_join_ib_multicast(id_priv, mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_init(&mc->mcref); + ret = cma_iboe_join_multicast(id_priv, mc); + break; + default: + ret = -EINVAL; + } break; default: ret = -ENOSYS; @@ -2817,8 +3077,19 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) ib_detach_mcast(id->qp, &mc->multicast.ib->rec.mgid, mc->multicast.ib->rec.mlid); - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); + if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) { + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ib_sa_free_multicast(mc->multicast.ib); + kfree(mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_put(&mc->mcref, release_mc); + break; + default: + break; + } + } return; } } diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 27674c790a73..91a660310b7c 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -496,6 +496,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, { int ret; u16 gid_index; + int force_grh; memset(ah_attr, 0, sizeof *ah_attr); ah_attr->dlid = be16_to_cpu(rec->dlid); @@ -505,7 +506,9 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, ah_attr->port_num = port_num; ah_attr->static_rate = rec->rate; - if (rec->hop_limit > 1) { + force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET; + + if (rec->hop_limit > 1 || force_grh) { ah_attr->ah_flags = IB_AH_GRH; ah_attr->grh.dgid = rec->dgid; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ac7edc24165c..3d3c9264c450 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -583,6 +583,34 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp, } } +static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, + struct rdma_route *route) +{ + struct rdma_dev_addr *dev_addr; + + resp->num_paths = route->num_paths; + switch (route->num_paths) { + case 0: + dev_addr = &route->addr.dev_addr; + iboe_mac_to_ll((union ib_gid *) &resp->ib_route[0].dgid, + dev_addr->dst_dev_addr); + iboe_addr_get_sgid(dev_addr, + (union ib_gid *) &resp->ib_route[0].sgid); + resp->ib_route[0].pkey = cpu_to_be16(0xffff); + break; + case 2: + ib_copy_path_rec_to_user(&resp->ib_route[1], + &route->path_rec[1]); + /* fall through */ + case 1: + ib_copy_path_rec_to_user(&resp->ib_route[0], + &route->path_rec[0]); + break; + default: + break; + } +} + static ssize_t ucma_query_route(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) @@ -617,12 +645,17 @@ static ssize_t ucma_query_route(struct ucma_file *file, resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid; resp.port_num = ctx->cm_id->port_num; - switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) { - case RDMA_TRANSPORT_IB: - ucma_copy_ib_route(&resp, &ctx->cm_id->route); - break; - default: - break; + if (rdma_node_get_transport(ctx->cm_id->device->node_type) == RDMA_TRANSPORT_IB) { + switch (rdma_port_get_link_layer(ctx->cm_id->device, ctx->cm_id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ucma_copy_ib_route(&resp, &ctx->cm_id->route); + break; + case IB_LINK_LAYER_ETHERNET: + ucma_copy_iboe_route(&resp, &ctx->cm_id->route); + break; + default: + break; + } } out: diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index fa0d52b8e622..904ffa92fc93 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -40,6 +40,7 @@ #include #include #include +#include struct rdma_addr_client { atomic_t refcount; @@ -63,6 +64,7 @@ struct rdma_dev_addr { unsigned char broadcast[MAX_ADDR_LEN]; unsigned short dev_type; int bound_dev_if; + enum rdma_transport_type transport; }; /** @@ -127,9 +129,31 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } +static inline void iboe_mac_to_ll(union ib_gid *gid, u8 *mac) +{ + memset(gid->raw, 0, 16); + *((__be32 *) gid->raw) = cpu_to_be32(0xfe800000); + gid->raw[12] = 0xfe; + gid->raw[11] = 0xff; + memcpy(gid->raw + 13, mac + 3, 3); + memcpy(gid->raw + 8, mac, 3); + gid->raw[8] ^= 2; +} + +static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr, + union ib_gid *gid) +{ + iboe_mac_to_ll(gid, dev_addr->src_dev_addr); +} + static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { - memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); + if (dev_addr->transport == RDMA_TRANSPORT_IB && + dev_addr->dev_type != ARPHRD_INFINIBAND) + iboe_addr_get_sgid(dev_addr, gid); + else + memcpy(gid, dev_addr->src_dev_addr + + rdma_addr_gid_offset(dev_addr), sizeof *gid); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) @@ -147,4 +171,77 @@ static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_g memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } +static inline enum ib_mtu iboe_get_mtu(int mtu) +{ + /* + * reduce IB headers from effective IBoE MTU. 28 stands for + * atomic header which is the biggest possible header after BTH + */ + mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28; + + if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) + return IB_MTU_4096; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) + return IB_MTU_2048; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) + return IB_MTU_1024; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) + return IB_MTU_512; + else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) + return IB_MTU_256; + else + return 0; +} + +static inline int iboe_get_rate(struct net_device *dev) +{ + struct ethtool_cmd cmd; + + if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings || + dev->ethtool_ops->get_settings(dev, &cmd)) + return IB_RATE_PORT_CURRENT; + + if (cmd.speed >= 40000) + return IB_RATE_40_GBPS; + else if (cmd.speed >= 30000) + return IB_RATE_30_GBPS; + else if (cmd.speed >= 20000) + return IB_RATE_20_GBPS; + else if (cmd.speed >= 10000) + return IB_RATE_10_GBPS; + else + return IB_RATE_PORT_CURRENT; +} + +static inline int rdma_link_local_addr(struct in6_addr *addr) +{ + if (addr->s6_addr32[0] == htonl(0xfe800000) && + addr->s6_addr32[1] == 0) + return 1; + + return 0; +} + +static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) +{ + memcpy(mac, &addr->s6_addr[8], 3); + memcpy(mac + 3, &addr->s6_addr[13], 3); + mac[0] ^= 2; +} + +static inline int rdma_is_multicast_addr(struct in6_addr *addr) +{ + return addr->s6_addr[0] == 0xff; +} + +static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) +{ + int i; + + mac[0] = 0x33; + mac[1] = 0x33; + for (i = 2; i < 6; ++i) + mac[i] = addr->s6_addr[i + 10]; +} + #endif /* IB_ADDR_H */ -- cgit v1.3-14-g43fede From ff7f5aab354dee01f29c9c00933f6d4aa590eadb Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 26 Aug 2010 14:17:56 +0000 Subject: IB/pack: IBoE UD packet packing support Add support for packing IBoE packet headers. Signed-off-by: Eli Cohen [ Clean up and fix ib_ud_header_init() a bit. - Roland ] Signed-off-by: Roland Dreier --- drivers/infiniband/core/ud_header.c | 117 +++++++++++++++++++++++++-------- drivers/infiniband/hw/mlx4/qp.c | 2 +- drivers/infiniband/hw/mthca/mthca_qp.c | 2 +- include/rdma/ib_pack.h | 30 ++++++--- 4 files changed, 113 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c index 650b501eb142..cb0dd5ae2777 100644 --- a/drivers/infiniband/core/ud_header.c +++ b/drivers/infiniband/core/ud_header.c @@ -80,6 +80,29 @@ static const struct ib_field lrh_table[] = { .size_bits = 16 } }; +static const struct ib_field eth_table[] = { + { STRUCT_FIELD(eth, dmac_h), + .offset_words = 0, + .offset_bits = 0, + .size_bits = 32 }, + { STRUCT_FIELD(eth, dmac_l), + .offset_words = 1, + .offset_bits = 0, + .size_bits = 16 }, + { STRUCT_FIELD(eth, smac_h), + .offset_words = 1, + .offset_bits = 16, + .size_bits = 16 }, + { STRUCT_FIELD(eth, smac_l), + .offset_words = 2, + .offset_bits = 0, + .size_bits = 32 }, + { STRUCT_FIELD(eth, type), + .offset_words = 3, + .offset_bits = 0, + .size_bits = 16 } +}; + static const struct ib_field grh_table[] = { { STRUCT_FIELD(grh, ip_version), .offset_words = 0, @@ -180,38 +203,38 @@ static const struct ib_field deth_table[] = { /** * ib_ud_header_init - Initialize UD header structure * @payload_bytes:Length of packet payload + * @lrh_present: specify if LRH is present + * @eth_present: specify if Eth header is present * @grh_present:GRH flag (if non-zero, GRH will be included) - * @immediate_present: specify if immediate data should be used + * @immediate_present: specify if immediate data is present * @header:Structure to initialize - * - * ib_ud_header_init() initializes the lrh.link_version, lrh.link_next_header, - * lrh.packet_length, grh.ip_version, grh.payload_length, - * grh.next_header, bth.opcode, bth.pad_count and - * bth.transport_header_version fields of a &struct ib_ud_header given - * the payload length and whether a GRH will be included. */ void ib_ud_header_init(int payload_bytes, + int lrh_present, + int eth_present, int grh_present, int immediate_present, struct ib_ud_header *header) { - u16 packet_length; - memset(header, 0, sizeof *header); - header->lrh.link_version = 0; - header->lrh.link_next_header = - grh_present ? IB_LNH_IBA_GLOBAL : IB_LNH_IBA_LOCAL; - packet_length = (IB_LRH_BYTES + - IB_BTH_BYTES + - IB_DETH_BYTES + - payload_bytes + - 4 + /* ICRC */ - 3) / 4; /* round up */ - - header->grh_present = grh_present; + if (lrh_present) { + u16 packet_length; + + header->lrh.link_version = 0; + header->lrh.link_next_header = + grh_present ? IB_LNH_IBA_GLOBAL : IB_LNH_IBA_LOCAL; + packet_length = (IB_LRH_BYTES + + IB_BTH_BYTES + + IB_DETH_BYTES + + (grh_present ? IB_GRH_BYTES : 0) + + payload_bytes + + 4 + /* ICRC */ + 3) / 4; /* round up */ + header->lrh.packet_length = cpu_to_be16(packet_length); + } + if (grh_present) { - packet_length += IB_GRH_BYTES / 4; header->grh.ip_version = 6; header->grh.payload_length = cpu_to_be16((IB_BTH_BYTES + @@ -222,18 +245,50 @@ void ib_ud_header_init(int payload_bytes, header->grh.next_header = 0x1b; } - header->lrh.packet_length = cpu_to_be16(packet_length); - - header->immediate_present = immediate_present; if (immediate_present) header->bth.opcode = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE; else header->bth.opcode = IB_OPCODE_UD_SEND_ONLY; header->bth.pad_count = (4 - payload_bytes) & 3; header->bth.transport_header_version = 0; + + header->lrh_present = lrh_present; + header->eth_present = eth_present; + header->grh_present = grh_present; + header->immediate_present = immediate_present; } EXPORT_SYMBOL(ib_ud_header_init); +/** + * ib_lrh_header_pack - Pack LRH header struct into wire format + * @lrh:unpacked LRH header struct + * @buf:Buffer to pack into + * + * ib_lrh_header_pack() packs the LRH header structure @lrh into + * wire format in the buffer @buf. + */ +int ib_lrh_header_pack(struct ib_unpacked_lrh *lrh, void *buf) +{ + ib_pack(lrh_table, ARRAY_SIZE(lrh_table), lrh, buf); + return 0; +} +EXPORT_SYMBOL(ib_lrh_header_pack); + +/** + * ib_lrh_header_unpack - Unpack LRH structure from wire format + * @lrh:unpacked LRH header struct + * @buf:Buffer to pack into + * + * ib_lrh_header_unpack() unpacks the LRH header structure from + * wire format (in buf) into @lrh. + */ +int ib_lrh_header_unpack(void *buf, struct ib_unpacked_lrh *lrh) +{ + ib_unpack(lrh_table, ARRAY_SIZE(lrh_table), buf, lrh); + return 0; +} +EXPORT_SYMBOL(ib_lrh_header_unpack); + /** * ib_ud_header_pack - Pack UD header struct into wire format * @header:UD header struct @@ -247,10 +302,16 @@ int ib_ud_header_pack(struct ib_ud_header *header, { int len = 0; - ib_pack(lrh_table, ARRAY_SIZE(lrh_table), - &header->lrh, buf); - len += IB_LRH_BYTES; - + if (header->lrh_present) { + ib_pack(lrh_table, ARRAY_SIZE(lrh_table), + &header->lrh, buf + len); + len += IB_LRH_BYTES; + } + if (header->eth_present) { + ib_pack(eth_table, ARRAY_SIZE(eth_table), + &header->eth, buf + len); + len += IB_ETH_BYTES; + } if (header->grh_present) { ib_pack(grh_table, ARRAY_SIZE(grh_table), &header->grh, buf + len); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 6a60827b2301..bb1277c8fbf0 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1231,7 +1231,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, for (i = 0; i < wr->num_sge; ++i) send_size += wr->sg_list[i].length; - ib_ud_header_init(send_size, mlx4_ib_ah_grh_present(ah), 0, &sqp->ud_header); + ib_ud_header_init(send_size, 1, 0, mlx4_ib_ah_grh_present(ah), 0, &sqp->ud_header); sqp->ud_header.lrh.service_level = be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28; diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c index d2d172e6289c..1a1c55fb13f3 100644 --- a/drivers/infiniband/hw/mthca/mthca_qp.c +++ b/drivers/infiniband/hw/mthca/mthca_qp.c @@ -1493,7 +1493,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp, int err; u16 pkey; - ib_ud_header_init(256, /* assume a MAD */ + ib_ud_header_init(256, /* assume a MAD */ 1, 0, mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), 0, &sqp->ud_header); diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index cbb50f4da3dd..6b91d8e7a1fa 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -37,6 +37,7 @@ enum { IB_LRH_BYTES = 8, + IB_ETH_BYTES = 14, IB_GRH_BYTES = 40, IB_BTH_BYTES = 12, IB_DETH_BYTES = 8 @@ -210,14 +211,25 @@ struct ib_unpacked_deth { __be32 source_qpn; }; +struct ib_unpacked_eth { + u8 dmac_h[4]; + u8 dmac_l[2]; + u8 smac_h[2]; + u8 smac_l[4]; + __be16 type; +}; + struct ib_ud_header { + int lrh_present; struct ib_unpacked_lrh lrh; - int grh_present; - struct ib_unpacked_grh grh; - struct ib_unpacked_bth bth; + int eth_present; + struct ib_unpacked_eth eth; + int grh_present; + struct ib_unpacked_grh grh; + struct ib_unpacked_bth bth; struct ib_unpacked_deth deth; - int immediate_present; - __be32 immediate_data; + int immediate_present; + __be32 immediate_data; }; void ib_pack(const struct ib_field *desc, @@ -230,9 +242,11 @@ void ib_unpack(const struct ib_field *desc, void *buf, void *structure); -void ib_ud_header_init(int payload_bytes, - int grh_present, - int immediate_present, +void ib_ud_header_init(int payload_bytes, + int lrh_present, + int eth_present, + int grh_present, + int immediate_present, struct ib_ud_header *header); int ib_ud_header_pack(struct ib_ud_header *header, -- cgit v1.3-14-g43fede From bb12588a38e6db85e01dceadff7bc161fc92e7d2 Mon Sep 17 00:00:00 2001 From: David Dillow Date: Fri, 8 Oct 2010 14:40:47 -0400 Subject: IB/srp: Implement SRP_CRED_REQ and SRP_AER_REQ This patch adds support for SRP_CRED_REQ to avoid a lockup by targets that use that mechanism to return credits to the initiator. This prevents a lockup observed in the field where we would never add the credits from the SRP_CRED_REQ to our current count, and would therefore never send another command to the target. Minimal support for SRP_AER_REQ is also added, as these messages can also be used to convey additional credits to the initiator. Based upon extensive debugging and code by Bart Van Assche and a bug report by Chris Worley. Signed-off-by: David Dillow Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/srp/ib_srp.c | 105 +++++++++++++++++++++++++++++++++--- drivers/infiniband/ulp/srp/ib_srp.h | 8 +-- include/scsi/srp.h | 38 +++++++++++++ 3 files changed, 141 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index b8b09a4f012a..a54eee9324b6 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -83,6 +83,10 @@ static void srp_remove_one(struct ib_device *device); static void srp_recv_completion(struct ib_cq *cq, void *target_ptr); static void srp_send_completion(struct ib_cq *cq, void *target_ptr); static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); +static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target, + enum srp_iu_type iu_type); +static int __srp_post_send(struct srp_target_port *target, + struct srp_iu *iu, int len); static struct scsi_transport_template *ib_srp_transport_template; @@ -896,6 +900,71 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp) spin_unlock_irqrestore(target->scsi_host->host_lock, flags); } +static int srp_response_common(struct srp_target_port *target, s32 req_delta, + void *rsp, int len) +{ + struct ib_device *dev; + unsigned long flags; + struct srp_iu *iu; + int err = 1; + + dev = target->srp_host->srp_dev->dev; + + spin_lock_irqsave(target->scsi_host->host_lock, flags); + target->req_lim += req_delta; + + iu = __srp_get_tx_iu(target, SRP_IU_RSP); + if (!iu) { + shost_printk(KERN_ERR, target->scsi_host, PFX + "no IU available to send response\n"); + goto out; + } + + ib_dma_sync_single_for_cpu(dev, iu->dma, len, DMA_TO_DEVICE); + memcpy(iu->buf, rsp, len); + ib_dma_sync_single_for_device(dev, iu->dma, len, DMA_TO_DEVICE); + + err = __srp_post_send(target, iu, len); + if (err) + shost_printk(KERN_ERR, target->scsi_host, PFX + "unable to post response: %d\n", err); + +out: + spin_unlock_irqrestore(target->scsi_host->host_lock, flags); + return err; +} + +static void srp_process_cred_req(struct srp_target_port *target, + struct srp_cred_req *req) +{ + struct srp_cred_rsp rsp = { + .opcode = SRP_CRED_RSP, + .tag = req->tag, + }; + s32 delta = be32_to_cpu(req->req_lim_delta); + + if (srp_response_common(target, delta, &rsp, sizeof rsp)) + shost_printk(KERN_ERR, target->scsi_host, PFX + "problems processing SRP_CRED_REQ\n"); +} + +static void srp_process_aer_req(struct srp_target_port *target, + struct srp_aer_req *req) +{ + struct srp_aer_rsp rsp = { + .opcode = SRP_AER_RSP, + .tag = req->tag, + }; + s32 delta = be32_to_cpu(req->req_lim_delta); + + shost_printk(KERN_ERR, target->scsi_host, PFX + "ignoring AER for LUN %llu\n", be64_to_cpu(req->lun)); + + if (srp_response_common(target, delta, &rsp, sizeof rsp)) + shost_printk(KERN_ERR, target->scsi_host, PFX + "problems processing SRP_AER_REQ\n"); +} + static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) { struct ib_device *dev; @@ -923,6 +992,14 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) srp_process_rsp(target, iu->buf); break; + case SRP_CRED_REQ: + srp_process_cred_req(target, iu->buf); + break; + + case SRP_AER_REQ: + srp_process_aer_req(target, iu->buf); + break; + case SRP_T_LOGOUT: /* XXX Handle target logout */ shost_printk(KERN_WARNING, target->scsi_host, @@ -985,23 +1062,36 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr) * Must be called with target->scsi_host->host_lock held to protect * req_lim and tx_head. Lock cannot be dropped between call here and * call to __srp_post_send(). + * + * Note: + * An upper limit for the number of allocated information units for each + * request type is: + * - SRP_IU_CMD: SRP_CMD_SQ_SIZE, since the SCSI mid-layer never queues + * more than Scsi_Host.can_queue requests. + * - SRP_IU_TSK_MGMT: SRP_TSK_MGMT_SQ_SIZE. + * - SRP_IU_RSP: 1, since a conforming SRP target never sends more than + * one unanswered SRP request to an initiator. */ static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target, - enum srp_request_type req_type) + enum srp_iu_type iu_type) { - s32 rsv = (req_type == SRP_REQ_TASK_MGMT) ? 0 : SRP_TSK_MGMT_SQ_SIZE; + s32 rsv = (iu_type == SRP_IU_TSK_MGMT) ? 0 : SRP_TSK_MGMT_SQ_SIZE; + struct srp_iu *iu; srp_send_completion(target->send_cq, target); if (target->tx_head - target->tx_tail >= SRP_SQ_SIZE) return NULL; - if (target->req_lim <= rsv) { + /* Initiator responses to target requests do not consume credits */ + if (target->req_lim <= rsv && iu_type != SRP_IU_RSP) { ++target->zero_req_lim; return NULL; } - return target->tx_ring[target->tx_head & SRP_SQ_MASK]; + iu = target->tx_ring[target->tx_head & SRP_SQ_MASK]; + iu->type = iu_type; + return iu; } /* @@ -1030,7 +1120,8 @@ static int __srp_post_send(struct srp_target_port *target, if (!ret) { ++target->tx_head; - --target->req_lim; + if (iu->type != SRP_IU_RSP) + --target->req_lim; } return ret; @@ -1056,7 +1147,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, return 0; } - iu = __srp_get_tx_iu(target, SRP_REQ_NORMAL); + iu = __srp_get_tx_iu(target, SRP_IU_CMD); if (!iu) goto err; @@ -1363,7 +1454,7 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target, init_completion(&req->done); - iu = __srp_get_tx_iu(target, SRP_REQ_TASK_MGMT); + iu = __srp_get_tx_iu(target, SRP_IU_TSK_MGMT); if (!iu) goto out; diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 7a959d5f2fa6..ed0dce9e479f 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -82,9 +82,10 @@ enum srp_target_state { SRP_TARGET_REMOVED }; -enum srp_request_type { - SRP_REQ_NORMAL, - SRP_REQ_TASK_MGMT, +enum srp_iu_type { + SRP_IU_CMD, + SRP_IU_TSK_MGMT, + SRP_IU_RSP, }; struct srp_device { @@ -171,6 +172,7 @@ struct srp_iu { void *buf; size_t size; enum dma_data_direction direction; + enum srp_iu_type type; }; #endif /* IB_SRP_H */ diff --git a/include/scsi/srp.h b/include/scsi/srp.h index ad178fa78f66..1ae84db4c9fb 100644 --- a/include/scsi/srp.h +++ b/include/scsi/srp.h @@ -239,4 +239,42 @@ struct srp_rsp { u8 data[0]; } __attribute__((packed)); +struct srp_cred_req { + u8 opcode; + u8 sol_not; + u8 reserved[2]; + __be32 req_lim_delta; + u64 tag; +}; + +struct srp_cred_rsp { + u8 opcode; + u8 reserved[7]; + u64 tag; +}; + +/* + * The SRP spec defines the fixed portion of the AER_REQ structure to be + * 36 bytes, so it needs to be packed to avoid having it padded to 40 bytes + * on 64-bit architectures. + */ +struct srp_aer_req { + u8 opcode; + u8 sol_not; + u8 reserved[2]; + __be32 req_lim_delta; + u64 tag; + u32 reserved2; + __be64 lun; + __be32 sense_data_len; + u32 reserved3; + u8 sense_data[0]; +} __attribute__((packed)); + +struct srp_aer_rsp { + u8 opcode; + u8 reserved[7]; + u64 tag; +}; + #endif /* SCSI_SRP_H */ -- cgit v1.3-14-g43fede From d0d68b8693bd16bfbbc93b89f1d9f3351723307c Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 4 Oct 2010 12:11:34 +0000 Subject: IB/mlx4: Signal node desc changes to SM by using FW to generate trap 144 The Node Description cannot be changed via MADs (it is read-only). Until now, it was changed in the driver via sysfs, and the new Node Description was simply inserted by the driver into MAD responses (replacing the description returned by FW). System startup scripts use the sysfs interface to change the node description at driver startup to show the hostname, etc. However, this has a race condition: the SM could discover the original FW node description rather than the system-specific description if it queried the port before the startup scripts finish running. For mlx4, we fix this with a new FW command (SET_NODE) that allows passing the new node description to FW. When this command is invoked, FW sends a trap 144 to the SM. When it gets this trap, the SM can query the node to obtain the new node description -- thus eliminating the effects of the race. This patch simply calls SET_NODE command when a new node description is entered via sysfs (thus causing trap 144 to be issued by the FW). We ignore all failures of the SET_NODE command (including those caused by using a device FW that predates the SET_NODE command), since in that case things work just as before. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 28 +++++++++++++++++++++++----- include/linux/mlx4/cmd.h | 1 + 2 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 62e8cd6f0371..ac6951d99336 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -272,14 +272,32 @@ out: static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, struct ib_device_modify *props) { + struct mlx4_cmd_mailbox *mailbox; + if (mask & ~IB_DEVICE_MODIFY_NODE_DESC) return -EOPNOTSUPP; - if (mask & IB_DEVICE_MODIFY_NODE_DESC) { - spin_lock(&to_mdev(ibdev)->sm_lock); - memcpy(ibdev->node_desc, props->node_desc, 64); - spin_unlock(&to_mdev(ibdev)->sm_lock); - } + if (!(mask & IB_DEVICE_MODIFY_NODE_DESC)) + return 0; + + spin_lock(&to_mdev(ibdev)->sm_lock); + memcpy(ibdev->node_desc, props->node_desc, 64); + spin_unlock(&to_mdev(ibdev)->sm_lock); + + /* + * If possible, pass node desc to FW, so it can generate + * a 144 trap. If cmd fails, just ignore. + */ + mailbox = mlx4_alloc_cmd_mailbox(to_mdev(ibdev)->dev); + if (IS_ERR(mailbox)) + return 0; + + memset(mailbox->buf, 0, 256); + memcpy(mailbox->buf, props->node_desc, 64); + mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0, + MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A); + + mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox); return 0; } diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 0f82293a82ed..2731266e73a7 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -57,6 +57,7 @@ enum { MLX4_CMD_QUERY_PORT = 0x43, MLX4_CMD_SENSE_PORT = 0x4d, MLX4_CMD_SET_PORT = 0xc, + MLX4_CMD_SET_NODE = 0x5a, MLX4_CMD_ACCESS_DDR = 0x2e, MLX4_CMD_MAP_ICM = 0xffa, MLX4_CMD_UNMAP_ICM = 0xff9, -- cgit v1.3-14-g43fede From 2420b60b1dc4ed98cb1788e928bc57ff2efa1a8d Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 18 Oct 2010 14:45:20 -0700 Subject: IB/uverbs: Return link layer type to userspace for query port operation Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/infiniband/core/uverbs_cmd.c | 2 ++ include/rdma/ib_user_verbs.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 6fcfbeb24a23..b342248aec05 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -460,6 +460,8 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file, resp.active_width = attr.active_width; resp.active_speed = attr.active_speed; resp.phys_state = attr.phys_state; + resp.link_layer = rdma_port_get_link_layer(file->device->ib_dev, + cmd.port_num); if (copy_to_user((void __user *) (unsigned long) cmd.response, &resp, sizeof resp)) diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h index a17f77106149..fe5b05177a2c 100644 --- a/include/rdma/ib_user_verbs.h +++ b/include/rdma/ib_user_verbs.h @@ -205,7 +205,8 @@ struct ib_uverbs_query_port_resp { __u8 active_width; __u8 active_speed; __u8 phys_state; - __u8 reserved[3]; + __u8 link_layer; + __u8 reserved[2]; }; struct ib_uverbs_alloc_pd { -- cgit v1.3-14-g43fede From 33c87f0af60146b375220809c1cb745ac1a86edf Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 26 Aug 2010 14:18:43 +0000 Subject: mlx4_core: Allow protocol drivers to find corresponding interfaces Add a mechanism for mlx4 protocol drivers to get a pointer to other drivers's device objects. For this, an exported function, mlx4_get_protocol_dev() is added, which allows a driver to get some other driver's device based on the protocol that the driver implements. Two protocols are added: MLX4_PROTOCOL_IB and MLX4_PROTOCOL_EN. This will be used in mlx4 IBoE support so that mlx4_ib can find the corresponding mlx4_en netdev. Signed-off-by: Eli Cohen [ Clean up and rename a few things. - Roland ] Signed-off-by: Roland Dreier --- drivers/net/mlx4/en_main.c | 15 ++++++++++++--- drivers/net/mlx4/intf.c | 21 +++++++++++++++++++++ include/linux/mlx4/driver.h | 9 +++++++++ 3 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/mlx4/en_main.c b/drivers/net/mlx4/en_main.c index 97934f1ec53a..b2df3eeb1598 100644 --- a/drivers/net/mlx4/en_main.c +++ b/drivers/net/mlx4/en_main.c @@ -124,6 +124,13 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev) return 0; } +static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port) +{ + struct mlx4_en_dev *endev = ctx; + + return endev->pndev[port]; +} + static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, enum mlx4_dev_event event, int port) { @@ -282,9 +289,11 @@ err_free_res: } static struct mlx4_interface mlx4_en_interface = { - .add = mlx4_en_add, - .remove = mlx4_en_remove, - .event = mlx4_en_event, + .add = mlx4_en_add, + .remove = mlx4_en_remove, + .event = mlx4_en_event, + .get_dev = mlx4_en_get_netdev, + .protocol = MLX4_PROTOCOL_EN, }; static int __init mlx4_en_init(void) diff --git a/drivers/net/mlx4/intf.c b/drivers/net/mlx4/intf.c index 555067802751..73c94fcdfddf 100644 --- a/drivers/net/mlx4/intf.c +++ b/drivers/net/mlx4/intf.c @@ -161,3 +161,24 @@ void mlx4_unregister_device(struct mlx4_dev *dev) mutex_unlock(&intf_mutex); } + +void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_device_context *dev_ctx; + unsigned long flags; + void *result = NULL; + + spin_lock_irqsave(&priv->ctx_lock, flags); + + list_for_each_entry(dev_ctx, &priv->ctx_list, list) + if (dev_ctx->intf->protocol == proto && dev_ctx->intf->get_dev) { + result = dev_ctx->intf->get_dev(dev, dev_ctx->context, port); + break; + } + + spin_unlock_irqrestore(&priv->ctx_lock, flags); + + return result; +} +EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 53c5fdb6eac4..f407cd4bfb34 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -44,15 +44,24 @@ enum mlx4_dev_event { MLX4_DEV_EVENT_PORT_REINIT, }; +enum mlx4_protocol { + MLX4_PROTOCOL_IB, + MLX4_PROTOCOL_EN, +}; + struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); void (*event) (struct mlx4_dev *dev, void *context, enum mlx4_dev_event event, int port); + void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); struct list_head list; + enum mlx4_protocol protocol; }; int mlx4_register_interface(struct mlx4_interface *intf); void mlx4_unregister_interface(struct mlx4_interface *intf); +void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); + #endif /* MLX4_DRIVER_H */ -- cgit v1.3-14-g43fede From 96dfa684c85d24b697f865f37a4f0c8678fc86e9 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 20 Oct 2010 21:57:02 -0700 Subject: mlx4_core: Update data structures and constants for IBoE Add fields to hardware data structures and add new constants required for IBoE support. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/net/mlx4/fw.c | 3 ++- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 3 ++- include/linux/mlx4/qp.h | 7 +++++-- 4 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c index 04f42ae1eda0..5b3593d3cd74 100644 --- a/drivers/net/mlx4/fw.c +++ b/drivers/net/mlx4/fw.c @@ -98,7 +98,8 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u32 flags) [20] = "Address vector port checking support", [21] = "UD multicast support", [24] = "Demand paging support", - [25] = "Router support" + [25] = "Router support", + [30] = "IBoE support" }; int i; diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 0f82293a82ed..22bd8d3b84a2 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -140,6 +140,7 @@ enum { MLX4_SET_PORT_MAC_TABLE = 0x2, MLX4_SET_PORT_VLAN_TABLE = 0x3, MLX4_SET_PORT_PRIO_MAP = 0x4, + MLX4_SET_PORT_GID_TABLE = 0x5, }; struct mlx4_dev; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7a7f9c1e679a..47e163ad3d11 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -67,7 +67,8 @@ enum { MLX4_DEV_CAP_FLAG_ATOMIC = 1 << 18, MLX4_DEV_CAP_FLAG_RAW_MCAST = 1 << 19, MLX4_DEV_CAP_FLAG_UD_AV_PORT = 1 << 20, - MLX4_DEV_CAP_FLAG_UD_MCAST = 1 << 21 + MLX4_DEV_CAP_FLAG_UD_MCAST = 1 << 21, + MLX4_DEV_CAP_FLAG_IBOE = 1 << 30 }; enum { diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 7abe64326f72..97cfdc8d7e2f 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -112,7 +112,8 @@ struct mlx4_qp_path { u8 snooper_flags; u8 reserved3[2]; u8 counter_index; - u8 reserved4[7]; + u8 reserved4; + u8 dmac[6]; }; struct mlx4_qp_context { @@ -166,6 +167,7 @@ enum { MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, MLX4_WQE_CTRL_INS_VLAN = 1 << 6, MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7, + MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; struct mlx4_wqe_ctrl_seg { @@ -219,7 +221,8 @@ struct mlx4_wqe_datagram_seg { __be32 av[8]; __be32 dqpn; __be32 qkey; - __be32 reservd[2]; + __be16 vlan; + u8 mac[6]; }; struct mlx4_wqe_lso_seg { -- cgit v1.3-14-g43fede From fa417f7b520ee60b39f7e23528d2030af30a07d1 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Sun, 24 Oct 2010 21:08:52 -0700 Subject: IB/mlx4: Add support for IBoE Add support for IBoE to mlx4_ib. The bulk of the code is handling the new address vector fields; mlx4 needs the MAC address of a remote node to include it in a WQE (for datagrams) or in the QP context (for connected QPs). Address resolution is done by assuming all unicast GIDs are either link-local IPv6 addresses. Multicast group attach/detach needs to update the NIC's multicast filters; but since attaching a QP to a multicast group can be done before the QP is bound to a port, for IBoE we need to keep track of all multicast groups that a QP is attached too before it transitions from INIT to RTR (since it does not have a port in the INIT state). Signed-off-by: Eli Cohen [ Many things cleaned up and otherwise monkeyed with; hope I didn't introduce too many bugs. - Roland ] Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/ah.c | 153 +++++++++--- drivers/infiniband/hw/mlx4/mad.c | 32 ++- drivers/infiniband/hw/mlx4/main.c | 448 ++++++++++++++++++++++++++++++++--- drivers/infiniband/hw/mlx4/mlx4_ib.h | 32 ++- drivers/infiniband/hw/mlx4/qp.c | 130 ++++++++-- include/linux/mlx4/device.h | 27 +++ 6 files changed, 714 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 11a236f8d884..3bf3544c0aa0 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -30,66 +30,153 @@ * SOFTWARE. */ +#include + #include +#include +#include #include "mlx4_ib.h" -struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr) +int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr, + u8 *mac, int *is_mcast, u8 port) { - struct mlx4_dev *dev = to_mdev(pd->device)->dev; - struct mlx4_ib_ah *ah; + struct in6_addr in6; - ah = kmalloc(sizeof *ah, GFP_ATOMIC); - if (!ah) - return ERR_PTR(-ENOMEM); + *is_mcast = 0; - memset(&ah->av, 0, sizeof ah->av); + memcpy(&in6, ah_attr->grh.dgid.raw, sizeof in6); + if (rdma_link_local_addr(&in6)) + rdma_get_ll_mac(&in6, mac); + else if (rdma_is_multicast_addr(&in6)) { + rdma_get_mcast_mac(&in6, mac); + *is_mcast = 1; + } else + return -EINVAL; - ah->av.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); - ah->av.g_slid = ah_attr->src_path_bits; - ah->av.dlid = cpu_to_be16(ah_attr->dlid); - if (ah_attr->static_rate) { - ah->av.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET; - while (ah->av.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET && - !(1 << ah->av.stat_rate & dev->caps.stat_rate_support)) - --ah->av.stat_rate; - } - ah->av.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); + return 0; +} + +static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, + struct mlx4_ib_ah *ah) +{ + struct mlx4_dev *dev = to_mdev(pd->device)->dev; + + ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); + ah->av.ib.g_slid = ah_attr->src_path_bits; if (ah_attr->ah_flags & IB_AH_GRH) { - ah->av.g_slid |= 0x80; - ah->av.gid_index = ah_attr->grh.sgid_index; - ah->av.hop_limit = ah_attr->grh.hop_limit; - ah->av.sl_tclass_flowlabel |= + ah->av.ib.g_slid |= 0x80; + ah->av.ib.gid_index = ah_attr->grh.sgid_index; + ah->av.ib.hop_limit = ah_attr->grh.hop_limit; + ah->av.ib.sl_tclass_flowlabel |= cpu_to_be32((ah_attr->grh.traffic_class << 20) | ah_attr->grh.flow_label); - memcpy(ah->av.dgid, ah_attr->grh.dgid.raw, 16); + memcpy(ah->av.ib.dgid, ah_attr->grh.dgid.raw, 16); + } + + ah->av.ib.dlid = cpu_to_be16(ah_attr->dlid); + if (ah_attr->static_rate) { + ah->av.ib.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET; + while (ah->av.ib.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET && + !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support)) + --ah->av.ib.stat_rate; } + ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); return &ah->ibah; } +static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, + struct mlx4_ib_ah *ah) +{ + struct mlx4_ib_dev *ibdev = to_mdev(pd->device); + struct mlx4_dev *dev = ibdev->dev; + u8 mac[6]; + int err; + int is_mcast; + + err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num); + if (err) + return ERR_PTR(err); + + memcpy(ah->av.eth.mac, mac, 6); + ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); + ah->av.eth.gid_index = ah_attr->grh.sgid_index; + if (ah_attr->static_rate) { + ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET; + while (ah->av.eth.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET && + !(1 << ah->av.eth.stat_rate & dev->caps.stat_rate_support)) + --ah->av.eth.stat_rate; + } + + /* + * HW requires multicast LID so we just choose one. + */ + if (is_mcast) + ah->av.ib.dlid = cpu_to_be16(0xc000); + + memcpy(ah->av.eth.dgid, ah_attr->grh.dgid.raw, 16); + ah->av.eth.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); + + return &ah->ibah; +} + +struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr) +{ + struct mlx4_ib_ah *ah; + struct ib_ah *ret; + + ah = kzalloc(sizeof *ah, GFP_ATOMIC); + if (!ah) + return ERR_PTR(-ENOMEM); + + if (rdma_port_get_link_layer(pd->device, ah_attr->port_num) == IB_LINK_LAYER_ETHERNET) { + if (!(ah_attr->ah_flags & IB_AH_GRH)) { + ret = ERR_PTR(-EINVAL); + } else { + /* + * TBD: need to handle the case when we get + * called in an atomic context and there we + * might sleep. We don't expect this + * currently since we're working with link + * local addresses which we can translate + * without going to sleep. + */ + ret = create_iboe_ah(pd, ah_attr, ah); + } + + if (IS_ERR(ret)) + kfree(ah); + + return ret; + } else + return create_ib_ah(pd, ah_attr, ah); /* never fails */ +} + int mlx4_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr) { struct mlx4_ib_ah *ah = to_mah(ibah); + enum rdma_link_layer ll; memset(ah_attr, 0, sizeof *ah_attr); - ah_attr->dlid = be16_to_cpu(ah->av.dlid); - ah_attr->sl = be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28; - ah_attr->port_num = be32_to_cpu(ah->av.port_pd) >> 24; - if (ah->av.stat_rate) - ah_attr->static_rate = ah->av.stat_rate - MLX4_STAT_RATE_OFFSET; - ah_attr->src_path_bits = ah->av.g_slid & 0x7F; + ah_attr->sl = be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28; + ah_attr->port_num = be32_to_cpu(ah->av.ib.port_pd) >> 24; + ll = rdma_port_get_link_layer(ibah->device, ah_attr->port_num); + ah_attr->dlid = ll == IB_LINK_LAYER_INFINIBAND ? be16_to_cpu(ah->av.ib.dlid) : 0; + if (ah->av.ib.stat_rate) + ah_attr->static_rate = ah->av.ib.stat_rate - MLX4_STAT_RATE_OFFSET; + ah_attr->src_path_bits = ah->av.ib.g_slid & 0x7F; if (mlx4_ib_ah_grh_present(ah)) { ah_attr->ah_flags = IB_AH_GRH; ah_attr->grh.traffic_class = - be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 20; + be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20; ah_attr->grh.flow_label = - be32_to_cpu(ah->av.sl_tclass_flowlabel) & 0xfffff; - ah_attr->grh.hop_limit = ah->av.hop_limit; - ah_attr->grh.sgid_index = ah->av.gid_index; - memcpy(ah_attr->grh.dgid.raw, ah->av.dgid, 16); + be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) & 0xfffff; + ah_attr->grh.hop_limit = ah->av.ib.hop_limit; + ah_attr->grh.sgid_index = ah->av.ib.gid_index; + memcpy(ah_attr->grh.dgid.raw, ah->av.ib.dgid, 16); } return 0; diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index f38d5b118927..c9a8dd63b9e2 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -311,19 +311,25 @@ int mlx4_ib_mad_init(struct mlx4_ib_dev *dev) struct ib_mad_agent *agent; int p, q; int ret; + enum rdma_link_layer ll; - for (p = 0; p < dev->num_ports; ++p) + for (p = 0; p < dev->num_ports; ++p) { + ll = rdma_port_get_link_layer(&dev->ib_dev, p + 1); for (q = 0; q <= 1; ++q) { - agent = ib_register_mad_agent(&dev->ib_dev, p + 1, - q ? IB_QPT_GSI : IB_QPT_SMI, - NULL, 0, send_handler, - NULL, NULL); - if (IS_ERR(agent)) { - ret = PTR_ERR(agent); - goto err; - } - dev->send_agent[p][q] = agent; + if (ll == IB_LINK_LAYER_INFINIBAND) { + agent = ib_register_mad_agent(&dev->ib_dev, p + 1, + q ? IB_QPT_GSI : IB_QPT_SMI, + NULL, 0, send_handler, + NULL, NULL); + if (IS_ERR(agent)) { + ret = PTR_ERR(agent); + goto err; + } + dev->send_agent[p][q] = agent; + } else + dev->send_agent[p][q] = NULL; } + } return 0; @@ -344,8 +350,10 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev) for (p = 0; p < dev->num_ports; ++p) { for (q = 0; q <= 1; ++q) { agent = dev->send_agent[p][q]; - dev->send_agent[p][q] = NULL; - ib_unregister_mad_agent(agent); + if (agent) { + dev->send_agent[p][q] = NULL; + ib_unregister_mad_agent(agent); + } } if (dev->sm_ah[p]) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 4e94e360e43b..e65db73fc277 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -35,9 +35,13 @@ #include #include #include +#include +#include +#include #include #include +#include #include #include @@ -58,6 +62,15 @@ static const char mlx4_ib_version[] = DRV_NAME ": Mellanox ConnectX InfiniBand driver v" DRV_VERSION " (" DRV_RELDATE ")\n"; +struct update_gid_work { + struct work_struct work; + union ib_gid gids[128]; + struct mlx4_ib_dev *dev; + int port; +}; + +static struct workqueue_struct *wq; + static void init_query_mad(struct ib_smp *mad) { mad->base_version = 1; @@ -154,28 +167,19 @@ out: return err; } -static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, - struct ib_port_attr *props) +static enum rdma_link_layer +mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num) { - struct ib_smp *in_mad = NULL; - struct ib_smp *out_mad = NULL; - int err = -ENOMEM; + struct mlx4_dev *dev = to_mdev(device)->dev; - in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); - out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); - if (!in_mad || !out_mad) - goto out; - - memset(props, 0, sizeof *props); - - init_query_mad(in_mad); - in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; - in_mad->attr_mod = cpu_to_be32(port); - - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad); - if (err) - goto out; + return dev->caps.port_mask & (1 << (port_num - 1)) ? + IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET; +} +static int ib_link_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props, + struct ib_smp *out_mad) +{ props->lid = be16_to_cpup((__be16 *) (out_mad->data + 16)); props->lmc = out_mad->data[34] & 0x7; props->sm_lid = be16_to_cpup((__be16 *) (out_mad->data + 18)); @@ -196,6 +200,80 @@ static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, props->max_vl_num = out_mad->data[37] >> 4; props->init_type_reply = out_mad->data[41] >> 4; + return 0; +} + +static u8 state_to_phys_state(enum ib_port_state state) +{ + return state == IB_PORT_ACTIVE ? 5 : 3; +} + +static int eth_link_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props, + struct ib_smp *out_mad) +{ + struct mlx4_ib_iboe *iboe = &to_mdev(ibdev)->iboe; + struct net_device *ndev; + enum ib_mtu tmp; + + props->active_width = IB_WIDTH_4X; + props->active_speed = 4; + props->port_cap_flags = IB_PORT_CM_SUP; + props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len[port]; + props->max_msg_sz = to_mdev(ibdev)->dev->caps.max_msg_sz; + props->pkey_tbl_len = 1; + props->bad_pkey_cntr = be16_to_cpup((__be16 *) (out_mad->data + 46)); + props->qkey_viol_cntr = be16_to_cpup((__be16 *) (out_mad->data + 48)); + props->max_mtu = IB_MTU_2048; + props->subnet_timeout = 0; + props->max_vl_num = out_mad->data[37] >> 4; + props->init_type_reply = 0; + props->state = IB_PORT_DOWN; + props->phys_state = state_to_phys_state(props->state); + props->active_mtu = IB_MTU_256; + spin_lock(&iboe->lock); + ndev = iboe->netdevs[port - 1]; + if (!ndev) + goto out; + + tmp = iboe_get_mtu(ndev->mtu); + props->active_mtu = tmp ? min(props->max_mtu, tmp) : IB_MTU_256; + + props->state = netif_running(ndev) && netif_oper_up(ndev) ? + IB_PORT_ACTIVE : IB_PORT_DOWN; + props->phys_state = state_to_phys_state(props->state); + +out: + spin_unlock(&iboe->lock); + return 0; +} + +static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props) +{ + struct ib_smp *in_mad = NULL; + struct ib_smp *out_mad = NULL; + int err = -ENOMEM; + + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); + out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); + if (!in_mad || !out_mad) + goto out; + + memset(props, 0, sizeof *props); + + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; + in_mad->attr_mod = cpu_to_be32(port); + + err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad); + if (err) + goto out; + + err = mlx4_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND ? + ib_link_query_port(ibdev, port, props, out_mad) : + eth_link_query_port(ibdev, port, props, out_mad); + out: kfree(in_mad); kfree(out_mad); @@ -203,8 +281,8 @@ out: return err; } -static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, - union ib_gid *gid) +static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, + union ib_gid *gid) { struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; @@ -241,6 +319,25 @@ out: return err; } +static int iboe_query_gid(struct ib_device *ibdev, u8 port, int index, + union ib_gid *gid) +{ + struct mlx4_ib_dev *dev = to_mdev(ibdev); + + *gid = dev->iboe.gid_table[port - 1][index]; + + return 0; +} + +static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, + union ib_gid *gid) +{ + if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND) + return __mlx4_ib_query_gid(ibdev, port, index, gid); + else + return iboe_query_gid(ibdev, port, index, gid); +} + static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) { @@ -289,6 +386,7 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols, { struct mlx4_cmd_mailbox *mailbox; int err; + u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH; mailbox = mlx4_alloc_cmd_mailbox(dev->dev); if (IS_ERR(mailbox)) @@ -304,7 +402,7 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols, ((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask); } - err = mlx4_cmd(dev->dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT, + err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B); mlx4_free_cmd_mailbox(dev->dev, mailbox); @@ -447,18 +545,132 @@ static int mlx4_ib_dealloc_pd(struct ib_pd *pd) return 0; } +static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid) +{ + struct mlx4_ib_qp *mqp = to_mqp(ibqp); + struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); + struct mlx4_ib_gid_entry *ge; + + ge = kzalloc(sizeof *ge, GFP_KERNEL); + if (!ge) + return -ENOMEM; + + ge->gid = *gid; + if (mlx4_ib_add_mc(mdev, mqp, gid)) { + ge->port = mqp->port; + ge->added = 1; + } + + mutex_lock(&mqp->mutex); + list_add_tail(&ge->list, &mqp->gid_list); + mutex_unlock(&mqp->mutex); + + return 0; +} + +int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, + union ib_gid *gid) +{ + u8 mac[6]; + struct net_device *ndev; + int ret = 0; + + if (!mqp->port) + return 0; + + spin_lock(&mdev->iboe.lock); + ndev = mdev->iboe.netdevs[mqp->port - 1]; + if (ndev) + dev_hold(ndev); + spin_unlock(&mdev->iboe.lock); + + if (ndev) { + rdma_get_mcast_mac((struct in6_addr *)gid, mac); + rtnl_lock(); + dev_mc_add(mdev->iboe.netdevs[mqp->port - 1], mac); + ret = 1; + rtnl_unlock(); + dev_put(ndev); + } + + return ret; +} + static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { - return mlx4_multicast_attach(to_mdev(ibqp->device)->dev, - &to_mqp(ibqp)->mqp, gid->raw, - !!(to_mqp(ibqp)->flags & - MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK)); + int err; + struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); + struct mlx4_ib_qp *mqp = to_mqp(ibqp); + + err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, !!(mqp->flags & + MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK)); + if (err) + return err; + + err = add_gid_entry(ibqp, gid); + if (err) + goto err_add; + + return 0; + +err_add: + mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw); + return err; +} + +static struct mlx4_ib_gid_entry *find_gid_entry(struct mlx4_ib_qp *qp, u8 *raw) +{ + struct mlx4_ib_gid_entry *ge; + struct mlx4_ib_gid_entry *tmp; + struct mlx4_ib_gid_entry *ret = NULL; + + list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) { + if (!memcmp(raw, ge->gid.raw, 16)) { + ret = ge; + break; + } + } + + return ret; } static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { - return mlx4_multicast_detach(to_mdev(ibqp->device)->dev, - &to_mqp(ibqp)->mqp, gid->raw); + int err; + struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); + struct mlx4_ib_qp *mqp = to_mqp(ibqp); + u8 mac[6]; + struct net_device *ndev; + struct mlx4_ib_gid_entry *ge; + + err = mlx4_multicast_detach(mdev->dev, + &mqp->mqp, gid->raw); + if (err) + return err; + + mutex_lock(&mqp->mutex); + ge = find_gid_entry(mqp, gid->raw); + if (ge) { + spin_lock(&mdev->iboe.lock); + ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL; + if (ndev) + dev_hold(ndev); + spin_unlock(&mdev->iboe.lock); + rdma_get_mcast_mac((struct in6_addr *)gid, mac); + if (ndev) { + rtnl_lock(); + dev_mc_del(mdev->iboe.netdevs[ge->port - 1], mac); + rtnl_unlock(); + dev_put(ndev); + } + list_del(&ge->list); + kfree(ge); + } else + printk(KERN_WARNING "could not find mgid entry\n"); + + mutex_unlock(&mqp->mutex); + + return 0; } static int init_node_data(struct mlx4_ib_dev *dev) @@ -543,15 +755,143 @@ static struct device_attribute *mlx4_class_attributes[] = { &dev_attr_board_id }; +static void mlx4_addrconf_ifid_eui48(u8 *eui, struct net_device *dev) +{ + memcpy(eui, dev->dev_addr, 3); + memcpy(eui + 5, dev->dev_addr + 3, 3); + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; +} + +static void update_gids_task(struct work_struct *work) +{ + struct update_gid_work *gw = container_of(work, struct update_gid_work, work); + struct mlx4_cmd_mailbox *mailbox; + union ib_gid *gids; + int err; + struct mlx4_dev *dev = gw->dev->dev; + struct ib_event event; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) { + printk(KERN_WARNING "update gid table failed %ld\n", PTR_ERR(mailbox)); + return; + } + + gids = mailbox->buf; + memcpy(gids, gw->gids, sizeof gw->gids); + + err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port, + 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B); + if (err) + printk(KERN_WARNING "set port command failed\n"); + else { + memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids); + event.device = &gw->dev->ib_dev; + event.element.port_num = gw->port; + event.event = IB_EVENT_LID_CHANGE; + ib_dispatch_event(&event); + } + + mlx4_free_cmd_mailbox(dev, mailbox); + kfree(gw); +} + +static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear) +{ + struct net_device *ndev = dev->iboe.netdevs[port - 1]; + struct update_gid_work *work; + + work = kzalloc(sizeof *work, GFP_ATOMIC); + if (!work) + return -ENOMEM; + + if (!clear) { + mlx4_addrconf_ifid_eui48(&work->gids[0].raw[8], ndev); + work->gids[0].global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); + } + + INIT_WORK(&work->work, update_gids_task); + work->port = port; + work->dev = dev; + queue_work(wq, &work->work); + + return 0; +} + +static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event) +{ + switch (event) { + case NETDEV_UP: + update_ipv6_gids(dev, port, 0); + break; + + case NETDEV_DOWN: + update_ipv6_gids(dev, port, 1); + dev->iboe.netdevs[port - 1] = NULL; + } +} + +static void netdev_added(struct mlx4_ib_dev *dev, int port) +{ + update_ipv6_gids(dev, port, 0); +} + +static void netdev_removed(struct mlx4_ib_dev *dev, int port) +{ + update_ipv6_gids(dev, port, 1); +} + +static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct mlx4_ib_dev *ibdev; + struct net_device *oldnd; + struct mlx4_ib_iboe *iboe; + int port; + + if (!net_eq(dev_net(dev), &init_net)) + return NOTIFY_DONE; + + ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb); + iboe = &ibdev->iboe; + + spin_lock(&iboe->lock); + mlx4_foreach_ib_transport_port(port, ibdev->dev) { + oldnd = iboe->netdevs[port - 1]; + iboe->netdevs[port - 1] = + mlx4_get_protocol_dev(ibdev->dev, MLX4_PROTOCOL_EN, port); + if (oldnd != iboe->netdevs[port - 1]) { + if (iboe->netdevs[port - 1]) + netdev_added(ibdev, port); + else + netdev_removed(ibdev, port); + } + } + + if (dev == iboe->netdevs[0]) + handle_en_event(ibdev, 1, event); + else if (dev == iboe->netdevs[1]) + handle_en_event(ibdev, 2, event); + + spin_unlock(&iboe->lock); + + return NOTIFY_DONE; +} + static void *mlx4_ib_add(struct mlx4_dev *dev) { struct mlx4_ib_dev *ibdev; int num_ports = 0; int i; + int err; + struct mlx4_ib_iboe *iboe; printk_once(KERN_INFO "%s", mlx4_ib_version); - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + mlx4_foreach_ib_transport_port(i, dev) num_ports++; /* No point in registering a device with no ports... */ @@ -564,6 +904,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) return NULL; } + iboe = &ibdev->iboe; + if (mlx4_pd_alloc(dev, &ibdev->priv_pdn)) goto err_dealloc; @@ -612,6 +954,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.query_device = mlx4_ib_query_device; ibdev->ib_dev.query_port = mlx4_ib_query_port; + ibdev->ib_dev.get_link_layer = mlx4_ib_port_link_layer; ibdev->ib_dev.query_gid = mlx4_ib_query_gid; ibdev->ib_dev.query_pkey = mlx4_ib_query_pkey; ibdev->ib_dev.modify_device = mlx4_ib_modify_device; @@ -656,6 +999,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.unmap_fmr = mlx4_ib_unmap_fmr; ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc; + spin_lock_init(&iboe->lock); + if (init_node_data(ibdev)) goto err_map; @@ -668,16 +1013,28 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (mlx4_ib_mad_init(ibdev)) goto err_reg; + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) { + iboe->nb.notifier_call = mlx4_ib_netdev_event; + err = register_netdevice_notifier(&iboe->nb); + if (err) + goto err_reg; + } + for (i = 0; i < ARRAY_SIZE(mlx4_class_attributes); ++i) { if (device_create_file(&ibdev->ib_dev.dev, mlx4_class_attributes[i])) - goto err_reg; + goto err_notif; } ibdev->ib_active = true; return ibdev; +err_notif: + if (unregister_netdevice_notifier(&ibdev->iboe.nb)) + printk(KERN_WARNING "failure unregistering notifier\n"); + flush_workqueue(wq); + err_reg: ib_unregister_device(&ibdev->ib_dev); @@ -703,11 +1060,16 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) mlx4_ib_mad_cleanup(ibdev); ib_unregister_device(&ibdev->ib_dev); + if (ibdev->iboe.nb.notifier_call) { + if (unregister_netdevice_notifier(&ibdev->iboe.nb)) + printk(KERN_WARNING "failure unregistering notifier\n"); + ibdev->iboe.nb.notifier_call = NULL; + } + iounmap(ibdev->uar_map); - for (p = 1; p <= ibdev->num_ports; ++p) + mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB) mlx4_CLOSE_PORT(dev, p); - iounmap(ibdev->uar_map); mlx4_uar_free(dev, &ibdev->priv_uar); mlx4_pd_free(dev, ibdev->priv_pdn); ib_dealloc_device(&ibdev->ib_dev); @@ -747,19 +1109,33 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, } static struct mlx4_interface mlx4_ib_interface = { - .add = mlx4_ib_add, - .remove = mlx4_ib_remove, - .event = mlx4_ib_event + .add = mlx4_ib_add, + .remove = mlx4_ib_remove, + .event = mlx4_ib_event, + .protocol = MLX4_PROTOCOL_IB }; static int __init mlx4_ib_init(void) { - return mlx4_register_interface(&mlx4_ib_interface); + int err; + + wq = create_singlethread_workqueue("mlx4_ib"); + if (!wq) + return -ENOMEM; + + err = mlx4_register_interface(&mlx4_ib_interface); + if (err) { + destroy_workqueue(wq); + return err; + } + + return 0; } static void __exit mlx4_ib_cleanup(void) { mlx4_unregister_interface(&mlx4_ib_interface); + destroy_workqueue(wq); } module_init(mlx4_ib_init); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 3486d7675e56..2a322f21049f 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -112,6 +112,13 @@ enum mlx4_ib_qp_flags { MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = 1 << 1, }; +struct mlx4_ib_gid_entry { + struct list_head list; + union ib_gid gid; + int added; + u8 port; +}; + struct mlx4_ib_qp { struct ib_qp ibqp; struct mlx4_qp mqp; @@ -138,6 +145,8 @@ struct mlx4_ib_qp { u8 resp_depth; u8 sq_no_prefetch; u8 state; + int mlx_type; + struct list_head gid_list; }; struct mlx4_ib_srq { @@ -157,7 +166,14 @@ struct mlx4_ib_srq { struct mlx4_ib_ah { struct ib_ah ibah; - struct mlx4_av av; + union mlx4_ext_av av; +}; + +struct mlx4_ib_iboe { + spinlock_t lock; + struct net_device *netdevs[MLX4_MAX_PORTS]; + struct notifier_block nb; + union ib_gid gid_table[MLX4_MAX_PORTS][128]; }; struct mlx4_ib_dev { @@ -176,6 +192,7 @@ struct mlx4_ib_dev { struct mutex cap_mask_mutex; bool ib_active; + struct mlx4_ib_iboe iboe; }; static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev) @@ -314,9 +331,20 @@ int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, int npages, int mlx4_ib_unmap_fmr(struct list_head *fmr_list); int mlx4_ib_fmr_dealloc(struct ib_fmr *fmr); +int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr, + u8 *mac, int *is_mcast, u8 port); + static inline int mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah) { - return !!(ah->av.g_slid & 0x80); + u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3; + + if (rdma_port_get_link_layer(ah->ibah.device, port) == IB_LINK_LAYER_ETHERNET) + return 1; + + return !!(ah->av.ib.g_slid & 0x80); } +int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, + union ib_gid *gid); + #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index bb1277c8fbf0..17f60fe6e5b6 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -33,6 +33,7 @@ #include #include +#include #include #include @@ -48,17 +49,25 @@ enum { enum { MLX4_IB_DEFAULT_SCHED_QUEUE = 0x83, - MLX4_IB_DEFAULT_QP0_SCHED_QUEUE = 0x3f + MLX4_IB_DEFAULT_QP0_SCHED_QUEUE = 0x3f, + MLX4_IB_LINK_TYPE_IB = 0, + MLX4_IB_LINK_TYPE_ETH = 1 }; enum { /* - * Largest possible UD header: send with GRH and immediate data. + * Largest possible UD header: send with GRH and immediate + * data plus 14 bytes for an Ethernet header. (LRH would only + * use 8 bytes, so Ethernet is the biggest case) */ - MLX4_IB_UD_HEADER_SIZE = 72, + MLX4_IB_UD_HEADER_SIZE = 78, MLX4_IB_LSO_HEADER_SPARE = 128, }; +enum { + MLX4_IB_IBOE_ETHERTYPE = 0x8915 +}; + struct mlx4_ib_sqp { struct mlx4_ib_qp qp; int pkey_index; @@ -462,6 +471,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); + INIT_LIST_HEAD(&qp->gid_list); qp->state = IB_QPS_RESET; if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) @@ -649,6 +659,16 @@ static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *re } } +static void del_gid_entries(struct mlx4_ib_qp *qp) +{ + struct mlx4_ib_gid_entry *ge, *tmp; + + list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) { + list_del(&ge->list); + kfree(ge); + } +} + static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, int is_user) { @@ -695,6 +715,8 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, if (!qp->ibqp.srq) mlx4_db_free(dev->dev, &qp->db); } + + del_gid_entries(qp); } struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, @@ -852,6 +874,12 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port) static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, struct mlx4_qp_path *path, u8 port) { + int err; + int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) == + IB_LINK_LAYER_ETHERNET; + u8 mac[6]; + int is_mcast; + path->grh_mylmc = ah->src_path_bits & 0x7f; path->rlid = cpu_to_be16(ah->dlid); if (ah->static_rate) { @@ -882,9 +910,35 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((port - 1) << 6) | ((ah->sl & 0xf) << 2); + if (is_eth) { + if (!(ah->ah_flags & IB_AH_GRH)) + return -1; + + err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port); + if (err) + return err; + + memcpy(path->dmac, mac, 6); + path->ackto = MLX4_IB_LINK_TYPE_ETH; + /* use index 0 into MAC table for IBoE */ + path->grh_mylmc &= 0x80; + } + return 0; } +static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) +{ + struct mlx4_ib_gid_entry *ge, *tmp; + + list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) { + if (!ge->added && mlx4_ib_add_mc(dev, qp, &ge->gid)) { + ge->added = 1; + ge->port = qp->port; + } + } +} + static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int attr_mask, enum ib_qp_state cur_state, enum ib_qp_state new_state) @@ -980,7 +1034,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (attr_mask & IB_QP_TIMEOUT) { - context->pri_path.ackto = attr->timeout << 3; + context->pri_path.ackto |= attr->timeout << 3; optpar |= MLX4_QP_OPTPAR_ACK_TIMEOUT; } @@ -1118,8 +1172,10 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, qp->atomic_rd_en = attr->qp_access_flags; if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) qp->resp_depth = attr->max_dest_rd_atomic; - if (attr_mask & IB_QP_PORT) + if (attr_mask & IB_QP_PORT) { qp->port = attr->port_num; + update_mcg_macs(dev, qp); + } if (attr_mask & IB_QP_ALT_PATH) qp->alt_port = attr->alt_port_num; @@ -1226,35 +1282,45 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, int header_size; int spc; int i; + int is_eth; + int is_grh; send_size = 0; for (i = 0; i < wr->num_sge; ++i) send_size += wr->sg_list[i].length; - ib_ud_header_init(send_size, 1, 0, mlx4_ib_ah_grh_present(ah), 0, &sqp->ud_header); + is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET; + is_grh = mlx4_ib_ah_grh_present(ah); + ib_ud_header_init(send_size, !is_eth, is_eth, is_grh, 0, &sqp->ud_header); + + if (!is_eth) { + sqp->ud_header.lrh.service_level = + be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28; + sqp->ud_header.lrh.destination_lid = ah->av.ib.dlid; + sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.ib.g_slid & 0x7f); + } - sqp->ud_header.lrh.service_level = - be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28; - sqp->ud_header.lrh.destination_lid = ah->av.dlid; - sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.g_slid & 0x7f); - if (mlx4_ib_ah_grh_present(ah)) { + if (is_grh) { sqp->ud_header.grh.traffic_class = - (be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 20) & 0xff; + (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff; sqp->ud_header.grh.flow_label = - ah->av.sl_tclass_flowlabel & cpu_to_be32(0xfffff); - sqp->ud_header.grh.hop_limit = ah->av.hop_limit; - ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.port_pd) >> 24, - ah->av.gid_index, &sqp->ud_header.grh.source_gid); + ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff); + sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit; + ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.ib.port_pd) >> 24, + ah->av.ib.gid_index, &sqp->ud_header.grh.source_gid); memcpy(sqp->ud_header.grh.destination_gid.raw, - ah->av.dgid, 16); + ah->av.ib.dgid, 16); } mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE); - mlx->flags |= cpu_to_be32((!sqp->qp.ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) | - (sqp->ud_header.lrh.destination_lid == - IB_LID_PERMISSIVE ? MLX4_WQE_MLX_SLR : 0) | - (sqp->ud_header.lrh.service_level << 8)); - mlx->rlid = sqp->ud_header.lrh.destination_lid; + + if (!is_eth) { + mlx->flags |= cpu_to_be32((!sqp->qp.ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) | + (sqp->ud_header.lrh.destination_lid == + IB_LID_PERMISSIVE ? MLX4_WQE_MLX_SLR : 0) | + (sqp->ud_header.lrh.service_level << 8)); + mlx->rlid = sqp->ud_header.lrh.destination_lid; + } switch (wr->opcode) { case IB_WR_SEND: @@ -1270,9 +1336,21 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, return -EINVAL; } - sqp->ud_header.lrh.virtual_lane = !sqp->qp.ibqp.qp_num ? 15 : 0; - if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE) - sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE; + if (is_eth) { + u8 *smac; + + memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6); + /* FIXME: cache smac value? */ + smac = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]->dev_addr; + memcpy(sqp->ud_header.eth.smac_h, smac, 6); + if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) + mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); + sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + } else { + sqp->ud_header.lrh.virtual_lane = !sqp->qp.ibqp.qp_num ? 15 : 0; + if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE) + sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE; + } sqp->ud_header.bth.solicited_event = !!(wr->send_flags & IB_SEND_SOLICITED); if (!sqp->qp.ibqp.qp_num) ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey); @@ -1434,6 +1512,8 @@ static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg, memcpy(dseg->av, &to_mah(wr->wr.ud.ah)->av, sizeof (struct mlx4_av)); dseg->dqpn = cpu_to_be32(wr->wr.ud.remote_qpn); dseg->qkey = cpu_to_be32(wr->wr.ud.remote_qkey); + dseg->vlan = to_mah(wr->wr.ud.ah)->av.eth.vlan; + memcpy(dseg->mac, to_mah(wr->wr.ud.ah)->av.eth.mac, 6); } static void set_mlx_icrc_seg(void *dseg) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 47e163ad3d11..ca5645c43f61 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -374,6 +374,27 @@ struct mlx4_av { u8 dgid[16]; }; +struct mlx4_eth_av { + __be32 port_pd; + u8 reserved1; + u8 smac_idx; + u16 reserved2; + u8 reserved3; + u8 gid_index; + u8 stat_rate; + u8 hop_limit; + __be32 sl_tclass_flowlabel; + u8 dgid[16]; + u32 reserved4[2]; + __be16 vlan; + u8 mac[6]; +}; + +union mlx4_ext_av { + struct mlx4_av ib; + struct mlx4_eth_av eth; +}; + struct mlx4_dev { struct pci_dev *pdev; unsigned long flags; @@ -402,6 +423,12 @@ struct mlx4_init_port_param { if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \ ~(dev)->caps.port_mask) & 1 << ((port) - 1)) +#define mlx4_foreach_ib_transport_port(port, dev) \ + for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \ + if (((dev)->caps.port_mask & 1 << ((port) - 1)) || \ + ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)) + + int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, struct mlx4_buf *buf); void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); -- cgit v1.3-14-g43fede From af7bd463761c6abd8ca8d831f9cc0ac19f3b7d4b Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 26 Aug 2010 17:18:59 +0300 Subject: IB/core: Add VLAN support for IBoE Add 802.1q VLAN support to IBoE. The VLAN tag is encoded within the GID derived from a link local address in the following way: GID[11] GID[12] contain the VLAN ID when the GID contains a VLAN. The 3 bits user priority field of the packets are identical to the 3 bits of the SL. In case of rdma_cm apps, the TOS field is used to generate the SL field by doing a shift right of 5 bits effectively taking to 3 MS bits of the TOS field. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/infiniband/core/cma.c | 20 +++++++++------- drivers/infiniband/core/ucma.c | 12 ++++++++-- drivers/infiniband/core/ud_header.c | 23 ++++++++++++++++++ drivers/infiniband/hw/mlx4/qp.c | 2 +- drivers/infiniband/hw/mthca/mthca_qp.c | 2 +- include/rdma/ib_addr.h | 43 ++++++++++++++++++++++++++++++---- include/rdma/ib_pack.h | 9 +++++++ 7 files changed, 95 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f61bc0738488..6884da24fde1 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1791,6 +1791,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) struct sockaddr_in *src_addr = (struct sockaddr_in *)&route->addr.src_addr; struct sockaddr_in *dst_addr = (struct sockaddr_in *)&route->addr.dst_addr; struct net_device *ndev = NULL; + u16 vid; if (src_addr->sin_family != dst_addr->sin_family) return -EINVAL; @@ -1810,14 +1811,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->num_paths = 1; - iboe_mac_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr); - iboe_mac_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr); - - route->path_rec->hop_limit = 1; - route->path_rec->reversible = 1; - route->path_rec->pkey = cpu_to_be16(0xffff); - route->path_rec->mtu_selector = IB_SA_EQ; - if (addr->dev_addr.bound_dev_if) ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); if (!ndev) { @@ -1825,6 +1818,17 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) goto err2; } + vid = rdma_vlan_dev_vlan_id(ndev); + + iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid); + iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid); + + route->path_rec->hop_limit = 1; + route->path_rec->reversible = 1; + route->path_rec->pkey = cpu_to_be16(0xffff); + route->path_rec->mtu_selector = IB_SA_EQ; + route->path_rec->sl = id_priv->tos >> 5; + route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = iboe_get_rate(ndev); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 3d3c9264c450..357a766bd220 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -587,13 +587,21 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, struct rdma_route *route) { struct rdma_dev_addr *dev_addr; + struct net_device *dev; + u16 vid = 0; resp->num_paths = route->num_paths; switch (route->num_paths) { case 0: dev_addr = &route->addr.dev_addr; - iboe_mac_to_ll((union ib_gid *) &resp->ib_route[0].dgid, - dev_addr->dst_dev_addr); + dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); + if (dev) { + vid = rdma_vlan_dev_vlan_id(dev); + dev_put(dev); + } + + iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid, + dev_addr->dst_dev_addr, vid); iboe_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid); resp->ib_route[0].pkey = cpu_to_be16(0xffff); diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c index cb0dd5ae2777..bb7e19280821 100644 --- a/drivers/infiniband/core/ud_header.c +++ b/drivers/infiniband/core/ud_header.c @@ -33,6 +33,7 @@ #include #include +#include #include @@ -103,6 +104,17 @@ static const struct ib_field eth_table[] = { .size_bits = 16 } }; +static const struct ib_field vlan_table[] = { + { STRUCT_FIELD(vlan, tag), + .offset_words = 0, + .offset_bits = 0, + .size_bits = 16 }, + { STRUCT_FIELD(vlan, type), + .offset_words = 0, + .offset_bits = 16, + .size_bits = 16 } +}; + static const struct ib_field grh_table[] = { { STRUCT_FIELD(grh, ip_version), .offset_words = 0, @@ -205,6 +217,7 @@ static const struct ib_field deth_table[] = { * @payload_bytes:Length of packet payload * @lrh_present: specify if LRH is present * @eth_present: specify if Eth header is present + * @vlan_present: packet is tagged vlan * @grh_present:GRH flag (if non-zero, GRH will be included) * @immediate_present: specify if immediate data is present * @header:Structure to initialize @@ -212,6 +225,7 @@ static const struct ib_field deth_table[] = { void ib_ud_header_init(int payload_bytes, int lrh_present, int eth_present, + int vlan_present, int grh_present, int immediate_present, struct ib_ud_header *header) @@ -234,6 +248,9 @@ void ib_ud_header_init(int payload_bytes, header->lrh.packet_length = cpu_to_be16(packet_length); } + if (vlan_present) + header->eth.type = cpu_to_be16(ETH_P_8021Q); + if (grh_present) { header->grh.ip_version = 6; header->grh.payload_length = @@ -254,6 +271,7 @@ void ib_ud_header_init(int payload_bytes, header->lrh_present = lrh_present; header->eth_present = eth_present; + header->vlan_present = vlan_present; header->grh_present = grh_present; header->immediate_present = immediate_present; } @@ -312,6 +330,11 @@ int ib_ud_header_pack(struct ib_ud_header *header, &header->eth, buf + len); len += IB_ETH_BYTES; } + if (header->vlan_present) { + ib_pack(vlan_table, ARRAY_SIZE(vlan_table), + &header->vlan, buf + len); + len += IB_VLAN_BYTES; + } if (header->grh_present) { ib_pack(grh_table, ARRAY_SIZE(grh_table), &header->grh, buf + len); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 17f60fe6e5b6..269648445113 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1291,7 +1291,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET; is_grh = mlx4_ib_ah_grh_present(ah); - ib_ud_header_init(send_size, !is_eth, is_eth, is_grh, 0, &sqp->ud_header); + ib_ud_header_init(send_size, !is_eth, is_eth, 0, is_grh, 0, &sqp->ud_header); if (!is_eth) { sqp->ud_header.lrh.service_level = diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c index 1a1c55fb13f3..a34c9d38e822 100644 --- a/drivers/infiniband/hw/mthca/mthca_qp.c +++ b/drivers/infiniband/hw/mthca/mthca_qp.c @@ -1493,7 +1493,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp, int err; u16 pkey; - ib_ud_header_init(256, /* assume a MAD */ 1, 0, + ib_ud_header_init(256, /* assume a MAD */ 1, 0, 0, mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), 0, &sqp->ud_header); diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index 904ffa92fc93..b5fc9f39122b 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -129,21 +130,41 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } -static inline void iboe_mac_to_ll(union ib_gid *gid, u8 *mac) +static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid) { memset(gid->raw, 0, 16); *((__be32 *) gid->raw) = cpu_to_be32(0xfe800000); - gid->raw[12] = 0xfe; - gid->raw[11] = 0xff; + if (vid < 0x1000) { + gid->raw[12] = vid & 0xff; + gid->raw[11] = vid >> 8; + } else { + gid->raw[12] = 0xfe; + gid->raw[11] = 0xff; + } memcpy(gid->raw + 13, mac + 3, 3); memcpy(gid->raw + 8, mac, 3); gid->raw[8] ^= 2; } +static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) +{ + return dev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_vlan_id(dev) : 0xffff; +} + static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { - iboe_mac_to_ll(gid, dev_addr->src_dev_addr); + struct net_device *dev; + u16 vid = 0xffff; + + dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); + if (dev) { + vid = rdma_vlan_dev_vlan_id(dev); + dev_put(dev); + } + + iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid); } static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) @@ -244,4 +265,18 @@ static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) mac[i] = addr->s6_addr[i + 10]; } +static inline u16 rdma_get_vlan_id(union ib_gid *dgid) +{ + u16 vid; + + vid = dgid->raw[11] << 8 | dgid->raw[12]; + return vid < 0x1000 ? vid : 0xffff; +} + +static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) +{ + return dev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_real_dev(dev) : 0; +} + #endif /* IB_ADDR_H */ diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h index 6b91d8e7a1fa..b37fe3b10a9d 100644 --- a/include/rdma/ib_pack.h +++ b/include/rdma/ib_pack.h @@ -38,6 +38,7 @@ enum { IB_LRH_BYTES = 8, IB_ETH_BYTES = 14, + IB_VLAN_BYTES = 4, IB_GRH_BYTES = 40, IB_BTH_BYTES = 12, IB_DETH_BYTES = 8 @@ -219,11 +220,18 @@ struct ib_unpacked_eth { __be16 type; }; +struct ib_unpacked_vlan { + __be16 tag; + __be16 type; +}; + struct ib_ud_header { int lrh_present; struct ib_unpacked_lrh lrh; int eth_present; struct ib_unpacked_eth eth; + int vlan_present; + struct ib_unpacked_vlan vlan; int grh_present; struct ib_unpacked_grh grh; struct ib_unpacked_bth bth; @@ -245,6 +253,7 @@ void ib_unpack(const struct ib_field *desc, void ib_ud_header_init(int payload_bytes, int lrh_present, int eth_present, + int vlan_present, int grh_present, int immediate_present, struct ib_ud_header *header); -- cgit v1.3-14-g43fede From 4c3eb3ca13966508bcb64f39dcdef48be22f1731 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 26 Aug 2010 17:19:22 +0300 Subject: IB/mlx4: Add VLAN support for IBoE This patch allows IBoE traffic to be encapsulated in 802.1Q tagged VLAN frames. The VLAN tag is encoded in the GID and derived from it by a simple computation. The netdev notifier callback is modified to catch VLAN device addition/removal and the port's GID table is updated to reflect the change, so that for each netdevice there is an entry in the GID table. When the port's GID table is exhausted, GID entries will not be added. Only children of the main interfaces can add to the GID table; if a VLAN interface is added on another VLAN interface (e.g. "vconfig add eth2.6 8"), then that interfaces will not add an entry to the GID table. Signed-off-by: Eli Cohen Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/ah.c | 10 ++++ drivers/infiniband/hw/mlx4/main.c | 99 ++++++++++++++++++++++++++++++++++----- drivers/infiniband/hw/mlx4/qp.c | 79 +++++++++++++++++++++++++------ drivers/net/mlx4/en_netdev.c | 10 ++++ drivers/net/mlx4/mlx4_en.h | 1 + drivers/net/mlx4/port.c | 19 ++++++++ include/linux/mlx4/device.h | 1 + include/linux/mlx4/qp.h | 2 +- 8 files changed, 193 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 3bf3544c0aa0..4b8f9c49397e 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -31,6 +31,7 @@ */ #include +#include #include #include @@ -91,17 +92,26 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr { struct mlx4_ib_dev *ibdev = to_mdev(pd->device); struct mlx4_dev *dev = ibdev->dev; + union ib_gid sgid; u8 mac[6]; int err; int is_mcast; + u16 vlan_tag; err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num); if (err) return ERR_PTR(err); memcpy(ah->av.eth.mac, mac, 6); + err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid); + if (err) + return ERR_PTR(err); + vlan_tag = rdma_get_vlan_id(&sgid); + if (vlan_tag < 0x1000) + vlan_tag |= (ah_attr->sl & 7) << 13; ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); ah->av.eth.gid_index = ah_attr->grh.sgid_index; + ah->av.eth.vlan = cpu_to_be16(vlan_tag); if (ah_attr->static_rate) { ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET; while (ah->av.eth.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET && diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index e65db73fc277..8736bd836dc0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -79,6 +80,8 @@ static void init_query_mad(struct ib_smp *mad) mad->method = IB_MGMT_METHOD_GET; } +static union ib_gid zgid; + static int mlx4_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props) { @@ -755,12 +758,17 @@ static struct device_attribute *mlx4_class_attributes[] = { &dev_attr_board_id }; -static void mlx4_addrconf_ifid_eui48(u8 *eui, struct net_device *dev) +static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, struct net_device *dev) { memcpy(eui, dev->dev_addr, 3); memcpy(eui + 5, dev->dev_addr + 3, 3); - eui[3] = 0xFF; - eui[4] = 0xFE; + if (vlan_id < 0x1000) { + eui[3] = vlan_id >> 8; + eui[4] = vlan_id & 0xff; + } else { + eui[3] = 0xff; + eui[4] = 0xfe; + } eui[0] ^= 2; } @@ -802,28 +810,93 @@ static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear) { struct net_device *ndev = dev->iboe.netdevs[port - 1]; struct update_gid_work *work; + struct net_device *tmp; + int i; + u8 *hits; + int ret; + union ib_gid gid; + int free; + int found; + int need_update = 0; + u16 vid; work = kzalloc(sizeof *work, GFP_ATOMIC); if (!work) return -ENOMEM; - if (!clear) { - mlx4_addrconf_ifid_eui48(&work->gids[0].raw[8], ndev); - work->gids[0].global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); + hits = kzalloc(128, GFP_ATOMIC); + if (!hits) { + ret = -ENOMEM; + goto out; + } + + read_lock(&dev_base_lock); + for_each_netdev(&init_net, tmp) { + if (ndev && (tmp == ndev || rdma_vlan_dev_real_dev(tmp) == ndev)) { + gid.global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); + vid = rdma_vlan_dev_vlan_id(tmp); + mlx4_addrconf_ifid_eui48(&gid.raw[8], vid, ndev); + found = 0; + free = -1; + for (i = 0; i < 128; ++i) { + if (free < 0 && + !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid)) + free = i; + if (!memcmp(&dev->iboe.gid_table[port - 1][i], &gid, sizeof gid)) { + hits[i] = 1; + found = 1; + break; + } + } + + if (!found) { + if (tmp == ndev && + (memcmp(&dev->iboe.gid_table[port - 1][0], + &gid, sizeof gid) || + !memcmp(&dev->iboe.gid_table[port - 1][0], + &zgid, sizeof gid))) { + dev->iboe.gid_table[port - 1][0] = gid; + ++need_update; + hits[0] = 1; + } else if (free >= 0) { + dev->iboe.gid_table[port - 1][free] = gid; + hits[free] = 1; + ++need_update; + } + } + } } + read_unlock(&dev_base_lock); + + for (i = 0; i < 128; ++i) + if (!hits[i]) { + if (memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid)) + ++need_update; + dev->iboe.gid_table[port - 1][i] = zgid; + } - INIT_WORK(&work->work, update_gids_task); - work->port = port; - work->dev = dev; - queue_work(wq, &work->work); + if (need_update) { + memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof work->gids); + INIT_WORK(&work->work, update_gids_task); + work->port = port; + work->dev = dev; + queue_work(wq, &work->work); + } else + kfree(work); + kfree(hits); return 0; + +out: + kfree(work); + return ret; } static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event) { switch (event) { case NETDEV_UP: + case NETDEV_CHANGEADDR: update_ipv6_gids(dev, port, 0); break; @@ -871,9 +944,11 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event } } - if (dev == iboe->netdevs[0]) + if (dev == iboe->netdevs[0] || + (iboe->netdevs[0] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[0])) handle_en_event(ibdev, 1, event); - else if (dev == iboe->netdevs[1]) + else if (dev == iboe->netdevs[1] + || (iboe->netdevs[1] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[1])) handle_en_event(ibdev, 2, event); spin_unlock(&iboe->lock); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 269648445113..9a7794ac34c1 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -37,6 +37,7 @@ #include #include +#include #include @@ -57,10 +58,11 @@ enum { enum { /* * Largest possible UD header: send with GRH and immediate - * data plus 14 bytes for an Ethernet header. (LRH would only - * use 8 bytes, so Ethernet is the biggest case) + * data plus 18 bytes for an Ethernet header with VLAN/802.1Q + * tag. (LRH would only use 8 bytes, so Ethernet is the + * biggest case) */ - MLX4_IB_UD_HEADER_SIZE = 78, + MLX4_IB_UD_HEADER_SIZE = 82, MLX4_IB_LSO_HEADER_SPARE = 128, }; @@ -879,6 +881,8 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, IB_LINK_LAYER_ETHERNET; u8 mac[6]; int is_mcast; + u16 vlan_tag; + int vidx; path->grh_mylmc = ah->src_path_bits & 0x7f; path->rlid = cpu_to_be16(ah->dlid); @@ -907,10 +911,10 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, memcpy(path->rgid, ah->grh.dgid.raw, 16); } - path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | - ((port - 1) << 6) | ((ah->sl & 0xf) << 2); - if (is_eth) { + path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | + ((port - 1) << 6) | ((ah->sl & 7) << 3) | ((ah->sl & 8) >> 1); + if (!(ah->ah_flags & IB_AH_GRH)) return -1; @@ -922,7 +926,18 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, path->ackto = MLX4_IB_LINK_TYPE_ETH; /* use index 0 into MAC table for IBoE */ path->grh_mylmc &= 0x80; - } + + vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]); + if (vlan_tag < 0x1000) { + if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx)) + return -ENOENT; + + path->vlan_index = vidx; + path->fl = 1 << 6; + } + } else + path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | + ((port - 1) << 6) | ((ah->sl & 0xf) << 2); return 0; } @@ -1277,13 +1292,16 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, struct mlx4_wqe_mlx_seg *mlx = wqe; struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx; struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah); + union ib_gid sgid; u16 pkey; int send_size; int header_size; int spc; int i; int is_eth; + int is_vlan = 0; int is_grh; + u16 vlan; send_size = 0; for (i = 0; i < wr->num_sge; ++i) @@ -1291,7 +1309,13 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET; is_grh = mlx4_ib_ah_grh_present(ah); - ib_ud_header_init(send_size, !is_eth, is_eth, 0, is_grh, 0, &sqp->ud_header); + if (is_eth) { + ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.ib.port_pd) >> 24, + ah->av.ib.gid_index, &sgid); + vlan = rdma_get_vlan_id(&sgid); + is_vlan = vlan < 0x1000; + } + ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header); if (!is_eth) { sqp->ud_header.lrh.service_level = @@ -1345,7 +1369,15 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, memcpy(sqp->ud_header.eth.smac_h, smac, 6); if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); - sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + if (!is_vlan) { + sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + } else { + u16 pcp; + + sqp->ud_header.vlan.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE); + pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 27 & 3) << 13; + sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp); + } } else { sqp->ud_header.lrh.virtual_lane = !sqp->qp.ibqp.qp_num ? 15 : 0; if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE) @@ -1507,13 +1539,14 @@ static void set_masked_atomic_seg(struct mlx4_wqe_masked_atomic_seg *aseg, } static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg, - struct ib_send_wr *wr) + struct ib_send_wr *wr, __be16 *vlan) { memcpy(dseg->av, &to_mah(wr->wr.ud.ah)->av, sizeof (struct mlx4_av)); dseg->dqpn = cpu_to_be32(wr->wr.ud.remote_qpn); dseg->qkey = cpu_to_be32(wr->wr.ud.remote_qkey); dseg->vlan = to_mah(wr->wr.ud.ah)->av.eth.vlan; memcpy(dseg->mac, to_mah(wr->wr.ud.ah)->av.eth.mac, 6); + *vlan = dseg->vlan; } static void set_mlx_icrc_seg(void *dseg) @@ -1616,6 +1649,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, __be32 uninitialized_var(lso_hdr_sz); __be32 blh; int i; + __be16 vlan = cpu_to_be16(0xffff); spin_lock_irqsave(&qp->sq.lock, flags); @@ -1719,7 +1753,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, break; case IB_QPT_UD: - set_datagram_seg(wqe, wr); + set_datagram_seg(wqe, wr, &vlan); wqe += sizeof (struct mlx4_wqe_datagram_seg); size += sizeof (struct mlx4_wqe_datagram_seg) / 16; @@ -1797,6 +1831,11 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, ctrl->owner_opcode = mlx4_ib_opcode[wr->opcode] | (ind & qp->sq.wqe_cnt ? cpu_to_be32(1 << 31) : 0) | blh; + if (be16_to_cpu(vlan) < 0x1000) { + ctrl->ins_vlan = 1 << 6; + ctrl->vlan_tag = vlan; + } + stamp = ind + qp->sq_spare_wqes; ind += DIV_ROUND_UP(size * 16, 1U << qp->sq.wqe_shift); @@ -1946,17 +1985,27 @@ static int to_ib_qp_access_flags(int mlx4_flags) return ib_flags; } -static void to_ib_ah_attr(struct mlx4_dev *dev, struct ib_ah_attr *ib_ah_attr, +static void to_ib_ah_attr(struct mlx4_ib_dev *ibdev, struct ib_ah_attr *ib_ah_attr, struct mlx4_qp_path *path) { + struct mlx4_dev *dev = ibdev->dev; + int is_eth; + memset(ib_ah_attr, 0, sizeof *ib_ah_attr); ib_ah_attr->port_num = path->sched_queue & 0x40 ? 2 : 1; if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->caps.num_ports) return; + is_eth = rdma_port_get_link_layer(&ibdev->ib_dev, ib_ah_attr->port_num) == + IB_LINK_LAYER_ETHERNET; + if (is_eth) + ib_ah_attr->sl = ((path->sched_queue >> 3) & 0x7) | + ((path->sched_queue & 4) << 1); + else + ib_ah_attr->sl = (path->sched_queue >> 2) & 0xf; + ib_ah_attr->dlid = be16_to_cpu(path->rlid); - ib_ah_attr->sl = (path->sched_queue >> 2) & 0xf; ib_ah_attr->src_path_bits = path->grh_mylmc & 0x7f; ib_ah_attr->static_rate = path->static_rate ? path->static_rate - 5 : 0; ib_ah_attr->ah_flags = (path->grh_mylmc & (1 << 7)) ? IB_AH_GRH : 0; @@ -2009,8 +2058,8 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr to_ib_qp_access_flags(be32_to_cpu(context.params2)); if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) { - to_ib_ah_attr(dev->dev, &qp_attr->ah_attr, &context.pri_path); - to_ib_ah_attr(dev->dev, &qp_attr->alt_ah_attr, &context.alt_path); + to_ib_ah_attr(dev, &qp_attr->ah_attr, &context.pri_path); + to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context.alt_path); qp_attr->alt_pkey_index = context.alt_path.pkey_index & 0x7f; qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num; } diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c index a0d8a26f5a02..9a87c4f3bbbd 100644 --- a/drivers/net/mlx4/en_netdev.c +++ b/drivers/net/mlx4/en_netdev.c @@ -69,6 +69,7 @@ static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; int err; + int idx; if (!priv->vlgrp) return; @@ -83,7 +84,10 @@ static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) if (err) en_err(priv, "Failed configuring VLAN filter\n"); } + if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx)) + en_err(priv, "failed adding vlan %d\n", vid); mutex_unlock(&mdev->state_lock); + } static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) @@ -91,6 +95,7 @@ static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; int err; + int idx; if (!priv->vlgrp) return; @@ -101,6 +106,11 @@ static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) /* Remove VID from port VLAN filter */ mutex_lock(&mdev->state_lock); + if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx)) + mlx4_unregister_vlan(mdev->dev, priv->port, idx); + else + en_err(priv, "could not find vid %d in cache\n", vid); + if (mdev->device_up && priv->port_up) { err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp); if (err) diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h index 449210994ee9..dab5eafb8946 100644 --- a/drivers/net/mlx4/mlx4_en.h +++ b/drivers/net/mlx4/mlx4_en.h @@ -463,6 +463,7 @@ struct mlx4_en_priv { char *mc_addrs; int mc_addrs_cnt; struct mlx4_en_stat_out_mbox hw_stats; + int vids[128]; }; diff --git a/drivers/net/mlx4/port.c b/drivers/net/mlx4/port.c index 606aa58afdea..56371ef328ef 100644 --- a/drivers/net/mlx4/port.c +++ b/drivers/net/mlx4/port.c @@ -182,6 +182,25 @@ static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port, return err; } +int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx) +{ + struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table; + int i; + + for (i = 0; i < MLX4_MAX_VLAN_NUM; ++i) { + if (table->refs[i] && + (vid == (MLX4_VLAN_MASK & + be32_to_cpu(table->entries[i])))) { + /* VLAN already registered, increase reference count */ + *idx = i; + return 0; + } + } + + return -ENOENT; +} +EXPORT_SYMBOL_GPL(mlx4_find_cached_vlan); + int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index) { struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index ca5645c43f61..ff9893a33e90 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -496,6 +496,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]); int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index); void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index); +int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 97cfdc8d7e2f..0eeb2a1a867c 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -109,7 +109,7 @@ struct mlx4_qp_path { __be32 tclass_flowlabel; u8 rgid[16]; u8 sched_queue; - u8 snooper_flags; + u8 vlan_index; u8 reserved3[2]; u8 counter_index; u8 reserved4; -- cgit v1.3-14-g43fede