From ebd61f68e1c79eab022c550f95cb8bf37cc925cb Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:16 +0200 Subject: IB/mlx5: Support IB device's callback for getting the link layer Make the existing mlx5_ib_port_link_layer() signature match the ib device callback signature (add port_num parameter). Refactor it to use a sub function so that the link layer could be queried also before the ibdev is created. Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 7e97cb55a6bf..a3295bb15891 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -64,11 +64,9 @@ static char mlx5_version[] = DRIVER_VERSION " (" DRIVER_RELDATE ")\n"; static enum rdma_link_layer -mlx5_ib_port_link_layer(struct ib_device *device) +mlx5_port_type_cap_to_rdma_ll(int port_type_cap) { - struct mlx5_ib_dev *dev = to_mdev(device); - - switch (MLX5_CAP_GEN(dev->mdev, port_type)) { + switch (port_type_cap) { case MLX5_CAP_PORT_TYPE_IB: return IB_LINK_LAYER_INFINIBAND; case MLX5_CAP_PORT_TYPE_ETH: @@ -78,6 +76,15 @@ mlx5_ib_port_link_layer(struct ib_device *device) } } +static enum rdma_link_layer +mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num) +{ + struct mlx5_ib_dev *dev = to_mdev(device); + int port_type_cap = MLX5_CAP_GEN(dev->mdev, port_type); + + return mlx5_port_type_cap_to_rdma_ll(port_type_cap); +} + static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev) { return !dev->mdev->issi; @@ -94,7 +101,7 @@ static int mlx5_get_vport_access_method(struct ib_device *ibdev) if (mlx5_use_mad_ifc(to_mdev(ibdev))) return MLX5_VPORT_ACCESS_METHOD_MAD; - if (mlx5_ib_port_link_layer(ibdev) == + if (mlx5_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) return MLX5_VPORT_ACCESS_METHOD_NIC; @@ -1325,11 +1332,16 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, static void *mlx5_ib_add(struct mlx5_core_dev *mdev) { struct mlx5_ib_dev *dev; + enum rdma_link_layer ll; + int port_type_cap; int err; int i; + port_type_cap = MLX5_CAP_GEN(mdev, port_type); + ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); + /* don't create IB instance over Eth ports, no RoCE yet! */ - if (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) + if (ll == IB_LINK_LAYER_ETHERNET) return NULL; printk_once(KERN_INFO "%s", mlx5_version); @@ -1389,6 +1401,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->ib_dev.query_device = mlx5_ib_query_device; dev->ib_dev.query_port = mlx5_ib_query_port; + dev->ib_dev.get_link_layer = mlx5_ib_port_link_layer; dev->ib_dev.query_gid = mlx5_ib_query_gid; dev->ib_dev.query_pkey = mlx5_ib_query_pkey; dev->ib_dev.modify_device = mlx5_ib_modify_device; -- cgit v1.2.3 From fc24fc5e9530a4fde7feddaa543f5885af013461 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:17 +0200 Subject: IB/mlx5: Support IB device's callback for getting its netdev For Eth ports only: Maintain a net device pointer in mlx5_ib_device and update it upon NETDEV_REGISTER and NETDEV_UNREGISTER events if the net-device and IB device have the same PCI parent device. Implement the get_netdev callback to return this net device. Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 64 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 63 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a3295bb15891..8c6e144ae75b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -85,6 +85,41 @@ mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num) return mlx5_port_type_cap_to_rdma_ll(port_type_cap); } +static int mlx5_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct mlx5_ib_dev *ibdev = container_of(this, struct mlx5_ib_dev, + roce.nb); + + if ((event != NETDEV_UNREGISTER) && (event != NETDEV_REGISTER)) + return NOTIFY_DONE; + + write_lock(&ibdev->roce.netdev_lock); + if (ndev->dev.parent == &ibdev->mdev->pdev->dev) + ibdev->roce.netdev = (event == NETDEV_UNREGISTER) ? NULL : ndev; + write_unlock(&ibdev->roce.netdev_lock); + + return NOTIFY_DONE; +} + +static struct net_device *mlx5_ib_get_netdev(struct ib_device *device, + u8 port_num) +{ + struct mlx5_ib_dev *ibdev = to_mdev(device); + struct net_device *ndev; + + /* Ensure ndev does not disappear before we invoke dev_hold() + */ + read_lock(&ibdev->roce.netdev_lock); + ndev = ibdev->roce.netdev; + if (ndev) + dev_hold(ndev); + read_unlock(&ibdev->roce.netdev_lock); + + return ndev; +} + static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev) { return !dev->mdev->issi; @@ -1329,6 +1364,17 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } +static int mlx5_enable_roce(struct mlx5_ib_dev *dev) +{ + dev->roce.nb.notifier_call = mlx5_netdev_event; + return register_netdevice_notifier(&dev->roce.nb); +} + +static void mlx5_disable_roce(struct mlx5_ib_dev *dev) +{ + unregister_netdevice_notifier(&dev->roce.nb); +} + static void *mlx5_ib_add(struct mlx5_core_dev *mdev) { struct mlx5_ib_dev *dev; @@ -1352,6 +1398,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->mdev = mdev; + rwlock_init(&dev->roce.netdev_lock); err = get_port_caps(dev); if (err) goto err_dealloc; @@ -1402,6 +1449,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->ib_dev.query_device = mlx5_ib_query_device; dev->ib_dev.query_port = mlx5_ib_query_port; dev->ib_dev.get_link_layer = mlx5_ib_port_link_layer; + if (ll == IB_LINK_LAYER_ETHERNET) + dev->ib_dev.get_netdev = mlx5_ib_get_netdev; dev->ib_dev.query_gid = mlx5_ib_query_gid; dev->ib_dev.query_pkey = mlx5_ib_query_pkey; dev->ib_dev.modify_device = mlx5_ib_modify_device; @@ -1458,9 +1507,15 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) mutex_init(&dev->cap_mask_mutex); + if (ll == IB_LINK_LAYER_ETHERNET) { + err = mlx5_enable_roce(dev); + if (err) + goto err_dealloc; + } + err = create_dev_resources(&dev->devr); if (err) - goto err_dealloc; + goto err_disable_roce; err = mlx5_ib_odp_init_one(dev); if (err) @@ -1497,6 +1552,10 @@ err_odp: err_rsrc: destroy_dev_resources(&dev->devr); +err_disable_roce: + if (ll == IB_LINK_LAYER_ETHERNET) + mlx5_disable_roce(dev); + err_dealloc: ib_dealloc_device((struct ib_device *)dev); @@ -1506,11 +1565,14 @@ err_dealloc: static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) { struct mlx5_ib_dev *dev = context; + enum rdma_link_layer ll = mlx5_ib_port_link_layer(&dev->ib_dev, 1); ib_unregister_device(&dev->ib_dev); destroy_umrc_res(dev); mlx5_ib_odp_remove_one(dev); destroy_dev_resources(&dev->devr); + if (ll == IB_LINK_LAYER_ETHERNET) + mlx5_disable_roce(dev); ib_dealloc_device(&dev->ib_dev); } -- cgit v1.2.3 From 3f89a643eb29543af0838d37604bbc29a4e1eb60 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:21 +0200 Subject: IB/mlx5: Extend query_device/port to support RoCE Using the vport access functions to retrieve the Ethernet specific information and return this information in ib_query_device and ib_query_port. Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 75 +++++++++++++++++++++++++++++++++++---- 1 file changed, 69 insertions(+), 6 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8c6e144ae75b..2b6ac2e7b4a0 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -120,6 +121,50 @@ static struct net_device *mlx5_ib_get_netdev(struct ib_device *device, return ndev; } +static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, + struct ib_port_attr *props) +{ + struct mlx5_ib_dev *dev = to_mdev(device); + struct net_device *ndev; + enum ib_mtu ndev_ib_mtu; + + memset(props, 0, sizeof(*props)); + + props->port_cap_flags |= IB_PORT_CM_SUP; + props->port_cap_flags |= IB_PORT_IP_BASED_GIDS; + + props->gid_tbl_len = MLX5_CAP_ROCE(dev->mdev, + roce_address_table_size); + props->max_mtu = IB_MTU_4096; + props->max_msg_sz = 1 << MLX5_CAP_GEN(dev->mdev, log_max_msg); + props->pkey_tbl_len = 1; + props->state = IB_PORT_DOWN; + props->phys_state = 3; + + mlx5_query_nic_vport_qkey_viol_cntr(dev->mdev, + (u16 *)&props->qkey_viol_cntr); + + ndev = mlx5_ib_get_netdev(device, port_num); + if (!ndev) + return 0; + + if (netif_running(ndev) && netif_carrier_ok(ndev)) { + props->state = IB_PORT_ACTIVE; + props->phys_state = 5; + } + + ndev_ib_mtu = iboe_get_mtu(ndev->mtu); + + dev_put(ndev); + + props->active_mtu = min(props->max_mtu, ndev_ib_mtu); + + props->active_width = IB_WIDTH_4X; /* TODO */ + props->active_speed = IB_SPEED_QDR; /* TODO */ + + return 0; +} + static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev) { return !dev->mdev->issi; @@ -158,13 +203,21 @@ static int mlx5_query_system_image_guid(struct ib_device *ibdev, case MLX5_VPORT_ACCESS_METHOD_HCA: err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp); - if (!err) - *sys_image_guid = cpu_to_be64(tmp); - return err; + break; + + case MLX5_VPORT_ACCESS_METHOD_NIC: + err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp); + break; default: return -EINVAL; } + + if (!err) + *sys_image_guid = cpu_to_be64(tmp); + + return err; + } static int mlx5_query_max_pkeys(struct ib_device *ibdev, @@ -218,13 +271,20 @@ static int mlx5_query_node_guid(struct mlx5_ib_dev *dev, case MLX5_VPORT_ACCESS_METHOD_HCA: err = mlx5_query_hca_vport_node_guid(dev->mdev, &tmp); - if (!err) - *node_guid = cpu_to_be64(tmp); - return err; + break; + + case MLX5_VPORT_ACCESS_METHOD_NIC: + err = mlx5_query_nic_vport_node_guid(dev->mdev, &tmp); + break; default: return -EINVAL; } + + if (!err) + *node_guid = cpu_to_be64(tmp); + + return err; } struct mlx5_reg_node_desc { @@ -522,6 +582,9 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port, case MLX5_VPORT_ACCESS_METHOD_HCA: return mlx5_query_hca_port(ibdev, port, props); + case MLX5_VPORT_ACCESS_METHOD_NIC: + return mlx5_query_port_roce(ibdev, port, props); + default: return -EINVAL; } -- cgit v1.2.3 From 3cca26069a4b7f6d8fd3dc0ed707e795c22712e2 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:23 +0200 Subject: IB/mlx5: Support IB device's callbacks for adding/deleting GIDs These callbacks write into the mlx5 RoCE address table. Upon del_gid we write a zero'd GID. Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 89 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 2b6ac2e7b4a0..bbe92caba93b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -165,6 +165,93 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, return 0; } +static void ib_gid_to_mlx5_roce_addr(const union ib_gid *gid, + const struct ib_gid_attr *attr, + void *mlx5_addr) +{ +#define MLX5_SET_RA(p, f, v) MLX5_SET(roce_addr_layout, p, f, v) + char *mlx5_addr_l3_addr = MLX5_ADDR_OF(roce_addr_layout, mlx5_addr, + source_l3_address); + void *mlx5_addr_mac = MLX5_ADDR_OF(roce_addr_layout, mlx5_addr, + source_mac_47_32); + + if (!gid) + return; + + ether_addr_copy(mlx5_addr_mac, attr->ndev->dev_addr); + + if (is_vlan_dev(attr->ndev)) { + MLX5_SET_RA(mlx5_addr, vlan_valid, 1); + MLX5_SET_RA(mlx5_addr, vlan_id, vlan_dev_vlan_id(attr->ndev)); + } + + switch (attr->gid_type) { + case IB_GID_TYPE_IB: + MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_1); + break; + case IB_GID_TYPE_ROCE_UDP_ENCAP: + MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_2); + break; + + default: + WARN_ON(true); + } + + if (attr->gid_type != IB_GID_TYPE_IB) { + if (ipv6_addr_v4mapped((void *)gid)) + MLX5_SET_RA(mlx5_addr, roce_l3_type, + MLX5_ROCE_L3_TYPE_IPV4); + else + MLX5_SET_RA(mlx5_addr, roce_l3_type, + MLX5_ROCE_L3_TYPE_IPV6); + } + + if ((attr->gid_type == IB_GID_TYPE_IB) || + !ipv6_addr_v4mapped((void *)gid)) + memcpy(mlx5_addr_l3_addr, gid, sizeof(*gid)); + else + memcpy(&mlx5_addr_l3_addr[12], &gid->raw[12], 4); +} + +static int set_roce_addr(struct ib_device *device, u8 port_num, + unsigned int index, + const union ib_gid *gid, + const struct ib_gid_attr *attr) +{ + struct mlx5_ib_dev *dev = to_mdev(device); + u32 in[MLX5_ST_SZ_DW(set_roce_address_in)]; + u32 out[MLX5_ST_SZ_DW(set_roce_address_out)]; + void *in_addr = MLX5_ADDR_OF(set_roce_address_in, in, roce_address); + enum rdma_link_layer ll = mlx5_ib_port_link_layer(device, port_num); + + if (ll != IB_LINK_LAYER_ETHERNET) + return -EINVAL; + + memset(in, 0, sizeof(in)); + + ib_gid_to_mlx5_roce_addr(gid, attr, in_addr); + + MLX5_SET(set_roce_address_in, in, roce_address_index, index); + MLX5_SET(set_roce_address_in, in, opcode, MLX5_CMD_OP_SET_ROCE_ADDRESS); + + memset(out, 0, sizeof(out)); + return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_ib_add_gid(struct ib_device *device, u8 port_num, + unsigned int index, const union ib_gid *gid, + const struct ib_gid_attr *attr, + __always_unused void **context) +{ + return set_roce_addr(device, port_num, index, gid, attr); +} + +static int mlx5_ib_del_gid(struct ib_device *device, u8 port_num, + unsigned int index, __always_unused void **context) +{ + return set_roce_addr(device, port_num, index, NULL, NULL); +} + static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev) { return !dev->mdev->issi; @@ -1515,6 +1602,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) if (ll == IB_LINK_LAYER_ETHERNET) dev->ib_dev.get_netdev = mlx5_ib_get_netdev; dev->ib_dev.query_gid = mlx5_ib_query_gid; + dev->ib_dev.add_gid = mlx5_ib_add_gid; + dev->ib_dev.del_gid = mlx5_ib_del_gid; dev->ib_dev.query_pkey = mlx5_ib_query_pkey; dev->ib_dev.modify_device = mlx5_ib_modify_device; dev->ib_dev.modify_port = mlx5_ib_modify_port; -- cgit v1.2.3 From 2811ba51b04958cd001b6409c9f70e8563376346 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:24 +0200 Subject: IB/mlx5: Add RoCE fields to Address Vector Set the address handle and QP address path fields according to the link layer type (IB/Eth). Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bbe92caba93b..3ee431ab8ea9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -252,6 +253,26 @@ static int mlx5_ib_del_gid(struct ib_device *device, u8 port_num, return set_roce_addr(device, port_num, index, NULL, NULL); } +__be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num, + int index) +{ + struct ib_gid_attr attr; + union ib_gid gid; + + if (ib_get_cached_gid(&dev->ib_dev, port_num, index, &gid, &attr)) + return 0; + + if (!attr.ndev) + return 0; + + dev_put(attr.ndev); + + if (attr.gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP) + return 0; + + return cpu_to_be16(MLX5_CAP_ROCE(dev->mdev, r_roce_min_src_udp_port)); +} + static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev) { return !dev->mdev->issi; -- cgit v1.2.3 From e53505a802048dc0292609c56411ffdaad013c8e Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Wed, 23 Dec 2015 18:47:25 +0200 Subject: IB/mlx5: Support RoCE Advertise RoCE support for IB/core layer and set the hardware to work in RoCE mode. Signed-off-by: Achiad Shochat Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 48 +++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 3ee431ab8ea9..22ae0939b20e 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1517,6 +1517,32 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr) mlx5_ib_dealloc_pd(devr->p0); } +static u32 get_core_cap_flags(struct ib_device *ibdev) +{ + struct mlx5_ib_dev *dev = to_mdev(ibdev); + enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, 1); + u8 l3_type_cap = MLX5_CAP_ROCE(dev->mdev, l3_type); + u8 roce_version_cap = MLX5_CAP_ROCE(dev->mdev, roce_version); + u32 ret = 0; + + if (ll == IB_LINK_LAYER_INFINIBAND) + return RDMA_CORE_PORT_IBA_IB; + + if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV4_CAP)) + return 0; + + if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV6_CAP)) + return 0; + + if (roce_version_cap & MLX5_ROCE_VERSION_1_CAP) + ret |= RDMA_CORE_PORT_IBA_ROCE; + + if (roce_version_cap & MLX5_ROCE_VERSION_2_CAP) + ret |= RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; + + return ret; +} + static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, struct ib_port_immutable *immutable) { @@ -1529,7 +1555,7 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, immutable->pkey_tbl_len = attr.pkey_tbl_len; immutable->gid_tbl_len = attr.gid_tbl_len; - immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + immutable->core_cap_flags = get_core_cap_flags(ibdev); immutable->max_mad_size = IB_MGMT_MAD_SIZE; return 0; @@ -1537,12 +1563,27 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, static int mlx5_enable_roce(struct mlx5_ib_dev *dev) { + int err; + dev->roce.nb.notifier_call = mlx5_netdev_event; - return register_netdevice_notifier(&dev->roce.nb); + err = register_netdevice_notifier(&dev->roce.nb); + if (err) + return err; + + err = mlx5_nic_vport_enable_roce(dev->mdev); + if (err) + goto err_unregister_netdevice_notifier; + + return 0; + +err_unregister_netdevice_notifier: + unregister_netdevice_notifier(&dev->roce.nb); + return err; } static void mlx5_disable_roce(struct mlx5_ib_dev *dev) { + mlx5_nic_vport_disable_roce(dev->mdev); unregister_netdevice_notifier(&dev->roce.nb); } @@ -1557,8 +1598,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); - /* don't create IB instance over Eth ports, no RoCE yet! */ - if (ll == IB_LINK_LAYER_ETHERNET) + if ((ll == IB_LINK_LAYER_ETHERNET) && !MLX5_CAP_GEN(mdev, roce)) return NULL; printk_once(KERN_INFO "%s", mlx5_version); -- cgit v1.2.3 From 7c60bcbb68122b39fe3e92143abce01be75f3fa6 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Tue, 15 Dec 2015 20:30:11 +0200 Subject: IB/mlx5: Add support for hca_core_clock and timestamp_mask Reporting the hca_core_clock (in kHZ) and the timestamp_mask in query_device extended verb. timestamp_mask is used by users in order to know what is the valid range of the raw timestamps, while hca_core_clock reports the clock frequency that is used for timestamps. Signed-off-by: Matan Barak Reviewed-by: Moshe Lazer Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 22ae0939b20e..2d7fac53214f 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -503,6 +503,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * props->max_mcast_grp; props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */ + props->hca_core_clock = MLX5_CAP_GEN(mdev, device_frequency_khz); + props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL; #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING if (MLX5_CAP_GEN(mdev, pg)) -- cgit v1.2.3 From b368d7cb8ceb77f481b066bd8be5fada82da7301 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Tue, 15 Dec 2015 20:30:12 +0200 Subject: IB/mlx5: Add hca_core_clock_offset to udata in init_ucontext Pass hca_core_clock_offset to user-space is mandatory in order to let the user-space read the free-running clock register from the right offset in the memory mapped page. Passing this value is done by changing the vendor's command and response of init_ucontext to be in extensible form. Signed-off-by: Matan Barak Reviewed-by: Moshe Lazer Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 37 +++++++++++++++++++++++++++++-------- 1 file changed, 29 insertions(+), 8 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 2d7fac53214f..a3ae9ccde460 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -795,8 +795,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - struct mlx5_ib_alloc_ucontext_req_v2 req; - struct mlx5_ib_alloc_ucontext_resp resp; + struct mlx5_ib_alloc_ucontext_req_v2 req = {}; + struct mlx5_ib_alloc_ucontext_resp resp = {}; struct mlx5_ib_ucontext *context; struct mlx5_uuar_info *uuari; struct mlx5_uar *uars; @@ -811,20 +811,19 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (!dev->ib_active) return ERR_PTR(-EAGAIN); - memset(&req, 0, sizeof(req)); reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req)) ver = 0; - else if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req_v2)) + else if (reqlen >= sizeof(struct mlx5_ib_alloc_ucontext_req_v2)) ver = 2; else return ERR_PTR(-EINVAL); - err = ib_copy_from_udata(&req, udata, reqlen); + err = ib_copy_from_udata(&req, udata, min(reqlen, sizeof(req))); if (err) return ERR_PTR(err); - if (req.flags || req.reserved) + if (req.flags) return ERR_PTR(-EINVAL); if (req.total_num_uuars > MLX5_MAX_UUARS) @@ -833,6 +832,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (req.total_num_uuars == 0) return ERR_PTR(-EINVAL); + if (req.comp_mask) + return ERR_PTR(-EOPNOTSUPP); + + if (reqlen > sizeof(req) && + !ib_is_udata_cleared(udata, sizeof(req), + udata->inlen - sizeof(req))) + return ERR_PTR(-EOPNOTSUPP); + req.total_num_uuars = ALIGN(req.total_num_uuars, MLX5_NON_FP_BF_REGS_PER_PAGE); if (req.num_low_latency_uuars > req.total_num_uuars - 1) @@ -848,6 +855,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); + resp.response_length = min(offsetof(typeof(resp), response_length) + + sizeof(resp.response_length), udata->outlen); context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) @@ -898,8 +907,20 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.tot_uuars = req.total_num_uuars; resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports); - err = ib_copy_to_udata(udata, &resp, - sizeof(resp) - sizeof(resp.reserved)); + + if (field_avail(typeof(resp), reserved2, udata->outlen)) + resp.response_length += sizeof(resp.reserved2); + + if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { + resp.comp_mask |= + MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET; + resp.hca_core_clock_offset = + offsetof(struct mlx5_init_seg, internal_timer_h) % + PAGE_SIZE; + resp.response_length += sizeof(resp.hca_core_clock_offset); + } + + err = ib_copy_to_udata(udata, &resp, resp.response_length); if (err) goto out_uars; -- cgit v1.2.3 From d69e3bcf79764ed833e0cc6e0645dc87589cec22 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Tue, 15 Dec 2015 20:30:13 +0200 Subject: IB/mlx5: Mmap the HCA's core clock register to user-space In order to read the HCA's current cycles register, we need to map it to user-space. Add support to map this register via mmap command. Signed-off-by: Matan Barak Reviewed-by: Moshe Lazer Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a3ae9ccde460..602f067c14cc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1023,6 +1023,34 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm case MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES: return -ENOSYS; + case MLX5_IB_MMAP_CORE_CLOCK: + { + phys_addr_t pfn; + + if (vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL; + + if (vma->vm_flags & (VM_WRITE | VM_EXEC)) + return -EPERM; + + /* Don't expose to user-space information it shouldn't have */ + if (PAGE_SIZE > 4096) + return -EOPNOTSUPP; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + pfn = (dev->mdev->iseg_base + + offsetof(struct mlx5_init_seg, internal_timer_h)) >> + PAGE_SHIFT; + if (io_remap_pfn_range(vma, vma->vm_start, pfn, + PAGE_SIZE, vma->vm_page_prot)) + return -EAGAIN; + + mlx5_ib_dbg(dev, "mapped internal timer at 0x%lx, PA 0x%llx\n", + vma->vm_start, + (unsigned long long)pfn << PAGE_SHIFT); + break; + } + default: return -EINVAL; } -- cgit v1.2.3 From 051f263098a90d208e2d20251bfd4834bc783214 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 20 Dec 2015 12:16:11 +0200 Subject: IB/mlx5: Add driver cross-channel support Add support of cross-channel functionality to mlx5 driver. This includes ability to ignore overrun for CQ which intended for cross-channel, export device capability and configure the QP to be sync master/slave queues. The cross-channel enabled QP supports combination of three possible properties: * WQE processing on the receive queue of this QP * WQE processing on the send queue of this QP * WQE are supported on the send queue Reviewed-by: Sagi Grimberg Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 602f067c14cc..8bee6fe732a1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -512,6 +512,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->odp_caps = dev->odp_caps; #endif + if (MLX5_CAP_GEN(mdev, cd)) + props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL; + return 0; } -- cgit v1.2.3 From da7525d2a9ae9d9d9af754441befcf2560f6cac3 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 14 Dec 2015 16:34:10 +0200 Subject: IB/mlx5: Advertise atomic capabilities in query device In order to ensure IB spec atomic correctness in atomic operations, if HW is configured to host endianness, advertise IB_ATOMIC_HCA. if not, advertise IB_ATOMIC_NONE. Signed-off-by: Eran Ben Elisha Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8bee6fe732a1..03ce0f9fdd86 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -65,6 +65,10 @@ static char mlx5_version[] = DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v" DRIVER_VERSION " (" DRIVER_RELDATE ")\n"; +enum { + MLX5_ATOMIC_SIZE_QP_8BYTES = 1 << 3, +}; + static enum rdma_link_layer mlx5_port_type_cap_to_rdma_ll(int port_type_cap) { @@ -296,6 +300,28 @@ static int mlx5_get_vport_access_method(struct ib_device *ibdev) return MLX5_VPORT_ACCESS_METHOD_HCA; } +static void get_atomic_caps(struct mlx5_ib_dev *dev, + struct ib_device_attr *props) +{ + u8 tmp; + u8 atomic_operations = MLX5_CAP_ATOMIC(dev->mdev, atomic_operations); + u8 atomic_size_qp = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_qp); + u8 atomic_req_8B_endianness_mode = + MLX5_CAP_ATOMIC(dev->mdev, atomic_req_8B_endianess_mode); + + /* Check if HW supports 8 bytes standard atomic operations and capable + * of host endianness respond + */ + tmp = MLX5_ATOMIC_OPS_CMP_SWAP | MLX5_ATOMIC_OPS_FETCH_ADD; + if (((atomic_operations & tmp) == tmp) && + (atomic_size_qp & MLX5_ATOMIC_SIZE_QP_8BYTES) && + (atomic_req_8B_endianness_mode)) { + props->atomic_cap = IB_ATOMIC_HCA; + } else { + props->atomic_cap = IB_ATOMIC_NONE; + } +} + static int mlx5_query_system_image_guid(struct ib_device *ibdev, __be64 *sys_image_guid) { @@ -496,7 +522,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp; props->max_srq_sge = max_rq_sg - 1; props->max_fast_reg_page_list_len = (unsigned int)-1; - props->atomic_cap = IB_ATOMIC_NONE; + get_atomic_caps(dev, props); props->masked_atomic_cap = IB_ATOMIC_NONE; props->max_mcast_grp = 1 << MLX5_CAP_GEN(mdev, log_max_mcg); props->max_mcast_qp_attach = MLX5_CAP_GEN(mdev, max_qp_mcg); -- cgit v1.2.3 From 88115fe7a0e45a200a6ae9d07e424c62fb13621a Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 18 Dec 2015 13:53:20 +0200 Subject: IB/mlx5: report tx/rx checksum cap in query results This patch will report the tx/rx checksum cap for raw qp via the query device results. Signed-off-by: Bodong Wang Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 03ce0f9fdd86..5e3d3aea35bc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -496,6 +496,10 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, if (MLX5_CAP_GEN(mdev, block_lb_mc)) props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK; + if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) && + (MLX5_CAP_ETH(dev->mdev, csum_cap))) + props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM; + props->vendor_part_id = mdev->pdev->device; props->hw_ver = mdev->pdev->revision; -- cgit v1.2.3 From 9f17768611ebf81dfac69948dd12622b6f2e45fc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 14 Jan 2016 08:11:40 +0200 Subject: IB/mlx5: Expose correct maximum number of CQE capacity Maximum number of EQE capacity per CQ was mistakenly exposed as CQE. Fix that. Fixes: 938fe83c8dcb ("net/mlx5_core: New device capabilities handling") Signed-off-by: Leon Romanovsky Cc: Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5e3d3aea35bc..155dbe3826f8 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -515,7 +515,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->max_sge = min(max_rq_sg, max_sq_sg); props->max_sge_rd = props->max_sge; props->max_cq = 1 << MLX5_CAP_GEN(mdev, log_max_cq); - props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_eq_sz)) - 1; + props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1; props->max_mr = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); props->max_pd = 1 << MLX5_CAP_GEN(mdev, log_max_pd); props->max_qp_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_req_qp); -- cgit v1.2.3 From 50ca6ed21e7c389c250ee30b0bb4df66157a1115 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 19 Jan 2016 11:11:24 +0200 Subject: IB/mlx5: Delete locally redefined variable Fix the following sparse warning: drivers/infiniband/hw/mlx5/main.c:1061:29: warning: symbol 'pfn' shadows an earlier one drivers/infiniband/hw/mlx5/main.c:1030:21: originally declared here Fixes: d69e3bcf7976 ('IB/mlx5: Mmap the HCA's core clock register to user-space') Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 155dbe3826f8..5dffb9e6abec 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1057,9 +1057,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm return -ENOSYS; case MLX5_IB_MMAP_CORE_CLOCK: - { - phys_addr_t pfn; - if (vma->vm_end - vma->vm_start != PAGE_SIZE) return -EINVAL; @@ -1082,7 +1079,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm vma->vm_start, (unsigned long long)pfn << PAGE_SHIFT); break; - } default: return -EINVAL; -- cgit v1.2.3 From c876a1b7dd6da5dd2d54990fa2772cbfe3779726 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sat, 9 Jan 2016 13:06:25 +0200 Subject: IB/mlx5: Fix passing casted pointer in mlx5_query_port_roce Fix static checker warning: drivers/infiniband/hw/mlx5/main.c:149 mlx5_query_port_roce() warn: passing casted pointer '&props->qkey_viol_cntr' to 'mlx5_query_nic_vport_qkey_viol_cntr()' 32 vs 16. Fixes: 3f89a643eb29 ("IB/mlx5: Extend query_device/port to support RoCE") Reported-by: Dan Carpenter Signed-off-by: Leon Romanovsky Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5dffb9e6abec..f509dcb85665 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -132,6 +132,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, struct mlx5_ib_dev *dev = to_mdev(device); struct net_device *ndev; enum ib_mtu ndev_ib_mtu; + u16 qkey_viol_cntr; memset(props, 0, sizeof(*props)); @@ -146,8 +147,8 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, props->state = IB_PORT_DOWN; props->phys_state = 3; - mlx5_query_nic_vport_qkey_viol_cntr(dev->mdev, - (u16 *)&props->qkey_viol_cntr); + mlx5_query_nic_vport_qkey_viol_cntr(dev->mdev, &qkey_viol_cntr); + props->qkey_viol_cntr = qkey_viol_cntr; ndev = mlx5_ib_get_netdev(device, port_num); if (!ndev) -- cgit v1.2.3 From dfbee8598d24668b882bcc97d28d5108441cc88a Mon Sep 17 00:00:00 2001 From: Haggai Abramovsky Date: Thu, 14 Jan 2016 19:12:56 +0200 Subject: IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext The wrong buffer size was passed to ib_is_udata_cleared. Signed-off-by: Haggai Abramovsky Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f509dcb85665..f82336699c3e 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -845,6 +845,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (!dev->ib_active) return ERR_PTR(-EAGAIN); + if (udata->inlen < sizeof(struct ib_uverbs_cmd_hdr)) + return ERR_PTR(-EINVAL); + reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req)) ver = 0; @@ -871,7 +874,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (reqlen > sizeof(req) && !ib_is_udata_cleared(udata, sizeof(req), - udata->inlen - sizeof(req))) + reqlen - sizeof(req))) return ERR_PTR(-EOPNOTSUPP); req.total_num_uuars = ALIGN(req.total_num_uuars, -- cgit v1.2.3 From f72300c56c3bedac5fdb22cdc90f6633dc858c84 Mon Sep 17 00:00:00 2001 From: Haggai Abramovsky Date: Thu, 14 Jan 2016 19:12:58 +0200 Subject: IB/mlx5: Expose CQE version to user-space Per user context, work with CQE version that both the user-space and the kernel support. Report this CQE version via the response of the alloc_ucontext command. Signed-off-by: Haggai Abramovsky Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f82336699c3e..829c37c95d60 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -869,7 +869,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (req.total_num_uuars == 0) return ERR_PTR(-EINVAL); - if (req.comp_mask) + if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2) return ERR_PTR(-EOPNOTSUPP); if (reqlen > sizeof(req) && @@ -892,6 +892,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz); resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); + resp.cqe_version = min_t(__u8, + (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version), + req.max_cqe_version); resp.response_length = min(offsetof(typeof(resp), response_length) + sizeof(resp.response_length), udata->outlen); @@ -945,8 +948,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.tot_uuars = req.total_num_uuars; resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports); - if (field_avail(typeof(resp), reserved2, udata->outlen)) - resp.response_length += sizeof(resp.reserved2); + if (field_avail(typeof(resp), cqe_version, udata->outlen)) + resp.response_length += sizeof(resp.cqe_version); if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { resp.comp_mask |= @@ -954,7 +957,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, resp.hca_core_clock_offset = offsetof(struct mlx5_init_seg, internal_timer_h) % PAGE_SIZE; - resp.response_length += sizeof(resp.hca_core_clock_offset); + resp.response_length += sizeof(resp.hca_core_clock_offset) + + sizeof(resp.reserved2) + + sizeof(resp.reserved3); } err = ib_copy_to_udata(udata, &resp, resp.response_length); @@ -965,6 +970,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, uuari->num_low_latency_uuars = req.num_low_latency_uuars; uuari->uars = uars; uuari->num_uars = num_uars; + context->cqe_version = resp.cqe_version; + return &context->ibucontext; out_uars: -- cgit v1.2.3 From 146d2f1af3245a10b13eef263687e54f4e253d1d Mon Sep 17 00:00:00 2001 From: "majd@mellanox.com" Date: Thu, 14 Jan 2016 19:13:02 +0200 Subject: IB/mlx5: Allocate a Transport Domain for each ucontext Transport Domain groups several TIS and TIR object. By grouping these object, it defines wheather local loopback packets that are sent from the TIS objects in the group are received by the TIR objects in the same group. Allocate a Transport Domain(TD) for each user context to be used in the future by Raw Packet QP for Self-Loopback Control. Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw/mlx5/main.c') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 829c37c95d60..a55bf05c8522 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -942,6 +942,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range; #endif + if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) { + err = mlx5_core_alloc_transport_domain(dev->mdev, + &context->tdn); + if (err) + goto out_uars; + } + INIT_LIST_HEAD(&context->db_page_list); mutex_init(&context->db_page_mutex); @@ -964,7 +971,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, err = ib_copy_to_udata(udata, &resp, resp.response_length); if (err) - goto out_uars; + goto out_td; uuari->ver = ver; uuari->num_low_latency_uuars = req.num_low_latency_uuars; @@ -974,6 +981,10 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, return &context->ibucontext; +out_td: + if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) + mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn); + out_uars: for (i--; i >= 0; i--) mlx5_cmd_free_uar(dev->mdev, uars[i].index); @@ -998,6 +1009,9 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) struct mlx5_uuar_info *uuari = &context->uuari; int i; + if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) + mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn); + for (i = 0; i < uuari->num_uars; i++) { if (mlx5_cmd_free_uar(dev->mdev, uuari->uars[i].index)) mlx5_ib_warn(dev, "failed to free UAR 0x%x\n", uuari->uars[i].index); -- cgit v1.2.3