From a3100a78794175d7f2488a3155d247da3d7390e4 Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Thu, 18 Feb 2016 18:31:05 +0200 Subject: IB/core: Add don't trap flag to flow creation Don't trap flag (i.e. IB_FLOW_ATTR_FLAGS_DONT_TRAP) indicates that QP will receive traffic, but will not steal it. When a packet matches a flow steering rule that was created with the don't trap flag, the QPs assigned to this rule will get this packet, but matching will continue to other equal/lower priority rules. This will let other QPs assigned to those rules to get the packet too. If both don't trap rule and other rules have the same priority and match the same packet, the behavior is undefined. The don't trap flag can't be set with default rule types (i.e. IB_FLOW_ATTR_ALL_DEFAULT, IB_FLOW_ATTR_MC_DEFAULT) as default rules don't have rules after them and don't trap has no meaning here. Signed-off-by: Marina Varshaver Reviewed-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 284b00c8fea4..514223f522c8 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1487,6 +1487,11 @@ enum ib_flow_domain { IB_FLOW_DOMAIN_NUM /* Must be last */ }; +enum ib_flow_flags { + IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ + IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 2 /* Must be last */ +}; + struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; -- cgit v1.2.3 From 0e451e883bd13ce616f439e2414b8c17fa28318a Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Thu, 18 Feb 2016 18:31:06 +0200 Subject: IB/mlx4: Add support for the don't trap rule Add support for receiving multicast/unicast traffic with the don't trap rule. Sniffing these packets requires a flow steering rule of type NORMAL at priority 0 with flag IB_FLOW_ATTR_FLAGS_DONT_TRAP set. Choosing between multicast or unicast is done via ethernet L2 dest_mac mask and value: - If mask is all zeros - unicast and multicast are set. - If mask non zero - only mask with multicast bit 1 and rest 0 is supported, the mac value will choose if it is multicast or unicast rule. If the mask multicast bit is on and some other bits are on too, it means a request for specific multicast or unicast, this is not supported, either receive all multicast or all unicast. Only when limitations are met registered QP will receive requested type but other QPs can receive same traffic if registered for it. Otherwise, if limitations are not met, an error will be returned. Limitations: - Rule must be with priority 0. - A0 mode is not supported. - Sniffer QP cannot appear in any other flow steering rule. Signed-off-by: Marina Varshaver Reviewed-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/main.c | 71 ++++++++++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/fw.c | 5 ++- drivers/net/ethernet/mellanox/mlx4/mcg.c | 6 ++- include/linux/mlx4/device.h | 3 ++ 4 files changed, 78 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 41f2c25df0d6..914bc98e753f 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1643,6 +1643,56 @@ static int mlx4_ib_tunnel_steer_add(struct ib_qp *qp, struct ib_flow_attr *flow_ return err; } +static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev, + struct ib_flow_attr *flow_attr, + enum mlx4_net_trans_promisc_mode *type) +{ + int err = 0; + + if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER) || + (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC) || + (flow_attr->num_of_specs > 1) || (flow_attr->priority != 0)) { + return -EOPNOTSUPP; + } + + if (flow_attr->num_of_specs == 0) { + type[0] = MLX4_FS_MC_SNIFFER; + type[1] = MLX4_FS_UC_SNIFFER; + } else { + union ib_flow_spec *ib_spec; + + ib_spec = (union ib_flow_spec *)(flow_attr + 1); + if (ib_spec->type != IB_FLOW_SPEC_ETH) + return -EINVAL; + + /* if all is zero than MC and UC */ + if (is_zero_ether_addr(ib_spec->eth.mask.dst_mac)) { + type[0] = MLX4_FS_MC_SNIFFER; + type[1] = MLX4_FS_UC_SNIFFER; + } else { + u8 mac[ETH_ALEN] = {ib_spec->eth.mask.dst_mac[0] ^ 0x01, + ib_spec->eth.mask.dst_mac[1], + ib_spec->eth.mask.dst_mac[2], + ib_spec->eth.mask.dst_mac[3], + ib_spec->eth.mask.dst_mac[4], + ib_spec->eth.mask.dst_mac[5]}; + + /* Above xor was only on MC bit, non empty mask is valid + * only if this bit is set and rest are zero. + */ + if (!is_zero_ether_addr(&mac[0])) + return -EINVAL; + + if (is_multicast_ether_addr(ib_spec->eth.val.dst_mac)) + type[0] = MLX4_FS_MC_SNIFFER; + else + type[0] = MLX4_FS_UC_SNIFFER; + } + } + + return err; +} + static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain) @@ -1653,7 +1703,8 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct mlx4_dev *dev = (to_mdev(qp->device))->dev; int is_bonded = mlx4_is_bonded(dev); - if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) + if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) && + (flow_attr->type != IB_FLOW_ATTR_NORMAL)) return ERR_PTR(-EOPNOTSUPP); memset(type, 0, sizeof(type)); @@ -1666,7 +1717,19 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, switch (flow_attr->type) { case IB_FLOW_ATTR_NORMAL: - type[0] = MLX4_FS_REGULAR; + /* If dont trap flag (continue match) is set, under specific + * condition traffic be replicated to given qp, + * without stealing it + */ + if (unlikely(flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)) { + err = mlx4_ib_add_dont_trap_rule(dev, + flow_attr, + type); + if (err) + goto err_free; + } else { + type[0] = MLX4_FS_REGULAR; + } break; case IB_FLOW_ATTR_ALL_DEFAULT: @@ -1678,8 +1741,8 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, break; case IB_FLOW_ATTR_SNIFFER: - type[0] = MLX4_FS_UC_SNIFFER; - type[1] = MLX4_FS_MC_SNIFFER; + type[0] = MLX4_FS_MIRROR_RX_PORT; + type[1] = MLX4_FS_MIRROR_SX_PORT; break; default: diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index d66c690a8597..e97094598b2d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -157,7 +157,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [29] = "802.1ad offload support", [31] = "Modifying loopback source checks using UPDATE_QP support", [32] = "Loopback source checks support", - [33] = "RoCEv2 support" + [33] = "RoCEv2 support", + [34] = "DMFS Sniffer support (UC & MC)" }; int i; @@ -810,6 +811,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (field & 0x80) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN; dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f; + if (field & 0x20) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER; MLX4_GET(field, outbox, QUERY_DEV_CAP_PORT_BEACON_OFFSET); if (field & 0x80) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_BEACON; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 1d4e2e054647..42d8de892bfe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -752,8 +752,10 @@ static const u8 __promisc_mode[] = { [MLX4_FS_REGULAR] = 0x0, [MLX4_FS_ALL_DEFAULT] = 0x1, [MLX4_FS_MC_DEFAULT] = 0x3, - [MLX4_FS_UC_SNIFFER] = 0x4, - [MLX4_FS_MC_SNIFFER] = 0x5, + [MLX4_FS_MIRROR_RX_PORT] = 0x4, + [MLX4_FS_MIRROR_SX_PORT] = 0x5, + [MLX4_FS_UC_SNIFFER] = 0x6, + [MLX4_FS_MC_SNIFFER] = 0x7, }; int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a0e8cc8dcc67..8541a913f6a3 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -219,6 +219,7 @@ enum { MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB = 1ULL << 31, MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32, MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, + MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, }; enum { @@ -1160,6 +1161,8 @@ enum mlx4_net_trans_promisc_mode { MLX4_FS_REGULAR = 1, MLX4_FS_ALL_DEFAULT, MLX4_FS_MC_DEFAULT, + MLX4_FS_MIRROR_RX_PORT, + MLX4_FS_MIRROR_SX_PORT, MLX4_FS_UC_SNIFFER, MLX4_FS_MC_SNIFFER, MLX4_FS_MODE_NUM, /* should be last */ -- cgit v1.2.3 From b54ba2772b7af82a07eb48f88c88f7cadfb33401 Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:14:59 +0200 Subject: net/mlx5_core: Add helper function to read virtual port counters Added helper function to read 64bit virtual port Infiniband traffic counters. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 40 +++++++++++++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 3 +- include/linux/mlx5/vport.h | 2 ++ 3 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index c7398b95aecd..90ab09e375b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -850,3 +850,43 @@ int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev) return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED); } EXPORT_SYMBOL_GPL(mlx5_nic_vport_disable_roce); + +int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, void *out, size_t out_sz) +{ + int in_sz = MLX5_ST_SZ_BYTES(query_vport_counter_in); + int is_group_manager; + void *in; + int err; + + is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager); + in = mlx5_vzalloc(in_sz); + if (!in) { + err = -ENOMEM; + return err; + } + + MLX5_SET(query_vport_counter_in, in, opcode, + MLX5_CMD_OP_QUERY_VPORT_COUNTER); + if (other_vport) { + if (is_group_manager) { + MLX5_SET(query_vport_counter_in, in, other_vport, 1); + MLX5_SET(query_vport_counter_in, in, vport_number, 0); + } else { + err = -EPERM; + goto free; + } + } + if (MLX5_CAP_GEN(dev, num_ports) == 2) + MLX5_SET(query_vport_counter_in, in, port_num, port_num); + + err = mlx5_cmd_exec(dev, in, in_sz, out, out_sz); + if (err) + goto free; + err = mlx5_cmd_status_to_err_v2(out); + +free: + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..0732e6c1fe7a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3126,7 +3126,8 @@ struct mlx5_ifc_query_vport_counter_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 reserved_at_41[0xb]; + u8 port_num[0x4]; u8 vport_number[0x10]; u8 reserved_at_60[0x60]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 123771003e68..a9f2bcc98cab 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -92,5 +92,7 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev); int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev); +int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, void *out, size_t out_sz); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 1c64bf6f291cae7cbe779e407db9477378bb4e7d Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:15:00 +0200 Subject: net/mlx5_core: Add helper function to read IB error counters Added helper function to read IB standard error counters via the PPCNT register. The PPCNT register read command provides the 32-bit error counters of both IB/RoCE link layer and transport layer. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 23 ++++++++++++++++++ include/linux/mlx5/device.h | 3 ++- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 32 ++++++++++++++++++++++++++ 4 files changed, 59 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index a87e773e93f3..5635ce7ad693 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -324,6 +324,29 @@ int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_vl_hw_cap); +int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, + u8 port_num, void *out, size_t sz) +{ + u32 *in; + int err; + + in = mlx5_vzalloc(sz); + if (!in) { + err = -ENOMEM; + return err; + } + + MLX5_SET(ppcnt_reg, in, local_port, port_num); + + MLX5_SET(ppcnt_reg, in, grp, MLX5_INFINIBAND_PORT_COUNTERS_GROUP); + err = mlx5_core_access_reg(dev, in, sz, out, + sz, MLX5_REG_PPCNT, 0, 0); + + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_core_query_ib_ppcnt); + int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause) { u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..99e2edc93d27 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1284,7 +1284,8 @@ enum { MLX5_RFC_3635_COUNTERS_GROUP = 0x3, MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP = 0x5, MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, - MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11 + MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11, + MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, }; static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e3006dcf35d..8edcd08853dd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -847,6 +847,8 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); +int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, + u8 port_num, void *out, size_t sz); static inline int fw_initializing(struct mlx5_core_dev *dev) { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0732e6c1fe7a..9f404de5f99b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1208,6 +1208,36 @@ struct mlx5_ifc_phys_layer_cntrs_bits { u8 reserved_at_640[0x180]; }; +struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { + u8 symbol_error_counter[0x10]; + + u8 link_error_recovery_counter[0x8]; + + u8 link_downed_counter[0x8]; + + u8 port_rcv_errors[0x10]; + + u8 port_rcv_remote_physical_errors[0x10]; + + u8 port_rcv_switch_relay_errors[0x10]; + + u8 port_xmit_discards[0x10]; + + u8 port_xmit_constraint_errors[0x8]; + + u8 port_rcv_constraint_errors[0x8]; + + u8 reserved_at_70[0x8]; + + u8 link_overrun_errors[0x8]; + + u8 reserved_at_80[0x10]; + + u8 vl_15_dropped[0x10]; + + u8 reserved_at_a0[0xa0]; +}; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { u8 transmit_queue_high[0x20]; @@ -2618,6 +2648,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; u8 reserved_at_0[0x7c0]; }; @@ -6955,6 +6986,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_peir_reg_bits peir_reg; struct mlx5_ifc_pelc_reg_bits pelc_reg; struct mlx5_ifc_pfcc_reg_bits pfcc_reg; + struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_pifr_reg_bits pifr_reg; struct mlx5_ifc_pipg_reg_bits pipg_reg; -- cgit v1.2.3 From 3efd9a11212d500e36c2837db853178cdaa86d5a Mon Sep 17 00:00:00 2001 From: Meny Yossefi Date: Thu, 18 Feb 2016 18:15:01 +0200 Subject: IB/mlx5: Modify MAD reading counters method to use counter registers Modify mlx5_ib_process_mad to use PPCNT and query_vport commands instead of MAD_IFC, as MAD_IFC is deprecated on new firmware versions (and doesn't support RoCE anyway). Traffic counters exist in both 32-bit and 64-bit forms. Declaring support of extended coutners results in traffic counters to be read in their 64-bit form only via the query_vport command. Error counters exist only in 32-bit form and read via PPCNT command. This commit also adds counters support in RoCE. Signed-off-by: Meny Yossefi Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mad.c | 166 ++++++++++++++++++++++++++++++++++++--- include/linux/mlx5/device.h | 23 ++++++ 2 files changed, 178 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index b84d13a487cc..41d8a0036465 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -31,8 +31,10 @@ */ #include +#include #include #include +#include #include "mlx5_ib.h" enum { @@ -57,20 +59,12 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, return mlx5_core_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, port); } -int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const struct ib_mad_hdr *in, size_t in_mad_size, - struct ib_mad_hdr *out, size_t *out_mad_size, - u16 *out_mad_pkey_index) +static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad *in_mad, struct ib_mad *out_mad) { u16 slid; int err; - const struct ib_mad *in_mad = (const struct ib_mad *)in; - struct ib_mad *out_mad = (struct ib_mad *)out; - - if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || - *out_mad_size != sizeof(*out_mad))) - return IB_MAD_RESULT_FAILURE; slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE); @@ -117,6 +111,156 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; } +static void pma_cnt_ext_assign(struct ib_pma_portcounters_ext *pma_cnt_ext, + void *out) +{ +#define MLX5_SUM_CNT(p, cntr1, cntr2) \ + (MLX5_GET64(query_vport_counter_out, p, cntr1) + \ + MLX5_GET64(query_vport_counter_out, p, cntr2)) + + pma_cnt_ext->port_xmit_data = + cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets, + transmitted_ib_multicast.octets) >> 2); + pma_cnt_ext->port_xmit_data = + cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets, + received_ib_multicast.octets) >> 2); + pma_cnt_ext->port_xmit_packets = + cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.packets, + transmitted_ib_multicast.packets)); + pma_cnt_ext->port_rcv_packets = + cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.packets, + received_ib_multicast.packets)); + pma_cnt_ext->port_unicast_xmit_packets = + MLX5_GET64_BE(query_vport_counter_out, + out, transmitted_ib_unicast.packets); + pma_cnt_ext->port_unicast_rcv_packets = + MLX5_GET64_BE(query_vport_counter_out, + out, received_ib_unicast.packets); + pma_cnt_ext->port_multicast_xmit_packets = + MLX5_GET64_BE(query_vport_counter_out, + out, transmitted_ib_multicast.packets); + pma_cnt_ext->port_multicast_rcv_packets = + MLX5_GET64_BE(query_vport_counter_out, + out, received_ib_multicast.packets); +} + +static void pma_cnt_assign(struct ib_pma_portcounters *pma_cnt, + void *out) +{ + /* Traffic counters will be reported in + * their 64bit form via ib_pma_portcounters_ext by default. + */ + void *out_pma = MLX5_ADDR_OF(ppcnt_reg, out, + counter_set); + +#define MLX5_ASSIGN_PMA_CNTR(counter_var, counter_name) { \ + counter_var = MLX5_GET_BE(typeof(counter_var), \ + ib_port_cntrs_grp_data_layout, \ + out_pma, counter_name); \ + } + + MLX5_ASSIGN_PMA_CNTR(pma_cnt->symbol_error_counter, + symbol_error_counter); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->link_error_recovery_counter, + link_error_recovery_counter); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->link_downed_counter, + link_downed_counter); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_rcv_errors, + port_rcv_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_rcv_remphys_errors, + port_rcv_remote_physical_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_rcv_switch_relay_errors, + port_rcv_switch_relay_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_xmit_discards, + port_xmit_discards); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_xmit_constraint_errors, + port_xmit_constraint_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->port_rcv_constraint_errors, + port_rcv_constraint_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->link_overrun_errors, + link_overrun_errors); + MLX5_ASSIGN_PMA_CNTR(pma_cnt->vl15_dropped, + vl_15_dropped); +} + +static int process_pma_cmd(struct ib_device *ibdev, u8 port_num, + const struct ib_mad *in_mad, struct ib_mad *out_mad) +{ + struct mlx5_ib_dev *dev = to_mdev(ibdev); + int err; + void *out_cnt; + + /* Decalring support of extended counters */ + if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) { + struct ib_class_port_info cpi = {}; + + cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH; + memcpy((out_mad->data + 40), &cpi, sizeof(cpi)); + return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; + } + + if (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT) { + struct ib_pma_portcounters_ext *pma_cnt_ext = + (struct ib_pma_portcounters_ext *)(out_mad->data + 40); + int sz = MLX5_ST_SZ_BYTES(query_vport_counter_out); + + out_cnt = mlx5_vzalloc(sz); + if (!out_cnt) + return IB_MAD_RESULT_FAILURE; + + err = mlx5_core_query_vport_counter(dev->mdev, 0, + port_num, out_cnt, sz); + if (!err) + pma_cnt_ext_assign(pma_cnt_ext, out_cnt); + } else { + struct ib_pma_portcounters *pma_cnt = + (struct ib_pma_portcounters *)(out_mad->data + 40); + int sz = MLX5_ST_SZ_BYTES(ppcnt_reg); + + out_cnt = mlx5_vzalloc(sz); + if (!out_cnt) + return IB_MAD_RESULT_FAILURE; + + err = mlx5_core_query_ib_ppcnt(dev->mdev, port_num, + out_cnt, sz); + if (!err) + pma_cnt_assign(pma_cnt, out_cnt); + } + + kvfree(out_cnt); + if (err) + return IB_MAD_RESULT_FAILURE; + + return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; +} + +int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad_hdr *in, size_t in_mad_size, + struct ib_mad_hdr *out, size_t *out_mad_size, + u16 *out_mad_pkey_index) +{ + struct mlx5_ib_dev *dev = to_mdev(ibdev); + struct mlx5_core_dev *mdev = dev->mdev; + const struct ib_mad *in_mad = (const struct ib_mad *)in; + struct ib_mad *out_mad = (struct ib_mad *)out; + + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; + + memset(out_mad->data, 0, sizeof(out_mad->data)); + + if (MLX5_CAP_GEN(mdev, vport_counters) && + in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && + in_mad->mad_hdr.method == IB_MGMT_METHOD_GET) { + return process_pma_cmd(ibdev, port_num, in_mad, out_mad); + } else { + return process_mad(ibdev, mad_flags, port_num, in_wc, in_grh, + in_mad, out_mad); + } +} + int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port) { struct ib_smp *in_mad = NULL; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 99e2edc93d27..12079fd20413 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -105,6 +105,29 @@ __mlx5_mask(typ, fld)) ___t; \ }) +/* Big endian getters */ +#define MLX5_GET64_BE(typ, p, fld) (*((__be64 *)(p) +\ + __mlx5_64_off(typ, fld))) + +#define MLX5_GET_BE(type_t, typ, p, fld) ({ \ + type_t tmp; \ + switch (sizeof(tmp)) { \ + case sizeof(u8): \ + tmp = (__force type_t)MLX5_GET(typ, p, fld); \ + break; \ + case sizeof(u16): \ + tmp = (__force type_t)cpu_to_be16(MLX5_GET(typ, p, fld)); \ + break; \ + case sizeof(u32): \ + tmp = (__force type_t)cpu_to_be32(MLX5_GET(typ, p, fld)); \ + break; \ + case sizeof(u64): \ + tmp = (__force type_t)MLX5_GET64_BE(typ, p, fld); \ + break; \ + } \ + tmp; \ + }) + enum { MLX5_MAX_COMMANDS = 32, MLX5_CMD_DATA_BLOCK_SIZE = 512, -- cgit v1.2.3 From 1015c2e8ca2b94d8964f8ab30d925b6f678fd9d2 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Sun, 21 Feb 2016 16:27:16 +0200 Subject: IB/mlx5: Define interface bits for IPoIB offloads The HW can supply several offloads for UD QP, added offloads for checksumming for both TX and RX and LSO for TX. Two new bits were added in order to expose and enable these offloads: 1. HCA capability bit: declares the support for IPoIB basic offloads. 2. QPC bit which will be used in the QP creation flow, which set these abilities in the QP. Signed-off-by: Erez Shitrit Signed-off-by: Eran Ben Elisha Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9f404de5f99b..711c9dc87f63 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -736,7 +736,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; - u8 reserved_at_200[0xe]; + u8 reserved_at_200[0x3]; + u8 ipoib_basic_offloads[0x1]; + u8 reserved_at_204[0xa]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; @@ -1810,7 +1812,7 @@ struct mlx5_ifc_qpc_bits { u8 log_sq_size[0x4]; u8 reserved_at_55[0x6]; u8 rlky[0x1]; - u8 reserved_at_5c[0x4]; + u8 ulp_stateless_offload_mode[0x4]; u8 counter_set_id[0x8]; u8 uar_page[0x18]; -- cgit v1.2.3 From b11a4f9cde1c06e0073662882b60c1fb95a1d597 Mon Sep 17 00:00:00 2001 From: Haggai Eran Date: Mon, 29 Feb 2016 15:45:03 +0200 Subject: IB/mlx5: Add support for setting source QP number In order to create multiple GSI QPs, we need to set the source QP number to one on all these QPs. Add the necessary definitions and infrastructure to do that. Reviewed-by: Leon Romanovsky Signed-off-by: Haggai Eran Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 14 ++++++++++++++ drivers/infiniband/hw/mlx5/qp.c | 17 ++++++++++++++++- include/linux/mlx5/mlx5_ifc.h | 3 ++- include/linux/mlx5/qp.h | 3 ++- 4 files changed, 34 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 14396b0eac74..32699f92480a 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -165,6 +165,18 @@ struct mlx5_ib_flow_db { #define MLX5_IB_QPT_REG_UMR IB_QPT_RESERVED1 #define MLX5_IB_WR_UMR IB_WR_RESERVED1 +/* Private QP creation flags to be passed in ib_qp_init_attr.create_flags. + * + * These flags are intended for internal use by the mlx5_ib driver, and they + * rely on the range reserved for that use in the ib_qp_create_flags enum. + */ + +/* Create a UD QP whose source QP number is 1 */ +static inline enum ib_qp_create_flags mlx5_ib_create_qp_sqpn_qp1(void) +{ + return IB_QP_CREATE_RESERVED_START; +} + struct wr_list { u16 opcode; u16 next; @@ -331,6 +343,8 @@ enum mlx5_ib_qp_flags { MLX5_IB_QP_MANAGED_SEND = IB_QP_CREATE_MANAGED_SEND, MLX5_IB_QP_MANAGED_RECV = IB_QP_CREATE_MANAGED_RECV, MLX5_IB_QP_SIGNATURE_HANDLING = 1 << 5, + /* QP uses 1 as its source QP number */ + MLX5_IB_QP_SQPN_QP1 = 1 << 6, }; struct mlx5_umr_wr { diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index baa88084d89d..794e760a17a0 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -793,7 +793,8 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, uuari = &dev->mdev->priv.uuari; if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN | IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK | - IB_QP_CREATE_IPOIB_UD_LSO)) + IB_QP_CREATE_IPOIB_UD_LSO | + mlx5_ib_create_qp_sqpn_qp1())) return -EINVAL; if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR) @@ -838,6 +839,11 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, (*in)->ctx.params1 |= cpu_to_be32(1 << 11); (*in)->ctx.sq_crq_size |= cpu_to_be16(1 << 4); + if (init_attr->create_flags & mlx5_ib_create_qp_sqpn_qp1()) { + (*in)->ctx.deth_sqpn = cpu_to_be32(1); + qp->flags |= MLX5_IB_QP_SQPN_QP1; + } + mlx5_fill_page_array(&qp->buf, (*in)->pas); err = mlx5_db_alloc(dev->mdev, &qp->db); @@ -1289,6 +1295,11 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, ucmd.sq_wqe_count, max_wqes); return -EINVAL; } + if (init_attr->create_flags & + mlx5_ib_create_qp_sqpn_qp1()) { + mlx5_ib_dbg(dev, "user-space is not allowed to create UD QPs spoofing as QP1\n"); + return -EINVAL; + } err = create_user_qp(dev, pd, qp, udata, init_attr, &in, &resp, &inlen, base); if (err) @@ -2309,6 +2320,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) context->sq_crq_size |= cpu_to_be16(1 << 4); + if (qp->flags & MLX5_IB_QP_SQPN_QP1) + context->deth_sqpn = cpu_to_be32(1); mlx5_cur = to_mlx5_state(cur_state); mlx5_new = to_mlx5_state(new_state); @@ -3973,6 +3986,8 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_init_attr->create_flags |= IB_QP_CREATE_MANAGED_SEND; if (qp->flags & MLX5_IB_QP_MANAGED_RECV) qp_init_attr->create_flags |= IB_QP_CREATE_MANAGED_RECV; + if (qp->flags & MLX5_IB_QP_SQPN_QP1) + qp_init_attr->create_flags |= mlx5_ib_create_qp_sqpn_qp1(); qp_init_attr->sq_sig_type = qp->sq_signal_bits & MLX5_WQE_CTRL_CQ_UPDATE ? IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 711c9dc87f63..72bba5261766 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -772,7 +772,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_22e[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_at_237[0x4]; + u8 set_deth_sqpn[0x1]; + u8 reserved_at_239[0x3]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 5b8c89ffaa58..e5bbcf06de95 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -499,7 +499,8 @@ struct mlx5_qp_context { u8 reserved2[4]; __be32 next_send_psn; __be32 cqn_send; - u8 reserved3[8]; + __be32 deth_sqpn; + u8 reserved3[4]; __be32 last_acked_psn; __be32 ssn; __be32 params2; -- cgit v1.2.3 From a606b0f6691daf861482f8b77326f672238ffbfd Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 29 Feb 2016 18:05:28 +0200 Subject: net/mlx5: Refactor mlx5_core_mr to mkey Mlx5's mkey mechanism is also used for memory windows. The current code base uses MR (memory region) naming, which is inaccurate. Changing MR to mkey in order to represent its different usages more accurately. Signed-off-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/cq.c | 16 +++---- drivers/infiniband/hw/mlx5/mlx5_ib.h | 6 +-- drivers/infiniband/hw/mlx5/mr.c | 58 +++++++++++------------ drivers/infiniband/hw/mlx5/odp.c | 10 ++-- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++--- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 +-- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 54 +++++++++++---------- include/linux/mlx5/driver.h | 24 +++++----- include/linux/mlx5/qp.h | 4 +- 10 files changed, 98 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 2a9ad8401750..a00ba4418de9 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -434,7 +434,7 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq, struct mlx5_core_qp *mqp; struct mlx5_ib_wq *wq; struct mlx5_sig_err_cqe *sig_err_cqe; - struct mlx5_core_mr *mmr; + struct mlx5_core_mkey *mmkey; struct mlx5_ib_mr *mr; uint8_t opcode; uint32_t qpn; @@ -539,17 +539,17 @@ repoll: case MLX5_CQE_SIG_ERR: sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64; - read_lock(&dev->mdev->priv.mr_table.lock); - mmr = __mlx5_mr_lookup(dev->mdev, - mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey))); - if (unlikely(!mmr)) { - read_unlock(&dev->mdev->priv.mr_table.lock); + read_lock(&dev->mdev->priv.mkey_table.lock); + mmkey = __mlx5_mr_lookup(dev->mdev, + mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey))); + if (unlikely(!mmkey)) { + read_unlock(&dev->mdev->priv.mkey_table.lock); mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n", cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey)); return -EINVAL; } - mr = to_mibmr(mmr); + mr = to_mibmr(mmkey); get_sig_err_item(sig_err_cqe, &mr->sig->err_item); mr->sig->sig_err_exists = true; mr->sig->sigerr_count++; @@ -561,7 +561,7 @@ repoll: mr->sig->err_item.expected, mr->sig->err_item.actual); - read_unlock(&dev->mdev->priv.mr_table.lock); + read_unlock(&dev->mdev->priv.mkey_table.lock); goto repoll; } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index f84ec2b6425c..4167d67179ff 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -446,7 +446,7 @@ struct mlx5_ib_mr { int ndescs; int max_descs; int desc_size; - struct mlx5_core_mr mmr; + struct mlx5_core_mkey mmkey; struct ib_umem *umem; struct mlx5_shared_mr_info *smr_info; struct list_head list; @@ -603,9 +603,9 @@ static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp) return container_of(mqp, struct mlx5_ib_qp_base, mqp)->container_mibqp; } -static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr) +static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mkey *mmkey) { - return container_of(mmr, struct mlx5_ib_mr, mmr); + return container_of(mmkey, struct mlx5_ib_mr, mmkey); } static inline struct mlx5_ib_pd *to_mpd(struct ib_pd *ibpd) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index cf26cd1f1fa2..399e2b5fb573 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -57,7 +57,7 @@ static int clean_mr(struct mlx5_ib_mr *mr); static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmr); + int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING /* Wait until all page fault handlers using the mr complete. */ @@ -120,7 +120,7 @@ static void reg_mr_callback(int status, void *context) struct mlx5_cache_ent *ent = &cache->ent[c]; u8 key; unsigned long flags; - struct mlx5_mr_table *table = &dev->mdev->priv.mr_table; + struct mlx5_mkey_table *table = &dev->mdev->priv.mkey_table; int err; spin_lock_irqsave(&ent->lock, flags); @@ -147,7 +147,7 @@ static void reg_mr_callback(int status, void *context) spin_lock_irqsave(&dev->mdev->priv.mkey_lock, flags); key = dev->mdev->priv.mkey_key++; spin_unlock_irqrestore(&dev->mdev->priv.mkey_lock, flags); - mr->mmr.key = mlx5_idx_to_mkey(be32_to_cpu(mr->out.mkey) & 0xffffff) | key; + mr->mmkey.key = mlx5_idx_to_mkey(be32_to_cpu(mr->out.mkey) & 0xffffff) | key; cache->last_add = jiffies; @@ -158,10 +158,10 @@ static void reg_mr_callback(int status, void *context) spin_unlock_irqrestore(&ent->lock, flags); write_lock_irqsave(&table->lock, flags); - err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmr.key), - &mr->mmr); + err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmkey.key), + &mr->mmkey); if (err) - pr_err("Error inserting to mr tree. 0x%x\n", -err); + pr_err("Error inserting to mkey tree. 0x%x\n", -err); write_unlock_irqrestore(&table->lock, flags); } @@ -202,7 +202,7 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) spin_lock_irq(&ent->lock); ent->pending++; spin_unlock_irq(&ent->lock); - err = mlx5_core_create_mkey(dev->mdev, &mr->mmr, in, + err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, sizeof(*in), reg_mr_callback, mr, &mr->out); if (err) { @@ -691,14 +691,14 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc) seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); seg->start_addr = 0; - err = mlx5_core_create_mkey(mdev, &mr->mmr, in, sizeof(*in), NULL, NULL, + err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, sizeof(*in), NULL, NULL, NULL); if (err) goto err_in; kfree(in); - mr->ibmr.lkey = mr->mmr.key; - mr->ibmr.rkey = mr->mmr.key; + mr->ibmr.lkey = mr->mmkey.key; + mr->ibmr.rkey = mr->mmkey.key; mr->umem = NULL; return &mr->ibmr; @@ -897,7 +897,7 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem, memset(&umrwr, 0, sizeof(umrwr)); umrwr.wr.wr_id = (u64)(unsigned long)&umr_context; - prep_umr_reg_wqe(pd, &umrwr.wr, &sg, dma, npages, mr->mmr.key, + prep_umr_reg_wqe(pd, &umrwr.wr, &sg, dma, npages, mr->mmkey.key, page_shift, virt_addr, len, access_flags); mlx5_ib_init_umr_context(&umr_context); @@ -914,9 +914,9 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem, } } - mr->mmr.iova = virt_addr; - mr->mmr.size = len; - mr->mmr.pd = to_mpd(pd)->pdn; + mr->mmkey.iova = virt_addr; + mr->mmkey.size = len; + mr->mmkey.pd = to_mpd(pd)->pdn; mr->live = 1; @@ -1027,7 +1027,7 @@ int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index, int npages, wr.wr.opcode = MLX5_IB_WR_UMR; wr.npages = sg.length / sizeof(u64); wr.page_shift = PAGE_SHIFT; - wr.mkey = mr->mmr.key; + wr.mkey = mr->mmkey.key; wr.target.offset = start_page_index; mlx5_ib_init_umr_context(&umr_context); @@ -1100,7 +1100,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd, in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); in->xlat_oct_act_size = cpu_to_be32(get_octo_len(virt_addr, length, 1 << page_shift)); - err = mlx5_core_create_mkey(dev->mdev, &mr->mmr, in, inlen, NULL, + err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen, NULL, NULL, NULL); if (err) { mlx5_ib_warn(dev, "create mkey failed\n"); @@ -1111,7 +1111,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd, mr->live = 1; kvfree(in); - mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmr.key); + mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmkey.key); return mr; @@ -1130,8 +1130,8 @@ static void set_mr_fileds(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, { mr->npages = npages; atomic_add(npages, &dev->mdev->priv.reg_pages); - mr->ibmr.lkey = mr->mmr.key; - mr->ibmr.rkey = mr->mmr.key; + mr->ibmr.lkey = mr->mmkey.key; + mr->ibmr.rkey = mr->mmkey.key; mr->ibmr.length = length; mr->access_flags = access_flags; } @@ -1179,7 +1179,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto error; } - mlx5_ib_dbg(dev, "mkey 0x%x\n", mr->mmr.key); + mlx5_ib_dbg(dev, "mkey 0x%x\n", mr->mmkey.key); mr->umem = umem; set_mr_fileds(dev, mr, npages, length, access_flags); @@ -1205,7 +1205,7 @@ static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) memset(&umrwr.wr, 0, sizeof(umrwr)); umrwr.wr.wr_id = (u64)(unsigned long)&umr_context; - prep_umr_unreg_wqe(dev, &umrwr.wr, mr->mmr.key); + prep_umr_unreg_wqe(dev, &umrwr.wr, mr->mmkey.key); mlx5_ib_init_umr_context(&umr_context); down(&umrc->sem); @@ -1259,7 +1259,7 @@ static int rereg_umr(struct ib_pd *pd, struct mlx5_ib_mr *mr, u64 virt_addr, umrwr.wr.send_flags |= MLX5_IB_SEND_UMR_UPDATE_TRANSLATION; } - prep_umr_wqe_common(pd, &umrwr.wr, &sg, dma, npages, mr->mmr.key, + prep_umr_wqe_common(pd, &umrwr.wr, &sg, dma, npages, mr->mmkey.key, page_shift); if (flags & IB_MR_REREG_PD) { @@ -1371,7 +1371,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (flags & IB_MR_REREG_PD) { ib_mr->pd = pd; - mr->mmr.pd = to_mpd(pd)->pdn; + mr->mmkey.pd = to_mpd(pd)->pdn; } if (flags & IB_MR_REREG_ACCESS) @@ -1380,8 +1380,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (flags & IB_MR_REREG_TRANS) { atomic_sub(mr->npages, &dev->mdev->priv.reg_pages); set_mr_fileds(dev, mr, npages, len, access_flags); - mr->mmr.iova = addr; - mr->mmr.size = len; + mr->mmkey.iova = addr; + mr->mmkey.size = len; } #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING update_odp_mr(mr); @@ -1461,7 +1461,7 @@ static int clean_mr(struct mlx5_ib_mr *mr) err = destroy_mkey(dev, mr); if (err) { mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n", - mr->mmr.key, err); + mr->mmkey.key, err); return err; } } else { @@ -1587,13 +1587,13 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, } in->seg.flags = MLX5_PERM_UMR_EN | access_mode; - err = mlx5_core_create_mkey(dev->mdev, &mr->mmr, in, sizeof(*in), + err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, sizeof(*in), NULL, NULL, NULL); if (err) goto err_destroy_psv; - mr->ibmr.lkey = mr->mmr.key; - mr->ibmr.rkey = mr->mmr.key; + mr->ibmr.lkey = mr->mmkey.key; + mr->ibmr.rkey = mr->mmkey.key; mr->umem = NULL; kfree(in); diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index b8d76361a48d..34e79e709c67 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -142,13 +142,13 @@ static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev, u32 key) { u32 base_key = mlx5_base_mkey(key); - struct mlx5_core_mr *mmr = __mlx5_mr_lookup(dev->mdev, base_key); - struct mlx5_ib_mr *mr = container_of(mmr, struct mlx5_ib_mr, mmr); + struct mlx5_core_mkey *mmkey = __mlx5_mr_lookup(dev->mdev, base_key); + struct mlx5_ib_mr *mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); - if (!mmr || mmr->key != key || !mr->live) + if (!mmkey || mmkey->key != key || !mr->live) return NULL; - return container_of(mmr, struct mlx5_ib_mr, mmr); + return container_of(mmkey, struct mlx5_ib_mr, mmkey); } static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp, @@ -232,7 +232,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_qp *qp, io_virt += pfault->mpfault.bytes_committed; bcnt -= pfault->mpfault.bytes_committed; - start_idx = (io_virt - (mr->mmr.iova & PAGE_MASK)) >> PAGE_SHIFT; + start_idx = (io_virt - (mr->mmkey.iova & PAGE_MASK)) >> PAGE_SHIFT; if (mr->umem->writable) access_mask |= ODP_WRITE_ALLOWED_BIT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830..6ef0bfded2ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -515,7 +515,7 @@ struct mlx5e_priv { struct mlx5_uar cq_uar; u32 pdn; u32 tdn; - struct mlx5_core_mr mr; + struct mlx5_core_mkey mkey; struct mlx5e_rq drop_rq; struct mlx5e_channel **channel; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4e1c3045200..43a148939557 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -982,7 +982,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->cpu = cpu; c->pdev = &priv->mdev->pdev->dev; c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mr.key); + c->mkey_be = cpu_to_be32(priv->mkey.key); c->num_tc = priv->params.num_tc; mlx5e_build_channeltc_to_txq_map(priv, ix); @@ -2194,7 +2194,7 @@ static void mlx5e_build_netdev(struct net_device *netdev) } static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn, - struct mlx5_core_mr *mr) + struct mlx5_core_mkey *mkey) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_create_mkey_mbox_in *in; @@ -2210,7 +2210,7 @@ static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn, in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64); in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); - err = mlx5_core_create_mkey(mdev, mr, in, sizeof(*in), NULL, NULL, + err = mlx5_core_create_mkey(mdev, mkey, in, sizeof(*in), NULL, NULL, NULL); kvfree(in); @@ -2259,7 +2259,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) goto err_dealloc_pd; } - err = mlx5e_create_mkey(priv, priv->pdn, &priv->mr); + err = mlx5e_create_mkey(priv, priv->pdn, &priv->mkey); if (err) { mlx5_core_err(mdev, "create mkey failed, %d\n", err); goto err_dealloc_transport_domain; @@ -2333,7 +2333,7 @@ err_destroy_tises: mlx5e_destroy_tises(priv); err_destroy_mkey: - mlx5_core_destroy_mkey(mdev, &priv->mr); + mlx5_core_destroy_mkey(mdev, &priv->mkey); err_dealloc_transport_domain: mlx5_core_dealloc_transport_domain(mdev, priv->tdn); @@ -2367,7 +2367,7 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5e_destroy_rqt(priv, MLX5E_INDIRECTION_RQT); mlx5e_close_drop_rq(priv); mlx5e_destroy_tises(priv); - mlx5_core_destroy_mkey(priv->mdev, &priv->mr); + mlx5_core_destroy_mkey(priv->mdev, &priv->mkey); mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn); mlx5_core_dealloc_pd(priv->mdev, priv->pdn); mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1545a944c309..0916bbc69269 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1117,7 +1117,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_cq_table(dev); mlx5_init_qp_table(dev); mlx5_init_srq_table(dev); - mlx5_init_mr_table(dev); + mlx5_init_mkey_table(dev); err = mlx5_init_fs(dev); if (err) { @@ -1164,7 +1164,7 @@ err_sriov: err_reg_dev: mlx5_cleanup_fs(dev); err_fs: - mlx5_cleanup_mr_table(dev); + mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); @@ -1237,7 +1237,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) #endif mlx5_cleanup_fs(dev); - mlx5_cleanup_mr_table(dev); + mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 6fa22b51e460..77a7293921d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -36,25 +36,26 @@ #include #include "mlx5_core.h" -void mlx5_init_mr_table(struct mlx5_core_dev *dev) +void mlx5_init_mkey_table(struct mlx5_core_dev *dev) { - struct mlx5_mr_table *table = &dev->priv.mr_table; + struct mlx5_mkey_table *table = &dev->priv.mkey_table; memset(table, 0, sizeof(*table)); rwlock_init(&table->lock); INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); } -void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev) +void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev) { } -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey, struct mlx5_create_mkey_mbox_in *in, int inlen, mlx5_cmd_cbk_t callback, void *context, struct mlx5_create_mkey_mbox_out *out) { - struct mlx5_mr_table *table = &dev->priv.mr_table; + struct mlx5_mkey_table *table = &dev->priv.mkey_table; struct mlx5_create_mkey_mbox_out lout; int err; u8 key; @@ -83,34 +84,35 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, return mlx5_cmd_status_to_err(&lout.hdr); } - mr->iova = be64_to_cpu(in->seg.start_addr); - mr->size = be64_to_cpu(in->seg.len); - mr->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key; - mr->pd = be32_to_cpu(in->seg.flags_pd) & 0xffffff; + mkey->iova = be64_to_cpu(in->seg.start_addr); + mkey->size = be64_to_cpu(in->seg.len); + mkey->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key; + mkey->pd = be32_to_cpu(in->seg.flags_pd) & 0xffffff; mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n", - be32_to_cpu(lout.mkey), key, mr->key); + be32_to_cpu(lout.mkey), key, mkey->key); - /* connect to MR tree */ + /* connect to mkey tree */ write_lock_irq(&table->lock); - err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr); + err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key), mkey); write_unlock_irq(&table->lock); if (err) { - mlx5_core_warn(dev, "failed radix tree insert of mr 0x%x, %d\n", - mlx5_base_mkey(mr->key), err); - mlx5_core_destroy_mkey(dev, mr); + mlx5_core_warn(dev, "failed radix tree insert of mkey 0x%x, %d\n", + mlx5_base_mkey(mkey->key), err); + mlx5_core_destroy_mkey(dev, mkey); } return err; } EXPORT_SYMBOL(mlx5_core_create_mkey); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr) +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey) { - struct mlx5_mr_table *table = &dev->priv.mr_table; + struct mlx5_mkey_table *table = &dev->priv.mkey_table; struct mlx5_destroy_mkey_mbox_in in; struct mlx5_destroy_mkey_mbox_out out; - struct mlx5_core_mr *deleted_mr; + struct mlx5_core_mkey *deleted_mkey; unsigned long flags; int err; @@ -118,16 +120,16 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr) memset(&out, 0, sizeof(out)); write_lock_irqsave(&table->lock, flags); - deleted_mr = radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key)); + deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key)); write_unlock_irqrestore(&table->lock, flags); - if (!deleted_mr) { - mlx5_core_warn(dev, "failed radix tree delete of mr 0x%x\n", - mlx5_base_mkey(mr->key)); + if (!deleted_mkey) { + mlx5_core_warn(dev, "failed radix tree delete of mkey 0x%x\n", + mlx5_base_mkey(mkey->key)); return -ENOENT; } in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_MKEY); - in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key)); + in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mkey->key)); err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); if (err) return err; @@ -139,7 +141,7 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr) } EXPORT_SYMBOL(mlx5_core_destroy_mkey); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, struct mlx5_query_mkey_mbox_out *out, int outlen) { struct mlx5_query_mkey_mbox_in in; @@ -149,7 +151,7 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, memset(out, 0, outlen); in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_MKEY); - in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key)); + in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mkey->key)); err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen); if (err) return err; @@ -161,7 +163,7 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, } EXPORT_SYMBOL(mlx5_core_query_mkey); -int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey, u32 *mkey) { struct mlx5_query_special_ctxs_mbox_in in; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8edcd08853dd..9108904a6a56 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -338,7 +338,7 @@ struct mlx5_core_sig_ctx { u32 sigerr_count; }; -struct mlx5_core_mr { +struct mlx5_core_mkey { u64 iova; u64 size; u32 key; @@ -426,7 +426,7 @@ struct mlx5_srq_table { struct radix_tree_root tree; }; -struct mlx5_mr_table { +struct mlx5_mkey_table { /* protect radix tree */ rwlock_t lock; @@ -484,9 +484,9 @@ struct mlx5_priv { struct mlx5_cq_table cq_table; /* end: cq staff */ - /* start: mr staff */ - struct mlx5_mr_table mr_table; - /* end: mr staff */ + /* start: mkey staff */ + struct mlx5_mkey_table mkey_table; + /* end: mkey staff */ /* start: alloc staff */ /* protect buffer alocation according to numa node */ @@ -739,16 +739,18 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, struct mlx5_query_srq_mbox_out *out); int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, u16 lwm, int is_srq); -void mlx5_init_mr_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev); -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +void mlx5_init_mkey_table(struct mlx5_core_dev *dev); +void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey, struct mlx5_create_mkey_mbox_in *in, int inlen, mlx5_cmd_cbk_t callback, void *context, struct mlx5_create_mkey_mbox_out *out); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, + struct mlx5_core_mkey *mkey); +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, struct mlx5_query_mkey_mbox_out *out, int outlen); -int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, +int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey, u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index e5bbcf06de95..cf031a3f16c5 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -622,9 +622,9 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); } -static inline struct mlx5_core_mr *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) +static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) { - return radix_tree_lookup(&dev->priv.mr_table.tree, key); + return radix_tree_lookup(&dev->priv.mkey_table.tree, key); } struct mlx5_page_fault_resume_mbox_in { -- cgit v1.2.3 From b2a239df4e65fe35240ddf3e5f9f31335c90589b Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 29 Feb 2016 18:05:29 +0200 Subject: IB/core: Add vendor's specific data to alloc mw Passing udata to the vendor's driver in order to pass data from the user-space driver to the kernel-space driver. This data will be used in downstream patches. Signed-off-by: Matan Barak Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs_cmd.c | 8 +++++++- drivers/infiniband/hw/cxgb3/iwch_provider.c | 3 ++- drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 3 ++- drivers/infiniband/hw/cxgb4/mem.c | 4 +++- drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 ++- drivers/infiniband/hw/mlx4/mr.c | 4 +++- drivers/infiniband/hw/nes/nes_verbs.c | 3 ++- include/rdma/ib_verbs.h | 3 ++- 8 files changed, 23 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 6ffc9c4e93af..2bf751ecad15 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1174,6 +1174,7 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file, struct ib_uobject *uobj; struct ib_pd *pd; struct ib_mw *mw; + struct ib_udata udata; int ret; if (out_len < sizeof(resp)) @@ -1195,7 +1196,12 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file, goto err_free; } - mw = pd->device->alloc_mw(pd, cmd.mw_type); + INIT_UDATA(&udata, buf + sizeof(cmd), + (unsigned long)cmd.response + sizeof(resp), + in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof(resp)); + + mw = pd->device->alloc_mw(pd, cmd.mw_type, &udata); if (IS_ERR(mw)) { ret = PTR_ERR(mw); goto err_put; diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 2734820d291b..42a7b8952d13 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -657,7 +657,8 @@ err: return ERR_PTR(err); } -static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd, enum ib_mw_type type) +static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata) { struct iwch_dev *rhp; struct iwch_pd *php; diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index fb2de75a0392..423a3a91bf41 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -961,7 +961,8 @@ int c4iw_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents); int c4iw_dealloc_mw(struct ib_mw *mw); -struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type); +struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata); struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt, int acc, struct ib_udata *udata); diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 7849890c4781..766d39cff06c 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "iw_cxgb4.h" @@ -552,7 +553,8 @@ err: return ERR_PTR(err); } -struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type) +struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata) { struct c4iw_dev *rhp; struct c4iw_pd *php; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 52ce7b000044..1eca01cebe51 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -711,7 +711,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int access_flags, struct ib_udata *udata); int mlx4_ib_dereg_mr(struct ib_mr *mr); -struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type); +struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata); int mlx4_ib_dealloc_mw(struct ib_mw *mw); struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 242b94ec105b..ce0b5aa8eb9b 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -32,6 +32,7 @@ */ #include +#include #include "mlx4_ib.h" @@ -334,7 +335,8 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr) return 0; } -struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type) +struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata) { struct mlx4_ib_dev *dev = to_mdev(pd->device); struct mlx4_ib_mw *mw; diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 8c4daf7f22ec..5af19b4cde51 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -56,7 +56,8 @@ static int nes_dereg_mr(struct ib_mr *ib_mr); /** * nes_alloc_mw */ -static struct ib_mw *nes_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type) +static struct ib_mw *nes_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type, + struct ib_udata *udata) { struct nes_pd *nespd = to_nespd(ibpd); struct nes_vnic *nesvnic = to_nesvnic(ibpd->device); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 284b00c8fea4..3f79070de547 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1808,7 +1808,8 @@ struct ib_device { struct scatterlist *sg, int sg_nents); struct ib_mw * (*alloc_mw)(struct ib_pd *pd, - enum ib_mw_type type); + enum ib_mw_type type, + struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); struct ib_fmr * (*alloc_fmr)(struct ib_pd *pd, int mr_access_flags, -- cgit v1.2.3 From d2370e0a573e5c5ea9c96373558727abb3ea71f7 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 29 Feb 2016 18:05:30 +0200 Subject: IB/mlx5: Add memory windows allocation support This patch adds user-space support for memory windows allocation and deallocation. It also exposes the supported types via query_device_caps verb. Signed-off-by: Matan Barak Reviewed-by: Yishai Hadas Tested-by: Max Gurtovoy Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 13 ++++++ drivers/infiniband/hw/mlx5/mlx5_ib.h | 14 ++++++ drivers/infiniband/hw/mlx5/mr.c | 83 ++++++++++++++++++++++++++++++++++++ drivers/infiniband/hw/mlx5/user.h | 7 +++ include/linux/mlx5/mlx5_ifc.h | 4 +- 5 files changed, 120 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 16f7d0b41c04..4d9b7cc4ca73 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -487,6 +487,11 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG; if (MLX5_CAP_GEN(mdev, xrc)) props->device_cap_flags |= IB_DEVICE_XRC; + if (MLX5_CAP_GEN(mdev, imaicl)) { + props->device_cap_flags |= IB_DEVICE_MEM_WINDOW | + IB_DEVICE_MEM_WINDOW_TYPE_2B; + props->max_mw = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); + } props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; if (MLX5_CAP_GEN(mdev, sho)) { props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER; @@ -2306,6 +2311,14 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) mlx5_ib_internal_fill_odp_caps(dev); + if (MLX5_CAP_GEN(mdev, imaicl)) { + dev->ib_dev.alloc_mw = mlx5_ib_alloc_mw; + dev->ib_dev.dealloc_mw = mlx5_ib_dealloc_mw; + dev->ib_dev.uverbs_cmd_mask |= + (1ull << IB_USER_VERBS_CMD_ALLOC_MW) | + (1ull << IB_USER_VERBS_CMD_DEALLOC_MW); + } + if (MLX5_CAP_GEN(mdev, xrc)) { dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd; dev->ib_dev.dealloc_xrcd = mlx5_ib_dealloc_xrcd; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 4167d67179ff..648d2e2e445b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -43,6 +43,7 @@ #include #include #include +#include #define mlx5_ib_dbg(dev, format, arg...) \ pr_debug("%s:%s:%d:(pid %d): " format, (dev)->ib_dev.name, __func__, \ @@ -461,6 +462,11 @@ struct mlx5_ib_mr { int access_flags; /* Needed for rereg MR */ }; +struct mlx5_ib_mw { + struct ib_mw ibmw; + struct mlx5_core_mkey mmkey; +}; + struct mlx5_ib_umr_context { enum ib_wc_status status; struct completion done; @@ -633,6 +639,11 @@ static inline struct mlx5_ib_mr *to_mmr(struct ib_mr *ibmr) return container_of(ibmr, struct mlx5_ib_mr, ibmr); } +static inline struct mlx5_ib_mw *to_mmw(struct ib_mw *ibmw) +{ + return container_of(ibmw, struct mlx5_ib_mw, ibmw); +} + struct mlx5_ib_ah { struct ib_ah ibah; struct mlx5_av av; @@ -693,6 +704,9 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc); struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int access_flags, struct ib_udata *udata); +struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata); +int mlx5_ib_dealloc_mw(struct ib_mw *mw); int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index, int npages, int zap); int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 399e2b5fb573..70a047dde69e 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -40,6 +40,7 @@ #include #include #include "mlx5_ib.h" +#include "user.h" enum { MAX_PENDING_REG_MR = 8, @@ -1620,6 +1621,88 @@ err_free: return ERR_PTR(err); } +struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, + struct ib_udata *udata) +{ + struct mlx5_ib_dev *dev = to_mdev(pd->device); + struct mlx5_create_mkey_mbox_in *in = NULL; + struct mlx5_ib_mw *mw = NULL; + int ndescs; + int err; + struct mlx5_ib_alloc_mw req = {}; + struct { + __u32 comp_mask; + __u32 response_length; + } resp = {}; + + err = ib_copy_from_udata(&req, udata, min(udata->inlen, sizeof(req))); + if (err) + return ERR_PTR(err); + + if (req.comp_mask || req.reserved1 || req.reserved2) + return ERR_PTR(-EOPNOTSUPP); + + if (udata->inlen > sizeof(req) && + !ib_is_udata_cleared(udata, sizeof(req), + udata->inlen - sizeof(req))) + return ERR_PTR(-EOPNOTSUPP); + + ndescs = req.num_klms ? roundup(req.num_klms, 4) : roundup(1, 4); + + mw = kzalloc(sizeof(*mw), GFP_KERNEL); + in = kzalloc(sizeof(*in), GFP_KERNEL); + if (!mw || !in) { + err = -ENOMEM; + goto free; + } + + in->seg.status = MLX5_MKEY_STATUS_FREE; + in->seg.xlt_oct_size = cpu_to_be32(ndescs); + in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn); + in->seg.flags = MLX5_PERM_UMR_EN | MLX5_ACCESS_MODE_KLM | + MLX5_PERM_LOCAL_READ; + if (type == IB_MW_TYPE_2) + in->seg.flags_pd |= cpu_to_be32(MLX5_MKEY_REMOTE_INVAL); + in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); + + err = mlx5_core_create_mkey(dev->mdev, &mw->mmkey, in, sizeof(*in), + NULL, NULL, NULL); + if (err) + goto free; + + mw->ibmw.rkey = mw->mmkey.key; + + resp.response_length = min(offsetof(typeof(resp), response_length) + + sizeof(resp.response_length), udata->outlen); + if (resp.response_length) { + err = ib_copy_to_udata(udata, &resp, resp.response_length); + if (err) { + mlx5_core_destroy_mkey(dev->mdev, &mw->mmkey); + goto free; + } + } + + kfree(in); + return &mw->ibmw; + +free: + kfree(mw); + kfree(in); + return ERR_PTR(err); +} + +int mlx5_ib_dealloc_mw(struct ib_mw *mw) +{ + struct mlx5_ib_mw *mmw = to_mmw(mw); + int err; + + err = mlx5_core_destroy_mkey((to_mdev(mw->device))->mdev, + &mmw->mmkey); + if (!err) + kfree(mmw); + return err; +} + int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask, struct ib_mr_status *mr_status) { diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h index b94a55404a59..61bc308bb802 100644 --- a/drivers/infiniband/hw/mlx5/user.h +++ b/drivers/infiniband/hw/mlx5/user.h @@ -152,6 +152,13 @@ struct mlx5_ib_create_qp_resp { __u32 uuar_index; }; +struct mlx5_ib_alloc_mw { + __u32 comp_mask; + __u8 num_klms; + __u8 reserved1; + __u16 reserved2; +}; + static inline int get_qp_user_index(struct mlx5_ib_ucontext *ucontext, struct mlx5_ib_create_qp *ucmd, int inlen, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 72bba5261766..3044cfa683f1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -769,7 +769,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cd[0x1]; u8 reserved_at_22c[0x1]; u8 apm[0x1]; - u8 reserved_at_22e[0x7]; + u8 reserved_at_22e[0x2]; + u8 imaicl[0x1]; + u8 reserved_at_231[0x4]; u8 qkv[0x1]; u8 pkv[0x1]; u8 set_deth_sqpn[0x1]; -- cgit v1.2.3 From f5aa9159a418726d74b67c8815ffd2739afb4c7a Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 29 Feb 2016 19:07:32 +0200 Subject: IB/core: Add arbitrary sg_list support Devices that are capable in registering SG lists with gaps can now expose it in the core to ULPs using a new device capability IB_DEVICE_SG_GAPS_REG (in a new field device_cap_flags_ex in the device attributes as we ran out of bits), and a new mr_type IB_MR_TYPE_SG_GAPS_REG which allocates a memory region which is capable of handling SG lists with gaps. Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/verbs.c | 2 ++ include/rdma/ib_verbs.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 5af6d024e053..16f3fb1b9d75 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1567,6 +1567,8 @@ EXPORT_SYMBOL(ib_check_mr_status); * - The last sg element is allowed to have length less than page_size. * - If sg_nents total byte length exceeds the mr max_num_sge * page_size * then only max_num_sg entries will be mapped. + * - If the MR was allocated with type IB_MR_TYPE_SG_GAPS_REG, non of these + * constraints holds and the page_size argument is ignored. * * Returns the number of sg elements that were mapped to the memory region. * diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 3f79070de547..bcd5b242e6b1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -212,6 +212,7 @@ enum ib_device_cap_flags { IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30), IB_DEVICE_ON_DEMAND_PAGING = (1 << 31), + IB_DEVICE_SG_GAPS_REG = (1ULL << 32), }; enum ib_signature_prot_cap { @@ -662,10 +663,15 @@ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); * @IB_MR_TYPE_SIGNATURE: memory region that is used for * signature operations (data-integrity * capable regions) + * @IB_MR_TYPE_SG_GAPS: memory region that is capable to + * register any arbitrary sg lists (without + * the normal mr constraints - see + * ib_map_mr_sg) */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SIGNATURE, + IB_MR_TYPE_SG_GAPS, }; /** -- cgit v1.2.3 From 153fefbf34e5079c2dd69490f5f23373758d2e9c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:45 +0200 Subject: net/mlx5_core: Create anchor of last flow table Create an empty flow table in the end of NIC rx namesapce. Adding this flow table simplify the implementation of "forward to next prio" rules. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 40 ++++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 6 ++++ include/linux/mlx5/fs.h | 1 + 3 files changed, 46 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 6f68dba8d7ed..a2781ee0fd15 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -77,6 +77,9 @@ #define KERNEL_NUM_PRIOS 1 #define KENREL_MIN_LEVEL 2 +#define ANCHOR_MAX_FT 1 +#define ANCHOR_NUM_PRIOS 1 +#define ANCHOR_MIN_LEVEL (BY_PASS_MIN_LEVEL + 1) struct node_caps { size_t arr_sz; long *caps; @@ -92,7 +95,7 @@ static struct init_tree_node { int max_ft; } root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 3, + .ar_size = 4, .children = (struct init_tree_node[]) { ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_REQUIRED_CAPS(FS_CAP(flow_table_properties_nic_receive.flow_modify_en), @@ -108,6 +111,8 @@ static struct init_tree_node { FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode), FS_CAP(flow_table_properties_nic_receive.flow_table_modify)), ADD_NS(ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, LEFTOVERS_MAX_FT))), + ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {}, + ADD_NS(ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, ANCHOR_MAX_FT))), } }; @@ -1126,6 +1131,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, case MLX5_FLOW_NAMESPACE_BYPASS: case MLX5_FLOW_NAMESPACE_KERNEL: case MLX5_FLOW_NAMESPACE_LEFTOVERS: + case MLX5_FLOW_NAMESPACE_ANCHOR: prio = type; break; case MLX5_FLOW_NAMESPACE_FDB: @@ -1351,6 +1357,25 @@ static void set_prio_attrs(struct mlx5_flow_root_namespace *root_ns) } } +#define ANCHOR_PRIO 0 +#define ANCHOR_SIZE 1 +static int create_anchor_flow_table(struct mlx5_core_dev + *dev) +{ + struct mlx5_flow_namespace *ns = NULL; + struct mlx5_flow_table *ft; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ANCHOR); + if (!ns) + return -EINVAL; + ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE); + if (IS_ERR(ft)) { + mlx5_core_err(dev, "Failed to create last anchor flow table"); + return PTR_ERR(ft); + } + return 0; +} + static int init_root_ns(struct mlx5_core_dev *dev) { @@ -1363,6 +1388,9 @@ static int init_root_ns(struct mlx5_core_dev *dev) set_prio_attrs(dev->priv.root_ns); + if (create_anchor_flow_table(dev)) + goto cleanup; + return 0; cleanup: @@ -1392,6 +1420,15 @@ static void cleanup_single_prio_root_ns(struct mlx5_core_dev *dev, root_ns = NULL; } +static void destroy_flow_tables(struct fs_prio *prio) +{ + struct mlx5_flow_table *iter; + struct mlx5_flow_table *tmp; + + fs_for_each_ft_safe(iter, tmp, prio) + mlx5_destroy_flow_table(iter); +} + static void cleanup_root_ns(struct mlx5_core_dev *dev) { struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; @@ -1420,6 +1457,7 @@ static void cleanup_root_ns(struct mlx5_core_dev *dev) list); fs_get_obj(obj_iter_prio2, iter_prio2); + destroy_flow_tables(obj_iter_prio2); if (tree_remove_node(iter_prio2)) { mlx5_core_warn(dev, "Priority %d wasn't destroyed, refcount > 1\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 00245fd7e4bc..574a903180ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -142,6 +142,9 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); #define fs_list_for_each_entry(pos, root) \ list_for_each_entry(pos, root, node.list) +#define fs_list_for_each_entry_safe(pos, tmp, root) \ + list_for_each_entry_safe(pos, tmp, root, node.list) + #define fs_for_each_ns_or_ft_reverse(pos, prio) \ list_for_each_entry_reverse(pos, &(prio)->node.children, list) @@ -157,6 +160,9 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); #define fs_for_each_ft(pos, prio) \ fs_list_for_each_entry(pos, &(prio)->node.children) +#define fs_for_each_ft_safe(pos, tmp, prio) \ + fs_list_for_each_entry_safe(pos, tmp, &(prio)->node.children) + #define fs_for_each_fg(pos, ft) \ fs_list_for_each_entry(pos, &(ft)->node.children) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8230caa3fb6e..72adf53fdcba 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -52,6 +52,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, + MLX5_FLOW_NAMESPACE_ANCHOR, MLX5_FLOW_NAMESPACE_FDB, }; -- cgit v1.2.3 From b3638e1a76648dbd482cc5a8f27eb6948cc3bc86 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:46 +0200 Subject: net/mlx5_core: Introduce forward to next priority action Add support to create flow rule that forward packets to the first flow table in the next priority (next priority could be the first priority in the next namespace or the next priority in the same namespace). This feature could be used for DONT_TRAP rules or rules that only want to mark the packet with flow tag. In order to do it optimally, each flow table has list of all rules that point to this flow table, when a flow table is destroyed/created, we update the list head correspondingly. This kind of rule is created when destination is NULL and action is MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 185 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 9 ++ include/linux/mlx5/fs.h | 4 + include/linux/mlx5/mlx5_ifc.h | 3 +- 4 files changed, 188 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a2781ee0fd15..bf3446794bd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -201,8 +201,10 @@ static void tree_put_node(struct fs_node *node) static int tree_remove_node(struct fs_node *node) { - if (atomic_read(&node->refcount) > 1) - return -EPERM; + if (atomic_read(&node->refcount) > 1) { + atomic_dec(&node->refcount); + return -EEXIST; + } tree_put_node(node); return 0; } @@ -365,6 +367,11 @@ static void del_rule(struct fs_node *node) memcpy(match_value, fte->val, sizeof(fte->val)); fs_get_obj(ft, fg->node.parent); list_del(&rule->node.list); + if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { + mutex_lock(&rule->dest_attr.ft->lock); + list_del(&rule->next_ft); + mutex_unlock(&rule->dest_attr.ft->lock); + } fte->dests_size--; if (fte->dests_size) { err = mlx5_cmd_update_fte(dev, ft, @@ -470,6 +477,8 @@ static struct mlx5_flow_table *alloc_flow_table(int level, int max_fte, ft->node.type = FS_TYPE_FLOW_TABLE; ft->type = table_type; ft->max_fte = max_fte; + INIT_LIST_HEAD(&ft->fwd_rules); + mutex_init(&ft->lock); return ft; } @@ -606,9 +615,63 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio return err; } +static int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct fs_fte *fte; + int err = 0; + + fs_get_obj(fte, rule->node.parent); + if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) + return -EINVAL; + lock_ref_node(&fte->node); + fs_get_obj(fg, fte->node.parent); + fs_get_obj(ft, fg->node.parent); + + memcpy(&rule->dest_attr, dest, sizeof(*dest)); + err = mlx5_cmd_update_fte(get_dev(&ft->node), + ft, fg->id, fte); + unlock_ref_node(&fte->node); + + return err; +} + +/* Modify/set FWD rules that point on old_next_ft to point on new_next_ft */ +static int connect_fwd_rules(struct mlx5_core_dev *dev, + struct mlx5_flow_table *new_next_ft, + struct mlx5_flow_table *old_next_ft) +{ + struct mlx5_flow_destination dest; + struct mlx5_flow_rule *iter; + int err = 0; + + /* new_next_ft and old_next_ft could be NULL only + * when we create/destroy the anchor flow table. + */ + if (!new_next_ft || !old_next_ft) + return 0; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = new_next_ft; + + mutex_lock(&old_next_ft->lock); + list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules); + mutex_unlock(&old_next_ft->lock); + list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) { + err = mlx5_modify_rule_destination(iter, &dest); + if (err) + pr_err("mlx5_core: failed to modify rule to point on flow table %d\n", + new_next_ft->id); + } + return 0; +} + static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { + struct mlx5_flow_table *next_ft; int err = 0; /* Connect_prev_fts and update_root_ft_create are mutually exclusive */ @@ -617,6 +680,11 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table err = connect_prev_fts(dev, ft, prio); if (err) return err; + + next_ft = find_next_chained_ft(prio); + err = connect_fwd_rules(dev, ft, next_ft); + if (err) + return err; } if (MLX5_CAP_FLOWTABLE(dev, @@ -767,6 +835,7 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) if (!rule) return NULL; + INIT_LIST_HEAD(&rule->next_ft); rule->node.type = FS_TYPE_FLOW_DEST; memcpy(&rule->dest_attr, dest, sizeof(*dest)); @@ -787,9 +856,14 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, return ERR_PTR(-ENOMEM); fs_get_obj(ft, fg->node.parent); - /* Add dest to dests list- added as first element after the head */ + /* Add dest to dests list- we need flow tables to be in the + * end of the list for forward to next prio rules. + */ tree_init_node(&rule->node, 1, del_rule); - list_add_tail(&rule->node.list, &fte->node.children); + if (dest && dest->type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) + list_add(&rule->node.list, &fte->node.children); + else + list_add_tail(&rule->node.list, &fte->node.children); fte->dests_size++; if (fte->dests_size == 1) err = mlx5_cmd_create_fte(get_dev(&ft->node), @@ -908,6 +982,25 @@ out: return fg; } +static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_rule *rule; + + list_for_each_entry(rule, &fte->node.children, node.list) { + if (rule->dest_attr.type == dest->type) { + if ((dest->type == MLX5_FLOW_DESTINATION_TYPE_VPORT && + dest->vport_num == rule->dest_attr.vport_num) || + (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && + dest->ft == rule->dest_attr.ft) || + (dest->type == MLX5_FLOW_DESTINATION_TYPE_TIR && + dest->tir_num == rule->dest_attr.tir_num)) + return rule; + } + } + return NULL; +} + static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg, u32 *match_value, u8 action, @@ -924,6 +1017,13 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg, nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); if (compare_match_value(&fg->mask, match_value, &fte->val) && action == fte->action && flow_tag == fte->flow_tag) { + rule = find_flow_rule(fte, dest); + if (rule) { + atomic_inc(&rule->node.refcount); + unlock_ref_node(&fte->node); + unlock_ref_node(&fg->node); + return rule; + } rule = add_rule_fte(fte, fg, dest); unlock_ref_node(&fte->node); if (IS_ERR(rule)) @@ -989,14 +1089,14 @@ static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft, return rule; } -struct mlx5_flow_rule * -mlx5_add_flow_rule(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) +static struct mlx5_flow_rule * +_mlx5_add_flow_rule(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + u32 *match_criteria, + u32 *match_value, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest) { struct mlx5_flow_group *g; struct mlx5_flow_rule *rule; @@ -1019,6 +1119,63 @@ unlock: unlock_ref_node(&ft->node); return rule; } + +static bool fwd_next_prio_supported(struct mlx5_flow_table *ft) +{ + return ((ft->type == FS_FT_NIC_RX) && + (MLX5_CAP_FLOWTABLE(get_dev(&ft->node), nic_rx_multi_path_tirs))); +} + +struct mlx5_flow_rule * +mlx5_add_flow_rule(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + u32 *match_criteria, + u32 *match_value, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_root_namespace *root = find_root(&ft->node); + struct mlx5_flow_destination gen_dest; + struct mlx5_flow_table *next_ft = NULL; + struct mlx5_flow_rule *rule = NULL; + u32 sw_action = action; + struct fs_prio *prio; + + fs_get_obj(prio, ft->node.parent); + if (action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { + if (!fwd_next_prio_supported(ft)) + return ERR_PTR(-EOPNOTSUPP); + if (dest) + return ERR_PTR(-EINVAL); + mutex_lock(&root->chain_lock); + next_ft = find_next_chained_ft(prio); + if (next_ft) { + gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + gen_dest.ft = next_ft; + dest = &gen_dest; + action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + } else { + mutex_unlock(&root->chain_lock); + return ERR_PTR(-EOPNOTSUPP); + } + } + + rule = _mlx5_add_flow_rule(ft, match_criteria_enable, match_criteria, + match_value, action, flow_tag, dest); + + if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { + if (!IS_ERR_OR_NULL(rule) && + (list_empty(&rule->next_ft))) { + mutex_lock(&next_ft->lock); + list_add(&rule->next_ft, &next_ft->fwd_rules); + mutex_unlock(&next_ft->lock); + rule->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; + } + mutex_unlock(&root->chain_lock); + } + return rule; +} EXPORT_SYMBOL(mlx5_add_flow_rule); void mlx5_del_flow_rule(struct mlx5_flow_rule *rule) @@ -1082,6 +1239,10 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) return 0; next_ft = find_next_chained_ft(prio); + err = connect_fwd_rules(dev, next_ft, ft); + if (err) + return err; + err = connect_prev_fts(dev, next_ft, prio); if (err) mlx5_core_warn(dev, "Failed to disconnect flow table %d\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 574a903180ed..f37a6248a27b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -68,6 +68,11 @@ struct fs_node { struct mlx5_flow_rule { struct fs_node node; struct mlx5_flow_destination dest_attr; + /* next_ft should be accessed under chain_lock and only of + * destination type is FWD_NEXT_fT. + */ + struct list_head next_ft; + u32 sw_action; }; /* Type of children is mlx5_flow_group */ @@ -82,6 +87,10 @@ struct mlx5_flow_table { unsigned int required_groups; unsigned int num_groups; } autogroup; + /* Protect fwd_rules */ + struct mutex lock; + /* FWD rules that point on this flow table */ + struct list_head fwd_rules; }; /* Type of children is mlx5_flow_rule */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 72adf53fdcba..8dec5508d93d 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -38,6 +38,10 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 +enum { + MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, +}; + #define LEFTOVERS_RULE_NUM 2 static inline void build_leftovers_ft_param(int *priority, int *n_ent, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..5f70f36af3cd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -458,7 +458,8 @@ struct mlx5_ifc_ads_bits { }; struct mlx5_ifc_flow_table_nic_cap_bits { - u8 reserved_at_0[0x200]; + u8 nic_rx_multi_path_tirs[0x1]; + u8 reserved_at_1[0x1ff]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; -- cgit v1.2.3 From 35d1901134e97cf95c0ab6ef70f5aead6cb34e9e Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 7 Mar 2016 18:51:47 +0200 Subject: IB/mlx5: Add support for don't trap rules Each bypass flow steering priority will be split into two priorities: 1. Priority for don't trap rules. 2. Priority for normal rules. When user creates a flow using IB_FLOW_ATTR_FLAGS_DONT_TRAP flag, the driver creates two flow rules, one used for receiving the traffic and the other one for forwarding the packet to continue matching in lower or equal priorities. Signed-off-by: Maor Gottlieb Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 54 ++++++++++++++++++++++++++++++++---- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +- include/linux/mlx5/device.h | 7 ++++- 3 files changed, 55 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 03c418ccbc98..5863644f0872 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1369,11 +1369,20 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id) return 0; } +static int ib_prio_to_core_prio(unsigned int priority, bool dont_trap) +{ + priority *= 2; + if (!dont_trap) + priority++; + return priority; +} + #define MLX5_FS_MAX_TYPES 10 #define MLX5_FS_MAX_ENTRIES 32000UL static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev, struct ib_flow_attr *flow_attr) { + bool dont_trap = flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP; struct mlx5_flow_namespace *ns = NULL; struct mlx5_ib_flow_prio *prio; struct mlx5_flow_table *ft; @@ -1383,10 +1392,12 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev, int err = 0; if (flow_attr->type == IB_FLOW_ATTR_NORMAL) { - if (flow_is_multicast_only(flow_attr)) + if (flow_is_multicast_only(flow_attr) && + !dont_trap) priority = MLX5_IB_FLOW_MCAST_PRIO; else - priority = flow_attr->priority; + priority = ib_prio_to_core_prio(flow_attr->priority, + dont_trap); ns = mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS); num_entries = MLX5_FS_MAX_ENTRIES; @@ -1434,6 +1445,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev, unsigned int spec_index; u32 *match_c; u32 *match_v; + u32 action; int err = 0; if (!is_valid_attr(flow_attr)) @@ -1459,9 +1471,11 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev, /* Outer header support only */ match_criteria_enable = (!outer_header_zero(match_c)) << 0; + action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST : + MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; handler->rule = mlx5_add_flow_rule(ft, match_criteria_enable, match_c, match_v, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + action, MLX5_FS_DEFAULT_FLOW_TAG, dst); @@ -1481,6 +1495,29 @@ free: return err ? ERR_PTR(err) : handler; } +static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *dev, + struct mlx5_ib_flow_prio *ft_prio, + struct ib_flow_attr *flow_attr, + struct mlx5_flow_destination *dst) +{ + struct mlx5_ib_flow_handler *handler_dst = NULL; + struct mlx5_ib_flow_handler *handler = NULL; + + handler = create_flow_rule(dev, ft_prio, flow_attr, NULL); + if (!IS_ERR(handler)) { + handler_dst = create_flow_rule(dev, ft_prio, + flow_attr, dst); + if (IS_ERR(handler_dst)) { + mlx5_del_flow_rule(handler->rule); + kfree(handler); + handler = handler_dst; + } else { + list_add(&handler_dst->list, &handler->list); + } + } + + return handler; +} enum { LEFTOVERS_MC, LEFTOVERS_UC, @@ -1558,7 +1595,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, if (domain != IB_FLOW_DOMAIN_USER || flow_attr->port > MLX5_CAP_GEN(dev->mdev, num_ports) || - flow_attr->flags) + (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP)) return ERR_PTR(-EINVAL); dst = kzalloc(sizeof(*dst), GFP_KERNEL); @@ -1577,8 +1614,13 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn; if (flow_attr->type == IB_FLOW_ATTR_NORMAL) { - handler = create_flow_rule(dev, ft_prio, flow_attr, - dst); + if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) { + handler = create_dont_trap_rule(dev, ft_prio, + flow_attr, dst); + } else { + handler = create_flow_rule(dev, ft_prio, flow_attr, + dst); + } } else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) { handler = create_leftovers_rule(dev, ft_prio, flow_attr, diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index d2b9737baa36..bd84b1fbb787 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -126,7 +126,7 @@ struct mlx5_ib_pd { }; #define MLX5_IB_FLOW_MCAST_PRIO (MLX5_BY_PASS_NUM_PRIOS - 1) -#define MLX5_IB_FLOW_LAST_PRIO (MLX5_IB_FLOW_MCAST_PRIO - 1) +#define MLX5_IB_FLOW_LAST_PRIO (MLX5_BY_PASS_NUM_REGULAR_PRIOS - 1) #if (MLX5_IB_FLOW_LAST_PRIO <= 0) #error "Invalid number of bypass priorities" #endif diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..2bf222e65e6b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1294,6 +1294,11 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } -#define MLX5_BY_PASS_NUM_PRIOS 9 +#define MLX5_BY_PASS_NUM_REGULAR_PRIOS 8 +#define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 8 +#define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1 +#define MLX5_BY_PASS_NUM_PRIOS (MLX5_BY_PASS_NUM_REGULAR_PRIOS +\ + MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS +\ + MLX5_BY_PASS_NUM_MULTICAST_PRIOS) #endif /* MLX5_DEVICE_H */ -- cgit v1.2.3