Merge tag 'rdma-next-2017-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma into rdma-netlink

RDMA netlink infrastructure v2

Signed-off-by: Doug Ledford <dledford@redhat.com>

16 files changed, 414 insertions, 47 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index aad5d81dfb44..3607da001ad3 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -428,6 +428,12 @@ enum mlx4_steer_type {
 	MLX4_NUM_STEERS
 };
 
+enum mlx4_resource_usage {
+	MLX4_RES_USAGE_NONE,
+	MLX4_RES_USAGE_DRIVER,
+	MLX4_RES_USAGE_USER_VERBS,
+};
+
 enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
@@ -748,6 +754,7 @@ struct mlx4_cq {
 	} tasklet_ctx;
 	int		reset_notify_added;
 	struct list_head	reset_notify;
+	u8			usage;
 };
 
 struct mlx4_qp {
@@ -757,6 +764,7 @@ struct mlx4_qp {
 
 	atomic_t		refcount;
 	struct completion	free;
+	u8			usage;
 };
 
 struct mlx4_srq {
@@ -1120,7 +1128,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  unsigned vector, int collapsed, int timestamp_en);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
 int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-			  int *base, u8 flags);
+			  int *base, u8 flags, u8 usage);
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 
 int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp);
@@ -1417,7 +1425,7 @@ int mlx4_get_phys_port_id(struct mlx4_dev *dev);
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
 int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
 
-int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
+int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage);
 void mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
 int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port);
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f31a0b5377e1..c13d71deaeca 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -290,6 +290,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_GPIO_EVENT	   = 0x15,
 	MLX5_EVENT_TYPE_PORT_MODULE_EVENT  = 0x16,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
+	MLX5_EVENT_TYPE_GENERAL_EVENT	   = 0x22,
 	MLX5_EVENT_TYPE_PPS_EVENT          = 0x25,
 
 	MLX5_EVENT_TYPE_DB_BF_CONGESTION   = 0x1a,
@@ -305,6 +306,10 @@ enum mlx5_event {
 };
 
 enum {
+	MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
+};
+
+enum {
 	MLX5_PORT_CHANGE_SUBTYPE_DOWN		= 1,
 	MLX5_PORT_CHANGE_SUBTYPE_ACTIVE		= 4,
 	MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED	= 5,
@@ -968,7 +973,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_ATOMIC,
 	MLX5_CAP_ROCE,
 	MLX5_CAP_IPOIB_OFFLOADS,
-	MLX5_CAP_EOIB_OFFLOADS,
+	MLX5_CAP_IPOIB_ENHANCED_OFFLOADS,
 	MLX5_CAP_FLOW_TABLE,
 	MLX5_CAP_ESWITCH_FLOW_TABLE,
 	MLX5_CAP_ESWITCH,
@@ -1011,6 +1016,10 @@ enum mlx5_mcam_feature_groups {
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap)
 
+#define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \
+	MLX5_GET(per_protocol_networking_offload_caps,\
+		 mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap)
+
 #define MLX5_CAP_ROCE(mdev, cap) \
 	MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index df6ce59a1f95..758ef40f9316 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -162,6 +162,13 @@ enum dbg_rsc_type {
 	MLX5_DBG_RSC_CQ,
 };
 
+enum port_state_policy {
+	MLX5_POLICY_DOWN	= 0,
+	MLX5_POLICY_UP		= 1,
+	MLX5_POLICY_FOLLOW	= 2,
+	MLX5_POLICY_INVALID	= 0xffffffff
+};
+
 struct mlx5_field_desc {
 	struct dentry	       *dent;
 	int			i;
@@ -185,6 +192,7 @@ enum mlx5_dev_event {
 	MLX5_DEV_EVENT_GUID_CHANGE,
 	MLX5_DEV_EVENT_CLIENT_REREG,
 	MLX5_DEV_EVENT_PPS,
+	MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT,
 };
 
 enum mlx5_port_status {
@@ -525,6 +533,9 @@ struct mlx5_mkey_table {
 
 struct mlx5_vf_context {
 	int	enabled;
+	u64	port_guid;
+	u64	node_guid;
+	enum port_state_policy	policy;
 };
 
 struct mlx5_core_sriov {
@@ -842,13 +853,6 @@ struct mlx5_pas {
 	u8	log_sz;
 };
 
-enum port_state_policy {
-	MLX5_POLICY_DOWN	= 0,
-	MLX5_POLICY_UP		= 1,
-	MLX5_POLICY_FOLLOW	= 2,
-	MLX5_POLICY_INVALID	= 0xffffffff
-};
-
 enum phy_port_state {
 	MLX5_AAA_111
 };
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 87869c04849a..5bae70eb25af 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -200,6 +200,7 @@ enum {
 	MLX5_CMD_OP_QUERY_SQ                      = 0x907,
 	MLX5_CMD_OP_CREATE_RQ                     = 0x908,
 	MLX5_CMD_OP_MODIFY_RQ                     = 0x909,
+	MLX5_CMD_OP_SET_DELAY_DROP_PARAMS         = 0x910,
 	MLX5_CMD_OP_DESTROY_RQ                    = 0x90a,
 	MLX5_CMD_OP_QUERY_RQ                      = 0x90b,
 	MLX5_CMD_OP_CREATE_RMP                    = 0x90c,
@@ -840,7 +841,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         retransmission_q_counters[0x1];
 	u8         reserved_at_183[0x1];
 	u8         modify_rq_counter_set_id[0x1];
-	u8         reserved_at_185[0x1];
+	u8         rq_delay_drop[0x1];
 	u8         max_qp_cnt[0xa];
 	u8         pkey_table_size[0x10];
 
@@ -857,7 +858,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         pcam_reg[0x1];
 	u8         local_ca_ack_delay[0x5];
 	u8         port_module_event[0x1];
-	u8         reserved_at_1b1[0x1];
+	u8         enhanced_error_q_counters[0x1];
 	u8         ports_check[0x1];
 	u8         reserved_at_1b3[0x1];
 	u8         disable_link_up[0x1];
@@ -873,7 +874,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_tc[0x4];
 	u8         reserved_at_1d0[0x1];
 	u8         dcbx[0x1];
-	u8         reserved_at_1d2[0x3];
+	u8         general_notification_event[0x1];
+	u8         reserved_at_1d3[0x2];
 	u8         fpga[0x1];
 	u8         rol_s[0x1];
 	u8         rol_g[0x1];
@@ -1016,7 +1018,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_wq_sz[0x5];
 
 	u8         nic_vport_change_event[0x1];
-	u8         reserved_at_3e1[0xa];
+	u8         disable_local_lb[0x1];
+	u8         reserved_at_3e2[0x9];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
 	u8         log_max_current_mc_list[0x5];
@@ -1187,7 +1190,8 @@ struct mlx5_ifc_cong_control_r_roce_ecn_np_bits {
 
 	u8         reserved_at_c0[0x12];
 	u8         cnp_dscp[0x6];
-	u8         reserved_at_d8[0x5];
+	u8         reserved_at_d8[0x4];
+	u8         cnp_prio_mode[0x1];
 	u8         cnp_802p_prio[0x3];
 
 	u8         reserved_at_e0[0x720];
@@ -2515,7 +2519,7 @@ enum {
 
 struct mlx5_ifc_rqc_bits {
 	u8         rlky[0x1];
-	u8         reserved_at_1[0x1];
+	u8	   delay_drop_en[0x1];
 	u8         scatter_fcs[0x1];
 	u8         vsd[0x1];
 	u8         mem_rq_type[0x4];
@@ -2562,7 +2566,9 @@ struct mlx5_ifc_rmpc_bits {
 struct mlx5_ifc_nic_vport_context_bits {
 	u8         reserved_at_0[0x5];
 	u8         min_wqe_inline_mode[0x3];
-	u8         reserved_at_8[0x17];
+	u8         reserved_at_8[0x15];
+	u8         disable_mc_local_lb[0x1];
+	u8         disable_uc_local_lb[0x1];
 	u8         roce_en[0x1];
 
 	u8         arm_change_event[0x1];
@@ -3947,7 +3953,47 @@ struct mlx5_ifc_query_q_counter_out_bits {
 
 	u8         local_ack_timeout_err[0x20];
 
-	u8         reserved_at_320[0x4e0];
+	u8         reserved_at_320[0xa0];
+
+	u8         resp_local_length_error[0x20];
+
+	u8         req_local_length_error[0x20];
+
+	u8         resp_local_qp_error[0x20];
+
+	u8         local_operation_error[0x20];
+
+	u8         resp_local_protection[0x20];
+
+	u8         req_local_protection[0x20];
+
+	u8         resp_cqe_error[0x20];
+
+	u8         req_cqe_error[0x20];
+
+	u8         req_mw_binding[0x20];
+
+	u8         req_bad_response[0x20];
+
+	u8         req_remote_invalid_request[0x20];
+
+	u8         resp_remote_invalid_request[0x20];
+
+	u8         req_remote_access_errors[0x20];
+
+	u8	   resp_remote_access_errors[0x20];
+
+	u8         req_remote_operation_errors[0x20];
+
+	u8         req_transport_retries_exceeded[0x20];
+
+	u8         cq_overflow[0x20];
+
+	u8         resp_cqe_flush_error[0x20];
+
+	u8         req_cqe_flush_error[0x20];
+
+	u8         reserved_at_620[0x1e0];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
@@ -5229,7 +5275,9 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_at_0[0x16];
+	u8         reserved_at_0[0x14];
+	u8         disable_uc_local_lb[0x1];
+	u8         disable_mc_local_lb[0x1];
 	u8         node_guid[0x1];
 	u8         port_guid[0x1];
 	u8         min_inline[0x1];
@@ -5847,6 +5895,28 @@ struct mlx5_ifc_destroy_rq_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_set_delay_drop_params_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x10];
+	u8         delay_drop_timeout[0x10];
+};
+
+struct mlx5_ifc_set_delay_drop_params_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_destroy_rmp_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 6f41270d80c0..66d19b611fe4 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg {
 #define MLX5_WQE_CTRL_OPCODE_MASK 0xff
 #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00
 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8
-#define MLX5_WQE_AV_EXT 0x80000000
 
 enum {
 	MLX5_ETH_WQE_L3_INNER_CSUM      = 1 << 4,
@@ -561,6 +560,9 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
 int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 		       u32 *out, int outlen);
 
+int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev,
+			     u32 timeout_usec);
+
 int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn);
 int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn);
 void mlx5_init_qp_table(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 656c70b65dd2..aaa0bb9e7655 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -114,5 +114,6 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 				       u8 other_vport, u8 port_num,
 				       int vf,
 				       struct mlx5_hca_vport_context *req);
-
+int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable);
+int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status);
 #endif /* __MLX5_VPORT_H__ */
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index b73a14edc85e..7aca12188ef3 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -304,7 +304,13 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
 
 static inline int rdma_is_multicast_addr(struct in6_addr *addr)
 {
-	return addr->s6_addr[0] == 0xff;
+	u32 ipv4_addr;
+
+	if (addr->s6_addr[0] == 0xff)
+		return 1;
+
+	memcpy(&ipv4_addr, addr->s6_addr + 12, 4);
+	return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr));
 }
 
 static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h
index 5519f31f043a..c124d515f7d5 100644
--- a/include/rdma/ib_hdrs.h
+++ b/include/rdma/ib_hdrs.h
@@ -193,8 +193,12 @@ static inline void put_ib_ateth_compare(u64 val, struct ib_atomic_eth *ateth)
 #define IB_LNH_MASK		3
 #define IB_SC_MASK		0xf
 #define IB_SC_SHIFT		12
+#define IB_SC5_MASK		0x10
 #define IB_SL_MASK		0xf
 #define IB_SL_SHIFT		4
+#define IB_SL_SHIFT		4
+#define IB_LVER_MASK	0xf
+#define IB_LVER_SHIFT	8
 
 static inline u8 ib_get_lnh(struct ib_header *hdr)
 {
@@ -206,6 +210,11 @@ static inline u8 ib_get_sc(struct ib_header *hdr)
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SC_SHIFT) & IB_SC_MASK);
 }
 
+static inline bool ib_is_sc5(u16 sc5)
+{
+	return !!(sc5 & IB_SC5_MASK);
+}
+
 static inline u8 ib_get_sl(struct ib_header *hdr)
 {
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SL_SHIFT) & IB_SL_MASK);
@@ -221,6 +230,27 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 	return (be16_to_cpu(hdr->lrh[3]));
 }
 
+static inline u8 ib_get_lver(struct ib_header *hdr)
+{
+	return (u8)((be16_to_cpu(hdr->lrh[0]) >> IB_LVER_SHIFT) &
+		   IB_LVER_MASK);
+}
+
+static inline u16 ib_get_len(struct ib_header *hdr)
+{
+	return (u16)(be16_to_cpu(hdr->lrh[2]));
+}
+
+static inline u32 ib_get_qkey(struct ib_other_headers *ohdr)
+{
+	return be32_to_cpu(ohdr->u.ud.deth[0]);
+}
+
+static inline u32 ib_get_sqpn(struct ib_other_headers *ohdr)
+{
+	return ((be32_to_cpu(ohdr->u.ud.deth[1])) & IB_QPN_MASK);
+}
+
 /*
  * BTH
  */
@@ -229,6 +259,14 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 #define IB_BTH_PAD_MASK	3
 #define IB_BTH_PKEY_MASK	0xffff
 #define IB_BTH_PAD_SHIFT	20
+#define IB_BTH_A_MASK		1
+#define IB_BTH_A_SHIFT		31
+#define IB_BTH_M_MASK		1
+#define IB_BTH_M_SHIFT		22
+#define IB_BTH_SE_MASK		1
+#define IB_BTH_SE_SHIFT	23
+#define IB_BTH_TVER_MASK	0xf
+#define IB_BTH_TVER_SHIFT	16
 
 static inline u8 ib_bth_get_pad(struct ib_other_headers *ohdr)
 {
@@ -247,4 +285,50 @@ static inline u8 ib_bth_get_opcode(struct ib_other_headers *ohdr)
 		   IB_BTH_OPCODE_MASK);
 }
 
+static inline u8 ib_bth_get_ackreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[2]) >> IB_BTH_A_SHIFT) &
+		   IB_BTH_A_MASK);
+}
+
+static inline u8 ib_bth_get_migreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_M_SHIFT) &
+		    IB_BTH_M_MASK);
+}
+
+static inline u8 ib_bth_get_se(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_SE_SHIFT) &
+		    IB_BTH_SE_MASK);
+}
+
+static inline u32 ib_bth_get_psn(struct ib_other_headers *ohdr)
+{
+	return (u32)(be32_to_cpu(ohdr->bth[2]));
+}
+
+static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr)
+{
+	return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK);
+}
+
+static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
+		     IB_BECN_MASK);
+}
+
+static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
+		    IB_FECN_MASK);
+}
+
+static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_TVER_SHIFT)  &
+		    IB_BTH_TVER_MASK);
+}
+
 #endif                          /* IB_HDRS_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b5732432bb29..e0e87a1f66fb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 
+#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
+
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 
@@ -577,7 +579,8 @@ struct ib_device_modify {
 enum ib_port_modify_flags {
 	IB_PORT_SHUTDOWN		= 1,
 	IB_PORT_INIT_TYPE		= (1<<2),
-	IB_PORT_RESET_QKEY_CNTR		= (1<<3)
+	IB_PORT_RESET_QKEY_CNTR		= (1<<3),
+	IB_PORT_OPA_MASK_CHG		= (1<<4)
 };
 
 struct ib_port_modify {
@@ -664,6 +667,8 @@ union rdma_network_hdr {
 	};
 };
 
+#define IB_QPN_MASK		0xFFFFFF
+
 enum {
 	IB_MULTICAST_QPN = 0xffffff
 };
@@ -1059,6 +1064,7 @@ enum ib_qp_create_flags {
 	/* FREE					= 1 << 7, */
 	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
+	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1086,6 +1092,7 @@ struct ib_qp_init_attr {
 	 */
 	u8			port_num;
 	struct ib_rwq_ind_table *rwq_ind_tbl;
+	u32			source_qpn;
 };
 
 struct ib_qp_open_attr {
@@ -1546,6 +1553,10 @@ enum ib_raw_packet_caps {
 	IB_RAW_PACKET_CAP_SCATTER_FCS		= (1 << 1),
 	/* Checksum offloads are supported (for both send and receive). */
 	IB_RAW_PACKET_CAP_IP_CSUM		= (1 << 2),
+	/* When a packet is received for an RQ with no receive WQEs, the
+	 * packet processing is delayed.
+	 */
+	IB_RAW_PACKET_CAP_DELAY_DROP		= (1 << 3),
 };
 
 enum ib_wq_type {
@@ -1574,6 +1585,7 @@ struct ib_wq {
 enum ib_wq_flags {
 	IB_WQ_FLAGS_CVLAN_STRIPPING	= 1 << 0,
 	IB_WQ_FLAGS_SCATTER_FCS		= 1 << 1,
+	IB_WQ_FLAGS_DELAY_DROP		= 1 << 2,
 };
 
 struct ib_wq_init_attr {
@@ -2288,6 +2300,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this
@@ -2295,7 +2309,7 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
-	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	void (*get_dev_fw_str)(struct ib_device *, char *str);
 };
 
 struct ib_client {
@@ -2331,7 +2345,7 @@ struct ib_client {
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
-void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+void ib_get_device_fw_str(struct ib_device *device, char *str);
 
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
@@ -3555,6 +3569,7 @@ void ib_drain_qp(struct ib_qp *qp);
 
 int ib_resolve_eth_dmac(struct ib_device *device,
 			struct rdma_ah_attr *ah_attr);
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
 
 static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
 {
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 348c102cb5f6..e25bf1988846 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -5,29 +5,31 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
-	struct module *module;
+	u8 flags;
+};
+
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
 /**
- * Add a a client to the list of IB netlink exporters.
+ * Register client in RDMA netlink.
  * @index: Index of the added client
- * @nops: Number of supported ops by the added client.
  * @cb_table: A table for op->callback
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[]);
+void rdma_nl_register(unsigned int index,
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
  * @index: Index of the removed IB client.
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_remove_client(int index);
+void rdma_nl_unregister(unsigned int index);
 
 /**
  * Put a new message in a supplied skb.
@@ -56,22 +58,32 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
+
+/**
+ * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int rdma_nl_chk_listeners(unsigned int group);
 #endif /* _RDMA_NETLINK_H */
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 55af69271053..fdfac0fd2f82 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -57,11 +57,21 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_mad.h>
 #include <rdma/rdmavt_mr.h>
 #include <rdma/rdmavt_qp.h>
 
 #define RVT_MAX_PKEY_VALUES 16
 
+#define RVT_MAX_TRAP_LEN 100 /* Limit pending trap list */
+#define RVT_MAX_TRAP_LISTS ((IB_NOTICE_TYPE_INFO & 0x0F) + 1)
+#define RVT_TRAP_TIMEOUT 4096 /* 4.096 usec */
+
+struct trap_list {
+	u32 list_len;
+	struct list_head list;
+};
+
 struct rvt_ibport {
 	struct rvt_qp __rcu *qp[2];
 	struct ib_mad_agent *send_agent;	/* agent for SMI (traps) */
@@ -75,6 +85,7 @@ struct rvt_ibport {
 	__be64 mkey;
 	u64 tid;
 	u32 port_cap_flags;
+	u16 port_cap3_flags;
 	u32 pma_sample_start;
 	u32 pma_sample_interval;
 	__be16 pma_counter_select[5];
@@ -127,6 +138,13 @@ struct rvt_ibport {
 	u16 *pkey_table;
 
 	struct rvt_ah *sm_ah;
+
+	/*
+	 * Keep a list of traps that have not been repressed.  They will be
+	 * resent based on trap_timer.
+	 */
+	struct trap_list trap_lists[RVT_MAX_TRAP_LISTS];
+	struct timer_list trap_timer;
 };
 
 #define RVT_CQN_MAX 16 /* maximum length of cq name */
@@ -514,7 +532,8 @@ int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey);
 int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc);
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc);
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc);
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid,
 				 u16 lid);
 
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index d664d2e76280..07e2fffa6de6 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -396,7 +396,7 @@ struct rvt_srq {
 #define RVT_QPNMAP_ENTRIES          (RVT_QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE           (PAGE_SIZE * BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE_MASK      (RVT_BITS_PER_PAGE - 1)
-#define RVT_QPN_MASK		    0xFFFFFF
+#define RVT_QPN_MASK		    IB_QPN_MASK
 
 /*
  * QPN-map pages start out as NULL, they get allocated upon
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 270c350bedc6..63656d2e8705 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -578,7 +578,7 @@ struct ib_uverbs_ex_create_qp {
 	__u32 comp_mask;
 	__u32 create_flags;
 	__u32 rwq_ind_tbl_handle;
-	__u32  reserved1;
+	__u32  source_qpn;
 };
 
 struct ib_uverbs_open_qp {
diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h
index af431752655c..d915cab37ec3 100644
--- a/include/uapi/rdma/mlx4-abi.h
+++ b/include/uapi/rdma/mlx4-abi.h
@@ -95,13 +95,65 @@ struct mlx4_ib_create_srq_resp {
 	__u32	reserved;
 };
 
+struct mlx4_ib_create_qp_rss {
+	__u64   rx_hash_fields_mask;
+	__u8    rx_hash_function;
+	__u8    rx_key_len;
+	__u8    reserved[6];
+	__u8    rx_hash_key[40];
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
 struct mlx4_ib_create_qp {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u8	log_sq_bb_count;
 	__u8	log_sq_stride;
 	__u8	sq_no_prefetch;
-	__u8	reserved[5];
+	__u32	inl_recv_sz;
+	__u8	reserved;
+};
+
+struct mlx4_ib_create_wq {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u8	log_range_size;
+	__u8	reserved[3];
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
+struct mlx4_ib_modify_wq {
+	__u32	comp_mask;
+	__u32	reserved;
+};
+
+struct mlx4_ib_create_rwq_ind_tbl_resp {
+	__u32	response_length;
+	__u32	reserved;
+};
+
+/* RX Hash function flags */
+enum mlx4_ib_rx_hash_function_flags {
+	MLX4_IB_RX_HASH_FUNC_TOEPLITZ	= 1 << 0,
+};
+
+/*
+ * RX Hash flags, these flags allows to set which incoming packet's field should
+ * participates in RX Hash. Each flag represent certain packet's field,
+ * when the flag is set the field that is represented by the flag will
+ * participate in RX Hash calculation.
+ */
+enum mlx4_ib_rx_hash_fields {
+	MLX4_IB_RX_HASH_SRC_IPV4	= 1 << 0,
+	MLX4_IB_RX_HASH_DST_IPV4	= 1 << 1,
+	MLX4_IB_RX_HASH_SRC_IPV6	= 1 << 2,
+	MLX4_IB_RX_HASH_DST_IPV6	= 1 << 3,
+	MLX4_IB_RX_HASH_SRC_PORT_TCP	= 1 << 4,
+	MLX4_IB_RX_HASH_DST_PORT_TCP	= 1 << 5,
+	MLX4_IB_RX_HASH_SRC_PORT_UDP	= 1 << 6,
+	MLX4_IB_RX_HASH_DST_PORT_UDP	= 1 << 7
 };
 
 #endif /* MLX4_ABI_USER_H */
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index 75c270d839c8..54b64357ab24 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -49,6 +49,9 @@ struct qedr_alloc_ucontext_resp {
 	__u32 sges_per_recv_wr;
 	__u32 sges_per_srq_wr;
 	__u32 max_cqes;
+	__u8 dpm_enabled;
+	__u8 wids_enabled;
+	__u16 wid_count;
 };
 
 struct qedr_alloc_pd_ureq {
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 02fe8390c18f..861440a87e7c 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 
@@ -222,4 +222,86 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET commamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
+	/*
+	 * FW version
+	 */
+	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
+
+	/*
+	 * Node GUID (in host byte order) associated with the RDMA device.
+	 */
+	RDMA_NLDEV_ATTR_NODE_GUID,			/* u64 */
+
+	/*
+	 * System image GUID (in host byte order) associated with
+	 * this RDMA device and other devices which are part of a
+	 * single system.
+	 */
+	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
+
+	/*
+	 * Subnet prefix (in host byte order)
+	 */
+	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
+
+	/*
+	 * Local Identifier (LID),
+	 * According to IB specification, It is 16-bit address assigned
+	 * by the Subnet Manager. Extended to be 32-bit for OmniPath users.
+	 */
+	RDMA_NLDEV_ATTR_LID,			/* u32 */
+	RDMA_NLDEV_ATTR_SM_LID,			/* u32 */
+
+	/*
+	 * LID mask control (LMC)
+	 */
+	RDMA_NLDEV_ATTR_LMC,			/* u8 */
+
+	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
+	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
+
+	RDMA_NLDEV_ATTR_DEV_NODE_TYPE,		/* u8 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */