Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A more active cycle than most of the recent past, with a few large,
  long discussed works this time.

  The RNBD block driver has been posted for nearly two years now, and
  flowing through RDMA due to it also introducing a new ULP.

  The removal of FMR has been a recurring discussion theme for a long
  time.

  And the usual smattering of features and bug fixes.

  Summary:

   - Various small driver bugs fixes in rxe, mlx5, hfi1, and efa

   - Continuing driver cleanups in bnxt_re, hns

   - Big cleanup of mlx5 QP creation flows

   - More consistent use of src port and flow label when LAG is used and
     a mlx5 implementation

   - Additional set of cleanups for IB CM

   - 'RNBD' network block driver and target. This is a network block
     RDMA device specific to ionos's cloud environment. It brings strong
     multipath and resiliency capabilities.

   - Accelerated IPoIB for HFI1

   - QP/WQ/SRQ ioctl migration for uverbs, and support for multiple
     async fds

   - Support for exchanging the new IBTA defiend ECE data during RDMA CM
     exchanges

   - Removal of the very old and insecure FMR interface from all ULPs
     and drivers. FRWR should be preferred for at least a decade now"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (247 commits)
  RDMA/cm: Spurious WARNING triggered in cm_destroy_id()
  RDMA/mlx5: Return ECE DC support
  RDMA/mlx5: Don't rely on FW to set zeros in ECE response
  RDMA/mlx5: Return an error if copy_to_user fails
  IB/hfi1: Use free_netdev() in hfi1_netdev_free()
  RDMA/hns: Uninitialized variable in modify_qp_init_to_rtr()
  RDMA/core: Move and rename trace_cm_id_create()
  IB/hfi1: Fix hfi1_netdev_rx_init() error handling
  RDMA: Remove 'max_map_per_fmr'
  RDMA: Remove 'max_fmr'
  RDMA/core: Remove FMR device ops
  RDMA/rdmavt: Remove FMR memory registration
  RDMA/mthca: Remove FMR support for memory registration
  RDMA/mlx4: Remove FMR support for memory registration
  RDMA/i40iw: Remove FMR leftovers
  RDMA/bnxt_re: Remove FMR leftovers
  RDMA/mlx5: Remove FMR leftovers
  RDMA/core: Remove FMR pool API
  RDMA/rds: Remove FMR support for memory registration
  RDMA/srp: Remove support for FMR memory registration
  ...

23 files changed, 450 insertions, 370 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 20372de0b587..06e066e04a4b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -573,7 +573,6 @@ struct mlx4_caps {
 	int			reserved_eqs;
 	int			num_comp_vectors;
 	int			num_mpts;
-	int			max_fmr_maps;
 	int			num_mtts;
 	int			fmr_reserved_mtts;
 	int			reserved_mtts;
@@ -707,17 +706,6 @@ struct mlx4_mw {
 	int			enabled;
 };
 
-struct mlx4_fmr {
-	struct mlx4_mr		mr;
-	struct mlx4_mpt_entry  *mpt;
-	__be64		       *mtts;
-	dma_addr_t		dma_handle;
-	int			max_pages;
-	int			max_maps;
-	int			maps;
-	u8			page_shift;
-};
-
 struct mlx4_uar {
 	unsigned long		pfn;
 	int			index;
@@ -1412,14 +1400,6 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
 
-int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
-		      int npages, u64 iova, u32 *lkey, u32 *rkey);
-int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
-		   int max_maps, u8 page_shift, struct mlx4_fmr *fmr);
-int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
-void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
-		    u32 *lkey, u32 *rkey);
-int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupt(struct mlx4_dev *dev, int vector);
 int mlx4_test_async(struct mlx4_dev *dev);
@@ -1522,6 +1502,8 @@ int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
 				 int enable);
+
+struct mlx4_mpt_entry;
 int mlx4_mr_hw_get_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr,
 		       struct mlx4_mpt_entry ***mpt_entry);
 int mlx4_mr_hw_write_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1a56dc079c32..116bd9bb347f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1321,7 +1321,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         stat_rate_support[0x10];
 	u8         reserved_at_1f0[0x1];
 	u8         pci_sync_for_fw_update_event[0x1];
-	u8         reserved_at_1f2[0xa];
+	u8         reserved_at_1f2[0x6];
+	u8         init2_lag_tx_port_affinity[0x1];
+	u8         reserved_at_1fa[0x3];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
@@ -3688,7 +3690,8 @@ struct mlx5_ifc_dctc_bits {
 	u8         ecn[0x2];
 	u8         dscp[0x6];
 
-	u8         reserved_at_1c0[0x40];
+	u8         reserved_at_1c0[0x20];
+	u8         ece[0x20];
 };
 
 enum {
@@ -7938,7 +7941,7 @@ struct mlx5_ifc_create_dct_out_bits {
 	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_create_dct_in_bits {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 1af5e460b5f6..b8992b861ae6 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -66,6 +66,7 @@ enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_RETRY_COUNT		= 1 << 12,
 	MLX5_QP_OPTPAR_RNR_RETRY		= 1 << 13,
 	MLX5_QP_OPTPAR_ACK_TIMEOUT		= 1 << 14,
+	MLX5_QP_OPTPAR_LAG_TX_AFF		= 1 << 15,
 	MLX5_QP_OPTPAR_PRI_PORT			= 1 << 16,
 	MLX5_QP_OPTPAR_SRQN			= 1 << 18,
 	MLX5_QP_OPTPAR_CQN_RCV			= 1 << 19,
@@ -321,6 +322,7 @@ struct mlx5_av {
 struct mlx5_ib_ah {
 	struct ib_ah		ibah;
 	struct mlx5_av		av;
+	u8			xmit_port;
 };
 
 static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah)
@@ -493,72 +495,6 @@ struct mlx5_core_dct {
 	struct completion	drained;
 };
 
-struct mlx5_qp_path {
-	u8			fl_free_ar;
-	u8			rsvd3;
-	__be16			pkey_index;
-	u8			rsvd0;
-	u8			grh_mlid;
-	__be16			rlid;
-	u8			ackto_lt;
-	u8			mgid_index;
-	u8			static_rate;
-	u8			hop_limit;
-	__be32			tclass_flowlabel;
-	union {
-		u8		rgid[16];
-		u8		rip[16];
-	};
-	u8			f_dscp_ecn_prio;
-	u8			ecn_dscp;
-	__be16			udp_sport;
-	u8			dci_cfi_prio_sl;
-	u8			port;
-	u8			rmac[6];
-};
-
-/* FIXME: use mlx5_ifc.h qpc */
-struct mlx5_qp_context {
-	__be32			flags;
-	__be32			flags_pd;
-	u8			mtu_msgmax;
-	u8			rq_size_stride;
-	__be16			sq_crq_size;
-	__be32			qp_counter_set_usr_page;
-	__be32			wire_qpn;
-	__be32			log_pg_sz_remote_qpn;
-	struct			mlx5_qp_path pri_path;
-	struct			mlx5_qp_path alt_path;
-	__be32			params1;
-	u8			reserved2[4];
-	__be32			next_send_psn;
-	__be32			cqn_send;
-	__be32			deth_sqpn;
-	u8			reserved3[4];
-	__be32			last_acked_psn;
-	__be32			ssn;
-	__be32			params2;
-	__be32			rnr_nextrecvpsn;
-	__be32			xrcd;
-	__be32			cqn_recv;
-	__be64			db_rec_addr;
-	__be32			qkey;
-	__be32			rq_type_srqn;
-	__be32			rmsn;
-	__be16			hw_sq_wqe_counter;
-	__be16			sw_sq_wqe_counter;
-	__be16			hw_rcyclic_byte_counter;
-	__be16			hw_rq_counter;
-	__be16			sw_rcyclic_byte_counter;
-	__be16			sw_rq_counter;
-	u8			rsvd0[5];
-	u8			cgs;
-	u8			cs_req;
-	u8			cs_res;
-	__be64			dc_access_key;
-	u8			rsvd1[24];
-};
-
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 584077565f12..2d3ddd2b85e0 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -98,7 +98,6 @@ struct qed_rdma_device {
 	u64 max_mr_size;
 	u32 max_cqe;
 	u32 max_mw;
-	u32 max_fmr;
 	u32 max_mr_mw_fmr_pbl;
 	u64 max_mr_mw_fmr_size;
 	u32 max_pd;
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 058cfbc2b37f..0f1ea5f2d01c 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -11,6 +11,7 @@
 
 #include <rdma/ib_mad.h>
 #include <rdma/ib_sa.h>
+#include <rdma/rdma_cm.h>
 
 /* ib_cm and ib_user_cm modules share /sys/class/infiniband_cm */
 extern struct class cm_class;
@@ -115,6 +116,7 @@ struct ib_cm_req_event_param {
 	unsigned int		retry_count:3;
 	unsigned int		rnr_retry_count:3;
 	unsigned int		srq:1;
+	struct rdma_ucm_ece	ece;
 };
 
 struct ib_cm_rep_event_param {
@@ -129,6 +131,7 @@ struct ib_cm_rep_event_param {
 	unsigned int		flow_control:1;
 	unsigned int		rnr_retry_count:3;
 	unsigned int		srq:1;
+	struct rdma_ucm_ece	ece;
 };
 
 enum ib_cm_rej_reason {
@@ -164,7 +167,8 @@ enum ib_cm_rej_reason {
 	IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID	= 30,
 	IB_CM_REJ_INVALID_CLASS_VERSION		= 31,
 	IB_CM_REJ_INVALID_FLOW_LABEL		= 32,
-	IB_CM_REJ_INVALID_ALT_FLOW_LABEL	= 33
+	IB_CM_REJ_INVALID_ALT_FLOW_LABEL	= 33,
+	IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED	= 35,
 };
 
 struct ib_cm_rej_event_param {
@@ -369,6 +373,7 @@ struct ib_cm_req_param {
 	u8			rnr_retry_count;
 	u8			max_cm_retries;
 	u8			srq;
+	struct rdma_ucm_ece	ece;
 };
 
 /**
@@ -392,6 +397,7 @@ struct ib_cm_rep_param {
 	u8		flow_control;
 	u8		rnr_retry_count;
 	u8		srq;
+	struct rdma_ucm_ece ece;
 };
 
 /**
@@ -546,6 +552,7 @@ struct ib_cm_sidr_rep_param {
 	u8			info_length;
 	const void		*private_data;
 	u8			private_data_len;
+	struct rdma_ucm_ece	ece;
 };
 
 /**
diff --git a/include/rdma/ib_fmr_pool.h b/include/rdma/ib_fmr_pool.h
deleted file mode 100644
index 2fd9bfb6d648..000000000000
--- a/include/rdma/ib_fmr_pool.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
- * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#if !defined(IB_FMR_POOL_H)
-#define IB_FMR_POOL_H
-
-#include <rdma/ib_verbs.h>
-
-struct ib_fmr_pool;
-
-/**
- * struct ib_fmr_pool_param - Parameters for creating FMR pool
- * @max_pages_per_fmr:Maximum number of pages per map request.
- * @page_shift: Log2 of sizeof "pages" mapped by this fmr
- * @access:Access flags for FMRs in pool.
- * @pool_size:Number of FMRs to allocate for pool.
- * @dirty_watermark:Flush is triggered when @dirty_watermark dirty
- *     FMRs are present.
- * @flush_function:Callback called when unmapped FMRs are flushed and
- *     more FMRs are possibly available for mapping
- * @flush_arg:Context passed to user's flush function.
- * @cache:If set, FMRs may be reused after unmapping for identical map
- *     requests.
- */
-struct ib_fmr_pool_param {
-	int                     max_pages_per_fmr;
-	int                     page_shift;
-	enum ib_access_flags    access;
-	int                     pool_size;
-	int                     dirty_watermark;
-	void                  (*flush_function)(struct ib_fmr_pool *pool,
-						void               *arg);
-	void                   *flush_arg;
-	unsigned                cache:1;
-};
-
-struct ib_pool_fmr {
-	struct ib_fmr      *fmr;
-	struct ib_fmr_pool *pool;
-	struct list_head    list;
-	struct hlist_node   cache_node;
-	int                 ref_count;
-	int                 remap_count;
-	u64                 io_virtual_address;
-	int                 page_list_len;
-	u64                 page_list[];
-};
-
-struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
-				       struct ib_fmr_pool_param *params);
-
-void ib_destroy_fmr_pool(struct ib_fmr_pool *pool);
-
-int ib_flush_fmr_pool(struct ib_fmr_pool *pool);
-
-struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle,
-					 u64                *page_list,
-					 int                 list_len,
-					 u64                 io_virtual_address);
-
-void ib_fmr_pool_unmap(struct ib_pool_fmr *fmr);
-
-#endif /* IB_FMR_POOL_H */
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 4e62650e2127..8c093fc1bb9f 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -559,20 +559,6 @@ typedef void (*ib_mad_send_handler)(struct ib_mad_agent *mad_agent,
 				    struct ib_mad_send_wc *mad_send_wc);
 
 /**
- * ib_mad_snoop_handler - Callback handler for snooping sent MADs.
- * @mad_agent: MAD agent that snooped the MAD.
- * @send_buf: send MAD data buffer.
- * @mad_send_wc: Work completion information on the sent MAD.  Valid
- *   only for snooping that occurs on a send completion.
- *
- * Clients snooping MADs should not modify data referenced by the @send_buf
- * or @mad_send_wc.
- */
-typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
-				     struct ib_mad_send_buf *send_buf,
-				     struct ib_mad_send_wc *mad_send_wc);
-
-/**
  * ib_mad_recv_handler - callback handler for a received MAD.
  * @mad_agent: MAD agent requesting the received MAD.
  * @send_buf: Send buffer if found, else NULL
@@ -581,8 +567,7 @@ typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
  * MADs received in response to a send request operation will be handed to
  * the user before the send operation completes.  All data buffers given
  * to registered agents through this routine are owned by the receiving
- * client, except for snooping agents.  Clients snooping MADs should not
- * modify the data referenced by @mad_recv_wc.
+ * client.
  */
 typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
 				    struct ib_mad_send_buf *send_buf,
@@ -595,7 +580,6 @@ typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
  * @mr: Memory region for system memory usable for DMA.
  * @recv_handler: Callback handler for a received MAD.
  * @send_handler: Callback handler for a sent MAD.
- * @snoop_handler: Callback handler for snooped sent MADs.
  * @context: User-specified context associated with this registration.
  * @hi_tid: Access layer assigned transaction ID for this client.
  *   Unsolicited MADs sent by this client will have the upper 32-bits
@@ -612,7 +596,6 @@ struct ib_mad_agent {
 	struct ib_qp		*qp;
 	ib_mad_recv_handler	recv_handler;
 	ib_mad_send_handler	send_handler;
-	ib_mad_snoop_handler	snoop_handler;
 	void			*context;
 	u32			hi_tid;
 	u32			flags;
@@ -720,36 +703,6 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 					   ib_mad_recv_handler recv_handler,
 					   void *context,
 					   u32 registration_flags);
-
-enum ib_mad_snoop_flags {
-	/*IB_MAD_SNOOP_POSTED_SENDS	   = 1,*/
-	/*IB_MAD_SNOOP_RMPP_SENDS	   = (1<<1),*/
-	IB_MAD_SNOOP_SEND_COMPLETIONS	   = (1<<2),
-	/*IB_MAD_SNOOP_RMPP_SEND_COMPLETIONS = (1<<3),*/
-	IB_MAD_SNOOP_RECVS		   = (1<<4)
-	/*IB_MAD_SNOOP_RMPP_RECVS	   = (1<<5),*/
-	/*IB_MAD_SNOOP_REDIRECTED_QPS	   = (1<<6)*/
-};
-
-/**
- * ib_register_mad_snoop - Register to snoop sent and received MADs.
- * @device: The device to register with.
- * @port_num: The port on the specified device to use.
- * @qp_type: Specifies which QP traffic to snoop.  Must be either
- *   IB_QPT_SMI or IB_QPT_GSI.
- * @mad_snoop_flags: Specifies information where snooping occurs.
- * @send_handler: The callback routine invoked for a snooped send.
- * @recv_handler: The callback routine invoked for a snooped receive.
- * @context: User specified context associated with the registration.
- */
-struct ib_mad_agent *ib_register_mad_snoop(struct ib_device *device,
-					   u8 port_num,
-					   enum ib_qp_type qp_type,
-					   int mad_snoop_flags,
-					   ib_mad_snoop_handler snoop_handler,
-					   ib_mad_recv_handler recv_handler,
-					   void *context);
-
 /**
  * ib_unregister_mad_agent - Unregisters a client from using MAD services.
  * @mad_agent: Corresponding MAD registration request to deregister.
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index bbc5cfb57cd2..033e7044f29c 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -305,7 +305,7 @@ enum ib_device_cap_flags {
 	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
 	/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
 	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
-	IB_DEVICE_RDMA_NETDEV_OPA_VNIC		= (1ULL << 35),
+	IB_DEVICE_RDMA_NETDEV_OPA		= (1ULL << 35),
 	/* The device supports padding incoming writes to cacheline. */
 	IB_DEVICE_PCI_WRITE_END_PADDING		= (1ULL << 36),
 	IB_DEVICE_ALLOW_USER_UNREG		= (1ULL << 37),
@@ -430,8 +430,6 @@ struct ib_device_attr {
 	int			max_mcast_qp_attach;
 	int			max_total_mcast_qp_attach;
 	int			max_ah;
-	int			max_fmr;
-	int			max_map_per_fmr;
 	int			max_srq;
 	int			max_srq_wr;
 	int			max_srq_sge;
@@ -462,6 +460,11 @@ enum ib_mtu {
 	IB_MTU_4096 = 5
 };
 
+enum opa_mtu {
+	OPA_MTU_8192 = 6,
+	OPA_MTU_10240 = 7
+};
+
 static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
 {
 	switch (mtu) {
@@ -488,6 +491,28 @@ static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
 		return IB_MTU_256;
 }
 
+static inline int opa_mtu_enum_to_int(enum opa_mtu mtu)
+{
+	switch (mtu) {
+	case OPA_MTU_8192:
+		return 8192;
+	case OPA_MTU_10240:
+		return 10240;
+	default:
+		return(ib_mtu_enum_to_int((enum ib_mtu)mtu));
+	}
+}
+
+static inline enum opa_mtu opa_mtu_int_to_enum(int mtu)
+{
+	if (mtu >= 10240)
+		return OPA_MTU_10240;
+	else if (mtu >= 8192)
+		return OPA_MTU_8192;
+	else
+		return ((enum opa_mtu)ib_mtu_int_to_enum(mtu));
+}
+
 enum ib_port_state {
 	IB_PORT_NOP		= 0,
 	IB_PORT_DOWN		= 1,
@@ -651,6 +676,7 @@ struct ib_port_attr {
 	enum ib_port_state	state;
 	enum ib_mtu		max_mtu;
 	enum ib_mtu		active_mtu;
+	u32                     phys_mtu;
 	int			gid_tbl_len;
 	unsigned int		ip_gids:1;
 	/* This is the value from PortInfo CapabilityMask, defined by IBA */
@@ -880,6 +906,12 @@ struct ib_mr_status {
  */
 __attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
 
+struct rdma_ah_init_attr {
+	struct rdma_ah_attr *ah_attr;
+	u32 flags;
+	struct net_device *xmit_slave;
+};
+
 enum rdma_ah_attr_type {
 	RDMA_AH_ATTR_TYPE_UNDEFINED,
 	RDMA_AH_ATTR_TYPE_IB,
@@ -1006,9 +1038,9 @@ enum ib_cq_notify_flags {
 };
 
 enum ib_srq_type {
-	IB_SRQT_BASIC,
-	IB_SRQT_XRC,
-	IB_SRQT_TM,
+	IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC,
+	IB_SRQT_XRC = IB_UVERBS_SRQT_XRC,
+	IB_SRQT_TM = IB_UVERBS_SRQT_TM,
 };
 
 static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
@@ -1077,16 +1109,16 @@ enum ib_qp_type {
 	IB_QPT_SMI,
 	IB_QPT_GSI,
 
-	IB_QPT_RC,
-	IB_QPT_UC,
-	IB_QPT_UD,
+	IB_QPT_RC = IB_UVERBS_QPT_RC,
+	IB_QPT_UC = IB_UVERBS_QPT_UC,
+	IB_QPT_UD = IB_UVERBS_QPT_UD,
 	IB_QPT_RAW_IPV6,
 	IB_QPT_RAW_ETHERTYPE,
-	IB_QPT_RAW_PACKET = 8,
-	IB_QPT_XRC_INI = 9,
-	IB_QPT_XRC_TGT,
+	IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET,
+	IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI,
+	IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT,
 	IB_QPT_MAX,
-	IB_QPT_DRIVER = 0xFF,
+	IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER,
 	/* Reserve a range for qp types internal to the low level driver.
 	 * These qp types will not be visible at the IB core layer, so the
 	 * IB_QPT_MAX usages should not be affected in the core layer
@@ -1105,17 +1137,21 @@ enum ib_qp_type {
 
 enum ib_qp_create_flags {
 	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
-	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
+	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	=
+		IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
 	IB_QP_CREATE_CROSS_CHANNEL              = 1 << 2,
 	IB_QP_CREATE_MANAGED_SEND               = 1 << 3,
 	IB_QP_CREATE_MANAGED_RECV               = 1 << 4,
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	IB_QP_CREATE_INTEGRITY_EN		= 1 << 6,
-	/* FREE					= 1 << 7, */
-	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
-	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
+	IB_QP_CREATE_NETDEV_USE			= 1 << 7,
+	IB_QP_CREATE_SCATTER_FCS		=
+		IB_UVERBS_QP_CREATE_SCATTER_FCS,
+	IB_QP_CREATE_CVLAN_STRIPPING		=
+		IB_UVERBS_QP_CREATE_CVLAN_STRIPPING,
 	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
-	IB_QP_CREATE_PCI_WRITE_END_PADDING	= 1 << 11,
+	IB_QP_CREATE_PCI_WRITE_END_PADDING	=
+		IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1267,6 +1303,7 @@ struct ib_qp_attr {
 	u8			alt_port_num;
 	u8			alt_timeout;
 	u32			rate_limit;
+	struct net_device	*xmit_slave;
 };
 
 enum ib_wr_opcode {
@@ -1436,12 +1473,6 @@ enum ib_mr_rereg_flags {
 	IB_MR_REREG_SUPPORTED	= ((IB_MR_REREG_ACCESS << 1) - 1)
 };
 
-struct ib_fmr_attr {
-	int	max_pages;
-	int	max_maps;
-	u8	page_shift;
-};
-
 struct ib_umem;
 
 enum rdma_remove_reason {
@@ -1456,6 +1487,11 @@ enum rdma_remove_reason {
 	RDMA_REMOVE_DRIVER_REMOVE,
 	/* uobj is being cleaned-up before being committed */
 	RDMA_REMOVE_ABORT,
+	/*
+	 * uobj has been fully created, with the uobj->object set, but is being
+	 * cleaned up before being comitted
+	 */
+	RDMA_REMOVE_ABORT_HWOBJ,
 };
 
 struct ib_rdmacg_object {
@@ -1544,10 +1580,12 @@ struct ib_ah {
 typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
 
 enum ib_poll_context {
-	IB_POLL_DIRECT,		   /* caller context, no hw completions */
 	IB_POLL_SOFTIRQ,	   /* poll from softirq context */
 	IB_POLL_WORKQUEUE,	   /* poll from workqueue */
 	IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */
+	IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE,
+
+	IB_POLL_DIRECT,		   /* caller context, no hw completions */
 };
 
 struct ib_cq {
@@ -1557,9 +1595,11 @@ struct ib_cq {
 	void                  (*event_handler)(struct ib_event *, void *);
 	void                   *cq_context;
 	int               	cqe;
+	unsigned int		cqe_used;
 	atomic_t          	usecnt; /* count number of work queues */
 	enum ib_poll_context	poll_ctx;
 	struct ib_wc		*wc;
+	struct list_head        pool_entry;
 	union {
 		struct irq_poll		iop;
 		struct work_struct	work;
@@ -1569,7 +1609,9 @@ struct ib_cq {
 
 	/* updated only by trace points */
 	ktime_t timestamp;
-	bool interrupt;
+	u8 interrupt:1;
+	u8 shared:1;
+	unsigned int comp_vector;
 
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
@@ -1614,7 +1656,7 @@ enum ib_raw_packet_caps {
 };
 
 enum ib_wq_type {
-	IB_WQT_RQ
+	IB_WQT_RQ = IB_UVERBS_WQT_RQ,
 };
 
 enum ib_wq_state {
@@ -1637,10 +1679,11 @@ 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,
-	IB_WQ_FLAGS_PCI_WRITE_END_PADDING = 1 << 3,
+	IB_WQ_FLAGS_CVLAN_STRIPPING	= IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING,
+	IB_WQ_FLAGS_SCATTER_FCS		= IB_UVERBS_WQ_FLAGS_SCATTER_FCS,
+	IB_WQ_FLAGS_DELAY_DROP		= IB_UVERBS_WQ_FLAGS_DELAY_DROP,
+	IB_WQ_FLAGS_PCI_WRITE_END_PADDING =
+				IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING,
 };
 
 struct ib_wq_init_attr {
@@ -1804,14 +1847,6 @@ struct ib_mw {
 	enum ib_mw_type         type;
 };
 
-struct ib_fmr {
-	struct ib_device	*device;
-	struct ib_pd		*pd;
-	struct list_head	list;
-	u32			lkey;
-	u32			rkey;
-};
-
 /* Supported steering options */
 enum ib_flow_attr_type {
 	/* steering according to rule specifications */
@@ -2198,6 +2233,7 @@ struct rdma_netdev {
 	void              *clnt_priv;
 	struct ib_device  *hca;
 	u8                 port_num;
+	int                mtu;
 
 	/*
 	 * cleanup function must be specified.
@@ -2403,8 +2439,8 @@ struct ib_device_ops {
 	void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
 	int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
 	void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
-	int (*create_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr,
-			 u32 flags, struct ib_udata *udata);
+	int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
+			 struct ib_udata *udata);
 	int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 	int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 	void (*destroy_ah)(struct ib_ah *ah, u32 flags);
@@ -2453,12 +2489,6 @@ struct ib_device_ops {
 	struct ib_mw *(*alloc_mw)(struct ib_pd *pd, 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,
-				    struct ib_fmr_attr *fmr_attr);
-	int (*map_phys_fmr)(struct ib_fmr *fmr, u64 *page_list, int list_len,
-			    u64 iova);
-	int (*unmap_fmr)(struct list_head *fmr_list);
-	int (*dealloc_fmr)(struct ib_fmr *fmr);
 	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	struct ib_xrcd *(*alloc_xrcd)(struct ib_device *device,
@@ -2687,6 +2717,10 @@ struct ib_device {
 #endif
 
 	u32                          index;
+
+	spinlock_t                   cq_pools_lock;
+	struct list_head             cq_pools[IB_POLL_LAST_POOL_TYPE + 1];
+
 	struct rdma_restrack_root *res;
 
 	const struct uapi_definition   *driver_def;
@@ -2709,12 +2743,13 @@ struct ib_device {
 	/* Used by iWarp CM */
 	char iw_ifname[IFNAMSIZ];
 	u32 iw_driver_flags;
+	u32 lag_flags;
 };
 
 struct ib_client_nl_info;
 struct ib_client {
 	const char *name;
-	void (*add)   (struct ib_device *);
+	int (*add)(struct ib_device *ibdev);
 	void (*remove)(struct ib_device *, void *client_data);
 	void (*rename)(struct ib_device *dev, void *client_data);
 	int (*get_nl_info)(struct ib_device *ibdev, void *client_data,
@@ -3355,6 +3390,55 @@ static inline unsigned int rdma_find_pg_bit(unsigned long addr,
 	return __fls(pgsz);
 }
 
+/**
+ * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not.
+ * @device: Device
+ * @port_num: 1 based Port number
+ *
+ * Return true if port is an Intel OPA port , false if not
+ */
+static inline bool rdma_core_cap_opa_port(struct ib_device *device,
+					  u32 port_num)
+{
+	return (device->port_data[port_num].immutable.core_cap_flags &
+		RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA;
+}
+
+/**
+ * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value.
+ * @device: Device
+ * @port_num: Port number
+ * @mtu: enum value of MTU
+ *
+ * Return the MTU size supported by the port as an integer value. Will return
+ * -1 if enum value of mtu is not supported.
+ */
+static inline int rdma_mtu_enum_to_int(struct ib_device *device, u8 port,
+				       int mtu)
+{
+	if (rdma_core_cap_opa_port(device, port))
+		return opa_mtu_enum_to_int((enum opa_mtu)mtu);
+	else
+		return ib_mtu_enum_to_int((enum ib_mtu)mtu);
+}
+
+/**
+ * rdma_mtu_from_attr - Return the mtu of the port from the port attribute.
+ * @device: Device
+ * @port_num: Port number
+ * @attr: port attribute
+ *
+ * Return the MTU size supported by the port as an integer value.
+ */
+static inline int rdma_mtu_from_attr(struct ib_device *device, u8 port,
+				     struct ib_port_attr *attr)
+{
+	if (rdma_core_cap_opa_port(device, port))
+		return attr->phys_mtu;
+	else
+		return ib_mtu_enum_to_int(attr->max_mtu);
+}
+
 int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port,
 			 int state);
 int ib_get_vf_config(struct ib_device *device, int vf, u8 port,
@@ -3551,21 +3635,18 @@ static inline int rdma_destroy_ah(struct ib_ah *ah, u32 flags)
 	return rdma_destroy_ah_user(ah, flags, NULL);
 }
 
-/**
- * ib_create_srq - Creates a SRQ associated with the specified protection
- *   domain.
- * @pd: The protection domain associated with the SRQ.
- * @srq_init_attr: A list of initial attributes required to create the
- *   SRQ.  If SRQ creation succeeds, then the attributes are updated to
- *   the actual capabilities of the created SRQ.
- *
- * srq_attr->max_wr and srq_attr->max_sge are read the determine the
- * requested size of the SRQ, and set to the actual values allocated
- * on return.  If ib_create_srq() succeeds, then max_wr and max_sge
- * will always be at least as large as the requested values.
- */
-struct ib_srq *ib_create_srq(struct ib_pd *pd,
-			     struct ib_srq_init_attr *srq_init_attr);
+struct ib_srq *ib_create_srq_user(struct ib_pd *pd,
+				  struct ib_srq_init_attr *srq_init_attr,
+				  struct ib_usrq_object *uobject,
+				  struct ib_udata *udata);
+static inline struct ib_srq *
+ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr)
+{
+	if (!pd->device->ops.create_srq)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	return ib_create_srq_user(pd, srq_init_attr, NULL, NULL);
+}
 
 /**
  * ib_modify_srq - Modifies the attributes for the specified SRQ.
@@ -3816,6 +3897,8 @@ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev,
  * ib_free_cq_user - Free kernel/user CQ
  * @cq: The CQ to free
  * @udata: Valid user data or NULL for kernel objects
+ *