mlx5 feature for 4.14

index 894aec4a7c9d..544b0ae5d8dc 100644
@@ -821,6 +821,27 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (field_avail(typeof(resp), reserved, uhw->outlen))
 		resp.response_length += sizeof(resp.reserved);
 
+	if (field_avail(typeof(resp), sw_parsing_caps,
+			uhw->outlen)) {
+		resp.response_length += sizeof(resp.sw_parsing_caps);
+		if (MLX5_CAP_ETH(mdev, swp)) {
+			resp.sw_parsing_caps.sw_parsing_offloads |=
+				MLX5_IB_SW_PARSING;
+
+			if (MLX5_CAP_ETH(mdev, swp_csum))
+				resp.sw_parsing_caps.sw_parsing_offloads |=
+					MLX5_IB_SW_PARSING_CSUM;
+
+			if (MLX5_CAP_ETH(mdev, swp_lso))
+				resp.sw_parsing_caps.sw_parsing_offloads |=
+					MLX5_IB_SW_PARSING_LSO;
+
+			if (resp.sw_parsing_caps.sw_parsing_offloads)
+				resp.sw_parsing_caps.supported_qpts =
+					BIT(IB_QPT_RAW_PACKET);
+		}
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 

index ebbfd721661d..e58cc42a77a2 100644
@@ -1083,6 +1083,9 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 	MLX5_SET(sqc, sqc, cqn, MLX5_GET(qpc, qpc, cqn_snd));
 	MLX5_SET(sqc, sqc, tis_lst_sz, 1);
 	MLX5_SET(sqc, sqc, tis_num_0, sq->tisn);
+	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
+	    MLX5_CAP_ETH(dev->mdev, swp))
+		MLX5_SET(sqc, sqc, allow_swp, 1);
 
 	wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);

index 0b3d30837a9f..64d398e662cd 100644
@@ -168,6 +168,22 @@ struct mlx5_packet_pacing_caps {
 	__u32 reserved;
 };
 
+enum mlx5_ib_sw_parsing_offloads {
+	MLX5_IB_SW_PARSING = 1 << 0,
+	MLX5_IB_SW_PARSING_CSUM = 1 << 1,
+	MLX5_IB_SW_PARSING_LSO = 1 << 2,
+};
+
+struct mlx5_ib_sw_parsing_caps {
+	__u32 sw_parsing_offloads; /* enum mlx5_ib_sw_parsing_offloads */
+
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_RAW_PACKET
+	 */
+	__u32 supported_qpts;
+};
+
 struct mlx5_ib_query_device_resp {
 	__u32	comp_mask;
 	__u32	response_length;

@@ -177,6 +193,7 @@ struct mlx5_ib_query_device_resp {
 	struct	mlx5_packet_pacing_caps packet_pacing_caps;
 	__u32	mlx5_ib_support_multi_pkt_send_wqes;
 	__u32	reserved;
+	struct mlx5_ib_sw_parsing_caps sw_parsing_caps;
 };
 
 struct mlx5_ib_create_cq {

index 76a731f39d2b..189e80cd6b2f 100644
@@ -508,7 +508,7 @@ struct mlx5_ib_mr {
 	struct mlx5_shared_mr_info	*smr_info;
 	struct list_head	list;
 	int			order;
-	int			umred;
+	bool			allocated_from_cache;
 	int			npages;
 	struct mlx5_ib_dev     *dev;
 	u32 out[MLX5_ST_SZ_DW(create_mkey_out)];

index a0eb2f96179a..bc87016021e3 100644
@@ -48,8 +48,7 @@ enum {
 #define MLX5_UMR_ALIGN 2048
 
 static int clean_mr(struct mlx5_ib_mr *mr);
-static int max_umr_order(struct mlx5_ib_dev *dev);
-static int use_umr(struct mlx5_ib_dev *dev, int order);
+static int mr_cache_max_order(struct mlx5_ib_dev *dev);
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 
 static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)

@@ -184,7 +183,7 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 			break;
 		}
 		mr->order = ent->order;
-		mr->umred = 1;
+		mr->allocated_from_cache = 1;
 		mr->dev = dev;
 
 		MLX5_SET(mkc, mkc, free, 1);

@@ -497,7 +496,7 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 	int i;
 
 	c = order2idx(dev, order);
-	last_umr_cache_entry = order2idx(dev, max_umr_order(dev));
+	last_umr_cache_entry = order2idx(dev, mr_cache_max_order(dev));
 	if (c < 0 || c > last_umr_cache_entry) {
 		mlx5_ib_warn(dev, "order %d, cache index %d\n", order, c);
 		return NULL;

@@ -677,12 +676,12 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
 		queue_work(cache->wq, &ent->work);
 
-		if (i > MAX_UMR_CACHE_ENTRY) {
+		if (i > MR_CACHE_LAST_STD_ENTRY) {
 			mlx5_odp_init_mr_cache_entry(ent);
 			continue;
 		}
 
-		if (!use_umr(dev, ent->order))
+		if (ent->order > mr_cache_max_order(dev))
 			continue;
 
 		ent->page = PAGE_SHIFT;

@@ -819,18 +818,13 @@ static int get_octo_len(u64 addr, u64 len, int page_size)
 	return (npages + 1) / 2;
 }
 
-static int max_umr_order(struct mlx5_ib_dev *dev)
+static int mr_cache_max_order(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
-		return MAX_UMR_CACHE_ENTRY + 2;
+		return MR_CACHE_LAST_STD_ENTRY + 2;
 	return MLX5_MAX_UMR_SHIFT;
 }
 
-static int use_umr(struct mlx5_ib_dev *dev, int order)
-{
-	return order <= max_umr_order(dev);
-}
-
 static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,
 		       int access_flags, struct ib_umem **umem,
 		       int *npages, int *page_shift, int *ncont,

@@ -1149,6 +1143,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	MLX5_SET(mkc, mkc, rr, !!(access_flags & IB_ACCESS_REMOTE_READ));
 	MLX5_SET(mkc, mkc, lw, !!(access_flags & IB_ACCESS_LOCAL_WRITE));
 	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, umr_en, 1);
 
 	MLX5_SET64(mkc, mkc, start_addr, virt_addr);
 	MLX5_SET64(mkc, mkc, len, length);

@@ -1231,7 +1226,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
         if (err < 0)
 		return ERR_PTR(err);
 
-	if (use_umr(dev, order)) {
+	if (order <= mr_cache_max_order(dev)) {
 		mr = reg_umr(pd, umem, virt_addr, length, ncont, page_shift,
 			     order, access_flags);
 		if (PTR_ERR(mr) == -EAGAIN) {

@@ -1355,7 +1350,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		/*
 		 * UMR can't be used - MKey needs to be replaced.
 		 */
-		if (mr->umred) {
+		if (mr->allocated_from_cache) {
 			err = unreg_umr(dev, mr);
 			if (err)
 				mlx5_ib_warn(dev, "Failed to unregister MR\n");

@@ -1373,7 +1368,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		if (IS_ERR(mr))
 			return PTR_ERR(mr);
 
-		mr->umred = 0;
+		mr->allocated_from_cache = 0;
 	} else {
 		/*
 		 * Send a UMR WQE

@@ -1461,7 +1456,7 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 static int clean_mr(struct mlx5_ib_mr *mr)
 {
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
-	int umred = mr->umred;
+	int allocated_from_cache = mr->allocated_from_cache;
 	int err;
 
 	if (mr->sig) {

@@ -1479,7 +1474,7 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 
 	mlx5_free_priv_descs(mr);
 
-	if (!umred) {
+	if (!allocated_from_cache) {
 		err = destroy_mkey(dev, mr);
 		if (err) {
 			mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",

@@ -1490,7 +1485,7 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 		mlx5_mr_cache_free(dev, mr);
 	}
 
-	if (!umred)
+	if (!allocated_from_cache)
 		kfree(mr);
 
 	return 0;

index f17e51a4ef94..1640de3200b8 100644
@@ -1099,7 +1099,7 @@ enum {
 };
 
 enum {
-	MAX_UMR_CACHE_ENTRY = 20,
+	MR_CACHE_LAST_STD_ENTRY = 20,
 	MLX5_IMR_MTT_CACHE_ENTRY,
 	MLX5_IMR_KSM_CACHE_ENTRY,
 	MAX_MR_CACHE_ENTRIES

index bc87016021e3..aa6f71570b77 100644
@@ -898,7 +898,8 @@ static int mlx5_ib_post_send_wait(struct mlx5_ib_dev *dev,
 	return err;
 }
 
-static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
+static struct mlx5_ib_mr *alloc_mr_from_cache(
+				  struct ib_pd *pd, struct ib_umem *umem,
 				  u64 virt_addr, u64 len, int npages,
 				  int page_shift, int order, int access_flags)
 {

@@ -930,16 +931,6 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	mr->mmkey.size = len;
 	mr->mmkey.pd = to_mpd(pd)->pdn;
 
-	err = mlx5_ib_update_xlt(mr, 0, npages, page_shift,
-				 MLX5_IB_UPD_XLT_ENABLE);
-
-	if (err) {
-		mlx5_mr_cache_free(dev, mr);
-		return ERR_PTR(err);
-	}
-
-	mr->live = 1;
-
 	return mr;
 }
 

@@ -1105,7 +1096,8 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 				     u64 virt_addr, u64 length,
 				     struct ib_umem *umem, int npages,
-				     int page_shift, int access_flags)
+				     int page_shift, int access_flags,
+				     bool populate)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_mr *mr;

@@ -1120,15 +1112,19 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
-	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
-		sizeof(*pas) * ((npages + 1) / 2) * 2;
+	mr->ibmr.pd = pd;
+	mr->access_flags = access_flags;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	if (populate)
+		inlen += sizeof(*pas) * roundup(npages, 2);
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		err = -ENOMEM;
 		goto err_1;
 	}
 	pas = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
-	if (!(access_flags & IB_ACCESS_ON_DEMAND))
+	if (populate && !(access_flags & IB_ACCESS_ON_DEMAND))
 		mlx5_ib_populate_pas(dev, umem, page_shift, pas,
 				     pg_cap ? MLX5_IB_MTT_PRESENT : 0);
 

@@ -1137,6 +1133,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	MLX5_SET(create_mkey_in, in, pg_access, !!(pg_cap));
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, free, !populate);
 	MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT);
 	MLX5_SET(mkc, mkc, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE));

@@ -1153,8 +1150,10 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 		 get_octo_len(virt_addr, length, 1 << page_shift));
 	MLX5_SET(mkc, mkc, log_page_size, page_shift);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
-		 get_octo_len(virt_addr, length, 1 << page_shift));
+	if (populate) {
+		MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+			 get_octo_len(virt_addr, length, 1 << page_shift));
+	}
 
 	err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen);
 	if (err) {

@@ -1163,9 +1162,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	}
 	mr->mmkey.type = MLX5_MKEY_MR;
 	mr->desc_size = sizeof(struct mlx5_mtt);
-	mr->umem = umem;
 	mr->dev = dev;
-	mr->live = 1;
 	kvfree(in);
 
 	mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmkey.key);

@@ -1205,6 +1202,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int ncont;
 	int order;
 	int err;
+	bool use_umr = true;
 
 	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
 		    start, virt_addr, length, access_flags);

@@ -1223,27 +1221,29 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	err = mr_umem_get(pd, start, length, access_flags, &umem, &npages,
 			   &page_shift, &ncont, &order);
 
-        if (err < 0)
+	if (err < 0)
 		return ERR_PTR(err);
 
 	if (order <= mr_cache_max_order(dev)) {
-		mr = reg_umr(pd, umem, virt_addr, length, ncont, page_shift,
-			     order, access_flags);
+		mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont,
+					 page_shift, order, access_flags);
 		if (PTR_ERR(mr) == -EAGAIN) {
 			mlx5_ib_dbg(dev, "cache empty for order %d", order);
 			mr = NULL;
 		}
-	} else if (access_flags & IB_ACCESS_ON_DEMAND &&
-		   !MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
-		err = -EINVAL;
-		pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
-		goto error;
+	} else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
+		if (access_flags & IB_ACCESS_ON_DEMAND) {
+			err = -EINVAL;
+			pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
+			goto error;
+		}
+		use_umr = false;
 	}
 
 	if (!mr) {
 		mutex_lock(&dev->slow_path_mutex);
 		mr = reg_create(NULL, pd, virt_addr, length, umem, ncont,
-				page_shift, access_flags);
+				page_shift, access_flags, !use_umr);
 		mutex_unlock(&dev->slow_path_mutex);
 	}
 

@@ -1261,8 +1261,22 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	update_odp_mr(mr);
 #endif
 
-	return &mr->ibmr;
+	if (use_umr) {
+		int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE;
+
+		if (access_flags & IB_ACCESS_ON_DEMAND)
+			update_xlt_flags |= MLX5_IB_UPD_XLT_ZAP;
 
+		err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift,
+					 update_xlt_flags);
+		if (err) {
+			mlx5_ib_dereg_mr(&mr->ibmr);
+			return ERR_PTR(err);
+		}
+	}
+
+	mr->live = 1;
+	return &mr->ibmr;
 error:
 	ib_umem_release(umem);
 	return ERR_PTR(err);

@@ -1363,12 +1377,13 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			return err;
 
 		mr = reg_create(ib_mr, pd, addr, len, mr->umem, ncont,
-				page_shift, access_flags);
+				page_shift, access_flags, true);
 
 		if (IS_ERR(mr))
 			return PTR_ERR(mr);
 
 		mr->allocated_from_cache = 0;
+		mr->live = 1;
 	} else {
 		/*
 		 * Send a UMR WQE

index aa6f71570b77..8cf53eb13148 100644
@@ -1490,19 +1490,19 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 	mlx5_free_priv_descs(mr);
 
 	if (!allocated_from_cache) {
+		u32 key = mr->mmkey.key;
+
 		err = destroy_mkey(dev, mr);
+		kfree(mr);
 		if (err) {
 			mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
-				     mr->mmkey.key, err);
+				     key, err);
 			return err;
 		}
 	} else {
 		mlx5_mr_cache_free(dev, mr);
 	}
 
-	if (!allocated_from_cache)
-		kfree(mr);
-
 	return 0;
 }
 

index 8cf53eb13148..0e2789d9bb4d 100644
@@ -808,13 +808,14 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc)
 	return ERR_PTR(err);
 }
 
-static int get_octo_len(u64 addr, u64 len, int page_size)
+static int get_octo_len(u64 addr, u64 len, int page_shift)
 {
+	u64 page_size = 1ULL << page_shift;
 	u64 offset;
 	int npages;
 
 	offset = addr & (page_size - 1);
-	npages = ALIGN(len + offset, page_size) >> ilog2(page_size);
+	npages = ALIGN(len + offset, page_size) >> page_shift;
 	return (npages + 1) / 2;
 }
 

@@ -1147,12 +1148,12 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, bsf_octword_size, 0);
 	MLX5_SET(mkc, mkc, translations_octword_size,
-		 get_octo_len(virt_addr, length, 1 << page_shift));
+		 get_octo_len(virt_addr, length, page_shift));
 	MLX5_SET(mkc, mkc, log_page_size, page_shift);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	if (populate) {
 		MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
-			 get_octo_len(virt_addr, length, 1 << page_shift));
+			 get_octo_len(virt_addr, length, page_shift));
 	}
 
 	err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen);

index 544b0ae5d8dc..438663356982 100644
@@ -2134,7 +2134,7 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
  * it won't fall into the multicast flow steering table and this rule
  * could steal other multicast packets.
  */
-static bool flow_is_multicast_only(struct ib_flow_attr *ib_attr)
+static bool flow_is_multicast_only(const struct ib_flow_attr *ib_attr)
 {
 	union ib_flow_spec *flow_spec;
 

@@ -2346,10 +2346,31 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 	return err ? ERR_PTR(err) : prio;
 }
 
-static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
-						     struct mlx5_ib_flow_prio *ft_prio,
-						     const struct ib_flow_attr *flow_attr,
-						     struct mlx5_flow_destination *dst)
+static void set_underlay_qp(struct mlx5_ib_dev *dev,
+			    struct mlx5_flow_spec *spec,
+			    u32 underlay_qpn)
+{
+	void *misc_params_c = MLX5_ADDR_OF(fte_match_param,
+					   spec->match_criteria,
+					   misc_parameters);
+	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+					   misc_parameters);
+
+	if (underlay_qpn &&
+	    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
+				      ft_field_support.bth_dst_qp)) {
+		MLX5_SET(fte_match_set_misc,
+			 misc_params_v, bth_dst_qp, underlay_qpn);
+		MLX5_SET(fte_match_set_misc,
+			 misc_params_c, bth_dst_qp, 0xffffff);
+	}
+}
+
+static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
+						      struct mlx5_ib_flow_prio *ft_prio,
+						      const struct ib_flow_attr *flow_attr,
+						      struct mlx5_flow_destination *dst,
+						      u32 underlay_qpn)
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;

@@ -2385,6 +2406,9 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 		ib_flow += ((union ib_flow_spec *)ib_flow)->size;
 	}
 
+	if (!flow_is_multicast_only(flow_attr))
+		set_underlay_qp(dev, spec, underlay_qpn);
+
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
 	if (is_drop) {
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;

@@ -2424,6 +2448,14 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	return err ? ERR_PTR(err) : handler;
 }
 
+static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
+						     struct mlx5_ib_flow_prio *ft_prio,
+						     const struct ib_flow_attr *flow_attr,
+						     struct mlx5_flow_destination *dst)
+{
+	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0);
+}
+
 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,

@@ -2560,6 +2592,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
 	struct mlx5_ib_flow_prio *ft_prio;
 	int err;
+	int underlay_qpn;
 
 	if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
 		return ERR_PTR(-ENOMEM);

@@ -2600,8 +2633,10 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 			handler = create_dont_trap_rule(dev, ft_prio,
 							flow_attr, dst);
 		} else {
-			handler = create_flow_rule(dev, ft_prio, flow_attr,
-						   dst);
+			underlay_qpn = (mqp->flags & MLX5_IB_QP_UNDERLAY) ?
+					mqp->underlay_qpn : 0;
+			handler = _create_flow_rule(dev, ft_prio, flow_attr,
+						    dst, underlay_qpn);
 		}
 	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
 		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {

index 8d62c108dd80..640313da25c7 100644
@@ -295,8 +295,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         inner_tcp_dport[0x1];
 	u8         inner_tcp_flags[0x1];
 	u8         reserved_at_37[0x9];
+	u8         reserved_at_40[0x1a];
+	u8         bth_dst_qp[0x1];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_5b[0x25];
 };
 
 struct mlx5_ifc_flow_table_prop_layout_bits {

@@ -432,7 +434,9 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         reserved_at_100[0xc];
 	u8         inner_ipv6_flow_label[0x14];
 
-	u8         reserved_at_120[0xe0];
+	u8         reserved_at_120[0x28];
+	u8         bth_dst_qp[0x18];
+	u8         reserved_at_160[0xa0];
 };
 
 struct mlx5_ifc_cmd_pas_bits {

index 438663356982..aef1d8a0f4e4 100644
@@ -812,8 +812,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 
 	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
 			uhw->outlen)) {
-		resp.mlx5_ib_support_multi_pkt_send_wqes =
-			MLX5_CAP_ETH(mdev, multi_pkt_send_wqe);
+		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
+			resp.mlx5_ib_support_multi_pkt_send_wqes =
+				MLX5_IB_ALLOW_MPW;
 		resp.response_length +=
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}

index e58cc42a77a2..ecfa27920554 100644
@@ -1078,6 +1078,8 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 
 	sqc = MLX5_ADDR_OF(create_sq_in, in, ctx);
 	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+	if (MLX5_CAP_ETH(dev->mdev, multi_pkt_send_wqe))
+		MLX5_SET(sqc, sqc, allow_multi_pkt_send_wqe, 1);
 	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
 	MLX5_SET(sqc, sqc, user_index, MLX5_GET(qpc, qpc, user_index));
 	MLX5_SET(sqc, sqc, cqn, MLX5_GET(qpc, qpc, cqn_snd));

index 640313da25c7..4334ce9fc803 100644
@@ -2448,7 +2448,7 @@ struct mlx5_ifc_sqc_bits {
 	u8         cd_master[0x1];
 	u8         fre[0x1];
 	u8         flush_in_error_en[0x1];
-	u8         reserved_at_4[0x1];
+	u8         allow_multi_pkt_send_wqe[0x1];
 	u8	   min_wqe_inline_mode[0x3];
 	u8         state[0x4];
 	u8         reg_umr[0x1];

index 64d398e662cd..a61a512e5747 100644
@@ -168,6 +168,11 @@ struct mlx5_packet_pacing_caps {
 	__u32 reserved;
 };
 
+enum mlx5_ib_mpw_caps {
+	MPW_RESERVED		= 1 << 0,
+	MLX5_IB_ALLOW_MPW	= 1 << 1,
+};
+
 enum mlx5_ib_sw_parsing_offloads {
 	MLX5_IB_SW_PARSING = 1 << 0,
 	MLX5_IB_SW_PARSING_CSUM = 1 << 1,

index aef1d8a0f4e4..06cdc279364d 100644
@@ -815,6 +815,11 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
 			resp.mlx5_ib_support_multi_pkt_send_wqes =
 				MLX5_IB_ALLOW_MPW;
+
+		if (MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
+			resp.mlx5_ib_support_multi_pkt_send_wqes |=
+				MLX5_IB_SUPPORT_EMPW;
+
 		resp.response_length +=
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}

index 4334ce9fc803..6329348ff1d2 100644
@@ -604,7 +604,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         rss_ind_tbl_cap[0x4];
 	u8         reg_umr_sq[0x1];
 	u8         scatter_fcs[0x1];
-	u8         reserved_at_1a[0x1];
+	u8         enhanced_multi_pkt_send_wqe[0x1];
 	u8         tunnel_lso_const_out_ip_id[0x1];
 	u8         reserved_at_1c[0x2];
 	u8         tunnel_statless_gre[0x1];

index a61a512e5747..1791bf123ba9 100644
@@ -171,6 +171,7 @@ struct mlx5_packet_pacing_caps {
 enum mlx5_ib_mpw_caps {
 	MPW_RESERVED		= 1 << 0,
 	MLX5_IB_ALLOW_MPW	= 1 << 1,
+	MLX5_IB_SUPPORT_EMPW	= 1 << 2,
 };
 
 enum mlx5_ib_sw_parsing_offloads {