From b4749bf25652689d8e33827460266b78bb2ec42c Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Tue, 28 Aug 2018 14:18:51 +0300
Subject: RDMA/mlx5: Add a new flow action verb - modify header

Expose the ability to create a flow action which changes packet
headers. The data passed from userspace should be modify header actions as
defined by HW specification.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/uapi/rdma/mlx5_user_ioctl_cmds.h  | 10 ++++++++++
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |  5 +++++
 2 files changed, 15 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 9c51801b9e64..9c83e13c0e89 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -166,4 +166,14 @@ enum mlx5_ib_flow_methods {
 	MLX5_IB_METHOD_DESTROY_FLOW,
 };
 
+enum mlx5_ib_flow_action_methods {
+	MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum mlx5_ib_create_flow_action_create_modify_header_attrs {
+	MLX5_IB_ATTR_CREATE_MODIFY_HEADER_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_CREATE_MODIFY_HEADER_ACTIONS_PRM,
+	MLX5_IB_ATTR_CREATE_MODIFY_HEADER_FT_TYPE,
+};
+
 #endif
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 8a2fb33f3ed4..ceb6d0d8529a 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -39,5 +39,10 @@ enum mlx5_ib_uapi_flow_action_flags {
 	MLX5_IB_UAPI_FLOW_ACTION_FLAGS_REQUIRE_METADATA	= 1 << 0,
 };
 
+enum mlx5_ib_uapi_flow_table_type {
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX     = 0x0,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX	= 0x1,
+};
+
 #endif
 
-- 
cgit v1.2.3


From 08aeb97cb82483192bd8ad8e60d1b73ce1b75923 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Tue, 28 Aug 2018 14:18:53 +0300
Subject: RDMA/mlx5: Add new flow action verb - packet reformat

For now, only add L2_TUNNEL_TO_L2 option. This will allow to perform
generic decap operation if the encapsulating protocol is L2 based, and the
inner packet is also L2 based. For example this can be used to decap VXLAN
packets.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c         | 76 ++++++++++++++++++++++++++++++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h      |  1 +
 include/uapi/rdma/mlx5_user_ioctl_cmds.h  |  7 +++
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |  4 ++
 4 files changed, 87 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 0c89d5431c7e..888f79d6a125 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -202,6 +202,8 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
 		mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev,
 					   maction->flow_action_raw.action_id);
 		break;
+	case MLX5_IB_FLOW_ACTION_DECAP:
+		break;
 	default:
 		break;
 	}
@@ -286,6 +288,64 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER)(
 	return 0;
 }
 
+static bool mlx5_ib_flow_action_packet_reformat_valid(struct mlx5_ib_dev *ibdev,
+						      u8 packet_reformat_type,
+						      u8 ft_type)
+{
+	switch (packet_reformat_type) {
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2:
+		if (ft_type == MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX)
+			return MLX5_CAP_FLOWTABLE_NIC_RX(ibdev->mdev, decap);
+		break;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT)(
+	struct ib_uverbs_file *file,
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs,
+		MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_HANDLE);
+	struct mlx5_ib_dev *mdev = to_mdev(uobj->context->device);
+	enum mlx5_ib_uapi_flow_action_packet_reformat_type dv_prt;
+	enum mlx5_ib_uapi_flow_table_type ft_type;
+	struct mlx5_ib_flow_action *maction;
+	int ret;
+
+	ret = uverbs_get_const(&ft_type, attrs,
+			       MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_FT_TYPE);
+	if (ret)
+		return ret;
+
+	ret = uverbs_get_const(&dv_prt, attrs,
+			       MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_TYPE);
+	if (ret)
+		return ret;
+
+	if (!mlx5_ib_flow_action_packet_reformat_valid(mdev, dv_prt, ft_type))
+		return -EOPNOTSUPP;
+
+	maction = kzalloc(sizeof(*maction), GFP_KERNEL);
+	if (!maction)
+		return -ENOMEM;
+
+	if (dv_prt ==
+	    MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2) {
+		maction->flow_action_raw.sub_type =
+			MLX5_IB_FLOW_ACTION_DECAP;
+		maction->flow_action_raw.dev = mdev;
+	}
+
+	uverbs_flow_action_fill_action(&maction->ib_action, uobj,
+				       uobj->context->device,
+				       IB_FLOW_ACTION_UNSPECIFIED);
+	return 0;
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	MLX5_IB_METHOD_CREATE_FLOW,
 	UVERBS_ATTR_IDR(MLX5_IB_ATTR_CREATE_FLOW_HANDLE,
@@ -335,10 +395,24 @@ DECLARE_UVERBS_NAMED_METHOD(
 			     enum mlx5_ib_uapi_flow_table_type,
 			     UA_MANDATORY));
 
+DECLARE_UVERBS_NAMED_METHOD(
+	MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_HANDLE,
+			UVERBS_OBJECT_FLOW_ACTION,
+			UVERBS_ACCESS_NEW,
+			UA_MANDATORY),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_TYPE,
+			     enum mlx5_ib_uapi_flow_action_packet_reformat_type,
+			     UA_MANDATORY),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_FT_TYPE,
+			     enum mlx5_ib_uapi_flow_table_type,
+			     UA_MANDATORY));
+
 ADD_UVERBS_METHODS(
 	mlx5_ib_flow_actions,
 	UVERBS_OBJECT_FLOW_ACTION,
-	&UVERBS_METHOD(MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER));
+	&UVERBS_METHOD(MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER),
+	&UVERBS_METHOD(MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT));
 
 DECLARE_UVERBS_NAMED_METHOD(
 	MLX5_IB_METHOD_FLOW_MATCHER_CREATE,
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index c26ea868b4f1..8ac84cc00fd5 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -153,6 +153,7 @@ struct mlx5_ib_pd {
 
 enum {
 	MLX5_IB_FLOW_ACTION_MODIFY_HEADER,
+	MLX5_IB_FLOW_ACTION_DECAP,
 };
 
 #define MLX5_IB_FLOW_MCAST_PRIO		(MLX5_BY_PASS_NUM_PRIOS - 1)
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 9c83e13c0e89..40db7fca3d0b 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -168,6 +168,7 @@ enum mlx5_ib_flow_methods {
 
 enum mlx5_ib_flow_action_methods {
 	MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT,
 };
 
 enum mlx5_ib_create_flow_action_create_modify_header_attrs {
@@ -176,4 +177,10 @@ enum mlx5_ib_create_flow_action_create_modify_header_attrs {
 	MLX5_IB_ATTR_CREATE_MODIFY_HEADER_FT_TYPE,
 };
 
+enum mlx5_ib_create_flow_action_create_packet_reformat_attrs {
+	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_TYPE,
+	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_FT_TYPE,
+};
+
 #endif
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index ceb6d0d8529a..b5fda0fcd484 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -44,5 +44,9 @@ enum mlx5_ib_uapi_flow_table_type {
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX	= 0x1,
 };
 
+enum mlx5_ib_uapi_flow_action_packet_reformat_type {
+	MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2 = 0x0,
+};
+
 #endif
 
-- 
cgit v1.2.3


From a090d0d859ff88dd4c34614d01cee9b0603f4313 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Tue, 28 Aug 2018 14:18:54 +0300
Subject: RDMA/mlx5: Extend packet reformat verbs

We expose new actions:

L2_TO_L2_TUNNEL - A generic encap from L2 to L2, the data passed should
		  be the encapsulating headers.

L3_TUNNEL_TO_L2 - Will do decap where the inner packet starts from L3,
		  the data should be mac or mac + vlan (14 or 18 bytes).

L2_TO_L3_TUNNEL - Will do encap where is L2 of the original packet will
		  not be included, the data should be the encapsulating
		  header.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c         | 95 +++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/mlx5_ib.h      |  1 +
 include/uapi/rdma/mlx5_user_ioctl_cmds.h  |  1 +
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |  3 +
 4 files changed, 100 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 888f79d6a125..5750a650884e 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -202,6 +202,10 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
 		mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev,
 					   maction->flow_action_raw.action_id);
 		break;
+	case MLX5_IB_FLOW_ACTION_PACKET_REFORMAT:
+		mlx5_packet_reformat_dealloc(maction->flow_action_raw.dev->mdev,
+			maction->flow_action_raw.action_id);
+		break;
 	case MLX5_IB_FLOW_ACTION_DECAP:
 		break;
 	default:
@@ -293,6 +297,21 @@ static bool mlx5_ib_flow_action_packet_reformat_valid(struct mlx5_ib_dev *ibdev,
 						      u8 ft_type)
 {
 	switch (packet_reformat_type) {
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		if (ft_type == MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX)
+			return MLX5_CAP_FLOWTABLE(ibdev->mdev,
+						  encap_general_header);
+		break;
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		if (ft_type == MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX)
+			return MLX5_CAP_FLOWTABLE_NIC_TX(ibdev->mdev,
+				reformat_l2_to_l3_tunnel);
+		break;
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		if (ft_type == MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX)
+			return MLX5_CAP_FLOWTABLE_NIC_RX(ibdev->mdev,
+				reformat_l3_tunnel_to_l2);
+		break;
 	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2:
 		if (ft_type == MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX)
 			return MLX5_CAP_FLOWTABLE_NIC_RX(ibdev->mdev, decap);
@@ -304,6 +323,56 @@ static bool mlx5_ib_flow_action_packet_reformat_valid(struct mlx5_ib_dev *ibdev,
 	return false;
 }
 
+static int mlx5_ib_dv_to_prm_packet_reforamt_type(u8 dv_prt, u8 *prm_prt)
+{
+	switch (dv_prt) {
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		*prm_prt = MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL;
+		break;
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		*prm_prt = MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
+		break;
+	case MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		*prm_prt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mlx5_ib_flow_action_create_packet_reformat_ctx(
+	struct mlx5_ib_dev *dev,
+	struct mlx5_ib_flow_action *maction,
+	u8 ft_type, u8 dv_prt,
+	void *in, size_t len)
+{
+	enum mlx5_flow_namespace_type namespace;
+	u8 prm_prt;
+	int ret;
+
+	ret = mlx5_ib_ft_type_to_namespace(ft_type, &namespace);
+	if (ret)
+		return ret;
+
+	ret = mlx5_ib_dv_to_prm_packet_reforamt_type(dv_prt, &prm_prt);
+	if (ret)
+		return ret;
+
+	ret = mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
+					 in, namespace,
+					 &maction->flow_action_raw.action_id);
+	if (ret)
+		return ret;
+
+	maction->flow_action_raw.sub_type =
+		MLX5_IB_FLOW_ACTION_PACKET_REFORMAT;
+	maction->flow_action_raw.dev = dev;
+
+	return 0;
+}
+
 static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT)(
 	struct ib_uverbs_file *file,
 	struct uverbs_attr_bundle *attrs)
@@ -338,12 +407,34 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_PACKET_REFORMAT)(
 		maction->flow_action_raw.sub_type =
 			MLX5_IB_FLOW_ACTION_DECAP;
 		maction->flow_action_raw.dev = mdev;
+	} else {
+		void *in;
+		int len;
+
+		in = uverbs_attr_get_alloced_ptr(attrs,
+			MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF);
+		if (IS_ERR(in)) {
+			ret = PTR_ERR(in);
+			goto free_maction;
+		}
+
+		len = uverbs_attr_get_len(attrs,
+			MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF);
+
+		ret = mlx5_ib_flow_action_create_packet_reformat_ctx(mdev,
+			maction, ft_type, dv_prt, in, len);
+		if (ret)
+			goto free_maction;
 	}
 
 	uverbs_flow_action_fill_action(&maction->ib_action, uobj,
 				       uobj->context->device,
 				       IB_FLOW_ACTION_UNSPECIFIED);
 	return 0;
+
+free_maction:
+	kfree(maction);
+	return ret;
 }
 
 DECLARE_UVERBS_NAMED_METHOD(
@@ -401,6 +492,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			UVERBS_OBJECT_FLOW_ACTION,
 			UVERBS_ACCESS_NEW,
 			UA_MANDATORY),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF,
+			   UVERBS_ATTR_MIN_SIZE(1),
+			   UA_ALLOC_AND_COPY,
+			   UA_OPTIONAL),
 	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_TYPE,
 			     enum mlx5_ib_uapi_flow_action_packet_reformat_type,
 			     UA_MANDATORY),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 8ac84cc00fd5..eb6a0ca0247f 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -153,6 +153,7 @@ struct mlx5_ib_pd {
 
 enum {
 	MLX5_IB_FLOW_ACTION_MODIFY_HEADER,
+	MLX5_IB_FLOW_ACTION_PACKET_REFORMAT,
 	MLX5_IB_FLOW_ACTION_DECAP,
 };
 
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 40db7fca3d0b..75c7093fd95b 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -181,6 +181,7 @@ enum mlx5_ib_create_flow_action_create_packet_reformat_attrs {
 	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_TYPE,
 	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_FT_TYPE,
+	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF,
 };
 
 #endif
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index b5fda0fcd484..4ef62c0e8452 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -46,6 +46,9 @@ enum mlx5_ib_uapi_flow_table_type {
 
 enum mlx5_ib_uapi_flow_action_packet_reformat_type {
 	MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TUNNEL_TO_L2 = 0x0,
+	MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x1,
+	MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x2,
+	MLX5_IB_UAPI_FLOW_ACTION_PACKET_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x3,
 };
 
 #endif
-- 
cgit v1.2.3


From 70cd20aed00f719f3536154df02596106e431e45 Mon Sep 17 00:00:00 2001
From: Guy Levi <guyle@mellanox.com>
Date: Thu, 6 Sep 2018 17:27:01 +0300
Subject: IB/uverbs: Add IDRs array attribute type to ioctl() interface

Methods sometimes need to get a flexible set of IDRs and not a strict set
as can be achieved today by the conventional IDR attribute. Add a new
IDRS_ARRAY attribute to the generic uverbs ioctl layer.

IDRS_ARRAY points to array of idrs of the same object type and same access
rights, only write and read are supported.

Signed-off-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>``
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/uverbs_ioctl.c   | 114 +++++++++++++++++++++++++++++++
 drivers/infiniband/core/uverbs_uapi.c    |  12 ++++
 include/rdma/uverbs_ioctl.h              |  71 ++++++++++++++++++-
 include/uapi/rdma/rdma_user_ioctl_cmds.h |   7 +-
 4 files changed, 201 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index 4bafd4671de2..0e95a5888274 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -57,6 +57,7 @@ struct bundle_priv {
 	struct ib_uverbs_attr *uattrs;
 
 	DECLARE_BITMAP(uobj_finalize, UVERBS_API_ATTR_BKEY_LEN);
+	DECLARE_BITMAP(spec_finalize, UVERBS_API_ATTR_BKEY_LEN);
 
 	/*
 	 * Must be last. bundle ends in a flex array which overlaps
@@ -143,6 +144,86 @@ static bool uverbs_is_attr_cleared(const struct ib_uverbs_attr *uattr,
 			   0, uattr->len - len);
 }
 
+static int uverbs_process_idrs_array(struct bundle_priv *pbundle,
+				     const struct uverbs_api_attr *attr_uapi,
+				     struct uverbs_objs_arr_attr *attr,
+				     struct ib_uverbs_attr *uattr,
+				     u32 attr_bkey)
+{
+	const struct uverbs_attr_spec *spec = &attr_uapi->spec;
+	size_t array_len;
+	u32 *idr_vals;
+	int ret = 0;
+	size_t i;
+
+	if (uattr->attr_data.reserved)
+		return -EINVAL;
+
+	if (uattr->len % sizeof(u32))
+		return -EINVAL;
+
+	array_len = uattr->len / sizeof(u32);
+	if (array_len < spec->u2.objs_arr.min_len ||
+	    array_len > spec->u2.objs_arr.max_len)
+		return -EINVAL;
+
+	attr->uobjects =
+		uverbs_alloc(&pbundle->bundle,
+			     array_size(array_len, sizeof(*attr->uobjects)));
+	if (IS_ERR(attr->uobjects))
+		return PTR_ERR(attr->uobjects);
+
+	/*
+	 * Since idr is 4B and *uobjects is >= 4B, we can use attr->uobjects
+	 * to store idrs array and avoid additional memory allocation. The
+	 * idrs array is offset to the end of the uobjects array so we will be
+	 * able to read idr and replace with a pointer.
+	 */
+	idr_vals = (u32 *)(attr->uobjects + array_len) - array_len;
+
+	if (uattr->len > sizeof(uattr->data)) {
+		ret = copy_from_user(idr_vals, u64_to_user_ptr(uattr->data),
+				     uattr->len);
+		if (ret)
+			return -EFAULT;
+	} else {
+		memcpy(idr_vals, &uattr->data, uattr->len);
+	}
+
+	for (i = 0; i != array_len; i++) {
+		attr->uobjects[i] = uverbs_get_uobject_from_file(
+			spec->u2.objs_arr.obj_type, pbundle->bundle.ufile,
+			spec->u2.objs_arr.access, idr_vals[i]);
+		if (IS_ERR(attr->uobjects[i])) {
+			ret = PTR_ERR(attr->uobjects[i]);
+			break;
+		}
+	}
+
+	attr->len = i;
+	__set_bit(attr_bkey, pbundle->spec_finalize);
+	return ret;
+}
+
+static int uverbs_free_idrs_array(const struct uverbs_api_attr *attr_uapi,
+				  struct uverbs_objs_arr_attr *attr,
+				  bool commit)
+{
+	const struct uverbs_attr_spec *spec = &attr_uapi->spec;
+	int current_ret;
+	int ret = 0;
+	size_t i;
+
+	for (i = 0; i != attr->len; i++) {
+		current_ret = uverbs_finalize_object(
+			attr->uobjects[i], spec->u2.objs_arr.access, commit);
+		if (!ret)
+			ret = current_ret;
+	}
+
+	return ret;
+}
+
 static int uverbs_process_attr(struct bundle_priv *pbundle,
 			       const struct uverbs_api_attr *attr_uapi,
 			       struct ib_uverbs_attr *uattr, u32 attr_bkey)
@@ -246,6 +327,11 @@ static int uverbs_process_attr(struct bundle_priv *pbundle,
 		}
 
 		break;
+
+	case UVERBS_ATTR_TYPE_IDRS_ARRAY:
+		return uverbs_process_idrs_array(pbundle, attr_uapi,
+						 &e->objs_arr_attr, uattr,
+						 attr_bkey);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -384,6 +470,7 @@ static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
 	unsigned int i;
 	int ret = 0;
 
+	/* fast path for simple uobjects */
 	i = -1;
 	while ((i = find_next_bit(pbundle->uobj_finalize, key_bitmap_len,
 				  i + 1)) < key_bitmap_len) {
@@ -397,6 +484,32 @@ static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
 			ret = current_ret;
 	}
 
+	i = -1;
+	while ((i = find_next_bit(pbundle->spec_finalize, key_bitmap_len,
+				  i + 1)) < key_bitmap_len) {
+		struct uverbs_attr *attr = &pbundle->bundle.attrs[i];
+		const struct uverbs_api_attr *attr_uapi;
+		void __rcu **slot;
+		int current_ret;
+
+		slot = uapi_get_attr_for_method(
+			pbundle,
+			pbundle->method_key | uapi_bkey_to_key_attr(i));
+		if (WARN_ON(!slot))
+			continue;
+
+		attr_uapi = srcu_dereference(
+			*slot,
+			&pbundle->bundle.ufile->device->disassociate_srcu);
+
+		if (attr_uapi->spec.type == UVERBS_ATTR_TYPE_IDRS_ARRAY) {
+			current_ret = uverbs_free_idrs_array(
+				attr_uapi, &attr->objs_arr_attr, commit);
+			if (!ret)
+				ret = current_ret;
+		}
+	}
+
 	for (memblock = pbundle->allocated_mem; memblock;) {
 		struct bundle_alloc_head *tmp = memblock;
 
@@ -461,6 +574,7 @@ static int ib_uverbs_cmd_verbs(struct ib_uverbs_file *ufile,
 	memset(pbundle->bundle.attr_present, 0,
 	       sizeof(pbundle->bundle.attr_present));
 	memset(pbundle->uobj_finalize, 0, sizeof(pbundle->uobj_finalize));
+	memset(pbundle->spec_finalize, 0, sizeof(pbundle->spec_finalize));
 
 	ret = ib_uverbs_run_method(pbundle, hdr->num_attrs);
 	destroy_ret = bundle_destroy(pbundle, ret == 0);
diff --git a/drivers/infiniband/core/uverbs_uapi.c b/drivers/infiniband/core/uverbs_uapi.c
index 73ea6f0db88f..cdf5ced2c84f 100644
--- a/drivers/infiniband/core/uverbs_uapi.c
+++ b/drivers/infiniband/core/uverbs_uapi.c
@@ -73,6 +73,18 @@ static int uapi_merge_method(struct uverbs_api *uapi,
 		if (attr->attr.type == UVERBS_ATTR_TYPE_ENUM_IN)
 			method_elm->driver_method |= is_driver;
 
+		/*
+		 * Like other uobject based things we only support a single
+		 * uobject being NEW'd or DESTROY'd
+		 */
+		if (attr->attr.type == UVERBS_ATTR_TYPE_IDRS_ARRAY) {
+			u8 access = attr->attr.u2.objs_arr.access;
+
+			if (WARN_ON(access == UVERBS_ACCESS_NEW ||
+				    access == UVERBS_ACCESS_DESTROY))
+				return -EINVAL;
+		}
+
 		attr_slot =
 			uapi_add_elm(uapi, method_key | uapi_key_attr(attr->id),
 				     sizeof(*attr_slot));
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index fc2e52234a2a..84d3d15f1f38 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -52,6 +52,7 @@ enum uverbs_attr_type {
 	UVERBS_ATTR_TYPE_IDR,
 	UVERBS_ATTR_TYPE_FD,
 	UVERBS_ATTR_TYPE_ENUM_IN,
+	UVERBS_ATTR_TYPE_IDRS_ARRAY,
 };
 
 enum uverbs_obj_access {
@@ -101,7 +102,7 @@ struct uverbs_attr_spec {
 		} enum_def;
 	} u;
 
-	/* This weird split of the enum lets us remove some padding */
+	/* This weird split lets us remove some padding */
 	union {
 		struct {
 			/*
@@ -111,6 +112,17 @@ struct uverbs_attr_spec {
 			 */
 			const struct uverbs_attr_spec *ids;
 		} enum_def;
+
+		struct {
+			/*
+			 * higher bits mean the namespace and lower bits mean
+			 * the type id within the namespace.
+			 */
+			u16				obj_type;
+			u16				min_len;
+			u16				max_len;
+			u8				access;
+		} objs_arr;
 	} u2;
 };
 
@@ -251,6 +263,11 @@ static inline __attribute_const__ u32 uapi_bkey_attr(u32 attr_key)
 	return attr_key - 1;
 }
 
+static inline __attribute_const__ u32 uapi_bkey_to_key_attr(u32 attr_bkey)
+{
+	return attr_bkey + 1;
+}
+
 /*
  * =======================================
  *	Verbs definitions
@@ -323,6 +340,27 @@ struct uverbs_object_tree_def {
 #define UA_MANDATORY .mandatory = 1
 #define UA_OPTIONAL .mandatory = 0
 
+/*
+ * min_len must be bigger than 0 and _max_len must be smaller than 4095.  Only
+ * READ\WRITE accesses are supported.
+ */
+#define UVERBS_ATTR_IDRS_ARR(_attr_id, _idr_type, _access, _min_len, _max_len, \
+			     ...)                                              \
+	(&(const struct uverbs_attr_def){                                      \
+		.id = (_attr_id) +                                             \
+		      BUILD_BUG_ON_ZERO((_min_len) == 0 ||                     \
+					(_max_len) >                           \
+						PAGE_SIZE / sizeof(void *) ||  \
+					(_min_len) > (_max_len) ||             \
+					(_access) == UVERBS_ACCESS_NEW ||      \
+					(_access) == UVERBS_ACCESS_DESTROY),   \
+		.attr = { .type = UVERBS_ATTR_TYPE_IDRS_ARRAY,                 \
+			  .u2.objs_arr.obj_type = _idr_type,                   \
+			  .u2.objs_arr.access = _access,                       \
+			  .u2.objs_arr.min_len = _min_len,                     \
+			  .u2.objs_arr.max_len = _max_len,                     \
+			  __VA_ARGS__ } })
+
 #define UVERBS_ATTR_IDR(_attr_id, _idr_type, _access, ...)                     \
 	(&(const struct uverbs_attr_def){                                      \
 		.id = _attr_id,                                                \
@@ -440,10 +478,16 @@ struct uverbs_obj_attr {
 	const struct uverbs_api_attr	*attr_elm;
 };
 
+struct uverbs_objs_arr_attr {
+	struct ib_uobject **uobjects;
+	u16 len;
+};
+
 struct uverbs_attr {
 	union {
 		struct uverbs_ptr_attr	ptr_attr;
 		struct uverbs_obj_attr	obj_attr;
+		struct uverbs_objs_arr_attr objs_arr_attr;
 	};
 };
 
@@ -516,6 +560,31 @@ uverbs_attr_get_len(const struct uverbs_attr_bundle *attrs_bundle, u16 idx)
 	return attr->ptr_attr.len;
 }
 
+/**
+ * uverbs_attr_get_uobjs_arr() - Provides array's properties for attribute for
+ * UVERBS_ATTR_TYPE_IDRS_ARRAY.
+ * @arr: Returned pointer to array of pointers for uobjects or NULL if
+ *       the attribute isn't provided.
+ *
+ * Return: The array length or 0 if no attribute was provided.
+ */
+static inline int uverbs_attr_get_uobjs_arr(
+	const struct uverbs_attr_bundle *attrs_bundle, u16 attr_idx,
+	struct ib_uobject ***arr)
+{
+	const struct uverbs_attr *attr =
+			uverbs_attr_get(attrs_bundle, attr_idx);
+
+	if (IS_ERR(attr)) {
+		*arr = NULL;
+		return 0;
+	}
+
+	*arr = attr->objs_arr_attr.uobjects;
+
+	return attr->objs_arr_attr.len;
+}
+
 static inline bool uverbs_attr_ptr_is_inline(const struct uverbs_attr *attr)
 {
 	return attr->ptr_attr.len <= sizeof(attr->ptr_attr.data);
diff --git a/include/uapi/rdma/rdma_user_ioctl_cmds.h b/include/uapi/rdma/rdma_user_ioctl_cmds.h
index 24800c6c1f32..06c34d99be85 100644
--- a/include/uapi/rdma/rdma_user_ioctl_cmds.h
+++ b/include/uapi/rdma/rdma_user_ioctl_cmds.h
@@ -53,7 +53,7 @@ enum {
 
 struct ib_uverbs_attr {
 	__u16 attr_id;		/* command specific type attribute */
-	__u16 len;		/* only for pointers */
+	__u16 len;		/* only for pointers and IDRs array */
 	__u16 flags;		/* combination of UVERBS_ATTR_F_XXXX */
 	union {
 		struct {
@@ -63,7 +63,10 @@ struct ib_uverbs_attr {
 		__u16 reserved;
 	} attr_data;
 	union {
-		/* Used by PTR_IN/OUT, ENUM_IN and IDR */
+		/*
+		 * ptr to command, inline data, idr/fd or
+		 * ptr to __u32 array of IDRs
+		 */
 		__aligned_u64 data;
 		/* Used by FD_IN and FD_OUT */
 		__s64 data_s64;
-- 
cgit v1.2.3


From fa76d24ee0aa24fff3fa9ba71fc2179fb88fef6a Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 6 Sep 2018 17:27:06 +0300
Subject: RDMA/mlx5: Add flow actions support to raw create flow

Support attaching flow actions to a flow rule via raw create flow.
For now only NIC RX path is supported. This change requires to export
flow resources management functions so we can maintain proper bookkeeping
of flow actions.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/uverbs_cmd.c     | 11 +++++----
 drivers/infiniband/hw/mlx5/flow.c        | 40 ++++++++++++++++++++++++++++----
 include/rdma/uverbs_std_types.h          |  6 +++++
 include/uapi/rdma/mlx5_user_ioctl_cmds.h |  1 +
 4 files changed, 50 insertions(+), 8 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c054d65dec1b..9c87c98a0f19 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2747,7 +2747,7 @@ out_put:
 	return ret ? ret : in_len;
 }
 
-static struct ib_uflow_resources *flow_resources_alloc(size_t num_specs)
+struct ib_uflow_resources *flow_resources_alloc(size_t num_specs)
 {
 	struct ib_uflow_resources *resources;
 
@@ -2777,6 +2777,7 @@ err:
 
 	return NULL;
 }
+EXPORT_SYMBOL(flow_resources_alloc);
 
 void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res)
 {
@@ -2795,10 +2796,11 @@ void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res)
 	kfree(uflow_res->counters);
 	kfree(uflow_res);
 }
+EXPORT_SYMBOL(ib_uverbs_flow_resources_free);
 
-static void flow_resources_add(struct ib_uflow_resources *uflow_res,
-			       enum ib_flow_spec_type type,
-			       void *ibobj)
+void flow_resources_add(struct ib_uflow_resources *uflow_res,
+			enum ib_flow_spec_type type,
+			void *ibobj)
 {
 	WARN_ON(uflow_res->num >= uflow_res->max);
 
@@ -2819,6 +2821,7 @@ static void flow_resources_add(struct ib_uflow_resources *uflow_res,
 
 	uflow_res->num++;
 }
+EXPORT_SYMBOL(flow_resources_add);
 
 static int kern_spec_to_ib_spec_action(struct ib_uverbs_file *ufile,
 				       struct ib_uverbs_flow_spec *kern_spec,
diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 0e913491d139..ce9276a2aaa5 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -58,12 +58,15 @@ static const struct uverbs_attr_spec mlx5_ib_flow_type[] = {
 	},
 };
 
+#define MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS 2
 static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	struct ib_uverbs_file *file, struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
 	struct mlx5_ib_flow_handler *flow_handler;
 	struct mlx5_ib_flow_matcher *fs_matcher;
+	struct ib_uobject **arr_flow_actions;
+	struct ib_uflow_resources *uflow_res;
 	void *devx_obj;
 	int dest_id, dest_type;
 	void *cmd_in;
@@ -73,6 +76,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	struct ib_uobject *uobj =
 		uverbs_attr_get_uobject(attrs, MLX5_IB_ATTR_CREATE_FLOW_HANDLE);
 	struct mlx5_ib_dev *dev = to_mdev(uobj->context->device);
+	int len, ret, i;
 
 	if (!capable(CAP_NET_RAW))
 		return -EPERM;
@@ -124,15 +128,38 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 				    MLX5_IB_ATTR_CREATE_FLOW_MATCH_VALUE);
 	fs_matcher = uverbs_attr_get_obj(attrs,
 					 MLX5_IB_ATTR_CREATE_FLOW_MATCHER);
+
+	uflow_res = flow_resources_alloc(MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS);
+	if (!uflow_res)
+		return -ENOMEM;
+
+	len = uverbs_attr_get_uobjs_arr(attrs,
+		MLX5_IB_ATTR_CREATE_FLOW_ARR_FLOW_ACTIONS, &arr_flow_actions);
+	for (i = 0; i < len; i++) {
+		struct mlx5_ib_flow_action *maction =
+			to_mflow_act(arr_flow_actions[i]->object);
+
+		ret = parse_flow_flow_action(maction, false, &flow_act);
+		if (ret)
+			goto err_out;
+		flow_resources_add(uflow_res, IB_FLOW_SPEC_ACTION_HANDLE,
+				   arr_flow_actions[i]->object);
+	}
+
 	flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher, &flow_act,
 					       cmd_in, inlen,
 					       dest_id, dest_type);
-	if (IS_ERR(flow_handler))
-		return PTR_ERR(flow_handler);
+	if (IS_ERR(flow_handler)) {
+		ret = PTR_ERR(flow_handler);
+		goto err_out;
+	}
 
-	ib_set_flow(uobj, &flow_handler->ibflow, qp, &dev->ib_dev, NULL);
+	ib_set_flow(uobj, &flow_handler->ibflow, qp, &dev->ib_dev, uflow_res);
 
 	return 0;
+err_out:
+	ib_uverbs_flow_resources_free(uflow_res);
+	return ret;
 }
 
 static int flow_matcher_cleanup(struct ib_uobject *uobject,
@@ -459,7 +486,12 @@ DECLARE_UVERBS_NAMED_METHOD(
 			UVERBS_ACCESS_READ),
 	UVERBS_ATTR_IDR(MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX,
 			MLX5_IB_OBJECT_DEVX_OBJ,
-			UVERBS_ACCESS_READ));
+			UVERBS_ACCESS_READ),
+	UVERBS_ATTR_IDRS_ARR(MLX5_IB_ATTR_CREATE_FLOW_ARR_FLOW_ACTIONS,
+			     UVERBS_OBJECT_FLOW_ACTION,
+			     UVERBS_ACCESS_READ, 1,
+			     MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS,
+			     UA_OPTIONAL));
 
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 	MLX5_IB_METHOD_DESTROY_FLOW,
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index dfd6d35f1783..3db2802fbc68 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -166,6 +166,12 @@ struct ib_uflow_object {
 	struct ib_uflow_resources	*resources;
 };
 
+struct ib_uflow_resources *flow_resources_alloc(size_t num_specs);
+void flow_resources_add(struct ib_uflow_resources *uflow_res,
+			enum ib_flow_spec_type type,
+			void *ibobj);
+void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res);
+
 static inline void ib_set_flow(struct ib_uobject *uobj, struct ib_flow *ibflow,
 			       struct ib_qp *qp, struct ib_device *device,
 			       struct ib_uflow_resources *uflow_res)
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 75c7093fd95b..91c3d42ebd0f 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -155,6 +155,7 @@ enum mlx5_ib_create_flow_attrs {
 	MLX5_IB_ATTR_CREATE_FLOW_DEST_QP,
 	MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX,
 	MLX5_IB_ATTR_CREATE_FLOW_MATCHER,
+	MLX5_IB_ATTR_CREATE_FLOW_ARR_FLOW_ACTIONS,
 };
 
 enum mlx5_ib_destoy_flow_attrs {
-- 
cgit v1.2.3


From a7ee18bdee837e4703f01588993504b72074ffc6 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 6 Sep 2018 17:27:08 +0300
Subject: RDMA/mlx5: Allow creating a matcher for a NIC TX flow table

Currently a matcher can only be created and attached to a NIC RX flow
table. Extend it to allow it on NIC TX flow tables as well.

In order to achieve that, we:

1) Expose a new attribute: MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS.
   enum ib_flow_flags is used as valid flags. Only
   IB_FLOW_ATTR_FLAGS_EGRESS is supported.

2) Remove the requirement to have a DEVX or QP destination when creating a
   flow. A flow added to NIC TX flow table will forward the packet outside
   of the vport (Wire or E-Switch in the SR-iOV case).

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c        | 34 +++++++++++++++++++++++++++-----
 drivers/infiniband/hw/mlx5/main.c        |  5 ++++-
 include/uapi/rdma/mlx5_user_ioctl_cmds.h |  1 +
 3 files changed, 34 insertions(+), 6 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 16e677c549e6..4ee4af450720 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -86,7 +86,14 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	dest_qp = uverbs_attr_is_valid(attrs,
 				       MLX5_IB_ATTR_CREATE_FLOW_DEST_QP);
 
-	if ((dest_devx && dest_qp) || (!dest_devx && !dest_qp))
+	fs_matcher = uverbs_attr_get_obj(attrs,
+					 MLX5_IB_ATTR_CREATE_FLOW_MATCHER);
+	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS &&
+	    ((dest_devx && dest_qp) || (!dest_devx && !dest_qp)))
+		return -EINVAL;
+
+	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS &&
+	    (dest_devx || dest_qp))
 		return -EINVAL;
 
 	if (dest_devx) {
@@ -100,7 +107,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		 */
 		if (!mlx5_ib_devx_is_flow_dest(devx_obj, &dest_id, &dest_type))
 			return -EINVAL;
-	} else {
+	} else if (dest_qp) {
 		struct mlx5_ib_qp *mqp;
 
 		qp = uverbs_attr_get_obj(attrs,
@@ -117,6 +124,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		else
 			dest_id = mqp->raw_packet_qp.rq.tirn;
 		dest_type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+	} else {
+		dest_type = MLX5_FLOW_DESTINATION_TYPE_PORT;
 	}
 
 	if (dev->rep)
@@ -126,8 +135,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		attrs, MLX5_IB_ATTR_CREATE_FLOW_MATCH_VALUE);
 	inlen = uverbs_attr_get_len(attrs,
 				    MLX5_IB_ATTR_CREATE_FLOW_MATCH_VALUE);
-	fs_matcher = uverbs_attr_get_obj(attrs,
-					 MLX5_IB_ATTR_CREATE_FLOW_MATCHER);
 
 	uflow_res = flow_resources_alloc(MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS);
 	if (!uflow_res)
@@ -183,6 +190,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 		attrs, MLX5_IB_ATTR_FLOW_MATCHER_CREATE_HANDLE);
 	struct mlx5_ib_dev *dev = to_mdev(uobj->context->device);
 	struct mlx5_ib_flow_matcher *obj;
+	u32 flags;
 	int err;
 
 	obj = kzalloc(sizeof(struct mlx5_ib_flow_matcher), GFP_KERNEL);
@@ -215,6 +223,19 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 	if (err)
 		goto end;
 
+	err = uverbs_get_flags32(&flags, attrs,
+				 MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
+				 IB_FLOW_ATTR_FLAGS_EGRESS);
+	if (err)
+		goto end;
+
+	if (flags) {
+		err = mlx5_ib_ft_type_to_namespace(
+			MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX, &obj->ns_type);
+		if (err)
+			goto end;
+	}
+
 	uobj->object = obj;
 	obj->mdev = dev->mdev;
 	atomic_set(&obj->usecnt, 0);
@@ -559,7 +580,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			    UA_MANDATORY),
 	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA,
 			   UVERBS_ATTR_TYPE(u8),
-			   UA_MANDATORY));
+			   UA_MANDATORY),
+	UVERBS_ATTR_FLAGS_IN(MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
+			     enum ib_flow_flags,
+			     UA_OPTIONAL));
 
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 	MLX5_IB_METHOD_FLOW_MATCHER_DESTROY,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e311b6f8e1ee..2be6a4377558 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3892,10 +3892,13 @@ mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
 		dst->type = dest_type;
 		dst->tir_num = dest_id;
 		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	} else {
+	} else if (dest_type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) {
 		dst->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM;
 		dst->ft_num = dest_id;
 		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	} else {
+		dst->type = MLX5_FLOW_DESTINATION_TYPE_PORT;
+		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
 	}
 
 	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 91c3d42ebd0f..fb4a8b17cca8 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -125,6 +125,7 @@ enum mlx5_ib_flow_matcher_create_attrs {
 	MLX5_IB_ATTR_FLOW_MATCHER_MATCH_MASK,
 	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_TYPE,
 	MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA,
+	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
 };
 
 enum mlx5_ib_flow_matcher_destroy_attrs {
-- 
cgit v1.2.3


From 9a59739bd01f77db6fbe2955a4fce165f0f43568 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 14 Aug 2018 15:33:02 -0700
Subject: IB/rxe: Revise the ib_wr_opcode enum

This enum has become part of the uABI, as both RXE and the
ib_uverbs_post_send() command expect userspace to supply values from this
enum. So it should be properly placed in include/uapi/rdma.

In userspace this enum is called 'enum ibv_wr_opcode' as part of
libibverbs.h. That enum defines different values for IB_WR_LOCAL_INV,
IB_WR_SEND_WITH_INV, and IB_WR_LSO. These were introduced (incorrectly, it
turns out) into libiberbs in 2015.

The kernel has changed its mind on the numbering for several of the IB_WC
values over the years, but has remained stable on IB_WR_LOCAL_INV and
below.

Based on this we can conclude that there is no real user space user of the
values beyond IB_WR_ATOMIC_FETCH_AND_ADD, as they have never worked via
rdma-core. This is confirmed by inspection, only rxe uses the kernel enum
and implements the latter operations. rxe has clearly never worked with
these attributes from userspace. Other drivers that support these opcodes
implement the functionality without calling out to the kernel.

To make IB_WR_SEND_WITH_INV and related work for RXE in userspace we
choose to renumber the IB_WR enum in the kernel to match the uABI that
userspace has bee using since before Soft RoCE was merged. This is an
overall simpler configuration for the whole software stack, and obviously
can't break anything existing.

Reported-by: Seth Howell <seth.howell@intel.com>
Tested-by: Seth Howell <seth.howell@intel.com>
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Cc: <stable@vger.kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/rdma/ib_verbs.h           | 34 ++++++++++++++++++++--------------
 include/uapi/rdma/ib_user_verbs.h | 20 +++++++++++++++++++-
 2 files changed, 39 insertions(+), 15 deletions(-)

(limited to 'include/uapi')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6076c9b72ab9..e463d3007a35 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1281,21 +1281,27 @@ struct ib_qp_attr {
 };
 
 enum ib_wr_opcode {
-	IB_WR_RDMA_WRITE,
-	IB_WR_RDMA_WRITE_WITH_IMM,
-	IB_WR_SEND,
-	IB_WR_SEND_WITH_IMM,
-	IB_WR_RDMA_READ,
-	IB_WR_ATOMIC_CMP_AND_SWP,
-	IB_WR_ATOMIC_FETCH_AND_ADD,
-	IB_WR_LSO,
-	IB_WR_SEND_WITH_INV,
-	IB_WR_RDMA_READ_WITH_INV,
-	IB_WR_LOCAL_INV,
-	IB_WR_REG_MR,
-	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
-	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+	/* These are shared with userspace */
+	IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE,
+	IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM,
+	IB_WR_SEND = IB_UVERBS_WR_SEND,
+	IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM,
+	IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
+	IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
+	IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
+	IB_WR_LSO = IB_UVERBS_WR_TSO,
+	IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
+	IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
+	IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV,
+	IB_WR_MASKED_ATOMIC_CMP_AND_SWP =
+		IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
+	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
+		IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+
+	/* These are kernel only and can not be issued by userspace */
+	IB_WR_REG_MR = 0x20,
 	IB_WR_REG_SIG_MR,
+
 	/* reserve values for low level drivers' internal use.
 	 * These values will not be used at all in the ib core layer.
 	 */
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 25a16760de2a..1254b51a551a 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -763,10 +763,28 @@ struct ib_uverbs_sge {
 	__u32 lkey;
 };
 
+enum ib_uverbs_wr_opcode {
+	IB_UVERBS_WR_RDMA_WRITE = 0,
+	IB_UVERBS_WR_RDMA_WRITE_WITH_IMM = 1,
+	IB_UVERBS_WR_SEND = 2,
+	IB_UVERBS_WR_SEND_WITH_IMM = 3,
+	IB_UVERBS_WR_RDMA_READ = 4,
+	IB_UVERBS_WR_ATOMIC_CMP_AND_SWP = 5,
+	IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD = 6,
+	IB_UVERBS_WR_LOCAL_INV = 7,
+	IB_UVERBS_WR_BIND_MW = 8,
+	IB_UVERBS_WR_SEND_WITH_INV = 9,
+	IB_UVERBS_WR_TSO = 10,
+	IB_UVERBS_WR_RDMA_READ_WITH_INV = 11,
+	IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP = 12,
+	IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD = 13,
+	/* Review enum ib_wr_opcode before modifying this */
+};
+
 struct ib_uverbs_send_wr {
 	__aligned_u64 wr_id;
 	__u32 num_sge;
-	__u32 opcode;
+	__u32 opcode;		/* see enum ib_uverbs_wr_opcode */
 	__u32 send_flags;
 	union {
 		__be32 imm_data;
-- 
cgit v1.2.3


From 175edba85634a8be0ddab5ee96d0b23d9f17627e Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Mon, 17 Sep 2018 13:30:48 +0300
Subject: RDMA/mlx5: Allow creating RAW ethernet QP with loopback support

Expose two new flags:
MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC
MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC

Those flags can be used at creation time in order to allow a QP
to be able to receive loopback traffic (unicast and multicast).
We store the state in the QP to be used on the destroy path
to indicate with which flags the QP was created with.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  2 +-
 drivers/infiniband/hw/mlx5/qp.c      | 62 ++++++++++++++++++++++++++++--------
 include/uapi/rdma/mlx5-abi.h         |  2 ++
 3 files changed, 52 insertions(+), 14 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index fde5a867a7d3..ca435654c30b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -428,7 +428,7 @@ struct mlx5_ib_qp {
 	struct list_head	cq_send_list;
 	struct mlx5_rate_limit	rl;
 	u32                     underlay_qpn;
-	bool			tunnel_offload_en;
+	u32			flags_en;
 	/* storage for qp sub type when core qp type is IB_QPT_DRIVER */
 	enum ib_qp_type		qp_sub_type;
 };
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index daf1eb84cd31..f29ae401b232 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1258,8 +1258,9 @@ static bool tunnel_offload_supported(struct mlx5_core_dev *dev)
 
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_rq *rq, u32 tdn,
-				    bool tunnel_offload_en)
+				    u32 *qp_flags_en)
 {
+	u8 lb_flag = 0;
 	u32 *in;
 	void *tirc;
 	int inlen;
@@ -1274,12 +1275,21 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
 	MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn);
 	MLX5_SET(tirc, tirc, transport_domain, tdn);
-	if (tunnel_offload_en)
+	if (*qp_flags_en & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
 		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
 
-	if (dev->rep)
-		MLX5_SET(tirc, tirc, self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST);
+	if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC)
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+
+	if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+	if (dev->rep) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+		*qp_flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+	}
+
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
 
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
 
@@ -1332,8 +1342,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			goto err_destroy_sq;
 
 
-		err = create_raw_packet_qp_tir(dev, rq, tdn,
-					       qp->tunnel_offload_en);
+		err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en);
 		if (err)
 			goto err_destroy_rq;
 	}
@@ -1410,6 +1419,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	u32 tdn = mucontext->tdn;
 	struct mlx5_ib_create_qp_rss ucmd = {};
 	size_t required_cmd_sz;
+	u8 lb_flag = 0;
 
 	if (init_attr->qp_type != IB_QPT_RAW_PACKET)
 		return -EOPNOTSUPP;
@@ -1444,7 +1454,9 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return -EOPNOTSUPP;
 	}
 
-	if (ucmd.flags & ~MLX5_QP_FLAG_TUNNEL_OFFLOADS) {
+	if (ucmd.flags & ~(MLX5_QP_FLAG_TUNNEL_OFFLOADS |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)) {
 		mlx5_ib_dbg(dev, "invalid flags\n");
 		return -EOPNOTSUPP;
 	}
@@ -1461,6 +1473,16 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return -EOPNOTSUPP;
 	}
 
+	if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC || dev->rep) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+		qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+	}
+
+	if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+		qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
+	}
+
 	err = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
 	if (err) {
 		mlx5_ib_dbg(dev, "copy failed\n");
@@ -1484,6 +1506,8 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
 		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
 
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
+
 	if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER)
 		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner);
 	else
@@ -1580,10 +1604,6 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
 
 create_tir:
-	if (dev->rep)
-		MLX5_SET(tirc, tirc, self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST);
-
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
 
 	if (err)
@@ -1710,7 +1730,23 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 				mlx5_ib_dbg(dev, "Tunnel offload isn't supported\n");
 				return -EOPNOTSUPP;
 			}
-			qp->tunnel_offload_en = true;
+			qp->flags_en |= MLX5_QP_FLAG_TUNNEL_OFFLOADS;
+		}
+
+		if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC) {
+			if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+				mlx5_ib_dbg(dev, "Self-LB UC isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+			qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+		}
+
+		if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+			if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+				mlx5_ib_dbg(dev, "Self-LB UM isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+			qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
 		}
 
 		if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) {
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index addbb9c4529e..e584ba40208e 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -45,6 +45,8 @@ enum {
 	MLX5_QP_FLAG_BFREG_INDEX	= 1 << 3,
 	MLX5_QP_FLAG_TYPE_DCT		= 1 << 4,
 	MLX5_QP_FLAG_TYPE_DCI		= 1 << 5,
+	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC = 1 << 6,
+	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC = 1 << 7,
 };
 
 enum {
-- 
cgit v1.2.3


From 7f72052cb48efb5637ed99d2f45cb33a0bf60719 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Thu, 20 Sep 2018 21:45:18 +0300
Subject: IB/mlx5: Expose RAW QP device handles to user space

Expose RAW QP device handles to user space by extending the UHW part of
mlx5_ib_create_qp_resp.

This data is returned only when DEVX context is used where it may be
applicable.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 38 ++++++++++++++++++++++++++++++++++++--
 include/uapi/rdma/mlx5-abi.h    | 13 +++++++++++++
 2 files changed, 49 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 3455b50705cd..c49a0815a12b 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1325,7 +1325,9 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 
 static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 				u32 *in, size_t inlen,
-				struct ib_pd *pd)
+				struct ib_pd *pd,
+				struct ib_udata *udata,
+				struct mlx5_ib_create_qp_resp *resp)
 {
 	struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
 	struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
@@ -1335,6 +1337,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	struct mlx5_ib_ucontext *mucontext = to_mucontext(ucontext);
 	int err;
 	u32 tdn = mucontext->tdn;
+	u16 uid = to_mpd(pd)->uid;
 
 	if (qp->sq.wqe_cnt) {
 		err = create_raw_packet_qp_tis(dev, qp, sq, tdn, pd);
@@ -1345,6 +1348,13 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		if (err)
 			goto err_destroy_tis;
 
+		if (uid) {
+			resp->tisn = sq->tisn;
+			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_TISN;
+			resp->sqn = sq->base.mqp.qpn;
+			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_SQN;
+		}
+
 		sq->base.container_mibqp = qp;
 		sq->base.mqp.event = mlx5_ib_qp_event;
 	}
@@ -1363,13 +1373,25 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en, pd);
 		if (err)
 			goto err_destroy_rq;
+
+		if (uid) {
+			resp->rqn = rq->base.mqp.qpn;
+			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_RQN;
+			resp->tirn = rq->tirn;
+			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_TIRN;
+		}
 	}
 
 	qp->trans_qp.base.mqp.qpn = qp->sq.wqe_cnt ? sq->base.mqp.qpn :
 						     rq->base.mqp.qpn;
+	err = ib_copy_to_udata(udata, resp, min(udata->outlen, sizeof(*resp)));
+	if (err)
+		goto err_destroy_tir;
 
 	return 0;
 
+err_destroy_tir:
+	destroy_raw_packet_qp_tir(dev, rq, qp->flags_en, pd);
 err_destroy_rq:
 	destroy_raw_packet_qp_rq(dev, rq);
 err_destroy_sq:
@@ -1640,12 +1662,23 @@ create_tir:
 	if (err)
 		goto err;
 
+	if (mucontext->devx_uid) {
+		resp.comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_TIRN;
+		resp.tirn = qp->rss_qp.tirn;
+	}
+
+	err = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
+	if (err)
+		goto err_copy;
+
 	kvfree(in);
 	/* qpn is reserved for that QP */
 	qp->trans_qp.base.mqp.qpn = 0;
 	qp->flags |= MLX5_IB_QP_RSS;
 	return 0;
 
+err_copy:
+	mlx5_cmd_destroy_tir(dev->mdev, qp->rss_qp.tirn, mucontext->devx_uid);
 err:
 	kvfree(in);
 	return err;
@@ -1978,7 +2011,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr;
 		raw_packet_qp_copy_info(qp, &qp->raw_packet_qp);
-		err = create_raw_packet_qp(dev, qp, in, inlen, pd);
+		err = create_raw_packet_qp(dev, qp, in, inlen, pd, udata,
+					   &resp);
 	} else {
 		err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen);
 	}
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index e584ba40208e..6056625237cf 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -351,9 +351,22 @@ struct mlx5_ib_create_qp_rss {
 	__u32	flags;
 };
 
+enum mlx5_ib_create_qp_resp_mask {
+	MLX5_IB_CREATE_QP_RESP_MASK_TIRN = 1UL << 0,
+	MLX5_IB_CREATE_QP_RESP_MASK_TISN = 1UL << 1,
+	MLX5_IB_CREATE_QP_RESP_MASK_RQN  = 1UL << 2,
+	MLX5_IB_CREATE_QP_RESP_MASK_SQN  = 1UL << 3,
+};
+
 struct mlx5_ib_create_qp_resp {
 	__u32	bfreg_index;
 	__u32   reserved;
+	__u32	comp_mask;
+	__u32	tirn;
+	__u32	tisn;
+	__u32	rqn;
+	__u32	sqn;
+	__u32   reserved1;
 };
 
 struct mlx5_ib_alloc_mw {
-- 
cgit v1.2.3


From ba4a41198324be2e6fbb06c270fdc8500c0e38de Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Wed, 10 Oct 2018 09:55:10 +0300
Subject: RDMA/mlx5: Add support for flow tag to raw create flow

A user can provide a hint which will be attached to the packet and written
to the CQE on receive. This can be used as a way to offload operations
into the HW, for example parsing a packet which is a tunneled packet, and
if so, pass 0x1 as the hint. The software can use that hint to decapsulate
the packet and parse only the inner headers thus saving CPU cycles.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c        | 15 ++++++++++++++-
 include/uapi/rdma/mlx5_user_ioctl_cmds.h |  1 +
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 4ee4af450720..e57435cb6d96 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -153,6 +153,16 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 				   arr_flow_actions[i]->object);
 	}
 
+	ret = uverbs_copy_from(&flow_act.flow_tag, attrs,
+			       MLX5_IB_ATTR_CREATE_FLOW_TAG);
+	if (!ret) {
+		if (flow_act.flow_tag >= BIT(24)) {
+			ret = -EINVAL;
+			goto err_out;
+		}
+		flow_act.has_flow_tag = true;
+	}
+
 	flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher, &flow_act,
 					       cmd_in, inlen,
 					       dest_id, dest_type);
@@ -513,7 +523,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			     UVERBS_OBJECT_FLOW_ACTION,
 			     UVERBS_ACCESS_READ, 1,
 			     MLX5_IB_CREATE_FLOW_MAX_FLOW_ACTIONS,
-			     UA_OPTIONAL));
+			     UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_CREATE_FLOW_TAG,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_OPTIONAL));
 
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 	MLX5_IB_METHOD_DESTROY_FLOW,
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index fb4a8b17cca8..408e220034de 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -157,6 +157,7 @@ enum mlx5_ib_create_flow_attrs {
 	MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX,
 	MLX5_IB_ATTR_CREATE_FLOW_MATCHER,
 	MLX5_IB_ATTR_CREATE_FLOW_ARR_FLOW_ACTIONS,
+	MLX5_IB_ATTR_CREATE_FLOW_TAG,
 };
 
 enum mlx5_ib_destoy_flow_attrs {
-- 
cgit v1.2.3


From 05d940d3a3ec4e6d5d6a726aae4d73c5c64603c6 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 10 Oct 2018 09:19:12 +0300
Subject: RDMA/nldev: Allow IB device rename through RDMA netlink

Provide an option to rename IB device name through RDMA netlink and
limit it to users with ADMIN capability only.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/nldev.c  | 34 ++++++++++++++++++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h |  3 ++-
 2 files changed, 36 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index ba5403fbcd88..573399e3ccc1 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -646,6 +646,36 @@ err:
 	return err;
 }
 
+static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	u32 index;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy,
+			  extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
+		char name[IB_DEVICE_NAME_MAX] = {};
+
+		nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+			    IB_DEVICE_NAME_MAX);
+		err = ib_device_rename(device, name);
+	}
+
+	put_device(&device->dev);
+	return err;
+}
+
 static int _nldev_get_dumpit(struct ib_device *device,
 			     struct sk_buff *skb,
 			     struct netlink_callback *cb,
@@ -1078,6 +1108,10 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
+	[RDMA_NLDEV_CMD_SET] = {
+		.doit = nldev_set_doit,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NLDEV_CMD_PORT_GET] = {
 		.doit = nldev_port_get_doit,
 		.dump = nldev_port_get_dumpit,
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index edba6351ac13..f9c41bf59efc 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -227,8 +227,9 @@ enum rdma_nldev_command {
 	RDMA_NLDEV_CMD_UNSPEC,
 
 	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
 
-	/* 2 - 4 are free to use */
+	/* 3 - 4 are free to use */
 
 	RDMA_NLDEV_CMD_PORT_GET = 5, /* can dump */
 
-- 
cgit v1.2.3


From 6f4bc0ea682b59d7013cbc5ced2d4dd73067a33f Mon Sep 17 00:00:00 2001
From: Yonatan Cohen <yonatanc@mellanox.com>
Date: Tue, 9 Oct 2018 12:05:15 +0300
Subject: IB/mlx5: Allow scatter to CQE without global signaled WRs

Requester scatter to CQE is restricted to QPs configured to signal
all WRs.

This patch adds ability to enable scatter to cqe (force enable)
in the requester without sig_all, for users who do not want all WRs
signaled but rather just the ones whose data found in the CQE.

Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 14 +++++++++++---
 include/uapi/rdma/mlx5-abi.h    |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 5b1811be6677..368728e6f980 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1706,15 +1706,20 @@ static void configure_responder_scat_cqe(struct ib_qp_init_attr *init_attr,
 
 static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
 					 struct ib_qp_init_attr *init_attr,
+					 struct mlx5_ib_create_qp *ucmd,
 					 void *qpc)
 {
 	enum ib_qp_type qpt = init_attr->qp_type;
 	int scqe_sz;
+	bool allow_scat_cqe = 0;
 
 	if (qpt == IB_QPT_UC || qpt == IB_QPT_UD)
 		return;
 
-	if (init_attr->sq_sig_type != IB_SIGNAL_ALL_WR)
+	if (ucmd)
+		allow_scat_cqe = ucmd->flags & MLX5_QP_FLAG_ALLOW_SCATTER_CQE;
+
+	if (!allow_scat_cqe && init_attr->sq_sig_type != IB_SIGNAL_ALL_WR)
 		return;
 
 	scqe_sz = mlx5_ib_get_cqe_size(init_attr->send_cq);
@@ -1836,7 +1841,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 					      MLX5_QP_FLAG_TUNNEL_OFFLOADS |
 					      MLX5_QP_FLAG_BFREG_INDEX |
 					      MLX5_QP_FLAG_TYPE_DCT |
-					      MLX5_QP_FLAG_TYPE_DCI))
+					      MLX5_QP_FLAG_TYPE_DCI |
+					      MLX5_QP_FLAG_ALLOW_SCATTER_CQE))
 			return -EINVAL;
 
 		err = get_qp_user_index(to_mucontext(pd->uobject->context),
@@ -1971,7 +1977,9 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 	if (qp->scat_cqe && is_connected(init_attr->qp_type)) {
 		configure_responder_scat_cqe(init_attr, qpc);
-		configure_requester_scat_cqe(dev, init_attr, qpc);
+		configure_requester_scat_cqe(dev, init_attr,
+					     (pd && pd->uobject) ? &ucmd : NULL,
+					     qpc);
 	}
 
 	if (qp->rq.wqe_cnt) {
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 6056625237cf..8fa9f90e2bb1 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -47,6 +47,7 @@ enum {
 	MLX5_QP_FLAG_TYPE_DCI		= 1 << 5,
 	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC = 1 << 6,
 	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC = 1 << 7,
+	MLX5_QP_FLAG_ALLOW_SCATTER_CQE	= 1 << 8,
 };
 
 enum {
-- 
cgit v1.2.3