From 850d8fd765079d223d47de89f1f03ab95d1036cb Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Thu, 10 Nov 2016 11:30:56 +0200
Subject: IB/mlx4: Handle IPv4 header when demultiplexing MAD

When MAD arrives to the hypervisor, we need to identify which slave it
should be sent by destination GID. When L3 protocol is IPv4 the
GRH is replaced by an IPv4 header. This patch detects when IPv4 header
needs to be parsed instead of GRH.

Fixes: b6ffaeffaea4 ('mlx4: In RoCE allow guests to have multiple GIDS')
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/rdma/ib_verbs.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5ad43a487745..467a4b476e29 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2580,6 +2580,24 @@ void ib_dealloc_pd(struct ib_pd *pd);
  */
 struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
 
+/**
+ * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header
+ *   work completion.
+ * @hdr: the L3 header to parse
+ * @net_type: type of header to parse
+ * @sgid: place to store source gid
+ * @dgid: place to store destination gid
+ */
+int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
+			      enum rdma_network_type net_type,
+			      union ib_gid *sgid, union ib_gid *dgid);
+
+/**
+ * ib_get_rdma_header_version - Get the header version
+ * @hdr: the L3 header to parse
+ */
+int ib_get_rdma_header_version(const union rdma_network_hdr *hdr);
+
 /**
  * ib_init_ah_from_wc - Initializes address handle attributes from a
  *   work completion.
@@ -3357,4 +3375,5 @@ int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
 void ib_drain_rq(struct ib_qp *qp);
 void ib_drain_sq(struct ib_qp *qp);
 void ib_drain_qp(struct ib_qp *qp);
+
 #endif /* IB_VERBS_H */
-- 
cgit v1.2.3


From c226dc22ec4904340e3e14a536983cda3dbe7914 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 31 Oct 2016 12:15:20 +0200
Subject: net/mlx5: Report multi packet WQE capabilities

Multi packet WQE enables sending multiple fix sized packets
using a single WQE. The exposed field reports such HW support.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/linux/mlx5/mlx5_ifc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 2632cb2caf10..0779ad2e8f51 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -576,7 +576,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         self_lb_en_modifiable[0x1];
 	u8         reserved_at_9[0x2];
 	u8         max_lso_cap[0x5];
-	u8         reserved_at_10[0x2];
+	u8         multi_pkt_send_wqe[0x2];
 	u8	   wqe_inline_mode[0x2];
 	u8         rss_ind_tbl_cap[0x4];
 	u8         reg_umr_sq[0x1];
-- 
cgit v1.2.3


From 191ded4a4d991acf17207e0b4370fef070bce3e9 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 31 Oct 2016 12:15:21 +0200
Subject: IB/mlx5: Report mlx5 multi packet WQE caps during query

The capabilities whether hardware support multi packet WQE or not is
exposed to user space through query_device by uhw.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/main.c | 11 +++++++++++
 include/uapi/rdma/mlx5-abi.h      |  2 ++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 46facd30e672..a16207c33333 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -672,6 +672,17 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
 	}
 
+	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);
+		resp.response_length +=
+			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
+	}
+
+	if (field_avail(typeof(resp), reserved, uhw->outlen))
+		resp.response_length += sizeof(resp.reserved);
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index f5d0f4e83b59..93d6b9fe8e78 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -129,6 +129,8 @@ struct mlx5_ib_query_device_resp {
 	__u32	response_length;
 	struct	mlx5_ib_tso_caps tso_caps;
 	struct	mlx5_ib_rss_caps rss_caps;
+	__u32	mlx5_ib_support_multi_pkt_send_wqes;
+	__u32	reserved;
 };
 
 struct mlx5_ib_create_cq {
-- 
cgit v1.2.3


From 7e43a2a5bae39fedaa7cce21d637e0c8d96d8e54 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 31 Oct 2016 12:16:44 +0200
Subject: IB/mlx5: Report mlx5 CQE compression caps during query

The capabilities include:
- Max number of compressed and aggregated CQEs in a single session,
  while zero means unsupported.
- For Responder, there are two formats of mini CQE: mini CQE with Rx
  hash and mini CQE with checksum. They're mutual exclusive.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/main.c | 10 ++++++++++
 include/uapi/rdma/mlx5-abi.h      | 12 ++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a16207c33333..2687a93c4af2 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -683,6 +683,16 @@ 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), cqe_comp_caps, uhw->outlen)) {
+		resp.cqe_comp_caps.max_num =
+			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
+			MLX5_CAP_GEN(dev->mdev, cqe_compression_max_num) : 0;
+		resp.cqe_comp_caps.supported_format =
+			MLX5_IB_CQE_RES_FORMAT_HASH |
+			MLX5_IB_CQE_RES_FORMAT_CSUM;
+		resp.response_length += sizeof(resp.cqe_comp_caps);
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 93d6b9fe8e78..6649d13a2dbb 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -124,11 +124,23 @@ struct mlx5_ib_rss_caps {
 	__u8 reserved[7];
 };
 
+enum mlx5_ib_cqe_comp_res_format {
+	MLX5_IB_CQE_RES_FORMAT_HASH	= 1 << 0,
+	MLX5_IB_CQE_RES_FORMAT_CSUM	= 1 << 1,
+	MLX5_IB_CQE_RES_RESERVED	= 1 << 2,
+};
+
+struct mlx5_ib_cqe_comp_caps {
+	__u32 max_num;
+	__u32 supported_format; /* enum mlx5_ib_cqe_comp_res_format */
+};
+
 struct mlx5_ib_query_device_resp {
 	__u32	comp_mask;
 	__u32	response_length;
 	struct	mlx5_ib_tso_caps tso_caps;
 	struct	mlx5_ib_rss_caps rss_caps;
+	struct	mlx5_ib_cqe_comp_caps cqe_comp_caps;
 	__u32	mlx5_ib_support_multi_pkt_send_wqes;
 	__u32	reserved;
 };
-- 
cgit v1.2.3


From 1cbe6fc86ccfe05a910be4883da7c7bd28c190fe Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 31 Oct 2016 12:16:45 +0200
Subject: IB/mlx5: Add support for CQE compressing

CQE compressing reduces PCI overhead by coalescing and compressing
multiple CQEs into a single merged CQE. Successful compressing
improves message rate especially for small packet traffic.

CQE compressing is supported for all 64B CQE formats (with certain
limitations) generated by RQ/Responder or by SQ/Requestor.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/cq.c | 30 +++++++++++++++++++++++++++++-
 include/uapi/rdma/mlx5-abi.h    |  4 +++-
 2 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 9e0598b5615f..d72a4367c891 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -731,7 +731,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int entries, u32 **cqb,
 			  int *cqe_size, int *index, int *inlen)
 {
-	struct mlx5_ib_create_cq ucmd;
+	struct mlx5_ib_create_cq ucmd = {};
 	size_t ucmdlen;
 	int page_shift;
 	__be64 *pas;
@@ -792,8 +792,36 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 
 	*index = to_mucontext(context)->uuari.uars[0].index;
 
+	if (ucmd.cqe_comp_en == 1) {
+		if (unlikely((*cqe_size != 64) ||
+			     !MLX5_CAP_GEN(dev->mdev, cqe_compression))) {
+			err = -EOPNOTSUPP;
+			mlx5_ib_warn(dev, "CQE compression is not supported for size %d!\n",
+				     *cqe_size);
+			goto err_cqb;
+		}
+
+		if (unlikely(!ucmd.cqe_comp_res_format ||
+			     !(ucmd.cqe_comp_res_format <
+			       MLX5_IB_CQE_RES_RESERVED) ||
+			     (ucmd.cqe_comp_res_format &
+			      (ucmd.cqe_comp_res_format - 1)))) {
+			err = -EOPNOTSUPP;
+			mlx5_ib_warn(dev, "CQE compression res format %d is not supported!\n",
+				     ucmd.cqe_comp_res_format);
+			goto err_cqb;
+		}
+
+		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
+		MLX5_SET(cqc, cqc, mini_cqe_res_format,
+			 ilog2(ucmd.cqe_comp_res_format));
+	}
+
 	return 0;
 
+err_cqb:
+	kfree(cqb);
+
 err_db:
 	mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 6649d13a2dbb..b0a41c8dc1fb 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -149,7 +149,9 @@ struct mlx5_ib_create_cq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	cqe_size;
-	__u32	reserved; /* explicit padding (optional on i386) */
+	__u8    cqe_comp_en;
+	__u8    cqe_comp_res_format;
+	__u16	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_cq_resp {
-- 
cgit v1.2.3


From 0dbf3332b7b683db33a385a3ce9baab157e3ff9a Mon Sep 17 00:00:00 2001
From: Moses Reuben <mosesr@mellanox.com>
Date: Mon, 14 Nov 2016 19:04:47 +0200
Subject: IB/core: Add flow spec tunneling support

In order to support tunneling, that can be used by the QP,
both struct ib_flow_spec_tunnel and struct ib_flow_tunnel_filter can be
used to more IP or UDP based tunneling protocols (e.g NVGRE, GRE, etc).

IB_FLOW_SPEC_VXLAN_TUNNEL type flow specification is added to use this
functionality and match specific Vxlan packets.

In similar to IPv6, we check overflow of the vni value by
comparing with the maximum size.

Signed-off-by: Moses Reuben <mosesr@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 15 +++++++++++++++
 include/rdma/ib_verbs.h              | 19 ++++++++++++++++++-
 2 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2690c9263ee4..deb06fa3548b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3175,6 +3175,21 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 		memcpy(&ib_spec->tcp_udp.val, kern_spec_val, actual_filter_sz);
 		memcpy(&ib_spec->tcp_udp.mask, kern_spec_mask, actual_filter_sz);
 		break;
+	case IB_FLOW_SPEC_VXLAN_TUNNEL:
+		ib_filter_sz = offsetof(struct ib_flow_tunnel_filter, real_sz);
+		actual_filter_sz = spec_filter_size(kern_spec_mask,
+						    kern_filter_sz,
+						    ib_filter_sz);
+		if (actual_filter_sz <= 0)
+			return -EINVAL;
+		ib_spec->tunnel.size = sizeof(struct ib_flow_spec_tunnel);
+		memcpy(&ib_spec->tunnel.val, kern_spec_val, actual_filter_sz);
+		memcpy(&ib_spec->tunnel.mask, kern_spec_mask, actual_filter_sz);
+
+		if ((ntohl(ib_spec->tunnel.mask.tunnel_id)) >= BIT(24) ||
+		    (ntohl(ib_spec->tunnel.val.tunnel_id)) >= BIT(24))
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 467a4b476e29..b8213818de89 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1599,7 +1599,8 @@ enum ib_flow_spec_type {
 	IB_FLOW_SPEC_IPV6	= 0x31,
 	/* L4 headers*/
 	IB_FLOW_SPEC_TCP	= 0x40,
-	IB_FLOW_SPEC_UDP	= 0x41
+	IB_FLOW_SPEC_UDP	= 0x41,
+	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 4
@@ -1707,6 +1708,21 @@ struct ib_flow_spec_tcp_udp {
 	struct ib_flow_tcp_udp_filter mask;
 };
 
+struct ib_flow_tunnel_filter {
+	__be32	tunnel_id;
+	u8	real_sz[0];
+};
+
+/* ib_flow_spec_tunnel describes the Vxlan tunnel
+ * the tunnel_id from val has the vni value
+ */
+struct ib_flow_spec_tunnel {
+	enum ib_flow_spec_type	      type;
+	u16			      size;
+	struct ib_flow_tunnel_filter  val;
+	struct ib_flow_tunnel_filter  mask;
+};
+
 union ib_flow_spec {
 	struct {
 		enum ib_flow_spec_type	type;
@@ -1717,6 +1733,7 @@ union ib_flow_spec {
 	struct ib_flow_spec_ipv4        ipv4;
 	struct ib_flow_spec_tcp_udp	tcp_udp;
 	struct ib_flow_spec_ipv6        ipv6;
+	struct ib_flow_spec_tunnel      tunnel;
 };
 
 struct ib_flow_attr {
-- 
cgit v1.2.3


From 76bd23b34204cad78f48aec4cef38869a66aa594 Mon Sep 17 00:00:00 2001
From: Moses Reuben <mosesr@mellanox.com>
Date: Mon, 14 Nov 2016 19:04:48 +0200
Subject: IB/core: Align structure ib_flow_spec_type

Aligned the structure ib_flow_spec_type indentation,
after adding a new definition.

Signed-off-by: Moses Reuben <mosesr@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/rdma/ib_verbs.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b8213818de89..4bc748fddcac 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1592,14 +1592,14 @@ enum ib_flow_attr_type {
 /* Supported steering header types */
 enum ib_flow_spec_type {
 	/* L2 headers*/
-	IB_FLOW_SPEC_ETH	= 0x20,
-	IB_FLOW_SPEC_IB		= 0x22,
+	IB_FLOW_SPEC_ETH		= 0x20,
+	IB_FLOW_SPEC_IB			= 0x22,
 	/* L3 header*/
-	IB_FLOW_SPEC_IPV4	= 0x30,
-	IB_FLOW_SPEC_IPV6	= 0x31,
+	IB_FLOW_SPEC_IPV4		= 0x30,
+	IB_FLOW_SPEC_IPV6		= 0x31,
 	/* L4 headers*/
-	IB_FLOW_SPEC_TCP	= 0x40,
-	IB_FLOW_SPEC_UDP	= 0x41,
+	IB_FLOW_SPEC_TCP		= 0x40,
+	IB_FLOW_SPEC_UDP		= 0x41,
 	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
-- 
cgit v1.2.3


From a0cb4c759af12943806564294fa53ab08cb7cf93 Mon Sep 17 00:00:00 2001
From: Moses Reuben <mosesr@mellanox.com>
Date: Mon, 14 Nov 2016 19:04:49 +0200
Subject: IB/uverbs: Add support for Vxlan protocol

Add ib_uverbs_flow_spec_tunnel to define the rule to match Vxlan,
the type, size, reserved fields are identical to rest of the protocols,
and are used to identify the spec.
The tunnel id is the vni value of the Vxlan protocol, and it is used
as part of the steering rule, it is limited by the mask.
The steering rule configured on the hardware does a match
according to vni and other protocols.
In the same way as rest of the protocols that we match,
the uniq field's of each protocol are represented on
the val and the mask.

Signed-off-by: Moses Reuben <mosesr@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/uapi/rdma/ib_user_verbs.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 25225ebbc7d5..90ba5e88ec00 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -908,6 +908,23 @@ struct ib_uverbs_flow_spec_ipv6 {
 	struct ib_uverbs_flow_ipv6_filter mask;
 };
 
+struct ib_uverbs_flow_tunnel_filter {
+	__be32 tunnel_id;
+};
+
+struct ib_uverbs_flow_spec_tunnel {
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
+	struct ib_uverbs_flow_tunnel_filter val;
+	struct ib_uverbs_flow_tunnel_filter mask;
+};
+
 struct ib_uverbs_flow_attr {
 	__u32 type;
 	__u16 size;
-- 
cgit v1.2.3


From fbf46860b19ddb485f00bef1ad1a43aabc9f71ad Mon Sep 17 00:00:00 2001
From: Moses Reuben <mosesr@mellanox.com>
Date: Mon, 14 Nov 2016 19:04:51 +0200
Subject: IB/core: Introduce inner flow steering

For a tunneled packet which contains external and internal headers,
we refer to the external headers as "outer fields" and the internal
headers as "inner fields".

Example of a tunneled packet:

{ L2 | L3 | L4 | tunnel header | L2 | L3 | l4 | data }
  |     |    |         |         |    |    |
{       outer fields           }{ inner fields }

This patch introduces a new flag for flow steering rules
- IB_FLOW_SPEC_INNER - which specifies that the rule applies
to the inner fields, rather than to the outer fields of the packet.

Signed-off-by: Moses Reuben <mosesr@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c |  4 +++-
 include/rdma/ib_verbs.h              | 17 +++++++++--------
 2 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index deb06fa3548b..d84dcde7a8bb 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3124,8 +3124,10 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 	kern_spec_val = (void *)kern_spec +
 		sizeof(struct ib_uverbs_flow_spec_hdr);
 	kern_spec_mask = kern_spec_val + kern_filter_sz;
+	if (ib_spec->type == (IB_FLOW_SPEC_INNER | IB_FLOW_SPEC_VXLAN_TUNNEL))
+		return -EINVAL;
 
-	switch (ib_spec->type) {
+	switch (ib_spec->type & ~IB_FLOW_SPEC_INNER) {
 	case IB_FLOW_SPEC_ETH:
 		ib_filter_sz = offsetof(struct ib_flow_eth_filter, real_sz);
 		actual_filter_sz = spec_filter_size(kern_spec_mask,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 4bc748fddcac..6d0dd6525e14 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1601,9 +1601,10 @@ enum ib_flow_spec_type {
 	IB_FLOW_SPEC_TCP		= 0x40,
 	IB_FLOW_SPEC_UDP		= 0x41,
 	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
+	IB_FLOW_SPEC_INNER		= 0x100,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
-#define IB_FLOW_SPEC_SUPPORT_LAYERS 4
+#define IB_FLOW_SPEC_SUPPORT_LAYERS 8
 
 /* Flow steering rule priority is set according to it's domain.
  * Lower domain value means higher priority.
@@ -1631,7 +1632,7 @@ struct ib_flow_eth_filter {
 };
 
 struct ib_flow_spec_eth {
-	enum ib_flow_spec_type	  type;
+	u32			  type;
 	u16			  size;
 	struct ib_flow_eth_filter val;
 	struct ib_flow_eth_filter mask;
@@ -1645,7 +1646,7 @@ struct ib_flow_ib_filter {
 };
 
 struct ib_flow_spec_ib {
-	enum ib_flow_spec_type	 type;
+	u32			 type;
 	u16			 size;
 	struct ib_flow_ib_filter val;
 	struct ib_flow_ib_filter mask;
@@ -1670,7 +1671,7 @@ struct ib_flow_ipv4_filter {
 };
 
 struct ib_flow_spec_ipv4 {
-	enum ib_flow_spec_type	   type;
+	u32			   type;
 	u16			   size;
 	struct ib_flow_ipv4_filter val;
 	struct ib_flow_ipv4_filter mask;
@@ -1688,7 +1689,7 @@ struct ib_flow_ipv6_filter {
 };
 
 struct ib_flow_spec_ipv6 {
-	enum ib_flow_spec_type	   type;
+	u32			   type;
 	u16			   size;
 	struct ib_flow_ipv6_filter val;
 	struct ib_flow_ipv6_filter mask;
@@ -1702,7 +1703,7 @@ struct ib_flow_tcp_udp_filter {
 };
 
 struct ib_flow_spec_tcp_udp {
-	enum ib_flow_spec_type	      type;
+	u32			      type;
 	u16			      size;
 	struct ib_flow_tcp_udp_filter val;
 	struct ib_flow_tcp_udp_filter mask;
@@ -1717,7 +1718,7 @@ struct ib_flow_tunnel_filter {
  * the tunnel_id from val has the vni value
  */
 struct ib_flow_spec_tunnel {
-	enum ib_flow_spec_type	      type;
+	u32			      type;
 	u16			      size;
 	struct ib_flow_tunnel_filter  val;
 	struct ib_flow_tunnel_filter  mask;
@@ -1725,7 +1726,7 @@ struct ib_flow_spec_tunnel {
 
 union ib_flow_spec {
 	struct {
-		enum ib_flow_spec_type	type;
+		u32			type;
 		u16			size;
 	};
 	struct ib_flow_spec_eth		eth;
-- 
cgit v1.2.3


From c90ea9d8e51196d9c528e57d9ab09ee7d41f0ba0 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Wed, 23 Nov 2016 08:23:22 +0200
Subject: IB/core: Change ib_resolve_eth_dmac to use it in create AH

The function ib_resolve_eth_dmac() requires struct qp_attr * and
qp_attr_mask as parameters while the function might be useful to resolve
dmac for address handles. This patch changes the signature of the
function so it can be used in the flow of creating an address handle.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/core_priv.h  |  3 --
 drivers/infiniband/core/uverbs_cmd.c |  8 ++--
 drivers/infiniband/core/verbs.c      | 84 ++++++++++++++++++------------------
 include/rdma/ib_verbs.h              |  2 +
 4 files changed, 49 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 19d499dcab76..1acc95b3aaa3 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -72,9 +72,6 @@ void ib_device_unregister_sysfs(struct ib_device *device);
 void ib_cache_setup(void);
 void ib_cache_cleanup(void);
 
-int ib_resolve_eth_dmac(struct ib_qp *qp,
-			struct ib_qp_attr *qp_attr, int *qp_attr_mask);
-
 typedef void (*roce_netdev_callback)(struct ib_device *device, u8 port,
 	      struct net_device *idev, void *cookie);
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index d84dcde7a8bb..77bb15f66414 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2402,9 +2402,11 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;
 
 	if (qp->real_qp == qp) {
-		ret = ib_resolve_eth_dmac(qp, attr, &cmd.attr_mask);
-		if (ret)
-			goto release_qp;
+		if (cmd.attr_mask & IB_QP_AV) {
+			ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr);
+			if (ret)
+				goto release_qp;
+		}
 		ret = qp->device->modify_qp(qp, attr,
 			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
 	} else {
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 98e10c5f2a96..cacee169cd55 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1198,66 +1198,66 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 }
 EXPORT_SYMBOL(ib_modify_qp_is_ok);
 
-int ib_resolve_eth_dmac(struct ib_qp *qp,
-			struct ib_qp_attr *qp_attr, int *qp_attr_mask)
+int ib_resolve_eth_dmac(struct ib_device *device,
+			struct ib_ah_attr *ah_attr)
 {
 	int           ret = 0;
 
-	if (*qp_attr_mask & IB_QP_AV) {
-		if (qp_attr->ah_attr.port_num < rdma_start_port(qp->device) ||
-		    qp_attr->ah_attr.port_num > rdma_end_port(qp->device))
-			return -EINVAL;
-
-		if (!rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))
-			return 0;
-
-		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
-			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw,
-					qp_attr->ah_attr.dmac);
-		} else {
-			union ib_gid		sgid;
-			struct ib_gid_attr	sgid_attr;
-			int			ifindex;
-			int			hop_limit;
-
-			ret = ib_query_gid(qp->device,
-					   qp_attr->ah_attr.port_num,
-					   qp_attr->ah_attr.grh.sgid_index,
-					   &sgid, &sgid_attr);
-
-			if (ret || !sgid_attr.ndev) {
-				if (!ret)
-					ret = -ENXIO;
-				goto out;
-			}
+	if (ah_attr->port_num < rdma_start_port(device) ||
+	    ah_attr->port_num > rdma_end_port(device))
+		return -EINVAL;
 
-			ifindex = sgid_attr.ndev->ifindex;
+	if (!rdma_cap_eth_ah(device, ah_attr->port_num))
+		return 0;
 
-			ret = rdma_addr_find_l2_eth_by_grh(&sgid,
-							   &qp_attr->ah_attr.grh.dgid,
-							   qp_attr->ah_attr.dmac,
-							   NULL, &ifindex, &hop_limit);
+	if (rdma_link_local_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+		rdma_get_ll_mac((struct in6_addr *)ah_attr->grh.dgid.raw,
+				ah_attr->dmac);
+	} else {
+		union ib_gid		sgid;
+		struct ib_gid_attr	sgid_attr;
+		int			ifindex;
+		int			hop_limit;
+
+		ret = ib_query_gid(device,
+				   ah_attr->port_num,
+				   ah_attr->grh.sgid_index,
+				   &sgid, &sgid_attr);
+
+		if (ret || !sgid_attr.ndev) {
+			if (!ret)
+				ret = -ENXIO;
+			goto out;
+		}
 
-			dev_put(sgid_attr.ndev);
+		ifindex = sgid_attr.ndev->ifindex;
 
-			qp_attr->ah_attr.grh.hop_limit = hop_limit;
-		}
+		ret = rdma_addr_find_l2_eth_by_grh(&sgid,
+						   &ah_attr->grh.dgid,
+						   ah_attr->dmac,
+						   NULL, &ifindex, &hop_limit);
+
+		dev_put(sgid_attr.ndev);
+
+		ah_attr->grh.hop_limit = hop_limit;
 	}
 out:
 	return ret;
 }
 EXPORT_SYMBOL(ib_resolve_eth_dmac);
 
-
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
 {
-	int ret;
 
-	ret = ib_resolve_eth_dmac(qp, qp_attr, &qp_attr_mask);
-	if (ret)
-		return ret;
+	if (qp_attr_mask & IB_QP_AV) {
+		int ret;
+
+		ret = ib_resolve_eth_dmac(qp->device, &qp_attr->ah_attr);
+		if (ret)
+			return ret;
+	}
 
 	return qp->device->modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
 }
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6d0dd6525e14..0c6f973e407c 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3394,4 +3394,6 @@ void ib_drain_rq(struct ib_qp *qp);
 void ib_drain_sq(struct ib_qp *qp);
 void ib_drain_qp(struct ib_qp *qp);
 
+int ib_resolve_eth_dmac(struct ib_device *device,
+			struct ib_ah_attr *ah_attr);
 #endif /* IB_VERBS_H */
-- 
cgit v1.2.3


From 6ad279c5a2e55bf2bd100b4222090d4717de88d5 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Wed, 23 Nov 2016 08:23:23 +0200
Subject: IB/mlx5: Report that device has udata response in create_ah

To make mlx5 user driver aware of whether kernel driver returns dmac
in user data response add a new flag that will be returned back to
user-space through alloc_ucontext.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/main.c | 3 ++-
 include/uapi/rdma/mlx5-abi.h      | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f7a299431e6c..f2ef2a170d9f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1117,7 +1117,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.cqe_version);
 
 	if (field_avail(typeof(resp), cmds_supp_uhw, udata->outlen)) {
-		resp.cmds_supp_uhw |= MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE;
+		resp.cmds_supp_uhw |= MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE |
+				      MLX5_USER_CMDS_SUPP_UHW_CREATE_AH;
 		resp.response_length += sizeof(resp.cmds_supp_uhw);
 	}
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index b0a41c8dc1fb..ac28729a1245 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -82,6 +82,7 @@ enum mlx5_ib_alloc_ucontext_resp_mask {
 
 enum mlx5_user_cmds_supp_uhw {
 	MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE = 1 << 0,
+	MLX5_USER_CMDS_SUPP_UHW_CREATE_AH    = 1 << 1,
 };
 
 struct mlx5_ib_alloc_ucontext_resp {
-- 
cgit v1.2.3


From 477864c8fcd953e5a988073ca5be18bb7fd93410 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Wed, 23 Nov 2016 08:23:24 +0200
Subject: IB/core: Let create_ah return extended response to user

Add struct ib_udata to the signature of create_ah callback that is
implemented by IB device drivers. This allows HW drivers to return extra
data to the userspace library.
This patch prepares the ground for mlx5 driver to resolve destination
mac address for a given GID and return it to userspace.
This patch was previously submitted by Knut Omang as a part of the
patch set to support Oracle's Infiniband HCA (SIF).

Signed-off-by: Knut Omang <knut.omang@oracle.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c         | 11 ++++++++++-
 drivers/infiniband/core/verbs.c              |  2 +-
 drivers/infiniband/hw/cxgb3/iwch_provider.c  |  3 ++-
 drivers/infiniband/hw/cxgb4/provider.c       |  4 +++-
 drivers/infiniband/hw/hns/hns_roce_ah.c      |  3 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h  |  3 ++-
 drivers/infiniband/hw/i40iw/i40iw_verbs.c    |  4 +++-
 drivers/infiniband/hw/mlx4/ah.c              |  4 +++-
 drivers/infiniband/hw/mlx4/mlx4_ib.h         |  3 ++-
 drivers/infiniband/hw/mlx5/ah.c              |  4 +++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h         |  3 ++-
 drivers/infiniband/hw/mthca/mthca_provider.c |  4 +++-
 drivers/infiniband/hw/nes/nes_verbs.c        |  3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_ah.c     |  3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_ah.h     |  4 +++-
 drivers/infiniband/hw/qedr/verbs.c           |  3 ++-
 drivers/infiniband/hw/qedr/verbs.h           |  3 ++-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c |  4 +++-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.h |  4 +++-
 drivers/infiniband/sw/rxe/rxe_verbs.c        |  4 +++-
 include/rdma/ib_verbs.h                      |  3 ++-
 21 files changed, 58 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 77bb15f66414..cdb935ddab69 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2877,6 +2877,7 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	struct ib_ah			*ah;
 	struct ib_ah_attr		attr;
 	int ret;
+	struct ib_udata                   udata;
 
 	if (out_len < sizeof resp)
 		return -ENOSPC;
@@ -2884,6 +2885,10 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long)cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd), out_len - sizeof(resp));
+
 	uobj = kmalloc(sizeof *uobj, GFP_KERNEL);
 	if (!uobj)
 		return -ENOMEM;
@@ -2910,12 +2915,16 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	memset(&attr.dmac, 0, sizeof(attr.dmac));
 	memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
 
-	ah = ib_create_ah(pd, &attr);
+	ah = pd->device->create_ah(pd, &attr, &udata);
+
 	if (IS_ERR(ah)) {
 		ret = PTR_ERR(ah);
 		goto err_put;
 	}
 
+	ah->device  = pd->device;
+	ah->pd      = pd;
+	atomic_inc(&pd->usecnt);
 	ah->uobject  = uobj;
 	uobj->object = ah;
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index cacee169cd55..c976f29f7ad2 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -315,7 +315,7 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 {
 	struct ib_ah *ah;
 
-	ah = pd->device->create_ah(pd, ah_attr);
+	ah = pd->device->create_ah(pd, ah_attr, NULL);
 
 	if (!IS_ERR(ah)) {
 		ah->device  = pd->device;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index cba57bb53dba..9d5fe1853da4 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -62,7 +62,8 @@
 #include "common.h"
 
 static struct ib_ah *iwch_ah_create(struct ib_pd *pd,
-				    struct ib_ah_attr *ah_attr)
+				    struct ib_ah_attr *ah_attr,
+				    struct ib_udata *udata)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 645e606a17c5..49b51b7e0fd7 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -59,7 +59,9 @@ module_param(fastreg_support, int, 0644);
 MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=1)");
 
 static struct ib_ah *c4iw_ah_create(struct ib_pd *pd,
-				    struct ib_ah_attr *ah_attr)
+				    struct ib_ah_attr *ah_attr,
+				    struct ib_udata *udata)
+
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index 24f79ee39fdf..0ac294db3b29 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -39,7 +39,8 @@
 #define HNS_ROCE_VLAN_SL_BIT_MASK	7
 #define HNS_ROCE_VLAN_SL_SHIFT		13
 
-struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *ah_attr)
+struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibpd->device);
 	struct device *dev = &hr_dev->pdev->dev;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 341731553a60..470615f7b517 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -667,7 +667,8 @@ int hns_roce_bitmap_alloc_range(struct hns_roce_bitmap *bitmap, int cnt,
 void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
 				unsigned long obj, int cnt);
 
-struct ib_ah *hns_roce_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+struct ib_ah *hns_roce_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata);
 int hns_roce_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
 int hns_roce_destroy_ah(struct ib_ah *ah);
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 6329c971c22f..f03fc1527d70 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -2562,7 +2562,9 @@ static int i40iw_query_pkey(struct ib_device *ibdev,
  * @ah_attr: address handle attributes
  */
 static struct ib_ah *i40iw_create_ah(struct ib_pd *ibpd,
-				     struct ib_ah_attr *attr)
+				     struct ib_ah_attr *attr,
+				     struct ib_udata *udata)
+
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 6be7dc320ff7..20c6d17ac8b8 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -126,7 +126,9 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 	return &ah->ibah;
 }
 
-struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata)
+
 {
 	struct mlx4_ib_ah *ah;
 	struct ib_ah *ret;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 35141f451e5c..7f3d976d81ed 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -742,7 +742,8 @@ int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
 void mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
 
-struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata);
 int mlx4_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
 int mlx4_ib_destroy_ah(struct ib_ah *ah);
 
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 745efa4cfc71..ecac9ea2c85f 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -64,7 +64,9 @@ static struct ib_ah *create_ib_ah(struct mlx5_ib_dev *dev,
 	return &ah->ibah;
 }
 
-struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata)
+
 {
 	struct mlx5_ib_ah *ah;
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 95937e7d2584..ff05afa864ee 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -739,7 +739,8 @@ void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index);
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
 		 const void *in_mad, void *response_mad);
-struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata);
 int mlx5_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
 int mlx5_ib_destroy_ah(struct ib_ah *ah);
 struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 358930a41e36..d31708742ba5 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -410,7 +410,9 @@ static int mthca_dealloc_pd(struct ib_pd *pd)
 }
 
 static struct ib_ah *mthca_ah_create(struct ib_pd *pd,
-				     struct ib_ah_attr *ah_attr)
+				     struct ib_ah_attr *ah_attr,
+				     struct ib_udata *udata)
+
 {
 	int err;
 	struct mthca_ah *ah;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index bd69125731c1..0bb857c7e439 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -771,7 +771,8 @@ static int nes_dealloc_pd(struct ib_pd *ibpd)
 /**
  * nes_create_ah
  */
-static struct ib_ah *nes_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+static struct ib_ah *nes_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				   struct ib_udata *udata)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 797362a297b2..14d33b0f3950 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -154,7 +154,8 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 	return status;
 }
 
-struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr,
+			       struct ib_udata *udata)
 {
 	u32 *ahid_addr;
 	int status;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index 3856dd4c7e3d..0704a24b17c8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -50,7 +50,9 @@ enum {
 	OCRDMA_AH_L3_TYPE_MASK		= 0x03,
 	OCRDMA_AH_L3_TYPE_SHIFT		= 0x1D /* 29 bits */
 };
-struct ib_ah *ocrdma_create_ah(struct ib_pd *, struct ib_ah_attr *);
+
+struct ib_ah *ocrdma_create_ah(struct ib_pd *, struct ib_ah_attr *,
+			       struct ib_udata *);
 int ocrdma_destroy_ah(struct ib_ah *);
 int ocrdma_query_ah(struct ib_ah *, struct ib_ah_attr *);
 int ocrdma_modify_ah(struct ib_ah *, struct ib_ah_attr *);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index a61514296767..ccff6c6e3f33 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2094,7 +2094,8 @@ int qedr_destroy_qp(struct ib_qp *ibqp)
 	return rc;
 }
 
-struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr,
+			     struct ib_udata *udata)
 {
 	struct qedr_ah *ah;
 
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index a9b5e67bb81e..070677ca4d19 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -70,7 +70,8 @@ int qedr_query_qp(struct ib_qp *, struct ib_qp_attr *qp_attr,
 		  int qp_attr_mask, struct ib_qp_init_attr *);
 int qedr_destroy_qp(struct ib_qp *ibqp);
 
-struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr);
+struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr,
+			     struct ib_udata *udata);
 int qedr_destroy_ah(struct ib_ah *ibah);
 
 int qedr_dereg_mr(struct ib_mr *);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index a5bfbba6bbac..fd2a50eb4c91 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -738,7 +738,9 @@ int usnic_ib_mmap(struct ib_ucontext *context,
 
 /* In ib callbacks section -  Start of stub funcs */
 struct ib_ah *usnic_ib_create_ah(struct ib_pd *pd,
-					struct ib_ah_attr *ah_attr)
+				 struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata)
+
 {
 	usnic_dbg("\n");
 	return ERR_PTR(-EPERM);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index 0d9d2e6a14d5..0ed8e072329e 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -75,7 +75,9 @@ int usnic_ib_dealloc_ucontext(struct ib_ucontext *ibcontext);
 int usnic_ib_mmap(struct ib_ucontext *context,
 			struct vm_area_struct *vma);
 struct ib_ah *usnic_ib_create_ah(struct ib_pd *pd,
-					struct ib_ah_attr *ah_attr);
+				 struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata);
+
 int usnic_ib_destroy_ah(struct ib_ah *ah);
 int usnic_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			struct ib_send_wr **bad_wr);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 19841c863daf..187d85ccfe58 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -316,7 +316,9 @@ static int rxe_init_av(struct rxe_dev *rxe, struct ib_ah_attr *attr,
 	return err;
 }
 
-static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr,
+				   struct ib_udata *udata)
+
 {
 	int err;
 	struct rxe_dev *rxe = to_rdev(ibpd->device);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0c6f973e407c..73417a22ee4d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1951,7 +1951,8 @@ struct ib_device {
 					       struct ib_udata *udata);
 	int                        (*dealloc_pd)(struct ib_pd *pd);
 	struct ib_ah *             (*create_ah)(struct ib_pd *pd,
-						struct ib_ah_attr *ah_attr);
+						struct ib_ah_attr *ah_attr,
+						struct ib_udata *udata);
 	int                        (*modify_ah)(struct ib_ah *ah,
 						struct ib_ah_attr *ah_attr);
 	int                        (*query_ah)(struct ib_ah *ah,
-- 
cgit v1.2.3


From 5097e71f3edafad3e7d8d4f9c4a137d9aad0fae2 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Wed, 23 Nov 2016 08:23:25 +0200
Subject: IB/mlx5: Use kernel driver to help userspace create ah

Resolving a MAC address for a given IP address in userspace is inefficient.
This patch lets mlx5 user driver using the kernel driver to resolve the mac
and get the answer in the private section of the response.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/ah.c | 21 +++++++++++++++++++++
 include/uapi/rdma/mlx5-abi.h    |  6 ++++++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index ecac9ea2c85f..d090e96f6f01 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -77,6 +77,27 @@ struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 	if (ll == IB_LINK_LAYER_ETHERNET && !(ah_attr->ah_flags & IB_AH_GRH))
 		return ERR_PTR(-EINVAL);
 
+	if (ll == IB_LINK_LAYER_ETHERNET && udata) {
+		int err;
+		struct mlx5_ib_create_ah_resp resp = {};
+		u32 min_resp_len = offsetof(typeof(resp), dmac) +
+				   sizeof(resp.dmac);
+
+		if (udata->outlen < min_resp_len)
+			return ERR_PTR(-EINVAL);
+
+		resp.response_length = min_resp_len;
+
+		err = ib_resolve_eth_dmac(pd->device, ah_attr);
+		if (err)
+			return ERR_PTR(err);
+
+		memcpy(resp.dmac, ah_attr->dmac, ETH_ALEN);
+		err = ib_copy_to_udata(udata, &resp, resp.response_length);
+		if (err)
+			return ERR_PTR(err);
+	}
+
 	ah = kzalloc(sizeof(*ah), GFP_ATOMIC);
 	if (!ah)
 		return ERR_PTR(-ENOMEM);
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index ac28729a1245..3ebf3db24c34 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -249,6 +249,12 @@ struct mlx5_ib_create_wq {
 	__u32   reserved;
 };
 
+struct mlx5_ib_create_ah_resp {
+	__u32	response_length;
+	__u8	dmac[ETH_ALEN];
+	__u8	reserved[6];
+};
+
 struct mlx5_ib_create_wq_resp {
 	__u32	response_length;
 	__u32	reserved;
-- 
cgit v1.2.3


From d949167d68b304c0a00331cf33ef49a29b65d85f Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Thu, 1 Dec 2016 13:43:13 +0200
Subject: IB/mlx5: Report mlx5 packet pacing capabilities when querying device

Enable mlx5 based hardware to report packet pacing capabilities
from kernel to user space. Packet pacing allows to limit the rate to any
number between the maximum and minimum, based on user settings.

The capabilities are exposed to user space through query_device by uhw.
The following capabilities are reported:

1. The maximum and minimum rate limit in kbps supported by packet pacing.
2. Bitmap showing which QP types are supported by packet pacing operation.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/main.c | 13 +++++++++++++
 include/uapi/rdma/mlx5-abi.h      | 13 +++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8b013f8b832a..6c194000903d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -693,6 +693,19 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.cqe_comp_caps);
 	}
 
+	if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen)) {
+		if (MLX5_CAP_QOS(mdev, packet_pacing) &&
+		    MLX5_CAP_GEN(mdev, qos)) {
+			resp.packet_pacing_caps.qp_rate_limit_max =
+				MLX5_CAP_QOS(mdev, packet_pacing_max_rate);
+			resp.packet_pacing_caps.qp_rate_limit_min =
+				MLX5_CAP_QOS(mdev, packet_pacing_min_rate);
+			resp.packet_pacing_caps.supported_qpts |=
+				1 << IB_QPT_RAW_PACKET;
+		}
+		resp.response_length += sizeof(resp.packet_pacing_caps);
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 3ebf3db24c34..fae6cdaeb56d 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -136,12 +136,25 @@ struct mlx5_ib_cqe_comp_caps {
 	__u32 supported_format; /* enum mlx5_ib_cqe_comp_res_format */
 };
 
+struct mlx5_packet_pacing_caps {
+	__u32 qp_rate_limit_min;
+	__u32 qp_rate_limit_max; /* In kpbs */
+
+	/* 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;
+	__u32 reserved;
+};
+
 struct mlx5_ib_query_device_resp {
 	__u32	comp_mask;
 	__u32	response_length;
 	struct	mlx5_ib_tso_caps tso_caps;
 	struct	mlx5_ib_rss_caps rss_caps;
 	struct	mlx5_ib_cqe_comp_caps cqe_comp_caps;
+	struct	mlx5_packet_pacing_caps packet_pacing_caps;
 	__u32	mlx5_ib_support_multi_pkt_send_wqes;
 	__u32	reserved;
 };
-- 
cgit v1.2.3


From 528e5a1bd3f0e9b760cb3a1062fce7513712a15d Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Thu, 1 Dec 2016 13:43:14 +0200
Subject: IB/core: Support rate limit for packet pacing

Add new member rate_limit to ib_qp_attr which holds the packet pacing rate
in kbps, 0 means unlimited.

IB_QP_RATE_LIMIT is added to ib_attr_mask and could be used by RAW
QPs when changing QP state from RTR to RTS, RTS to RTS.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 2 ++
 include/rdma/ib_verbs.h         | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index c976f29f7ad2..71580cc28c9e 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1016,6 +1016,7 @@ static const struct {
 						 IB_QP_QKEY),
 				 [IB_QPT_GSI] = (IB_QP_CUR_STATE		|
 						 IB_QP_QKEY),
+				 [IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
 			 }
 		}
 	},
@@ -1049,6 +1050,7 @@ static const struct {
 						IB_QP_QKEY),
 				[IB_QPT_GSI] = (IB_QP_CUR_STATE			|
 						IB_QP_QKEY),
+				[IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
 			}
 		},
 		[IB_QPS_SQD]   = {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 73417a22ee4d..8029d2a51f14 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1102,6 +1102,7 @@ enum ib_qp_attr_mask {
 	IB_QP_RESERVED2			= (1<<22),
 	IB_QP_RESERVED3			= (1<<23),
 	IB_QP_RESERVED4			= (1<<24),
+	IB_QP_RATE_LIMIT		= (1<<25),
 };
 
 enum ib_qp_state {
@@ -1151,6 +1152,7 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
+	u32			rate_limit;
 };
 
 enum ib_wr_opcode {
-- 
cgit v1.2.3


From 189aba99e70030cfb56bd8f199bc5b077a1bc6ff Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Thu, 1 Dec 2016 13:43:15 +0200
Subject: IB/uverbs: Extend modify_qp and support packet pacing

An new uverbs command ib_uverbs_ex_modify_qp is added to support more QP
attributes. User driver should choose to call the legacy/extended API
based on input mask.

IB_USER_LAST_QP_ATTR_MASK is added to indicated the maximum bit position
which supports legacy ib_uverbs_modify_qp.
IB_USER_LEGACY_LAST_QP_ATTR_MASK indicates the maximum bit position
which supports ib_uverbs_ex_modify_qp, the value of this mask should be
updated if new mask is added later.

Along with this change, rate_limit is supported by the extended command,
user driver could use it to control packet packing.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs.h      |   1 +
 drivers/infiniband/core/uverbs_cmd.c  | 192 ++++++++++++++++++++++------------
 drivers/infiniband/core/uverbs_main.c |   1 +
 include/uapi/rdma/ib_user_verbs.h     |  21 ++++
 4 files changed, 146 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index df26a741cda6..455034ac994e 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -289,5 +289,6 @@ IB_UVERBS_DECLARE_EX_CMD(modify_wq);
 IB_UVERBS_DECLARE_EX_CMD(destroy_wq);
 IB_UVERBS_DECLARE_EX_CMD(create_rwq_ind_table);
 IB_UVERBS_DECLARE_EX_CMD(destroy_rwq_ind_table);
+IB_UVERBS_DECLARE_EX_CMD(modify_qp);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index cdb935ddab69..09b649159e6c 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2328,96 +2328,88 @@ static int modify_qp_mask(enum ib_qp_type qp_type, int mask)
 	}
 }
 
-ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
-			    struct ib_device *ib_dev,
-			    const char __user *buf, int in_len,
-			    int out_len)
+static int modify_qp(struct ib_uverbs_file *file,
+		     struct ib_uverbs_ex_modify_qp *cmd, struct ib_udata *udata)
 {
-	struct ib_uverbs_modify_qp cmd;
-	struct ib_udata            udata;
-	struct ib_qp              *qp;
-	struct ib_qp_attr         *attr;
-	int                        ret;
-
-	if (copy_from_user(&cmd, buf, sizeof cmd))
-		return -EFAULT;
-
-	INIT_UDATA(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd,
-		   out_len);
+	struct ib_qp_attr *attr;
+	struct ib_qp *qp;
+	int ret;
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
 	if (!attr)
 		return -ENOMEM;
 
-	qp = idr_read_qp(cmd.qp_handle, file->ucontext);
+	qp = idr_read_qp(cmd->base.qp_handle, file->ucontext);
 	if (!qp) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	attr->qp_state 		  = cmd.qp_state;
-	attr->cur_qp_state 	  = cmd.cur_qp_state;
-	attr->path_mtu 		  = cmd.path_mtu;
-	attr->path_mig_state 	  = cmd.path_mig_state;
-	attr->qkey 		  = cmd.qkey;
-	attr->rq_psn 		  = cmd.rq_psn;
-	attr->sq_psn 		  = cmd.sq_psn;
-	attr->dest_qp_num 	  = cmd.dest_qp_num;
-	attr->qp_access_flags 	  = cmd.qp_access_flags;
-	attr->pkey_index 	  = cmd.pkey_index;
-	attr->alt_pkey_index 	  = cmd.alt_pkey_index;
-	attr->en_sqd_async_notify = cmd.en_sqd_async_notify;
-	attr->max_rd_atomic 	  = cmd.max_rd_atomic;
-	attr->max_dest_rd_atomic  = cmd.max_dest_rd_atomic;
-	attr->min_rnr_timer 	  = cmd.min_rnr_timer;
-	attr->port_num 		  = cmd.port_num;
-	attr->timeout 		  = cmd.timeout;
-	attr->retry_cnt 	  = cmd.retry_cnt;
-	attr->rnr_retry 	  = cmd.rnr_retry;
-	attr->alt_port_num 	  = cmd.alt_port_num;
-	attr->alt_timeout 	  = cmd.alt_timeout;
-
-	memcpy(attr->ah_attr.grh.dgid.raw, cmd.dest.dgid, 16);
-	attr->ah_attr.grh.flow_label        = cmd.dest.flow_label;
-	attr->ah_attr.grh.sgid_index        = cmd.dest.sgid_index;
-	attr->ah_attr.grh.hop_limit         = cmd.dest.hop_limit;
-	attr->ah_attr.grh.traffic_class     = cmd.dest.traffic_class;
-	attr->ah_attr.dlid 	    	    = cmd.dest.dlid;
-	attr->ah_attr.sl   	    	    = cmd.dest.sl;
-	attr->ah_attr.src_path_bits 	    = cmd.dest.src_path_bits;
-	attr->ah_attr.static_rate   	    = cmd.dest.static_rate;
-	attr->ah_attr.ah_flags 	    	    = cmd.dest.is_global ? IB_AH_GRH : 0;
-	attr->ah_attr.port_num 	    	    = cmd.dest.port_num;
-
-	memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd.alt_dest.dgid, 16);
-	attr->alt_ah_attr.grh.flow_label    = cmd.alt_dest.flow_label;
-	attr->alt_ah_attr.grh.sgid_index    = cmd.alt_dest.sgid_index;
-	attr->alt_ah_attr.grh.hop_limit     = cmd.alt_dest.hop_limit;
-	attr->alt_ah_attr.grh.traffic_class = cmd.alt_dest.traffic_class;
-	attr->alt_ah_attr.dlid 	    	    = cmd.alt_dest.dlid;
-	attr->alt_ah_attr.sl   	    	    = cmd.alt_dest.sl;
-	attr->alt_ah_attr.src_path_bits     = cmd.alt_dest.src_path_bits;
-	attr->alt_ah_attr.static_rate       = cmd.alt_dest.static_rate;
-	attr->alt_ah_attr.ah_flags 	    = cmd.alt_dest.is_global ? IB_AH_GRH : 0;
-	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;
+	attr->qp_state		  = cmd->base.qp_state;
+	attr->cur_qp_state	  = cmd->base.cur_qp_state;
+	attr->path_mtu		  = cmd->base.path_mtu;
+	attr->path_mig_state	  = cmd->base.path_mig_state;
+	attr->qkey		  = cmd->base.qkey;
+	attr->rq_psn		  = cmd->base.rq_psn;
+	attr->sq_psn		  = cmd->base.sq_psn;
+	attr->dest_qp_num	  = cmd->base.dest_qp_num;
+	attr->qp_access_flags	  = cmd->base.qp_access_flags;
+	attr->pkey_index	  = cmd->base.pkey_index;
+	attr->alt_pkey_index	  = cmd->base.alt_pkey_index;
+	attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify;
+	attr->max_rd_atomic	  = cmd->base.max_rd_atomic;
+	attr->max_dest_rd_atomic  = cmd->base.max_dest_rd_atomic;
+	attr->min_rnr_timer	  = cmd->base.min_rnr_timer;
+	attr->port_num		  = cmd->base.port_num;
+	attr->timeout		  = cmd->base.timeout;
+	attr->retry_cnt		  = cmd->base.retry_cnt;
+	attr->rnr_retry		  = cmd->base.rnr_retry;
+	attr->alt_port_num	  = cmd->base.alt_port_num;
+	attr->alt_timeout	  = cmd->base.alt_timeout;
+	attr->rate_limit	  = cmd->rate_limit;
+
+	memcpy(attr->ah_attr.grh.dgid.raw, cmd->base.dest.dgid, 16);
+	attr->ah_attr.grh.flow_label	= cmd->base.dest.flow_label;
+	attr->ah_attr.grh.sgid_index	= cmd->base.dest.sgid_index;
+	attr->ah_attr.grh.hop_limit	= cmd->base.dest.hop_limit;
+	attr->ah_attr.grh.traffic_class	= cmd->base.dest.traffic_class;
+	attr->ah_attr.dlid		= cmd->base.dest.dlid;
+	attr->ah_attr.sl		= cmd->base.dest.sl;
+	attr->ah_attr.src_path_bits	= cmd->base.dest.src_path_bits;
+	attr->ah_attr.static_rate	= cmd->base.dest.static_rate;
+	attr->ah_attr.ah_flags		= cmd->base.dest.is_global ?
+					  IB_AH_GRH : 0;
+	attr->ah_attr.port_num		= cmd->base.dest.port_num;
+
+	memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd->base.alt_dest.dgid, 16);
+	attr->alt_ah_attr.grh.flow_label    = cmd->base.alt_dest.flow_label;
+	attr->alt_ah_attr.grh.sgid_index    = cmd->base.alt_dest.sgid_index;
+	attr->alt_ah_attr.grh.hop_limit     = cmd->base.alt_dest.hop_limit;
+	attr->alt_ah_attr.grh.traffic_class = cmd->base.alt_dest.traffic_class;
+	attr->alt_ah_attr.dlid		    = cmd->base.alt_dest.dlid;
+	attr->alt_ah_attr.sl		    = cmd->base.alt_dest.sl;
+	attr->alt_ah_attr.src_path_bits	    = cmd->base.alt_dest.src_path_bits;
+	attr->alt_ah_attr.static_rate	    = cmd->base.alt_dest.static_rate;
+	attr->alt_ah_attr.ah_flags	    = cmd->base.alt_dest.is_global ?
+					      IB_AH_GRH : 0;
+	attr->alt_ah_attr.port_num	    = cmd->base.alt_dest.port_num;
 
 	if (qp->real_qp == qp) {
-		if (cmd.attr_mask & IB_QP_AV) {
+		if (cmd->base.attr_mask & IB_QP_AV) {
 			ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr);
 			if (ret)
 				goto release_qp;
 		}
 		ret = qp->device->modify_qp(qp, attr,
-			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
+					    modify_qp_mask(qp->qp_type,
+							   cmd->base.attr_mask),
+					    udata);
 	} else {
-		ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask));
+		ret = ib_modify_qp(qp, attr,
+				   modify_qp_mask(qp->qp_type,
+						  cmd->base.attr_mask));
 	}
 
-	if (ret)
-		goto release_qp;
-
-	ret = in_len;
-
 release_qp:
 	put_qp_read(qp);
 
@@ -2427,6 +2419,68 @@ out:
 	return ret;
 }
 
+ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
+			    struct ib_device *ib_dev,
+			    const char __user *buf, int in_len,
+			    int out_len)
+{
+	struct ib_uverbs_ex_modify_qp cmd = {};
+	struct ib_udata udata;
+	int ret;
+
+	if (copy_from_user(&cmd.base, buf, sizeof(cmd.base)))
+		return -EFAULT;
+
+	if (cmd.base.attr_mask &
+	    ~((IB_USER_LEGACY_LAST_QP_ATTR_MASK << 1) - 1))
+		return -EOPNOTSUPP;
+
+	INIT_UDATA(&udata, buf + sizeof(cmd.base), NULL,
+		   in_len - sizeof(cmd.base), out_len);
+
+	ret = modify_qp(file, &cmd, &udata);
+	if (ret)
+		return ret;
+
+	return in_len;
+}
+
+int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
+			   struct ib_device *ib_dev,
+			   struct ib_udata *ucore,
+			   struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_modify_qp cmd = {};
+	int ret;
+
+	/*
+	 * Last bit is reserved for extending the attr_mask by
+	 * using another field.
+	 */
+	BUILD_BUG_ON(IB_USER_LAST_QP_ATTR_MASK == (1 << 31));
+
+	if (ucore->inlen < sizeof(cmd.base))
+		return -EINVAL;
+
+	ret = ib_copy_from_udata(&cmd, ucore, min(sizeof(cmd), ucore->inlen));
+	if (ret)
+		return ret;
+
+	if (cmd.base.attr_mask &
+	    ~((IB_USER_LAST_QP_ATTR_MASK << 1) - 1))
+		return -EOPNOTSUPP;
+
+	if (ucore->inlen > sizeof(cmd)) {
+		if (ib_is_udata_cleared(ucore, sizeof(cmd),
+					ucore->inlen - sizeof(cmd)))
+			return -EOPNOTSUPP;
+	}
+
+	ret = modify_qp(file, &cmd, uhw);
+
+	return ret;
+}
+
 ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
 			     struct ib_device *ib_dev,
 			     const char __user *buf, int in_len,
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 0012fa58c105..80839c31c887 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -137,6 +137,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_DESTROY_WQ]       = ib_uverbs_ex_destroy_wq,
 	[IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL] = ib_uverbs_ex_create_rwq_ind_table,
 	[IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL] = ib_uverbs_ex_destroy_rwq_ind_table,
+	[IB_USER_VERBS_EX_CMD_MODIFY_QP]        = ib_uverbs_ex_modify_qp,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 90ba5e88ec00..dfdfe4e92d31 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -37,6 +37,7 @@
 #define IB_USER_VERBS_H
 
 #include <linux/types.h>
+#include <rdma/ib_verbs.h>
 
 /*
  * Increment this value if any changes that break userspace ABI
@@ -93,6 +94,7 @@ enum {
 	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
 	IB_USER_VERBS_EX_CMD_CREATE_CQ = IB_USER_VERBS_CMD_CREATE_CQ,
 	IB_USER_VERBS_EX_CMD_CREATE_QP = IB_USER_VERBS_CMD_CREATE_QP,
+	IB_USER_VERBS_EX_CMD_MODIFY_QP = IB_USER_VERBS_CMD_MODIFY_QP,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 	IB_USER_VERBS_EX_CMD_CREATE_WQ,
@@ -545,6 +547,14 @@ enum {
 	IB_UVERBS_CREATE_QP_SUP_COMP_MASK = IB_UVERBS_CREATE_QP_MASK_IND_TABLE,
 };
 
+enum {
+	IB_USER_LEGACY_LAST_QP_ATTR_MASK = IB_QP_DEST_QPN
+};
+
+enum {
+	IB_USER_LAST_QP_ATTR_MASK = IB_QP_RATE_LIMIT
+};
+
 struct ib_uverbs_ex_create_qp {
 	__u64 user_handle;
 	__u32 pd_handle;
@@ -684,9 +694,20 @@ struct ib_uverbs_modify_qp {
 	__u64 driver_data[0];
 };
 
+struct ib_uverbs_ex_modify_qp {
+	struct ib_uverbs_modify_qp base;
+	__u32	rate_limit;
+	__u32	reserved;
+};
+
 struct ib_uverbs_modify_qp_resp {
 };
 
+struct ib_uverbs_ex_modify_qp_resp {
+	__u32  comp_mask;
+	__u32  response_length;
+};
+
 struct ib_uverbs_destroy_qp {
 	__u64 response;
 	__u32 qp_handle;
-- 
cgit v1.2.3