IB/mad: Add final OPA MAD processing

For devices which support OPA MADs

   1) Use previously defined SMP support functions.

   2) Pass correct base version to ib_create_send_mad when processing OPA MADs.

   3) Process out_mad_key_index returned by agents for a response.  This is
      necessary because OPA SMP packets must carry a valid pkey.

   4) Carry the correct segment size (OPA vs IBTA) of RMPP messages within
      ib_mad_recv_wc.

   5) Handle variable length OPA MADs by:

        * Adjusting the 'fake' WC for locally routed SMP's to represent the
          proper incoming byte_len
        * out_mad_size is used from the local HCA agents
                1) when sending agent responses on the wire
                2) when passing responses through the local_completions
		   function

	NOTE: wc.byte_len includes the GRH length and therefore is different
	      from the in_mad_size specified to the local HCA agents.
	      out_mad_size should _not_ include the GRH length as it is added
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/core/agent.c

@@ -80,7 +80,7 @@ ib_get_agent_port(const struct ib_device *device, int port_num)
 
 void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
 			 const struct ib_wc *wc, const struct ib_device *device,
-			 int port_num, int qpn, size_t resp_mad_len)
+			 int port_num, int qpn, size_t resp_mad_len, bool opa)
 {
 	struct ib_agent_port_private *port_priv;
 	struct ib_mad_agent *agent;
@@ -106,11 +106,14 @@ void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *
 		return;
 	}
 
+	if (opa && mad_hdr->base_version != OPA_MGMT_BASE_VERSION)
+		resp_mad_len = IB_MGMT_MAD_SIZE;
+
 	send_buf = ib_create_send_mad(agent, wc->src_qp, wc->pkey_index, 0,
 				      IB_MGMT_MAD_HDR,
 				      resp_mad_len - IB_MGMT_MAD_HDR,
 				      GFP_KERNEL,
-				      IB_MGMT_BASE_VERSION);
+				      mad_hdr->base_version);
 	if (IS_ERR(send_buf)) {
 		dev_err(&device->dev, "ib_create_send_mad error\n");
 		goto err1;

drivers/infiniband/core/agent.h

@@ -46,6 +46,6 @@ extern int ib_agent_port_close(struct ib_device *device, int port_num);
 
 extern void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
 				const struct ib_wc *wc, const struct ib_device *device,
-				int port_num, int qpn, size_t resp_mad_len);
+				int port_num, int qpn, size_t resp_mad_len, bool opa);
 
 #endif	/* __AGENT_H_ */

drivers/infiniband/core/mad_priv.h

@@ -148,6 +148,7 @@ struct ib_mad_local_private {
 	struct ib_mad_private *mad_priv;
 	struct ib_mad_agent_private *recv_mad_agent;
 	struct ib_mad_send_wr_private *mad_send_wr;
+	size_t return_wc_byte_len;
 };
 
 struct ib_mad_mgmt_method_table {

drivers/infiniband/core/mad_rmpp.c

 /*
  * Copyright (c) 2005 Intel Inc. All rights reserved.
  * Copyright (c) 2005-2006 Voltaire, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -67,6 +68,7 @@ struct mad_rmpp_recv {
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;
+	u8 base_version;
 };
 
 static inline void deref_rmpp_recv(struct mad_rmpp_recv *rmpp_recv)
@@ -318,6 +320,7 @@ create_rmpp_recv(struct ib_mad_agent_private *agent,
 	rmpp_recv->mgmt_class = mad_hdr->mgmt_class;
 	rmpp_recv->class_version = mad_hdr->class_version;
 	rmpp_recv->method  = mad_hdr->method;
+	rmpp_recv->base_version  = mad_hdr->base_version;
 	return rmpp_recv;
 
 error:	kfree(rmpp_recv);
@@ -433,14 +436,23 @@ static inline int get_mad_len(struct mad_rmpp_recv *rmpp_recv)
 {
 	struct ib_rmpp_mad *rmpp_mad;
 	int hdr_size, data_size, pad;
+	bool opa = rdma_cap_opa_mad(rmpp_recv->agent->qp_info->port_priv->device,
+				    rmpp_recv->agent->qp_info->port_priv->port_num);
 
 	rmpp_mad = (struct ib_rmpp_mad *)rmpp_recv->cur_seg_buf->mad;
 
 	hdr_size = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
-	data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
-	pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
-	if (pad > IB_MGMT_RMPP_DATA || pad < 0)
-		pad = 0;
+	if (opa && rmpp_recv->base_version == OPA_MGMT_BASE_VERSION) {
+		data_size = sizeof(struct opa_rmpp_mad) - hdr_size;
+		pad = OPA_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > OPA_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	} else {
+		data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
+		pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > IB_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	}
 
 	return hdr_size + rmpp_recv->seg_num * data_size - pad;
 }

drivers/infiniband/core/user_mad.c

@@ -262,20 +262,23 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 {
 	struct ib_mad_recv_buf *recv_buf;
 	int left, seg_payload, offset, max_seg_payload;
+	size_t seg_size;
 
-	/* We need enough room to copy the first (or only) MAD segment. */
 	recv_buf = &packet->recv_wc->recv_buf;
-	if ((packet->length <= sizeof (*recv_buf->mad) &&
+	seg_size = packet->recv_wc->mad_seg_size;
+
+	/* We need enough room to copy the first (or only) MAD segment. */
+	if ((packet->length <= seg_size &&
 	     count < hdr_size(file) + packet->length) ||
-	    (packet->length > sizeof (*recv_buf->mad) &&
-	     count < hdr_size(file) + sizeof (*recv_buf->mad)))
+	    (packet->length > seg_size &&
+	     count < hdr_size(file) + seg_size))
 		return -EINVAL;
 
 	if (copy_to_user(buf, &packet->mad, hdr_size(file)))
 		return -EFAULT;
 
 	buf += hdr_size(file);
-	seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
+	seg_payload = min_t(int, packet->length, seg_size);
 	if (copy_to_user(buf, recv_buf->mad, seg_payload))
 		return -EFAULT;
 
@@ -292,7 +295,7 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 			return -ENOSPC;
 		}
 		offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class);
-		max_seg_payload = sizeof (struct ib_mad) - offset;
+		max_seg_payload = seg_size - offset;
 
 		for (left = packet->length - seg_payload, buf += seg_payload;
 		     left; left -= seg_payload, buf += seg_payload) {
@@ -450,6 +453,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 	struct ib_rmpp_mad *rmpp_mad;
 	__be64 *tid;
 	int ret, data_len, hdr_len, copy_offset, rmpp_active;
+	u8 base_version;
 
 	if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
 		return -EINVAL;
@@ -516,12 +520,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 		rmpp_active = 0;
 	}
 
+	base_version = ((struct ib_mad_hdr *)&packet->mad.data)->base_version;
 	data_len = count - hdr_size(file) - hdr_len;
 	packet->msg = ib_create_send_mad(agent,
 					 be32_to_cpu(packet->mad.hdr.qpn),
 					 packet->mad.hdr.pkey_index, rmpp_active,
 					 hdr_len, data_len, GFP_KERNEL,
-					 IB_MGMT_BASE_VERSION);
+					 base_version);
 	if (IS_ERR(packet->msg)) {
 		ret = PTR_ERR(packet->msg);
 		goto err_ah;

include/rdma/ib_mad.h

@@ -199,6 +199,12 @@ struct ib_rmpp_mad {
 	u8			data[IB_MGMT_RMPP_DATA];
 };
 
+struct opa_rmpp_mad {
+	struct ib_mad_hdr	mad_hdr;
+	struct ib_rmpp_hdr	rmpp_hdr;
+	u8			data[OPA_MGMT_RMPP_DATA];
+};
+
 struct ib_sa_mad {
 	struct ib_mad_hdr	mad_hdr;
 	struct ib_rmpp_hdr	rmpp_hdr;
@@ -429,6 +435,7 @@ struct ib_mad_recv_buf {
  * @recv_buf: Specifies the location of the received data buffer(s).
  * @rmpp_list: Specifies a list of RMPP reassembled received MAD buffers.
  * @mad_len: The length of the received MAD, without duplicated headers.
+ * @mad_seg_size: The size of individual MAD segments
  *
  * For received response, the wr_id contains a pointer to the ib_mad_send_buf
  *   for the corresponding send request.
@@ -438,6 +445,7 @@ struct ib_mad_recv_wc {
 	struct ib_mad_recv_buf	recv_buf;
 	struct list_head	rmpp_list;
 	int			mad_len;
+	size_t			mad_seg_size;
 };
 
 /**