[ofa-general] [RFC 1/2] ib/mad: report number of times a mad was retried

[Sean Hefty]

To allow ULPs to tune timeout values and capture retry statistics,
report the number of times that a mad send operation was retried.

For RMPP mads, report the total number of times that any portion
(send window) of the send operation was retried.

Signed-off-by: Sean Hefty <sean.hefty at intel.com>
---

 drivers/infiniband/core/mad.c      |    9 +++++++--
 drivers/infiniband/core/mad_priv.h |    3 ++-
 drivers/infiniband/core/mad_rmpp.c |    2 +-
 include/rdma/ib_mad.h              |    4 +++-
 4 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 6f42877..91e62c3 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -1100,7 +1100,9 @@ int ib_post_send_mad(struct ib_mad_send_buf *send_buf,
 		mad_send_wr->tid = ((struct ib_mad_hdr *) send_buf->mad)->tid;
 		/* Timeout will be updated after send completes */
 		mad_send_wr->timeout = msecs_to_jiffies(send_buf->timeout_ms);
-		mad_send_wr->retries = send_buf->retries;
+		mad_send_wr->max_retries = send_buf->retries;
+		mad_send_wr->retries_left = send_buf->retries;
+		send_buf->retries = 0;
 		/* Reference for work request to QP + response */
 		mad_send_wr->refcount = 1 + (mad_send_wr->timeout > 0);
 		mad_send_wr->status = IB_WC_SUCCESS;
@@ -2445,9 +2447,12 @@ static int retry_send(struct ib_mad_send_wr_private *mad_send_wr)
 {
 	int ret;
 
-	if (!mad_send_wr->retries--)
+	if (!mad_send_wr->retries_left)
 		return -ETIMEDOUT;
 
+	mad_send_wr->retries_left--;
+	mad_send_wr->send_buf.retries++;
+
 	mad_send_wr->timeout = msecs_to_jiffies(mad_send_wr->send_buf.timeout_ms);
 
 	if (mad_send_wr->mad_agent_priv->agent.rmpp_version) {
diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h
index 9be5cc0..8b75010 100644
--- a/drivers/infiniband/core/mad_priv.h
+++ b/drivers/infiniband/core/mad_priv.h
@@ -131,7 +131,8 @@ struct ib_mad_send_wr_private {
 	struct ib_sge sg_list[IB_MAD_SEND_REQ_MAX_SG];
 	__be64 tid;
 	unsigned long timeout;
-	int retries;
+	int max_retries;
+	int retries_left;
 	int retry;
 	int refcount;
 	enum ib_wc_status status;
diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c
index d43bc62..a5e2a31 100644
--- a/drivers/infiniband/core/mad_rmpp.c
+++ b/drivers/infiniband/core/mad_rmpp.c
@@ -684,7 +684,7 @@ static void process_rmpp_ack(struct ib_mad_agent_private *agent,
 
 	if (seg_num > mad_send_wr->last_ack) {
 		adjust_last_ack(mad_send_wr, seg_num);
-		mad_send_wr->retries = mad_send_wr->send_buf.retries;
+		mad_send_wr->retries_left = mad_send_wr->max_retries;
 	}
 	mad_send_wr->newwin = newwin;
 	if (mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count) {
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 8ec3799..7228c05 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -230,7 +230,9 @@ struct ib_class_port_info
  * @seg_count: The number of RMPP segments allocated for this send.
  * @seg_size: Size of each RMPP segment.
  * @timeout_ms: Time to wait for a response.
- * @retries: Number of times to retry a request for a response.
+ * @retries: Number of times to retry a request for a response.  For MADs
+ *   using RMPP, this applies per window.  On completion, returns the number
+ *   of retries needed to complete the transfer.
  *
  * Users are responsible for initializing the MAD buffer itself, with the
  * exception of any RMPP header.  Additional segment buffer space allocated