On 2018/6/14 9:47, Vijay Immanuel wrote:
Error retries can occur due to timeouts, NAKs or receiving
packets beyond the current read request. Avoid back-to-back
retries due to packet processing, by only retrying the initial
attempt immediately. Subsequent retries must be due to timeouts.
Continue to process completion packets after scheduling a retry.
Signed-off-by: Vijay Immanuel <vijayi@xxxxxxxxxxxxxxxxx>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 19 ++++++++++++++++++-
drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
2 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 6cdc40e..b1d5624 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -191,6 +191,7 @@ static inline void reset_retry_counters(struct rxe_qp *qp)
{
qp->comp.retry_cnt = qp->attr.retry_cnt;
qp->comp.rnr_retry = qp->attr.rnr_retry;
+ qp->comp.started_retry = 0;
}
static inline enum comp_state check_psn(struct rxe_qp *qp,
@@ -679,6 +680,21 @@ int rxe_completer(void *arg)
goto exit;
}
+ /* if we've started a retry, don't start another
+ * retry sequence, unless this is a timeout.
+ */
Sorry. Is it possible that several SKBs require retry at almost the same
time?
+ if (qp->comp.started_retry &&
+ !qp->comp.timeout_retry) {
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ skb = NULL;
+ }
+
+ WARN_ON_ONCE(skb);
+ goto done;
+ }
+
if (qp->comp.retry_cnt > 0) {
if (qp->comp.retry_cnt != 7)
qp->comp.retry_cnt--;
@@ -695,6 +711,7 @@ int rxe_completer(void *arg)
rxe_counter_inc(rxe,
RXE_CNT_COMP_RETRY);
qp->req.need_retry = 1;
+ qp->comp.started_retry = 1;
rxe_run_task(&qp->req.task, 1);
}
@@ -705,7 +722,7 @@ int rxe_completer(void *arg)
}
WARN_ON_ONCE(skb);
- goto exit;
+ goto done;
} else {
rxe_counter_inc(rxe, RXE_CNT_RETRY_EXCEEDED);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index af1470d..51a515b 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -158,6 +158,7 @@ struct rxe_comp_info {
int opcode;
int timeout;
int timeout_retry;
+ int started_retry;
u32 retry_cnt;
u32 rnr_retry;
struct rxe_task task;
