From: Vijay Immanuel <vijayi@attalasystems.com>
Date: Wed, 13 Jun 2018 18:47:30 -0700
Subject: IB/rxe: avoid back-to-back retries
Patch-mainline: v4.20-rc1
Git-commit: 4e4c53df567714b3d08b2b5d8ccb1d175fc9be01
References: bsc#1103992 FATE#326009
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@attalasystems.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 18 +++++++++++++++++-
drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
2 files changed, 18 insertions(+), 1 deletion(-)
--- 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(
{
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,
@@ -676,6 +677,20 @@ int rxe_completer(void *arg)
goto exit;
}
+ /* if we've started a retry, don't start another
+ * retry sequence, unless this is a timeout.
+ */
+ if (qp->comp.started_retry &&
+ !qp->comp.timeout_retry) {
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ skb = NULL;
+ }
+
+ goto done;
+ }
+
if (qp->comp.retry_cnt > 0) {
if (qp->comp.retry_cnt != 7)
qp->comp.retry_cnt--;
@@ -692,6 +707,7 @@ 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);
}
@@ -701,7 +717,7 @@ int rxe_completer(void *arg)
skb = NULL;
}
- goto exit;
+ goto done;
} else {
rxe_counter_inc(rxe, RXE_CNT_RETRY_EXCEEDED);
--- 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;