* [PATCH] RDMA/rxe: Generate a completion on error after getting a wqe
@ 2022-03-28 9:54 Xiao Yang
2022-03-28 11:27 ` Leon Romanovsky
0 siblings, 1 reply; 3+ messages in thread
From: Xiao Yang @ 2022-03-28 9:54 UTC (permalink / raw)
To: linux-rdma; +Cc: leonro, jgg, rpearsonhpe, yanjun.zhu, Xiao Yang
Current rxe_requester() doesn't generate a completion on error after
getting a wqe. Fix the issue by calling "goto err;" instead.
Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
---
drivers/infiniband/sw/rxe/rxe_req.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index ae5fbc79dd5c..6f8dd2b3b817 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -648,26 +648,26 @@ int rxe_requester(void *arg)
psn_compare(qp->req.psn, (qp->comp.psn +
RXE_MAX_UNACKED_PSNS)) > 0)) {
qp->req.wait_psn = 1;
- goto exit;
+ goto err;
}
/* Limit the number of inflight SKBs per QP */
if (unlikely(atomic_read(&qp->skb_out) >
RXE_INFLIGHT_SKBS_PER_QP_HIGH)) {
qp->need_req_skb = 1;
- goto exit;
+ goto err;
}
opcode = next_opcode(qp, wqe, wqe->wr.opcode);
if (unlikely(opcode < 0)) {
wqe->status = IB_WC_LOC_QP_OP_ERR;
- goto exit;
+ goto err;
}
mask = rxe_opcode[opcode].mask;
if (unlikely(mask & RXE_READ_OR_ATOMIC_MASK)) {
if (check_init_depth(qp, wqe))
- goto exit;
+ goto err;
}
mtu = get_mtu(qp);
--
2.23.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] RDMA/rxe: Generate a completion on error after getting a wqe
2022-03-28 9:54 [PATCH] RDMA/rxe: Generate a completion on error after getting a wqe Xiao Yang
@ 2022-03-28 11:27 ` Leon Romanovsky
2022-03-28 15:12 ` yangx.jy
0 siblings, 1 reply; 3+ messages in thread
From: Leon Romanovsky @ 2022-03-28 11:27 UTC (permalink / raw)
To: Xiao Yang; +Cc: linux-rdma, jgg, rpearsonhpe, yanjun.zhu
On Mon, Mar 28, 2022 at 05:54:36PM +0800, Xiao Yang wrote:
> Current rxe_requester() doesn't generate a completion on error after
> getting a wqe. Fix the issue by calling "goto err;" instead.
>
> Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
> ---
> drivers/infiniband/sw/rxe/rxe_req.c | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
Don't you need to set wqe->status too to have complete fix?
Thanks
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
> index ae5fbc79dd5c..6f8dd2b3b817 100644
> --- a/drivers/infiniband/sw/rxe/rxe_req.c
> +++ b/drivers/infiniband/sw/rxe/rxe_req.c
> @@ -648,26 +648,26 @@ int rxe_requester(void *arg)
> psn_compare(qp->req.psn, (qp->comp.psn +
> RXE_MAX_UNACKED_PSNS)) > 0)) {
> qp->req.wait_psn = 1;
> - goto exit;
> + goto err;
> }
>
> /* Limit the number of inflight SKBs per QP */
> if (unlikely(atomic_read(&qp->skb_out) >
> RXE_INFLIGHT_SKBS_PER_QP_HIGH)) {
> qp->need_req_skb = 1;
> - goto exit;
> + goto err;
> }
>
> opcode = next_opcode(qp, wqe, wqe->wr.opcode);
> if (unlikely(opcode < 0)) {
> wqe->status = IB_WC_LOC_QP_OP_ERR;
> - goto exit;
> + goto err;
> }
>
> mask = rxe_opcode[opcode].mask;
> if (unlikely(mask & RXE_READ_OR_ATOMIC_MASK)) {
> if (check_init_depth(qp, wqe))
> - goto exit;
> + goto err;
> }
>
> mtu = get_mtu(qp);
> --
> 2.23.0
>
>
>
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] RDMA/rxe: Generate a completion on error after getting a wqe
2022-03-28 11:27 ` Leon Romanovsky
@ 2022-03-28 15:12 ` yangx.jy
0 siblings, 0 replies; 3+ messages in thread
From: yangx.jy @ 2022-03-28 15:12 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: linux-rdma, jgg, rpearsonhpe, yanjun.zhu
On 2022/3/28 19:27, Leon Romanovsky wrote:
> On Mon, Mar 28, 2022 at 05:54:36PM +0800, Xiao Yang wrote:
>> Current rxe_requester() doesn't generate a completion on error after
>> getting a wqe. Fix the issue by calling "goto err;" instead.
>>
>> Signed-off-by: Xiao Yang <yangx.jy@fujitsu.com>
>> ---
>> drivers/infiniband/sw/rxe/rxe_req.c | 8 ++++----
>> 1 file changed, 4 insertions(+), 4 deletions(-)
> Don't you need to set wqe->status too to have complete fix?
Hi Leon,
Agreed. I will set wqe->status to IB_WC_LOC_QP_OP_ERR in my v2 patch.
Best Regards,
Xiao Yang
>
> Thanks
>
>> diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
>> index ae5fbc79dd5c..6f8dd2b3b817 100644
>> --- a/drivers/infiniband/sw/rxe/rxe_req.c
>> +++ b/drivers/infiniband/sw/rxe/rxe_req.c
>> @@ -648,26 +648,26 @@ int rxe_requester(void *arg)
>> psn_compare(qp->req.psn, (qp->comp.psn +
>> RXE_MAX_UNACKED_PSNS)) > 0)) {
>> qp->req.wait_psn = 1;
>> - goto exit;
>> + goto err;
>> }
>>
>> /* Limit the number of inflight SKBs per QP */
>> if (unlikely(atomic_read(&qp->skb_out) >
>> RXE_INFLIGHT_SKBS_PER_QP_HIGH)) {
>> qp->need_req_skb = 1;
>> - goto exit;
>> + goto err;
>> }
>>
>> opcode = next_opcode(qp, wqe, wqe->wr.opcode);
>> if (unlikely(opcode < 0)) {
>> wqe->status = IB_WC_LOC_QP_OP_ERR;
>> - goto exit;
>> + goto err;
>> }
>>
>> mask = rxe_opcode[opcode].mask;
>> if (unlikely(mask & RXE_READ_OR_ATOMIC_MASK)) {
>> if (check_init_depth(qp, wqe))
>> - goto exit;
>> + goto err;
>> }
>>
>> mtu = get_mtu(qp);
>> --
>> 2.23.0
>>
>>
>>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-03-28 15:13 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-03-28 9:54 [PATCH] RDMA/rxe: Generate a completion on error after getting a wqe Xiao Yang
2022-03-28 11:27 ` Leon Romanovsky
2022-03-28 15:12 ` yangx.jy
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.