system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-09-22 03:55:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

RDMA/siw: Fix broken RDMA Read Fence/Resume logic.

Browse source 
Code unconditionally resumed fenced SQ processing after next RDMA Read
completion, even if other RDMA Read responses are still outstanding, or
ORQ is full. Also adds comments for better readability of fence
processing, and removes orq_get_tail() helper, which is not needed
anymore.

Fixes: 8b6a361b8c ("rdma/siw: receive path")
Fixes: a531975279 ("rdma/siw: main include file")
Link: https://lore.kernel.org/r/20220130170815.1940-1-bmt@zurich.ibm.com
Reported-by: Jared Holzman <jared.holzman@excelero.com>
Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This commit is contained in:
Bernard Metzler 2022-01-30 18:08:15 +01:00 committed by Jason Gunthorpe
parent 4028bccb00
commit b43a76f423
2 changed files with 12 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
drivers/infiniband/sw/siw/siw.h
View file

@ -644,14 +644,9 @@ static inline struct siw_sqe *orq_get_current(struct siw_qp *qp)
return &qp->orq[qp->orq_get % qp->attrs.orq_size]; return &qp->orq[qp->orq_get % qp->attrs.orq_size];
} }
static inline struct siw_sqe *orq_get_tail(struct siw_qp *qp)
{
return &qp->orq[qp->orq_put % qp->attrs.orq_size];
}
static inline struct siw_sqe *orq_get_free(struct siw_qp *qp) static inline struct siw_sqe *orq_get_free(struct siw_qp *qp)
{ {
struct siw_sqe *orq_e = orq_get_tail(qp); struct siw_sqe *orq_e = &qp->orq[qp->orq_put % qp->attrs.orq_size];
if (READ_ONCE(orq_e->flags) == 0) if (READ_ONCE(orq_e->flags) == 0)
return orq_e; return orq_e;

20
drivers/infiniband/sw/siw/siw_qp_rx.c
View file

@ -1153,11 +1153,12 @@ static int siw_check_tx_fence(struct siw_qp *qp)
spin_lock_irqsave(&qp->orq_lock, flags); spin_lock_irqsave(&qp->orq_lock, flags);
rreq = orq_get_current(qp);
/* free current orq entry */ /* free current orq entry */
rreq = orq_get_current(qp);
WRITE_ONCE(rreq->flags, 0); WRITE_ONCE(rreq->flags, 0);
qp->orq_get++;
if (qp->tx_ctx.orq_fence) { if (qp->tx_ctx.orq_fence) {
if (unlikely(tx_waiting->wr_status != SIW_WR_QUEUED)) { if (unlikely(tx_waiting->wr_status != SIW_WR_QUEUED)) {
pr_warn("siw: [QP %u]: fence resume: bad status %d\n", pr_warn("siw: [QP %u]: fence resume: bad status %d\n",
@ -1165,10 +1166,12 @@ static int siw_check_tx_fence(struct siw_qp *qp)
rv = -EPROTO; rv = -EPROTO;
goto out; goto out;
} }
/* resume SQ processing */ /* resume SQ processing, if possible */
if (tx_waiting->sqe.opcode == SIW_OP_READ || if (tx_waiting->sqe.opcode == SIW_OP_READ ||
tx_waiting->sqe.opcode == SIW_OP_READ_LOCAL_INV) { tx_waiting->sqe.opcode == SIW_OP_READ_LOCAL_INV) {
rreq = orq_get_tail(qp);
/* SQ processing was stopped because of a full ORQ */
rreq = orq_get_free(qp);
if (unlikely(!rreq)) { if (unlikely(!rreq)) {
pr_warn("siw: [QP %u]: no ORQE\n", qp_id(qp)); pr_warn("siw: [QP %u]: no ORQE\n", qp_id(qp));
rv = -EPROTO; rv = -EPROTO;
@ -1181,15 +1184,14 @@ static int siw_check_tx_fence(struct siw_qp *qp)
resume_tx = 1; resume_tx = 1;
} else if (siw_orq_empty(qp)) { } else if (siw_orq_empty(qp)) {
/*
* SQ processing was stopped by fenced work request.
* Resume since all previous Read's are now completed.
*/
qp->tx_ctx.orq_fence = 0; qp->tx_ctx.orq_fence = 0;
resume_tx = 1; resume_tx = 1;
} else {
pr_warn("siw: [QP %u]: fence resume: orq idx: %d:%d\n",
qp_id(qp), qp->orq_get, qp->orq_put);
rv = -EPROTO;
} }
} }
qp->orq_get++;
out: out:
spin_unlock_irqrestore(&qp->orq_lock, flags); spin_unlock_irqrestore(&qp->orq_lock, flags);