@@ -578,10 +578,11 @@ static void save_state(struct rxe_send_wqe *wqe,
struct rxe_send_wqe *rollback_wqe,
u32 *rollback_psn)
{
- rollback_wqe->state = wqe->state;
+ rollback_wqe->state = wqe->state;
rollback_wqe->first_psn = wqe->first_psn;
- rollback_wqe->last_psn = wqe->last_psn;
- *rollback_psn = qp->req.psn;
+ rollback_wqe->last_psn = wqe->last_psn;
+ rollback_wqe->dma = wqe->dma;
+ *rollback_psn = qp->req.psn;
}
static void rollback_state(struct rxe_send_wqe *wqe,
@@ -589,10 +590,11 @@ static void rollback_state(struct rxe_send_wqe *wqe,
struct rxe_send_wqe *rollback_wqe,
u32 rollback_psn)
{
- wqe->state = rollback_wqe->state;
+ wqe->state = rollback_wqe->state;
wqe->first_psn = rollback_wqe->first_psn;
- wqe->last_psn = rollback_wqe->last_psn;
- qp->req.psn = rollback_psn;
+ wqe->last_psn = rollback_wqe->last_psn;
+ wqe->dma = rollback_wqe->dma;
+ qp->req.psn = rollback_psn;
}
static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
@@ -797,6 +799,9 @@ int rxe_requester(struct rxe_qp *qp)
pkt.mask = rxe_opcode[opcode].mask;
pkt.wqe = wqe;
+ /* save wqe state before we build and send packet */
+ save_state(wqe, qp, &rollback_wqe, &rollback_psn);
+
av = rxe_get_av(&pkt, &ah);
if (unlikely(!av)) {
rxe_dbg_qp(qp, "Failed no address vector\n");
@@ -829,29 +834,29 @@ int rxe_requester(struct rxe_qp *qp)
if (ah)
rxe_put(ah);
- /*
- * To prevent a race on wqe access between requester and completer,
- * wqe members state and psn need to be set before calling
- * rxe_xmit_packet().
- * Otherwise, completer might initiate an unjustified retry flow.
- */
- save_state(wqe, qp, &rollback_wqe, &rollback_psn);
+ /* update wqe state as though we had sent it */
update_wqe_state(qp, wqe, &pkt);
update_wqe_psn(qp, wqe, &pkt, payload);
err = rxe_xmit_packet(qp, &pkt, skb);
if (err) {
- qp->need_req_skb = 1;
+ if (err != -EAGAIN) {
+ wqe->status = IB_WC_LOC_QP_OP_ERR;
+ goto err;
+ }
+ /* the packet was dropped so reset wqe to the state
+ * before we sent it so we can try to resend
+ */
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
- if (err == -EAGAIN) {
- rxe_sched_task(&qp->req.task);
- goto exit;
- }
+ /* force a delay until the dropped packet is freed and
+ * the send queue is drained below the low water mark
+ */
+ qp->need_req_skb = 1;
- wqe->status = IB_WC_LOC_QP_OP_ERR;
- goto err;
+ rxe_sched_task(&qp->req.task);
+ goto exit;
}
update_state(qp, &pkt);
If a send packet is dropped by the IP layer in rxe_requester() the call to rxe_xmit_packet() can fail with err == -EAGAIN. To recover, the state of the wqe is restored to the state before the packet was sent so it can be resent. However, the routines that save and restore the state miss a significnt part of the variable state in the wqe, the dma struct which is used to process through the sge table. And, the state is not saved before the packet is built which modifies the dma struct. Under heavy stress testing with many QPs on a fast node sending large messages to a slow node dropped packets are observed and the resent packets are corrupted because the dma struct was not restored. This patch fixes this behavior and allows the test cases to succeed. Fixes: 3050b9985024 ("IB/rxe: Fix race condition between requester and completer") Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com> --- v2: Rebased to for-next drivers/infiniband/sw/rxe/rxe_req.c | 45 ++++++++++++++++------------- 1 file changed, 25 insertions(+), 20 deletions(-) base-commit: b3d2b014b259ba758d72d7026685091bde1cf2d6