IB/hfi1: Unreserve a flushed OPFN request

When an OPFN request is flushed, the request is completed without
unreserving itself from the send queue. Subsequently, when a new
request is post sent, the following warning will be triggered:

WARNING: CPU: 4 PID: 8130 at rdmavt/qp.c:1761 rvt_post_send+0x72a/0x880 [rdmavt]
Call Trace:
[<ffffffffbbb61e41>] dump_stack+0x19/0x1b
[<ffffffffbb497688>] __warn+0xd8/0x100
[<ffffffffbb4977cd>] warn_slowpath_null+0x1d/0x20
[<ffffffffc01c941a>] rvt_post_send+0x72a/0x880 [rdmavt]
[<ffffffffbb4dcabe>] ? account_entity_dequeue+0xae/0xd0
[<ffffffffbb61d645>] ? __kmalloc+0x55/0x230
[<ffffffffc04e1a4c>] ib_uverbs_post_send+0x37c/0x5d0 [ib_uverbs]
[<ffffffffc04e5e36>] ? rdma_lookup_put_uobject+0x26/0x60 [ib_uverbs]
[<ffffffffc04dbce6>] ib_uverbs_write+0x286/0x460 [ib_uverbs]
[<ffffffffbb6f9457>] ? security_file_permission+0x27/0xa0
[<ffffffffbb641650>] vfs_write+0xc0/0x1f0
[<ffffffffbb64246f>] SyS_write+0x7f/0xf0
[<ffffffffbbb74ddb>] system_call_fastpath+0x22/0x27

This patch fixes the problem by moving rvt_qp_wqe_unreserve() into
rvt_qp_complete_swqe() to simplify the code and make it less
error-prone.

Fixes: ca95f80 ("IB/hfi1: Unreserve a reserved request when it is completed")
Link: https://lore.kernel.org/r/[email protected]
Cc: <[email protected]>
Reviewed-by: Mike Marciniszyn <[email protected]>
Reviewed-by: Dennis Dalessandro <[email protected]>
Signed-off-by: Kaike Wan <[email protected]>
Signed-off-by: Mike Marciniszyn <[email protected]>
Signed-off-by: Jason Gunthorpe <[email protected]>

Author: kwan-intc

drivers/infiniband/hw/hfi1/rc.c

@@ -1835,7 +1835,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah)
 		    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0)
 			break;
 		trdma_clean_swqe(qp, wqe);
-		rvt_qp_wqe_unreserve(qp, wqe);
 		trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
 		rvt_qp_complete_swqe(qp,
 				     wqe,
@@ -1882,7 +1881,6 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 ||
 	    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
 		trdma_clean_swqe(qp, wqe);
-		rvt_qp_wqe_unreserve(qp, wqe);
 		trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
 		rvt_qp_complete_swqe(qp,
 				     wqe,

include/rdma/rdmavt_qp.h

@@ -608,7 +608,7 @@ static inline void rvt_qp_wqe_reserve(
 /**
  * rvt_qp_wqe_unreserve - clean reserved operation
  * @qp - the rvt qp
- * @wqe - the send wqe
+ * @flags - send wqe flags
  *
  * This decrements the reserve use count.
  *
@@ -620,11 +620,9 @@ static inline void rvt_qp_wqe_reserve(
  * the compiler does not juggle the order of the s_last
  * ring index and the decrementing of s_reserved_used.
  */
-static inline void rvt_qp_wqe_unreserve(
-	struct rvt_qp *qp,
-	struct rvt_swqe *wqe)
+static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags)
 {
-	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) {
+	if (unlikely(flags & RVT_SEND_RESERVE_USED)) {
 		atomic_dec(&qp->s_reserved_used);
 		/* insure no compiler re-order up to s_last change */
 		smp_mb__after_atomic();
@@ -853,6 +851,7 @@ rvt_qp_complete_swqe(struct rvt_qp *qp,
 	u32 byte_len, last;
 	int flags = wqe->wr.send_flags;
 
+	rvt_qp_wqe_unreserve(qp, flags);
 	rvt_put_qp_swqe(qp, wqe);
 
 	need_completion =