[PATCH for-rc v2 8/8] RDMA/bnxt_re: Check is_in_used before trusting RCFW completion

[Selvin Xavier <selvin.xavier@broadcom.com>]

Gate the crsqe->resp memcpy in bnxt_qplib_process_qp_event() on
is_in_used in addition to is_waiter_alive, since a late/duplicate
completion for an already-retired cookie could still write through a
stale resp pointer.

Also disarm the waiter and clear resp when a wait call bails out early
on ERR_DEVICE_DETACHED, and require is_in_used before re-triggering
__destroy_timedout_ah(), closing the same stale-cookie exposure
elsewhere in the completion path.

Fixes: 691eb7c6110f ("RDMA/bnxt_re: handle command completions after driver detect a timedout")
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 9ee0d500436c..0339e55bea88 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -511,14 +511,16 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 	else
 		rc = __poll_for_resp(rcfw, cookie);
 
-	if (rc) {
+	if (rc || test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags)) {
 		spin_lock_bh(&rcfw->cmdq.hwq.lock);
 		crsqe = &rcfw->crsqe_tbl[cookie];
 		crsqe->is_waiter_alive = false;
+		crsqe->resp = NULL;
 		if (rc == -ENODEV)
 			set_bit(FIRMWARE_STALL_DETECTED, &rcfw->cmdq.flags);
 		spin_unlock_bh(&rcfw->cmdq.hwq.lock);
-		return -ETIMEDOUT;
+		if (rc)
+			return -ETIMEDOUT;
 	}
 
 	if (evnt->status) {
@@ -627,6 +629,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 	struct bnxt_qplib_qp *qp;
 	u16 cookie, blocked = 0;
 	bool is_waiter_alive;
+	bool is_in_used;
 	struct pci_dev *pdev;
 	u32 wait_cmds = 0;
 	int rc = 0;
@@ -682,7 +685,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 		if (crsqe->is_internal_cmd && !qp_event->status)
 			atomic_dec(&rcfw->timeout_send);
 
-		if (crsqe->is_waiter_alive) {
+		if (crsqe->is_waiter_alive && crsqe->is_in_used) {
 			if (crsqe->resp) {
 				memcpy(crsqe->resp, qp_event, sizeof(*qp_event));
 				/* Insert write memory barrier to ensure that
@@ -697,6 +700,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 
 		req_size = crsqe->req_size;
 		is_waiter_alive = crsqe->is_waiter_alive;
+		is_in_used = crsqe->is_in_used;
 
 		crsqe->req_size = 0;
 		if (!is_waiter_alive)
@@ -718,7 +722,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 		 * resource leak and relatively not critical +  unlikely
 		 * scenario. Current design is not to handle such case.
 		 */
-		if (!is_waiter_alive && !qp_event->status &&
+		if (is_in_used && !is_waiter_alive && !qp_event->status &&
 		    qp_event->event == CREQ_QP_EVENT_EVENT_CREATE_AH)
 			__destroy_timedout_ah(rcfw,
 					      (struct creq_create_ah_resp *)
-- 
2.39.3