RDMA/core: Reduce poll batch for direct cq polling

Fix warning limit for kernel stack consumption:

drivers/infiniband/core/cq.c: In function 'ib_process_cq_direct':
drivers/infiniband/core/cq.c:78:1: error: the frame size of 1032 bytes
is larger than 1024 bytes [-Werror=frame-larger-than=]

Using smaller ib_wc array on the stack brings us comfortably below that
limit again.

Fixes: 246d8b18 ("IB/cq: Don't force IB_POLL_DIRECT poll context for ib_process_cq_direct")
Reported-by: NArnd Bergmann <arnd@arndb.de>
Reviewed-by: NSergey Gorenko <sergeygo@mellanox.com>
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/core/cq.c

@@ -17,6 +17,7 @@
 
 /* # of WCs to poll for with a single call to ib_poll_cq */
 #define IB_POLL_BATCH			16
+#define IB_POLL_BATCH_DIRECT		8
 
 /* # of WCs to iterate over before yielding */
 #define IB_POLL_BUDGET_IRQ		256
@@ -25,18 +26,18 @@
 #define IB_POLL_FLAGS \
 	(IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS)
 
-static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc)
+static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
+			   int batch)
 {
 	int i, n, completed = 0;
-	struct ib_wc *wcs = poll_wc ? : cq->wc;
 
 	/*
 	 * budget might be (-1) if the caller does not
 	 * want to bound this call, thus we need unsigned
 	 * minimum here.
 	 */
-	while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH,
-			budget - completed), wcs)) > 0) {
+	while ((n = ib_poll_cq(cq, min_t(u32, batch,
+					 budget - completed), wcs)) > 0) {
 		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = &wcs[i];
 
@@ -48,8 +49,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc)
 
 		completed += n;
 
-		if (n != IB_POLL_BATCH ||
-		    (budget != -1 && completed >= budget))
+		if (n != batch || (budget != -1 && completed >= budget))
 			break;
 	}
 
@@ -72,9 +72,9 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc)
  */
 int ib_process_cq_direct(struct ib_cq *cq, int budget)
 {
-	struct ib_wc wcs[IB_POLL_BATCH];
+	struct ib_wc wcs[IB_POLL_BATCH_DIRECT];
 
-	return __ib_process_cq(cq, budget, wcs);
+	return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT);
 }
 EXPORT_SYMBOL(ib_process_cq_direct);
 
@@ -88,7 +88,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 	struct ib_cq *cq = container_of(iop, struct ib_cq, iop);
 	int completed;
 
-	completed = __ib_process_cq(cq, budget, NULL);
+	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
 	if (completed < budget) {
 		irq_poll_complete(&cq->iop);
 		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
@@ -108,7 +108,8 @@ static void ib_cq_poll_work(struct work_struct *work)
 	struct ib_cq *cq = container_of(work, struct ib_cq, work);
 	int completed;
 
-	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, NULL);
+	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc,
+				    IB_POLL_BATCH);
 	if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
 	    ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
 		queue_work(ib_comp_wq, &cq->work);