IB/hfi1: Use napi_schedule_irqoff() for tx napi
authorMike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
Mon, 29 Mar 2021 13:54:10 +0000 (09:54 -0400)
committerJason Gunthorpe <jgg@nvidia.com>
Wed, 7 Apr 2021 23:19:00 +0000 (20:19 -0300)
The call is from an ISR context and napi_schedule_irqoff() can be used.

Change the call to the more efficient type.

Link: https://lore.kernel.org/r/1617026056-50483-5-git-send-email-dennis.dalessandro@cornelisnetworks.com
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
drivers/infiniband/hw/hfi1/ipoib_tx.c

index 1c38c38..8ebb653 100644 (file)
@@ -209,7 +209,7 @@ static void hfi1_ipoib_add_tx(struct ipoib_txreq *tx)
 
                /* Finish storing txreq before incrementing head. */
                smp_store_release(&tx_ring->head, CIRC_ADD(head, 1, max_tx));
-               napi_schedule(tx->txq->napi);
+               napi_schedule_irqoff(tx->txq->napi);
        } else {
                struct hfi1_ipoib_txq *txq = tx->txq;
                struct hfi1_ipoib_dev_priv *priv = tx->priv;