Blob Blame History Raw
From: Shannon Nelson <snelson@pensando.io>
Date: Fri, 6 Mar 2020 17:04:03 -0800
Subject: ionic: improve irq numa locality
Patch-mainline: v5.7-rc1
Git-commit: b7f55b81f2ac40e52c5a56e22c80488eac531c91
References: bsc#1167773

Spreading the interrupts across the CPU cores is good for load
balancing, but not necessarily as good when using a CPU/core
that is not part of the NUMA local CPU.  If it can be localized,
the kernel's cpumask_local_spread() service will pick a core
that is on the node close to the PCI device.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -424,8 +424,9 @@ static int ionic_qcq_alloc(struct ionic_
 		ionic_intr_mask_assert(idev->intr_ctrl, new->intr.index,
 				       IONIC_INTR_MASK_SET);
 
-		new->intr.cpu = new->intr.index % num_online_cpus();
-		if (cpu_online(new->intr.cpu))
+		new->intr.cpu = cpumask_local_spread(new->intr.index,
+						     dev_to_node(dev));
+		if (new->intr.cpu != -1)
 			cpumask_set_cpu(new->intr.cpu,
 					&new->intr.affinity_mask);
 	} else {