linux-kernel - [PATCH net-next V4 3/3] enic: Use NUMA distances logic when setting affinity hints

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20220728191203.4055-4-tariqt@nvidia.com>
Date:   Thu, 28 Jul 2022 22:12:03 +0300
From:   Tariq Toukan <tariqt@...dia.com>
To:     "David S. Miller" <davem@...emloft.net>,
        Saeed Mahameed <saeedm@...dia.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Juri Lelli <juri.lelli@...hat.com>
CC:     Eric Dumazet <edumazet@...gle.com>,
        Paolo Abeni <pabeni@...hat.com>, <netdev@...r.kernel.org>,
        Gal Pressman <gal@...dia.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        <linux-kernel@...r.kernel.org>, Tariq Toukan <tariqt@...dia.com>,
        Christian Benvenuti <benve@...co.com>,
        "Govindarajulu Varadarajan" <_govind@....com>
Subject: [PATCH net-next V4 3/3] enic: Use NUMA distances logic when setting affinity hints

Use the new CPU spread API to sort cpus preference of remote NUMA nodes
according to their distance.

Cc: Christian Benvenuti <benve@...co.com>
Cc: Govindarajulu Varadarajan <_govind@....com>
Reviewed-by: Gal Pressman <gal@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 372fb7b3a282..9de3c3ffa1e3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -44,6 +44,7 @@
 #include <linux/cpu_rmap.h>
 #endif
 #include <linux/crash_dump.h>
+#include <linux/sched/topology.h>
 #include <net/busy_poll.h>
 #include <net/vxlan.h>
 
@@ -114,8 +115,14 @@ static struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = {
 static void enic_init_affinity_hint(struct enic *enic)
 {
 	int numa_node = dev_to_node(&enic->pdev->dev);
+	u16 *cpus;
 	int i;
 
+	cpus = kcalloc(enic->intr_count, sizeof(*cpus), GFP_KERNEL);
+	if (!cpus)
+		return;
+
+	sched_cpus_set_spread(numa_node, cpus, enic->intr_count);
 	for (i = 0; i < enic->intr_count; i++) {
 		if (enic_is_err_intr(enic, i) || enic_is_notify_intr(enic, i) ||
 		    (cpumask_available(enic->msix[i].affinity_mask) &&
@@ -123,9 +130,10 @@ static void enic_init_affinity_hint(struct enic *enic)
 			continue;
 		if (zalloc_cpumask_var(&enic->msix[i].affinity_mask,
 				       GFP_KERNEL))
-			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+			cpumask_set_cpu(cpus[i],
 					enic->msix[i].affinity_mask);
 	}
+	kfree(cpus);
 }
 
 static void enic_free_affinity_hint(struct enic *enic)
-- 
2.21.0