linux-kernel - [PATCH] irqchip/gic-v4.1: Use the ITS of the NUMA node where current cpu is located

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>] [day] [month] [year] [list]

Message-ID: <20240624122510.3906474-1-tangnianyao@huawei.com>
Date: Mon, 24 Jun 2024 12:25:10 +0000
From: Nianyao Tang <tangnianyao@...wei.com>
To: <maz@...nel.org>, <tglx@...utronix.de>,
	<linux-arm-kernel@...ts.infradead.org>, <linux-kernel@...r.kernel.org>
CC: <guoyang2@...wei.com>, <wangwudi@...ilicon.com>, <tangnianyao@...wei.com>
Subject: [PATCH] irqchip/gic-v4.1: Use the ITS of the NUMA node where current cpu is located

When GICv4.1 enabled, guest sending IPI use the last ITS reported.
On multi-NUMA environment with more than one ITS, it makes IPI performance
various from VM to VM, depending on which NUMA the VM is deployed on. We can
use closer ITS instead of the last ITS reported.

Modify find_4_1_its to find the ITS of the NUMA node where current
cpu is located and save it with per cpu variable.

Signed-off-by: Nianyao Tang <tangnianyao@...wei.com>
---
 drivers/irqchip/irq-gic-v3-its.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 3c755d5dad6e..d35b42f3b2af 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -193,6 +193,8 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock);
 
 static DEFINE_IDA(its_vpeid_ida);
 
+static DEFINE_PER_CPU(struct its_node *, its_on_cpu);
+
 #define gic_data_rdist()		(raw_cpu_ptr(gic_rdists->rdist))
 #define gic_data_rdist_cpu(cpu)		(per_cpu_ptr(gic_rdists->rdist, cpu))
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
@@ -4058,19 +4060,26 @@ static struct irq_chip its_vpe_irq_chip = {
 
 static struct its_node *find_4_1_its(void)
 {
-	static struct its_node *its = NULL;
+	struct its_node *its = NULL;
+	struct its_node *its_non_cpu_node = NULL;
+	int cpu = smp_processor_id();
 
-	if (!its) {
-		list_for_each_entry(its, &its_nodes, entry) {
-			if (is_v4_1(its))
-				return its;
-		}
+	if (per_cpu(its_on_cpu, cpu))
+		return per_cpu(its_on_cpu, cpu);
 
-		/* Oops? */
-		its = NULL;
-	}
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (is_v4_1(its) && its->numa_node == cpu_to_node(cpu)) {
+			per_cpu(its_on_cpu, cpu) = its;
+			return its;
+		}
+		else if (is_v4_1(its))
+			its_non_cpu_node = its;
+ 	}
 
-	return its;
+	if (!per_cpu(its_on_cpu, cpu) && its_non_cpu_node)
+		per_cpu(its_on_cpu, cpu) = its_non_cpu_node;
+
+	return its_non_cpu_node;
 }
 
 static void its_vpe_4_1_send_inv(struct irq_data *d)
-- 
2.30.0