Received-SPF: pass (google.com: domain of linux-kernel+bounces-63318-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Marc Zyngier <maz@kernel.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Kunkun Jiang <jiangkunkun@huawei.com>,
	Lorenzo Pieralisi <lpieralisi@kernel.org>,
	Zenghui Yu <yuzenghui@huawei.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	stable@vger.kernel.org
Subject: [PATCH 3/3] irqchip/gic-v3-its: Fix GICv4.1 VPE affinity update
Date: Tue, 13 Feb 2024 10:12:06 +0000
Message-Id: <20240213101206.2137483-4-maz@kernel.org>
In-Reply-To: <20240213101206.2137483-1-maz@kernel.org>
References: <20240213101206.2137483-1-maz@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

When updating the affinity of a VPE, we currently skip the VMOVP
command if the two CPUs are part of the same VPE affinity.

But this is wrong, as the doorbell corresponding to this VPE
is still delivered on the 'old' CPU, which screws up the balancing.
Furthermore, offlining that 'old' CPU results in doorbell interrupts
generated for this VPE being discarded.

The harsh reality is that we cannot easily elide VMOVP when
a set_affinity request occurs. It needs to be obeyed, and if
an optimisation is to be made, it is at the point where the affinity
change request is made (such as in KVM).

Drop the VMOVP elision altogether, and only use the vpe_table_mask
to try and stay within the same ITS affinity group if at all possible.

Fixes: dd3f050a216e (irqchip/gic-v4.1: Implement the v4.1 flavour of VMOVP)
Reported-by: Kunkun Jiang <jiangkunkun@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 250b4562f308..53abd4779914 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3826,8 +3826,9 @@ static int its_vpe_set_affinity(struct irq_data *d,
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	int from, cpu = cpumask_first(mask_val);
+	struct cpumask common, *table_mask;
 	unsigned long flags;
+	int from, cpu;
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
@@ -3843,19 +3844,22 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * taken on any vLPI handling path that evaluates vpe->col_idx.
 	 */
 	from = vpe_to_cpuid_lock(vpe, &flags);
-	if (from == cpu)
-		goto out;
-
-	vpe->col_idx = cpu;
+	table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
 
 	/*
-	 * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
-	 * is sharing its VPE table with the current one.
+	 * If we are offered another CPU in the same GICv4.1 ITS
+	 * affinity, pick this one. Otherwise, any CPU will do.
 	 */
-	if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
-	    cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+	if (table_mask && cpumask_and(&common, mask_val, table_mask))
+		cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (from == cpu)
 		goto out;
 
+	vpe->col_idx = cpu;
+
 	its_send_vmovp(vpe);
 	its_vpe_db_proxy_move(vpe, from, cpu);
 
-- 
2.39.2