This is a note to let you know that I've just added the patch titled
irqchip/gic-v3-its: Fix GICv4.1 VPE affinity update
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From af9acbfc2c4b72c378d0b9a2ee023ed01055d3e2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@xxxxxxxxxx>
Date: Tue, 13 Feb 2024 10:12:06 +0000
Subject: irqchip/gic-v3-its: Fix GICv4.1 VPE affinity update
From: Marc Zyngier <maz@xxxxxxxxxx>
commit af9acbfc2c4b72c378d0b9a2ee023ed01055d3e2 upstream.
When updating the affinity of a VPE, the VMOVP command is currently skipped
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 VMOVP cannot be elided 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@xxxxxxxxxx>
Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20240213101206.2137483-4-maz@xxxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/irqchip/irq-gic-v3-its.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3800,8 +3800,9 @@ static int its_vpe_set_affinity(struct i
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
@@ -3817,19 +3818,22 @@ static int its_vpe_set_affinity(struct i
* 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);
Patches currently in stable-queue which might be from maz@xxxxxxxxxx are
queue-5.15/irqchip-irq-brcmstb-l2-add-write-memory-barrier-before-exit.patch
queue-5.15/irqchip-gic-v3-its-fix-gicv4.1-vpe-affinity-update.patch
