diff mbox series

[SRU,F/aws,3/6] x86/kvm: Teardown PV features on boot CPU as well

Message ID 20210519151513.309935-4-andrea.righi@canonical.com
State New
Headers show
Series aws: proper fix for c5.18xlarge hibernation issues | expand

Commit Message

Andrea Righi May 19, 2021, 3:15 p.m. UTC 
From: Vitaly Kuznetsov <vkuznets@redhat.com>

BugLink: https://bugs.launchpad.net/bugs/1920944

Various PV features (Async PF, PV EOI, steal time) work through memory
shared with hypervisor and when we restore from hibernation we must
properly teardown all these features to make sure hypervisor doesn't
write to stale locations after we jump to the previously hibernated kernel
(which can try to place anything there). For secondary CPUs the job is
already done by kvm_cpu_down_prepare(), register syscore ops to do
the same for boot CPU.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210414123544.1060604-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(backported from 8b79feffeca28c5459458fe78676b081e87c93a4)
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
---
 arch/x86/kernel/kvm.c | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

Comments

Krzysztof Kozlowski May 20, 2021, 5:19 p.m. UTC | #1 
On 19/05/2021 11:15, Andrea Righi wrote:
> From: Vitaly Kuznetsov <vkuznets@redhat.com>
> 
> BugLink: https://bugs.launchpad.net/bugs/1920944
> 
> Various PV features (Async PF, PV EOI, steal time) work through memory
> shared with hypervisor and when we restore from hibernation we must
> properly teardown all these features to make sure hypervisor doesn't
> write to stale locations after we jump to the previously hibernated kernel
> (which can try to place anything there). For secondary CPUs the job is
> already done by kvm_cpu_down_prepare(), register syscore ops to do
> the same for boot CPU.
> 
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> Message-Id: <20210414123544.1060604-3-vkuznets@redhat.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> (backported from 8b79feffeca28c5459458fe78676b081e87c93a4)

This differs significantly against mainline kernel and
kvm_guest_cpu_offline() ends up in different section - under ifdef. Is
it on purpose?


Best regards,
Krzysztof
diff mbox series

Patch

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index ec7e4b9f50a5..7bf47e41bb46 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -24,6 +24,7 @@ 
 #include <linux/debugfs.h>
 #include <linux/nmi.h>
 #include <linux/swait.h>
+#include <linux/syscore_ops.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -558,17 +559,21 @@  static void kvm_guest_cpu_offline(void)
 
 static int kvm_cpu_online(unsigned int cpu)
 {
-	local_irq_disable();
+	unsigned long flags;
+
+	local_irq_save(flags);
 	kvm_guest_cpu_init();
-	local_irq_enable();
+	local_irq_restore(flags);
 	return 0;
 }
 
 static int kvm_cpu_down_prepare(unsigned int cpu)
 {
-	local_irq_disable();
+	unsigned long flags;
+
+	local_irq_save(flags);
 	kvm_guest_cpu_offline();
-	local_irq_enable();
+	local_irq_restore(flags);
 	return 0;
 }
 #endif
@@ -606,6 +611,23 @@  static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 	native_flush_tlb_others(flushmask, info);
 }
 
+static int kvm_suspend(void)
+{
+	kvm_guest_cpu_offline();
+
+	return 0;
+}
+
+static void kvm_resume(void)
+{
+	kvm_cpu_online(raw_smp_processor_id());
+}
+
+static struct syscore_ops kvm_syscore_ops = {
+	.suspend	= kvm_suspend,
+	.resume		= kvm_resume,
+};
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -649,6 +671,8 @@  static void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 
+	register_syscore_ops(&kvm_syscore_ops);
+
 	/*
 	 * Hard lockup detection is enabled by default. Disable it, as guests
 	 * can get false positives too easily, for example if the host is