[PATCH stable v5.4+ 1/3] x86/kvm: Teardown PV features on boot CPU as well

From: Krzysztof Kozlowski
Date: Thu May 20 2021 - 08:58:57 EST


From: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>

commit 8b79feffeca28c5459458fe78676b081e87c93a4 upstream.

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.

Krzysztof:
This fixes memory corruption visible after second resume from
hibernation:

BUG: Bad page state in process dbus-daemon pfn:18b01
page:ffffea000062c040 refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 compound_mapcount: -30591
flags: 0xfffffc0078141(locked|error|workingset|writeback|head|mappedtodisk|reclaim)
raw: 000fffffc0078141 dead0000000002d0 dead000000000100 0000000000000000
raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: PAGE_FLAGS_CHECK_AT_PREP flag set
bad because of flags: 0x78141(locked|error|workingset|writeback|head|mappedtodisk|reclaim)

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Message-Id: <20210414123544.1060604-3-vkuznets@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Andrea Righi <andrea.righi@xxxxxxxxxxxxx>
[krzysztof: Extend the commit message]
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@xxxxxxxxxxxxx>
---

Backport to v5.4 seems reasonable. Might have sense to earlier versions,
but this was not tested/investigated.

arch/x86/kernel/kvm.c | 32 ++++++++++++++++++++++++++++----
1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index e820568ed4d5..6b906a651fb1 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
--
2.27.0