[SRU][H][PATCH 4/5] x86/kvm: Disable all PV features on crash

[Andrea Righi]

From: Vitaly Kuznetsov <vkuznets at redhat.com>

Crash shutdown handler only disables kvmclock and steal time, other PV
features remain active so we risk corrupting memory or getting some
side-effects in kdump kernel. Move crash handler to kvm.c and unify
with CPU offline.

Signed-off-by: Vitaly Kuznetsov <vkuznets at redhat.com>
Message-Id: <20210414123544.1060604-5-vkuznets at redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini at redhat.com>
(backported from commit 3d6b84132d2a57b5a74100f6923a8feb679ac2ce)
Signed-off-by: Andrea Righi <andrea.righi at canonical.com>
---
 arch/x86/include/asm/kvm_para.h |  6 -----
 arch/x86/kernel/kvm.c           | 44 ++++++++++++++++++++++++---------
 arch/x86/kernel/kvmclock.c      | 21 ----------------
 3 files changed, 32 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 9c56e0defd45..69299878b200 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -92,7 +92,6 @@ unsigned int kvm_arch_para_hints(void);
 void kvm_async_pf_task_wait_schedule(u32 token);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_apf_flags(void);
-void kvm_disable_steal_time(void);
 bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token);
 
 DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
@@ -137,11 +136,6 @@ static inline u32 kvm_read_and_reset_apf_flags(void)
 	return 0;
 }
 
-static inline void kvm_disable_steal_time(void)
-{
-	return;
-}
-
 static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	return false;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 464eb2a13c89..147281852ca9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -38,6 +38,7 @@
 #include <asm/tlb.h>
 #include <asm/cpuidle_haltpoll.h>
 #include <asm/ptrace.h>
+#include <asm/reboot.h>
 #include <asm/svm.h>
 
 DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
@@ -375,6 +376,14 @@ static void kvm_pv_disable_apf(void)
 	pr_info("disable async PF for cpu %d\n", smp_processor_id());
 }
 
+static void kvm_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+}
+
 static void kvm_pv_guest_cpu_reboot(void *unused)
 {
 	/*
@@ -417,14 +426,6 @@ static u64 kvm_steal_clock(int cpu)
 	return steal;
 }
 
-void kvm_disable_steal_time(void)
-{
-	if (!has_steal_clock)
-		return;
-
-	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
-}
-
 static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
 {
 	early_set_memory_decrypted((unsigned long) ptr, size);
@@ -452,13 +453,14 @@ static void __init sev_map_percpu_data(void)
 	}
 }
 
-static void kvm_guest_cpu_offline(void)
+static void kvm_guest_cpu_offline(bool shutdown)
 {
 	kvm_disable_steal_time();
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
 	kvm_pv_disable_apf();
-	apf_task_wake_all();
+	if (!shutdown)
+		apf_task_wake_all();
 	kvmclock_disable();
 }
 
@@ -613,7 +615,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	kvm_guest_cpu_offline();
+	kvm_guest_cpu_offline(false);
 	local_irq_restore(flags);
 	return 0;
 }
@@ -622,7 +624,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
-	kvm_guest_cpu_offline();
+	kvm_guest_cpu_offline(false);
 
 	return 0;
 }
@@ -663,6 +665,20 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 	native_flush_tlb_others(flushmask, info);
 }
 
+/*
+ * After a PV feature is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written.
+ */
+#ifdef CONFIG_KEXEC_CORE
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+	kvm_guest_cpu_offline(true);
+	native_machine_crash_shutdown(regs);
+}
+#endif
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -705,6 +721,10 @@ static void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.crash_shutdown = kvm_crash_shutdown;
+#endif
+
 	register_syscore_ops(&kvm_syscore_ops);
 
 	/*
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index cf869de98eec..b825c87c12ef 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -20,7 +20,6 @@
 #include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
-#include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
 static int kvmclock __initdata = 1;
@@ -203,23 +202,6 @@ static void kvm_setup_secondary_clock(void)
 }
 #endif
 
-/*
- * After the clock is registered, the host will keep writing to the
- * registered memory location. If the guest happens to shutdown, this memory
- * won't be valid. In cases like kexec, in which you install a new kernel, this
- * means a random memory location will be kept being written. So before any
- * kind of shutdown from our side, we unregister the clock by writing anything
- * that does not have the 'enable' bit set in the msr
- */
-#ifdef CONFIG_KEXEC_CORE
-static void kvm_crash_shutdown(struct pt_regs *regs)
-{
-	native_write_msr(msr_kvm_system_time, 0, 0);
-	kvm_disable_steal_time();
-	native_machine_crash_shutdown(regs);
-}
-#endif
-
 void kvmclock_disable(void)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
@@ -349,9 +331,6 @@ void __init kvmclock_init(void)
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
-#ifdef CONFIG_KEXEC_CORE
-	machine_ops.crash_shutdown  = kvm_crash_shutdown;
-#endif
 	kvm_get_preset_lpj();
 
 	/*
-- 
2.31.1