x86/kvm: Disable all PV features on crash

commit 3d6b84132d2a57b5a74100f6923a8feb679ac2ce upstream.

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@redhat.com>
Message-Id: <20210414123544.1060604-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index a617fd3600235d9b8f3b110eaf21cbbefcf7c7ef..f913f62eb6c3512478ab622054471aa9db6b9454 100644 (file)
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -91,7 +91,6 @@ unsigned int kvm_arch_para_hints(void);
 void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
-extern void kvm_disable_steal_time(void);
 void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
@@ -125,11 +124,6 @@ static inline u32 kvm_read_and_reset_pf_reason(void)
 {
        return 0;
 }
-
-static inline void kvm_disable_steal_time(void)
-{
-       return;
-}
 #endif
 
 #endif /* _ASM_X86_KVM_PARA_H */

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d6f04d32dec0a6cef8f93fbc4fcec5b38db7b4a0..6ff2c7cac4c463e991b56e430c5d9cd84f863a1c 100644 (file)
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -34,6 +34,7 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/tlb.h>
+#include <asm/reboot.h>
 
 static int kvmapf = 1;
 
@@ -352,6 +353,14 @@ static void kvm_pv_disable_apf(void)
               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)
 {
        /*
@@ -394,14 +403,6 @@ 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);
@@ -429,13 +430,14 @@ 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();
 }
 
@@ -573,7 +575,7 @@ 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;
 }
@@ -582,7 +584,7 @@ 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;
 }
@@ -597,6 +599,20 @@ static struct syscore_ops kvm_syscore_ops = {
        .resume         = kvm_resume,
 };
 
+/*
+ * 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_apf_trap_init(void)
 {
        update_intr_gate(X86_TRAP_PF, async_page_fault);
@@ -673,6 +689,10 @@ 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 bd3962953f78a55d6ae486ad4b7fc489a28c11f9..4a0802af2e3e0acd8fdcd61669d54c5937fec012 100644 (file)
--- 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;
@@ -197,23 +196,6 @@ 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);
@@ -344,9 +326,6 @@ 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();
 
        /*