[Devel] [PATCH RHEL9 COMMIT] ms/x86/reboot: VMCLEAR active VMCSes before emergency reboot
Konstantin Khorenko
khorenko at virtuozzo.com
Wed Nov 1 16:44:23 MSK 2023
The commit is pushed to "branch-rh9-5.14.0-284.25.1.vz9.30.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh9-5.14.0-284.25.1.vz9.30.6
------>
commit c9b607e3c5db81c51d54f615834d6509c5361ecc
Author: Sean Christopherson <seanjc at google.com>
Date: Fri Jul 21 13:18:41 2023 -0700
ms/x86/reboot: VMCLEAR active VMCSes before emergency reboot
VMCLEAR active VMCSes before any emergency reboot, not just if the kernel
may kexec into a new kernel after a crash. Per Intel's SDM, the VMX
architecture doesn't require the CPU to flush the VMCS cache on INIT. If
an emergency reboot doesn't RESET CPUs, cached VMCSes could theoretically
be kept and only be written back to memory after the new kernel is booted,
i.e. could effectively corrupt memory after reboot.
Opportunistically remove the setting of the global pointer to NULL to make
checkpatch happy.
Cc: Andrew Cooper <Andrew.Cooper3 at citrix.com>
Link: https://lore.kernel.org/r/20230721201859.2307736-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc at google.com>
Without this patch applied to the L1 VM kernel
L2 VMs may crash on boot in case L1 VM is reset using following command:
# echo b > /proc/sysrq-trigger
Following message appeared in the L2 VM log:
KVM: entry failed, hardware error 0x80000021
https://pmc.acronis.work/browse/VSTOR-76102
(cherry picked from ms commit b23c83ad2c638420ec0608a9de354507c41bec29)
Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
Feature: fix ms/KVM
---
arch/x86/include/asm/kexec.h | 2 --
arch/x86/include/asm/reboot.h | 2 ++
arch/x86/kernel/crash.c | 31 -------------------------------
arch/x86/kernel/reboot.c | 22 ++++++++++++++++++++++
arch/x86/kvm/vmx/vmx.c | 10 +++-------
5 files changed, 27 insertions(+), 40 deletions(-)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a3760ca796aa..256eee99afc8 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -208,8 +208,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
#endif
#endif
-typedef void crash_vmclear_fn(void);
-extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
extern void kdump_nmi_shootdown_cpus(void);
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index bc5b4d788c08..2551baec927d 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type);
#define MRR_BIOS 0
#define MRR_APM 1
+typedef void crash_vmclear_fn(void);
+extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
void cpu_emergency_disable_virtualization(void);
typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index eddd5e066990..00a0d0512ae9 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -48,38 +48,12 @@ struct crash_memmap_data {
unsigned int type;
};
-/*
- * This is used to VMCLEAR all VMCSs loaded on the
- * processor. And when loading kvm_intel module, the
- * callback function pointer will be assigned.
- *
- * protected by rcu.
- */
-crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
-EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
-
-static inline void cpu_crash_vmclear_loaded_vmcss(void)
-{
- crash_vmclear_fn *do_vmclear_operation = NULL;
-
- rcu_read_lock();
- do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
- if (do_vmclear_operation)
- do_vmclear_operation();
- rcu_read_unlock();
-}
-
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
{
crash_save_cpu(regs, cpu);
- /*
- * VMCLEAR VMCSs loaded on all cpus if needed.
- */
- cpu_crash_vmclear_loaded_vmcss();
-
/*
* Disable Intel PT to stop its logging
*/
@@ -133,11 +107,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
crash_smp_send_stop();
- /*
- * VMCLEAR VMCSs loaded on this cpu if needed.
- */
- cpu_crash_vmclear_loaded_vmcss();
-
cpu_emergency_disable_virtualization();
/*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index bcc45ea53938..5eb320c1d4a7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -794,6 +794,26 @@ void machine_crash_shutdown(struct pt_regs *regs)
}
#endif
+/*
+ * This is used to VMCLEAR all VMCSs loaded on the
+ * processor. And when loading kvm_intel module, the
+ * callback function pointer will be assigned.
+ *
+ * protected by rcu.
+ */
+crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
+EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+
+static inline void cpu_crash_vmclear_loaded_vmcss(void)
+{
+ crash_vmclear_fn *do_vmclear_operation = NULL;
+
+ rcu_read_lock();
+ do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
+ if (do_vmclear_operation)
+ do_vmclear_operation();
+ rcu_read_unlock();
+}
/* This is the CPU performing the emergency shutdown work. */
int crashing_cpu = -1;
@@ -805,6 +825,8 @@ int crashing_cpu = -1;
*/
void cpu_emergency_disable_virtualization(void)
{
+ cpu_crash_vmclear_loaded_vmcss();
+
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bff42eae72c1..48a1f89a040e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -40,7 +40,7 @@
#include <asm/idtentry.h>
#include <asm/io.h>
#include <asm/irq_remapping.h>
-#include <asm/kexec.h>
+#include <asm/reboot.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
#include <asm/mshyperv.h>
@@ -703,7 +703,6 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
return ret;
}
-#ifdef CONFIG_KEXEC_CORE
static void crash_vmclear_local_loaded_vmcss(void)
{
int cpu = raw_smp_processor_id();
@@ -713,7 +712,6 @@ static void crash_vmclear_local_loaded_vmcss(void)
loaded_vmcss_on_cpu_link)
vmcs_clear(v->vmcs);
}
-#endif /* CONFIG_KEXEC_CORE */
static void __loaded_vmcs_clear(void *arg)
{
@@ -8433,10 +8431,9 @@ static void __vmx_exit(void)
{
allow_smaller_maxphyaddr = false;
-#ifdef CONFIG_KEXEC_CORE
RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
synchronize_rcu();
-#endif
+
vmx_cleanup_l1d_flush();
}
@@ -8509,10 +8506,9 @@ static int __init vmx_init(void)
pi_init_cpu(cpu);
}
-#ifdef CONFIG_KEXEC_CORE
rcu_assign_pointer(crash_vmclear_loaded_vmcss,
crash_vmclear_local_loaded_vmcss);
-#endif
+
vmx_check_vmcs12_offsets();
/*
More information about the Devel
mailing list