From: Sean Christopherson <seanjc@xxxxxxxxxx> [ Upstream commit b23c83ad2c638420ec0608a9de354507c41bec29 ] 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@xxxxxxxxxx> Link: https://lore.kernel.org/r/20230721201859.2307736-2-seanjc@xxxxxxxxxx Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- 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 a3760ca796aa2..256eee99afc8f 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 bc5b4d788c08d..2551baec927d2 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 cdd92ab43cda4..54cd959cb3160 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 d03c551defccf..299b970e5f829 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -787,6 +787,26 @@ 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; @@ -798,6 +818,8 @@ 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 4e972b9b68e59..31a10d774df6d 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> @@ -702,7 +702,6 @@ 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(); @@ -712,7 +711,6 @@ 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) { @@ -8522,10 +8520,9 @@ 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(); } @@ -8598,10 +8595,9 @@ 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(); /* -- 2.40.1
