From: Sean Christopherson seanjc@google.com

mainline inclusion from mainline-v6.6-rc1 commit b23c83ad2c638420ec0608a9de354507c41bec29 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I95B2J CVE: CVE-2023-52514

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id...

--------------------------------

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@citrix.com Link: https://lore.kernel.org/r/20230721201859.2307736-2-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Wei Li liwei391@huawei.com --- 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 | 9 ++------- 5 files changed, 26 insertions(+), 40 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 3533ede83b42..5f5b83bdaa3e 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -209,8 +209,6 @@ extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages);

#endif

-typedef void crash_vmclear_fn(void); -extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; extern void kdump_nmi_shootdown_cpus(void);

#ifdef CONFIG_KEXEC_CORE 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 bd4b566ec917..1247cdafe353 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -48,27 +48,6 @@ 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(); -} - /* * When the crashkernel option is specified, only use the low * 1M for the real mode trampoline. @@ -88,11 +67,6 @@ 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 */ @@ -146,11 +120,6 @@ 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 52c77932c4d2..970296f4403b 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 74a717ca46e7..ff783fed0fd0 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/mce.h> #include <asm/mmu_context.h> @@ -780,7 +780,6 @@ 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(); @@ -790,7 +789,6 @@ 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) { @@ -8514,10 +8512,8 @@ static void vmx_cleanup_l1d_flush(void)

static void vmx_exit(void) { -#ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); -#endif

kvm_exit();

@@ -8612,10 +8608,9 @@ 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();

/*