UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

KVM/VMX: Invoke NMI non-IST entry instead of IST entry 

In VMX, the host NMI handler needs to be invoked after NMI VM-Exit.
Before commit 1a5488ef0d ("KVM: VMX: Invoke NMI handler via indirect
call instead of INTn"), this was done by INTn ("int $2"). But INTn
microcode is relatively expensive, so the commit reworked NMI VM-Exit
handling to invoke the kernel handler by function call.

But this missed a detail. The NMI entry point for direct invocation is
fetched from the IDT table and called on the kernel stack.  But on 64-bit
the NMI entry installed in the IDT expects to be invoked on the IST stack.
It relies on the "NMI executing" variable on the IST stack to work
correctly, which is at a fixed position in the IST stack.  When the entry
point is unexpectedly called on the kernel stack, the RSP-addressed "NMI
executing" variable is obviously also on the kernel stack and is
"uninitialized" and can cause the NMI entry code to run in the wrong way.

Provide a non-ist entry point for VMX which shares the C-function with
the regular NMI entry and invoke the new asm entry point instead.

On 32-bit this just maps to the regular NMI entry point as 32-bit has no
ISTs and is not affected.

[ tglx: Made it independent for backporting, massaged changelog ]

Fixes: 1a5488ef0d ("KVM: VMX: Invoke NMI handler via indirect call instead of INTn")
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Lai Jiangshan <laijs@linux.alibaba.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/87r1imi8i1.ffs@nanos.tec.linutronix.de
This commit is contained in:
Lai Jiangshan 2021-05-04 21:50:14 +02:00 committed by Thomas Gleixner
parent fc48a6d1fa
commit a217a6593c
3 changed files with 34 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
arch/x86/include/asm/idtentry.h
View File

@ -588,6 +588,21 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check);
#endif
/* NMI */
#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL)
/*
* Special NOIST entry point for VMX which invokes this on the kernel
* stack. asm_exc_nmi() requires an IST to work correctly vs. the NMI
* 'executing' marker.
*
* On 32bit this just uses the regular NMI entry point because 32-bit does
* not have ISTs.
*/
DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_noist);
#else
#define asm_exc_nmi_noist asm_exc_nmi
#endif
DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi);
#ifdef CONFIG_XEN_PV
DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi);

10
arch/x86/kernel/nmi.c
View File

@ -524,6 +524,16 @@ nmi_restart:
mds_user_clear_cpu_buffers();
}
#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL)
DEFINE_IDTENTRY_RAW(exc_nmi_noist)
{
exc_nmi(regs);
}
#endif
#if IS_MODULE(CONFIG_KVM_INTEL)
EXPORT_SYMBOL_GPL(asm_exc_nmi_noist);
#endif
void stop_nmi(void)
{
ignore_nmis++;

16
arch/x86/kvm/vmx/vmx.c
View File

@ -36,6 +36,7 @@
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/idtentry.h>
#include <asm/io.h>
#include <asm/irq_remapping.h>
#include <asm/kexec.h>
@ -6415,18 +6416,17 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
unsigned long entry)
{
unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
gate_desc *desc = (gate_desc *)host_idt_base + vector;
kvm_before_interrupt(vcpu);
vmx_do_interrupt_nmi_irqoff(gate_offset(desc));
vmx_do_interrupt_nmi_irqoff(entry);
kvm_after_interrupt(vcpu);
}
static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
{
const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
/* if exit due to PF check for async PF */
@ -6437,18 +6437,20 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
kvm_machine_check();
/* We need to handle NMIs before interrupts are enabled */
else if (is_nmi(intr_info))
handle_interrupt_nmi_irqoff(&vmx->vcpu, intr_info);
handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry);
}
static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
{
u32 intr_info = vmx_get_intr_info(vcpu);
unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
gate_desc *desc = (gate_desc *)host_idt_base + vector;
if (WARN_ONCE(!is_external_intr(intr_info),
"KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info))
return;
handle_interrupt_nmi_irqoff(vcpu, intr_info);
handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
}
static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)