KVM: VMX: Move IRQ invocation to assembly subroutine

Move the asm blob that invokes the appropriate IRQ handler after VM-Exit
into a proper subroutine.  Unconditionally create a stack frame in the
subroutine so that, as objtool sees things, the function has standard
stack behavior.  The dynamic stack adjustment makes using unwind hints
problematic.

Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200915191505.10355-2-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 37 insertions, 30 deletions

diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 799db084a336..90ad7a6246e3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -4,6 +4,7 @@
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/nospec-branch.h>
+#include <asm/segment.h>
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -294,3 +295,36 @@ SYM_FUNC_START(vmread_error_trampoline)
 
 	ret
 SYM_FUNC_END(vmread_error_trampoline)
+
+SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff)
+	/*
+	 * Unconditionally create a stack frame, getting the correct RSP on the
+	 * stack (for x86-64) would take two instructions anyways, and RBP can
+	 * be used to restore RSP to make objtool happy (see below).
+	 */
+	push %_ASM_BP
+	mov %_ASM_SP, %_ASM_BP
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Align RSP to a 16-byte boundary (to emulate CPU behavior) before
+	 * creating the synthetic interrupt stack frame for the IRQ/NMI.
+	 */
+	and  $-16, %rsp
+	push $__KERNEL_DS
+	push %rbp
+#endif
+	pushf
+	push $__KERNEL_CS
+	CALL_NOSPEC _ASM_ARG1
+
+	/*
+	 * "Restore" RSP from RBP, even though IRET has already unwound RSP to
+	 * the correct value.  objtool doesn't know the callee will IRET and,
+	 * without the explicit restore, thinks the stack is getting walloped.
+	 * Using an unwind hint is problematic due to x86-64's dynamic alignment.
+	 */
+	mov %_ASM_BP, %_ASM_SP
+	pop %_ASM_BP
+	ret
+SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f002d3415840..6f425a658865 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6323,6 +6323,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
 }
 
+void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
+
 static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 {
 	u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
@@ -6344,10 +6346,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 {
 	unsigned int vector;
-	unsigned long entry;
-#ifdef CONFIG_X86_64
-	unsigned long tmp;
-#endif
 	gate_desc *desc;
 	u32 intr_info = vmx_get_intr_info(vcpu);
 
@@ -6357,36 +6355,11 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 
 	vector = intr_info & INTR_INFO_VECTOR_MASK;
 	desc = (gate_desc *)host_idt_base + vector;
-	entry = gate_offset(desc);
 
 	kvm_before_interrupt(vcpu);
-
-	asm volatile(
-#ifdef CONFIG_X86_64
-		"mov %%rsp, %[sp]\n\t"
-		"and $-16, %%rsp\n\t"
-		"push %[ss]\n\t"
-		"push %[sp]\n\t"
-#endif
-		"pushf\n\t"
-		"push %[cs]\n\t"
-		CALL_NOSPEC
-		:
-#ifdef CONFIG_X86_64
-		[sp]"=&r"(tmp),
-#endif
-		ASM_CALL_CONSTRAINT
-		:
-		[thunk_target]"r"(entry),
-#ifdef CONFIG_X86_64
-		[ss]"i"(__KERNEL_DS),
-#endif
-		[cs]"i"(__KERNEL_CS)
-	);
-
+	vmx_do_interrupt_nmi_irqoff(gate_offset(desc));
 	kvm_after_interrupt(vcpu);
 }
-STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {