KVM: VMX: Avoid atomic operation in vmx_vcpu_run

Instead of exchanging the guest and host rcx, have separate storage
for each.  This allows us to avoid using the xchg instruction, which
is is a little slower than normal operations.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index da468c26639d55740b1a6623d931eca4d76a94ce..ae4f02d470917ca94b84bb2f805adf814ba09615 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4022,6 +4022,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
        asm(
                /* Store host registers */
                "push %%"R"dx; push %%"R"bp;"
+               "push %%"R"cx \n\t" /* placeholder for guest rcx */
                "push %%"R"cx \n\t"
                "cmp %%"R"sp, %c[host_rsp](%0) \n\t"
                "je 1f \n\t"
@@ -4063,7 +4064,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
                ".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t"
                ".Lkvm_vmx_return: "
                /* Save guest registers, load host registers, keep flags */
-               "xchg %0,     (%%"R"sp) \n\t"
+               "mov %0, %c[wordsize](%%"R"sp) \n\t"
+               "pop %0 \n\t"
                "mov %%"R"ax, %c[rax](%0) \n\t"
                "mov %%"R"bx, %c[rbx](%0) \n\t"
                "pop"Q" %c[rcx](%0) \n\t"
@@ -4107,7 +4109,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
                [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])),
                [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])),
 #endif
-               [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2))
+               [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
+               [wordsize]"i"(sizeof(ulong))
              : "cc", "memory"
                , R"ax", R"bx", R"di", R"si"
 #ifdef CONFIG_X86_64