KVM/VMX: Avoid stack engine synchronization uop in __vmx_vcpu_run

Avoid instructions with explicit uses of the stack pointer between
instructions that implicitly refer to it. The sequence of
POP %reg; ADD $x, %RSP; POP %reg forces emission of synchronization
uop to synchronize the value of the stack pointer in the stack engine
and the out-of-order core.

Using POP with the dummy register instead of ADD $x, %RSP results in a
smaller code size and faster code.

The patch also fixes the reference to the wrong register in the
nearby comment.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20220816211010.25693-1-ubizjak@gmail.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 6de96b9..5355e1a 100644 (file)
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -189,13 +189,16 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
        xor %ebx, %ebx
 
 .Lclear_regs:
+       /* Discard @regs.  The register is irrelevant, it just can't be RBX. */
+       pop %_ASM_AX
+
        /*
         * Clear all general purpose registers except RSP and RBX to prevent
         * speculative use of the guest's values, even those that are reloaded
         * via the stack.  In theory, an L1 cache miss when restoring registers
         * could lead to speculative execution with the guest's values.
         * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
-        * free.  RSP and RAX are exempt as RSP is restored by hardware during
+        * free.  RSP and RBX are exempt as RSP is restored by hardware during
         * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return
         * value.
         */
@@ -216,9 +219,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
        xor %r15d, %r15d
 #endif
 
-       /* "POP" @regs. */
-       add $WORD_SIZE, %_ASM_SP
-
        /*
         * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before
         * the first unbalanced RET after vmexit!
@@ -234,7 +234,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
        FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
                           X86_FEATURE_RSB_VMEXIT_LITE
 
-
        pop %_ASM_ARG2  /* @flags */
        pop %_ASM_ARG1  /* @vmx */