arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling

We want SMCCC_ARCH_WORKAROUND_1 to be fast. As fast as possible.
So let's intercept it as early as we can by testing for the
function call number as soon as we've identified a HVC call
coming from the guest.
Tested-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: NChristoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>

arch/arm64/kvm/hyp/hyp-entry.S

@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -64,10 +65,11 @@ alternative_endif
 	lsr	x0, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x0, #ESR_ELx_EC_HVC64
+	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
-	mrs	x1, vttbr_el2		// If vttbr is valid, the 64bit guest
-	cbnz	x1, el1_trap		// called HVC
+	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
+	cbnz	x1, el1_hvc_guest	// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
 	ldp	x0, x1, [sp], #16
@@ -100,6 +102,20 @@ alternative_endif
 
 	eret
 
+el1_hvc_guest:
+	/*
+	 * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1.
+	 * The workaround has already been applied on the host,
+	 * so let's quickly get back to the guest. We don't bother
+	 * restoring x1, as it can be clobbered anyway.
+	 */
+	ldr	x1, [sp]				// Guest's x0
+	eor	w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1
+	cbnz	w1, el1_trap
+	mov	x0, x1
+	add	sp, sp, #16
+	eret
+
 el1_trap:
 	/*
 	 * x0: ESR_EC