arm64: KVM: Optimize __guest_enter/exit() to save a few instructions

We are doing an unnecessary stack push/pop operation when restoring
the guest registers x0-x18 in __guest_enter(). This patch saves the
two instructions by using x18 as a base register. No need to store
the vcpu context pointer in stack because it is redundant, the same
information is available in tpidr_el2. The function __guest_exit()
calling convention is slightly modified, caller only pushes the regs
x0-x1 to stack instead of regs x0-x3.

Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

arch/arm64/kvm/hyp/entry.S

@@ -55,79 +55,78 @@
  */
 ENTRY(__guest_enter)
 	// x0: vcpu
-	// x1: host/guest context
-	// x2-x18: clobbered by macros
+	// x1: host context
+	// x2-x17: clobbered by macros
+	// x18: guest context
 
 	// Store the host regs
 	save_callee_saved_regs x1
 
-	// Preserve vcpu & host_ctxt for use at exit time
-	stp	x0, x1, [sp, #-16]!
+	// Store the host_ctxt for use at exit time
+	str	x1, [sp, #-16]!
 
-	add	x1, x0, #VCPU_CONTEXT
+	add	x18, x0, #VCPU_CONTEXT
 
-	// Prepare x0-x1 for later restore by pushing them onto the stack
-	ldp	x2, x3, [x1, #CPU_XREG_OFFSET(0)]
-	stp	x2, x3, [sp, #-16]!
+	// Restore guest regs x0-x17
+	ldp	x0, x1,   [x18, #CPU_XREG_OFFSET(0)]
+	ldp	x2, x3,   [x18, #CPU_XREG_OFFSET(2)]
+	ldp	x4, x5,   [x18, #CPU_XREG_OFFSET(4)]
+	ldp	x6, x7,   [x18, #CPU_XREG_OFFSET(6)]
+	ldp	x8, x9,   [x18, #CPU_XREG_OFFSET(8)]
+	ldp	x10, x11, [x18, #CPU_XREG_OFFSET(10)]
+	ldp	x12, x13, [x18, #CPU_XREG_OFFSET(12)]
+	ldp	x14, x15, [x18, #CPU_XREG_OFFSET(14)]
+	ldp	x16, x17, [x18, #CPU_XREG_OFFSET(16)]
 
-	// x2-x18
-	ldp	x2, x3,   [x1, #CPU_XREG_OFFSET(2)]
-	ldp	x4, x5,   [x1, #CPU_XREG_OFFSET(4)]
-	ldp	x6, x7,   [x1, #CPU_XREG_OFFSET(6)]
-	ldp	x8, x9,   [x1, #CPU_XREG_OFFSET(8)]
-	ldp	x10, x11, [x1, #CPU_XREG_OFFSET(10)]
-	ldp	x12, x13, [x1, #CPU_XREG_OFFSET(12)]
-	ldp	x14, x15, [x1, #CPU_XREG_OFFSET(14)]
-	ldp	x16, x17, [x1, #CPU_XREG_OFFSET(16)]
-	ldr	x18,      [x1, #CPU_XREG_OFFSET(18)]
-
-	// x19-x29, lr
-	restore_callee_saved_regs x1
-
-	// Last bits of the 64bit state
-	ldp	x0, x1, [sp], #16
+	// Restore guest regs x19-x29, lr
+	restore_callee_saved_regs x18
+
+	// Restore guest reg x18
+	ldr	x18,      [x18, #CPU_XREG_OFFSET(18)]
 
 	// Do not touch any register after this!
 	eret
 ENDPROC(__guest_enter)
 
 ENTRY(__guest_exit)
-	// x0: vcpu
-	// x1: return code
-	// x2-x3: free
-	// x4-x29,lr: vcpu regs
-	// vcpu x0-x3 on the stack
-
-	add	x2, x0, #VCPU_CONTEXT
-
-	stp	x4, x5,   [x2, #CPU_XREG_OFFSET(4)]
-	stp	x6, x7,   [x2, #CPU_XREG_OFFSET(6)]
-	stp	x8, x9,   [x2, #CPU_XREG_OFFSET(8)]
-	stp	x10, x11, [x2, #CPU_XREG_OFFSET(10)]
-	stp	x12, x13, [x2, #CPU_XREG_OFFSET(12)]
-	stp	x14, x15, [x2, #CPU_XREG_OFFSET(14)]
-	stp	x16, x17, [x2, #CPU_XREG_OFFSET(16)]
-	str	x18,      [x2, #CPU_XREG_OFFSET(18)]
-
-	ldp	x6, x7, [sp], #16	// x2, x3
-	ldp	x4, x5, [sp], #16	// x0, x1
-
-	stp	x4, x5, [x2, #CPU_XREG_OFFSET(0)]
-	stp	x6, x7, [x2, #CPU_XREG_OFFSET(2)]
+	// x0: return code
+	// x1: vcpu
+	// x2-x29,lr: vcpu regs
+	// vcpu x0-x1 on the stack
+
+	add	x1, x1, #VCPU_CONTEXT
+
+	// Store the guest regs x2 and x3
+	stp	x2, x3,   [x1, #CPU_XREG_OFFSET(2)]
+
+	// Retrieve the guest regs x0-x1 from the stack
+	ldp	x2, x3, [sp], #16	// x0, x1
+
+	// Store the guest regs x0-x1 and x4-x18
+	stp	x2, x3,   [x1, #CPU_XREG_OFFSET(0)]
+	stp	x4, x5,   [x1, #CPU_XREG_OFFSET(4)]
+	stp	x6, x7,   [x1, #CPU_XREG_OFFSET(6)]
+	stp	x8, x9,   [x1, #CPU_XREG_OFFSET(8)]
+	stp	x10, x11, [x1, #CPU_XREG_OFFSET(10)]
+	stp	x12, x13, [x1, #CPU_XREG_OFFSET(12)]
+	stp	x14, x15, [x1, #CPU_XREG_OFFSET(14)]
+	stp	x16, x17, [x1, #CPU_XREG_OFFSET(16)]
+	str	x18,      [x1, #CPU_XREG_OFFSET(18)]
+
+	// Store the guest regs x19-x29, lr
+	save_callee_saved_regs x1
 
-	save_callee_saved_regs x2
+	// Restore the host_ctxt from the stack
+	ldr	x2, [sp], #16
 
-	// Restore vcpu & host_ctxt from the stack
-	// (preserving return code in x1)
-	ldp	x0, x2, [sp], #16
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 
-	mov	x0, x1
 	ret
 ENDPROC(__guest_exit)
 
 ENTRY(__fpsimd_guest_restore)
+	stp	x2, x3, [sp, #-16]!
 	stp	x4, lr, [sp, #-16]!
 
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN

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

@@ -27,16 +27,6 @@
 	.text
 	.pushsection	.hyp.text, "ax"
 
-.macro	save_x0_to_x3
-	stp	x0, x1, [sp, #-16]!
-	stp	x2, x3, [sp, #-16]!
-.endm
-
-.macro	restore_x0_to_x3
-	ldp	x2, x3, [sp], #16
-	ldp	x0, x1, [sp], #16
-.endm
-
 .macro do_el2_call
 	/*
 	 * Shuffle the parameters before calling the function
@@ -79,23 +69,23 @@ ENTRY(__kvm_hyp_teardown)
 ENDPROC(__kvm_hyp_teardown)
 	
 el1_sync:				// Guest trapped into EL2
-	save_x0_to_x3
+	stp	x0, x1, [sp, #-16]!
 
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x1, esr_el2
 alternative_else
 	mrs	x1, esr_el1
 alternative_endif
-	lsr	x2, x1, #ESR_ELx_EC_SHIFT
+	lsr	x0, x1, #ESR_ELx_EC_SHIFT
 
-	cmp	x2, #ESR_ELx_EC_HVC64
+	cmp	x0, #ESR_ELx_EC_HVC64
 	b.ne	el1_trap
 
-	mrs	x3, vttbr_el2		// If vttbr is valid, the 64bit guest
-	cbnz	x3, el1_trap		// called HVC
+	mrs	x1, vttbr_el2		// If vttbr is valid, the 64bit guest
+	cbnz	x1, el1_trap		// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
-	restore_x0_to_x3
+	ldp	x0, x1, [sp], #16
 
 	cmp	x0, #HVC_GET_VECTORS
 	b.ne	1f
@@ -113,22 +103,21 @@ alternative_endif
 
 el1_trap:
 	/*
-	 * x1: ESR
-	 * x2: ESR_EC
+	 * x0: ESR_EC
 	 */
 
 	/* Guest accessed VFP/SIMD registers, save host, restore Guest */
-	cmp	x2, #ESR_ELx_EC_FP_ASIMD
+	cmp	x0, #ESR_ELx_EC_FP_ASIMD
 	b.eq	__fpsimd_guest_restore
 
-	mrs	x0, tpidr_el2
-	mov	x1, #ARM_EXCEPTION_TRAP
+	mrs	x1, tpidr_el2
+	mov	x0, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
 
 el1_irq:
-	save_x0_to_x3
-	mrs	x0, tpidr_el2
-	mov	x1, #ARM_EXCEPTION_IRQ
+	stp     x0, x1, [sp, #-16]!
+	mrs	x1, tpidr_el2
+	mov	x0, #ARM_EXCEPTION_IRQ
 	b	__guest_exit
 
 ENTRY(__hyp_do_panic)