setjmp: optimize longjmp prologues

Use a branchless sequence that is one byte shorter on 64-bit, same size
on 32-bit. Thanks to Pete Cawley for suggesting this variant.

src/setjmp/i386/longjmp.s

@@ -6,10 +6,8 @@ _longjmp:
 longjmp:
 	mov  4(%esp),%edx
 	mov  8(%esp),%eax
-	test    %eax,%eax
-	jnz 1f
-	inc     %eax
-1:
+	cmp       $1,%eax
+	adc       $0, %al
 	mov   (%edx),%ebx
 	mov  4(%edx),%esi
 	mov  8(%edx),%edi

src/setjmp/x32/longjmp.s

@@ -5,11 +5,9 @@
 .type longjmp,@function
 _longjmp:
 longjmp:
-	mov %esi,%eax           /* val will be longjmp return */
-	test %esi,%esi
-	jnz 1f
-	inc %eax                /* if val==0, val=1 per longjmp semantics */
-1:
+	xor %eax,%eax
+	cmp $1,%esi             /* CF = val ? 0 : 1 */
+	adc %esi,%eax           /* eax = val + !val */
 	mov (%rdi),%rbx         /* rdi is the jmp_buf, restore regs from it */
 	mov 8(%rdi),%rbp
 	mov 16(%rdi),%r12

src/setjmp/x86_64/longjmp.s

@@ -5,11 +5,9 @@
 .type longjmp,@function
 _longjmp:
 longjmp:
-	mov %esi,%eax           /* val will be longjmp return */
-	test %esi,%esi
-	jnz 1f
-	inc %eax                /* if val==0, val=1 per longjmp semantics */
-1:
+	xor %eax,%eax
+	cmp $1,%esi             /* CF = val ? 0 : 1 */
+	adc %esi,%eax           /* eax = val + !val */
 	mov (%rdi),%rbx         /* rdi is the jmp_buf, restore regs from it */
 	mov 8(%rdi),%rbp
 	mov 16(%rdi),%r12