improve mips syscall asm constraints to use immediates, if possible

by using the "ir" constraint (immediate or register) and the carefully
constructed instruction addu $2,$0,%2 which can take either an
immediate or a register for %2, the new inline asm admits maximal
optimization with no register spillage to the stack when the compiler
successfully performs constant propagration, but still works by
allocating a register when the syscall number cannot be recognized as
a constant. in the case of syscalls with 0-3 arguments it barely
matters, but for 4-argument syscalls, using an immediate for the
syscall number avoids creating a stack frame for the syscall wrapper
function.

arch/mips/syscall_arch.h

@@ -10,8 +10,8 @@
 #define __asm_syscall(...) do { \
 	register long r2 __asm__("$2"); \
 	__asm__ __volatile__ ( \
-	"move $2,$7 ; syscall" \
-	: "=&r"(r2), "=r"(r7) : __VA_ARGS__ \
+	"addu $2,$0,%2 ; syscall" \
+	: "=&r"(r2), "=r"(r7) : "ir"(n), __VA_ARGS__, "r"(r2) \
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", \
 	  "$14", "$15", "$24", "$25", "hi", "lo", "memory"); \
 	return r7 ? -r2 : r2; \
@@ -19,32 +19,41 @@
 
 static inline long __syscall0(long n)
 {
-	register long r7 __asm__("$7") = n;
-	__asm_syscall("r"(r7));
+	register long r7 __asm__("$7");
+	__asm_syscall("i"(0));
 }
 
 static inline long __syscall1(long n, long a)
 {
-	register long r7 __asm__("$7") = n;
 	register long r4 __asm__("$4") = a;
-	__asm_syscall("r"(r7), "r"(r4));
+	register long r7 __asm__("$7");
+	__asm_syscall("r"(r4));
 }
 
 static inline long __syscall2(long n, long a, long b)
 {
-	register long r7 __asm__("$7") = n;
 	register long r4 __asm__("$4") = a;
 	register long r5 __asm__("$5") = b;
-	__asm_syscall("r"(r7), "r"(r4), "r"(r5));
+	register long r7 __asm__("$7");
+	__asm_syscall("r"(r4), "r"(r5));
 }
 
 static inline long __syscall3(long n, long a, long b, long c)
 {
-	register long r7 __asm__("$7") = n;
 	register long r4 __asm__("$4") = a;
 	register long r5 __asm__("$5") = b;
 	register long r6 __asm__("$6") = c;
-	__asm_syscall("r"(r7), "r"(r4), "r"(r5), "r"(r6));
+	register long r7 __asm__("$7");
+	__asm_syscall("r"(r4), "r"(r5), "r"(r6));
+}
+
+static inline long __syscall4(long n, long a, long b, long c, long d)
+{
+	register long r4 __asm__("$4") = a;
+	register long r5 __asm__("$5") = b;
+	register long r6 __asm__("$6") = c;
+	register long r7 __asm__("$7") = d;
+	__asm_syscall("r"(r4), "r"(r5), "r"(r6), "r"(r7));
 }
 
 #else
@@ -69,13 +78,13 @@ static inline long __syscall3(long n, long a, long b, long c)
 	return (__syscall)(n, a, b, c);
 }
 
-#endif
-
 static inline long __syscall4(long n, long a, long b, long c, long d)
 {
 	return (__syscall)(n, a, b, c, d);
 }
 
+#endif
+
 static inline long __syscall5(long n, long a, long b, long c, long d, long e)
 {
 	return (__syscall)(n, a, b, c, d, e);