crypto: curve25519-x86_64: solve register constraints with reserved registers

The register constraints for the inline assembly in fsqr() and fsqr2()
are pretty tight on what the compiler may assign to the remaining three
register variables. The clobber list only allows the following to be
used: RDI, RSI, RBP and R12. With RAP reserving R12 and a kernel having
CONFIG_FRAME_POINTER=y, claiming RBP, there are only two registers left
so the compiler rightfully complains about impossible constraints.

Provide alternatives that'll allow a memory reference for 'out' to solve
the allocation constraint dilemma for this configuration.

Also make 'out' an input-only operand as it is only used as such. This
not only allows gcc to optimize its usage further, but also works around
older gcc versions, apparently failing to handle multiple alternatives
correctly, as in failing to initialize the 'out' operand with its input
value.

Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

Author: minipli-oss

src/crypto/zinc/curve25519/curve25519-x86_64.c

@@ -581,8 +581,8 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 		"  cmovc %%rdx, %%rax;"
 		"  add %%rax, %%r8;"
 		"  movq %%r8, 0(%0);"
-	: "+&r" (tmp), "+&r" (f), "+&r" (out)
-	:
+	: "+&r,&r" (tmp), "+&r,&r" (f)
+	: "r,m" (out)
 	: "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc"
 	);
 }
@@ -743,8 +743,8 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		"  cmovc %%rdx, %%rax;"
 		"  add %%rax, %%r8;"
 		"  movq %%r8, 32(%0);"
-	: "+&r" (tmp), "+&r" (f), "+&r" (out)
-	:
+	: "+&r,&r" (tmp), "+&r,&r" (f)
+	: "r,m" (out)
 	: "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc"
 	);
 }