i386,amd64: Explicitly set ECX=0 in do_cpuid() to be future-proof

In principle, do_cpuid() should only be used for CPUID leaves without
sub-leaves.  Even accessing sub-leaf zero (ECX=0), one must use
cpuid_count(ax, 0) rather than cpuid(ax).

However, one might assume do_cpuid(ax) is equivalent to
cpuid_count(ax, 0), but the old do_cpuid() did not initialize ECX before
executing the CPUID instruction.  If ECX contained a non-zero value, the
instruction could return unexpected results, potentially leading to
subtle and hard-to-debug issues, especially in ported code.

To be future-proof and to help port code, adjust do_cpuid(ax) to be
cpuid_count(ax, 0) to explicitly set ECX=0.

It's believed that this change does not fix any real bugs in FreeBSD.

See also the DragonFly commit:
https://github.com/DragonFlyBSD/DragonFlyBSD/commit/0087a1d163488a57787a9a6431dd94070b1988d4

Signed-off-by: Aaron LI <aly@aaronly.me>
Reviewed by: kib
Pull Request: https://github.com/freebsd/freebsd-src/pull/2027

sys/amd64/include/cpufunc.h

@@ -99,14 +99,6 @@ disable_intr(void)
 	__asm __volatile("cli" : : : "memory");
 }
 
-static __inline void
-do_cpuid(u_int ax, u_int *p)
-{
-	__asm __volatile("cpuid"
-	    : "=a" (p[0]), "=b" (p[1]), "=c" (p[2]), "=d" (p[3])
-	    :  "0" (ax));
-}
-
 static __inline void
 cpuid_count(u_int ax, u_int cx, u_int *p)
 {
@@ -115,6 +107,12 @@ cpuid_count(u_int ax, u_int cx, u_int *p)
 	    :  "0" (ax), "c" (cx));
 }
 
+static __inline void
+do_cpuid(u_int ax, u_int *p)
+{
+	cpuid_count(ax, 0, p);
+}
+
 static __inline void
 enable_intr(void)
 {

sys/i386/include/cpufunc.h

@@ -91,14 +91,6 @@ disable_intr(void)
 }
 
 #ifdef _KERNEL
-static __inline void
-do_cpuid(u_int ax, u_int *p)
-{
-	__asm __volatile("cpuid"
-	    : "=a" (p[0]), "=b" (p[1]), "=c" (p[2]), "=d" (p[3])
-	    :  "0" (ax));
-}
-
 static __inline void
 cpuid_count(u_int ax, u_int cx, u_int *p)
 {
@@ -107,18 +99,6 @@ cpuid_count(u_int ax, u_int cx, u_int *p)
 	    :  "0" (ax), "c" (cx));
 }
 #else
-static __inline void
-do_cpuid(u_int ax, u_int *p)
-{
-	__asm __volatile(
-	    "pushl\t%%ebx\n\t"
-	    "cpuid\n\t"
-	    "movl\t%%ebx,%1\n\t"
-	    "popl\t%%ebx"
-	    : "=a" (p[0]), "=DS" (p[1]), "=c" (p[2]), "=d" (p[3])
-	    :  "0" (ax));
-}
-
 static __inline void
 cpuid_count(u_int ax, u_int cx, u_int *p)
 {
@@ -132,6 +112,12 @@ cpuid_count(u_int ax, u_int cx, u_int *p)
 }
 #endif
 
+static __inline void
+do_cpuid(u_int ax, u_int *p)
+{
+	cpuid_count(ax, 0, p);
+}
+
 static __inline void
 enable_intr(void)
 {