x86/alternatives: Discard dynamic check after init

Move the code to do the dynamic check to the altinstr_aux
section so that it is discarded after alternatives have run and
a static branch has been chosen.

This way we're changing the dynamic branch from C code to
assembly, which makes it *substantially* smaller while avoiding
a completely unnecessary call to an out of line function.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
[ Changed it to do TESTB, as hpa suggested. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Young <dyoung@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kristen Carlson Accardi <kristen@linux.intel.com>
Cc: Laura Abbott <labbott@fedoraproject.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1452972124-7380-1-git-send-email-brgerst@gmail.com
Link: http://lkml.kernel.org/r/20160127084525.GC30712@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/cpufeature.h

@@ -130,8 +130,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  */
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
-extern bool __static_cpu_has(u16 bit);
-
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These will statically patch the target code for additional
@@ -139,7 +137,7 @@ extern bool __static_cpu_has(u16 bit);
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
+		asm_volatile_goto("1: jmp 6f\n"
 			 "2:\n"
 			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			         "((5f-4f) - (2b-1b)),0x90\n"
@@ -164,13 +162,20 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 			 " .byte 0\n"			/* repl len */
 			 " .byte 0\n"			/* pad len */
 			 ".previous\n"
-			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
+			 ".section .altinstr_aux,\"ax\"\n"
-			 : : t_dynamic, t_no);
+			 "6:\n"
+			 " testb %[bitnum],%[cap_byte]\n"
+			 " jnz %l[t_yes]\n"
+			 " jmp %l[t_no]\n"
+			 ".previous\n"
+			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS),
+			     [bitnum] "i" (1 << (bit & 7)),
+			     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+			 : : t_yes, t_no);
+	t_yes:
 		return true;
 	t_no:
 		return false;
-	t_dynamic:
-		return __static_cpu_has(bit);
 }
 
 #define static_cpu_has(bit)					\

arch/x86/kernel/cpu/common.c

@@ -1475,12 +1475,6 @@ void cpu_init(void)
 }
 #endif
 
-inline bool __static_cpu_has(u16 bit)
-{
-	return boot_cpu_has(bit);
-}
-EXPORT_SYMBOL_GPL(__static_cpu_has);
-
 static void bsp_resume(void)
 {
 	if (this_cpu->c_bsp_resume)