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 <[email protected]>
[ Changed it to do TESTB, as hpa suggested. ]
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Young <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Kristen Carlson Accardi <[email protected]>
Cc: Laura Abbott <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra (Intel) <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Prarit Bhargava <[email protected]>
Cc: Ross Zwisler <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

2 files changed, 12 insertions, 13 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 9048c1bbc519..9fba7a5dd24a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/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)
-			 : : t_dynamic, t_no);
+			 ".section .altinstr_aux,\"ax\"\n"
+			 "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)					\
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ee499817f3f5..079d83fc6488 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/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)