[PATCH 2/3] x86/cpufeature: Macrofy inline assembly code to work around GCC inlining bugs

[Nadav Amit]

As described in:

77b0bf55bc67: ("kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs")

GCC's inlining heuristics are broken with common asm() patterns used in
kernel code, resulting in the effective disabling of inlining.

The workaround is to set an assembly macro and call it from the inline
assembly block - which is pretty pointless indirection in the static_cpu_has()
case, but is worth it to improve overall inlining quality.

The patch slightly increases the kernel size:

 text     data     bss      dec     hex  filename
18162879 10226256 2957312 31346447 1de4f0f  ./vmlinux before
18163528 10226300 2957312 31347140 1de51c4  ./vmlinux after (+693)

And enables the inlining of function such as free_ldt_pgtables().

Tested-by: Kees Cook <keescook@xxxxxxxxxxxx>
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/lkml/20181003213100.189959-10-namit@xxxxxxxxxx/T/#u
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/cpufeature.h | 82 ++++++++++++++++++-------------
 arch/x86/kernel/macros.S          |  1 +
 2 files changed, 48 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aced6c9290d6..7d442722ef24 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -2,10 +2,10 @@
 #ifndef _ASM_X86_CPUFEATURE_H
 #define _ASM_X86_CPUFEATURE_H
 
-#include <asm/processor.h>
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
 
+#include <asm/processor.h>
 #include <asm/asm.h>
 #include <linux/bitops.h>
 
@@ -161,37 +161,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
-		 "2:\n"
-		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			 "((5f-4f) - (2b-1b)),0x90\n"
-		 "3:\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 4f - .\n"		/* repl offset */
-		 " .word %P[always]\n"		/* always replace */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 5f - 4f\n"		/* repl len */
-		 " .byte 3b - 2b\n"		/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_replacement,\"ax\"\n"
-		 "4: jmp %l[t_no]\n"
-		 "5:\n"
-		 ".previous\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 0\n"			/* no replacement */
-		 " .word %P[feature]\n"		/* feature bit */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 0\n"			/* repl len */
-		 " .byte 0\n"			/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_aux,\"ax\"\n"
-		 "6:\n"
-		 " testb %[bitnum],%[cap_byte]\n"
-		 " jnz %l[t_yes]\n"
-		 " jmp %l[t_no]\n"
-		 ".previous\n"
+	asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] "
+			  "cap_byte=\"%[cap_byte]\" "
+			  "feature=%P[feature] t_yes=%l[t_yes] "
+			  "t_no=%l[t_no] always=%P[always]"
 		 : : [feature]  "i" (bit),
 		     [always]   "i" (X86_FEATURE_ALWAYS),
 		     [bitnum]   "i" (1 << (bit & 7)),
@@ -226,5 +199,44 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 #define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
 					boot_cpu_data.x86_model
 
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req
+1:
+	jmp 6f
+2:
+	.skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90
+3:
+	.section .altinstructions,"a"
+	.long 1b - .		/* src offset */
+	.long 4f - .		/* repl offset */
+	.word \always		/* always replace */
+	.byte 3b - 1b		/* src len */
+	.byte 5f - 4f		/* repl len */
+	.byte 3b - 2b		/* pad len */
+	.previous
+	.section .altinstr_replacement,"ax"
+4:
+	jmp \t_no
+5:
+	.previous
+	.section .altinstructions,"a"
+	.long 1b - .		/* src offset */
+	.long 0			/* no replacement */
+	.word \feature		/* feature bit */
+	.byte 3b - 1b		/* src len */
+	.byte 0			/* repl len */
+	.byte 0			/* pad len */
+	.previous
+	.section .altinstr_aux,"ax"
+6:
+	testb \bitnum,\cap_byte
+	jnz \t_yes
+	jmp \t_no
+	.previous
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
index 7baa40d5bf16..bf8b9c93e255 100644
--- a/arch/x86/kernel/macros.S
+++ b/arch/x86/kernel/macros.S
@@ -12,3 +12,4 @@
 #include <asm/bug.h>
 #include <asm/paravirt.h>
 #include <asm/asm.h>
+#include <asm/cpufeature.h>
-- 
2.17.1