x86/objtool: Use asm macros to work around GCC inlining bugs

anadav · Ingo Molnar · commit c06c4d809051 · 2018-10-04T11:24:58.000+02:00
As described in: 77b0bf5: ("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. In the case of objtool the resulting borkage can be significant, since all the annotations of objtool are discarded during linkage and never inlined, yet GCC bogusly considers most functions affected by objtool annotations as 'too large'. The workaround is to set an assembly macro and call it from the inline assembly block. As a result GCC considers the inline assembly block as a single instruction. (Which it isn't, but that's the best we can get.) This increases the kernel size slightly: text data bss dec hex filename 18140829 10224724 2957312 31322865 1ddf2f1 ./vmlinux before 18140970 10225412 2957312 31323694 1ddf62e ./vmlinux after (+829) The number of static text symbols (i.e. non-inlined functions) is reduced: Before: 40321 After: 40302 (-19) [ mingo: Rewrote the changelog. ] Tested-by: Kees Cook <keescook@chromium.org> Signed-off-by: Nadav Amit <namit@vmware.com> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Christopher Li <sparse@chrisli.org> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-sparse@vger.kernel.org Link: http://lkml.kernel.org/r/20181003213100.189959-4-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
@@ -5,3 +5,5 @@
  * commonly used. The macros are precompiled into assmebly file which is later
  * assembled together with each compiled file.
  */
+
+#include <linux/compiler.h>
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
@@ -99,22 +99,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * unique, to convince GCC not to merge duplicate inline asm statements.
  */
 #define annotate_reachable() ({						\
-	asm volatile("%c0:\n\t"						\
-		     ".pushsection .discard.reachable\n\t"		\
-		     ".long %c0b - .\n\t"				\
-		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+	asm volatile("ANNOTATE_REACHABLE counter=%c0"			\
+		     : : "i" (__COUNTER__));				\
 })
 #define annotate_unreachable() ({					\
-	asm volatile("%c0:\n\t"						\
-		     ".pushsection .discard.unreachable\n\t"		\
-		     ".long %c0b - .\n\t"				\
-		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+	asm volatile("ANNOTATE_UNREACHABLE counter=%c0"			\
+		     : : "i" (__COUNTER__));				\
 })
-#define ASM_UNREACHABLE							\
-	"999:\n\t"							\
-	".pushsection .discard.unreachable\n\t"				\
-	".long 999b - .\n\t"						\
-	".popsection\n\t"
 #else
 #define annotate_reachable()
 #define annotate_unreachable()
@@ -299,6 +290,45 @@ static inline void *offset_to_ptr(const int *off)
 	return (void *)((unsigned long)off + *off);
 }
 
+#else /* __ASSEMBLY__ */
+
+#ifdef __KERNEL__
+#ifndef LINKER_SCRIPT
+
+#ifdef CONFIG_STACK_VALIDATION
+.macro ANNOTATE_UNREACHABLE counter:req
+\counter:
+	.pushsection .discard.unreachable
+	.long \counter\()b -.
+	.popsection
+.endm
+
+.macro ANNOTATE_REACHABLE counter:req
+\counter:
+	.pushsection .discard.reachable
+	.long \counter\()b -.
+	.popsection
+.endm
+
+.macro ASM_UNREACHABLE
+999:
+	.pushsection .discard.unreachable
+	.long 999b - .
+	.popsection
+.endm
+#else /* CONFIG_STACK_VALIDATION */
+.macro ANNOTATE_UNREACHABLE counter:req
+.endm
+
+.macro ANNOTATE_REACHABLE counter:req
+.endm
+
+.macro ASM_UNREACHABLE
+.endm
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* LINKER_SCRIPT */
+#endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
 #ifndef __optimize
