[PATCH 3/3] x86/jump-labels: 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 also a minor cleanup for the jump-label code.

As a result the code size is slightly increased, but inlining decisions
are better:

 text     data     bss      dec     hex  filename
18163528 10226300 2957312 31347140 1de51c4  ./vmlinux before
18163608 10227348 2957312 31348268 1de562c  ./vmlinux after (+1128)

And functions such as intel_pstate_adjust_policy_max(),
kvm_cpu_accept_dm_intr(), kvm_register_readl() are inlined.

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: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Kate Stewart <kstewart@xxxxxxxxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Philippe Ombredanne <pombredanne@xxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/lkml/20181003213100.189959-11-namit@xxxxxxxxxx/T/#u
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/entry/calling.h          |  2 +-
 arch/x86/include/asm/jump_label.h | 72 ++++++++-----------------------
 arch/x86/kernel/macros.S          |  1 +
 3 files changed, 20 insertions(+), 55 deletions(-)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 352e70cd33e8..708b46a54578 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -338,7 +338,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro CALL_enter_from_user_mode
 #ifdef CONFIG_CONTEXT_TRACKING
 #ifdef HAVE_JUMP_LABEL
-	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+	STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
 #endif
 	call enter_from_user_mode
 .Lafter_call_\@:
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 21efc9d07ed9..a5fb34fe56a4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -2,19 +2,6 @@
 #ifndef _ASM_X86_JUMP_LABEL_H
 #define _ASM_X86_JUMP_LABEL_H
 
-#ifndef HAVE_JUMP_LABEL
-/*
- * For better or for worse, if jump labels (the gcc extension) are missing,
- * then the entire static branch patching infrastructure is compiled out.
- * If that happens, the code in here will malfunction.  Raise a compiler
- * error instead.
- *
- * In theory, jump labels and the static branch patching infrastructure
- * could be decoupled to fix this.
- */
-#error asm/jump_label.h included on a non-jump-label kernel
-#endif
-
 #define JUMP_LABEL_NOP_SIZE 5
 
 #ifdef CONFIG_X86_64
@@ -33,15 +20,9 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
-		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
-		".pushsection __jump_table,  \"aw\" \n\t"
-		_ASM_ALIGN "\n\t"
-		".long 1b - ., %l[l_yes] - . \n\t"
-		_ASM_PTR "%c0 + %c1 - .\n\t"
-		".popsection \n\t"
-		: :  "i" (key), "i" (branch) : : l_yes);
-
+	asm_volatile_goto("STATIC_BRANCH_NOP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+			  "branch=\"%c1\""
+			: :  "i" (key), "i" (branch) : : l_yes);
 	return false;
 l_yes:
 	return true;
@@ -49,14 +30,8 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
-		".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
-		"2:\n\t"
-		".pushsection __jump_table,  \"aw\" \n\t"
-		_ASM_ALIGN "\n\t"
-		".long 1b - ., %l[l_yes] - . \n\t"
-		_ASM_PTR "%c0 + %c1 - .\n\t"
-		".popsection \n\t"
+	asm_volatile_goto("STATIC_BRANCH_JMP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+			  "branch=\"%c1\""
 		: :  "i" (key), "i" (branch) : : l_yes);
 
 	return false;
@@ -66,37 +41,26 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool
 
 #else	/* __ASSEMBLY__ */
 
-.macro STATIC_JUMP_IF_TRUE target, key, def
-.Lstatic_jump_\@:
-	.if \def
-	/* Equivalent to "jmp.d32 \target" */
-	.byte		0xe9
-	.long		\target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
-	.else
-	.byte		STATIC_KEY_INIT_NOP
-	.endif
+.macro STATIC_BRANCH_NOP l_yes:req key:req branch:req
+.Lstatic_branch_nop_\@:
+	.byte STATIC_KEY_INIT_NOP
+.Lstatic_branch_no_after_\@:
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
-	.long		.Lstatic_jump_\@ - ., \target - .
-	_ASM_PTR	\key - .
+	.long		.Lstatic_branch_nop_\@ - ., \l_yes - .
+	_ASM_PTR        \key + \branch - .
 	.popsection
 .endm
 
-.macro STATIC_JUMP_IF_FALSE target, key, def
-.Lstatic_jump_\@:
-	.if \def
-	.byte		STATIC_KEY_INIT_NOP
-	.else
-	/* Equivalent to "jmp.d32 \target" */
-	.byte		0xe9
-	.long		\target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
-	.endif
+.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req
+.Lstatic_branch_jmp_\@:
+	.byte 0xe9
+	.long \l_yes - .Lstatic_branch_jmp_after_\@
+.Lstatic_branch_jmp_after_\@:
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
-	.long		.Lstatic_jump_\@ - ., \target - .
-	_ASM_PTR	\key + 1 - .
+	.long		.Lstatic_branch_jmp_\@ - ., \l_yes - .
+	_ASM_PTR	\key + \branch - .
 	.popsection
 .endm
 
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
index bf8b9c93e255..161c95059044 100644
--- a/arch/x86/kernel/macros.S
+++ b/arch/x86/kernel/macros.S
@@ -13,3 +13,4 @@
 #include <asm/paravirt.h>
 #include <asm/asm.h>
 #include <asm/cpufeature.h>
+#include <asm/jump_label.h>
-- 
2.17.1