[PATCH v6 3/9] x86: refcount: prevent gcc distortions

[Nadav Amit]

GCC considers the number of statements in inlined assembly blocks,
according to new-lines and semicolons, as an indication to the cost of
the block in time and space. This data is distorted by the kernel code,
which puts information in alternative sections. As a result, the
compiler may perform incorrect inlining and branch optimizations.

The solution is to set an assembly macro and call it from the inlined
assembly block. As a result GCC considers the inline assembly block as
a single instruction.

This patch allows to inline functions such as __get_seccomp_filter().
Interestingly, this allows more aggressive inlining while reducing the
kernel size.

   text	   data	    bss	    dec	    hex	filename
18140970 10225412 2957312 31323694 1ddf62e ./vmlinux before
18140140 10225284 2957312 31322736 1ddf270 ./vmlinux after (-958)

Static text symbols:
Before:	40302
After:	40286	(-16)

Functions such as kref_get(), free_user(), fuse_file_get() now get
inlined.

Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Jan Beulich <JBeulich@xxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
---
 arch/x86/include/asm/refcount.h | 74 ++++++++++++++++++++-------------
 arch/x86/kernel/macros.S        |  1 +
 2 files changed, 46 insertions(+), 29 deletions(-)

diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4cf11d88d3b3..6b2809a4d8e9 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -4,6 +4,41 @@
  * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
  * PaX/grsecurity.
  */
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/bug.h>
+
+.macro REFCOUNT_EXCEPTION counter:req
+	.pushsection .text..refcount
+111:	lea \counter, %_ASM_CX
+112:	ud2
+	ASM_UNREACHABLE
+	.popsection
+113:	_ASM_EXTABLE_REFCOUNT(112b, 113b)
+.endm
+
+/* Trigger refcount exception if refcount result is negative. */
+.macro REFCOUNT_CHECK_LT_ZERO counter:req
+	js 111f
+	REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+.macro REFCOUNT_CHECK_LE_ZERO counter:req
+	jz 111f
+	REFCOUNT_CHECK_LT_ZERO counter="\counter"
+.endm
+
+/* Trigger refcount exception unconditionally. */
+.macro REFCOUNT_ERROR counter:req
+	jmp 111f
+	REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+#else /* __ASSEMBLY__ */
+
 #include <linux/refcount.h>
 
 /*
@@ -14,34 +49,11 @@
  * central refcount exception. The fixup address for the exception points
  * back to the regular execution flow in .text.
  */
-#define _REFCOUNT_EXCEPTION				\
-	".pushsection .text..refcount\n"		\
-	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
-	"112:\t" ASM_UD2 "\n"				\
-	ASM_UNREACHABLE					\
-	".popsection\n"					\
-	"113:\n"					\
-	_ASM_EXTABLE_REFCOUNT(112b, 113b)
-
-/* Trigger refcount exception if refcount result is negative. */
-#define REFCOUNT_CHECK_LT_ZERO				\
-	"js 111f\n\t"					\
-	_REFCOUNT_EXCEPTION
-
-/* Trigger refcount exception if refcount result is zero or negative. */
-#define REFCOUNT_CHECK_LE_ZERO				\
-	"jz 111f\n\t"					\
-	REFCOUNT_CHECK_LT_ZERO
-
-/* Trigger refcount exception unconditionally. */
-#define REFCOUNT_ERROR					\
-	"jmp 111f\n\t"					\
-	_REFCOUNT_EXCEPTION
 
 static __always_inline void refcount_add(unsigned int i, refcount_t *r)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
-		REFCOUNT_CHECK_LT_ZERO
+		"REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
 		: [counter] "+m" (r->refs.counter)
 		: "ir" (i)
 		: "cc", "cx");
@@ -50,7 +62,7 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r)
 static __always_inline void refcount_inc(refcount_t *r)
 {
 	asm volatile(LOCK_PREFIX "incl %0\n\t"
-		REFCOUNT_CHECK_LT_ZERO
+		"REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
 		: [counter] "+m" (r->refs.counter)
 		: : "cc", "cx");
 }
@@ -58,7 +70,7 @@ static __always_inline void refcount_inc(refcount_t *r)
 static __always_inline void refcount_dec(refcount_t *r)
 {
 	asm volatile(LOCK_PREFIX "decl %0\n\t"
-		REFCOUNT_CHECK_LE_ZERO
+		"REFCOUNT_CHECK_LE_ZERO counter=\"%[counter]\""
 		: [counter] "+m" (r->refs.counter)
 		: : "cc", "cx");
 }
@@ -66,13 +78,15 @@ static __always_inline void refcount_dec(refcount_t *r)
 static __always_inline __must_check
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
-	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
+	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
+				  "REFCOUNT_CHECK_LT_ZERO counter=\"%0\"",
 				  r->refs.counter, "er", i, "%0", e, "cx");
 }
 
 static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
-	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
+	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
+				 "REFCOUNT_CHECK_LT_ZERO counter=\"%0\"",
 				 r->refs.counter, "%0", e, "cx");
 }
 
@@ -90,7 +104,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 
 		/* Did we try to increment from/to an undesirable state? */
 		if (unlikely(c < 0 || c == INT_MAX || result < c)) {
-			asm volatile(REFCOUNT_ERROR
+			asm volatile("REFCOUNT_ERROR counter=\"%[counter]\""
 				     : : [counter] "m" (r->refs.counter)
 				     : "cc", "cx");
 			break;
@@ -106,4 +120,6 @@ static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
 	return refcount_add_not_zero(1, r);
 }
 
+#endif /* __ASSEMBLY__ */
+
 #endif
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
index cee28c3246dc..f1fe1d570365 100644
--- a/arch/x86/kernel/macros.S
+++ b/arch/x86/kernel/macros.S
@@ -7,3 +7,4 @@
  */
 
 #include <linux/compiler.h>
+#include <asm/refcount.h>
-- 
2.17.1