Merge branches 'x86-build-for-linus', 'x86-cleanups-for-linus' and 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 build/cleanup/debug updates from Ingo Molnar:
 "Robustify the build process with a quirk to avoid GCC reordering
  related bugs.

  Two code cleanups.

  Simplify entry_64.S CFI annotations, by Jan Beulich"

* 'x86-build-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, build: Change code16gcc.h from a C header to an assembly header

* 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Simplify __HAVE_ARCH_CMPXCHG tests
  x86/tsc: Get rid of custom DIV_ROUND() macro

* 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/debug: Drop several unnecessary CFI annotations

arch/x86/Makefile

@@ -15,12 +15,9 @@ endif
 # that way we can complain to the user if the CPU is insufficient.
 #
 # The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
-# older versions of GCC, we need to play evil and unreliable tricks to
-# attempt to ensure that our asm(".code16gcc") is first in the asm
-# output.
-CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \
-		    $(call cc-option, -fno-toplevel-reorder,\
-		      $(call cc-option, -fno-unit-at-a-time))
+# older versions of GCC, include an *assembly* header to make sure that
+# gcc doesn't play any games behind our back.
+CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
 M16_CFLAGS	 := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
 
 REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -D__KERNEL__ \

arch/x86/boot/code16gcc.h

@@ -1,15 +1,11 @@
-/*
- * code16gcc.h
- *
- * This file is -include'd when compiling 16-bit C code.
- * Note: this asm() needs to be emitted before gcc emits any code.
- * Depending on gcc version, this requires -fno-unit-at-a-time or
- * -fno-toplevel-reorder.
- *
- * Hopefully gcc will eventually have a real -m16 option so we can
- * drop this hack long term.
- */
+#
+# code16gcc.h
+#
+# This file is added to the assembler via -Wa when compiling 16-bit C code.
+# This is done this way instead via asm() to make sure gcc does not reorder
+# things around us.
+#
+# gcc 4.9+ has a real -m16 option so we can drop this hack long term.
+#
 
-#ifndef __ASSEMBLY__
-asm(".code16gcc");
-#endif
+	.code16gcc

arch/x86/include/asm/cmpxchg.h

@@ -4,6 +4,8 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
+#define __HAVE_ARCH_CMPXCHG 1
+
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
@@ -143,7 +145,6 @@ extern void __add_wrong_size(void)
 # include <asm/cmpxchg_64.h>
 #endif
 
-#ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
 	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
@@ -152,7 +153,6 @@ extern void __add_wrong_size(void)
 
 #define cmpxchg_local(ptr, old, new)					\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
-#endif
 
 /*
  * xadd() adds "inc" to "*ptr" and atomically returns the previous

arch/x86/include/asm/cmpxchg_32.h

@@ -34,8 +34,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 		     : "memory");
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #ifdef CONFIG_X86_CMPXCHG64
 #define cmpxchg64(ptr, o, n)						\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \

arch/x86/include/asm/cmpxchg_64.h

@@ -6,8 +6,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	*ptr = val;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg64(ptr, o, n)						\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\

arch/x86/include/asm/mc146818rtc.h

@@ -13,7 +13,7 @@
 #define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
 #endif
 
-#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG)
+#if defined(CONFIG_X86_32)
 /*
  * This lock provides nmi access to the CMOS/RTC registers.  It has some
  * special properties.  It is owned by a CPU and stores the index register

arch/x86/include/asm/mutex_32.h

@@ -100,23 +100,11 @@ do {								\
 static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
+	/* cmpxchg because it never induces a false contention state. */
 	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
+
 	return 0;
-#else
-	return fail_fn(count);
-#endif
 }
 
 #endif /* _ASM_X86_MUTEX_32_H */

arch/x86/kernel/acpi/boot.c

@@ -74,10 +74,6 @@ int acpi_fix_pin2_polarity __initdata;
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #endif
 
-#ifndef __HAVE_ARCH_CMPXCHG
-#warning ACPI uses CMPXCHG, i486 and later hardware
-#endif
-
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */

arch/x86/kernel/entry_64.S

@@ -207,7 +207,6 @@ ENDPROC(native_usergs_sysret64)
  */
 	.macro XCPT_FRAME start=1 offset=0
 	INTR_FRAME \start, RIP+\offset-ORIG_RAX
-	/*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/
 	.endm
 
 /*
@@ -287,21 +286,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_paranoid)
 	XCPT_FRAME 1 RDI+8
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
 	movq_cfi rdx, RDX+8
 	movq_cfi rcx, RCX+8
 	movq_cfi rax, RAX+8
-	movq_cfi r8, R8+8
-	movq_cfi r9, R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %r8, R8+8(%rsp)
+	movq %r9, R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	movl $1,%ebx
 	movl $MSR_GS_BASE,%ecx
 	rdmsr
@@ -1387,21 +1386,21 @@ ENTRY(error_entry)
 	CFI_ADJUST_CFA_OFFSET 15*8
 	/* oldrax contains error code */
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
-	movq_cfi rdx, RDX+8
-	movq_cfi rcx, RCX+8
-	movq_cfi rax, RAX+8
-	movq_cfi  r8,  R8+8
-	movq_cfi  r9,  R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
+	movq %rdx, RDX+8(%rsp)
+	movq %rcx, RCX+8(%rsp)
+	movq %rax, RAX+8(%rsp)
+	movq  %r8,  R8+8(%rsp)
+	movq  %r9,  R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	xorl %ebx,%ebx
 	testl $3,CS+8(%rsp)
 	je error_kernelspace
@@ -1419,6 +1418,7 @@ error_sti:
  * compat mode. Check for these here too.
  */
 error_kernelspace:
+	CFI_REL_OFFSET rcx, RCX+8
 	incl %ebx
 	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)

arch/x86/kernel/tsc.c

@@ -234,9 +234,6 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-/* XXX surely we already have this someplace in the kernel?! */
-#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d))
-
 static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
 	unsigned long long tsc_now, ns_now;
@@ -259,7 +256,9 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 	 * time function is continuous; see the comment near struct
 	 * cyc2ns_data.
 	 */
-	data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz);
+	data->cyc2ns_mul =
+		DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
+				  cpu_khz);
 	data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
 	data->cyc2ns_offset = ns_now -
 		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);