Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "The changes in this cycle were:

   - Speed up the x86 __preempt_schedule() implementation
   - Fix/improve low level asm code debug info annotations"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Unwind-annotate thunk_32.S
  x86: Improve cmpxchg8b_emu.S
  x86: Improve cmpxchg16b_emu.S
  x86/lib/Makefile: Remove the unnecessary "+= thunk_64.o"
  x86: Speed up ___preempt_schedule*() by using THUNK helpers

5 files changed, 61 insertions, 41 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 7ef9a30e7dac..db92793b7e23 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -38,7 +38,7 @@ endif
 else
         obj-y += iomap_copy_64.o
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
-        lib-y += thunk_64.o clear_page_64.o copy_page_64.o
+        lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o copy_user_nocache_64.o
 	lib-y += cmpxchg16b_emu.o
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 1e572c507d06..40a172541ee2 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,15 +6,8 @@
  *
  */
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
 #include <asm/dwarf2.h>
-
-#ifdef CONFIG_SMP
-#define SEG_PREFIX %gs:
-#else
-#define SEG_PREFIX
-#endif
+#include <asm/percpu.h>
 
 .text
 
@@ -39,24 +32,25 @@ CFI_STARTPROC
 # *atomic* on a single cpu (as provided by the this_cpu_xx class of
 # macros).
 #
-this_cpu_cmpxchg16b_emu:
-	pushf
+	pushfq_cfi
 	cli
 
-	cmpq SEG_PREFIX(%rsi), %rax
-	jne not_same
-	cmpq SEG_PREFIX 8(%rsi), %rdx
-	jne not_same
+	cmpq PER_CPU_VAR((%rsi)), %rax
+	jne .Lnot_same
+	cmpq PER_CPU_VAR(8(%rsi)), %rdx
+	jne .Lnot_same
 
-	movq %rbx, SEG_PREFIX(%rsi)
-	movq %rcx, SEG_PREFIX 8(%rsi)
+	movq %rbx, PER_CPU_VAR((%rsi))
+	movq %rcx, PER_CPU_VAR(8(%rsi))
 
-	popf
+	CFI_REMEMBER_STATE
+	popfq_cfi
 	mov $1, %al
 	ret
 
- not_same:
-	popf
+	CFI_RESTORE_STATE
+.Lnot_same:
+	popfq_cfi
 	xor %al,%al
 	ret
 
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 828cb710dec2..b4807fce5177 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,11 +7,8 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
 #include <asm/dwarf2.h>
 
-
 .text
 
 /*
@@ -30,27 +27,28 @@ CFI_STARTPROC
 # set the whole ZF thing (caller will just compare
 # eax:edx with the expected value)
 #
-cmpxchg8b_emu:
-	pushfl
+	pushfl_cfi
 	cli
 
 	cmpl  (%esi), %eax
-	jne not_same
+	jne .Lnot_same
 	cmpl 4(%esi), %edx
-	jne half_same
+	jne .Lhalf_same
 
 	movl %ebx,  (%esi)
 	movl %ecx, 4(%esi)
 
-	popfl
+	CFI_REMEMBER_STATE
+	popfl_cfi
 	ret
 
- not_same:
+	CFI_RESTORE_STATE
+.Lnot_same:
 	movl  (%esi), %eax
- half_same:
+.Lhalf_same:
 	movl 4(%esi), %edx
 
-	popfl
+	popfl_cfi
 	ret
 
 CFI_ENDPROC
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 28f85c916712..e28cdaf5ac2c 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -6,25 +6,46 @@
  */
 	#include <linux/linkage.h>
 	#include <asm/asm.h>
+	#include <asm/dwarf2.h>
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 	/* put return address in eax (arg1) */
-	.macro thunk_ra name,func
+	.macro THUNK name, func, put_ret_addr_in_eax=0
 	.globl \name
 \name:
-	pushl %eax
-	pushl %ecx
-	pushl %edx
+	CFI_STARTPROC
+	pushl_cfi %eax
+	CFI_REL_OFFSET eax, 0
+	pushl_cfi %ecx
+	CFI_REL_OFFSET ecx, 0
+	pushl_cfi %edx
+	CFI_REL_OFFSET edx, 0
+
+	.if \put_ret_addr_in_eax
 	/* Place EIP in the arg1 */
 	movl 3*4(%esp), %eax
+	.endif
+
 	call \func
-	popl %edx
-	popl %ecx
-	popl %eax
+	popl_cfi %edx
+	CFI_RESTORE edx
+	popl_cfi %ecx
+	CFI_RESTORE ecx
+	popl_cfi %eax
+	CFI_RESTORE eax
 	ret
+	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
-	thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
-	thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#ifdef CONFIG_TRACE_IRQFLAGS
+	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+	THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+	THUNK ___preempt_schedule_context, preempt_schedule_context
 #endif
+#endif
+
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9feaff42b..b30b5ebd614a 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -38,6 +38,13 @@
 	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
 #endif
 
+#ifdef CONFIG_PREEMPT
+	THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+	THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
 	/* SAVE_ARGS below is used only for the .cfi directives it contains. */
 	CFI_STARTPROC
 	SAVE_ARGS