x86: Speed up ___preempt_schedule*() by using THUNK helpers

___preempt_schedule() does SAVE_ALL/RESTORE_ALL but this is
suboptimal, we do not need to save/restore the callee-saved
register. And we already have arch/x86/lib/thunk_*.S which
implements the similar asm wrappers, so it makes sense to
redefine ___preempt_schedule() as "THUNK ..." and remove
preempt.S altogether.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140921184153.GA23727@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/Makefile

@@ -39,8 +39,6 @@ obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
-obj-$(CONFIG_PREEMPT)	+= preempt.o
-
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o

arch/x86/kernel/preempt.S

@@ -1,25 +0,0 @@
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/asm.h>
-#include <asm/calling.h>
-
-ENTRY(___preempt_schedule)
-	CFI_STARTPROC
-	SAVE_ALL
-	call preempt_schedule
-	RESTORE_ALL
-	ret
-	CFI_ENDPROC
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-ENTRY(___preempt_schedule_context)
-	CFI_STARTPROC
-	SAVE_ALL
-	call preempt_schedule_context
-	RESTORE_ALL
-	ret
-	CFI_ENDPROC
-
-#endif

arch/x86/lib/thunk_32.S

@@ -7,16 +7,19 @@
 	#include <linux/linkage.h>
 	#include <asm/asm.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
+
+	.if \put_ret_addr_in_eax
 	/* Place EIP in the arg1 */
 	movl 3*4(%esp), %eax
+	.endif
+
 	call \func
 	popl %edx
 	popl %ecx
@@ -25,6 +28,15 @@
 	_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
+

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