Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Fix write lock scalability 64-bit issue
  x86: Unify rwsem assembly implementation
  x86: Unify rwlock assembly implementation
  x86, asm: Fix binutils 2.16 issue with __USER32_CS
  x86, asm: Cleanup thunk_64.S
  x86, asm: Flip RESTORE_ARGS arguments logic
  x86, asm: Flip SAVE_ARGS arguments logic
  x86, asm: Thin down SAVE/RESTORE_* asm macros

6 files changed, 125 insertions, 208 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 6ba4773..b00f678 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -20,6 +20,8 @@ lib-y := delay.o
 lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
+lib-$(CONFIG_SMP) += rwlock.o
+lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o
@@ -29,7 +31,7 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += atomic64_cx8_32.o
         lib-y += checksum_32.o
         lib-y += strstr_32.o
-        lib-y += semaphore_32.o string_32.o
+        lib-y += string_32.o
         lib-y += cmpxchg.o
 ifneq ($(CONFIG_X86_CMPXCHG64),y)
         lib-y += cmpxchg8b_emu.o atomic64_386_32.o
@@ -40,7 +42,6 @@ else
         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 += memmove_64.o memset_64.o
-        lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
-	lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o
+        lib-y += copy_user_64.o copy_user_nocache_64.o
 	lib-y += cmpxchg16b_emu.o
 endif
diff --git a/arch/x86/lib/rwlock.S b/arch/x86/lib/rwlock.S
new file mode 100644
index 0000000..1cad221
--- /dev/null
+++ b/arch/x86/lib/rwlock.S
@@ -0,0 +1,44 @@
+/* Slow paths of read/write spinlocks. */
+
+#include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/rwlock.h>
+
+#ifdef CONFIG_X86_32
+# define __lock_ptr eax
+#else
+# define __lock_ptr rdi
+#endif
+
+ENTRY(__write_lock_failed)
+	CFI_STARTPROC
+	FRAME
+0:	LOCK_PREFIX
+	WRITE_LOCK_ADD($RW_LOCK_BIAS) (%__lock_ptr)
+1:	rep; nop
+	cmpl	$WRITE_LOCK_CMP, (%__lock_ptr)
+	jne	1b
+	LOCK_PREFIX
+	WRITE_LOCK_SUB($RW_LOCK_BIAS) (%__lock_ptr)
+	jnz	0b
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+END(__write_lock_failed)
+
+ENTRY(__read_lock_failed)
+	CFI_STARTPROC
+	FRAME
+0:	LOCK_PREFIX
+	READ_LOCK_SIZE(inc) (%__lock_ptr)
+1:	rep; nop
+	READ_LOCK_SIZE(cmp) $1, (%__lock_ptr)
+	js	1b
+	LOCK_PREFIX
+	READ_LOCK_SIZE(dec) (%__lock_ptr)
+	js	0b
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+END(__read_lock_failed)
diff --git a/arch/x86/lib/rwlock_64.S b/arch/x86/lib/rwlock_64.S
deleted file mode 100644
index 05ea55f..0000000
--- a/arch/x86/lib/rwlock_64.S
+++ /dev/null
@@ -1,38 +0,0 @@
-/* Slow paths of read/write spinlocks. */
-
-#include <linux/linkage.h>
-#include <asm/rwlock.h>
-#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
-
-/* rdi:	pointer to rwlock_t */
-ENTRY(__write_lock_failed)
-	CFI_STARTPROC
-	LOCK_PREFIX
-	addl $RW_LOCK_BIAS,(%rdi)
-1:	rep
-	nop
-	cmpl $RW_LOCK_BIAS,(%rdi)
-	jne 1b
-	LOCK_PREFIX
-	subl $RW_LOCK_BIAS,(%rdi)
-	jnz  __write_lock_failed
-	ret
-	CFI_ENDPROC
-END(__write_lock_failed)
-
-/* rdi:	pointer to rwlock_t */
-ENTRY(__read_lock_failed)
-	CFI_STARTPROC
-	LOCK_PREFIX
-	incl (%rdi)
-1:	rep
-	nop
-	cmpl $1,(%rdi)
-	js 1b
-	LOCK_PREFIX
-	decl (%rdi)
-	js __read_lock_failed
-	ret
-	CFI_ENDPROC
-END(__read_lock_failed)
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem.S
index 6774397..5dff5f0 100644
--- a/arch/x86/lib/rwsem_64.S
+++ b/arch/x86/lib/rwsem.S
@@ -1,4 +1,51 @@
 /*
+ * x86 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/dwarf2.h>
+
+#define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
+#define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
+
+#ifdef CONFIG_X86_32
+
+/*
+ * The semaphore operations have a special calling sequence that
+ * allow us to do a simpler in-line version of them. These routines
+ * need to convert that sequence back into the C sequence when
+ * there is contention on the semaphore.
+ *
+ * %eax contains the semaphore pointer on entry. Save the C-clobbered
+ * registers (%eax, %edx and %ecx) except %eax whish is either a return
+ * value or just clobbered..
+ */
+
+#define save_common_regs \
+	pushl_cfi %ecx; CFI_REL_OFFSET ecx, 0
+
+#define restore_common_regs \
+	popl_cfi %ecx; CFI_RESTORE ecx
+
+	/* Avoid uglifying the argument copying x86-64 needs to do. */
+	.macro movq src, dst
+	.endm
+
+#else
+
+/*
  * x86-64 rwsem wrappers
  *
  * This interfaces the inline asm code to the slow-path
@@ -16,12 +63,6 @@
  * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
  */
 
-#include <linux/linkage.h>
-#include <asm/rwlock.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-#include <asm/dwarf2.h>
-
 #define save_common_regs \
 	pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \
 	pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \
@@ -40,16 +81,18 @@
 	popq_cfi %rsi; CFI_RESTORE rsi; \
 	popq_cfi %rdi; CFI_RESTORE rdi
 
+#endif
+
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
 	CFI_STARTPROC
 	save_common_regs
-	pushq_cfi %rdx
-	CFI_REL_OFFSET rdx, 0
+	__ASM_SIZE(push,_cfi) %__ASM_REG(dx)
+	CFI_REL_OFFSET __ASM_REG(dx), 0
 	movq %rax,%rdi
 	call rwsem_down_read_failed
-	popq_cfi %rdx
-	CFI_RESTORE rdx
+	__ASM_SIZE(pop,_cfi) %__ASM_REG(dx)
+	CFI_RESTORE __ASM_REG(dx)
 	restore_common_regs
 	ret
 	CFI_ENDPROC
@@ -67,7 +110,8 @@ ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
 	CFI_STARTPROC
-	decl %edx	/* do nothing if still outstanding active readers */
+	/* do nothing if still outstanding active readers */
+	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
 	jnz 1f
 	save_common_regs
 	movq %rax,%rdi
@@ -77,16 +121,15 @@ ENTRY(call_rwsem_wake)
 	CFI_ENDPROC
 ENDPROC(call_rwsem_wake)
 
-/* Fix up special calling conventions */
 ENTRY(call_rwsem_downgrade_wake)
 	CFI_STARTPROC
 	save_common_regs
-	pushq_cfi %rdx
-	CFI_REL_OFFSET rdx, 0
+	__ASM_SIZE(push,_cfi) %__ASM_REG(dx)
+	CFI_REL_OFFSET __ASM_REG(dx), 0
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
-	popq_cfi %rdx
-	CFI_RESTORE rdx
+	__ASM_SIZE(pop,_cfi) %__ASM_REG(dx)
+	CFI_RESTORE __ASM_REG(dx)
 	restore_common_regs
 	ret
 	CFI_ENDPROC
diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S
deleted file mode 100644
index 06691da..0000000
--- a/arch/x86/lib/semaphore_32.S
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * i386 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
- */
-
-#include <linux/linkage.h>
-#include <asm/rwlock.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-#include <asm/dwarf2.h>
-
-/*
- * The semaphore operations have a special calling sequence that
- * allow us to do a simpler in-line version of them. These routines
- * need to convert that sequence back into the C sequence when
- * there is contention on the semaphore.
- *
- * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax whish is either a return
- * value or just clobbered..
- */
-	.section .sched.text, "ax"
-
-/*
- * rw spinlock fallbacks
- */
-#ifdef CONFIG_SMP
-ENTRY(__write_lock_failed)
-	CFI_STARTPROC
-	FRAME
-2: 	LOCK_PREFIX
-	addl	$ RW_LOCK_BIAS,(%eax)
-1:	rep; nop
-	cmpl	$ RW_LOCK_BIAS,(%eax)
-	jne	1b
-	LOCK_PREFIX
-	subl	$ RW_LOCK_BIAS,(%eax)
-	jnz	2b
-	ENDFRAME
-	ret
-	CFI_ENDPROC
-	ENDPROC(__write_lock_failed)
-
-ENTRY(__read_lock_failed)
-	CFI_STARTPROC
-	FRAME
-2: 	LOCK_PREFIX
-	incl	(%eax)
-1:	rep; nop
-	cmpl	$1,(%eax)
-	js	1b
-	LOCK_PREFIX
-	decl	(%eax)
-	js	2b
-	ENDFRAME
-	ret
-	CFI_ENDPROC
-	ENDPROC(__read_lock_failed)
-
-#endif
-
-#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM
-
-/* Fix up special calling conventions */
-ENTRY(call_rwsem_down_read_failed)
-	CFI_STARTPROC
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx,0
-	pushl_cfi %edx
-	CFI_REL_OFFSET edx,0
-	call rwsem_down_read_failed
-	popl_cfi %edx
-	popl_cfi %ecx
-	ret
-	CFI_ENDPROC
-	ENDPROC(call_rwsem_down_read_failed)
-
-ENTRY(call_rwsem_down_write_failed)
-	CFI_STARTPROC
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx,0
-	calll rwsem_down_write_failed
-	popl_cfi %ecx
-	ret
-	CFI_ENDPROC
-	ENDPROC(call_rwsem_down_write_failed)
-
-ENTRY(call_rwsem_wake)
-	CFI_STARTPROC
-	decw %dx    /* do nothing if still outstanding active readers */
-	jnz 1f
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx,0
-	call rwsem_wake
-	popl_cfi %ecx
-1:	ret
-	CFI_ENDPROC
-	ENDPROC(call_rwsem_wake)
-
-/* Fix up special calling conventions */
-ENTRY(call_rwsem_downgrade_wake)
-	CFI_STARTPROC
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx,0
-	pushl_cfi %edx
-	CFI_REL_OFFSET edx,0
-	call rwsem_downgrade_wake
-	popl_cfi %edx
-	popl_cfi %ecx
-	ret
-	CFI_ENDPROC
-	ENDPROC(call_rwsem_downgrade_wake)
-
-#endif
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 782b082..a63efd6 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -5,50 +5,41 @@
  * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/calling.h>
 
-	#include <linux/linkage.h>
-	#include <asm/dwarf2.h>
-	#include <asm/calling.h>			
-	#include <asm/rwlock.h>
-		
-	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */ 	
-	.macro thunk name,func
-	.globl \name
-\name:	
-	CFI_STARTPROC
-	SAVE_ARGS
-	call \func
-	jmp  restore
-	CFI_ENDPROC
-	.endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* put return address in rdi (arg1) */
-	.macro thunk_ra name,func
+	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
+	.macro THUNK name, func, put_ret_addr_in_rdi=0
 	.globl \name
 \name:
 	CFI_STARTPROC
+
+	/* this one pushes 9 elems, the next one would be %rIP */
 	SAVE_ARGS
-	/* SAVE_ARGS pushs 9 elements */
-	/* the next element would be the rip */
-	movq 9*8(%rsp), %rdi
+
+	.if \put_ret_addr_in_rdi
+	movq_cfi_restore 9*8, rdi
+	.endif
+
 	call \func
 	jmp  restore
 	CFI_ENDPROC
 	.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_DEBUG_LOCK_ALLOC
-	thunk lockdep_sys_exit_thunk,lockdep_sys_exit
+	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
 #endif
-	
+
 	/* SAVE_ARGS below is used only for the .cfi directives it contains. */
 	CFI_STARTPROC
 	SAVE_ARGS
 restore:
 	RESTORE_ARGS
-	ret	
+	ret
 	CFI_ENDPROC