[PATCH] i386: Redo semaphore and rwlock assembly helpers

- Move them to a pure assembly file. Previously they were in
a C file that only consisted of inline assembly. Doing it in pure
assembler is much nicer.
- Add a frame.i include with FRAME/ENDFRAME macros to easily
add frame pointers to assembly functions
- Add dwarf2 annotation to them so that the new dwarf2 unwinder
doesn't get stuck on them
- Random cleanups

Includes feedback from Jan Beulich and a UML build fix from Andrew
Morton.

Cc: jbeulich@novell.com
Cc: jdike@addtoit.com
Signed-off-by: Andi Kleen <ak@suse.de>

2 files changed, 155 insertions, 1 deletions

diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile
index 914933e9ec3d..d86a548b8d54 100644
--- a/arch/i386/lib/Makefile
+++ b/arch/i386/lib/Makefile
@@ -4,6 +4,6 @@
 
 
 lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \
-	bitops.o
+	bitops.o semaphore.o
 
 lib-$(CONFIG_X86_USE_3DNOW) += mmx.o
diff --git a/arch/i386/lib/semaphore.S b/arch/i386/lib/semaphore.S
new file mode 100644
index 000000000000..e16ff1696390
--- /dev/null
+++ b/arch/i386/lib/semaphore.S
@@ -0,0 +1,154 @@
+/*
+ * 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/config.h>
+#include <linux/linkage.h>
+#include <asm/rwlock.h>
+#include <asm/alternative-asm.i>
+#include <asm/frame.i>
+#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
+ENTRY(__down_failed)
+	CFI_STARTPROC
+	FRAME
+	pushl %edx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edx,0
+	pushl %ecx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ecx,0
+	call __down
+	popl %ecx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ecx
+	popl %edx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edx
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+	END(__down_failed)
+
+ENTRY(__down_failed_interruptible)
+	CFI_STARTPROC
+	FRAME
+	pushl %edx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edx,0
+	pushl %ecx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ecx,0
+	call __down_interruptible
+	popl %ecx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ecx
+	popl %edx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edx
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+	END(__down_failed_interruptible)
+
+ENTRY(__down_failed_trylock)
+	CFI_STARTPROC
+	FRAME
+	pushl %edx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edx,0
+	pushl %ecx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ecx,0
+	call __down_trylock
+	popl %ecx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ecx
+	popl %edx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edx
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+	END(__down_failed_trylock)
+
+ENTRY(__up_wakeup)
+	CFI_STARTPROC
+	FRAME
+	pushl %edx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edx,0
+	pushl %ecx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ecx,0
+	call __up
+	popl %ecx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ecx
+	popl %edx
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE edx
+	ENDFRAME
+	ret
+	CFI_ENDPROC
+	END(__up_wakeup)
+
+/*
+ * rw spinlock fallbacks
+ */
+#ifdef CONFIG_SMP
+ENTRY(__write_lock_failed)
+	CFI_STARTPROC simple
+	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
+	END(__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
+	END(__read_lock_failed)
+
+#endif