[PATCH] Clean up read write lock assembly

- Move the slow path fallbacks to their own assembly files
This makes them much easier to read and is needed for the next change.
- Add CFI annotations for unwinding (XXX need review)
- Remove constant case which can never happen with out of line spinlocks
- Use patchable LOCK prefixes
- Don't use lock sections anymore for inline code because they can't
be expressed by the unwinder (this adds one taken jump to the lock
fast path)

Cc: jbeulich@novell.com

Signed-off-by: Andi Kleen <ak@suse.de>
diff --git a/arch/x86_64/lib/rwlock.S b/arch/x86_64/lib/rwlock.S
new file mode 100644
index 0000000..0cde1f8
--- /dev/null
+++ b/arch/x86_64/lib/rwlock.S
@@ -0,0 +1,38 @@
+/* Slow paths of read/write spinlocks. */
+
+#include <linux/linkage.h>
+#include <asm/rwlock.h>
+#include <asm/alternative-asm.i>
+#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)