[PATCH] out-of-line locks / generic

This patch achieves out of line spinlocks by creating kernel/spinlock.c
and using the _raw_* inline locking functions.

Now, as much as this is supposed to be arch agnostic, there was still a
fair amount of rummaging about in archs, mostly for the cases where the
arch already has out of line locks and i wanted to avoid the extra call,
saving that extra call also makes lock profiling easier.  PPC32/64 was
an example of such an arch and i have added the necessary profile_pc()
function as an example. 

Size differences are with CONFIG_PREEMPT enabled since we wanted to
determine how much could be saved by moving that lot out of line too.

ppc64 = 259897 bytes:
   text    data     bss     dec     hex filename
5489808 1962724  709064 8161596  7c893c vmlinux-after
5749577 1962852  709064 8421493  808075 vmlinux-before

sparc64 = 193368 bytes:
  text    data     bss     dec     hex filename
3472037  633712  308920 4414669  435ccd vmlinux-after
3665285  633832  308920 4608037  465025 vmlinux-before

i386 = 416075 bytes
   text    data     bss     dec     hex filename
5808371  867442  326864 7002677  6ada35 vmlinux-after
6221254  870634  326864 7418752  713380 vmlinux-before

x86-64 = 282446 bytes
   text    data     bss     dec     hex filename
4598025 1450644  523632 6572301  64490d vmlinux-after
4881679 1449436  523632 6854747  68985b vmlinux-before

It has been compile tested (UP, SMP, PREEMPT) on i386, x86-64, sparc,
sparc64, ppc64, ppc32 and runtime tested on i386, x86-64 and sparc64.
Signed-off-by: Zwane Mwaikambo <zwane@fsmlabs.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/oprofile/timer_int.c

@@ -19,7 +19,7 @@ static int timer_notify(struct notifier_block * self, unsigned long val, void *
 {
 	struct pt_regs * regs = (struct pt_regs *)data;
 	int cpu = smp_processor_id();
-	unsigned long eip = instruction_pointer(regs);
+	unsigned long eip = profile_pc(regs);
  
 	oprofile_add_sample(eip, !user_mode(regs), 0, cpu);
 	return 0;

include/asm-generic/vmlinux.lds.h

@@ -77,3 +77,8 @@
 		VMLINUX_SYMBOL(__sched_text_start) = .;			\
 		*(.sched.text)						\
 		VMLINUX_SYMBOL(__sched_text_end) = .;
+
+#define LOCK_TEXT							\
+		VMLINUX_SYMBOL(__lock_text_start) = .;			\
+		*(.lock.text)						\
+		VMLINUX_SYMBOL(__lock_text_end) = .;

kernel/Makefile

@@ -11,7 +11,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 
 obj-$(CONFIG_FUTEX) += futex.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-obj-$(CONFIG_SMP) += cpu.o
+obj-$(CONFIG_SMP) += cpu.o spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o

kernel/spinlock.c

+/*
+ * Copyright (2004) Linus Torvalds
+ *
+ * Author: Zwane Mwaikambo <zwane@fsmlabs.com>
+ */
+
+#include <linux/config.h>
+#include <linux/linkage.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+
+int __lockfunc _spin_trylock(spinlock_t *lock)
+{
+	preempt_disable();
+	if (_raw_spin_trylock(lock))
+		return 1;
+	
+	preempt_enable();
+	return 0;
+}
+EXPORT_SYMBOL(_spin_trylock);
+
+int __lockfunc _write_trylock(rwlock_t *lock)
+{
+	preempt_disable();
+	if (_raw_write_trylock(lock))
+		return 1;
+
+	preempt_enable();
+	return 0;
+}
+EXPORT_SYMBOL(_write_trylock);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
+void __lockfunc _spin_lock(spinlock_t *lock)
+{
+	preempt_disable();
+	if (unlikely(!_raw_spin_trylock(lock)))
+		__preempt_spin_lock(lock);
+}
+
+void __lockfunc _write_lock(rwlock_t *lock)
+{
+	preempt_disable();
+	if (unlikely(!_raw_write_trylock(lock)))
+		__preempt_write_lock(lock);
+}
+#else
+void __lockfunc _spin_lock(spinlock_t *lock)
+{
+	preempt_disable();
+	_raw_spin_lock(lock);
+}
+
+void __lockfunc _write_lock(rwlock_t *lock)
+{
+	preempt_disable();
+	_raw_write_lock(lock);
+}
+#endif
+EXPORT_SYMBOL(_spin_lock);
+EXPORT_SYMBOL(_write_lock);
+
+void __lockfunc _read_lock(rwlock_t *lock)
+{
+	preempt_disable();
+	_raw_read_lock(lock);
+}
+EXPORT_SYMBOL(_read_lock);
+
+void __lockfunc _spin_unlock(spinlock_t *lock)
+{
+	_raw_spin_unlock(lock);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_spin_unlock);
+
+void __lockfunc _write_unlock(rwlock_t *lock)
+{
+	_raw_write_unlock(lock);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_write_unlock);
+
+void __lockfunc _read_unlock(rwlock_t *lock)
+{
+	_raw_read_unlock(lock);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_read_unlock);
+
+unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	_raw_spin_lock_flags(lock, flags);
+	return flags;
+}
+EXPORT_SYMBOL(_spin_lock_irqsave);
+
+void __lockfunc _spin_lock_irq(spinlock_t *lock)
+{
+	local_irq_disable();
+	preempt_disable();
+	_raw_spin_lock(lock);
+}
+EXPORT_SYMBOL(_spin_lock_irq);
+
+void __lockfunc _spin_lock_bh(spinlock_t *lock)
+{
+	local_bh_disable();
+	preempt_disable();
+	_raw_spin_lock(lock);
+}
+EXPORT_SYMBOL(_spin_lock_bh);
+
+unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	_raw_read_lock(lock);
+	return flags;
+}
+EXPORT_SYMBOL(_read_lock_irqsave);
+
+void __lockfunc _read_lock_irq(rwlock_t *lock)
+{
+	local_irq_disable();
+	preempt_disable();
+	_raw_read_lock(lock);
+}
+EXPORT_SYMBOL(_read_lock_irq);
+
+void __lockfunc _read_lock_bh(rwlock_t *lock)
+{
+	local_bh_disable();
+	preempt_disable();
+	_raw_read_lock(lock);
+}
+EXPORT_SYMBOL(_read_lock_bh);
+
+unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	_raw_write_lock(lock);
+	return flags;
+}
+EXPORT_SYMBOL(_write_lock_irqsave);
+
+void __lockfunc _write_lock_irq(rwlock_t *lock)
+{
+	local_irq_disable();
+	preempt_disable();
+	_raw_write_lock(lock);
+}
+EXPORT_SYMBOL(_write_lock_irq);
+
+void __lockfunc _write_lock_bh(rwlock_t *lock)
+{
+	local_bh_disable();
+	preempt_disable();
+	_raw_write_lock(lock);
+}
+EXPORT_SYMBOL(_write_lock_bh);
+
+void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
+{
+	_raw_spin_unlock(lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_spin_unlock_irqrestore);
+
+void __lockfunc _spin_unlock_irq(spinlock_t *lock)
+{
+	_raw_spin_unlock(lock);
+	local_irq_enable();
+	preempt_enable();
+}
+EXPORT_SYMBOL(_spin_unlock_irq);
+
+void __lockfunc _spin_unlock_bh(spinlock_t *lock)
+{
+	_raw_spin_unlock(lock);
+	preempt_enable();
+	local_bh_enable();
+}
+EXPORT_SYMBOL(_spin_unlock_bh);
+
+void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+	_raw_read_unlock(lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_read_unlock_irqrestore);
+
+void __lockfunc _read_unlock_irq(rwlock_t *lock)
+{
+	_raw_read_unlock(lock);
+	local_irq_enable();
+	preempt_enable();
+}
+EXPORT_SYMBOL(_read_unlock_irq);
+
+void __lockfunc _read_unlock_bh(rwlock_t *lock)
+{
+	_raw_read_unlock(lock);
+	preempt_enable();
+	local_bh_enable();
+}
+EXPORT_SYMBOL(_read_unlock_bh);
+
+void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+	_raw_write_unlock(lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+EXPORT_SYMBOL(_write_unlock_irqrestore);
+
+void __lockfunc _write_unlock_irq(rwlock_t *lock)
+{
+	_raw_write_unlock(lock);
+	local_irq_enable();
+	preempt_enable();
+}
+EXPORT_SYMBOL(_write_unlock_irq);
+
+void __lockfunc _write_unlock_bh(rwlock_t *lock)
+{
+	_raw_write_unlock(lock);
+	preempt_enable();
+	local_bh_enable();
+}
+EXPORT_SYMBOL(_write_unlock_bh);
+
+int __lockfunc _spin_trylock_bh(spinlock_t *lock)
+{
+	local_bh_disable();
+	preempt_disable();
+	if (_raw_spin_trylock(lock))
+		return 1;
+
+	preempt_enable();
+	local_bh_enable();
+	return 0;
+}
+EXPORT_SYMBOL(_spin_trylock_bh);