[PATCH] spinlock consolidation

This patch (written by me and also containing many suggestions of Arjan van
de Ven) does a major cleanup of the spinlock code.  It does the following
things:

 - consolidates and enhances the spinlock/rwlock debugging code

 - simplifies the asm/spinlock.h files

 - encapsulates the raw spinlock type and moves generic spinlock
   features (such as ->break_lock) into the generic code.

 - cleans up the spinlock code hierarchy to get rid of the spaghetti.

Most notably there's now only a single variant of the debugging code,
located in lib/spinlock_debug.c.  (previously we had one SMP debugging
variant per architecture, plus a separate generic one for UP builds)

Also, i've enhanced the rwlock debugging facility, it will now track
write-owners.  There is new spinlock-owner/CPU-tracking on SMP builds too.
All locks have lockup detection now, which will work for both soft and hard
spin/rwlock lockups.

The arch-level include files now only contain the minimally necessary
subset of the spinlock code - all the rest that can be generalized now
lives in the generic headers:

 include/asm-i386/spinlock_types.h       |   16
 include/asm-x86_64/spinlock_types.h     |   16

I have also split up the various spinlock variants into separate files,
making it easier to see which does what. The new layout is:

   SMP                         |  UP
   ----------------------------|-----------------------------------
   asm/spinlock_types_smp.h    |  linux/spinlock_types_up.h
   linux/spinlock_types.h      |  linux/spinlock_types.h
   asm/spinlock_smp.h          |  linux/spinlock_up.h
   linux/spinlock_api_smp.h    |  linux/spinlock_api_up.h
   linux/spinlock.h            |  linux/spinlock.h

/*
 * here's the role of the various spinlock/rwlock related include files:
 *
 * on SMP builds:
 *
 *  asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the
 *                        initializers
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  asm/spinlock.h:       contains the __raw_spin_*()/etc. lowlevel
 *                        implementations, mostly inline assembly code
 *
 *   (also included on UP-debug builds:)
 *
 *  linux/spinlock_api_smp.h:
 *                        contains the prototypes for the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 *
 * on UP builds:
 *
 *  linux/spinlock_type_up.h:
 *                        contains the generic, simplified UP spinlock type.
 *                        (which is an empty structure on non-debug builds)
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  linux/spinlock_up.h:
 *                        contains the __raw_spin_*()/etc. version of UP
 *                        builds. (which are NOPs on non-debug, non-preempt
 *                        builds)
 *
 *   (included on UP-non-debug builds:)
 *
 *  linux/spinlock_api_up.h:
 *                        builds the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 */

All SMP and UP architectures are converted by this patch.

arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via
crosscompilers.  m32r, mips, sh, sparc, have not been tested yet, but should
be mostly fine.

From: Grant Grundler <grundler@parisc-linux.org>

  Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU).
  Builds 32-bit SMP kernel (not booted or tested).  I did not try to build
  non-SMP kernels.  That should be trivial to fix up later if necessary.

  I converted bit ops atomic_hash lock to raw_spinlock_t.  Doing so avoids
  some ugly nesting of linux/*.h and asm/*.h files.  Those particular locks
  are well tested and contained entirely inside arch specific code.  I do NOT
  expect any new issues to arise with them.

 If someone does ever need to use debug/metrics with them, then they will
  need to unravel this hairball between spinlocks, atomic ops, and bit ops
  that exist only because parisc has exactly one atomic instruction: LDCW
  (load and clear word).

From: "Luck, Tony" <tony.luck@intel.com>

   ia64 fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjanv@infradead.org>
Signed-off-by: Grant Grundler <grundler@parisc-linux.org>
Cc: Matthew Wilcox <willy@debian.org>
Signed-off-by: Hirokazu Takata <takata@linux-m32r.org>
Signed-off-by: Mikael Pettersson <mikpe@csd.uu.se>
Signed-off-by: Benoit Boissinot <benoit.boissinot@ens-lyon.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 0 insertions, 204 deletions

diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 2296ff9..fa50069 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -9,5 +9,3 @@ lib-y := mul.o rem.o sdiv.o udiv.o umul.o urem.o ashrdi3.o memcpy.o memset.o \
 	 strncpy_from_user.o divdi3.o udivdi3.o strlen_user.o \
 	 copy_user.o locks.o atomic.o atomic32.o bitops.o \
 	 lshrdi3.o ashldi3.o rwsem.o muldi3.o bitext.o
-
-lib-$(CONFIG_DEBUG_SPINLOCK) +=	debuglocks.o
diff --git a/arch/sparc/lib/debuglocks.c b/arch/sparc/lib/debuglocks.c
deleted file mode 100644
index fb18235..0000000
--- a/arch/sparc/lib/debuglocks.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/* $Id: debuglocks.c,v 1.11 2001/09/20 00:35:31 davem Exp $
- * debuglocks.c: Debugging versions of SMP locking primitives.
- *
- * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
- * Copyright (C) 1998-99 Anton Blanchard (anton@progsoc.uts.edu.au)
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/threads.h>	/* For NR_CPUS */
-#include <linux/spinlock.h>
-#include <asm/psr.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_SMP
-
-/* Some notes on how these debugging routines work.  When a lock is acquired
- * an extra debugging member lock->owner_pc is set to the caller of the lock
- * acquisition routine.  Right before releasing a lock, the debugging program
- * counter is cleared to zero.
- *
- * Furthermore, since PC's are 4 byte aligned on Sparc, we stuff the CPU
- * number of the owner in the lowest two bits.
- */
-
-#define STORE_CALLER(A) __asm__ __volatile__("mov %%i7, %0" : "=r" (A));
-
-static inline void show(char *str, spinlock_t *lock, unsigned long caller)
-{
-	int cpu = smp_processor_id();
-
-	printk("%s(%p) CPU#%d stuck at %08lx, owner PC(%08lx):CPU(%lx)\n",str,
-		lock, cpu, caller, lock->owner_pc & ~3, lock->owner_pc & 3);
-}
-
-static inline void show_read(char *str, rwlock_t *lock, unsigned long caller)
-{
-	int cpu = smp_processor_id();
-
-	printk("%s(%p) CPU#%d stuck at %08lx, owner PC(%08lx):CPU(%lx)\n", str,
-		lock, cpu, caller, lock->owner_pc & ~3, lock->owner_pc & 3);
-}
-
-static inline void show_write(char *str, rwlock_t *lock, unsigned long caller)
-{
-	int cpu = smp_processor_id();
-	int i;
-
-	printk("%s(%p) CPU#%d stuck at %08lx, owner PC(%08lx):CPU(%lx)", str,
-		lock, cpu, caller, lock->owner_pc & ~3, lock->owner_pc & 3);
-
-	for(i = 0; i < NR_CPUS; i++)
-		printk(" reader[%d]=%08lx", i, lock->reader_pc[i]);
-
-	printk("\n");
-}
-
-#undef INIT_STUCK
-#define INIT_STUCK 100000000
-
-void _do_spin_lock(spinlock_t *lock, char *str)
-{
-	unsigned long caller;
-	unsigned long val;
-	int cpu = smp_processor_id();
-	int stuck = INIT_STUCK;
-
-	STORE_CALLER(caller);
-
-again:
-	__asm__ __volatile__("ldstub [%1], %0" : "=r" (val) : "r" (&(lock->lock)));
-	if(val) {
-		while(lock->lock) {
-			if (!--stuck) {
-				show(str, lock, caller);
-				stuck = INIT_STUCK;
-			}
-			barrier();
-		}
-		goto again;
-	}
-	lock->owner_pc = (cpu & 3) | (caller & ~3);
-}
-
-int _spin_trylock(spinlock_t *lock)
-{
-	unsigned long val;
-	unsigned long caller;
-	int cpu = smp_processor_id();
-
-	STORE_CALLER(caller);
-
-	__asm__ __volatile__("ldstub [%1], %0" : "=r" (val) : "r" (&(lock->lock)));
-	if(!val) {
-		/* We got it, record our identity for debugging. */
-		lock->owner_pc = (cpu & 3) | (caller & ~3);
-	}
-	return val == 0;
-}
-
-void _do_spin_unlock(spinlock_t *lock)
-{
-	lock->owner_pc = 0;
-	barrier();
-	lock->lock = 0;
-}
-
-void _do_read_lock(rwlock_t *rw, char *str)
-{
-	unsigned long caller;
-	unsigned long val;
-	int cpu = smp_processor_id();
-	int stuck = INIT_STUCK;
-
-	STORE_CALLER(caller);
-
-wlock_again:
-	__asm__ __volatile__("ldstub [%1 + 3], %0" : "=r" (val) : "r" (&(rw->lock)));
-	if(val) {
-		while(rw->lock & 0xff) {
-			if (!--stuck) {
-				show_read(str, rw, caller);
-				stuck = INIT_STUCK;
-			}
-			barrier();
-		}
-		goto wlock_again;
-	}
-
-	rw->reader_pc[cpu] = caller;
-	barrier();
-	rw->lock++;
-}
-
-void _do_read_unlock(rwlock_t *rw, char *str)
-{
-	unsigned long caller;
-	unsigned long val;
-	int cpu = smp_processor_id();
-	int stuck = INIT_STUCK;
-
-	STORE_CALLER(caller);
-
-wlock_again:
-	__asm__ __volatile__("ldstub [%1 + 3], %0" : "=r" (val) : "r" (&(rw->lock)));
-	if(val) {
-		while(rw->lock & 0xff) {
-			if (!--stuck) {
-				show_read(str, rw, caller);
-				stuck = INIT_STUCK;
-			}
-			barrier();
-		}
-		goto wlock_again;
-	}
-
-	rw->reader_pc[cpu] = 0;
-	barrier();
-	rw->lock -= 0x1ff;
-}
-
-void _do_write_lock(rwlock_t *rw, char *str)
-{
-	unsigned long caller;
-	unsigned long val;
-	int cpu = smp_processor_id();
-	int stuck = INIT_STUCK;
-
-	STORE_CALLER(caller);
-
-wlock_again:
-	__asm__ __volatile__("ldstub [%1 + 3], %0" : "=r" (val) : "r" (&(rw->lock)));
-	if(val) {
-wlock_wait:
-		while(rw->lock) {
-			if (!--stuck) {
-				show_write(str, rw, caller);
-				stuck = INIT_STUCK;
-			}
-			barrier();
-		}
-		goto wlock_again;
-	}
-
-	if (rw->lock & ~0xff) {
-		*(((unsigned char *)&rw->lock)+3) = 0;
-		barrier();
-		goto wlock_wait;
-	}
-
-	barrier();
-	rw->owner_pc = (cpu & 3) | (caller & ~3);
-}
-
-void _do_write_unlock(rwlock_t *rw)
-{
-	rw->owner_pc = 0;
-	barrier();
-	rw->lock = 0;
-}
-
-#endif /* SMP */