[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, 44 insertions, 40 deletions

diff --git a/include/asm-s390/spinlock.h b/include/asm-s390/spinlock.h
index 321b23b..273dbec 100644
--- a/include/asm-s390/spinlock.h
+++ b/include/asm-s390/spinlock.h
@@ -27,25 +27,19 @@ _raw_compare_and_swap(volatile unsigned int *lock,
  * on the local processor, one does not.
  *
  * We make no fairness assumptions. They have a cost.
+ *
+ * (the type definitions are in asm/spinlock_types.h)
  */
 
-typedef struct {
-	volatile unsigned int lock;
-#ifdef CONFIG_PREEMPT
-	unsigned int break_lock;
-#endif
-} __attribute__ ((aligned (4))) spinlock_t;
-
-#define SPIN_LOCK_UNLOCKED	(spinlock_t) { 0 }
-#define spin_lock_init(lp)	do { (lp)->lock = 0; } while(0)
-#define spin_unlock_wait(lp)	do { barrier(); } while(((volatile spinlock_t *)(lp))->lock)
-#define spin_is_locked(x)	((x)->lock != 0)
-#define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock)
+#define __raw_spin_is_locked(x) ((x)->lock != 0)
+#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+#define __raw_spin_unlock_wait(lock) \
+	do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
 
-extern void _raw_spin_lock_wait(spinlock_t *lp, unsigned int pc);
-extern int _raw_spin_trylock_retry(spinlock_t *lp, unsigned int pc);
+extern void _raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc);
+extern int _raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc);
 
-static inline void _raw_spin_lock(spinlock_t *lp)
+static inline void __raw_spin_lock(raw_spinlock_t *lp)
 {
 	unsigned long pc = 1 | (unsigned long) __builtin_return_address(0);
 
@@ -53,7 +47,7 @@ static inline void _raw_spin_lock(spinlock_t *lp)
 		_raw_spin_lock_wait(lp, pc);
 }
 
-static inline int _raw_spin_trylock(spinlock_t *lp)
+static inline int __raw_spin_trylock(raw_spinlock_t *lp)
 {
 	unsigned long pc = 1 | (unsigned long) __builtin_return_address(0);
 
@@ -62,7 +56,7 @@ static inline int _raw_spin_trylock(spinlock_t *lp)
 	return _raw_spin_trylock_retry(lp, pc);
 }
 
-static inline void _raw_spin_unlock(spinlock_t *lp)
+static inline void __raw_spin_unlock(raw_spinlock_t *lp)
 {
 	_raw_compare_and_swap(&lp->lock, lp->lock, 0);
 }
@@ -77,36 +71,25 @@ static inline void _raw_spin_unlock(spinlock_t *lp)
  * irq-safe write-lock, but readers can get non-irqsafe
  * read-locks.
  */
-typedef struct {
-	volatile unsigned int lock;
-	volatile unsigned long owner_pc;
-#ifdef CONFIG_PREEMPT
-	unsigned int break_lock;
-#endif
-} rwlock_t;
-
-#define RW_LOCK_UNLOCKED (rwlock_t) { 0, 0 }
-
-#define rwlock_init(x)	do { *(x) = RW_LOCK_UNLOCKED; } while(0)
 
 /**
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define read_can_lock(x) ((int)(x)->lock >= 0)
+#define __raw_read_can_lock(x) ((int)(x)->lock >= 0)
 
 /**
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define write_can_lock(x) ((x)->lock == 0)
+#define __raw_write_can_lock(x) ((x)->lock == 0)
 
-extern void _raw_read_lock_wait(rwlock_t *lp);
-extern int _raw_read_trylock_retry(rwlock_t *lp);
-extern void _raw_write_lock_wait(rwlock_t *lp);
-extern int _raw_write_trylock_retry(rwlock_t *lp);
+extern void _raw_read_lock_wait(raw_rwlock_t *lp);
+extern int _raw_read_trylock_retry(raw_rwlock_t *lp);
+extern void _raw_write_lock_wait(raw_rwlock_t *lp);
+extern int _raw_write_trylock_retry(raw_rwlock_t *lp);
 
-static inline void _raw_read_lock(rwlock_t *rw)
+static inline void __raw_read_lock(raw_rwlock_t *rw)
 {
 	unsigned int old;
 	old = rw->lock & 0x7fffffffU;
@@ -114,7 +97,7 @@ static inline void _raw_read_lock(rwlock_t *rw)
 		_raw_read_lock_wait(rw);
 }
 
-static inline void _raw_read_unlock(rwlock_t *rw)
+static inline void __raw_read_unlock(raw_rwlock_t *rw)
 {
 	unsigned int old, cmp;
 
@@ -125,18 +108,18 @@ static inline void _raw_read_unlock(rwlock_t *rw)
 	} while (cmp != old);
 }
 
-static inline void _raw_write_lock(rwlock_t *rw)
+static inline void __raw_write_lock(raw_rwlock_t *rw)
 {
 	if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0))
 		_raw_write_lock_wait(rw);
 }
 
-static inline void _raw_write_unlock(rwlock_t *rw)
+static inline void __raw_write_unlock(raw_rwlock_t *rw)
 {
 	_raw_compare_and_swap(&rw->lock, 0x80000000, 0);
 }
 
-static inline int _raw_read_trylock(rwlock_t *rw)
+static inline int __raw_read_trylock(raw_rwlock_t *rw)
 {
 	unsigned int old;
 	old = rw->lock & 0x7fffffffU;
@@ -145,7 +128,7 @@ static inline int _raw_read_trylock(rwlock_t *rw)
 	return _raw_read_trylock_retry(rw);
 }
 
-static inline int _raw_write_trylock(rwlock_t *rw)
+static inline int __raw_write_trylock(raw_rwlock_t *rw)
 {
 	if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0))
 		return 1;
diff --git a/include/asm-s390/spinlock_types.h b/include/asm-s390/spinlock_types.h
new file mode 100644
index 0000000..f79a221
--- /dev/null
+++ b/include/asm-s390/spinlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+	volatile unsigned int lock;
+} __attribute__ ((aligned (4))) raw_spinlock_t;
+
+#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	volatile unsigned int lock;
+	volatile unsigned int owner_pc;
+} raw_rwlock_t;
+
+#define __RAW_RW_LOCK_UNLOCKED		{ 0, 0 }
+
+#endif