[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, 47 insertions, 43 deletions

diff --git a/include/asm-ia64/spinlock.h b/include/asm-ia64/spinlock.h
index d2430aa..5b78611 100644
--- a/include/asm-ia64/spinlock.h
+++ b/include/asm-ia64/spinlock.h
@@ -17,28 +17,20 @@
 #include <asm/intrinsics.h>
 #include <asm/system.h>
 
-typedef struct {
-	volatile unsigned int lock;
-#ifdef CONFIG_PREEMPT
-	unsigned int break_lock;
-#endif
-} spinlock_t;
-
-#define SPIN_LOCK_UNLOCKED			(spinlock_t) { 0 }
-#define spin_lock_init(x)			((x)->lock = 0)
+#define __raw_spin_lock_init(x)			((x)->lock = 0)
 
 #ifdef ASM_SUPPORTED
 /*
  * Try to get the lock.  If we fail to get the lock, make a non-standard call to
  * ia64_spinlock_contention().  We do not use a normal call because that would force all
- * callers of spin_lock() to be non-leaf routines.  Instead, ia64_spinlock_contention() is
- * carefully coded to touch only those registers that spin_lock() marks "clobbered".
+ * callers of __raw_spin_lock() to be non-leaf routines.  Instead, ia64_spinlock_contention() is
+ * carefully coded to touch only those registers that __raw_spin_lock() marks "clobbered".
  */
 
 #define IA64_SPINLOCK_CLOBBERS "ar.ccv", "ar.pfs", "p14", "p15", "r27", "r28", "r29", "r30", "b6", "memory"
 
 static inline void
-_raw_spin_lock_flags (spinlock_t *lock, unsigned long flags)
+__raw_spin_lock_flags (raw_spinlock_t *lock, unsigned long flags)
 {
 	register volatile unsigned int *ptr asm ("r31") = &lock->lock;
 
@@ -94,17 +86,17 @@ _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags)
 #endif
 }
 
-#define _raw_spin_lock(lock) _raw_spin_lock_flags(lock, 0)
+#define __raw_spin_lock(lock) __raw_spin_lock_flags(lock, 0)
 
 /* Unlock by doing an ordered store and releasing the cacheline with nta */
-static inline void _raw_spin_unlock(spinlock_t *x) {
+static inline void __raw_spin_unlock(raw_spinlock_t *x) {
 	barrier();
 	asm volatile ("st4.rel.nta [%0] = r0\n\t" :: "r"(x));
 }
 
 #else /* !ASM_SUPPORTED */
-#define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock)
-# define _raw_spin_lock(x)								\
+#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+# define __raw_spin_lock(x)								\
 do {											\
 	__u32 *ia64_spinlock_ptr = (__u32 *) (x);					\
 	__u64 ia64_spinlock_val;							\
@@ -117,29 +109,20 @@ do {											\
 		} while (ia64_spinlock_val);						\
 	}										\
 } while (0)
-#define _raw_spin_unlock(x)	do { barrier(); ((spinlock_t *) x)->lock = 0; } while (0)
+#define __raw_spin_unlock(x)	do { barrier(); ((raw_spinlock_t *) x)->lock = 0; } while (0)
 #endif /* !ASM_SUPPORTED */
 
-#define spin_is_locked(x)	((x)->lock != 0)
-#define _raw_spin_trylock(x)	(cmpxchg_acq(&(x)->lock, 0, 1) == 0)
-#define spin_unlock_wait(x)	do { barrier(); } while ((x)->lock)
-
-typedef struct {
-	volatile unsigned int read_counter	: 24;
-	volatile unsigned int write_lock	:  8;
-#ifdef CONFIG_PREEMPT
-	unsigned int break_lock;
-#endif
-} rwlock_t;
-#define RW_LOCK_UNLOCKED (rwlock_t) { 0, 0 }
+#define __raw_spin_is_locked(x)		((x)->lock != 0)
+#define __raw_spin_trylock(x)		(cmpxchg_acq(&(x)->lock, 0, 1) == 0)
+#define __raw_spin_unlock_wait(lock) \
+	do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
 
-#define rwlock_init(x)		do { *(x) = RW_LOCK_UNLOCKED; } while(0)
-#define read_can_lock(rw)	(*(volatile int *)(rw) >= 0)
-#define write_can_lock(rw)	(*(volatile int *)(rw) == 0)
+#define __raw_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
+#define __raw_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
 
-#define _raw_read_lock(rw)								\
+#define __raw_read_lock(rw)								\
 do {											\
-	rwlock_t *__read_lock_ptr = (rw);						\
+	raw_rwlock_t *__read_lock_ptr = (rw);						\
 											\
 	while (unlikely(ia64_fetchadd(1, (int *) __read_lock_ptr, acq) < 0)) {		\
 		ia64_fetchadd(-1, (int *) __read_lock_ptr, rel);			\
@@ -148,14 +131,14 @@ do {											\
 	}										\
 } while (0)
 
-#define _raw_read_unlock(rw)					\
+#define __raw_read_unlock(rw)					\
 do {								\
-	rwlock_t *__read_lock_ptr = (rw);			\
+	raw_rwlock_t *__read_lock_ptr = (rw);			\
 	ia64_fetchadd(-1, (int *) __read_lock_ptr, rel);	\
 } while (0)
 
 #ifdef ASM_SUPPORTED
-#define _raw_write_lock(rw)							\
+#define __raw_write_lock(rw)							\
 do {										\
  	__asm__ __volatile__ (							\
 		"mov ar.ccv = r0\n"						\
@@ -170,7 +153,7 @@ do {										\
 		:: "r"(rw) : "ar.ccv", "p7", "r2", "r29", "memory");		\
 } while(0)
 
-#define _raw_write_trylock(rw)							\
+#define __raw_write_trylock(rw)							\
 ({										\
 	register long result;							\
 										\
@@ -182,7 +165,7 @@ do {										\
 	(result == 0);								\
 })
 
-static inline void _raw_write_unlock(rwlock_t *x)
+static inline void __raw_write_unlock(raw_rwlock_t *x)
 {
 	u8 *y = (u8 *)x;
 	barrier();
@@ -191,7 +174,7 @@ static inline void _raw_write_unlock(rwlock_t *x)
 
 #else /* !ASM_SUPPORTED */
 
-#define _raw_write_lock(l)								\
+#define __raw_write_lock(l)								\
 ({											\
 	__u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1);			\
 	__u32 *ia64_write_lock_ptr = (__u32 *) (l);					\
@@ -202,7 +185,7 @@ static inline void _raw_write_unlock(rwlock_t *x)
 	} while (ia64_val);								\
 })
 
-#define _raw_write_trylock(rw)						\
+#define __raw_write_trylock(rw)						\
 ({									\
 	__u64 ia64_val;							\
 	__u64 ia64_set_val = ia64_dep_mi(-1, 0, 31,1);			\
@@ -210,7 +193,7 @@ static inline void _raw_write_unlock(rwlock_t *x)
 	(ia64_val == 0);						\
 })
 
-static inline void _raw_write_unlock(rwlock_t *x)
+static inline void __raw_write_unlock(raw_rwlock_t *x)
 {
 	barrier();
 	x->write_lock = 0;
@@ -218,6 +201,6 @@ static inline void _raw_write_unlock(rwlock_t *x)
 
 #endif /* !ASM_SUPPORTED */
 
-#define _raw_read_trylock(lock) generic_raw_read_trylock(lock)
+#define __raw_read_trylock(lock) generic__raw_read_trylock(lock)
 
 #endif /*  _ASM_IA64_SPINLOCK_H */
diff --git a/include/asm-ia64/spinlock_types.h b/include/asm-ia64/spinlock_types.h
new file mode 100644
index 0000000..474e46f
--- /dev/null
+++ b/include/asm-ia64/spinlock_types.h
@@ -0,0 +1,21 @@
+#ifndef _ASM_IA64_SPINLOCK_TYPES_H
+#define _ASM_IA64_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+	volatile unsigned int lock;
+} raw_spinlock_t;
+
+#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	volatile unsigned int read_counter	: 31;
+	volatile unsigned int write_lock	:  1;
+} raw_rwlock_t;
+
+#define __RAW_RW_LOCK_UNLOCKED		{ 0, 0 }
+
+#endif