[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>

1 files changed, 27 insertions, 48 deletions

diff --git a/include/asm-mips/spinlock.h b/include/asm-mips/spinlock.h
index 114d3eb..4d0135b 100644
--- a/include/asm-mips/spinlock.h
+++ b/include/asm-mips/spinlock.h
@@ -16,20 +16,10 @@
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  */
 
-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)	do { (x)->lock = 0; } while(0)
-
-#define spin_is_locked(x)	((x)->lock != 0)
-#define spin_unlock_wait(x)	do { barrier(); } while ((x)->lock)
-#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(x) \
+		do { cpu_relax(); } while ((x)->lock)
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
@@ -38,13 +28,13 @@ typedef struct {
  * We make no fairness assumptions.  They have a cost.
  */
 
-static inline void _raw_spin_lock(spinlock_t *lock)
+static inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
 	unsigned int tmp;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_spin_lock	\n"
+		"	.set	noreorder	# __raw_spin_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bnez	%1, 1b					\n"
 		"	 li	%1, 1					\n"
@@ -58,7 +48,7 @@ static inline void _raw_spin_lock(spinlock_t *lock)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_spin_lock	\n"
+		"	.set	noreorder	# __raw_spin_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bnez	%1, 1b					\n"
 		"	 li	%1, 1					\n"
@@ -72,10 +62,10 @@ static inline void _raw_spin_lock(spinlock_t *lock)
 	}
 }
 
-static inline void _raw_spin_unlock(spinlock_t *lock)
+static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__asm__ __volatile__(
-	"	.set	noreorder	# _raw_spin_unlock	\n"
+	"	.set	noreorder	# __raw_spin_unlock	\n"
 	"	sync						\n"
 	"	sw	$0, %0					\n"
 	"	.set\treorder					\n"
@@ -84,13 +74,13 @@ static inline void _raw_spin_unlock(spinlock_t *lock)
 	: "memory");
 }
 
-static inline unsigned int _raw_spin_trylock(spinlock_t *lock)
+static inline unsigned int __raw_spin_trylock(raw_spinlock_t *lock)
 {
 	unsigned int temp, res;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_spin_trylock	\n"
+		"	.set	noreorder	# __raw_spin_trylock	\n"
 		"1:	ll	%0, %3					\n"
 		"	ori	%2, %0, 1				\n"
 		"	sc	%2, %1					\n"
@@ -104,7 +94,7 @@ static inline unsigned int _raw_spin_trylock(spinlock_t *lock)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_spin_trylock	\n"
+		"	.set	noreorder	# __raw_spin_trylock	\n"
 		"1:	ll	%0, %3					\n"
 		"	ori	%2, %0, 1				\n"
 		"	sc	%2, %1					\n"
@@ -129,24 +119,13 @@ static inline unsigned int _raw_spin_trylock(spinlock_t *lock)
  * read-locks.
  */
 
-typedef struct {
-	volatile unsigned int lock;
-#ifdef CONFIG_PREEMPT
-	unsigned int break_lock;
-#endif
-} rwlock_t;
-
-#define RW_LOCK_UNLOCKED (rwlock_t) { 0 }
-
-#define rwlock_init(x)  do { *(x) = RW_LOCK_UNLOCKED; } while(0)
-
-static inline void _raw_read_lock(rwlock_t *rw)
+static inline void __raw_read_lock(raw_rwlock_t *rw)
 {
 	unsigned int tmp;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_read_lock	\n"
+		"	.set	noreorder	# __raw_read_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bltz	%1, 1b					\n"
 		"	 addu	%1, 1					\n"
@@ -160,7 +139,7 @@ static inline void _raw_read_lock(rwlock_t *rw)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_read_lock	\n"
+		"	.set	noreorder	# __raw_read_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bltz	%1, 1b					\n"
 		"	 addu	%1, 1					\n"
@@ -177,13 +156,13 @@ static inline void _raw_read_lock(rwlock_t *rw)
 /* Note the use of sub, not subu which will make the kernel die with an
    overflow exception if we ever try to unlock an rwlock that is already
    unlocked or is being held by a writer.  */
-static inline void _raw_read_unlock(rwlock_t *rw)
+static inline void __raw_read_unlock(raw_rwlock_t *rw)
 {
 	unsigned int tmp;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"1:	ll	%1, %2		# _raw_read_unlock	\n"
+		"1:	ll	%1, %2		# __raw_read_unlock	\n"
 		"	sub	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
@@ -193,7 +172,7 @@ static inline void _raw_read_unlock(rwlock_t *rw)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_read_unlock	\n"
+		"	.set	noreorder	# __raw_read_unlock	\n"
 		"1:	ll	%1, %2					\n"
 		"	sub	%1, 1					\n"
 		"	sc	%1, %0					\n"
@@ -206,13 +185,13 @@ static inline void _raw_read_unlock(rwlock_t *rw)
 	}
 }
 
-static inline void _raw_write_lock(rwlock_t *rw)
+static inline void __raw_write_lock(raw_rwlock_t *rw)
 {
 	unsigned int tmp;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_write_lock	\n"
+		"	.set	noreorder	# __raw_write_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bnez	%1, 1b					\n"
 		"	 lui	%1, 0x8000				\n"
@@ -226,7 +205,7 @@ static inline void _raw_write_lock(rwlock_t *rw)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_write_lock	\n"
+		"	.set	noreorder	# __raw_write_lock	\n"
 		"1:	ll	%1, %2					\n"
 		"	bnez	%1, 1b					\n"
 		"	 lui	%1, 0x8000				\n"
@@ -241,26 +220,26 @@ static inline void _raw_write_lock(rwlock_t *rw)
 	}
 }
 
-static inline void _raw_write_unlock(rwlock_t *rw)
+static inline void __raw_write_unlock(raw_rwlock_t *rw)
 {
 	__asm__ __volatile__(
-	"	sync			# _raw_write_unlock	\n"
+	"	sync			# __raw_write_unlock	\n"
 	"	sw	$0, %0					\n"
 	: "=m" (rw->lock)
 	: "m" (rw->lock)
 	: "memory");
 }
 
-#define _raw_read_trylock(lock) generic_raw_read_trylock(lock)
+#define __raw_read_trylock(lock) generic__raw_read_trylock(lock)
 
-static inline int _raw_write_trylock(rwlock_t *rw)
+static inline int __raw_write_trylock(raw_rwlock_t *rw)
 {
 	unsigned int tmp;
 	int ret;
 
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_write_trylock	\n"
+		"	.set	noreorder	# __raw_write_trylock	\n"
 		"	li	%2, 0					\n"
 		"1:	ll	%1, %3					\n"
 		"	bnez	%1, 2f					\n"
@@ -277,7 +256,7 @@ static inline int _raw_write_trylock(rwlock_t *rw)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
-		"	.set	noreorder	# _raw_write_trylock	\n"
+		"	.set	noreorder	# __raw_write_trylock	\n"
 		"	li	%2, 0					\n"
 		"1:	ll	%1, %3					\n"
 		"	bnez	%1, 2f					\n"