From fb1c8f93d869b34cacb8b8932e2b83d96a19d720 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 10 Sep 2005 00:25:56 -0700 Subject: [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 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" ia64 fix Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven Signed-off-by: Grant Grundler Cc: Matthew Wilcox Signed-off-by: Hirokazu Takata Signed-off-by: Mikael Pettersson Signed-off-by: Benoit Boissinot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-i386/spinlock.h | 200 ++++++++++++++++---------------------------- 1 file changed, 70 insertions(+), 130 deletions(-) (limited to 'include/asm-i386/spinlock.h') diff --git a/include/asm-i386/spinlock.h b/include/asm-i386/spinlock.h index f9ff31f4003..23604350cdf 100644 --- a/include/asm-i386/spinlock.h +++ b/include/asm-i386/spinlock.h @@ -7,46 +7,21 @@ #include #include -asmlinkage int printk(const char * fmt, ...) - __attribute__ ((format (printf, 1, 2))); - /* * Your basic SMP spinlocks, allowing only a single CPU anywhere - */ - -typedef struct { - volatile unsigned int slock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned magic; -#endif -#ifdef CONFIG_PREEMPT - unsigned int break_lock; -#endif -} spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#ifdef CONFIG_DEBUG_SPINLOCK -#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC -#else -#define SPINLOCK_MAGIC_INIT /* */ -#endif - -#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT } - -#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0) - -/* + * * Simple spin lock operations. There are two variants, one clears IRQ's * 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) */ -#define spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) <= 0) -#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x)) +#define __raw_spin_is_locked(x) \ + (*(volatile signed char *)(&(x)->slock) <= 0) -#define spin_lock_string \ +#define __raw_spin_lock_string \ "\n1:\t" \ "lock ; decb %0\n\t" \ "jns 3f\n" \ @@ -57,7 +32,7 @@ typedef struct { "jmp 1b\n" \ "3:\n\t" -#define spin_lock_string_flags \ +#define __raw_spin_lock_string_flags \ "\n1:\t" \ "lock ; decb %0\n\t" \ "jns 4f\n\t" \ @@ -73,86 +48,71 @@ typedef struct { "jmp 1b\n" \ "4:\n\t" +static inline void __raw_spin_lock(raw_spinlock_t *lock) +{ + __asm__ __volatile__( + __raw_spin_lock_string + :"=m" (lock->slock) : : "memory"); +} + +static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags) +{ + __asm__ __volatile__( + __raw_spin_lock_string_flags + :"=m" (lock->slock) : "r" (flags) : "memory"); +} + +static inline int __raw_spin_trylock(raw_spinlock_t *lock) +{ + char oldval; + __asm__ __volatile__( + "xchgb %b0,%1" + :"=q" (oldval), "=m" (lock->slock) + :"0" (0) : "memory"); + return oldval > 0; +} + /* - * This works. Despite all the confusion. - * (except on PPro SMP or if we are using OOSTORE) + * __raw_spin_unlock based on writing $1 to the low byte. + * This method works. Despite all the confusion. + * (except on PPro SMP or if we are using OOSTORE, so we use xchgb there) * (PPro errata 66, 92) */ #if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) -#define spin_unlock_string \ +#define __raw_spin_unlock_string \ "movb $1,%0" \ :"=m" (lock->slock) : : "memory" -static inline void _raw_spin_unlock(spinlock_t *lock) +static inline void __raw_spin_unlock(raw_spinlock_t *lock) { -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(lock->magic != SPINLOCK_MAGIC); - BUG_ON(!spin_is_locked(lock)); -#endif __asm__ __volatile__( - spin_unlock_string + __raw_spin_unlock_string ); } #else -#define spin_unlock_string \ +#define __raw_spin_unlock_string \ "xchgb %b0, %1" \ :"=q" (oldval), "=m" (lock->slock) \ :"0" (oldval) : "memory" -static inline void _raw_spin_unlock(spinlock_t *lock) +static inline void __raw_spin_unlock(raw_spinlock_t *lock) { char oldval = 1; -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(lock->magic != SPINLOCK_MAGIC); - BUG_ON(!spin_is_locked(lock)); -#endif - __asm__ __volatile__( - spin_unlock_string - ); -} -#endif - -static inline int _raw_spin_trylock(spinlock_t *lock) -{ - char oldval; __asm__ __volatile__( - "xchgb %b0,%1" - :"=q" (oldval), "=m" (lock->slock) - :"0" (0) : "memory"); - return oldval > 0; + __raw_spin_unlock_string + ); } -static inline void _raw_spin_lock(spinlock_t *lock) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - if (unlikely(lock->magic != SPINLOCK_MAGIC)) { - printk("eip: %p\n", __builtin_return_address(0)); - BUG(); - } #endif - __asm__ __volatile__( - spin_lock_string - :"=m" (lock->slock) : : "memory"); -} -static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - if (unlikely(lock->magic != SPINLOCK_MAGIC)) { - printk("eip: %p\n", __builtin_return_address(0)); - BUG(); - } -#endif - __asm__ __volatile__( - spin_lock_string_flags - :"=m" (lock->slock) : "r" (flags) : "memory"); -} +#define __raw_spin_unlock_wait(lock) \ + do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0) /* * Read-write spinlocks, allowing multiple readers @@ -163,72 +123,41 @@ static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags) * can "mix" irq-safe locks - any writer needs to get a * irq-safe write-lock, but readers can get non-irqsafe * read-locks. + * + * On x86, we implement read-write locks as a 32-bit counter + * with the high bit (sign) being the "contended" bit. + * + * The inline assembly is non-obvious. Think about it. + * + * Changed to use the same technique as rw semaphores. See + * semaphore.h for details. -ben + * + * the helpers are in arch/i386/kernel/semaphore.c */ -typedef struct { - volatile unsigned int lock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned magic; -#endif -#ifdef CONFIG_PREEMPT - unsigned int break_lock; -#endif -} rwlock_t; - -#define RWLOCK_MAGIC 0xdeaf1eed - -#ifdef CONFIG_DEBUG_SPINLOCK -#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC -#else -#define RWLOCK_MAGIC_INIT /* */ -#endif - -#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT } - -#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 == RW_LOCK_BIAS) +#define __raw_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) -/* - * On x86, we implement read-write locks as a 32-bit counter - * with the high bit (sign) being the "contended" bit. - * - * The inline assembly is non-obvious. Think about it. - * - * Changed to use the same technique as rw semaphores. See - * semaphore.h for details. -ben - */ -/* the spinlock helpers are in arch/i386/kernel/semaphore.c */ - -static inline void _raw_read_lock(rwlock_t *rw) +static inline void __raw_read_lock(raw_rwlock_t *rw) { -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(rw->magic != RWLOCK_MAGIC); -#endif __build_read_lock(rw, "__read_lock_failed"); } -static inline void _raw_write_lock(rwlock_t *rw) +static inline void __raw_write_lock(raw_rwlock_t *rw) { -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(rw->magic != RWLOCK_MAGIC); -#endif __build_write_lock(rw, "__write_lock_failed"); } -#define _raw_read_unlock(rw) asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory") -#define _raw_write_unlock(rw) asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory") - -static inline int _raw_read_trylock(rwlock_t *lock) +static inline int __raw_read_trylock(raw_rwlock_t *lock) { atomic_t *count = (atomic_t *)lock; atomic_dec(count); @@ -238,7 +167,7 @@ static inline int _raw_read_trylock(rwlock_t *lock) return 0; } -static inline int _raw_write_trylock(rwlock_t *lock) +static inline int __raw_write_trylock(raw_rwlock_t *lock) { atomic_t *count = (atomic_t *)lock; if (atomic_sub_and_test(RW_LOCK_BIAS, count)) @@ -247,4 +176,15 @@ static inline int _raw_write_trylock(rwlock_t *lock) return 0; } +static inline void __raw_read_unlock(raw_rwlock_t *rw) +{ + asm volatile("lock ; incl %0" :"=m" (rw->lock) : : "memory"); +} + +static inline void __raw_write_unlock(raw_rwlock_t *rw) +{ + asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ", %0" + : "=m" (rw->lock) : : "memory"); +} + #endif /* __ASM_SPINLOCK_H */ -- cgit v1.2.3