There's a number of iffy in mutex because mutex::count and mutex::owner are two different fields; this too is the reason MUTEX_SPIN_ON_OWNER and DEBUG_MUTEX are mutually exclusive. Cure this by folding them into a single atomic_long_t field. This nessecairly kills all the architecture specific mutex code. Signed-off-by: Peter Zijlstra (Intel) --- arch/alpha/include/asm/mutex.h | 9 - arch/arc/include/asm/mutex.h | 18 -- arch/arm/include/asm/mutex.h | 21 -- arch/arm64/include/asm/Kbuild | 1 arch/avr32/include/asm/mutex.h | 9 - arch/blackfin/include/asm/Kbuild | 1 arch/c6x/include/asm/mutex.h | 6 arch/cris/include/asm/mutex.h | 9 - arch/frv/include/asm/mutex.h | 9 - arch/h8300/include/asm/mutex.h | 9 - arch/hexagon/include/asm/mutex.h | 8 arch/ia64/include/asm/mutex.h | 90 ---------- arch/m32r/include/asm/mutex.h | 9 - arch/m68k/include/asm/Kbuild | 1 arch/metag/include/asm/Kbuild | 1 arch/microblaze/include/asm/mutex.h | 1 arch/mips/include/asm/Kbuild | 1 arch/mn10300/include/asm/mutex.h | 16 - arch/nios2/include/asm/mutex.h | 1 arch/openrisc/include/asm/mutex.h | 27 --- arch/parisc/include/asm/Kbuild | 1 arch/powerpc/include/asm/mutex.h | 132 --------------- arch/s390/include/asm/mutex.h | 9 - arch/score/include/asm/mutex.h | 6 arch/sh/include/asm/mutex-llsc.h | 109 ------------ arch/sh/include/asm/mutex.h | 12 - arch/sparc/include/asm/Kbuild | 1 arch/tile/include/asm/Kbuild | 1 arch/um/include/asm/Kbuild | 1 arch/unicore32/include/asm/mutex.h | 20 -- arch/x86/include/asm/mutex.h | 5 arch/x86/include/asm/mutex_32.h | 110 ------------ arch/x86/include/asm/mutex_64.h | 127 -------------- arch/xtensa/include/asm/mutex.h | 9 - include/asm-generic/mutex-dec.h | 88 ---------- include/asm-generic/mutex-null.h | 19 -- include/asm-generic/mutex-xchg.h | 120 -------------- include/asm-generic/mutex.h | 9 - include/linux/mutex-debug.h | 24 -- include/linux/mutex.h | 46 +++-- kernel/locking/mutex-debug.c | 13 - kernel/locking/mutex-debug.h | 10 - kernel/locking/mutex.c | 307 ++++++++++++++---------------------- kernel/locking/mutex.h | 26 --- kernel/sched/core.c | 2 45 files changed, 155 insertions(+), 1299 deletions(-) --- a/arch/alpha/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/arc/include/asm/mutex.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -/* - * xchg() based mutex fast path maintains a state of 0 or 1, as opposed to - * atomic dec based which can "count" any number of lock contenders. - * This ideally needs to be fixed in core, but for now switching to dec ver. - */ -#if defined(CONFIG_SMP) && (CONFIG_NR_CPUS > 2) -#include -#else -#include -#endif --- a/arch/arm/include/asm/mutex.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * arch/arm/include/asm/mutex.h - * - * ARM optimized mutex locking primitives - * - * Please look into asm-generic/mutex-xchg.h for a formal definition. - */ -#ifndef _ASM_MUTEX_H -#define _ASM_MUTEX_H -/* - * On pre-ARMv6 hardware this results in a swp-based implementation, - * which is the most efficient. For ARMv6+, we have exclusive memory - * accessors and use atomic_dec to avoid the extra xchg operations - * on the locking slowpaths. - */ -#if __LINUX_ARM_ARCH__ < 6 -#include -#else -#include -#endif -#endif /* _ASM_MUTEX_H */ --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -26,7 +26,6 @@ generic-y += mm-arch-hooks.h generic-y += mman.h generic-y += msgbuf.h generic-y += msi.h -generic-y += mutex.h generic-y += pci.h generic-y += poll.h generic-y += preempt.h --- a/arch/avr32/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -24,7 +24,6 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mman.h generic-y += msgbuf.h -generic-y += mutex.h generic-y += param.h generic-y += percpu.h generic-y += pgalloc.h --- a/arch/c6x/include/asm/mutex.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_C6X_MUTEX_H -#define _ASM_C6X_MUTEX_H - -#include - -#endif /* _ASM_C6X_MUTEX_H */ --- a/arch/cris/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/frv/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/h8300/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/hexagon/include/asm/mutex.h +++ /dev/null @@ -1,8 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ -#include --- a/arch/ia64/include/asm/mutex.h +++ /dev/null @@ -1,90 +0,0 @@ -/* - * ia64 implementation of the mutex fastpath. - * - * Copyright (C) 2006 Ken Chen - * - */ - -#ifndef _ASM_MUTEX_H -#define _ASM_MUTEX_H - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if - * it wasn't 1 originally. This function MUST leave the value lower than - * 1 even when the "1" assertion wasn't true. - */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(ia64_fetchadd4_acq(count, -1) != 1)) - fail_fn(count); -} - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int -__mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(ia64_fetchadd4_acq(count, -1) != 1)) - return -1; - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the count from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * Try to promote the count from 0 to 1. If it wasn't 0, call . - * In the failure case, this function is allowed to either set the value to - * 1, or to set it to a value lower than 1. - * - * If the implementation sets it to a value of lower than 1, then the - * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs - * to return 0 otherwise. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int ret = ia64_fetchadd4_rel(count, 1); - if (unlikely(ret < 0)) - fail_fn(count); -} - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to a value lower than 1, and return 0 (failure) - * if it wasn't 1 originally, or return 1 (success) otherwise. This function - * MUST leave the value lower than 1 even when the "1" assertion wasn't true. - * Additionally, if the value was < 0 originally, this function must not leave - * it to 0 on failure. - * - * If the architecture has no effective trylock variant, it should call the - * spinlock-based trylock variant unconditionally. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - if (atomic_read(count) == 1 && cmpxchg_acq(count, 1, 0) == 1) - return 1; - return 0; -} - -#endif --- a/arch/m32r/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -20,7 +20,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += mman.h -generic-y += mutex.h generic-y += percpu.h generic-y += preempt.h generic-y += resource.h --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -27,7 +27,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += msgbuf.h -generic-y += mutex.h generic-y += param.h generic-y += pci.h generic-y += percpu.h --- a/arch/microblaze/include/asm/mutex.h +++ /dev/null @@ -1 +0,0 @@ -#include --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -9,7 +9,6 @@ generic-y += irq_work.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mutex.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h --- a/arch/mn10300/include/asm/mutex.h +++ /dev/null @@ -1,16 +0,0 @@ -/* MN10300 Mutex fastpath - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - * - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ -#include --- a/arch/nios2/include/asm/mutex.h +++ /dev/null @@ -1 +0,0 @@ -#include --- a/arch/openrisc/include/asm/mutex.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * OpenRISC Linux - * - * Linux architectural port borrowing liberally from similar works of - * others. All original copyrights apply as per the original source - * declaration. - * - * OpenRISC implementation: - * Copyright (C) 2003 Matjaz Breskvar - * Copyright (C) 2010-2011 Jonas Bonn - * et al. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mutex.h generic-y += param.h generic-y += percpu.h generic-y += poll.h --- a/arch/powerpc/include/asm/mutex.h +++ /dev/null @@ -1,132 +0,0 @@ -/* - * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm - */ -#ifndef _ASM_POWERPC_MUTEX_H -#define _ASM_POWERPC_MUTEX_H - -static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new) -{ - int t; - - __asm__ __volatile__ ( -"1: lwarx %0,0,%1 # mutex trylock\n\ - cmpw 0,%0,%2\n\ - bne- 2f\n" - PPC405_ERR77(0,%1) -" stwcx. %3,0,%1\n\ - bne- 1b" - PPC_ACQUIRE_BARRIER - "\n\ -2:" - : "=&r" (t) - : "r" (&v->counter), "r" (old), "r" (new) - : "cc", "memory"); - - return t; -} - -static inline int __mutex_dec_return_lock(atomic_t *v) -{ - int t; - - __asm__ __volatile__( -"1: lwarx %0,0,%1 # mutex lock\n\ - addic %0,%0,-1\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1\n\ - bne- 1b" - PPC_ACQUIRE_BARRIER - : "=&r" (t) - : "r" (&v->counter) - : "cc", "memory"); - - return t; -} - -static inline int __mutex_inc_return_unlock(atomic_t *v) -{ - int t; - - __asm__ __volatile__( - PPC_RELEASE_BARRIER -"1: lwarx %0,0,%1 # mutex unlock\n\ - addic %0,%0,1\n" - PPC405_ERR77(0,%1) -" stwcx. %0,0,%1 \n\ - bne- 1b" - : "=&r" (t) - : "r" (&v->counter) - : "cc", "memory"); - - return t; -} - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if - * it wasn't 1 originally. This function MUST leave the value lower than - * 1 even when the "1" assertion wasn't true. - */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(__mutex_dec_return_lock(count) < 0)) - fail_fn(count); -} - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int -__mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(__mutex_dec_return_lock(count) < 0)) - return -1; - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the count from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * Try to promote the count from 0 to 1. If it wasn't 0, call . - * In the failure case, this function is allowed to either set the value to - * 1, or to set it to a value lower than 1. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(__mutex_inc_return_unlock(count) <= 0)) - fail_fn(count); -} - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to 0, and return 1 (success), or if the count - * was not 1, then return 0 (failure). - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1)) - return 1; - return 0; -} - -#endif --- a/arch/s390/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/arch/score/include/asm/mutex.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_SCORE_MUTEX_H -#define _ASM_SCORE_MUTEX_H - -#include - -#endif /* _ASM_SCORE_MUTEX_H */ --- a/arch/sh/include/asm/mutex-llsc.h +++ /dev/null @@ -1,109 +0,0 @@ -/* - * arch/sh/include/asm/mutex-llsc.h - * - * SH-4A optimized mutex locking primitives - * - * Please look into asm-generic/mutex-xchg.h for a formal definition. - */ -#ifndef __ASM_SH_MUTEX_LLSC_H -#define __ASM_SH_MUTEX_LLSC_H - -/* - * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure. - * with a bastardized atomic decrement (it is not a reliable atomic decrement - * but it satisfies the defined semantics for our purpose, while being - * smaller and faster than a real atomic decrement or atomic swap. - * The idea is to attempt decrementing the lock value only once. If once - * decremented it isn't zero, or if its store-back fails due to a dispute - * on the exclusive store, we simply bail out immediately through the slow - * path where the lock will be reattempted until it succeeds. - */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __done, __res; - - __asm__ __volatile__ ( - "movli.l @%2, %0 \n" - "add #-1, %0 \n" - "movco.l %0, @%2 \n" - "movt %1 \n" - : "=&z" (__res), "=&r" (__done) - : "r" (&(count)->counter) - : "t"); - - if (unlikely(!__done || __res != 0)) - fail_fn(count); -} - -static inline int -__mutex_fastpath_lock_retval(atomic_t *count) -{ - int __done, __res; - - __asm__ __volatile__ ( - "movli.l @%2, %0 \n" - "add #-1, %0 \n" - "movco.l %0, @%2 \n" - "movt %1 \n" - : "=&z" (__res), "=&r" (__done) - : "r" (&(count)->counter) - : "t"); - - if (unlikely(!__done || __res != 0)) - __res = -1; - - return __res; -} - -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __done, __res; - - __asm__ __volatile__ ( - "movli.l @%2, %0 \n\t" - "add #1, %0 \n\t" - "movco.l %0, @%2 \n\t" - "movt %1 \n\t" - : "=&z" (__res), "=&r" (__done) - : "r" (&(count)->counter) - : "t"); - - if (unlikely(!__done || __res <= 0)) - fail_fn(count); -} - -/* - * If the unlock was done on a contended lock, or if the unlock simply fails - * then the mutex remains locked. - */ -#define __mutex_slowpath_needs_to_unlock() 1 - -/* - * For __mutex_fastpath_trylock we do an atomic decrement and check the - * result and put it in the __res variable. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int __res, __orig; - - __asm__ __volatile__ ( - "1: movli.l @%2, %0 \n\t" - "dt %0 \n\t" - "movco.l %0,@%2 \n\t" - "bf 1b \n\t" - "cmp/eq #0,%0 \n\t" - "bt 2f \n\t" - "mov #0, %1 \n\t" - "bf 3f \n\t" - "2: mov #1, %1 \n\t" - "3: " - : "=&z" (__orig), "=&r" (__res) - : "r" (&count->counter) - : "t"); - - return __res; -} -#endif /* __ASM_SH_MUTEX_LLSC_H */ --- a/arch/sh/include/asm/mutex.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ -#if defined(CONFIG_CPU_SH4A) -#include -#else -#include -#endif --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -14,7 +14,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h -generic-y += mutex.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -21,7 +21,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += msgbuf.h -generic-y += mutex.h generic-y += param.h generic-y += parport.h generic-y += poll.h --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -17,7 +17,6 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mutex.h generic-y += param.h generic-y += pci.h generic-y += percpu.h --- a/arch/unicore32/include/asm/mutex.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * linux/arch/unicore32/include/asm/mutex.h - * - * Code specific to PKUnity SoC and UniCore ISA - * - * Copyright (C) 2001-2010 GUAN Xue-tao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * UniCore optimized mutex locking primitives - * - * Please look into asm-generic/mutex-xchg.h for a formal definition. - */ -#ifndef __UNICORE_MUTEX_H__ -#define __UNICORE_MUTEX_H__ - -# include -#endif --- a/arch/x86/include/asm/mutex.h +++ /dev/null @@ -1,5 +0,0 @@ -#ifdef CONFIG_X86_32 -# include -#else -# include -#endif --- a/arch/x86/include/asm/mutex_32.h +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Assembly implementation of the mutex fastpath, based on atomic - * decrement/increment. - * - * started by Ingo Molnar: - * - * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar - */ -#ifndef _ASM_X86_MUTEX_32_H -#define _ASM_X86_MUTEX_32_H - -#include - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if it - * wasn't 1 originally. This function MUST leave the value lower than 1 - * even when the "1" assertion wasn't true. - */ -#define __mutex_fastpath_lock(count, fail_fn) \ -do { \ - unsigned int dummy; \ - \ - typecheck(atomic_t *, count); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " decl (%%eax)\n" \ - " jns 1f \n" \ - " call " #fail_fn "\n" \ - "1:\n" \ - : "=a" (dummy) \ - : "a" (count) \ - : "memory", "ecx", "edx"); \ -} while (0) - - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_dec_return(count) < 0)) - return -1; - else - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the mutex from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * try to promote the mutex from 0 to 1. if it wasn't 0, call . - * In the failure case, this function is allowed to either set the value - * to 1, or to set it to a value lower than 1. - * - * If the implementation sets it to a value of lower than 1, the - * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs - * to return 0 otherwise. - */ -#define __mutex_fastpath_unlock(count, fail_fn) \ -do { \ - unsigned int dummy; \ - \ - typecheck(atomic_t *, count); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " incl (%%eax)\n" \ - " jg 1f\n" \ - " call " #fail_fn "\n" \ - "1:\n" \ - : "=a" (dummy) \ - : "a" (count) \ - : "memory", "ecx", "edx"); \ -} while (0) - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to a value lower than 1, and return 0 (failure) - * if it wasn't 1 originally, or return 1 (success) otherwise. This function - * MUST leave the value lower than 1 even when the "1" assertion wasn't true. - * Additionally, if the value was < 0 originally, this function must not leave - * it to 0 on failure. - */ -static inline int __mutex_fastpath_trylock(atomic_t *count, - int (*fail_fn)(atomic_t *)) -{ - /* cmpxchg because it never induces a false contention state. */ - if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) - return 1; - - return 0; -} - -#endif /* _ASM_X86_MUTEX_32_H */ --- a/arch/x86/include/asm/mutex_64.h +++ /dev/null @@ -1,127 +0,0 @@ -/* - * Assembly implementation of the mutex fastpath, based on atomic - * decrement/increment. - * - * started by Ingo Molnar: - * - * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar - */ -#ifndef _ASM_X86_MUTEX_64_H -#define _ASM_X86_MUTEX_64_H - -/** - * __mutex_fastpath_lock - decrement and call function if negative - * @v: pointer of type atomic_t - * @fail_fn: function to call if the result is negative - * - * Atomically decrements @v and calls if the result is negative. - */ -#ifdef CC_HAVE_ASM_GOTO -static inline void __mutex_fastpath_lock(atomic_t *v, - void (*fail_fn)(atomic_t *)) -{ - asm_volatile_goto(LOCK_PREFIX " decl %0\n" - " jns %l[exit]\n" - : : "m" (v->counter) - : "memory", "cc" - : exit); - fail_fn(v); -exit: - return; -} -#else -#define __mutex_fastpath_lock(v, fail_fn) \ -do { \ - unsigned long dummy; \ - \ - typecheck(atomic_t *, v); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " decl (%%rdi)\n" \ - " jns 1f \n" \ - " call " #fail_fn "\n" \ - "1:" \ - : "=D" (dummy) \ - : "D" (v) \ - : "rax", "rsi", "rdx", "rcx", \ - "r8", "r9", "r10", "r11", "memory"); \ -} while (0) -#endif - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_dec_return(count) < 0)) - return -1; - else - return 0; -} - -/** - * __mutex_fastpath_unlock - increment and call function if nonpositive - * @v: pointer of type atomic_t - * @fail_fn: function to call if the result is nonpositive - * - * Atomically increments @v and calls if the result is nonpositive. - */ -#ifdef CC_HAVE_ASM_GOTO -static inline void __mutex_fastpath_unlock(atomic_t *v, - void (*fail_fn)(atomic_t *)) -{ - asm_volatile_goto(LOCK_PREFIX " incl %0\n" - " jg %l[exit]\n" - : : "m" (v->counter) - : "memory", "cc" - : exit); - fail_fn(v); -exit: - return; -} -#else -#define __mutex_fastpath_unlock(v, fail_fn) \ -do { \ - unsigned long dummy; \ - \ - typecheck(atomic_t *, v); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " incl (%%rdi)\n" \ - " jg 1f\n" \ - " call " #fail_fn "\n" \ - "1:" \ - : "=D" (dummy) \ - : "D" (v) \ - : "rax", "rsi", "rdx", "rcx", \ - "r8", "r9", "r10", "r11", "memory"); \ -} while (0) -#endif - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to 0 and return 1 (success), or return 0 (failure) - * if it wasn't 1 originally. [the fallback function is never used on - * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.] - */ -static inline int __mutex_fastpath_trylock(atomic_t *count, - int (*fail_fn)(atomic_t *)) -{ - if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) - return 1; - - return 0; -} - -#endif /* _ASM_X86_MUTEX_64_H */ --- a/arch/xtensa/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include --- a/include/asm-generic/mutex-dec.h +++ /dev/null @@ -1,88 +0,0 @@ -/* - * include/asm-generic/mutex-dec.h - * - * Generic implementation of the mutex fastpath, based on atomic - * decrement/increment. - */ -#ifndef _ASM_GENERIC_MUTEX_DEC_H -#define _ASM_GENERIC_MUTEX_DEC_H - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if - * it wasn't 1 originally. This function MUST leave the value lower than - * 1 even when the "1" assertion wasn't true. - */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(atomic_dec_return_acquire(count) < 0)) - fail_fn(count); -} - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int -__mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_dec_return_acquire(count) < 0)) - return -1; - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the count from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * Try to promote the count from 0 to 1. If it wasn't 0, call . - * In the failure case, this function is allowed to either set the value to - * 1, or to set it to a value lower than 1. - * - * If the implementation sets it to a value of lower than 1, then the - * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs - * to return 0 otherwise. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(atomic_inc_return_release(count) <= 0)) - fail_fn(count); -} - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to a value lower than 1, and return 0 (failure) - * if it wasn't 1 originally, or return 1 (success) otherwise. This function - * MUST leave the value lower than 1 even when the "1" assertion wasn't true. - * Additionally, if the value was < 0 originally, this function must not leave - * it to 0 on failure. - * - * If the architecture has no effective trylock variant, it should call the - * spinlock-based trylock variant unconditionally. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1)) - return 1; - return 0; -} - -#endif --- a/include/asm-generic/mutex-null.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * include/asm-generic/mutex-null.h - * - * Generic implementation of the mutex fastpath, based on NOP :-) - * - * This is used by the mutex-debugging infrastructure, but it can also - * be used by architectures that (for whatever reason) want to use the - * spinlock based slowpath. - */ -#ifndef _ASM_GENERIC_MUTEX_NULL_H -#define _ASM_GENERIC_MUTEX_NULL_H - -#define __mutex_fastpath_lock(count, fail_fn) fail_fn(count) -#define __mutex_fastpath_lock_retval(count) (-1) -#define __mutex_fastpath_unlock(count, fail_fn) fail_fn(count) -#define __mutex_fastpath_trylock(count, fail_fn) fail_fn(count) -#define __mutex_slowpath_needs_to_unlock() 1 - -#endif --- a/include/asm-generic/mutex-xchg.h +++ /dev/null @@ -1,120 +0,0 @@ -/* - * include/asm-generic/mutex-xchg.h - * - * Generic implementation of the mutex fastpath, based on xchg(). - * - * NOTE: An xchg based implementation might be less optimal than an atomic - * decrement/increment based implementation. If your architecture - * has a reasonable atomic dec/inc then you should probably use - * asm-generic/mutex-dec.h instead, or you could open-code an - * optimized version in asm/mutex.h. - */ -#ifndef _ASM_GENERIC_MUTEX_XCHG_H -#define _ASM_GENERIC_MUTEX_XCHG_H - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if it - * wasn't 1 originally. This function MUST leave the value lower than 1 - * even when the "1" assertion wasn't true. - */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(atomic_xchg(count, 0) != 1)) - /* - * We failed to acquire the lock, so mark it contended - * to ensure that any waiting tasks are woken up by the - * unlock slow path. - */ - if (likely(atomic_xchg_acquire(count, -1) != 1)) - fail_fn(count); -} - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int -__mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_xchg_acquire(count, 0) != 1)) - if (likely(atomic_xchg(count, -1) != 1)) - return -1; - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the mutex from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * try to promote the mutex from 0 to 1. if it wasn't 0, call - * In the failure case, this function is allowed to either set the value to - * 1, or to set it to a value lower than one. - * If the implementation sets it to a value of lower than one, the - * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs - * to return 0 otherwise. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - if (unlikely(atomic_xchg_release(count, 1) != 0)) - fail_fn(count); -} - -#define __mutex_slowpath_needs_to_unlock() 0 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: spinlock based trylock implementation - * - * Change the count from 1 to a value lower than 1, and return 0 (failure) - * if it wasn't 1 originally, or return 1 (success) otherwise. This function - * MUST leave the value lower than 1 even when the "1" assertion wasn't true. - * Additionally, if the value was < 0 originally, this function must not leave - * it to 0 on failure. - * - * If the architecture has no effective trylock variant, it should call the - * spinlock-based trylock variant unconditionally. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int prev; - - if (atomic_read(count) != 1) - return 0; - - prev = atomic_xchg_acquire(count, 0); - if (unlikely(prev < 0)) { - /* - * The lock was marked contended so we must restore that - * state. If while doing so we get back a prev value of 1 - * then we just own it. - * - * [ In the rare case of the mutex going to 1, to 0, to -1 - * and then back to 0 in this few-instructions window, - * this has the potential to trigger the slowpath for the - * owner's unlock path needlessly, but that's not a problem - * in practice. ] - */ - prev = atomic_xchg_acquire(count, prev); - if (prev < 0) - prev = 0; - } - - return prev; -} - -#endif --- a/include/asm-generic/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef __ASM_GENERIC_MUTEX_H -#define __ASM_GENERIC_MUTEX_H -/* - * Pull in the generic implementation for the mutex fastpath, - * which is a reasonable default on many architectures. - */ - -#include -#endif /* __ASM_GENERIC_MUTEX_H */ --- a/include/linux/mutex-debug.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef __LINUX_MUTEX_DEBUG_H -#define __LINUX_MUTEX_DEBUG_H - -#include -#include -#include - -/* - * Mutexes - debugging helpers: - */ - -#define __DEBUG_MUTEX_INITIALIZER(lockname) \ - , .magic = &lockname - -#define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ -} while (0) - -extern void mutex_destroy(struct mutex *lock); - -#endif --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -18,6 +18,7 @@ #include #include #include +#include /* * Simple, straightforward mutexes with strict semantics: @@ -48,16 +49,12 @@ * locks and tasks (and only those tasks) */ struct mutex { - /* 1: unlocked, 0: locked, negative: locked, possible waiters */ - atomic_t count; + atomic_long_t owner; spinlock_t wait_lock; - struct list_head wait_list; -#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) - struct task_struct *owner; -#endif #ifdef CONFIG_MUTEX_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif + struct list_head wait_list; #ifdef CONFIG_DEBUG_MUTEXES void *magic; #endif @@ -66,6 +63,11 @@ struct mutex { #endif }; +static inline struct task_struct *__mutex_owner(struct mutex *lock) +{ + return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03); +} + /* * This is the control structure for tasks blocked on mutex, * which resides on the blocked task's kernel stack: @@ -79,9 +81,20 @@ struct mutex_waiter { }; #ifdef CONFIG_DEBUG_MUTEXES -# include + +#define __DEBUG_MUTEX_INITIALIZER(lockname) \ + , .magic = &lockname + +extern void mutex_destroy(struct mutex *lock); + #else + # define __DEBUG_MUTEX_INITIALIZER(lockname) + +static inline void mutex_destroy(struct mutex *lock) {} + +#endif + /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -90,14 +103,12 @@ struct mutex_waiter { * * It is not allowed to initialize an already locked mutex. */ -# define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ +#define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + __mutex_init((mutex), #mutex, &__key); \ } while (0) -static inline void mutex_destroy(struct mutex *lock) {} -#endif #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -107,7 +118,7 @@ static inline void mutex_destroy(struct #endif #define __MUTEX_INITIALIZER(lockname) \ - { .count = ATOMIC_INIT(1) \ + { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ @@ -127,7 +138,10 @@ extern void __mutex_init(struct mutex *l */ static inline int mutex_is_locked(struct mutex *lock) { - return atomic_read(&lock->count) != 1; + /* + * XXX think about spin_is_locked + */ + return __mutex_owner(lock) != NULL; } /* --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -73,21 +73,8 @@ void debug_mutex_unlock(struct mutex *lo { if (likely(debug_locks)) { DEBUG_LOCKS_WARN_ON(lock->magic != lock); - - if (!lock->owner) - DEBUG_LOCKS_WARN_ON(!lock->owner); - else - DEBUG_LOCKS_WARN_ON(lock->owner != current); - DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); } - - /* - * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug - * mutexes so that we can do it here after we've verified state. - */ - mutex_clear_owner(lock); - atomic_set(&lock->count, 1); } void debug_mutex_init(struct mutex *lock, const char *name, --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -27,16 +27,6 @@ extern void debug_mutex_unlock(struct mu extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); -static inline void mutex_set_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, current); -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, NULL); -} - #define spin_lock_mutex(lock, flags) \ do { \ struct mutex *l = container_of(lock, struct mutex, wait_lock); \ --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -33,35 +33,90 @@ */ #ifdef CONFIG_DEBUG_MUTEXES # include "mutex-debug.h" -# include -/* - * Must be 0 for the debug case so we do not do the unlock outside of the - * wait_lock region. debug_mutex_unlock() will do the actual unlock in this - * case. - */ -# undef __mutex_slowpath_needs_to_unlock -# define __mutex_slowpath_needs_to_unlock() 0 #else # include "mutex.h" -# include #endif void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { - atomic_set(&lock->count, 1); + atomic_long_set(&lock->owner, 0); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); - mutex_clear_owner(lock); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER osq_lock_init(&lock->osq); #endif debug_mutex_init(lock, name, key); } - EXPORT_SYMBOL(__mutex_init); +#define MUTEX_FLAG_WAITERS 0x01 + +#define MUTEX_FLAGS 0x03 + +static inline struct task_struct *__owner_task(unsigned long owner) +{ + return (struct task_struct *)(owner & ~MUTEX_FLAGS); +} + +static inline unsigned long __owner_flags(unsigned long owner) +{ + return owner & MUTEX_FLAGS; +} + +/* + * Actual trylock that will work on any unlocked state. + */ +static inline bool __mutex_trylock(struct mutex *lock) +{ + unsigned long owner, curr = (unsigned long)current; + + owner = atomic_long_read(&lock->owner); + for (;;) { /* must loop, can race against a flag */ + unsigned long old; + + if (__owner_task(owner)) { + if ((unsigned long)__owner_task(owner) == curr) + return true; + + return false; + } + + curr |= __owner_flags(owner); + old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr); + if (old == owner) + return true; + + owner = old; + } +} + +/* + * Optimistic trylock that only works in the uncontended case. Make sure to + * follow with a __mutex_trylock() before failing. + */ +static __always_inline bool __mutex_trylock_fast(struct mutex *lock) +{ + unsigned long owner, curr = (unsigned long)current; + + owner = atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr); + if (!owner) + return true; + + return false; +} + +static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_or(flag, &lock->owner); +} + +static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_andnot(flag, &lock->owner); +} + #ifndef CONFIG_DEBUG_LOCK_ALLOC /* * We split the mutex lock/unlock logic into separate fastpath and @@ -69,7 +124,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); +static void __sched __mutex_lock_slowpath(struct mutex *lock); /** * mutex_lock - acquire the mutex @@ -95,14 +150,10 @@ __visible void __sched __mutex_lock_slow void __sched mutex_lock(struct mutex *lock) { might_sleep(); - /* - * The locking fastpath is the 1->0 transition from - * 'unlocked' into 'locked' state. - */ - __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); - mutex_set_owner(lock); -} + if (!__mutex_trylock_fast(lock)) + __mutex_lock_slowpath(lock); +} EXPORT_SYMBOL(mutex_lock); #endif @@ -176,7 +227,7 @@ ww_mutex_set_context_fastpath(struct ww_ /* * Check if lock is contended, if not there is nobody to wake up */ - if (likely(atomic_read(&lock->base.count) == 0)) + if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) return; /* @@ -227,7 +278,7 @@ bool mutex_spin_on_owner(struct mutex *l bool ret = true; rcu_read_lock(); - while (lock->owner == owner) { + while (__mutex_owner(lock) == owner) { /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking lock->owner still matches owner. If that fails, @@ -260,7 +311,7 @@ static inline int mutex_can_spin_on_owne return 0; rcu_read_lock(); - owner = READ_ONCE(lock->owner); + owner = __mutex_owner(lock); if (owner) retval = owner->on_cpu; rcu_read_unlock(); @@ -272,15 +323,6 @@ static inline int mutex_can_spin_on_owne } /* - * Atomically try to take the lock when it is available - */ -static inline bool mutex_try_to_acquire(struct mutex *lock) -{ - return !mutex_is_locked(lock) && - (atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1); -} - -/* * Optimistic spinning. * * We try to spin for acquisition when we find that the lock owner @@ -342,12 +384,12 @@ static bool mutex_optimistic_spin(struct * If there's an owner, wait for it to either * release the lock or go to sleep. */ - owner = READ_ONCE(lock->owner); + owner = __mutex_owner(lock); if (owner && !mutex_spin_on_owner(lock, owner)) break; /* Try to acquire the mutex if it is unlocked. */ - if (mutex_try_to_acquire(lock)) { + if (__mutex_trylock(lock)) { lock_acquired(&lock->dep_map, ip); if (use_ww_ctx) { @@ -357,7 +399,6 @@ static bool mutex_optimistic_spin(struct ww_mutex_set_context_fastpath(ww, ww_ctx); } - mutex_set_owner(lock); osq_unlock(&lock->osq); return true; } @@ -406,8 +447,7 @@ static bool mutex_optimistic_spin(struct } #endif -__visible __used noinline -void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock); /** * mutex_unlock - release the mutex @@ -422,21 +462,16 @@ void __sched __mutex_unlock_slowpath(ato */ void __sched mutex_unlock(struct mutex *lock) { - /* - * The unlocking fastpath is the 0->1 transition from 'locked' - * into 'unlocked' state: - */ -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(lock); + unsigned long owner; + +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(__mutex_owner(lock) != current); #endif - __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); -} + owner = atomic_long_fetch_and(MUTEX_FLAGS, &lock->owner); + if (__owner_flags(owner)) + __mutex_unlock_slowpath(lock); +} EXPORT_SYMBOL(mutex_unlock); /** @@ -465,15 +500,7 @@ void __sched ww_mutex_unlock(struct ww_m lock->ctx = NULL; } -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(&lock->base); -#endif - __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); + mutex_unlock(&lock->base); } EXPORT_SYMBOL(ww_mutex_unlock); @@ -520,7 +547,7 @@ __mutex_lock_common(struct mutex *lock, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); - if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + if (__mutex_trylock(lock) || mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { /* got the lock, yay! */ preempt_enable(); return 0; @@ -529,11 +556,9 @@ __mutex_lock_common(struct mutex *lock, spin_lock_mutex(&lock->wait_lock, flags); /* - * Once more, try to acquire the lock. Only try-lock the mutex if - * it is unlocked to reduce unnecessary xchg() operations. + * Once more, try to acquire the lock. */ - if (!mutex_is_locked(lock) && - (atomic_xchg_acquire(&lock->count, 0) == 1)) + if (__mutex_trylock(lock)) goto skip_wait; debug_mutex_lock_common(lock, &waiter); @@ -543,21 +568,20 @@ __mutex_lock_common(struct mutex *lock, list_add_tail(&waiter.list, &lock->wait_list); waiter.task = task; + if (list_first_entry(&lock->wait_list, struct mutex_waiter, list) == &waiter) { + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); + /* + * We must be sure to set WAITERS before attempting the trylock + * below, such that mutex_unlock() must either see our WAITERS + * or we see its unlock. + */ + smp_mb__after_atomic(); + } + lock_contended(&lock->dep_map, ip); for (;;) { - /* - * Lets try to take the lock again - this is needed even if - * we get here for the first time (shortly after failing to - * acquire the lock), to make sure that we get a wakeup once - * it's unlocked. Later on, if we sleep, this is the - * operation that gives us the lock. We xchg it to -1, so - * that when we release the lock, we properly wake up the - * other waiters. We only attempt the xchg if the count is - * non-negative in order to avoid unnecessary xchg operations: - */ - if (atomic_read(&lock->count) >= 0 && - (atomic_xchg_acquire(&lock->count, -1) == 1)) + if (__mutex_trylock(lock)) break; /* @@ -587,13 +611,13 @@ __mutex_lock_common(struct mutex *lock, mutex_remove_waiter(lock, &waiter, task); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); + __mutex_clear_flag(lock, MUTEX_FLAG_WAITERS); + debug_mutex_free_waiter(&waiter); skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); - mutex_set_owner(lock); if (use_ww_ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); @@ -631,7 +655,6 @@ _mutex_lock_nest_lock(struct mutex *lock __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_, NULL, 0); } - EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched @@ -650,7 +673,6 @@ mutex_lock_interruptible_nested(struct m return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_, NULL, 0); } - EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); static inline int @@ -715,29 +737,13 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interr /* * Release the lock, slowpath: */ -static inline void -__mutex_unlock_common_slowpath(struct mutex *lock, int nested) +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock) { unsigned long flags; WAKE_Q(wake_q); - /* - * As a performance measurement, release the lock before doing other - * wakeup related duties to follow. This allows other tasks to acquire - * the lock sooner, while still handling cleanups in past unlock calls. - * This can be done as we do not enforce strict equivalence between the - * mutex counter and wait_list. - * - * - * Some architectures leave the lock unlocked in the fastpath failure - * case, others need to leave it locked. In the later case we have to - * unlock it here - as the lock counter is currently 0 or negative. - */ - if (__mutex_slowpath_needs_to_unlock()) - atomic_set(&lock->count, 1); - spin_lock_mutex(&lock->wait_lock, flags); - mutex_release(&lock->dep_map, nested, _RET_IP_); + mutex_release(&lock->dep_map, 0, _RET_IP_); debug_mutex_unlock(lock); if (!list_empty(&lock->wait_list)) { @@ -754,17 +760,6 @@ __mutex_unlock_common_slowpath(struct mu wake_up_q(&wake_q); } -/* - * Release the lock, slowpath: - */ -__visible void -__mutex_unlock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); - - __mutex_unlock_common_slowpath(lock, 1); -} - #ifndef CONFIG_DEBUG_LOCK_ALLOC /* * Here come the less common (and hence less performance-critical) APIs: @@ -789,38 +784,29 @@ __mutex_lock_interruptible_slowpath(stru */ int __sched mutex_lock_interruptible(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_interruptible_slowpath(lock); + + return __mutex_lock_interruptible_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_killable_slowpath(lock); + + return __mutex_lock_killable_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_killable); -__visible void __sched -__mutex_lock_slowpath(atomic_t *lock_count) +static void __sched __mutex_lock_slowpath(struct mutex *lock) { - struct mutex *lock = container_of(lock_count, struct mutex, count); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_, NULL, 0); } @@ -856,37 +842,6 @@ __ww_mutex_lock_interruptible_slowpath(s #endif -/* - * Spinlock based trylock, we take the spinlock and check whether we - * can get the lock: - */ -static inline int __mutex_trylock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); - unsigned long flags; - int prev; - - /* No need to trylock if the mutex is locked. */ - if (mutex_is_locked(lock)) - return 0; - - spin_lock_mutex(&lock->wait_lock, flags); - - prev = atomic_xchg_acquire(&lock->count, -1); - if (likely(prev == 1)) { - mutex_set_owner(lock); - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - } - - /* Set it back to 0 if there are no waiters: */ - if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); - - spin_unlock_mutex(&lock->wait_lock, flags); - - return prev == 1; -} - /** * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired @@ -903,13 +858,7 @@ static inline int __mutex_trylock_slowpa */ int __sched mutex_trylock(struct mutex *lock) { - int ret; - - ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); - if (ret) - mutex_set_owner(lock); - - return ret; + return __mutex_trylock(lock); } EXPORT_SYMBOL(mutex_trylock); @@ -917,36 +866,28 @@ EXPORT_SYMBOL(mutex_trylock); int __sched __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); - - if (likely(!ret)) { + if (__mutex_trylock_fast(&lock->base)) { ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_slowpath(lock, ctx); - return ret; + return 0; + } + + return __ww_mutex_lock_slowpath(lock, ctx); } EXPORT_SYMBOL(__ww_mutex_lock); int __sched __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); - - if (likely(!ret)) { + if (__mutex_trylock_fast(&lock->base)) { ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx); - return ret; + return 0; + } + + return __ww_mutex_lock_interruptible_slowpath(lock, ctx); } EXPORT_SYMBOL(__ww_mutex_lock_interruptible); --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -16,32 +16,6 @@ #define mutex_remove_waiter(lock, waiter, task) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * The mutex owner can get read and written to locklessly. - * We should use WRITE_ONCE when writing the owner value to - * avoid store tearing, otherwise, a thread could potentially - * read a partially written and incomplete owner value. - */ -static inline void mutex_set_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, current); -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, NULL); -} -#else -static inline void mutex_set_owner(struct mutex *lock) -{ -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ -} -#endif - #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -75,11 +75,11 @@ #include #include #include +#include #include #include #include -#include #ifdef CONFIG_PARAVIRT #include #endif