From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: [PATCH] locking/spinlock, arch: Update and fix spin_unlock_wait() implementations This patch updates/fixes all spin_unlock_wait() implementations. The update is in semantics; where it previously was only a control dependency, we now upgrade to a full load-acquire to match the store-release from the spin_unlock() we waited on. This ensures that when spin_unlock_wait() returns, we're guaranteed to observe the full critical section we waited on. This fixes a number of spin_unlock_wait() users that (not unreasonably) rely on this. I also fixed a number of ticket lock versions to only wait on the current lock holder, instead of for a full unlock, as this is sufficient. Furthermore; again for ticket locks; I added an smp_rmb() in between the initial ticket load and the spin loop testing the current value because I could not convince myself the address dependency is sufficient, esp. if the loads are of different sizes. I'm more than happy to remove this smp_rmb() again if people are certain the address dependency does indeed work as expected. Note: PPC32 will be fixed independently Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: chris@zankel.net Cc: cmetcalf@mellanox.com Cc: davem@davemloft.net Cc: dhowells@redhat.com Cc: james.hogan@imgtec.com Cc: jejb@parisc-linux.org Cc: linux@armlinux.org.uk Cc: mpe@ellerman.id.au Cc: ralf@linux-mips.org Cc: realmz6@gmail.com Cc: rkuo@codeaurora.org Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: vgupta@synopsys.com Cc: ysato@users.sourceforge.jp Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/spinlock.h | 9 +++++++-- arch/arc/include/asm/spinlock.h | 7 +++++-- arch/arm/include/asm/spinlock.h | 19 +++++++++++++++++-- arch/blackfin/include/asm/spinlock.h | 5 +++-- arch/hexagon/include/asm/spinlock.h | 10 ++++++++-- arch/ia64/include/asm/spinlock.h | 4 ++++ arch/m32r/include/asm/spinlock.h | 9 +++++++-- arch/metag/include/asm/spinlock.h | 14 ++++++++++++-- arch/mips/include/asm/spinlock.h | 19 +++++++++++++++++-- arch/mn10300/include/asm/spinlock.h | 8 +++++++- arch/parisc/include/asm/spinlock.h | 9 +++++++-- arch/s390/include/asm/spinlock.h | 3 +++ arch/sh/include/asm/spinlock.h | 10 ++++++++-- arch/sparc/include/asm/spinlock_32.h | 7 +++++-- arch/sparc/include/asm/spinlock_64.h | 10 +++++++--- arch/tile/lib/spinlock_32.c | 6 ++++++ arch/tile/lib/spinlock_64.c | 6 ++++++ arch/xtensa/include/asm/spinlock.h | 10 ++++++++-- include/asm-generic/barrier.h | 2 +- include/linux/spinlock_up.h | 10 +++++++--- 20 files changed, 145 insertions(+), 32 deletions(-) diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index fed9c6f44c19..a40b9fc0c6c3 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -3,6 +3,8 @@ #include #include +#include +#include /* * Simple spin lock operations. There are two variants, one clears IRQ's @@ -13,8 +15,11 @@ #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #define arch_spin_is_locked(x) ((x)->lock != 0) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while ((x)->lock) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline int arch_spin_value_unlocked(arch_spinlock_t lock) { diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index cded4a9b5438..233d5ffe6ec7 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -15,8 +15,11 @@ #define arch_spin_is_locked(x) ((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} #ifdef CONFIG_ARC_HAS_LLSC diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 0fa418463f49..4bec45442072 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -6,6 +6,8 @@ #endif #include +#include +#include /* * sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K @@ -50,8 +52,21 @@ static inline void dsb_sev(void) * memory. */ -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + u16 owner = READ_ONCE(lock->tickets.owner); + + for (;;) { + arch_spinlock_t tmp = READ_ONCE(*lock); + + if (tmp.tickets.owner == tmp.tickets.next || + tmp.tickets.owner != owner) + break; + + wfe(); + } + smp_acquire__after_ctrl_dep(); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h index 490c7caa02d9..c58f4a83ed6f 100644 --- a/arch/blackfin/include/asm/spinlock.h +++ b/arch/blackfin/include/asm/spinlock.h @@ -12,6 +12,8 @@ #else #include +#include +#include asmlinkage int __raw_spin_is_locked_asm(volatile int *ptr); asmlinkage void __raw_spin_lock_asm(volatile int *ptr); @@ -48,8 +50,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { - while (arch_spin_is_locked(lock)) - cpu_relax(); + smp_cond_load_acquire(&lock->lock, !VAL); } static inline int arch_read_can_lock(arch_rwlock_t *rw) diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index 12ca4ebc0338..a1c55788c5d6 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -23,6 +23,8 @@ #define _ASM_SPINLOCK_H #include +#include +#include /* * This file is pulled in for SMP builds. @@ -176,8 +178,12 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) * SMP spinlocks are intended to allow only a single CPU at the lock */ #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(lock) \ - do {while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} + #define arch_spin_is_locked(x) ((x)->lock != 0) #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 45698cd15b7b..ca9e76149a4a 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -15,6 +15,8 @@ #include #include +#include +#include #define arch_spin_lock_init(x) ((x)->lock = 0) @@ -86,6 +88,8 @@ static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock) return; cpu_relax(); } + + smp_acquire__after_ctrl_dep(); } static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h index fa13694eaae3..323c7fc953cd 100644 --- a/arch/m32r/include/asm/spinlock.h +++ b/arch/m32r/include/asm/spinlock.h @@ -13,6 +13,8 @@ #include #include #include +#include +#include /* * Your basic SMP spinlocks, allowing only a single CPU anywhere @@ -27,8 +29,11 @@ #define arch_spin_is_locked(x) (*(volatile int *)(&(x)->slock) <= 0) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, VAL > 0); +} /** * arch_spin_trylock - Try spin lock and return a result diff --git a/arch/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h index 86a7cf3d1386..c0c7a22be1ae 100644 --- a/arch/metag/include/asm/spinlock.h +++ b/arch/metag/include/asm/spinlock.h @@ -1,14 +1,24 @@ #ifndef __ASM_SPINLOCK_H #define __ASM_SPINLOCK_H +#include +#include + #ifdef CONFIG_METAG_ATOMICITY_LOCK1 #include #else #include #endif -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +/* + * both lock1 and lnkget are test-and-set spinlocks with 0 unlocked and 1 + * locked. + */ + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 40196bebe849..f485afe51514 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -12,6 +12,7 @@ #include #include +#include #include #include @@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) } #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - while (arch_spin_is_locked(x)) { cpu_relax(); } + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + u16 owner = READ_ONCE(lock->h.serving_now); + smp_rmb(); + for (;;) { + arch_spinlock_t tmp = READ_ONCE(*lock); + + if (tmp.h.serving_now == tmp.h.ticket || + tmp.h.serving_now != owner) + break; + + cpu_relax(); + } + smp_acquire__after_ctrl_dep(); +} static inline int arch_spin_is_contended(arch_spinlock_t *lock) { diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h index 1ae580f38933..9c7b8f7942d8 100644 --- a/arch/mn10300/include/asm/spinlock.h +++ b/arch/mn10300/include/asm/spinlock.h @@ -12,6 +12,8 @@ #define _ASM_SPINLOCK_H #include +#include +#include #include #include @@ -23,7 +25,11 @@ */ #define arch_spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) != 0) -#define arch_spin_unlock_wait(x) do { barrier(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} static inline void arch_spin_unlock(arch_spinlock_t *lock) { diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 64f2992e439f..e32936cd7f10 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -13,8 +13,13 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x) } #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *x) +{ + volatile unsigned int *a = __ldcw_align(x); + + smp_cond_load_acquire(a, VAL); +} static inline void arch_spin_lock_flags(arch_spinlock_t *x, unsigned long flags) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 63ebf37d3143..7e9e09f600fa 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -10,6 +10,8 @@ #define __ASM_SPINLOCK_H #include +#include +#include #define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval) @@ -97,6 +99,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { while (arch_spin_is_locked(lock)) arch_spin_relax(lock); + smp_acquire__after_ctrl_dep(); } /* diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index bdc0f3b6c56a..416834b60ad0 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -19,14 +19,20 @@ #error "Need movli.l/movco.l for spinlocks" #endif +#include +#include + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere */ #define arch_spin_is_locked(x) ((x)->lock <= 0) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, VAL > 0); +} /* * Simple spin lock operations. There are two variants, one clears IRQ's diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index bcc98fc35281..d9c5876c6121 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -9,12 +9,15 @@ #ifndef __ASSEMBLY__ #include +#include #include /* for cpu_relax */ #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 968917694978..87990b7c6b0d 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -8,6 +8,9 @@ #ifndef __ASSEMBLY__ +#include +#include + /* To get debugging spinlocks which detect and catch * deadlock situations, set CONFIG_DEBUG_SPINLOCK * and rebuild your kernel. @@ -23,9 +26,10 @@ #define arch_spin_is_locked(lp) ((lp)->lock != 0) -#define arch_spin_unlock_wait(lp) \ - do { rmb(); \ - } while((lp)->lock) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c index 88c2a53362e7..076c6cc43113 100644 --- a/arch/tile/lib/spinlock_32.c +++ b/arch/tile/lib/spinlock_32.c @@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock) do { delay_backoff(iterations++); } while (READ_ONCE(lock->current_ticket) == curr); + + /* + * The TILE architecture doesn't do read speculation; therefore + * a control dependency guarantees a LOAD->{LOAD,STORE} order. + */ + barrier(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c index c8d1f94ff1fe..a4b5b2cbce93 100644 --- a/arch/tile/lib/spinlock_64.c +++ b/arch/tile/lib/spinlock_64.c @@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock) do { delay_backoff(iterations++); } while (arch_spin_current(READ_ONCE(lock->lock)) == curr); + + /* + * The TILE architecture doesn't do read speculation; therefore + * a control dependency guarantees a LOAD->{LOAD,STORE} order. + */ + barrier(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h index 1d95fa5dcd10..a36221cf6363 100644 --- a/arch/xtensa/include/asm/spinlock.h +++ b/arch/xtensa/include/asm/spinlock.h @@ -11,6 +11,9 @@ #ifndef _XTENSA_SPINLOCK_H #define _XTENSA_SPINLOCK_H +#include +#include + /* * spinlock * @@ -29,8 +32,11 @@ */ #define arch_spin_is_locked(x) ((x)->slock != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index ab7b0bd7d4dd..fe297b599b0a 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -194,7 +194,7 @@ do { \ }) #endif -#endif +#endif /* CONFIG_SMP */ /* Barriers for virtual machine guests when talking to an SMP host */ #define virt_mb() __smp_mb() diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 8b3ac0d718eb..0d9848de677d 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -6,6 +6,7 @@ #endif #include /* for cpu_relax() */ +#include /* * include/linux/spinlock_up.h - UP-debug version of spinlocks. @@ -25,6 +26,11 @@ #ifdef CONFIG_DEBUG_SPINLOCK #define arch_spin_is_locked(x) ((x)->slock == 0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, VAL); +} + static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; @@ -67,6 +73,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) +#define arch_spin_unlock_wait(lock) do { barrier(); (void)(lock); } while (0) /* for sched/core.c and kernel_lock.c: */ # define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) # define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) @@ -79,7 +86,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define arch_read_can_lock(lock) (((void)(lock), 1)) #define arch_write_can_lock(lock) (((void)(lock), 1)) -#define arch_spin_unlock_wait(lock) \ - do { cpu_relax(); } while (arch_spin_is_locked(lock)) - #endif /* __LINUX_SPINLOCK_UP_H */ -- 2.30.2