From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: 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/sh/include/asm/spinlock.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'arch/sh/include/asm/spinlock.h') 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 -- cgit v1.2.3 From 2b47d54ed41c33baf5825185168b493317c5572f Mon Sep 17 00:00:00 2001 From: Rich Felker Date: Thu, 28 Jul 2016 19:21:10 +0000 Subject: sh: add J2 atomics using the cas.l instruction Signed-off-by: Rich Felker --- arch/sh/include/asm/spinlock.h | 222 ++--------------------------------------- 1 file changed, 6 insertions(+), 216 deletions(-) (limited to 'arch/sh/include/asm/spinlock.h') diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index 416834b60ad0..c2c61ea6a8e2 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -11,222 +11,12 @@ #ifndef __ASM_SH_SPINLOCK_H #define __ASM_SH_SPINLOCK_H -/* - * The only locking implemented here uses SH-4A opcodes. For others, - * split this out as per atomic-*.h. - */ -#ifndef CONFIG_CPU_SH4A -#error "Need movli.l/movco.l for spinlocks" +#if defined(CONFIG_CPU_SH4A) +#include +#elif defined(CONFIG_CPU_J2) +#include +#else +#error "The configured cpu type does not support 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) - -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 - * on the local processor, one does not. - * - * We make no fairness assumptions. They have a cost. - */ -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned long tmp; - unsigned long oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_spin_lock \n\t" - "mov %0, %1 \n\t" - "mov #0, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "cmp/pl %1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&lock->lock) - : "t", "memory" - ); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "mov #1, %0 ! arch_spin_unlock \n\t" - "mov.l %0, @%1 \n\t" - : "=&z" (tmp) - : "r" (&lock->lock) - : "t", "memory" - ); -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_spin_trylock \n\t" - "mov %0, %1 \n\t" - "mov #0, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&lock->lock) - : "t", "memory" - ); - - return oldval; -} - -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * - * NOTE! it is quite common to have readers in interrupts but no interrupt - * writers. For those circumstances we can "mix" irq-safe locks - any writer - * needs to get a irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ - -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_read_lock \n\t" - "cmp/pl %0 \n\t" - "bf 1b \n\t" - "add #-1, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock) - : "t", "memory" - ); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_read_unlock \n\t" - "add #1, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock) - : "t", "memory" - ); -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_write_lock \n\t" - "cmp/hs %2, %0 \n\t" - "bf 1b \n\t" - "sub %2, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - __asm__ __volatile__ ( - "mov.l %1, @%0 ! arch_write_unlock \n\t" - : - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_read_trylock \n\t" - "mov %0, %1 \n\t" - "cmp/pl %0 \n\t" - "bf 2f \n\t" - "add #-1, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "2: \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&rw->lock) - : "t", "memory" - ); - - return (oldval > 0); -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_write_trylock \n\t" - "mov %0, %1 \n\t" - "cmp/hs %3, %0 \n\t" - "bf 2f \n\t" - "sub %3, %0 \n\t" - "2: \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); - - return (oldval > (RW_LOCK_BIAS - 1)); -} - -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - -#define arch_spin_relax(lock) cpu_relax() -#define arch_read_relax(lock) cpu_relax() -#define arch_write_relax(lock) cpu_relax() - #endif /* __ASM_SH_SPINLOCK_H */ -- cgit v1.2.3