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) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
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 <mingo@kernel.org>
#include <linux/kernel.h>
#include <asm/current.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
/*
* Simple spin lock operations. There are two variants, one clears IRQ's
#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)
{
#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
#endif
#include <linux/prefetch.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
/*
* sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K
* 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)
#else
#include <linux/atomic.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
asmlinkage int __raw_spin_is_locked_asm(volatile int *ptr);
asmlinkage void __raw_spin_lock_asm(volatile int *ptr);
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)
#define _ASM_SPINLOCK_H
#include <asm/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
/*
* This file is pulled in for SMP builds.
* 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)
#include <linux/atomic.h>
#include <asm/intrinsics.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
#define arch_spin_lock_init(x) ((x)->lock = 0)
return;
cpu_relax();
}
+
+ smp_acquire__after_ctrl_dep();
}
static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
#include <linux/atomic.h>
#include <asm/dcache_clear.h>
#include <asm/page.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
/*
* Your basic SMP spinlocks, allowing only a single CPU anywhere
#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
#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
#ifdef CONFIG_METAG_ATOMICITY_LOCK1
#include <asm/spinlock_lock1.h>
#else
#include <asm/spinlock_lnkget.h>
#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)
#include <linux/compiler.h>
#include <asm/barrier.h>
+#include <asm/processor.h>
#include <asm/compiler.h>
#include <asm/war.h>
}
#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)
{
#define _ASM_SPINLOCK_H
#include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
#include <asm/rwlock.h>
#include <asm/page.h>
*/
#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)
{
}
#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)
#define __ASM_SPINLOCK_H
#include <linux/smp.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
#define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
{
while (arch_spin_is_locked(lock))
arch_spin_relax(lock);
+ smp_acquire__after_ctrl_dep();
}
/*
#error "Need movli.l/movco.l for spinlocks"
#endif
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
/*
* 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
#ifndef __ASSEMBLY__
#include <asm/psr.h>
+#include <asm/barrier.h>
#include <asm/processor.h> /* 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)
{
#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
/* To get debugging spinlocks which detect and catch
* deadlock situations, set CONFIG_DEBUG_SPINLOCK
* and rebuild your kernel.
#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)
{
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);
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);
#ifndef _XTENSA_SPINLOCK_H
#define _XTENSA_SPINLOCK_H
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
/*
* spinlock
*
*/
#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)
})
#endif
-#endif
+#endif /* CONFIG_SMP */
/* Barriers for virtual machine guests when talking to an SMP host */
#define virt_mb() __smp_mb()
#endif
#include <asm/processor.h> /* for cpu_relax() */
+#include <asm/barrier.h>
/*
* include/linux/spinlock_up.h - UP-debug version of spinlocks.
#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;
#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)
#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 */
projects / linux.git / commitdiff