From d86b8da04dfa4771a68bdbad6c424d40f22f0d14 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 19 Nov 2015 17:48:31 +0000 Subject: [PATCH] arm64: spinlock: serialise spin_unlock_wait against concurrent lockers Boqun Feng reported a rather nasty ordering issue with spin_unlock_wait on architectures implementing spin_lock with LL/SC sequences and acquire semantics: | CPU 1 CPU 2 CPU 3 | ================== ==================== ============== | spin_unlock(&lock); | spin_lock(&lock): | r1 = *lock; // r1 == 0; | o = READ_ONCE(object); // reordered here | object = NULL; | smp_mb(); | spin_unlock_wait(&lock); | *lock = 1; | smp_mb(); | o->dead = true; | if (o) // true | BUG_ON(o->dead); // true!! The crux of the problem is that spin_unlock_wait(&lock) can return on CPU 1 whilst CPU 2 is in the process of taking the lock. This can be resolved by upgrading spin_unlock_wait to a LOCK operation, forcing it to serialise against a concurrent locker and giving it acquire semantics in the process (although it is not at all clear whether this is needed - different callers seem to assume different things about the barrier semantics and architectures are similarly disjoint in their implementations of the macro). This patch implements spin_unlock_wait using an LL/SC sequence with acquire semantics on arm64. For v8.1 systems with the LSE atomics, the exclusive writeback is omitted, since the spin_lock operation is indivisible and no intermediate state can be observed. Signed-off-by: Will Deacon --- arch/arm64/include/asm/spinlock.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index c85e96d174a5..fc9682bfe002 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -26,9 +26,28 @@ * The memory barriers are implicit with the load-acquire and store-release * instructions. */ +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + unsigned int tmp; + arch_spinlock_t lockval; -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + asm volatile( +" sevl\n" +"1: wfe\n" +"2: ldaxr %w0, %2\n" +" eor %w1, %w0, %w0, ror #16\n" +" cbnz %w1, 1b\n" + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ +" stxr %w1, %w0, %2\n" +" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ + /* LSE atomics */ +" nop\n" +" nop\n") + : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) + : + : "memory"); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -- 2.45.2