Will Deacon's on March 2, 2019 12:03 am:
> @@ -177,6 +178,7 @@ do {
> \
> static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
> {
> __acquire(lock);
> + mmiowb_spin_lock();
> arch_spin_lock(&lock->raw_lock);
> }
>
> @@ -188,16 +190,23 @@ static inline void
> do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags)
> __acquires(lock)
> {
> __acquire(lock);
> + mmiowb_spin_lock();
> arch_spin_lock_flags(&lock->raw_lock, *flags);
> }
You'd be better to put these inside the spin lock, to match your
trylock.
Also it means the mmiowb state can be used inside a lock/unlock pair
without a compiler barrer forcing it to be reloaded, should be better
code generation for very small critical sections on archs which inline
lock and unlock.
>
> static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
> {
> - return arch_spin_trylock(&(lock)->raw_lock);
> + int ret = arch_spin_trylock(&(lock)->raw_lock);
> +
> + if (ret)
> + mmiowb_spin_lock();
> +
> + return ret;
> }
>
> static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
> {
> + mmiowb_spin_unlock();
> arch_spin_unlock(&lock->raw_lock);
> __release(lock);
> }
Thanks,
Nick
