lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y+otv+QGyMpHAFO1@hirez.programming.kicks-ass.net>
Date:   Mon, 13 Feb 2023 13:31:59 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Waiman Long <longman@...hat.com>
Cc:     Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>,
        linux-kernel@...r.kernel.org, john.p.donnelly@...cle.com,
        Hillf Danton <hdanton@...a.com>,
        Mukesh Ojha <quic_mojha@...cinc.com>,
        Ting11 Wang 王婷 <wangting11@...omi.com>
Subject: Re: [PATCH v7 4/4] locking/rwsem: Enable direct rwsem lock handoff

On Wed, Jan 25, 2023 at 07:36:28PM -0500, Waiman Long wrote:

> @@ -609,6 +618,12 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
>  
>  	lockdep_assert_held(&sem->wait_lock);
>  
> +	if (!waiter->task) {
> +		/* Write lock handed off */
> +		smp_acquire__after_ctrl_dep();
> +		return true;
> +	}
> +
>  	count = atomic_long_read(&sem->count);
>  	do {
>  		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
> @@ -754,6 +769,10 @@ rwsem_spin_on_owner(struct rw_semaphore *sem)
>  
>  	owner = rwsem_owner_flags(sem, &flags);
>  	state = rwsem_owner_state(owner, flags);
> +
> +	if (owner == current)
> +		return OWNER_NONSPINNABLE;	/* Handoff granted */
> +
>  	if (state != OWNER_WRITER)
>  		return state;
>  
> @@ -1168,21 +1186,23 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
>  		 * without sleeping.
>  		 */
>  		if (waiter.handoff_set) {
> -			enum owner_state owner_state;
> -
> -			owner_state = rwsem_spin_on_owner(sem);
> -			if (owner_state == OWNER_NULL)
> -				goto trylock_again;
> +			rwsem_spin_on_owner(sem);
> +			if (!READ_ONCE(waiter.task)) {
> +				/* Write lock handed off */
> +				smp_acquire__after_ctrl_dep();
> +				set_current_state(TASK_RUNNING);
> +				goto out;
> +			}
>  		}
>  
>  		schedule_preempt_disabled();
>  		lockevent_inc(rwsem_sleep_writer);
>  		set_current_state(state);
> -trylock_again:
>  		raw_spin_lock_irq(&sem->wait_lock);
>  	}
>  	__set_current_state(TASK_RUNNING);
>  	raw_spin_unlock_irq(&sem->wait_lock);
> +out:
>  	lockevent_inc(rwsem_wlock);
>  	trace_contention_end(sem, 0);
>  	return sem;
> @@ -1190,6 +1210,11 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
>  out_nolock:
>  	__set_current_state(TASK_RUNNING);
>  	raw_spin_lock_irq(&sem->wait_lock);
> +	if (!waiter.task) {
> +		smp_acquire__after_ctrl_dep();
> +		raw_spin_unlock_irq(&sem->wait_lock);
> +		goto out;
> +	}
>  	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
>  	lockevent_inc(rwsem_wlock_fail);
>  	trace_contention_end(sem, -EINTR);
> @@ -1202,14 +1227,41 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
>   */
>  static struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
>  {
> -	unsigned long flags;
>  	DEFINE_WAKE_Q(wake_q);
> +	unsigned long flags;
> +	unsigned long count;
>  
>  	raw_spin_lock_irqsave(&sem->wait_lock, flags);
>  
> -	if (!list_empty(&sem->wait_list))
> -		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
> +	if (list_empty(&sem->wait_list))
> +		goto unlock_out;
> +
> +	/*
> +	 * If the rwsem is free and handoff flag is set with wait_lock held,
> +	 * no other CPUs can take an active lock.
> +	 */
> +	count = atomic_long_read(&sem->count);
> +	if (!(count & RWSEM_LOCK_MASK) && (count & RWSEM_FLAG_HANDOFF)) {
> +		/*
> +		 * Since rwsem_mark_wake() will handle the handoff to reader
> +		 * properly, we don't need to do anything extra for reader.
> +		 * Special handoff processing will only be needed for writer.
> +		 */
> +		struct rwsem_waiter *waiter = rwsem_first_waiter(sem);
> +		long adj = RWSEM_WRITER_LOCKED - RWSEM_FLAG_HANDOFF;
> +
> +		if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
> +			atomic_long_set(&sem->owner, (long)waiter->task);
> +			atomic_long_add(adj, &sem->count);
> +			wake_q_add(&wake_q, waiter->task);
> +			rwsem_del_waiter(sem, waiter);
> +			waiter->task = NULL;	/* Signal the handoff */
> +			goto unlock_out;
> +		}
> +	}
> +	rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
>  
> +unlock_out:
>  	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
>  	wake_up_q(&wake_q);
>  

I am once again confused...

*WHY* are you changing the writer wake-up path? The comments added here
don't clarify anything.

If we set handoff, we terminate/disallow the spinning/stealing. The
direct consequence is that the slowpath/wait-list becomes the only way
forward.

Since we don't take wait_lock on up, we fundamentally have a race
condition. But *WHY* do you insist on handling that in rwsem_wake()?
Delaying all that until rwsem_try_write_lock()? Doing so would render
pretty much all of the above pointless, no?

After all, rwsem_mark_wake() already wakes the writer if it is first,
no? Why invent yet another special way to wake up the writer.


Also; and I asked this last time around; why do we care about the
handoff to writer *at*all* ? It is the readers that set HANDOFF.

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ