Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH 5/5] locking/percpu-rwsem: Remove the embedded rwsem
To:     Peter Zijlstra <peterz@infradead.org>, mingo@kernel.org,
        will@kernel.org
Cc:     oleg@redhat.com, tglx@linutronix.de, linux-kernel@vger.kernel.org,
        bigeasy@linutronix.de, juri.lelli@redhat.com, williams@redhat.com,
        bristot@redhat.com, dave@stgolabs.net, jack@suse.com
References: <20191113102115.116470462@infradead.org>
 <20191113102855.925208237@infradead.org>
From:   Waiman Long <longman@redhat.com>
Organization: Red Hat
Message-ID: <ee75fc38-c3c8-3f9e-13ba-5c8312d61325@redhat.com>
Date:   Tue, 19 Nov 2019 08:50:11 -0500
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.7.2
MIME-Version: 1.0
In-Reply-To: <20191113102855.925208237@infradead.org>
Content-Language: en-US
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 11/13/19 5:21 AM, Peter Zijlstra wrote:
> +static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
> +=09=09=09=09      unsigned int mode, int wake_flags,
> +=09=09=09=09      void *key)
> +{
> +=09struct task_struct *p =3D get_task_struct(wq_entry->private);
> +=09bool reader =3D wq_entry->flags & WQ_FLAG_CUSTOM;
> +=09struct percpu_rw_semaphore *sem =3D key;
> +
> +=09/* concurrent against percpu_down_write(), can get stolen */
> +=09if (!__percpu_rwsem_trylock(sem, reader))
> +=09=09return 1;
> +
> +=09list_del_init(&wq_entry->entry);
> +=09smp_store_release(&wq_entry->private, NULL);
> +
> +=09wake_up_process(p);
> +=09put_task_struct(p);
> +
> +=09return !reader; /* wake 'all' readers and 1 writer */
> +}
> +
> +static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool read=
er)
> +{
> +=09DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
> +=09bool wait;
> +
> +=09spin_lock_irq(&sem->waiters.lock);
> +=09/*
> +=09 * Serialize against the wakeup in percpu_up_write(), if we fail
> +=09 * the trylock, the wakeup must see us on the list.
> +=09 */
> +=09wait =3D !__percpu_rwsem_trylock(sem, reader);
> +=09if (wait) {
> +=09=09wq_entry.flags |=3D WQ_FLAG_EXCLUSIVE | reader * WQ_FLAG_CUSTOM;
> +=09=09__add_wait_queue_entry_tail(&sem->waiters, &wq_entry);
> +=09}
> +=09spin_unlock_irq(&sem->waiters.lock);
> +
> +=09while (wait) {
> +=09=09set_current_state(TASK_UNINTERRUPTIBLE);
> +=09=09if (!smp_load_acquire(&wq_entry.private))
> +=09=09=09break;
> +=09=09schedule();
> +=09}

If I read the function correctly, you are setting the WQ_FLAG_EXCLUSIVE
for both readers and writers and __wake_up() is called with an exclusive
count of one. So only one reader or writer is woken up each time.
However, the comment above said we wake 'all' readers and 1 writer. That
doesn't match the actual code, IMO. To match the comments, you should
have set WQ_FLAG_EXCLUSIVE flag only on writer. In this case, you
probably don't need WQ_FLAG_CUSTOM to differentiate between readers and
writers.

Cheers,
Longman