Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-ID: <db7192d474c09c17843c9fed41baeee67bc7a420.camel@redhat.com>
Subject: Re: [PATCH 2/6] mm/swap: Introduce alternative per-cpu LRU cache
 locking
From:   nsaenzju@redhat.com
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     akpm@linux-foundation.org, frederic@kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        tglx@linutronix.de, cl@linux.com, juri.lelli@redhat.com,
        mingo@redhat.com, mtosatti@redhat.com, nilal@redhat.com,
        mgorman@suse.de, ppandit@redhat.com, williams@redhat.com,
        bigeasy@linutronix.de, anna-maria@linutronix.de,
        linux-rt-users@vger.kernel.org
Date:   Wed, 22 Sep 2021 13:43:11 +0200
In-Reply-To: <20210922113736.GP4323@worktop.programming.kicks-ass.net>
References: <20210921161323.607817-1-nsaenzju@redhat.com>
         <20210921161323.607817-3-nsaenzju@redhat.com>
         <20210921220358.GN4323@worktop.programming.kicks-ass.net>
         <0ec733daf2daaf8a6f5b1fbf56676b9892d5bf73.camel@redhat.com>
         <20210922113736.GP4323@worktop.programming.kicks-ass.net>
Content-Type: text/plain; charset="UTF-8"
User-Agent: Evolution 3.40.4 (3.40.4-1.fc34) 
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

On Wed, 2021-09-22 at 13:37 +0200, Peter Zijlstra wrote:
> On Wed, Sep 22, 2021 at 10:47:07AM +0200, nsaenzju@redhat.com wrote:
> > On Wed, 2021-09-22 at 00:03 +0200, Peter Zijlstra wrote:
> > > On Tue, Sep 21, 2021 at 06:13:20PM +0200, Nicolas Saenz Julienne wrote:
> > > > +static inline void lru_cache_lock(struct lru_cache_locks *locks)
> > > > +{
> > > > +	if (static_branch_unlikely(&remote_pcpu_cache_access)) {
> > > > +		/* Avoid migration between this_cpu_ptr() and spin_lock() */
> > > > +		migrate_disable();
> > > > +		spin_lock(this_cpu_ptr(&locks->spin));
> > > > +	} else {
> > > > +		local_lock(&locks->local);
> > > > +	}
> > > > +}
> > > 
> > > > +static inline void lru_cache_unlock(struct lru_cache_locks *locks)
> > > > +{
> > > > +	if (static_branch_unlikely(&remote_pcpu_cache_access)) {
> > > > +		spin_unlock(this_cpu_ptr(&locks->spin));
> > > > +		migrate_enable();
> > > > +	} else {
> > > > +		local_unlock(&locks->local);
> > > > +	}
> > > > +}
> > > 
> > > *why* use migrate_disable(), that's horrible!
> > 
> > I was trying to be mindful of RT. They don't appreciate people taking spinlocks
> > just after having disabled preemption.
> > 
> > I think getting local_lock(&locks->local) is my only option then. But it adds
> > an extra redundant spinlock in the RT+NOHZ_FULL case.
> 
> That doesn't make it less horrible. The fundamental problem you seem to
> have is that you have to do the this_cpu thing multiple times.
> 
> If instead you make sure to only ever do the per-cpu deref *once* and
> then make sure you use the same lru_rotate.pvec as you used
> lru_rotate.locks, it all works out much nicer.
> 
> Then you can write things like:
> 
> 	struct lru_rotate *lr = raw_cpu_ptr(&lru_rotate);
> 
> 	frob_lock(&lr->locks);
> 	frob_pvec(&lr->pvec);
> 	frob_unlock(&lr->locks);
> 
> and it all no longer matters if you got this or that CPU's instance.
> 
> After all, you no longer rely on per-cpu ness for serialization but the
> lock.

Thanks, understood. I'll look into it.

-- 
Nicolás Sáenz