linux-kernel - Re: [PATCH 5/5] irqtime: drop local_irq_save/restore from irqtime_account

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1466632519.15275.29.camel@redhat.com>
Date:	Wed, 22 Jun 2016 17:55:19 -0400
From:	Rik van Riel <riel@...hat.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	linux-kernel@...r.kernel.org, mingo@...nel.org,
	pbonzini@...hat.com, fweisbec@...il.com, wanpeng.li@...mail.com,
	efault@....de, tglx@...utronix.de, rkrcmar@...hat.com
Subject: Re: [PATCH 5/5] irqtime: drop local_irq_save/restore from
 irqtime_account_irq

On Tue, 2016-06-21 at 23:49 +0200, Peter Zijlstra wrote:
> On Thu, Jun 16, 2016 at 12:06:07PM -0400, riel@...hat.com wrote:
> > 
> > @@ -53,36 +56,72 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq);
> >   * softirq -> hardirq, hardirq -> softirq
> >   *
> >   * When exiting hardirq or softirq time, account the elapsed time.
> > + *
> > + * When exiting softirq time, subtract the amount of hardirq time
> > that
> > + * interrupted this softirq run, to avoid double accounting of
> > that time.
> >   */
> >  void irqtime_account_irq(struct task_struct *curr, int irqtype)
> >  {
> > +	u64 prev_softirq_start;
> > +	u64 prev_hardirq;
> > +	u64 hardirq_time;
> > +	s64 delta = 0;
> We appear to always assign to delta, so this initialization seems
> superfluous.

It gets rid of a compiler warning, since gcc is not
smart enough to know that the result of in_softirq()
will be the same throughout the function.

Using a bool leaving_softirq = in_softirq() also
gets rid of the warning, and makes the function a
little more readable, so I am doing that.

> > +	if (irqtype == HARDIRQ_OFFSET) {
> > +		delta = sched_clock_cpu(cpu) -
> > __this_cpu_read(hardirq_start_time);
> > +		__this_cpu_add(hardirq_start_time, delta);
> > +	} else do {
> > +		u64 now = sched_clock_cpu(cpu);
> > +		hardirq_time = READ_ONCE(per_cpu(cpu_hardirq_time,
> > cpu));
> Which makes this per_cpu(,cpu) usage somewhat curious. What's wrong
> with
> __this_cpu_read() ?

I played around with it a bit, and it seems that
__this_cpu_read does not want to nest inside
READ_ONCE.  Nobody else seems to be doing that,
either.

Back to READ_ONCE(per_cpu(,cpu)) it is...

> Maybe split the whole thing on irqtype at the very start, instead of
> the
> endless repeated branches?

I untangled the whole thing in the next version,
which I will post after testing.

-- 
All rights reversed

Download attachment "signature.asc" of type "application/pgp-signature" (474 bytes)