linux-kernel - Re: [LKP] Re: [perf/x86] 81ec3f3c4c: will-it-scale.per_process

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]

Date:   Sun, 23 Feb 2020 17:06:33 -0800
From:   Linus Torvalds <torvalds@...ux-foundation.org>
To:     Feng Tang <feng.tang@...el.com>
Cc:     Jiri Olsa <jolsa@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        kernel test robot <rong.a.chen@...el.com>,
        Ingo Molnar <mingo@...nel.org>,
        Vince Weaver <vincent.weaver@...ne.edu>,
        Jiri Olsa <jolsa@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...hat.com>,
        "Naveen N. Rao" <naveen.n.rao@...ux.vnet.ibm.com>,
        Ravi Bangoria <ravi.bangoria@...ux.ibm.com>,
        Stephane Eranian <eranian@...gle.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org,
        andi.kleen@...el.com, "Huang, Ying" <ying.huang@...el.com>
Subject: Re: [LKP] Re: [perf/x86] 81ec3f3c4c: will-it-scale.per_process_ops
 -5.5% regression

On Sun, Feb 23, 2020 at 4:33 PM Feng Tang <feng.tang@...el.com> wrote:
>
> From the perf c2c data, and the source code checking, the conflicts
> only happens for root_user.__count, and root_user.sigpending, as
> all running tasks are accessing this global data for get/put and
> other operations.

That's odd.

Why? Because those two would be guaranteed to be in the same cacheline
_after_ you've aligned that user_struct.

So if it were a false sharing issue between those two, it would
actually get _worse_ with alignment. Those two fields are basically
next to each other.

But maybe it was straddling a cacheline before, and it caused two
cache accesses each time?

I find this as confusing as you do.

If it's sigpending vs the __refcount, then we almost always change
them together. sigpending gets incremented by __sigqueue_alloc() -
which also does a "get_uid()", and then we decrement it in
__sigqueue_free() - which also does a "free_uid().

That said, exactly *because* they get incremented and decremented
together, maybe we could do something clever: make the "sigpending" be
a separate user counter, kind of how we do mm->user vs mm-.count.

And we'd only increment __refcount as the sigpending goes from zero to
non-zero, and decrement it as sigpending goes back to zero. Avoiding
the double atomics for the case of "lots of signals".

>      ffffffff8225b580 d types__ptrace
>      ffffffff8225b5c0 D root_user
>      ffffffff8225b680 D init_user_ns

I'm assuming this is after the alignment patch (since that's 64-byte
aligned there).

What was it without the alignment?

> No, it's not the biggest, I tried another machine 'Xeon Phi(TM) CPU 7295',
> which has 72C/288T, and the regression is not seen. This is the part
> confusing me :)

Hmm.

Humor me - what  happens if you turn off SMT on that Cascade Lake
system?  Maybe it's about the thread ID bit in the L1? Although again,
I'd have expected things to get _worse_ if it's the two fields that
are now in the same cachline thanks to alignment.

The Xeon Phi is the small-core setup, right? They may be slow enough
to not show the issue as clearly despite having more cores. And it
wouldn't show effects of some out-of-order speculative cache accesses.

                Linus