linux-kernel - Re: [lkp] [ipc/sem.c] 5864a2fd30: aim9.shared_memory.ops_per

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: <1476851896-3590-1-git-send-email-manfred@colorfullife.com>
Date:   Wed, 19 Oct 2016 06:38:14 +0200
From:   Manfred Spraul <manfred@...orfullife.com>
To:     LKML <linux-kernel@...r.kernel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Davidlohr Bueso <dave@...olabs.net>
Cc:     Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...e.hu>,
        "H. Peter Anvin" <hpa@...or.com>, 1vier1@....de,
        Andrew Morton <akpm@...ux-foundation.org>,
        torvalds@...ux-foundation.org, xiaolong.ye@...el.com,
        felixh@...ormatik.uni-bremen.de,
        Manfred Spraul <manfred@...orfullife.com>
Subject: Re: [lkp] [ipc/sem.c]  5864a2fd30:  aim9.shared_memory.ops_per_sec -13.0%

Hi,

as discussed before:
The root cause for the performance regression is the smp_mb() that was
added into the fast path.

I see two options:
1) switch to full spin_lock()/spin_unlock() for the rare codepath,
  then the fast path doesn't need the smp_mb() anymore.

2) confirm that no arch needs the smp_mb(), then remove it.
  - powerpc is ok after commit
     6262db7c088b ("powerpc/spinlock: Fix spin_unlock_wait()")
  - arm is ok after commit
     d86b8da04dfa ("arm64: spinlock: serialise spin_unlock_wait against concurrent lockers")
  - for x86 is ok after commit
     2c6100227116 ("locking/qspinlock: Fix spin_unlock_wait() some more")
  - for the remaining SMP architectures, I don't have a status.

I would prefer the approach 1:
The memory ordering provided by spin_lock()/spin_unlock() is clear.

Thus:
Attached are patches for approach 1:

- Patch 1 replaces spin_unlock_wait() with spin_lock()/spin_unlock() and
  removes all memory barriers that are then unnecessary.

- Patch 2 adds the hysteresis code: This makes the rare codepath
  extremely rare.
  It also corrects some wrong comments, e.g. regarding switching
  from global lock to per-sem lock (we "must' switch, not we "can"
  switch as written right now).

The patches passed stress-testing.

What do you think?
My initial idea was to aim for 4.10, then we have more time to decide.

--
        Manfred