linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Xu <peterx@redhat.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Guo Ren <guoren@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Gerald Schaefer <gerald.schaefer@de.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andrea Arcangeli <aarcange@redhat.com>,
	linux-csky@vger.kernel.org
Subject: Re: [PATCH 07/25] mm/csky: Use mm_fault_accounting()
Date: Thu, 18 Jun 2020 10:38:01 -0400	[thread overview]
Message-ID: <20200618143801.GK76766@xz-x1> (raw)
In-Reply-To: <CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com>

On Wed, Jun 17, 2020 at 01:15:31PM -0700, Linus Torvalds wrote:
> On Wed, Jun 17, 2020 at 12:58 PM Peter Xu <peterx@redhat.com> wrote:
> >
> > But currently remote GUP will still do the page fault accounting on the remote
> > task_struct, am I right?  E.g., when the get_user_pages_remote() is called with
> > "tsk != current", it seems the faultin_page() will still do maj_flt/min_flt
> > accounting for that remote task/thread?
> 
> Well, that would be a data race and fundamentally buggy.
> 
> It would be ok with something like ptrace (which only works when the
> target is quiescent), but is completely wrong otherwise.
> 
> I guess it works fine in practice, and it's only statistics so even if
> you were to have a data race it doesn't much matter, but it's
> definitely conceptually very very wrong.
> 
> The fault stats should be about who does the fault (they are about the
> _thread_) not about who the fault is done to (which is about the
> _mm_).
> 
> Allocating the fault data to somebody else sounds frankly silly and
> stupid to me, exactly because it's (a) racy and (b) not even
> conceptually correct. The other thread literally _isn't_ doing a major
> page fault, for crissake!
> 
> Now, there are some actual per-mm statistics too (the rss stuff etc),
> and it's fundamentally harder exactly because of the shared data. See
> the mm_counter stuff etc. Those are not about who does soemthing, they
> are about the resulting MM state.

I see.  How about I move another small step further to cover GUP (to be
explicit, faultin_page() and fixup_user_fault())?

GUP needs the per-task accounting, but not the perf events.  We can do that by
slightly changing the new approach into:

        bool major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);

        if (major)
                current->maj_flt++;
        else
                current->min_flt++;

        if (!regs)
                return ret;

        if (major)
                perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
        else
                perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);

With the change we will always account that onto current task.  Since there're
GUP calls that are not even accounted at all, e.g., get_user_pages_remote()
with tsk==NULL: for these calls, we also account these page faults onto current
task.

Another major benefit I can see (besides a completely cleaned up accounting) is
that we can remove the task_struct pointer in the whole GUP code, because
AFAICT that's only used for this pf accounting either in faultin_page() or
fixup_user_fault(), which seems questionable itself now to not use current...

Any opinions?

Thanks,

--
Peter Xu


  reply	other threads:[~2020-06-18 14:38 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-15 22:15 [PATCH 00/25] mm: Page fault accounting cleanups Peter Xu
2020-06-15 22:15 ` [PATCH 01/25] mm/um: Fix extra accounting for page fault retries Peter Xu
2020-06-15 22:15 ` [PATCH 02/25] mm: Introduce mm_fault_accounting() Peter Xu
2020-06-15 22:32   ` Linus Torvalds
2020-06-15 23:19     ` Peter Xu
2020-06-16 19:00       ` Andrew Morton
2020-06-17 16:26         ` Peter Xu
2020-06-15 22:15 ` [PATCH 03/25] mm/alpha: Use mm_fault_accounting() Peter Xu
2020-06-15 22:15 ` [PATCH 04/25] mm/arc: " Peter Xu
2020-06-15 22:15 ` [PATCH 05/25] mm/arm: " Peter Xu
2020-06-15 22:15 ` [PATCH 06/25] mm/arm64: " Peter Xu
2020-06-16  7:43   ` Will Deacon
2020-06-16 15:59     ` Peter Xu
2020-06-15 22:15 ` [PATCH 07/25] mm/csky: " Peter Xu
2020-06-17  7:04   ` Guo Ren
2020-06-17 15:49     ` Peter Xu
2020-06-17 17:53       ` Linus Torvalds
2020-06-17 19:58         ` Peter Xu
2020-06-17 20:15           ` Linus Torvalds
2020-06-18 14:38             ` Peter Xu [this message]
2020-06-18 17:15               ` Linus Torvalds
2020-06-18 21:24                 ` Peter Xu
2020-06-18 22:28                   ` Peter Xu
2020-06-18 22:59                     ` Linus Torvalds
2020-06-15 22:15 ` [PATCH 08/25] mm/hexagon: " Peter Xu
2020-06-15 22:15 ` [PATCH 09/25] mm/ia64: " Peter Xu
2020-06-15 22:15 ` [PATCH 10/25] mm/m68k: " Peter Xu
2020-06-15 22:15 ` [PATCH 11/25] mm/microblaze: " Peter Xu
2020-06-15 22:15 ` [PATCH 12/25] mm/mips: " Peter Xu
2020-06-15 22:15 ` [PATCH 13/25] mm/nds32: " Peter Xu
2020-06-17  1:05   ` Greentime Hu
2020-06-15 22:15 ` [PATCH 14/25] mm/nios2: " Peter Xu
2020-06-15 22:15 ` [PATCH 15/25] mm/openrisc: " Peter Xu
2020-06-16 18:11   ` Stafford Horne
2020-06-15 22:15 ` [PATCH 16/25] mm/parisc: " Peter Xu
2020-06-15 22:15 ` [PATCH 17/25] mm/powerpc: " Peter Xu
2020-06-15 22:16 ` [PATCH 18/25] mm/riscv: " Peter Xu
2020-06-18 23:49   ` Palmer Dabbelt
2020-06-19  0:12     ` Peter Xu
2020-06-15 22:23 ` [PATCH 19/25] mm/s390: " Peter Xu
2020-06-16 15:59   ` Alexander Gordeev
2020-06-16 16:35     ` Peter Xu
2020-06-17  6:19       ` Christian Borntraeger
2020-06-17 16:06         ` Peter Xu
2020-06-17 16:14           ` Christian Borntraeger
2020-06-17 16:44             ` Peter Xu
2020-06-15 22:23 ` [PATCH 20/25] mm/sh: " Peter Xu
2020-07-20 21:25   ` Rich Felker
2020-07-20 22:05     ` Peter Xu
2020-06-15 22:23 ` [PATCH 21/25] mm/sparc32: " Peter Xu
2020-06-15 22:23 ` [PATCH 22/25] mm/sparc64: " Peter Xu
2020-06-15 22:23 ` [PATCH 23/25] mm/unicore32: " Peter Xu
2020-06-15 22:23 ` [PATCH 24/25] mm/x86: " Peter Xu
2020-06-15 22:23 ` [PATCH 25/25] mm/xtensa: " Peter Xu
2020-06-15 23:13   ` Max Filippov
2020-06-16 18:55 ` [PATCH 00/25] mm: Page fault accounting cleanups Linus Torvalds
2020-06-16 21:03   ` Peter Xu
2020-06-17  0:55   ` Michael Ellerman
2020-06-17  8:04     ` Will Deacon
2020-06-17 16:10       ` Peter Xu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200618143801.GK76766@xz-x1 \
    --to=peterx@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=gerald.schaefer@de.ibm.com \
    --cc=guoren@kernel.org \
    --cc=linux-csky@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [PATCH 07/25] mm/csky: Use mm_fault_accounting()' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox