From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
To: Peter Xu <peterx@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Will Deacon <will@kernel.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH 01/26] mm: Do page fault accounting in handle_mm_fault
Date: Fri, 26 Jun 2020 21:54:24 +0200 [thread overview]
Message-ID: <20200626215424.581d6077@thinkpad> (raw)
In-Reply-To: <20200624203412.GB64004@xz-x1>
On Wed, 24 Jun 2020 16:34:12 -0400
Peter Xu <peterx@redhat.com> wrote:
> On Wed, Jun 24, 2020 at 08:49:03PM +0200, Gerald Schaefer wrote:
> > On Fri, 19 Jun 2020 12:05:13 -0400
> > Peter Xu <peterx@redhat.com> wrote:
> >
> > [...]
> >
> > > @@ -4393,6 +4425,38 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
> > > mem_cgroup_oom_synchronize(false);
> > > }
> > >
> > > + if (ret & VM_FAULT_RETRY)
> > > + return ret;
> >
> > I'm wondering if this also needs a check and exit for VM_FAULT_ERROR.
> > In arch code (s390 and all others I briefly checked), the accounting
> > was skipped for VM_FAULT_ERROR case.
>
> Yes. I didn't explicitly add the check because I thought it's still OK to count
> the error cases, especially after we've discussed about
> PERF_COUNT_SW_PAGE_FAULTS in v1. So far, the major reason (iiuc) to have
> PERF_COUNT_SW_PAGE_FAULTS still in per-arch handlers is to also cover these
> corner cases like VM_FAULT_ERROR. So to me it makes sense too to also count
> them in here. But I agree it changes the old counting on most archs.
Having PERF_COUNT_SW_PAGE_FAULTS count everything including VM_FAULT_ERROR
is OK. Just major/minor accounting should be only about successes, IIRC from
v1 discussion.
The "new rules" also say
+ * - faults that never even got here (because the address
+ * wasn't valid). That includes arch_vma_access_permitted()
+ * failing above.
VM_FAULT_ERROR, and also the arch-specific VM_FAULT_BADxxx, qualify
as "address wasn't valid" I think, so they should not be counted as
major/minor.
IIRC from v1, and we want to only count success as major/minor, maybe
the rule could also be made more clear about that, e.g. like
+ * - unsuccessful faults (because the address wasn't valid)
+ * do not count. That includes arch_vma_access_permitted()
+ * failing above.
>
> Again, I don't have strong opinion either on this, just like the same to
> PERF_COUNT_SW_PAGE_FAULTS... But if no one disagree, I will change this to:
>
> if (ret & (VM_FAULT_RETRY | VM_FAULT_ERROR))
> return ret;
>
> So we try our best to follow the past.
Sounds good to me, and VM_FAULT_BADxxx should never show up here.
>
> Btw, note that there will still be some even more special corner cases. E.g.,
> for ARM64 it's also not accounted for some ARM64 specific fault errors
> (VM_FAULT_BADMAP, VM_FAULT_BADACCESS). So even if we don't count
> VM_FAULT_ERROR, we might still count these for ARM64. We can try to redefine
> VM_FAULT_ERROR in ARM64 to cover all the arch-specific errors, however that
> seems an overkill to me sololy for fault accountings, so hopefully I can ignore
> that difference.
Hmm, arm64 already does not count the VM_FAULT_BADxxx, but also does not
call handle_mm_fault() for those, so no change with this patch. arm (and
also unicore32) do count those, but also not call handle_mm_fault(), so
there would be the change that they lose accounting, IIUC.
I agree that this probably can be ignored. The code in arm64 also looks
more recent, so it's probably just a left-over in arm/unicore32 code.
Regards,
Gerald
next prev parent reply other threads:[~2020-06-26 19:54 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-19 16:05 [PATCH 00/26] mm: Page fault accounting cleanups Peter Xu
2020-06-19 16:05 ` [PATCH 01/26] mm: Do page fault accounting in handle_mm_fault Peter Xu
2020-06-24 18:49 ` Gerald Schaefer
2020-06-24 20:34 ` Peter Xu
2020-06-26 19:54 ` Gerald Schaefer [this message]
2020-06-26 21:53 ` Peter Xu
2020-06-26 22:27 ` Peter Xu
2020-06-19 16:05 ` [PATCH 02/26] mm/alpha: Use general page fault accounting Peter Xu
2020-06-19 16:05 ` [PATCH 03/26] mm/arc: " Peter Xu
2020-06-19 16:05 ` [PATCH 04/26] mm/arm: " Peter Xu
2020-06-19 16:05 ` [PATCH 05/26] mm/arm64: " Peter Xu
2020-06-19 16:05 ` [PATCH 06/26] mm/csky: " Peter Xu
2020-06-20 1:44 ` Guo Ren
2020-06-20 16:08 ` Peter Xu
2020-06-19 16:05 ` [PATCH 07/26] mm/hexagon: " Peter Xu
2020-06-19 16:05 ` [PATCH 08/26] mm/ia64: " Peter Xu
2020-06-19 16:05 ` [PATCH 09/26] mm/m68k: " Peter Xu
2020-06-19 16:05 ` [PATCH 10/26] mm/microblaze: " Peter Xu
2020-06-19 16:05 ` [PATCH 11/26] mm/mips: " Peter Xu
2020-06-25 8:28 ` Thomas Bogendoerfer
2020-06-19 16:05 ` [PATCH 12/26] mm/nds32: " Peter Xu
2020-06-19 16:12 ` [PATCH 13/26] mm/nios2: " Peter Xu
2020-06-19 16:12 ` [PATCH 14/26] mm/openrisc: " Peter Xu
2020-06-19 16:13 ` [PATCH 15/26] mm/parisc: " Peter Xu
2020-06-19 16:13 ` [PATCH 16/26] mm/powerpc: " Peter Xu
2020-06-19 16:13 ` [PATCH 17/26] mm/riscv: " Peter Xu
2020-06-19 16:13 ` [PATCH 18/26] mm/s390: " Peter Xu
2020-06-24 18:49 ` Gerald Schaefer
2020-06-24 20:40 ` Peter Xu
2020-06-19 16:13 ` [PATCH 19/26] mm/sh: " Peter Xu
2020-06-19 16:13 ` [PATCH 20/26] mm/sparc32: " Peter Xu
2020-06-19 16:13 ` [PATCH 21/26] mm/sparc64: " Peter Xu
2020-06-19 16:13 ` [PATCH 22/26] mm/unicore32: " Peter Xu
2020-06-19 16:13 ` [PATCH 23/26] mm/x86: " Peter Xu
2020-06-19 16:13 ` [PATCH 24/26] mm/xtensa: " Peter Xu
2020-06-19 16:14 ` [PATCH 25/26] mm: Clean up the last pieces of page fault accountings Peter Xu
2020-06-19 16:14 ` [PATCH 26/26] mm/gup: Remove task_struct pointer for all gup code Peter Xu
2020-06-26 22:31 [PATCH 00/26] mm: Page fault accounting cleanups Peter Xu
2020-06-26 22:31 ` [PATCH 01/26] mm: Do page fault accounting in handle_mm_fault Peter Xu
2020-06-29 1:52 ` John Hubbard
2020-06-29 14:56 ` 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=20200626215424.581d6077@thinkpad \
--to=gerald.schaefer@de.ibm.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mpe@ellerman.id.au \
--cc=peterx@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=will@kernel.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).