From: Yang Shi <shy828301@gmail.com>
To: Jiri Slaby <jirislaby@kernel.org>
Cc: Rik van Riel <riel@surriel.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
kernel-team@fb.com, Matthew Wilcox <willy@infradead.org>,
Christoph Lameter <cl@linux.com>
Subject: Re: [PATCH v2] mm: align larger anonymous mappings on THP boundaries
Date: Tue, 16 Jan 2024 12:55:08 -0800 [thread overview]
Message-ID: <CAHbLzkp-s1rr3496rpgx_td75waE=P=sv=5OCK9HWvWjmz-0GA@mail.gmail.com> (raw)
In-Reply-To: <3193bf5b-4e22-412f-8c5b-68574942d9bc@kernel.org>
On Tue, Jan 16, 2024 at 4:09 AM Jiri Slaby <jirislaby@kernel.org> wrote:
>
> On 16. 01. 24, 12:53, Jiri Slaby wrote:
> > Hi,
> >
> > On 09. 08. 22, 20:24, Rik van Riel wrote:
> >> Align larger anonymous memory mappings on THP boundaries by
> >> going through thp_get_unmapped_area if THPs are enabled for
> >> the current process.
> >>
> >> With this patch, larger anonymous mappings are now THP aligned.
> >> When a malloc library allocates a 2MB or larger arena, that
> >> arena can now be mapped with THPs right from the start, which
> >> can result in better TLB hit rates and execution time.
> >
> > This appears to break 32bit processes on x86_64 (at least). In
> > particular, 32bit kernel or firefox builds in our build system.
> >
> > Reverting this on top of 6.7 makes it work again.
> >
> > Downstream report:
> > https://bugzilla.suse.com/show_bug.cgi?id=1218841
> >
> > So running:
> > pahole -J --btf_gen_floats -j --lang_exclude=rust
> > --skip_encoding_btf_inconsistent_proto --btf_gen_optimized .tmp_vmlinux.btf
> >
> > crashes or errors out with some random errors:
> > [182671] STRUCT idr's field 'idr_next' offset=128 bit_size=0 type=181346
> > Error emitting field
> >
> > strace shows mmap() fails with ENOMEM right before the errors:
> > 1223 mmap2(NULL, 5783552, PROT_READ|PROT_WRITE,
> > MAP_PRIVATE|MAP_ANONYMOUS, -1, 0 <unfinished ...>
> > ...
> > 1223 <... mmap2 resumed>) = -1 ENOMEM (Cannot allocate
> > memory)
It should be due to the virtual address space size on 32-bit machine.
> >
> > Note the .tmp_vmlinux.btf above can be arbitrary, but likely large
> > enough. For reference, one is available at:
> > https://decibel.fi.muni.cz/~xslaby/n/btf
> >
> > Any ideas?
>
> This works around the problem, of course (but is a band-aid, not a fix):
>
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1829,7 +1829,7 @@ get_unmapped_area(struct file *file, unsigned long
> addr, unsigned long len,
> */
> pgoff = 0;
> get_area = shmem_get_unmapped_area;
> - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
> + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
> !in_32bit_syscall()) {
> /* Ensures that larger anonymous mappings are THP
> aligned. */
> get_area = thp_get_unmapped_area;
> }
>
>
> thp_get_unmapped_area() does not take care of the legacy stuff...
Thanks for the report. I think we can just make
thp_get_unmapped_area() no-op on 32 bit.
>
> regards,
> --
> js
> suse labs
>
next prev parent reply other threads:[~2024-01-16 20:55 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-09 18:24 [PATCH v2] mm: align larger anonymous mappings on THP boundaries Rik van Riel
2022-08-10 17:06 ` Yang Shi
2024-01-16 11:53 ` Jiri Slaby
2024-01-16 12:09 ` Jiri Slaby
2024-01-16 19:16 ` Suren Baghdasaryan
2024-01-16 20:56 ` Yang Shi
2024-01-16 21:57 ` Suren Baghdasaryan
2024-01-16 22:25 ` Yang Shi
2024-01-16 22:30 ` Suren Baghdasaryan
2024-01-16 23:14 ` Yang Shi
2024-01-17 17:40 ` Kees Cook
2024-01-17 23:32 ` Yang Shi
2024-01-18 0:01 ` Suren Baghdasaryan
2024-01-18 0:13 ` Yang Shi
2024-01-18 0:29 ` Suren Baghdasaryan
2024-01-18 1:34 ` Suren Baghdasaryan
2024-01-18 2:10 ` Suren Baghdasaryan
2024-01-16 20:55 ` Yang Shi [this message]
2024-01-18 0:07 ` Yang Shi
2024-01-18 0:09 ` Suren Baghdasaryan
2024-01-18 0:11 ` Suren Baghdasaryan
2024-01-18 0:15 ` Yang Shi
2024-01-18 0:28 ` Suren Baghdasaryan
2024-01-18 7:04 ` Jiri Slaby
2024-01-18 17:48 ` Suren Baghdasaryan
2024-01-18 18:42 ` Yang Shi
2024-01-18 18:42 ` Yang Shi
2024-01-20 13:43 ` Linux regression tracking #adding (Thorsten Leemhuis)
2024-01-20 15:47 ` Linux regression tracking #adding (Thorsten Leemhuis)
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='CAHbLzkp-s1rr3496rpgx_td75waE=P=sv=5OCK9HWvWjmz-0GA@mail.gmail.com' \
--to=shy828301@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=jirislaby@kernel.org \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=riel@surriel.com \
--cc=willy@infradead.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).