From: David Hildenbrand <david@redhat.com>
To: Uladzislau Rezki <urezki@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
Ping Fang <pifang@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Roman Gushchin <guro@fb.com>, Michal Hocko <mhocko@suse.com>,
Oscar Salvador <osalvador@suse.de>,
Linux Memory Management List <linux-mm@kvack.org>
Subject: Re: [PATCH v1] mm/vmalloc: fix exact allocations with an alignment > 1
Date: Wed, 29 Sep 2021 18:10:24 +0200 [thread overview]
Message-ID: <f4884091-8448-bebc-61f1-4af3226ca00d@redhat.com> (raw)
In-Reply-To: <CA+KHdyVC1KCP2r2st_TmfmXaPZ49ym0gyN31CwLZfE=ipLGjmA@mail.gmail.com>
On 29.09.21 18:08, Uladzislau Rezki wrote:
>>> Could you please to be more specific? I mean how is it connected with huge
>>> pages mappings? Huge-pages are which have order > 0. Or you mean that
>>> a special alignments are needed for mapping huge pages?
>>
>> Let me try to clarify:
>>
>>
>> KASAN does an exact allocation when onlining a memory block,
>> __vmalloc_node_range() will try placing huge pages first, increasing the
>> alignment to e.g., "1 << PMD_SHIFT".
>>
>> If we increase the search length in find_vmap_lowest_match(), that
>> search will fail if the exact allocation is surrounded by other
>> allocations. In that case, we won't place a huge page although we could
>> -- because find_vmap_lowest_match() would be imprecise for alignments >
>> PAGE_SIZE.
>>
>>
>> Memory blocks we online/offline on x86 are at least 128MB. The KASAN
>> "overhead" we have to allocate is 1/8 of that -- 16 MB, so essentially 8
>> huge pages.
>>
>> __vmalloc_node_range() will increase the alignment to 2MB to try placing
>> huge pages first. find_vmap_lowest_match() will search within the given
>> exact 16MB are a 18MB area (size + align), which won't work. So
>> __vmalloc_node_range() will fallback to the original PAGE_SIZE alignment
>> and shift=PAGE_SHIFT.
>>
>> __vmalloc_area_node() will set the set_vm_area_page_order effectively to
>> 0 -- small pages.
>>
>> Does that make sense or am I missing something?
>>
> Thank you for clarification. OK, we come back anyway to the "problem" with fixed
> range and an exact allocation plus a special alignment > PAGE_SIZE. Thus the
> KASAN will not make use of huge pages mappings and go with regular instead
> as a fallback path. But we would like to utilize huge-mappings for KASAN.
>
> I will send the patch you tested and add your "tested-by" tag. Does it
> sound good?
Feel free to add
Tested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Thanks!
--
Thanks,
David / dhildenb
prev parent reply other threads:[~2021-09-29 16:10 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-08 13:27 [PATCH v1] mm/vmalloc: fix exact allocations with an alignment > 1 David Hildenbrand
2021-09-13 8:44 ` Uladzislau Rezki
2021-09-14 19:15 ` Uladzislau Rezki
2021-09-15 9:02 ` David Hildenbrand
2021-09-16 19:34 ` Uladzislau Rezki
2021-09-17 8:47 ` David Hildenbrand
2021-09-21 22:13 ` Uladzislau Rezki
2021-09-22 8:34 ` David Hildenbrand
2021-09-22 10:41 ` Uladzislau Rezki
2021-09-23 17:42 ` David Hildenbrand
2021-09-24 12:42 ` David Hildenbrand
2021-09-29 14:30 ` Uladzislau Rezki
2021-09-29 14:40 ` David Hildenbrand
2021-09-29 14:49 ` Uladzislau Rezki
2021-09-29 15:05 ` David Hildenbrand
2021-09-29 16:08 ` Uladzislau Rezki
2021-09-29 16:10 ` David Hildenbrand [this message]
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=f4884091-8448-bebc-61f1-4af3226ca00d@redhat.com \
--to=david@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=guro@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=osalvador@suse.de \
--cc=pifang@redhat.com \
--cc=urezki@gmail.com \
/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).