linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: David Hildenbrand <david@redhat.com>
To: Usama Arif <usamaarif642@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org
Cc: hannes@cmpxchg.org, shakeel.butt@linux.dev, riel@surriel.com,
	ziy@nvidia.com, baolin.wang@linux.alibaba.com,
	lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com,
	npache@redhat.com, ryan.roberts@arm.com,
	linux-kernel@vger.kernel.org, kernel-team@meta.com
Subject: Re: [PATCH 0/1] prctl: allow overriding system THP policy to always
Date: Thu, 8 May 2025 19:39:42 +0200	[thread overview]
Message-ID: <3f7ba97d-04d5-4ea4-9f08-6ec3584e0d4c@redhat.com> (raw)
In-Reply-To: <e706e2fc-201f-4e45-8dd9-e2e17c269466@gmail.com>

>> We did something similar with PR_SET_MEMORY_MERGE.
>>
> 
> For this you mean the prctl command would do for_each_vma and set VM_HUGEPAGE to implement point 2.

Yes. The expectation would be that the prctl is either a) triggered 
early when there are not that many VMAs yet or b) inherited during 
fork+exec such that the target process immediately gets it enabled for 
all VMAs.

> For having point 1, I think we will still need extra mm->flags, i.e. MMF_VM_THP_MADVISE/DEFER/ALWAYS/NEVER.

Yes, and it's unclear what we really want here.

> 
> I think it would have the same affect as what this patch is trying to do? But would be just more
> expensive in terms of both code changes and the cost of the actual call as you now have to walk
> all vmas. On the other hand you wont need the below diff in from v1. I do feel the current approach
> in the patch is simpler? But if your point 3 is better in terms of code maintainability, happy to make
> it the change to it in v2.

Yes. Having a toggle that

a) Changes the default of new VMAs to be VM_HUGEPAGE

b) Modifies all existing VMAs that are not VM_NOHUGEPAGE to be VM_HUGEPAGE

c) Is inherited during fork+exec

Would not add any additional checks in our already-complicated THP 
allocation logic, it simply changes the default/value of VM_HUGEPAGE.


At least to me, this sounds like better semantics. Would that make your 
use case happy?

-- 
Cheers,

David / dhildenb



  reply	other threads:[~2025-05-08 17:39 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-07 14:00 Usama Arif
2025-05-07 14:00 ` [PATCH 1/1] prctl: allow overriding system THP policy to always per process Usama Arif
2025-05-07 15:02   ` Usama Arif
2025-05-07 20:14   ` Zi Yan
2025-05-08 10:53     ` Usama Arif
2025-05-08 20:29       ` Zi Yan
2025-05-07 14:57 ` [PATCH 0/1] prctl: allow overriding system THP policy to always Zi Yan
2025-05-07 15:12   ` Usama Arif
2025-05-07 15:57     ` Zi Yan
2025-05-07 16:09       ` Usama Arif
2025-05-08  5:41         ` Yafang Shao
2025-05-08 16:04           ` Usama Arif
2025-05-09  2:15             ` Yafang Shao
2025-05-09  5:13               ` Johannes Weiner
2025-05-09  9:24                 ` Yafang Shao
2025-05-09  9:30                   ` David Hildenbrand
2025-05-09  9:43                     ` Yafang Shao
2025-05-09 16:46                       ` Johannes Weiner
2025-05-09 22:42                         ` David Hildenbrand
2025-05-09 23:34                           ` Zi Yan
2025-05-11  8:15                             ` David Hildenbrand
2025-05-11 14:08                               ` Usama Arif
2025-05-13 11:43                                 ` Yafang Shao
2025-05-13 12:04                                 ` David Hildenbrand
2025-05-11  2:08                         ` Yafang Shao
2025-05-08 11:06 ` David Hildenbrand
2025-05-08 16:35   ` Usama Arif
2025-05-08 17:39     ` David Hildenbrand [this message]
2025-05-08 18:05       ` Usama Arif

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=3f7ba97d-04d5-4ea4-9f08-6ec3584e0d4c@redhat.com \
    --to=david@redhat.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=npache@redhat.com \
    --cc=riel@surriel.com \
    --cc=ryan.roberts@arm.com \
    --cc=shakeel.butt@linux.dev \
    --cc=usamaarif642@gmail.com \
    --cc=ziy@nvidia.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