From: Baolin Wang <baolin.wang@linux.alibaba.com>
To: Zi Yan <ziy@nvidia.com>
Cc: akpm@linux-foundation.org, hughd@google.com, david@redhat.com,
lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com,
npache@redhat.com, ryan.roberts@arm.com, dev.jain@arm.com,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] mm: huge_memory: disallow hugepages if the system-wide THP sysfs settings are disabled
Date: Fri, 30 May 2025 09:51:46 +0800 [thread overview]
Message-ID: <5acbfc5f-81b6-40e2-b87b-ac50423172f0@linux.alibaba.com> (raw)
In-Reply-To: <33577DDE-D88E-44F9-9B91-7AA46EACCCE8@nvidia.com>
On 2025/5/29 23:10, Zi Yan wrote:
> On 29 May 2025, at 4:23, Baolin Wang wrote:
>
>> The MADV_COLLAPSE will ignore the system-wide Anon THP sysfs settings, which
>> means that even though we have disabled the Anon THP configuration, MADV_COLLAPSE
>> will still attempt to collapse into a Anon THP. This violates the rule we have
>> agreed upon: never means never.
>>
>> To address this issue, should check whether the Anon THP configuration is disabled
>> in thp_vma_allowable_orders(), even when the TVA_ENFORCE_SYSFS flag is set.
>>
>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>> ---
>> include/linux/huge_mm.h | 23 +++++++++++++++++++----
>> 1 file changed, 19 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
>> index 2f190c90192d..199ddc9f04a1 100644
>> --- a/include/linux/huge_mm.h
>> +++ b/include/linux/huge_mm.h
>> @@ -287,20 +287,35 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
>> unsigned long orders)
>> {
>> /* Optimization to check if required orders are enabled early. */
>> - if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) {
>> - unsigned long mask = READ_ONCE(huge_anon_orders_always);
>> + if (vma_is_anonymous(vma)) {
>> + unsigned long always = READ_ONCE(huge_anon_orders_always);
>> + unsigned long madvise = READ_ONCE(huge_anon_orders_madvise);
>> + unsigned long inherit = READ_ONCE(huge_anon_orders_inherit);
>> + unsigned long mask = always | madvise;
>> +
>> + /*
>> + * If the system-wide THP/mTHP sysfs settings are disabled,
>> + * then we should never allow hugepages.
>> + */
>> + if (!(mask & orders) && !(hugepage_global_enabled() && (inherit & orders)))
>
> Can you explain the logic here? Is it equivalent to:
> 1. if THP is set to always, always_mask & orders == 0, or
> 2. if THP if set to madvise, madvise_mask & order == 0, or
> 3. if THP is set to inherit, inherit_mask & order == 0?
>
> I cannot figure out why (always | madvise) & orders does not check
> THP enablement case, but inherit & orders checks hugepage_global_enabled().
Sorry for not being clear. Let me try again:
Now we can control per-sized mTHP through ‘huge_anon_orders_always’, so
always does not need to rely on the check of hugepage_global_enabled().
For madvise, referring to David's suggestion: “allowing for collapsing
in a VM without VM_HUGEPAGE in the "madvise" mode would be fine", so we
can just check 'huge_anon_orders_madvise' without relying on
hugepage_global_enabled().
In the case where hugepage_global_enabled() is enabled, we need to check
whether the 'inherit' has enabled the corresponding orders.
In summary, the current strategy is:
1. If always & orders == 0, and madvise & orders == 0, and
hugepage_global_enabled() == false (global THP settings are not
enabled), it means mTHP of the orders are prohibited from being used,
then madvise_collapse() is forbidden.
2. If always & orders == 0, and madvise & orders == 0, and
hugepage_global_enabled() == true (global THP settings are enabled), and
inherit & orders == 0, it means mTHP of the orders are still prohibited
from being used, and thus madvise_collapse() is not allowed.
next prev parent reply other threads:[~2025-05-30 1:51 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-29 8:23 [PATCH 0/2] fix MADV_COLLAPSE issue if THP " Baolin Wang
2025-05-29 8:23 ` [PATCH 1/2] mm: huge_memory: disallow hugepages if the system-wide THP sysfs " Baolin Wang
2025-05-29 15:10 ` Zi Yan
2025-05-30 1:51 ` Baolin Wang [this message]
2025-05-30 2:04 ` Zi Yan
2025-05-30 2:21 ` Baolin Wang
2025-05-30 2:22 ` Zi Yan
2025-05-29 8:23 ` [PATCH 2/2] mm: shmem: disallow hugepages if the system-wide shmem " Baolin Wang
2025-05-29 15:21 ` Zi Yan
2025-05-30 1:58 ` Baolin Wang
2025-05-30 2:17 ` Zi Yan
2025-05-30 2:32 ` Baolin Wang
2025-05-30 2:35 ` Zi Yan
2025-05-30 2:39 ` Baolin Wang
2025-05-30 8:04 ` [PATCH 0/2] fix MADV_COLLAPSE issue if THP " Ryan Roberts
2025-05-30 8:44 ` David Hildenbrand
2025-05-30 8:47 ` Lorenzo Stoakes
2025-05-30 8:52 ` David Hildenbrand
2025-05-30 9:07 ` Ryan Roberts
2025-05-30 9:14 ` Lorenzo Stoakes
2025-05-30 8:59 ` Ryan Roberts
2025-05-30 9:10 ` David Hildenbrand
2025-05-30 9:16 ` David Hildenbrand
2025-05-30 9:34 ` Lorenzo Stoakes
2025-05-30 9:52 ` Baolin Wang
2025-05-30 10:45 ` David Hildenbrand
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=5acbfc5f-81b6-40e2-b87b-ac50423172f0@linux.alibaba.com \
--to=baolin.wang@linux.alibaba.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=dev.jain@arm.com \
--cc=hughd@google.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=npache@redhat.com \
--cc=ryan.roberts@arm.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
all inboxes | Powered by JetHome®