From: Lance Yang <lance.yang@linux.dev>
To: luizcap@redhat.com
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
david@kernel.org, baolin.wang@linux.alibaba.com, ziy@nvidia.com,
lance.yang@linux.dev, corbet@lwn.net, tsbogend@alpha.franken.de,
maddy@linux.ibm.com, mpe@ellerman.id.au, agordeev@linux.ibm.com,
gerald.schaefer@linux.ibm.com, hca@linux.ibm.com,
gor@linux.ibm.com, x86@kernel.org, tglx@kernel.org,
mingo@redhat.com, bp@alien8.de, hughd@google.com,
dave.hansen@linux.intel.com, djbw@kernel.org,
vishal.l.verma@intel.com, dave.jiang@intel.com,
akpm@linux-foundation.org, yintirui@huawei.com, dev.jain@arm.com,
usama.arif@linux.dev
Subject: Re: [PATCH v8 14/14] mm: thp: always enable mTHP support
Date: Sat, 3 Oct 2026 11:13:01 +0800 [thread overview]
Message-ID: <20261003031301.48957-1-lance.yang@linux.dev> (raw)
In-Reply-To: <752f528f0fed5cdc9de12b54260b0495d4e5a6cb.1789695931.git.luizcap@redhat.com>
On Thu, Sep 17, 2026 at 09:45:35PM -0400, Luiz Capitulino wrote:
>If PMD-sized pages are not supported on an architecture (ie. the
>arch implements arch_has_pmd_leaves() and it returns false) then the
>current code disables all THP, including mTHP.
>
>This commit fixes this by allowing mTHP to be always enabled for all
>archs. When PMD-sized pages are not supported, its sysfs entry won't be
>created and their mapping will be disallowed at page-fault time.
>
>Similarly, this commit implements the following changes for shmem in
>shmem_allowable_huge_orders():
>
> - Drop the pgtable_has_pmd_leaves() check so that mTHP sizes are
> considered
> - Filter out PMD and PUD orders from allowable orders when
> PMD-sized pages are not supported by the CPU
Nit: "and PUD" can go.
David mentioned
"
There is no need to disable PUD-orders, as shmem does not support PUD-orders
(unlike DAX). So you can keep it simpler here.
"
in v4
https://lore.kernel.org/all/ff7bcd65-d444-4da1-890e-75504303ec3f@kernel.org/
Cheers, Lance
next prev parent reply other threads:[~2026-10-03 3:13 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-18 1:45 [PATCH v8 00/14] mm: thp: always enable mTHP support Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 01/14] docs: tmpfs: remove implementation detail reference Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 02/14] mm: shmem: shmem_getattr(): set blksize to highest supported THP order Luiz Capitulino
2026-10-02 19:11 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 03/14] mm: introduce pgtable_has_pmd_leaves() Luiz Capitulino
2026-09-22 2:07 ` Zi Yan
2026-10-02 19:13 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 04/14] drivers: dax: use pgtable_has_pmd_leaves() Luiz Capitulino
2026-09-22 2:08 ` Zi Yan
2026-10-02 19:15 ` David Hildenbrand (Arm)
2026-10-03 14:55 ` Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 05/14] drivers: nvdimm: " Luiz Capitulino
2026-10-02 19:18 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 06/14] mm: debug_vm_pgtable: " Luiz Capitulino
2026-10-02 19:19 ` David Hildenbrand (Arm)
2026-10-03 14:55 ` Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 07/14] mm: shmem: allow THP support determination at folio allocation time Luiz Capitulino
2026-09-22 2:20 ` Zi Yan
2026-09-23 1:37 ` Luiz Capitulino
2026-10-02 19:23 ` David Hildenbrand (Arm)
2026-10-03 15:09 ` Luiz Capitulino
2026-10-08 1:50 ` Baolin Wang
2026-10-08 2:14 ` Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 08/14] s390: move has_transparent_hugepage() out of THP guard Luiz Capitulino
2026-09-22 2:21 ` Zi Yan
2026-10-02 19:24 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 09/14] powerpc: " Luiz Capitulino
2026-10-02 19:28 ` David Hildenbrand (Arm)
2026-10-03 15:44 ` Luiz Capitulino
2026-10-05 4:52 ` Christophe Leroy (CS GROUP)
2026-10-05 20:40 ` Luiz Capitulino
2026-10-06 4:48 ` Christophe Leroy (CS GROUP)
2026-09-18 1:45 ` [PATCH v8 10/14] mips: " Luiz Capitulino
2026-10-02 19:29 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 11/14] x86: " Luiz Capitulino
2026-09-18 1:45 ` [PATCH v8 12/14] treewide: introduce arch_has_pmd_leaves() Luiz Capitulino
2026-09-22 2:26 ` Zi Yan
2026-09-18 1:45 ` [PATCH v8 13/14] mm: replace thp_disabled_by_hw() with pgtable_has_pmd_leaves() Luiz Capitulino
2026-10-02 19:32 ` David Hildenbrand (Arm)
2026-09-18 1:45 ` [PATCH v8 14/14] mm: thp: always enable mTHP support Luiz Capitulino
2026-09-18 9:01 ` Baolin Wang
2026-09-21 10:29 ` Usama Arif
2026-09-22 2:06 ` Luiz Capitulino
2026-10-03 3:13 ` Lance Yang [this message]
2026-10-03 15:50 ` Luiz Capitulino
2026-10-08 2:07 ` Baolin Wang
2026-10-08 12:08 ` Luiz Capitulino
2026-09-18 10:37 ` [PATCH v8 00/14] " Usama Arif
2026-09-18 14:01 ` Luiz Capitulino
2026-09-18 20:23 ` David Hildenbrand (Arm)
2026-09-21 10:36 ` Usama Arif
2026-09-22 2:11 ` Luiz Capitulino
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=20261003031301.48957-1-lance.yang@linux.dev \
--to=lance.yang@linux.dev \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=dave.jiang@intel.com \
--cc=david@kernel.org \
--cc=dev.jain@arm.com \
--cc=djbw@kernel.org \
--cc=gerald.schaefer@linux.ibm.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luizcap@redhat.com \
--cc=maddy@linux.ibm.com \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=tglx@kernel.org \
--cc=tsbogend@alpha.franken.de \
--cc=usama.arif@linux.dev \
--cc=vishal.l.verma@intel.com \
--cc=x86@kernel.org \
--cc=yintirui@huawei.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.