From: Luiz Capitulino <luizcap@redhat.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, david@kernel.org
Cc: ryan.roberts@arm.com, akpm@linux-foundation.org,
lorenzo.stoakes@oracle.com
Subject: [PATCH 00/11] mm: thp: always enable mTHP support
Date: Mon, 15 Dec 2025 16:16:42 -0500 [thread overview]
Message-ID: <cover.1765833318.git.luizcap@redhat.com> (raw)
Today, if an architecture implements has_transparent_hugepage() and the CPU
lacks support for PMD-sized pages, the THP code disables all THP, including
mTHP. In addition, the kernel lacks a well defined API to check for
PMD-sized page support. It currently relies on has_transparent_hugepage()
and thp_disabled_by_hw(), but they are not well defined and are tied to
THP support.
This series addresses both issues by introducing a new well defined API
to query PMD-sized page support: pgtable_has_pmd_leaves(). Using this
new helper, we ensure that mTHP remains enabled even when the
architecture or CPU doesn't support PMD-sized pages.
Please, note that we need to do the same refactoring for
has_transparent_pud_hugepage(). I actually have patches for this one too,
I'm planning to post it as a follow up to this series in the near future.
Thanks to David Hildenbrand for suggesting this improvement and for
providing guidance (all bugs and misconcentpions are mine).
This is on top of latest mm-new branch commit d0a24447990a ("mm/hugetlb:
fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather").
v1
--
- Call init_arch_has_pmd_leaves() from start_kernel()
- Keep pgtable_has_pmd_leaves() calls tied to CONFIG_TRANSPARENT_HUGEPAGE (David)
- Clear PUD_ORDER when clearing PMD_ORDER (David)
- Small changelog improvements (David)
- Rebased on top of latest mm-new
Luiz Capitulino (11):
docs: tmpfs: remove implementation detail reference
mm: introduce pgtable_has_pmd_leaves()
drivers: dax: use pgtable_has_pmd_leaves()
drivers: i915 selftest: use pgtable_has_pmd_leaves()
drivers: nvdimm: use pgtable_has_pmd_leaves()
mm: debug_vm_pgtable: use pgtable_has_pmd_leaves()
mm: shmem: use pgtable_has_pmd_leaves()
treewide: rename has_transparent_hugepage() to arch_has_pmd_leaves()
mm: replace thp_disabled_by_hw() with pgtable_has_pmd_leaves()
mm/thp: always enable mTHP support
mm/thp: x86: cleanup PSE feature bit usage
Documentation/filesystems/tmpfs.rst | 5 ++---
arch/mips/include/asm/pgtable.h | 4 ++--
arch/mips/mm/tlb-r4k.c | 4 ++--
arch/powerpc/include/asm/book3s/64/hash-4k.h | 2 +-
arch/powerpc/include/asm/book3s/64/hash-64k.h | 2 +-
arch/powerpc/include/asm/book3s/64/pgtable.h | 10 +++++-----
arch/powerpc/include/asm/book3s/64/radix.h | 2 +-
arch/powerpc/mm/book3s64/hash_pgtable.c | 4 ++--
arch/s390/include/asm/pgtable.h | 4 ++--
arch/x86/include/asm/pgtable.h | 6 ------
arch/x86/include/asm/pgtable_32.h | 6 ++++++
drivers/dax/dax-private.h | 2 +-
.../gpu/drm/i915/gem/selftests/huge_pages.c | 4 +++-
drivers/nvdimm/pfn_devs.c | 6 ++++--
include/linux/huge_mm.h | 7 -------
include/linux/pgtable.h | 11 ++++++++--
init/main.c | 1 +
mm/debug_vm_pgtable.c | 20 +++++++++----------
mm/huge_memory.c | 13 ++++++------
mm/memory.c | 10 +++++++++-
mm/shmem.c | 9 +++++----
21 files changed, 73 insertions(+), 59 deletions(-)
--
2.52.0
next reply other threads:[~2025-12-15 21:17 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-12-15 21:16 Luiz Capitulino [this message]
2025-12-15 21:16 ` [PATCH 01/11] docs: tmpfs: remove implementation detail reference Luiz Capitulino
2025-12-16 7:40 ` Baolin Wang
2025-12-15 21:16 ` [PATCH 02/11] mm: introduce pgtable_has_pmd_leaves() Luiz Capitulino
2025-12-15 21:16 ` [PATCH 03/11] drivers: dax: use pgtable_has_pmd_leaves() Luiz Capitulino
2025-12-15 21:16 ` [PATCH 04/11] drivers: i915 selftest: " Luiz Capitulino
2025-12-15 21:16 ` [PATCH 05/11] drivers: nvdimm: " Luiz Capitulino
2025-12-15 21:16 ` [PATCH 06/11] mm: debug_vm_pgtable: " Luiz Capitulino
2025-12-15 21:16 ` [PATCH 07/11] mm: shmem: " Luiz Capitulino
2025-12-16 7:52 ` Baolin Wang
2025-12-16 13:47 ` Luiz Capitulino
2025-12-17 2:03 ` Baolin Wang
2025-12-17 18:50 ` Luiz Capitulino
2025-12-15 21:16 ` [PATCH 08/11] treewide: rename has_transparent_hugepage() to arch_has_pmd_leaves() Luiz Capitulino
2025-12-15 21:16 ` [PATCH 09/11] mm: replace thp_disabled_by_hw() with pgtable_has_pmd_leaves() Luiz Capitulino
2025-12-15 21:16 ` [PATCH 10/11] mm/thp: always enable mTHP support Luiz Capitulino
2025-12-15 21:16 ` [PATCH 11/11] mm/thp: x86: cleanup PSE feature bit usage 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=cover.1765833318.git.luizcap@redhat.com \
--to=luizcap@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=david@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=ryan.roberts@arm.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).