| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <d578c86d96040f070a1be88441fccf262b92647e.1761288179.git.lorenzo.stoakes@oracle.com>
Date: Fri, 24 Oct 2025 08:41:24 +0100
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Christian Borntraeger <borntraeger@...ux.ibm.com>,
Janosch Frank <frankja@...ux.ibm.com>,
Claudio Imbrenda <imbrenda@...ux.ibm.com>,
David Hildenbrand <david@...hat.com>,
Alexander Gordeev <agordeev@...ux.ibm.com>,
Gerald Schaefer <gerald.schaefer@...ux.ibm.com>,
Heiko Carstens <hca@...ux.ibm.com>, Vasily Gorbik <gor@...ux.ibm.com>,
Sven Schnelle <svens@...ux.ibm.com>, Zi Yan <ziy@...dia.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
"Liam R . Howlett" <Liam.Howlett@...cle.com>,
Nico Pache <npache@...hat.com>, Ryan Roberts <ryan.roberts@....com>,
Dev Jain <dev.jain@....com>, Barry Song <baohua@...nel.org>,
Lance Yang <lance.yang@...ux.dev>,
Kemeng Shi <shikemeng@...weicloud.com>,
Kairui Song <kasong@...cent.com>, Nhat Pham <nphamcs@...il.com>,
Baoquan He <bhe@...hat.com>, Chris Li <chrisl@...nel.org>,
Peter Xu <peterx@...hat.com>, Matthew Wilcox <willy@...radead.org>,
Jason Gunthorpe <jgg@...pe.ca>, Leon Romanovsky <leon@...nel.org>,
Muchun Song <muchun.song@...ux.dev>,
Oscar Salvador <osalvador@...e.de>, Vlastimil Babka <vbabka@...e.cz>,
Mike Rapoport <rppt@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>, Michal Hocko <mhocko@...e.com>,
Jann Horn <jannh@...gle.com>, Matthew Brost <matthew.brost@...el.com>,
Joshua Hahn <joshua.hahnjy@...il.com>, Rakie Kim <rakie.kim@...com>,
Byungchul Park <byungchul@...com>, Gregory Price <gourry@...rry.net>,
Ying Huang <ying.huang@...ux.alibaba.com>,
Alistair Popple <apopple@...dia.com>, Pedro Falcato <pfalcato@...e.de>,
Pasha Tatashin <pasha.tatashin@...een.com>,
Rik van Riel <riel@...riel.com>, Harry Yoo <harry.yoo@...cle.com>,
kvm@...r.kernel.org, linux-s390@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
linux-mm@...ck.org
Subject: [RFC PATCH 08/12] mm/huge_memory: refactor copy_huge_pmd() non-present logic
Right now we are inconsistent in our use of thp_migration_supported():
static inline bool thp_migration_supported(void)
{
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
}
And simply having arbitrary and ugly #ifdef
CONFIG_ARCH_ENABLE_THP_MIGRATION blocks in code.
This is exhibited in copy_huge_pmd(), which inserts a large #ifdef
CONFIG_ARCH_ENABLE_THP_MIGRATION block and an if-branch which is difficult
to follow
It's difficult to follow the logic of such a large function and the
non-present PMD logic is clearly separate as it sits in a giant if-branch.
Therefore this patch both separates out the logic and utilises
thp_migration_supported().
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
mm/huge_memory.c | 109 +++++++++++++++++++++++++----------------------
1 file changed, 59 insertions(+), 50 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e0fe1c3e01c9..755d38f82aec 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1773,6 +1773,62 @@ void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
update_mmu_cache_pmd(vma, addr, pmd);
}
+static void copy_huge_non_present_pmd(
+ struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+ struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+ pmd_t pmd, pgtable_t pgtable)
+{
+ swp_entry_t entry = pmd_to_swp_entry(pmd);
+ struct folio *src_folio;
+
+ VM_WARN_ON(!is_pmd_non_present_folio_entry(pmd));
+
+ if (is_writable_migration_entry(entry) ||
+ is_readable_exclusive_migration_entry(entry)) {
+ entry = make_readable_migration_entry(swp_offset(entry));
+ pmd = swp_entry_to_pmd(entry);
+ if (pmd_swp_soft_dirty(*src_pmd))
+ pmd = pmd_swp_mksoft_dirty(pmd);
+ if (pmd_swp_uffd_wp(*src_pmd))
+ pmd = pmd_swp_mkuffd_wp(pmd);
+ set_pmd_at(src_mm, addr, src_pmd, pmd);
+ } else if (is_device_private_entry(entry)) {
+ /*
+ * For device private entries, since there are no
+ * read exclusive entries, writable = !readable
+ */
+ if (is_writable_device_private_entry(entry)) {
+ entry = make_readable_device_private_entry(swp_offset(entry));
+ pmd = swp_entry_to_pmd(entry);
+
+ if (pmd_swp_soft_dirty(*src_pmd))
+ pmd = pmd_swp_mksoft_dirty(pmd);
+ if (pmd_swp_uffd_wp(*src_pmd))
+ pmd = pmd_swp_mkuffd_wp(pmd);
+ set_pmd_at(src_mm, addr, src_pmd, pmd);
+ }
+
+ src_folio = pfn_swap_entry_folio(entry);
+ VM_WARN_ON(!folio_test_large(src_folio));
+
+ folio_get(src_folio);
+ /*
+ * folio_try_dup_anon_rmap_pmd does not fail for
+ * device private entries.
+ */
+ folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
+ dst_vma, src_vma);
+ }
+
+ add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+ mm_inc_nr_ptes(dst_mm);
+ pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
+ if (!userfaultfd_wp(dst_vma))
+ pmd = pmd_swp_clear_uffd_wp(pmd);
+ set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+}
+
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
@@ -1818,59 +1874,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
ret = -EAGAIN;
pmd = *src_pmd;
-#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
- if (unlikely(is_swap_pmd(pmd))) {
- swp_entry_t entry = pmd_to_swp_entry(pmd);
-
- VM_WARN_ON(!is_pmd_non_present_folio_entry(pmd));
-
- if (is_writable_migration_entry(entry) ||
- is_readable_exclusive_migration_entry(entry)) {
- entry = make_readable_migration_entry(swp_offset(entry));
- pmd = swp_entry_to_pmd(entry);
- if (pmd_swp_soft_dirty(*src_pmd))
- pmd = pmd_swp_mksoft_dirty(pmd);
- if (pmd_swp_uffd_wp(*src_pmd))
- pmd = pmd_swp_mkuffd_wp(pmd);
- set_pmd_at(src_mm, addr, src_pmd, pmd);
- } else if (is_device_private_entry(entry)) {
- /*
- * For device private entries, since there are no
- * read exclusive entries, writable = !readable
- */
- if (is_writable_device_private_entry(entry)) {
- entry = make_readable_device_private_entry(swp_offset(entry));
- pmd = swp_entry_to_pmd(entry);
-
- if (pmd_swp_soft_dirty(*src_pmd))
- pmd = pmd_swp_mksoft_dirty(pmd);
- if (pmd_swp_uffd_wp(*src_pmd))
- pmd = pmd_swp_mkuffd_wp(pmd);
- set_pmd_at(src_mm, addr, src_pmd, pmd);
- }
-
- src_folio = pfn_swap_entry_folio(entry);
- VM_WARN_ON(!folio_test_large(src_folio));
-
- folio_get(src_folio);
- /*
- * folio_try_dup_anon_rmap_pmd does not fail for
- * device private entries.
- */
- folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page,
- dst_vma, src_vma);
- }
-
- add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
- mm_inc_nr_ptes(dst_mm);
- pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
- if (!userfaultfd_wp(dst_vma))
- pmd = pmd_swp_clear_uffd_wp(pmd);
- set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+ if (unlikely(thp_migration_supported() && is_swap_pmd(pmd))) {
+ copy_huge_non_present_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr,
+ dst_vma, src_vma, pmd, pgtable);
ret = 0;
goto out_unlock;
}
-#endif
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
--
2.51.0
Powered by blists - more mailing lists