From: Usama Arif <usama.arif@linux.dev>
To: Andrew Morton <akpm@linux-foundation.org>,
david@kernel.org, lorenzo.stoakes@oracle.com,
willy@infradead.org, linux-mm@kvack.org
Cc: fvdl@google.com, hannes@cmpxchg.org, riel@surriel.com,
shakeel.butt@linux.dev, kas@kernel.org, baohua@kernel.org,
dev.jain@arm.com, baolin.wang@linux.alibaba.com,
npache@redhat.com, Liam.Howlett@oracle.com, ryan.roberts@arm.com,
Vlastimil Babka <vbabka@kernel.org>,
lance.yang@linux.dev, linux-kernel@vger.kernel.org,
kernel-team@meta.com, maddy@linux.ibm.com, mpe@ellerman.id.au,
linuxppc-dev@lists.ozlabs.org, hca@linux.ibm.com,
gor@linux.ibm.com, agordeev@linux.ibm.com,
borntraeger@linux.ibm.com, svens@linux.ibm.com,
linux-s390@vger.kernel.org, Usama Arif <usama.arif@linux.dev>
Subject: [RFC v2 01/21] mm: thp: make split_huge_pmd functions return int for error propagation
Date: Thu, 26 Feb 2026 03:23:30 -0800 [thread overview]
Message-ID: <20260226113233.3987674-2-usama.arif@linux.dev> (raw)
In-Reply-To: <20260226113233.3987674-1-usama.arif@linux.dev>
Currently split cannot fail, but future patches will add lazy PTE page
table allocation. With lazy PTE page table allocation at THP split time
__split_huge_pmd() calls pte_alloc_one() which can fail if order-0
allocation cannot be satisfied.
Split functions currently return void, so callers have no way to detect
this failure. The PMD would remain huge, but callers assumed the split
succeeded and proceeded to operate on that basis — interpreting a huge PMD
entry as a page table pointer could result in a kernel bug.
Change __split_huge_pmd(), split_huge_pmd(), split_huge_pmd_if_needed()
and split_huge_pmd_address() to return 0 on success (-ENOMEM on
allocation failure in later patch). Convert the split_huge_pmd macro
to a static inline function that propagates the return value. The return
values will be handled by the callers in future commits.
The CONFIG_TRANSPARENT_HUGEPAGE=n stubs are changed to return 0.
No behaviour change is expected with this patch.
Signed-off-by: Usama Arif <usama.arif@linux.dev>
---
include/linux/huge_mm.h | 34 ++++++++++++++++++----------------
mm/huge_memory.c | 16 ++++++++++------
2 files changed, 28 insertions(+), 22 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a4d9f964dfdea..e4cbf5afdbe7e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -419,7 +419,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped);
void reparent_deferred_split_queue(struct mem_cgroup *memcg);
#endif
-void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+int __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze);
/**
@@ -448,15 +448,15 @@ static inline bool pmd_is_huge(pmd_t pmd)
return false;
}
-#define split_huge_pmd(__vma, __pmd, __address) \
- do { \
- pmd_t *____pmd = (__pmd); \
- if (pmd_is_huge(*____pmd)) \
- __split_huge_pmd(__vma, __pmd, __address, \
- false); \
- } while (0)
+static inline int split_huge_pmd(struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long address)
+{
+ if (pmd_is_huge(*pmd))
+ return __split_huge_pmd(vma, pmd, address, false);
+ return 0;
+}
-void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
+int split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
bool freeze);
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
@@ -651,13 +651,15 @@ static inline int try_folio_split_to_order(struct folio *folio,
static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {}
static inline void reparent_deferred_split_queue(struct mem_cgroup *memcg) {}
-#define split_huge_pmd(__vma, __pmd, __address) \
- do { } while (0)
-
-static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long address, bool freeze) {}
-static inline void split_huge_pmd_address(struct vm_area_struct *vma,
- unsigned long address, bool freeze) {}
+static inline int split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address)
+{
+ return 0;
+}
+static inline int __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address, bool freeze) { return 0; }
+static inline int split_huge_pmd_address(struct vm_area_struct *vma,
+ unsigned long address, bool freeze) { return 0; }
static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
bool freeze) {}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8003d3a498220..125ff36f475de 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3273,7 +3273,7 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
__split_huge_pmd_locked(vma, pmd, address, freeze);
}
-void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+int __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze)
{
spinlock_t *ptl;
@@ -3287,20 +3287,22 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
split_huge_pmd_locked(vma, range.start, pmd, freeze);
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
+
+ return 0;
}
-void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
+int split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
bool freeze)
{
pmd_t *pmd = mm_find_pmd(vma->vm_mm, address);
if (!pmd)
- return;
+ return 0;
- __split_huge_pmd(vma, pmd, address, freeze);
+ return __split_huge_pmd(vma, pmd, address, freeze);
}
-static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address)
+static inline int split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address)
{
/*
* If the new address isn't hpage aligned and it could previously
@@ -3309,7 +3311,9 @@ static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned
if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) &&
range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE),
ALIGN(address, HPAGE_PMD_SIZE)))
- split_huge_pmd_address(vma, address, false);
+ return split_huge_pmd_address(vma, address, false);
+
+ return 0;
}
void vma_adjust_trans_huge(struct vm_area_struct *vma,
--
2.47.3
next prev parent reply other threads:[~2026-02-26 11:33 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-26 11:23 [RFC v2 00/21] mm: thp: lazy PTE page table allocation at PMD split Usama Arif
2026-02-26 11:23 ` Usama Arif [this message]
2026-02-26 11:23 ` [RFC v2 02/21] mm: thp: propagate split failure from vma_adjust_trans_huge() Usama Arif
2026-02-26 11:23 ` [RFC v2 03/21] mm: thp: handle split failure in copy_huge_pmd() Usama Arif
2026-02-26 11:23 ` [RFC v2 04/21] mm: thp: handle split failure in do_huge_pmd_wp_page() Usama Arif
2026-02-26 11:23 ` [RFC v2 05/21] mm: thp: handle split failure in zap_pmd_range() Usama Arif
2026-02-26 11:23 ` [RFC v2 06/21] mm: thp: handle split failure in wp_huge_pmd() Usama Arif
2026-02-26 11:23 ` [RFC v2 07/21] mm: thp: retry on split failure in change_pmd_range() Usama Arif
2026-02-26 11:23 ` [RFC v2 08/21] mm: thp: handle split failure in follow_pmd_mask() Usama Arif
2026-02-26 11:23 ` [RFC v2 09/21] mm: handle walk_page_range() failure from THP split Usama Arif
2026-02-26 11:23 ` [RFC v2 10/21] mm: thp: handle split failure in mremap move_page_tables() Usama Arif
2026-02-26 11:23 ` [RFC v2 11/21] mm: thp: handle split failure in userfaultfd move_pages() Usama Arif
2026-02-26 11:23 ` [RFC v2 12/21] mm: thp: handle split failure in device migration Usama Arif
2026-02-26 11:23 ` [RFC v2 13/21] mm: huge_mm: Make sure all split_huge_pmd calls are checked Usama Arif
2026-02-26 11:23 ` [RFC v2 14/21] mm: thp: allocate PTE page tables lazily at split time Usama Arif
2026-02-26 11:23 ` [RFC v2 15/21] mm: thp: remove pgtable_trans_huge_{deposit/withdraw} when not needed Usama Arif
2026-02-26 11:23 ` [RFC v2 16/21] mm: thp: add THP_SPLIT_PMD_FAILED counter Usama Arif
2026-02-26 14:22 ` Usama Arif
2026-02-26 11:23 ` [RFC v2 17/21] selftests/mm: add THP PMD split test infrastructure Usama Arif
2026-02-26 11:23 ` [RFC v2 18/21] selftests/mm: add partial_mprotect test for change_pmd_range Usama Arif
2026-02-26 11:23 ` [RFC v2 19/21] selftests/mm: add partial_mlock test Usama Arif
2026-02-26 11:23 ` [RFC v2 20/21] selftests/mm: add partial_mremap test for move_page_tables Usama Arif
2026-02-26 11:23 ` [RFC v2 21/21] selftests/mm: add madv_dontneed_partial test 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=20260226113233.3987674-2-usama.arif@linux.dev \
--to=usama.arif@linux.dev \
--cc=Liam.Howlett@oracle.com \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=borntraeger@linux.ibm.com \
--cc=david@kernel.org \
--cc=dev.jain@arm.com \
--cc=fvdl@google.com \
--cc=gor@linux.ibm.com \
--cc=hannes@cmpxchg.org \
--cc=hca@linux.ibm.com \
--cc=kas@kernel.org \
--cc=kernel-team@meta.com \
--cc=lance.yang@linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=maddy@linux.ibm.com \
--cc=mpe@ellerman.id.au \
--cc=npache@redhat.com \
--cc=riel@surriel.com \
--cc=ryan.roberts@arm.com \
--cc=shakeel.butt@linux.dev \
--cc=svens@linux.ibm.com \
--cc=vbabka@kernel.org \
--cc=willy@infradead.org \
/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