| 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: <7702eec12584bb3332b0013a8372f0f61e006886.1761288179.git.lorenzo.stoakes@oracle.com>
Date: Fri, 24 Oct 2025 08:41:22 +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 06/12] mm: avoid unnecessary use of is_swap_pmd()
PMD 'non-swap' swap entries are currently used for PMD-level migration
entries and device private entries.
To add to the confusion in this terminology we use is_swap_pmd() in an
inconsistent way similar to how is_swap_pte() was being used - sometimes
adopting the convention that pmd_none(), !pmd_present() implies PMD 'swap'
entry, sometimes not.
This patch handles the low-hanging fruit of cases where we can simply
substitute other predicates for is_swap_pmd().
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
fs/proc/task_mmu.c | 15 ++++++++++---
include/linux/swapops.h | 16 +++++++++++--
mm/huge_memory.c | 4 +++-
mm/memory.c | 50 +++++++++++++++++++++++------------------
mm/page_table_check.c | 12 ++++++----
5 files changed, 65 insertions(+), 32 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3c8be2579253..1c32a0e2b965 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1059,10 +1059,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
bool present = false;
struct folio *folio;
+ if (pmd_none(*pmd))
+ return;
if (pmd_present(*pmd)) {
page = vm_normal_page_pmd(vma, addr, *pmd);
present = true;
- } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
+ } else if (unlikely(thp_migration_supported())) {
swp_entry_t entry = pmd_to_swp_entry(*pmd);
if (is_pfn_swap_entry(entry))
@@ -1999,6 +2001,9 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr,
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
+ if (pmd_none(pmd))
+ goto populate_pagemap;
+
if (pmd_present(pmd)) {
page = pmd_page(pmd);
@@ -2009,7 +2014,7 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr,
flags |= PM_UFFD_WP;
if (pm->show_pfn)
frame = pmd_pfn(pmd) + idx;
- } else if (thp_migration_supported() && is_swap_pmd(pmd)) {
+ } else if (thp_migration_supported()) {
swp_entry_t entry = pmd_to_swp_entry(pmd);
unsigned long offset;
@@ -2036,6 +2041,7 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr,
flags |= PM_FILE;
}
+populate_pagemap:
for (; addr != end; addr += PAGE_SIZE, idx++) {
u64 cur_flags = flags;
pagemap_entry_t pme;
@@ -2396,6 +2402,9 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
{
unsigned long categories = PAGE_IS_HUGE;
+ if (pmd_none(pmd))
+ return categories;
+
if (pmd_present(pmd)) {
struct page *page;
@@ -2413,7 +2422,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
categories |= PAGE_IS_PFNZERO;
if (pmd_soft_dirty(pmd))
categories |= PAGE_IS_SOFT_DIRTY;
- } else if (is_swap_pmd(pmd)) {
+ } else {
swp_entry_t swp;
categories |= PAGE_IS_SWAPPED;
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 728e27e834be..8642e590504a 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -573,7 +573,13 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
static inline int is_pmd_migration_entry(pmd_t pmd)
{
- return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
+ swp_entry_t entry;
+
+ if (pmd_present(pmd))
+ return 0;
+
+ entry = pmd_to_swp_entry(pmd);
+ return is_migration_entry(entry);
}
#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
@@ -621,7 +627,13 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
*/
static inline int is_pmd_device_private_entry(pmd_t pmd)
{
- return is_swap_pmd(pmd) && is_device_private_entry(pmd_to_swp_entry(pmd));
+ swp_entry_t entry;
+
+ if (pmd_present(pmd))
+ return 0;
+
+ entry = pmd_to_swp_entry(pmd);
+ return is_device_private_entry(entry);
}
#else /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 370ecfd6a182..a59718f85ec3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2428,9 +2428,11 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
{
+ if (pmd_none(pmd))
+ return pmd;
if (pmd_present(pmd))
pmd = pmd_clear_uffd_wp(pmd);
- else if (is_swap_pmd(pmd))
+ else
pmd = pmd_swp_clear_uffd_wp(pmd);
return pmd;
diff --git a/mm/memory.c b/mm/memory.c
index 19615bcf234f..83828548ef5f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1375,6 +1375,7 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
next = pmd_addr_end(addr, end);
if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)) {
int err;
+
VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
addr, dst_vma, src_vma);
@@ -6331,35 +6332,40 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
if (pmd_none(*vmf.pmd) &&
thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PMD_ORDER)) {
ret = create_huge_pmd(&vmf);
- if (!(ret & VM_FAULT_FALLBACK))
+ if (ret & VM_FAULT_FALLBACK)
+ goto fallback;
+ else
return ret;
- } else {
- vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
+ }
- if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
- if (is_pmd_device_private_entry(vmf.orig_pmd))
- return do_huge_pmd_device_private(&vmf);
+ vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
+ if (pmd_none(vmf.orig_pmd))
+ goto fallback;
- if (is_pmd_migration_entry(vmf.orig_pmd))
- pmd_migration_entry_wait(mm, vmf.pmd);
- return 0;
- }
- if (pmd_trans_huge(vmf.orig_pmd)) {
- if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
- return do_huge_pmd_numa_page(&vmf);
+ if (unlikely(!pmd_present(vmf.orig_pmd))) {
+ if (is_pmd_device_private_entry(vmf.orig_pmd))
+ return do_huge_pmd_device_private(&vmf);
- if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
- !pmd_write(vmf.orig_pmd)) {
- ret = wp_huge_pmd(&vmf);
- if (!(ret & VM_FAULT_FALLBACK))
- return ret;
- } else {
- huge_pmd_set_accessed(&vmf);
- return 0;
- }
+ if (is_pmd_migration_entry(vmf.orig_pmd))
+ pmd_migration_entry_wait(mm, vmf.pmd);
+ return 0;
+ }
+ if (pmd_trans_huge(vmf.orig_pmd)) {
+ if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
+ return do_huge_pmd_numa_page(&vmf);
+
+ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
+ !pmd_write(vmf.orig_pmd)) {
+ ret = wp_huge_pmd(&vmf);
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
+ } else {
+ huge_pmd_set_accessed(&vmf);
+ return 0;
}
}
+fallback:
return handle_pte_fault(&vmf);
}
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 43f75d2f7c36..f5f25e120f69 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -215,10 +215,14 @@ EXPORT_SYMBOL(__page_table_check_ptes_set);
static inline void page_table_check_pmd_flags(pmd_t pmd)
{
- if (pmd_present(pmd) && pmd_uffd_wp(pmd))
- WARN_ON_ONCE(pmd_write(pmd));
- else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd))
- WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd)));
+ if (pmd_present(pmd)) {
+ if (pmd_uffd_wp(pmd))
+ WARN_ON_ONCE(pmd_write(pmd));
+ } else if (pmd_swp_uffd_wp(pmd)) {
+ swp_entry_t entry = pmd_to_swp_entry(pmd);
+
+ WARN_ON_ONCE(swap_cached_writable(entry));
+ }
}
void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
--
2.51.0
Powered by blists - more mailing lists