mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-08-27 19:53:15 -04:00
Code Issues Packages Projects Releases Wiki Activity

mm/pagemap: add PAGE_IS_ACCESSED for RWP tracking

Browse Source 
PAGEMAP_SCAN already reports PAGE_IS_WRITTEN from the inverted uffd PTE
bit, targeting the UFFDIO_WRITEPROTECT workflow.  UFFDIO_RWPROTECT reuses
the same PTE bit as a marker for read-write protection, but "has been
written" and "has been accessed" are distinct semantic signals — they
happen to share one PTE bit today only because the two implementations
share infrastructure.

Give RWP its own pagemap category so the UAPI does not conflate them:

  PAGE_IS_WRITTEN   reported on VM_UFFD_WP VMAs,  !pte_uffd(pte)
  PAGE_IS_ACCESSED  reported on VM_UFFD_RWP VMAs, !pte_uffd(pte)

Both still read the same PTE bit today, but each is scoped to the VMA
whose registered mode makes the bit meaningful.  If a future
implementation moves RWP to a separate PTE bit, only PAGE_IS_ACCESSED
switches over.

This is a UAPI narrowing.  Outside VM_UFFD_WP VMAs the uffd bit is always
clear, so PAGEMAP_SCAN used to flag PAGE_IS_WRITTEN on every present PTE
there — a meaningless duplicate of PAGE_IS_PRESENT.  Now PAGE_IS_WRITTEN
fires only inside VM_UFFD_WP VMAs.

pagemap_hugetlb_category() now takes the vma like its PTE/PMD peers.

Link: https://lore.kernel.org/20260708111417.173443-12-kirill@shutemov.name
Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
Assisted-by: Claude:claude-opus-4-6
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: James Houghton <jthoughton@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Liam Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Kiryl Shutsemau (Meta)
2026-07-08 12:14:12 +01:00
committed by Andrew Morton
parent 2d427bb016
commit 3389648819
4 changed files with 67 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
Documentation/admin-guide/mm/pagemap.rst
View File

@@ -19,8 +19,11 @@ There are four components to pagemap:
* Bit 55 pte is soft-dirty (see
Documentation/admin-guide/mm/soft-dirty.rst)
* Bit 56 page exclusively mapped (since 4.2)
* Bit 57 pte is uffd-wp write-protected (since 5.13) (see
Documentation/admin-guide/mm/userfaultfd.rst)
* Bit 57 pte is tracked by userfaultfd (since 5.13) — in a
``VM_UFFD_WP`` VMA this indicates a write-protected PTE; in a
``VM_UFFD_RWP`` VMA it indicates an RWP-protected PTE. WP and
RWP are mutually exclusive per VMA, so the meaning is
unambiguous. See Documentation/admin-guide/mm/userfaultfd.rst.
* Bit 58 pte is a guard region (since 6.15) (see madvise (2) man page)
* Bits 59-60 zero
* Bit 61 page is file-page or shared-anon (since 3.5)
@@ -244,7 +247,8 @@ in this IOCTL:
Following flags about pages are currently supported:
- ``PAGE_IS_WPALLOWED`` - Page has async-write-protection enabled
- ``PAGE_IS_WRITTEN`` - Page has been written to from the time it was write protected
- ``PAGE_IS_WRITTEN`` - Page in a ``UFFDIO_REGISTER_MODE_WP`` VMA has been
written to since it was write-protected. Only reported inside such VMAs.
- ``PAGE_IS_FILE`` - Page is file backed
- ``PAGE_IS_PRESENT`` - Page is present in the memory
- ``PAGE_IS_SWAPPED`` - Page is in swapped
@@ -252,6 +256,9 @@ Following flags about pages are currently supported:
- ``PAGE_IS_HUGE`` - Page is PMD-mapped THP or Hugetlb backed
- ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty
- ``PAGE_IS_GUARD`` - Page is a part of a guard region
- ``PAGE_IS_ACCESSED`` - Page in a ``UFFDIO_REGISTER_MODE_RWP`` VMA has been
accessed since RWP was applied. Only reported inside such VMAs. See
Documentation/admin-guide/mm/userfaultfd.rst for the RWP workflow.
The ``struct pm_scan_arg`` is used as the argument of the IOCTL.

81
fs/proc/task_mmu.c
View File

@@ -2284,7 +2284,7 @@ static const struct mm_walk_ops pagemap_ops = {
* Bits 5-54 swap offset if swapped
* Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
* Bit 56 page exclusively mapped
* Bit 57 pte is uffd-wp write-protected
* Bit 57 pte is tracked by userfaultfd (uffd-wp or RWP)
* Bit 58 pte is a guard region
* Bits 59-60 zero
* Bit 61 page is file-page or shared-anon
@@ -2419,7 +2419,7 @@ static int pagemap_release(struct inode *inode, struct file *file)
PAGE_IS_FILE | PAGE_IS_PRESENT | \
PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \
PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY | \
PAGE_IS_GUARD)
PAGE_IS_GUARD | PAGE_IS_ACCESSED)
#define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
struct pagemap_scan_private {
@@ -2438,15 +2438,17 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
if (pte_none(pte)) {
/*
* An unpopulated pte carries no uffd-wp marker, i.e. it is not
* write-protected, the same condition under which the present
* and swap cases below report PAGE_IS_WRITTEN. Report it here
* too so this generic path agrees with the PAGE_IS_WRITTEN fast
* path in pagemap_scan_pmd_entry(), which reports pte_none as
* written and, under PM_SCAN_WP_MATCHING, arms a marker. The
* fast path applies no VMA test, so neither does this.
* An unpopulated pte carries no uffd bit, i.e. it is not
* write-protected. The PAGE_IS_WRITTEN fast path in
* pagemap_scan_pmd_entry() is now gated on a VM_UFFD_WP VMA;
* gate the pte_none report here the same way so the two paths
* still agree. RWP has no such fast path and an unpopulated
* page is not part of the RWP working set, so it is reported as
* neither.
*/
return PAGE_IS_WRITTEN;
if (userfaultfd_wp(vma))
return PAGE_IS_WRITTEN;
return 0;
}
if (pte_present(pte)) {
@@ -2454,8 +2456,12 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
categories = PAGE_IS_PRESENT;
if (!pte_uffd(pte))
categories |= PAGE_IS_WRITTEN;
if (!pte_uffd(pte)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
if (p->masks_of_interest & PAGE_IS_FILE) {
page = vm_normal_page(vma, addr, pte);
@@ -2472,8 +2478,12 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
categories = PAGE_IS_SWAPPED;
if (!pte_swp_uffd_any(pte))
categories |= PAGE_IS_WRITTEN;
if (!pte_swp_uffd_any(pte)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
entry = softleaf_from_pte(pte);
if (softleaf_is_guard_marker(entry))
@@ -2522,8 +2532,12 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
struct page *page;
categories |= PAGE_IS_PRESENT;
if (!pmd_uffd(pmd))
categories |= PAGE_IS_WRITTEN;
if (!pmd_uffd(pmd)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
if (p->masks_of_interest & PAGE_IS_FILE) {
page = vm_normal_page_pmd(vma, addr, pmd);
@@ -2537,8 +2551,12 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
categories |= PAGE_IS_SOFT_DIRTY;
} else {
categories |= PAGE_IS_SWAPPED;
if (!pmd_swp_uffd(pmd))
categories |= PAGE_IS_WRITTEN;
if (!pmd_swp_uffd(pmd)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
if (pmd_swp_soft_dirty(pmd))
categories |= PAGE_IS_SOFT_DIRTY;
@@ -2571,7 +2589,8 @@ static void make_uffd_wp_pmd(struct vm_area_struct *vma,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long pagemap_hugetlb_category(pte_t pte)
static unsigned long pagemap_hugetlb_category(struct vm_area_struct *vma,
pte_t pte)
{
unsigned long categories = PAGE_IS_HUGE;
@@ -2586,8 +2605,12 @@ static unsigned long pagemap_hugetlb_category(pte_t pte)
if (pte_present(pte)) {
categories |= PAGE_IS_PRESENT;
if (!huge_pte_uffd(pte))
categories |= PAGE_IS_WRITTEN;
if (!huge_pte_uffd(pte)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
if (!PageAnon(pte_page(pte)))
categories |= PAGE_IS_FILE;
if (is_zero_pfn(pte_pfn(pte)))
@@ -2597,8 +2620,12 @@ static unsigned long pagemap_hugetlb_category(pte_t pte)
} else {
categories |= PAGE_IS_SWAPPED;
if (!pte_swp_uffd_any(pte))
categories |= PAGE_IS_WRITTEN;
if (!pte_swp_uffd_any(pte)) {
if (userfaultfd_wp(vma))
categories |= PAGE_IS_WRITTEN;
if (userfaultfd_rwp(vma))
categories |= PAGE_IS_ACCESSED;
}
if (pte_swp_soft_dirty(pte))
categories |= PAGE_IS_SOFT_DIRTY;
}
@@ -2874,7 +2901,8 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
goto flush_and_return;
}
if (!p->arg.category_anyof_mask && !p->arg.category_inverted &&
if (userfaultfd_wp(vma) && !p->arg.category_anyof_mask &&
!p->arg.category_inverted &&
p->arg.category_mask == PAGE_IS_WRITTEN &&
p->arg.return_mask == PAGE_IS_WRITTEN) {
for (addr = start; addr < end; pte++, addr += PAGE_SIZE) {
@@ -2949,7 +2977,8 @@ static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask,
/* Go the short route when not write-protecting pages. */
pte = huge_ptep_get(walk->mm, start, ptep);
categories = p->cur_vma_category | pagemap_hugetlb_category(pte);
categories = p->cur_vma_category |
pagemap_hugetlb_category(vma, pte);
if (!pagemap_scan_is_interesting_page(categories, p))
return 0;
@@ -2961,7 +2990,7 @@ static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask,
ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, ptep);
pte = huge_ptep_get(walk->mm, start, ptep);
categories = p->cur_vma_category | pagemap_hugetlb_category(pte);
categories = p->cur_vma_category | pagemap_hugetlb_category(vma, pte);
if (!pagemap_scan_is_interesting_page(categories, p))
goto out_unlock;

1
include/uapi/linux/fs.h
View File

@@ -471,6 +471,7 @@ typedef int __bitwise __kernel_rwf_t;
#define PAGE_IS_HUGE (1 << 6)
#define PAGE_IS_SOFT_DIRTY (1 << 7)
#define PAGE_IS_GUARD (1 << 8)
#define PAGE_IS_ACCESSED (1 << 9)
/*
* struct page_region - Page region with flags

1
tools/include/uapi/linux/fs.h
View File

@@ -364,6 +364,7 @@ typedef int __bitwise __kernel_rwf_t;
#define PAGE_IS_HUGE (1 << 6)
#define PAGE_IS_SOFT_DIRTY (1 << 7)
#define PAGE_IS_GUARD (1 << 8)
#define PAGE_IS_ACCESSED (1 << 9)
/*
* struct page_region - Page region with flags