From 2d427bb0163978875dfbbcec7b7dd0c1320f419e Mon Sep 17 00:00:00 2001 From: "Kiryl Shutsemau (Meta)" Date: Wed, 8 Jul 2026 12:14:11 +0100 Subject: mm/userfaultfd: add RWP fault delivery and expose UFFDIO_REGISTER_MODE_RWP Wire the fault side of read-write protection tracking and turn the userspace interface on. An RWP-protected PTE is PAGE_NONE with the uffd bit set. The PROT_NONE triggers a fault on any access; the uffd bit distinguishes it from plain mprotect(PROT_NONE) or NUMA hinting. Fault dispatch, per level: PTE handle_pte_fault() -> do_uffd_rwp() PMD __handle_mm_fault() -> do_huge_pmd_uffd_rwp() hugetlb hugetlb_fault() -> hugetlb_handle_userfault() The RWP branches gate on userfaultfd_pte_rwp() / userfaultfd_huge_pmd_rwp() (VM_UFFD_RWP plus the uffd bit) and fall through to do_numa_page() / do_huge_pmd_numa_page() otherwise. Each delivers a UFFD_PAGEFAULT_FLAG_RWP message through handle_userfault(); the handler resolves it with UFFDIO_RWPROTECT clearing MODE_RWP. userfaultfd_must_wait() and userfaultfd_huge_must_wait() add matching protnone+uffd waiters so sync-mode fault handlers block correctly. Expose the UAPI: UFFDIO_REGISTER_MODE_RWP -> UFFD_API_REGISTER_MODES UFFD_FEATURE_RWP -> UFFD_API_FEATURES _UFFDIO_RWPROTECT -> UFFD_API_RANGE_IOCTLS UFFD_API_RANGE_IOCTLS_BASIC UFFD_FEATURE_RWP is masked out at UFFDIO_API time when PROT_NONE is not available or VM_UFFD_RWP aliases VM_NONE (32-bit), so userspace never sees an advertised-but-broken feature. Works on anonymous, shmem, and hugetlb memory. Link: https://lore.kernel.org/20260708111417.173443-11-kirill@shutemov.name Signed-off-by: Kiryl Shutsemau Assisted-by: Claude:claude-opus-4-6 Reviewed-by: Mike Rapoport (Microsoft) Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: James Houghton Cc: Jonathan Corbet Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Paolo Bonzini Cc: Peter Xu Cc: Sean Christopherson Cc: SeongJae Park Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 7 +++++++ include/linux/userfaultfd_k.h | 24 ++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b34e8e5e5f9a..19a7bfce279e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -529,6 +529,8 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); +vm_fault_t do_huge_pmd_uffd_rwp(struct vm_fault *vmf); + vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf); extern struct folio *huge_zero_folio; @@ -723,6 +725,11 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } +static inline vm_fault_t do_huge_pmd_uffd_rwp(struct vm_fault *vmf) +{ + return 0; +} + static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index d31648ba898d..6f7245609bd4 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -241,6 +241,18 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, return userfaultfd_wp(vma) && pmd_uffd(pmd); } +static inline bool userfaultfd_pte_rwp(struct vm_area_struct *vma, + pte_t pte) +{ + return userfaultfd_rwp(vma) && pte_uffd(pte); +} + +static inline bool userfaultfd_huge_pmd_rwp(struct vm_area_struct *vma, + pmd_t pmd) +{ + return userfaultfd_rwp(vma) && pmd_uffd(pmd); +} + static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return vma_test_any_mask(vma, __VMA_UFFD_FLAGS); @@ -371,6 +383,18 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, return false; } +static inline bool userfaultfd_pte_rwp(struct vm_area_struct *vma, + pte_t pte) +{ + return false; +} + +static inline bool userfaultfd_huge_pmd_rwp(struct vm_area_struct *vma, + pmd_t pmd) +{ + return false; +} + static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return false; -- cgit v1.2.3