diff options
| author | Kiryl Shutsemau (Meta) <kas@kernel.org> | 2026-07-08 12:14:11 +0100 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2026-08-04 19:18:38 -0700 |
| commit | 2d427bb0163978875dfbbcec7b7dd0c1320f419e (patch) | |
| tree | 93afd795828dbf6f63ac79d7f018aa38d1f3538c /include | |
| parent | 6eab8f2cc6465ab093b5171ece815ec24e678d4e (diff) | |
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 <kas@kernel.org>
Assisted-by: Claude:claude-opus-4-6
Reviewed-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>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/huge_mm.h | 7 | ||||
| -rw-r--r-- | include/linux/userfaultfd_k.h | 24 | ||||
| -rw-r--r-- | include/uapi/linux/userfaultfd.h | 12 |
3 files changed, 39 insertions, 4 deletions
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; diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 7b78aa3b5318..d803e76d47ad 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -25,7 +25,8 @@ #define UFFD_API ((__u64)0xAA) #define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ UFFDIO_REGISTER_MODE_WP | \ - UFFDIO_REGISTER_MODE_MINOR) + UFFDIO_REGISTER_MODE_MINOR | \ + UFFDIO_REGISTER_MODE_RWP) #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ @@ -42,7 +43,8 @@ UFFD_FEATURE_WP_UNPOPULATED | \ UFFD_FEATURE_POISON | \ UFFD_FEATURE_WP_ASYNC | \ - UFFD_FEATURE_MOVE) + UFFD_FEATURE_MOVE | \ + UFFD_FEATURE_RWP) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -54,13 +56,15 @@ (__u64)1 << _UFFDIO_MOVE | \ (__u64)1 << _UFFDIO_WRITEPROTECT | \ (__u64)1 << _UFFDIO_CONTINUE | \ - (__u64)1 << _UFFDIO_POISON) + (__u64)1 << _UFFDIO_POISON | \ + (__u64)1 << _UFFDIO_RWPROTECT) #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_WRITEPROTECT | \ (__u64)1 << _UFFDIO_CONTINUE | \ - (__u64)1 << _UFFDIO_POISON) + (__u64)1 << _UFFDIO_POISON | \ + (__u64)1 << _UFFDIO_RWPROTECT) /* * Valid ioctl command number range with this API is from 0x00 to |
