diff options
Diffstat (limited to 'include/linux/userfaultfd_k.h')
| -rw-r--r-- | include/linux/userfaultfd_k.h | 206 |
1 files changed, 118 insertions, 88 deletions
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index fd5f42765497..a4351cffc60c 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -21,7 +21,11 @@ #include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ -#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) +#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_MINOR | \ + VM_UFFD_WP | VM_UFFD_RWP) + +#define __VMA_UFFD_FLAGS mk_vma_flags_from_masks(VMA_UFFD_MISSING, VMA_UFFD_WP, \ + VMA_UFFD_MINOR, VMA_UFFD_RWP) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -80,6 +84,39 @@ struct userfaultfd_ctx { extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); +/* VMA userfaultfd operations */ +struct vm_uffd_ops { + /* Checks if a VMA can support userfaultfd */ + bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags); + /* + * Called to resolve UFFDIO_CONTINUE request. + * Should return the folio found at pgoff in the VMA's pagecache if it + * exists or ERR_PTR otherwise. + * The returned folio is locked and with reference held. + */ + struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff); + /* + * Called during resolution of UFFDIO_COPY request. + * Should allocate and return a folio or NULL if allocation fails. + */ + struct folio *(*alloc_folio)(struct vm_area_struct *vma, + unsigned long addr); + /* + * Called during resolution of UFFDIO_COPY request. + * Should only be called with a folio returned by alloc_folio() above. + * The folio will be set to locked. + * Returns 0 on success, error code on failure. + */ + int (*filemap_add)(struct folio *folio, struct vm_area_struct *vma, + unsigned long addr); + /* + * Called during resolution of UFFDIO_COPY request on the error + * handling path. + * Should revert the operation of ->filemap_add(). + */ + void (*filemap_remove)(struct folio *folio, struct vm_area_struct *vma); +}; + /* A combined operation mode + behavior flags. */ typedef unsigned int __bitwise uffd_flags_t; @@ -111,31 +148,14 @@ static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_at /* Flags controlling behavior. These behavior changes are mode-independent. */ #define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) -extern int mfill_atomic_install_pte(pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, struct page *page, - bool newly_allocated, uffd_flags_t flags); - -extern ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start, - unsigned long src_start, unsigned long len, - uffd_flags_t flags); -extern ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, - unsigned long dst_start, - unsigned long len); -extern ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, - unsigned long len, uffd_flags_t flags); -extern ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, - unsigned long len, uffd_flags_t flags); -extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, - unsigned long len, bool enable_wp); extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); +extern int mrwprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, bool enable_rwp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); -ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, - unsigned long src_start, unsigned long len, __u64 flags); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, @@ -151,7 +171,8 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, /* * Never enable huge pmd sharing on some uffd registered vmas: * - * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. + * - VM_UFFD_WP and VM_UFFD_RWP VMAs, because the write protect / access + * tracking information is per pgtable entry. * * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for * VMAs which share huge pmds. (If you have two mappings to the same @@ -161,85 +182,86 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, */ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); + return vma_test_any_mask(vma, + mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_RWP, + VMA_UFFD_MINOR)); } /* - * Don't do fault around for either WP or MINOR registered uffd range. For + * Don't do fault around for WP, RWP or MINOR registered uffd range. For * MINOR registered range, fault around will be a total disaster and ptes can * be installed without notifications; for WP it should mostly be fine as long * as the fault around checks for pte_none() before the installation, however - * to be super safe we just forbid it. + * to be super safe we just forbid it; for RWP, pre-faulted neighbours would + * be indistinguishable from accessed pages in PAGEMAP_SCAN (PAGE_IS_ACCESSED) + * and pollute the tracked working set, so each page must be populated by its + * own fault. */ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); + return vma_test_any_mask(vma, + mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_RWP, + VMA_UFFD_MINOR)); } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { - return vma->vm_flags & VM_UFFD_MISSING; + return vma_test_any_mask(vma, VMA_UFFD_MISSING); } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { - return vma->vm_flags & VM_UFFD_WP; + return vma_test_any_mask(vma, VMA_UFFD_WP); } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { - return vma->vm_flags & VM_UFFD_MINOR; + return vma_test_any_mask(vma, VMA_UFFD_MINOR); +} + +static inline bool userfaultfd_rwp(struct vm_area_struct *vma) +{ + /* + * Callers gate PAGE_NONE usage on this; PAGE_NONE is a BUILD_BUG() + * without CONFIG_ARCH_HAS_PTE_PROTNONE, so fold to false. + */ + if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_PROTNONE)) + return false; + return vma_test_single_mask(vma, VMA_UFFD_RWP); +} + +static inline bool userfaultfd_protected(struct vm_area_struct *vma) +{ + return userfaultfd_wp(vma) || userfaultfd_rwp(vma); } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { - return userfaultfd_wp(vma) && pte_uffd_wp(pte); + return userfaultfd_wp(vma) && pte_uffd(pte); } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { - return userfaultfd_wp(vma) && pmd_uffd_wp(pmd); + return userfaultfd_wp(vma) && pmd_uffd(pmd); } -static inline bool userfaultfd_armed(struct vm_area_struct *vma) +static inline bool userfaultfd_pte_rwp(struct vm_area_struct *vma, + pte_t pte) { - return vma->vm_flags & __VM_UFFD_FLAGS; + return userfaultfd_rwp(vma) && pte_uffd(pte); } -static inline bool vma_can_userfault(struct vm_area_struct *vma, - vm_flags_t vm_flags, - bool wp_async) +static inline bool userfaultfd_huge_pmd_rwp(struct vm_area_struct *vma, + pmd_t pmd) { - vm_flags &= __VM_UFFD_FLAGS; - - if (vma->vm_flags & VM_DROPPABLE) - return false; - - if ((vm_flags & VM_UFFD_MINOR) && - (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) - return false; - - /* - * If wp async enabled, and WP is the only mode enabled, allow any - * memory type. - */ - if (wp_async && (vm_flags == VM_UFFD_WP)) - return true; - - /* - * If user requested uffd-wp but not enabled pte markers for - * uffd-wp, then shmem & hugetlbfs are not supported but only - * anonymous. - */ - if (!uffd_supports_wp_marker() && (vm_flags & VM_UFFD_WP) && - !vma_is_anonymous(vma)) - return false; + return userfaultfd_rwp(vma) && pmd_uffd(pmd); +} - /* By default, allow any of anon|shmem|hugetlb */ - return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || - vma_is_shmem(vma); +static inline bool userfaultfd_armed(struct vm_area_struct *vma) +{ + return vma_test_any_mask(vma, __VMA_UFFD_FLAGS); } static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) @@ -270,25 +292,7 @@ extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); extern bool userfaultfd_wp_async(struct vm_area_struct *vma); - -void userfaultfd_reset_ctx(struct vm_area_struct *vma); - -struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end); - -int userfaultfd_register_range(struct userfaultfd_ctx *ctx, - struct vm_area_struct *vma, - vm_flags_t vm_flags, - unsigned long start, unsigned long end, - bool wp_async); - -void userfaultfd_release_new(struct userfaultfd_ctx *ctx); - -void userfaultfd_release_all(struct mm_struct *mm, - struct userfaultfd_ctx *ctx); +extern bool userfaultfd_rwp_async(struct vm_area_struct *vma); static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) { @@ -308,10 +312,10 @@ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) } /* - * Returns true if this is a swap pte and was uffd-wp wr-protected in either - * forms (pte marker or a normal swap pte), false otherwise. + * Returns true if this swap pte carries uffd-tracked state in either + * form (pte marker or a normal swap pte), false otherwise. */ -static inline bool pte_swp_uffd_wp_any(pte_t pte) +static inline bool pte_swp_uffd_any(pte_t pte) { if (!uffd_supports_wp_marker()) return false; @@ -319,7 +323,7 @@ static inline bool pte_swp_uffd_wp_any(pte_t pte) if (pte_present(pte)) return false; - if (pte_swp_uffd_wp(pte)) + if (pte_swp_uffd(pte)) return true; if (pte_is_uffd_wp_marker(pte)) @@ -364,6 +368,16 @@ static inline bool userfaultfd_minor(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_rwp(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool userfaultfd_protected(struct vm_area_struct *vma) +{ + return false; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { @@ -376,6 +390,17 @@ 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) { @@ -446,6 +471,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_rwp_async(struct vm_area_struct *vma) +{ + return false; +} + static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) { return false; @@ -457,10 +487,10 @@ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) } /* - * Returns true if this is a swap pte and was uffd-wp wr-protected in either - * forms (pte marker or a normal swap pte), false otherwise. + * Returns true if this swap pte carries uffd-tracked state in either + * form (pte marker or a normal swap pte), false otherwise. */ -static inline bool pte_swp_uffd_wp_any(pte_t pte) +static inline bool pte_swp_uffd_any(pte_t pte) { return false; } |