// SPDX-License-Identifier: GPL-2.0-only /* * mm/userfaultfd.c * * Copyright (C) 2015 Red Hat, Inc. */ #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" static __always_inline struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len) { /* * Make sure that the dst range is both valid and fully within a * single existing vma. */ struct vm_area_struct *dst_vma; dst_vma = find_vma(dst_mm, dst_start); if (!dst_vma) return NULL; if (dst_start < dst_vma->vm_start || dst_start + len > dst_vma->vm_end) return NULL; /* * Check the vma is registered in uffd, this is required to * enforce the VM_MAYWRITE check done at uffd registration * time. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) return NULL; return dst_vma; } /* * Install PTEs, to map dst_addr (within dst_vma) to page. * * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem * and anon, and for both shared and private VMAs. */ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy) { int ret; pte_t _dst_pte, *dst_pte; bool writable = dst_vma->vm_flags & VM_WRITE; bool vm_shared = dst_vma->vm_flags & VM_SHARED; bool page_in_cache = page->mapping; spinlock_t *ptl; struct inode *inode; pgoff_t offset, max_off; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; /* * Always mark a PTE as write-protected when needed, regardless of * VM_WRITE, which the user might change. */ if (wp_copy) { _dst_pte = pte_mkuffd_wp(_dst_pte); writable = false; } if (writable) _dst_pte = pte_mkwrite(_dst_pte); else /* * We need this to make sure write bit removed; as mk_pte() * could return a pte with write bit set. */ _dst_pte = pte_wrprotect(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (vma_is_shmem(dst_vma)) { /* serialize against truncate with the page table lock */ inode = dst_vma->vm_file->f_inode; offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); ret = -EFAULT; if (unlikely(offset >= max_off)) goto out_unlock; } ret = -EEXIST; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ if (!pte_none_mostly(*dst_pte)) goto out_unlock; if (page_in_cache) { /* Usually, cache pages are already added to LRU */ if (newly_allocated) lru_cache_add(page); page_add_file_rmap(page, dst_vma, false); } else { page_add_new_anon_rmap(page, dst_vma, dst_addr); lru_cache_add_inactive_or_unevictable(page, dst_vma); } /* * Must happen after rmap, as mm_counter() checks mapping (via * PageAnon()), which is set by __page_set_anon_rmap(). */ inc_mm_counter(dst_mm, mm_counter(page)); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); return ret; } static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep, bool wp_copy) { void *page_kaddr; int ret; struct page *page; if (!*pagep) { ret = -ENOMEM; page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr); if (!page) goto out; page_kaddr = kmap_local_page(page); /* * The read mmap_lock is held here. Despite the * mmap_lock being read recursive a deadlock is still * possible if a writer has taken a lock. For example: * * process A thread 1 takes read lock on own mmap_lock * process A thread 2 calls mmap, blocks taking write lock * process B thread 1 takes page fault, read lock on own mmap lock * process B thread 2 calls mmap, blocks taking write lock * process A thread 1 blocks taking read lock on process B * process B thread 1 blocks taking read lock on process A * * Disable page faults to prevent potential deadlock * and retry the copy outside the mmap_lock. */ pagefault_disable(); ret = copy_from_user(page_kaddr, (const void __user *) src_addr, PAGE_SIZE); pagefault_enable(); kunmap_local(page_kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; *pagep = page; /* don't free the page */ goto out; } flush_dcache_page(page); } else { page = *pagep; *pagep = NULL; } /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); ret = -ENOMEM; if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, page, true, wp_copy); if (ret) goto out_release; out: return ret; out_release: put_page(page); goto out; } static int mfill_zeropage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { pte_t _dst_pte, *dst_pte; spinlock_t *ptl; int ret; pgoff_t offset, max_off; struct inode *inode; _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (dst_vma->vm_file) { /* the shmem MAP_PRIVATE case requires checking the i_size */ inode = dst_vma->vm_file->f_inode; offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); ret = -EFAULT; if (unlikely(offset >= max_off)) goto out_unlock; } ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); return ret; } /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, bool wp_copy) { struct inode *inode = file_inode(dst_vma->vm_file); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); struct folio *folio; struct page *page; int ret; ret = shmem_get_folio(inode, pgoff, &folio, SGP_NOALLOC); /* Our caller expects us to return -EFAULT if we failed to find folio */ if (ret == -ENOENT) ret = -EFAULT; if (ret) goto out; if (!folio) { ret = -EFAULT; goto out; } page = folio_file_page(folio, pgoff); if (PageHWPoison(page)) { ret = -EIO; goto out_release; } ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, page, false, wp_copy); if (ret) goto out_release; folio_unlock(folio); ret = 0; out: return ret; out_release: folio_unlock(folio); folio_put(folio); goto out; } static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, address); if (!pud) return NULL; /* * Note that we didn't run this because the pmd was * missing, the *pmd may be already established and in * turn it may also be a trans_huge_pmd. */ return pmd_alloc(mm, pud, address); } #ifdef CONFIG_HUGETLB_PAGE /* * __mcopy_atomic processing for HUGETLB vmas. Note that this routine is * called with mmap_lock held, it will release mmap_lock before returning. */ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, enum mcopy_atomic_mode mode, bool wp_copy) { int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; unsigned long src_addr, dst_addr; long copied; struct page *page; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; struct address_space *mapping; /* * There is no default zero huge page for all huge page sizes as * supported by hugetlb. A PMD_SIZE huge pages may exist as used * by THP. Since we can not reliably insert a zero page, this * feature is not supported. */ if (mode == MCOPY_ATOMIC_ZEROPAGE) { mmap_read_unlock(dst_mm); return -EINVAL; } src_addr = src_start; dst_addr = dst_start; copied = 0; page = NULL; vma_hpagesize = vma_kernel_pagesize(dst_vma); /* * Validate alignment based on huge page size */ err = -EINVAL; if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1)) goto out_unlock; retry: /* * On routine entry dst_vma is set. If we had to drop mmap_lock and * retry, dst_vma will be set to NULL and we must lookup again. */ if (!dst_vma) { err = -ENOENT; dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) goto out_unlock; err = -EINVAL; if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) goto out_unlock; vm_shared = dst_vma->vm_flags & VM_SHARED; } /* * If not shared, ensure the dst_vma has a anon_vma. */ err = -ENOMEM; if (!vm_shared) { if (unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; } while (src_addr < src_start + len) { BUG_ON(dst_addr >= dst_start + len); /* * Serialize via vma_lock and hugetlb_fault_mutex. * vma_lock ensures the dst_pte remains valid even * in the case of shared pmds. fault mutex prevents * races with other faulting threads. */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(dst_vma); err = -ENOMEM; dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize); if (!dst_pte) { hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } if (mode != MCOPY_ATOMIC_CONTINUE && !huge_pte_none_mostly(huge_ptep_get(dst_pte))) { err = -EEXIST; hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, src_addr, mode, &page, wp_copy); hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); cond_resched(); if (unlikely(err == -ENOENT)) { mmap_read_unlock(dst_mm); BUG_ON(!page); err = copy_huge_page_from_user(page, (const void __user *)src_addr, vma_hpagesize / PAGE_SIZE, true); if (unlikely(err)) { err = -EFAULT; goto out; } mmap_read_lock(dst_mm); dst_vma = NULL; goto retry; } else BUG_ON(page); if (!err) { dst_addr += vma_hpagesize; src_addr += vma_hpagesize; copied += vma_hpagesize; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: mmap_read_unlock(dst_mm); out: if (page) put_page(page); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; } #else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, enum mcopy_atomic_mode mode, bool wp_copy); #endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **page, enum mcopy_atomic_mode mode, bool wp_copy) { ssize_t err; if (mode == MCOPY_ATOMIC_CONTINUE) { return mcontinue_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, wp_copy); } /* * The normal page fault path for a shmem will invoke the * fault, fill the hole in the file and COW it right away. The * result generates plain anonymous memory. So when we are * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll * generate anonymous memory directly without actually filling * the hole. For the MAP_PRIVATE case the robustness check * only happens in the pagetable (to verify it's still none) * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { if (mode == MCOPY_ATOMIC_NORMAL) err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page, wp_copy); else err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, dst_addr); } else { err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, mode != MCOPY_ATOMIC_NORMAL, wp_copy, page); } return err; } static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, enum mcopy_atomic_mode mcopy_mode, atomic_t *mmap_changing, __u64 mode) { struct vm_area_struct *dst_vma; ssize_t err; pmd_t *dst_pmd; unsigned long src_addr, dst_addr; long copied; struct page *page; bool wp_copy; /* * Sanitize the command parameters: */ BUG_ON(dst_start & ~PAGE_MASK); BUG_ON(len & ~PAGE_MASK); /* Does the address range wrap, or is the span zero-sized? */ BUG_ON(src_start + len <= src_start); BUG_ON(dst_start + len <= dst_start); src_addr = src_start; dst_addr = dst_start; copied = 0; page = NULL; retry: mmap_read_lock(dst_mm); /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ err = -EAGAIN; if (mmap_changing && atomic_read(mmap_changing)) goto out_unlock; /* * Make sure the vma is not shared, that the dst range is * both valid and fully within a single existing vma. */ err = -ENOENT; dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma) goto out_unlock; err = -EINVAL; /* * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but * it will overwrite vm_ops, so vma_is_anonymous must return false. */ if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) && dst_vma->vm_flags & VM_SHARED)) goto out_unlock; /* * validate 'mode' now that we know the dst_vma: don't allow * a wrprotect copy if the userfaultfd didn't register as WP. */ wp_copy = mode & UFFDIO_COPY_MODE_WP; if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP)) goto out_unlock; /* * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, src_start, len, mcopy_mode, wp_copy); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE) goto out_unlock; /* * Ensure the dst_vma has a anon_vma or this page * would get a NULL anon_vma when moved in the * dst_vma. */ err = -ENOMEM; if (!(dst_vma->vm_flags & VM_SHARED) && unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; while (src_addr < src_start + len) { pmd_t dst_pmdval; BUG_ON(dst_addr >= dst_start + len); dst_pmd = mm_alloc_pmd(dst_mm, dst_addr); if (unlikely(!dst_pmd)) { err = -ENOMEM; break; } dst_pmdval = pmdp_get_lockless(dst_pmd); /* * If the dst_pmd is mapped as THP don't * override it and just be strict. */ if (unlikely(pmd_trans_huge(dst_pmdval))) { err = -EEXIST; break; } if (unlikely(pmd_none(dst_pmdval)) && unlikely(__pte_alloc(dst_mm, dst_pmd))) { err = -ENOMEM; break; } /* If an huge pmd materialized from under us fail */ if (unlikely(pmd_trans_huge(*dst_pmd))) { err = -EFAULT; break; } BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, &page, mcopy_mode, wp_copy); cond_resched(); if (unlikely(err == -ENOENT)) { void *page_kaddr; mmap_read_unlock(dst_mm); BUG_ON(!page); page_kaddr = kmap_local_page(page); err = copy_from_user(page_kaddr, (const void __user *) src_addr, PAGE_SIZE); kunmap_local(page_kaddr); if (unlikely(err)) { err = -EFAULT; goto out; } flush_dcache_page(page); goto retry; } else BUG_ON(page); if (!err) { dst_addr += PAGE_SIZE; src_addr += PAGE_SIZE; copied += PAGE_SIZE; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: mmap_read_unlock(dst_mm); out: if (page) put_page(page); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; } ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, atomic_t *mmap_changing, __u64 mode) { return __mcopy_atomic(dst_mm, dst_start, src_start, len, MCOPY_ATOMIC_NORMAL, mmap_changing, mode); } ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, unsigned long len, atomic_t *mmap_changing) { return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, mmap_changing, 0); } ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, unsigned long len, atomic_t *mmap_changing) { return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, mmap_changing, 0); } void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long start, unsigned long len, bool enable_wp) { struct mmu_gather tlb; pgprot_t newprot; if (enable_wp) newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); else newprot = vm_get_page_prot(dst_vma->vm_flags); tlb_gather_mmu(&tlb, dst_mm); change_protection(&tlb, dst_vma, start, start + len, newprot, enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); tlb_finish_mmu(&tlb); } int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; unsigned long page_mask; int err; /* * Sanitize the command parameters: */ BUG_ON(start & ~PAGE_MASK); BUG_ON(len & ~PAGE_MASK); /* Does the address range wrap, or is the span zero-sized? */ BUG_ON(start + len <= start); mmap_read_lock(dst_mm); /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ err = -EAGAIN; if (mmap_changing && atomic_read(mmap_changing)) goto out_unlock; err = -ENOENT; dst_vma = find_dst_vma(dst_mm, start, len); if (!dst_vma) goto out_unlock; if (!userfaultfd_wp(dst_vma)) goto out_unlock; if (!vma_can_userfault(dst_vma, dst_vma->vm_flags)) goto out_unlock; if (is_vm_hugetlb_page(dst_vma)) { err = -EINVAL; page_mask = vma_kernel_pagesize(dst_vma) - 1; if ((start & page_mask) || (len & page_mask)) goto out_unlock; } uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); err = 0; out_unlock: mmap_read_unlock(dst_mm); return err; }