The patch titled Subject: userfaultfd: use vma iterator has been added to the -mm mm-unstable branch. Its filename is userfaultfd-use-vma-iterator.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/userfaultfd-use-vma-iterator.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: "Liam R. Howlett" <Liam.Howlett@xxxxxxxxxx> Subject: userfaultfd: use vma iterator Date: Fri, 20 Jan 2023 11:26:17 -0500 Use the vma iterator so that the iterator can be invalidated or updated to avoid each caller doing so. Link: https://lkml.kernel.org/r/20230120162650.984577-17-Liam.Howlett@xxxxxxxxxx Signed-off-by: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- --- a/fs/userfaultfd.c~userfaultfd-use-vma-iterator +++ a/fs/userfaultfd.c @@ -883,7 +883,7 @@ static int userfaultfd_release(struct in /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, mm, 0); WRITE_ONCE(ctx->released, true); @@ -900,7 +900,7 @@ static int userfaultfd_release(struct in */ mmap_write_lock(mm); prev = NULL; - mas_for_each(&mas, vma, ULONG_MAX) { + for_each_vma(vmi, vma) { cond_resched(); BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ !!(vma->vm_flags & __VM_UFFD_FLAGS)); @@ -909,13 +909,12 @@ static int userfaultfd_release(struct in continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, + prev = vmi_vma_merge(&vmi, mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { - mas_pause(&mas); vma = prev; } else { prev = vma; @@ -1302,7 +1301,7 @@ static int userfaultfd_register(struct u bool found; bool basic_ioctls; unsigned long start, end, vma_end; - MA_STATE(mas, &mm->mm_mt, 0, 0); + struct vma_iterator vmi; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1344,17 +1343,13 @@ static int userfaultfd_register(struct u if (!mmget_not_zero(mm)) goto out; + ret = -EINVAL; mmap_write_lock(mm); - mas_set(&mas, start); - vma = mas_find(&mas, ULONG_MAX); + vma_iter_init(&vmi, mm, start); + vma = vma_find(&vmi, end); if (!vma) goto out_unlock; - /* check that there's at least one vma in the range */ - ret = -EINVAL; - if (vma->vm_start >= end) - goto out_unlock; - /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. @@ -1371,7 +1366,8 @@ static int userfaultfd_register(struct u */ found = false; basic_ioctls = false; - for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { + cur = vma; + do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ @@ -1428,16 +1424,14 @@ static int userfaultfd_register(struct u basic_ioctls = true; found = true; - } + } for_each_vma_range(vmi, cur, end); BUG_ON(!found); - mas_set(&mas, start); - prev = mas_prev(&mas, 0); - if (prev != vma) - mas_next(&mas, ULONG_MAX); + vma_iter_set(&vmi, start); + prev = vma_prev(&vmi); ret = 0; - do { + for_each_vma_range(vmi, vma, end) { cond_resched(); BUG_ON(!vma_can_userfault(vma, vm_flags)); @@ -1458,30 +1452,25 @@ static int userfaultfd_register(struct u vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; - prev = vma_merge(mm, prev, start, vma_end, new_flags, + prev = vmi_vma_merge(&vmi, mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), anon_vma_name(vma)); if (prev) { /* vma_merge() invalidated the mas */ - mas_pause(&mas); vma = prev; goto next; } if (vma->vm_start < start) { - ret = split_vma(mm, vma, start, 1); + ret = vmi_split_vma(&vmi, mm, vma, start, 1); if (ret) break; - /* split_vma() invalidated the mas */ - mas_pause(&mas); } if (vma->vm_end > end) { - ret = split_vma(mm, vma, end, 0); + ret = vmi_split_vma(&vmi, mm, vma, end, 0); if (ret) break; - /* split_vma() invalidated the mas */ - mas_pause(&mas); } next: /* @@ -1498,8 +1487,8 @@ static int userfaultfd_register(struct u skip: prev = vma; start = vma->vm_end; - vma = mas_next(&mas, end - 1); - } while (vma); + } + out_unlock: mmap_write_unlock(mm); mmput(mm); @@ -1543,7 +1532,7 @@ static int userfaultfd_unregister(struct bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; - MA_STATE(mas, &mm->mm_mt, 0, 0); + struct vma_iterator vmi; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) @@ -1562,14 +1551,10 @@ static int userfaultfd_unregister(struct goto out; mmap_write_lock(mm); - mas_set(&mas, start); - vma = mas_find(&mas, ULONG_MAX); - if (!vma) - goto out_unlock; - - /* check that there's at least one vma in the range */ ret = -EINVAL; - if (vma->vm_start >= end) + vma_iter_init(&vmi, mm, start); + vma = vma_find(&vmi, end); + if (!vma) goto out_unlock; /* @@ -1587,8 +1572,8 @@ static int userfaultfd_unregister(struct * Search for not compatible vmas. */ found = false; - ret = -EINVAL; - for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { + cur = vma; + do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ @@ -1605,16 +1590,13 @@ static int userfaultfd_unregister(struct goto out_unlock; found = true; - } + } for_each_vma_range(vmi, cur, end); BUG_ON(!found); - mas_set(&mas, start); - prev = mas_prev(&mas, 0); - if (prev != vma) - mas_next(&mas, ULONG_MAX); - + vma_iter_set(&vmi, start); + prev = vma_prev(&vmi); ret = 0; - do { + for_each_vma_range(vmi, vma, end) { cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); @@ -1650,26 +1632,23 @@ static int userfaultfd_unregister(struct uffd_wp_range(mm, vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - prev = vma_merge(mm, prev, start, vma_end, new_flags, + prev = vmi_vma_merge(&vmi, mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; - mas_pause(&mas); goto next; } if (vma->vm_start < start) { - ret = split_vma(mm, vma, start, 1); + ret = vmi_split_vma(&vmi, mm, vma, start, 1); if (ret) break; - mas_pause(&mas); } if (vma->vm_end > end) { - ret = split_vma(mm, vma, end, 0); + ret = vmi_split_vma(&vmi, mm, vma, end, 0); if (ret) break; - mas_pause(&mas); } next: /* @@ -1683,8 +1662,8 @@ static int userfaultfd_unregister(struct skip: prev = vma; start = vma->vm_end; - vma = mas_next(&mas, end - 1); - } while (vma); + } + out_unlock: mmap_write_unlock(mm); mmput(mm); _ Patches currently in -mm which might be from Liam.Howlett@xxxxxxxxxx are maple_tree-add-mas_init-function.patch maple_tree-fix-potential-rcu-issue.patch maple_tree-reduce-user-error-potential.patch test_maple_tree-test-modifications-while-iterating.patch mm-expand-vma-iterator-interface.patch mm-mmap-convert-brk-to-use-vma-iterator.patch kernel-fork-convert-forking-to-using-the-vmi-iterator.patch mmap-convert-vma_link-vma-iterator.patch mm-mmap-remove-preallocation-from-do_mas_align_munmap.patch mmap-change-do_mas_munmap-and-do_mas_aligned_munmap-to-use-vma-iterator.patch mmap-convert-vma_expand-to-use-vma-iterator.patch mm-add-temporary-vma-iterator-versions-of-vma_merge-split_vma-and-__split_vma.patch ipc-shm-use-the-vma-iterator-for-munmap-calls.patch userfaultfd-use-vma-iterator.patch mm-change-mprotect_fixup-to-vma-iterator.patch mlock-convert-mlock-to-vma-iterator.patch coredump-convert-to-vma-iterator.patch mempolicy-convert-to-vma-iterator.patch task_mmu-convert-to-vma-iterator.patch sched-convert-to-vma-iterator.patch madvise-use-vmi-iterator-for-__split_vma-and-vma_merge.patch mmap-pass-through-vmi-iterator-to-__split_vma.patch mmap-use-vmi-version-of-vma_merge.patch mm-mremap-use-vmi-version-of-vma_merge.patch nommu-convert-nommu-to-using-the-vma-iterator.patch mm-switch-vma_merge-split_vma-and-__split_vma-to-vma-iterator.patch mmap-convert-__vma_adjust-to-use-vma-iterator.patch mm-pass-through-vma-iterator-to-__vma_adjust.patch madvise-use-split_vma-instead-of-__split_vma.patch mm-remove-unnecessary-write-to-vma-iterator-in-__vma_adjust.patch mm-pass-vma-iterator-through-to-__vma_adjust.patch mm-add-vma-iterator-to-vma_adjust-arguments.patch mmap-clean-up-mmap_region-unrolling.patch mm-change-munmap-splitting-order-and-move_vma.patch mm-mmap-move-anon_vma-setting-in-__vma_adjust.patch mm-mmap-refactor-locking-out-of-__vma_adjust.patch mm-mmap-use-vma_prepare-and-vma_complete-in-vma_expand.patch mm-mmap-introduce-init_vma_prep-and-init_multi_vma_prep.patch mm-dont-use-__vma_adjust-in-__split_vma.patch mm-mmap-dont-use-__vma_adjust-in-shift_arg_pages.patch mm-mmap-introduce-dup_vma_anon-helper.patch mm-mmap-convert-do_brk_flags-to-use-vma_prepare-and-vma_complete.patch mm-mmap-remove-__vma_adjust.patch vma_merge-set-vma-iterator-to-correct-position.patch