From f69069dddda206b190706eef7b2dad3a67a6df10 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Thu, 9 Feb 2023 16:13:23 +0500 Subject: [PATCH v3 1/2] mm/userfaultfd: Support WP on multiple VMAs To: peterx@redhat.com, david@redhat.com Cc: usama.anjum@collabora.com, kernel@collabora.com mwriteprotect_range() errors out if [start, end) doesn't fall in one VMA. We are facing a use case where multiple VMAs are present in one range of interest. For example, the following pseudocode reproduces the error which we are trying to fix: - Allocate memory of size 16 pages with PROT_NONE with mmap - Register userfaultfd - Change protection of the first half (1 to 8 pages) of memory to PROT_READ | PROT_WRITE. This breaks the memory area in two VMAs. - Now UFFDIO_WRITEPROTECT_MODE_WP on the whole memory of 16 pages errors out. This is a simple use case where user may or may not know if the memory area has been divided into multiple VMAs. Reported-by: Paul Gofman Signed-off-by: Muhammad Usama Anjum --- Changes since v2: - Correct the return error code Changes since v1: - Correct the start and ending values passed to uffd_wp_range() --- mm/userfaultfd.c | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 65ad172add27..a3b48a99b942 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -738,9 +738,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { + unsigned long end = start + len; + unsigned long _start, _end; struct vm_area_struct *dst_vma; unsigned long page_mask; - int err; + int err = -ENOENT; + VMA_ITERATOR(vmi, dst_mm, start); /* * Sanitize the command parameters: @@ -758,30 +761,34 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, * 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)) + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; goto out_unlock; + } - err = -ENOENT; - dst_vma = find_dst_vma(dst_mm, start, len); + for_each_vma_range(vmi, dst_vma, end) { + err = -ENOENT; - 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 (!dst_vma->vm_userfaultfd_ctx.ctx) + break; + if (!userfaultfd_wp(dst_vma)) + break; + if (!vma_can_userfault(dst_vma, dst_vma->vm_flags)) + break; - 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; - } + if (is_vm_hugetlb_page(dst_vma)) { + err = -EINVAL; + page_mask = vma_kernel_pagesize(dst_vma) - 1; + if ((start & page_mask) || (len & page_mask)) + break; + } - uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); + _start = (dst_vma->vm_start > start) ? dst_vma->vm_start : start; + _end = (dst_vma->vm_end < end) ? dst_vma->vm_end : end; - err = 0; + uffd_wp_range(dst_mm, dst_vma, _start, _end - _start, enable_wp); + err = 0; + } out_unlock: mmap_read_unlock(dst_mm); return err; -- 2.39.1