When mapping /dev/zero with MAP_PRIVATE, one ends up with strange VMAs originating from Linux's distant past. These have vma->vm_file set but NULL vma->vm_ops, meaning they satisfy vma_is_anonymous() but otherwise resemble a file-backed VMA. The introduction of anonymous page offsets and their subsequent use as indexes for MAP_PRIVATE-file-backed mappings mean the rmap does the right thing with these but we are left with inconsistencies. The vma_start_pgoff(vma) == vma_start_anon_pgoff(vma) invariant is true for all other anonymous VMAs, but not these. These VMAs are also observable as files in /proc//[maps, smaps, map_files] but otherwise behave like anonymous mappings. Therefore let's make these VMAs actually anonymous at mapping time which will activate the anonymous code path for mappings. This means we no longer have to account for this discrepancy anywhere and no longer have to think about these at all. This is user-observable, as MAP_PRIVATE-/dev/zero will no longer appear in procfs as a file-backed mapping, but the impact of this change should be low as likely nobody is relying upon this. However in any case, in using MAP_PRIVATE-/dev/zero they are explicitly asking anonymous memory, so no longer seeing these as file mappings is in fact correct. A previous commit gave us map_is_dev_zero() to positively identify these mappings, so we expressly only do so for these alone. Update assert_sane_pgoff(), the comment for vma_start_pgoff() and linear_anon_page_index() to reflect the change. We make this change in call_mmap_prepare() alone as /dev/zero has been converted to an mmap_prepare hook and we do not permit nested MAP_PRIVATE mapping of /dev/zero. We also remove the now defunct vma_desc_set_anonymous() and eliminate the temporary bisection hazard fix from the previous commit. Also update the VMA userland tests to reflect the change. Finally, update the procfs self tests proc-self-map-files-001 and proc-self-map-files-002 which both intend to map an arbitrary file MAP_PRIVATE then assert procfs state, but happen to choose /dev/zero. Fix them by updating these to /proc/self/exe which is guaranteed to be present if procfs is mounted. Signed-off-by: Lorenzo Stoakes (ARM) --- include/linux/mm.h | 10 ++------- include/linux/pagemap.h | 3 +-- mm/vma.c | 26 ++++++++++++++-------- mm/vma.h | 3 --- .../selftests/proc/proc-self-map-files-001.c | 2 +- .../selftests/proc/proc-self-map-files-002.c | 2 +- tools/testing/vma/include/dup.h | 3 +-- 7 files changed, 23 insertions(+), 26 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index a65371d05e89..660e1004a6f7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1554,11 +1554,6 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma) vma->vm_ops = NULL; } -static inline void vma_desc_set_anonymous(struct vm_area_desc *desc) -{ - desc->vm_ops = NULL; -} - static inline bool vma_is_anonymous(const struct vm_area_struct *vma) { return !vma->vm_ops; @@ -4352,9 +4347,8 @@ static inline unsigned long vma_pages(const struct vm_area_struct *vma) * If @vma is a MAP_PRIVATE file-backed mapping, then this returns the * page offset within the file. * - * Edge cases: nommu does not abide by these, MAP_PRIVATE-/dev/zero satisfies - * vma_is_anonymous() but has file-backed page offset, and MAP_PRIVATE-pfnmap - * regions have their page offset set to the first PFN in the range. + * Edge cases: nommu does not abide by these and CoW MAP_PRIVATE-pfnmap regions + * have their page offset set to the first PFN in the range. * * Returns: The page offset of the start of @vma. */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 939b8850df49..4b6ce8affe89 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1136,8 +1136,7 @@ static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma, const pgoff_t pgoff = __linear_anon_page_index(vma, address); VM_WARN_ON_ONCE(vma_test(vma, VMA_SHARED_BIT)); - /* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */ - if (vma_is_anonymous(vma) && !vma->vm_file) + if (vma_is_anonymous(vma)) VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address)); return pgoff; diff --git a/mm/vma.c b/mm/vma.c index bb68fef2393b..9b565a1967c8 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -2632,6 +2632,13 @@ static bool map_is_dev_zero(const struct mmap_state *map) return imajor(inode) == MEM_MAJOR && iminor(inode) == DEVZERO_MINOR; } +static void map_set_anon(struct mmap_state *map) +{ + map->file = NULL; + map->vm_ops = NULL; + map->pgoff = map->addr >> PAGE_SHIFT; +} + static bool map_is_private(const struct mmap_state *map) { return !vma_flags_test(&map->vma_flags, VMA_SHARED_BIT); @@ -2639,10 +2646,7 @@ static bool map_is_private(const struct mmap_state *map) static bool map_is_anon(const struct mmap_state *map) { - if (!map_is_private(map)) - return false; - - return !map->file || map_is_dev_zero(map); + return map_is_private(map) && !map->file; } /* @@ -2674,7 +2678,7 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap, vma_iter_config(vmi, map->addr, map->end); - if (is_anon && !map->file) + if (is_anon) vma_set_anonymous(vma); vma_set_range(vma, map->addr, map->end, map->pgoff, map->anon_pgoff); @@ -2692,10 +2696,6 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap, else if (!is_anon) error = shmem_zero_setup(vma); - /* Temporary MAP_PRIVATE-/dev/zero workaround. */ - if (is_anon && map->file) - vma_set_anonymous(vma); - if (error) goto free_iter_vma; @@ -2824,6 +2824,14 @@ static int call_mmap_prepare(struct mmap_state *map, map->vm_ops = desc->vm_ops; map->vm_private_data = desc->private_data; + /* + * MAP_PRIVATE-/dev/zero mappings are an ancient way of getting + * anonymous mappings. Rather than allowing these mappings to be odd + * outliers, simply make them truly anonymous. + */ + if (map_is_private(map) && map_is_dev_zero(map)) + map_set_anon(map); + return 0; } diff --git a/mm/vma.h b/mm/vma.h index 024fabe63560..e97bd2dfa786 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -267,9 +267,6 @@ static inline void assert_sane_pgoff(struct vm_area_struct *vma, pgoff_t pgoff) */ if (!vma_is_anonymous(vma)) return; - /* MAP_PRIVATE-/dev/zero is anon, non-NULL vm_file, but has file pgoff. */ - if (vma->vm_file) - return; /* If faulted in, could have been remapped. */ if (vma->anon_vma) return; diff --git a/tools/testing/selftests/proc/proc-self-map-files-001.c b/tools/testing/selftests/proc/proc-self-map-files-001.c index 4209c64283d6..bbca9f9e2743 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-001.c +++ b/tools/testing/selftests/proc/proc-self-map-files-001.c @@ -51,7 +51,7 @@ int main(void) int fd; unsigned long a, b; - fd = open("/dev/zero", O_RDONLY); + fd = open("/proc/self/exe", O_RDONLY); if (fd == -1) return 1; diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index e6aa00a183bc..5786cdffbbf6 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -57,7 +57,7 @@ int main(void) int fd; unsigned long a, b; - fd = open("/dev/zero", O_RDONLY); + fd = open("/proc/self/exe", O_RDONLY); if (fd == -1) return 1; diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h index 1713602e93cd..556a57c48a75 100644 --- a/tools/testing/vma/include/dup.h +++ b/tools/testing/vma/include/dup.h @@ -1648,8 +1648,7 @@ static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma, const pgoff_t pgoff = __linear_anon_page_index(vma, address); VM_WARN_ON_ONCE(vma_test(vma, VMA_SHARED_BIT)); - /* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */ - if (vma_is_anonymous(vma) && !vma->vm_file) + if (vma_is_anonymous(vma)) VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address)); return pgoff; -- 2.55.0