Implicit vma locking inside vm_flags_reset() and vm_flags_reset_once() is
not obvious and makes it hard to understand where vma locking is happening.
Also in some cases (like in dup_userfaultfd()) vma should be locked earlier
than vma_flags modification. To make locking more visible, change these
functions to assert that the vma write lock is taken and explicitly lock
the vma beforehand. Fix userfaultfd functions which should lock the vma
earlier.
Link: https://lkml.kernel.org/r/20230804152724.3090321-5-surenb@google.com
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
ret = H_STATE;
break;
}
+ vma_start_write(vma);
/* Copy vm_flags to avoid partial modifications in ksm_madvise */
vm_flags = vma->vm_flags;
ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
mmap_write_lock(mm);
for_each_vma(vmi, vma) {
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
+ vma_start_write(vma);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
userfaultfd_set_vm_flags(vma,
vma->vm_flags & ~__VM_UFFD_FLAGS);
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+ vma_start_write(vma);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
return 0;
atomic_inc(&ctx->mmap_changing);
} else {
/* Drop uffd context if remap feature not enabled */
+ vma_start_write(vma);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
}
prev = vma;
}
+ vma_start_write(vma);
userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
+ vma_start_write(vma);
userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
+ vma_start_write(vma);
userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
ACCESS_PRIVATE(vma, __vm_flags) = flags;
}
-/* Use when VMA is part of the VMA tree and modifications need coordination */
+/*
+ * Use when VMA is part of the VMA tree and modifications need coordination
+ * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
+ * it should be locked explicitly beforehand.
+ */
static inline void vm_flags_reset(struct vm_area_struct *vma,
vm_flags_t flags)
{
- vma_start_write(vma);
+ vma_assert_write_locked(vma);
vm_flags_init(vma, flags);
}
static inline void vm_flags_reset_once(struct vm_area_struct *vma,
vm_flags_t flags)
{
- vma_start_write(vma);
+ vma_assert_write_locked(vma);
WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
}
}
success:
- /*
- * vm_flags is protected by the mmap_lock held in write mode.
- */
+ /* vm_flags is protected by the mmap_lock held in write mode. */
+ vma_start_write(vma);
vm_flags_reset(vma, new_flags);
if (!vma->vm_file || vma_is_anon_shmem(vma)) {
error = replace_anon_vma_name(vma, anon_name);
*/
if (newflags & VM_LOCKED)
newflags |= VM_IO;
+ vma_start_write(vma);
vm_flags_reset_once(vma, newflags);
lru_add_drain();
* It's okay if try_to_unmap_one unmaps a page just after we
* set VM_LOCKED, populate_vma_page_range will bring it back.
*/
-
if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) {
/* No work to do, and mlocking twice would be wrong */
+ vma_start_write(vma);
vm_flags_reset(vma, newflags);
} else {
mlock_vma_pages_range(vma, start, end, newflags);
* vm_flags and vm_page_prot are protected by the mmap_lock
* held in write mode.
*/
+ vma_start_write(vma);
vm_flags_reset(vma, newflags);
if (vma_wants_manual_pte_write_upgrade(vma))
mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;