@@ -901,26 +901,19 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
return -EINVAL;
}
-static long madvise_populate(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end,
- int behavior)
+static long madvise_populate(struct mm_struct *mm, unsigned long start,
+ unsigned long end, int behavior)
{
const bool write = behavior == MADV_POPULATE_WRITE;
- struct mm_struct *mm = vma->vm_mm;
int locked = 1;
long pages;
- *prev = vma;
-
while (start < end) {
/* Populate (prefault) page tables readable/writable. */
pages = faultin_page_range(mm, start, end, write, &locked);
if (!locked) {
mmap_read_lock(mm);
locked = 1;
- *prev = NULL;
- vma = NULL;
}
if (pages < 0) {
switch (pages) {
@@ -1021,9 +1014,6 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
case MADV_DONTNEED:
case MADV_DONTNEED_LOCKED:
return madvise_dontneed_free(vma, prev, start, end, behavior);
- case MADV_POPULATE_READ:
- case MADV_POPULATE_WRITE:
- return madvise_populate(vma, prev, start, end, behavior);
case MADV_NORMAL:
new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
break;
@@ -1425,8 +1415,16 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
end = start + len;
blk_start_plug(&plug);
- error = madvise_walk_vmas(mm, start, end, behavior,
- madvise_vma_behavior);
+ switch (behavior) {
+ case MADV_POPULATE_READ:
+ case MADV_POPULATE_WRITE:
+ error = madvise_populate(mm, start, end, behavior);
+ break;
+ default:
+ error = madvise_walk_vmas(mm, start, end, behavior,
+ madvise_vma_behavior);
+ break;
+ }
blk_finish_plug(&plug);
if (write)
mmap_write_unlock(mm);
We changed faultin_page_range() to no longer consume a VMA, because faultin_page_range() might internally release the mm lock to lookup the VMA again -- required to cleanly handle VM_FAULT_RETRY. But independent of that, __get_user_pages() will always lookup the VMA itself. Now that we let __get_user_pages() just handle VMA checks in a way that is suitable for MADV_POPULATE_(READ|WRITE), the VMA walk in madvise() is just overhead. So let's just call madvise_populate() on the full range instead. There is one change in behavior: madvise_walk_vmas() would skip any VMA holes, and if everything succeeded, it would return -ENOMEM after processing all VMAs. However, for MADV_POPULATE_(READ|WRITE) it's unlikely for the caller to notice any difference: -ENOMEM might either indicate that there were VMA holes or that populating page tables failed because there was not enough memory. So it's unlikely that user space will notice the difference, and that special handling likely only makes sense for some other madvise() actions. Further, we'd already fail with -ENOMEM early in the past if looking up the VMA after dropping the MM lock failed because of concurrent VMA modifications. So let's just keep it simple and avoid the madvise VMA walk, and consistently fail early if we find a VMA hole. Signed-off-by: David Hildenbrand <david@redhat.com> --- mm/madvise.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-)