On Tue, Jun 19, 2018 at 07:34:16AM +0800, Yang Shi wrote:
> diff --git a/mm/mmap.c b/mm/mmap.c
> index fc41c05..e84f80c 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -2686,6 +2686,141 @@ int split_vma(struct mm_struct *mm, struct
> vm_area_struct *vma,
> return __split_vma(mm, vma, addr, new_below);
> }
>
> +/* Consider PUD size or 1GB mapping as large mapping */
> +#ifdef HPAGE_PUD_SIZE
> +#define LARGE_MAP_THRESH HPAGE_PUD_SIZE
> +#else
> +#define LARGE_MAP_THRESH (1 * 1024 * 1024 * 1024)
> +#endif
> +
> +/* Unmap large mapping early with acquiring read mmap_sem */
> +static int do_munmap_zap_early(struct mm_struct *mm, unsigned long start,
> + size_t len, struct list_head *uf)
> +{
> + unsigned long end = 0;
> + struct vm_area_struct *vma = NULL, *prev, *last, *tmp;
> + bool success = false;
> + int ret = 0;
> +
> + if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE -
> start)
> + return -EINVAL;
> +
> + len = (PAGE_ALIGN(len));
> + if (len == 0)
> + return -EINVAL;
> +
> + /* Just deal with uf in regular path */
> + if (unlikely(uf))
> + goto regular_path;
> +
> + if (len >= LARGE_MAP_THRESH) {
> + down_read(&mm->mmap_sem);
> + vma = find_vma(mm, start);
> + if (!vma) {
> + up_read(&mm->mmap_sem);
> + return 0;
> + }
> +
> + prev = vma->vm_prev;
> +
> + end = start + len;
> + if (vma->vm_start > end) {
> + up_read(&mm->mmap_sem);
> + return 0;
> + }
> +
> + if (start > vma->vm_start) {
> + int error;
> +
> + if (end < vma->vm_end &&
> + mm->map_count > sysctl_max_map_count) {
> + up_read(&mm->mmap_sem);
> + return -ENOMEM;
> + }
> +
> + error = __split_vma(mm, vma, start, 0);
> + if (error) {
> + up_read(&mm->mmap_sem);
> + return error;
> + }
> + prev = vma;
> + }
> +
> + last = find_vma(mm, end);
> + if (last && end > last->vm_start) {
> + int error = __split_vma(mm, last, end, 1);
> +
> + if (error) {
> + up_read(&mm->mmap_sem);
> + return error;
> + }
> + }
> + vma = prev ? prev->vm_next : mm->mmap;
Hold up, two things: you having to copy most of do_munmap() didn't seem
to suggest a helper function? And second, since when are we allowed to
split VMAs under a read lock?
