On Wed 24-03-21 17:28:33, Mike Kravetz wrote:
[...]
> @@ -2074,17 +2067,16 @@ static int gather_surplus_pages(struct hstate *h, long delta)
> * to the associated reservation map.
> * 2) Free any unused surplus pages that may have been allocated to satisfy
> * the reservation. As many as unused_resv_pages may be freed.
> - *
> - * Called with hugetlb_lock held. However, the lock could be dropped (and
> - * reacquired) during calls to cond_resched_lock. Whenever dropping the lock,
> - * we must make sure nobody else can claim pages we are in the process of
> - * freeing. Do this by ensuring resv_huge_page always is greater than the
> - * number of huge pages we plan to free when dropping the lock.
> */
> static void return_unused_surplus_pages(struct hstate *h,
> unsigned long unused_resv_pages)
> {
> unsigned long nr_pages;
> + struct page *page, *t_page;
> + struct list_head page_list;
> +
> + /* Uncommit the reservation */
> + h->resv_huge_pages -= unused_resv_pages;
Is this ok for cases where remove_pool_huge_page fails early? I have to
say I am kinda lost in the resv_huge_pages accounting here. The original
code was already quite supicious to me. TBH.
>
> /* Cannot return gigantic pages currently */
> if (hstate_is_gigantic(h))
> @@ -2101,24 +2093,27 @@ static void return_unused_surplus_pages(struct hstate *h,
> * evenly across all nodes with memory. Iterate across these nodes
> * until we can no longer free unreserved surplus pages. This occurs
> * when the nodes with surplus pages have no free pages.
> - * free_pool_huge_page() will balance the freed pages across the
> + * remove_pool_huge_page() will balance the freed pages across the
> * on-line nodes with memory and will handle the hstate accounting.
> - *
> - * Note that we decrement resv_huge_pages as we free the pages. If
> - * we drop the lock, resv_huge_pages will still be sufficiently large
> - * to cover subsequent pages we may free.
> */
> + INIT_LIST_HEAD(&page_list);
> while (nr_pages--) {
> - h->resv_huge_pages--;
> - unused_resv_pages--;
> - if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
> + page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
> + if (!page)
> goto out;
> - cond_resched_lock(&hugetlb_lock);
> +
> + INIT_LIST_HEAD(&page->lru);
again unnecessary INIT_LIST_HEAD
> + list_add(&page->lru, &page_list);
> }
>
> out:
> - /* Fully uncommit the reservation */
> - h->resv_huge_pages -= unused_resv_pages;
> + spin_unlock(&hugetlb_lock);
> + list_for_each_entry_safe(page, t_page, &page_list, lru) {
> + list_del(&page->lru);
> + update_and_free_page(h, page);
> + cond_resched();
> + }
You have the same construct at 3 different places maybe it deserves a
little helper update_and_free_page_batch.
> + spin_lock(&hugetlb_lock);
> }
>
>
> @@ -2648,6 +2643,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
> nodemask_t *nodes_allowed)
> {
> unsigned long min_count, ret;
> + struct page *page, *t_page;
> + struct list_head page_list;
> NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
>
> /*
> @@ -2757,11 +2754,28 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
> min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
> min_count = max(count, min_count);
> try_to_free_low(h, min_count, nodes_allowed);
> +
> + /*
> + * Collect pages to be removed on list without dropping lock
> + */
> + INIT_LIST_HEAD(&page_list);
> while (min_count < persistent_huge_pages(h)) {
> - if (!free_pool_huge_page(h, nodes_allowed, 0))
> + page = remove_pool_huge_page(h, nodes_allowed, 0);
> + if (!page)
> break;
> - cond_resched_lock(&hugetlb_lock);
> +
> + INIT_LIST_HEAD(&page->lru);
INIT_LIST_HEAD again.
> + list_add(&page->lru, &page_list);
> }
> + /* free the pages after dropping lock */
> + spin_unlock(&hugetlb_lock);
> + list_for_each_entry_safe(page, t_page, &page_list, lru) {
> + list_del(&page->lru);
> + update_and_free_page(h, page);
> + cond_resched();
> + }
> + spin_lock(&hugetlb_lock);
> +
> while (count < persistent_huge_pages(h)) {
> if (!adjust_pool_surplus(h, nodes_allowed, 1))
> break;
> --
> 2.30.2
--
Michal Hocko
SUSE Labs
