On 2021/3/25 8:28, Mike Kravetz wrote:
> The new remove_hugetlb_page() routine is designed to remove a hugetlb
> page from hugetlbfs processing. It will remove the page from the active
> or free list, update global counters and set the compound page
> destructor to NULL so that PageHuge() will return false for the 'page'.
> After this call, the 'page' can be treated as a normal compound page or
> a collection of base size pages.
>
> remove_hugetlb_page is to be called with the hugetlb_lock held.
>
> Creating this routine and separating functionality is in preparation for
> restructuring code to reduce lock hold times.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
> ---
> mm/hugetlb.c | 70 +++++++++++++++++++++++++++++++++-------------------
> 1 file changed, 45 insertions(+), 25 deletions(-)
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 404b0b1c5258..3938ec086b5c 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1327,6 +1327,46 @@ static inline void destroy_compound_gigantic_page(struct page *page,
> unsigned int order) { }
> #endif
>
> +/*
> + * Remove hugetlb page from lists, and update dtor so that page appears
> + * as just a compound page. A reference is held on the page.
> + * NOTE: hugetlb specific page flags stored in page->private are not
> + * automatically cleared. These flags may be used in routines
> + * which operate on the resulting compound page.
It seems HPageFreed and HPageTemporary is cleared. Which hugetlb specific page flags
is reserverd here and why? Could you please give a simple example to clarify
this in the comment to help understand this NOTE?
The code looks good to me. Many thanks!
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
> + *
> + * Must be called with hugetlb lock held.
> + */
> +static void remove_hugetlb_page(struct hstate *h, struct page *page,
> + bool adjust_surplus)
> +{
> + int nid = page_to_nid(page);
> +
> + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
> + return;
> +
> + list_del(&page->lru);
> +
> + if (HPageFreed(page)) {
> + h->free_huge_pages--;
> + h->free_huge_pages_node[nid]--;
> + ClearHPageFreed(page);
> + }
> + if (adjust_surplus) {
> + h->surplus_huge_pages--;
> + h->surplus_huge_pages_node[nid]--;
> + }
> +
> + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
> + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page);
> +
> + ClearHPageTemporary(page);
> + set_page_refcounted(page);
> + set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
> +
> + h->nr_huge_pages--;
> + h->nr_huge_pages_node[nid]--;
> +}
> +
> static void update_and_free_page(struct hstate *h, struct page *page)
> {
> int i;
> @@ -1335,8 +1375,6 @@ static void update_and_free_page(struct hstate *h, struct page *page)
> if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
> return;
>
> - h->nr_huge_pages--;
> - h->nr_huge_pages_node[page_to_nid(page)]--;
> for (i = 0; i < pages_per_huge_page(h);
> i++, subpage = mem_map_next(subpage, page, i)) {
> subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
> @@ -1344,10 +1382,6 @@ static void update_and_free_page(struct hstate *h, struct page *page)
> 1 << PG_active | 1 << PG_private |
> 1 << PG_writeback);
> }
> - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
> - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page);
> - set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
> - set_page_refcounted(page);
> if (hstate_is_gigantic(h)) {
> destroy_compound_gigantic_page(page, huge_page_order(h));
> free_gigantic_page(page, huge_page_order(h));
> @@ -1415,15 +1449,12 @@ static void __free_huge_page(struct page *page)
> h->resv_huge_pages++;
>
> if (HPageTemporary(page)) {
> - list_del(&page->lru);
> - ClearHPageTemporary(page);
> + remove_hugetlb_page(h, page, false);
> update_and_free_page(h, page);
> } else if (h->surplus_huge_pages_node[nid]) {
> /* remove the page from active list */
> - list_del(&page->lru);
> + remove_hugetlb_page(h, page, true);
> update_and_free_page(h, page);
> - h->surplus_huge_pages--;
> - h->surplus_huge_pages_node[nid]--;
> } else {
> arch_clear_hugepage_flags(page);
> enqueue_huge_page(h, page);
> @@ -1708,13 +1739,7 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
> struct page *page =
> list_entry(h->hugepage_freelists[node].next,
> struct page, lru);
> - list_del(&page->lru);
> - h->free_huge_pages--;
> - h->free_huge_pages_node[node]--;
> - if (acct_surplus) {
> - h->surplus_huge_pages--;
> - h->surplus_huge_pages_node[node]--;
> - }
> + remove_hugetlb_page(h, page, acct_surplus);
> update_and_free_page(h, page);
> ret = 1;
> break;
> @@ -1752,7 +1777,6 @@ int dissolve_free_huge_page(struct page *page)
> if (!page_count(page)) {
> struct page *head = compound_head(page);
> struct hstate *h = page_hstate(head);
> - int nid = page_to_nid(head);
> if (h->free_huge_pages - h->resv_huge_pages == 0)
> goto out;
>
> @@ -1783,9 +1807,7 @@ int dissolve_free_huge_page(struct page *page)
> SetPageHWPoison(page);
> ClearPageHWPoison(head);
> }
> - list_del(&head->lru);
> - h->free_huge_pages--;
> - h->free_huge_pages_node[nid]--;
> + remove_hugetlb_page(h, page, false);
> h->max_huge_pages--;
> update_and_free_page(h, head);
> rc = 0;
> @@ -2553,10 +2575,8 @@ static void try_to_free_low(struct hstate *h, unsigned long count,
> return;
> if (PageHighMem(page))
> continue;
> - list_del(&page->lru);
> + remove_hugetlb_page(h, page, false);
> update_and_free_page(h, page);
> - h->free_huge_pages--;
> - h->free_huge_pages_node[page_to_nid(page)]--;
> }
> }
> }
>
