Re: [PATCH v9 05/11] mm/hugetlb: Allocate the vmemmap pages associated with each HugeTLB page

[Mike Kravetz <mike.kravetz@oracle.com>]

On 12/13/20 7:45 AM, Muchun Song wrote:
> When we free a HugeTLB page to the buddy allocator, we should allocate the
> vmemmap pages associated with it. We can do that in the __free_hugepage()
> before freeing it to buddy.

...

> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
> index 78c527617e8d..ffcf092c92ed 100644
> --- a/mm/sparse-vmemmap.c
> +++ b/mm/sparse-vmemmap.c
> @@ -29,6 +29,7 @@
>  #include <linux/sched.h>
>  #include <linux/pgtable.h>
>  #include <linux/bootmem_info.h>
> +#include <linux/delay.h>
>  
>  #include <asm/dma.h>
>  #include <asm/pgalloc.h>
> @@ -39,7 +40,8 @@
>   *
>   * @rmap_pte:		called for each non-empty PTE (lowest-level) entry.
>   * @reuse:		the page which is reused for the tail vmemmap pages.
> - * @vmemmap_pages:	the list head of the vmemmap pages that can be freed.
> + * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
> + *			or is mapped from.
>   */
>  struct vmemmap_rmap_walk {
>  	void (*rmap_pte)(pte_t *pte, unsigned long addr,
> @@ -54,6 +56,9 @@ struct vmemmap_rmap_walk {
>   */
>  #define VMEMMAP_TAIL_PAGE_REUSE		-1
>  
> +/* The gfp mask of allocating vmemmap page */
> +#define GFP_VMEMMAP_PAGE	(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
> +
>  static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
>  			      unsigned long end, struct vmemmap_rmap_walk *walk)
>  {
> @@ -200,6 +205,68 @@ void vmemmap_remap_reuse(unsigned long start, unsigned long size)
>  	free_vmemmap_page_list(&vmemmap_pages);
>  }
>  
> +static void vmemmap_remap_restore_pte(pte_t *pte, unsigned long addr,
> +				      struct vmemmap_rmap_walk *walk)
> +{
> +	pgprot_t pgprot = PAGE_KERNEL;
> +	struct page *page;
> +	void *to;
> +
> +	BUG_ON(pte_page(*pte) != walk->reuse);
> +
> +	page = list_first_entry(walk->vmemmap_pages, struct page, lru);
> +	list_del(&page->lru);
> +	to = page_to_virt(page);
> +	copy_page(to, page_to_virt(walk->reuse));
> +
> +	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
> +}
> +
> +static void alloc_vmemmap_page_list(struct list_head *list,
> +				    unsigned long nr_pages)
> +{
> +	while (nr_pages--) {
> +		struct page *page;
> +
> +retry:
> +		page = alloc_page(GFP_VMEMMAP_PAGE);

Should we try (or require) the vmemmap page be on the same node as the
pages they describe?  I imagine performance would be impacted if a
struct page and the page it describes are on different numa nodes.

> +		if (unlikely(!page)) {
> +			msleep(100);
> +			/*
> +			 * We should retry infinitely, because we cannot
> +			 * handle allocation failures. Once we allocate
> +			 * vmemmap pages successfully, then we can free
> +			 * a HugeTLB page.
> +			 */
> +			goto retry;
> +		}
> +		list_add_tail(&page->lru, list);
> +	}
> +}
> +

-- 
Mike Kravetz