Re: [PATCH v2 05/19] mm/hugetlb: Introduce pgtable allocation/freeing helpers

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

On 10/26/20 7:51 AM, Muchun Song wrote:
> On some architectures, the vmemmap areas use huge page mapping.
> If we want to free the unused vmemmap pages, we have to split
> the huge pmd firstly. So we should pre-allocate pgtable to split
> huge pmd.
> 
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  arch/x86/include/asm/hugetlb.h |   5 ++
>  include/linux/hugetlb.h        |  17 +++++
>  mm/hugetlb.c                   | 117 +++++++++++++++++++++++++++++++++
>  3 files changed, 139 insertions(+)
> 
> diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
> index 1721b1aadeb1..f5e882f999cd 100644
> --- a/arch/x86/include/asm/hugetlb.h
> +++ b/arch/x86/include/asm/hugetlb.h
> @@ -5,6 +5,11 @@
>  #include <asm/page.h>
>  #include <asm-generic/hugetlb.h>
>  
> +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
> +#define VMEMMAP_HPAGE_SHIFT			PMD_SHIFT
> +#define arch_vmemmap_support_huge_mapping()	boot_cpu_has(X86_FEATURE_PSE)
> +#endif
> +
>  #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
>  
>  #endif /* _ASM_X86_HUGETLB_H */
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index eed3dd3bd626..ace304a6196c 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -593,6 +593,23 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h)
>  
>  #include <asm/hugetlb.h>
>  
> +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
> +#ifndef arch_vmemmap_support_huge_mapping
> +static inline bool arch_vmemmap_support_huge_mapping(void)
> +{
> +	return false;
> +}
> +#endif
> +
> +#ifndef VMEMMAP_HPAGE_SHIFT
> +#define VMEMMAP_HPAGE_SHIFT		PMD_SHIFT
> +#endif
> +#define VMEMMAP_HPAGE_ORDER		(VMEMMAP_HPAGE_SHIFT - PAGE_SHIFT)
> +#define VMEMMAP_HPAGE_NR		(1 << VMEMMAP_HPAGE_ORDER)
> +#define VMEMMAP_HPAGE_SIZE		((1UL) << VMEMMAP_HPAGE_SHIFT)
> +#define VMEMMAP_HPAGE_MASK		(~(VMEMMAP_HPAGE_SIZE - 1))
> +#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
> +
>  #ifndef is_hugepage_only_range
>  static inline int is_hugepage_only_range(struct mm_struct *mm,
>  					unsigned long addr, unsigned long len)
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index f1b2b733b49b..d6ae9b6876be 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1295,11 +1295,108 @@ static inline void destroy_compound_gigantic_page(struct page *page,
>  #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
>  #define RESERVE_VMEMMAP_NR	2U
>  
> +#define page_huge_pte(page)	((page)->pmd_huge_pte)
> +

I am not good at function names.  The following suggestions may be too
verbose.  However, they helped me understand purpose of routines.

>  static inline unsigned int nr_free_vmemmap(struct hstate *h)

	perhaps?	 	free_vmemmap_pages_per_hpage()

>  {
>  	return h->nr_free_vmemmap_pages;
>  }
>  
> +static inline unsigned int nr_vmemmap(struct hstate *h)

	perhaps?		vmemmap_pages_per_hpage()

> +{
> +	return nr_free_vmemmap(h) + RESERVE_VMEMMAP_NR;
> +}
> +
> +static inline unsigned long nr_vmemmap_size(struct hstate *h)

	perhaps?		vmemmap_pages_size_per_hpage()

> +{
> +	return (unsigned long)nr_vmemmap(h) << PAGE_SHIFT;
> +}
> +
> +static inline unsigned int nr_pgtable(struct hstate *h)

	perhaps?	pgtable_pages_to_prealloc_per_hpage()

> +{
> +	unsigned long vmemmap_size = nr_vmemmap_size(h);
> +
> +	if (!arch_vmemmap_support_huge_mapping())
> +		return 0;
> +
> +	/*
> +	 * No need pre-allocate page tabels when there is no vmemmap pages
> +	 * to free.
> +	 */
> +	if (!nr_free_vmemmap(h))
> +		return 0;
> +
> +	return ALIGN(vmemmap_size, VMEMMAP_HPAGE_SIZE) >> VMEMMAP_HPAGE_SHIFT;
> +}
> +
> +static inline void vmemmap_pgtable_init(struct page *page)
> +{
> +	page_huge_pte(page) = NULL;
> +}
> +

I see the following routines follow the pattern for vmemmap manipulation
in dax.

> +static void vmemmap_pgtable_deposit(struct page *page, pte_t *pte_p)
> +{
> +	pgtable_t pgtable = virt_to_page(pte_p);
> +
> +	/* FIFO */
> +	if (!page_huge_pte(page))
> +		INIT_LIST_HEAD(&pgtable->lru);
> +	else
> +		list_add(&pgtable->lru, &page_huge_pte(page)->lru);
> +	page_huge_pte(page) = pgtable;
> +}
> +
> +static pte_t *vmemmap_pgtable_withdraw(struct page *page)
> +{
> +	pgtable_t pgtable;
> +
> +	/* FIFO */
> +	pgtable = page_huge_pte(page);
> +	if (unlikely(!pgtable))
> +		return NULL;
> +	page_huge_pte(page) = list_first_entry_or_null(&pgtable->lru,
> +						       struct page, lru);
> +	if (page_huge_pte(page))
> +		list_del(&pgtable->lru);
> +	return page_to_virt(pgtable);
> +}
> +
> +static int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
> +{
> +	int i;
> +	pte_t *pte_p;
> +	unsigned int nr = nr_pgtable(h);
> +
> +	if (!nr)
> +		return 0;
> +
> +	vmemmap_pgtable_init(page);
> +
> +	for (i = 0; i < nr; i++) {
> +		pte_p = pte_alloc_one_kernel(&init_mm);
> +		if (!pte_p)
> +			goto out;
> +		vmemmap_pgtable_deposit(page, pte_p);
> +	}
> +
> +	return 0;
> +out:
> +	while (i-- && (pte_p = vmemmap_pgtable_withdraw(page)))
> +		pte_free_kernel(&init_mm, pte_p);
> +	return -ENOMEM;
> +}
> +
> +static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
> +{
> +	pte_t *pte_p;
> +
> +	if (!nr_pgtable(h))
> +		return;
> +
> +	while ((pte_p = vmemmap_pgtable_withdraw(page)))
> +		pte_free_kernel(&init_mm, pte_p);
> +}
> +
>  static void __init hugetlb_vmemmap_init(struct hstate *h)
>  {
>  	unsigned int order = huge_page_order(h);
> @@ -1323,6 +1420,15 @@ static void __init hugetlb_vmemmap_init(struct hstate *h)
>  static inline void hugetlb_vmemmap_init(struct hstate *h)
>  {
>  }
> +
> +static inline int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
> +{
> +	return 0;
> +}
> +
> +static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
> +{
> +}
>  #endif
>  
>  static void update_and_free_page(struct hstate *h, struct page *page)
> @@ -1531,6 +1637,9 @@ void free_huge_page(struct page *page)
>  
>  static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
>  {
> +	/* Must be called before the initialization of @page->lru */
> +	vmemmap_pgtable_free(h, page);
> +
>  	INIT_LIST_HEAD(&page->lru);
>  	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
>  	set_hugetlb_cgroup(page, NULL);
> @@ -1783,6 +1892,14 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
>  	if (!page)
>  		return NULL;
>  
> +	if (vmemmap_pgtable_prealloc(h, page)) {
> +		if (hstate_is_gigantic(h))
> +			free_gigantic_page(page, huge_page_order(h));
> +		else
> +			put_page(page);
> +		return NULL;
> +	}
> +

It seems a bit strange that we will fail a huge page allocation if
vmemmap_pgtable_prealloc fails.  Not sure, but it almost seems like we shold
allow the allocation and log a warning?  It is somewhat unfortunate that
we need to allocate a page to free pages.

>  	if (hstate_is_gigantic(h))
>  		prep_compound_gigantic_page(page, huge_page_order(h));
>  	prep_new_huge_page(h, page, page_to_nid(page));
> 


-- 
Mike Kravetz