Commit 77490587 authored by Muchun Song's avatar Muchun Song Committed by Linus Torvalds
Browse files

mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate 

All the infrastructure is ready, so we introduce nr_free_vmemmap_pages
field in the hstate to indicate how many vmemmap pages associated with a
HugeTLB page that can be freed to buddy allocator.  And initialize it in
the hugetlb_vmemmap_init().  This patch is actual enablement of the
feature.

There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct page
structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, so add a
BUILD_BUG_ON to catch invalid usage of the tail struct page.

Link: https://lkml.kernel.org/r/20210510030027.56044-10-songmuchun@bytedance.com


Signed-off-by: default avatarMuchun Song <songmuchun@bytedance.com>
Acked-by: default avatarMike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: default avatarOscar Salvador <osalvador@suse.de>
Reviewed-by: default avatarMiaohe Lin <linmiaohe@huawei.com>
Tested-by: default avatarChen Huang <chenhuang5@huawei.com>
Tested-by: default avatarBodeddula Balasubramaniam <bodeddub@amazon.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Barry Song <song.bao.hua@hisilicon.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 4bab4964

include/linux/hugetlb.h

+3 −0
Original line number Diff line number Diff line
@@ -608,6 +608,9 @@ struct hstate { 
	unsigned int nr_huge_pages_node[MAX_NUMNODES];

	unsigned int free_huge_pages_node[MAX_NUMNODES];

	unsigned int surplus_huge_pages_node[MAX_NUMNODES];

#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP

	unsigned int nr_free_vmemmap_pages;

#endif

#ifdef CONFIG_CGROUP_HUGETLB

	/* cgroup control files */

	struct cftype cgroup_files_dfl[7];

mm/hugetlb.c

+1 −0
Original line number Diff line number Diff line
@@ -3585,6 +3585,7 @@ void __init hugetlb_add_hstate(unsigned int order) 
	h->next_nid_to_free = first_memory_node;

	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",

					huge_page_size(h)/1024);

	hugetlb_vmemmap_init(h);



	parsed_hstate = h;

}

mm/hugetlb_vmemmap.c

+33 −0
Original line number Diff line number Diff line
@@ -262,3 +262,36 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head) 


	SetHPageVmemmapOptimized(head);

}



void __init hugetlb_vmemmap_init(struct hstate *h)

{

	unsigned int nr_pages = pages_per_huge_page(h);

	unsigned int vmemmap_pages;



	/*

	 * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct

	 * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,

	 * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.

	 */

	BUILD_BUG_ON(__NR_USED_SUBPAGE >=

		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));



	if (!hugetlb_free_vmemmap_enabled)

		return;



	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;

	/*

	 * The head page and the first tail page are not to be freed to buddy

	 * allocator, the other pages will map to the first tail page, so they

	 * can be freed.

	 *

	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true

	 * on some architectures (e.g. aarch64). See Documentation/arm64/

	 * hugetlbpage.rst for more details.

	 */

	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))

		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;



	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,

		h->name);

}

mm/hugetlb_vmemmap.h

+6 −4
Original line number Diff line number Diff line
@@ -13,17 +13,15 @@ 
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP

int alloc_huge_page_vmemmap(struct hstate *h, struct page *head);

void free_huge_page_vmemmap(struct hstate *h, struct page *head);

void hugetlb_vmemmap_init(struct hstate *h);



/*

 * How many vmemmap pages associated with a HugeTLB page that can be freed

 * to the buddy allocator.

 *

 * Todo: Returns zero for now, which means the feature is disabled. We will

 * enable it once all the infrastructure is there.

 */

static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)

{

	return 0;

	return h->nr_free_vmemmap_pages;

}

#else

static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
@@ -35,6 +33,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head) 
{

}



static inline void hugetlb_vmemmap_init(struct hstate *h)

{

}



static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)

{

	return 0;