On Mon 08-03-21 18:28:06, Muchun Song wrote:
> For HugeTLB page, there are more metadata to save in the struct page.
> But the head struct page cannot meet our needs, so we have to abuse
> other tail struct page to store the metadata. In order to avoid
> conflicts caused by subsequent use of more tail struct pages, we can
> gather these discrete indexes of tail struct page. In this case, it
> will be easier to add a new tail page index later.
>
> 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.
OK, so this is what I have asked in an earlier patch. Good. I would
reorder and make this patch prior to the one relying on the fact though.
> Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
> Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
> Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
> Tested-by: Chen Huang <chenhuang5@xxxxxxxxxx>
> Tested-by: Bodeddula Balasubramaniam <bodeddub@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
> ---
> include/linux/hugetlb.h | 24 ++++++++++++++++++++++--
> include/linux/hugetlb_cgroup.h | 19 +++++++++++--------
> mm/hugetlb.c | 6 +++---
> mm/hugetlb_vmemmap.c | 8 ++++++++
> 4 files changed, 44 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index a4d80f7263fc..c70421e26189 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -28,6 +28,26 @@ typedef struct { unsigned long pd; } hugepd_t;
> #include <linux/shm.h>
> #include <asm/tlbflush.h>
>
> +/*
> + * For HugeTLB page, there are more metadata to save in the struct page. But
> + * the head struct page cannot meet our needs, so we have to abuse other tail
> + * struct page to store the metadata. In order to avoid conflicts caused by
> + * subsequent use of more tail struct pages, we gather these discrete indexes
> + * of tail struct page here.
> + */
> +enum {
> + SUBPAGE_INDEX_SUBPOOL = 1, /* reuse page->private */
> +#ifdef CONFIG_CGROUP_HUGETLB
> + SUBPAGE_INDEX_CGROUP, /* reuse page->private */
> + SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */
> + __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
> +#endif
> +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
> + SUBPAGE_INDEX_HWPOISON, /* reuse page->private */
> +#endif
> + __NR_USED_SUBPAGE,
> +};
> +
> struct hugepage_subpool {
> spinlock_t lock;
> long count;
> @@ -607,13 +627,13 @@ extern unsigned int default_hstate_idx;
> */
> static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
> {
> - return (struct hugepage_subpool *)(hpage+1)->private;
> + return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
> }
>
> static inline void hugetlb_set_page_subpool(struct page *hpage,
> struct hugepage_subpool *subpool)
> {
> - set_page_private(hpage+1, (unsigned long)subpool);
> + set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
> }
>
> static inline struct hstate *hstate_file(struct file *f)
> diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
> index 2ad6e92f124a..54ec689e3c9c 100644
> --- a/include/linux/hugetlb_cgroup.h
> +++ b/include/linux/hugetlb_cgroup.h
> @@ -21,15 +21,16 @@ struct hugetlb_cgroup;
> struct resv_map;
> struct file_region;
>
> +#ifdef CONFIG_CGROUP_HUGETLB
> /*
> * Minimum page order trackable by hugetlb cgroup.
> * At least 4 pages are necessary for all the tracking information.
> - * The second tail page (hpage[2]) is the fault usage cgroup.
> - * The third tail page (hpage[3]) is the reservation usage cgroup.
> + * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
> + * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
> + * is the reservation usage cgroup.
> */
> -#define HUGETLB_CGROUP_MIN_ORDER 2
> +#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1)
>
> -#ifdef CONFIG_CGROUP_HUGETLB
> enum hugetlb_memory_event {
> HUGETLB_MAX,
> HUGETLB_NR_MEMORY_EVENTS,
> @@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd)
> if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
> return NULL;
> if (rsvd)
> - return (struct hugetlb_cgroup *)page[3].private;
> + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
> else
> - return (struct hugetlb_cgroup *)page[2].private;
> + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
> }
>
> static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
> @@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page,
> if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
> return -1;
> if (rsvd)
> - page[3].private = (unsigned long)h_cg;
> + set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
> + (unsigned long)h_cg);
> else
> - page[2].private = (unsigned long)h_cg;
> + set_page_private(page + SUBPAGE_INDEX_CGROUP,
> + (unsigned long)h_cg);
> return 0;
> }
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index c221b937be17..4956880a7861 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1312,7 +1312,7 @@ static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
> if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
> return;
>
> - page = head + page_private(head + 4);
> + page = head + page_private(head + SUBPAGE_INDEX_HWPOISON);
>
> /*
> * Move PageHWPoison flag from head page to the raw error page,
> @@ -1331,7 +1331,7 @@ static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
> return;
>
> if (free_vmemmap_pages_per_hpage(h)) {
> - set_page_private(head + 4, page - head);
> + set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
> } else if (page != head) {
> /*
> * Move PageHWPoison flag from head page to the raw error page,
> @@ -1347,7 +1347,7 @@ static inline void hwpoison_subpage_clear(struct hstate *h, struct page *head)
> if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
> return;
>
> - set_page_private(head + 4, 0);
> + set_page_private(head + SUBPAGE_INDEX_HWPOISON, 0);
> }
> #else
> static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index b65f0d5189bd..33e42678abe3 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -257,6 +257,14 @@ 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;
>
> --
> 2.11.0
>
--
Michal Hocko
SUSE Labs
