On Thu, Feb 21, 2013 at 02:41:47PM -0500, Naoya Horiguchi wrote:
> Date: Thu, 21 Feb 2013 14:41:47 -0500
> From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> To: linux-mm@xxxxxxxxx
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>, Mel Gorman <mel@xxxxxxxxx>,
> Hugh Dickins <hughd@xxxxxxxxxx>, KOSAKI Motohiro
> <kosaki.motohiro@xxxxxxxxxxxxxx>, Andi Kleen <andi@xxxxxxxxxxxxxx>,
> linux-kernel@xxxxxxxxxxxxxxx
> Subject: [PATCH 8/9] memory-hotplug: enable memory hotplug to handle
> hugepage
>
> Currently we can't offline memory blocks which contain hugepages because
> a hugepage is considered as an unmovable page. But now with this patch
> series, a hugepage has become movable, so by using hugepage migration we
> can offline such memory blocks.
>
> What's different from other users of hugepage migration is that we need
> to decompose all the hugepages inside the target memory block into free
> buddy pages after hugepage migration, because otherwise free hugepages
> remaining in the memory block intervene the memory offlining.
> For this reason we introduce new functions dissolve_free_huge_page() and
> dissolve_free_huge_pages().
>
> Other than that, what this patch does is straightforwardly to add hugepage
> migration code, that is, adding hugepage code to the functions which scan
> over pfn and collect hugepages to be migrated, and adding a hugepage
> allocation function to alloc_migrate_target().
>
> As for larger hugepages (1GB for x86_64), it's not easy to do hotremove
> over them because it's larger than memory block. So we now simply leave
> it to fail as it is.
>
> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> ---
> include/linux/hugetlb.h | 8 ++++++++
> mm/hugetlb.c | 43 +++++++++++++++++++++++++++++++++++++++++
> mm/memory_hotplug.c | 51 ++++++++++++++++++++++++++++++++++++++++---------
> mm/migrate.c | 12 +++++++++++-
> mm/page_alloc.c | 12 ++++++++++++
> mm/page_isolation.c | 5 +++++
> 6 files changed, 121 insertions(+), 10 deletions(-)
>
> diff --git v3.8.orig/include/linux/hugetlb.h v3.8/include/linux/hugetlb.h
> index 86a4d78..e33f07f 100644
> --- v3.8.orig/include/linux/hugetlb.h
> +++ v3.8/include/linux/hugetlb.h
> @@ -70,6 +70,7 @@ int dequeue_hwpoisoned_huge_page(struct page *page);
> void putback_active_hugepage(struct page *page);
> void putback_active_hugepages(struct list_head *l);
> void migrate_hugepage_add(struct page *page, struct list_head *list);
> +int is_hugepage_movable(struct page *page);
> void copy_huge_page(struct page *dst, struct page *src);
>
> extern unsigned long hugepages_treat_as_movable;
> @@ -136,6 +137,7 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page)
> #define putback_active_hugepage(p) 0
> #define putback_active_hugepages(l) 0
> #define migrate_hugepage_add(p, l) 0
> +#define is_hugepage_movable(x) 0
> static inline void copy_huge_page(struct page *dst, struct page *src)
> {
> }
> @@ -358,6 +360,10 @@ static inline int hstate_index(struct hstate *h)
> return h - hstates;
> }
>
> +extern void dissolve_free_huge_page(struct page *page);
> +extern void dissolve_free_huge_pages(unsigned long start_pfn,
> + unsigned long end_pfn);
> +
> #else
> struct hstate {};
> #define alloc_huge_page(v, a, r) NULL
> @@ -378,6 +384,8 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
> }
> #define hstate_index_to_shift(index) 0
> #define hstate_index(h) 0
> +#define dissolve_free_huge_page(p) 0
> +#define dissolve_free_huge_pages(s, e) 0
> #endif
>
> #endif /* _LINUX_HUGETLB_H */
> diff --git v3.8.orig/mm/hugetlb.c v3.8/mm/hugetlb.c
> index ccf9995..c28e6c9 100644
> --- v3.8.orig/mm/hugetlb.c
> +++ v3.8/mm/hugetlb.c
> @@ -843,6 +843,30 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
> return ret;
> }
>
> +/* Dissolve a given free hugepage into free pages. */
> +void dissolve_free_huge_page(struct page *page)
> +{
> + if (PageHuge(page) && !page_count(page)) {
> + struct hstate *h = page_hstate(page);
> + int nid = page_to_nid(page);
> + spin_lock(&hugetlb_lock);
> + list_del(&page->lru);
> + h->free_huge_pages--;
> + h->free_huge_pages_node[nid]--;
> + update_and_free_page(h, page);
> + spin_unlock(&hugetlb_lock);
> + }
> +}
> +
> +/* Dissolve free hugepages in a given pfn range. Used by memory hotplug. */
> +void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
> +{
> + unsigned long pfn;
> + unsigned int step = 1 << (HUGETLB_PAGE_ORDER);
> + for (pfn = start_pfn; pfn < end_pfn; pfn += step)
> + dissolve_free_huge_page(pfn_to_page(pfn));
> +}
> +
> static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
> {
> struct page *page;
> @@ -3158,6 +3182,25 @@ static int is_hugepage_on_freelist(struct page *hpage)
> return 0;
> }
>
> +/* Returns true for head pages of in-use hugepages, otherwise returns false. */
> +int is_hugepage_movable(struct page *hpage)
> +{
> + struct page *page;
> + struct page *tmp;
> + struct hstate *h = page_hstate(hpage);
> + int ret = 0;
> +
> + VM_BUG_ON(!PageHuge(hpage));
> + if (PageTail(hpage))
> + return 0;
> + spin_lock(&hugetlb_lock);
> + list_for_each_entry_safe(page, tmp, &h->hugepage_activelist, lru)
> + if (page == hpage)
> + ret = 1;
I don't understand the logic here. 1) page is not removed why tmp is used?
2) why hitting (page ==hpage) but not breaking from the loop?
> + spin_unlock(&hugetlb_lock);
> + return ret;
> +}
> +
> [...]
Attachment:
signature.asc
Description: Digital signature