From 31caf665e666b51fe36efd1e54031ed29e86c0b4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:21:59 -0700 Subject: mm: migrate: make core migration code aware of hugepage Currently hugepage migration is available only for soft offlining, but it's also useful for some other users of page migration (clearly because users of hugepage can enjoy the benefit of mempolicy and memory hotplug.) So this patchset tries to extend such users to support hugepage migration. The target of this patchset is to enable hugepage migration for NUMA related system calls (migrate_pages(2), move_pages(2), and mbind(2)), and memory hotplug. This patchset does not add hugepage migration for memory compaction, because users of memory compaction mainly expect to construct thp by arranging raw pages, and there's little or no need to compact hugepages. CMA, another user of page migration, can have benefit from hugepage migration, but is not enabled to support it for now (just because of lack of testing and expertise in CMA.) Hugepage migration of non pmd-based hugepage (for example 1GB hugepage in x86_64, or hugepages in architectures like ia64) is not enabled for now (again, because of lack of testing.) As for how these are achived, I extended the API (migrate_pages()) to handle hugepage (with patch 1 and 2) and adjusted code of each caller to check and collect movable hugepages (with patch 3-7). Remaining 2 patches are kind of miscellaneous ones to avoid unexpected behavior. Patch 8 is about making sure that we only migrate pmd-based hugepages. And patch 9 is about choosing appropriate zone for hugepage allocation. My test is mainly functional one, simply kicking hugepage migration via each entry point and confirm that migration is done correctly. Test code is available here: git://github.com/Naoya-Horiguchi/test_hugepage_migration_extension.git And I always run libhugetlbfs test when changing hugetlbfs's code. With this patchset, no regression was found in the test. This patch (of 9): Before enabling each user of page migration to support hugepage, this patch enables the list of pages for migration to link not only LRU pages, but also hugepages. As a result, putback_movable_pages() and migrate_pages() can handle both of LRU pages and hugepages. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c2b1801a160b..bc8d8370cd0d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -66,6 +66,8 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); int dequeue_hwpoisoned_huge_page(struct page *page); +bool isolate_huge_page(struct page *page, struct list_head *list); +void putback_active_hugepage(struct page *page); void copy_huge_page(struct page *dst, struct page *src); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -134,6 +136,8 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) return 0; } +#define isolate_huge_page(p, l) false +#define putback_active_hugepage(p) do {} while (0) static inline void copy_huge_page(struct page *dst, struct page *src) { } -- cgit v1.2.3 From 74060e4d78795c7c43805133cb717d82533d4e0d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:06 -0700 Subject: mm: mbind: add hugepage migration code to mbind() Extend do_mbind() to handle vma with VM_HUGETLB set. We will be able to migrate hugepage with mbind(2) after applying the enablement patch which comes later in this series. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bc8d8370cd0d..d1db00790a84 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -265,6 +265,8 @@ struct huge_bootmem_page { }; struct page *alloc_huge_page_node(struct hstate *h, int nid); +struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve); /* arch callback */ int __init alloc_bootmem_huge_page(struct hstate *h); @@ -378,6 +380,7 @@ static inline pgoff_t basepage_index(struct page *page) #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL #define hstate_sizelog(s) NULL -- cgit v1.2.3 From c8721bbbdd36382de51cd6b7a56322e0acca2414 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:09 -0700 Subject: mm: memory-hotplug: enable memory hotplug to handle hugepage Until now 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. [yongjun_wei@trendmicro.com.cn: remove duplicated include] Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Cc: Hillf Danton Cc: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Wei Yongjun Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d1db00790a84..2e02c4ed1035 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -68,6 +68,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); +bool is_hugepage_active(struct page *page); void copy_huge_page(struct page *dst, struct page *src); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -138,6 +139,7 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) #define isolate_huge_page(p, l) false #define putback_active_hugepage(p) do {} while (0) +#define is_hugepage_active(x) false static inline void copy_huge_page(struct page *dst, struct page *src) { } @@ -377,6 +379,9 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern void dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn); + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL @@ -403,6 +408,7 @@ static inline pgoff_t basepage_index(struct page *page) { return page->index; } +#define dissolve_free_huge_pages(s, e) do {} while (0) #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From 83467efbdb7948146581a56cbd683a22a0684bbb Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:11 -0700 Subject: mm: migrate: check movability of hugepage in unmap_and_move_huge_page() Currently hugepage migration works well only for pmd-based hugepages (mainly due to lack of testing,) so we had better not enable migration of other levels of hugepages until we are ready for it. Some users of hugepage migration (mbind, move_pages, and migrate_pages) do page table walk and check pud/pmd_huge() there, so they are safe. But the other users (softoffline and memory hotremove) don't do this, so without this patch they can try to migrate unexpected types of hugepages. To prevent this, we introduce hugepage_migration_support() as an architecture dependent check of whether hugepage are implemented on a pmd basis or not. And on some architecture multiple sizes of hugepages are available, so hugepage_migration_support() also checks hugepage size. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Hillf Danton Cc: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2e02c4ed1035..0393270466c3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -381,6 +381,16 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); +int pmd_huge_support(void); +/* + * Currently hugepage migration is enabled only for pmd-based hugepage. + * This function will be updated when hugepage migration is more widely + * supported. + */ +static inline int hugepage_migration_support(struct hstate *h) +{ + return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +} #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -409,6 +419,8 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) +#define pmd_huge_support() 0 +#define hugepage_migration_support(h) 0 #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3