From 94310cbcaa3c2bc1b790ba997270f28dc173d8ce Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 6 Jul 2017 15:38:38 -0700 Subject: [PATCH] mm/madvise: enable (soft|hard) offline of HugeTLB pages at PGD level Though migrating gigantic HugeTLB pages does not sound much like real world use case, they can be affected by memory errors. Hence migration at the PGD level HugeTLB pages should be supported just to enable soft and hard offline use cases. While allocating the new gigantic HugeTLB page, it should not matter whether new page comes from the same node or not. There would be very few gigantic pages on the system afterall, we should not be bothered about node locality when trying to save a big page from crashing. This change renames dequeu_huge_page_node() function as dequeue_huge _page_node_exact() preserving it's original functionality. Now the new dequeue_huge_page_node() function scans through all available online nodes to allocate a huge page for the NUMA_NO_NODE case and just falls back calling dequeu_huge_page_node_exact() for all other cases. [arnd@arndb.de: make hstate_is_gigantic() inline] Link: http://lkml.kernel.org/r/20170522124748.3911296-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170516100509.20122-1-khandual@linux.vnet.ibm.com Signed-off-by: Anshuman Khandual Signed-off-by: Arnd Bergmann Cc: "Aneesh Kumar K.V" Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 11 ++++++++++- mm/hugetlb.c | 18 +++++++++++++++++- mm/memory-failure.c | 13 +++++++++---- 3 files changed, 36 insertions(+), 6 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b857fc8cc2ec..5f539f985e2a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -466,7 +466,11 @@ extern int dissolve_free_huge_pages(unsigned long start_pfn, static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION - return huge_page_shift(h) == PMD_SHIFT; + if ((huge_page_shift(h) == PMD_SHIFT) || + (huge_page_shift(h) == PGDIR_SHIFT)) + return true; + else + return false; #else return false; #endif @@ -518,6 +522,11 @@ struct hstate {}; #define vma_mmu_pagesize(v) PAGE_SIZE #define huge_page_order(h) 0 #define huge_page_shift(h) PAGE_SHIFT +static inline bool hstate_is_gigantic(struct hstate *h) +{ + return false; +} + static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3eedb187e549..040d53ac1f8d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -867,7 +867,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page_node(struct hstate *h, int nid) +static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) { struct page *page; @@ -887,6 +887,22 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) return page; } +static struct page *dequeue_huge_page_node(struct hstate *h, int nid) +{ + struct page *page; + int node; + + if (nid != NUMA_NO_NODE) + return dequeue_huge_page_node_exact(h, nid); + + for_each_online_node(node) { + page = dequeue_huge_page_node_exact(h, node); + if (page) + return page; + } + return NULL; +} + /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ecc183fd94f3..a74c8311db95 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1492,11 +1492,16 @@ EXPORT_SYMBOL(unpoison_memory); static struct page *new_page(struct page *p, unsigned long private, int **x) { int nid = page_to_nid(p); - if (PageHuge(p)) - return alloc_huge_page_node(page_hstate(compound_head(p)), - nid); - else + if (PageHuge(p)) { + struct hstate *hstate = page_hstate(compound_head(p)); + + if (hstate_is_gigantic(hstate)) + return alloc_huge_page_node(hstate, NUMA_NO_NODE); + + return alloc_huge_page_node(hstate, nid); + } else { return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0); + } } /* -- 2.20.1