Subject: madvise(MADV_HUGEPAGE) From: Andrea Arcangeli Add madvise MADV_HUGEPAGE to mark regions that are important to be hugepage backed. Return -EINVAL if the vma is not of an anonymous type, or the feature isn't built into the kernel. Never silently return success. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel --- diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -101,6 +101,7 @@ extern int split_huge_page(struct page * #endif extern unsigned long vma_address(struct page *page, struct vm_area_struct *vma); +extern int hugepage_madvise(unsigned long *vm_flags); static inline int PageTransHuge(struct page *page) { VM_BUG_ON(PageTail(page)); @@ -119,6 +120,11 @@ static inline int split_huge_page(struct #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) #define PageTransHuge(page) 0 +static inline int hugepage_madvise(unsigned long *vm_flags) +{ + BUG_ON(0); + return 0; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -463,9 +463,11 @@ int do_huge_pmd_wp_page(struct mm_struct put_page(new_page); new_page = NULL; } - if (unlikely(!new_page)) - return do_huge_pmd_wp_page_fallback(mm, vma, address, - pmd, orig_pmd, page, haddr); + if (unlikely(!new_page)) { + ret = do_huge_pmd_wp_page_fallback(mm, vma, address, + pmd, orig_pmd, page, haddr); + goto out; + } copy_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR); __SetPageUptodate(new_page); @@ -495,6 +497,7 @@ int do_huge_pmd_wp_page(struct mm_struct } out_unlock: spin_unlock(&mm->page_table_lock); +out: return ret; } @@ -854,3 +857,19 @@ out_unlock: out: return ret; } + +int hugepage_madvise(unsigned long *vm_flags) +{ + /* + * Be somewhat over-protective like KSM for now! + */ + if (*vm_flags & (VM_HUGEPAGE | VM_SHARED | VM_MAYSHARE | + VM_PFNMAP | VM_IO | VM_DONTEXPAND | + VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | + VM_MIXEDMAP | VM_SAO)) + return -EINVAL; + + *vm_flags |= VM_HUGEPAGE; + + return 0; +} diff --git a/mm/madvise.c b/mm/madvise.c --- a/mm/madvise.c +++ b/mm/madvise.c @@ -71,6 +71,11 @@ static long madvise_behavior(struct vm_a if (error) goto out; break; + case MADV_HUGEPAGE: + error = hugepage_madvise(&new_flags); + if (error) + goto out; + break; } if (new_flags == vma->vm_flags) { @@ -283,6 +288,9 @@ madvise_behavior_valid(int behavior) case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + case MADV_HUGEPAGE: +#endif return 1; default: