From fafaa4264eba49fd10695c193a82760558d093f4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:37 -0800 Subject: pagewalk: improve vma handling Current implementation of page table walker has a fundamental problem in vma handling, which started when we tried to handle vma(VM_HUGETLB). Because it's done in pgd loop, considering vma boundary makes code complicated and bug-prone. From the users viewpoint, some user checks some vma-related condition to determine whether the user really does page walk over the vma. In order to solve these, this patch moves vma check outside pgd loop and introduce a new callback ->test_walk(). Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6106d3f3dab..3891a368e5e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1171,10 +1171,16 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry - * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry - * is used. + * @test_walk: caller specific callback function to determine whether + * we walk over the current vma or not. A positive returned + * value means "do page table walk over the current vma," + * and a negative one means "abort current page table walk + * right now." 0 means "skip the current vma." + * @mm: mm_struct representing the target process of page table walk + * @vma: vma currently walked (NULL if walking outside vmas) + * @private: private data for callbacks' usage * - * (see walk_page_range for more details) + * (see the comment on walk_page_range() for more details) */ struct mm_walk { int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -1186,7 +1192,10 @@ struct mm_walk { int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); + int (*test_walk)(unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; + struct vm_area_struct *vma; void *private; }; -- cgit v1.2.1