From a0f7a756c2f7543585657cdeeefdfcc11b567293 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 23 Jul 2014 14:00:01 -0700 Subject: [PATCH] mm/rmap.c: fix pgoff calculation to handle hugepage correctly I triggered VM_BUG_ON() in vma_address() when I tried to migrate an anonymous hugepage with mbind() in the kernel v3.16-rc3. This is because pgoff's calculation in rmap_walk_anon() fails to consider compound_order() only to have an incorrect value. This patch introduces page_to_pgoff(), which gets the page's offset in PAGE_CACHE_SIZE. Kirill pointed out that page cache tree should natively handle hugepages, and in order to make hugetlbfs fit it, page->index of hugetlbfs page should be in PAGE_CACHE_SIZE. This is beyond this patch, but page_to_pgoff() contains the point to be fixed in a single function. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: Joonsoo Kim Cc: Hugh Dickins Cc: Rik van Riel Cc: Hillf Danton Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 12 ++++++++++++ mm/memory-failure.c | 4 ++-- mm/rmap.c | 10 +++------- 3 files changed, 17 insertions(+), 9 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0a97b583ee8d..e1474ae18c88 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -398,6 +398,18 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, filler, data); } +/* + * Get the offset in PAGE_SIZE. + * (TODO: hugepage should have ->index in PAGE_SIZE) + */ +static inline pgoff_t page_to_pgoff(struct page *page) +{ + if (unlikely(PageHeadHuge(page))) + return page->index << compound_order(page); + else + return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); +} + /* * Return byte-offset into filesystem object for page. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c6399e328931..7211a73ba14d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -435,7 +435,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (av == NULL) /* Not actually mapped anymore */ return; - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = page_to_pgoff(page); read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; @@ -469,7 +469,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, mutex_lock(&mapping->i_mmap_mutex); read_lock(&tasklist_lock); for_each_process(tsk) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_to_pgoff(page); struct task_struct *t = task_early_kill(tsk, force_early); if (!t) diff --git a/mm/rmap.c b/mm/rmap.c index b7e94ebbd09e..22a4a7699cdb 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -517,11 +517,7 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - - if (unlikely(is_vm_hugetlb_page(vma))) - pgoff = page->index << huge_page_order(page_hstate(page)); - + pgoff_t pgoff = page_to_pgoff(page); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } @@ -1639,7 +1635,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff_t pgoff = page_to_pgoff(page); struct anon_vma_chain *avc; int ret = SWAP_AGAIN; @@ -1680,7 +1676,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) { struct address_space *mapping = page->mapping; - pgoff_t pgoff = page->index << compound_order(page); + pgoff_t pgoff = page_to_pgoff(page); struct vm_area_struct *vma; int ret = SWAP_AGAIN; -- 2.20.1