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 <n-horiguchi@ah.jp.nec.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0a97b58..e1474ae 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -399,6 +399,18 @@
}
/*
+ * 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.
*/
static inline loff_t page_offset(struct page *page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c6399e3..7211a73 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -435,7 +435,7 @@
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 @@
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 b7e94eb..22a4a76 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -517,11 +517,7 @@
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 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_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;