mm: fix huge zero page accounting in smaps report

As a small zero page, huge zero page should not be accounted in smaps
report as normal page.

For small pages we rely on vm_normal_page() to filter out zero page, but
vm_normal_page() is not designed to handle pmds.  We only get here due
hackish cast pmd to pte in smaps_pte_range() -- pte and pmd format is not
necessary compatible on each and every architecture.

Let's add separate codepath to handle pmds.  follow_trans_huge_pmd() will
detect huge zero page for us.

We would need pmd_dirty() helper to do this properly.  The patch adds it
to THP-enabled architectures which don't yet have one.

[akpm@linux-foundation.org: use do_div to fix 32-bit build]
Signed-off-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Tested-by: Fengwei Yin <yfw.kernel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 68 insertions, 36 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f6734c6b66a6..246eae84b13b 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -447,58 +447,91 @@ struct mem_size_stats {
         u64 pss;
 };
 
+static void smaps_account(struct mem_size_stats *mss, struct page *page,
+                unsigned long size, bool young, bool dirty)
+{
+        int mapcount;
+
+        if (PageAnon(page))
+                mss->anonymous += size;
 
-static void smaps_pte_entry(pte_t ptent, unsigned long addr,
-                unsigned long ptent_size, struct mm_walk *walk)
+        mss->resident += size;
+        /* Accumulate the size in pages that have been accessed. */
+        if (young || PageReferenced(page))
+                mss->referenced += size;
+        mapcount = page_mapcount(page);
+        if (mapcount >= 2) {
+                u64 pss_delta;
+
+                if (dirty || PageDirty(page))
+                        mss->shared_dirty += size;
+                else
+                        mss->shared_clean += size;
+                pss_delta = (u64)size << PSS_SHIFT;
+                do_div(pss_delta, mapcount);
+                mss->pss += pss_delta;
+        } else {
+                if (dirty || PageDirty(page))
+                        mss->private_dirty += size;
+                else
+                        mss->private_clean += size;
+                mss->pss += (u64)size << PSS_SHIFT;
+        }
+}
+
+static void smaps_pte_entry(pte_t *pte, unsigned long addr,
+                struct mm_walk *walk)
 {
         struct mem_size_stats *mss = walk->private;
         struct vm_area_struct *vma = mss->vma;
         pgoff_t pgoff = linear_page_index(vma, addr);
         struct page *page = NULL;
-        int mapcount;
 
-        if (pte_present(ptent)) {
-                page = vm_normal_page(vma, addr, ptent);
-        } else if (is_swap_pte(ptent)) {
-                swp_entry_t swpent = pte_to_swp_entry(ptent);
+        if (pte_present(*pte)) {
+                page = vm_normal_page(vma, addr, *pte);
+        } else if (is_swap_pte(*pte)) {
+                swp_entry_t swpent = pte_to_swp_entry(*pte);
 
                 if (!non_swap_entry(swpent))
-                        mss->swap += ptent_size;
+                        mss->swap += PAGE_SIZE;
                 else if (is_migration_entry(swpent))
                         page = migration_entry_to_page(swpent);
-        } else if (pte_file(ptent)) {
-                if (pte_to_pgoff(ptent) != pgoff)
-                        mss->nonlinear += ptent_size;
+        } else if (pte_file(*pte)) {
+                if (pte_to_pgoff(*pte) != pgoff)
+                        mss->nonlinear += PAGE_SIZE;
         }
 
         if (!page)
                 return;
 
-        if (PageAnon(page))
-                mss->anonymous += ptent_size;
-
         if (page->index != pgoff)
-                mss->nonlinear += ptent_size;
+                mss->nonlinear += PAGE_SIZE;
 
-        mss->resident += ptent_size;
-        /* Accumulate the size in pages that have been accessed. */
-        if (pte_young(ptent) || PageReferenced(page))
-                mss->referenced += ptent_size;
-        mapcount = page_mapcount(page);
-        if (mapcount >= 2) {
-                if (pte_dirty(ptent) || PageDirty(page))
-                        mss->shared_dirty += ptent_size;
-                else
-                        mss->shared_clean += ptent_size;
-                mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
-        } else {
-                if (pte_dirty(ptent) || PageDirty(page))
-                        mss->private_dirty += ptent_size;
-                else
-                        mss->private_clean += ptent_size;
-                mss->pss += (ptent_size << PSS_SHIFT);
-        }
+        smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+                struct mm_walk *walk)
+{
+        struct mem_size_stats *mss = walk->private;
+        struct vm_area_struct *vma = mss->vma;
+        struct page *page;
+
+        /* FOLL_DUMP will return -EFAULT on huge zero page */
+        page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+        if (IS_ERR_OR_NULL(page))
+                return;
+        mss->anonymous_thp += HPAGE_PMD_SIZE;
+        smaps_account(mss, page, HPAGE_PMD_SIZE,
+                        pmd_young(*pmd), pmd_dirty(*pmd));
 }
+#else
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+                struct mm_walk *walk)
+{
+}
+#endif
 
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
                            struct mm_walk *walk)
@@ -509,9 +542,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
         spinlock_t *ptl;
 
         if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-                smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+                smaps_pmd_entry(pmd, addr, walk);
                 spin_unlock(ptl);
-                mss->anonymous_thp += HPAGE_PMD_SIZE;
                 return 0;
         }
 
@@ -524,7 +556,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
          */
         pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
         for (; addr != end; pte++, addr += PAGE_SIZE)
-                smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
+                smaps_pte_entry(pte, addr, walk);
         pte_unmap_unlock(pte - 1, ptl);
         cond_resched();
         return 0;