[PATCH] mm: rss = file_rss + anon_rss

I was lazy when we added anon_rss, and chose to change as few places as
possible.  So currently each anonymous page has to be counted twice, in rss
and in anon_rss.  Which won't be so good if those are atomic counts in some
configurations.

Change that around: keep file_rss and anon_rss separately, and add them
together (with get_mm_rss macro) when the total is needed - reading two
atomics is much cheaper than updating two atomics.  And update anon_rss
upfront, typically in memory.c, not tucked away in page_add_anon_rmap.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 27 insertions, 26 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index ab23a06..fd7f2a1 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -39,7 +39,7 @@ static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 					set_page_dirty(page);
 				page_remove_rmap(page);
 				page_cache_release(page);
-				dec_mm_counter(mm, rss);
+				dec_mm_counter(mm, file_rss);
 			}
 		}
 	} else {
@@ -95,7 +95,7 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	zap_pte(mm, vma, addr, pte);
 
-	inc_mm_counter(mm,rss);
+	inc_mm_counter(mm, file_rss);
 	flush_icache_page(vma, page);
 	set_pte_at(mm, addr, pte, mk_pte(page, prot));
 	page_add_file_rmap(page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 61d3806..094455b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -286,7 +286,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = *src_pte;
 			ptepage = pte_page(entry);
 			get_page(ptepage);
-			add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
+			add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
@@ -324,7 +324,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
 		page = pte_page(pte);
 		put_page(page);
-		add_mm_counter(mm, rss,  - (HPAGE_SIZE / PAGE_SIZE));
+		add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
 	}
 	flush_tlb_range(vma, start, end);
 }
@@ -386,7 +386,7 @@ int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
 				goto out;
 			}
 		}
-		add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
+		add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
 		set_huge_pte_at(mm, addr, pte, make_huge_pte(vma, page));
 	}
 out:
diff --git a/mm/memory.c b/mm/memory.c
index 51eb3857..59d42e5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -397,9 +397,10 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pte = pte_mkclean(pte);
 	pte = pte_mkold(pte);
 	get_page(page);
-	inc_mm_counter(dst_mm, rss);
 	if (PageAnon(page))
 		inc_mm_counter(dst_mm, anon_rss);
+	else
+		inc_mm_counter(dst_mm, file_rss);
 	set_pte_at(dst_mm, addr, dst_pte, pte);
 	page_dup_rmap(page);
 }
@@ -581,8 +582,8 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 					set_page_dirty(page);
 				if (pte_young(ptent))
 					mark_page_accessed(page);
+				dec_mm_counter(tlb->mm, file_rss);
 			}
-			dec_mm_counter(tlb->mm, rss);
 			page_remove_rmap(page);
 			tlb_remove_page(tlb, page);
 			continue;
@@ -1290,13 +1291,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 	page_table = pte_offset_map(pmd, address);
 	if (likely(pte_same(*page_table, orig_pte))) {
-		if (PageAnon(old_page))
-			dec_mm_counter(mm, anon_rss);
 		if (PageReserved(old_page))
-			inc_mm_counter(mm, rss);
-		else
+			inc_mm_counter(mm, anon_rss);
+		else {
 			page_remove_rmap(old_page);
-
+			if (!PageAnon(old_page)) {
+				inc_mm_counter(mm, anon_rss);
+				dec_mm_counter(mm, file_rss);
+			}
+		}
 		flush_cache_page(vma, address, pfn);
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -1701,7 +1704,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* The page isn't present yet, go ahead with the fault. */
 
-	inc_mm_counter(mm, rss);
+	inc_mm_counter(mm, anon_rss);
 	pte = mk_pte(page, vma->vm_page_prot);
 	if (write_access && can_share_swap_page(page)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
@@ -1774,7 +1777,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			page_cache_release(page);
 			goto unlock;
 		}
-		inc_mm_counter(mm, rss);
+		inc_mm_counter(mm, anon_rss);
 		entry = mk_pte(page, vma->vm_page_prot);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		lru_cache_add_active(page);
@@ -1887,19 +1890,19 @@ retry:
 	 */
 	/* Only go through if we didn't race with anybody else... */
 	if (pte_none(*page_table)) {
-		if (!PageReserved(new_page))
-			inc_mm_counter(mm, rss);
-
 		flush_icache_page(vma, new_page);
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		if (write_access)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		set_pte_at(mm, address, page_table, entry);
 		if (anon) {
+			inc_mm_counter(mm, anon_rss);
 			lru_cache_add_active(new_page);
 			page_add_anon_rmap(new_page, vma, address);
-		} else
+		} else if (!PageReserved(new_page)) {
+			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(new_page);
+		}
 	} else {
 		/* One of our sibling threads was faster, back out. */
 		page_cache_release(new_page);
@@ -2192,7 +2195,7 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 void update_mem_hiwater(struct task_struct *tsk)
 {
 	if (tsk->mm) {
-		unsigned long rss = get_mm_counter(tsk->mm, rss);
+		unsigned long rss = get_mm_rss(tsk->mm);
 
 		if (tsk->mm->hiwater_rss < rss)
 			tsk->mm->hiwater_rss = rss;
diff --git a/mm/nommu.c b/mm/nommu.c
index 0ef241a..59992488 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1083,7 +1083,7 @@ void update_mem_hiwater(struct task_struct *tsk)
 	unsigned long rss;
 
 	if (likely(tsk->mm)) {
-		rss = get_mm_counter(tsk->mm, rss);
+		rss = get_mm_rss(tsk->mm);
 		if (tsk->mm->hiwater_rss < rss)
 			tsk->mm->hiwater_rss = rss;
 		if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
diff --git a/mm/rmap.c b/mm/rmap.c
index 1fc559e..5047576 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -445,8 +445,6 @@ void page_add_anon_rmap(struct page *page,
 {
 	BUG_ON(PageReserved(page));
 
-	inc_mm_counter(vma->vm_mm, anon_rss);
-
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		struct anon_vma *anon_vma = vma->anon_vma;
 
@@ -561,9 +559,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
 		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 		BUG_ON(pte_file(*pte));
 		dec_mm_counter(mm, anon_rss);
-	}
+	} else
+		dec_mm_counter(mm, file_rss);
 
-	dec_mm_counter(mm, rss);
 	page_remove_rmap(page);
 	page_cache_release(page);
 
@@ -667,7 +665,7 @@ static void try_to_unmap_cluster(unsigned long cursor,
 
 		page_remove_rmap(page);
 		page_cache_release(page);
-		dec_mm_counter(mm, rss);
+		dec_mm_counter(mm, file_rss);
 		(*mapcount)--;
 	}
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 05c8512..296e0bb 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -407,7 +407,7 @@ void free_swap_and_cache(swp_entry_t entry)
 static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
 		unsigned long addr, swp_entry_t entry, struct page *page)
 {
-	inc_mm_counter(vma->vm_mm, rss);
+	inc_mm_counter(vma->vm_mm, anon_rss);
 	get_page(page);
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));