[PATCH] mm: rmap optimisation

Optimise rmap functions by minimising atomic operations when we know there
will be no concurrent modifications.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/exec.c

@@ -324,7 +324,7 @@ void install_arg_page(struct vm_area_struct *vma,
 	lru_cache_add_active(page);
 	set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
 					page, vma->vm_page_prot))));
-	page_add_anon_rmap(page, vma, address);
+	page_add_new_anon_rmap(page, vma, address);
 	pte_unmap_unlock(pte, ptl);
 
 	/* no need for flush_tlb */

include/linux/rmap.h

@@ -71,6 +71,7 @@ void __anon_vma_link(struct vm_area_struct *);
  * rmap interfaces called when adding or removing pte of page
  */
 void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
+void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
 void page_add_file_rmap(struct page *);
 void page_remove_rmap(struct page *);
 

mm/memory.c

@@ -1498,7 +1498,7 @@ gotten:
 		update_mmu_cache(vma, address, entry);
 		lazy_mmu_prot_update(entry);
 		lru_cache_add_active(new_page);
-		page_add_anon_rmap(new_page, vma, address);
+		page_add_new_anon_rmap(new_page, vma, address);
 
 		/* Free the old page.. */
 		new_page = old_page;
@@ -1978,7 +1978,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		inc_mm_counter(mm, anon_rss);
 		lru_cache_add_active(page);
 		SetPageReferenced(page);
-		page_add_anon_rmap(page, vma, address);
+		page_add_new_anon_rmap(page, vma, address);
 	} else {
 		/* Map the ZERO_PAGE - vm_page_prot is readonly */
 		page = ZERO_PAGE(address);
@@ -2109,7 +2109,7 @@ retry:
 		if (anon) {
 			inc_mm_counter(mm, anon_rss);
 			lru_cache_add_active(new_page);
-			page_add_anon_rmap(new_page, vma, address);
+			page_add_new_anon_rmap(new_page, vma, address);
 		} else {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(new_page);

mm/rmap.c

@@ -435,17 +435,14 @@ int page_referenced(struct page *page, int is_locked)
 }
 
 /**
- * page_add_anon_rmap - add pte mapping to an anonymous page
+ * page_set_anon_rmap - setup new anonymous rmap
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
- *
- * The caller needs to hold the pte lock.
  */
-void page_add_anon_rmap(struct page *page,
+static void __page_set_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address)
 {
-	if (atomic_inc_and_test(&page->_mapcount)) {
 	struct anon_vma *anon_vma = vma->anon_vma;
 
 	BUG_ON(!anon_vma);
@@ -455,10 +452,40 @@ void page_add_anon_rmap(struct page *page,
 	page->index = linear_page_index(vma, address);
 
 	inc_page_state(nr_mapped);
-	}
+}
+
+/**
+ * page_add_anon_rmap - add pte mapping to an anonymous page
+ * @page:	the page to add the mapping to
+ * @vma:	the vm area in which the mapping is added
+ * @address:	the user virtual address mapped
+ *
+ * The caller needs to hold the pte lock.
+ */
+void page_add_anon_rmap(struct page *page,
+	struct vm_area_struct *vma, unsigned long address)
+{
+	if (atomic_inc_and_test(&page->_mapcount))
+		__page_set_anon_rmap(page, vma, address);
 	/* else checking page index and mapping is racy */
 }
 
+/*
+ * page_add_new_anon_rmap - add pte mapping to a new anonymous page
+ * @page:	the page to add the mapping to
+ * @vma:	the vm area in which the mapping is added
+ * @address:	the user virtual address mapped
+ *
+ * Same as page_add_anon_rmap but must only be called on *new* pages.
+ * This means the inc-and-test can be bypassed.
+ */
+void page_add_new_anon_rmap(struct page *page,
+	struct vm_area_struct *vma, unsigned long address)
+{
+	atomic_set(&page->_mapcount, 0); /* elevate count by 1 (starts at -1) */
+	__page_set_anon_rmap(page, vma, address);
+}
+
 /**
  * page_add_file_rmap - add pte mapping to a file page
  * @page: the page to add the mapping to