[PATCH] swap: swap extent list is ordered

[linux-2.6] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 81d7117aa58b65ec7f93cef8e212a337735ba440..a596c1172248e56b8fb220408548330ebd1de538 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -498,6 +498,17 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        unsigned long addr = vma->vm_start;
        unsigned long end = vma->vm_end;
 
+       /*
+        * Don't copy ptes where a page fault will fill them correctly.
+        * Fork becomes much lighter when there are big shared or private
+        * readonly mappings. The tradeoff is that copy_page_range is more
+        * efficient than faulting.
+        */
+       if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) {
+               if (!vma->anon_vma)
+                       return 0;
+       }
+
        if (is_vm_hugetlb_page(vma))
                return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
@@ -949,6 +960,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
                        cond_resched_lock(&mm->page_table_lock);
                        while (!(page = follow_page(mm, start, write_access))) {
+                               int ret;
+
                                /*
                                 * Shortcut for anonymous pages. We don't want
                                 * to force the creation of pages tables for
@@ -961,16 +974,18 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                        break;
                                }
                                spin_unlock(&mm->page_table_lock);
-                               switch (__handle_mm_fault(mm, vma, start,
-                                                       write_access)) {
-                               case VM_FAULT_WRITE:
-                                       /*
-                                        * do_wp_page has broken COW when
-                                        * necessary, even if maybe_mkwrite
-                                        * decided not to set pte_write
-                                        */
+                               ret = __handle_mm_fault(mm, vma, start, write_access);
+
+                               /*
+                                * The VM_FAULT_WRITE bit tells us that do_wp_page has
+                                * broken COW when necessary, even if maybe_mkwrite
+                                * decided not to set pte_write. We can thus safely do
+                                * subsequent page lookups as if they were reads.
+                                */
+                               if (ret & VM_FAULT_WRITE)
                                        write_access = 0;
-                                       /* FALLTHRU */
+                               
+                               switch (ret & ~VM_FAULT_WRITE) {
                                case VM_FAULT_MINOR:
                                        tsk->min_flt++;
                                        break;