X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmemory.c;h=788a628103405e955a7d28f9935be690eb6d021a;hb=5ac353f9baf7169298ebb7de86b2d697b25bca44;hp=81d7117aa58b65ec7f93cef8e212a337735ba440;hpb=f33ea7f404e592e4563b12101b7a4d17da6558d7;p=linux-2.6

diff --git a/mm/memory.c b/mm/memory.c
index 81d7117aa5..788a628103 100644
--- 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);
 
@@ -551,7 +562,8 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 				     page->index > details->last_index))
 					continue;
 			}
-			ptent = ptep_get_and_clear(tlb->mm, addr, pte);
+			ptent = ptep_get_and_clear_full(tlb->mm, addr, pte,
+							tlb->fullmm);
 			tlb_remove_tlb_entry(tlb, pte, addr);
 			if (unlikely(!page))
 				continue;
@@ -579,7 +591,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 			continue;
 		if (!pte_file(ptent))
 			free_swap_and_cache(pte_to_swp_entry(ptent));
-		pte_clear(tlb->mm, addr, pte);
+		pte_clear_full(tlb->mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap(pte - 1);
 }
@@ -949,6 +961,8 @@ 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 +975,18 @@ 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;
@@ -1940,7 +1956,7 @@ static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
 	 * Fall back to the linear mapping if the fs does not support
 	 * ->populate:
 	 */
-	if (!vma->vm_ops || !vma->vm_ops->populate || 
+	if (!vma->vm_ops->populate ||
 			(write_access && !(vma->vm_flags & VM_SHARED))) {
 		pte_clear(mm, address, pte);
 		return do_no_page(mm, vma, address, write_access, pte, pmd);