X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmemory.c;h=a596c1172248e56b8fb220408548330ebd1de538;hb=4d7670e0f649f9e6e6ea6c8bb9f52441fa00f92b;hp=2405289dfdf88d03fa0113712a37c4bf5444c640;hpb=62778ba1aa2589dc78c36a32edc6f5a6ccaf50c6;p=linux-2.6

diff --git a/mm/memory.c b/mm/memory.c
index 2405289dfd..a596c11722 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);
 
@@ -811,15 +822,18 @@ static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
 	pte = *ptep;
 	pte_unmap(ptep);
 	if (pte_present(pte)) {
-		if (write && !pte_dirty(pte))
+		if (write && !pte_write(pte))
 			goto out;
 		if (read && !pte_read(pte))
 			goto out;
 		pfn = pte_pfn(pte);
 		if (pfn_valid(pfn)) {
 			page = pfn_to_page(pfn);
-			if (accessed)
+			if (accessed) {
+				if (write && !pte_dirty(pte) &&!PageDirty(page))
+					set_page_dirty(page);
 				mark_page_accessed(page);
+			}
 			return page;
 		}
 	}
@@ -941,10 +955,13 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		}
 		spin_lock(&mm->page_table_lock);
 		do {
+			int write_access = write;
 			struct page *page;
 
 			cond_resched_lock(&mm->page_table_lock);
-			while (!(page = follow_page(mm, start, write))) {
+			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
@@ -957,7 +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)) {
+				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;
+				
+				switch (ret & ~VM_FAULT_WRITE) {
 				case VM_FAULT_MINOR:
 					tsk->min_flt++;
 					break;
@@ -1220,6 +1248,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
 	struct page *old_page, *new_page;
 	unsigned long pfn = pte_pfn(pte);
 	pte_t entry;
+	int ret;
 
 	if (unlikely(!pfn_valid(pfn))) {
 		/*
@@ -1247,7 +1276,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
 			lazy_mmu_prot_update(entry);
 			pte_unmap(page_table);
 			spin_unlock(&mm->page_table_lock);
-			return VM_FAULT_MINOR;
+			return VM_FAULT_MINOR|VM_FAULT_WRITE;
 		}
 	}
 	pte_unmap(page_table);
@@ -1274,6 +1303,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
 	/*
 	 * Re-check the pte - we dropped the lock
 	 */
+	ret = VM_FAULT_MINOR;
 	spin_lock(&mm->page_table_lock);
 	page_table = pte_offset_map(pmd, address);
 	if (likely(pte_same(*page_table, pte))) {
@@ -1290,12 +1320,13 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
 
 		/* Free the old page.. */
 		new_page = old_page;
+		ret |= VM_FAULT_WRITE;
 	}
 	pte_unmap(page_table);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 	spin_unlock(&mm->page_table_lock);
-	return VM_FAULT_MINOR;
+	return ret;
 
 no_new_page:
 	page_cache_release(old_page);
@@ -1987,7 +2018,6 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 	if (write_access) {
 		if (!pte_write(entry))
 			return do_wp_page(mm, vma, address, pte, pmd, entry);
-
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
@@ -2002,7 +2032,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 /*
  * By the time we get here, we already hold the mm semaphore
  */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
 		unsigned long address, int write_access)
 {
 	pgd_t *pgd;