---

yaml
---
r: 98388
b: refs/heads/master
c: 8dca7ff
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 3e14b50dd4a3178f4f635267a2706b5d4f8c61ee
+refs/heads/master: 8dca7ffe2cdbcf8a2f188c8230044c3225b70418

trunk/drivers/char/tty_ioctl.c

@@ -981,16 +981,9 @@ EXPORT_SYMBOL_GPL(tty_perform_flush);
 int n_tty_ioctl(struct tty_struct *tty, struct file *file,
 		       unsigned int cmd, unsigned long arg)
 {
-	struct tty_struct *real_tty;
 	unsigned long flags;
 	int retval;
 
-	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
-	    tty->driver->subtype == PTY_TYPE_MASTER)
-		real_tty = tty->link;
-	else
-		real_tty = tty;
-
 	switch (cmd) {
 	case TCXONC:
 		retval = tty_check_change(tty);

trunk/fs/select.c

@@ -249,14 +249,14 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 						retval++;
 					}
 				}
-				cond_resched();
 			}
 			if (res_in)
 				*rinp = res_in;
 			if (res_out)
 				*routp = res_out;
 			if (res_ex)
 				*rexp = res_ex;
+			cond_resched();
 		}
 		wait = NULL;
 		if (retval || !*timeout || signal_pending(current))

trunk/include/linux/tty_driver.h

@@ -27,8 +27,7 @@
  * 	This routine is called by the kernel to write a series of
  * 	characters to the tty device.  The characters may come from
  * 	user space or kernel space.  This routine will return the
- *	number of characters actually accepted for writing.  This
- *	routine is mandatory.
+ *	number of characters actually accepted for writing.
  *
  *	Optional: Required for writable devices.
  *
@@ -134,7 +133,7 @@
  * 	This routine notifies the tty driver that it should hangup the
  * 	tty device.
  *
- *	Required:
+ *	Optional:
  *
  * void (*break_ctl)(struct tty_stuct *tty, int state);
  *

trunk/mm/memory.c

@@ -1045,6 +1045,26 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	return page;
 }
 
+/* Can we do the FOLL_ANON optimization? */
+static inline int use_zero_page(struct vm_area_struct *vma)
+{
+	/*
+	 * We don't want to optimize FOLL_ANON for make_pages_present()
+	 * when it tries to page in a VM_LOCKED region. As to VM_SHARED,
+	 * we want to get the page from the page tables to make sure
+	 * that we serialize and update with any other user of that
+	 * mapping.
+	 */
+	if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
+		return 0;
+	/*
+	 * And if we have a fault or a nopfn routine, it's not an
+	 * anonymous region.
+	 */
+	return !vma->vm_ops ||
+		(!vma->vm_ops->fault && !vma->vm_ops->nopfn);
+}
+
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, int len, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
@@ -1119,8 +1139,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		foll_flags = FOLL_TOUCH;
 		if (pages)
 			foll_flags |= FOLL_GET;
-		if (!write && !(vma->vm_flags & VM_LOCKED) &&
-		    (!vma->vm_ops || !vma->vm_ops->fault))
+		if (!write && use_zero_page(vma))
 			foll_flags |= FOLL_ANON;
 
 		do {
@@ -1766,7 +1785,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (likely(pte_same(*page_table, orig_pte))) {
 		if (old_page) {
-			page_remove_rmap(old_page, vma);
 			if (!PageAnon(old_page)) {
 				dec_mm_counter(mm, file_rss);
 				inc_mm_counter(mm, anon_rss);
@@ -1788,6 +1806,32 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		lru_cache_add_active(new_page);
 		page_add_new_anon_rmap(new_page, vma, address);
 
+		if (old_page) {
+			/*
+			 * Only after switching the pte to the new page may
+			 * we remove the mapcount here. Otherwise another
+			 * process may come and find the rmap count decremented
+			 * before the pte is switched to the new page, and
+			 * "reuse" the old page writing into it while our pte
+			 * here still points into it and can be read by other
+			 * threads.
+			 *
+			 * The critical issue is to order this
+			 * page_remove_rmap with the ptp_clear_flush above.
+			 * Those stores are ordered by (if nothing else,)
+			 * the barrier present in the atomic_add_negative
+			 * in page_remove_rmap.
+			 *
+			 * Then the TLB flush in ptep_clear_flush ensures that
+			 * no process can access the old page before the
+			 * decremented mapcount is visible. And the old page
+			 * cannot be reused until after the decremented
+			 * mapcount is visible. So transitively, TLBs to
+			 * old page will be flushed before it can be reused.
+			 */
+			page_remove_rmap(old_page, vma);
+		}
+
 		/* Free the old page.. */
 		new_page = old_page;
 		ret |= VM_FAULT_WRITE;