1 files changed, 185 insertions, 98 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 3d4df44e4221..c641edf553a9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -80,8 +80,8 @@
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
  *
- *  ->inode_lock
- *    ->sb_lock			(fs/fs-writeback.c)
+ *  inode_wb_list_lock
+ *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
  *  ->i_mmap_lock
@@ -98,24 +98,23 @@
  *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode_lock		(zap_pte_range->set_page_dirty)
+ *    inode_wb_list_lock	(page_remove_rmap->set_page_dirty)
+ *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
+ *    inode_wb_list_lock	(zap_pte_range->set_page_dirty)
+ *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- *  ->task->proc_lock
- *    ->dcache_lock		(proc_pid_lookup)
- *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
  *    ->i_mmap_lock
  */
 
 /*
- * Remove a page from the page cache and free it. Caller has to make
+ * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
  * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __remove_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
@@ -140,58 +139,42 @@ void __remove_from_page_cache(struct page *page)
 	}
 }
 
-void remove_from_page_cache(struct page *page)
+/**
+ * delete_from_page_cache - delete page from page cache
+ * @page: the page which the kernel is trying to remove from page cache
+ *
+ * This must be called only on pages that have been verified to be in the page
+ * cache and locked.  It will never put the page into the free list, the caller
+ * has a reference on the page.
+ */
+void delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
+	void (*freepage)(struct page *);
 
 	BUG_ON(!PageLocked(page));
 
+	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
-	__remove_from_page_cache(page);
+	__delete_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
+
+	if (freepage)
+		freepage(page);
+	page_cache_release(page);
 }
-EXPORT_SYMBOL(remove_from_page_cache);
+EXPORT_SYMBOL(delete_from_page_cache);
 
-static int sync_page(void *word)
+static int sleep_on_page(void *word)
 {
-	struct address_space *mapping;
-	struct page *page;
-
-	page = container_of((unsigned long *)word, struct page, flags);
-
-	/*
-	 * page_mapping() is being called without PG_locked held.
-	 * Some knowledge of the state and use of the page is used to
-	 * reduce the requirements down to a memory barrier.
-	 * The danger here is of a stale page_mapping() return value
-	 * indicating a struct address_space different from the one it's
-	 * associated with when it is associated with one.
-	 * After smp_mb(), it's either the correct page_mapping() for
-	 * the page, or an old page_mapping() and the page's own
-	 * page_mapping() has gone NULL.
-	 * The ->sync_page() address_space operation must tolerate
-	 * page_mapping() going NULL. By an amazing coincidence,
-	 * this comes about because none of the users of the page
-	 * in the ->sync_page() methods make essential use of the
-	 * page_mapping(), merely passing the page down to the backing
-	 * device's unplug functions when it's non-NULL, which in turn
-	 * ignore it for all cases but swap, where only page_private(page) is
-	 * of interest. When page_mapping() does go NULL, the entire
-	 * call stack gracefully ignores the page and returns.
-	 * -- wli
-	 */
-	smp_mb();
-	mapping = page_mapping(page);
-	if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
-		mapping->a_ops->sync_page(page);
 	io_schedule();
 	return 0;
 }
 
-static int sync_page_killable(void *word)
+static int sleep_on_page_killable(void *word)
 {
-	sync_page(word);
+	sleep_on_page(word);
 	return fatal_signal_pending(current) ? -EINTR : 0;
 }
 
@@ -296,7 +279,7 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 				continue;
 
 			wait_on_page_writeback(page);
-			if (PageError(page))
+			if (TestClearPageError(page))
 				ret = -EIO;
 		}
 		pagevec_release(&pvec);
@@ -385,6 +368,76 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 EXPORT_SYMBOL(filemap_write_and_wait_range);
 
 /**
+ * replace_page_cache_page - replace a pagecache page with a new one
+ * @old:	page to be replaced
+ * @new:	page to replace with
+ * @gfp_mask:	allocation mode
+ *
+ * This function replaces a page in the pagecache with a new one.  On
+ * success it acquires the pagecache reference for the new page and
+ * drops it for the old page.  Both the old and new pages must be
+ * locked.  This function does not add the new page to the LRU, the
+ * caller must do that.
+ *
+ * The remove + add is atomic.  The only way this function can fail is
+ * memory allocation failure.
+ */
+int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
+{
+	int error;
+	struct mem_cgroup *memcg = NULL;
+
+	VM_BUG_ON(!PageLocked(old));
+	VM_BUG_ON(!PageLocked(new));
+	VM_BUG_ON(new->mapping);
+
+	/*
+	 * This is not page migration, but prepare_migration and
+	 * end_migration does enough work for charge replacement.
+	 *
+	 * In the longer term we probably want a specialized function
+	 * for moving the charge from old to new in a more efficient
+	 * manner.
+	 */
+	error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
+	if (error)
+		return error;
+
+	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	if (!error) {
+		struct address_space *mapping = old->mapping;
+		void (*freepage)(struct page *);
+
+		pgoff_t offset = old->index;
+		freepage = mapping->a_ops->freepage;
+
+		page_cache_get(new);
+		new->mapping = mapping;
+		new->index = offset;
+
+		spin_lock_irq(&mapping->tree_lock);
+		__delete_from_page_cache(old);
+		error = radix_tree_insert(&mapping->page_tree, offset, new);
+		BUG_ON(error);
+		mapping->nrpages++;
+		__inc_zone_page_state(new, NR_FILE_PAGES);
+		if (PageSwapBacked(new))
+			__inc_zone_page_state(new, NR_SHMEM);
+		spin_unlock_irq(&mapping->tree_lock);
+		radix_tree_preload_end();
+		if (freepage)
+			freepage(old);
+		page_cache_release(old);
+		mem_cgroup_end_migration(memcg, old, new, true);
+	} else {
+		mem_cgroup_end_migration(memcg, old, new, false);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(replace_page_cache_page);
+
+/**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:	page to add
  * @mapping:	the page's address_space
@@ -477,12 +530,6 @@ struct page *__page_cache_alloc(gfp_t gfp)
 EXPORT_SYMBOL(__page_cache_alloc);
 #endif
 
-static int __sleep_on_page_lock(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -510,7 +557,7 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
 
 	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
+		__wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
@@ -574,17 +621,12 @@ EXPORT_SYMBOL(end_page_writeback);
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
- *
- * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
- * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
- * chances are that on the second loop, the block layer's plug list is empty,
- * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
  */
 void __lock_page(struct page *page)
 {
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+	__wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
@@ -594,22 +636,23 @@ int __lock_page_killable(struct page *page)
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
 	return __wait_on_bit_lock(page_waitqueue(page), &wait,
-					sync_page_killable, TASK_KILLABLE);
+					sleep_on_page_killable, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
-/**
- * __lock_page_nosync - get a lock on the page, without calling sync_page()
- * @page: the page to lock
- *
- * Variant of lock_page that does not require the caller to hold a reference
- * on the page's mapping.
- */
-void __lock_page_nosync(struct page *page)
+int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+			 unsigned int flags)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
-	__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
-							TASK_UNINTERRUPTIBLE);
+	if (!(flags & FAULT_FLAG_ALLOW_RETRY)) {
+		__lock_page(page);
+		return 1;
+	} else {
+		if (!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
+			up_read(&mm->mmap_sem);
+			wait_on_page_locked(page);
+		}
+		return 0;
+	}
 }
 
 /**
@@ -631,7 +674,9 @@ repeat:
 	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
 	if (pagep) {
 		page = radix_tree_deref_slot(pagep);
-		if (unlikely(!page || page == RADIX_TREE_RETRY))
+		if (unlikely(!page))
+			goto out;
+		if (radix_tree_deref_retry(page))
 			goto repeat;
 
 		if (!page_cache_get_speculative(page))
@@ -647,6 +692,7 @@ repeat:
 			goto repeat;
 		}
 	}
+out:
 	rcu_read_unlock();
 
 	return page;
@@ -764,12 +810,15 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
+
 		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
+		 * This can only trigger when the entry at index 0 moves out
+		 * of or back to the root: none yet gotten, safe to restart.
 		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page)) {
+			WARN_ON(start | i);
 			goto restart;
+		}
 
 		if (!page_cache_get_speculative(page))
 			goto repeat;
@@ -783,6 +832,13 @@ repeat:
 		pages[ret] = page;
 		ret++;
 	}
+
+	/*
+	 * If all entries were removed before we could secure them,
+	 * try again, because callers stop trying once 0 is returned.
+	 */
+	if (unlikely(!ret && nr_found))
+		goto restart;
 	rcu_read_unlock();
 	return ret;
 }
@@ -817,16 +873,14 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
+
 		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
+		 * This can only trigger when the entry at index 0 moves out
+		 * of or back to the root: none yet gotten, safe to restart.
 		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
-		if (page->mapping == NULL || page->index != index)
-			break;
-
 		if (!page_cache_get_speculative(page))
 			goto repeat;
 
@@ -836,6 +890,16 @@ repeat:
 			goto repeat;
 		}
 
+		/*
+		 * must check mapping and index after taking the ref.
+		 * otherwise we can get both false positives and false
+		 * negatives, which is just confusing to the caller.
+		 */
+		if (page->mapping == NULL || page->index != index) {
+			page_cache_release(page);
+			break;
+		}
+
 		pages[ret] = page;
 		ret++;
 		index++;
@@ -874,11 +938,12 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
+
 		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
+		 * This can only trigger when the entry at index 0 moves out
+		 * of or back to the root: none yet gotten, safe to restart.
 		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
 		if (!page_cache_get_speculative(page))
@@ -893,6 +958,13 @@ repeat:
 		pages[ret] = page;
 		ret++;
 	}
+
+	/*
+	 * If all entries were removed before we could secure them,
+	 * try again, because callers stop trying once 0 is returned.
+	 */
+	if (unlikely(!ret && nr_found))
+		goto restart;
 	rcu_read_unlock();
 
 	if (ret)
@@ -1016,6 +1088,9 @@ find_page:
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;
+			/* Did it get truncated before we got the lock? */
+			if (!page->mapping)
+				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
 								desc, offset))
 				goto page_not_up_to_date_locked;
@@ -1279,12 +1354,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
+	struct blk_plug plug;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
 
+	blk_start_plug(&plug);
+
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
 		loff_t size;
@@ -1357,6 +1435,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			break;
 	}
 out:
+	blk_finish_plug(&plug);
 	return retval;
 }
 EXPORT_SYMBOL(generic_file_aio_read);
@@ -1539,25 +1618,30 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * waiting for the lock.
 		 */
 		do_async_mmap_readahead(vma, ra, file, page, offset);
-		lock_page(page);
-
-		/* Did it get truncated? */
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
-			goto no_cached_page;
-		}
 	} else {
 		/* No page in the page cache at all */
 		do_sync_mmap_readahead(vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 retry_find:
-		page = find_lock_page(mapping, offset);
+		page = find_get_page(mapping, offset);
 		if (!page)
 			goto no_cached_page;
 	}
 
+	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+		page_cache_release(page);
+		return ret | VM_FAULT_RETRY;
+	}
+
+	/* Did it get truncated? */
+	if (unlikely(page->mapping != mapping)) {
+		unlock_page(page);
+		put_page(page);
+		goto retry_find;
+	}
+	VM_BUG_ON(page->index != offset);
+
 	/*
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
@@ -2177,12 +2261,12 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 
 	if (written > 0) {
-		loff_t end = pos + written;
-		if (end > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
-			i_size_write(inode,  end);
+		pos += written;
+		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
+			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
-		*ppos = end;
+		*ppos = pos;
 	}
 out:
 	return written;
@@ -2203,7 +2287,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		gfp_notmask = __GFP_FS;
 repeat:
 	page = find_lock_page(mapping, index);
-	if (likely(page))
+	if (page)
 		return page;
 
 	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
@@ -2463,11 +2547,13 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct blk_plug plug;
 	ssize_t ret;
 
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
+	blk_start_plug(&plug);
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
@@ -2478,6 +2564,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
+	blk_finish_plug(&plug);
 	return ret;
 }
 EXPORT_SYMBOL(generic_file_aio_write);