1 files changed, 122 insertions, 23 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index d1458ecf2f51..0fad08331cf4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -76,8 +76,9 @@
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->i_pages lock
  *
- *  ->i_mutex
- *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
+ *  ->i_rwsem
+ *    ->invalidate_lock		(acquired by fs in truncate path)
+ *      ->i_mmap_rwsem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_lock
  *    ->i_mmap_rwsem
@@ -85,9 +86,10 @@
  *        ->i_pages lock	(arch-dependent flush_dcache_mmap_lock)
  *
  *  ->mmap_lock
- *    ->lock_page		(access_process_vm)
+ *    ->invalidate_lock		(filemap_fault)
+ *      ->lock_page		(filemap_fault, access_process_vm)
  *
- *  ->i_mutex			(generic_perform_write)
+ *  ->i_rwsem			(generic_perform_write)
  *    ->mmap_lock		(fault_in_pages_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
@@ -1008,6 +1010,44 @@ EXPORT_SYMBOL(__page_cache_alloc);
 #endif
 
 /*
+ * filemap_invalidate_lock_two - lock invalidate_lock for two mappings
+ *
+ * Lock exclusively invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to lock
+ * @mapping2: the second mapping to lock
+ */
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+				 struct address_space *mapping2)
+{
+	if (mapping1 > mapping2)
+		swap(mapping1, mapping2);
+	if (mapping1)
+		down_write(&mapping1->invalidate_lock);
+	if (mapping2 && mapping1 != mapping2)
+		down_write_nested(&mapping2->invalidate_lock, 1);
+}
+EXPORT_SYMBOL(filemap_invalidate_lock_two);
+
+/*
+ * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings
+ *
+ * Unlock exclusive invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to unlock
+ * @mapping2: the second mapping to unlock
+ */
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+				   struct address_space *mapping2)
+{
+	if (mapping1)
+		up_write(&mapping1->invalidate_lock);
+	if (mapping2 && mapping1 != mapping2)
+		up_write(&mapping2->invalidate_lock);
+}
+EXPORT_SYMBOL(filemap_invalidate_unlock_two);
+
+/*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
  * waitqueues where the bucket discipline is to maintain all
@@ -2368,20 +2408,30 @@ static int filemap_update_page(struct kiocb *iocb,
 {
 	int error;
 
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!filemap_invalidate_trylock_shared(mapping))
+			return -EAGAIN;
+	} else {
+		filemap_invalidate_lock_shared(mapping);
+	}
+
 	if (!trylock_page(page)) {
+		error = -EAGAIN;
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
-			return -EAGAIN;
+			goto unlock_mapping;
 		if (!(iocb->ki_flags & IOCB_WAITQ)) {
+			filemap_invalidate_unlock_shared(mapping);
 			put_and_wait_on_page_locked(page, TASK_KILLABLE);
 			return AOP_TRUNCATED_PAGE;
 		}
 		error = __lock_page_async(page, iocb->ki_waitq);
 		if (error)
-			return error;
+			goto unlock_mapping;
 	}
 
+	error = AOP_TRUNCATED_PAGE;
 	if (!page->mapping)
-		goto truncated;
+		goto unlock;
 
 	error = 0;
 	if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
@@ -2392,15 +2442,13 @@ static int filemap_update_page(struct kiocb *iocb,
 		goto unlock;
 
 	error = filemap_read_page(iocb->ki_filp, mapping, page);
-	if (error == AOP_TRUNCATED_PAGE)
-		put_page(page);
-	return error;
-truncated:
-	unlock_page(page);
-	put_page(page);
-	return AOP_TRUNCATED_PAGE;
+	goto unlock_mapping;
 unlock:
 	unlock_page(page);
+unlock_mapping:
+	filemap_invalidate_unlock_shared(mapping);
+	if (error == AOP_TRUNCATED_PAGE)
+		put_page(page);
 	return error;
 }
 
@@ -2415,6 +2463,19 @@ static int filemap_create_page(struct file *file,
 	if (!page)
 		return -ENOMEM;
 
+	/*
+	 * Protect against truncate / hole punch. Grabbing invalidate_lock here
+	 * assures we cannot instantiate and bring uptodate new pagecache pages
+	 * after evicting page cache during truncate and before actually
+	 * freeing blocks.  Note that we could release invalidate_lock after
+	 * inserting the page into page cache as the locked page would then be
+	 * enough to synchronize with hole punching. But there are code paths
+	 * such as filemap_update_page() filling in partially uptodate pages or
+	 * ->readpages() that need to hold invalidate_lock while mapping blocks
+	 * for IO so let's hold the lock here as well to keep locking rules
+	 * simple.
+	 */
+	filemap_invalidate_lock_shared(mapping);
 	error = add_to_page_cache_lru(page, mapping, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2426,9 +2487,11 @@ static int filemap_create_page(struct file *file,
 	if (error)
 		goto error;
 
+	filemap_invalidate_unlock_shared(mapping);
 	pagevec_add(pvec, page);
 	return 0;
 error:
+	filemap_invalidate_unlock_shared(mapping);
 	put_page(page);
 	return error;
 }
@@ -2967,6 +3030,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	pgoff_t max_off;
 	struct page *page;
 	vm_fault_t ret = 0;
+	bool mapping_locked = false;
 
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(offset >= max_off))
@@ -2976,25 +3040,39 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
-	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+	if (likely(page)) {
 		/*
-		 * We found the page, so try async readahead before
-		 * waiting for the lock.
+		 * We found the page, so try async readahead before waiting for
+		 * the lock.
 		 */
-		fpin = do_async_mmap_readahead(vmf, page);
-	} else if (!page) {
+		if (!(vmf->flags & FAULT_FLAG_TRIED))
+			fpin = do_async_mmap_readahead(vmf, page);
+		if (unlikely(!PageUptodate(page))) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
+	} else {
 		/* No page in the page cache at all */
 		count_vm_event(PGMAJFAULT);
 		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 		fpin = do_sync_mmap_readahead(vmf);
 retry_find:
+		/*
+		 * See comment in filemap_create_page() why we need
+		 * invalidate_lock
+		 */
+		if (!mapping_locked) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
 		page = pagecache_get_page(mapping, offset,
 					  FGP_CREAT|FGP_FOR_MMAP,
 					  vmf->gfp_mask);
 		if (!page) {
 			if (fpin)
 				goto out_retry;
+			filemap_invalidate_unlock_shared(mapping);
 			return VM_FAULT_OOM;
 		}
 	}
@@ -3014,8 +3092,20 @@ retry_find:
 	 * 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.
 	 */
-	if (unlikely(!PageUptodate(page)))
+	if (unlikely(!PageUptodate(page))) {
+		/*
+		 * The page was in cache and uptodate and now it is not.
+		 * Strange but possible since we didn't hold the page lock all
+		 * the time. Let's drop everything get the invalidate lock and
+		 * try again.
+		 */
+		if (!mapping_locked) {
+			unlock_page(page);
+			put_page(page);
+			goto retry_find;
+		}
 		goto page_not_uptodate;
+	}
 
 	/*
 	 * We've made it this far and we had to drop our mmap_lock, now is the
@@ -3026,6 +3116,8 @@ retry_find:
 		unlock_page(page);
 		goto out_retry;
 	}
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 
 	/*
 	 * Found the page and have a reference on it.
@@ -3056,6 +3148,7 @@ page_not_uptodate:
 
 	if (!error || error == AOP_TRUNCATED_PAGE)
 		goto retry_find;
+	filemap_invalidate_unlock_shared(mapping);
 
 	return VM_FAULT_SIGBUS;
 
@@ -3067,6 +3160,8 @@ out_retry:
 	 */
 	if (page)
 		put_page(page);
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 	if (fpin)
 		fput(fpin);
 	return ret | VM_FAULT_RETRY;
@@ -3437,6 +3532,8 @@ out:
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page(struct address_space *mapping,
@@ -3460,6 +3557,8 @@ EXPORT_SYMBOL(read_cache_page);
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page_gfp(struct address_space *mapping,
@@ -3704,12 +3803,12 @@ EXPORT_SYMBOL(generic_perform_write);
  * modification times and calls proper subroutines depending on whether we
  * do direct IO or a standard buffered write.
  *
- * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * It expects i_rwsem to be grabbed unless we work on a block device or similar
  * object which does not need locking at all.
  *
  * This function does *not* take care of syncing data in case of O_SYNC write.
  * A caller has to handle it. This is mainly due to the fact that we want to
- * avoid syncing under i_mutex.
+ * avoid syncing under i_rwsem.
  *
  * Return:
  * * number of bytes written, even for truncated writes
@@ -3797,7 +3896,7 @@ EXPORT_SYMBOL(__generic_file_write_iter);
  *
  * This is a wrapper around __generic_file_write_iter() to be used by most
  * filesystems. It takes care of syncing the file in case of O_SYNC file
- * and acquires i_mutex as needed.
+ * and acquires i_rwsem as needed.
  * Return:
  * * negative error code if no data has been written at all of
  *   vfs_fsync_range() failed for a synchronous write