block: Fix io_context leak after failure of clone with CLONE_IO

With CLONE_IO, parent's io_context->nr_tasks is incremented, but never
decremented whenever copy_process() fails afterwards, which prevents
exit_io_context() from calling IO schedulers exit functions.

Give a task_struct to exit_io_context(), and call exit_io_context() instead of
put_io_context() in copy_process() cleanup path.

Signed-off-by: Louis Rilling <louis.rilling@kerlabs.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

block/blk-ioc.c

@@ -66,14 +66,14 @@ static void cfq_exit(struct io_context *ioc)
 }
 
 /* Called by the exitting task */
-void exit_io_context(void)
+void exit_io_context(struct task_struct *task)
 {
 	struct io_context *ioc;
 
-	task_lock(current);
-	ioc = current->io_context;
-	current->io_context = NULL;
-	task_unlock(current);
+	task_lock(task);
+	ioc = task->io_context;
+	task->io_context = NULL;
+	task_unlock(task);
 
 	if (atomic_dec_and_test(&ioc->nr_tasks)) {
 		if (ioc->aic && ioc->aic->exit)

include/linux/iocontext.h

@@ -98,14 +98,15 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
 	return NULL;
 }
 
+struct task_struct;
 #ifdef CONFIG_BLOCK
 int put_io_context(struct io_context *ioc);
-void exit_io_context(void);
+void exit_io_context(struct task_struct *task);
 struct io_context *get_io_context(gfp_t gfp_flags, int node);
 struct io_context *alloc_io_context(gfp_t gfp_flags, int node);
 void copy_io_context(struct io_context **pdst, struct io_context **psrc);
 #else
-static inline void exit_io_context(void)
+static inline void exit_io_context(struct task_struct *task)
 {
 }
 

kernel/exit.c

@@ -1004,7 +1004,7 @@ NORET_TYPE void do_exit(long code)
 	tsk->flags |= PF_EXITPIDONE;
 
 	if (tsk->io_context)
-		exit_io_context();
+		exit_io_context(tsk);
 
 	if (tsk->splice_pipe)
 		__free_pipe_info(tsk->splice_pipe);

kernel/fork.c

@@ -1310,7 +1310,8 @@ bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_io:
-	put_io_context(p->io_context);
+	if (p->io_context)
+		exit_io_context(p);
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm: