fork, vhost: Use CLONE_THREAD to fix freezer/ps regression

When switching from kthreads to vhost_tasks two bugs were added:
1. The vhost worker tasks's now show up as processes so scripts doing
ps or ps a would not incorrectly detect the vhost task as another
process.  2. kthreads disabled freeze by setting PF_NOFREEZE, but
vhost tasks's didn't disable or add support for them.

To fix both bugs, this switches the vhost task to be thread in the
process that does the VHOST_SET_OWNER ioctl, and has vhost_worker call
get_signal to support SIGKILL/SIGSTOP and freeze signals. Note that
SIGKILL/STOP support is required because CLONE_THREAD requires
CLONE_SIGHAND which requires those 2 signals to be supported.

This is a modified version of the patch written by Mike Christie
<michael.christie@oracle.com> which was a modified version of patch
originally written by Linus.

Much of what depended upon PF_IO_WORKER now depends on PF_USER_WORKER.
Including ignoring signals, setting up the register state, and having
get_signal return instead of calling do_group_exit.

Tidied up the vhost_task abstraction so that the definition of
vhost_task only needs to be visible inside of vhost_task.c.  Making
it easier to review the code and tell what needs to be done where.
As part of this the main loop has been moved from vhost_worker into
vhost_task_fn.  vhost_worker now returns true if work was done.

The main loop has been updated to call get_signal which handles
SIGSTOP, freezing, and collects the message that tells the thread to
exit as part of process exit.  This collection clears
__fatal_signal_pending.  This collection is not guaranteed to
clear signal_pending() so clear that explicitly so the schedule()
sleeps.

For now the vhost thread continues to exist and run work until the
last file descriptor is closed and the release function is called as
part of freeing struct file.  To avoid hangs in the coredump
rendezvous and when killing threads in a multi-threaded exec.  The
coredump code and de_thread have been modified to ignore vhost threads.

Remvoing the special case for exec appears to require teaching
vhost_dev_flush how to directly complete transactions in case
the vhost thread is no longer running.

Removing the special case for coredump rendezvous requires either the
above fix needed for exec or moving the coredump rendezvous into
get_signal.

Fixes: 6e890c5d5021 ("vhost: use vhost_tasks for worker threads")
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Co-developed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 61 insertions, 31 deletions

diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index b7cbd66f889e..f80d5c51ae67 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -12,58 +12,88 @@ enum vhost_task_flags {
 	VHOST_TASK_FLAGS_STOP,
 };
 
+struct vhost_task {
+	bool (*fn)(void *data);
+	void *data;
+	struct completion exited;
+	unsigned long flags;
+	struct task_struct *task;
+};
+
 static int vhost_task_fn(void *data)
 {
 	struct vhost_task *vtsk = data;
-	int ret;
+	bool dead = false;
+
+	for (;;) {
+		bool did_work;
+
+		/* mb paired w/ vhost_task_stop */
+		if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags))
+			break;
+
+		if (!dead && signal_pending(current)) {
+			struct ksignal ksig;
+			/*
+			 * Calling get_signal will block in SIGSTOP,
+			 * or clear fatal_signal_pending, but remember
+			 * what was set.
+			 *
+			 * This thread won't actually exit until all
+			 * of the file descriptors are closed, and
+			 * the release function is called.
+			 */
+			dead = get_signal(&ksig);
+			if (dead)
+				clear_thread_flag(TIF_SIGPENDING);
+		}
+
+		did_work = vtsk->fn(vtsk->data);
+		if (!did_work) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+		}
+	}
 
-	ret = vtsk->fn(vtsk->data);
 	complete(&vtsk->exited);
-	do_exit(ret);
+	do_exit(0);
+}
+
+/**
+ * vhost_task_wake - wakeup the vhost_task
+ * @vtsk: vhost_task to wake
+ *
+ * wake up the vhost_task worker thread
+ */
+void vhost_task_wake(struct vhost_task *vtsk)
+{
+	wake_up_process(vtsk->task);
 }
+EXPORT_SYMBOL_GPL(vhost_task_wake);
 
 /**
  * vhost_task_stop - stop a vhost_task
  * @vtsk: vhost_task to stop
  *
- * Callers must call vhost_task_should_stop and return from their worker
- * function when it returns true;
+ * vhost_task_fn ensures the worker thread exits after
+ * VHOST_TASK_FLAGS_SOP becomes true.
  */
 void vhost_task_stop(struct vhost_task *vtsk)
 {
-	pid_t pid = vtsk->task->pid;
-
 	set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
-	wake_up_process(vtsk->task);
+	vhost_task_wake(vtsk);
 	/*
 	 * Make sure vhost_task_fn is no longer accessing the vhost_task before
-	 * freeing it below. If userspace crashed or exited without closing,
-	 * then the vhost_task->task could already be marked dead so
-	 * kernel_wait will return early.
+	 * freeing it below.
 	 */
 	wait_for_completion(&vtsk->exited);
-	/*
-	 * If we are just closing/removing a device and the parent process is
-	 * not exiting then reap the task.
-	 */
-	kernel_wait4(pid, NULL, __WCLONE, NULL);
 	kfree(vtsk);
 }
 EXPORT_SYMBOL_GPL(vhost_task_stop);
 
 /**
- * vhost_task_should_stop - should the vhost task return from the work function
- * @vtsk: vhost_task to stop
- */
-bool vhost_task_should_stop(struct vhost_task *vtsk)
-{
-	return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
-}
-EXPORT_SYMBOL_GPL(vhost_task_should_stop);
-
-/**
- * vhost_task_create - create a copy of a process to be used by the kernel
- * @fn: thread stack
+ * vhost_task_create - create a copy of a task to be used by the kernel
+ * @fn: vhost worker function
  * @arg: data to be passed to fn
  * @name: the thread's name
  *
@@ -71,17 +101,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop);
  * failure. The returned task is inactive, and the caller must fire it up
  * through vhost_task_start().
  */
-struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg,
+struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg,
 				     const char *name)
 {
 	struct kernel_clone_args args = {
-		.flags		= CLONE_FS | CLONE_UNTRACED | CLONE_VM,
+		.flags		= CLONE_FS | CLONE_UNTRACED | CLONE_VM |
+				  CLONE_THREAD | CLONE_SIGHAND,
 		.exit_signal	= 0,
 		.fn		= vhost_task_fn,
 		.name		= name,
 		.user_worker	= 1,
 		.no_files	= 1,
-		.ignore_signals	= 1,
 	};
 	struct vhost_task *vtsk;
 	struct task_struct *tsk;