Virtualization - May 2023 - [PATCH 0/3] vhost: Fix freezer/ps regressions

The following patches made over Linus's tree fix the 2 bugs:

1. vhost worker task shows up as a process forked from the parent
that did VHOST_SET_OWNER ioctl instead of a process under root/kthreadd.
This was causing breaking scripts.
2. vhost_tasks didn't disable or add support for freeze requests.

The following patches fix these issues by making the vhost_task task
a thread under the process that did the VHOST_SET_OWNER and uses
get_signal() to handle freeze and SIGSTOP/KILL signals which is required
when using CLONE_THREAD (really CLONE_THREAD requires CLONE_SIGHAND
which requires SIGKILL/STOP to be supported).

When get_pending detects the task has been marked to be killed we try to
clean up the SIGKLL by doing a sigdelset and recalc_sigpending, but we
still leave it in shared_pending. If the signal is being short circuit
delivered there is no need to put in shared_pending so this adds a check
in complete_signal.

This patch was modified from Eric Biederman <ebiederm at xmission.com>
original patch.

Signed-off-by: Mike Christie <michael.christie at oracle.com>
---
 kernel/signal.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/signal.c b/kernel/signal.c
index 8f6330f0e9ca..3dc99b9aec7f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1052,6 +1052,14 @@ static void complete_signal(int sig, struct task_struct
*p, enum pid_type type)
 			signal->flags = SIGNAL_GROUP_EXIT;
 			signal->group_exit_code = sig;
 			signal->group_stop_count = 0;
+
+			/*
+			 * The signal is being short circuit delivered so
+			 * don't set pending.
+			 */
+			if (type != PIDTYPE_PID)
+				sigdelset(&signal->shared_pending.signal, sig);
+
 			t = p;
 			do {
 				task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
-- 
2.25.1

vhost_tasks also need to perform cleanup before exiting so this changes
the check in get_signal to be more generic so both io thread and vhost
tasks can do their cleanup.

Signed-off-by: Mike Christie <michael.christie at oracle.com>
---
 kernel/signal.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index 3dc99b9aec7f..8050fe23c732 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2869,11 +2869,11 @@ bool get_signal(struct ksignal *ksig)
 		}
 
 		/*
-		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * PF_USER_WORKER threads will catch and exit on fatal signals
 		 * themselves. They have cleanup that must be performed, so
 		 * we cannot call do_exit() on their behalf.
 		 */
-		if (current->flags & PF_IO_WORKER)
+		if (current->flags & PF_USER_WORKER)
 			goto out;
 
 		/*
-- 
2.25.1

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 suppported.

This a modified version of patch originally written by Linus which
handles his review comment to himself to rename ignore_signals to
block_signals to better represent what it now does. And it includes a
change to vhost_worker() to support SIGSTOP/KILL and freeze, and it
drops the wait use per Oleg's review comment that it's no longer needed
when using CLONE_THREAD.

Fixes: 6e890c5d5021 ("vhost: use vhost_tasks for worker threads")
Signed-off-by: Mike Christie <michael.christie at oracle.com>
---
 drivers/vhost/vhost.c      | 17 ++++++++++++++++-
 include/linux/sched/task.h |  2 +-
 kernel/fork.c              | 12 +++---------
 kernel/signal.c            |  1 +
 kernel/vhost_task.c        | 16 ++++------------
 5 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a92af08e7864..bf83e9340e40 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -338,6 +338,7 @@ static int vhost_worker(void *data)
 	struct vhost_worker *worker = data;
 	struct vhost_work *work, *work_next;
 	struct llist_node *node;
+	bool dead = false;
 
 	for (;;) {
 		/* mb paired w/ kthread_stop */
@@ -349,8 +350,22 @@ static int vhost_worker(void *data)
 		}
 
 		node = llist_del_all(&worker->work_list);
-		if (!node)
+		if (!node) {
 			schedule();
+			/*
+			 * When we get a SIGKILL our release function will
+			 * be called. That will stop new IOs from being queued
+			 * and check for outstanding cmd responses. It will then
+			 * call vhost_task_stop to tell us to return and exit.
+			 */
+			if (!dead && signal_pending(current)) {
+				struct ksignal ksig;
+
+				dead = get_signal(&ksig);
+				if (dead)
+					clear_thread_flag(TIF_SIGPENDING);
+			}
+		}
 
 		node = llist_reverse_order(node);
 		/* make sure flag is seen after deletion */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 537cbf9a2ade..249a5ece9def 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -29,7 +29,7 @@ struct kernel_clone_args {
 	u32 io_thread:1;
 	u32 user_worker:1;
 	u32 no_files:1;
-	u32 ignore_signals:1;
+	u32 block_signals:1;
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..9e04ab5c3946 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2338,14 +2338,10 @@ __latent_entropy struct task_struct *copy_process(
 		p->flags |= PF_KTHREAD;
 	if (args->user_worker)
 		p->flags |= PF_USER_WORKER;
-	if (args->io_thread) {
-		/*
-		 * Mark us an IO worker, and block any signal that isn't
-		 * fatal or STOP
-		 */
+	if (args->io_thread)
 		p->flags |= PF_IO_WORKER;
+	if (args->block_signals)
 		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
-	}
 
 	if (args->name)
 		strscpy_pad(p->comm, args->name, sizeof(p->comm));
@@ -2517,9 +2513,6 @@ __latent_entropy struct task_struct *copy_process(
 	if (retval)
 		goto bad_fork_cleanup_io;
 
-	if (args->ignore_signals)
-		ignore_signals(p);
-
 	stackleak_task_init(p);
 
 	if (pid != &init_struct_pid) {
@@ -2861,6 +2854,7 @@ struct task_struct *create_io_thread(int (*fn)(void *),
void *arg, int node)
 		.fn_arg		= arg,
 		.io_thread	= 1,
 		.user_worker	= 1,
+		.block_signals	= 1,
 	};
 
 	return copy_process(NULL, 0, node, &args);
diff --git a/kernel/signal.c b/kernel/signal.c
index 8050fe23c732..a0f00a078cbb 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2891,6 +2891,7 @@ bool get_signal(struct ksignal *ksig)
 
 	return ksig->sig > 0;
 }
+EXPORT_SYMBOL_GPL(get_signal);
 
 /**
  * signal_delivered - called after signal delivery to update blocked signals
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index b7cbd66f889e..7a2d7d9fe772 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -31,22 +31,13 @@ static int vhost_task_fn(void *data)
  */
 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);
 	/*
 	 * 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);
@@ -75,13 +66,14 @@ struct vhost_task *vhost_task_create(int (*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,
+		.block_signals	= 1,
 	};
 	struct vhost_task *vtsk;
 	struct task_struct *tsk;
-- 
2.25.1