kobject: don't block for each kobject_uevent

Currently kobject_uevent has somewhat unpredictable semantics.  The
point is, since it may call a usermode helper and wait for it to execute
(UMH_WAIT_EXEC), it is impossible to say for sure what lock dependencies
it will introduce for the caller - strictly speaking it depends on what
fs the binary is located on and the set of locks fork may take.  There
are quite a few kobject_uevent's users that do not take this into
account and call it with various mutexes taken, e.g.  rtnl_mutex,
net_mutex, which might potentially lead to a deadlock.

Since there is actually no reason to wait for the usermode helper to
execute there, let's make kobject_uevent start the helper asynchronously
with the aid of the UMH_NO_WAIT flag.

Personally, I'm interested in this, because I really want kobject_uevent
to be called under the slab_mutex in the slub implementation as it used
to be some time ago, because it greatly simplifies synchronization and
automatically fixes a kmemcg-related race.  However, there was a
deadlock detected on an attempt to call kobject_uevent under the
slab_mutex (see https://lkml.org/lkml/2012/1/14/45), which was reported
to be fixed by releasing the slab_mutex for kobject_uevent.

Unfortunately, there was no information about who exactly blocked on the
slab_mutex causing the usermode helper to stall, neither have I managed
to find this out or reproduce the issue.

BTW, this is not the first attempt to make kobject_uevent use
UMH_NO_WAIT.  Previous one was made by commit f520360d93 ("kobject:
don't block for each kobject_uevent"), but it was wrong (it passed
arguments allocated on stack to async thread) so it was reverted in
05f54c13cd ("Revert "kobject: don't block for each kobject_uevent".").
It targeted on speeding up the boot process though.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg KH <greg@kroah.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/kobject.h

@@ -119,6 +119,7 @@ struct kobj_type {
 };
 
 struct kobj_uevent_env {
+	char *argv[3];
 	char *envp[UEVENT_NUM_ENVP];
 	int envp_idx;
 	char buf[UEVENT_BUFFER_SIZE];

lib/kobject_uevent.c

@@ -124,6 +124,30 @@ static int kobj_usermode_filter(struct kobject *kobj)
 	return 0;
 }
 
+static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem)
+{
+	int len;
+
+	len = strlcpy(&env->buf[env->buflen], subsystem,
+		      sizeof(env->buf) - env->buflen);
+	if (len >= (sizeof(env->buf) - env->buflen)) {
+		WARN(1, KERN_ERR "init_uevent_argv: buffer size too small\n");
+		return -ENOMEM;
+	}
+
+	env->argv[0] = uevent_helper;
+	env->argv[1] = &env->buf[env->buflen];
+	env->argv[2] = NULL;
+
+	env->buflen += len + 1;
+	return 0;
+}
+
+static void cleanup_uevent_env(struct subprocess_info *info)
+{
+	kfree(info->data);
+}
+
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -301,11 +325,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 
 	/* call uevent_helper, usually only enabled during early boot */
 	if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
-		char *argv [3];
+		struct subprocess_info *info;
 
-		argv [0] = uevent_helper;
-		argv [1] = (char *)subsystem;
-		argv [2] = NULL;
 		retval = add_uevent_var(env, "HOME=/");
 		if (retval)
 			goto exit;
@@ -313,9 +334,18 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 					"PATH=/sbin:/bin:/usr/sbin:/usr/bin");
 		if (retval)
 			goto exit;
+		retval = init_uevent_argv(env, subsystem);
+		if (retval)
+			goto exit;
 
-		retval = call_usermodehelper(argv[0], argv,
-					     env->envp, UMH_WAIT_EXEC);
+		retval = -ENOMEM;
+		info = call_usermodehelper_setup(env->argv[0], env->argv,
+						 env->envp, GFP_KERNEL,
+						 NULL, cleanup_uevent_env, env);
+		if (info) {
+			retval = call_usermodehelper_exec(info, UMH_NO_WAIT);
+			env = NULL;	/* freed by cleanup_uevent_env */
+		}
 	}
 
 exit: