From:   Mike Christie <michael.christie@oracle.com>
To:     geert@linux-m68k.org, vverma@digitalocean.com, hdanton@sina.com,
        hch@infradead.org, stefanha@redhat.com, jasowang@redhat.com,
        mst@redhat.com, sgarzare@redhat.com,
        virtualization@lists.linux-foundation.org,
        christian.brauner@ubuntu.com, axboe@kernel.dk,
        linux-kernel@vger.kernel.org
Cc:     Mike Christie <michael.christie@oracle.com>,
        Christoph Hellwig <hch@lst.de>
Subject: [PATCH V5 10/10] vhost: use kernel_worker to check RLIMITs
Date:   Sun, 21 Nov 2021 11:49:30 -0600
Message-Id: <20211121174930.6690-11-michael.christie@oracle.com>
In-Reply-To: <20211121174930.6690-1-michael.christie@oracle.com>
References: <20211121174930.6690-1-michael.christie@oracle.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?qADtCSov4K1tIGyr2/JLggQ1lL0RTUyu/tpLCgqMXakrq/TFkfMQ699982IA?=
 =?us-ascii?Q?1M6wLR58TjBgBBmAw4mPL4AT5byismY4+MZCrVKZwXHeA+V5VyJWo0Fi/MVz?=
 =?us-ascii?Q?OuXEWh30wpYJKtOT0jy4VZHYaistBGFShOpd24K4uqvdWyuowVQh/UdDSjcR?=
 =?us-ascii?Q?uTDpLK8y0N6tOTm+WgMrOsO77LaLrQs9P66ewUnJdUUHk0kQq3byCo5+phXT?=
 =?us-ascii?Q?a4MFwmTx/eplFMxTf5sPIQ7pMbHoZi+r6Bok1pYEeYH1Dzj7CWj7j36rMmag?=
 =?us-ascii?Q?gtwjUv++cTZRnBnqI1rtvZolBZ38EARoQdABzf4+bd63X6lc8H6c7XD4SE9c?=
 =?us-ascii?Q?PJuilmpH0kfxWw57VWBj0SBity3W0E0z3FBKYmrVtkRBVLFI2v57AX3z0Qq9?=
 =?us-ascii?Q?Rk3dpkTjQky+5PS50TgooFIPdhpAnnUXkgJj58l0riqJFab4wgDXVnfHfWf2?=
 =?us-ascii?Q?4FWhnoWu02MzajZzh818TYbhpUiAjqi6xhcWoPXRb6JFjBY7WdayDJkkqvja?=
 =?us-ascii?Q?Swasu5Fo/y1TMaiiRnHV4Vk4AMxwWddBZj2bTP7aI4skbejJ/EdyK+lJPuTF?=
 =?us-ascii?Q?q15Adv3ox42FkLbeuza0wdpt8ZmN9YbcLPkGC7oF4+dLtj8yaC3gj1WErAch?=
 =?us-ascii?Q?lWxrUtcO6+bGWx287SdauhRerlYXPHe4iyo1yZPGIV6Ux4VydLChMrYDkwtE?=
 =?us-ascii?Q?JYo+3aEAniZ21TmCFzN9jzt2mkrz03hKIl9ILoZs3vExBsfcPBkj3+uv6Hth?=
 =?us-ascii?Q?n9WMpdgCdClprI8EbIocNdfCE1XAJriFpl8INtZE/qaJQm2ixEkZDrOL6bFH?=
 =?us-ascii?Q?rOTqPmAACcP1BUGTPe+aE15Yj/px93/16MhnuCWs3XPx4ecgkOCdDN930fhZ?=
 =?us-ascii?Q?fcnVOeZqa8Ndp5FEQtl127faFKZbCSuH93/hOA2fOVpvby/FaEFAWmq+SVZj?=
 =?us-ascii?Q?gt8Yvmz3R/+aDhi7S5zIenHvBrnNOOf0rKv3scSQ5PdaslZZpft2mtEy97BS?=
 =?us-ascii?Q?dMfhiChNva/g+ichIalb2+INTKwh5wAbWT+PtyaOJSDVMqoRt7SeKRpNGqqE?=
 =?us-ascii?Q?iRgX47xB8AXCuVZ5vjA2f2Mc7C39OA+/45+zyHgNE7UXYJeGuly/1teuFcNn?=
 =?us-ascii?Q?9e0wwUS5Fh1RQkTH+nOKbe23NYVsfGCYb5L4MxcHxnQoQxE6fpdDBcqBNQck?=
 =?us-ascii?Q?FqkgTNL4IFOan382+jEr75o4aAmjWqdjmkZivMkKUy8hVlW+7lYFUOhl5Ntu?=
 =?us-ascii?Q?jX0FP+G9ok8XPCqgi5//jqVAaRi7wWjhGIwRPP1P/jtDX8/usEDDN6gFx0YP?=
 =?us-ascii?Q?wRKvHjXnoUWwgInoonez8NPPk0p4AC47k0ntnbLYmOOwnCW+Sg0/KVCzwYIj?=
 =?us-ascii?Q?Vx+JaMvlkJKt01wH3PDM7kMRnI/9I5mmYuOixaZz5P0/5Hj60x2/LtCuiufd?=
 =?us-ascii?Q?9O0n9VrSC6sMpG9FhrR6Ins/z0kPYPboelWRJrgCZFoI37TGKzisCc1sH1V8?=
 =?us-ascii?Q?WjuK38XoPctBANCqGGyigrkEQk1sAatjWxFxRE7UnHpilae8I8EuiDoUQ1r+?=
 =?us-ascii?Q?4e90Vh+dcOtvX/CbXz8hLH2hIN8q10A1gSER2I+9vrST0bPWhj6Oto/z3hxJ?=
 =?us-ascii?Q?tqi4A7FRUNuxUVM4gkRR0J5qaySjtPpQ+Ik7e/zeZ2MP7Ar8bPw6fFKbOLkD?=
 =?us-ascii?Q?2Flzjw=3D=3D?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 6b276576-b108-45a8-a036-08d9ad1751bd
X-MS-Exchange-CrossTenant-AuthSource: DM5PR10MB1466.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 21 Nov 2021 17:49:51.8719
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: 2pHsqdj5v4VjY/blO3u8V2/R8Vb5UTHMq1HQeJ9K2Xyjqpbx0ysTEbehYwA2E5ROKidV2qUBGGWJcS6ACfL6Hlnpso3F/yWIRS96Yhipx8M=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS7PR10MB5055
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10175 signatures=668683
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=0 mlxscore=0 spamscore=0
 mlxlogscore=999 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2110150000
 definitions=main-2111210110
X-Proofpoint-GUID: Tw-dUKMii5ZMI-xEwld6BWBTXEU-RZug
X-Proofpoint-ORIG-GUID: Tw-dUKMii5ZMI-xEwld6BWBTXEU-RZug
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

For vhost workers we use the kthread API which inherit's its values from
and checks against the kthreadd thread. This results in the wrong RLIMITs
being checked. This patch has us use the kernel_copy_process function
which will inherit its values/checks from the thread that owns the device.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

---
 drivers/vhost/vhost.c | 65 +++++++++++++++----------------------------
 drivers/vhost/vhost.h |  7 ++++-
 2 files changed, 28 insertions(+), 44 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c9a1f706989c..9aa04fcdf210 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/kthread.h>
-#include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <linux/sched/mm.h>
@@ -344,17 +343,14 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 static int vhost_worker(void *data)
 {
 	struct vhost_worker *worker = data;
-	struct vhost_dev *dev = worker->dev;
 	struct vhost_work *work, *work_next;
 	struct llist_node *node;
 
-	kthread_use_mm(dev->mm);
-
 	for (;;) {
 		/* mb paired w/ kthread_stop */
 		set_current_state(TASK_INTERRUPTIBLE);
 
-		if (kthread_should_stop()) {
+		if (test_bit(VHOST_WORKER_FLAG_STOP, &worker->flags)) {
 			__set_current_state(TASK_RUNNING);
 			break;
 		}
@@ -376,8 +372,9 @@ static int vhost_worker(void *data)
 				schedule();
 		}
 	}
-	kthread_unuse_mm(dev->mm);
-	return 0;
+
+	complete(worker->exit_done);
+	do_exit(0);
 }
 
 static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
@@ -517,31 +514,6 @@ long vhost_dev_check_owner(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_check_owner);
 
-struct vhost_attach_cgroups_struct {
-	struct vhost_work work;
-	struct task_struct *owner;
-	int ret;
-};
-
-static void vhost_attach_cgroups_work(struct vhost_work *work)
-{
-	struct vhost_attach_cgroups_struct *s;
-
-	s = container_of(work, struct vhost_attach_cgroups_struct, work);
-	s->ret = cgroup_attach_task_all(s->owner, current);
-}
-
-static int vhost_attach_cgroups(struct vhost_dev *dev)
-{
-	struct vhost_attach_cgroups_struct attach;
-
-	attach.owner = current;
-	vhost_work_init(&attach.work, vhost_attach_cgroups_work);
-	vhost_work_queue(dev, &attach.work);
-	vhost_work_dev_flush(dev);
-	return attach.ret;
-}
-
 /* Caller should have device mutex */
 bool vhost_dev_has_owner(struct vhost_dev *dev)
 {
@@ -579,6 +551,16 @@ static void vhost_detach_mm(struct vhost_dev *dev)
 	dev->mm = NULL;
 }
 
+static void vhost_worker_stop(struct vhost_worker *worker)
+{
+	DECLARE_COMPLETION_ONSTACK(exit_done);
+
+	worker->exit_done = &exit_done;
+	set_bit(VHOST_WORKER_FLAG_STOP, &worker->flags);
+	wake_up_process(worker->task);
+	wait_for_completion(worker->exit_done);
+}
+
 static void vhost_worker_free(struct vhost_dev *dev)
 {
 	struct vhost_worker *worker = dev->worker;
@@ -588,7 +570,7 @@ static void vhost_worker_free(struct vhost_dev *dev)
 
 	dev->worker = NULL;
 	WARN_ON(!llist_empty(&worker->work_list));
-	kthread_stop(worker->task);
+	vhost_worker_stop(worker);
 	kfree(worker);
 }
 
@@ -603,27 +585,24 @@ static int vhost_worker_create(struct vhost_dev *dev)
 		return -ENOMEM;
 
 	dev->worker = worker;
-	worker->dev = dev;
 	worker->kcov_handle = kcov_common_handle();
 	init_llist_head(&worker->work_list);
 
-	task = kthread_create(vhost_worker, worker, "vhost-%d", current->pid);
+	/*
+	 * vhost used to use the kthread API which ignores all signals by
+	 * default and the drivers expect this behavior.
+	 */
+	task = kernel_worker(vhost_worker, worker, NUMA_NO_NODE, CLONE_FS,
+			     KERN_WORKER_NO_FILES | KERN_WORKER_SIG_IGN);
 	if (IS_ERR(task)) {
 		ret = PTR_ERR(task);
 		goto free_worker;
 	}
 
 	worker->task = task;
-	wake_up_process(task); /* avoid contributing to loadavg */
-
-	ret = vhost_attach_cgroups(dev);
-	if (ret)
-		goto stop_worker;
-
+	kernel_worker_start(task, "vhost-%d", current->pid);
 	return 0;
 
-stop_worker:
-	kthread_stop(worker->task);
 free_worker:
 	kfree(worker);
 	dev->worker = NULL;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 102ce25e4e13..09748694cb66 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -25,11 +25,16 @@ struct vhost_work {
 	unsigned long		flags;
 };
 
+enum {
+	VHOST_WORKER_FLAG_STOP,
+};
+
 struct vhost_worker {
 	struct task_struct	*task;
+	struct completion	*exit_done;
 	struct llist_head	work_list;
-	struct vhost_dev	*dev;
 	u64			kcov_handle;
+	unsigned long		flags;
 };
 
 /* Poll a file (eventfd or socket) */
-- 
2.25.1