Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
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>
Subject: [PATCH V3 9/9] vhost: use kernel_worker to check RLIMITs and inherit v2 cgroups
Date:   Mon,  4 Oct 2021 14:21:28 -0500
Message-Id: <20211004192128.381453-10-michael.christie@oracle.com>
In-Reply-To: <20211004192128.381453-1-michael.christie@oracle.com>
References: <20211004192128.381453-1-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?WvDzvoGjVbQsD/9JmxAJ1/wPJ68Zp0bIYKxpYNoRwH4cog/jK1xVNKKJv5uG?=
 =?us-ascii?Q?mRur110+Nm/JI48oxB3mbZIicnVsW6soCrZiW3aXhwu1gLrUktYN3CD5Ag99?=
 =?us-ascii?Q?omxLdOsRxMTrf3cBit47umHFO1kLyLspeZdrwVVxc88PnPPxXgzbqI0+LkXm?=
 =?us-ascii?Q?9griTFhI4QduUKT4ucTe7lkO/B5x6KtxkQ7lxTzw1DxM0Fc7qOc13k35DCTZ?=
 =?us-ascii?Q?2LGTLJf8DdHdji4sVE7ygTeLF6C4FcEuWiQWvYYLqvyQx2zSo4s+VV5lthmj?=
 =?us-ascii?Q?Cd6otc3yHcPRpk6vb1gIGpKy4JZlfuG4g2KN2g2jOg+13gnz3EExUYfdu+46?=
 =?us-ascii?Q?V9k/7nWMqXxfhcA0qvdQU9UPrSMiZbUpu7ALC3FDOMx+8xZmQi7J23osDsu+?=
 =?us-ascii?Q?S691r9kLAEYHsDOWNMgJDI5HOgwjeOicOzjSwxu+3Qfjb8bAc0pL03WSf/nD?=
 =?us-ascii?Q?n/Nt9+xhlLORpFnxALB9n7HhKXwqbEW1gFGTYeglkZzb4UlLa/LpKLF7gSeo?=
 =?us-ascii?Q?4h5QTHnAmVypkae22/SCseL/rvfOiLKGGY0EGSe6qYpZivjJHy1MQtuQRMt7?=
 =?us-ascii?Q?FcB+4xWv14kx+dqR9xPKzU9rrMOXS4mtl7A+wI++VBj3/gtOvOLk0FZpL8c+?=
 =?us-ascii?Q?S7kmDEeZyWjHsl+AZZaVP2hOUuFK6MWuB53dfxE3TuY3tnYOteLPIQrLWn5A?=
 =?us-ascii?Q?PeeE1Pi0VW6BK0qi6COxA9QCb34tttEPpCHlZNhrqJzzvUdJqe9FRL6OaBul?=
 =?us-ascii?Q?s8NfbYWZDbxreozWCnuP94mX5/Oz8ivJOjUkQZ1xWHjmu9f1D+FPqFmTnbXw?=
 =?us-ascii?Q?lBuBrsJnJVnbtLmKVNSmkeSx3hBdls2tKjCbjhecVmYSun1QDS8Z2xIYv602?=
 =?us-ascii?Q?EFN7u4Wowa98zvy00FSMKI5tn8cthGavrcXnBeZ6D6xzbDIDIv8+0hDtiU3F?=
 =?us-ascii?Q?w4tljqJfiM/7BMWBfgeyVJJxnDSBuHjPzm4uvQGG14MdHROW6jYt5juRqRM8?=
 =?us-ascii?Q?CUd71M1H8+B4A/KEYeoTHrPmSiwg7t/dAzFNQ6ftclFOAJLIcHZOnT8VMmFj?=
 =?us-ascii?Q?bXApyk3gDEVnEHMuo1JJutplt+859jlcpvzGV0kQupqRX+xrCx8BogmFgVxI?=
 =?us-ascii?Q?+eyJjxcfeUqFk4vXo2yEsKH443PZqHlw+d6YbfS0+20ymLMgvd5xFeLzRYk9?=
 =?us-ascii?Q?hkHLQmYf7IVbY1fNv5bOj+LeE2iBZMDEYZYeOMYkL/FZfiJgZaIDfxnjLUce?=
 =?us-ascii?Q?NM7oR6bKNH9/WeZ/yb58HkcR2piHcAo0lt85pOMDAqWofXGbgeBkTS2tJAlF?=
 =?us-ascii?Q?uIt9YQItZMudNxZrMHBtk988?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 296a1422-1bef-4e0b-c6cd-08d9876c3352
X-MS-Exchange-CrossTenant-AuthSource: DM5PR10MB1466.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 04 Oct 2021 19:21:44.0774
 (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: 355+a58jbc0bll3fkufnNu9U4X7CsNlDnANnSZpZAcu6XgwpIBmUBDPB8vPAq9HYRDiXM3AgIKUfXF3SS+juPAcEhKfOlTr9QXHETXl/fpc=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR10MB1548
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10127 signatures=668683
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=0 adultscore=0
 mlxscore=0 phishscore=0 bulkscore=0 mlxlogscore=999 malwarescore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2109230001
 definitions=main-2110040131
X-Proofpoint-GUID: CtH34_iRtE1tZcpypDe8msS4ASbXqdls
X-Proofpoint-ORIG-GUID: CtH34_iRtE1tZcpypDe8msS4ASbXqdls
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 cgroups v2 not
working and 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>
---
 drivers/vhost/vhost.c | 68 ++++++++++++++++---------------------------
 drivers/vhost/vhost.h |  7 ++++-
 2 files changed, 31 insertions(+), 44 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c9a1f706989c..7a5142dcde1b 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 +585,27 @@ 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. So we do not want to
+	 * ineherit the parent's signal handlers and set our worker to ignore
+	 * everything below.
+	 */
+	task = kernel_worker(vhost_worker, worker, NUMA_NO_NODE,
+			     CLONE_FS | CLONE_CLEAR_SIGHAND,
+			     KERN_WORKER_NO_FILES | KERN_WORKER_NO_SIGS);
 	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