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:     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 V2 5/9] fork: add helper to clone a process
Date:   Tue, 21 Sep 2021 16:52:14 -0500
Message-Id: <20210921215218.89844-6-michael.christie@oracle.com>
In-Reply-To: <20210921215218.89844-1-michael.christie@oracle.com>
References: <20210921215218.89844-1-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?BMVkctPAUgOSPQuNyw/0P2gkOhvqHTehhnZmDlKCnunSBNCo2QN7Gs6Z47cm?=
 =?us-ascii?Q?VnI/7HtugdeTd2/W+umArTj0N9ax1z6dda7M3q7CXZQgQF2gcfkXpbBYrD2y?=
 =?us-ascii?Q?J0i1x95aotzV/mzWA0zcuwPCnDZLdKopEKWS4mmBDnOrG3tLaIpKAwvKEJsy?=
 =?us-ascii?Q?io2n2zZ405BFDKYcFwk3TmDwhikLf9pXnW3oogdww7X5IbCnxdBXzCS9XcoV?=
 =?us-ascii?Q?Fs81ZAkJwZJ1Q/I+20pA0PCCgLWoAqqHoGhY1c4xNZymw6/GNdD+OFmVbspe?=
 =?us-ascii?Q?JPlp210xY4/C6CAGPhxfsLdHh/oYltiAx4ZnE5bebIGu/fbM7I5n2ceOsQAu?=
 =?us-ascii?Q?BjxBd1U7zQ2C7dEvcS+nX1blG63fDpusRlW9wW1EGeiS6A3/U8m9flMeJHY2?=
 =?us-ascii?Q?Ty9wyknZKGFrI6+GPMmt76VudhjseKbN0nDWlBzojlVQP6lv9OMKpw6r1lqI?=
 =?us-ascii?Q?GdL+z/3rYTgL9Vs/5GwZcPJwhQu8h/cDiwnNpdj6KyHflj8eIvxlKeGQVDiC?=
 =?us-ascii?Q?0u0wBq7B9m6SdhHo75mpocVcpBb2Q+Y1/TtAeAVQOp9aAbYNU8UfKKzzRL3G?=
 =?us-ascii?Q?lW7QEFKDgC8SKGYdC5JWDUb1b6TPfZmPGKkNNEMktQWza6C/aAWXu22FrYW9?=
 =?us-ascii?Q?NhnC6Geodbw90nv8H0gBfeqXG2OPZ+qlP21c0Z7LH7tVZ/0/y/sEeRpIhm1V?=
 =?us-ascii?Q?q4q+Wbwm/6lsOqc83NwiumTtmPirn8+auogx8LH/QwtHaHtOWhNRuATImujD?=
 =?us-ascii?Q?uR9Oz2BwQj7lm4aE0/Y9Z1Y+jnlOP/mzhLEu3UWGi/uGRc2dzk92uPapMRGi?=
 =?us-ascii?Q?l88XE94MK51ObWS1MNX0r86Gkn060JTY0uiqHe+Z3bfzwEuZBUvbvl2g7q2p?=
 =?us-ascii?Q?tjeydhNLB/7B6tQsar9swh3twIf0c7SYUYmEah8A4AWnqvRTvQpWNztPhDCe?=
 =?us-ascii?Q?6WKFZRuKzQ7kg+7JNqDmzimCrdBQ7nfFbi8r2i4Te3ntsuHLN1fNNBPpfvy7?=
 =?us-ascii?Q?iVPWDw+RK8ZFKGW2BAXFZtkfjdeWabvbC6OxbxA7rWVXZfpDqgWYozmAdAEu?=
 =?us-ascii?Q?4SEUi2AGqHAQYTFjM7wqAPmh/V8G1jfdGhqLfNJAUp6u+77nw0kupFzucOao?=
 =?us-ascii?Q?DwtQOVUbj8T4svcZlxuq9jg35ph5ItBQQmPuGEXtC+7momtsWCwjoJm2ZUBP?=
 =?us-ascii?Q?M+XNGRY17k9mb/KvDLaBGQWXCoLJLYvFJQp2NzFGlcSZsgex3XI3ZLbTsmft?=
 =?us-ascii?Q?OUzsAwaOsCGqgyqeUTartRUJnHs4Gz/27mh8F5b4/Y1t2LB0q2DEuGLzU/2N?=
 =?us-ascii?Q?KNjN3WsTs1L2aBRvzBvRTpvn?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: c1aa08ff-94fc-4ccb-4d26-08d97d4a1e71
X-MS-Exchange-CrossTenant-AuthSource: BYAPR10MB3573.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 21 Sep 2021 21:52:34.3088
 (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: uIT5cHQATsKfaYN2TbtHEbr9nFIQQjeFvdH+LwnRpN0fC3Yk27q2kEaNi9c89X21dph/N8HRlVR+hnpwwBrbutkzfTMbxNocXmf129Dw0rU=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BY5PR10MB3892
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10114 signatures=668682
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 malwarescore=0 spamscore=0
 suspectscore=0 phishscore=0 mlxlogscore=999 bulkscore=0 mlxscore=0
 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1
 engine=8.12.0-2109200000 definitions=main-2109210130
X-Proofpoint-GUID: 0L3KNyMezGyb4WTqzfXyIRdp7jLydZwF
X-Proofpoint-ORIG-GUID: 0L3KNyMezGyb4WTqzfXyIRdp7jLydZwF
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

The vhost layer has similar requirements as io_uring where its worker
threads need to access the userspace thread's memory, want to inherit the
parents's cgroups and namespaces, and be checked against the parent's
RLIMITs. Right now, the vhost layer uses the kthread API which has
kthread_use_mm for mem access, and those threads can use
cgroup_attach_task_all for v1 cgroups, but there are no helpers for the
other items.

This adds a helper to clone a process so we can inherit everything we
want in one call. It's a more generic version of create_io_thread which
will be used by the vhost layer and io_uring in later patches in this set.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
---
 include/linux/sched/task.h |  6 ++++-
 kernel/fork.c              | 48 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index e165cc67fd3c..ba0499b6627c 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -87,7 +87,11 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
-struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
+struct task_struct *create_io_thread(int (*fn)(void *i), void *arg, int node);
+struct task_struct *kernel_worker(int (*fn)(void *), void *arg, int node,
+				  unsigned long clone_flags, u32 worker_flags);
+__printf(2, 3)
+void kernel_worker_start(struct task_struct *tsk, const char namefmt[], ...);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/kernel/fork.c b/kernel/fork.c
index 98264cf1d6a6..3f3fcabffa5f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2540,6 +2540,54 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 	return copy_process(NULL, 0, node, &args);
 }
 
+/**
+ * kernel_worker - create a copy of a process to be used by the kernel
+ * @fn: thread stack
+ * @arg: data to be passed to fn
+ * @node: numa node to allocate task from
+ * @clone_flags: CLONE flags
+ * @worker_flags: KERN_WORKER flags
+ *
+ * This returns a created task, or an error pointer. The returned task is
+ * inactive, and the caller must fire it up through kernel_worker_start(). If
+ * this is an PF_IO_WORKER all singals but KILL and STOP are blocked.
+ */
+struct task_struct *kernel_worker(int (*fn)(void *), void *arg, int node,
+				  unsigned long clone_flags, u32 worker_flags)
+{
+	struct kernel_clone_args args = {
+		.flags		= ((lower_32_bits(clone_flags) | CLONE_VM |
+				   CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
+		.stack		= (unsigned long)fn,
+		.stack_size	= (unsigned long)arg,
+		.worker_flags	= KERN_WORKER_USER | worker_flags,
+	};
+
+	return copy_process(NULL, 0, node, &args);
+}
+EXPORT_SYMBOL_GPL(kernel_worker);
+
+/**
+ * kernel_worker_start - Start a task created with kernel_worker
+ * @tsk: task to wake up
+ * @namefmt: printf-style format string for the thread name
+ * @arg: arguments for @namefmt
+ */
+void kernel_worker_start(struct task_struct *tsk, const char namefmt[], ...)
+{
+	char name[TASK_COMM_LEN];
+	va_list args;
+
+	va_start(args, namefmt);
+	vsnprintf(name, sizeof(name), namefmt, args);
+	set_task_comm(tsk, name);
+	va_end(args);
+
+	wake_up_new_task(tsk);
+}
+EXPORT_SYMBOL_GPL(kernel_worker_start);
+
 /*
  *  Ok, this is the main fork-routine.
  *
-- 
2.25.1