All of lore.kernel.org
 help / color / mirror / Atom feed
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: Christoph Hellwig <hch@lst.de>
Subject: [PATCH V6 10/10] vhost: use user_worker to check RLIMITs
Date: Mon, 29 Nov 2021 13:47:07 -0600	[thread overview]
Message-ID: <20211129194707.5863-11-michael.christie@oracle.com> (raw)
In-Reply-To: <20211129194707.5863-1-michael.christie@oracle.com>

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 user_worker helpers which will
inherit its values/checks from the thread that owns the device similar to
if we did a clone in userspace.

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..8cf259d798c0 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 = user_worker_create(vhost_worker, worker, NUMA_NO_NODE, CLONE_FS,
+				  USER_WORKER_NO_FILES | USER_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;
-
+	user_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

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

WARNING: multiple messages have this Message-ID (diff)
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 V6 10/10] vhost: use user_worker to check RLIMITs
Date: Mon, 29 Nov 2021 13:47:07 -0600	[thread overview]
Message-ID: <20211129194707.5863-11-michael.christie@oracle.com> (raw)
In-Reply-To: <20211129194707.5863-1-michael.christie@oracle.com>

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 user_worker helpers which will
inherit its values/checks from the thread that owns the device similar to
if we did a clone in userspace.

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..8cf259d798c0 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 = user_worker_create(vhost_worker, worker, NUMA_NO_NODE, CLONE_FS,
+				  USER_WORKER_NO_FILES | USER_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;
-
+	user_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


  parent reply	other threads:[~2021-11-29 19:47 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-29 19:46 [PATCH V6 01/10] Use copy_process in vhost layer Mike Christie
2021-11-29 19:46 ` Mike Christie
2021-11-29 19:46 ` [PATCH V6 01/10] fork: Make IO worker options flag based Mike Christie
2021-11-29 19:46   ` Mike Christie
2021-11-29 19:46 ` [PATCH V6 02/10] fork/vm: Move common PF_IO_WORKER behavior to new flag Mike Christie
2021-11-29 19:46   ` Mike Christie
2021-11-29 19:47 ` [PATCH V6 03/10] fork: add USER_WORKER flag to not dup/clone files Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-11-29 19:47 ` [PATCH V6 04/10] fork: Add USER_WORKER flag to ignore signals Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-11-29 19:47 ` [PATCH V6 05/10] signal: Perfom autoreap for PF_USER_WORKER Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-12-17 18:42   ` Eric W. Biederman
2021-12-17 18:42     ` Eric W. Biederman
2021-11-29 19:47 ` [PATCH V6 06/10] fork: add helpers to clone a process for kernel use Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-12-17 18:53   ` Eric W. Biederman
2021-12-17 18:53     ` Eric W. Biederman
2021-11-29 19:47 ` [PATCH V6 07/10] io_uring: switch to user_worker Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-11-29 19:47 ` [PATCH V6 08/10] fork: remove create_io_thread Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-11-29 19:47 ` [PATCH V6 09/10] vhost: move worker thread fields to new struct Mike Christie
2021-11-29 19:47   ` Mike Christie
2021-11-29 19:47 ` Mike Christie [this message]
2021-11-29 19:47   ` [PATCH V6 10/10] vhost: use user_worker to check RLIMITs Mike Christie
2021-12-17 19:01   ` Eric W. Biederman
2021-12-17 19:01     ` Eric W. Biederman
2021-12-08 20:34 ` [PATCH V6 01/10] Use copy_process in vhost layer Michael S. Tsirkin
2021-12-08 20:34   ` Michael S. Tsirkin
2021-12-08 22:13   ` michael.christie
2021-12-08 22:13     ` michael.christie
2021-12-09  9:32     ` Christian Brauner
2021-12-17 19:26 ` Eric W. Biederman
2021-12-17 19:26   ` Eric W. Biederman
2021-12-17 22:08   ` michael.christie
2021-12-17 22:08     ` michael.christie
2021-12-22  0:20     ` Eric W. Biederman
2021-12-22  0:20       ` Eric W. Biederman
2021-12-22 17:32       ` Mike Christie
2021-12-22 17:32         ` Mike Christie
2021-12-22 18:24         ` Eric W. Biederman
2021-12-22 18:24           ` Eric W. Biederman
2021-12-22 20:25           ` Michael S. Tsirkin
2021-12-22 20:25             ` Michael S. Tsirkin
2022-01-17 16:41           ` Mike Christie
2022-01-17 16:41             ` Mike Christie
2022-01-17 17:31             ` Eric W. Biederman
2022-01-17 17:31               ` Eric W. Biederman
2022-01-18 18:51               ` Mike Christie
2022-01-18 18:51                 ` Mike Christie
2022-01-18 19:00                 ` Mike Christie
2022-01-18 19:00                   ` Mike Christie
2022-01-18 19:12                 ` Eric W. Biederman
2022-01-18 19:12                   ` Eric W. Biederman
2022-02-02 21:02                   ` Mike Christie
2022-02-02 21:02                     ` Mike Christie

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211129194707.5863-11-michael.christie@oracle.com \
    --to=michael.christie@oracle.com \
    --cc=axboe@kernel.dk \
    --cc=christian.brauner@ubuntu.com \
    --cc=geert@linux-m68k.org \
    --cc=hch@infradead.org \
    --cc=hch@lst.de \
    --cc=hdanton@sina.com \
    --cc=jasowang@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=vverma@digitalocean.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.