| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20230720090415-mutt-send-email-mst@kernel.org>
Date: Thu, 20 Jul 2023 09:06:08 -0400
From: "Michael S. Tsirkin" <mst@...hat.com>
To: Mike Christie <michael.christie@...cle.com>
Cc: hch@...radead.org, stefanha@...hat.com, jasowang@...hat.com,
sgarzare@...hat.com, virtualization@...ts.linux-foundation.org,
brauner@...nel.org, ebiederm@...ssion.com,
torvalds@...ux-foundation.org, konrad.wilk@...cle.com,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v11 8/8] vhost: use vhost_tasks for worker threads
On Thu, Feb 02, 2023 at 05:25:17PM -0600, Mike Christie wrote:
> 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, so while tools like libvirt try to control the number of
> threads based on the nproc rlimit setting we can end up creating more
> threads than the user wanted.
>
> This patch has us use the vhost_task helpers which will inherit its
> values/checks from the thread that owns the device similar to if we did
> a clone in userspace. The vhost threads will now be counted in the nproc
> rlimits. And we get features like cgroups and mm sharing automatically,
> so we can remove those calls.
>
> Signed-off-by: Mike Christie <michael.christie@...cle.com>
> Acked-by: Michael S. Tsirkin <mst@...hat.com>
Hi Mike,
So this seems to have caused a measureable regression in networking
performance (about 30%). Take a look here, and there's a zip file
with detailed measuraments attached:
https://bugzilla.redhat.com/show_bug.cgi?id=2222603
Could you take a look please?
You can also ask reporter questions there assuming you
have or can create a (free) account.
> ---
> drivers/vhost/vhost.c | 58 ++++++++-----------------------------------
> drivers/vhost/vhost.h | 4 +--
> 2 files changed, 13 insertions(+), 49 deletions(-)
>
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 74378d241f8d..d3c7c37b69a7 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -22,11 +22,11 @@
> #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>
> #include <linux/sched/signal.h>
> +#include <linux/sched/vhost_task.h>
> #include <linux/interval_tree_generic.h>
> #include <linux/nospec.h>
> #include <linux/kcov.h>
> @@ -256,7 +256,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
> * test_and_set_bit() implies a memory barrier.
> */
> llist_add(&work->node, &dev->worker->work_list);
> - wake_up_process(dev->worker->task);
> + wake_up_process(dev->worker->vtsk->task);
> }
> }
> EXPORT_SYMBOL_GPL(vhost_work_queue);
> @@ -336,17 +336,14 @@ 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 (vhost_task_should_stop(worker->vtsk)) {
> __set_current_state(TASK_RUNNING);
> break;
> }
> @@ -368,7 +365,7 @@ static int vhost_worker(void *data)
> schedule();
> }
> }
> - kthread_unuse_mm(dev->mm);
> +
> return 0;
> }
>
> @@ -509,31 +506,6 @@ 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_dev_flush(dev);
> - return attach.ret;
> -}
> -
> /* Caller should have device mutex */
> bool vhost_dev_has_owner(struct vhost_dev *dev)
> {
> @@ -580,14 +552,14 @@ static void vhost_worker_free(struct vhost_dev *dev)
>
> dev->worker = NULL;
> WARN_ON(!llist_empty(&worker->work_list));
> - kthread_stop(worker->task);
> + vhost_task_stop(worker->vtsk);
> kfree(worker);
> }
>
> static int vhost_worker_create(struct vhost_dev *dev)
> {
> struct vhost_worker *worker;
> - struct task_struct *task;
> + struct vhost_task *vtsk;
> int ret;
>
> worker = kzalloc(sizeof(*worker), GFP_KERNEL_ACCOUNT);
> @@ -595,27 +567,19 @@ 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);
> - if (IS_ERR(task)) {
> - ret = PTR_ERR(task);
> + vtsk = vhost_task_create(vhost_worker, worker, NUMA_NO_NODE);
> + if (!vtsk) {
> + ret = -ENOMEM;
> goto free_worker;
> }
>
> - worker->task = task;
> - wake_up_process(task); /* avoid contributing to loadavg */
> -
> - ret = vhost_attach_cgroups(dev);
> - if (ret)
> - goto stop_worker;
> -
> + worker->vtsk = vtsk;
> + vhost_task_start(vtsk, "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 2f6beab93784..3af59c65025e 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -16,6 +16,7 @@
> #include <linux/irqbypass.h>
>
> struct vhost_work;
> +struct vhost_task;
> typedef void (*vhost_work_fn_t)(struct vhost_work *work);
>
> #define VHOST_WORK_QUEUED 1
> @@ -26,9 +27,8 @@ struct vhost_work {
> };
>
> struct vhost_worker {
> - struct task_struct *task;
> + struct vhost_task *vtsk;
> struct llist_head work_list;
> - struct vhost_dev *dev;
> u64 kcov_handle;
> };
>
> --
> 2.25.1
Powered by blists - more mailing lists