L: netdev@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git
+F: kernel/vhost_task.c
F: drivers/vhost/
+F: include/linux/sched/vhost_task.h
F: include/linux/vhost_iotlb.h
F: include/uapi/linux/vhost.h
/* Prepare to copy thread state - unlazy all lazy status */
#define prepare_to_copy(tsk) do { } while (0)
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
unsigned long __get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
This option is selected by any driver which needs to access
the host side of a virtio ring.
+config VHOST_TASK
+ bool
+ default n
+
config VHOST
tristate
select VHOST_IOTLB
+ select VHOST_TASK
help
This option is selected by any driver which needs to access
the core of vhost.
#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>
* sure it was not in the list.
* test_and_set_bit() implies a memory barrier.
*/
- llist_add(&work->node, &dev->work_list);
- wake_up_process(dev->worker);
+ llist_add(&work->node, &dev->worker->work_list);
+ wake_up_process(dev->worker->vtsk->task);
}
}
EXPORT_SYMBOL_GPL(vhost_work_queue);
/* A lockless hint for busy polling code to exit the loop */
bool vhost_has_work(struct vhost_dev *dev)
{
- return !llist_empty(&dev->work_list);
+ return dev->worker && !llist_empty(&dev->worker->work_list);
}
EXPORT_SYMBOL_GPL(vhost_has_work);
static int vhost_worker(void *data)
{
- struct vhost_dev *dev = data;
+ struct vhost_worker *worker = data;
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;
}
- node = llist_del_all(&dev->work_list);
+ node = llist_del_all(&worker->work_list);
if (!node)
schedule();
llist_for_each_entry_safe(work, work_next, node, node) {
clear_bit(VHOST_WORK_QUEUED, &work->flags);
__set_current_state(TASK_RUNNING);
- kcov_remote_start_common(dev->kcov_handle);
+ kcov_remote_start_common(worker->kcov_handle);
work->fn(work);
kcov_remote_stop();
if (need_resched())
schedule();
}
}
- kthread_unuse_mm(dev->mm);
+
return 0;
}
dev->byte_weight = byte_weight;
dev->use_worker = use_worker;
dev->msg_handler = msg_handler;
- init_llist_head(&dev->work_list);
init_waitqueue_head(&dev->wait);
INIT_LIST_HEAD(&dev->read_list);
INIT_LIST_HEAD(&dev->pending_list);
}
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)
{
dev->mm = NULL;
}
+static void vhost_worker_free(struct vhost_dev *dev)
+{
+ struct vhost_worker *worker = dev->worker;
+
+ if (!worker)
+ return;
+
+ dev->worker = NULL;
+ WARN_ON(!llist_empty(&worker->work_list));
+ vhost_task_stop(worker->vtsk);
+ kfree(worker);
+}
+
+static int vhost_worker_create(struct vhost_dev *dev)
+{
+ struct vhost_worker *worker;
+ struct vhost_task *vtsk;
+ char name[TASK_COMM_LEN];
+ int ret;
+
+ worker = kzalloc(sizeof(*worker), GFP_KERNEL_ACCOUNT);
+ if (!worker)
+ return -ENOMEM;
+
+ dev->worker = worker;
+ worker->kcov_handle = kcov_common_handle();
+ init_llist_head(&worker->work_list);
+ snprintf(name, sizeof(name), "vhost-%d", current->pid);
+
+ vtsk = vhost_task_create(vhost_worker, worker, name);
+ if (!vtsk) {
+ ret = -ENOMEM;
+ goto free_worker;
+ }
+
+ worker->vtsk = vtsk;
+ vhost_task_start(vtsk);
+ return 0;
+
+free_worker:
+ kfree(worker);
+ dev->worker = NULL;
+ return ret;
+}
+
/* Caller should have device mutex */
long vhost_dev_set_owner(struct vhost_dev *dev)
{
- struct task_struct *worker;
int err;
/* Is there an owner already? */
vhost_attach_mm(dev);
- dev->kcov_handle = kcov_common_handle();
if (dev->use_worker) {
- worker = kthread_create(vhost_worker, dev,
- "vhost-%d", current->pid);
- if (IS_ERR(worker)) {
- err = PTR_ERR(worker);
- goto err_worker;
- }
-
- dev->worker = worker;
- wake_up_process(worker); /* avoid contributing to loadavg */
-
- err = vhost_attach_cgroups(dev);
+ err = vhost_worker_create(dev);
if (err)
- goto err_cgroup;
+ goto err_worker;
}
err = vhost_dev_alloc_iovecs(dev);
if (err)
- goto err_cgroup;
+ goto err_iovecs;
return 0;
-err_cgroup:
- if (dev->worker) {
- kthread_stop(dev->worker);
- dev->worker = NULL;
- }
+err_iovecs:
+ vhost_worker_free(dev);
err_worker:
vhost_detach_mm(dev);
- dev->kcov_handle = 0;
err_mm:
return err;
}
dev->iotlb = NULL;
vhost_clear_msg(dev);
wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
- WARN_ON(!llist_empty(&dev->work_list));
- if (dev->worker) {
- kthread_stop(dev->worker);
- dev->worker = NULL;
- dev->kcov_handle = 0;
- }
+ vhost_worker_free(dev);
vhost_detach_mm(dev);
}
EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
#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
unsigned long flags;
};
+struct vhost_worker {
+ struct vhost_task *vtsk;
+ struct llist_head work_list;
+ u64 kcov_handle;
+};
+
/* Poll a file (eventfd or socket) */
/* Note: there's nothing vhost specific about this structure. */
struct vhost_poll {
struct vhost_virtqueue **vqs;
int nvqs;
struct eventfd_ctx *log_ctx;
- struct llist_head work_list;
- struct task_struct *worker;
+ struct vhost_worker *worker;
struct vhost_iotlb *umem;
struct vhost_iotlb *iotlb;
spinlock_t iotlb_lock;
int iov_limit;
int weight;
int byte_weight;
- u64 kcov_handle;
bool use_worker;
int (*msg_handler)(struct vhost_dev *dev, u32 asid,
struct vhost_iotlb_msg *msg);
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
#define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */
-#define PF__HOLE__00004000 0x00004000
+#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */
#define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */
#define PF__HOLE__00010000 0x00010000
#define PF_KSWAPD 0x00020000 /* I am kswapd */
int __user *pidfd;
int __user *child_tid;
int __user *parent_tid;
+ const char *name;
int exit_signal;
+ u32 kthread:1;
+ u32 io_thread:1;
+ u32 user_worker:1;
+ u32 no_files:1;
+ u32 ignore_signals:1;
unsigned long stack;
unsigned long stack_size;
unsigned long tls;
/* Number of elements in *set_tid */
size_t set_tid_size;
int cgroup;
- int io_thread;
- int kthread;
int idle;
int (*fn)(void *);
void *fn_arg;
extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
+struct task_struct *copy_process(struct pid *pid, int trace, int node,
+ struct kernel_clone_args *args);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
struct task_struct *fork_idle(int);
-extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name,
+ unsigned long flags);
extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
int kernel_wait(pid_t pid, int *stat);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VHOST_TASK_H
+#define _LINUX_VHOST_TASK_H
+
+#include <linux/completion.h>
+
+struct task_struct;
+
+struct vhost_task {
+ int (*fn)(void *data);
+ void *data;
+ struct completion exited;
+ unsigned long flags;
+ struct task_struct *task;
+};
+
+struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg,
+ const char *name);
+void vhost_task_start(struct vhost_task *vtsk);
+void vhost_task_stop(struct vhost_task *vtsk);
+bool vhost_task_should_stop(struct vhost_task *vtsk);
+
+#endif
rcu_read_unlock();
numa_default_policy();
- pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
+ pid = kernel_thread(kthreadd, NULL, NULL, CLONE_FS | CLONE_FILES);
rcu_read_lock();
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
rcu_read_unlock();
obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o
obj-$(CONFIG_MODULES) += kmod.o
obj-$(CONFIG_MULTIUSER) += groups.o
+obj-$(CONFIG_VHOST_TASK) += vhost_task.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace internal ftrace files
return 0;
}
-static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
+static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
+ int no_files)
{
struct files_struct *oldf, *newf;
int error = 0;
if (!oldf)
goto out;
+ if (no_files) {
+ tsk->files = NULL;
+ goto out;
+ }
+
if (clone_flags & CLONE_FILES) {
atomic_inc(&oldf->count);
goto out;
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
-static __latent_entropy struct task_struct *copy_process(
+__latent_entropy struct task_struct *copy_process(
struct pid *pid,
int trace,
int node,
p->flags &= ~PF_KTHREAD;
if (args->kthread)
p->flags |= PF_KTHREAD;
+ if (args->user_worker)
+ p->flags |= PF_USER_WORKER;
if (args->io_thread) {
/*
* Mark us an IO worker, and block any signal that isn't
siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
}
+ if (args->name)
+ strscpy_pad(p->comm, args->name, sizeof(p->comm));
+
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
/*
* Clear TID on mm_release()?
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_security;
- retval = copy_files(clone_flags, p);
+ retval = copy_files(clone_flags, p, args->no_files);
if (retval)
goto bad_fork_cleanup_semundo;
retval = copy_fs(clone_flags, p);
if (retval)
goto bad_fork_cleanup_io;
+ if (args->ignore_signals)
+ ignore_signals(p);
+
stackleak_task_init(p);
if (pid != &init_struct_pid) {
.fn = fn,
.fn_arg = arg,
.io_thread = 1,
+ .user_worker = 1,
};
return copy_process(NULL, 0, node, &args);
/*
* Create a kernel thread.
*/
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name,
+ unsigned long flags)
{
struct kernel_clone_args args = {
.flags = ((lower_32_bits(flags) | CLONE_VM |
.exit_signal = (lower_32_bits(flags) & CSIGNAL),
.fn = fn,
.fn_arg = arg,
+ .name = name,
.kthread = 1,
};
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
+ char *full_name;
int (*threadfn)(void *data);
void *data;
int node;
/* Release the structure when caller killed by a fatal signal. */
done = xchg(&create->done, NULL);
if (!done) {
+ kfree(create->full_name);
kfree(create);
kthread_exit(-EINTR);
}
+ self->full_name = create->full_name;
self->threadfn = threadfn;
self->data = data;
current->pref_node_fork = create->node;
#endif
/* We want our own signal handler (we take no signals by default). */
- pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
+ pid = kernel_thread(kthread, create, create->full_name,
+ CLONE_FS | CLONE_FILES | SIGCHLD);
if (pid < 0) {
/* Release the structure when caller killed by a fatal signal. */
struct completion *done = xchg(&create->done, NULL);
+ kfree(create->full_name);
if (!done) {
kfree(create);
return;
create->data = data;
create->node = node;
create->done = &done;
+ create->full_name = kvasprintf(GFP_KERNEL, namefmt, args);
+ if (!create->full_name) {
+ task = ERR_PTR(-ENOMEM);
+ goto free_create;
+ }
spin_lock(&kthread_create_lock);
list_add_tail(&create->list, &kthread_create_list);
wait_for_completion(&done);
}
task = create->result;
- if (!IS_ERR(task)) {
- char name[TASK_COMM_LEN];
- va_list aq;
- int len;
-
- /*
- * task is already visible to other tasks, so updating
- * COMM must be protected.
- */
- va_copy(aq, args);
- len = vsnprintf(name, sizeof(name), namefmt, aq);
- va_end(aq);
- if (len >= TASK_COMM_LEN) {
- struct kthread *kthread = to_kthread(task);
-
- /* leave it truncated when out of memory. */
- kthread->full_name = kvasprintf(GFP_KERNEL, namefmt, args);
- }
- set_task_comm(task, name);
- }
+free_create:
kfree(create);
return task;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Oracle Corporation
+ */
+#include <linux/slab.h>
+#include <linux/completion.h>
+#include <linux/sched/task.h>
+#include <linux/sched/vhost_task.h>
+#include <linux/sched/signal.h>
+
+enum vhost_task_flags {
+ VHOST_TASK_FLAGS_STOP,
+};
+
+static int vhost_task_fn(void *data)
+{
+ struct vhost_task *vtsk = data;
+ int ret;
+
+ ret = vtsk->fn(vtsk->data);
+ complete(&vtsk->exited);
+ do_exit(ret);
+}
+
+/**
+ * vhost_task_stop - stop a vhost_task
+ * @vtsk: vhost_task to stop
+ *
+ * Callers must call vhost_task_should_stop and return from their worker
+ * function when it returns true;
+ */
+void vhost_task_stop(struct vhost_task *vtsk)
+{
+ pid_t pid = vtsk->task->pid;
+
+ set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
+ wake_up_process(vtsk->task);
+ /*
+ * Make sure vhost_task_fn is no longer accessing the vhost_task before
+ * freeing it below. If userspace crashed or exited without closing,
+ * then the vhost_task->task could already be marked dead so
+ * kernel_wait will return early.
+ */
+ wait_for_completion(&vtsk->exited);
+ /*
+ * If we are just closing/removing a device and the parent process is
+ * not exiting then reap the task.
+ */
+ kernel_wait4(pid, NULL, __WCLONE, NULL);
+ kfree(vtsk);
+}
+EXPORT_SYMBOL_GPL(vhost_task_stop);
+
+/**
+ * vhost_task_should_stop - should the vhost task return from the work function
+ * @vtsk: vhost_task to stop
+ */
+bool vhost_task_should_stop(struct vhost_task *vtsk)
+{
+ return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
+}
+EXPORT_SYMBOL_GPL(vhost_task_should_stop);
+
+/**
+ * vhost_task_create - create a copy of a process to be used by the kernel
+ * @fn: thread stack
+ * @arg: data to be passed to fn
+ * @name: the thread's name
+ *
+ * This returns a specialized task for use by the vhost layer or NULL on
+ * failure. The returned task is inactive, and the caller must fire it up
+ * through vhost_task_start().
+ */
+struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg,
+ const char *name)
+{
+ struct kernel_clone_args args = {
+ .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM,
+ .exit_signal = 0,
+ .fn = vhost_task_fn,
+ .name = name,
+ .user_worker = 1,
+ .no_files = 1,
+ .ignore_signals = 1,
+ };
+ struct vhost_task *vtsk;
+ struct task_struct *tsk;
+
+ vtsk = kzalloc(sizeof(*vtsk), GFP_KERNEL);
+ if (!vtsk)
+ return NULL;
+ init_completion(&vtsk->exited);
+ vtsk->data = arg;
+ vtsk->fn = fn;
+
+ args.fn_arg = vtsk;
+
+ tsk = copy_process(NULL, 0, NUMA_NO_NODE, &args);
+ if (IS_ERR(tsk)) {
+ kfree(vtsk);
+ return NULL;
+ }
+
+ vtsk->task = tsk;
+ return vtsk;
+}
+EXPORT_SYMBOL_GPL(vhost_task_create);
+
+/**
+ * vhost_task_start - start a vhost_task created with vhost_task_create
+ * @vtsk: vhost_task to wake up
+ */
+void vhost_task_start(struct vhost_task *vtsk)
+{
+ wake_up_new_task(vtsk->task);
+}
+EXPORT_SYMBOL_GPL(vhost_task_start);
DEFINE_WAIT(wait);
/*
- * Do not throttle IO workers, kthreads other than kswapd or
+ * Do not throttle user workers, kthreads other than kswapd or
* workqueues. They may be required for reclaim to make
* forward progress (e.g. journalling workqueues or kthreads).
*/
if (!current_is_kswapd() &&
- current->flags & (PF_IO_WORKER|PF_KTHREAD)) {
+ current->flags & (PF_USER_WORKER|PF_KTHREAD)) {
cond_resched();
return;
}
projects / linux-block.git / commitdiff