linux_old1/kernel/kthread.c

444 lines
12 KiB
C
Raw Normal View History

/* Kernel thread helper functions.
* Copyright (C) 2004 IBM Corporation, Rusty Russell.
*
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
* Creation is done via kthreadd, so that we get a clean environment
* even if we're invoked from userspace (think modprobe, hotplug cpu,
* etc.).
*/
#include <linux/sched.h>
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
cpuset,mm: update tasks' mems_allowed in time Fix allocating page cache/slab object on the unallowed node when memory spread is set by updating tasks' mems_allowed after its cpuset's mems is changed. In order to update tasks' mems_allowed in time, we must modify the code of memory policy. Because the memory policy is applied in the process's context originally. After applying this patch, one task directly manipulates anothers mems_allowed, and we use alloc_lock in the task_struct to protect mems_allowed and memory policy of the task. But in the fast path, we didn't use lock to protect them, because adding a lock may lead to performance regression. But if we don't add a lock,the task might see no nodes when changing cpuset's mems_allowed to some non-overlapping set. In order to avoid it, we set all new allowed nodes, then clear newly disallowed ones. [lee.schermerhorn@hp.com: The rework of mpol_new() to extract the adjusting of the node mask to apply cpuset and mpol flags "context" breaks set_mempolicy() and mbind() with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local allocation. Fix this by adding the check for MPOL_PREFERRED and empty node mask to mpol_new_mpolicy(). Remove the now unneeded 'nodes = NULL' from mpol_new(). Note that mpol_new_mempolicy() is always called with a non-NULL 'nodes' parameter now that it has been removed from mpol_new(). Therefore, we don't need to test nodes for NULL before testing it for 'empty'. However, just to be extra paranoid, add a VM_BUG_ON() to verify this assumption.] [lee.schermerhorn@hp.com: I don't think the function name 'mpol_new_mempolicy' is descriptive enough to differentiate it from mpol_new(). This function applies cpuset set context, usually constraining nodes to those allowed by the cpuset. However, when the 'RELATIVE_NODES flag is set, it also translates the nodes. So I settled on 'mpol_set_nodemask()', because the comment block for mpol_new() mentions that we need to call this function to "set nodes". Some additional minor line length, whitespace and typo cleanup.] Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Paul Menage <menage@google.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:31:49 +08:00
#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/freezer.h>
#include <trace/events/sched.h>
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
struct kthread_create_info
{
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
/* Information passed to kthread() from kthreadd. */
int (*threadfn)(void *data);
void *data;
int node;
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
struct completion done;
2006-11-22 22:55:48 +08:00
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
struct list_head list;
};
struct kthread {
int should_stop;
void *data;
struct completion exited;
};
#define to_kthread(tsk) \
container_of((tsk)->vfork_done, struct kthread, exited)
/**
* kthread_should_stop - should this kthread return now?
*
* When someone calls kthread_stop() on your kthread, it will be woken
* and this will return true. You should then return, and your return
* value will be passed through to kthread_stop().
*/
int kthread_should_stop(void)
{
return to_kthread(current)->should_stop;
}
EXPORT_SYMBOL(kthread_should_stop);
/**
* kthread_data - return data value specified on kthread creation
* @task: kthread task in question
*
* Return the data value specified when kthread @task was created.
* The caller is responsible for ensuring the validity of @task when
* calling this function.
*/
void *kthread_data(struct task_struct *task)
{
return to_kthread(task)->data;
}
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
struct kthread_create_info *create = _create;
int (*threadfn)(void *data) = create->threadfn;
void *data = create->data;
struct kthread self;
int ret;
self.should_stop = 0;
self.data = data;
init_completion(&self.exited);
current->vfork_done = &self.exited;
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
complete(&create->done);
schedule();
ret = -EINTR;
if (!self.should_stop)
ret = threadfn(data);
/* we can't just return, we must preserve "self" on stack */
do_exit(ret);
}
/* called from do_fork() to get node information for about to be created task */
int tsk_fork_get_node(struct task_struct *tsk)
{
#ifdef CONFIG_NUMA
if (tsk == kthreadd_task)
return tsk->pref_node_fork;
#endif
return numa_node_id();
}
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
static void create_kthread(struct kthread_create_info *create)
{
int pid;
#ifdef CONFIG_NUMA
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);
if (pid < 0) {
create->result = ERR_PTR(pid);
complete(&create->done);
}
}
/**
* kthread_create_on_node - create a kthread.
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @node: memory node number.
* @namefmt: printf-style name for the thread.
*
* Description: This helper function creates and names a kernel
* thread. The thread will be stopped: use wake_up_process() to start
* it. See also kthread_run().
*
* If thread is going to be bound on a particular cpu, give its node
* in @node, to get NUMA affinity for kthread stack, or else give -1.
* When woken, the thread will run @threadfn() with @data as its
* argument. @threadfn() can either call do_exit() directly if it is a
* standalone thread for which no one will call kthread_stop(), or
* return when 'kthread_should_stop()' is true (which means
* kthread_stop() has been called). The return value should be zero
* or a negative error number; it will be passed to kthread_stop().
*
* Returns a task_struct or ERR_PTR(-ENOMEM).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
void *data,
int node,
const char namefmt[],
...)
{
struct kthread_create_info create;
create.threadfn = threadfn;
create.data = data;
create.node = node;
init_completion(&create.done);
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
spin_lock(&kthread_create_lock);
list_add_tail(&create.list, &kthread_create_list);
spin_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
wait_for_completion(&create.done);
if (!IS_ERR(create.result)) {
static const struct sched_param param = { .sched_priority = 0 };
va_list args;
va_start(args, namefmt);
vsnprintf(create.result->comm, sizeof(create.result->comm),
namefmt, args);
va_end(args);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
*/
sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
set_cpus_allowed_ptr(create.result, cpu_all_mask);
}
return create.result;
}
EXPORT_SYMBOL(kthread_create_on_node);
/**
* kthread_bind - bind a just-created kthread to a cpu.
* @p: thread created by kthread_create().
* @cpu: cpu (might not be online, must be possible) for @k to run on.
*
* Description: This function is equivalent to set_cpus_allowed(),
* except that @cpu doesn't need to be online, and the thread must be
* stopped (i.e., just returned from kthread_create()).
*/
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
/* Must have done schedule() in kthread() before we set_task_cpu */
if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
WARN_ON(1);
return;
}
p->cpus_allowed = cpumask_of_cpu(cpu);
p->rt.nr_cpus_allowed = 1;
p->flags |= PF_THREAD_BOUND;
}
EXPORT_SYMBOL(kthread_bind);
/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
* waits for it to exit. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
* If threadfn() may call do_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.
*/
int kthread_stop(struct task_struct *k)
{
struct kthread *kthread;
int ret;
trace_sched_kthread_stop(k);
get_task_struct(k);
kthread = to_kthread(k);
barrier(); /* it might have exited */
if (k->vfork_done != NULL) {
kthread->should_stop = 1;
wake_up_process(k);
wait_for_completion(&kthread->exited);
}
ret = k->exit_code;
put_task_struct(k);
trace_sched_kthread_stop_ret(ret);
return ret;
}
EXPORT_SYMBOL(kthread_stop);
int kthreadd(void *unused)
{
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
struct task_struct *tsk = current;
/* Setup a clean context for our children to inherit. */
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
set_task_comm(tsk, "kthreadd");
ignore_signals(tsk);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
set_mems_allowed(node_states[N_HIGH_MEMORY]);
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
kthread: don't depend on work queues Currently there is a circular reference between work queue initialization and kthread initialization. This prevents the kthread infrastructure from initializing until after work queues have been initialized. We want the properties of tasks created with kthread_create to be as close as possible to the init_task and to not be contaminated by user processes. The later we start our kthreadd that creates these tasks the harder it is to avoid contamination from user processes and the more of a mess we have to clean up because the defaults have changed on us. So this patch modifies the kthread support to not use work queues but to instead use a simple list of structures, and to have kthreadd start from init_task immediately after our kernel thread that execs /sbin/init. By being a true child of init_task we only have to change those process settings that we want to have different from init_task, such as our process name, the cpus that are allowed, blocking all signals and setting SIGCHLD to SIG_IGN so that all of our children are reaped automatically. By being a true child of init_task we also naturally get our ppid set to 0 and do not wind up as a child of PID == 1. Ensuring that tasks generated by kthread_create will not slow down the functioning of the wait family of functions. [akpm@linux-foundation.org: use interruptible sleeps] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:32 +08:00
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (list_empty(&kthread_create_list))
schedule();
__set_current_state(TASK_RUNNING);
spin_lock(&kthread_create_lock);
while (!list_empty(&kthread_create_list)) {
struct kthread_create_info *create;
create = list_entry(kthread_create_list.next,
struct kthread_create_info, list);
list_del_init(&create->list);
spin_unlock(&kthread_create_lock);
create_kthread(create);
spin_lock(&kthread_create_lock);
}
spin_unlock(&kthread_create_lock);
}
return 0;
}
void __init_kthread_worker(struct kthread_worker *worker,
const char *name,
struct lock_class_key *key)
{
spin_lock_init(&worker->lock);
lockdep_set_class_and_name(&worker->lock, key, name);
INIT_LIST_HEAD(&worker->work_list);
worker->task = NULL;
}
EXPORT_SYMBOL_GPL(__init_kthread_worker);
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
*
* This function can be used as @threadfn to kthread_create() or
* kthread_run() with @worker_ptr argument pointing to an initialized
* kthread_worker. The started kthread will process work_list until
* the it is stopped with kthread_stop(). A kthread can also call
* this function directly after extra initialization.
*
* Different kthreads can be used for the same kthread_worker as long
* as there's only one kthread attached to it at any given time. A
* kthread_worker without an attached kthread simply collects queued
* kthread_works.
*/
int kthread_worker_fn(void *worker_ptr)
{
struct kthread_worker *worker = worker_ptr;
struct kthread_work *work;
WARN_ON(worker->task);
worker->task = current;
repeat:
set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
spin_lock_irq(&worker->lock);
worker->task = NULL;
spin_unlock_irq(&worker->lock);
return 0;
}
work = NULL;
spin_lock_irq(&worker->lock);
if (!list_empty(&worker->work_list)) {
work = list_first_entry(&worker->work_list,
struct kthread_work, node);
list_del_init(&work->node);
}
spin_unlock_irq(&worker->lock);
if (work) {
__set_current_state(TASK_RUNNING);
work->func(work);
smp_wmb(); /* wmb worker-b0 paired with flush-b1 */
work->done_seq = work->queue_seq;
smp_mb(); /* mb worker-b1 paired with flush-b0 */
if (atomic_read(&work->flushing))
wake_up_all(&work->done);
} else if (!freezing(current))
schedule();
try_to_freeze();
goto repeat;
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
/**
* queue_kthread_work - queue a kthread_work
* @worker: target kthread_worker
* @work: kthread_work to queue
*
* Queue @work to work processor @task for async execution. @task
* must have been created with kthread_worker_create(). Returns %true
* if @work was successfully queued, %false if it was already pending.
*/
bool queue_kthread_work(struct kthread_worker *worker,
struct kthread_work *work)
{
bool ret = false;
unsigned long flags;
spin_lock_irqsave(&worker->lock, flags);
if (list_empty(&work->node)) {
list_add_tail(&work->node, &worker->work_list);
work->queue_seq++;
if (likely(worker->task))
wake_up_process(worker->task);
ret = true;
}
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_kthread_work);
/**
* flush_kthread_work - flush a kthread_work
* @work: work to flush
*
* If @work is queued or executing, wait for it to finish execution.
*/
void flush_kthread_work(struct kthread_work *work)
{
int seq = work->queue_seq;
atomic_inc(&work->flushing);
/*
* mb flush-b0 paired with worker-b1, to make sure either
* worker sees the above increment or we see done_seq update.
*/
smp_mb__after_atomic_inc();
/* A - B <= 0 tests whether B is in front of A regardless of overflow */
wait_event(work->done, seq - work->done_seq <= 0);
atomic_dec(&work->flushing);
/*
* rmb flush-b1 paired with worker-b0, to make sure our caller
* sees every change made by work->func().
*/
smp_mb__after_atomic_dec();
}
EXPORT_SYMBOL_GPL(flush_kthread_work);
struct kthread_flush_work {
struct kthread_work work;
struct completion done;
};
static void kthread_flush_work_fn(struct kthread_work *work)
{
struct kthread_flush_work *fwork =
container_of(work, struct kthread_flush_work, work);
complete(&fwork->done);
}
/**
* flush_kthread_worker - flush all current works on a kthread_worker
* @worker: worker to flush
*
* Wait until all currently executing or pending works on @worker are
* finished.
*/
void flush_kthread_worker(struct kthread_worker *worker)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
queue_kthread_work(worker, &fwork.work);
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(flush_kthread_worker);