2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-15 08:44:14 +08:00
linux-next/kernel/kthread.c

716 lines
19 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/export.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/freezer.h>
#include <linux/ptrace.h>
kthread: implement probe_kthread_data() One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. For example, after writeback is converted to use workqueue instead of priviate thread pool, there's no easy to tell which backing device a writeback work item was working on at the time of task dump, which, according to our writeback brethren, is important in tracking down issues with a lot of mounted file systems on a lot of different devices. This patchset implements a way for a work function to mark its execution instance so that task dump of the worker task includes information to indicate what the work item was doing. An example WARN dump would look like the following. WARNING: at fs/fs-writeback.c:1015 bdi_writeback_workfn+0x2b4/0x3c0() Modules linked in: CPU: 0 Pid: 28 Comm: kworker/u18:0 Not tainted 3.9.0-rc1-work+ #24 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 Workqueue: writeback bdi_writeback_workfn (flush-8:16) ffffffff820a3a98 ffff88015b927cb8 ffffffff81c61855 ffff88015b927cf8 ffffffff8108f500 0000000000000000 ffff88007a171948 ffff88007a1716b0 ffff88015b49df00 ffff88015b8d3940 0000000000000000 ffff88015b927d08 Call Trace: [<ffffffff81c61855>] dump_stack+0x19/0x1b [<ffffffff8108f500>] warn_slowpath_common+0x70/0xa0 ... This patch: Implement probe_kthread_data() which returns kthread_data if accessible. The function is equivalent to kthread_data() except that the specified @task may not be a kthread or its vfork_done is already cleared rendering struct kthread inaccessible. In the former case, probe_kthread_data() may return any value. In the latter, NULL. This will be used to safely print debug information without affecting synchronization in the normal paths. Workqueue debug info printing on dump_stack() and friends will make use of it. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:21 +08:00
#include <linux/uaccess.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 {
unsigned long flags;
unsigned int cpu;
void *data;
struct completion parked;
struct completion exited;
};
enum KTHREAD_BITS {
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
KTHREAD_IS_PARKED,
};
#define __to_kthread(vfork) \
container_of(vfork, struct kthread, exited)
static inline struct kthread *to_kthread(struct task_struct *k)
{
return __to_kthread(k->vfork_done);
}
static struct kthread *to_live_kthread(struct task_struct *k)
{
struct completion *vfork = ACCESS_ONCE(k->vfork_done);
if (likely(vfork) && try_get_task_stack(k))
return __to_kthread(vfork);
return NULL;
}
/**
* 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().
*/
bool kthread_should_stop(void)
{
return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
}
EXPORT_SYMBOL(kthread_should_stop);
/**
* kthread_should_park - should this kthread park now?
*
* When someone calls kthread_park() on your kthread, it will be woken
* and this will return true. You should then do the necessary
* cleanup and call kthread_parkme()
*
* Similar to kthread_should_stop(), but this keeps the thread alive
* and in a park position. kthread_unpark() "restarts" the thread and
* calls the thread function again.
*/
bool kthread_should_park(void)
{
return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
}
EXPORT_SYMBOL_GPL(kthread_should_park);
/**
* kthread_freezable_should_stop - should this freezable kthread return now?
* @was_frozen: optional out parameter, indicates whether %current was frozen
*
* kthread_should_stop() for freezable kthreads, which will enter
* refrigerator if necessary. This function is safe from kthread_stop() /
* freezer deadlock and freezable kthreads should use this function instead
* of calling try_to_freeze() directly.
*/
bool kthread_freezable_should_stop(bool *was_frozen)
{
bool frozen = false;
might_sleep();
if (unlikely(freezing(current)))
frozen = __refrigerator(true);
if (was_frozen)
*was_frozen = frozen;
return kthread_should_stop();
}
EXPORT_SYMBOL_GPL(kthread_freezable_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;
}
kthread: implement probe_kthread_data() One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. For example, after writeback is converted to use workqueue instead of priviate thread pool, there's no easy to tell which backing device a writeback work item was working on at the time of task dump, which, according to our writeback brethren, is important in tracking down issues with a lot of mounted file systems on a lot of different devices. This patchset implements a way for a work function to mark its execution instance so that task dump of the worker task includes information to indicate what the work item was doing. An example WARN dump would look like the following. WARNING: at fs/fs-writeback.c:1015 bdi_writeback_workfn+0x2b4/0x3c0() Modules linked in: CPU: 0 Pid: 28 Comm: kworker/u18:0 Not tainted 3.9.0-rc1-work+ #24 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 Workqueue: writeback bdi_writeback_workfn (flush-8:16) ffffffff820a3a98 ffff88015b927cb8 ffffffff81c61855 ffff88015b927cf8 ffffffff8108f500 0000000000000000 ffff88007a171948 ffff88007a1716b0 ffff88015b49df00 ffff88015b8d3940 0000000000000000 ffff88015b927d08 Call Trace: [<ffffffff81c61855>] dump_stack+0x19/0x1b [<ffffffff8108f500>] warn_slowpath_common+0x70/0xa0 ... This patch: Implement probe_kthread_data() which returns kthread_data if accessible. The function is equivalent to kthread_data() except that the specified @task may not be a kthread or its vfork_done is already cleared rendering struct kthread inaccessible. In the former case, probe_kthread_data() may return any value. In the latter, NULL. This will be used to safely print debug information without affecting synchronization in the normal paths. Workqueue debug info printing on dump_stack() and friends will make use of it. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:21 +08:00
/**
* kthread_probe_data - speculative version of kthread_data()
kthread: implement probe_kthread_data() One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. For example, after writeback is converted to use workqueue instead of priviate thread pool, there's no easy to tell which backing device a writeback work item was working on at the time of task dump, which, according to our writeback brethren, is important in tracking down issues with a lot of mounted file systems on a lot of different devices. This patchset implements a way for a work function to mark its execution instance so that task dump of the worker task includes information to indicate what the work item was doing. An example WARN dump would look like the following. WARNING: at fs/fs-writeback.c:1015 bdi_writeback_workfn+0x2b4/0x3c0() Modules linked in: CPU: 0 Pid: 28 Comm: kworker/u18:0 Not tainted 3.9.0-rc1-work+ #24 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 Workqueue: writeback bdi_writeback_workfn (flush-8:16) ffffffff820a3a98 ffff88015b927cb8 ffffffff81c61855 ffff88015b927cf8 ffffffff8108f500 0000000000000000 ffff88007a171948 ffff88007a1716b0 ffff88015b49df00 ffff88015b8d3940 0000000000000000 ffff88015b927d08 Call Trace: [<ffffffff81c61855>] dump_stack+0x19/0x1b [<ffffffff8108f500>] warn_slowpath_common+0x70/0xa0 ... This patch: Implement probe_kthread_data() which returns kthread_data if accessible. The function is equivalent to kthread_data() except that the specified @task may not be a kthread or its vfork_done is already cleared rendering struct kthread inaccessible. In the former case, probe_kthread_data() may return any value. In the latter, NULL. This will be used to safely print debug information without affecting synchronization in the normal paths. Workqueue debug info printing on dump_stack() and friends will make use of it. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:21 +08:00
* @task: possible kthread task in question
*
* @task could be a kthread task. Return the data value specified when it
* was created if accessible. If @task isn't a kthread task or its data is
* inaccessible for any reason, %NULL is returned. This function requires
* that @task itself is safe to dereference.
*/
void *kthread_probe_data(struct task_struct *task)
kthread: implement probe_kthread_data() One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. For example, after writeback is converted to use workqueue instead of priviate thread pool, there's no easy to tell which backing device a writeback work item was working on at the time of task dump, which, according to our writeback brethren, is important in tracking down issues with a lot of mounted file systems on a lot of different devices. This patchset implements a way for a work function to mark its execution instance so that task dump of the worker task includes information to indicate what the work item was doing. An example WARN dump would look like the following. WARNING: at fs/fs-writeback.c:1015 bdi_writeback_workfn+0x2b4/0x3c0() Modules linked in: CPU: 0 Pid: 28 Comm: kworker/u18:0 Not tainted 3.9.0-rc1-work+ #24 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 Workqueue: writeback bdi_writeback_workfn (flush-8:16) ffffffff820a3a98 ffff88015b927cb8 ffffffff81c61855 ffff88015b927cf8 ffffffff8108f500 0000000000000000 ffff88007a171948 ffff88007a1716b0 ffff88015b49df00 ffff88015b8d3940 0000000000000000 ffff88015b927d08 Call Trace: [<ffffffff81c61855>] dump_stack+0x19/0x1b [<ffffffff8108f500>] warn_slowpath_common+0x70/0xa0 ... This patch: Implement probe_kthread_data() which returns kthread_data if accessible. The function is equivalent to kthread_data() except that the specified @task may not be a kthread or its vfork_done is already cleared rendering struct kthread inaccessible. In the former case, probe_kthread_data() may return any value. In the latter, NULL. This will be used to safely print debug information without affecting synchronization in the normal paths. Workqueue debug info printing on dump_stack() and friends will make use of it. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:21 +08:00
{
struct kthread *kthread = to_kthread(task);
void *data = NULL;
probe_kernel_read(&data, &kthread->data, sizeof(data));
return data;
}
static void __kthread_parkme(struct kthread *self)
{
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
__set_current_state(TASK_PARKED);
while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
complete(&self->parked);
schedule();
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
__set_current_state(TASK_PARKED);
}
clear_bit(KTHREAD_IS_PARKED, &self->flags);
__set_current_state(TASK_RUNNING);
}
void kthread_parkme(void)
{
__kthread_parkme(to_kthread(current));
}
EXPORT_SYMBOL_GPL(kthread_parkme);
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 completion *done;
struct kthread self;
int ret;
self.flags = 0;
self.data = data;
init_completion(&self.exited);
init_completion(&self.parked);
current->vfork_done = &self.exited;
/* If user was SIGKILLed, I release the structure. */
done = xchg(&create->done, NULL);
if (!done) {
kfree(create);
do_exit(-EINTR);
}
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
complete(done);
schedule();
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
__kthread_parkme(&self);
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_NO_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
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) {
/* If user was SIGKILLed, I release the structure. */
struct completion *done = xchg(&create->done, NULL);
if (!done) {
kfree(create);
return;
}
create->result = ERR_PTR(pid);
complete(done);
}
}
/**
* kthread_create_on_node - create a kthread.
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @node: task and thread structures for the thread are allocated on this node
* @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(). The new thread has SCHED_NORMAL policy and
* is affine to all CPUs.
*
* 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 NUMA_NO_NODE.
* 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) or ERR_PTR(-EINTR).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
...)
{
DECLARE_COMPLETION_ONSTACK(done);
struct task_struct *task;
struct kthread_create_info *create = kmalloc(sizeof(*create),
GFP_KERNEL);
if (!create)
return ERR_PTR(-ENOMEM);
create->threadfn = threadfn;
create->data = data;
create->node = node;
create->done = &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);
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_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
/*
* Wait for completion in killable state, for I might be chosen by
* the OOM killer while kthreadd is trying to allocate memory for
* new kernel thread.
*/
if (unlikely(wait_for_completion_killable(&done))) {
/*
* If I was SIGKILLed before kthreadd (or new kernel thread)
* calls complete(), leave the cleanup of this structure to
* that thread.
*/
if (xchg(&create->done, NULL))
return ERR_PTR(-EINTR);
/*
* kthreadd (or new kernel thread) will call complete()
* shortly.
*/
wait_for_completion(&done);
}
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
va_list args;
va_start(args, namefmt);
vsnprintf(task->comm, sizeof(task->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(task, SCHED_NORMAL, &param);
set_cpus_allowed_ptr(task, cpu_all_mask);
}
kfree(create);
return task;
}
EXPORT_SYMBOL(kthread_create_on_node);
static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state)
{
unsigned long flags;
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
if (!wait_task_inactive(p, state)) {
WARN_ON(1);
return;
}
/* It's safe because the task is inactive. */
raw_spin_lock_irqsave(&p->pi_lock, flags);
do_set_cpus_allowed(p, mask);
p->flags |= PF_NO_SETAFFINITY;
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
{
__kthread_bind_mask(p, cpumask_of(cpu), state);
}
void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
{
__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
}
/**
* 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)
{
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(kthread_bind);
/**
* kthread_create_on_cpu - Create a cpu bound kthread
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @cpu: The cpu on which the thread should be bound,
* @namefmt: printf-style name for the thread. Format is restricted
* to "name.*%u". Code fills in cpu number.
*
* Description: This helper function creates and names a kernel thread
* The thread will be woken and put into park mode.
*/
struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
void *data, unsigned int cpu,
const char *namefmt)
{
struct task_struct *p;
p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
cpu);
if (IS_ERR(p))
return p;
set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
to_kthread(p)->cpu = cpu;
/* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
kthread_park(p);
return p;
}
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
{
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
* We clear the IS_PARKED bit here as we don't wait
* until the task has left the park code. So if we'd
* park before that happens we'd see the IS_PARKED bit
* which might be about to be cleared.
*/
if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
wake_up_state(k, TASK_PARKED);
}
}
/**
* kthread_unpark - unpark a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return false, wakes it, and
* waits for it to return. If the thread is marked percpu then its
* bound to the cpu again.
*/
void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_live_kthread(k);
if (kthread) {
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
__kthread_unpark(k, kthread);
put_task_stack(k);
}
}
EXPORT_SYMBOL_GPL(kthread_unpark);
/**
* kthread_park - park a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return true, wakes it, and
* waits for it to return. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will park without
* calling threadfn().
*
* Returns 0 if the thread is parked, -ENOSYS if the thread exited.
* If called by the kthread itself just the park bit is set.
*/
int kthread_park(struct task_struct *k)
{
struct kthread *kthread = to_live_kthread(k);
int ret = -ENOSYS;
if (kthread) {
if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
wait_for_completion(&kthread->parked);
}
}
put_task_stack(k);
ret = 0;
}
return ret;
}
EXPORT_SYMBOL_GPL(kthread_park);
/**
* 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_live_kthread(k);
if (kthread) {
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
__kthread_unpark(k, kthread);
wake_up_process(k);
wait_for_completion(&kthread->exited);
put_task_stack(k);
}
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_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;
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);
}
worker->current_work = work;
spin_unlock_irq(&worker->lock);
if (work) {
__set_current_state(TASK_RUNNING);
work->func(work);
} else if (!freezing(current))
schedule();
try_to_freeze();
goto repeat;
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
/* insert @work before @pos in @worker */
static void insert_kthread_work(struct kthread_worker *worker,
struct kthread_work *work,
struct list_head *pos)
{
lockdep_assert_held(&worker->lock);
list_add_tail(&work->node, pos);
work->worker = worker;
if (!worker->current_work && likely(worker->task))
wake_up_process(worker->task);
}
/**
* 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)) {
insert_kthread_work(worker, work, &worker->work_list);
ret = true;
}
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_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_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)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
struct kthread_worker *worker;
bool noop = false;
retry:
worker = work->worker;
if (!worker)
return;
spin_lock_irq(&worker->lock);
if (work->worker != worker) {
spin_unlock_irq(&worker->lock);
goto retry;
}
if (!list_empty(&work->node))
insert_kthread_work(worker, &fwork.work, work->node.next);
else if (worker->current_work == work)
insert_kthread_work(worker, &fwork.work, worker->work_list.next);
else
noop = true;
spin_unlock_irq(&worker->lock);
if (!noop)
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(flush_kthread_work);
/**
* 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);