linux/kernel/sched/stop_task.c

138 lines
2.9 KiB
C
Raw Normal View History

#include "sched.h"
/*
* stop-task scheduling class.
*
* The stop task is the highest priority task in the system, it preempts
* everything and will be preempted by nothing.
*
* See kernel/stop_machine.c
*/
#ifdef CONFIG_SMP
static int
select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* stop tasks as never migrate */
}
#endif /* CONFIG_SMP */
static void
check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
{
/* we're never preempted */
}
static struct task_struct *
pick_next_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *stop = rq->stop;
if (!stop || !task_on_rq_queued(stop))
return NULL;
sched: Fix hotplug task migration Dan Carpenter reported: > kernel/sched/rt.c:1347 pick_next_task_rt() warn: variable dereferenced before check 'prev' (see line 1338) > kernel/sched/deadline.c:1011 pick_next_task_dl() warn: variable dereferenced before check 'prev' (see line 1005) Kirill also spotted that migrate_tasks() will have an instant NULL deref because pick_next_task() will immediately deref prev. Instead of fixing all the corner cases because migrate_tasks() can pass in a NULL prev task in the unlikely case of hot-un-plug, provide a fake task such that we can remove all the NULL checks from the far more common paths. A further problem; not previously spotted; is that because we pushed pre_schedule() and idle_balance() into pick_next_task() we now need to avoid those getting called and pulling more tasks on our dying CPU. We avoid pull_{dl,rt}_task() by setting fake_task.prio to MAX_PRIO+1. We also note that since we call pick_next_task() exactly the amount of times we have runnable tasks present, we should never land in idle_balance(). Fixes: 38033c37faab ("sched: Push down pre_schedule() and idle_balance()") Cc: Juri Lelli <juri.lelli@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Reported-by: Kirill Tkhai <tkhai@yandex.ru> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140212094930.GB3545@laptop.programming.kicks-ass.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-02-12 09:49:30 +00:00
put_prev_task(rq, prev);
stop->se.exec_start = rq_clock_task(rq);
return stop;
}
static void
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
add_nr_running(rq, 1);
}
static void
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
sub_nr_running(rq, 1);
}
static void yield_task_stop(struct rq *rq)
{
BUG(); /* the stop task should never yield, its pointless. */
}
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;
delta_exec = rq_clock_task(rq) - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
curr->se.sum_exec_runtime += delta_exec;
account_group_exec_runtime(curr, delta_exec);
curr->se.exec_start = rq_clock_task(rq);
cpuacct_charge(curr, delta_exec);
}
static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
{
}
static void set_curr_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;
stop->se.exec_start = rq_clock_task(rq);
}
static void switched_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
}
static void
prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG(); /* how!?, what priority? */
}
static unsigned int
get_rr_interval_stop(struct rq *rq, struct task_struct *task)
{
return 0;
}
sched: Provide update_curr callbacks for stop/idle scheduling classes Chris bisected a NULL pointer deference in task_sched_runtime() to commit 6e998916dfe3 'sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency'. Chris observed crashes in atop or other /proc walking programs when he started fork bombs on his machine. He assumed that this is a new exit race, but that does not make any sense when looking at that commit. What's interesting is that, the commit provides update_curr callbacks for all scheduling classes except stop_task and idle_task. While nothing can ever hit that via the clock_nanosleep() and clock_gettime() interfaces, which have been the target of the commit in question, the author obviously forgot that there are other code paths which invoke task_sched_runtime() do_task_stat(() thread_group_cputime_adjusted() thread_group_cputime() task_cputime() task_sched_runtime() if (task_current(rq, p) && task_on_rq_queued(p)) { update_rq_clock(rq); up->sched_class->update_curr(rq); } If the stats are read for a stomp machine task, aka 'migration/N' and that task is current on its cpu, this will happily call the NULL pointer of stop_task->update_curr. Ooops. Chris observation that this happens faster when he runs the fork bomb makes sense as the fork bomb will kick migration threads more often so the probability to hit the issue will increase. Add the missing update_curr callbacks to the scheduler classes stop_task and idle_task. While idle tasks cannot be monitored via /proc we have other means to hit the idle case. Fixes: 6e998916dfe3 'sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency' Reported-by: Chris Mason <clm@fb.com> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-23 22:04:52 +00:00
static void update_curr_stop(struct rq *rq)
{
}
/*
* Simple, special scheduling class for the per-CPU stop tasks:
*/
const struct sched_class stop_sched_class = {
sched/deadline: Add SCHED_DEADLINE structures & implementation Introduces the data structures, constants and symbols needed for SCHED_DEADLINE implementation. Core data structure of SCHED_DEADLINE are defined, along with their initializers. Hooks for checking if a task belong to the new policy are also added where they are needed. Adds a scheduling class, in sched/dl.c and a new policy called SCHED_DEADLINE. It is an implementation of the Earliest Deadline First (EDF) scheduling algorithm, augmented with a mechanism (called Constant Bandwidth Server, CBS) that makes it possible to isolate the behaviour of tasks between each other. The typical -deadline task will be made up of a computation phase (instance) which is activated on a periodic or sporadic fashion. The expected (maximum) duration of such computation is called the task's runtime; the time interval by which each instance need to be completed is called the task's relative deadline. The task's absolute deadline is dynamically calculated as the time instant a task (better, an instance) activates plus the relative deadline. The EDF algorithms selects the task with the smallest absolute deadline as the one to be executed first, while the CBS ensures each task to run for at most its runtime every (relative) deadline length time interval, avoiding any interference between different tasks (bandwidth isolation). Thanks to this feature, also tasks that do not strictly comply with the computational model sketched above can effectively use the new policy. To summarize, this patch: - introduces the data structures, constants and symbols needed; - implements the core logic of the scheduling algorithm in the new scheduling class file; - provides all the glue code between the new scheduling class and the core scheduler and refines the interactions between sched/dl and the other existing scheduling classes. Signed-off-by: Dario Faggioli <raistlin@linux.it> Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com> Signed-off-by: Fabio Checconi <fchecconi@gmail.com> Signed-off-by: Juri Lelli <juri.lelli@gmail.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 10:14:43 +00:00
.next = &dl_sched_class,
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
.yield_task = yield_task_stop,
.check_preempt_curr = check_preempt_curr_stop,
.pick_next_task = pick_next_task_stop,
.put_prev_task = put_prev_task_stop,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_stop,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.set_curr_task = set_curr_task_stop,
.task_tick = task_tick_stop,
.get_rr_interval = get_rr_interval_stop,
.prio_changed = prio_changed_stop,
.switched_to = switched_to_stop,
sched: Provide update_curr callbacks for stop/idle scheduling classes Chris bisected a NULL pointer deference in task_sched_runtime() to commit 6e998916dfe3 'sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency'. Chris observed crashes in atop or other /proc walking programs when he started fork bombs on his machine. He assumed that this is a new exit race, but that does not make any sense when looking at that commit. What's interesting is that, the commit provides update_curr callbacks for all scheduling classes except stop_task and idle_task. While nothing can ever hit that via the clock_nanosleep() and clock_gettime() interfaces, which have been the target of the commit in question, the author obviously forgot that there are other code paths which invoke task_sched_runtime() do_task_stat(() thread_group_cputime_adjusted() thread_group_cputime() task_cputime() task_sched_runtime() if (task_current(rq, p) && task_on_rq_queued(p)) { update_rq_clock(rq); up->sched_class->update_curr(rq); } If the stats are read for a stomp machine task, aka 'migration/N' and that task is current on its cpu, this will happily call the NULL pointer of stop_task->update_curr. Ooops. Chris observation that this happens faster when he runs the fork bomb makes sense as the fork bomb will kick migration threads more often so the probability to hit the issue will increase. Add the missing update_curr callbacks to the scheduler classes stop_task and idle_task. While idle tasks cannot be monitored via /proc we have other means to hit the idle case. Fixes: 6e998916dfe3 'sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency' Reported-by: Chris Mason <clm@fb.com> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-11-23 22:04:52 +00:00
.update_curr = update_curr_stop,
};