mkdir $ARGV[0],0777;
$state = 0;
while (<STDIN>) {
- if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) {
+ if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
if ($state == 1) { close OUT }
$state = 1;
- $fn = "$ARGV[0]/$1.4";
+ $fn = "$ARGV[0]/$1.9";
print STDERR "Creating $fn\n";
open OUT, ">$fn" or die "can't open $fn: $!\n";
print OUT $_;
+ =============
+ CFS Scheduler
+ =============
-This is the CFS scheduler.
-
-80% of CFS's design can be summed up in a single sentence: CFS basically
-models an "ideal, precise multi-tasking CPU" on real hardware.
-
-"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100%
-physical power and which can run each task at precise equal speed, in
-parallel, each at 1/nr_running speed. For example: if there are 2 tasks
-running then it runs each at 50% physical power - totally in parallel.
-
-On real hardware, we can run only a single task at once, so while that
-one task runs, the other tasks that are waiting for the CPU are at a
-disadvantage - the current task gets an unfair amount of CPU time. In
-CFS this fairness imbalance is expressed and tracked via the per-task
-p->wait_runtime (nanosec-unit) value. "wait_runtime" is the amount of
-time the task should now run on the CPU for it to become completely fair
-and balanced.
-
-( small detail: on 'ideal' hardware, the p->wait_runtime value would
- always be zero - no task would ever get 'out of balance' from the
- 'ideal' share of CPU time. )
-
-CFS's task picking logic is based on this p->wait_runtime value and it
-is thus very simple: it always tries to run the task with the largest
-p->wait_runtime value. In other words, CFS tries to run the task with
-the 'gravest need' for more CPU time. So CFS always tries to split up
-CPU time between runnable tasks as close to 'ideal multitasking
-hardware' as possible.
-
-Most of the rest of CFS's design just falls out of this really simple
-concept, with a few add-on embellishments like nice levels,
-multiprocessing and various algorithm variants to recognize sleepers.
-
-In practice it works like this: the system runs a task a bit, and when
-the task schedules (or a scheduler tick happens) the task's CPU usage is
-'accounted for': the (small) time it just spent using the physical CPU
-is deducted from p->wait_runtime. [minus the 'fair share' it would have
-gotten anyway]. Once p->wait_runtime gets low enough so that another
-task becomes the 'leftmost task' of the time-ordered rbtree it maintains
-(plus a small amount of 'granularity' distance relative to the leftmost
-task so that we do not over-schedule tasks and trash the cache) then the
-new leftmost task is picked and the current task is preempted.
-
-The rq->fair_clock value tracks the 'CPU time a runnable task would have
-fairly gotten, had it been runnable during that time'. So by using
-rq->fair_clock values we can accurately timestamp and measure the
-'expected CPU time' a task should have gotten. All runnable tasks are
-sorted in the rbtree by the "rq->fair_clock - p->wait_runtime" key, and
-CFS picks the 'leftmost' task and sticks to it. As the system progresses
-forwards, newly woken tasks are put into the tree more and more to the
-right - slowly but surely giving a chance for every task to become the
-'leftmost task' and thus get on the CPU within a deterministic amount of
-time.
-
-Some implementation details:
-
- - the introduction of Scheduling Classes: an extensible hierarchy of
- scheduler modules. These modules encapsulate scheduling policy
- details and are handled by the scheduler core without the core
- code assuming about them too much.
-
- - sched_fair.c implements the 'CFS desktop scheduler': it is a
- replacement for the vanilla scheduler's SCHED_OTHER interactivity
- code.
-
- I'd like to give credit to Con Kolivas for the general approach here:
- he has proven via RSDL/SD that 'fair scheduling' is possible and that
- it results in better desktop scheduling. Kudos Con!
-
- The CFS patch uses a completely different approach and implementation
- from RSDL/SD. My goal was to make CFS's interactivity quality exceed
- that of RSDL/SD, which is a high standard to meet :-) Testing
- feedback is welcome to decide this one way or another. [ and, in any
- case, all of SD's logic could be added via a kernel/sched_sd.c module
- as well, if Con is interested in such an approach. ]
-
- CFS's design is quite radical: it does not use runqueues, it uses a
- time-ordered rbtree to build a 'timeline' of future task execution,
- and thus has no 'array switch' artifacts (by which both the vanilla
- scheduler and RSDL/SD are affected).
-
- CFS uses nanosecond granularity accounting and does not rely on any
- jiffies or other HZ detail. Thus the CFS scheduler has no notion of
- 'timeslices' and has no heuristics whatsoever. There is only one
- central tunable (you have to switch on CONFIG_SCHED_DEBUG):
-
- /proc/sys/kernel/sched_granularity_ns
-
- which can be used to tune the scheduler from 'desktop' (low
- latencies) to 'server' (good batching) workloads. It defaults to a
- setting suitable for desktop workloads. SCHED_BATCH is handled by the
- CFS scheduler module too.
-
- Due to its design, the CFS scheduler is not prone to any of the
- 'attacks' that exist today against the heuristics of the stock
- scheduler: fiftyp.c, thud.c, chew.c, ring-test.c, massive_intr.c all
- work fine and do not impact interactivity and produce the expected
- behavior.
-
- the CFS scheduler has a much stronger handling of nice levels and
- SCHED_BATCH: both types of workloads should be isolated much more
- agressively than under the vanilla scheduler.
-
- ( another detail: due to nanosec accounting and timeline sorting,
- sched_yield() support is very simple under CFS, and in fact under
- CFS sched_yield() behaves much better than under any other
- scheduler i have tested so far. )
-
- - sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler
- way than the vanilla scheduler does. It uses 100 runqueues (for all
- 100 RT priority levels, instead of 140 in the vanilla scheduler)
- and it needs no expired array.
-
- - reworked/sanitized SMP load-balancing: the runqueue-walking
- assumptions are gone from the load-balancing code now, and
- iterators of the scheduling modules are used. The balancing code got
- quite a bit simpler as a result.
-
-
-Group scheduler extension to CFS
-================================
-
-Normally the scheduler operates on individual tasks and strives to provide
-fair CPU time to each task. Sometimes, it may be desirable to group tasks
-and provide fair CPU time to each such task group. For example, it may
-be desirable to first provide fair CPU time to each user on the system
-and then to each task belonging to a user.
-
-CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets
-SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such
-groups. At present, there are two (mutually exclusive) mechanisms to group
-tasks for CPU bandwidth control purpose:
-
- - Based on user id (CONFIG_FAIR_USER_SCHED)
- In this option, tasks are grouped according to their user id.
- - Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED)
- This options lets the administrator create arbitrary groups
- of tasks, using the "cgroup" pseudo filesystem. See
- Documentation/cgroups.txt for more information about this
- filesystem.
-Only one of these options to group tasks can be chosen and not both.
+1. OVERVIEW
+
+CFS stands for "Completely Fair Scheduler," and is the new "desktop" process
+scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the
+replacement for the previous vanilla scheduler's SCHED_OTHER interactivity
+code.
+
+80% of CFS's design can be summed up in a single sentence: CFS basically models
+an "ideal, precise multi-tasking CPU" on real hardware.
+
+"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical
+power and which can run each task at precise equal speed, in parallel, each at
+1/nr_running speed. For example: if there are 2 tasks running, then it runs
+each at 50% physical power --- i.e., actually in parallel.
+
+On real hardware, we can run only a single task at once, so we have to
+introduce the concept of "virtual runtime." The virtual runtime of a task
+specifies when its next timeslice would start execution on the ideal
+multi-tasking CPU described above. In practice, the virtual runtime of a task
+is its actual runtime normalized to the total number of running tasks.
+
+
+
+2. FEW IMPLEMENTATION DETAILS
+
+In CFS the virtual runtime is expressed and tracked via the per-task
+p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately
+timestamp and measure the "expected CPU time" a task should have gotten.
+
+[ small detail: on "ideal" hardware, at any time all tasks would have the same
+ p->se.vruntime value --- i.e., tasks would execute simultaneously and no task
+ would ever get "out of balance" from the "ideal" share of CPU time. ]
+
+CFS's task picking logic is based on this p->se.vruntime value and it is thus
+very simple: it always tries to run the task with the smallest p->se.vruntime
+value (i.e., the task which executed least so far). CFS always tries to split
+up CPU time between runnable tasks as close to "ideal multitasking hardware" as
+possible.
+
+Most of the rest of CFS's design just falls out of this really simple concept,
+with a few add-on embellishments like nice levels, multiprocessing and various
+algorithm variants to recognize sleepers.
+
+
+
+3. THE RBTREE
+
+CFS's design is quite radical: it does not use the old data structures for the
+runqueues, but it uses a time-ordered rbtree to build a "timeline" of future
+task execution, and thus has no "array switch" artifacts (by which both the
+previous vanilla scheduler and RSDL/SD are affected).
+
+CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic
+increasing value tracking the smallest vruntime among all tasks in the
+runqueue. The total amount of work done by the system is tracked using
+min_vruntime; that value is used to place newly activated entities on the left
+side of the tree as much as possible.
+
+The total number of running tasks in the runqueue is accounted through the
+rq->cfs.load value, which is the sum of the weights of the tasks queued on the
+runqueue.
+
+CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
+p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
+account for possible wraparounds). CFS picks the "leftmost" task from this
+tree and sticks to it.
+As the system progresses forwards, the executed tasks are put into the tree
+more and more to the right --- slowly but surely giving a chance for every task
+to become the "leftmost task" and thus get on the CPU within a deterministic
+amount of time.
+
+Summing up, CFS works like this: it runs a task a bit, and when the task
+schedules (or a scheduler tick happens) the task's CPU usage is "accounted
+for": the (small) time it just spent using the physical CPU is added to
+p->se.vruntime. Once p->se.vruntime gets high enough so that another task
+becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a
+small amount of "granularity" distance relative to the leftmost task so that we
+do not over-schedule tasks and trash the cache), then the new leftmost task is
+picked and the current task is preempted.
+
+
+
+4. SOME FEATURES OF CFS
+
+CFS uses nanosecond granularity accounting and does not rely on any jiffies or
+other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the
+way the previous scheduler had, and has no heuristics whatsoever. There is
+only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
+
+ /proc/sys/kernel/sched_granularity_ns
+
+which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
+"server" (i.e., good batching) workloads. It defaults to a setting suitable
+for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too.
+
+Due to its design, the CFS scheduler is not prone to any of the "attacks" that
+exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c,
+chew.c, ring-test.c, massive_intr.c all work fine and do not impact
+interactivity and produce the expected behavior.
+
+The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH
+than the previous vanilla scheduler: both types of workloads are isolated much
+more aggressively.
+
+SMP load-balancing has been reworked/sanitized: the runqueue-walking
+assumptions are gone from the load-balancing code now, and iterators of the
+scheduling modules are used. The balancing code got quite a bit simpler as a
+result.
+
+
+
+5. Scheduling policies
+
+CFS implements three scheduling policies:
+
+ - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
+ policy that is used for regular tasks.
+
+ - SCHED_BATCH: Does not preempt nearly as often as regular tasks
+ would, thereby allowing tasks to run longer and make better use of
+ caches but at the cost of interactivity. This is well suited for
+ batch jobs.
+
+ - SCHED_IDLE: This is even weaker than nice 19, but its not a true
+ idle timer scheduler in order to avoid to get into priority
+ inversion problems which would deadlock the machine.
+
+SCHED_FIFO/_RR are implemented in sched_rt.c and are as specified by
+POSIX.
+
+The command chrt from util-linux-ng 2.13.1.1 can set all of these except
+SCHED_IDLE.
-Group scheduler tunables:
-When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for
-each new user and a "cpu_share" file is added in that directory.
+
+6. SCHEDULING CLASSES
+
+The new CFS scheduler has been designed in such a way to introduce "Scheduling
+Classes," an extensible hierarchy of scheduler modules. These modules
+encapsulate scheduling policy details and are handled by the scheduler core
+without the core code assuming too much about them.
+
+sched_fair.c implements the CFS scheduler described above.
+
+sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than
+the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT
+priority levels, instead of 140 in the previous scheduler) and it needs no
+expired array.
+
+Scheduling classes are implemented through the sched_class structure, which
+contains hooks to functions that must be called whenever an interesting event
+occurs.
+
+This is the (partial) list of the hooks:
+
+ - enqueue_task(...)
+
+ Called when a task enters a runnable state.
+ It puts the scheduling entity (task) into the red-black tree and
+ increments the nr_running variable.
+
+ - dequeue_tree(...)
+
+ When a task is no longer runnable, this function is called to keep the
+ corresponding scheduling entity out of the red-black tree. It decrements
+ the nr_running variable.
+
+ - yield_task(...)
+
+ This function is basically just a dequeue followed by an enqueue, unless the
+ compat_yield sysctl is turned on; in that case, it places the scheduling
+ entity at the right-most end of the red-black tree.
+
+ - check_preempt_curr(...)
+
+ This function checks if a task that entered the runnable state should
+ preempt the currently running task.
+
+ - pick_next_task(...)
+
+ This function chooses the most appropriate task eligible to run next.
+
+ - set_curr_task(...)
+
+ This function is called when a task changes its scheduling class or changes
+ its task group.
+
+ - task_tick(...)
+
+ This function is mostly called from time tick functions; it might lead to
+ process switch. This drives the running preemption.
+
+ - task_new(...)
+
+ The core scheduler gives the scheduling module an opportunity to manage new
+ task startup. The CFS scheduling module uses it for group scheduling, while
+ the scheduling module for a real-time task does not use it.
+
+
+
+7. GROUP SCHEDULER EXTENSIONS TO CFS
+
+Normally, the scheduler operates on individual tasks and strives to provide
+fair CPU time to each task. Sometimes, it may be desirable to group tasks and
+provide fair CPU time to each such task group. For example, it may be
+desirable to first provide fair CPU time to each user on the system and then to
+each task belonging to a user.
+
+CONFIG_GROUP_SCHED strives to achieve exactly that. It lets tasks to be
+grouped and divides CPU time fairly among such groups.
+
+CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
+SCHED_RR) tasks.
+
+CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
+SCHED_BATCH) tasks.
+
+At present, there are two (mutually exclusive) mechanisms to group tasks for
+CPU bandwidth control purposes:
+
+ - Based on user id (CONFIG_USER_SCHED)
+
+ With this option, tasks are grouped according to their user id.
+
+ - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
+
+ This options needs CONFIG_CGROUPS to be defined, and lets the administrator
+ create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See
+ Documentation/cgroups.txt for more information about this filesystem.
+
+Only one of these options to group tasks can be chosen and not both.
+
+When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
+user and a "cpu_share" file is added in that directory.
# cd /sys/kernel/uids
# cat 512/cpu_share # Display user 512's CPU share
2048
#
-CPU bandwidth between two users are divided in the ratio of their CPU shares.
-For ex: if you would like user "root" to get twice the bandwidth of user
-"guest", then set the cpu_share for both the users such that "root"'s
-cpu_share is twice "guest"'s cpu_share
-
+CPU bandwidth between two users is divided in the ratio of their CPU shares.
+For example: if you would like user "root" to get twice the bandwidth of user
+"guest," then set the cpu_share for both the users such that "root"'s cpu_share
+is twice "guest"'s cpu_share.
-When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created
-for each group created using the pseudo filesystem. See example steps
-below to create task groups and modify their CPU share using the "cgroups"
-pseudo filesystem
+When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
+group created using the pseudo filesystem. See example steps below to create
+task groups and modify their CPU share using the "cgroups" pseudo filesystem.
# mkdir /dev/cpuctl
# mount -t cgroup -ocpu none /dev/cpuctl
#include <linux/wait.h>
+/**
+ * struct completion - structure used to maintain state for a "completion"
+ *
+ * This is the opaque structure used to maintain the state for a "completion".
+ * Completions currently use a FIFO to queue threads that have to wait for
+ * the "completion" event.
+ *
+ * See also: complete(), wait_for_completion() (and friends _timeout,
+ * _interruptible, _interruptible_timeout, and _killable), init_completion(),
+ * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and
+ * INIT_COMPLETION().
+ */
struct completion {
unsigned int done;
wait_queue_head_t wait;
#define COMPLETION_INITIALIZER_ONSTACK(work) \
({ init_completion(&work); work; })
+/**
+ * DECLARE_COMPLETION: - declare and initialize a completion structure
+ * @work: identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure. Generally used
+ * for static declarations. You should use the _ONSTACK variant for automatic
+ * variables.
+ */
#define DECLARE_COMPLETION(work) \
struct completion work = COMPLETION_INITIALIZER(work)
* completions - so we use the _ONSTACK() variant for those that
* are on the kernel stack:
*/
+/**
+ * DECLARE_COMPLETION_ONSTACK: - declare and initialize a completion structure
+ * @work: identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure on the kernel
+ * stack.
+ */
#ifdef CONFIG_LOCKDEP
# define DECLARE_COMPLETION_ONSTACK(work) \
struct completion work = COMPLETION_INITIALIZER_ONSTACK(work)
# define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work)
#endif
+/**
+ * init_completion: - Initialize a dynamically allocated completion
+ * @x: completion structure that is to be initialized
+ *
+ * This inline function will initialize a dynamically created completion
+ * structure.
+ */
static inline void init_completion(struct completion *x)
{
x->done = 0;
extern void complete(struct completion *);
extern void complete_all(struct completion *);
+/**
+ * INIT_COMPLETION: - reinitialize a completion structure
+ * @x: completion structure to be reinitialized
+ *
+ * This macro should be used to reinitialize a completion structure so it can
+ * be reused. This is especially important after complete_all() is used.
+ */
#define INIT_COMPLETION(x) ((x).done = 0)
* snapshot of the last seen global state
* and a lock protecting this state
*/
- int shift;
unsigned long period;
+ int shift;
spinlock_t lock; /* protect the snapshot state */
};
* - everyone except group_exit_task is stopped during signal delivery
* of fatal signals, group_exit_task processes the signal.
*/
- struct task_struct *group_exit_task;
int notify_count;
+ struct task_struct *group_exit_task;
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
void (*yield_task) (struct rq *rq);
int (*select_task_rq)(struct task_struct *p, int sync);
- void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
+ void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
struct sched_rt_entity {
struct list_head run_list;
- unsigned int time_slice;
unsigned long timeout;
+ unsigned int time_slice;
int nr_cpus_allowed;
struct sched_rt_entity *back;
struct take_cpu_down_param *param = _param;
int err;
- raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
- param->hcpu);
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
if (err < 0)
return err;
+ raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+ param->hcpu);
+
/* Force idle task to run as soon as we yield: it should
immediately notice cpu is offline and die quickly. */
sched_idle_next();
rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
}
+static inline int rt_bandwidth_enabled(void)
+{
+ return sysctl_sched_rt_runtime >= 0;
+}
+
static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
ktime_t now;
- if (rt_b->rt_runtime == RUNTIME_INF)
+ if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
return;
if (hrtimer_active(&rt_b->rt_period_timer))
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
#endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_FAIR_GROUP_SCHED */
+#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+#endif /* CONFIG_USER_SCHED */
/* task_group_lock serializes add/remove of task groups and also changes to
* a task group's cpu shares.
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
+static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
{
- rq->curr->sched_class->check_preempt_curr(rq, p);
+ rq->curr->sched_class->check_preempt_curr(rq, p, sync);
}
static inline int cpu_of(struct rq *rq)
hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
}
-static void init_hrtick(void)
+static inline void init_hrtick(void)
{
}
#endif /* CONFIG_SMP */
rq->hrtick_timer.function = hrtick;
rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
}
-#else
+#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
{
}
static inline void init_hrtick(void)
{
}
-#endif
+#endif /* CONFIG_SCHED_HRTICK */
/*
* resched_task - mark a task 'to be rescheduled now'.
update_load_sub(&rq->load, load);
}
-#ifdef CONFIG_SMP
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
-static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
-
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
- struct rq *rq = cpu_rq(cpu);
-
- if (rq->nr_running)
- rq->avg_load_per_task = rq->load.weight / rq->nr_running;
-
- return rq->avg_load_per_task;
-}
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);
+#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
+typedef int (*tg_visitor)(struct task_group *, void *);
/*
* Iterate the full tree, calling @down when first entering a node and @up when
* leaving it for the final time.
*/
-static void
-walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd)
+static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
struct task_group *parent, *child;
+ int ret;
rcu_read_lock();
parent = &root_task_group;
down:
- (*down)(parent, cpu, sd);
+ ret = (*down)(parent, data);
+ if (ret)
+ goto out_unlock;
list_for_each_entry_rcu(child, &parent->children, siblings) {
parent = child;
goto down;
up:
continue;
}
- (*up)(parent, cpu, sd);
+ ret = (*up)(parent, data);
+ if (ret)
+ goto out_unlock;
child = parent;
parent = parent->parent;
if (parent)
goto up;
+out_unlock:
rcu_read_unlock();
+
+ return ret;
}
+static int tg_nop(struct task_group *tg, void *data)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+
+static unsigned long cpu_avg_load_per_task(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ if (rq->nr_running)
+ rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+
+ return rq->avg_load_per_task;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
/*
* This needs to be done in a bottom-up fashion because the rq weight of a
* parent group depends on the shares of its child groups.
*/
-static void
-tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_shares_up(struct task_group *tg, void *data)
{
unsigned long rq_weight = 0;
unsigned long shares = 0;
+ struct sched_domain *sd = data;
int i;
for_each_cpu_mask(i, sd->span) {
__update_group_shares_cpu(tg, i, shares, rq_weight);
spin_unlock_irqrestore(&rq->lock, flags);
}
+
+ return 0;
}
/*
* This needs to be done in a top-down fashion because the load of a child
* group is a fraction of its parents load.
*/
-static void
-tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_load_down(struct task_group *tg, void *data)
{
unsigned long load;
+ long cpu = (long)data;
if (!tg->parent) {
load = cpu_rq(cpu)->load.weight;
}
tg->cfs_rq[cpu]->h_load = load;
-}
-static void
-tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
-{
+ return 0;
}
static void update_shares(struct sched_domain *sd)
if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
sd->last_update = now;
- walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
+ walk_tg_tree(tg_nop, tg_shares_up, sd);
}
}
spin_lock(&rq->lock);
}
-static void update_h_load(int cpu)
+static void update_h_load(long cpu)
{
- walk_tg_tree(tg_load_down, tg_nop, cpu, NULL);
+ walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}
#else
running = task_running(rq, p);
on_rq = p->se.on_rq;
ncsw = 0;
- if (!match_state || p->state == match_state) {
- ncsw = p->nivcsw + p->nvcsw;
- if (unlikely(!ncsw))
- ncsw = 1;
- }
+ if (!match_state || p->state == match_state)
+ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
task_rq_unlock(rq, &flags);
/*
trace_mark(kernel_sched_wakeup,
"pid %d state %ld ## rq %p task %p rq->curr %p",
p->pid, p->state, rq, p, rq->curr);
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, sync);
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
trace_mark(kernel_sched_wakeup_new,
"pid %d state %ld ## rq %p task %p rq->curr %p",
p->pid, p->state, rq, p, rq->curr);
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
p->sched_class->task_wake_up(rq, p);
* Note that idle threads have a prio of MAX_PRIO, for this test
* to be always true for them.
*/
- check_preempt_curr(this_rq, p);
+ check_preempt_curr(this_rq, p, 0);
}
/*
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x: holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ */
void complete(struct completion *x)
{
unsigned long flags;
}
EXPORT_SYMBOL(complete);
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x: holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ */
void complete_all(struct completion *x)
{
unsigned long flags;
wait.flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_tail(&x->wait, &wait);
do {
- if ((state == TASK_INTERRUPTIBLE &&
- signal_pending(current)) ||
- (state == TASK_KILLABLE &&
- fatal_signal_pending(current))) {
+ if (signal_pending_state(state, current)) {
timeout = -ERESTARTSYS;
break;
}
return timeout;
}
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
void __sched wait_for_completion(struct completion *x)
{
wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion);
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ */
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
}
EXPORT_SYMBOL(wait_for_completion_timeout);
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x: holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ */
int __sched wait_for_completion_interruptible(struct completion *x)
{
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_interruptible);
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ */
unsigned long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
unsigned long timeout)
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ */
int __sched wait_for_completion_killable(struct completion *x)
{
long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
* Do not allow realtime tasks into groups that have no runtime
* assigned.
*/
- if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+ if (rt_bandwidth_enabled() && rt_policy(policy) &&
+ task_group(p)->rt_bandwidth.rt_runtime == 0)
return -EPERM;
#endif
set_task_cpu(p, dest_cpu);
if (on_rq) {
activate_task(rq_dest, p, 0);
- check_preempt_curr(rq_dest, p);
+ check_preempt_curr(rq_dest, p, 0);
}
done:
ret = 1;
#ifdef in_atomic
static unsigned long prev_jiffy; /* ratelimiting */
- if ((in_atomic() || irqs_disabled()) &&
- system_state == SYSTEM_RUNNING && !oops_in_progress) {
- if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
- return;
- prev_jiffy = jiffies;
- printk(KERN_ERR "BUG: sleeping function called from invalid"
- " context at %s:%d\n", file, line);
- printk("in_atomic():%d, irqs_disabled():%d\n",
- in_atomic(), irqs_disabled());
- debug_show_held_locks(current);
- if (irqs_disabled())
- print_irqtrace_events(current);
- dump_stack();
- }
+ if ((!in_atomic() && !irqs_disabled()) ||
+ system_state != SYSTEM_RUNNING || oops_in_progress)
+ return;
+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+ return;
+ prev_jiffy = jiffies;
+
+ printk(KERN_ERR
+ "BUG: sleeping function called from invalid context at %s:%d\n",
+ file, line);
+ printk(KERN_ERR
+ "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+ in_atomic(), irqs_disabled(),
+ current->pid, current->comm);
+
+ debug_show_held_locks(current);
+ if (irqs_disabled())
+ print_irqtrace_events(current);
+ dump_stack();
#endif
}
EXPORT_SYMBOL(__might_sleep);
static unsigned long to_ratio(u64 period, u64 runtime)
{
if (runtime == RUNTIME_INF)
- return 1ULL << 16;
+ return 1ULL << 20;
- return div64_u64(runtime << 16, period);
+ return div64_u64(runtime << 20, period);
}
-#ifdef CONFIG_CGROUP_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
{
- struct task_group *tgi, *parent = tg->parent;
- unsigned long total = 0;
+ struct task_struct *g, *p;
- if (!parent) {
- if (global_rt_period() < period)
- return 0;
+ do_each_thread(g, p) {
+ if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+ return 1;
+ } while_each_thread(g, p);
- return to_ratio(period, runtime) <
- to_ratio(global_rt_period(), global_rt_runtime());
- }
+ return 0;
+}
- if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period)
- return 0;
+struct rt_schedulable_data {
+ struct task_group *tg;
+ u64 rt_period;
+ u64 rt_runtime;
+};
- rcu_read_lock();
- list_for_each_entry_rcu(tgi, &parent->children, siblings) {
- if (tgi == tg)
- continue;
+static int tg_schedulable(struct task_group *tg, void *data)
+{
+ struct rt_schedulable_data *d = data;
+ struct task_group *child;
+ unsigned long total, sum = 0;
+ u64 period, runtime;
- total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
- tgi->rt_bandwidth.rt_runtime);
+ period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+ runtime = tg->rt_bandwidth.rt_runtime;
+
+ if (tg == d->tg) {
+ period = d->rt_period;
+ runtime = d->rt_runtime;
}
- rcu_read_unlock();
- return total + to_ratio(period, runtime) <=
- to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
- parent->rt_bandwidth.rt_runtime);
-}
-#elif defined CONFIG_USER_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
- struct task_group *tgi;
- unsigned long total = 0;
- unsigned long global_ratio =
- to_ratio(global_rt_period(), global_rt_runtime());
+ if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+ return -EBUSY;
- rcu_read_lock();
- list_for_each_entry_rcu(tgi, &task_groups, list) {
- if (tgi == tg)
- continue;
+ total = to_ratio(period, runtime);
+
+ list_for_each_entry_rcu(child, &tg->children, siblings) {
+ period = ktime_to_ns(child->rt_bandwidth.rt_period);
+ runtime = child->rt_bandwidth.rt_runtime;
- total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
- tgi->rt_bandwidth.rt_runtime);
+ if (child == d->tg) {
+ period = d->rt_period;
+ runtime = d->rt_runtime;
+ }
+
+ sum += to_ratio(period, runtime);
}
- rcu_read_unlock();
- return total + to_ratio(period, runtime) < global_ratio;
+ if (sum > total)
+ return -EINVAL;
+
+ return 0;
}
-#endif
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
- struct task_struct *g, *p;
- do_each_thread(g, p) {
- if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
- return 1;
- } while_each_thread(g, p);
- return 0;
+ struct rt_schedulable_data data = {
+ .tg = tg,
+ .rt_period = period,
+ .rt_runtime = runtime,
+ };
+
+ return walk_tg_tree(tg_schedulable, tg_nop, &data);
}
static int tg_set_bandwidth(struct task_group *tg,
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
- if (rt_runtime == 0 && tg_has_rt_tasks(tg)) {
- err = -EBUSY;
- goto unlock;
- }
- if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
- err = -EINVAL;
+ err = __rt_schedulable(tg, rt_period, rt_runtime);
+ if (err)
goto unlock;
- }
spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
rt_runtime = tg->rt_bandwidth.rt_runtime;
mutex_lock(&rt_constraints_mutex);
- if (!__rt_schedulable(tg, rt_period, rt_runtime))
- ret = -EINVAL;
+ read_lock(&tasklist_lock);
+ ret = __rt_schedulable(tg, rt_period, rt_runtime);
+ read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
return ret;
return __sched_period(nr_running);
}
-/*
- * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
- * that it favours >=0 over <0.
- *
- * -20 |
- * |
- * 0 --------+-------
- * .'
- * 19 .'
- *
- */
-static unsigned long
-calc_delta_asym(unsigned long delta, struct sched_entity *se)
-{
- struct load_weight lw = {
- .weight = NICE_0_LOAD,
- .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
- };
-
- for_each_sched_entity(se) {
- struct load_weight *se_lw = &se->load;
- unsigned long rw = cfs_rq_of(se)->load.weight;
-
-#ifdef CONFIG_FAIR_SCHED_GROUP
- struct cfs_rq *cfs_rq = se->my_q;
- struct task_group *tg = NULL
-
- if (cfs_rq)
- tg = cfs_rq->tg;
-
- if (tg && tg->shares < NICE_0_LOAD) {
- /*
- * scale shares to what it would have been had
- * tg->weight been NICE_0_LOAD:
- *
- * weight = 1024 * shares / tg->weight
- */
- lw.weight *= se->load.weight;
- lw.weight /= tg->shares;
-
- lw.inv_weight = 0;
-
- se_lw = &lw;
- rw += lw.weight - se->load.weight;
- } else
-#endif
-
- if (se->load.weight < NICE_0_LOAD) {
- se_lw = &lw;
- rw += NICE_0_LOAD - se->load.weight;
- }
-
- delta = calc_delta_mine(delta, rw, se_lw);
- }
-
- return delta;
-}
-
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
* + nice tasks.
*/
if (sched_feat(ASYM_GRAN))
- gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
- else
- gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+ gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
return gran;
}
-/*
- * Should 'se' preempt 'curr'.
- *
- * |s1
- * |s2
- * |s3
- * g
- * |<--->|c
- *
- * w(c, s1) = -1
- * w(c, s2) = 0
- * w(c, s3) = 1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
- s64 gran, vdiff = curr->vruntime - se->vruntime;
-
- if (vdiff < 0)
- return -1;
-
- gran = wakeup_gran(curr);
- if (vdiff > gran)
- return 1;
-
- return 0;
-}
-
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
- int depth = 0;
-
- for_each_sched_entity(se)
- depth++;
-
- return depth;
-}
-
/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
{
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
- int se_depth, pse_depth;
+ s64 delta_exec;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
if (unlikely(se == pse))
return;
+ /*
+ * We can come here with TIF_NEED_RESCHED already set from new task
+ * wake up path.
+ */
+ if (test_tsk_need_resched(curr))
+ return;
+
cfs_rq_of(pse)->next = pse;
/*
if (!sched_feat(WAKEUP_PREEMPT))
return;
- /*
- * preemption test can be made between sibling entities who are in the
- * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
- * both tasks until we find their ancestors who are siblings of common
- * parent.
- */
-
- /* First walk up until both entities are at same depth */
- se_depth = depth_se(se);
- pse_depth = depth_se(pse);
-
- while (se_depth > pse_depth) {
- se_depth--;
- se = parent_entity(se);
- }
-
- while (pse_depth > se_depth) {
- pse_depth--;
- pse = parent_entity(pse);
- }
-
- while (!is_same_group(se, pse)) {
- se = parent_entity(se);
- pse = parent_entity(pse);
+ if (sched_feat(WAKEUP_OVERLAP) && sync &&
+ se->avg_overlap < sysctl_sched_migration_cost &&
+ pse->avg_overlap < sysctl_sched_migration_cost) {
+ resched_task(curr);
+ return;
}
- if (wakeup_preempt_entity(se, pse) == 1)
+ delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+ if (delta_exec > wakeup_gran(pse))
resched_task(curr);
}
next = next->next;
} while (next != &cfs_rq->tasks && !entity_is_task(se));
- if (next == &cfs_rq->tasks)
+ if (next == &cfs_rq->tasks && !entity_is_task(se))
return NULL;
cfs_rq->balance_iterator = next;
rcu_read_lock();
update_h_load(busiest_cpu);
- list_for_each_entry(tg, &task_groups, list) {
+ list_for_each_entry_rcu(tg, &task_groups, list) {
struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
unsigned long busiest_h_load = busiest_cfs_rq->h_load;
unsigned long busiest_weight = busiest_cfs_rq->load.weight;
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
+ resched_task(rq->curr);
}
enqueue_task_fair(rq, p, 0);
- resched_task(rq->curr);
}
/*
if (p->prio > oldprio)
resched_task(rq->curr);
} else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/*
if (running)
resched_task(rq->curr);
else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.
SCHED_FEAT(LB_BIAS, 1)
SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
SCHED_FEAT(ASYM_EFF_LOAD, 1)
+SCHED_FEAT(WAKEUP_OVERLAP, 0)
/*
* Idle tasks are unconditionally rescheduled:
*/
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync)
{
resched_task(rq->idle);
}
if (running)
resched_task(rq->curr);
else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
static void prio_changed_idle(struct rq *rq, struct task_struct *p,
if (p->prio > oldprio)
resched_task(rq->curr);
} else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/*
int i, idle = 1;
cpumask_t span;
- if (rt_b->rt_runtime == RUNTIME_INF)
+ if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
return 1;
span = sched_rt_period_mask();
curr->se.exec_start = rq->clock;
cpuacct_charge(curr, delta_exec);
+ if (!rt_bandwidth_enabled())
+ return;
+
for_each_sched_rt_entity(rt_se) {
rt_rq = rt_rq_of_se(rt_se);
/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync)
{
if (p->prio < rq->curr->prio) {
resched_task(rq->curr);
{
struct user_struct *up = container_of(kobj, struct user_struct, kobj);
- return sprintf(buf, "%lu\n", sched_group_rt_runtime(up->tg));
+ return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg));
}
static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
unsigned long rt_runtime;
int rc;
- sscanf(buf, "%lu", &rt_runtime);
+ sscanf(buf, "%ld", &rt_runtime);
rc = sched_group_set_rt_runtime(up->tg, rt_runtime);