unimore/kernel-hacking-2024-linux-steffo
unimore/kernel-hacking-2024-linux-steffo
1
Fork 0
Code Pull requests 5 Wiki Activity
kernel-hacking-2024-linux-s.../kernel/sched_fair.c
Frank Mayhar f06febc96b timers: fix itimer/many thread hang 
Overview

This patch reworks the handling of POSIX CPU timers, including the
ITIMER_PROF, ITIMER_VIRT timers and rlimit handling.  It was put together
with the help of Roland McGrath, the owner and original writer of this code.

The problem we ran into, and the reason for this rework, has to do with using
a profiling timer in a process with a large number of threads.  It appears
that the performance of the old implementation of run_posix_cpu_timers() was
at least O(n*3) (where "n" is the number of threads in a process) or worse.
Everything is fine with an increasing number of threads until the time taken
for that routine to run becomes the same as or greater than the tick time, at
which point things degrade rather quickly.

This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF."

Code Changes

This rework corrects the implementation of run_posix_cpu_timers() to make it
run in constant time for a particular machine.  (Performance may vary between
one machine and another depending upon whether the kernel is built as single-
or multiprocessor and, in the latter case, depending upon the number of
running processors.)  To do this, at each tick we now update fields in
signal_struct as well as task_struct.  The run_posix_cpu_timers() function
uses those fields to make its decisions.

We define a new structure, "task_cputime," to contain user, system and
scheduler times and use these in appropriate places:

struct task_cputime {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};

This is included in the structure "thread_group_cputime," which is a new
substructure of signal_struct and which varies for uniprocessor versus
multiprocessor kernels.  For uniprocessor kernels, it uses "task_cputime" as
a simple substructure, while for multiprocessor kernels it is a pointer:

struct thread_group_cputime {
	struct task_cputime totals;
};

struct thread_group_cputime {
	struct task_cputime *totals;
};

We also add a new task_cputime substructure directly to signal_struct, to
cache the earliest expiration of process-wide timers, and task_cputime also
replaces the it_*_expires fields of task_struct (used for earliest expiration
of thread timers).  The "thread_group_cputime" structure contains process-wide
timers that are updated via account_user_time() and friends.  In the non-SMP
case the structure is a simple aggregator; unfortunately in the SMP case that
simplicity was not achievable due to cache-line contention between CPUs (in
one measured case performance was actually _worse_ on a 16-cpu system than
the same test on a 4-cpu system, due to this contention).  For SMP, the
thread_group_cputime counters are maintained as a per-cpu structure allocated
using alloc_percpu().  The timer functions update only the timer field in
the structure corresponding to the running CPU, obtained using per_cpu_ptr().

We define a set of inline functions in sched.h that we use to maintain the
thread_group_cputime structure and hide the differences between UP and SMP
implementations from the rest of the kernel.  The thread_group_cputime_init()
function initializes the thread_group_cputime structure for the given task.
The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the
out-of-line function thread_group_cputime_alloc_smp() to allocate and fill
in the per-cpu structures and fields.  The thread_group_cputime_free()
function, also a no-op for UP, in SMP frees the per-cpu structures.  The
thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls
thread_group_cputime_alloc() if the per-cpu structures haven't yet been
allocated.  The thread_group_cputime() function fills the task_cputime
structure it is passed with the contents of the thread_group_cputime fields;
in UP it's that simple but in SMP it must also safely check that tsk->signal
is non-NULL (if it is it just uses the appropriate fields of task_struct) and,
if so, sums the per-cpu values for each online CPU.  Finally, the three
functions account_group_user_time(), account_group_system_time() and
account_group_exec_runtime() are used by timer functions to update the
respective fields of the thread_group_cputime structure.

Non-SMP operation is trivial and will not be mentioned further.

The per-cpu structure is always allocated when a task creates its first new
thread, via a call to thread_group_cputime_clone_thread() from copy_signal().
It is freed at process exit via a call to thread_group_cputime_free() from
cleanup_signal().

All functions that formerly summed utime/stime/sum_sched_runtime values from
from all threads in the thread group now use thread_group_cputime() to
snapshot the values in the thread_group_cputime structure or the values in
the task structure itself if the per-cpu structure hasn't been allocated.

Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit.
The run_posix_cpu_timers() function has been split into a fast path and a
slow path; the former safely checks whether there are any expired thread
timers and, if not, just returns, while the slow path does the heavy lifting.
With the dedicated thread group fields, timers are no longer "rebalanced" and
the process_timer_rebalance() function and related code has gone away.  All
summing loops are gone and all code that used them now uses the
thread_group_cputime() inline.  When process-wide timers are set, the new
task_cputime structure in signal_struct is used to cache the earliest
expiration; this is checked in the fast path.

Performance

The fix appears not to add significant overhead to existing operations.  It
generally performs the same as the current code except in two cases, one in
which it performs slightly worse (Case 5 below) and one in which it performs
very significantly better (Case 2 below).  Overall it's a wash except in those
two cases.

I've since done somewhat more involved testing on a dual-core Opteron system.

Case 1: With no itimer running, for a test with 100,000 threads, the fixed
	kernel took 1428.5 seconds, 513 seconds more than the unfixed system,
	all of which was spent in the system.  There were twice as many
	voluntary context switches with the fix as without it.

Case 2: With an itimer running at .01 second ticks and 4000 threads (the most
	an unmodified kernel can handle), the fixed kernel ran the test in
	eight percent of the time (5.8 seconds as opposed to 70 seconds) and
	had better tick accuracy (.012 seconds per tick as opposed to .023
	seconds per tick).

Case 3: A 4000-thread test with an initial timer tick of .01 second and an
	interval of 10,000 seconds (i.e. a timer that ticks only once) had
	very nearly the same performance in both cases:  6.3 seconds elapsed
	for the fixed kernel versus 5.5 seconds for the unfixed kernel.

With fewer threads (eight in these tests), the Case 1 test ran in essentially
the same time on both the modified and unmodified kernels (5.2 seconds versus
5.8 seconds).  The Case 2 test ran in about the same time as well, 5.9 seconds
versus 5.4 seconds but again with much better tick accuracy, .013 seconds per
tick versus .025 seconds per tick for the unmodified kernel.

Since the fix affected the rlimit code, I also tested soft and hard CPU limits.

Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer
	running), the modified kernel was very slightly favored in that while
	it killed the process in 19.997 seconds of CPU time (5.002 seconds of
	wall time), only .003 seconds of that was system time, the rest was
	user time.  The unmodified kernel killed the process in 20.001 seconds
	of CPU (5.014 seconds of wall time) of which .016 seconds was system
	time.  Really, though, the results were too close to call.  The results
	were essentially the same with no itimer running.

Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds
	(where the hard limit would never be reached) and an itimer running,
	the modified kernel exhibited worse tick accuracy than the unmodified
	kernel: .050 seconds/tick versus .028 seconds/tick.  Otherwise,
	performance was almost indistinguishable.  With no itimer running this
	test exhibited virtually identical behavior and times in both cases.

In times past I did some limited performance testing.  those results are below.

On a four-cpu Opteron system without this fix, a sixteen-thread test executed
in 3569.991 seconds, of which user was 3568.435s and system was 1.556s.  On
the same system with the fix, user and elapsed time were about the same, but
system time dropped to 0.007 seconds.  Performance with eight, four and one
thread were comparable.  Interestingly, the timer ticks with the fix seemed
more accurate:  The sixteen-thread test with the fix received 149543 ticks
for 0.024 seconds per tick, while the same test without the fix received 58720
for 0.061 seconds per tick.  Both cases were configured for an interval of
0.01 seconds.  Again, the other tests were comparable.  Each thread in this
test computed the primes up to 25,000,000.

I also did a test with a large number of threads, 100,000 threads, which is
impossible without the fix.  In this case each thread computed the primes only
up to 10,000 (to make the runtime manageable).  System time dominated, at
1546.968 seconds out of a total 2176.906 seconds (giving a user time of
629.938s).  It received 147651 ticks for 0.015 seconds per tick, still quite
accurate.  There is obviously no comparable test without the fix.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-14 16:25:35 +02:00

1733 lines
41 KiB
C
Raw Blame History

/*
* Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
*
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*
* Interactivity improvements by Mike Galbraith
* (C) 2007 Mike Galbraith <efault@gmx.de>
*
* Various enhancements by Dmitry Adamushko.
* (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
*
* Group scheduling enhancements by Srivatsa Vaddagiri
* Copyright IBM Corporation, 2007
* Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
*
* Scaled math optimizations by Thomas Gleixner
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
*
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*/
#include <linux/latencytop.h>
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
*
* NOTE: this latency value is not the same as the concept of
* 'timeslice length' - timeslices in CFS are of variable length
* and have no persistent notion like in traditional, time-slice
* based scheduling concepts.
*
* (to see the precise effective timeslice length of your workload,
* run vmstat and monitor the context-switches (cs) field)
*/
unsigned int sysctl_sched_latency = 20000000ULL;
/*
* Minimal preemption granularity for CPU-bound tasks:
* (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_min_granularity = 4000000ULL;
/*
* is kept at sysctl_sched_latency / sysctl_sched_min_granularity
*/
static unsigned int sched_nr_latency = 5;
/*
* After fork, child runs first. (default) If set to 0 then
* parent will (try to) run first.
*/
const_debug unsigned int sysctl_sched_child_runs_first = 1;
/*
* sys_sched_yield() compat mode
*
* This option switches the agressive yield implementation of the
* old scheduler back on.
*/
unsigned int __read_mostly sysctl_sched_compat_yield;
/*
* SCHED_OTHER wake-up granularity.
* (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
/**************************************************************
* CFS operations on generic schedulable entities:
*/
static inline struct task_struct *task_of(struct sched_entity *se)
{
return container_of(se, struct task_struct, se);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return cfs_rq->rq;
}
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return p->se.cfs_rq;
}
/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
return se->cfs_rq;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
* another cpu ('this_cpu')
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
return 1;
return 0;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return se->parent;
}
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return container_of(cfs_rq, struct rq, cfs);
}
#define entity_is_task(se) 1
#define for_each_sched_entity(se) \
for (; se; se = NULL)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return &task_rq(p)->cfs;
}
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return NULL;
}
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return &cpu_rq(this_cpu)->cfs;
}
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
return 1;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
/**************************************************************
* Scheduling class tree data structure manipulation methods:
*/
static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - min_vruntime);
if (delta > 0)
min_vruntime = vruntime;
return min_vruntime;
}
static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - min_vruntime);
if (delta < 0)
min_vruntime = vruntime;
return min_vruntime;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return se->vruntime - cfs_rq->min_vruntime;
}
/*
* Enqueue an entity into the rb-tree:
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
s64 key = entity_key(cfs_rq, se);
int leftmost = 1;
/*
* Find the right place in the rbtree:
*/
while (*link) {
parent = *link;
entry = rb_entry(parent, struct sched_entity, run_node);
/*
* We dont care about collisions. Nodes with
* the same key stay together.
*/
if (key < entity_key(cfs_rq, entry)) {
link = &parent->rb_left;
} else {
link = &parent->rb_right;
leftmost = 0;
}
}
/*
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
if (leftmost) {
cfs_rq->rb_leftmost = &se->run_node;
/*
* maintain cfs_rq->min_vruntime to be a monotonic increasing
* value tracking the leftmost vruntime in the tree.
*/
cfs_rq->min_vruntime =
max_vruntime(cfs_rq->min_vruntime, se->vruntime);
}
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->rb_leftmost == &se->run_node) {
struct rb_node *next_node;
struct sched_entity *next;
next_node = rb_next(&se->run_node);
cfs_rq->rb_leftmost = next_node;
if (next_node) {
next = rb_entry(next_node,
struct sched_entity, run_node);
cfs_rq->min_vruntime =
max_vruntime(cfs_rq->min_vruntime,
next->vruntime);
}
}
if (cfs_rq->next == se)
cfs_rq->next = NULL;
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
{
return cfs_rq->rb_leftmost;
}
static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
}
static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
if (!last)
return NULL;
return rb_entry(last, struct sched_entity, run_node);
}
/**************************************************************
* Scheduling class statistics methods:
*/
#ifdef CONFIG_SCHED_DEBUG
int sched_nr_latency_handler(struct ctl_table *table, int write,
struct file *filp, void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
if (ret || !write)
return ret;
sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
sysctl_sched_min_granularity);
return 0;
}
#endif
/*
* delta *= w / rw
*/
static inline unsigned long
calc_delta_weight(unsigned long delta, struct sched_entity *se)
{
for_each_sched_entity(se) {
delta = calc_delta_mine(delta,
se->load.weight, &cfs_rq_of(se)->load);
}
return delta;
}
/*
* delta *= rw / w
*/
static inline unsigned long
calc_delta_fair(unsigned long delta, struct sched_entity *se)
{
for_each_sched_entity(se) {
delta = calc_delta_mine(delta,
cfs_rq_of(se)->load.weight, &se->load);
}
return delta;
}
/*
* The idea is to set a period in which each task runs once.
*
* When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
* this period because otherwise the slices get too small.
*
* p = (nr <= nl) ? l : l*nr/nl
*/
static u64 __sched_period(unsigned long nr_running)
{
u64 period = sysctl_sched_latency;
unsigned long nr_latency = sched_nr_latency;
if (unlikely(nr_running > nr_latency)) {
period = sysctl_sched_min_granularity;
period *= nr_running;
}
return period;
}
/*
* We calculate the wall-time slice from the period by taking a part
* proportional to the weight.
*
* s = p*w/rw
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
}
/*
* We calculate the vruntime slice of a to be inserted task
*
* vs = s*rw/w = p
*/
static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long nr_running = cfs_rq->nr_running;
if (!se->on_rq)
nr_running++;
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.
*/
static inline void
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
unsigned long delta_exec)
{
unsigned long delta_exec_weighted;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
}
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_of(cfs_rq)->clock;
unsigned long delta_exec;
if (unlikely(!curr))
return;
/*
* Get the amount of time the current task was running
* since the last time we changed load (this cannot
* overflow on 32 bits):
*/
delta_exec = (unsigned long)(now - curr->exec_start);
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
cpuacct_charge(curtask, delta_exec);
account_group_exec_runtime(curtask, delta_exec);
}
}
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}
/*
* Task is being enqueued - update stats:
*/
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Are we enqueueing a waiting task? (for current tasks
* a dequeue/enqueue event is a NOP)
*/
if (se != cfs_rq->curr)
update_stats_wait_start(cfs_rq, se);
}
static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->wait_max, max(se->wait_max,
rq_of(cfs_rq)->clock - se->wait_start));
schedstat_set(se->wait_count, se->wait_count + 1);
schedstat_set(se->wait_sum, se->wait_sum +
rq_of(cfs_rq)->clock - se->wait_start);
schedstat_set(se->wait_start, 0);
}
static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Mark the end of the wait period if dequeueing a
* waiting task:
*/
if (se != cfs_rq->curr)
update_stats_wait_end(cfs_rq, se);
}
/*
* We are picking a new current task - update its stats:
*/
static inline void
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* We are starting a new run period:
*/
se->exec_start = rq_of(cfs_rq)->clock;
}
/**************************************************
* Scheduling class queueing methods:
*/
#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
static void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
cfs_rq->task_weight += weight;
}
#else
static inline void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
}
#endif
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
inc_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se))
add_cfs_task_weight(cfs_rq, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
list_add(&se->group_node, &cfs_rq->tasks);
}
static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
dec_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se))
add_cfs_task_weight(cfs_rq, -se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
list_del_init(&se->group_node);
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->sleep_max))
se->sleep_max = delta;
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->block_max))
se->block_max = delta;
se->block_start = 0;
se->sum_sleep_runtime += delta;
/*
* Blocking time is in units of nanosecs, so shift by 20 to
* get a milliseconds-range estimation of the amount of
* time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
delta >> 20);
}
account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
s64 d = se->vruntime - cfs_rq->min_vruntime;
if (d < 0)
d = -d;
if (d > 3*sysctl_sched_latency)
schedstat_inc(cfs_rq, nr_spread_over);
#endif
}
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
u64 vruntime;
if (first_fair(cfs_rq)) {
vruntime = min_vruntime(cfs_rq->min_vruntime,
__pick_next_entity(cfs_rq)->vruntime);
} else
vruntime = cfs_rq->min_vruntime;
/*
* The 'current' period is already promised to the current tasks,
* however the extra weight of the new task will slow them down a
* little, place the new task so that it fits in the slot that
* stays open at the end.
*/
if (initial && sched_feat(START_DEBIT))
vruntime += sched_vslice_add(cfs_rq, se);
if (!initial) {
/* sleeps upto a single latency don't count. */
if (sched_feat(NEW_FAIR_SLEEPERS)) {
unsigned long thresh = sysctl_sched_latency;
/*
* convert the sleeper threshold into virtual time
*/
if (sched_feat(NORMALIZED_SLEEPER))
thresh = calc_delta_fair(thresh, se);
vruntime -= thresh;
}
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
}
se->vruntime = vruntime;
}
static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
account_entity_enqueue(cfs_rq, se);
if (wakeup) {
place_entity(cfs_rq, se, 0);
enqueue_sleeper(cfs_rq, se);
}
update_stats_enqueue(cfs_rq, se);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
}
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
update_stats_dequeue(cfs_rq, se);
if (sleep) {
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
if (tsk->state & TASK_INTERRUPTIBLE)
se->sleep_start = rq_of(cfs_rq)->clock;
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->block_start = rq_of(cfs_rq)->clock;
}
#endif
}
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
account_entity_dequeue(cfs_rq, se);
}
/*
* Preempt the current task with a newly woken task if needed:
*/
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
unsigned long ideal_runtime, delta_exec;
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime)
resched_task(rq_of(cfs_rq)->curr);
}
static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/* 'current' is not kept within the tree. */
if (se->on_rq) {
/*
* Any task has to be enqueued before it get to execute on
* a CPU. So account for the time it spent waiting on the
* runqueue.
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
}
update_stats_curr_start(cfs_rq, se);
cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
/*
* Track our maximum slice length, if the CPU's load is at
* least twice that of our own weight (i.e. dont track it
* when there are only lesser-weight tasks around):
*/
if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
se->slice_max = max(se->slice_max,
se->sum_exec_runtime - se->prev_sum_exec_runtime);
}
#endif
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static struct sched_entity *
pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct rq *rq = rq_of(cfs_rq);
u64 pair_slice = rq->clock - cfs_rq->pair_start;
if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
cfs_rq->pair_start = rq->clock;
return se;
}
return cfs_rq->next;
}
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = NULL;
if (first_fair(cfs_rq)) {
se = __pick_next_entity(cfs_rq);
se = pick_next(cfs_rq, se);
set_next_entity(cfs_rq, se);
}
return se;
}
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
/*
* If still on the runqueue then deactivate_task()
* was not called and update_curr() has to be done:
*/
if (prev->on_rq)
update_curr(cfs_rq);
check_spread(cfs_rq, prev);
if (prev->on_rq) {
update_stats_wait_start(cfs_rq, prev);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
}
cfs_rq->curr = NULL;
}
static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
* queued ticks are scheduled to match the slice, so don't bother
* validating it and just reschedule.
*/
if (queued) {
resched_task(rq_of(cfs_rq)->curr);
return;
}
/*
* don't let the period tick interfere with the hrtick preemption
*/
if (!sched_feat(DOUBLE_TICK) &&
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
return;
#endif
if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
check_preempt_tick(cfs_rq, curr);
}
/**************************************************
* CFS operations on tasks:
*/
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
WARN_ON(task_rq(p) != rq);
if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
u64 slice = sched_slice(cfs_rq, se);
u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
s64 delta = slice - ran;
if (delta < 0) {
if (rq->curr == p)
resched_task(p);
return;
}
/*
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
if (rq->curr != p)
delta = max_t(s64, 10000LL, delta);
hrtick_start(rq, delta);
}
}
#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
#endif
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
* then put the task into the rbtree:
*/
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
if (se->on_rq)
break;
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, wakeup);
wakeup = 1;
}
hrtick_start_fair(rq, rq->curr);
}
/*
* The dequeue_task method is called before nr_running is
* decreased. We remove the task from the rbtree and
* update the fair scheduling stats:
*/
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, sleep);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight)
break;
sleep = 1;
}
hrtick_start_fair(rq, rq->curr);
}
/*
* sched_yield() support is very simple - we dequeue and enqueue.
*
* If compat_yield is turned on then we requeue to the end of the tree.
*/
static void yield_task_fair(struct rq *rq)
{
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *rightmost, *se = &curr->se;
/*
* Are we the only task in the tree?
*/
if (unlikely(cfs_rq->nr_running == 1))
return;
if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
return;
}
/*
* Find the rightmost entry in the rbtree:
*/
rightmost = __pick_last_entity(cfs_rq);
/*
* Already in the rightmost position?
*/
if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
return;
/*
* Minimally necessary key value to be last in the tree:
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
se->vruntime = rightmost->vruntime + 1;
}
/*
* wake_idle() will wake a task on an idle cpu if task->cpu is
* not idle and an idle cpu is available. The span of cpus to
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
* Domains may include CPUs that are not usable for migration,
* hence we need to mask them out (cpu_active_map)
*
* Returns the CPU we should wake onto.
*/
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, struct task_struct *p)
{
cpumask_t tmp;
struct sched_domain *sd;
int i;
/*
* If it is idle, then it is the best cpu to run this task.
*
* This cpu is also the best, if it has more than one task already.
* Siblings must be also busy(in most cases) as they didn't already
* pickup the extra load from this cpu and hence we need not check
* sibling runqueue info. This will avoid the checks and cache miss
* penalities associated with that.
*/
if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
return cpu;
for_each_domain(cpu, sd) {
if ((sd->flags & SD_WAKE_IDLE)
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
cpus_and(tmp, tmp, cpu_active_map);
for_each_cpu_mask_nr(i, tmp) {
if (idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
se.nr_wakeups_idle);
}
return i;
}
}
} else {
break;
}
}
return cpu;
}
#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
}
#endif
#ifdef CONFIG_SMP
static const struct sched_class fair_sched_class;
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* effective_load() calculates the load change as seen from the root_task_group
*
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
*
* The problem is that perfectly aligning the shares is rather expensive, hence
* we try to avoid doing that too often - see update_shares(), which ratelimits
* this change.
*
* We compensate this by not only taking the current delta into account, but
* also considering the delta between when the shares were last adjusted and
* now.
*
* We still saw a performance dip, some tracing learned us that between
* cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
* significantly. Therefore try to bias the error in direction of failing
* the affine wakeup.
*
*/
static long effective_load(struct task_group *tg, int cpu,
long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
long more_w;
if (!tg->parent)
return wl;
/*
* By not taking the decrease of shares on the other cpu into
* account our error leans towards reducing the affine wakeups.
*/
if (!wl && sched_feat(ASYM_EFF_LOAD))
return wl;
/*
* Instead of using this increment, also add the difference
* between when the shares were last updated and now.
*/
more_w = se->my_q->load.weight - se->my_q->rq_weight;
wl += more_w;
wg += more_w;
for_each_sched_entity(se) {
#define D(n) (likely(n) ? (n) : 1)
long S, rw, s, a, b;
S = se->my_q->tg->shares;
s = se->my_q->shares;
rw = se->my_q->rq_weight;
a = S*(rw + wl);
b = S*rw + s*wg;
wl = s*(a-b)/D(b);
/*
* Assume the group is already running and will
* thus already be accounted for in the weight.
*
* That is, moving shares between CPUs, does not
* alter the group weight.
*/
wg = 0;
#undef D
}
return wl;
}
#else
static inline unsigned long effective_load(struct task_group *tg, int cpu,
unsigned long wl, unsigned long wg)
{
return wl;
}
#endif
static int
wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
struct task_struct *p, int prev_cpu, int this_cpu, int sync,
int idx, unsigned long load, unsigned long this_load,
unsigned int imbalance)
{
struct task_struct *curr = this_rq->curr;
struct task_group *tg;
unsigned long tl = this_load;
unsigned long tl_per_task;
unsigned long weight;
int balanced;
if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
if (sync) {
tg = task_group(current);
weight = current->se.load.weight;
tl += effective_load(tg, this_cpu, -weight, -weight);
load += effective_load(tg, prev_cpu, 0, -weight);
}
tg = task_group(p);
weight = p->se.load.weight;
balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
if (sync && balanced) {
if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
p->se.avg_overlap < sysctl_sched_migration_cost)
return 1;
}
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
balanced) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
* there is no bad imbalance.
*/
schedstat_inc(this_sd, ttwu_move_affine);
schedstat_inc(p, se.nr_wakeups_affine);
return 1;
}
return 0;
}
static int select_task_rq_fair(struct task_struct *p, int sync)
{
struct sched_domain *sd, *this_sd = NULL;
int prev_cpu, this_cpu, new_cpu;
unsigned long load, this_load;
struct rq *rq, *this_rq;
unsigned int imbalance;
int idx;
prev_cpu = task_cpu(p);
rq = task_rq(p);
this_cpu = smp_processor_id();
this_rq = cpu_rq(this_cpu);
new_cpu = prev_cpu;
/*
* 'this_sd' is the first domain that both
* this_cpu and prev_cpu are present in:
*/
for_each_domain(this_cpu, sd) {
if (cpu_isset(prev_cpu, sd->span)) {
this_sd = sd;
break;
}
}
if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
goto out;
/*
* Check for affine wakeup and passive balancing possibilities.
*/
if (!this_sd)
goto out;
idx = this_sd->wake_idx;
imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
load, this_load, imbalance))
return this_cpu;
if (prev_cpu == this_cpu)
goto out;
/*
* Start passive balancing when half the imbalance_pct
* limit is reached.
*/
if (this_sd->flags & SD_WAKE_BALANCE) {
if (imbalance*this_load <= 100*load) {
schedstat_inc(this_sd, ttwu_move_balance);
schedstat_inc(p, se.nr_wakeups_passive);
return this_cpu;
}
}
out:
return wake_idle(new_cpu, p);
}
#endif /* CONFIG_SMP */
static unsigned long wakeup_gran(struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
/*
* More easily preempt - nice tasks, while not making it harder for
* + 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);
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)
{
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;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
update_curr(cfs_rq);
resched_task(curr);
return;
}
if (unlikely(se == pse))
return;
cfs_rq_of(pse)->next = pse;
/*
* Batch tasks do not preempt (their preemption is driven by
* the tick):
*/
if (unlikely(p->policy == SCHED_BATCH))
return;
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 (wakeup_preempt_entity(se, pse) == 1)
resched_task(curr);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
{
struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
if (unlikely(!cfs_rq->nr_running))
return NULL;
do {
se = pick_next_entity(cfs_rq);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
hrtick_start_fair(rq, p);
return p;
}
/*
* Account for a descheduled task:
*/
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
put_prev_entity(cfs_rq, se);
}
}
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
*/
/*
* Load-balancing iterator. Note: while the runqueue stays locked
* during the whole iteration, the current task might be
* dequeued so the iterator has to be dequeue-safe. Here we
* achieve that by always pre-iterating before returning
* the current task:
*/
static struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
struct task_struct *p = NULL;
struct sched_entity *se;
if (next == &cfs_rq->tasks)
return NULL;
/* Skip over entities that are not tasks */
do {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
} while (next != &cfs_rq->tasks && !entity_is_task(se));
if (next == &cfs_rq->tasks)
return NULL;
cfs_rq->balance_iterator = next;
if (entity_is_task(se))
p = task_of(se);
return p;
}
static struct task_struct *load_balance_start_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}
static struct task_struct *load_balance_next_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
static unsigned long
__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move, struct sched_domain *sd,
enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
struct cfs_rq *cfs_rq)
{
struct rq_iterator cfs_rq_iterator;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
cfs_rq_iterator.arg = cfs_rq;
return balance_tasks(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &cfs_rq_iterator);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
long rem_load_move = max_load_move;
int busiest_cpu = cpu_of(busiest);
struct task_group *tg;
rcu_read_lock();
update_h_load(busiest_cpu);
list_for_each_entry(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;
u64 rem_load, moved_load;
/*
* empty group
*/
if (!busiest_cfs_rq->task_weight)
continue;
rem_load = (u64)rem_load_move * busiest_weight;
rem_load = div_u64(rem_load, busiest_h_load + 1);
moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
rem_load, sd, idle, all_pinned, this_best_prio,
tg->cfs_rq[busiest_cpu]);
if (!moved_load)
continue;
moved_load *= busiest_h_load;
moved_load = div_u64(moved_load, busiest_weight + 1);
rem_load_move -= moved_load;
if (rem_load_move < 0)
break;
}
rcu_read_unlock();
return max_load_move - rem_load_move;
}
#else
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
return __load_balance_fair(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &busiest->cfs);
}
#endif
static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
struct sched_domain *sd, enum cpu_idle_type idle)
{
struct cfs_rq *busy_cfs_rq;
struct rq_iterator cfs_rq_iterator;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
/*
* pass busy_cfs_rq argument into
* load_balance_[start|next]_fair iterators
*/
cfs_rq_iterator.arg = busy_cfs_rq;
if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
&cfs_rq_iterator))
return 1;
}
return 0;
}
#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
*/
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &curr->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
entity_tick(cfs_rq, se, queued);
}
}
#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
/*
* Share the fairness runtime between parent and child, thus the
* total amount of pressure for CPU stays equal - new tasks
* get a chance to run but frequent forkers are not allowed to
* monopolize the CPU. Note: the parent runqueue is locked,
* the child is not running yet.
*/
static void task_new_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
int this_cpu = smp_processor_id();
sched_info_queued(p);
update_curr(cfs_rq);
place_entity(cfs_rq, se, 1);
/* 'curr' will be NULL if the child belongs to a different group */
if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
curr && curr->vruntime < se->vruntime) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
}
enqueue_task_fair(rq, p, 0);
resched_task(rq->curr);
}
/*
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
static void prio_changed_fair(struct rq *rq, struct task_struct *p,
int oldprio, int running)
{
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
if (running) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p);
}
/*
* We switched to the sched_fair class.
*/
static void switched_to_fair(struct rq *rq, struct task_struct *p,
int running)
{
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
if (running)
resched_task(rq->curr);
else
check_preempt_curr(rq, p);
}
/* Account for a task changing its policy or group.
*
* This routine is mostly called to set cfs_rq->curr field when a task
* migrates between groups/classes.
*/
static void set_curr_task_fair(struct rq *rq)
{
struct sched_entity *se = &rq->curr->se;
for_each_sched_entity(se)
set_next_entity(cfs_rq_of(se), se);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void moved_group_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
update_curr(cfs_rq);
place_entity(cfs_rq, &p->se, 1);
}
#endif
/*
* All the scheduling class methods:
*/
static const struct sched_class fair_sched_class = {
.next = &idle_sched_class,
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_fair,
#endif /* CONFIG_SMP */
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair,
.put_prev_task = put_prev_task_fair,
#ifdef CONFIG_SMP
.load_balance = load_balance_fair,
.move_one_task = move_one_task_fair,
#endif
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_new = task_new_fair,
.prio_changed = prio_changed_fair,
.switched_to = switched_to_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
.moved_group = moved_group_fair,
#endif
};
#ifdef CONFIG_SCHED_DEBUG
static void print_cfs_stats(struct seq_file *m, int cpu)
{
struct cfs_rq *cfs_rq;
rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
#endif
View git blame Copy permalink