From 45ceebf77653975815d82fcf7cec0a164215ae11 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Fri, 19 Apr 2013 15:10:49 -0400
Subject: sched: Factor out load calculation code from sched/core.c -->
 sched/proc.c

This large chunk of load calculation code can be easily divorced
from the main core.c scheduler file, with only a couple
prototypes and externs added to a kernel/sched header.

Some recent commits expanded the code and the documentation of
it, making it large enough to warrant separation.  For example,
see:

  556061b, "sched/nohz: Fix rq->cpu_load[] calculations"
  5aaa0b7, "sched/nohz: Fix rq->cpu_load calculations some more"
  5167e8d, "sched/nohz: Rewrite and fix load-avg computation -- again"

More importantly, it helps reduce the size of the main
sched/core.c by yet another significant amount (~600 lines).

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1366398650-31599-2-git-send-email-paul.gortmaker@windriver.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 569 ----------------------------------------------------
 1 file changed, 569 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 58453b8272f..bfa7e77e0b5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2056,575 +2056,6 @@ unsigned long nr_iowait_cpu(int cpu)
 	return atomic_read(&this->nr_iowait);
 }
 
-unsigned long this_cpu_load(void)
-{
-	struct rq *this = this_rq();
-	return this->cpu_load[0];
-}
-
-
-/*
- * Global load-average calculations
- *
- * We take a distributed and async approach to calculating the global load-avg
- * in order to minimize overhead.
- *
- * The global load average is an exponentially decaying average of nr_running +
- * nr_uninterruptible.
- *
- * Once every LOAD_FREQ:
- *
- *   nr_active = 0;
- *   for_each_possible_cpu(cpu)
- *   	nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
- *
- *   avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
- *
- * Due to a number of reasons the above turns in the mess below:
- *
- *  - for_each_possible_cpu() is prohibitively expensive on machines with
- *    serious number of cpus, therefore we need to take a distributed approach
- *    to calculating nr_active.
- *
- *        \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
- *                      = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
- *
- *    So assuming nr_active := 0 when we start out -- true per definition, we
- *    can simply take per-cpu deltas and fold those into a global accumulate
- *    to obtain the same result. See calc_load_fold_active().
- *
- *    Furthermore, in order to avoid synchronizing all per-cpu delta folding
- *    across the machine, we assume 10 ticks is sufficient time for every
- *    cpu to have completed this task.
- *
- *    This places an upper-bound on the IRQ-off latency of the machine. Then
- *    again, being late doesn't loose the delta, just wrecks the sample.
- *
- *  - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
- *    this would add another cross-cpu cacheline miss and atomic operation
- *    to the wakeup path. Instead we increment on whatever cpu the task ran
- *    when it went into uninterruptible state and decrement on whatever cpu
- *    did the wakeup. This means that only the sum of nr_uninterruptible over
- *    all cpus yields the correct result.
- *
- *  This covers the NO_HZ=n code, for extra head-aches, see the comment below.
- */
-
-/* Variables and functions for calc_load */
-static atomic_long_t calc_load_tasks;
-static unsigned long calc_load_update;
-unsigned long avenrun[3];
-EXPORT_SYMBOL(avenrun); /* should be removed */
-
-/**
- * get_avenrun - get the load average array
- * @loads:	pointer to dest load array
- * @offset:	offset to add
- * @shift:	shift count to shift the result left
- *
- * These values are estimates at best, so no need for locking.
- */
-void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
-{
-	loads[0] = (avenrun[0] + offset) << shift;
-	loads[1] = (avenrun[1] + offset) << shift;
-	loads[2] = (avenrun[2] + offset) << shift;
-}
-
-static long calc_load_fold_active(struct rq *this_rq)
-{
-	long nr_active, delta = 0;
-
-	nr_active = this_rq->nr_running;
-	nr_active += (long) this_rq->nr_uninterruptible;
-
-	if (nr_active != this_rq->calc_load_active) {
-		delta = nr_active - this_rq->calc_load_active;
-		this_rq->calc_load_active = nr_active;
-	}
-
-	return delta;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- */
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	load += 1UL << (FSHIFT - 1);
-	return load >> FSHIFT;
-}
-
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * Handle NO_HZ for the global load-average.
- *
- * Since the above described distributed algorithm to compute the global
- * load-average relies on per-cpu sampling from the tick, it is affected by
- * NO_HZ.
- *
- * The basic idea is to fold the nr_active delta into a global idle-delta upon
- * entering NO_HZ state such that we can include this as an 'extra' cpu delta
- * when we read the global state.
- *
- * Obviously reality has to ruin such a delightfully simple scheme:
- *
- *  - When we go NO_HZ idle during the window, we can negate our sample
- *    contribution, causing under-accounting.
- *
- *    We avoid this by keeping two idle-delta counters and flipping them
- *    when the window starts, thus separating old and new NO_HZ load.
- *
- *    The only trick is the slight shift in index flip for read vs write.
- *
- *        0s            5s            10s           15s
- *          +10           +10           +10           +10
- *        |-|-----------|-|-----------|-|-----------|-|
- *    r:0 0 1           1 0           0 1           1 0
- *    w:0 1 1           0 0           1 1           0 0
- *
- *    This ensures we'll fold the old idle contribution in this window while
- *    accumlating the new one.
- *
- *  - When we wake up from NO_HZ idle during the window, we push up our
- *    contribution, since we effectively move our sample point to a known
- *    busy state.
- *
- *    This is solved by pushing the window forward, and thus skipping the
- *    sample, for this cpu (effectively using the idle-delta for this cpu which
- *    was in effect at the time the window opened). This also solves the issue
- *    of having to deal with a cpu having been in NOHZ idle for multiple
- *    LOAD_FREQ intervals.
- *
- * When making the ILB scale, we should try to pull this in as well.
- */
-static atomic_long_t calc_load_idle[2];
-static int calc_load_idx;
-
-static inline int calc_load_write_idx(void)
-{
-	int idx = calc_load_idx;
-
-	/*
-	 * See calc_global_nohz(), if we observe the new index, we also
-	 * need to observe the new update time.
-	 */
-	smp_rmb();
-
-	/*
-	 * If the folding window started, make sure we start writing in the
-	 * next idle-delta.
-	 */
-	if (!time_before(jiffies, calc_load_update))
-		idx++;
-
-	return idx & 1;
-}
-
-static inline int calc_load_read_idx(void)
-{
-	return calc_load_idx & 1;
-}
-
-void calc_load_enter_idle(void)
-{
-	struct rq *this_rq = this_rq();
-	long delta;
-
-	/*
-	 * We're going into NOHZ mode, if there's any pending delta, fold it
-	 * into the pending idle delta.
-	 */
-	delta = calc_load_fold_active(this_rq);
-	if (delta) {
-		int idx = calc_load_write_idx();
-		atomic_long_add(delta, &calc_load_idle[idx]);
-	}
-}
-
-void calc_load_exit_idle(void)
-{
-	struct rq *this_rq = this_rq();
-
-	/*
-	 * If we're still before the sample window, we're done.
-	 */
-	if (time_before(jiffies, this_rq->calc_load_update))
-		return;
-
-	/*
-	 * We woke inside or after the sample window, this means we're already
-	 * accounted through the nohz accounting, so skip the entire deal and
-	 * sync up for the next window.
-	 */
-	this_rq->calc_load_update = calc_load_update;
-	if (time_before(jiffies, this_rq->calc_load_update + 10))
-		this_rq->calc_load_update += LOAD_FREQ;
-}
-
-static long calc_load_fold_idle(void)
-{
-	int idx = calc_load_read_idx();
-	long delta = 0;
-
-	if (atomic_long_read(&calc_load_idle[idx]))
-		delta = atomic_long_xchg(&calc_load_idle[idx], 0);
-
-	return delta;
-}
-
-/**
- * fixed_power_int - compute: x^n, in O(log n) time
- *
- * @x:         base of the power
- * @frac_bits: fractional bits of @x
- * @n:         power to raise @x to.
- *
- * By exploiting the relation between the definition of the natural power
- * function: x^n := x*x*...*x (x multiplied by itself for n times), and
- * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
- * (where: n_i \elem {0, 1}, the binary vector representing n),
- * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
- * of course trivially computable in O(log_2 n), the length of our binary
- * vector.
- */
-static unsigned long
-fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
-{
-	unsigned long result = 1UL << frac_bits;
-
-	if (n) for (;;) {
-		if (n & 1) {
-			result *= x;
-			result += 1UL << (frac_bits - 1);
-			result >>= frac_bits;
-		}
-		n >>= 1;
-		if (!n)
-			break;
-		x *= x;
-		x += 1UL << (frac_bits - 1);
-		x >>= frac_bits;
-	}
-
-	return result;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- *
- * a2 = a1 * e + a * (1 - e)
- *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
- *    = a0 * e^2 + a * (1 - e) * (1 + e)
- *
- * a3 = a2 * e + a * (1 - e)
- *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
- *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
- *
- *  ...
- *
- * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
- *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
- *    = a0 * e^n + a * (1 - e^n)
- *
- * [1] application of the geometric series:
- *
- *              n         1 - x^(n+1)
- *     S_n := \Sum x^i = -------------
- *             i=0          1 - x
- */
-static unsigned long
-calc_load_n(unsigned long load, unsigned long exp,
-	    unsigned long active, unsigned int n)
-{
-
-	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
-}
-
-/*
- * NO_HZ can leave us missing all per-cpu ticks calling
- * calc_load_account_active(), but since an idle CPU folds its delta into
- * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
- * in the pending idle delta if our idle period crossed a load cycle boundary.
- *
- * Once we've updated the global active value, we need to apply the exponential
- * weights adjusted to the number of cycles missed.
- */
-static void calc_global_nohz(void)
-{
-	long delta, active, n;
-
-	if (!time_before(jiffies, calc_load_update + 10)) {
-		/*
-		 * Catch-up, fold however many we are behind still
-		 */
-		delta = jiffies - calc_load_update - 10;
-		n = 1 + (delta / LOAD_FREQ);
-
-		active = atomic_long_read(&calc_load_tasks);
-		active = active > 0 ? active * FIXED_1 : 0;
-
-		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
-		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
-		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
-
-		calc_load_update += n * LOAD_FREQ;
-	}
-
-	/*
-	 * Flip the idle index...
-	 *
-	 * Make sure we first write the new time then flip the index, so that
-	 * calc_load_write_idx() will see the new time when it reads the new
-	 * index, this avoids a double flip messing things up.
-	 */
-	smp_wmb();
-	calc_load_idx++;
-}
-#else /* !CONFIG_NO_HZ_COMMON */
-
-static inline long calc_load_fold_idle(void) { return 0; }
-static inline void calc_global_nohz(void) { }
-
-#endif /* CONFIG_NO_HZ_COMMON */
-
-/*
- * calc_load - update the avenrun load estimates 10 ticks after the
- * CPUs have updated calc_load_tasks.
- */
-void calc_global_load(unsigned long ticks)
-{
-	long active, delta;
-
-	if (time_before(jiffies, calc_load_update + 10))
-		return;
-
-	/*
-	 * Fold the 'old' idle-delta to include all NO_HZ cpus.
-	 */
-	delta = calc_load_fold_idle();
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks);
-
-	active = atomic_long_read(&calc_load_tasks);
-	active = active > 0 ? active * FIXED_1 : 0;
-
-	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
-	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
-	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
-
-	calc_load_update += LOAD_FREQ;
-
-	/*
-	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
-	 */
-	calc_global_nohz();
-}
-
-/*
- * Called from update_cpu_load() to periodically update this CPU's
- * active count.
- */
-static void calc_load_account_active(struct rq *this_rq)
-{
-	long delta;
-
-	if (time_before(jiffies, this_rq->calc_load_update))
-		return;
-
-	delta  = calc_load_fold_active(this_rq);
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks);
-
-	this_rq->calc_load_update += LOAD_FREQ;
-}
-
-/*
- * End of global load-average stuff
- */
-
-/*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
- *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
- *
- * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
- *
- * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
- */
-#define DEGRADE_SHIFT		7
-static const unsigned char
-		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
-		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
-					{0, 0, 0, 0, 0, 0, 0, 0},
-					{64, 32, 8, 0, 0, 0, 0, 0},
-					{96, 72, 40, 12, 1, 0, 0},
-					{112, 98, 75, 43, 15, 1, 0},
-					{120, 112, 98, 76, 45, 16, 2} };
-
-/*
- * Update cpu_load for any missed ticks, due to tickless idle. The backlog
- * would be when CPU is idle and so we just decay the old load without
- * adding any new load.
- */
-static unsigned long
-decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
-{
-	int j = 0;
-
-	if (!missed_updates)
-		return load;
-
-	if (missed_updates >= degrade_zero_ticks[idx])
-		return 0;
-
-	if (idx == 1)
-		return load >> missed_updates;
-
-	while (missed_updates) {
-		if (missed_updates % 2)
-			load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
-
-		missed_updates >>= 1;
-		j++;
-	}
-	return load;
-}
-
-/*
- * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
- */
-static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
-			      unsigned long pending_updates)
-{
-	int i, scale;
-
-	this_rq->nr_load_updates++;
-
-	/* Update our load: */
-	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
-	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
-		unsigned long old_load, new_load;
-
-		/* scale is effectively 1 << i now, and >> i divides by scale */
-
-		old_load = this_rq->cpu_load[i];
-		old_load = decay_load_missed(old_load, pending_updates - 1, i);
-		new_load = this_load;
-		/*
-		 * Round up the averaging division if load is increasing. This
-		 * prevents us from getting stuck on 9 if the load is 10, for
-		 * example.
-		 */
-		if (new_load > old_load)
-			new_load += scale - 1;
-
-		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
-	}
-
-	sched_avg_update(this_rq);
-}
-
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * There is no sane way to deal with nohz on smp when using jiffies because the
- * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
- * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
- *
- * Therefore we cannot use the delta approach from the regular tick since that
- * would seriously skew the load calculation. However we'll make do for those
- * updates happening while idle (nohz_idle_balance) or coming out of idle
- * (tick_nohz_idle_exit).
- *
- * This means we might still be one tick off for nohz periods.
- */
-
-/*
- * Called from nohz_idle_balance() to update the load ratings before doing the
- * idle balance.
- */
-void update_idle_cpu_load(struct rq *this_rq)
-{
-	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
-	unsigned long load = this_rq->load.weight;
-	unsigned long pending_updates;
-
-	/*
-	 * bail if there's load or we're actually up-to-date.
-	 */
-	if (load || curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
-	__update_cpu_load(this_rq, load, pending_updates);
-}
-
-/*
- * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
- */
-void update_cpu_load_nohz(void)
-{
-	struct rq *this_rq = this_rq();
-	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
-	unsigned long pending_updates;
-
-	if (curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	raw_spin_lock(&this_rq->lock);
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	if (pending_updates) {
-		this_rq->last_load_update_tick = curr_jiffies;
-		/*
-		 * We were idle, this means load 0, the current load might be
-		 * !0 due to remote wakeups and the sort.
-		 */
-		__update_cpu_load(this_rq, 0, pending_updates);
-	}
-	raw_spin_unlock(&this_rq->lock);
-}
-#endif /* CONFIG_NO_HZ_COMMON */
-
-/*
- * Called from scheduler_tick()
- */
-static void update_cpu_load_active(struct rq *this_rq)
-{
-	/*
-	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
-	 */
-	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, this_rq->load.weight, 1);
-
-	calc_load_account_active(this_rq);
-}
-
 #ifdef CONFIG_SMP
 
 /*
-- 
cgit v1.2.3-70-g09d2


From c5405a495e88d93cf9b4f4cc91507c7f4afcb901 Mon Sep 17 00:00:00 2001
From: Neil Zhang <zhangwm@marvell.com>
Date: Thu, 11 Apr 2013 21:04:59 +0800
Subject: sched: Remove redundant update_runtime notifier

migration_call() will do all the things that update_runtime() does.
So let's remove it.

Furthermore, there is potential risk that the current code will catch
BUG_ON at line 689 of rt.c when do cpu hotplug while there are realtime
threads running because of enabling runtime twice while the rt_runtime
may already changed.

Signed-off-by: Neil Zhang <zhangwm@marvell.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1365685499-26515-1-git-send-email-zhangwm@marvell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  |  3 ---
 kernel/sched/rt.c    | 40 ----------------------------------------
 kernel/sched/sched.h |  1 -
 3 files changed, 44 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bfa7e77e0b5..79e48e6a938 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6285,9 +6285,6 @@ void __init sched_init_smp(void)
 	hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
 	hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
 
-	/* RT runtime code needs to handle some hotplug events */
-	hotcpu_notifier(update_runtime, 0);
-
 	init_hrtick();
 
 	/* Move init over to a non-isolated CPU */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7aced2e3b08..8853ab17b75 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -699,15 +699,6 @@ balanced:
 	}
 }
 
-static void disable_runtime(struct rq *rq)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	__disable_runtime(rq);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
 static void __enable_runtime(struct rq *rq)
 {
 	rt_rq_iter_t iter;
@@ -732,37 +723,6 @@ static void __enable_runtime(struct rq *rq)
 	}
 }
 
-static void enable_runtime(struct rq *rq)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	__enable_runtime(rq);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
-int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-	int cpu = (int)(long)hcpu;
-
-	switch (action) {
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		disable_runtime(cpu_rq(cpu));
-		return NOTIFY_OK;
-
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		enable_runtime(cpu_rq(cpu));
-		return NOTIFY_OK;
-
-	default:
-		return NOTIFY_DONE;
-	}
-}
-
 static int balance_runtime(struct rt_rq *rt_rq)
 {
 	int more = 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f1f6256c122..c806c61a126 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1041,7 +1041,6 @@ static inline void idle_balance(int cpu, struct rq *rq)
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
-extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
-- 
cgit v1.2.3-70-g09d2


From 77bd39702f0b3840cea17681409270b16a3b93c0 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 12 Apr 2013 01:50:58 +0200
Subject: sched: Update rq clock before migrating tasks out of dying CPU

Because the sched_class::put_prev_task() callback of rt and fair
classes are referring to the rq clock to update their runtime
statistics. There is a missing rq clock update from the CPU
hotplug notifier's entry point of the scheduler.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Turner <pjt@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1365724262-20142-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 79e48e6a938..7bf0418dc60 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4378,6 +4378,13 @@ static void migrate_tasks(unsigned int dead_cpu)
 	 */
 	rq->stop = NULL;
 
+	/*
+	 * put_prev_task() and pick_next_task() sched
+	 * class method both need to have an up-to-date
+	 * value of rq->clock[_task]
+	 */
+	update_rq_clock(rq);
+
 	for ( ; ; ) {
 		/*
 		 * There's this thread running, bail when that's the only
-- 
cgit v1.2.3-70-g09d2


From 1ad4ec0dc740c4183acd6d6e367ca52b28e4fa94 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 12 Apr 2013 01:51:00 +0200
Subject: sched: Update rq clock before calling check_preempt_curr()

check_preempt_curr() of fair class needs an uptodate sched clock
value to update runtime stats of the current task of the target's rq.

When a task is woken up, activate_task() is usually called right before
ttwu_do_wakeup() unless the task is still in the runqueue. In the latter
case we need to update the rq clock explicitly because activate_task()
isn't here to do the job for us.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Turner <pjt@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1365724262-20142-4-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7bf0418dc60..46d00172ae4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1365,6 +1365,8 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p);
 	if (p->on_rq) {
+		/* check_preempt_curr() may use rq clock */
+		update_rq_clock(rq);
 		ttwu_do_wakeup(rq, p, wake_flags);
 		ret = 1;
 	}
-- 
cgit v1.2.3-70-g09d2


From 78becc27097585c6aec7043834cadde950ae79f2 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 12 Apr 2013 01:51:02 +0200
Subject: sched: Use an accessor to read the rq clock

Read the runqueue clock through an accessor. This
prepares for adding a debugging infrastructure to
detect missing or redundant calls to update_rq_clock()
between a scheduler's entry and exit point.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Turner <pjt@google.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1365724262-20142-6-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c      |  6 +++---
 kernel/sched/fair.c      | 44 ++++++++++++++++++++++----------------------
 kernel/sched/rt.c        |  8 ++++----
 kernel/sched/sched.h     | 10 ++++++++++
 kernel/sched/stats.h     |  8 ++++----
 kernel/sched/stop_task.c |  8 ++++----
 6 files changed, 47 insertions(+), 37 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 46d00172ae4..36f85be2932 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -667,7 +667,7 @@ void sched_avg_update(struct rq *rq)
 {
 	s64 period = sched_avg_period();
 
-	while ((s64)(rq->clock - rq->age_stamp) > period) {
+	while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
 		/*
 		 * Inline assembly required to prevent the compiler
 		 * optimising this loop into a divmod call.
@@ -1328,7 +1328,7 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 		p->sched_class->task_woken(rq, p);
 
 	if (rq->idle_stamp) {
-		u64 delta = rq->clock - rq->idle_stamp;
+		u64 delta = rq_clock(rq) - rq->idle_stamp;
 		u64 max = 2*sysctl_sched_migration_cost;
 
 		if (delta > max)
@@ -2106,7 +2106,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
 
 	if (task_current(rq, p)) {
 		update_rq_clock(rq);
-		ns = rq->clock_task - p->se.exec_start;
+		ns = rq_clock_task(rq) - p->se.exec_start;
 		if ((s64)ns < 0)
 			ns = 0;
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c8762a5370..3ee1c2e4ae6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -704,7 +704,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_of(cfs_rq)->clock_task;
+	u64 now = rq_clock_task(rq_of(cfs_rq));
 	unsigned long delta_exec;
 
 	if (unlikely(!curr))
@@ -736,7 +736,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
 }
 
 /*
@@ -756,14 +756,14 @@ static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
 	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
 	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 	}
 #endif
 	schedstat_set(se->statistics.wait_start, 0);
@@ -789,7 +789,7 @@ 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_task;
+	se->exec_start = rq_clock_task(rq_of(cfs_rq));
 }
 
 /**************************************************
@@ -1515,7 +1515,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 
@@ -1530,7 +1530,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	 * accumulated while sleeping.
 	 */
 	if (unlikely(se->avg.decay_count <= 0)) {
-		se->avg.last_runnable_update = rq_of(cfs_rq)->clock_task;
+		se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
 		if (se->avg.decay_count) {
 			/*
 			 * In a wake-up migration we have to approximate the
@@ -1625,7 +1625,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		tsk = task_of(se);
 
 	if (se->statistics.sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1642,7 +1642,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		}
 	}
 	if (se->statistics.block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1823,9 +1823,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 			struct task_struct *tsk = task_of(se);
 
 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
 		}
 #endif
 	}
@@ -2100,7 +2100,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 	if (unlikely(cfs_rq->throttle_count))
 		return cfs_rq->throttled_clock_task;
 
-	return rq_of(cfs_rq)->clock_task - cfs_rq->throttled_clock_task_time;
+	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
 }
 
 /* returns 0 on failure to allocate runtime */
@@ -2159,7 +2159,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 
 	/* if the deadline is ahead of our clock, nothing to do */
-	if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))
+	if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
 		return;
 
 	if (cfs_rq->runtime_remaining < 0)
@@ -2248,7 +2248,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 #ifdef CONFIG_SMP
 	if (!cfs_rq->throttle_count) {
 		/* adjust cfs_rq_clock_task() */
-		cfs_rq->throttled_clock_task_time += rq->clock_task -
+		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 	}
 #endif
@@ -2263,7 +2263,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 
 	/* group is entering throttled state, stop time */
 	if (!cfs_rq->throttle_count)
-		cfs_rq->throttled_clock_task = rq->clock_task;
+		cfs_rq->throttled_clock_task = rq_clock_task(rq);
 	cfs_rq->throttle_count++;
 
 	return 0;
@@ -2302,7 +2302,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		rq->nr_running -= task_delta;
 
 	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq->clock;
+	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 	raw_spin_unlock(&cfs_b->lock);
@@ -2323,7 +2323,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	update_rq_clock(rq);
 
 	raw_spin_lock(&cfs_b->lock);
-	cfs_b->throttled_time += rq->clock - cfs_rq->throttled_clock;
+	cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
 	list_del_rcu(&cfs_rq->throttled_list);
 	raw_spin_unlock(&cfs_b->lock);
 
@@ -2726,7 +2726,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 #else /* CONFIG_CFS_BANDWIDTH */
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 {
-	return rq_of(cfs_rq)->clock_task;
+	return rq_clock_task(rq_of(cfs_rq));
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
@@ -3966,7 +3966,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 2) too many balance attempts have failed.
 	 */
 
-	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 
@@ -4322,7 +4322,7 @@ static unsigned long scale_rt_power(int cpu)
 	age_stamp = ACCESS_ONCE(rq->age_stamp);
 	avg = ACCESS_ONCE(rq->rt_avg);
 
-	total = sched_avg_period() + (rq->clock - age_stamp);
+	total = sched_avg_period() + (rq_clock(rq) - age_stamp);
 
 	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
@@ -5261,7 +5261,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 
-	this_rq->idle_stamp = this_rq->clock;
+	this_rq->idle_stamp = rq_clock(this_rq);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8853ab17b75..8d85f9ac426 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -886,7 +886,7 @@ static void update_curr_rt(struct rq *rq)
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
-	delta_exec = rq->clock_task - curr->se.exec_start;
+	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
@@ -896,7 +896,7 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
 
-	curr->se.exec_start = rq->clock_task;
+	curr->se.exec_start = rq_clock_task(rq);
 	cpuacct_charge(curr, delta_exec);
 
 	sched_rt_avg_update(rq, delta_exec);
@@ -1345,7 +1345,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	} while (rt_rq);
 
 	p = rt_task_of(rt_se);
-	p->se.exec_start = rq->clock_task;
+	p->se.exec_start = rq_clock_task(rq);
 
 	return p;
 }
@@ -1997,7 +1997,7 @@ static void set_curr_task_rt(struct rq *rq)
 {
 	struct task_struct *p = rq->curr;
 
-	p->se.exec_start = rq->clock_task;
+	p->se.exec_start = rq_clock_task(rq);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c806c61a126..74ff659e964 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -548,6 +548,16 @@ DECLARE_PER_CPU(struct rq, runqueues);
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		(&__raw_get_cpu_var(runqueues))
 
+static inline u64 rq_clock(struct rq *rq)
+{
+	return rq->clock;
+}
+
+static inline u64 rq_clock_task(struct rq *rq)
+{
+	return rq->clock_task;
+}
+
 #ifdef CONFIG_SMP
 
 #define rcu_dereference_check_sched_domain(p) \
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 2ef90a51ec5..17d7065c387 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -61,7 +61,7 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
  */
 static inline void sched_info_dequeued(struct task_struct *t)
 {
-	unsigned long long now = task_rq(t)->clock, delta = 0;
+	unsigned long long now = rq_clock(task_rq(t)), delta = 0;
 
 	if (unlikely(sched_info_on()))
 		if (t->sched_info.last_queued)
@@ -79,7 +79,7 @@ static inline void sched_info_dequeued(struct task_struct *t)
  */
 static void sched_info_arrive(struct task_struct *t)
 {
-	unsigned long long now = task_rq(t)->clock, delta = 0;
+	unsigned long long now = rq_clock(task_rq(t)), delta = 0;
 
 	if (t->sched_info.last_queued)
 		delta = now - t->sched_info.last_queued;
@@ -100,7 +100,7 @@ static inline void sched_info_queued(struct task_struct *t)
 {
 	if (unlikely(sched_info_on()))
 		if (!t->sched_info.last_queued)
-			t->sched_info.last_queued = task_rq(t)->clock;
+			t->sched_info.last_queued = rq_clock(task_rq(t));
 }
 
 /*
@@ -112,7 +112,7 @@ static inline void sched_info_queued(struct task_struct *t)
  */
 static inline void sched_info_depart(struct task_struct *t)
 {
-	unsigned long long delta = task_rq(t)->clock -
+	unsigned long long delta = rq_clock(task_rq(t)) -
 					t->sched_info.last_arrival;
 
 	rq_sched_info_depart(task_rq(t), delta);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index da5eb5bed84..e08fbeeb54b 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -28,7 +28,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 	struct task_struct *stop = rq->stop;
 
 	if (stop && stop->on_rq) {
-		stop->se.exec_start = rq->clock_task;
+		stop->se.exec_start = rq_clock_task(rq);
 		return stop;
 	}
 
@@ -57,7 +57,7 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 	struct task_struct *curr = rq->curr;
 	u64 delta_exec;
 
-	delta_exec = rq->clock_task - curr->se.exec_start;
+	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
@@ -67,7 +67,7 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
 
-	curr->se.exec_start = rq->clock_task;
+	curr->se.exec_start = rq_clock_task(rq);
 	cpuacct_charge(curr, delta_exec);
 }
 
@@ -79,7 +79,7 @@ static void set_curr_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	stop->se.exec_start = rq->clock_task;
+	stop->se.exec_start = rq_clock_task(rq);
 }
 
 static void switched_to_stop(struct rq *rq, struct task_struct *p)
-- 
cgit v1.2.3-70-g09d2


From 4a850cbefa9592ddde3670a41c10c9576a657c43 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 4 Jun 2013 16:12:43 +0530
Subject: sched: Remove unused params of build_sched_domain()

build_sched_domain() never uses parameter struct s_data *d and so passing it is
useless.

Remove it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/545e0b4536166a15b4475abcafe5ed0db4ad4a2c.1370436120.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d8f071cc9f5..342e74419f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5943,9 +5943,8 @@ static void __sdt_free(const struct cpumask *cpu_map)
 }
 
 struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
-		struct s_data *d, const struct cpumask *cpu_map,
-		struct sched_domain_attr *attr, struct sched_domain *child,
-		int cpu)
+		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+		struct sched_domain *child, int cpu)
 {
 	struct sched_domain *sd = tl->init(tl, cpu);
 	if (!sd)
@@ -5985,7 +5984,7 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 
 		sd = NULL;
 		for (tl = sched_domain_topology; tl->init; tl++) {
-			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
+			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
-- 
cgit v1.2.3-70-g09d2


From 22da956953f371c1ee7a578c31ed8c5702cb52b1 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 4 Jun 2013 15:41:15 +0530
Subject: sched: Optimize build_sched_domains() for saving first SD node for a
 cpu

We are saving first scheduling domain for a cpu in build_sched_domains() by
iterating over the nested sd->child list. We don't actually need to do it this
way.

tl will be equal to sched_domain_topology for the first iteration and so we can
set *per_cpu_ptr(d.sd, i) based on that.  So, save pointer to first SD while
running the iteration loop over tl's.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/fc473527cbc4dfa0b8eeef2a59db74684eb59a83.1370436120.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 342e74419f8..137dcc03f66 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5985,16 +5985,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		sd = NULL;
 		for (tl = sched_domain_topology; tl->init; tl++) {
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+			if (tl == sched_domain_topology)
+				*per_cpu_ptr(d.sd, i) = sd;
 			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
 		}
-
-		while (sd->child)
-			sd = sd->child;
-
-		*per_cpu_ptr(d.sd, i) = sd;
 	}
 
 	/* Build the groups for the domains */
-- 
cgit v1.2.3-70-g09d2


From 1c6321694074163b5863c13d71c19ca953a3fb08 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 10 Jun 2013 16:27:18 +0530
Subject: sched: Don't initialize alloc_state in build_sched_domains()

alloc_state will be overwritten by __visit_domain_allocation_hell() and so we
don't actually need to initialize alloc_state.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/df57734a075cc5ad130e1ae498702e24f2529ab8.1370861520.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 137dcc03f66..3de62649869 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5969,7 +5969,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 static int build_sched_domains(const struct cpumask *cpu_map,
 			       struct sched_domain_attr *attr)
 {
-	enum s_alloc alloc_state = sa_none;
+	enum s_alloc alloc_state;
 	struct sched_domain *sd;
 	struct s_data d;
 	int i, ret = -ENOMEM;
-- 
cgit v1.2.3-70-g09d2


From c75e01288ce9c9a6b7beb6b23c07d2e4d1db8c84 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 10 Jun 2013 16:27:19 +0530
Subject: sched: Don't set sd->child to NULL when it is already NULL

Memory for sd is allocated with kzalloc_node() which will initialize its fields
with zero. In build_sched_domain() we are setting sd->child to child even if
child is NULL, which isn't required.

Lets do it only if child isn't NULL.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/f4753a1730051341003ad2ad29a3229c7356678e.1370861520.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3de62649869..88c2c0ee5a5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5955,8 +5955,8 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		sd->level = child->level + 1;
 		sched_domain_level_max = max(sched_domain_level_max, sd->level);
 		child->parent = sd;
+		sd->child = child;
 	}
-	sd->child = child;
 	set_domain_attribute(sd, attr);
 
 	return sd;
-- 
cgit v1.2.3-70-g09d2


From 27723a68caf05381b0b0bc6e127da2c9e7bcb775 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 10 Jun 2013 16:27:20 +0530
Subject: sched: Create for_each_sd_topology()

For loop for traversing sched_domain_topology was used at multiple placed in
core.c. This patch removes code redundancy by creating for_each_sd_topology().

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/e0e04542f54e9464bd9da54f5ccfe62ec6c4c0bc.1370861520.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 88c2c0ee5a5..547b7d3ff89 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5565,6 +5565,9 @@ static struct sched_domain_topology_level default_topology[] = {
 
 static struct sched_domain_topology_level *sched_domain_topology = default_topology;
 
+#define for_each_sd_topology(tl)			\
+	for (tl = sched_domain_topology; tl->init; tl++)
+
 #ifdef CONFIG_NUMA
 
 static int sched_domains_numa_levels;
@@ -5862,7 +5865,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 	struct sched_domain_topology_level *tl;
 	int j;
 
-	for (tl = sched_domain_topology; tl->init; tl++) {
+	for_each_sd_topology(tl) {
 		struct sd_data *sdd = &tl->data;
 
 		sdd->sd = alloc_percpu(struct sched_domain *);
@@ -5915,7 +5918,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 	struct sched_domain_topology_level *tl;
 	int j;
 
-	for (tl = sched_domain_topology; tl->init; tl++) {
+	for_each_sd_topology(tl) {
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
@@ -5983,7 +5986,7 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		struct sched_domain_topology_level *tl;
 
 		sd = NULL;
-		for (tl = sched_domain_topology; tl->init; tl++) {
+		for_each_sd_topology(tl) {
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-- 
cgit v1.2.3-70-g09d2


From 0936629f01bb1b11772db8c36be421365238cbec Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 11 Jun 2013 16:32:43 +0530
Subject: sched: Use cached value of span instead of calling
 sched_domain_span()

In the beginning of build_sched_groups() we called sched_domain_span() and
cached its return value in span. Few statements later we are calling it again to
get the same pointer.

Lets use the cached value instead as it hasn't changed in between.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/834ecd507071ad88aff039352dbc7e063dd996a7.1370948150.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 547b7d3ff89..3388387e133 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5347,7 +5347,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 	get_group(cpu, sdd, &sd->groups);
 	atomic_inc(&sd->groups->ref);
 
-	if (cpu != cpumask_first(sched_domain_span(sd)))
+	if (cpu != cpumask_first(span))
 		return 0;
 
 	lockdep_assert_held(&sched_domains_mutex);
-- 
cgit v1.2.3-70-g09d2


From cd08e9234c987766ad077bba80eb5a07d0855525 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 11 Jun 2013 16:32:44 +0530
Subject: sched: Fix memory leakage in build_sched_groups()

In build_sched_groups() we don't need to call get_group() for cpus
which are already covered in previous iterations. Calling get_group()
would mark the group used and eventually leak it since we wouldn't
connect it and not find it again to free it.

This will happen only in cases where sg->cpumask contained more than
one cpu (For any topology level). This patch would free sg's memory
for all cpus leaving the group leader as the group isn't marked used
now.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/7a61e955abdcbb1dfa9fe493f11a5ec53a11ddd3.1370948150.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3388387e133..014c97f0073 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5357,12 +5357,12 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 
 	for_each_cpu(i, span) {
 		struct sched_group *sg;
-		int group = get_group(i, sdd, &sg);
-		int j;
+		int group, j;
 
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
+		group = get_group(i, sdd, &sg);
 		cpumask_clear(sched_group_cpus(sg));
 		sg->sgp->power = 0;
 		cpumask_setall(sched_group_mask(sg));
-- 
cgit v1.2.3-70-g09d2


From 94c95ba69f31e435416988ddb223c92e5b0e9e83 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 11 Jun 2013 16:32:45 +0530
Subject: sched: Remove WARN_ON(!sd) from init_sched_groups_power()

sd can't be NULL in init_sched_groups_power() and so checking it for NULL isn't
useful. In case it is required, then also we need to rearrange the code a bit as
we already accessed invalid pointer sd to get sg: sg = sd->groups.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/2bbe633cd74b431c05253a8ce61fdfd5066a531b.1370948150.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 014c97f0073..21b1403a10a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5400,7 +5400,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_group *sg = sd->groups;
 
-	WARN_ON(!sd || !sg);
+	WARN_ON(!sg);
 
 	do {
 		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
-- 
cgit v1.2.3-70-g09d2


From be7002e6c613d22976f2b8d4bae6121a5fc0433a Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 12 Jun 2013 11:55:36 -0700
Subject: sched: Don't mix use of typedef ctl_table and struct ctl_table

Just use struct ctl_table.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371063336.2069.22.camel@joe-AO722
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 21b1403a10a..ceeaf0f45be 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4533,7 +4533,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 	return table;
 }
 
-static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
 {
 	struct ctl_table *entry, *table;
 	struct sched_domain *sd;
-- 
cgit v1.2.3-70-g09d2


From 141965c7494d984b2bf24efd361a3125278869c6 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@intel.com>
Date: Wed, 26 Jun 2013 13:05:39 +0800
Subject: Revert "sched: Introduce temporary FAIR_GROUP_SCHED dependency for
 load-tracking"

Remove CONFIG_FAIR_GROUP_SCHED that covers the runnable info, then
we can use runnable load variables.

Also remove 2 CONFIG_FAIR_GROUP_SCHED setting which is not in reverted
patch(introduced in 9ee474f), but also need to revert.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/51CA76A3.3050207@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  7 +------
 kernel/sched/core.c   |  7 +------
 kernel/sched/fair.c   | 17 ++++-------------
 kernel/sched/sched.h  | 19 ++-----------------
 4 files changed, 8 insertions(+), 42 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 178a8d909f1..0019befea59 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -994,12 +994,7 @@ struct sched_entity {
 	struct cfs_rq		*my_q;
 #endif
 
-/*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+#ifdef CONFIG_SMP
 	/* Per-entity load-tracking */
 	struct sched_avg	avg;
 #endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ceeaf0f45be..0241b1b55a0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1611,12 +1611,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
-/*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+#ifdef CONFIG_SMP
 	p->se.avg.runnable_avg_period = 0;
 	p->se.avg.runnable_avg_sum = 0;
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c0ac2c3b56e..36eadaaa4e5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1128,8 +1128,7 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
-#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+#ifdef CONFIG_SMP
 /*
  * We choose a half-life close to 1 scheduling period.
  * Note: The tables below are dependent on this value.
@@ -3430,12 +3429,6 @@ unlock:
 	return new_cpu;
 }
 
-/*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -3459,7 +3452,6 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
 	}
 }
-#endif
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -5861,7 +5853,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
 
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	/*
 	* Remove our load from contribution when we leave sched_fair
 	* and ensure we don't carry in an old decay_count if we
@@ -5920,7 +5912,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	atomic64_set(&cfs_rq->decay_counter, 1);
 	atomic64_set(&cfs_rq->removed_load, 0);
 #endif
@@ -6162,9 +6154,8 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
-#ifdef CONFIG_FAIR_GROUP_SCHED
 	.migrate_task_rq	= migrate_task_rq_fair,
-#endif
+
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 029601a6158..77ce668ba30 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -269,12 +269,6 @@ struct cfs_rq {
 #endif
 
 #ifdef CONFIG_SMP
-/*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
 	 * CFS Load tracking
 	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
@@ -284,9 +278,9 @@ struct cfs_rq {
 	u64 runnable_load_avg, blocked_load_avg;
 	atomic64_t decay_counter, removed_load;
 	u64 last_decay;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-/* These always depend on CONFIG_FAIR_GROUP_SCHED */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	/* Required to track per-cpu representation of a task_group */
 	u32 tg_runnable_contrib;
 	u64 tg_load_contrib;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -1027,17 +1021,8 @@ extern void update_group_power(struct sched_domain *sd, int cpu);
 extern void trigger_load_balance(struct rq *rq, int cpu);
 extern void idle_balance(int this_cpu, struct rq *this_rq);
 
-/*
- * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg
- * becomes useful in lb
- */
-#if defined(CONFIG_FAIR_GROUP_SCHED)
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
-#else
-static inline void idle_enter_fair(struct rq *this_rq) {}
-static inline void idle_exit_fair(struct rq *this_rq) {}
-#endif
 
 #else	/* CONFIG_SMP */
 
-- 
cgit v1.2.3-70-g09d2


From a75cdaa915e42ef0e6f38dc7f2a6a1deca91d648 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@intel.com>
Date: Thu, 20 Jun 2013 10:18:47 +0800
Subject: sched: Set an initial value of runnable avg for new forked task

We need to initialize the se.avg.{decay_count, load_avg_contrib} for a
new forked task. Otherwise random values of above variables cause a
mess when a new task is enqueued:

    enqueue_task_fair
        enqueue_entity
            enqueue_entity_load_avg

and make fork balancing imbalance due to incorrect load_avg_contrib.

Further more, Morten Rasmussen notice some tasks were not launched at
once after created. So Paul and Peter suggest giving a start value for
new task runnable avg time same as sched_slice().

PeterZ said:

> So the 'problem' is that our running avg is a 'floating' average; ie. it
> decays with time. Now we have to guess about the future of our newly
> spawned task -- something that is nigh impossible seeing these CPU
> vendors keep refusing to implement the crystal ball instruction.
>
> So there's two asymptotic cases we want to deal well with; 1) the case
> where the newly spawned program will be 'nearly' idle for its lifetime;
> and 2) the case where its cpu-bound.
>
> Since we have to guess, we'll go for worst case and assume its
> cpu-bound; now we don't want to make the avg so heavy adjusting to the
> near-idle case takes forever. We want to be able to quickly adjust and
> lower our running avg.
>
> Now we also don't want to make our avg too light, such that it gets
> decremented just for the new task not having had a chance to run yet --
> even if when it would run, it would be more cpu-bound than not.
>
> So what we do is we make the initial avg of the same duration as that we
> guess it takes to run each task on the system at least once -- aka
> sched_slice().
>
> Of course we can defeat this with wakeup/fork bombs, but in the 'normal'
> case it should be good enough.

Paul also contributed most of the code comments in this commit.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Reviewed-by: Paul Turner <pjt@google.com>
[peterz; added explanation of sched_slice() usage]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  |  6 ++----
 kernel/sched/fair.c  | 24 ++++++++++++++++++++++++
 kernel/sched/sched.h |  2 ++
 3 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0241b1b55a0..729e7fc7634 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1611,10 +1611,6 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
-#ifdef CONFIG_SMP
-	p->se.avg.runnable_avg_period = 0;
-	p->se.avg.runnable_avg_sum = 0;
-#endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
@@ -1758,6 +1754,8 @@ void wake_up_new_task(struct task_struct *p)
 	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
 #endif
 
+	/* Initialize new task's runnable average */
+	init_task_runnable_average(p);
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = 1;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 36eadaaa4e5..e1602a0fdbf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -680,6 +680,26 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
+#ifdef CONFIG_SMP
+static inline void __update_task_entity_contrib(struct sched_entity *se);
+
+/* Give new task start runnable values to heavy its load in infant time */
+void init_task_runnable_average(struct task_struct *p)
+{
+	u32 slice;
+
+	p->se.avg.decay_count = 0;
+	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
+	p->se.avg.runnable_avg_sum = slice;
+	p->se.avg.runnable_avg_period = slice;
+	__update_task_entity_contrib(&p->se);
+}
+#else
+void init_task_runnable_average(struct task_struct *p)
+{
+}
+#endif
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -1527,6 +1547,10 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	 * We track migrations using entity decay_count <= 0, on a wake-up
 	 * migration we use a negative decay count to track the remote decays
 	 * accumulated while sleeping.
+	 *
+	 * Newly forked tasks are enqueued with se->avg.decay_count == 0, they
+	 * are seen by enqueue_entity_load_avg() as a migration with an already
+	 * constructed load_avg_contrib.
 	 */
 	if (unlikely(se->avg.decay_count <= 0)) {
 		se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 31d25f80a7c..9c65d46504b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1048,6 +1048,8 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 
 extern void update_idle_cpu_load(struct rq *this_rq);
 
+extern void init_task_runnable_average(struct task_struct *p);
+
 #ifdef CONFIG_PARAVIRT
 static inline u64 steal_ticks(u64 steal)
 {
-- 
cgit v1.2.3-70-g09d2


From 83dfd5235ebd66c284b97befe6eabff7132333e6 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@intel.com>
Date: Thu, 20 Jun 2013 10:18:49 +0800
Subject: sched: Update cpu load after task_tick

To get the latest runnable info, we need do this cpuload update after
task_tick.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Reviewed-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-6-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 729e7fc7634..08746cc1237 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2165,8 +2165,8 @@ void scheduler_tick(void)
 
 	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
-	update_cpu_load_active(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
+	update_cpu_load_active(rq);
 	raw_spin_unlock(&rq->lock);
 
 	perf_event_task_tick();
-- 
cgit v1.2.3-70-g09d2


From 971ee28cbd1ccd87b3164facd9359a534c1d2892 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 28 Jun 2013 11:18:53 +0200
Subject: sched: Fix HRTICK

David reported that the HRTICK sched feature was borken; which was enough
motivation for me to finally fix it ;-)

We should not allow hrtimer code to do softirq wakeups while holding scheduler
locks. The hrtimer code only needs this when we accidentally try to program an
expired time. We don't much care about those anyway since we have the regular
tick to fall back to.

Reported-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20130628091853.GE29209@dyad.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9b1f2e533b9..0d8eb4525e7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -370,13 +370,6 @@ static struct rq *this_rq_lock(void)
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
- *
- * Its all a bit involved since we cannot program an hrt while holding the
- * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
- * reschedule event.
- *
- * When we get rescheduled we reprogram the hrtick_timer outside of the
- * rq->lock.
  */
 
 static void hrtick_clear(struct rq *rq)
@@ -404,6 +397,15 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 }
 
 #ifdef CONFIG_SMP
+
+static int __hrtick_restart(struct rq *rq)
+{
+	struct hrtimer *timer = &rq->hrtick_timer;
+	ktime_t time = hrtimer_get_softexpires(timer);
+
+	return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+}
+
 /*
  * called from hardirq (IPI) context
  */
@@ -412,7 +414,7 @@ static void __hrtick_start(void *arg)
 	struct rq *rq = arg;
 
 	raw_spin_lock(&rq->lock);
-	hrtimer_restart(&rq->hrtick_timer);
+	__hrtick_restart(rq);
 	rq->hrtick_csd_pending = 0;
 	raw_spin_unlock(&rq->lock);
 }
@@ -430,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	hrtimer_set_expires(timer, time);
 
 	if (rq == this_rq()) {
-		hrtimer_restart(timer);
+		__hrtick_restart(rq);
 	} else if (!rq->hrtick_csd_pending) {
 		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
 		rq->hrtick_csd_pending = 1;
-- 
cgit v1.2.3-70-g09d2


From 0db0628d90125193280eabb501c94feaf48fa9ab Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Wed, 19 Jun 2013 14:53:51 -0400
Subject: kernel: delete __cpuinit usage from all core kernel files

The __cpuinit type of throwaway sections might have made sense
some time ago when RAM was more constrained, but now the savings
do not offset the cost and complications.  For example, the fix in
commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time")
is a good example of the nasty type of bugs that can be created
with improper use of the various __init prefixes.

After a discussion on LKML[1] it was decided that cpuinit should go
the way of devinit and be phased out.  Once all the users are gone,
we can then finally remove the macros themselves from linux/init.h.

This removes all the uses of the __cpuinit macros from C files in
the core kernel directories (kernel, init, lib, mm, and include)
that don't really have a specific maintainer.

[1] https://lkml.org/lkml/2013/5/20/589

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 Documentation/cpu-hotplug.txt |  6 +++---
 include/linux/cpu.h           |  2 +-
 include/linux/perf_event.h    |  2 +-
 init/calibrate.c              | 13 ++++++++-----
 kernel/cpu.c                  |  6 +++---
 kernel/events/core.c          |  4 ++--
 kernel/fork.c                 |  2 +-
 kernel/hrtimer.c              |  6 +++---
 kernel/printk.c               |  2 +-
 kernel/profile.c              |  2 +-
 kernel/relay.c                |  2 +-
 kernel/sched/core.c           | 12 ++++++------
 kernel/sched/fair.c           |  2 +-
 kernel/smp.c                  |  2 +-
 kernel/smpboot.c              |  2 +-
 kernel/softirq.c              |  8 ++++----
 kernel/time/tick-sched.c      |  2 +-
 kernel/timer.c                | 10 +++++-----
 kernel/workqueue.c            |  4 ++--
 lib/Kconfig.debug             |  2 +-
 lib/earlycpio.c               |  2 +-
 lib/percpu_counter.c          |  2 +-
 mm/memcontrol.c               |  2 +-
 mm/page-writeback.c           |  4 ++--
 mm/slab.c                     | 10 +++++-----
 mm/slub.c                     |  4 ++--
 mm/vmstat.c                   |  6 +++---
 27 files changed, 62 insertions(+), 59 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index edd4b4df393..786dc82f98c 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -267,8 +267,8 @@ Q: If i have some kernel code that needs to be aware of CPU arrival and
 A: This is what you would need in your kernel code to receive notifications.
 
 	#include <linux/cpu.h>
-	static int __cpuinit foobar_cpu_callback(struct notifier_block *nfb,
-					    unsigned long action, void *hcpu)
+	static int foobar_cpu_callback(struct notifier_block *nfb,
+				       unsigned long action, void *hcpu)
 	{
 		unsigned int cpu = (unsigned long)hcpu;
 
@@ -285,7 +285,7 @@ A: This is what you would need in your kernel code to receive notifications.
 		return NOTIFY_OK;
 	}
 
-	static struct notifier_block __cpuinitdata foobar_cpu_notifer =
+	static struct notifier_block foobar_cpu_notifer =
 	{
 	   .notifier_call = foobar_cpu_callback,
 	};
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 944f283f01c..ab0eade7303 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -114,7 +114,7 @@ enum {
 /* Need to know about CPUs going up/down? */
 #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
 #define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb __cpuinitdata =	\
+	static struct notifier_block fn##_nb =			\
 		{ .notifier_call = fn, .priority = pri };	\
 	register_cpu_notifier(&fn##_nb);			\
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8873f82c7ba..c43f6eabad5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -826,7 +826,7 @@ static inline void perf_restore_debug_store(void)			{ }
  */
 #define perf_cpu_notifier(fn)						\
 do {									\
-	static struct notifier_block fn##_nb __cpuinitdata =		\
+	static struct notifier_block fn##_nb =				\
 		{ .notifier_call = fn, .priority = CPU_PRI_PERF };	\
 	unsigned long cpu = smp_processor_id();				\
 	unsigned long flags;						\
diff --git a/init/calibrate.c b/init/calibrate.c
index fda0a7b0f06..520702db9ac 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -31,7 +31,7 @@ __setup("lpj=", lpj_setup);
 #define DELAY_CALIBRATION_TICKS			((HZ < 100) ? 1 : (HZ/100))
 #define MAX_DIRECT_CALIBRATION_RETRIES		5
 
-static unsigned long __cpuinit calibrate_delay_direct(void)
+static unsigned long calibrate_delay_direct(void)
 {
 	unsigned long pre_start, start, post_start;
 	unsigned long pre_end, end, post_end;
@@ -166,7 +166,10 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
 	return 0;
 }
 #else
-static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
+static unsigned long calibrate_delay_direct(void)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -180,7 +183,7 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
  */
 #define LPS_PREC 8
 
-static unsigned long __cpuinit calibrate_delay_converge(void)
+static unsigned long calibrate_delay_converge(void)
 {
 	/* First stage - slowly accelerate to find initial bounds */
 	unsigned long lpj, lpj_base, ticks, loopadd, loopadd_base, chop_limit;
@@ -254,12 +257,12 @@ static DEFINE_PER_CPU(unsigned long, cpu_loops_per_jiffy) = { 0 };
  * Architectures should override this function if a faster calibration
  * method is available.
  */
-unsigned long __attribute__((weak)) __cpuinit calibrate_delay_is_known(void)
+unsigned long __attribute__((weak)) calibrate_delay_is_known(void)
 {
 	return 0;
 }
 
-void __cpuinit calibrate_delay(void)
+void calibrate_delay(void)
 {
 	unsigned long lpj;
 	static bool printed;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 198a38883e6..b2b227b8212 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -366,7 +366,7 @@ EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /* Requires cpu_add_remove_lock to be held */
-static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
+static int _cpu_up(unsigned int cpu, int tasks_frozen)
 {
 	int ret, nr_calls = 0;
 	void *hcpu = (void *)(long)cpu;
@@ -419,7 +419,7 @@ out:
 	return ret;
 }
 
-int __cpuinit cpu_up(unsigned int cpu)
+int cpu_up(unsigned int cpu)
 {
 	int err = 0;
 
@@ -618,7 +618,7 @@ core_initcall(cpu_hotplug_pm_sync_init);
  * It must be called by the arch code on the new cpu, before the new cpu
  * enables interrupts and before the "boot" cpu returns from __cpu_up().
  */
-void __cpuinit notify_cpu_starting(unsigned int cpu)
+void notify_cpu_starting(unsigned int cpu)
 {
 	unsigned long val = CPU_STARTING;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eba8fb5834a..f3e9dce39bc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7630,7 +7630,7 @@ static void __init perf_event_init_all_cpus(void)
 	}
 }
 
-static void __cpuinit perf_event_init_cpu(int cpu)
+static void perf_event_init_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
@@ -7719,7 +7719,7 @@ static struct notifier_block perf_reboot_notifier = {
 	.priority = INT_MIN,
 };
 
-static int __cpuinit
+static int
 perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
diff --git a/kernel/fork.c b/kernel/fork.c
index 66635c80a81..403d2bb8a96 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1546,7 +1546,7 @@ static inline void init_idle_pids(struct pid_link *links)
 	}
 }
 
-struct task_struct * __cpuinit fork_idle(int cpu)
+struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
 	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f0f4fe29cd2..383319bae3f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1659,7 +1659,7 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 /*
  * Functions related to boot-time initialization:
  */
-static void __cpuinit init_hrtimers_cpu(int cpu)
+static void init_hrtimers_cpu(int cpu)
 {
 	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
@@ -1740,7 +1740,7 @@ static void migrate_hrtimers(int scpu)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
+static int hrtimer_cpu_notify(struct notifier_block *self,
 					unsigned long action, void *hcpu)
 {
 	int scpu = (long)hcpu;
@@ -1773,7 +1773,7 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata hrtimers_nb = {
+static struct notifier_block hrtimers_nb = {
 	.notifier_call = hrtimer_cpu_notify,
 };
 
diff --git a/kernel/printk.c b/kernel/printk.c
index d37d45c90ae..69b0890ed7e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1921,7 +1921,7 @@ void resume_console(void)
  * called when a new CPU comes online (or fails to come up), and ensures
  * that any such output gets printed.
  */
-static int __cpuinit console_cpu_notify(struct notifier_block *self,
+static int console_cpu_notify(struct notifier_block *self,
 	unsigned long action, void *hcpu)
 {
 	switch (action) {
diff --git a/kernel/profile.c b/kernel/profile.c
index 0bf40073766..6631e1ef55a 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -331,7 +331,7 @@ out:
 	put_cpu();
 }
 
-static int __cpuinit profile_cpu_callback(struct notifier_block *info,
+static int profile_cpu_callback(struct notifier_block *info,
 					unsigned long action, void *__cpu)
 {
 	int node, cpu = (unsigned long)__cpu;
diff --git a/kernel/relay.c b/kernel/relay.c
index b91488ba2e5..5001c9887db 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -516,7 +516,7 @@ static void setup_callbacks(struct rchan *chan,
  *
  * 	Returns the success/failure of the operation. (%NOTIFY_OK, %NOTIFY_BAD)
  */
-static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
+static int relay_hotcpu_callback(struct notifier_block *nb,
 				unsigned long action,
 				void *hcpu)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0d8eb4525e7..b7c32cb7bfe 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4133,7 +4133,7 @@ void show_state_filter(unsigned long state_filter)
 		debug_show_all_locks();
 }
 
-void __cpuinit init_idle_bootup_task(struct task_struct *idle)
+void init_idle_bootup_task(struct task_struct *idle)
 {
 	idle->sched_class = &idle_sched_class;
 }
@@ -4146,7 +4146,7 @@ void __cpuinit init_idle_bootup_task(struct task_struct *idle)
  * NOTE: this function does not set the idle thread's NEED_RESCHED
  * flag, to make booting more robust.
  */
-void __cpuinit init_idle(struct task_struct *idle, int cpu)
+void init_idle(struct task_struct *idle, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
@@ -4630,7 +4630,7 @@ static void set_rq_offline(struct rq *rq)
  * migration_call - callback that gets triggered when a CPU is added.
  * Here we can start up the necessary migration thread for the new CPU.
  */
-static int __cpuinit
+static int
 migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int cpu = (long)hcpu;
@@ -4684,12 +4684,12 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
  * happens before everything else.  This has to be lower priority than
  * the notifier in the perf_event subsystem, though.
  */
-static struct notifier_block __cpuinitdata migration_notifier = {
+static struct notifier_block migration_notifier = {
 	.notifier_call = migration_call,
 	.priority = CPU_PRI_MIGRATION,
 };
 
-static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
+static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
@@ -4702,7 +4702,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
 	}
 }
 
-static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
+static int sched_cpu_inactive(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f77f9c52744..bb456f44b7b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5506,7 +5506,7 @@ void nohz_balance_enter_idle(int cpu)
 	set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
 }
 
-static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb,
+static int sched_ilb_notifier(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
diff --git a/kernel/smp.c b/kernel/smp.c
index 4dba0f7b72a..fe9f773d711 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -73,7 +73,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
+static struct notifier_block hotplug_cfd_notifier = {
 	.notifier_call		= hotplug_cfd,
 };
 
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 02fc5c93367..eb89e180740 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -24,7 +24,7 @@
  */
 static DEFINE_PER_CPU(struct task_struct *, idle_threads);
 
-struct task_struct * __cpuinit idle_thread_get(unsigned int cpu)
+struct task_struct *idle_thread_get(unsigned int cpu)
 {
 	struct task_struct *tsk = per_cpu(idle_threads, cpu);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index ca25e6e704a..be3d3514c32 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -699,7 +699,7 @@ void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
 }
 EXPORT_SYMBOL(send_remote_softirq);
 
-static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
+static int remote_softirq_cpu_notify(struct notifier_block *self,
 					       unsigned long action, void *hcpu)
 {
 	/*
@@ -728,7 +728,7 @@ static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
+static struct notifier_block remote_softirq_cpu_notifier = {
 	.notifier_call	= remote_softirq_cpu_notify,
 };
 
@@ -830,7 +830,7 @@ static void takeover_tasklets(unsigned int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit cpu_callback(struct notifier_block *nfb,
+static int cpu_callback(struct notifier_block *nfb,
 				  unsigned long action,
 				  void *hcpu)
 {
@@ -845,7 +845,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata cpu_nfb = {
+static struct notifier_block cpu_nfb = {
 	.notifier_call = cpu_callback
 };
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 69601726a74..e80183f4a6c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -298,7 +298,7 @@ static int __init tick_nohz_full_setup(char *str)
 }
 __setup("nohz_full=", tick_nohz_full_setup);
 
-static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb,
+static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
 						 unsigned long action,
 						 void *hcpu)
 {
diff --git a/kernel/timer.c b/kernel/timer.c
index 15bc1b41021..4296d13db3d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1505,11 +1505,11 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 }
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
-static int __cpuinit init_timers_cpu(int cpu)
+static int init_timers_cpu(int cpu)
 {
 	int j;
 	struct tvec_base *base;
-	static char __cpuinitdata tvec_base_done[NR_CPUS];
+	static char tvec_base_done[NR_CPUS];
 
 	if (!tvec_base_done[cpu]) {
 		static char boot_done;
@@ -1577,7 +1577,7 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea
 	}
 }
 
-static void __cpuinit migrate_timers(int cpu)
+static void migrate_timers(int cpu)
 {
 	struct tvec_base *old_base;
 	struct tvec_base *new_base;
@@ -1610,7 +1610,7 @@ static void __cpuinit migrate_timers(int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit timer_cpu_notify(struct notifier_block *self,
+static int timer_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
@@ -1635,7 +1635,7 @@ static int __cpuinit timer_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata timers_nb = {
+static struct notifier_block timers_nb = {
 	.notifier_call	= timer_cpu_notify,
 };
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f02c4a4a0c3..0b72e816b8d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4644,7 +4644,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
  * Workqueues should be brought up before normal priority CPU notifiers.
  * This will be registered high priority CPU notifier.
  */
-static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb,
+static int workqueue_cpu_up_callback(struct notifier_block *nfb,
 					       unsigned long action,
 					       void *hcpu)
 {
@@ -4697,7 +4697,7 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb,
  * Workqueues should be brought down after normal priority CPU notifiers.
  * This will be registered as low priority CPU notifier.
  */
-static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb,
+static int workqueue_cpu_down_callback(struct notifier_block *nfb,
 						 unsigned long action,
 						 void *hcpu)
 {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 98ac17ed622..1501aa55322 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -238,7 +238,7 @@ config DEBUG_SECTION_MISMATCH
 	  any use of code/data previously in these sections would
 	  most likely result in an oops.
 	  In the code, functions and variables are annotated with
-	  __init, __cpuinit, etc. (see the full list in include/linux/init.h),
+	  __init,, etc. (see the full list in include/linux/init.h),
 	  which results in the code/data being placed in specific sections.
 	  The section mismatch analysis is always performed after a full
 	  kernel build, and enabling this option causes the following
diff --git a/lib/earlycpio.c b/lib/earlycpio.c
index 8078ef49cb7..7aa7ce250c9 100644
--- a/lib/earlycpio.c
+++ b/lib/earlycpio.c
@@ -63,7 +63,7 @@ enum cpio_fields {
  *          the match returned an empty filename string.
  */
 
-struct cpio_data __cpuinit find_cpio_data(const char *path, void *data,
+struct cpio_data find_cpio_data(const char *path, void *data,
 					  size_t len,  long *offset)
 {
 	const size_t cpio_header_len = 8*C_NFIELDS - 2;
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 1fc23a3277e..93c5d5ecff4 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -158,7 +158,7 @@ static void compute_batch_value(void)
 	percpu_counter_batch = max(32, nr*2);
 }
 
-static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
+static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
 					unsigned long action, void *hcpu)
 {
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d12ca6f3c29..00a7a664b9c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2522,7 +2522,7 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
 	spin_unlock(&memcg->pcp_counter_lock);
 }
 
-static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
+static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 					unsigned long action,
 					void *hcpu)
 {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4514ad7415c..3f0c895c71f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1619,7 +1619,7 @@ void writeback_set_ratelimit(void)
 		ratelimit_pages = 16;
 }
 
-static int __cpuinit
+static int
 ratelimit_handler(struct notifier_block *self, unsigned long action,
 		  void *hcpu)
 {
@@ -1634,7 +1634,7 @@ ratelimit_handler(struct notifier_block *self, unsigned long action,
 	}
 }
 
-static struct notifier_block __cpuinitdata ratelimit_nb = {
+static struct notifier_block ratelimit_nb = {
 	.notifier_call	= ratelimit_handler,
 	.next		= NULL,
 };
diff --git a/mm/slab.c b/mm/slab.c
index 35cb0c86150..2580db062df 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -787,7 +787,7 @@ static void next_reap_node(void)
  * the CPUs getting into lockstep and contending for the global cache chain
  * lock.
  */
-static void __cpuinit start_cpu_timer(int cpu)
+static void start_cpu_timer(int cpu)
 {
 	struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
 
@@ -1186,7 +1186,7 @@ static inline int slabs_tofree(struct kmem_cache *cachep,
 	return (n->free_objects + cachep->num - 1) / cachep->num;
 }
 
-static void __cpuinit cpuup_canceled(long cpu)
+static void cpuup_canceled(long cpu)
 {
 	struct kmem_cache *cachep;
 	struct kmem_cache_node *n = NULL;
@@ -1251,7 +1251,7 @@ free_array_cache:
 	}
 }
 
-static int __cpuinit cpuup_prepare(long cpu)
+static int cpuup_prepare(long cpu)
 {
 	struct kmem_cache *cachep;
 	struct kmem_cache_node *n = NULL;
@@ -1334,7 +1334,7 @@ bad:
 	return -ENOMEM;
 }
 
-static int __cpuinit cpuup_callback(struct notifier_block *nfb,
+static int cpuup_callback(struct notifier_block *nfb,
 				    unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
@@ -1390,7 +1390,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block __cpuinitdata cpucache_notifier = {
+static struct notifier_block cpucache_notifier = {
 	&cpuup_callback, NULL, 0
 };
 
diff --git a/mm/slub.c b/mm/slub.c
index 3b482c86300..2b02d666bf6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3773,7 +3773,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
  * Use the cpu notifier to insure that the cpu slabs are flushed when
  * necessary.
  */
-static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
+static int slab_cpuup_callback(struct notifier_block *nfb,
 		unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
@@ -3799,7 +3799,7 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata slab_notifier = {
+static struct notifier_block slab_notifier = {
 	.notifier_call = slab_cpuup_callback
 };
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f42745e6578..20c2ef4458f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1182,7 +1182,7 @@ static void vmstat_update(struct work_struct *w)
 		round_jiffies_relative(sysctl_stat_interval));
 }
 
-static void __cpuinit start_cpu_timer(int cpu)
+static void start_cpu_timer(int cpu)
 {
 	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
@@ -1194,7 +1194,7 @@ static void __cpuinit start_cpu_timer(int cpu)
  * Use the cpu notifier to insure that the thresholds are recalculated
  * when necessary.
  */
-static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
+static int vmstat_cpuup_callback(struct notifier_block *nfb,
 		unsigned long action,
 		void *hcpu)
 {
@@ -1226,7 +1226,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata vmstat_notifier =
+static struct notifier_block vmstat_notifier =
 	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
-- 
cgit v1.2.3-70-g09d2


From e69f61862ab833e9b8d3c15b6ce07fd69f3bfecc Mon Sep 17 00:00:00 2001
From: Yacine Belkadi <yacine.belkadi.1@gmail.com>
Date: Fri, 12 Jul 2013 20:45:47 +0200
Subject: sched: Fix some kernel-doc warnings

When building the htmldocs (in verbose mode), scripts/kernel-doc
reports the follwing type of warnings:

  Warning(kernel/sched/core.c:936): No description found for return value of 'task_curr'
  ...

Fix those by:

 - adding the missing descriptions
 - using "Return" sections for the descriptions

Signed-off-by: Yacine Belkadi <yacine.belkadi.1@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1373654747-2389-1-git-send-email-yacine.belkadi.1@gmail.com
[ While at it, fix the cpupri_set() explanation. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  6 ++++
 kernel/sched/core.c   | 82 ++++++++++++++++++++++++++++++++++++++-------------
 kernel/sched/cpupri.c |  4 +--
 kernel/sched/fair.c   |  9 ++++--
 4 files changed, 76 insertions(+), 25 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50d04b92ced..82300247974 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1532,6 +1532,8 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
  * Test if a process is not yet dead (at most zombie state)
  * If pid_alive fails, then pointers within the task structure
  * can be stale and must not be dereferenced.
+ *
+ * Return: 1 if the process is alive. 0 otherwise.
  */
 static inline int pid_alive(struct task_struct *p)
 {
@@ -1543,6 +1545,8 @@ static inline int pid_alive(struct task_struct *p)
  * @tsk: Task structure to be checked.
  *
  * Check if a task structure is the first user space task the kernel created.
+ *
+ * Return: 1 if the task structure is init. 0 otherwise.
  */
 static inline int is_global_init(struct task_struct *tsk)
 {
@@ -1893,6 +1897,8 @@ extern struct task_struct *idle_task(int cpu);
 /**
  * is_idle_task - is the specified task an idle task?
  * @p: the task in question.
+ *
+ * Return: 1 if @p is an idle task. 0 otherwise.
  */
 static inline bool is_idle_task(const struct task_struct *p)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0d8eb4525e7..4c3967f91e2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -933,6 +933,8 @@ static int effective_prio(struct task_struct *p)
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
+ *
+ * Return: 1 if the task is currently executing. 0 otherwise.
  */
 inline int task_curr(const struct task_struct *p)
 {
@@ -1482,7 +1484,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
  * the simpler "current->state = TASK_RUNNING" to mark yourself
  * runnable without the overhead of this.
  *
- * Returns %true if @p was woken up, %false if it was already running
+ * Return: %true if @p was woken up, %false if it was already running.
  * or @state didn't match @p's state.
  */
 static int
@@ -1577,8 +1579,9 @@ out:
  * @p: The process to be woken up.
  *
  * Attempt to wake up the nominated process and move it to the set of runnable
- * processes.  Returns 1 if the process was woken up, 0 if it was already
- * running.
+ * processes.
+ *
+ * Return: 1 if the process was woken up, 0 if it was already running.
  *
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
@@ -2191,6 +2194,8 @@ void scheduler_tick(void)
  * This makes sure that uptime, CFS vruntime, load
  * balancing, etc... continue to move forward, even
  * with a very low granularity.
+ *
+ * Return: Maximum deferment in nanoseconds.
  */
 u64 scheduler_tick_max_deferment(void)
 {
@@ -2796,8 +2801,8 @@ EXPORT_SYMBOL(wait_for_completion);
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible.
  *
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -2829,8 +2834,8 @@ EXPORT_SYMBOL(wait_for_completion_io);
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible. The caller is accounted as waiting for IO.
  *
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
@@ -2846,7 +2851,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout);
  * This waits for completion of a specific task to be signaled. It is
  * interruptible.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
@@ -2865,8 +2870,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  * 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.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
@@ -2883,7 +2888,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
  * This waits to be signaled for completion of a specific task. It can be
  * interrupted by a kill signal.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_killable(struct completion *x)
 {
@@ -2903,8 +2908,8 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_killable_timeout(struct completion *x,
@@ -2918,7 +2923,7 @@ EXPORT_SYMBOL(wait_for_completion_killable_timeout);
  *	try_wait_for_completion - try to decrement a completion without blocking
  *	@x:	completion structure
  *
- *	Returns: 0 if a decrement cannot be done without blocking
+ *	Return: 0 if a decrement cannot be done without blocking
  *		 1 if a decrement succeeded.
  *
  *	If a completion is being used as a counting completion,
@@ -2945,7 +2950,7 @@ EXPORT_SYMBOL(try_wait_for_completion);
  *	completion_done - Test to see if a completion has any waiters
  *	@x:	completion structure
  *
- *	Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *	Return: 0 if there are waiters (wait_for_completion() in progress)
  *		 1 if there are no waiters.
  *
  */
@@ -3182,7 +3187,7 @@ SYSCALL_DEFINE1(nice, int, increment)
  * task_prio - return the priority value of a given task.
  * @p: the task in question.
  *
- * This is the priority value as seen by users in /proc.
+ * Return: The priority value as seen by users in /proc.
  * RT tasks are offset by -200. Normal tasks are centered
  * around 0, value goes from -16 to +15.
  */
@@ -3194,6 +3199,8 @@ int task_prio(const struct task_struct *p)
 /**
  * task_nice - return the nice value of a given task.
  * @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
  */
 int task_nice(const struct task_struct *p)
 {
@@ -3204,6 +3211,8 @@ EXPORT_SYMBOL(task_nice);
 /**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
  */
 int idle_cpu(int cpu)
 {
@@ -3226,6 +3235,8 @@ int idle_cpu(int cpu)
 /**
  * idle_task - return the idle task for a given cpu.
  * @cpu: the processor in question.
+ *
+ * Return: The idle task for the cpu @cpu.
  */
 struct task_struct *idle_task(int cpu)
 {
@@ -3235,6 +3246,8 @@ struct task_struct *idle_task(int cpu)
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
+ *
+ * The task of @pid, if found. %NULL otherwise.
  */
 static struct task_struct *find_process_by_pid(pid_t pid)
 {
@@ -3432,6 +3445,8 @@ recheck:
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Return: 0 on success. An error code otherwise.
+ *
  * NOTE that the task may be already dead.
  */
 int sched_setscheduler(struct task_struct *p, int policy,
@@ -3451,6 +3466,8 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
  * current context has permission.  For example, this is needed in
  * stop_machine(): we create temporary high priority worker threads,
  * but our caller might not have that capability.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 			       const struct sched_param *param)
@@ -3485,6 +3502,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @pid: the pid in question.
  * @policy: new policy.
  * @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
 		struct sched_param __user *, param)
@@ -3500,6 +3519,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
  * sys_sched_setparam - set/change the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
@@ -3509,6 +3530,9 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 /**
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
+ *
+ * Return: On success, the policy of the thread. Otherwise, a negative error
+ * code.
  */
 SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 {
@@ -3535,6 +3559,9 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
+ *
+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
+ * code.
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
@@ -3659,6 +3686,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to the new cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
 		unsigned long __user *, user_mask_ptr)
@@ -3710,6 +3739,8 @@ out_unlock:
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 		unsigned long __user *, user_mask_ptr)
@@ -3744,6 +3775,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
  *
  * This function yields the current CPU to other tasks. If there are no
  * other threads running on this CPU then this function will return.
+ *
+ * Return: 0.
  */
 SYSCALL_DEFINE0(sched_yield)
 {
@@ -3869,7 +3902,7 @@ EXPORT_SYMBOL(yield);
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
  *
- * Returns:
+ * Return:
  *	true (>0) if we indeed boosted the target task.
  *	false (0) if we failed to boost the target.
  *	-ESRCH if there's no task to yield to.
@@ -3972,8 +4005,9 @@ long __sched io_schedule_timeout(long timeout)
  * sys_sched_get_priority_max - return maximum RT priority.
  * @policy: scheduling class.
  *
- * this syscall returns the maximum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the maximum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
  */
 SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 {
@@ -3997,8 +4031,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
  * sys_sched_get_priority_min - return minimum RT priority.
  * @policy: scheduling class.
  *
- * this syscall returns the minimum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the minimum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
  */
 SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 {
@@ -4024,6 +4059,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
  *
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
  */
 SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 		struct timespec __user *, interval)
@@ -6632,6 +6670,8 @@ void normalize_rt_tasks(void)
  * @cpu: the processor in question.
  *
  * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ *
+ * Return: The current task for @cpu.
  */
 struct task_struct *curr_task(int cpu)
 {
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 1095e878a46..8b836b376d9 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -62,7 +62,7 @@ static int convert_prio(int prio)
  * any discrepancies created by racing against the uncertainty of the current
  * priority configuration.
  *
- * Returns: (int)bool - CPUs were found
+ * Return: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
 		struct cpumask *lowest_mask)
@@ -203,7 +203,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
  * cpupri_init - initialize the cpupri structure
  * @cp: The cpupri context
  *
- * Returns: -ENOMEM if memory fails.
+ * Return: -ENOMEM on memory allocation failure.
  */
 int cpupri_init(struct cpupri *cp)
 {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f77f9c52744..98d135584b4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4280,6 +4280,8 @@ struct sg_lb_stats {
  * get_sd_load_idx - Obtain the load index for a given sched domain.
  * @sd: The sched_domain whose load_idx is to be obtained.
  * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ *
+ * Return: The load index.
  */
 static inline int get_sd_load_idx(struct sched_domain *sd,
 					enum cpu_idle_type idle)
@@ -4574,6 +4576,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
  *
  * Determine if @sg is a busier group than the previously selected
  * busiest group.
+ *
+ * Return: %true if @sg is a busier group than the previously selected
+ * busiest group. %false otherwise.
  */
 static bool update_sd_pick_busiest(struct lb_env *env,
 				   struct sd_lb_stats *sds,
@@ -4691,7 +4696,7 @@ static inline void update_sd_lb_stats(struct lb_env *env,
  * assuming lower CPU number will be equivalent to lower a SMT thread
  * number.
  *
- * Returns 1 when packing is required and a task should be moved to
+ * Return: 1 when packing is required and a task should be moved to
  * this CPU.  The amount of the imbalance is returned in *imbalance.
  *
  * @env: The load balancing environment.
@@ -4869,7 +4874,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * @balance: Pointer to a variable indicating if this_cpu
  *	is the appropriate cpu to perform load balancing at this_level.
  *
- * Returns:	- the busiest group if imbalance exists.
+ * Return:	- The busiest group if imbalance exists.
  *		- If no imbalance and user has opted for power-savings balance,
  *		   return the least loaded group whose CPUs can be
  *		   put to idle by rebalancing its tasks onto our group.
-- 
cgit v1.2.3-70-g09d2


From e0acd0a68ec7dbf6b7a81a87a867ebd7ac9b76c4 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 12 Aug 2013 18:14:00 +0200
Subject: sched: fix the theoretical signal_wake_up() vs schedule() race

This is only theoretical, but after try_to_wake_up(p) was changed
to check p->state under p->pi_lock the code like

	__set_current_state(TASK_INTERRUPTIBLE);
	schedule();

can miss a signal. This is the special case of wait-for-condition,
it relies on try_to_wake_up/schedule interaction and thus it does
not need mb() between __set_current_state() and if(signal_pending).

However, this __set_current_state() can move into the critical
section protected by rq->lock, now that try_to_wake_up() takes
another lock we need to ensure that it can't be reordered with
"if (signal_pending(current))" check inside that section.

The patch is actually one-liner, it simply adds smp_wmb() before
spin_lock_irq(rq->lock). This is what try_to_wake_up() already
does by the same reason.

We turn this wmb() into the new helper, smp_mb__before_spinlock(),
for better documentation and to allow the architectures to change
the default implementation.

While at it, kill smp_mb__after_lock(), it has no callers.

Perhaps we can also add smp_mb__before/after_spinunlock() for
prepare_to_wait().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/spinlock.h |  4 ----
 include/linux/spinlock.h        | 14 +++++++++++---
 kernel/sched/core.c             | 14 +++++++++++++-
 3 files changed, 24 insertions(+), 8 deletions(-)

(limited to 'kernel/sched/core.c')

diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692eaabab..e3ddd7db723 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 7d537ced949..75f34949d9a 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -117,9 +117,17 @@ do {								\
 #endif /*arch_spin_is_contended*/
 #endif
 
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
+/*
+ * Despite its name it doesn't necessarily has to be a full barrier.
+ * It should only guarantee that a STORE before the critical section
+ * can not be reordered with a LOAD inside this section.
+ * spin_lock() is the one-way barrier, this LOAD can not escape out
+ * of the region. So the default implementation simply ensures that
+ * a STORE can not move into the critical section, smp_wmb() should
+ * serialize it with another STORE done by spin_lock().
+ */
+#ifndef smp_mb__before_spinlock
+#define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
 /**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb7bfe..ef51b0ef4bd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1491,7 +1491,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	unsigned long flags;
 	int cpu, success = 0;
 
-	smp_wmb();
+	/*
+	 * If we are going to wake up a thread waiting for CONDITION we
+	 * need to ensure that CONDITION=1 done by the caller can not be
+	 * reordered with p->state check below. This pairs with mb() in
+	 * set_current_state() the waiting thread does.
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	if (!(p->state & state))
 		goto out;
@@ -2394,6 +2400,12 @@ need_resched:
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	/*
+	 * Make sure that signal_pending_state()->signal_pending() below
+	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+	 * done by the caller to avoid the race with signal_wake_up().
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irq(&rq->lock);
 
 	switch_count = &prev->nivcsw;
-- 
cgit v1.2.3-70-g09d2