Skip to contentSkip to conversation

scheduler tree updates for v3.20

GIT PULL Ingo Molnar 1 participant 1 message Feb 9, 2015

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest sched-core-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-core-for-linus

# HEAD: 139b6fd26d85a65c4e0d2795b87b94f9505e5943 sched/Documentation: Remove unneeded word

The main scheduler changes in this cycle were:

- various sched/deadline fixes and enhancements

- rescheduling latency fixes/cleanups

- rework the rq->clock code to be more consistent and more robust.

- minor micro-optimizations

- ->avg.decay_count fixes

- add a stack overflow check to might_sleep()

- idle-poll handler fix, possibly resulting in power savings

- misc smaller updates and fixes

Thanks,

Ingo

------------------>
Eric Sandeen (1):
sched/debug: Check for stack overflow in ___might_sleep()

Frederic Weisbecker (2):
sched: Fix missing preemption opportunity
sched: Pull resched loop to __schedule() callers

Johan Hedberg (1):
sched/wait: Introduce wait_on_bit_timeout()

Kirill Tkhai (1):
sched/fair: Fix sched_entity::avg::decay_count initialization

Peter Zijlstra (4):
sched/core: Validate rq_clock*() serialization sched/core: Rework rq->clock update skips sched/debug: Print rq->clock_task sched/deadline: Fix stale yield state

Preeti U Murthy (1):
sched/idle: Add missing checks to the exit condition of cpu_idle_poll()

Sharon Dvir (1):
sched/Documentation: Remove unneeded word

Tetsuo Handa (1):
sched/debug: Fix potential call to __ffs(0) in sched_show_task()

Tim Chen (1):
sched/rt: Reduce rq lock contention by eliminating locking of non-feasible target

Wanpeng Li (3):
sched/deadline: Fix hrtick for a non-leftmost task sched/deadline: Avoid pointless __setscheduler()
sched: Fix hrtick_start() on UP

Xunlei Pang (3):
sched/fair: Fix the dealing with decay_count in __synchronize_entity_decay() sched/deadline: Modify cpudl::free_cpus to reflect rd->online sched/deadline: Remove cpu_active_mask from cpudl_find()

Yao Dongdong (1):

      sched/core: Remove check of p->sched_class
 include/linux/wait.h       |  26 +++++++++++
 kernel/locking/mutex.c     |   2 +-
 kernel/sched/core.c        | 107 +++++++++++++++++++++++++++++----------------
 kernel/sched/cpudeadline.c |  27 ++++++++++--
 kernel/sched/cpudeadline.h |   2 +
 kernel/sched/deadline.c    |  51 +++++++++++----------
 kernel/sched/debug.c       |   1 +
 kernel/sched/fair.c        |   7 ++-
 kernel/sched/idle.c        |   3 +-
 kernel/sched/rt.c          |  26 +++++++++--
 kernel/sched/sched.h       |  22 +++++++++-
 11 files changed, 197 insertions(+), 77 deletions(-)
include/linux/wait.h +26 -0
index 37423e0e1379..537d58eea8a0 100644
@@ -990,6 +990,32 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
 }
 
 /**
+ * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ * @timeout: timeout, in jiffies
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared. This is similar to wait_on_bit(), except also takes a
+ * timeout parameter.
+ *
+ * Returned value will be zero if the bit was cleared before the
+ * @timeout elapsed, or non-zero if the @timeout elapsed or process
+ * received a signal and the mode permitted wakeup on that signal.
+ */
+static inline int
+wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_timeout(word, bit,
+					       bit_wait_timeout,
+					       mode, timeout);
+}
+
+/**
  * wait_on_bit_action - wait for a bit to be cleared
  * @word: the word being waited on, a kernel virtual address
  * @bit: the bit of the word being waited on
kernel/locking/mutex.c +1 -1
index 454195194d4a..5b49f652a3cf 100644
@@ -81,7 +81,7 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
  * The mutex must later on be released by the same task that
  * acquired it. Recursive locking is not allowed. The task
  * may not exit without first unlocking the mutex. Also, kernel
- * memory where the mutex resides mutex must not be freed with
+ * memory where the mutex resides must not be freed with
  * the mutex still locked. The mutex must first be initialized
  * (or statically defined) before it can be locked. memset()-ing
  * the mutex to 0 is not allowed.
kernel/sched/core.c +69 -38

248 lines not on this page · raw message

kernel/sched/cpudeadline.c +23 -4
index 539ca3ce071b..c6acb07466bb 100644
@@ -107,7 +107,8 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	int best_cpu = -1;
 	const struct sched_dl_entity *dl_se = &p->dl;
 
-	if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) {
+	if (later_mask &&
+	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
 		best_cpu = cpumask_any(later_mask);
 		goto out;
 	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
@@ -186,6 +187,26 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 }
 
 /*
+ * cpudl_set_freecpu - Set the cpudl.free_cpus
+ * @cp: the cpudl max-heap context
+ * @cpu: rd attached cpu
+ */
+void cpudl_set_freecpu(struct cpudl *cp, int cpu)
+{
+	cpumask_set_cpu(cpu, cp->free_cpus);
+}
+
+/*
+ * cpudl_clear_freecpu - Clear the cpudl.free_cpus
+ * @cp: the cpudl max-heap context
+ * @cpu: rd attached cpu
+ */
+void cpudl_clear_freecpu(struct cpudl *cp, int cpu)
+{
+	cpumask_clear_cpu(cpu, cp->free_cpus);
+}
+
+/*
  * cpudl_init - initialize the cpudl structure
  * @cp: the cpudl max-heap context
  */
@@ -203,7 +224,7 @@ int cpudl_init(struct cpudl *cp)
 	if (!cp->elements)
 		return -ENOMEM;
 
-	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
 		kfree(cp->elements);
 		return -ENOMEM;
 	}
@@ -211,8 +232,6 @@ int cpudl_init(struct cpudl *cp)
 	for_each_possible_cpu(i)
 		cp->elements[i].idx = IDX_INVALID;
 
-	cpumask_setall(cp->free_cpus);
-
 	return 0;
 }
 
kernel/sched/cpudeadline.h +2 -0
index 020039bd1326..1a0a6ef2fbe1 100644
@@ -24,6 +24,8 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	       struct cpumask *later_mask);
 void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
 int cpudl_init(struct cpudl *cp);
+void cpudl_set_freecpu(struct cpudl *cp, int cpu);
+void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
 void cpudl_cleanup(struct cpudl *cp);
 #endif /* CONFIG_SMP */
 
kernel/sched/deadline.c +28 -23

102 lines not on this page · raw message

kernel/sched/debug.c +1 -0
index 92cc52001e74..8baaf858d25c 100644
@@ -305,6 +305,7 @@ do {									\
 	PN(next_balance);
 	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
 	PN(clock);
+	PN(clock_task);
 	P(cpu_load[0]);
 	P(cpu_load[1]);
 	P(cpu_load[2]);
kernel/sched/fair.c +3 -4
index fe331fc391f5..7ce18f3c097a 100644
@@ -676,7 +676,6 @@ 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;
@@ -2574,11 +2573,11 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
 	u64 decays = atomic64_read(&cfs_rq->decay_counter);
 
 	decays -= se->avg.decay_count;
+	se->avg.decay_count = 0;
 	if (!decays)
 		return 0;
 
 	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
-	se->avg.decay_count = 0;
 
 	return decays;
 }
@@ -5157,7 +5156,7 @@ static void yield_task_fair(struct rq *rq)
 		 * so we don't do microscopic update in schedule()
 		 * and double the fastpath cost.
 		 */
-		 rq->skip_clock_update = 1;
+		rq_clock_skip_update(rq, true);
 	}
 
 	set_skip_buddy(se);
@@ -5949,8 +5948,8 @@ static unsigned long scale_rt_capacity(int cpu)
 	 */
 	age_stamp = ACCESS_ONCE(rq->age_stamp);
 	avg = ACCESS_ONCE(rq->rt_avg);
+	delta = __rq_clock_broken(rq) - age_stamp;
 
-	delta = rq_clock(rq) - age_stamp;
 	if (unlikely(delta < 0))
 		delta = 0;
 
kernel/sched/idle.c +2 -1
index c47fce75e666..aaf1c1d5cf5d 100644
@@ -47,7 +47,8 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!tif_need_resched())
+	while (!tif_need_resched() &&
+		(cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
kernel/sched/rt.c +22 -4
index ee15f5a0d1c1..f4d4b077eba0 100644
@@ -831,11 +831,14 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 				enqueue = 1;
 
 				/*
-				 * Force a clock update if the CPU was idle,
-				 * lest wakeup -> unthrottle time accumulate.
+				 * When we're idle and a woken (rt) task is
+				 * throttled check_preempt_curr() will set
+				 * skip_update and the time between the wakeup
+				 * and this unthrottle will get accounted as
+				 * 'runtime'.
 				 */
 				if (rt_rq->rt_nr_running && rq->curr == rq->idle)
-					rq->skip_clock_update = -1;
+					rq_clock_skip_update(rq, false);
 			}
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
@@ -1337,7 +1340,12 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	     curr->prio <= p->prio)) {
 		int target = find_lowest_rq(p);
 
-		if (target != -1)
+		/*
+		 * Don't bother moving it if the destination CPU is
+		 * not running a lower priority task.
+		 */
+		if (target != -1 &&
+		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
 			cpu = target;
 	}
 	rcu_read_unlock();
@@ -1614,6 +1622,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 
 		lowest_rq = cpu_rq(cpu);
 
+		if (lowest_rq->rt.highest_prio.curr <= task->prio) {
+			/*
+			 * Target rq has tasks of equal or higher priority,
+			 * retrying does not release any lock and is unlikely
+			 * to yield a different result.
+			 */
+			lowest_rq = NULL;
+			break;
+		}
+
 		/* if the prio of this runqueue changed, try again */
 		if (double_lock_balance(rq, lowest_rq)) {
 			/*
kernel/sched/sched.h +20 -2
index 9a2a45c970e7..0870db23d79c 100644
@@ -558,8 +558,6 @@ struct rq {
 #ifdef CONFIG_NO_HZ_FULL
 	unsigned long last_sched_tick;
 #endif
-	int skip_clock_update;
-
 	/* capture load from *all* tasks on this cpu: */
 	struct load_weight load;
 	unsigned long nr_load_updates;
@@ -588,6 +586,7 @@ struct rq {
 	unsigned long next_balance;
 	struct mm_struct *prev_mm;
 
+	unsigned int clock_skip_update;
 	u64 clock;
 	u64 clock_task;
 
@@ -687,16 +686,35 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		raw_cpu_ptr(&runqueues)
 
+static inline u64 __rq_clock_broken(struct rq *rq)
+{
+	return ACCESS_ONCE(rq->clock);
+}
+
 static inline u64 rq_clock(struct rq *rq)
 {
+	lockdep_assert_held(&rq->lock);
 	return rq->clock;
 }
 
 static inline u64 rq_clock_task(struct rq *rq)
 {
+	lockdep_assert_held(&rq->lock);
 	return rq->clock_task;
 }
 
+#define RQCF_REQ_SKIP	0x01
+#define RQCF_ACT_SKIP	0x02
+
+static inline void rq_clock_skip_update(struct rq *rq, bool skip)
+{
+	lockdep_assert_held(&rq->lock);
+	if (skip)
+		rq->clock_skip_update |= RQCF_REQ_SKIP;
+	else
+		rq->clock_skip_update &= ~RQCF_REQ_SKIP;
+}
+
 #ifdef CONFIG_NUMA
 enum numa_topology_type {
 	NUMA_DIRECT,