Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying new patches

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 65 insertions, 31 deletions

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index ab32b7b0db5c..46be87024875 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -1,5 +1,5 @@
 ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_clock.o = -pg
+CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
 endif
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c27e4f8f4879..c0a205101c23 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -420,3 +420,16 @@ u64 local_clock(void)
 
 EXPORT_SYMBOL_GPL(cpu_clock);
 EXPORT_SYMBOL_GPL(local_clock);
+
+/*
+ * Running clock - returns the time that has elapsed while a guest has been
+ * running.
+ * On a guest this value should be local_clock minus the time the guest was
+ * suspended by the hypervisor (for any reason).
+ * On bare metal this function should return the same as local_clock.
+ * Architectures and sub-architectures can override this.
+ */
+u64 __weak running_clock(void)
+{
+        return local_clock();
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97fe79cf613e..feda520bd034 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3051,6 +3051,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         } else {
                 if (dl_prio(oldprio))
                         p->dl.dl_boosted = 0;
+                if (rt_prio(oldprio))
+                        p->rt.timeout = 0;
                 p->sched_class = &fair_sched_class;
         }
 
@@ -5412,9 +5414,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                                   struct cpumask *groupmask)
 {
         struct sched_group *group = sd->groups;
-        char str[256];
 
-        cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
         cpumask_clear(groupmask);
 
         printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@@ -5427,7 +5427,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                 return -1;
         }
 
-        printk(KERN_CONT "span %s level %s\n", str, sd->name);
+        printk(KERN_CONT "span %*pbl level %s\n",
+               cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
         if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
                 printk(KERN_ERR "ERROR: domain->span does not contain "
@@ -5472,9 +5473,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
                 cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
-                cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
-
-                printk(KERN_CONT " %s", str);
+                printk(KERN_CONT " %*pbl",
+                       cpumask_pr_args(sched_group_cpus(group)));
                 if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
                         printk(KERN_CONT " (cpu_capacity = %d)",
                                 group->sgc->capacity);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index aaf1c1d5cf5d..80014a178342 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -7,6 +7,7 @@
 #include <linux/tick.h>
 #include <linux/mm.h>
 #include <linux/stackprotector.h>
+#include <linux/suspend.h>
 
 #include <asm/tlb.h>
 
@@ -81,6 +82,7 @@ static void cpuidle_idle_call(void)
         struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
         int next_state, entered_state;
         unsigned int broadcast;
+        bool reflect;
 
         /*
          * Check if the idle task must be rescheduled. If it is the
@@ -104,25 +106,37 @@ static void cpuidle_idle_call(void)
          */
         rcu_idle_enter();
 
+        if (cpuidle_not_available(drv, dev))
+                goto use_default;
+
         /*
-         * Ask the cpuidle framework to choose a convenient idle state.
-         * Fall back to the default arch idle method on errors.
+         * Suspend-to-idle ("freeze") is a system state in which all user space
+         * has been frozen, all I/O devices have been suspended and the only
+         * activity happens here and in iterrupts (if any).  In that case bypass
+         * the cpuidle governor and go stratight for the deepest idle state
+         * available.  Possibly also suspend the local tick and the entire
+         * timekeeping to prevent timer interrupts from kicking us out of idle
+         * until a proper wakeup interrupt happens.
          */
-        next_state = cpuidle_select(drv, dev);
-        if (next_state < 0) {
-use_default:
-                /*
-                 * We can't use the cpuidle framework, let's use the default
-                 * idle routine.
-                 */
-                if (current_clr_polling_and_test())
+        if (idle_should_freeze()) {
+                entered_state = cpuidle_enter_freeze(drv, dev);
+                if (entered_state >= 0) {
                         local_irq_enable();
-                else
-                        arch_cpu_idle();
+                        goto exit_idle;
+                }
 
-                goto exit_idle;
+                reflect = false;
+                next_state = cpuidle_find_deepest_state(drv, dev);
+        } else {
+                reflect = true;
+                /*
+                 * Ask the cpuidle framework to choose a convenient idle state.
+                 */
+                next_state = cpuidle_select(drv, dev);
         }
-
+        /* Fall back to the default arch idle method on errors. */
+        if (next_state < 0)
+                goto use_default;
 
         /*
          * The idle task must be scheduled, it is pointless to
@@ -167,7 +181,8 @@ use_default:
         /*
          * Give the governor an opportunity to reflect on the outcome
          */
-        cpuidle_reflect(dev, entered_state);
+        if (reflect)
+                cpuidle_reflect(dev, entered_state);
 
 exit_idle:
         __current_set_polling();
@@ -180,6 +195,19 @@ exit_idle:
 
         rcu_idle_exit();
         start_critical_timings();
+        return;
+
+use_default:
+        /*
+         * We can't use the cpuidle framework, let's use the default
+         * idle routine.
+         */
+        if (current_clr_polling_and_test())
+                local_irq_enable();
+        else
+                arch_cpu_idle();
+
+        goto exit_idle;
 }
 
 /*
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index a476bea17fbc..87e2c9f0c33e 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -15,11 +15,6 @@
 static int show_schedstat(struct seq_file *seq, void *v)
 {
         int cpu;
-        int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
-        char *mask_str = kmalloc(mask_len, GFP_KERNEL);
-
-        if (mask_str == NULL)
-                return -ENOMEM;
 
         if (v == (void *)1) {
                 seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
@@ -50,9 +45,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
                 for_each_domain(cpu, sd) {
                         enum cpu_idle_type itype;
 
-                        cpumask_scnprintf(mask_str, mask_len,
-                                          sched_domain_span(sd));
-                        seq_printf(seq, "domain%d %s", dcount++, mask_str);
+                        seq_printf(seq, "domain%d %*pb", dcount++,
+                                   cpumask_pr_args(sched_domain_span(sd)));
                         for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
                                         itype++) {
                                 seq_printf(seq, " %u %u %u %u %u %u %u %u",
@@ -76,7 +70,6 @@ static int show_schedstat(struct seq_file *seq, void *v)
                 rcu_read_unlock();
 #endif
         }
-        kfree(mask_str);
         return 0;
 }