Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip Pull scheduler updates from Ingo Molnar: "The main changes are: - Migrate CPU-intense 'misfit' tasks on asymmetric capacity systems, to better utilize (much) faster 'big core' CPUs. (Morten Rasmussen, Valentin Schneider) - Topology handling improvements, in particular when CPU capacity changes and related load-balancing fixes/improvements (Morten Rasmussen) - ... plus misc other improvements, fixes and updates" * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits) sched/completions/Documentation: Add recommendation for dynamic and ONSTACK completions sched/completions/Documentation: Clean up the document some more sched/completions/Documentation: Fix a couple of punctuation nits cpu/SMT: State SMT is disabled even with nosmt and without "=force" sched/core: Fix comment regarding nr_iowait_cpu() and get_iowait_load() sched/fair: Remove setting task's se->runnable_weight during PELT update sched/fair: Disable LB_BIAS by default sched/pelt: Fix warning and clean up IRQ PELT config sched/topology: Make local variables static sched/debug: Use symbolic names for task state constants sched/numa: Remove unused numa_stats::nr_running field sched/numa: Remove unused code from update_numa_stats() sched/debug: Explicitly cast sched_feat() to bool sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains sched/fair: Don't move tasks to lower capacity CPUs unless necessary sched/fair: Set rq->rd->overload when misfit sched/fair: Wrap rq->rd->overload accesses with READ/WRITE_ONCE() sched/core: Change root_domain->overload type to int sched/fair: Change 'prefer_sibling' type to bool sched/fair: Kick nohz balance if rq->misfit_task_load ...
torvalds · Oct 23, 2018 · 42f52e1 · 42f52e1
2 parents 0d1b82c + 11e1369
commit 42f52e1
Show file tree

Hide file tree

Showing 16 changed files with 463 additions and 199 deletions.
diff --git a/Documentation/scheduler/completion.txt b/Documentation/scheduler/completion.txt
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
@@ -33,6 +33,9 @@ const struct cpumask *cpu_coregroup_mask(int cpu);
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
 
+/* Enable topology flag updates */
+#define arch_update_cpu_topology topology_update_cpu_topology
+
 #else
 
 static inline void init_cpu_topology(void) { }

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
@@ -45,6 +45,9 @@ int pcibus_to_node(struct pci_bus *bus);
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
 
+/* Enable topology flag updates */
+#define arch_update_cpu_topology topology_update_cpu_topology
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sched/topology.h>
+#include <linux/cpuset.h>
 
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
@@ -47,6 +48,9 @@ static ssize_t cpu_capacity_show(struct device *dev,
 	return sprintf(buf, "%lu\n", topology_get_cpu_scale(NULL, cpu->dev.id));
 }
 
+static void update_topology_flags_workfn(struct work_struct *work);
+static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn);
+
 static ssize_t cpu_capacity_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf,
@@ -72,6 +76,8 @@ static ssize_t cpu_capacity_store(struct device *dev,
 		topology_set_cpu_scale(i, new_capacity);
 	mutex_unlock(&cpu_scale_mutex);
 
+	schedule_work(&update_topology_flags_work);
+
 	return count;
 }
 
@@ -96,6 +102,25 @@ static int register_cpu_capacity_sysctl(void)
 }
 subsys_initcall(register_cpu_capacity_sysctl);
 
+static int update_topology;
+
+int topology_update_cpu_topology(void)
+{
+	return update_topology;
+}
+
+/*
+ * Updating the sched_domains can't be done directly from cpufreq callbacks
+ * due to locking, so queue the work for later.
+ */
+static void update_topology_flags_workfn(struct work_struct *work)
+{
+	update_topology = 1;
+	rebuild_sched_domains();
+	pr_debug("sched_domain hierarchy rebuilt, flags updated\n");
+	update_topology = 0;
+}
+
 static u32 capacity_scale;
 static u32 *raw_capacity;
 
@@ -201,6 +226,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 
 	if (cpumask_empty(cpus_to_visit)) {
 		topology_normalize_cpu_scale();
+		schedule_work(&update_topology_flags_work);
 		free_raw_capacity();
 		pr_debug("cpu_capacity: parsing done\n");
 		schedule_work(&parsing_done_work);

diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
@@ -9,6 +9,7 @@
 #include <linux/percpu.h>
 
 void topology_normalize_cpu_scale(void);
+int topology_update_cpu_topology(void);
 
 struct device_node;
 bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
@@ -23,10 +23,10 @@
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
-#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Domain members have different CPU capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share CPU capacity */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share CPU pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
 #define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
@@ -159,9 +159,14 @@ TRACE_EVENT(sched_switch,
 
 		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
 		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
-				{ 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" },
-				{ 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" },
-				{ 0x40, "P" }, { 0x80, "I" }) :
+				{ TASK_INTERRUPTIBLE, "S" },
+				{ TASK_UNINTERRUPTIBLE, "D" },
+				{ __TASK_STOPPED, "T" },
+				{ __TASK_TRACED, "t" },
+				{ EXIT_DEAD, "X" },
+				{ EXIT_ZOMBIE, "Z" },
+				{ TASK_PARKED, "P" },
+				{ TASK_DEAD, "I" }) :
 		  "R",
 
 		__entry->prev_state & TASK_REPORT_MAX ? "+" : "",

diff --git a/init/Kconfig b/init/Kconfig
@@ -415,6 +415,11 @@ config IRQ_TIME_ACCOUNTING
 
 	  If in doubt, say N here.
 
+config HAVE_SCHED_AVG_IRQ
+	def_bool y
+	depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING
+	depends on SMP
+
 config BSD_PROCESS_ACCT
 	bool "BSD Process Accounting"
 	depends on MULTIUSER

diff --git a/kernel/cpu.c b/kernel/cpu.c
@@ -383,6 +383,7 @@ void __init cpu_smt_disable(bool force)
 		pr_info("SMT: Force disabled\n");
 		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
 	} else {
+		pr_info("SMT: disabled\n");
 		cpu_smt_control = CPU_SMT_DISABLED;
 	}
 }

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
@@ -135,9 +135,8 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
  * In theory, the compile should just see 0 here, and optimize out the call
  * to sched_rt_avg_update. But I don't trust it...
  */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
+	s64 __maybe_unused steal = 0, irq_delta = 0;
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
@@ -177,7 +176,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#ifdef HAVE_SCHED_AVG_IRQ
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
@@ -701,6 +700,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	if (idle_policy(p->policy)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
+		p->se.runnable_weight = load->weight;
 		return;
 	}
 
@@ -713,6 +713,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	} else {
 		load->weight = scale_load(sched_prio_to_weight[prio]);
 		load->inv_weight = sched_prio_to_wmult[prio];
+		p->se.runnable_weight = load->weight;
 	}
 }
 
@@ -2915,10 +2916,10 @@ unsigned long nr_iowait(void)
 }
 
 /*
- * Consumers of these two interfaces, like for example the cpufreq menu
- * governor are using nonsensical data. Boosting frequency for a CPU that has
- * IO-wait which might not even end up running the task when it does become
- * runnable.
+ * Consumers of these two interfaces, like for example the cpuidle menu
+ * governor, are using nonsensical data. Preferring shallow idle state selection
+ * for a CPU that has IO-wait which might not even end up running the task when
+ * it does become runnable.
  */
 
 unsigned long nr_iowait_cpu(int cpu)