Merge tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - reorganize & clean up the SD* flags definitions and add a bunch of
   sanity checks. These new checks caught quite a few bugs or at least
   inconsistencies, resulting in another set of patches.

 - rseq updates, add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

 - add a new tracepoint to improve CPU capacity tracking

 - improve overloaded SMP system load-balancing behavior

 - tweak SMT balancing

 - energy-aware scheduling updates

 - NUMA balancing improvements

 - deadline scheduler fixes and improvements

 - CPU isolation fixes

 - misc cleanups, simplifications and smaller optimizations

* tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  sched/deadline: Unthrottle PI boosted threads while enqueuing
  sched/debug: Add new tracepoint to track cpu_capacity
  sched/fair: Tweak pick_next_entity()
  rseq/selftests: Test MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  rseq/selftests,x86_64: Add rseq_offset_deref_addv()
  rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  sched/fair: Use dst group while checking imbalance for NUMA balancer
  sched/fair: Reduce busy load balance interval
  sched/fair: Minimize concurrent LBs between domain level
  sched/fair: Reduce minimal imbalance threshold
  sched/fair: Relax constraint on task's load during load balance
  sched/fair: Remove the force parameter of update_tg_load_avg()
  sched/fair: Fix wrong cpu selecting from isolated domain
  sched: Remove unused inline function uclamp_bucket_base_value()
  sched/rt: Disable RT_RUNTIME_SHARE by default
  sched/deadline: Fix stale throttling on de-/boosted tasks
  sched/numa: Use runnable_avg to classify node
  sched/topology: Move sd_flag_debug out of #ifdef CONFIG_SYSCTL
  MAINTAINERS: Add myself as SCHED_DEADLINE reviewer
  sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of linux/sched/topology.h
  ...

1 files changed, 40 insertions, 29 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 1bd7e3af904f..dd7770226086 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -25,10 +25,18 @@ static inline bool sched_debug(void)
 	return sched_debug_enabled;
 }
 
+#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
+const struct sd_flag_debug sd_flag_debug[] = {
+#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  struct cpumask *groupmask)
 {
 	struct sched_group *group = sd->groups;
+	unsigned long flags = sd->flags;
+	unsigned int idx;
 
 	cpumask_clear(groupmask);
 
@@ -43,6 +51,21 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
 	}
 
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		unsigned int flag = BIT(idx);
+		unsigned int meta_flags = sd_flag_debug[idx].meta_flags;
+
+		if ((meta_flags & SDF_SHARED_CHILD) && sd->child &&
+		    !(sd->child->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in child\n",
+			       sd_flag_debug[idx].name);
+
+		if ((meta_flags & SDF_SHARED_PARENT) && sd->parent &&
+		    !(sd->parent->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in parent\n",
+			       sd_flag_debug[idx].name);
+	}
+
 	printk(KERN_DEBUG "%*s groups:", level + 1, "");
 	do {
 		if (!group) {
@@ -137,22 +160,22 @@ static inline bool sched_debug(void)
 }
 #endif /* CONFIG_SCHED_DEBUG */
 
+/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
+static const unsigned int SD_DEGENERATE_GROUPS_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 static int sd_degenerate(struct sched_domain *sd)
 {
 	if (cpumask_weight(sched_domain_span(sd)) == 1)
 		return 1;
 
 	/* Following flags need at least 2 groups */
-	if (sd->flags & (SD_BALANCE_NEWIDLE |
-			 SD_BALANCE_FORK |
-			 SD_BALANCE_EXEC |
-			 SD_SHARE_CPUCAPACITY |
-			 SD_ASYM_CPUCAPACITY |
-			 SD_SHARE_PKG_RESOURCES |
-			 SD_SHARE_POWERDOMAIN)) {
-		if (sd->groups != sd->groups->next)
-			return 0;
-	}
+	if ((sd->flags & SD_DEGENERATE_GROUPS_MASK) &&
+	    (sd->groups != sd->groups->next))
+		return 0;
 
 	/* Following flags don't use groups */
 	if (sd->flags & (SD_WAKE_AFFINE))
@@ -173,18 +196,9 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 		return 0;
 
 	/* Flags needing groups don't count if only 1 group in parent */
-	if (parent->groups == parent->groups->next) {
-		pflags &= ~(SD_BALANCE_NEWIDLE |
-			    SD_BALANCE_FORK |
-			    SD_BALANCE_EXEC |
-			    SD_ASYM_CPUCAPACITY |
-			    SD_SHARE_CPUCAPACITY |
-			    SD_SHARE_PKG_RESOURCES |
-			    SD_PREFER_SIBLING |
-			    SD_SHARE_POWERDOMAIN);
-		if (nr_node_ids == 1)
-			pflags &= ~SD_SERIALIZE;
-	}
+	if (parent->groups == parent->groups->next)
+		pflags &= ~SD_DEGENERATE_GROUPS_MASK;
+
 	if (~cflags & pflags)
 		return 0;
 
@@ -1292,7 +1306,6 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
  *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
- *   SD_SHARE_POWERDOMAIN   - describes shared power domain
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1303,8 +1316,7 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
 	(SD_SHARE_CPUCAPACITY	|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
-	 SD_ASYM_PACKING	|	\
-	 SD_SHARE_POWERDOMAIN)
+	 SD_ASYM_PACKING)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
@@ -1336,8 +1348,8 @@ sd_init(struct sched_domain_topology_level *tl,
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
-		.busy_factor		= 32,
-		.imbalance_pct		= 125,
+		.busy_factor		= 16,
+		.imbalance_pct		= 117,
 
 		.cache_nice_tries	= 0,
 
@@ -1989,11 +2001,10 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
 		struct sched_domain_topology_level *tl;
+		int dflags = 0;
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			int dflags = 0;
-
 			if (tl == tl_asym) {
 				dflags |= SD_ASYM_CPUCAPACITY;
 				has_asym = true;