Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Mostly simple overlapping changes.

For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 35 insertions, 19 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94732d1ab00a..42d4027f9e26 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7515,11 +7515,27 @@ static struct kmem_cache *task_group_cache __read_mostly;
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
 void __init sched_init(void)
 {
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
+	for (i = 0; i < WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(bit_wait_table + i);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 13935886a471..fa178b62ea79 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -415,7 +415,8 @@ static char *task_group_path(struct task_group *tg)
 	if (autogroup_path(tg, group_path, PATH_MAX))
 		return group_path;
 
-	return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+	return group_path;
 }
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 502e95a6e927..c242944f5cbd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -690,7 +690,14 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * will definitely be update (after enqueue).
 	 */
 	sa->period_contrib = 1023;
-	sa->load_avg = scale_load_down(se->load.weight);
+	/*
+	 * Tasks are intialized with full load to be seen as heavy tasks until
+	 * they get a chance to stabilize to their real load level.
+	 * Group entities are intialized with zero load to reflect the fact that
+	 * nothing has been attached to the task group yet.
+	 */
+	if (entity_is_task(se))
+		sa->load_avg = scale_load_down(se->load.weight);
 	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
 	/*
 	 * At this point, util_avg won't be used in select_task_rq_fair anyway
@@ -5471,13 +5478,18 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
  */
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
-	u64 avg_idle = this_rq()->avg_idle;
-	u64 avg_cost = this_sd->avg_scan_cost;
+	struct sched_domain *this_sd;
+	u64 avg_cost, avg_idle = this_rq()->avg_idle;
 	u64 time, cost;
 	s64 delta;
 	int cpu, wrap;
 
+	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
+	if (!this_sd)
+		return -1;
+
+	avg_cost = this_sd->avg_scan_cost;
+
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
@@ -8522,7 +8534,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
  * run_rebalance_domains is triggered when needed from the scheduler tick.
  * Also triggered for nohz idle balancing (with nohz_balancing_kick set).
  */
-static void run_rebalance_domains(struct softirq_action *h)
+static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
 {
 	struct rq *this_rq = this_rq();
 	enum cpu_idle_type idle = this_rq->idle_balance ?
@@ -8827,7 +8839,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
-	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8842,8 +8853,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4f7053579fe3..9453efe9b25a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -480,16 +480,6 @@ void wake_up_bit(void *word, int bit)
 }
 EXPORT_SYMBOL(wake_up_bit);
 
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
-	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
-	const struct zone *zone = page_zone(virt_to_page(word));
-	unsigned long val = (unsigned long)word << shift | bit;
-
-	return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
 /*
  * Manipulate the atomic_t address to produce a better bit waitqueue table hash
  * index (we're keying off bit -1, but that would produce a horrible hash