1 files changed, 115 insertions, 31 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..257002c13bb0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -72,6 +72,7 @@
 #include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
+#include <linux/context_tracking.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -192,23 +193,10 @@ static void sched_feat_disable(int i) { };
 static void sched_feat_enable(int i) { };
 #endif /* HAVE_JUMP_LABEL */
 
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-                size_t cnt, loff_t *ppos)
+static int sched_feat_set(char *cmp)
 {
-        char buf[64];
-        char *cmp;
-        int neg = 0;
         int i;
-
-        if (cnt > 63)
-                cnt = 63;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-        cmp = strstrip(buf);
+        int neg = 0;
 
         if (strncmp(cmp, "NO_", 3) == 0) {
                 neg = 1;
@@ -228,6 +216,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 }
         }
 
+        return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+                size_t cnt, loff_t *ppos)
+{
+        char buf[64];
+        char *cmp;
+        int i;
+
+        if (cnt > 63)
+                cnt = 63;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+        cmp = strstrip(buf);
+
+        i = sched_feat_set(cmp);
         if (i == __SCHED_FEAT_NR)
                 return -EINVAL;
 
@@ -922,6 +931,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
                 rq->skip_clock_update = 1;
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+        atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -952,8 +968,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
         trace_sched_migrate_task(p, new_cpu);
 
         if (task_cpu(p) != new_cpu) {
+                struct task_migration_notifier tmn;
+
+                if (p->sched_class->migrate_task_rq)
+                        p->sched_class->migrate_task_rq(p, new_cpu);
                 p->se.nr_migrations++;
                 perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+
+                tmn.task = p;
+                tmn.from_cpu = task_cpu(p);
+                tmn.to_cpu = new_cpu;
+
+                atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
         }
 
         __set_task_cpu(p, new_cpu);
@@ -1524,6 +1550,15 @@ static void __sched_fork(struct task_struct *p)
         p->se.vruntime                  = 0;
         INIT_LIST_HEAD(&p->se.group_node);
 
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+        p->se.avg.runnable_avg_period = 0;
+        p->se.avg.runnable_avg_sum = 0;
+#endif
 #ifdef CONFIG_SCHEDSTATS
         memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
@@ -1533,7 +1568,40 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
         INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
+
+#ifdef CONFIG_NUMA_BALANCING
+        if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
+                p->mm->numa_next_scan = jiffies;
+                p->mm->numa_next_reset = jiffies;
+                p->mm->numa_scan_seq = 0;
+        }
+
+        p->node_stamp = 0ULL;
+        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
+        p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
+        p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+        p->numa_work.next = &p->numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_SCHED_DEBUG
+void set_numabalancing_state(bool enabled)
+{
+        if (enabled)
+                sched_feat_set("NUMA");
+        else
+                sched_feat_set("NO_NUMA");
 }
+#else
+__read_mostly bool numabalancing_enabled;
+
+void set_numabalancing_state(bool enabled)
+{
+        numabalancing_enabled = enabled;
+}
+#endif /* CONFIG_SCHED_DEBUG */
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * fork()/clone()-time setup:
@@ -1886,8 +1954,8 @@ context_switch(struct rq *rq, struct task_struct *prev,
         spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 #endif
 
+        context_tracking_task_switch(prev, next);
         /* Here we just switch the register state and the stack. */
-        rcu_switch(prev, next);
         switch_to(prev, next, prev);
 
         barrier();
@@ -2911,7 +2979,7 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
 asmlinkage void __sched schedule_user(void)
 {
         /*
@@ -2920,9 +2988,9 @@ asmlinkage void __sched schedule_user(void)
          * we haven't yet exited the RCU idle mode. Do it here manually until
          * we find a better solution.
          */
-        rcu_user_exit();
+        user_exit();
         schedule();
-        rcu_user_enter();
+        user_enter();
 }
 #endif
 
@@ -3027,7 +3095,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
         /* Catch callers which need to be fixed */
         BUG_ON(ti->preempt_count || !irqs_disabled());
 
-        rcu_user_exit();
+        user_exit();
         do {
                 add_preempt_count(PREEMPT_ACTIVE);
                 local_irq_enable();
@@ -4029,8 +4097,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
                 goto out_free_cpus_allowed;
         }
         retval = -EPERM;
-        if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE))
-                goto out_unlock;
+        if (!check_same_owner(p)) {
+                rcu_read_lock();
+                if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
+                        rcu_read_unlock();
+                        goto out_unlock;
+                }
+                rcu_read_unlock();
+        }
 
         retval = security_task_setscheduler(p);
         if (retval)
@@ -4474,6 +4548,7 @@ static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
 void sched_show_task(struct task_struct *p)
 {
         unsigned long free = 0;
+        int ppid;
         unsigned state;
 
         state = p->state ? __ffs(p->state) + 1 : 0;
@@ -4493,8 +4568,11 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
         free = stack_not_used(p);
 #endif
+        rcu_read_lock();
+        ppid = task_pid_nr(rcu_dereference(p->real_parent));
+        rcu_read_unlock();
         printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
-                task_pid_nr(p), task_pid_nr(rcu_dereference(p->real_parent)),
+                task_pid_nr(p), ppid,
                 (unsigned long)task_thread_info(p)->flags);
 
         show_stack(p, NULL);
@@ -7468,7 +7546,7 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
                             struct task_group, css);
 }
 
-static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 {
         struct task_group *tg, *parent;
 
@@ -7485,7 +7563,7 @@ static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
         return &tg->css;
 }
 
-static void cpu_cgroup_destroy(struct cgroup *cgrp)
+static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
         struct task_group *tg = cgroup_tg(cgrp);
 
@@ -7845,8 +7923,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgroup_subsys = {
         .name           = "cpu",
-        .create         = cpu_cgroup_create,
-        .destroy        = cpu_cgroup_destroy,
+        .css_alloc      = cpu_cgroup_css_alloc,
+        .css_free       = cpu_cgroup_css_free,
         .can_attach     = cpu_cgroup_can_attach,
         .attach         = cpu_cgroup_attach,
         .exit           = cpu_cgroup_exit,
@@ -7869,7 +7947,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct root_cpuacct;
 
 /* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
 {
         struct cpuacct *ca;
 
@@ -7899,7 +7977,7 @@ out:
 }
 
 /* destroy an existing cpu accounting group */
-static void cpuacct_destroy(struct cgroup *cgrp)
+static void cpuacct_css_free(struct cgroup *cgrp)
 {
         struct cpuacct *ca = cgroup_ca(cgrp);
 
@@ -8070,9 +8148,15 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 
 struct cgroup_subsys cpuacct_subsys = {
         .name = "cpuacct",
-        .create = cpuacct_create,
-        .destroy = cpuacct_destroy,
+        .css_alloc = cpuacct_css_alloc,
+        .css_free = cpuacct_css_free,
         .subsys_id = cpuacct_subsys_id,
         .base_cftypes = files,
 };
 #endif  /* CONFIG_CGROUP_CPUACCT */
+
+void dump_cpu_task(int cpu)
+{
+        pr_info("Task dump for CPU %d:\n", cpu);
+        sched_show_task(cpu_curr(cpu));
+}