1 files changed, 34 insertions, 15 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 6a212c97f52..3c2a54f70ff 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -322,6 +323,15 @@ static inline struct task_group *task_group(struct task_struct *p)
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 {
+        /*
+         * Strictly speaking this rcu_read_lock() is not needed since the
+         * task_group is tied to the cgroup, which in turn can never go away
+         * as long as there are tasks attached to it.
+         *
+         * However since task_group() uses task_subsys_state() which is an
+         * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
+         */
+        rcu_read_lock();
 #ifdef CONFIG_FAIR_GROUP_SCHED
         p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
         p->se.parent = task_group(p)->se[cpu];
@@ -331,6 +341,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
         p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
         p->rt.parent = task_group(p)->rt_se[cpu];
 #endif
+        rcu_read_unlock();
 }
 
 #else
@@ -1521,7 +1532,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static __read_mostly unsigned long *update_shares_data;
+static __read_mostly unsigned long __percpu *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -2359,7 +2370,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
-        struct rq *rq, *orig_rq;
+        struct rq *rq;
 
         if (!sched_feat(SYNC_WAKEUPS))
                 wake_flags &= ~WF_SYNC;
@@ -2367,7 +2378,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
         this_cpu = get_cpu();
 
         smp_wmb();
-        rq = orig_rq = task_rq_lock(p, &flags);
+        rq = task_rq_lock(p, &flags);
         update_rq_clock(rq);
         if (!(p->state & state))
                 goto out;
@@ -2650,7 +2661,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 {
         unsigned long flags;
         struct rq *rq;
-        int cpu = get_cpu();
+        int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
         /*
@@ -3779,7 +3790,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
          * the mutex owner just released it and exited.
          */
         if (probe_kernel_address(&owner->cpu, cpu))
-                goto out;
+                return 0;
 #else
         cpu = owner->cpu;
 #endif
@@ -3789,14 +3800,14 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
          * the cpu field may no longer be valid.
          */
         if (cpu >= nr_cpumask_bits)
-                goto out;
+                return 0;
 
         /*
          * We need to validate that we can do a
          * get_cpu() and that we have the percpu area.
          */
         if (!cpu_online(cpu))
-                goto out;
+                return 0;
 
         rq = cpu_rq(cpu);
 
@@ -3815,7 +3826,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 
                 cpu_relax();
         }
-out:
+
         return 1;
 }
 #endif
@@ -4353,7 +4364,7 @@ int can_nice(const struct task_struct *p, const int nice)
         /* convert nice value [19,-20] to rlimit style value [1,40] */
         int nice_rlim = 20 - nice;
 
-        return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+        return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
                 capable(CAP_SYS_NICE));
 }
 
@@ -4530,7 +4541,7 @@ recheck:
 
                         if (!lock_task_sighand(p, &flags))
                                 return -ESRCH;
-                        rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+                        rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
                         unlock_task_sighand(p, &flags);
 
                         /* can't set/change the rt policy */
@@ -4902,7 +4913,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
         int ret;
         cpumask_var_t mask;
 
-        if (len < cpumask_size())
+        if ((len * BITS_PER_BYTE) < nr_cpu_ids)
+                return -EINVAL;
+        if (len & (sizeof(unsigned long)-1))
                 return -EINVAL;
 
         if (!alloc_cpumask_var(&mask, GFP_KERNEL))
@@ -4910,10 +4923,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 
         ret = sched_getaffinity(pid, mask);
         if (ret == 0) {
-                if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+                size_t retlen = min_t(size_t, len, cpumask_size());
+
+                if (copy_to_user(user_mask_ptr, mask, retlen))
                         ret = -EFAULT;
                 else
-                        ret = cpumask_size();
+                        ret = retlen;
         }
         free_cpumask_var(mask);
 
@@ -5383,7 +5398,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
                 get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(rq->migration_thread);
+                wake_up_process(mt);
                 put_task_struct(mt);
                 wait_for_completion(&req.done);
                 tlb_migrate_finish(p->mm);
@@ -7406,11 +7421,13 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 
 #ifdef CONFIG_SCHED_MC
 static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+                                           struct sysdev_class_attribute *attr,
                                            char *page)
 {
         return sprintf(page, "%u\n", sched_mc_power_savings);
 }
 static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
+                                            struct sysdev_class_attribute *attr,
                                             const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 0);
@@ -7422,11 +7439,13 @@ static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
 
 #ifdef CONFIG_SCHED_SMT
 static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+                                            struct sysdev_class_attribute *attr,
                                             char *page)
 {
         return sprintf(page, "%u\n", sched_smt_power_savings);
 }
 static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
+                                             struct sysdev_class_attribute *attr,
                                              const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 1);
@@ -8813,7 +8832,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct {
         struct cgroup_subsys_state css;
         /* cpuusage holds pointer to a u64-type object on every cpu */
-        u64 *cpuusage;
+        u64 __percpu *cpuusage;
         struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
         struct cpuacct *parent;
 };