1 files changed, 59 insertions, 40 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index deb5ac8c12f3..7d97ff7c4478 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -125,6 +125,9 @@ DEFINE_TRACE(sched_switch);
 DEFINE_TRACE(sched_migrate_task);
 
 #ifdef CONFIG_SMP
+
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
  * Since cpu_power is a 'constant', we can use a reciprocal divide.
@@ -1320,8 +1323,8 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
  * slice expiry etc.
  */
 
-#define WEIGHT_IDLEPRIO         2
-#define WMULT_IDLEPRIO          (1 << 31)
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
 
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
@@ -3877,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick)
         int cpu = smp_processor_id();
 
         if (stop_tick) {
-                cpumask_set_cpu(cpu, nohz.cpu_mask);
                 cpu_rq(cpu)->in_nohz_recently = 1;
 
-                /*
-                 * If we are going offline and still the leader, give up!
-                 */
-                if (!cpu_active(cpu) &&
-                    atomic_read(&nohz.load_balancer) == cpu) {
+                if (!cpu_active(cpu)) {
+                        if (atomic_read(&nohz.load_balancer) != cpu)
+                                return 0;
+
+                        /*
+                         * If we are going offline and still the leader,
+                         * give up!
+                         */
                         if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
                                 BUG();
+
                         return 0;
                 }
 
+                cpumask_set_cpu(cpu, nohz.cpu_mask);
+
                 /* time for ilb owner also to sleep */
                 if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
                         if (atomic_read(&nohz.load_balancer) == cpu)
@@ -4437,7 +4445,7 @@ void __kprobes sub_preempt_count(int val)
         /*
          * Underflow?
          */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+        if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
                 return;
         /*
          * Is the spinlock portion underflowing?
@@ -4684,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-                             int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+                        int nr_exclusive, int sync, void *key)
 {
         wait_queue_t *curr, *next;
 
@@ -5123,7 +5131,7 @@ int can_nice(const struct task_struct *p, const int nice)
  * sys_setpriority is a more generic, but much slower function that
  * does similar things.
  */
-asmlinkage long sys_nice(int increment)
+SYSCALL_DEFINE1(nice, int, increment)
 {
         long nice, retval;
 
@@ -5430,8 +5438,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long
-sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
+                struct sched_param __user *, param)
 {
         /* negative values for policy are not valid */
         if (policy < 0)
@@ -5445,7 +5453,7 @@ sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @pid: the pid in question.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
         return do_sched_setscheduler(pid, -1, param);
 }
@@ -5454,7 +5462,7 @@ asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
  */
-asmlinkage long sys_sched_getscheduler(pid_t pid)
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 {
         struct task_struct *p;
         int retval;
@@ -5479,7 +5487,7 @@ asmlinkage long sys_sched_getscheduler(pid_t pid)
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
-asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
         struct sched_param lp;
         struct task_struct *p;
@@ -5597,8 +5605,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to the new cpu mask
  */
-asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
-                                      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+                unsigned long __user *, user_mask_ptr)
 {
         cpumask_var_t new_mask;
         int retval;
@@ -5645,8 +5653,8 @@ out_unlock:
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
  */
-asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
-                                      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+                unsigned long __user *, user_mask_ptr)
 {
         int ret;
         cpumask_var_t mask;
@@ -5675,7 +5683,7 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
  * This function yields the current CPU to other tasks. If there are no
  * other threads running on this CPU then this function will return.
  */
-asmlinkage long sys_sched_yield(void)
+SYSCALL_DEFINE0(sched_yield)
 {
         struct rq *rq = this_rq_lock();
 
@@ -5816,7 +5824,7 @@ long __sched io_schedule_timeout(long timeout)
  * this syscall returns the maximum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_max(int policy)
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 {
         int ret = -EINVAL;
 
@@ -5841,7 +5849,7 @@ asmlinkage long sys_sched_get_priority_max(int policy)
  * this syscall returns the minimum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_min(int policy)
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 {
         int ret = -EINVAL;
 
@@ -5866,8 +5874,8 @@ asmlinkage long sys_sched_get_priority_min(int policy)
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
  */
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+                struct timespec __user *, interval)
 {
         struct task_struct *p;
         unsigned int time_slice;
@@ -5936,12 +5944,7 @@ void sched_show_task(struct task_struct *p)
                 printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-        {
-                unsigned long *n = end_of_stack(p);
-                while (!*n)
-                        n++;
-                free = (unsigned long)n - (unsigned long)end_of_stack(p);
-        }
+        free = stack_not_used(p);
 #endif
         printk(KERN_CONT "%5lu %5d %6d\n", free,
                 task_pid_nr(p), task_pid_nr(p->real_parent));
@@ -6936,20 +6939,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+        struct root_domain *old_rd = NULL;
         unsigned long flags;
 
         spin_lock_irqsave(&rq->lock, flags);
 
         if (rq->rd) {
-                struct root_domain *old_rd = rq->rd;
+                old_rd = rq->rd;
 
                 if (cpumask_test_cpu(rq->cpu, old_rd->online))
                         set_rq_offline(rq);
 
                 cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-                if (atomic_dec_and_test(&old_rd->refcount))
-                        free_rootdomain(old_rd);
+                /*
+                 * If we dont want to free the old_rt yet then
+                 * set old_rd to NULL to skip the freeing later
+                 * in this function:
+                 */
+                if (!atomic_dec_and_test(&old_rd->refcount))
+                        old_rd = NULL;
         }
 
         atomic_inc(&rd->refcount);
@@ -6960,6 +6969,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
                 set_rq_online(rq);
 
         spin_unlock_irqrestore(&rq->lock, flags);
+
+        if (old_rd)
+                free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -7282,10 +7294,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
  * groups, so roll our own. Now each node has its own list of groups which
  * gets dynamically allocated.
  */
-static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
 static struct sched_group ***sched_group_nodes_bycpu;
 
-static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
 
 static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
@@ -7560,7 +7572,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 #ifdef CONFIG_NUMA
                 if (cpumask_weight(cpu_map) >
                                 SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
-                        sd = &per_cpu(allnodes_domains, i);
+                        sd = &per_cpu(allnodes_domains, i).sd;
                         SD_INIT(sd, ALLNODES);
                         set_domain_attribute(sd, attr);
                         cpumask_copy(sched_domain_span(sd), cpu_map);
@@ -7570,7 +7582,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 } else
                         p = NULL;
 
-                sd = &per_cpu(node_domains, i);
+                sd = &per_cpu(node_domains, i).sd;
                 SD_INIT(sd, NODE);
                 set_domain_attribute(sd, attr);
                 sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
@@ -7688,7 +7700,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 for_each_cpu(j, nodemask) {
                         struct sched_domain *sd;
 
-                        sd = &per_cpu(node_domains, j);
+                        sd = &per_cpu(node_domains, j).sd;
                         sd->groups = sg;
                 }
                 sg->__cpu_power = 0;
@@ -9047,6 +9059,13 @@ static int tg_schedulable(struct task_group *tg, void *data)
                 runtime = d->rt_runtime;
         }
 
+#ifdef CONFIG_USER_SCHED
+        if (tg == &root_task_group) {
+                period = global_rt_period();
+                runtime = global_rt_runtime();
+        }
+#endif
+
         /*
          * Cannot have more runtime than the period.
          */