Merge branch 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (66 commits)
  x86: export vector_used_by_percpu_irq
  x86: use logical apicid in x2apic_cluster's x2apic_cpu_mask_to_apicid_and()
  sched: nominate preferred wakeup cpu, fix
  x86: fix lguest used_vectors breakage, -v2
  x86: fix warning in arch/x86/kernel/io_apic.c
  sched: fix warning in kernel/sched.c
  sched: move test_sd_parent() to an SMP section of sched.h
  sched: add SD_BALANCE_NEWIDLE at MC and CPU level for sched_mc>0
  sched: activate active load balancing in new idle cpus
  sched: bias task wakeups to preferred semi-idle packages
  sched: nominate preferred wakeup cpu
  sched: favour lower logical cpu number for sched_mc balance
  sched: framework for sched_mc/smt_power_savings=N
  sched: convert BALANCE_FOR_xx_POWER to inline functions
  x86: use possible_cpus=NUM to extend the possible cpus allowed
  x86: fix cpu_mask_to_apicid_and to include cpu_online_mask
  x86: update io_apic.c to the new cpumask code
  x86: Introduce topology_core_cpumask()/topology_thread_cpumask()
  x86: xen: use smp_call_function_many()
  x86: use work_on_cpu in x86/kernel/cpu/mcheck/mce_amd_64.c
  ...

Fixed up trivial conflict in kernel/time/tick-sched.c manually

1 files changed, 72 insertions, 20 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8395e715809d..158d53d07765 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -250,7 +250,7 @@ extern void init_idle_bootup_task(struct task_struct *idle);
 extern int runqueue_is_locked(void);
 extern void task_rq_unlock_wait(struct task_struct *p);
 
-extern cpumask_t nohz_cpu_mask;
+extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern int select_nohz_load_balancer(int cpu);
 #else
@@ -758,20 +758,51 @@ enum cpu_idle_type {
 #define SD_SERIALIZE            1024    /* Only a single load balancing instance */
 #define SD_WAKE_IDLE_FAR        2048    /* Gain latency sacrificing cache hit */
 
-#define BALANCE_FOR_MC_POWER    \
-        (sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)
+enum powersavings_balance_level {
+        POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
+        POWERSAVINGS_BALANCE_BASIC,     /* Fill one thread/core/package
+                                         * first for long running threads
+                                         */
+        POWERSAVINGS_BALANCE_WAKEUP,    /* Also bias task wakeups to semi-idle
+                                         * cpu package for power savings
+                                         */
+        MAX_POWERSAVINGS_BALANCE_LEVELS
+};
 
-#define BALANCE_FOR_PKG_POWER   \
-        ((sched_mc_power_savings || sched_smt_power_savings) ?  \
-         SD_POWERSAVINGS_BALANCE : 0)
+extern int sched_mc_power_savings, sched_smt_power_savings;
 
-#define test_sd_parent(sd, flag)        ((sd->parent &&         \
-                                         (sd->parent->flags & flag)) ? 1 : 0)
+static inline int sd_balance_for_mc_power(void)
+{
+        if (sched_smt_power_savings)
+                return SD_POWERSAVINGS_BALANCE;
 
+        return 0;
+}
+
+static inline int sd_balance_for_package_power(void)
+{
+        if (sched_mc_power_savings | sched_smt_power_savings)
+                return SD_POWERSAVINGS_BALANCE;
+
+        return 0;
+}
+
+/*
+ * Optimise SD flags for power savings:
+ * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
+ * Keep default SD flags if sched_{smt,mc}_power_saving=0
+ */
+
+static inline int sd_power_saving_flags(void)
+{
+        if (sched_mc_power_savings | sched_smt_power_savings)
+                return SD_BALANCE_NEWIDLE;
+
+        return 0;
+}
 
 struct sched_group {
         struct sched_group *next;       /* Must be a circular list */
-        cpumask_t cpumask;
 
         /*
          * CPU power of this group, SCHED_LOAD_SCALE being max power for a
@@ -784,8 +815,15 @@ struct sched_group {
          * (see include/linux/reciprocal_div.h)
          */
         u32 reciprocal_cpu_power;
+
+        unsigned long cpumask[];
 };
 
+static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+{
+        return to_cpumask(sg->cpumask);
+}
+
 enum sched_domain_level {
         SD_LV_NONE = 0,
         SD_LV_SIBLING,
@@ -809,7 +847,6 @@ struct sched_domain {
         struct sched_domain *parent;    /* top domain must be null terminated */
         struct sched_domain *child;     /* bottom domain must be null terminated */
         struct sched_group *groups;     /* the balancing groups of the domain */
-        cpumask_t span;                 /* span of all CPUs in this domain */
         unsigned long min_interval;     /* Minimum balance interval ms */
         unsigned long max_interval;     /* Maximum balance interval ms */
         unsigned int busy_factor;       /* less balancing by factor if busy */
@@ -864,18 +901,35 @@ struct sched_domain {
 #ifdef CONFIG_SCHED_DEBUG
         char *name;
 #endif
+
+        /* span of all CPUs in this domain */
+        unsigned long span[];
 };
 
-extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
+{
+        return to_cpumask(sd->span);
+}
+
+extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
                                     struct sched_domain_attr *dattr_new);
 extern int arch_reinit_sched_domains(void);
 
+/* Test a flag in parent sched domain */
+static inline int test_sd_parent(struct sched_domain *sd, int flag)
+{
+        if (sd->parent && (sd->parent->flags & flag))
+                return 1;
+
+        return 0;
+}
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
                         struct sched_domain_attr *dattr_new)
 {
 }
@@ -926,7 +980,7 @@ struct sched_class {
         void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 
         void (*set_cpus_allowed)(struct task_struct *p,
-                                 const cpumask_t *newmask);
+                                 const struct cpumask *newmask);
 
         void (*rq_online)(struct rq *rq);
         void (*rq_offline)(struct rq *rq);
@@ -1579,12 +1633,12 @@ extern cputime_t task_gtime(struct task_struct *p);
 
 #ifdef CONFIG_SMP
 extern int set_cpus_allowed_ptr(struct task_struct *p,
-                                const cpumask_t *new_mask);
+                                const struct cpumask *new_mask);
 #else
 static inline int set_cpus_allowed_ptr(struct task_struct *p,
-                                       const cpumask_t *new_mask)
+                                       const struct cpumask *new_mask)
 {
-        if (!cpu_isset(0, *new_mask))
+        if (!cpumask_test_cpu(0, new_mask))
                 return -EINVAL;
         return 0;
 }
@@ -2195,10 +2249,8 @@ __trace_special(void *__tr, void *__data,
 }
 #endif
 
-extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask);
-extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
-
-extern int sched_mc_power_savings, sched_smt_power_savings;
+extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
+extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 extern void normalize_rt_tasks(void);