---

yaml --- r: 366075 b: refs/heads/master c: 56dd947 h: refs/heads/master i: 366073: 7a6ea4c 366071: 93e5400 v: v3
git-mirror · Mar 7, 2013 · 1ef7f95 · 1ef7f95
1 parent a1b3217
commit 1ef7f95
Show file tree

Hide file tree

Showing 10 changed files with 225 additions and 195 deletions.
diff --git a/[refs] b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 27b4b9319a3c2e8654d45df99ce584c7c2cfe100
+refs/heads/master: 56dd9470d7c8734f055da2a6bac553caf4a468eb
diff --git a/trunk/arch/x86/include/asm/context_tracking.h b/trunk/arch/x86/include/asm/context_tracking.h
@@ -1,31 +1,10 @@
 #ifndef _ASM_X86_CONTEXT_TRACKING_H
 #define _ASM_X86_CONTEXT_TRACKING_H
 
-#ifndef __ASSEMBLY__
-#include <linux/context_tracking.h>
-#include <asm/ptrace.h>
-
-static inline void exception_enter(struct pt_regs *regs)
-{
-	user_exit();
-}
-
-static inline void exception_exit(struct pt_regs *regs)
-{
-#ifdef CONFIG_CONTEXT_TRACKING
-	if (user_mode(regs))
-		user_enter();
-#endif
-}
-
-#else /* __ASSEMBLY__ */
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER call schedule_user
 #else
 # define SCHEDULE_USER call schedule
 #endif
 
-#endif /* !__ASSEMBLY__ */
-
 #endif
diff --git a/trunk/arch/x86/kernel/kvm.c b/trunk/arch/x86/kernel/kvm.c
@@ -20,6 +20,7 @@
  *   Authors: Anthony Liguori <aliguori@us.ibm.com>
  */
 
+#include <linux/context_tracking.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/kvm_para.h>
@@ -43,7 +44,6 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/kvm_guest.h>
-#include <asm/context_tracking.h>
 
 static int kvmapf = 1;
 

diff --git a/trunk/arch/x86/kernel/traps.c b/trunk/arch/x86/kernel/traps.c
@@ -12,6 +12,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/context_tracking.h>
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 #include <linux/spinlock.h>
@@ -55,8 +56,6 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/context_tracking.h>
-
 #include <asm/mach_traps.h>
 
 #ifdef CONFIG_X86_64

diff --git a/trunk/arch/x86/mm/fault.c b/trunk/arch/x86/mm/fault.c
@@ -13,12 +13,12 @@
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
+#include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/context_tracking.h>	/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:

diff --git a/trunk/include/linux/context_tracking.h b/trunk/include/linux/context_tracking.h
@@ -1,10 +1,11 @@
 #ifndef _LINUX_CONTEXT_TRACKING_H
 #define _LINUX_CONTEXT_TRACKING_H
 
-#ifdef CONFIG_CONTEXT_TRACKING
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <asm/ptrace.h>
 
+#ifdef CONFIG_CONTEXT_TRACKING
 struct context_tracking {
 	/*
 	 * When active is false, probes are unset in order
@@ -33,12 +34,26 @@ static inline bool context_tracking_active(void)
 
 extern void user_enter(void);
 extern void user_exit(void);
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+	user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		user_enter();
+}
+
 extern void context_tracking_task_switch(struct task_struct *prev,
 					 struct task_struct *next);
 #else
 static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
+static inline void exception_enter(struct pt_regs *regs) { }
+static inline void exception_exit(struct pt_regs *regs) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */

diff --git a/trunk/include/linux/sched.h b/trunk/include/linux/sched.h
@@ -127,6 +127,18 @@ extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
 extern void
 print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+#else
+static inline void
+proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+{
+}
+static inline void proc_sched_set_task(struct task_struct *p)
+{
+}
+static inline void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
+{
+}
 #endif
 
 /*
@@ -755,6 +767,31 @@ enum cpu_idle_type {
 	CPU_MAX_IDLE_TYPES
 };
 
+/*
+ * Increase resolution of nice-level calculations for 64-bit architectures.
+ * The extra resolution improves shares distribution and load balancing of
+ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
+ * hierarchies, especially on larger systems. This is not a user-visible change
+ * and does not change the user-interface for setting shares/weights.
+ *
+ * We increase resolution only if we have enough bits to allow this increased
+ * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
+ * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
+ * increased costs.
+ */
+#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
+# define SCHED_LOAD_RESOLUTION	10
+# define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
+# define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)
+#else
+# define SCHED_LOAD_RESOLUTION	0
+# define scale_load(w)		(w)
+# define scale_load_down(w)	(w)
+#endif
+
+#define SCHED_LOAD_SHIFT	(10 + SCHED_LOAD_RESOLUTION)
+#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)
+
 /*
  * Increase resolution of cpu_power calculations
  */
@@ -780,6 +817,62 @@ enum cpu_idle_type {
 
 extern int __weak arch_sd_sibiling_asym_packing(void);
 
+struct sched_group_power {
+	atomic_t ref;
+	/*
+	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
+	 * single CPU.
+	 */
+	unsigned int power, power_orig;
+	unsigned long next_update;
+	/*
+	 * Number of busy cpus in this group.
+	 */
+	atomic_t nr_busy_cpus;
+
+	unsigned long cpumask[0]; /* iteration mask */
+};
+
+struct sched_group {
+	struct sched_group *next;	/* Must be a circular list */
+	atomic_t ref;
+
+	unsigned int group_weight;
+	struct sched_group_power *sgp;
+
+	/*
+	 * The CPUs this group covers.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 */
+	unsigned long cpumask[0];
+};
+
+static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+{
+	return to_cpumask(sg->cpumask);
+}
+
+/*
+ * cpumask masking which cpus in the group are allowed to iterate up the domain
+ * tree.
+ */
+static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+{
+	return to_cpumask(sg->sgp->cpumask);
+}
+
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
+
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -790,8 +883,6 @@ struct sched_domain_attr {
 
 extern int sched_domain_level_max;
 
-struct sched_group;
-
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -880,6 +971,18 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
+/* 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;
+}
+
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
 #else /* CONFIG_SMP */
@@ -914,6 +1017,72 @@ struct mempolicy;
 struct pipe_inode_info;
 struct uts_namespace;
 
+struct rq;
+struct sched_domain;
+
+/*
+ * wake flags
+ */
+#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
+#define WF_FORK		0x02		/* child wakeup after fork */
+#define WF_MIGRATED	0x04		/* internal use, task got migrated */
+
+#define ENQUEUE_WAKEUP		1
+#define ENQUEUE_HEAD		2
+#ifdef CONFIG_SMP
+#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
+#else
+#define ENQUEUE_WAKING		0
+#endif
+
+#define DEQUEUE_SLEEP		1
+
+struct sched_class {
+	const struct sched_class *next;
+
+	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
+	void (*yield_task) (struct rq *rq);
+	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
+
+	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
+
+	struct task_struct * (*pick_next_task) (struct rq *rq);
+	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
+
+#ifdef CONFIG_SMP
+	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
+
+	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
+	void (*post_schedule) (struct rq *this_rq);
+	void (*task_waking) (struct task_struct *task);
+	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
+
+	void (*set_cpus_allowed)(struct task_struct *p,
+				 const struct cpumask *newmask);
+
+	void (*rq_online)(struct rq *rq);
+	void (*rq_offline)(struct rq *rq);
+#endif
+
+	void (*set_curr_task) (struct rq *rq);
+	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
+	void (*task_fork) (struct task_struct *p);
+
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
+	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
+			     int oldprio);
+
+	unsigned int (*get_rr_interval) (struct rq *rq,
+					 struct task_struct *task);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	void (*task_move_group) (struct task_struct *p, int on_rq);
+#endif
+};
+
 struct load_weight {
 	unsigned long weight, inv_weight;
 };
@@ -2512,7 +2681,28 @@ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 #ifdef CONFIG_CGROUP_SCHED
+
 extern struct task_group root_task_group;
+
+extern struct task_group *sched_create_group(struct task_group *parent);
+extern void sched_online_group(struct task_group *tg,
+			       struct task_group *parent);
+extern void sched_destroy_group(struct task_group *tg);
+extern void sched_offline_group(struct task_group *tg);
+extern void sched_move_task(struct task_struct *tsk);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
+extern unsigned long sched_group_shares(struct task_group *tg);
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+extern int sched_group_set_rt_runtime(struct task_group *tg,
+				      long rt_runtime_us);
+extern long sched_group_rt_runtime(struct task_group *tg);
+extern int sched_group_set_rt_period(struct task_group *tg,
+				      long rt_period_us);
+extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
+#endif
 #endif /* CONFIG_CGROUP_SCHED */
 
 extern int task_can_switch_user(struct user_struct *up,