Merge branch 'sched-for-linus' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/tip/linux-2.6-tip * 'sched-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (46 commits) sched: Add comments to find_busiest_group() function sched: Refactor the power savings balance code sched: Optimize the !power_savings_balance during fbg() sched: Create a helper function to calculate imbalance sched: Create helper to calculate small_imbalance in fbg() sched: Create a helper function to calculate sched_domain stats for fbg() sched: Define structure to store the sched_domain statistics for fbg() sched: Create a helper function to calculate sched_group stats for fbg() sched: Define structure to store the sched_group statistics for fbg() sched: Fix indentations in find_busiest_group() using gotos sched: Simple helper functions for find_busiest_group() sched: remove unused fields from struct rq sched: jiffies not printed per CPU sched: small optimisation of can_migrate_task() sched: fix typos in documentation sched: add avg_overlap decay x86, sched_clock(): mark variables read-mostly sched: optimize ttwu vs group scheduling sched: TIF_NEED_RESCHED -> need_reshed() cleanup sched: don't rebalance if attached on NULL domain ...
kyagi · Mar 26, 2009 · 831576f · 831576f
2 parents 21cdbc1 + 66fef08
commit 831576f
Show file tree

Hide file tree

Showing 20 changed files with 1,262 additions and 642 deletions.
diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX
@@ -2,8 +2,6 @@
 	- this file.
 sched-arch.txt
 	- CPU Scheduler implementation hints for architecture specific code.
-sched-coding.txt
-	- reference for various scheduler-related methods in the O(1) scheduler.
 sched-design-CFS.txt
 	- goals, design and implementation of the Complete Fair Scheduler.
 sched-domains.txt

diff --git a/Documentation/scheduler/sched-coding.txt b/Documentation/scheduler/sched-coding.txt
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
@@ -4,6 +4,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
+#include <linux/sched.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
 
@@ -56,11 +57,16 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 
 	/*
 	 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
-	 * with P/T states and does not stop in deep C-states
+	 * with P/T states and does not stop in deep C-states.
+	 *
+	 * It is also reliable across cores and sockets. (but not across
+	 * cabinets - we turn it off in that case explicitly.)
 	 */
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+		set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+		sched_clock_stable = 1;
 	}
 
 }

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
@@ -17,20 +17,21 @@
 #include <asm/delay.h>
 #include <asm/hypervisor.h>
 
-unsigned int cpu_khz;           /* TSC clocks / usec, not used here */
+unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
-unsigned int tsc_khz;
+
+unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
-static int tsc_unstable;
+static int __read_mostly tsc_unstable;
 
 /* native_sched_clock() is called before tsc_init(), so
    we must start with the TSC soft disabled to prevent
    erroneous rdtsc usage on !cpu_has_tsc processors */
-static int tsc_disabled = -1;
+static int __read_mostly tsc_disabled = -1;
 
 static int tsc_clocksource_reliable;
 /*

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
@@ -147,6 +147,7 @@ extern struct cred init_cred;
 		.nr_cpus_allowed = NR_CPUS,				\
 	},								\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
+	.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \
 	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\
 	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\
 	.real_parent	= &tsk,						\

diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
@@ -9,6 +9,7 @@
 #ifndef _INCLUDE_GUARD_LATENCYTOP_H_
 #define _INCLUDE_GUARD_LATENCYTOP_H_
 
+#include <linux/compiler.h>
 #ifdef CONFIG_LATENCYTOP
 
 #define LT_SAVECOUNT		32
@@ -24,7 +25,14 @@ struct latency_record {
 
 struct task_struct;
 
-void account_scheduler_latency(struct task_struct *task, int usecs, int inter);
+extern int latencytop_enabled;
+void __account_scheduler_latency(struct task_struct *task, int usecs, int inter);
+static inline void
+account_scheduler_latency(struct task_struct *task, int usecs, int inter)
+{
+	if (unlikely(latencytop_enabled))
+		__account_scheduler_latency(task, usecs, inter);
+}
 
 void clear_all_latency_tracing(struct task_struct *p);
 

diff --git a/include/linux/plist.h b/include/linux/plist.h
@@ -96,15 +96,18 @@ struct plist_node {
 # define PLIST_HEAD_LOCK_INIT(_lock)
 #endif
 
+#define _PLIST_HEAD_INIT(head)				\
+	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
+	.node_list = LIST_HEAD_INIT((head).node_list)
+
 /**
  * PLIST_HEAD_INIT - static struct plist_head initializer
  * @head:	struct plist_head variable name
  * @_lock:	lock to initialize for this list
  */
 #define PLIST_HEAD_INIT(head, _lock)			\
 {							\
-	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
-	.node_list = LIST_HEAD_INIT((head).node_list),	\
+        _PLIST_HEAD_INIT(head),                         \
 	PLIST_HEAD_LOCK_INIT(&(_lock))			\
 }
 
@@ -116,7 +119,7 @@ struct plist_node {
 #define PLIST_NODE_INIT(node, __prio)			\
 {							\
 	.prio  = (__prio),				\
-	.plist = PLIST_HEAD_INIT((node).plist, NULL),	\
+	.plist = { _PLIST_HEAD_INIT((node).plist) }, 	\
 }
 
 /**

diff --git a/include/linux/sched.h b/include/linux/sched.h
@@ -998,6 +998,7 @@ struct sched_class {
 			      struct rq *busiest, struct sched_domain *sd,
 			      enum cpu_idle_type idle);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
+	int (*needs_post_schedule) (struct rq *this_rq);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 
@@ -1052,6 +1053,10 @@ struct sched_entity {
 	u64			last_wakeup;
 	u64			avg_overlap;
 
+	u64			start_runtime;
+	u64			avg_wakeup;
+	u64			nr_migrations;
+
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
 	u64			wait_max;
@@ -1067,7 +1072,6 @@ struct sched_entity {
 	u64			exec_max;
 	u64			slice_max;
 
-	u64			nr_migrations;
 	u64			nr_migrations_cold;
 	u64			nr_failed_migrations_affine;
 	u64			nr_failed_migrations_running;
@@ -1164,6 +1168,7 @@ struct task_struct {
 #endif
 
 	struct list_head tasks;
+	struct plist_node pushable_tasks;
 
 	struct mm_struct *mm, *active_mm;
 
@@ -1675,6 +1680,16 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 	return set_cpus_allowed_ptr(p, &new_mask);
 }
 
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+extern int sched_clock_stable;
+#endif
+
 extern unsigned long long sched_clock(void);
 
 extern void sched_clock_init(void);

diff --git a/init/Kconfig b/init/Kconfig
@@ -966,7 +966,6 @@ config SLABINFO
 
 config RT_MUTEXES
 	boolean
-	select PLIST
 
 config BASE_SMALL
 	int
-Original file line number
+Diff line change
@@ Expand Up / @@ -966,7 +966,6 @@ config SLABINFO @@
     config RT_MUTEXES
     	boolean
-    	select PLIST
     config BASE_SMALL
     	int
@@ Expand Down @@