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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (29 commits)
  sched: Export account_system_vtime()
  sched: Call tick_check_idle before __irq_enter
  sched: Remove irq time from available CPU power
  sched: Do not account irq time to current task
  x86: Add IRQ_TIME_ACCOUNTING
  sched: Add IRQ_TIME_ACCOUNTING, finer accounting of irq time
  sched: Add a PF flag for ksoftirqd identification
  sched: Consolidate account_system_vtime extern declaration
  sched: Fix softirq time accounting
  sched: Drop group_capacity to 1 only if local group has extra capacity
  sched: Force balancing on newidle balance if local group has capacity
  sched: Set group_imb only a task can be pulled from the busiest cpu
  sched: Do not consider SCHED_IDLE tasks to be cache hot
  sched: Drop all load weight manipulation for RT tasks
  sched: Create special class for stop/migrate work
  sched: Unindent labels
  sched: Comment updates: fix default latency and granularity numbers
  tracing/sched: Add sched_pi_setprio tracepoint
  sched: Give CPU bound RT tasks preference
  sched: Try not to migrate higher priority RT tasks
  ...

8 files changed, 142 insertions, 70 deletions

diff --git a/arch/ia64/include/asm/system.h b/arch/ia64/include/asm/system.h
index 9f342a574ce..dd028f2b13b 100644
--- a/arch/ia64/include/asm/system.h
+++ b/arch/ia64/include/asm/system.h
@@ -272,10 +272,6 @@ void cpu_idle_wait(void);
 
 void default_idle(void);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index 6c294acac84..9c3d160670b 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -542,10 +542,6 @@ extern void reloc_got2(unsigned long);
 
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 extern struct dentry *powerpc_debugfs_root;
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 958f0dadead..75976a14194 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -199,6 +199,13 @@ config HOTPLUG_CPU
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+	bool "Book scheduler support"
+	depends on SMP
+	help
+	  Book scheduler support improves the CPU scheduler's decision making
+	  when dealing with machines that have several books.
+
 config MATHEMU
 	bool "IEEE FPU emulation"
 	depends on MARCH_G5
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index cef66210c84..38ddd8a9a9e 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -97,7 +97,6 @@ static inline void restore_access_regs(unsigned int *acrs)
 
 extern void account_vtime(struct task_struct *, struct task_struct *);
 extern void account_tick_vtime(struct task_struct *);
-extern void account_system_vtime(struct task_struct *);
 
 #ifdef CONFIG_PFAULT
 extern void pfault_irq_init(void);
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 831bd033ea7..051107a2c5e 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()	(1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+#define mc_capable()			(1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+	return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)		(cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@ static inline void s390_init_cpu_topology(void)
 };
 #endif
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bcef00766a6..13559c99384 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@ struct tl_info {
 	union tl_entry tle[0];
 };
 
-struct core_info {
-	struct core_info *next;
+struct mask_info {
+	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
@@ -66,7 +66,6 @@ struct core_info {
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topology_work_fn);
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-	struct core_info *core = &core_info;
-	unsigned long flags;
 	cpumask_t mask;
 
 	cpus_clear(mask);
 	if (!topology_enabled || !machine_has_topology)
 		return cpu_possible_map;
-	spin_lock_irqsave(&topology_lock, flags);
-	while (core) {
-		if (cpu_isset(cpu, core->mask)) {
-			mask = core->mask;
+	while (info) {
+		if (cpu_isset(cpu, info->mask)) {
+			mask = info->mask;
 			break;
 		}
-		core = core->next;
+		info = info->next;
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
 	if (cpus_empty(mask))
 		mask = cpumask_of_cpu(cpu);
 	return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-	return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+			     struct mask_info *core)
 {
 	unsigned int cpu;
 
@@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 
 		rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
 		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) == rcpu) {
-				cpu_set(lcpu, core->mask);
-				cpu_core_id[lcpu] = core->id;
-				smp_cpu_polarization[lcpu] = tl_cpu->pp;
-			}
+			if (cpu_logical_map(lcpu) != rcpu)
+				continue;
+#ifdef CONFIG_SCHED_BOOK
+			cpu_set(lcpu, book->mask);
+			cpu_book_id[lcpu] = book->id;
+#endif
+			cpu_set(lcpu, core->mask);
+			cpu_core_id[lcpu] = core->id;
+			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-	struct core_info *core = &core_info;
+	struct mask_info *info;
 
-	while (core) {
-		cpus_clear(core->mask);
-		core = core->next;
+	info = &core_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
+	}
+#ifdef CONFIG_SCHED_BOOK
+	info = &book_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
 	}
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl_entry *tle)
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+	struct mask_info *book = &book_info;
+#else
+	struct mask_info *book = NULL;
+#endif
+	struct mask_info *core = &core_info;
 	union tl_entry *tle, *end;
-	struct core_info *core = &core_info;
+
 
 	spin_lock_irq(&topology_lock);
-	clear_cores();
+	clear_masks();
 	tle = info->tle;
 	end = (union tl_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
-		case 5:
-		case 4:
-		case 3:
+#ifdef CONFIG_SCHED_BOOK
 		case 2:
+			book = book->next;
+			book->id = tle->container.id;
 			break;
+#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_core(&tle->cpu, core);
+			add_cpus_to_mask(&tle->cpu, book, core);
 			break;
 		default:
-			clear_cores();
+			clear_masks();
 			machine_has_topology = 0;
 			goto out;
 		}
@@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_core_map(void)
 {
+	unsigned long flags;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+	int rc;
+
+	rc = stsi(info, 15, 1, 3);
+	if (rc != -ENOSYS)
+		return;
+#endif
+	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@ int arch_update_cpu_topology(void)
 		topology_update_polarization_simple();
 		return 0;
 	}
-	stsi(info, 15, 1, 2);
+	store_topology(info);
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@ out:
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask = mask->next;
+	}
+}
+
 void __init s390_init_cpu_topology(void)
 {
 	unsigned long long facility_bits;
 	struct tl_info *info;
-	struct core_info *core;
-	int nr_cores;
 	int i;
 
 	if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void)
 
 	tl_info = alloc_bootmem_pages(PAGE_SIZE);
 	info = tl_info;
-	stsi(info, 15, 1, 2);
-
-	nr_cores = info->mag[NR_MAG - 2];
-	for (i = 0; i < info->mnest - 2; i++)
-		nr_cores *= info->mag[NR_MAG - 3 - i];
-
+	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-
-	core = &core_info;
-	for (i = 0; i < nr_cores; i++) {
-		core->next = alloc_bootmem(sizeof(struct core_info));
-		core = core->next;
-		if (!core)
-			goto error;
-	}
-	return;
-error:
-	machine_has_topology = 0;
+	alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+	alloc_masks(info, &book_info, 3);
+#endif
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fd227d6b8d9..89b88e3a56e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -799,6 +799,17 @@ config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config IRQ_TIME_ACCOUNTING
+	bool "Fine granularity task level IRQ time accounting"
+	default n
+	---help---
+	  Select this option to enable fine granularity task irq time
+	  accounting. This is done by reading a timestamp on each
+	  transitions between softirq and hardirq state, so there can be a
+	  small performance impact.
+
+	  If in doubt, say N here.
+
 source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 26a863a9c2a..a1c2cd76853 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,10 +104,14 @@ int __init notsc_setup(char *str)
 
 __setup("notsc", notsc_setup);
 
+static int no_sched_irq_time;
+
 static int __init tsc_setup(char *str)
 {
 	if (!strcmp(str, "reliable"))
 		tsc_clocksource_reliable = 1;
+	if (!strncmp(str, "noirqtime", 9))
+		no_sched_irq_time = 1;
 	return 1;
 }
 
@@ -801,6 +805,7 @@ void mark_tsc_unstable(char *reason)
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
 		sched_clock_stable = 0;
+		disable_sched_clock_irqtime();
 		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
@@ -987,6 +992,9 @@ void __init tsc_init(void)
 	/* now allow native_sched_clock() to use rdtsc */
 	tsc_disabled = 0;
 
+	if (!no_sched_irq_time)
+		enable_sched_clock_irqtime();
+
 	lpj = ((u64)tsc_khz * 1000);
 	do_div(lpj, HZ);
 	lpj_fine = lpj;