scheduler changes for v3.5

index 09f6467..a2496e4 100644
@@ -70,31 +70,6 @@ void build_cpu_to_node_map(void);
 	.nr_balance_failed	= 0,			\
 }
 
-/* sched_domains SD_NODE_INIT for IA64 NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 8*(min(num_online_cpus(), 32U)), \
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 64,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP

index 1b1a7d1..b2cf641 100644
@@ -36,23 +36,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
 
 #define node_distance(from, to)	(__node_distances[(from)][(to)])
 
-/* sched_domains SD_NODE_INIT for SGI IP27 machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 1,			\
-	.flags			= SD_LOAD_BALANCE |	\
-				  SD_BALANCE_EXEC,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_MACH_TOPOLOGY_H */

index c971858..852ed1b 100644
@@ -18,12 +18,6 @@ struct device_node;
  */
 #define RECLAIM_DISTANCE 10
 
-/*
- * Avoid creating an extra level of balancing (SD_ALLNODES) on the largest
- * POWER7 boxes which have a maximum of 32 nodes.
- */
-#define SD_NODES_PER_DOMAIN 32
-
 #include <asm/mmzone.h>
 
 static inline int cpu_to_node(int cpu)

@@ -51,36 +45,6 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 
-/* sched_domains SD_NODE_INIT for PPC64 machines */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 8,					\
-	.max_interval		= 32,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 3,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 0*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-}
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 

index 88e7340..b0a282d 100644
@@ -3,31 +3,6 @@
 
 #ifdef CONFIG_NUMA
 
-/* sched_domains SD_NODE_INIT for sh machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #define cpu_to_node(cpu)	((void)(cpu),0)
 #define parent_node(node)	((void)(node),0)
 

index 8b9c556..1754390 100644
@@ -31,25 +31,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 	 cpu_all_mask : \
 	 cpumask_of_node(pcibus_to_node(bus)))
 
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 2,			\
-	.newidle_idx		= 0, 			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-}
-
 #else /* CONFIG_NUMA */
 
 #include <asm-generic/topology.h>

index 6fdd0c8..7a7ce39 100644
@@ -78,32 +78,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 	.balance_interval	= 32,					\
 }
 
-/* sched_domains SD_NODE_INIT for TILE architecture */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 16,					\
-	.max_interval		= 512,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 3,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 2,					\
-	.wake_idx		= 1,					\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 0*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 128,					\
-}
-
 /* By definition, we create nodes based on online memory. */
 #define node_has_online_mem(nid) 1
 

index b9676ae..095b215 100644
@@ -92,44 +92,6 @@ extern void setup_node_to_cpumask_map(void);
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
-#ifdef CONFIG_X86_32
-# define SD_CACHE_NICE_TRIES	1
-# define SD_IDLE_IDX		1
-#else
-# define SD_CACHE_NICE_TRIES	2
-# define SD_IDLE_IDX		2
-#endif
-
-/* sched_domains SD_NODE_INIT for NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) {				\
-	.min_interval		= 8,					\
-	.max_interval		= 32,					\
-	.busy_factor		= 32,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= SD_CACHE_NICE_TRIES,			\
-	.busy_idx		= 3,					\
-	.idle_idx		= SD_IDLE_IDX,				\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_PREFER_LOCAL			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_POWERSAVINGS_BALANCE		\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 1*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-}
-
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 

index 1d92a5a..ad57d83 100644
@@ -594,9 +594,17 @@ int mwait_usable(const struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
 
+	/* Use mwait if idle=mwait boot option is given */
 	if (boot_option_idle_override == IDLE_FORCE_MWAIT)
 		return 1;
 
+	/*
+	 * Any idle= boot option other than idle=mwait means that we must not
+	 * use mwait. Eg: idle=halt or idle=poll or idle=nomwait
+	 */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return 0;
+
 	if (c->cpuid_level < MWAIT_INFO)
 		return 0;
 

136 lines not on this page · raw message

index 53489ff..871dd88 100644
@@ -339,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	} else {
 		unsigned long n;
 
-		n = simple_strtoul(emu_cmdline, NULL, 0);
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
 		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
 	}
+	if (*emu_cmdline == ':')
+		emu_cmdline++;
 
 	if (ret < 0)
 		goto no_emu;

@@ -418,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 			int physj = emu_nid_to_phys[j];
 			int dist;
 
-			if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+			if (get_option(&emu_cmdline, &dist) == 2)
+				;
+			else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
 				dist = physi == physj ?
 					LOCAL_DISTANCE : REMOTE_DISTANCE;
 			else

index adf937b..6345294 100644
@@ -330,8 +330,4 @@ void __init cpu_dev_init(void)
 		panic("Failed to register CPU subsystem");
 
 	cpu_dev_register_generic();
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	sched_create_sysfs_power_savings_entries(cpu_subsys.dev_root);
-#endif
 }

index ee28844..7230bb5 100644
@@ -36,8 +36,6 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr);
 extern int cpu_add_dev_attr_group(struct attribute_group *attrs);
 extern void cpu_remove_dev_attr_group(struct attribute_group *attrs);
 
-extern int sched_create_sysfs_power_savings_entries(struct device *dev);
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 extern ssize_t arch_cpu_probe(const char *, size_t);

69 lines not on this page · raw message

78 lines not on this page · raw message

503 lines not on this page · raw message

index 09acaa1..6f79596 100644
@@ -202,7 +202,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(spread0));
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
-	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP

@@ -260,8 +260,14 @@ static void print_cpu(struct seq_file *m, int cpu)
 	SEQ_printf(m, "\ncpu#%d\n", cpu);
 #endif
 
-#define P(x) \
-	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))
+#define P(x)								\
+do {									\
+	if (sizeof(rq->x) == 4)						\
+		SEQ_printf(m, "  .%-30s: %ld\n", #x, (long)(rq->x));	\
+	else								\
+		SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x));\
+} while (0)
+
 #define PN(x) \
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
 

836 lines not on this page · raw message

index 91b4c95..b44d604 100644
@@ -4,7 +4,7 @@
  * idle-task scheduling class.
  *
  * (NOTE: these are not related to SCHED_IDLE tasks which are
- *  handled in sched_fair.c)
+ *  handled in sched/fair.c)
  */
 
 #ifdef CONFIG_SMP

70 lines not on this page · raw message

index fb3acba..ba9dccf 100644
@@ -201,7 +201,7 @@ struct cfs_bandwidth { };
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
-	unsigned long nr_running, h_nr_running;
+	unsigned int nr_running, h_nr_running;
 
 	u64 exec_clock;
 	u64 min_vruntime;

@@ -279,7 +279,7 @@ static inline int rt_bandwidth_enabled(void)
 /* Real-Time classes' related field in a runqueue: */
 struct rt_rq {
 	struct rt_prio_array active;
-	unsigned long rt_nr_running;
+	unsigned int rt_nr_running;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
 	struct {
 		int curr; /* highest queued rt task prio */

@@ -353,7 +353,7 @@ struct rq {
 	 * nr_running and cpu_load should be in the same cacheline because
 	 * remote CPUs use both these fields when doing load calculation.
 	 */
-	unsigned long nr_running;
+	unsigned int nr_running;
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 	unsigned long last_load_update_tick;

@@ -876,7 +876,7 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
-extern void update_cpu_load(struct rq *this_rq);
+extern void update_idle_cpu_load(struct rq *this_rq);
 
 #ifdef CONFIG_CGROUP_CPUACCT
 #include <linux/cgroup.h>

index c634302..96e28c1 100644
@@ -362,22 +362,7 @@ char *sysfs_get_cpuidle_driver(void)
  */
 int sysfs_get_sched(const char *smt_mc)
 {
-	unsigned long value;
-	char linebuf[MAX_LINE_LEN];
-	char *endp;
-	char path[SYSFS_PATH_MAX];
-
-	if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc))
-		return -EINVAL;
-
-	snprintf(path, sizeof(path),
-		PATH_TO_CPU "sched_%s_power_savings", smt_mc);
-	if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0)
-		return -1;
-	value = strtoul(linebuf, &endp, 0);
-	if (endp == linebuf || errno == ERANGE)
-		return -1;
-	return value;
+	return -ENODEV;
 }
 
 /*

@@ -388,21 +373,5 @@ int sysfs_get_sched(const char *smt_mc)
  */
 int sysfs_set_sched(const char *smt_mc, int val)
 {
-	char linebuf[MAX_LINE_LEN];
-	char path[SYSFS_PATH_MAX];
-	struct stat statbuf;
-
-	if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc))
-		return -EINVAL;
-
-	snprintf(path, sizeof(path),
-		PATH_TO_CPU "sched_%s_power_savings", smt_mc);
-	sprintf(linebuf, "%d", val);
-
-	if (stat(path, &statbuf) != 0)
-		return -ENODEV;
-
-	if (sysfs_write_file(path, linebuf, MAX_LINE_LEN) == 0)
-		return -1;
-	return 0;
+	return -ENODEV;
 }