[PATCH] sched: make domain setup overridable

Allow sched domain setup to be overridden by arch code. This functionality
is needed again.

From: Paul Jackson <pj@sgi.com>

  Builds of 2.6.9-rc1-mm5 ia64 NUMA configs fail, with many complaints that
  SD_NODE_INIT is defined twice, in asm/processor.h and linux/sched.h.

  I guess that the preprocessor conditionals were wrong when Nick added the
  per-arch override ability again of SD_NODE_INIT were wrong.  At least this
  change lets me rebuild ia64 again.

Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 148 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 389a70ebb189..7f6608ed3ce8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -406,6 +406,154 @@ struct sched_info {
 extern struct file_operations proc_schedstat_operations;
 #endif
 
+enum idle_type
+{
+	SCHED_IDLE,
+	NOT_IDLE,
+	NEWLY_IDLE,
+	MAX_IDLE_TYPES
+};
+
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+#define SCHED_LOAD_SCALE	128UL	/* increase resolution of load */
+
+#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		4	/* Balance on exec */
+#define SD_WAKE_IDLE		8	/* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE		16	/* Wake task to waking CPU */
+#define SD_WAKE_BALANCE		32	/* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER	64	/* Domain members share cpu power */
+
+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
+	 * single CPU. This is read only (except for setup, hotplug CPU).
+	 */
+	unsigned long cpu_power;
+};
+
+struct sched_domain {
+	/* These fields must be setup */
+	struct sched_domain *parent;	/* top 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 */
+	unsigned int imbalance_pct;	/* No balance until over watermark */
+	unsigned long long cache_hot_time; /* Task considered cache hot (ns) */
+	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int per_cpu_gain;	/* CPU % gained by adding domain cpus */
+	int flags;			/* See SD_* */
+
+	/* Runtime fields. */
+	unsigned long last_balance;	/* init to jiffies. units in jiffies */
+	unsigned int balance_interval;	/* initialise to 1. units in ms. */
+	unsigned int nr_balance_failed; /* initialise to 0 */
+
+#ifdef CONFIG_SCHEDSTATS
+	/* load_balance() stats */
+	unsigned long lb_cnt[MAX_IDLE_TYPES];
+	unsigned long lb_failed[MAX_IDLE_TYPES];
+	unsigned long lb_imbalance[MAX_IDLE_TYPES];
+	unsigned long lb_nobusyg[MAX_IDLE_TYPES];
+	unsigned long lb_nobusyq[MAX_IDLE_TYPES];
+
+	/* sched_balance_exec() stats */
+	unsigned long sbe_attempts;
+	unsigned long sbe_pushed;
+
+	/* try_to_wake_up() stats */
+	unsigned long ttwu_wake_affine;
+	unsigned long ttwu_wake_balance;
+#endif
+};
+
+#ifdef ARCH_HAS_SCHED_DOMAIN
+/* Useful helpers that arch setup code may use. Defined in kernel/sched.c */
+extern cpumask_t cpu_isolated_map;
+extern void init_sched_build_groups(struct sched_group groups[],
+	                        cpumask_t span, int (*group_fn)(int cpu));
+extern void cpu_attach_domain(struct sched_domain *sd, int cpu);
+#endif
+
+#ifndef ARCH_HAS_SCHED_TUNE
+#ifdef CONFIG_SCHED_SMT
+#define ARCH_HAS_SCHED_WAKE_IDLE
+/* Common values for SMT siblings */
+#define SD_SIBLING_INIT (struct sched_domain) {		\
+	.span			= CPU_MASK_NONE,	\
+	.parent			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 1,			\
+	.max_interval		= 2,			\
+	.busy_factor		= 8,			\
+	.imbalance_pct		= 110,			\
+	.cache_hot_time		= 0,			\
+	.cache_nice_tries	= 0,			\
+	.per_cpu_gain		= 25,			\
+	.flags			= SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_EXEC	\
+				| SD_WAKE_AFFINE	\
+				| SD_WAKE_IDLE		\
+				| SD_SHARE_CPUPOWER,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+#endif
+
+/* Common values for CPUs */
+#define SD_CPU_INIT (struct sched_domain) {		\
+	.span			= CPU_MASK_NONE,	\
+	.parent			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 1,			\
+	.max_interval		= 4,			\
+	.busy_factor		= 64,			\
+	.imbalance_pct		= 125,			\
+	.cache_hot_time		= (5*1000/2),		\
+	.cache_nice_tries	= 1,			\
+	.per_cpu_gain		= 100,			\
+	.flags			= SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_EXEC	\
+				| SD_WAKE_AFFINE	\
+				| SD_WAKE_BALANCE,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+
+#if defined(CONFIG_NUMA) && !defined(SD_NODE_INIT)
+#define SD_NODE_INIT (struct sched_domain) {		\
+	.span			= CPU_MASK_NONE,	\
+	.parent			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 8,			\
+	.max_interval		= 32,			\
+	.busy_factor		= 32,			\
+	.imbalance_pct		= 125,			\
+	.cache_hot_time		= (10*1000),		\
+	.cache_nice_tries	= 1,			\
+	.per_cpu_gain		= 100,			\
+	.flags			= SD_BALANCE_EXEC	\
+				| SD_WAKE_BALANCE,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+#endif
+#endif /* ARCH_HAS_SCHED_TUNE */
+#endif /* CONFIG_SMP */
+
+
 struct io_context;			/* See blkdev.h */
 void exit_io_context(void);