sched: Rework sched_domain topology definition

We replace the old way to configure the scheduler topology with a new method
which enables a platform to declare additionnal level (if needed).

We still have a default topology table definition that can be used by platform
that don't want more level than the SMT, MC, CPU and NUMA ones. This table can
be overwritten by an arch which either wants to add new level where a load
balance make sense like BOOK or powergating level or wants to change the flags
configuration of some levels.

For each level, we need a function pointer that returns cpumask for each cpu,
a function pointer that returns the flags for the level and a name. Only flags
that describe topology, can be set by an architecture. The current topology
flags are:

 SD_SHARE_CPUPOWER
 SD_SHARE_PKG_RESOURCES
 SD_NUMA
 SD_ASYM_PACKING

Then, each level must be a subset on the next one. The build sequence of the
sched_domain will take care of removing useless levels like those with 1 CPU
and those with the same CPU span and no more relevant information for
load balancing than its children.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hanjun Guo <hanjun.guo@linaro.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux390@de.ibm.com
Cc: linux-ia64@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Link: http://lkml.kernel.org/r/1397209481-28542-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 13 insertions, 115 deletions

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7062330a1329..973671ff9e7d 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -66,121 +66,6 @@ int arch_update_cpu_topology(void);
 #define PENALTY_FOR_NODE_WITH_CPUS	(1)
 #endif
 
-/*
- * Below are the 3 major initializers used in building sched_domains:
- * SD_SIBLING_INIT, for SMT domains
- * SD_CPU_INIT, for SMP domains
- *
- * Any architecture that cares to do any tuning to these values should do so
- * by defining their own arch-specific initializer in include/asm/topology.h.
- * A definition there will automagically override these default initializers
- * and allow arch-specific performance tuning of sched_domains.
- * (Only non-zero and non-null fields need be specified.)
- */
-
-#ifdef CONFIG_SCHED_SMT
-/* MCD - Do we really need this?  It is always on if CONFIG_SCHED_SMT is,
- * so can't we drop this in favor of CONFIG_SCHED_SMT?
- */
-#define ARCH_HAS_SCHED_WAKE_IDLE
-/* Common values for SMT siblings */
-#ifndef SD_SIBLING_INIT
-#define SD_SIBLING_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 2,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 110,					\
-									\
-	.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			\
-				| 1*SD_SHARE_CPUPOWER			\
-				| 1*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				| arch_sd_sibling_asym_packing()	\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.smt_gain		= 1178,	/* 15% */			\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-#endif /* CONFIG_SCHED_SMT */
-
-#ifdef CONFIG_SCHED_MC
-/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */
-#ifndef SD_MC_INIT
-#define SD_MC_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 4,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 2,					\
-	.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_SHARE_CPUPOWER			\
-				| 1*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-#endif /* CONFIG_SCHED_MC */
-
-/* Common values for CPUs */
-#ifndef SD_CPU_INIT
-#define SD_CPU_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 4,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 2,					\
-	.idle_idx		= 1,					\
-	.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_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				| 1*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-
-#ifdef CONFIG_SCHED_BOOK
-#ifndef SD_BOOK_INIT
-#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
-#endif
-#endif /* CONFIG_SCHED_BOOK */
-
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DECLARE_PER_CPU(int, numa_node);
 
@@ -295,4 +180,17 @@ static inline int cpu_to_mem(int cpu)
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
 #endif
 
+#ifdef CONFIG_SCHED_SMT
+static inline const struct cpumask *cpu_smt_mask(int cpu)
+{
+	return topology_thread_cpumask(cpu);
+}
+#endif
+
+static inline const struct cpumask *cpu_cpu_mask(int cpu)
+{
+	return cpumask_of_node(cpu_to_node(cpu));
+}
+
+
 #endif /* _LINUX_TOPOLOGY_H */