diff mbox

[v2,2/7] sched: rework of sched_domain topology definition

Message ID 1395165409-18055-3-git-send-email-vincent.guittot@linaro.org
State New
Headers show

Commit Message

Vincent Guittot March 18, 2014, 5:56 p.m. UTC
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 wants to add new level where a load balance
make sense like BOOK or powergating level.

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 relevant information for load balancing
than its child.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 arch/ia64/include/asm/topology.h |  24 ----
 arch/s390/include/asm/topology.h |   2 -
 arch/tile/include/asm/topology.h |  33 ------
 include/linux/sched.h            |  48 ++++++++
 include/linux/topology.h         | 128 +++------------------
 kernel/sched/core.c              | 235 ++++++++++++++++++++-------------------
 6 files changed, 183 insertions(+), 287 deletions(-)

Comments

Preeti U Murthy March 19, 2014, 6:01 a.m. UTC | #1
On 03/18/2014 11:26 PM, Vincent Guittot wrote:
> 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 wants to add new level where a load balance
> make sense like BOOK or powergating level.
> 
> 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 relevant information for load balancing
> than its child.
> 
> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> ---
>  arch/ia64/include/asm/topology.h |  24 ----
>  arch/s390/include/asm/topology.h |   2 -
>  arch/tile/include/asm/topology.h |  33 ------
>  include/linux/sched.h            |  48 ++++++++
>  include/linux/topology.h         | 128 +++------------------
>  kernel/sched/core.c              | 235 ++++++++++++++++++++-------------------
>  6 files changed, 183 insertions(+), 287 deletions(-)
> 
> diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
> index 5cb55a1..3202aa7 100644
> --- a/arch/ia64/include/asm/topology.h
> +++ b/arch/ia64/include/asm/topology.h
> @@ -46,30 +46,6 @@
> 
>  void build_cpu_to_node_map(void);
> 
> -#define SD_CPU_INIT (struct sched_domain) {		\
> -	.parent			= NULL,			\
> -	.child			= NULL,			\
> -	.groups			= NULL,			\
> -	.min_interval		= 1,			\
> -	.max_interval		= 4,			\
> -	.busy_factor		= 64,			\
> -	.imbalance_pct		= 125,			\
> -	.cache_nice_tries	= 2,			\
> -	.busy_idx		= 2,			\
> -	.idle_idx		= 1,			\
> -	.newidle_idx		= 0,			\
> -	.wake_idx		= 0,			\
> -	.forkexec_idx		= 0,			\
> -	.flags			= SD_LOAD_BALANCE	\
> -				| SD_BALANCE_NEWIDLE	\
> -				| SD_BALANCE_EXEC	\
> -				| SD_BALANCE_FORK	\
> -				| SD_WAKE_AFFINE,	\
> -	.last_balance		= jiffies,		\
> -	.balance_interval	= 1,			\
> -	.nr_balance_failed	= 0,			\
> -}
> -
>  #endif /* CONFIG_NUMA */
> 
>  #ifdef CONFIG_SMP
> diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
> index 05425b1..07763bd 100644
> --- a/arch/s390/include/asm/topology.h
> +++ b/arch/s390/include/asm/topology.h
> @@ -64,8 +64,6 @@ 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/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
> index d15c0d8..9383118 100644
> --- a/arch/tile/include/asm/topology.h
> +++ b/arch/tile/include/asm/topology.h
> @@ -44,39 +44,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
>  /* For now, use numa node -1 for global allocation. */
>  #define pcibus_to_node(bus)		((void)(bus), -1)
> 
> -/*
> - * TILE architecture has many cores integrated in one processor, so we need
> - * setup bigger balance_interval for both CPU/NODE scheduling domains to
> - * reduce process scheduling costs.
> - */
> -
> -/* sched_domains SD_CPU_INIT for TILE architecture */
> -#define SD_CPU_INIT (struct sched_domain) {				\
> -	.min_interval		= 4,					\
> -	.max_interval		= 128,					\
> -	.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			\
> -				| 0*SD_WAKE_AFFINE			\
> -				| 0*SD_SHARE_CPUPOWER			\
> -				| 0*SD_SHARE_PKG_RESOURCES		\
> -				| 0*SD_SERIALIZE			\
> -				,					\
> -	.last_balance		= jiffies,				\
> -	.balance_interval	= 32,					\
> -}
> -
>  /* By definition, we create nodes based on online memory. */
>  #define node_has_online_mem(nid) 1
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 825ed83..4db592a 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -870,6 +870,20 @@ enum cpu_idle_type {
> 
>  extern int __weak arch_sd_sibiling_asym_packing(void);
> 
> +#ifdef CONFIG_SCHED_SMT
> +static inline const int cpu_smt_flags(void)
> +{
> +	return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
> +}
> +#endif
> +
> +#ifdef CONFIG_SCHED_MC
> +static inline const int cpu_core_flags(void)
> +{
> +	return SD_SHARE_PKG_RESOURCES;
> +}
> +#endif
> +
>  struct sched_domain_attr {
>  	int relax_domain_level;
>  };
> @@ -976,6 +990,38 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
> 
>  bool cpus_share_cache(int this_cpu, int that_cpu);
> 
> +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
> +typedef const int (*sched_domain_flags_f)(void);
> +
> +#define SDTL_OVERLAP	0x01
> +
> +struct sd_data {
> +	struct sched_domain **__percpu sd;
> +	struct sched_group **__percpu sg;
> +	struct sched_group_power **__percpu sgp;
> +};
> +
> +struct sched_domain_topology_level {
> +	sched_domain_mask_f mask;
> +	sched_domain_flags_f sd_flags;
> +	int		    flags;
> +	int		    numa_level;
> +	struct sd_data      data;
> +#ifdef CONFIG_SCHED_DEBUG
> +	char                *name;
> +#endif
> +};
> +
> +extern struct sched_domain_topology_level *sched_domain_topology;
> +
> +extern void set_sched_topology(struct sched_domain_topology_level *tl);
> +
> +#ifdef CONFIG_SCHED_DEBUG
> +# define SD_INIT_NAME(type)		.name = #type
> +#else
> +# define SD_INIT_NAME(type)
> +#endif
> +
>  #else /* CONFIG_SMP */
> 
>  struct sched_domain_attr;
> @@ -991,6 +1037,8 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
>  	return true;
>  }
> 
> +static inline void set_sched_topology(struct sched_domain_topology_level *tl) { }
> +
>  #endif	/* !CONFIG_SMP */
> 
> 
> diff --git a/include/linux/topology.h b/include/linux/topology.h
> index 12ae6ce..3a9db05 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 */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index ae365aa..3397bcb 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5603,17 +5603,6 @@ static int __init isolated_cpu_setup(char *str)
> 
>  __setup("isolcpus=", isolated_cpu_setup);
> 
> -static const struct cpumask *cpu_cpu_mask(int cpu)
> -{
> -	return cpumask_of_node(cpu_to_node(cpu));
> -}
> -
> -struct sd_data {
> -	struct sched_domain **__percpu sd;
> -	struct sched_group **__percpu sg;
> -	struct sched_group_power **__percpu sgp;
> -};
> -
>  struct s_data {
>  	struct sched_domain ** __percpu sd;
>  	struct root_domain	*rd;
> @@ -5626,21 +5615,6 @@ enum s_alloc {
>  	sa_none,
>  };
> 
> -struct sched_domain_topology_level;
> -
> -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
> -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
> -
> -#define SDTL_OVERLAP	0x01
> -
> -struct sched_domain_topology_level {
> -	sched_domain_init_f init;
> -	sched_domain_mask_f mask;
> -	int		    flags;
> -	int		    numa_level;
> -	struct sd_data      data;
> -};
> -
>  /*
>   * Build an iteration mask that can exclude certain CPUs from the upwards
>   * domain traversal.
> @@ -5869,34 +5843,6 @@ int __weak arch_sd_sibling_asym_packing(void)
>   * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
>   */
> 
> -#ifdef CONFIG_SCHED_DEBUG
> -# define SD_INIT_NAME(sd, type)		sd->name = #type
> -#else
> -# define SD_INIT_NAME(sd, type)		do { } while (0)
> -#endif
> -
> -#define SD_INIT_FUNC(type)						\
> -static noinline struct sched_domain *					\
> -sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
> -{									\
> -	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
> -	*sd = SD_##type##_INIT;						\
> -	SD_INIT_NAME(sd, type);						\
> -	sd->private = &tl->data;					\
> -	return sd;							\
> -}
> -
> -SD_INIT_FUNC(CPU)
> -#ifdef CONFIG_SCHED_SMT
> - SD_INIT_FUNC(SIBLING)
> -#endif
> -#ifdef CONFIG_SCHED_MC
> - SD_INIT_FUNC(MC)
> -#endif
> -#ifdef CONFIG_SCHED_BOOK
> - SD_INIT_FUNC(BOOK)
> -#endif
> -
>  static int default_relax_domain_level = -1;
>  int sched_domain_level_max;
> 
> @@ -5984,97 +5930,156 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
>  		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
>  }
> 
> -#ifdef CONFIG_SCHED_SMT
> -static const struct cpumask *cpu_smt_mask(int cpu)
> -{
> -	return topology_thread_cpumask(cpu);
> -}
> -#endif
> -
> -/*
> - * Topology list, bottom-up.
> - */
> -static struct sched_domain_topology_level default_topology[] = {
> -#ifdef CONFIG_SCHED_SMT
> -	{ sd_init_SIBLING, cpu_smt_mask, },
> -#endif
> -#ifdef CONFIG_SCHED_MC
> -	{ sd_init_MC, cpu_coregroup_mask, },
> -#endif
> -#ifdef CONFIG_SCHED_BOOK
> -	{ sd_init_BOOK, cpu_book_mask, },
> -#endif
> -	{ sd_init_CPU, cpu_cpu_mask, },
> -	{ NULL, },
> -};
> -
> -static struct sched_domain_topology_level *sched_domain_topology = default_topology;
> -
> -#define for_each_sd_topology(tl)			\
> -	for (tl = sched_domain_topology; tl->init; tl++)
> -
>  #ifdef CONFIG_NUMA
> -
>  static int sched_domains_numa_levels;
>  static int *sched_domains_numa_distance;
>  static struct cpumask ***sched_domains_numa_masks;
>  static int sched_domains_curr_level;
> +#endif
> 
> -static inline int sd_local_flags(int level)
> -{
> -	if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
> -		return 0;
> -
> -	return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
> -}
> +/*
> + * SD_flags allowed in topology descriptions.
> + *
> + * SD_SHARE_CPUPOWER      - describes SMT topologies
> + * SD_SHARE_PKG_RESOURCES - describes shared caches
> + * SD_NUMA                - describes NUMA topologies
> + *
> + * Odd one out:
> + * SD_ASYM_PACKING        - describes SMT quirks
> + */
> +#define TOPOLOGY_SD_FLAGS		\
> +	(SD_SHARE_CPUPOWER |		\
> +	 SD_SHARE_PKG_RESOURCES |	\
> +	 SD_NUMA |			\
> +	 SD_ASYM_PACKING)
> 
>  static struct sched_domain *
> -sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
> +sd_init(struct sched_domain_topology_level *tl, int cpu)
>  {
>  	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
> -	int level = tl->numa_level;
> -	int sd_weight = cpumask_weight(
> -			sched_domains_numa_masks[level][cpu_to_node(cpu)]);
> +	int sd_weight, sd_flags = 0;
> +
> +#ifdef CONFIG_NUMA
> +	/*
> +	 * Ugly hack to pass state to sd_numa_mask()...
> +	 */
> +	sched_domains_curr_level = tl->numa_level;
> +#endif
> +
> +	sd_weight = cpumask_weight(tl->mask(cpu));
> +
> +	if (tl->sd_flags)
> +		sd_flags = (*tl->sd_flags)();
> +	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
> +			"wrong sd_flags in topology description\n"))
> +		sd_flags &= ~TOPOLOGY_SD_FLAGS;
> 
>  	*sd = (struct sched_domain){
>  		.min_interval		= sd_weight,
>  		.max_interval		= 2*sd_weight,
>  		.busy_factor		= 32,
>  		.imbalance_pct		= 125,
> -		.cache_nice_tries	= 2,
> -		.busy_idx		= 3,
> -		.idle_idx		= 2,
> +
> +		.cache_nice_tries	= 0,
> +		.busy_idx		= 0,
> +		.idle_idx		= 0,
>  		.newidle_idx		= 0,
>  		.wake_idx		= 0,
>  		.forkexec_idx		= 0,
> 
>  		.flags			= 1*SD_LOAD_BALANCE
>  					| 1*SD_BALANCE_NEWIDLE
> -					| 0*SD_BALANCE_EXEC
> -					| 0*SD_BALANCE_FORK
> +					| 1*SD_BALANCE_EXEC
> +					| 1*SD_BALANCE_FORK
>  					| 0*SD_BALANCE_WAKE
> -					| 0*SD_WAKE_AFFINE
> +					| 1*SD_WAKE_AFFINE
>  					| 0*SD_SHARE_CPUPOWER
>  					| 0*SD_SHARE_PKG_RESOURCES
> -					| 1*SD_SERIALIZE
> +					| 0*SD_SERIALIZE
>  					| 0*SD_PREFER_SIBLING
> -					| 1*SD_NUMA
> -					| sd_local_flags(level)
> +					| 0*SD_NUMA
> +					| sd_flags
>  					,
> +
>  		.last_balance		= jiffies,
>  		.balance_interval	= sd_weight,
> +		.smt_gain		= 0,
> +		.max_newidle_lb_cost	= 0,
> +		.next_decay_max_lb_cost	= jiffies,
> +#ifdef CONFIG_SCHED_DEBUG
> +		.name			= tl->name,
> +#endif
>  	};
> -	SD_INIT_NAME(sd, NUMA);
> -	sd->private = &tl->data;
> 
>  	/*
> -	 * Ugly hack to pass state to sd_numa_mask()...
> +	 * Convert topological properties into behaviour.
>  	 */
> -	sched_domains_curr_level = tl->numa_level;
> +
> +	if (sd->flags & SD_SHARE_CPUPOWER) {
> +		sd->imbalance_pct = 110;
> +		sd->smt_gain = 1178; /* ~15% */
> +		sd->flags |= arch_sd_sibling_asym_packing();
> +
> +	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
> +		sd->imbalance_pct = 117;
> +		sd->cache_nice_tries = 1;
> +		sd->busy_idx = 2;
> +
> +#ifdef CONFIG_NUMA
> +	} else if (sd->flags & SD_NUMA) {
> +		sd->cache_nice_tries = 2;
> +		sd->busy_idx = 3;
> +		sd->idle_idx = 2;
> +
> +		sd->flags |= SD_SERIALIZE;
> +		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
> +			sd->flags &= ~(SD_BALANCE_EXEC |
> +				       SD_BALANCE_FORK |
> +				       SD_WAKE_AFFINE);
> +		}
> +
> +#endif
> +	} else {
> +		sd->flags |= SD_PREFER_SIBLING;
> +		sd->cache_nice_tries = 1;
> +		sd->busy_idx = 2;
> +		sd->idle_idx = 1;
> +	}
> +
> +	sd->private = &tl->data;
> 
>  	return sd;
>  }
> 
> +/*
> + * Topology list, bottom-up.
> + */
> +static struct sched_domain_topology_level default_topology[] = {
> +#ifdef CONFIG_SCHED_SMT
> +	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
> +#endif
> +#ifdef CONFIG_SCHED_MC
> +	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
> +#endif
> +#ifdef CONFIG_SCHED_BOOK
> +	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
> +#endif
> +	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +	{ NULL, },
> +};
> +
> +struct sched_domain_topology_level *sched_domain_topology = default_topology;
> +
> +#define for_each_sd_topology(tl)			\
> +	for (tl = sched_domain_topology; tl->mask; tl++)
> +
> +void set_sched_topology(struct sched_domain_topology_level *tl)
> +{
> +	sched_domain_topology = tl;
> +}
> +
> +#ifdef CONFIG_NUMA
> +
>  static const struct cpumask *sd_numa_mask(int cpu)
>  {
>  	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
> @@ -6218,7 +6223,10 @@ static void sched_init_numa(void)
>  		}
>  	}
> 
> -	tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
> +	/* Compute default topology size */
> +	for (i = 0; sched_domain_topology[i].mask; i++);
> +
> +	tl = kzalloc((i + level) *
>  			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
>  	if (!tl)
>  		return;
> @@ -6226,18 +6234,19 @@ static void sched_init_numa(void)
>  	/*
>  	 * Copy the default topology bits..
>  	 */
> -	for (i = 0; default_topology[i].init; i++)
> -		tl[i] = default_topology[i];
> +	for (i = 0; sched_domain_topology[i].mask; i++)
> +		tl[i] = sched_domain_topology[i];
> 
>  	/*
>  	 * .. and append 'j' levels of NUMA goodness.
>  	 */
>  	for (j = 0; j < level; i++, j++) {
>  		tl[i] = (struct sched_domain_topology_level){
> -			.init = sd_numa_init,
>  			.mask = sd_numa_mask,
> +			.sd_flags = SD_NUMA,
>  			.flags = SDTL_OVERLAP,
>  			.numa_level = j,
> +			SD_INIT_NAME(NUMA)
>  		};
>  	}
> 
> @@ -6395,7 +6404,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
>  		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
>  		struct sched_domain *child, int cpu)
>  {
> -	struct sched_domain *sd = tl->init(tl, cpu);
> +	struct sched_domain *sd = sd_init(tl, cpu);
>  	if (!sd)
>  		return child;
> 
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Dietmar Eggemann March 19, 2014, 11:27 a.m. UTC | #2
On 18/03/14 17:56, Vincent Guittot wrote:
> 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 wants to add new level where a load balance
> make sense like BOOK or powergating level.
> 
> 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 relevant information for load balancing
> than its child.
> 
> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> ---
>  arch/ia64/include/asm/topology.h |  24 ----
>  arch/s390/include/asm/topology.h |   2 -
>  arch/tile/include/asm/topology.h |  33 ------
>  include/linux/sched.h            |  48 ++++++++
>  include/linux/topology.h         | 128 +++------------------
>  kernel/sched/core.c              | 235 ++++++++++++++++++++-------------------
>  6 files changed, 183 insertions(+), 287 deletions(-)
> 
> diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
> index 5cb55a1..3202aa7 100644
> --- a/arch/ia64/include/asm/topology.h
> +++ b/arch/ia64/include/asm/topology.h
> @@ -46,30 +46,6 @@
> 
>  void build_cpu_to_node_map(void);
> 
> -#define SD_CPU_INIT (struct sched_domain) {            \
> -       .parent                 = NULL,                 \
> -       .child                  = NULL,                 \
> -       .groups                 = NULL,                 \
> -       .min_interval           = 1,                    \
> -       .max_interval           = 4,                    \
> -       .busy_factor            = 64,                   \
> -       .imbalance_pct          = 125,                  \
> -       .cache_nice_tries       = 2,                    \
> -       .busy_idx               = 2,                    \
> -       .idle_idx               = 1,                    \
> -       .newidle_idx            = 0,                    \
> -       .wake_idx               = 0,                    \
> -       .forkexec_idx           = 0,                    \
> -       .flags                  = SD_LOAD_BALANCE       \
> -                               | SD_BALANCE_NEWIDLE    \
> -                               | SD_BALANCE_EXEC       \
> -                               | SD_BALANCE_FORK       \
> -                               | SD_WAKE_AFFINE,       \
> -       .last_balance           = jiffies,              \
> -       .balance_interval       = 1,                    \
> -       .nr_balance_failed      = 0,                    \
> -}
> -
>  #endif /* CONFIG_NUMA */
> 
>  #ifdef CONFIG_SMP
> diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
> index 05425b1..07763bd 100644
> --- a/arch/s390/include/asm/topology.h
> +++ b/arch/s390/include/asm/topology.h
> @@ -64,8 +64,6 @@ 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/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
> index d15c0d8..9383118 100644
> --- a/arch/tile/include/asm/topology.h
> +++ b/arch/tile/include/asm/topology.h
> @@ -44,39 +44,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
>  /* For now, use numa node -1 for global allocation. */
>  #define pcibus_to_node(bus)            ((void)(bus), -1)
> 
> -/*
> - * TILE architecture has many cores integrated in one processor, so we need
> - * setup bigger balance_interval for both CPU/NODE scheduling domains to
> - * reduce process scheduling costs.
> - */
> -
> -/* sched_domains SD_CPU_INIT for TILE architecture */
> -#define SD_CPU_INIT (struct sched_domain) {                            \
> -       .min_interval           = 4,                                    \
> -       .max_interval           = 128,                                  \
> -       .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                     \
> -                               | 0*SD_WAKE_AFFINE                      \
> -                               | 0*SD_SHARE_CPUPOWER                   \
> -                               | 0*SD_SHARE_PKG_RESOURCES              \
> -                               | 0*SD_SERIALIZE                        \
> -                               ,                                       \
> -       .last_balance           = jiffies,                              \
> -       .balance_interval       = 32,                                   \
> -}
> -
>  /* By definition, we create nodes based on online memory. */
>  #define node_has_online_mem(nid) 1
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 825ed83..4db592a 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -870,6 +870,20 @@ enum cpu_idle_type {
> 
>  extern int __weak arch_sd_sibiling_asym_packing(void);
> 
> +#ifdef CONFIG_SCHED_SMT
> +static inline const int cpu_smt_flags(void)
> +{
> +       return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
> +}
> +#endif
> +
> +#ifdef CONFIG_SCHED_MC
> +static inline const int cpu_core_flags(void)
> +{
> +       return SD_SHARE_PKG_RESOURCES;
> +}
> +#endif
> +
>  struct sched_domain_attr {
>         int relax_domain_level;
>  };
> @@ -976,6 +990,38 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
> 
>  bool cpus_share_cache(int this_cpu, int that_cpu);
> 
> +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
> +typedef const int (*sched_domain_flags_f)(void);
> +
> +#define SDTL_OVERLAP   0x01
> +
> +struct sd_data {
> +       struct sched_domain **__percpu sd;
> +       struct sched_group **__percpu sg;
> +       struct sched_group_power **__percpu sgp;
> +};
> +
> +struct sched_domain_topology_level {
> +       sched_domain_mask_f mask;
> +       sched_domain_flags_f sd_flags;
> +       int                 flags;
> +       int                 numa_level;
> +       struct sd_data      data;
> +#ifdef CONFIG_SCHED_DEBUG
> +       char                *name;
> +#endif
> +};
> +
> +extern struct sched_domain_topology_level *sched_domain_topology;
> +
> +extern void set_sched_topology(struct sched_domain_topology_level *tl);
> +
> +#ifdef CONFIG_SCHED_DEBUG
> +# define SD_INIT_NAME(type)            .name = #type
> +#else
> +# define SD_INIT_NAME(type)
> +#endif
> +
>  #else /* CONFIG_SMP */
> 
>  struct sched_domain_attr;
> @@ -991,6 +1037,8 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
>         return true;
>  }
> 
> +static inline void set_sched_topology(struct sched_domain_topology_level *tl) { }
> +
>  #endif /* !CONFIG_SMP */
> 
> 
> diff --git a/include/linux/topology.h b/include/linux/topology.h
> index 12ae6ce..3a9db05 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 */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index ae365aa..3397bcb 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5603,17 +5603,6 @@ static int __init isolated_cpu_setup(char *str)
> 
>  __setup("isolcpus=", isolated_cpu_setup);
> 
> -static const struct cpumask *cpu_cpu_mask(int cpu)
> -{
> -       return cpumask_of_node(cpu_to_node(cpu));
> -}
> -
> -struct sd_data {
> -       struct sched_domain **__percpu sd;
> -       struct sched_group **__percpu sg;
> -       struct sched_group_power **__percpu sgp;
> -};
> -
>  struct s_data {
>         struct sched_domain ** __percpu sd;
>         struct root_domain      *rd;
> @@ -5626,21 +5615,6 @@ enum s_alloc {
>         sa_none,
>  };
> 
> -struct sched_domain_topology_level;
> -
> -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
> -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
> -
> -#define SDTL_OVERLAP   0x01
> -
> -struct sched_domain_topology_level {
> -       sched_domain_init_f init;
> -       sched_domain_mask_f mask;
> -       int                 flags;
> -       int                 numa_level;
> -       struct sd_data      data;
> -};
> -
>  /*
>   * Build an iteration mask that can exclude certain CPUs from the upwards
>   * domain traversal.
> @@ -5869,34 +5843,6 @@ int __weak arch_sd_sibling_asym_packing(void)
>   * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
>   */
> 
> -#ifdef CONFIG_SCHED_DEBUG
> -# define SD_INIT_NAME(sd, type)                sd->name = #type
> -#else
> -# define SD_INIT_NAME(sd, type)                do { } while (0)
> -#endif
> -
> -#define SD_INIT_FUNC(type)                                             \
> -static noinline struct sched_domain *                                  \
> -sd_init_##type(struct sched_domain_topology_level *tl, int cpu)        \
> -{                                                                      \
> -       struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);       \
> -       *sd = SD_##type##_INIT;                                         \
> -       SD_INIT_NAME(sd, type);                                         \
> -       sd->private = &tl->data;                                        \
> -       return sd;                                                      \
> -}
> -
> -SD_INIT_FUNC(CPU)
> -#ifdef CONFIG_SCHED_SMT
> - SD_INIT_FUNC(SIBLING)
> -#endif
> -#ifdef CONFIG_SCHED_MC
> - SD_INIT_FUNC(MC)
> -#endif
> -#ifdef CONFIG_SCHED_BOOK
> - SD_INIT_FUNC(BOOK)
> -#endif
> -
>  static int default_relax_domain_level = -1;
>  int sched_domain_level_max;
> 
> @@ -5984,97 +5930,156 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
>                 *per_cpu_ptr(sdd->sgp, cpu) = NULL;
>  }
> 
> -#ifdef CONFIG_SCHED_SMT
> -static const struct cpumask *cpu_smt_mask(int cpu)
> -{
> -       return topology_thread_cpumask(cpu);
> -}
> -#endif
> -
> -/*
> - * Topology list, bottom-up.
> - */
> -static struct sched_domain_topology_level default_topology[] = {
> -#ifdef CONFIG_SCHED_SMT
> -       { sd_init_SIBLING, cpu_smt_mask, },
> -#endif
> -#ifdef CONFIG_SCHED_MC
> -       { sd_init_MC, cpu_coregroup_mask, },
> -#endif
> -#ifdef CONFIG_SCHED_BOOK
> -       { sd_init_BOOK, cpu_book_mask, },
> -#endif
> -       { sd_init_CPU, cpu_cpu_mask, },
> -       { NULL, },
> -};
> -
> -static struct sched_domain_topology_level *sched_domain_topology = default_topology;
> -
> -#define for_each_sd_topology(tl)                       \
> -       for (tl = sched_domain_topology; tl->init; tl++)
> -
>  #ifdef CONFIG_NUMA
> -
>  static int sched_domains_numa_levels;
>  static int *sched_domains_numa_distance;
>  static struct cpumask ***sched_domains_numa_masks;
>  static int sched_domains_curr_level;
> +#endif
> 
> -static inline int sd_local_flags(int level)
> -{
> -       if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
> -               return 0;
> -
> -       return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
> -}
> +/*
> + * SD_flags allowed in topology descriptions.
> + *
> + * SD_SHARE_CPUPOWER      - describes SMT topologies
> + * SD_SHARE_PKG_RESOURCES - describes shared caches
> + * SD_NUMA                - describes NUMA topologies
> + *
> + * Odd one out:
> + * SD_ASYM_PACKING        - describes SMT quirks
> + */
> +#define TOPOLOGY_SD_FLAGS              \
> +       (SD_SHARE_CPUPOWER |            \
> +        SD_SHARE_PKG_RESOURCES |       \
> +        SD_NUMA |                      \
> +        SD_ASYM_PACKING)
> 
>  static struct sched_domain *
> -sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
> +sd_init(struct sched_domain_topology_level *tl, int cpu)
>  {
>         struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
> -       int level = tl->numa_level;
> -       int sd_weight = cpumask_weight(
> -                       sched_domains_numa_masks[level][cpu_to_node(cpu)]);
> +       int sd_weight, sd_flags = 0;
> +
> +#ifdef CONFIG_NUMA
> +       /*
> +        * Ugly hack to pass state to sd_numa_mask()...
> +        */
> +       sched_domains_curr_level = tl->numa_level;
> +#endif
> +
> +       sd_weight = cpumask_weight(tl->mask(cpu));
> +
> +       if (tl->sd_flags)
> +               sd_flags = (*tl->sd_flags)();
> +       if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
> +                       "wrong sd_flags in topology description\n"))
> +               sd_flags &= ~TOPOLOGY_SD_FLAGS;
> 
>         *sd = (struct sched_domain){
>                 .min_interval           = sd_weight,
>                 .max_interval           = 2*sd_weight,
>                 .busy_factor            = 32,
>                 .imbalance_pct          = 125,
> -               .cache_nice_tries       = 2,
> -               .busy_idx               = 3,
> -               .idle_idx               = 2,
> +
> +               .cache_nice_tries       = 0,
> +               .busy_idx               = 0,
> +               .idle_idx               = 0,
>                 .newidle_idx            = 0,
>                 .wake_idx               = 0,
>                 .forkexec_idx           = 0,
> 
>                 .flags                  = 1*SD_LOAD_BALANCE
>                                         | 1*SD_BALANCE_NEWIDLE
> -                                       | 0*SD_BALANCE_EXEC
> -                                       | 0*SD_BALANCE_FORK
> +                                       | 1*SD_BALANCE_EXEC
> +                                       | 1*SD_BALANCE_FORK
>                                         | 0*SD_BALANCE_WAKE
> -                                       | 0*SD_WAKE_AFFINE
> +                                       | 1*SD_WAKE_AFFINE
>                                         | 0*SD_SHARE_CPUPOWER
>                                         | 0*SD_SHARE_PKG_RESOURCES
> -                                       | 1*SD_SERIALIZE
> +                                       | 0*SD_SERIALIZE
>                                         | 0*SD_PREFER_SIBLING
> -                                       | 1*SD_NUMA
> -                                       | sd_local_flags(level)
> +                                       | 0*SD_NUMA
> +                                       | sd_flags
>                                         ,
> +
>                 .last_balance           = jiffies,
>                 .balance_interval       = sd_weight,
> +               .smt_gain               = 0,
> +               .max_newidle_lb_cost    = 0,
> +               .next_decay_max_lb_cost = jiffies,
> +#ifdef CONFIG_SCHED_DEBUG
> +               .name                   = tl->name,
> +#endif
>         };
> -       SD_INIT_NAME(sd, NUMA);
> -       sd->private = &tl->data;
> 
>         /*
> -        * Ugly hack to pass state to sd_numa_mask()...
> +        * Convert topological properties into behaviour.
>          */
> -       sched_domains_curr_level = tl->numa_level;
> +
> +       if (sd->flags & SD_SHARE_CPUPOWER) {
> +               sd->imbalance_pct = 110;
> +               sd->smt_gain = 1178; /* ~15% */
> +               sd->flags |= arch_sd_sibling_asym_packing();
> +
> +       } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
> +               sd->imbalance_pct = 117;
> +               sd->cache_nice_tries = 1;
> +               sd->busy_idx = 2;
> +
> +#ifdef CONFIG_NUMA
> +       } else if (sd->flags & SD_NUMA) {
> +               sd->cache_nice_tries = 2;
> +               sd->busy_idx = 3;
> +               sd->idle_idx = 2;
> +
> +               sd->flags |= SD_SERIALIZE;
> +               if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
> +                       sd->flags &= ~(SD_BALANCE_EXEC |
> +                                      SD_BALANCE_FORK |
> +                                      SD_WAKE_AFFINE);
> +               }
> +
> +#endif
> +       } else {
> +               sd->flags |= SD_PREFER_SIBLING;
> +               sd->cache_nice_tries = 1;
> +               sd->busy_idx = 2;
> +               sd->idle_idx = 1;
> +       }

This 'if ... else statement' is still a weak point from the perspective
of making the code robust:

On TC2 w/ the following change in cpu_corepower_mask()

 const struct cpumask *cpu_corepower_mask(int cpu)
 {
-       return &cpu_topology[cpu].thread_sibling;
+       return cpu_topology[cpu].socket_id ?
&cpu_topology[cpu].thread_sibling :
+                       &cpu_topology[cpu].core_sibling;
 }

I get a sane set-up:

root@linaro-developer:~# cat /proc/sys/kernel/sched_domain/cpu*/domain*/name
GMC
DIE
GMC
DIE
MC
DIE
MC
DIE
MC
DIE
root@linaro-developer:~# cat
/proc/sys/kernel/sched_domain/cpu*/domain*/flags
815
4143
815
4143
559
4143
559
4143
559
4143

w/ 815 (0x32F : SD_LOAD_BALANCE SD_BALANCE_NEWIDLE SD_BALANCE_EXEC
SD_BALANCE_FORK SD_WAKE_AFFINE *SD_SHARE_POWERDOMAIN*
SD_SHARE_PKG_RESOURCES)

w/ 559 (0x22F : SD_LOAD_BALANCE SD_BALANCE_NEWIDLE SD_BALANCE_EXEC
SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_PKG_RESOURCES)

But when I introduce the following error into the arch specific
cpu_corepower_flags() function

 static inline const int cpu_corepower_flags(void)
 {
-       return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
+       return SD_SHARE_POWERDOMAIN;
 }

the GMC related sd's for CPU0,1 are initialized as DIE in sd_init()
resulting in this wrong set-up w/o any warning/error message:

root@linaro-developer:~# cat /proc/sys/kernel/sched_domain/cpu*/domain*/name
GMC
DIE
GMC
DIE
MC
DIE
MC
DIE
MC
DIE
root@linaro-developer:~# cat
/proc/sys/kernel/sched_domain/cpu*/domain*/flags
4399
4143
4399
4143
559
4143
559
4143
559
4143

w/ 4399 (0x112f : SD_LOAD_BALANCE SD_BALANCE_NEWIDLE SD_BALANCE_EXEC
SD_BALANCE_FORK SD_WAKE_AFFINE *SD_SHARE_POWERDOMAIN* SD_PREFER_SIBLING

Is there a way to check that MC and GMC have to have
SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?

-- Dietmar

> +
> +       sd->private = &tl->data;
> 
>         return sd;
>  }
> 
> +/*
> + * Topology list, bottom-up.
> + */
> +static struct sched_domain_topology_level default_topology[] = {
> +#ifdef CONFIG_SCHED_SMT
> +       { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
> +#endif
> +#ifdef CONFIG_SCHED_MC
> +       { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
> +#endif
> +#ifdef CONFIG_SCHED_BOOK
> +       { cpu_book_mask, SD_INIT_NAME(BOOK) },
> +#endif
> +       { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +       { NULL, },
> +};
> +
> +struct sched_domain_topology_level *sched_domain_topology = default_topology;
> +
> +#define for_each_sd_topology(tl)                       \
> +       for (tl = sched_domain_topology; tl->mask; tl++)
> +
> +void set_sched_topology(struct sched_domain_topology_level *tl)
> +{
> +       sched_domain_topology = tl;
> +}
> +
> +#ifdef CONFIG_NUMA
> +
>  static const struct cpumask *sd_numa_mask(int cpu)
>  {
>         return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
> @@ -6218,7 +6223,10 @@ static void sched_init_numa(void)
>                 }
>         }
> 
> -       tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
> +       /* Compute default topology size */
> +       for (i = 0; sched_domain_topology[i].mask; i++);
> +
> +       tl = kzalloc((i + level) *
>                         sizeof(struct sched_domain_topology_level), GFP_KERNEL);
>         if (!tl)
>                 return;
> @@ -6226,18 +6234,19 @@ static void sched_init_numa(void)
>         /*
>          * Copy the default topology bits..
>          */
> -       for (i = 0; default_topology[i].init; i++)
> -               tl[i] = default_topology[i];
> +       for (i = 0; sched_domain_topology[i].mask; i++)
> +               tl[i] = sched_domain_topology[i];
> 
>         /*
>          * .. and append 'j' levels of NUMA goodness.
>          */
>         for (j = 0; j < level; i++, j++) {
>                 tl[i] = (struct sched_domain_topology_level){
> -                       .init = sd_numa_init,
>                         .mask = sd_numa_mask,
> +                       .sd_flags = SD_NUMA,
>                         .flags = SDTL_OVERLAP,
>                         .numa_level = j,
> +                       SD_INIT_NAME(NUMA)
>                 };
>         }
> 
> @@ -6395,7 +6404,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
>                 const struct cpumask *cpu_map, struct sched_domain_attr *attr,
>                 struct sched_domain *child, int cpu)
>  {
> -       struct sched_domain *sd = tl->init(tl, cpu);
> +       struct sched_domain *sd = sd_init(tl, cpu);
>         if (!sd)
>                 return child;
> 
> --
> 1.9.0
> 
> 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Peter Zijlstra March 19, 2014, 12:41 p.m. UTC | #3
The keyboard deity gave us delete, please apply graciously when replying
to large emails.

On Wed, Mar 19, 2014 at 11:27:12AM +0000, Dietmar Eggemann wrote:
> On 18/03/14 17:56, Vincent Guittot wrote:
> > +       if (sd->flags & SD_SHARE_CPUPOWER) {
> > +               sd->imbalance_pct = 110;
> > +               sd->smt_gain = 1178; /* ~15% */
> > +               sd->flags |= arch_sd_sibling_asym_packing();
> > +
> > +       } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
> > +               sd->imbalance_pct = 117;
> > +               sd->cache_nice_tries = 1;
> > +               sd->busy_idx = 2;
> > +
> > +#ifdef CONFIG_NUMA
> > +       } else if (sd->flags & SD_NUMA) {
> > +               sd->cache_nice_tries = 2;
> > +               sd->busy_idx = 3;
> > +               sd->idle_idx = 2;
> > +
> > +               sd->flags |= SD_SERIALIZE;
> > +               if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
> > +                       sd->flags &= ~(SD_BALANCE_EXEC |
> > +                                      SD_BALANCE_FORK |
> > +                                      SD_WAKE_AFFINE);
> > +               }
> > +
> > +#endif
> > +       } else {
> > +               sd->flags |= SD_PREFER_SIBLING;
> > +               sd->cache_nice_tries = 1;
> > +               sd->busy_idx = 2;
> > +               sd->idle_idx = 1;
> > +       }
> 
> This 'if ... else statement' is still a weak point from the perspective
> of making the code robust:

<snip>

> Is there a way to check that MC and GMC have to have
> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?

So from the core codes perspective those names mean less than nothing.
Its just a string to carry along for us meat-bags. The string isn't even
there when !SCHED_DEBUG.

So from this codes POV you told it it had a domain without PKGSHARE,
that's fine.

That said; yeah the thing isn't the prettiest piece of code. But it has
the big advantage of being the one place where we convert topology into
behaviour.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Vincent Guittot March 19, 2014, 1:33 p.m. UTC | #4
On 19 March 2014 13:41, Peter Zijlstra <peterz@infradead.org> wrote:
>
> The keyboard deity gave us delete, please apply graciously when replying
> to large emails.
>
> On Wed, Mar 19, 2014 at 11:27:12AM +0000, Dietmar Eggemann wrote:
>> On 18/03/14 17:56, Vincent Guittot wrote:
>> > +       if (sd->flags & SD_SHARE_CPUPOWER) {
>> > +               sd->imbalance_pct = 110;
>> > +               sd->smt_gain = 1178; /* ~15% */
>> > +               sd->flags |= arch_sd_sibling_asym_packing();
>> > +
>> > +       } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
>> > +               sd->imbalance_pct = 117;
>> > +               sd->cache_nice_tries = 1;
>> > +               sd->busy_idx = 2;
>> > +
>> > +#ifdef CONFIG_NUMA
>> > +       } else if (sd->flags & SD_NUMA) {
>> > +               sd->cache_nice_tries = 2;
>> > +               sd->busy_idx = 3;
>> > +               sd->idle_idx = 2;
>> > +
>> > +               sd->flags |= SD_SERIALIZE;
>> > +               if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
>> > +                       sd->flags &= ~(SD_BALANCE_EXEC |
>> > +                                      SD_BALANCE_FORK |
>> > +                                      SD_WAKE_AFFINE);
>> > +               }
>> > +
>> > +#endif
>> > +       } else {
>> > +               sd->flags |= SD_PREFER_SIBLING;
>> > +               sd->cache_nice_tries = 1;
>> > +               sd->busy_idx = 2;
>> > +               sd->idle_idx = 1;
>> > +       }
>>
>> This 'if ... else statement' is still a weak point from the perspective
>> of making the code robust:
>
> <snip>
>
>> Is there a way to check that MC and GMC have to have
>> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?
>
> So from the core codes perspective those names mean less than nothing.
> Its just a string to carry along for us meat-bags. The string isn't even
> there when !SCHED_DEBUG.
>
> So from this codes POV you told it it had a domain without PKGSHARE,
> that's fine.
>
> That said; yeah the thing isn't the prettiest piece of code. But it has
> the big advantage of being the one place where we convert topology into
> behaviour.

We might add a check of the child in sd_init to ensure that the child
has at least some properties of the current level.
I mean that if a level has got the SD_SHARE_PKG_RESOURCES flag, its
child must also have it. The same for SD_SHARE_CPUPOWER and
SD_ASYM_PACKING.

so we can add something like the below in sd_init

child_flags = SD_SHARE_PKG_RESOURCES | SD_SHARE_CPUPOWER | SD_ASYM_PACKING
flags = sd->flags & child_flags
if (sd->child)
   child_flags &= sd->child->flags
child_flags &= flags
if (flags != child_flags)
    pr_info("The topology description looks strange \n");

Vincent
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Dietmar Eggemann March 19, 2014, 1:46 p.m. UTC | #5
On 19/03/14 12:41, Peter Zijlstra wrote:
> 
> The keyboard deity gave us delete, please apply graciously when replying
> to large emails.

Sorry about that, will do next time.

> 
> On Wed, Mar 19, 2014 at 11:27:12AM +0000, Dietmar Eggemann wrote:
>> On 18/03/14 17:56, Vincent Guittot wrote:
>>> +       if (sd->flags & SD_SHARE_CPUPOWER) {
>>> +               sd->imbalance_pct = 110;
>>> +               sd->smt_gain = 1178; /* ~15% */
>>> +               sd->flags |= arch_sd_sibling_asym_packing();
>>> +
>>> +       } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
>>> +               sd->imbalance_pct = 117;
>>> +               sd->cache_nice_tries = 1;
>>> +               sd->busy_idx = 2;
>>> +
>>> +#ifdef CONFIG_NUMA
>>> +       } else if (sd->flags & SD_NUMA) {
>>> +               sd->cache_nice_tries = 2;
>>> +               sd->busy_idx = 3;
>>> +               sd->idle_idx = 2;
>>> +
>>> +               sd->flags |= SD_SERIALIZE;
>>> +               if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
>>> +                       sd->flags &= ~(SD_BALANCE_EXEC |
>>> +                                      SD_BALANCE_FORK |
>>> +                                      SD_WAKE_AFFINE);
>>> +               }
>>> +
>>> +#endif
>>> +       } else {
>>> +               sd->flags |= SD_PREFER_SIBLING;
>>> +               sd->cache_nice_tries = 1;
>>> +               sd->busy_idx = 2;
>>> +               sd->idle_idx = 1;
>>> +       }
>>
>> This 'if ... else statement' is still a weak point from the perspective
>> of making the code robust:
> 
> <snip>
> 
>> Is there a way to check that MC and GMC have to have
>> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?
> 
> So from the core codes perspective those names mean less than nothing.
> Its just a string to carry along for us meat-bags. The string isn't even
> there when !SCHED_DEBUG.
> 
> So from this codes POV you told it it had a domain without PKGSHARE,
> that's fine.

I see your point. So what we want to avoid is to enable archs to create
different (per-cpu) set-ups inside a domain (as a specific set of cpu's
from a viewpoint of a cpu) but misconfiguration of the whole domain is a
different story. Got it!

> 
> That said; yeah the thing isn't the prettiest piece of code. But it has
> the big advantage of being the one place where we convert topology into
> behaviour.
> 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Dietmar Eggemann March 19, 2014, 3:22 p.m. UTC | #6
On 19/03/14 13:33, Vincent Guittot wrote:
[...]

>>> Is there a way to check that MC and GMC have to have
>>> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?
>>
>> So from the core codes perspective those names mean less than nothing.
>> Its just a string to carry along for us meat-bags. The string isn't even
>> there when !SCHED_DEBUG.
>>
>> So from this codes POV you told it it had a domain without PKGSHARE,
>> that's fine.
>>
>> That said; yeah the thing isn't the prettiest piece of code. But it has
>> the big advantage of being the one place where we convert topology into
>> behaviour.
> 
> We might add a check of the child in sd_init to ensure that the child
> has at least some properties of the current level.
> I mean that if a level has got the SD_SHARE_PKG_RESOURCES flag, its
> child must also have it. The same for SD_SHARE_CPUPOWER and
> SD_ASYM_PACKING.
> 
> so we can add something like the below in sd_init
> 
> child_flags = SD_SHARE_PKG_RESOURCES | SD_SHARE_CPUPOWER | SD_ASYM_PACKING
> flags = sd->flags & child_flags
> if (sd->child)
>    child_flags &= sd->child->flags
> child_flags &= flags
> if (flags != child_flags)
>     pr_info("The topology description looks strange \n");

I tried it with my faulty set-up on TC2 and I get the info message for
the GMC level for all CPU's in sd_init.

I had to pass an 'struct sched_domain *child' pointer into sd_init()
from build_sched_domain() because inside sd_init() sd->child is always NULL.

So one of the requirements of this approach is that a child level like
GMC (which could potentially replace its parent level or otherwise is
destroyed itself) has to specify all flags of its parent level (MC)?

What about SD_NUMA in child_flags? SD_ASYM_PACKING is also a little bit
different than SD_SHARE_PKG_RESOURCES or SD_SHARE_CPUPOWER because it's
not used in the if ... else statement.

But I'm afraid this only works for this specific case of the MC/GMC
layer and is not scalable. If sd->child is a level for which you don't
want to potentially destroy itself or its parent, then you would get
false alarms. IMHO, sd_init() has no information for which pair of
adjacent levels it should apply this check and for which not. Do I miss
something here?

-- Dietmar

> 
> Vincent
> 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Vincent Guittot March 19, 2014, 4:14 p.m. UTC | #7
On 19 March 2014 16:22, Dietmar Eggemann <dietmar.eggemann@arm.com> wrote:
> On 19/03/14 13:33, Vincent Guittot wrote:
> [...]
>
>>>> Is there a way to check that MC and GMC have to have
>>>> SD_SHARE_PKG_RESOURCES set so that this can't happen unnoticed?
>>>
>>> So from the core codes perspective those names mean less than nothing.
>>> Its just a string to carry along for us meat-bags. The string isn't even
>>> there when !SCHED_DEBUG.
>>>
>>> So from this codes POV you told it it had a domain without PKGSHARE,
>>> that's fine.
>>>
>>> That said; yeah the thing isn't the prettiest piece of code. But it has
>>> the big advantage of being the one place where we convert topology into
>>> behaviour.
>>
>> We might add a check of the child in sd_init to ensure that the child
>> has at least some properties of the current level.
>> I mean that if a level has got the SD_SHARE_PKG_RESOURCES flag, its
>> child must also have it. The same for SD_SHARE_CPUPOWER and
>> SD_ASYM_PACKING.
>>
>> so we can add something like the below in sd_init
>>
>> child_flags = SD_SHARE_PKG_RESOURCES | SD_SHARE_CPUPOWER | SD_ASYM_PACKING
>> flags = sd->flags & child_flags
>> if (sd->child)
>>    child_flags &= sd->child->flags
>> child_flags &= flags
>> if (flags != child_flags)
>>     pr_info("The topology description looks strange \n");
>
> I tried it with my faulty set-up on TC2 and I get the info message for
> the GMC level for all CPU's in sd_init.
>
> I had to pass an 'struct sched_domain *child' pointer into sd_init()
> from build_sched_domain() because inside sd_init() sd->child is always NULL.

ah yes... the child is set after the call to sd_init so we don't have
access to the child

>
> So one of the requirements of this approach is that a child level like
> GMC (which could potentially replace its parent level or otherwise is
> destroyed itself) has to specify all flags of its parent level (MC)?

yes among the 3 flags that i mention because we have simple
parent/child relation for this 3 flags

>
> What about SD_NUMA in child_flags? SD_ASYM_PACKING is also a little bit

SD_NUMA doesn't follow the same rule

> different than SD_SHARE_PKG_RESOURCES or SD_SHARE_CPUPOWER because it's
> not used in the if ... else statement.

It's not a matter of being in a if else statement but more a topology
dependency.

>
> But I'm afraid this only works for this specific case of the MC/GMC

This also works if a level with SD_SHARE_CPUPOWER flag is declared in
the table after a level without the flag which doesn't make sense
AFAIK.

> layer and is not scalable. If sd->child is a level for which you don't
> want to potentially destroy itself or its parent, then you would get
> false alarms. IMHO, sd_init() has no information for which pair of
> adjacent levels it should apply this check and for which not. Do I miss
> something here?

This check could apply on all level.

Vincent

>
> -- Dietmar
>
>>
>> Vincent
>>
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
diff mbox

Patch

diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 5cb55a1..3202aa7 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -46,30 +46,6 @@ 
 
 void build_cpu_to_node_map(void);
 
-#define SD_CPU_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 1,			\
-	.max_interval		= 4,			\
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 2,			\
-	.idle_idx		= 1,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_WAKE_AFFINE,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 05425b1..07763bd 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -64,8 +64,6 @@  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/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index d15c0d8..9383118 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -44,39 +44,6 @@  static inline const struct cpumask *cpumask_of_node(int node)
 /* For now, use numa node -1 for global allocation. */
 #define pcibus_to_node(bus)		((void)(bus), -1)
 
-/*
- * TILE architecture has many cores integrated in one processor, so we need
- * setup bigger balance_interval for both CPU/NODE scheduling domains to
- * reduce process scheduling costs.
- */
-
-/* sched_domains SD_CPU_INIT for TILE architecture */
-#define SD_CPU_INIT (struct sched_domain) {				\
-	.min_interval		= 4,					\
-	.max_interval		= 128,					\
-	.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			\
-				| 0*SD_WAKE_AFFINE			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 32,					\
-}
-
 /* By definition, we create nodes based on online memory. */
 #define node_has_online_mem(nid) 1
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 825ed83..4db592a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -870,6 +870,20 @@  enum cpu_idle_type {
 
 extern int __weak arch_sd_sibiling_asym_packing(void);
 
+#ifdef CONFIG_SCHED_SMT
+static inline const int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static inline const int cpu_core_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -976,6 +990,38 @@  void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef const int (*sched_domain_flags_f)(void);
+
+#define SDTL_OVERLAP	0x01
+
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_group **__percpu sg;
+	struct sched_group_power **__percpu sgp;
+};
+
+struct sched_domain_topology_level {
+	sched_domain_mask_f mask;
+	sched_domain_flags_f sd_flags;
+	int		    flags;
+	int		    numa_level;
+	struct sd_data      data;
+#ifdef CONFIG_SCHED_DEBUG
+	char                *name;
+#endif
+};
+
+extern struct sched_domain_topology_level *sched_domain_topology;
+
+extern void set_sched_topology(struct sched_domain_topology_level *tl);
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(type)		.name = #type
+#else
+# define SD_INIT_NAME(type)
+#endif
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -991,6 +1037,8 @@  static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline void set_sched_topology(struct sched_domain_topology_level *tl) { }
+
 #endif	/* !CONFIG_SMP */
 
 
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 12ae6ce..3a9db05 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 */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ae365aa..3397bcb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5603,17 +5603,6 @@  static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-static const struct cpumask *cpu_cpu_mask(int cpu)
-{
-	return cpumask_of_node(cpu_to_node(cpu));
-}
-
-struct sd_data {
-	struct sched_domain **__percpu sd;
-	struct sched_group **__percpu sg;
-	struct sched_group_power **__percpu sgp;
-};
-
 struct s_data {
 	struct sched_domain ** __percpu sd;
 	struct root_domain	*rd;
@@ -5626,21 +5615,6 @@  enum s_alloc {
 	sa_none,
 };
 
-struct sched_domain_topology_level;
-
-typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
-typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-
-#define SDTL_OVERLAP	0x01
-
-struct sched_domain_topology_level {
-	sched_domain_init_f init;
-	sched_domain_mask_f mask;
-	int		    flags;
-	int		    numa_level;
-	struct sd_data      data;
-};
-
 /*
  * Build an iteration mask that can exclude certain CPUs from the upwards
  * domain traversal.
@@ -5869,34 +5843,6 @@  int __weak arch_sd_sibling_asym_packing(void)
  * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
  */
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SD_INIT_NAME(sd, type)		sd->name = #type
-#else
-# define SD_INIT_NAME(sd, type)		do { } while (0)
-#endif
-
-#define SD_INIT_FUNC(type)						\
-static noinline struct sched_domain *					\
-sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
-{									\
-	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
-	*sd = SD_##type##_INIT;						\
-	SD_INIT_NAME(sd, type);						\
-	sd->private = &tl->data;					\
-	return sd;							\
-}
-
-SD_INIT_FUNC(CPU)
-#ifdef CONFIG_SCHED_SMT
- SD_INIT_FUNC(SIBLING)
-#endif
-#ifdef CONFIG_SCHED_MC
- SD_INIT_FUNC(MC)
-#endif
-#ifdef CONFIG_SCHED_BOOK
- SD_INIT_FUNC(BOOK)
-#endif
-
 static int default_relax_domain_level = -1;
 int sched_domain_level_max;
 
@@ -5984,97 +5930,156 @@  static void claim_allocations(int cpu, struct sched_domain *sd)
 		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
 }
 
-#ifdef CONFIG_SCHED_SMT
-static const struct cpumask *cpu_smt_mask(int cpu)
-{
-	return topology_thread_cpumask(cpu);
-}
-#endif
-
-/*
- * Topology list, bottom-up.
- */
-static struct sched_domain_topology_level default_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ sd_init_SIBLING, cpu_smt_mask, },
-#endif
-#ifdef CONFIG_SCHED_MC
-	{ sd_init_MC, cpu_coregroup_mask, },
-#endif
-#ifdef CONFIG_SCHED_BOOK
-	{ sd_init_BOOK, cpu_book_mask, },
-#endif
-	{ sd_init_CPU, cpu_cpu_mask, },
-	{ NULL, },
-};
-
-static struct sched_domain_topology_level *sched_domain_topology = default_topology;
-
-#define for_each_sd_topology(tl)			\
-	for (tl = sched_domain_topology; tl->init; tl++)
-
 #ifdef CONFIG_NUMA
-
 static int sched_domains_numa_levels;
 static int *sched_domains_numa_distance;
 static struct cpumask ***sched_domains_numa_masks;
 static int sched_domains_curr_level;
+#endif
 
-static inline int sd_local_flags(int level)
-{
-	if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
-		return 0;
-
-	return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
-}
+/*
+ * SD_flags allowed in topology descriptions.
+ *
+ * SD_SHARE_CPUPOWER      - describes SMT topologies
+ * SD_SHARE_PKG_RESOURCES - describes shared caches
+ * SD_NUMA                - describes NUMA topologies
+ *
+ * Odd one out:
+ * SD_ASYM_PACKING        - describes SMT quirks
+ */
+#define TOPOLOGY_SD_FLAGS		\
+	(SD_SHARE_CPUPOWER |		\
+	 SD_SHARE_PKG_RESOURCES |	\
+	 SD_NUMA |			\
+	 SD_ASYM_PACKING)
 
 static struct sched_domain *
-sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
+sd_init(struct sched_domain_topology_level *tl, int cpu)
 {
 	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
-	int level = tl->numa_level;
-	int sd_weight = cpumask_weight(
-			sched_domains_numa_masks[level][cpu_to_node(cpu)]);
+	int sd_weight, sd_flags = 0;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Ugly hack to pass state to sd_numa_mask()...
+	 */
+	sched_domains_curr_level = tl->numa_level;
+#endif
+
+	sd_weight = cpumask_weight(tl->mask(cpu));
+
+	if (tl->sd_flags)
+		sd_flags = (*tl->sd_flags)();
+	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
+			"wrong sd_flags in topology description\n"))
+		sd_flags &= ~TOPOLOGY_SD_FLAGS;
 
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
 		.busy_factor		= 32,
 		.imbalance_pct		= 125,
-		.cache_nice_tries	= 2,
-		.busy_idx		= 3,
-		.idle_idx		= 2,
+
+		.cache_nice_tries	= 0,
+		.busy_idx		= 0,
+		.idle_idx		= 0,
 		.newidle_idx		= 0,
 		.wake_idx		= 0,
 		.forkexec_idx		= 0,
 
 		.flags			= 1*SD_LOAD_BALANCE
 					| 1*SD_BALANCE_NEWIDLE
-					| 0*SD_BALANCE_EXEC
-					| 0*SD_BALANCE_FORK
+					| 1*SD_BALANCE_EXEC
+					| 1*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
-					| 0*SD_WAKE_AFFINE
+					| 1*SD_WAKE_AFFINE
 					| 0*SD_SHARE_CPUPOWER
 					| 0*SD_SHARE_PKG_RESOURCES
-					| 1*SD_SERIALIZE
+					| 0*SD_SERIALIZE
 					| 0*SD_PREFER_SIBLING
-					| 1*SD_NUMA
-					| sd_local_flags(level)
+					| 0*SD_NUMA
+					| sd_flags
 					,
+
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+		.smt_gain		= 0,
+		.max_newidle_lb_cost	= 0,
+		.next_decay_max_lb_cost	= jiffies,
+#ifdef CONFIG_SCHED_DEBUG
+		.name			= tl->name,
+#endif
 	};
-	SD_INIT_NAME(sd, NUMA);
-	sd->private = &tl->data;
 
 	/*
-	 * Ugly hack to pass state to sd_numa_mask()...
+	 * Convert topological properties into behaviour.
 	 */
-	sched_domains_curr_level = tl->numa_level;
+
+	if (sd->flags & SD_SHARE_CPUPOWER) {
+		sd->imbalance_pct = 110;
+		sd->smt_gain = 1178; /* ~15% */
+		sd->flags |= arch_sd_sibling_asym_packing();
+
+	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->imbalance_pct = 117;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+
+#ifdef CONFIG_NUMA
+	} else if (sd->flags & SD_NUMA) {
+		sd->cache_nice_tries = 2;
+		sd->busy_idx = 3;
+		sd->idle_idx = 2;
+
+		sd->flags |= SD_SERIALIZE;
+		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
+			sd->flags &= ~(SD_BALANCE_EXEC |
+				       SD_BALANCE_FORK |
+				       SD_WAKE_AFFINE);
+		}
+
+#endif
+	} else {
+		sd->flags |= SD_PREFER_SIBLING;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+		sd->idle_idx = 1;
+	}
+
+	sd->private = &tl->data;
 
 	return sd;
 }
 
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+#ifdef CONFIG_SCHED_BOOK
+	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
+struct sched_domain_topology_level *sched_domain_topology = default_topology;
+
+#define for_each_sd_topology(tl)			\
+	for (tl = sched_domain_topology; tl->mask; tl++)
+
+void set_sched_topology(struct sched_domain_topology_level *tl)
+{
+	sched_domain_topology = tl;
+}
+
+#ifdef CONFIG_NUMA
+
 static const struct cpumask *sd_numa_mask(int cpu)
 {
 	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
@@ -6218,7 +6223,10 @@  static void sched_init_numa(void)
 		}
 	}
 
-	tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
+	/* Compute default topology size */
+	for (i = 0; sched_domain_topology[i].mask; i++);
+
+	tl = kzalloc((i + level) *
 			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
 	if (!tl)
 		return;
@@ -6226,18 +6234,19 @@  static void sched_init_numa(void)
 	/*
 	 * Copy the default topology bits..
 	 */
-	for (i = 0; default_topology[i].init; i++)
-		tl[i] = default_topology[i];
+	for (i = 0; sched_domain_topology[i].mask; i++)
+		tl[i] = sched_domain_topology[i];
 
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
 	for (j = 0; j < level; i++, j++) {
 		tl[i] = (struct sched_domain_topology_level){
-			.init = sd_numa_init,
 			.mask = sd_numa_mask,
+			.sd_flags = SD_NUMA,
 			.flags = SDTL_OVERLAP,
 			.numa_level = j,
+			SD_INIT_NAME(NUMA)
 		};
 	}
 
@@ -6395,7 +6404,7 @@  struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 		struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = tl->init(tl, cpu);
+	struct sched_domain *sd = sd_init(tl, cpu);
 	if (!sd)
 		return child;