diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-05-22 18:27:32 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-05-22 18:27:32 -0700 |
commit | d79ee93de909dfb252279b9a95978bbda9a814a9 (patch) | |
tree | bfccca60fd36259ff4bcc5e78a2c272fbd680065 /include | |
parent | 2ff2b289a695807e291e1ed9f639d8a3ba5f4254 (diff) | |
parent | 1c2927f18576d65631d8e0ddd19e1d023183222e (diff) |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes from Ingo Molnar:
"The biggest change is the cleanup/simplification of the load-balancer:
instead of the current practice of architectures twiddling scheduler
internal data structures and providing the scheduler domains in
colorfully inconsistent ways, we now have generic scheduler code in
kernel/sched/core.c:sched_init_numa() that looks at the architecture's
node_distance() parameters and (while not fully trusting it) deducts a
NUMA topology from it.
This inevitably changes balancing behavior - hopefully for the better.
There are various smaller optimizations, cleanups and fixlets as well"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: Taint kernel with TAINT_WARN after sleep-in-atomic bug
sched: Remove stale power aware scheduling remnants and dysfunctional knobs
sched/debug: Fix printing large integers on 32-bit platforms
sched/fair: Improve the ->group_imb logic
sched/nohz: Fix rq->cpu_load[] calculations
sched/numa: Don't scale the imbalance
sched/fair: Revert sched-domain iteration breakage
sched/x86: Rewrite set_cpu_sibling_map()
sched/numa: Fix the new NUMA topology bits
sched/numa: Rewrite the CONFIG_NUMA sched domain support
sched/fair: Propagate 'struct lb_env' usage into find_busiest_group
sched/fair: Add some serialization to the sched_domain load-balance walk
sched/fair: Let minimally loaded cpu balance the group
sched: Change rq->nr_running to unsigned int
x86/numa: Check for nonsensical topologies on real hw as well
x86/numa: Hard partition cpu topology masks on node boundaries
x86/numa: Allow specifying node_distance() for numa=fake
x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly
sched: Update documentation and comments
sched_rt: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt()
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/cpu.h | 2 | ||||
-rw-r--r-- | include/linux/sched.h | 49 | ||||
-rw-r--r-- | include/linux/topology.h | 42 |
3 files changed, 1 insertions, 92 deletions
diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ee28844ae68e..7230bb59a06f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -36,8 +36,6 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern int sched_create_sysfs_power_savings_entries(struct device *dev); - #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index f774d88cd0aa..28fa9d02fd59 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -855,61 +855,14 @@ enum cpu_idle_type { #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ -#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -enum powersavings_balance_level { - POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ - POWERSAVINGS_BALANCE_BASIC, /* Fill one thread/core/package - * first for long running threads - */ - POWERSAVINGS_BALANCE_WAKEUP, /* Also bias task wakeups to semi-idle - * cpu package for power savings - */ - MAX_POWERSAVINGS_BALANCE_LEVELS -}; - -extern int sched_mc_power_savings, sched_smt_power_savings; - -static inline int sd_balance_for_mc_power(void) -{ - if (sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - if (!sched_mc_power_savings) - return SD_PREFER_SIBLING; - - return 0; -} - -static inline int sd_balance_for_package_power(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - return SD_PREFER_SIBLING; -} - extern int __weak arch_sd_sibiling_asym_packing(void); -/* - * Optimise SD flags for power savings: - * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings. - * Keep default SD flags if sched_{smt,mc}_power_saving=0 - */ - -static inline int sd_power_saving_flags(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_BALANCE_NEWIDLE; - - return 0; -} - struct sched_group_power { atomic_t ref; /* @@ -1962,7 +1915,7 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) */ extern unsigned long long notrace sched_clock(void); /* - * See the comment in kernel/sched_clock.c + * See the comment in kernel/sched/clock.c */ extern u64 cpu_clock(int cpu); extern u64 local_clock(void); diff --git a/include/linux/topology.h b/include/linux/topology.h index 9dc427cdb6ff..e91cd43394df 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -70,7 +70,6 @@ int arch_update_cpu_topology(void); * Below are the 3 major initializers used in building sched_domains: * SD_SIBLING_INIT, for SMT domains * SD_CPU_INIT, for SMP domains - * SD_NODE_INIT, for NUMA 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. @@ -99,7 +98,6 @@ int arch_update_cpu_topology(void); | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ @@ -135,8 +133,6 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_mc_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ @@ -168,56 +164,18 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_package_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ } #endif -/* sched_domains SD_ALLNODES_INIT for NUMA machines */ -#define SD_ALLNODES_INIT (struct sched_domain) { \ - .min_interval = 64, \ - .max_interval = 64*num_online_cpus(), \ - .busy_factor = 128, \ - .imbalance_pct = 133, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 3, \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 0*SD_BALANCE_EXEC \ - | 0*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 0*SD_WAKE_AFFINE \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 64, \ -} - -#ifndef SD_NODES_PER_DOMAIN -#define SD_NODES_PER_DOMAIN 16 -#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_NUMA -#ifndef SD_NODE_INIT -#error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! -#endif - -#endif /* CONFIG_NUMA */ - #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); |