From 27e4f9d0012a9bb7011aade862f08679d2921ab0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Apr 2014 12:50:34 +0200 Subject: sched/wait: Explain the shadowing and type inconsistencies Stick in a comment before someone else tries to fix the sparse warning this generates. Requested-by: Andrew Morton Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-o2ro6f3vkxklni0bc8f7m68s@git.kernel.org Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/wait.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 559044c79232..2b563a15a77d 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -191,11 +191,23 @@ wait_queue_head_t *bit_waitqueue(void *, int); (!__builtin_constant_p(state) || \ state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ +/* + * The below macro ___wait_event() has an explicit shadow of the __ret + * variable when used from the wait_event_*() macros. + * + * This is so that both can use the ___wait_cond_timeout() construct + * to wrap the condition. + * + * The type inconsistency of the wait_event_*() __ret variable is also + * on purpose; we use long where we can return timeout values and int + * otherwise. + */ + #define ___wait_event(wq, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ wait_queue_t __wait; \ - long __ret = ret; \ + long __ret = ret; /* explicit shadow */ \ \ INIT_LIST_HEAD(&__wait.task_list); \ if (exclusive) \ -- cgit v1.2.3 From 08f8aeb55d7727d644dbbbbfb798fe937d47751d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Apr 2014 14:27:25 +0200 Subject: sched: Remove set_need_resched() The last user is gone now, so we can safely remove this function. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/thread_info.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index fddbe2023a5d..cb0cec94fda3 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -104,20 +104,6 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) -static inline __deprecated void set_need_resched(void) -{ - /* - * Use of this function in deprecated. - * - * As of this writing there are only a few users in the DRM tree left - * all of which are wrong and can be removed without causing too much - * grief. - * - * The DRM people are aware and are working on removing the last few - * instances. - */ -} - #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK -- cgit v1.2.3 From 52c324f8a87b336496d0f5e9d8dff1aa32bb08cd Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 1 May 2014 00:13:47 +0200 Subject: cpuidle: Combine cpuidle_enabled() with cpuidle_select() Since both cpuidle_enabled() and cpuidle_select() are only called by cpuidle_idle_call(), it is not really useful to keep them separate and combining them will help to avoid complicating cpuidle_idle_call() even further if governors are changed to return error codes sometimes. This code modification shouldn't lead to any functional changes. Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 26 ++++++-------------------- include/linux/cpuidle.h | 5 ----- kernel/sched/idle.c | 20 +++++++------------- 3 files changed, 13 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 8236746e46bb..f38359f64cc6 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -64,26 +64,6 @@ int cpuidle_play_dead(void) return -ENODEV; } -/** - * cpuidle_enabled - check if the cpuidle framework is ready - * @dev: cpuidle device for this cpu - * @drv: cpuidle driver for this cpu - * - * Return 0 on success, otherwise: - * -NODEV : the cpuidle framework is not available - * -EBUSY : the cpuidle framework is not initialized - */ -int cpuidle_enabled(struct cpuidle_driver *drv, struct cpuidle_device *dev) -{ - if (off || !initialized) - return -ENODEV; - - if (!drv || !dev || !dev->enabled) - return -EBUSY; - - return 0; -} - /** * cpuidle_enter_state - enter the state and update stats * @dev: cpuidle device for this cpu @@ -138,6 +118,12 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, */ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) { + if (off || !initialized) + return -ENODEV; + + if (!drv || !dev || !dev->enabled) + return -EBUSY; + return cpuidle_curr_governor->select(drv, dev); } diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b0238cba440b..a8d5bd391a26 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -120,8 +120,6 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern void disable_cpuidle(void); -extern int cpuidle_enabled(struct cpuidle_driver *drv, - struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_enter(struct cpuidle_driver *drv, @@ -149,9 +147,6 @@ extern int cpuidle_play_dead(void); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else static inline void disable_cpuidle(void) { } -static inline int cpuidle_enabled(struct cpuidle_driver *drv, - struct cpuidle_device *dev) -{return -ENODEV; } static inline int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f4390a079c7..a8f12247ce7c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -101,19 +101,13 @@ static int cpuidle_idle_call(void) rcu_idle_enter(); /* - * Check if the cpuidle framework is ready, otherwise fallback - * to the default arch specific idle method + * Ask the cpuidle framework to choose a convenient idle state. + * Fall back to the default arch specific idle method on errors. */ - ret = cpuidle_enabled(drv, dev); - - if (!ret) { - /* - * Ask the governor to choose an idle state it thinks - * it is convenient to go to. There is *always* a - * convenient idle state - */ - next_state = cpuidle_select(drv, dev); + next_state = cpuidle_select(drv, dev); + ret = next_state; + if (ret >= 0) { /* * The idle task must be scheduled, it is pointless to * go to idle, just update no idle residency and get @@ -140,7 +134,7 @@ static int cpuidle_idle_call(void) CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); - if (!ret) { + if (ret >= 0) { trace_cpu_idle_rcuidle(next_state, dev->cpu); /* @@ -175,7 +169,7 @@ static int cpuidle_idle_call(void) * We can't use the cpuidle framework, let's use the default * idle routine */ - if (ret) + if (ret < 0) arch_cpu_idle(); __current_set_polling(); -- cgit v1.2.3 From a6220fc19afc07fe77cfd16f5b8e568615517091 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 5 May 2014 00:51:54 +0200 Subject: PM / suspend: Always use deepest C-state in the "freeze" sleep state If freeze_enter() is called, we want to bypass the current cpuidle governor and always use the deepest available (that is, not disabled) C-state, because we want to save as much energy as reasonably possible then and runtime latency constraints don't matter at that point, since the system is in a sleep state anyway. Signed-off-by: Rafael J. Wysocki Tested-by: Aubrey Li --- drivers/cpuidle/cpuidle.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/cpuidle.h | 2 ++ kernel/power/suspend.c | 2 ++ 3 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index f38359f64cc6..cb7019977c50 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -32,6 +32,7 @@ LIST_HEAD(cpuidle_detected_devices); static int enabled_devices; static int off __read_mostly; static int initialized __read_mostly; +static bool use_deepest_state __read_mostly; int cpuidle_disabled(void) { @@ -64,6 +65,45 @@ int cpuidle_play_dead(void) return -ENODEV; } +/** + * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode. + * @enable: Whether enable or disable the feature. + * + * If the "deepest idle" mode is enabled, cpuidle will ignore the governor and + * always use the state with the greatest exit latency (out of the states that + * are not disabled). + * + * This function can only be called after cpuidle_pause() to avoid races. + */ +void cpuidle_use_deepest_state(bool enable) +{ + use_deepest_state = enable; +} + +/** + * cpuidle_find_deepest_state - Find the state of the greatest exit latency. + * @drv: cpuidle driver for a given CPU. + * @dev: cpuidle device for a given CPU. + */ +static int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + unsigned int latency_req = 0; + int i, ret = CPUIDLE_DRIVER_STATE_START - 1; + + for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable || s->exit_latency <= latency_req) + continue; + + latency_req = s->exit_latency; + ret = i; + } + return ret; +} + /** * cpuidle_enter_state - enter the state and update stats * @dev: cpuidle device for this cpu @@ -124,6 +164,9 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) if (!drv || !dev || !dev->enabled) return -EBUSY; + if (unlikely(use_deepest_state)) + return cpuidle_find_deepest_state(drv, dev); + return cpuidle_curr_governor->select(drv, dev); } @@ -155,7 +198,7 @@ int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, */ void cpuidle_reflect(struct cpuidle_device *dev, int index) { - if (cpuidle_curr_governor->reflect) + if (cpuidle_curr_governor->reflect && !unlikely(use_deepest_state)) cpuidle_curr_governor->reflect(dev, index); } diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a8d5bd391a26..c51a436135c4 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -143,6 +143,7 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); +extern void cpuidle_use_deepest_state(bool enable); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else @@ -175,6 +176,7 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } +static inline void cpuidle_use_deepest_state(bool enable) {} static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } #endif diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 8233cd4047d7..155721f7f909 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -54,9 +54,11 @@ static void freeze_begin(void) static void freeze_enter(void) { + cpuidle_use_deepest_state(true); cpuidle_resume(); wait_event(suspend_freeze_wait_head, suspend_freeze_wake); cpuidle_pause(); + cpuidle_use_deepest_state(false); } void freeze_wake(void) -- cgit v1.2.3 From 143e1e28cb40bed836b0a06567208bd7347c9672 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:37 +0200 Subject: 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 Tested-by: Dietmar Eggemann Reviewed-by: Preeti U Murthy Reviewed-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Chris Metcalf Cc: Christoph Lameter Cc: David S. Miller Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Hanjun Guo Cc: Heiko Carstens Cc: Jason Low Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Tony Luck 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 --- 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 | 53 +++++++++ include/linux/topology.h | 128 +++------------------ kernel/sched/core.c | 233 ++++++++++++++++++++------------------- 6 files changed, 186 insertions(+), 287 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 5cb55a1e606b..3202aa74e0d6 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 05425b18c0aa..07763bdb408d 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 #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index d15c0d8d550f..938311844233 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 2a4298fb0d85..656b035c30e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -879,6 +879,27 @@ 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 + +#ifdef CONFIG_NUMA +static inline const int cpu_numa_flags(void) +{ + return SD_NUMA; +} +#endif + struct sched_domain_attr { int relax_domain_level; }; @@ -985,6 +1006,38 @@ 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; 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 */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 13584f1cccfc..7d332b7899cc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5566,17 +5566,6 @@ 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; @@ -5589,21 +5578,6 @@ 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. @@ -5832,34 +5806,6 @@ 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; @@ -5947,99 +5893,156 @@ 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)]; @@ -6183,7 +6186,10 @@ 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; @@ -6191,18 +6197,19 @@ 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 = cpu_numa_flags, .flags = SDTL_OVERLAP, .numa_level = j, + SD_INIT_NAME(NUMA) }; } @@ -6360,7 +6367,7 @@ 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; -- cgit v1.2.3 From 607b45e9a216e89a63351556e488eea06be0ff48 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:39 +0200 Subject: sched, powerpc: Create a dedicated topology table Create a dedicated topology table for handling asymetric feature of powerpc. Signed-off-by: Vincent Guittot Reviewed-by: Preeti U Murthy Signed-off-by: Peter Zijlstra Cc: Andy Fleming Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Grant Likely Cc: Linus Torvalds Cc: Michael Ellerman Cc: Paul Gortmaker Cc: Paul Mackerras Cc: Preeti U. Murthy Cc: Rob Herring Cc: Srivatsa S. Bhat Cc: Toshi Kani Cc: Vasant Hegde Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: schwidefsky@de.ibm.com Cc: cmetcalf@tilera.com Cc: dietmar.eggemann@arm.com Cc: devicetree@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1397209481-28542-4-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/smp.c | 31 +++++++++++++++++++++++-------- include/linux/sched.h | 2 -- kernel/sched/core.c | 6 ------ 3 files changed, 23 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e2a4232c5871..10ffffef0414 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -766,6 +766,28 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } +#ifdef CONFIG_SCHED_SMT +/* cpumask of CPUs with asymetric SMT dependancy */ +static const int powerpc_smt_flags(void) +{ + int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES; + + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + flags |= SD_ASYM_PACKING; + } + return flags; +} +#endif + +static struct sched_domain_topology_level powerpc_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + void __init smp_cpus_done(unsigned int max_cpus) { cpumask_var_t old_mask; @@ -790,15 +812,8 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); -} + set_sched_topology(powerpc_topology); -int arch_sd_sibling_asym_packing(void) -{ - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - return SD_ASYM_PACKING; - } - return 0; } #ifdef CONFIG_HOTPLUG_CPU diff --git a/include/linux/sched.h b/include/linux/sched.h index 656b035c30e5..439a153b8403 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -877,8 +877,6 @@ enum cpu_idle_type { #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ -extern int __weak arch_sd_sibiling_asym_packing(void); - #ifdef CONFIG_SCHED_SMT static inline const int cpu_smt_flags(void) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e59e5aec745a..7e348e238bf1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5796,11 +5796,6 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); } -int __weak arch_sd_sibling_asym_packing(void) -{ - return 0*SD_ASYM_PACKING; -} - /* * Initializers for schedule domains * Non-inlined to reduce accumulated stack pressure in build_sched_domains() @@ -5981,7 +5976,6 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) 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; -- cgit v1.2.3 From d77b3ed5c9f8ebedf154b52b5e943c461f3d37e6 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:40 +0200 Subject: sched: Add a new SD_SHARE_POWERDOMAIN for sched_domain A new flag SD_SHARE_POWERDOMAIN is created to reflect whether groups of CPUs in a sched_domain level can or not reach different power state. As an example, the flag should be cleared at CPU level if groups of cores can be power gated independently. This information can be used in the load balance decision or to add load balancing level between group of CPUs that can power gate independantly. This flag is part of the topology flags that can be set by arch. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: schwidefsky@de.ibm.com Cc: cmetcalf@tilera.com Cc: benh@kernel.crashing.org Cc: preeti@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1397209481-28542-5-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched/core.c | 10 +++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 439a153b8403..accb66bfd722 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -870,6 +870,7 @@ enum cpu_idle_type { #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ +#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ #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 */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7e348e238bf1..1c9c3b7b26af 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5261,7 +5261,8 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_FORK | SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) return 0; } @@ -5292,7 +5293,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING); + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5901,6 +5903,7 @@ static int sched_domains_curr_level; * SD_SHARE_CPUPOWER - describes SMT topologies * SD_SHARE_PKG_RESOURCES - describes shared caches * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain * * Odd one out: * SD_ASYM_PACKING - describes SMT quirks @@ -5909,7 +5912,8 @@ static int sched_domains_curr_level; (SD_SHARE_CPUPOWER | \ SD_SHARE_PKG_RESOURCES | \ SD_NUMA | \ - SD_ASYM_PACKING) + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) static struct sched_domain * sd_init(struct sched_domain_topology_level *tl, int cpu) -- cgit v1.2.3 From 69dd0f848879328ae6c6f54c2ec80e49eef042d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Apr 2014 14:30:10 +0200 Subject: sched/idle: Remove TS_POLLING support Now that there are no architectures left using it, kill the support for TS_POLLING. Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andy Lutomirski Link: http://lkml.kernel.org/n/tip-6yurip2tfix2f4bfc5agu2s0@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 46 ++-------------------------------------------- 1 file changed, 2 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index accb66bfd722..725eef121c9f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2775,51 +2775,9 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Idle thread specific functions to determine the need_resched - * polling state. We have two versions, one based on TS_POLLING in - * thread_info.status and one based on TIF_POLLING_NRFLAG in - * thread_info.flags + * polling state. */ -#ifdef TS_POLLING -static inline int tsk_is_polling(struct task_struct *p) -{ - return task_thread_info(p)->status & TS_POLLING; -} -static inline void __current_set_polling(void) -{ - current_thread_info()->status |= TS_POLLING; -} - -static inline bool __must_check current_set_polling_and_test(void) -{ - __current_set_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} - -static inline void __current_clr_polling(void) -{ - current_thread_info()->status &= ~TS_POLLING; -} - -static inline bool __must_check current_clr_polling_and_test(void) -{ - __current_clr_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() - */ - smp_mb(); - - return unlikely(tif_need_resched()); -} -#elif defined(TIF_POLLING_NRFLAG) +#ifdef TIF_POLLING_NRFLAG static inline int tsk_is_polling(struct task_struct *p) { return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); -- cgit v1.2.3 From 7aa2c016db2162defff77f6f5731bff3f25e5175 Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Thu, 8 May 2014 18:33:49 +0900 Subject: sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice() Signed-off-by: Dongsheng Yang Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/a568a1e3cc8e78648f41b5035fa5e381d36274da.1399532322.git.yangds.fnst@cn.fujitsu.com Signed-off-by: Ingo Molnar --- drivers/staging/android/binder.c | 2 +- include/linux/sched/prio.h | 16 ++++++++++++++++ kernel/sched/core.c | 2 +- kernel/sys.c | 6 +++--- 4 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c index 179b21b66504..9311bb67ec35 100644 --- a/drivers/staging/android/binder.c +++ b/drivers/staging/android/binder.c @@ -436,7 +436,7 @@ static void binder_set_nice(long nice) set_user_nice(current, nice); return; } - min_nice = 20 - current->signal->rlim[RLIMIT_NICE].rlim_cur; + min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur); binder_debug(BINDER_DEBUG_PRIORITY_CAP, "%d: nice value %ld not allowed use %ld instead\n", current->pid, nice, min_nice); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index ac322583c820..d9cf5a5762d9 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -41,4 +41,20 @@ #define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) #define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) +/* + * Convert nice value [19,-20] to rlimit style value [1,40]. + */ +static inline long nice_to_rlimit(long nice) +{ + return (MAX_NICE - nice + 1); +} + +/* + * Convert rlimit style value [1,40] to nice value [-20, 19]. + */ +static inline long rlimit_to_nice(long prio) +{ + return (MAX_NICE - prio + 1); +} + #endif /* _SCHED_PRIO_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da302ca98f60..321d800e4baa 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3033,7 +3033,7 @@ EXPORT_SYMBOL(set_user_nice); int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; + int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); diff --git a/kernel/sys.c b/kernel/sys.c index fba0f29401ea..66a751ebf9d9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -250,7 +250,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else p = current; if (p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } @@ -261,7 +261,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); @@ -277,7 +277,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) do_each_thread(g, p) { if (uid_eq(task_uid(p), uid)) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } -- cgit v1.2.3 From 4027d080854d1be96ef134a1c3024d5276114db6 Mon Sep 17 00:00:00 2001 From: "xiaofeng.yan" Date: Fri, 9 May 2014 03:21:27 +0000 Subject: sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code Signed-off-by: xiaofeng.yan Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1399605687-18094-1-git-send-email-xiaofeng.yan@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- kernel/sched/deadline.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 725eef121c9f..0f91d00efd87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1175,8 +1175,8 @@ struct sched_dl_entity { /* * Original scheduling parameters. Copied here from sched_attr - * during sched_setscheduler2(), they will remain the same until - * the next sched_setscheduler2(). + * during sched_setattr(), they will remain the same until + * the next sched_setattr(). */ u64 dl_runtime; /* maximum runtime for each instance */ u64 dl_deadline; /* relative deadline of each instance */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e0a04ae1e0dd..f9ca7d19781a 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -520,7 +520,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * We need to take care of a possible races here. In fact, the * task might have changed its scheduling policy to something * different from SCHED_DEADLINE or changed its reservation - * parameters (through sched_setscheduler()). + * parameters (through sched_setattr()). */ if (!dl_task(p) || dl_se->dl_new) goto unlock; -- cgit v1.2.3