From c8eaf6ac76f40f6c59fc7d056e2e08c4a57ea9c7 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Fri, 28 Jan 2022 17:50:25 +0800 Subject: sched: move autogroup sysctls into its own file move autogroup sysctls to autogroup.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220128095025.8745-1-nizhen@uniontech.com --- include/linux/sched/sysctl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..3f2b70f8d32c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; -#endif - extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; -- cgit v1.2.3 From c574bbe917036c8968b984c82c7b13194fe5ce98 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 22 Mar 2022 14:46:23 -0700 Subject: NUMA balancing: optimize page placement for memory tiering system With the advent of various new memory types, some machines will have multiple types of memory, e.g. DRAM and PMEM (persistent memory). The memory subsystem of these machines can be called memory tiering system, because the performance of the different types of memory are usually different. In such system, because of the memory accessing pattern changing etc, some pages in the slow memory may become hot globally. So in this patch, the NUMA balancing mechanism is enhanced to optimize the page placement among the different memory types according to hot/cold dynamically. In a typical memory tiering system, there are CPUs, fast memory and slow memory in each physical NUMA node. The CPUs and the fast memory will be put in one logical node (called fast memory node), while the slow memory will be put in another (faked) logical node (called slow memory node). That is, the fast memory is regarded as local while the slow memory is regarded as remote. So it's possible for the recently accessed pages in the slow memory node to be promoted to the fast memory node via the existing NUMA balancing mechanism. The original NUMA balancing mechanism will stop to migrate pages if the free memory of the target node becomes below the high watermark. This is a reasonable policy if there's only one memory type. But this makes the original NUMA balancing mechanism almost do not work to optimize page placement among different memory types. Details are as follows. It's the common cases that the working-set size of the workload is larger than the size of the fast memory nodes. Otherwise, it's unnecessary to use the slow memory at all. So, there are almost always no enough free pages in the fast memory nodes, so that the globally hot pages in the slow memory node cannot be promoted to the fast memory node. To solve the issue, we have 2 choices as follows, a. Ignore the free pages watermark checking when promoting hot pages from the slow memory node to the fast memory node. This will create some memory pressure in the fast memory node, thus trigger the memory reclaiming. So that, the cold pages in the fast memory node will be demoted to the slow memory node. b. Define a new watermark called wmark_promo which is higher than wmark_high, and have kswapd reclaiming pages until free pages reach such watermark. The scenario is as follows: when we want to promote hot-pages from a slow memory to a fast memory, but fast memory's free pages would go lower than high watermark with such promotion, we wake up kswapd with wmark_promo watermark in order to demote cold pages and free us up some space. So, next time we want to promote hot-pages we might have a chance of doing so. The choice "a" may create high memory pressure in the fast memory node. If the memory pressure of the workload is high, the memory pressure may become so high that the memory allocation latency of the workload is influenced, e.g. the direct reclaiming may be triggered. The choice "b" works much better at this aspect. If the memory pressure of the workload is high, the hot pages promotion will stop earlier because its allocation watermark is higher than that of the normal memory allocation. So in this patch, choice "b" is implemented. A new zone watermark (WMARK_PROMO) is added. Which is larger than the high watermark and can be controlled via watermark_scale_factor. In addition to the original page placement optimization among sockets, the NUMA balancing mechanism is extended to be used to optimize page placement according to hot/cold among different memory types. So the sysctl user space interface (numa_balancing) is extended in a backward compatible way as follow, so that the users can enable/disable these functionality individually. The sysctl is converted from a Boolean value to a bits field. The definition of the flags is, - 0: NUMA_BALANCING_DISABLED - 1: NUMA_BALANCING_NORMAL - 2: NUMA_BALANCING_MEMORY_TIERING We have tested the patch with the pmbench memory accessing benchmark with the 80:20 read/write ratio and the Gauss access address distribution on a 2 socket Intel server with Optane DC Persistent Memory Model. The test results shows that the pmbench score can improve up to 95.9%. Thanks Andrew Morton to help fix the document format error. Link: https://lkml.kernel.org/r/20220221084529.1052339-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Tested-by: Baolin Wang Reviewed-by: Baolin Wang Acked-by: Johannes Weiner Reviewed-by: Oscar Salvador Reviewed-by: Yang Shi Cc: Michal Hocko Cc: Rik van Riel Cc: Mel Gorman Cc: Peter Zijlstra Cc: Dave Hansen Cc: Zi Yan Cc: Wei Xu Cc: Shakeel Butt Cc: zhongjiang-ali Cc: Randy Dunlap Cc: Feng Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/sysctl/kernel.rst | 29 ++++++++++++++++++++--------- include/linux/mmzone.h | 1 + include/linux/sched/sysctl.h | 10 ++++++++++ kernel/sched/core.c | 21 +++++++++++++++++---- kernel/sysctl.c | 2 +- mm/migrate.c | 16 ++++++++++++++-- mm/page_alloc.c | 3 ++- mm/vmscan.c | 6 +++++- 8 files changed, 70 insertions(+), 18 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index d359bcfadd39..fdfd2b684822 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -595,16 +595,23 @@ Documentation/admin-guide/kernel-parameters.rst). numa_balancing ============== -Enables/disables automatic page fault based NUMA memory -balancing. Memory is moved automatically to nodes -that access it often. +Enables/disables and configures automatic page fault based NUMA memory +balancing. Memory is moved automatically to nodes that access it often. +The value to set can be the result of ORing the following: -Enables/disables automatic NUMA memory balancing. On NUMA machines, there -is a performance penalty if remote memory is accessed by a CPU. When this -feature is enabled the kernel samples what task thread is accessing memory -by periodically unmapping pages and later trapping a page fault. At the -time of the page fault, it is determined if the data being accessed should -be migrated to a local memory node. += ================================= +0 NUMA_BALANCING_DISABLED +1 NUMA_BALANCING_NORMAL +2 NUMA_BALANCING_MEMORY_TIERING += ================================= + +Or NUMA_BALANCING_NORMAL to optimize page placement among different +NUMA nodes to reduce remote accessing. On NUMA machines, there is a +performance penalty if remote memory is accessed by a CPU. When this +feature is enabled the kernel samples what task thread is accessing +memory by periodically unmapping pages and later trapping a page +fault. At the time of the page fault, it is determined if the data +being accessed should be migrated to a local memory node. The unmapping of pages and trapping faults incur additional overhead that ideally is offset by improved memory locality but there is no universal @@ -615,6 +622,10 @@ faults may be controlled by the `numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls. +Or NUMA_BALANCING_MEMORY_TIERING to optimize page placement among +different types of memory (represented as different NUMA nodes) to +place the hot pages in the fast memory. This is implemented based on +unmapping and page fault too. numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb =============================================================================================================================== diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 310b6e7ce58a..962b14d403e8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -353,6 +353,7 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..b5eec8854c5a 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -23,6 +23,16 @@ enum sched_tunable_scaling { SCHED_TUNABLESCALING_END, }; +#define NUMA_BALANCING_DISABLED 0x0 +#define NUMA_BALANCING_NORMAL 0x1 +#define NUMA_BALANCING_MEMORY_TIERING 0x2 + +#ifdef CONFIG_NUMA_BALANCING +extern int sysctl_numa_balancing_mode; +#else +#define sysctl_numa_balancing_mode 0 +#endif + /* * control realtime throttling: * diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9745613d531c..da6a60383645 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4279,7 +4279,9 @@ DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); #ifdef CONFIG_NUMA_BALANCING -void set_numabalancing_state(bool enabled) +int sysctl_numa_balancing_mode; + +static void __set_numabalancing_state(bool enabled) { if (enabled) static_branch_enable(&sched_numa_balancing); @@ -4287,13 +4289,22 @@ void set_numabalancing_state(bool enabled) static_branch_disable(&sched_numa_balancing); } +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sysctl_numa_balancing_mode = NUMA_BALANCING_NORMAL; + else + sysctl_numa_balancing_mode = NUMA_BALANCING_DISABLED; + __set_numabalancing_state(enabled); +} + #ifdef CONFIG_PROC_SYSCTL int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int err; - int state = static_branch_likely(&sched_numa_balancing); + int state = sysctl_numa_balancing_mode; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4303,8 +4314,10 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; - if (write) - set_numabalancing_state(state); + if (write) { + sysctl_numa_balancing_mode = state; + __set_numabalancing_state(state); + } return err; } #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 730ab56d9e92..3395b99d59a4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1696,7 +1696,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sysctl_numa_balancing, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ { diff --git a/mm/migrate.c b/mm/migrate.c index dc4adf979201..78b2cf87946d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -51,6 +51,7 @@ #include #include #include +#include #include @@ -2031,16 +2032,27 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; int nr_pages = thp_nr_pages(page); + int order = compound_order(page); - VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + VM_BUG_ON_PAGE(order && !PageTransHuge(page), page); /* Do not migrate THP mapped by multiple processes */ if (PageTransHuge(page) && total_mapcount(page) > 1) return 0; /* Avoid migrating to a node that is nearly full */ - if (!migrate_balanced_pgdat(pgdat, nr_pages)) + if (!migrate_balanced_pgdat(pgdat, nr_pages)) { + int z; + + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) + return 0; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + if (populated_zone(pgdat->node_zones + z)) + break; + } + wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); return 0; + } if (isolate_lru_page(page)) return 0; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a573aa9f5160..8b18a077c409 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8441,7 +8441,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark_boost = 0; zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; - zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; + zone->_watermark[WMARK_HIGH] = low_wmark_pages(zone) + tmp; + zone->_watermark[WMARK_PROMO] = high_wmark_pages(zone) + tmp; spin_unlock_irqrestore(&zone->lock, flags); } diff --git a/mm/vmscan.c b/mm/vmscan.c index f5ec53f19f3b..499fa86e754a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -56,6 +56,7 @@ #include #include +#include #include "internal.h" @@ -3895,7 +3896,10 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) if (!managed_zone(zone)) continue; - mark = high_wmark_pages(zone); + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) + mark = wmark_pages(zone, WMARK_PROMO); + else + mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } -- cgit v1.2.3 From a60707d74bd1d119cf7bcc5101cda912fc46d5e3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:57 +0800 Subject: sched: Move child_runs_first sysctls to fair.c move child_runs_first sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- kernel/sched/fair.c | 19 +++++++++++++++++++ kernel/sched/sched.h | 2 ++ kernel/sysctl.c | 7 ------- 4 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c1076b5e17fb..1d2ff3cd1728 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs; enum { sysctl_hung_task_timeout_secs = 0 }; #endif -extern unsigned int sysctl_sched_child_runs_first; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4bd299d67ab..788b1d6a3248 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -109,6 +109,25 @@ static unsigned int sched_nr_latency = 8; * parent will (try to) run first. */ unsigned int sysctl_sched_child_runs_first __read_mostly; +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_child_runs_first_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int __init sched_child_runs_first_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_child_runs_first_sysctls); + return 0; +} +late_initcall(sched_child_runs_first_sysctl_init); +#endif /* * SCHED_OTHER wake-up granularity. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..767fc1de9646 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -108,6 +108,8 @@ extern __read_mostly int scheduler_running; extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; +extern unsigned int sysctl_sched_child_runs_first; + extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 830aaf8ca08e..6bbb8e1af675 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1659,13 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write, } static struct ctl_table kern_table[] = { - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", -- cgit v1.2.3 From f5ef06d58be8311a9425e6a54a053ecb350952f3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:58 +0800 Subject: sched: Move schedstats sysctls to core.c move schedstats sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- kernel/sched/core.c | 22 +++++++++++++++++++++- kernel/sysctl.c | 11 ----------- 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1d2ff3cd1728..6c7a6850559b 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -64,8 +64,6 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..04440da5955f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4430,7 +4430,7 @@ out: __setup("schedstats=", setup_schedstats); #ifdef CONFIG_PROC_SYSCTL -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, +static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4449,6 +4449,26 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, set_schedstats(state); return err; } + +static struct ctl_table sched_schedstats_sysctls[] = { + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sched_schedstats_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_schedstats_sysctls); + return 0; +} +late_initcall(sched_schedstats_sysctl_init); #endif /* CONFIG_PROC_SYSCTL */ #endif /* CONFIG_SCHEDSTATS */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6bbb8e1af675..fc0eeca20718 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1659,17 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write, } static struct ctl_table kern_table[] = { -#ifdef CONFIG_SCHEDSTATS - { - .procname = "sched_schedstats", - .data = NULL, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_schedstats, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_TASK_DELAY_ACCT { .procname = "task_delayacct", -- cgit v1.2.3 From d9ab0e63fa7f8405fbb19e28c5191e0880a7f2db Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:59 +0800 Subject: sched: Move rt_period/runtime sysctls to rt.c move rt_period/runtime sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 11 ----------- kernel/rcu/rcu.h | 2 ++ kernel/sched/core.c | 13 ------------- kernel/sched/rt.c | 43 ++++++++++++++++++++++++++++++++++++++++++- kernel/sched/sched.h | 4 ++++ kernel/sysctl.c | 14 -------------- 6 files changed, 48 insertions(+), 39 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 6c7a6850559b..4391c1307945 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,15 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -/* - * control realtime throttling: - * - * /proc/sys/kernel/sched_rt_period_us - * /proc/sys/kernel/sched_rt_runtime_us - */ -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - extern unsigned int sysctl_sched_dl_period_max; extern unsigned int sysctl_sched_dl_period_min; @@ -58,8 +49,6 @@ extern int sched_rr_timeslice; int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 24b5f2c2de87..7812c740b3bf 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -23,6 +23,8 @@ #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) +extern int sysctl_sched_rt_runtime; + /* * Return the counter portion of a sequence number previously returned * by rcu_seq_snap() or rcu_seq_current(). diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 04440da5955f..774f3229db37 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -145,12 +145,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8; const_debug unsigned int sysctl_sched_nr_migrate = 32; #endif -/* - * period over which we measure -rt task CPU usage in us. - * default: 1s - */ -unsigned int sysctl_sched_rt_period = 1000000; - __read_mostly int scheduler_running; #ifdef CONFIG_SCHED_CORE @@ -444,13 +438,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } #endif /* CONFIG_SCHED_CORE */ -/* - * part of the period that we allow rt tasks to run in us. - * default: 0.95s - */ -int sysctl_sched_rt_runtime = 950000; - - /* * Serialization rules: * diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a32c46889af8..5663bb5ff890 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -13,6 +13,47 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); struct rt_bandwidth def_rt_bandwidth; +/* + * period over which we measure -rt task CPU usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_rt_sysctls[] = { + { + .procname = "sched_rt_period_us", + .data = &sysctl_sched_rt_period, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rt_runtime_us", + .data = &sysctl_sched_rt_runtime, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + {} +}; + +static int __init sched_rt_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_rt_sysctls); + return 0; +} +late_initcall(sched_rt_sysctl_init); +#endif + static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) { struct rt_bandwidth *rt_b = @@ -2925,7 +2966,7 @@ static void sched_rt_do_global(void) raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); } -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_period, old_runtime; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 767fc1de9646..3b406c78a8e9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -114,6 +114,10 @@ extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); extern void call_trace_sched_update_nr_running(struct rq *rq, int count); + +extern unsigned int sysctl_sched_rt_period; +extern int sysctl_sched_rt_runtime; + /* * Helpers for converting nanosecond timing to jiffy resolution */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index fc0eeca20718..029bfe06c68d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_rt_period_us", - .data = &sysctl_sched_rt_period, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, - { - .procname = "sched_rt_runtime_us", - .data = &sysctl_sched_rt_runtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, { .procname = "sched_deadline_period_max_us", .data = &sysctl_sched_dl_period_max, -- cgit v1.2.3 From 84227c12888b1105725cd2de14705b029bcbb4b2 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:00 +0800 Subject: sched: Move deadline_period sysctls to deadline.c move deadline_period sysctls to deadline.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 3 --- kernel/sched/deadline.c | 42 ++++++++++++++++++++++++++++++++++-------- kernel/sysctl.c | 14 -------------- 3 files changed, 34 insertions(+), 25 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4391c1307945..7da9b94c5e1c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,9 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -extern unsigned int sysctl_sched_dl_period_max; -extern unsigned int sysctl_sched_dl_period_min; - #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fb4255ae0b2c..82e10b74a7b2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,40 @@ * Fabio Checconi */ +/* + * Default limits for DL period; on the top end we guard against small util + * tasks still getting ridiculously long effective runtimes, on the bottom end we + * guard against timer DoS. + */ +static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ +static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_dl_sysctls[] = { + { + .procname = "sched_deadline_period_max_us", + .data = &sysctl_sched_dl_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_deadline_period_min_us", + .data = &sysctl_sched_dl_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int __init sched_dl_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_dl_sysctls); + return 0; +} +late_initcall(sched_dl_sysctl_init); +#endif + static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) { return container_of(dl_se, struct task_struct, dl); @@ -2879,14 +2913,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr) attr->sched_flags |= dl_se->flags; } -/* - * Default limits for DL period; on the top end we guard against small util - * tasks still getting ridiculously long effective runtimes, on the bottom end we - * guard against timer DoS. - */ -unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ -unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ - /* * This function validates the new parameters of a -deadline task. * We ask for the deadline not being zero, and greater or equal diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 029bfe06c68d..2c8c75e11a37 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_deadline_period_max_us", - .data = &sysctl_sched_dl_period_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sched_deadline_period_min_us", - .data = &sysctl_sched_dl_period_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "sched_rr_timeslice_ms", .data = &sysctl_sched_rr_timeslice, -- cgit v1.2.3 From dafd7a9dad22fadcb290b24dff54e2eae3b89776 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:01 +0800 Subject: sched: Move rr_timeslice sysctls to rt.c move rr_timeslice sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 5 ----- kernel/sched/rt.c | 13 +++++++++++-- kernel/sched/sched.h | 1 + kernel/sysctl.c | 7 ------- 4 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7da9b94c5e1c..3d307e512d1f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -41,11 +41,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -extern int sysctl_sched_rr_timeslice; -extern int sched_rr_timeslice; - -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 5663bb5ff890..71791be36065 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,7 +5,7 @@ */ int sched_rr_timeslice = RR_TIMESLICE; -int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; /* More than 4 hours if BW_SHIFT equals 20. */ static const u64 max_rt_runtime = MAX_BW; @@ -27,6 +27,8 @@ int sysctl_sched_rt_runtime = 950000; static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #ifdef CONFIG_SYSCTL static struct ctl_table sched_rt_sysctls[] = { { @@ -43,6 +45,13 @@ static struct ctl_table sched_rt_sysctls[] = { .mode = 0644, .proc_handler = sched_rt_handler, }, + { + .procname = "sched_rr_timeslice_ms", + .data = &sysctl_sched_rr_timeslice, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rr_handler, + }, {} }; @@ -3005,7 +3014,7 @@ undo: return ret; } -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3b406c78a8e9..ae0f6e5a76f9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -117,6 +117,7 @@ extern void call_trace_sched_update_nr_running(struct rq *rq, int count); extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +extern int sched_rr_timeslice; /* * Helpers for converting nanosecond timing to jiffy resolution diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2c8c75e11a37..b074f70a3e11 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,13 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_rr_timeslice_ms", - .data = &sysctl_sched_rr_timeslice, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rr_handler, - }, #ifdef CONFIG_UCLAMP_TASK { .procname = "sched_util_clamp_min", -- cgit v1.2.3 From 3267e0156c3341ac25b37a0f60551cdae1634b60 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:02 +0800 Subject: sched: Move uclamp_util sysctls to core.c move uclamp_util sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 8 -------- kernel/sched/core.c | 48 ++++++++++++++++++++++++++++++++++---------- kernel/sysctl.c | 23 --------------------- 3 files changed, 37 insertions(+), 42 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 3d307e512d1f..0934b21a57a4 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,18 +31,10 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_UCLAMP_TASK -extern unsigned int sysctl_sched_uclamp_util_min; -extern unsigned int sysctl_sched_uclamp_util_max; -extern unsigned int sysctl_sched_uclamp_util_min_rt_default; -#endif - #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 774f3229db37..ef31751c5799 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1306,10 +1306,10 @@ static void set_load_weight(struct task_struct *p, bool update_load) static DEFINE_MUTEX(uclamp_mutex); /* Max allowed minimum utilization */ -unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; /* Max allowed maximum utilization */ -unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; /* * By default RT tasks run at the maximum performance point/capacity of the @@ -1326,7 +1326,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; * This knob will not override the system default sched_util_clamp_min defined * above. */ -unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; @@ -1779,7 +1779,7 @@ static void uclamp_update_root_tg(void) static void uclamp_update_root_tg(void) { } #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, +static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; @@ -4436,8 +4436,12 @@ static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, set_schedstats(state); return err; } +#endif /* CONFIG_PROC_SYSCTL */ +#endif /* CONFIG_SCHEDSTATS */ -static struct ctl_table sched_schedstats_sysctls[] = { +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_core_sysctls[] = { +#ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", .data = NULL, @@ -4447,17 +4451,39 @@ static struct ctl_table sched_schedstats_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_UCLAMP_TASK + { + .procname = "sched_util_clamp_min", + .data = &sysctl_sched_uclamp_util_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_max", + .data = &sysctl_sched_uclamp_util_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_min_rt_default", + .data = &sysctl_sched_uclamp_util_min_rt_default, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, +#endif /* CONFIG_UCLAMP_TASK */ {} }; - -static int __init sched_schedstats_sysctl_init(void) +static int __init sched_core_sysctl_init(void) { - register_sysctl_init("kernel", sched_schedstats_sysctls); + register_sysctl_init("kernel", sched_core_sysctls); return 0; } -late_initcall(sched_schedstats_sysctl_init); -#endif /* CONFIG_PROC_SYSCTL */ -#endif /* CONFIG_SCHEDSTATS */ +late_initcall(sched_core_sysctl_init); +#endif /* CONFIG_SYSCTL */ /* * fork()/clone()-time setup: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b074f70a3e11..a48c090d57f9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,29 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_UCLAMP_TASK - { - .procname = "sched_util_clamp_min", - .data = &sysctl_sched_uclamp_util_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_max", - .data = &sysctl_sched_uclamp_util_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_min_rt_default", - .data = &sysctl_sched_uclamp_util_min_rt_default, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, -#endif #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", -- cgit v1.2.3 From d4ae80ffa64f87b9c355692b680b603add084e96 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:03 +0800 Subject: sched: Move cfs_bandwidth_slice sysctls to fair.c move cfs_bandwidth_slice sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 4 ---- kernel/sched/fair.c | 51 +++++++++++++++++++++++++++----------------- kernel/sysctl.c | 10 --------- 3 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 0934b21a57a4..198f77c8a873 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,10 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif - int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 788b1d6a3248..265bf7a75a37 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -109,25 +109,6 @@ static unsigned int sched_nr_latency = 8; * parent will (try to) run first. */ unsigned int sysctl_sched_child_runs_first __read_mostly; -#ifdef CONFIG_SYSCTL -static struct ctl_table sched_child_runs_first_sysctls[] = { - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - {} -}; - -static int __init sched_child_runs_first_sysctl_init(void) -{ - register_sysctl_init("kernel", sched_child_runs_first_sysctls); - return 0; -} -late_initcall(sched_child_runs_first_sysctl_init); -#endif /* * SCHED_OTHER wake-up granularity. @@ -192,7 +173,37 @@ int __weak arch_asym_cpu_priority(int cpu) * * (default: 5 msec, units: microseconds) */ -unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +static unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_fair_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, +#endif + {} +}; + +static int __init sched_fair_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_fair_sysctls); + return 0; +} +late_initcall(sched_fair_sysctl_init); #endif static inline void update_load_add(struct load_weight *lw, unsigned long inc) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a48c090d57f9..10ab81c7c457 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,16 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_CFS_BANDWIDTH - { - .procname = "sched_cfs_bandwidth_slice_us", - .data = &sysctl_sched_cfs_bandwidth_slice, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, -#endif #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) { .procname = "sched_energy_aware", -- cgit v1.2.3 From 8a0441415b3f9b9a920a6a5086580ea3daa7b884 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:04 +0800 Subject: sched: Move energy_aware sysctls to topology.c move energy_aware sysctls to topology.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 6 ------ kernel/sched/topology.c | 25 +++++++++++++++++++++++-- kernel/sysctl.c | 11 ----------- 3 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux/sched/sysctl.h') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 198f77c8a873..e650946816d0 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -34,10 +34,4 @@ extern int sysctl_numa_balancing_mode; int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -extern unsigned int sysctl_sched_energy_aware; -int sched_energy_aware_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 810750e62118..05b6c2ad90b9 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -206,7 +206,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) DEFINE_STATIC_KEY_FALSE(sched_energy_present); -unsigned int sysctl_sched_energy_aware = 1; +static unsigned int sysctl_sched_energy_aware = 1; DEFINE_MUTEX(sched_energy_mutex); bool sched_energy_update; @@ -220,7 +220,7 @@ void rebuild_sched_domains_energy(void) } #ifdef CONFIG_PROC_SYSCTL -int sched_energy_aware_handler(struct ctl_table *table, int write, +static int sched_energy_aware_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, state; @@ -237,6 +237,27 @@ int sched_energy_aware_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table sched_energy_aware_sysctls[] = { + { + .procname = "sched_energy_aware", + .data = &sysctl_sched_energy_aware, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_energy_aware_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sched_energy_aware_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_energy_aware_sysctls); + return 0; +} + +late_initcall(sched_energy_aware_sysctl_init); #endif static void free_pd(struct perf_domain *pd) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 10ab81c7c457..8241c5401ee8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,17 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) - { - .procname = "sched_energy_aware", - .data = &sysctl_sched_energy_aware, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_energy_aware_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- cgit v1.2.3