From 8d3d5ada56a692d36a9d55858881147ec10cfeb6 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Wed, 11 Apr 2012 09:06:04 +0400 Subject: [PATCH 01/20] sched_rt: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt() Migration status depends on a difference of weight from 0 and 1. If weight > 1 (<= 1) and old weight <= 1 (> 1) then task becomes pushable (or not pushable). We are not insterested in its exact values, is it 3 or 4, for example. Now if we are changing affinity from a set of 3 cpus to a set of 4, the- task will be dequeued and enqueued sequentially without important difference in comparison with initial state. The only difference is in internal representation of plist queue of pushable tasks and the fact that the task may won't be the first in a sequence of the same priority tasks. But it seems to me it gives nothing. Link: http://lkml.kernel.org/r/273741334120764@web83.yandex.ru Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Tkhai Kirill Signed-off-by: Steven Rostedt --- kernel/sched/rt.c | 56 ++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 30 deletions(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index b60dad720173..90607a94dd69 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1803,44 +1803,40 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) static void set_cpus_allowed_rt(struct task_struct *p, const struct cpumask *new_mask) { - int weight = cpumask_weight(new_mask); + struct rq *rq; + int weight; BUG_ON(!rt_task(p)); + if (!p->on_rq) + return; + + weight = cpumask_weight(new_mask); + /* - * Update the migration status of the RQ if we have an RT task - * which is running AND changing its weight value. + * Only update if the process changes its state from whether it + * can migrate or not. */ - if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { - struct rq *rq = task_rq(p); + if ((p->rt.nr_cpus_allowed > 1) == (weight > 1)) + return; - if (!task_current(rq, p)) { - /* - * Make sure we dequeue this task from the pushable list - * before going further. It will either remain off of - * the list because we are no longer pushable, or it - * will be requeued. - */ - if (p->rt.nr_cpus_allowed > 1) - dequeue_pushable_task(rq, p); + rq = task_rq(p); - /* - * Requeue if our weight is changing and still > 1 - */ - if (weight > 1) - enqueue_pushable_task(rq, p); - - } - - if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) { - rq->rt.rt_nr_migratory++; - } else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) { - BUG_ON(!rq->rt.rt_nr_migratory); - rq->rt.rt_nr_migratory--; - } - - update_rt_migration(&rq->rt); + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_task(rq, p); + BUG_ON(!rq->rt.rt_nr_migratory); + rq->rt.rt_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_task(rq, p); + rq->rt.rt_nr_migratory++; } + + update_rt_migration(&rq->rt); } /* Assumes rq->lock is held */ From 489a71b029cd94e3b0132795146e8be3a87bf3fa Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Mon, 2 Apr 2012 17:00:44 +0900 Subject: [PATCH 02/20] sched: Update documentation and comments Change sched_*.c to sched/*.c in documentation and comments. Signed-off-by: Hiroshi Shimamoto Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/4F795CAC.9080206@ct.jp.nec.com Signed-off-by: Ingo Molnar --- Documentation/scheduler/sched-design-CFS.txt | 6 +++--- include/linux/sched.h | 2 +- kernel/sched/idle_task.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index 91ecff07cede..d529e02d928d 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -130,7 +130,7 @@ CFS implements three scheduling policies: idle timer scheduler in order to avoid to get into priority inversion problems which would deadlock the machine. -SCHED_FIFO/_RR are implemented in sched_rt.c and are as specified by +SCHED_FIFO/_RR are implemented in sched/rt.c and are as specified by POSIX. The command chrt from util-linux-ng 2.13.1.1 can set all of these except @@ -145,9 +145,9 @@ Classes," an extensible hierarchy of scheduler modules. These modules encapsulate scheduling policy details and are handled by the scheduler core without the core code assuming too much about them. -sched_fair.c implements the CFS scheduler described above. +sched/fair.c implements the CFS scheduler described above. -sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than +sched/rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT priority levels, instead of 140 in the previous scheduler) and it needs no expired array. diff --git a/include/linux/sched.h b/include/linux/sched.h index 81a173c0897d..4a559bf0622f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1950,7 +1950,7 @@ 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/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 91b4c957f289..b44d604b35d1 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -4,7 +4,7 @@ * idle-task scheduling class. * * (NOTE: these are not related to SCHED_IDLE tasks which are - * handled in sched_fair.c) + * handled in sched/fair.c) */ #ifdef CONFIG_SMP From 19209bbb8612004bc20a1f70ff12926f99fe2643 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Mon, 30 Apr 2012 12:26:56 +0530 Subject: [PATCH 03/20] x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly The checks that exist in mwait_usable() for "idle=" kernel parameters are insufficient. As a result, mwait_usable() can return 1 even if "idle=nomwait" or "idle=poll" or "idle=halt" parameters are passed. Of these cases, incorrect handling of idle=nomwait is a universal problem since mwait can get used for usual CPU idling. However the rest of the cases are problematic only during CPU Hotplug (offline) because, in the CPU offline path, the function mwait_play_dead() is called, which might result in mwait being used in the offline CPUs, if mwait_usable() happens to return 1. Fix these issues by checking for the boot time "idle=" kernel parameter properly in mwait_usable(). The first issue (usual cpu idling) is demonstrated below: Before applying the patch (dmesg snippet): [ 0.000000] Command line: [...] idle=nomwait [ 0.000000] Kernel command line: [...] idle=nomwait [ 0.000000] RCU dyntick-idle grace-period acceleration is enabled. [ 0.140606] using mwait in idle threads. <======= mwait being used [ 4.303986] cpuidle: using governor ladder [ 4.308232] cpuidle: using governor menu After applying the patch: [ 0.000000] Command line: [...] idle=nomwait [ 0.000000] Kernel command line: [...] idle=nomwait [ 0.000000] RCU dyntick-idle grace-period acceleration is enabled. [ 4.264100] cpuidle: using governor ladder [ 4.268342] cpuidle: using governor menu Signed-off-by: Srivatsa S. Bhat Acked-by: Deepthi Dharwar Acked-by: Thomas Gleixner Cc: venki@google.com Cc: suresh.b.siddha@intel.com Cc: Borislav Petkov Cc: lenb@kernel.org Cc: Rafael J. Wysocki Link: http://lkml.kernel.org/r/4F9E37B8.30001@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/process.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1d92a5ab6e8b..ad57d832d96f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -594,9 +594,17 @@ int mwait_usable(const struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; + /* Use mwait if idle=mwait boot option is given */ if (boot_option_idle_override == IDLE_FORCE_MWAIT) return 1; + /* + * Any idle= boot option other than idle=mwait means that we must not + * use mwait. Eg: idle=halt or idle=poll or idle=nomwait + */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return 0; + if (c->cpuid_level < MWAIT_INFO) return 0; From 94c0dd3278dd3eae52eabf0fb77d472d0dd3e373 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Apr 2012 19:04:17 +0200 Subject: [PATCH 04/20] x86/numa: Allow specifying node_distance() for numa=fake Allows emulating more interesting NUMA configurations like a quad socket AMD Magny-Cour: "numa=fake=8:10,16,16,22,16,22,16,22, 16,10,22,16,22,16,22,16, 16,22,10,16,16,22,16,22, 22,16,16,10,22,16,22,16, 16,22,16,22,10,16,16,22, 22,16,22,16,16,10,22,16, 16,22,16,22,16,22,10,16, 22,16,22,16,22,16,16,10" Which has a non-fully-connected topology. Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-e1136ef7kdffj7yf9tjhydln@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/numa_emulation.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 53489ff6bf82..871dd8868170 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -339,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } else { unsigned long n; - n = simple_strtoul(emu_cmdline, NULL, 0); + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); } + if (*emu_cmdline == ':') + emu_cmdline++; if (ret < 0) goto no_emu; @@ -418,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) int physj = emu_nid_to_phys[j]; int dist; - if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) + if (get_option(&emu_cmdline, &dist) == 2) + ; + else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) dist = physi == physj ? LOCAL_DISTANCE : REMOTE_DISTANCE; else From 0acbb440f06302058e1515861dd534594521e892 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Apr 2012 19:04:09 +0200 Subject: [PATCH 05/20] x86/numa: Hard partition cpu topology masks on node boundaries When using numa=fake= you can get weird topologies where LLCs can span nodes and other such nonsense. Cure this by hard partitioning these masks on node boundaries. Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-di5vwjm96q5vrb76opwuflwx@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6e1e406038c2..edfd03a9e390 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -337,6 +337,11 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { struct cpuinfo_x86 *o = &cpu_data(i); +#ifdef CONFIG_NUMA_EMU + if (cpu_to_node(cpu) != cpu_to_node(i)) + continue; +#endif + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { if (c->phys_proc_id == o->phys_proc_id && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) && @@ -360,11 +365,17 @@ void __cpuinit set_cpu_sibling_map(int cpu) } for_each_cpu(i, cpu_sibling_setup_mask) { +#ifdef CONFIG_NUMA_EMU + if (cpu_to_node(cpu) != cpu_to_node(i)) + continue; +#endif + if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); } + if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); From ad7687dde8780a0d618a3e3b5a62bb383696fc22 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 9 May 2012 13:31:47 +0200 Subject: [PATCH 06/20] x86/numa: Check for nonsensical topologies on real hw as well Instead of only checking nonsensical topologies on numa-emu, do it on real hardware as well, and print a warning. Acked-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-re15l0jqjtpz709oxozt2zoh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index edfd03a9e390..7c53d96d44ab 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -337,10 +337,10 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { struct cpuinfo_x86 *o = &cpu_data(i); -#ifdef CONFIG_NUMA_EMU - if (cpu_to_node(cpu) != cpu_to_node(i)) + if (cpu_to_node(cpu) != cpu_to_node(i)) { + WARN_ONCE(1, "sched: CPU #%d's thread-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); continue; -#endif + } if (cpu_has(c, X86_FEATURE_TOPOEXT)) { if (c->phys_proc_id == o->phys_proc_id && @@ -365,10 +365,10 @@ void __cpuinit set_cpu_sibling_map(int cpu) } for_each_cpu(i, cpu_sibling_setup_mask) { -#ifdef CONFIG_NUMA_EMU - if (cpu_to_node(cpu) != cpu_to_node(i)) + if (cpu_to_node(cpu) != cpu_to_node(i)) { + WARN_ONCE(1, "sched: CPU #%d's core-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); continue; -#endif + } if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { From c82513e513556a04f81aa511cd890acd23349c48 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Apr 2012 13:12:27 +0200 Subject: [PATCH 07/20] sched: Change rq->nr_running to unsigned int Since there's a PID space limit of 30bits (see futex.h:FUTEX_TID_MASK) and allocating that many tasks (assuming a lower bound of 2 pages per task) would still take 8T of memory it seems reasonable to say that unsigned int is sufficient for rq->nr_running. When we do get anywhere near that amount of tasks I suspect other things would go funny, load-balancer load computations would really need to be hoisted to 128bit etc. So save a few bytes and convert rq->nr_running and friends to unsigned int. Suggested-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-y3tvyszjdmbibade5bw8zl81@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 2 +- kernel/sched/fair.c | 8 ++++---- kernel/sched/sched.h | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 09acaa15161d..31e4f61a1629 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -202,7 +202,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(spread0)); SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", cfs_rq->nr_spread_over); - SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); + SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e9553640c1c3..678966ca393b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4447,10 +4447,10 @@ static int load_balance(int this_cpu, struct rq *this_rq, * correctly treated as an imbalance. */ env.flags |= LBF_ALL_PINNED; - env.load_move = imbalance; - env.src_cpu = busiest->cpu; - env.src_rq = busiest; - env.loop_max = min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running); + env.load_move = imbalance; + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); more_balance: local_irq_save(flags); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index fb3acba4d52e..7282e7b5f4c7 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -201,7 +201,7 @@ struct cfs_bandwidth { }; /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; - unsigned long nr_running, h_nr_running; + unsigned int nr_running, h_nr_running; u64 exec_clock; u64 min_vruntime; @@ -279,7 +279,7 @@ static inline int rt_bandwidth_enabled(void) /* Real-Time classes' related field in a runqueue: */ struct rt_rq { struct rt_prio_array active; - unsigned long rt_nr_running; + unsigned int rt_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED struct { int curr; /* highest queued rt task prio */ @@ -353,7 +353,7 @@ struct rq { * nr_running and cpu_load should be in the same cacheline because * remote CPUs use both these fields when doing load calculation. */ - unsigned long nr_running; + unsigned int nr_running; #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; From c22402a2f76e88b04b7a8b6c0597ad9ba6fd71de Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Apr 2012 16:57:22 +0200 Subject: [PATCH 08/20] sched/fair: Let minimally loaded cpu balance the group Currently we let the leftmost (or first idle) cpu ascend the sched_domain tree and perform load-balancing. The result is that the busiest cpu in the group might be performing this function and pull more load to itself. The next load balance pass will then try to equalize this again. Change this to pick the least loaded cpu to perform higher domain balancing. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-v8zlrmgmkne3bkcy9dej1fvm@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 678966ca393b..968ffee24721 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3781,7 +3781,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, { unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; int i; - unsigned int balance_cpu = -1, first_idle_cpu = 0; + unsigned int balance_cpu = -1; + unsigned long balance_load = ~0UL; unsigned long avg_load_per_task = 0; if (local_group) @@ -3797,12 +3798,11 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, /* Bias balancing toward cpus of our domain */ if (local_group) { - if (idle_cpu(i) && !first_idle_cpu) { - first_idle_cpu = 1; + load = target_load(i, load_idx); + if (load < balance_load || idle_cpu(i)) { + balance_load = load; balance_cpu = i; } - - load = target_load(i, load_idx); } else { load = source_load(i, load_idx); if (load > max_cpu_load) { From 0ce90475dcdbe90affc218e9688c8401e468e84d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 25 Apr 2012 00:30:36 +0200 Subject: [PATCH 09/20] sched/fair: Add some serialization to the sched_domain load-balance walk Since the sched_domain walk is completely unserialized (!SD_SERIALIZE) it is possible that multiple cpus in the group get elected to do the next level. Avoid this by adding some serialization. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-vqh9ai6s0ewmeakjz80w4qz6@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched/core.c | 2 ++ kernel/sched/fair.c | 9 +++++++-- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a559bf0622f..3cbfb55bde25 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -927,6 +927,7 @@ struct sched_group_power { struct sched_group { struct sched_group *next; /* Must be a circular list */ atomic_t ref; + int balance_cpu; unsigned int group_weight; struct sched_group_power *sgp; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0533a688ce22..6001e5c3b4e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6060,6 +6060,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span)); atomic_inc(&sg->sgp->ref); + sg->balance_cpu = -1; if (cpumask_test_cpu(cpu, sg_span)) groups = sg; @@ -6135,6 +6136,7 @@ build_sched_groups(struct sched_domain *sd, int cpu) cpumask_clear(sched_group_cpus(sg)); sg->sgp->power = 0; + sg->balance_cpu = -1; for_each_cpu(j, span) { if (get_group(j, sdd, NULL) != group) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 968ffee24721..cf86f74bcac2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3828,7 +3828,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, */ if (local_group) { if (idle != CPU_NEWLY_IDLE) { - if (balance_cpu != this_cpu) { + if (balance_cpu != this_cpu || + cmpxchg(&group->balance_cpu, -1, balance_cpu) != -1) { *balance = 0; return; } @@ -4929,7 +4930,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) int balance = 1; struct rq *rq = cpu_rq(cpu); unsigned long interval; - struct sched_domain *sd; + struct sched_domain *sd, *last = NULL; /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; @@ -4939,6 +4940,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) rcu_read_lock(); for_each_domain(cpu, sd) { + last = sd; if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -4983,6 +4985,9 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (!balance) break; } + for (sd = last; sd; sd = sd->child) + (void)cmpxchg(&sd->groups->balance_cpu, cpu, -1); + rcu_read_unlock(); /* From bd939f45da24e25e08a8f5c993c50b1afada0fef Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 May 2012 14:20:37 +0200 Subject: [PATCH 10/20] sched/fair: Propagate 'struct lb_env' usage into find_busiest_group More function argument passing reduction. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-v66ivjfqdiqdso01lqgqx6qf@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 175 +++++++++++++++++++++----------------------- 1 file changed, 82 insertions(+), 93 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cf86f74bcac2..9bd3366dbb1c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3082,7 +3082,7 @@ struct lb_env { struct rq *dst_rq; enum cpu_idle_type idle; - long load_move; + long imbalance; unsigned int flags; unsigned int loop; @@ -3218,7 +3218,7 @@ static unsigned long task_h_load(struct task_struct *p); static const unsigned int sched_nr_migrate_break = 32; /* - * move_tasks tries to move up to load_move weighted load from busiest to + * move_tasks tries to move up to imbalance weighted load from busiest to * this_rq, as part of a balancing operation within domain "sd". * Returns 1 if successful and 0 otherwise. * @@ -3231,7 +3231,7 @@ static int move_tasks(struct lb_env *env) unsigned long load; int pulled = 0; - if (env->load_move <= 0) + if (env->imbalance <= 0) return 0; while (!list_empty(tasks)) { @@ -3257,7 +3257,7 @@ static int move_tasks(struct lb_env *env) if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) goto next; - if ((load / 2) > env->load_move) + if ((load / 2) > env->imbalance) goto next; if (!can_migrate_task(p, env)) @@ -3265,7 +3265,7 @@ static int move_tasks(struct lb_env *env) move_task(p, env); pulled++; - env->load_move -= load; + env->imbalance -= load; #ifdef CONFIG_PREEMPT /* @@ -3281,7 +3281,7 @@ static int move_tasks(struct lb_env *env) * We only want to steal up to the prescribed amount of * weighted load. */ - if (env->load_move <= 0) + if (env->imbalance <= 0) break; continue; @@ -3578,10 +3578,9 @@ static inline void update_sd_power_savings_stats(struct sched_group *group, /** * check_power_save_busiest_group - see if there is potential for some power-savings balance + * @env: load balance environment * @sds: Variable containing the statistics of the sched_domain * under consideration. - * @this_cpu: Cpu at which we're currently performing load-balancing. - * @imbalance: Variable to store the imbalance. * * Description: * Check if we have potential to perform some power-savings balance. @@ -3591,8 +3590,8 @@ static inline void update_sd_power_savings_stats(struct sched_group *group, * Returns 1 if there is potential to perform power-savings balance. * Else returns 0. */ -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) +static inline +int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) { if (!sds->power_savings_balance) return 0; @@ -3601,7 +3600,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, sds->group_leader == sds->group_min) return 0; - *imbalance = sds->min_load_per_task; + env->imbalance = sds->min_load_per_task; sds->busiest = sds->group_min; return 1; @@ -3620,8 +3619,8 @@ static inline void update_sd_power_savings_stats(struct sched_group *group, return; } -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) +static inline +int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) { return 0; } @@ -3765,25 +3764,22 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @sd: The sched_domain whose statistics are to be updated. * @group: sched_group whose statistics are to be updated. - * @this_cpu: Cpu for which load balance is currently performed. - * @idle: Idle status of this_cpu * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. * @sgs: variable to hold the statistics for this group. */ -static inline void update_sg_lb_stats(struct sched_domain *sd, - struct sched_group *group, int this_cpu, - enum cpu_idle_type idle, int load_idx, +static inline void update_sg_lb_stats(struct lb_env *env, + struct sched_group *group, int load_idx, int local_group, const struct cpumask *cpus, int *balance, struct sg_lb_stats *sgs) { unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; - int i; unsigned int balance_cpu = -1; unsigned long balance_load = ~0UL; unsigned long avg_load_per_task = 0; + int i; if (local_group) balance_cpu = group_first_cpu(group); @@ -3827,15 +3823,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * to do the newly idle load balance. */ if (local_group) { - if (idle != CPU_NEWLY_IDLE) { - if (balance_cpu != this_cpu || + if (env->idle != CPU_NEWLY_IDLE) { + if (balance_cpu != env->dst_cpu || cmpxchg(&group->balance_cpu, -1, balance_cpu) != -1) { *balance = 0; return; } - update_group_power(sd, this_cpu); + update_group_power(env->sd, env->dst_cpu); } else if (time_after_eq(jiffies, group->sgp->next_update)) - update_group_power(sd, this_cpu); + update_group_power(env->sd, env->dst_cpu); } /* Adjust by relative CPU power of the group */ @@ -3859,7 +3855,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power, SCHED_POWER_SCALE); if (!sgs->group_capacity) - sgs->group_capacity = fix_small_capacity(sd, group); + sgs->group_capacity = fix_small_capacity(env->sd, group); sgs->group_weight = group->group_weight; if (sgs->group_capacity > sgs->sum_nr_running) @@ -3877,11 +3873,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * Determine if @sg is a busier group than the previously selected * busiest group. */ -static bool update_sd_pick_busiest(struct sched_domain *sd, +static bool update_sd_pick_busiest(struct lb_env *env, struct sd_lb_stats *sds, struct sched_group *sg, - struct sg_lb_stats *sgs, - int this_cpu) + struct sg_lb_stats *sgs) { if (sgs->avg_load <= sds->max_load) return false; @@ -3897,8 +3892,8 @@ static bool update_sd_pick_busiest(struct sched_domain *sd, * numbered CPUs in the group, therefore mark all groups * higher than ourself as busy. */ - if ((sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running && - this_cpu < group_first_cpu(sg)) { + if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running && + env->dst_cpu < group_first_cpu(sg)) { if (!sds->busiest) return true; @@ -3918,28 +3913,28 @@ static bool update_sd_pick_busiest(struct sched_domain *sd, * @balance: Should we balance. * @sds: variable to hold the statistics for this sched_domain. */ -static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, - enum cpu_idle_type idle, const struct cpumask *cpus, - int *balance, struct sd_lb_stats *sds) +static inline void update_sd_lb_stats(struct lb_env *env, + const struct cpumask *cpus, + int *balance, struct sd_lb_stats *sds) { - struct sched_domain *child = sd->child; - struct sched_group *sg = sd->groups; + struct sched_domain *child = env->sd->child; + struct sched_group *sg = env->sd->groups; struct sg_lb_stats sgs; int load_idx, prefer_sibling = 0; if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; - init_sd_power_savings_stats(sd, sds, idle); - load_idx = get_sd_load_idx(sd, idle); + init_sd_power_savings_stats(env->sd, sds, env->idle); + load_idx = get_sd_load_idx(env->sd, env->idle); do { int local_group; - local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg)); + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, - local_group, cpus, balance, &sgs); + update_sg_lb_stats(env, sg, load_idx, local_group, + cpus, balance, &sgs); if (local_group && !(*balance)) return; @@ -3967,7 +3962,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, sds->this_load_per_task = sgs.sum_weighted_load; sds->this_has_capacity = sgs.group_has_capacity; sds->this_idle_cpus = sgs.idle_cpus; - } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) { + } else if (update_sd_pick_busiest(env, sds, sg, &sgs)) { sds->max_load = sgs.avg_load; sds->busiest = sg; sds->busiest_nr_running = sgs.sum_nr_running; @@ -3981,7 +3976,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, update_sd_power_savings_stats(sg, sds, local_group, &sgs); sg = sg->next; - } while (sg != sd->groups); + } while (sg != env->sd->groups); } /** @@ -4009,24 +4004,23 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, * @this_cpu: The cpu at whose sched_domain we're performing load-balance. * @imbalance: returns amount of imbalanced due to packing. */ -static int check_asym_packing(struct sched_domain *sd, - struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) +static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) { int busiest_cpu; - if (!(sd->flags & SD_ASYM_PACKING)) + if (!(env->sd->flags & SD_ASYM_PACKING)) return 0; if (!sds->busiest) return 0; busiest_cpu = group_first_cpu(sds->busiest); - if (this_cpu > busiest_cpu) + if (env->dst_cpu > busiest_cpu) return 0; - *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power, - SCHED_POWER_SCALE); + env->imbalance = DIV_ROUND_CLOSEST( + sds->max_load * sds->busiest->sgp->power, SCHED_POWER_SCALE); + return 1; } @@ -4038,8 +4032,8 @@ static int check_asym_packing(struct sched_domain *sd, * @this_cpu: The cpu at whose sched_domain we're performing load-balance. * @imbalance: Variable to store the imbalance. */ -static inline void fix_small_imbalance(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) +static inline +void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) { unsigned long tmp, pwr_now = 0, pwr_move = 0; unsigned int imbn = 2; @@ -4050,9 +4044,10 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, if (sds->busiest_load_per_task > sds->this_load_per_task) imbn = 1; - } else + } else { sds->this_load_per_task = - cpu_avg_load_per_task(this_cpu); + cpu_avg_load_per_task(env->dst_cpu); + } scaled_busy_load_per_task = sds->busiest_load_per_task * SCHED_POWER_SCALE; @@ -4060,7 +4055,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= (scaled_busy_load_per_task * imbn)) { - *imbalance = sds->busiest_load_per_task; + env->imbalance = sds->busiest_load_per_task; return; } @@ -4097,18 +4092,16 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, /* Move if we gain throughput */ if (pwr_move > pwr_now) - *imbalance = sds->busiest_load_per_task; + env->imbalance = sds->busiest_load_per_task; } /** * calculate_imbalance - Calculate the amount of imbalance present within the * groups of a given sched_domain during load balance. + * @env: load balance environment * @sds: statistics of the sched_domain whose imbalance is to be calculated. - * @this_cpu: Cpu for which currently load balance is being performed. - * @imbalance: The variable to store the imbalance. */ -static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, - unsigned long *imbalance) +static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds) { unsigned long max_pull, load_above_capacity = ~0UL; @@ -4124,8 +4117,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, * its cpu_power, while calculating max_load..) */ if (sds->max_load < sds->avg_load) { - *imbalance = 0; - return fix_small_imbalance(sds, this_cpu, imbalance); + env->imbalance = 0; + return fix_small_imbalance(env, sds); } if (!sds->group_imb) { @@ -4153,7 +4146,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, max_pull = min(sds->max_load - sds->avg_load, load_above_capacity); /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * sds->busiest->sgp->power, + env->imbalance = min(max_pull * sds->busiest->sgp->power, (sds->avg_load - sds->this_load) * sds->this->sgp->power) / SCHED_POWER_SCALE; @@ -4163,8 +4156,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, * a think about bumping its value to force at least one task to be * moved */ - if (*imbalance < sds->busiest_load_per_task) - return fix_small_imbalance(sds, this_cpu, imbalance); + if (env->imbalance < sds->busiest_load_per_task) + return fix_small_imbalance(env, sds); } @@ -4195,9 +4188,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, * put to idle by rebalancing its tasks onto our group. */ static struct sched_group * -find_busiest_group(struct sched_domain *sd, int this_cpu, - unsigned long *imbalance, enum cpu_idle_type idle, - const struct cpumask *cpus, int *balance) +find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance) { struct sd_lb_stats sds; @@ -4207,7 +4198,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * Compute the various statistics relavent for load balancing at * this level. */ - update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds); + update_sd_lb_stats(env, cpus, balance, &sds); /* * this_cpu is not the appropriate cpu to perform load balancing at @@ -4216,8 +4207,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!(*balance)) goto ret; - if ((idle == CPU_IDLE || idle == CPU_NEWLY_IDLE) && - check_asym_packing(sd, &sds, this_cpu, imbalance)) + if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && + check_asym_packing(env, &sds)) return sds.busiest; /* There is no busy sibling group to pull tasks from */ @@ -4235,7 +4226,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity && + if (env->idle == CPU_NEWLY_IDLE && sds.this_has_capacity && !sds.busiest_has_capacity) goto force_balance; @@ -4253,7 +4244,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (sds.this_load >= sds.avg_load) goto out_balanced; - if (idle == CPU_IDLE) { + if (env->idle == CPU_IDLE) { /* * This cpu is idle. If the busiest group load doesn't * have more tasks than the number of available cpu's and @@ -4268,13 +4259,13 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use * imbalance_pct to be conservative. */ - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + if (100 * sds.max_load <= env->sd->imbalance_pct * sds.this_load) goto out_balanced; } force_balance: /* Looks like there is an imbalance. Compute it */ - calculate_imbalance(&sds, this_cpu, imbalance); + calculate_imbalance(env, &sds); return sds.busiest; out_balanced: @@ -4282,20 +4273,19 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * There is no obvious imbalance. But check if we can do some balancing * to save power. */ - if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) + if (check_power_save_busiest_group(env, &sds)) return sds.busiest; ret: - *imbalance = 0; + env->imbalance = 0; return NULL; } /* * find_busiest_queue - find the busiest runqueue among the cpus in group. */ -static struct rq * -find_busiest_queue(struct sched_domain *sd, struct sched_group *group, - enum cpu_idle_type idle, unsigned long imbalance, - const struct cpumask *cpus) +static struct rq *find_busiest_queue(struct lb_env *env, + struct sched_group *group, + const struct cpumask *cpus) { struct rq *busiest = NULL, *rq; unsigned long max_load = 0; @@ -4308,7 +4298,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, unsigned long wl; if (!capacity) - capacity = fix_small_capacity(sd, group); + capacity = fix_small_capacity(env->sd, group); if (!cpumask_test_cpu(i, cpus)) continue; @@ -4320,7 +4310,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, * When comparing with imbalance, use weighted_cpuload() * which is not scaled with the cpu power. */ - if (capacity && rq->nr_running == 1 && wl > imbalance) + if (capacity && rq->nr_running == 1 && wl > env->imbalance) continue; /* @@ -4349,17 +4339,18 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, /* Working cpumask for load_balance and load_balance_newidle. */ DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); -static int need_active_balance(struct sched_domain *sd, int idle, - int busiest_cpu, int this_cpu) +static int need_active_balance(struct lb_env *env) { - if (idle == CPU_NEWLY_IDLE) { + struct sched_domain *sd = env->sd; + + if (env->idle == CPU_NEWLY_IDLE) { /* * ASYM_PACKING needs to force migrate tasks from busy but * higher numbered CPUs in order to pack all tasks in the * lowest numbered CPUs. */ - if ((sd->flags & SD_ASYM_PACKING) && busiest_cpu > this_cpu) + if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) return 1; /* @@ -4400,7 +4391,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, { int ld_moved, active_balance = 0; struct sched_group *group; - unsigned long imbalance; struct rq *busiest; unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); @@ -4418,8 +4408,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: - group = find_busiest_group(sd, this_cpu, &imbalance, idle, - cpus, balance); + group = find_busiest_group(&env, cpus, balance); if (*balance == 0) goto out_balanced; @@ -4429,7 +4418,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, goto out_balanced; } - busiest = find_busiest_queue(sd, group, idle, imbalance, cpus); + busiest = find_busiest_queue(&env, group, cpus); if (!busiest) { schedstat_inc(sd, lb_nobusyq[idle]); goto out_balanced; @@ -4437,7 +4426,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, BUG_ON(busiest == this_rq); - schedstat_add(sd, lb_imbalance[idle], imbalance); + schedstat_add(sd, lb_imbalance[idle], env.imbalance); ld_moved = 0; if (busiest->nr_running > 1) { @@ -4448,7 +4437,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, * correctly treated as an imbalance. */ env.flags |= LBF_ALL_PINNED; - env.load_move = imbalance; env.src_cpu = busiest->cpu; env.src_rq = busiest; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); @@ -4493,7 +4481,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, if (idle != CPU_NEWLY_IDLE) sd->nr_balance_failed++; - if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) { + if (need_active_balance(&env)) { raw_spin_lock_irqsave(&busiest->lock, flags); /* don't kick the active_load_balance_cpu_stop, @@ -4520,10 +4508,11 @@ static int load_balance(int this_cpu, struct rq *this_rq, } raw_spin_unlock_irqrestore(&busiest->lock, flags); - if (active_balance) + if (active_balance) { stop_one_cpu_nowait(cpu_of(busiest), active_load_balance_cpu_stop, busiest, &busiest->active_balance_work); + } /* * We've kicked active balancing, reset the failure From cb83b629bae0327cf9f44f096adc38d150ceb913 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Apr 2012 15:49:36 +0200 Subject: [PATCH 11/20] sched/numa: Rewrite the CONFIG_NUMA sched domain support The current code groups up to 16 nodes in a level and then puts an ALLNODES domain spanning the entire tree on top of that. This doesn't reflect the numa topology and esp for the smaller not-fully-connected machines out there today this might make a difference. Therefore, build a proper numa topology based on node_distance(). Since there's no fixed numa layers anymore, the static SD_NODE_INIT and SD_ALLNODES_INIT aren't usable anymore, the new code tries to construct something similar and scales some values either on the number of cpus in the domain and/or the node_distance() ratio. Signed-off-by: Peter Zijlstra Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: David Howells Cc: "David S. Miller" Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ivan Kokshaysky Cc: linux-alpha@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-sh@vger.kernel.org Cc: Matt Turner Cc: Paul Mackerras Cc: Paul Mundt Cc: Ralf Baechle Cc: Richard Henderson Cc: sparclinux@vger.kernel.org Cc: Tony Luck Cc: x86@kernel.org Cc: Dimitri Sivanich Cc: Greg Pearson Cc: KAMEZAWA Hiroyuki Cc: bob.picco@oracle.com Cc: chris.mason@oracle.com Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-r74n3n8hhuc2ynbrnp3vt954@git.kernel.org Signed-off-by: Ingo Molnar --- arch/ia64/include/asm/topology.h | 25 -- arch/mips/include/asm/mach-ip27/topology.h | 17 -- arch/powerpc/include/asm/topology.h | 36 --- arch/sh/include/asm/topology.h | 25 -- arch/sparc/include/asm/topology_64.h | 19 -- arch/tile/include/asm/topology.h | 26 -- arch/x86/include/asm/topology.h | 38 --- include/linux/topology.h | 37 --- kernel/sched/core.c | 280 ++++++++++++++------- 9 files changed, 185 insertions(+), 318 deletions(-) diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 09f646753d1a..a2496e449b75 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -70,31 +70,6 @@ void build_cpu_to_node_map(void); .nr_balance_failed = 0, \ } -/* sched_domains SD_NODE_INIT for IA64 NUMA machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 8*(min(num_online_cpus(), 32U)), \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_FORK \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 64, \ - .nr_balance_failed = 0, \ -} - #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h index 1b1a7d1632b9..b2cf641f206f 100644 --- a/arch/mips/include/asm/mach-ip27/topology.h +++ b/arch/mips/include/asm/mach-ip27/topology.h @@ -36,23 +36,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES]; #define node_distance(from, to) (__node_distances[(from)][(to)]) -/* sched_domains SD_NODE_INIT for SGI IP27 machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .flags = SD_LOAD_BALANCE | \ - SD_BALANCE_EXEC, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .nr_balance_failed = 0, \ -} - #include #endif /* _ASM_MACH_TOPOLOGY_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c97185885c6d..852ed1b384f6 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -18,12 +18,6 @@ struct device_node; */ #define RECLAIM_DISTANCE 10 -/* - * Avoid creating an extra level of balancing (SD_ALLNODES) on the largest - * POWER7 boxes which have a maximum of 32 nodes. - */ -#define SD_NODES_PER_DOMAIN 32 - #include static inline int cpu_to_node(int cpu) @@ -51,36 +45,6 @@ static inline int pcibus_to_node(struct pci_bus *bus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -/* sched_domains SD_NODE_INIT for PPC64 machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 0*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 0*SD_PREFER_LOCAL \ - | 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 = 1, \ -} - extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h index 88e734069fa6..b0a282d65f6a 100644 --- a/arch/sh/include/asm/topology.h +++ b/arch/sh/include/asm/topology.h @@ -3,31 +3,6 @@ #ifdef CONFIG_NUMA -/* sched_domains SD_NODE_INIT for sh machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_NEWIDLE \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .nr_balance_failed = 0, \ -} - #define cpu_to_node(cpu) ((void)(cpu),0) #define parent_node(node) ((void)(node),0) diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index 8b9c556d630b..1754390a426f 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -31,25 +31,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ -} - #else /* CONFIG_NUMA */ #include diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index 6fdd0c860193..7a7ce390534f 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -78,32 +78,6 @@ static inline const struct cpumask *cpumask_of_node(int node) .balance_interval = 32, \ } -/* sched_domains SD_NODE_INIT for TILE architecture */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 16, \ - .max_interval = 512, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 1, \ - .newidle_idx = 2, \ - .wake_idx = 1, \ - .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_PREFER_LOCAL \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - , \ - .last_balance = jiffies, \ - .balance_interval = 128, \ -} - /* By definition, we create nodes based on online memory. */ #define node_has_online_mem(nid) 1 diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index b9676ae37ada..095b21507b6a 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -92,44 +92,6 @@ extern void setup_node_to_cpumask_map(void); #define pcibus_to_node(bus) __pcibus_to_node(bus) -#ifdef CONFIG_X86_32 -# define SD_CACHE_NICE_TRIES 1 -# define SD_IDLE_IDX 1 -#else -# define SD_CACHE_NICE_TRIES 2 -# define SD_IDLE_IDX 2 -#endif - -/* sched_domains SD_NODE_INIT for NUMA machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = SD_CACHE_NICE_TRIES, \ - .busy_idx = 3, \ - .idle_idx = SD_IDLE_IDX, \ - .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_PREFER_LOCAL \ - | 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 = 1, \ -} - extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) diff --git a/include/linux/topology.h b/include/linux/topology.h index e26db031303b..4f59bf36f0af 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. @@ -176,48 +175,12 @@ int arch_update_cpu_topology(void); } #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); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6001e5c3b4e4..b4f2096980a3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5560,7 +5560,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (cpumask_intersects(groupmask, sched_group_cpus(group))) { + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; @@ -5898,92 +5899,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -#ifdef CONFIG_NUMA - -/** - * find_next_best_node - find the next node to include in a sched_domain - * @node: node whose sched_domain we're building - * @used_nodes: nodes already in the sched_domain - * - * Find the next node to include in a given scheduling domain. Simply - * finds the closest node not already in the @used_nodes map. - * - * Should use nodemask_t. - */ -static int find_next_best_node(int node, nodemask_t *used_nodes) -{ - int i, n, val, min_val, best_node = -1; - - min_val = INT_MAX; - - for (i = 0; i < nr_node_ids; i++) { - /* Start at @node */ - n = (node + i) % nr_node_ids; - - if (!nr_cpus_node(n)) - continue; - - /* Skip already used nodes */ - if (node_isset(n, *used_nodes)) - continue; - - /* Simple min distance search */ - val = node_distance(node, n); - - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - if (best_node != -1) - node_set(best_node, *used_nodes); - return best_node; -} - -/** - * sched_domain_node_span - get a cpumask for a node's sched_domain - * @node: node whose cpumask we're constructing - * @span: resulting cpumask - * - * Given a node, construct a good cpumask for its sched_domain to span. It - * should be one that prevents unnecessary balancing, but also spreads tasks - * out optimally. - */ -static void sched_domain_node_span(int node, struct cpumask *span) -{ - nodemask_t used_nodes; - int i; - - cpumask_clear(span); - nodes_clear(used_nodes); - - cpumask_or(span, span, cpumask_of_node(node)); - node_set(node, used_nodes); - - for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, &used_nodes); - if (next_node < 0) - break; - cpumask_or(span, span, cpumask_of_node(next_node)); - } -} - -static const struct cpumask *cpu_node_mask(int cpu) -{ - lockdep_assert_held(&sched_domains_mutex); - - sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask); - - return sched_domains_tmpmask; -} - -static const struct cpumask *cpu_allnodes_mask(int cpu) -{ - return cpu_possible_mask; -} -#endif /* CONFIG_NUMA */ - static const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); @@ -6020,6 +5935,7 @@ struct sched_domain_topology_level { sched_domain_init_f init; sched_domain_mask_f mask; int flags; + int numa_level; struct sd_data data; }; @@ -6213,10 +6129,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ } SD_INIT_FUNC(CPU) -#ifdef CONFIG_NUMA - SD_INIT_FUNC(ALLNODES) - SD_INIT_FUNC(NODE) -#endif #ifdef CONFIG_SCHED_SMT SD_INIT_FUNC(SIBLING) #endif @@ -6338,15 +6250,191 @@ static struct sched_domain_topology_level default_topology[] = { { sd_init_BOOK, cpu_book_mask, }, #endif { sd_init_CPU, cpu_cpu_mask, }, -#ifdef CONFIG_NUMA - { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, }, - { sd_init_ALLNODES, cpu_allnodes_mask, }, -#endif { NULL, }, }; static struct sched_domain_topology_level *sched_domain_topology = default_topology; +#ifdef CONFIG_NUMA + +static int sched_domains_numa_levels; +static int sched_domains_numa_scale; +static int *sched_domains_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; + +static inline unsigned long numa_scale(unsigned long x, int level) +{ + return x * sched_domains_numa_distance[level] / sched_domains_numa_scale; +} + +static inline int sd_local_flags(int level) +{ + if (sched_domains_numa_distance[level] > REMOTE_DISTANCE) + return 0; + + return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; +} + +static struct sched_domain * +sd_numa_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)]); + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 100 + numa_scale(25, level), + .cache_nice_tries = 2, + .busy_idx = 3, + .idle_idx = 2, + .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 + | 0*SD_BALANCE_WAKE + | 0*SD_WAKE_AFFINE + | 0*SD_PREFER_LOCAL + | 0*SD_SHARE_CPUPOWER + | 0*SD_POWERSAVINGS_BALANCE + | 0*SD_SHARE_PKG_RESOURCES + | 1*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | sd_local_flags(level) + , + .last_balance = jiffies, + .balance_interval = sd_weight, + }; + SD_INIT_NAME(sd, NUMA); + sd->private = &tl->data; + + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; + + return sd; +} + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_scale = curr_distance; + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + * + * XXX: could be optimized to O(n log n) by using sort() + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + int distance = node_distance(0, j); + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_nume_distance[] array includes the actual distance + * numbers. + */ + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(cpu_to_node(j), k) > + sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; default_topology[i].init; i++) + tl[i] = default_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, + .flags = SDTL_OVERLAP, + .numa_level = j, + }; + } + + sched_domain_topology = tl; +} +#else +static inline void sched_init_numa(void) +{ +} +#endif /* CONFIG_NUMA */ + static int __sdt_alloc(const struct cpumask *cpu_map) { struct sched_domain_topology_level *tl; @@ -6840,6 +6928,8 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + sched_init_numa(); + get_online_cpus(); mutex_lock(&sched_domains_mutex); init_sched_domains(cpu_active_mask); From dd7d8634e619b715a537402672d1383535ff4c54 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 00:56:20 +0200 Subject: [PATCH 12/20] sched/numa: Fix the new NUMA topology bits There's no need to convert a node number to a node number by pretending its a cpu number.. Reported-by: Yinghai Lu Reported-and-Tested-by: Greg Pearson Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-0sqhrht34phowgclj12dgk8h@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b4f2096980a3..0738036fa569 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6395,8 +6395,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; for (k = 0; k < nr_node_ids; k++) { - if (node_distance(cpu_to_node(j), k) > - sched_domains_numa_distance[i]) + if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; cpumask_or(mask, mask, cpumask_of_node(k)); From 316ad248307fba13be40f01e92a22b89457c32bc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 13:05:59 +0200 Subject: [PATCH 13/20] sched/x86: Rewrite set_cpu_sibling_map() Commit ad7687dde ("x86/numa: Check for nonsensical topologies on real hw as well") is broken in that the condition can trigger for valid setups but only changes the end result for invalid setups with no real means of discerning between those. Rewrite set_cpu_sibling_map() to make the code clearer and make sure to only warn when the check changes the end result. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-klcwahu3gx467uhfiqjyhdcs@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 112 ++++++++++++++++++++++---------------- 1 file changed, 66 insertions(+), 46 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c53d96d44ab..e84c1bbea339 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -315,70 +315,90 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } -static void __cpuinit link_thread_siblings(int cpu1, int cpu2) +static bool __cpuinit +topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) { - cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1)); - cpumask_set_cpu(cpu1, cpu_core_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); - cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2), + "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! " + "[node: %d != %d]. Ignoring dependency.\n", + cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } +#define link_mask(_m, c1, c2) \ +do { \ + cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ + cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ +} while (0) + +static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + if (c->phys_proc_id == o->phys_proc_id && + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && + c->compute_unit_id == o->compute_unit_id) + return topology_sane(c, o, "smt"); + + } else if (c->phys_proc_id == o->phys_proc_id && + c->cpu_core_id == o->cpu_core_id) { + return topology_sane(c, o, "smt"); + } + + return false; +} + +static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) + return topology_sane(c, o, "llc"); + + return false; +} + +static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + if (c->phys_proc_id == o->phys_proc_id) + return topology_sane(c, o, "mc"); + + return false; +} void __cpuinit set_cpu_sibling_map(int cpu) { - int i; + bool has_mc = boot_cpu_data.x86_max_cores > 1; + bool has_smt = smp_num_siblings > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); + struct cpuinfo_x86 *o; + int i; cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (smp_num_siblings > 1) { - for_each_cpu(i, cpu_sibling_setup_mask) { - struct cpuinfo_x86 *o = &cpu_data(i); - - if (cpu_to_node(cpu) != cpu_to_node(i)) { - WARN_ONCE(1, "sched: CPU #%d's thread-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); - continue; - } - - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { - if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) && - c->compute_unit_id == o->compute_unit_id) - link_thread_siblings(cpu, i); - } else if (c->phys_proc_id == o->phys_proc_id && - c->cpu_core_id == o->cpu_core_id) { - link_thread_siblings(cpu, i); - } - } - } else { + if (!has_smt && !has_mc) { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); - } - - cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - - if (__this_cpu_read(cpu_info.x86_max_cores) == 1) { - cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(cpu)); c->booted_cores = 1; return; } for_each_cpu(i, cpu_sibling_setup_mask) { - if (cpu_to_node(cpu) != cpu_to_node(i)) { - WARN_ONCE(1, "sched: CPU #%d's core-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); - continue; - } + o = &cpu_data(i); - if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); - } + if ((i == cpu) || (has_smt && match_smt(c, o))) + link_mask(sibling, cpu, i); + + if ((i == cpu) || (has_mc && match_llc(c, o))) + link_mask(llc_shared, cpu, i); + + if ((i == cpu) || (has_mc && match_mc(c, o))) { + link_mask(core, cpu, i); - if (c->phys_proc_id == cpu_data(i).phys_proc_id) { - cpumask_set_cpu(i, cpu_core_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(i)); /* * Does this new cpu bringup a new core? */ From 04f733b4afac5dc93ae9b0a8703c60b87def491e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 00:12:02 +0200 Subject: [PATCH 14/20] sched/fair: Revert sched-domain iteration breakage Patches c22402a2f ("sched/fair: Let minimally loaded cpu balance the group") and 0ce90475 ("sched/fair: Add some serialization to the sched_domain load-balance walk") are horribly broken so revert them. The problem is that while it sounds good to have the minimally loaded cpu do the pulling of more load, the way we walk the domains there is absolutely no guarantee this cpu will actually get to the domain. In fact its very likely it wont. Therefore the higher up the tree we get, the less likely it is we'll balance at all. The first of mask always walks up, while sucky in that it accumulates load on the first cpu and needs extra passes to spread it out at least guarantees a cpu gets up that far and load-balancing happens at all. Since its now always the first and idle cpus should always be able to balance so they get a task as fast as possible we can also do away with the added serialization. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-rpuhs5s56aiv1aw7khv9zkw6@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/sched/core.c | 2 -- kernel/sched/fair.c | 19 +++++++------------ 3 files changed, 7 insertions(+), 15 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 3cbfb55bde25..4a559bf0622f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -927,7 +927,6 @@ struct sched_group_power { struct sched_group { struct sched_group *next; /* Must be a circular list */ atomic_t ref; - int balance_cpu; unsigned int group_weight; struct sched_group_power *sgp; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0738036fa569..24922b7ff567 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5976,7 +5976,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span)); atomic_inc(&sg->sgp->ref); - sg->balance_cpu = -1; if (cpumask_test_cpu(cpu, sg_span)) groups = sg; @@ -6052,7 +6051,6 @@ build_sched_groups(struct sched_domain *sd, int cpu) cpumask_clear(sched_group_cpus(sg)); sg->sgp->power = 0; - sg->balance_cpu = -1; for_each_cpu(j, span) { if (get_group(j, sdd, NULL) != group) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9bd3366dbb1c..a259a614b394 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3776,8 +3776,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, int *balance, struct sg_lb_stats *sgs) { unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; - unsigned int balance_cpu = -1; - unsigned long balance_load = ~0UL; + unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long avg_load_per_task = 0; int i; @@ -3794,11 +3793,12 @@ static inline void update_sg_lb_stats(struct lb_env *env, /* Bias balancing toward cpus of our domain */ if (local_group) { - load = target_load(i, load_idx); - if (load < balance_load || idle_cpu(i)) { - balance_load = load; + if (idle_cpu(i) && !first_idle_cpu) { + first_idle_cpu = 1; balance_cpu = i; } + + load = target_load(i, load_idx); } else { load = source_load(i, load_idx); if (load > max_cpu_load) { @@ -3824,8 +3824,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, */ if (local_group) { if (env->idle != CPU_NEWLY_IDLE) { - if (balance_cpu != env->dst_cpu || - cmpxchg(&group->balance_cpu, -1, balance_cpu) != -1) { + if (balance_cpu != env->dst_cpu) { *balance = 0; return; } @@ -4919,7 +4918,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) int balance = 1; struct rq *rq = cpu_rq(cpu); unsigned long interval; - struct sched_domain *sd, *last = NULL; + struct sched_domain *sd; /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; @@ -4929,7 +4928,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) rcu_read_lock(); for_each_domain(cpu, sd) { - last = sd; if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -4974,9 +4972,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (!balance) break; } - for (sd = last; sd; sd = sd->child) - (void)cmpxchg(&sd->groups->balance_cpu, cpu, -1); - rcu_read_unlock(); /* From 870a0bb5d636156502769233d02a0d5791d4366a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 00:26:27 +0200 Subject: [PATCH 15/20] sched/numa: Don't scale the imbalance It's far too easy to get ridiculously large imbalance pct when you scale it like that. Use a fixed 125% for now. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-zsriaft1dv7hhboyrpvqjy6s@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 24922b7ff567..6883d998dc38 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6261,11 +6261,6 @@ static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; static int sched_domains_curr_level; -static inline unsigned long numa_scale(unsigned long x, int level) -{ - return x * sched_domains_numa_distance[level] / sched_domains_numa_scale; -} - static inline int sd_local_flags(int level) { if (sched_domains_numa_distance[level] > REMOTE_DISTANCE) @@ -6286,7 +6281,7 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) .min_interval = sd_weight, .max_interval = 2*sd_weight, .busy_factor = 32, - .imbalance_pct = 100 + numa_scale(25, level), + .imbalance_pct = 125, .cache_nice_tries = 2, .busy_idx = 3, .idle_idx = 2, From 556061b00c9f2fd6a5524b6bde823ef12f299ecf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 17:31:26 +0200 Subject: [PATCH 16/20] sched/nohz: Fix rq->cpu_load[] calculations While investigating why the load-balancer did funny I found that the rq->cpu_load[] tables were completely screwy.. a bit more digging revealed that the updates that got through were missing ticks followed by a catchup of 2 ticks. The catchup assumes the cpu was idle during that time (since only nohz can cause missed ticks and the machine is idle etc..) this means that esp. the higher indices were significantly lower than they ought to be. The reason for this is that its not correct to compare against jiffies on every jiffy on any other cpu than the cpu that updates jiffies. This patch cludges around it by only doing the catch-up stuff from nohz_idle_balance() and doing the regular stuff unconditionally from the tick. Signed-off-by: Peter Zijlstra Cc: pjt@google.com Cc: Venkatesh Pallipadi Link: http://lkml.kernel.org/n/tip-tp4kj18xdd5aj4vvj0qg55s2@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 53 ++++++++++++++++++++++++++++++++------------ kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 2 +- 3 files changed, 41 insertions(+), 16 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6883d998dc38..860fddfb7bb7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -692,8 +692,6 @@ int tg_nop(struct task_group *tg, void *data) } #endif -void update_cpu_load(struct rq *this_rq); - static void set_load_weight(struct task_struct *p) { int prio = p->static_prio - MAX_RT_PRIO; @@ -2486,22 +2484,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) * scheduler tick (TICK_NSEC). With tickless idle this will not be called * every tick. We fix it up based on jiffies. */ -void update_cpu_load(struct rq *this_rq) +static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) { - unsigned long this_load = this_rq->load.weight; - unsigned long curr_jiffies = jiffies; - unsigned long pending_updates; int i, scale; this_rq->nr_load_updates++; - /* Avoid repeated calls on same jiffy, when moving in and out of idle */ - if (curr_jiffies == this_rq->last_load_update_tick) - return; - - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - /* Update our load: */ this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { @@ -2526,9 +2515,45 @@ void update_cpu_load(struct rq *this_rq) sched_avg_update(this_rq); } +/* + * Called from nohz_idle_balance() to update the load ratings before doing the + * idle balance. + */ +void update_idle_cpu_load(struct rq *this_rq) +{ + unsigned long curr_jiffies = jiffies; + unsigned long load = this_rq->load.weight; + unsigned long pending_updates; + + /* + * Bloody broken means of dealing with nohz, but better than nothing.. + * jiffies is updated by one cpu, another cpu can drift wrt the jiffy + * update and see 0 difference the one time and 2 the next, even though + * we ticked at roughtly the same rate. + * + * Hence we only use this from nohz_idle_balance() and skip this + * nonsense when called from the scheduler_tick() since that's + * guaranteed a stable rate. + */ + if (load || curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + + __update_cpu_load(this_rq, load, pending_updates); +} + +/* + * Called from scheduler_tick() + */ static void update_cpu_load_active(struct rq *this_rq) { - update_cpu_load(this_rq); + /* + * See the mess in update_idle_cpu_load(). + */ + this_rq->last_load_update_tick = jiffies; + __update_cpu_load(this_rq, this_rq->load.weight, 1); calc_load_account_active(this_rq); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a259a614b394..124e6b6999a7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5012,7 +5012,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) raw_spin_lock_irq(&this_rq->lock); update_rq_clock(this_rq); - update_cpu_load(this_rq); + update_idle_cpu_load(this_rq); raw_spin_unlock_irq(&this_rq->lock); rebalance_domains(balance_cpu, CPU_IDLE); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7282e7b5f4c7..ba9dccfd24ce 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -876,7 +876,7 @@ extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); -extern void update_cpu_load(struct rq *this_rq); +extern void update_idle_cpu_load(struct rq *this_rq); #ifdef CONFIG_CGROUP_CPUACCT #include From e44bc5c5d00ee9b56dd87db47ed827d52948b9fa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 00:22:12 +0200 Subject: [PATCH 17/20] sched/fair: Improve the ->group_imb logic Group imbalance is meant to deal with situations where affinity masks and sched domains don't align well, such as 3 cpus from one group and 6 from another. In this case the domain based balancer will want to put an equal amount of tasks on each side even though they don't have equal cpus. Currently group_imb is set whenever two cpus of a group have a weight difference of at least one avg task and the heaviest cpu has at least two tasks. A group with imbalance set will always be picked as busiest and a balance pass will be forced. The problem is that even if there are no affinity masks this stuff can trigger and cause weird balancing decisions, eg. the observed behaviour was that of 6 cpus, 5 had 2 and 1 had 3 tasks, due to the difference of 1 avg load (they all had the same weight) and nr_running being >1 the group_imbalance logic triggered and did the weird thing of pulling more load instead of trying to move the 1 excess task to the other domain of 6 cpus that had 5 cpu with 2 tasks and 1 cpu with 1 task. Curb the group_imbalance stuff by making the nr_running condition weaker by also tracking the min_nr_running and using the difference in nr_running over the set instead of the absolute max nr_running. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-9s7dedozxo8kjsb9kqlrukkf@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 124e6b6999a7..0b42f4487329 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3775,7 +3775,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, int local_group, const struct cpumask *cpus, int *balance, struct sg_lb_stats *sgs) { - unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; + unsigned long nr_running, max_nr_running, min_nr_running; + unsigned long load, max_cpu_load, min_cpu_load; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long avg_load_per_task = 0; int i; @@ -3787,10 +3788,13 @@ static inline void update_sg_lb_stats(struct lb_env *env, max_cpu_load = 0; min_cpu_load = ~0UL; max_nr_running = 0; + min_nr_running = ~0UL; for_each_cpu_and(i, sched_group_cpus(group), cpus) { struct rq *rq = cpu_rq(i); + nr_running = rq->nr_running; + /* Bias balancing toward cpus of our domain */ if (local_group) { if (idle_cpu(i) && !first_idle_cpu) { @@ -3801,16 +3805,19 @@ static inline void update_sg_lb_stats(struct lb_env *env, load = target_load(i, load_idx); } else { load = source_load(i, load_idx); - if (load > max_cpu_load) { + if (load > max_cpu_load) max_cpu_load = load; - max_nr_running = rq->nr_running; - } if (min_cpu_load > load) min_cpu_load = load; + + if (nr_running > max_nr_running) + max_nr_running = nr_running; + if (min_nr_running > nr_running) + min_nr_running = nr_running; } sgs->group_load += load; - sgs->sum_nr_running += rq->nr_running; + sgs->sum_nr_running += nr_running; sgs->sum_weighted_load += weighted_cpuload(i); if (idle_cpu(i)) sgs->idle_cpus++; @@ -3848,7 +3855,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (sgs->sum_nr_running) avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; - if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1) + if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && + (max_nr_running - min_nr_running) > 1) sgs->group_imb = 1; sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power, From 13e099d2f77e1da3e4046860c48d956588633613 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 May 2012 14:34:00 +0200 Subject: [PATCH 18/20] sched/debug: Fix printing large integers on 32-bit platforms Some numbers like nr_running and nr_uninterruptible are fundamentally unsigned since its impossible to have a negative amount of tasks, yet we still print them as signed to easily recognise the underflow condition. rq->nr_uninterruptible has 'special' accounting and can in fact very easily become negative on a per-cpu basis. It was noted that since the P() macro assumes things are long long and the promotion of unsigned 'int/long' to long long on 32bit doesn't sign extend we print silly large numbers instead of the easier to read signed numbers. Therefore extend the P() macro to not require the sign extention. Reported-by: Diwakar Tundlam Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-gk5tm8t2n4ix2vkpns42uqqp@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 31e4f61a1629..6f79596e0ea9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -260,8 +260,14 @@ static void print_cpu(struct seq_file *m, int cpu) SEQ_printf(m, "\ncpu#%d\n", cpu); #endif -#define P(x) \ - SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x)) +#define P(x) \ +do { \ + if (sizeof(rq->x) == 4) \ + SEQ_printf(m, " .%-30s: %ld\n", #x, (long)(rq->x)); \ + else \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x));\ +} while (0) + #define PN(x) \ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) From 8e7fbcbc22c12414bcc9dfdd683637f58fb32759 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 9 Jan 2012 11:28:35 +0100 Subject: [PATCH 19/20] sched: Remove stale power aware scheduling remnants and dysfunctional knobs It's been broken forever (i.e. it's not scheduling in a power aware fashion), as reported by Suresh and others sending patches, and nobody cares enough to fix it properly ... so remove it to make space free for something better. There's various problems with the code as it stands today, first and foremost the user interface which is bound to topology levels and has multiple values per level. This results in a state explosion which the administrator or distro needs to master and almost nobody does. Furthermore large configuration state spaces aren't good, it means the thing doesn't just work right because it's either under so many impossibe to meet constraints, or even if there's an achievable state workloads have to be aware of it precisely and can never meet it for dynamic workloads. So pushing this kind of decision to user-space was a bad idea even with a single knob - it's exponentially worse with knobs on every node of the topology. There is a proposal to replace the user interface with a single 3 state knob: sched_balance_policy := { performance, power, auto } where 'auto' would be the preferred default which looks at things like Battery/AC mode and possible cpufreq state or whatever the hw exposes to show us power use expectations - but there's been no progress on it in the past many months. Aside from that, the actual implementation of the various knobs is known to be broken. There have been sporadic attempts at fixing things but these always stop short of reaching a mergable state. Therefore this wholesale removal with the hopes of spurring people who care to come forward once again and work on a coherent replacement. Signed-off-by: Peter Zijlstra Cc: Suresh Siddha Cc: Arjan van de Ven Cc: Vincent Guittot Cc: Vaidyanathan Srinivasan Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1326104915.2442.53.camel@twins Signed-off-by: Ingo Molnar --- .../ABI/testing/sysfs-devices-system-cpu | 25 -- Documentation/scheduler/sched-domains.txt | 4 - arch/x86/kernel/smpboot.c | 3 +- drivers/base/cpu.c | 4 - include/linux/cpu.h | 2 - include/linux/sched.h | 47 --- include/linux/topology.h | 5 - kernel/sched/core.c | 94 ------ kernel/sched/fair.c | 275 +----------------- tools/power/cpupower/man/cpupower-set.1 | 9 - tools/power/cpupower/utils/helpers/sysfs.c | 35 +-- 11 files changed, 5 insertions(+), 498 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index e7be75b96e4b..5dab36448b44 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -9,31 +9,6 @@ Description: /sys/devices/system/cpu/cpu#/ -What: /sys/devices/system/cpu/sched_mc_power_savings - /sys/devices/system/cpu/sched_smt_power_savings -Date: June 2006 -Contact: Linux kernel mailing list -Description: Discover and adjust the kernel's multi-core scheduler support. - - Possible values are: - - 0 - No power saving load balance (default value) - 1 - Fill one thread/core/package first for long running threads - 2 - Also bias task wakeups to semi-idle cpu package for power - savings - - sched_mc_power_savings is dependent upon SCHED_MC, which is - itself architecture dependent. - - sched_smt_power_savings is dependent upon SCHED_SMT, which - is itself architecture dependent. - - The two files are independent of each other. It is possible - that one file may be present without the other. - - Introduced by git commit 5c45bf27. - - What: /sys/devices/system/cpu/kernel_max /sys/devices/system/cpu/offline /sys/devices/system/cpu/online diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt index b7ee379b651b..443f0c76bab4 100644 --- a/Documentation/scheduler/sched-domains.txt +++ b/Documentation/scheduler/sched-domains.txt @@ -61,10 +61,6 @@ The implementor should read comments in include/linux/sched.h: struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of the specifics and what to tune. -For SMT, the architecture must define CONFIG_SCHED_SMT and provide a -cpumask_t cpu_sibling_map[NR_CPUS], where cpu_sibling_map[i] is the mask of -all "i"'s siblings as well as "i" itself. - Architectures may retain the regular override the default SD_*_INIT flags while using the generic domain builder in kernel/sched.c if they wish to retain the traditional SMT->SMP->NUMA topology (or some subset of that). This diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e84c1bbea339..256c20cc5e96 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -429,8 +429,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ - if ((sched_mc_power_savings || sched_smt_power_savings) && - !(cpu_has(c, X86_FEATURE_AMD_DCM))) + if (!(cpu_has(c, X86_FEATURE_AMD_DCM))) return cpu_core_mask(cpu); else return cpu_llc_shared_mask(cpu); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index adf937bf4091..63452943abd1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -330,8 +330,4 @@ void __init cpu_dev_init(void) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - sched_create_sysfs_power_savings_entries(cpu_subsys.dev_root); -#endif } 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 4a559bf0622f..3d644809c9db 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; /* diff --git a/include/linux/topology.h b/include/linux/topology.h index 4f59bf36f0af..09558d1daacd 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -98,7 +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 \ @@ -134,8 +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, \ @@ -167,8 +164,6 @@ 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, \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bd314d7cd9f8..24ca677b5457 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5929,8 +5929,6 @@ static const struct cpumask *cpu_cpu_mask(int cpu) return cpumask_of_node(cpu_to_node(cpu)); } -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; - struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; @@ -6322,7 +6320,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_WAKE_AFFINE | 0*SD_PREFER_LOCAL | 0*SD_SHARE_CPUPOWER - | 0*SD_POWERSAVINGS_BALANCE | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE | 0*SD_PREFER_SIBLING @@ -6819,97 +6816,6 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], mutex_unlock(&sched_domains_mutex); } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void reinit_sched_domains(void) -{ - get_online_cpus(); - - /* Destroy domains first to force the rebuild */ - partition_sched_domains(0, NULL, NULL); - - rebuild_sched_domains(); - put_online_cpus(); -} - -static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -{ - unsigned int level = 0; - - if (sscanf(buf, "%u", &level) != 1) - return -EINVAL; - - /* - * level is always be positive so don't check for - * level < POWERSAVINGS_BALANCE_NONE which is 0 - * What happens on 0 or 1 byte write, - * need to check for count as well? - */ - - if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) - return -EINVAL; - - if (smt) - sched_smt_power_savings = level; - else - sched_mc_power_savings = level; - - reinit_sched_domains(); - - return count; -} - -#ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_mc_power_savings); -} -static ssize_t sched_mc_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 0); -} -static DEVICE_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); -#endif - -#ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_smt_power_savings); -} -static ssize_t sched_smt_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 1); -} -static DEVICE_ATTR(sched_smt_power_savings, 0644, - sched_smt_power_savings_show, - sched_smt_power_savings_store); -#endif - -int __init sched_create_sysfs_power_savings_entries(struct device *dev) -{ - int err = 0; - -#ifdef CONFIG_SCHED_SMT - if (smt_capable()) - err = device_create_file(dev, &dev_attr_sched_smt_power_savings); -#endif -#ifdef CONFIG_SCHED_MC - if (!err && mc_capable()) - err = device_create_file(dev, &dev_attr_sched_mc_power_savings); -#endif - return err; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0b42f4487329..940e6d17cf96 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2721,7 +2721,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) * If power savings logic is enabled for a domain, see if we * are not overloaded, if so, don't balance wider. */ - if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) { + if (tmp->flags & (SD_PREFER_LOCAL)) { unsigned long power = 0; unsigned long nr_running = 0; unsigned long capacity; @@ -2734,9 +2734,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - nr_running /= 2; - if (nr_running < capacity) want_sd = 0; } @@ -3435,14 +3432,6 @@ struct sd_lb_stats { unsigned int busiest_group_weight; int group_imb; /* Is there imbalance in this sd */ -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance; /* Is powersave balance needed for this sd */ - struct sched_group *group_min; /* Least loaded group in sd */ - struct sched_group *group_leader; /* Group which relieves group_min */ - unsigned long min_load_per_task; /* load_per_task in group_min */ - unsigned long leader_nr_running; /* Nr running of group_leader */ - unsigned long min_nr_running; /* Nr running of group_min */ -#endif }; /* @@ -3486,147 +3475,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * init_sd_power_savings_stats - Initialize power savings statistics for - * the given sched_domain, during load balancing. - * - * @sd: Sched domain whose power-savings statistics are to be initialized. - * @sds: Variable containing the statistics for sd. - * @idle: Idle status of the CPU at which we're performing load-balancing. - */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - sds->power_savings_balance = 0; - else { - sds->power_savings_balance = 1; - sds->min_nr_running = ULONG_MAX; - sds->leader_nr_running = 0; - } -} - -/** - * update_sd_power_savings_stats - Update the power saving stats for a - * sched_domain while performing load balancing. - * - * @group: sched_group belonging to the sched_domain under consideration. - * @sds: Variable containing the statistics of the sched_domain - * @local_group: Does group contain the CPU for which we're performing - * load balancing ? - * @sgs: Variable containing the statistics of the group. - */ -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - - if (!sds->power_savings_balance) - return; - - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (sds->this_nr_running >= sgs->group_capacity || - !sds->this_nr_running)) - sds->power_savings_balance = 0; - - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!sds->power_savings_balance || - sgs->sum_nr_running >= sgs->group_capacity || - !sgs->sum_nr_running) - return; - - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sgs->sum_nr_running < sds->min_nr_running) || - (sgs->sum_nr_running == sds->min_nr_running && - group_first_cpu(group) > group_first_cpu(sds->group_min))) { - sds->group_min = group; - sds->min_nr_running = sgs->sum_nr_running; - sds->min_load_per_task = sgs->sum_weighted_load / - sgs->sum_nr_running; - } - - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sgs->sum_nr_running + 1 > sgs->group_capacity) - return; - - if (sgs->sum_nr_running > sds->leader_nr_running || - (sgs->sum_nr_running == sds->leader_nr_running && - group_first_cpu(group) < group_first_cpu(sds->group_leader))) { - sds->group_leader = group; - sds->leader_nr_running = sgs->sum_nr_running; - } -} - -/** - * check_power_save_busiest_group - see if there is potential for some power-savings balance - * @env: load balance environment - * @sds: Variable containing the statistics of the sched_domain - * under consideration. - * - * Description: - * Check if we have potential to perform some power-savings balance. - * If yes, set the busiest group to be the least loaded group in the - * sched_domain, so that it's CPUs can be put to idle. - * - * Returns 1 if there is potential to perform power-savings balance. - * Else returns 0. - */ -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - if (!sds->power_savings_balance) - return 0; - - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - env->imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - return 1; - -} -#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - return; -} - -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - return; -} - -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - return 0; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - - unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; @@ -3932,7 +3780,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; - init_sd_power_savings_stats(env->sd, sds, env->idle); load_idx = get_sd_load_idx(env->sd, env->idle); do { @@ -3981,7 +3828,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, sds->group_imb = sgs.group_imb; } - update_sd_power_savings_stats(sg, sds, local_group, &sgs); sg = sg->next; } while (sg != env->sd->groups); } @@ -4276,12 +4122,6 @@ find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance) return sds.busiest; out_balanced: - /* - * There is no obvious imbalance. But check if we can do some balancing - * to save power. - */ - if (check_power_save_busiest_group(env, &sds)) - return sds.busiest; ret: env->imbalance = 0; return NULL; @@ -4359,28 +4199,6 @@ static int need_active_balance(struct lb_env *env) */ if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) return 1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return 0; } return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); @@ -4700,104 +4518,15 @@ static struct { unsigned long next_balance; /* in jiffy units */ } nohz ____cacheline_aligned; -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * lowest_flag_domain - Return lowest sched_domain containing flag. - * @cpu: The cpu whose lowest level of sched domain is to - * be returned. - * @flag: The flag to check for the lowest sched_domain - * for the given cpu. - * - * Returns the lowest sched_domain of a cpu which contains the given flag. - */ -static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) -{ - struct sched_domain *sd; - - for_each_domain(cpu, sd) - if (sd->flags & flag) - break; - - return sd; -} - -/** - * for_each_flag_domain - Iterates over sched_domains containing the flag. - * @cpu: The cpu whose domains we're iterating over. - * @sd: variable holding the value of the power_savings_sd - * for cpu. - * @flag: The flag to filter the sched_domains to be iterated. - * - * Iterates over all the scheduler domains for a given cpu that has the 'flag' - * set, starting from the lowest sched_domain to the highest. - */ -#define for_each_flag_domain(cpu, sd, flag) \ - for (sd = lowest_flag_domain(cpu, flag); \ - (sd && (sd->flags & flag)); sd = sd->parent) - -/** - * find_new_ilb - Finds the optimum idle load balancer for nomination. - * @cpu: The cpu which is nominating a new idle_load_balancer. - * - * Returns: Returns the id of the idle load balancer if it exists, - * Else, returns >= nr_cpu_ids. - * - * This algorithm picks the idle load balancer such that it belongs to a - * semi-idle powersavings sched_domain. The idea is to try and avoid - * completely idle packages/cores just for the purpose of idle load balancing - * when there are other idle cpu's which are better suited for that job. - */ -static int find_new_ilb(int cpu) +static inline int find_new_ilb(int call_cpu) { int ilb = cpumask_first(nohz.idle_cpus_mask); - struct sched_group *ilbg; - struct sched_domain *sd; - /* - * Have idle load balancer selection from semi-idle packages only - * when power-aware load balancing is enabled - */ - if (!(sched_smt_power_savings || sched_mc_power_savings)) - goto out_done; - - /* - * Optimize for the case when we have no idle CPUs or only one - * idle CPU. Don't walk the sched_domain hierarchy in such cases - */ - if (cpumask_weight(nohz.idle_cpus_mask) < 2) - goto out_done; - - rcu_read_lock(); - for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { - ilbg = sd->groups; - - do { - if (ilbg->group_weight != - atomic_read(&ilbg->sgp->nr_busy_cpus)) { - ilb = cpumask_first_and(nohz.idle_cpus_mask, - sched_group_cpus(ilbg)); - goto unlock; - } - - ilbg = ilbg->next; - - } while (ilbg != sd->groups); - } -unlock: - rcu_read_unlock(); - -out_done: if (ilb < nr_cpu_ids && idle_cpu(ilb)) return ilb; return nr_cpu_ids; } -#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ -static inline int find_new_ilb(int call_cpu) -{ - return nr_cpu_ids; -} -#endif /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick the diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1 index c4954a9fe4e7..9dbd536518ab 100644 --- a/tools/power/cpupower/man/cpupower-set.1 +++ b/tools/power/cpupower/man/cpupower-set.1 @@ -85,15 +85,6 @@ Possible values are: savings .RE -sched_mc_power_savings is dependent upon SCHED_MC, which is -itself architecture dependent. - -sched_smt_power_savings is dependent upon SCHED_SMT, which -is itself architecture dependent. - -The two files are independent of each other. It is possible -that one file may be present without the other. - .SH "SEE ALSO" cpupower-info(1), cpupower-monitor(1), powertop(1) .PP diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c index c6343024a611..96e28c124b5c 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -362,22 +362,7 @@ char *sysfs_get_cpuidle_driver(void) */ int sysfs_get_sched(const char *smt_mc) { - unsigned long value; - char linebuf[MAX_LINE_LEN]; - char *endp; - char path[SYSFS_PATH_MAX]; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - value = strtoul(linebuf, &endp, 0); - if (endp == linebuf || errno == ERANGE) - return -1; - return value; + return -ENODEV; } /* @@ -388,21 +373,5 @@ int sysfs_get_sched(const char *smt_mc) */ int sysfs_set_sched(const char *smt_mc, int val) { - char linebuf[MAX_LINE_LEN]; - char path[SYSFS_PATH_MAX]; - struct stat statbuf; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - sprintf(linebuf, "%d", val); - - if (stat(path, &statbuf) != 0) - return -ENODEV; - - if (sysfs_write_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - return 0; + return -ENODEV; } From 1c2927f18576d65631d8e0ddd19e1d023183222e Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 10 May 2012 16:20:04 +0400 Subject: [PATCH 20/20] sched: Taint kernel with TAINT_WARN after sleep-in-atomic bug Usually sleep-in-atomic bugs are followed by dozens other warnings. This patch should help to figure out original source of problem. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20120510122004.4873.12726.stgit@zurg Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 24ca677b5457..ab9745f7e115 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3138,6 +3138,7 @@ static noinline void __schedule_bug(struct task_struct *prev) if (irqs_disabled()) print_irqtrace_events(prev); dump_stack(); + add_taint(TAINT_WARN); } /*