diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 10:31:44 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 10:31:44 -0700 |
commit | 2ba68940c893c8f0bfc8573c041254251bb6aeab (patch) | |
tree | fa83ebb01d32abd98123fa28f9f6f0b3eaeee25d | |
parent | 9c2b957db1772ebf942ae7a9346b14eba6c8ca66 (diff) | |
parent | 600e145882802d6ccbfe2c4aea243d97caeb91a9 (diff) |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes for v3.4 from Ingo Molnar
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
printk: Make it compile with !CONFIG_PRINTK
sched/x86: Fix overflow in cyc2ns_offset
sched: Fix nohz load accounting -- again!
sched: Update yield() docs
printk/sched: Introduce special printk_sched() for those awkward moments
sched/nohz: Correctly initialize 'next_balance' in 'nohz' idle balancer
sched: Cleanup cpu_active madness
sched: Fix load-balance wreckage
sched: Clean up parameter passing of proc_sched_autogroup_set_nice()
sched: Ditch per cgroup task lists for load-balancing
sched: Rename load-balancing fields
sched: Move load-balancing arguments into helper struct
sched/rt: Do not submit new work when PI-blocked
sched/rt: Prevent idle task boosting
sched/wait: Add __wake_up_all_locked() API
sched/rt: Document scheduler related skip-resched-check sites
sched/rt: Use schedule_preempt_disabled()
sched/rt: Add schedule_preempt_disabled()
sched/rt: Do not throttle when PI boosting
sched/rt: Keep period timer ticking when rt throttling is active
...
52 files changed, 462 insertions, 462 deletions
diff --git a/Documentation/scheduler/sched-stats.txt b/Documentation/scheduler/sched-stats.txt index 1cd5d51bc761..8259b34a66ae 100644 --- a/Documentation/scheduler/sched-stats.txt +++ b/Documentation/scheduler/sched-stats.txt @@ -38,7 +38,8 @@ First field is a sched_yield() statistic: 1) # of times sched_yield() was called Next three are schedule() statistics: - 2) # of times we switched to the expired queue and reused it + 2) This field is a legacy array expiration count field used in the O(1) + scheduler. We kept it for ABI compatibility, but it is always set to zero. 3) # of times schedule() was called 4) # of times schedule() left the processor idle diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 971d65c253a9..c2ae3cd331fe 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -239,9 +239,7 @@ void cpu_idle(void) leds_event(led_idle_end); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index cdeb727527d3..d616ed51e7a7 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -295,13 +295,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void) */ percpu_timer_setup(); - while (!cpu_active(cpu)) - cpu_relax(); - - /* - * cpu_active bit is set, so it's safe to enalbe interrupts - * now. - */ local_irq_enable(); local_fiq_enable(); diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index ea3395750324..92c5af98a6f7 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -40,9 +40,7 @@ void cpu_idle(void) cpu_idle_sleep(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 8dd0416673cb..a80a643f3691 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -94,9 +94,7 @@ void cpu_idle(void) idle(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index aa585e4e979e..d8f50ff6fadd 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -115,9 +115,7 @@ void cpu_idle (void) idle = default_idle; idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 3901df1213c0..29cc49783787 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -92,9 +92,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 933bd388efb2..1a173b35f475 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -81,9 +81,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index c871a2cffaef..0123c63e9a3a 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -179,8 +179,6 @@ void __cpuinit start_secondary(void) printk(KERN_INFO "%s cpu %d\n", __func__, current_thread_info()->cpu); set_cpu_online(cpu, true); - while (!cpumask_test_cpu(cpu, cpu_active_mask)) - cpu_relax(); local_irq_enable(); cpu_idle(); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6d33c5cc94f0..9dc52b63fc87 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -330,9 +330,7 @@ cpu_idle (void) normal_xtp(); #endif } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) play_dead(); diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 422bea9f1dbc..3a4a32b27208 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -90,9 +90,7 @@ void cpu_idle (void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c index 099283ee1a8f..fe4186b5fc32 100644 --- a/arch/m68k/kernel/process_mm.c +++ b/arch/m68k/kernel/process_mm.c @@ -78,9 +78,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c index 5e1078cabe0e..f7fe6c348595 100644 --- a/arch/m68k/kernel/process_no.c +++ b/arch/m68k/kernel/process_no.c @@ -73,9 +73,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 7dcb5bfffb75..9155f7d92669 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -110,9 +110,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 7955409051c4..61f1cb45a1d5 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -80,9 +80,7 @@ void __noreturn cpu_idle(void) #endif rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 28eec3102535..cac401d37f75 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -123,9 +123,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 62c60b87d039..d4b94b395c16 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -71,9 +71,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 0a48bf5db6c8..c97fc60c790c 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -101,11 +101,11 @@ void cpu_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - if (cpu_should_die()) + if (cpu_should_die()) { + sched_preempt_enable_no_resched(); cpu_die(); - schedule(); - preempt_disable(); + } + schedule_preempt_disabled(); } } diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 8fc62586a973..a5fbf4cb6329 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -584,9 +584,7 @@ static void iseries_shared_idle(void) if (hvlpevent_is_pending()) process_iSeries_events(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -615,9 +613,7 @@ static void iseries_dedicated_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index e795933eb2cb..7618085b4164 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -97,9 +97,7 @@ void cpu_idle(void) tick_nohz_idle_exit(); if (test_thread_flag(TIF_MCCK_PENDING)) s390_handle_mcck(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 2398ce6b15ae..b0e28c47ab83 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -550,12 +550,6 @@ int __cpuinit start_secondary(void *cpuvoid) S390_lowcore.restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; __ctl_set_bit(0, 28); /* Enable lowcore protection */ - /* - * Wait until the cpu which brought this one up marked it - * active before enabling interrupts. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); local_irq_enable(); /* cpu_idle will call schedule for us */ cpu_idle(); diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 25d08030a883..2707023c7563 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -53,9 +53,7 @@ void __noreturn cpu_idle(void) while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 406508d4ce74..7e4892826563 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -114,9 +114,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index f793742eec2b..935fdbcd88c2 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } @@ -138,9 +136,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 39d8b05201a2..06b5b5fc20c7 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -104,15 +104,13 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) { + sched_preempt_enable_no_resched(); cpu_play_dead(); + } #endif - - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 4c1ac6e5347a..6ae495ef2b99 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -108,9 +108,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 431793e5d484..34baa0eb5d0c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { - unsigned long long quot; - unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - quot = (cyc >> CYC2NS_SCALE_FACTOR); - rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); - ns += quot * per_cpu(cyc2ns, cpu) + - ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c08d1ff12b7c..49888fefe794 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -119,9 +119,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cfa5c90c01db..e34257c70c28 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -156,9 +156,7 @@ void cpu_idle(void) } tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 66d250c00d11..58f78165d308 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -291,19 +291,6 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); - /* - * Wait until the cpu which brought this one up marked it - * online before enabling interrupts. If we don't do that then - * we can end up waking up the softirq thread before this cpu - * reached the active state, which makes the scheduler unhappy - * and schedule the softirq thread on the wrong cpu. This is - * only observable with forced threaded interrupts, but in - * theory it could also happen w/o them. It's just way harder - * to achieve. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); - /* enable local interrupts */ local_irq_enable(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a62c201c97ec..183c5925a9fe 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -620,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 47041e7c088c..2c9004770c4e 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) platform_idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 1366a89d8e66..467c8de88642 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -8,6 +8,7 @@ #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/cpu.h> +#include <linux/sched.h> #include "blk.h" @@ -103,9 +104,10 @@ static struct notifier_block __cpuinitdata blk_cpu_notifier = { void __blk_complete_request(struct request *req) { - int ccpu, cpu, group_cpu = NR_CPUS; + int ccpu, cpu; struct request_queue *q = req->q; unsigned long flags; + bool shared = false; BUG_ON(!q->softirq_done_fn); @@ -117,22 +119,20 @@ void __blk_complete_request(struct request *req) */ if (req->cpu != -1) { ccpu = req->cpu; - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) { - ccpu = blk_cpu_to_group(ccpu); - group_cpu = blk_cpu_to_group(cpu); - } + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) + shared = cpus_share_cache(cpu, ccpu); } else ccpu = cpu; /* - * If current CPU and requested CPU are in the same group, running - * softirq in current CPU. One might concern this is just like + * If current CPU and requested CPU share a cache, run the softirq on + * the current CPU. One might concern this is just like * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is * running in interrupt handler, and currently I/O controller doesn't * support multiple interrupts, so current CPU is unique actually. This * avoids IPI sending from current CPU to the first CPU of a group. */ - if (ccpu == cpu || ccpu == group_cpu) { + if (ccpu == cpu || shared) { struct list_head *list; do_local: list = &__get_cpu_var(blk_cpu_done); diff --git a/block/blk.h b/block/blk.h index 9c12f80882b0..d45be871329e 100644 --- a/block/blk.h +++ b/block/blk.h @@ -166,22 +166,6 @@ static inline int queue_congestion_off_threshold(struct request_queue *q) return q->nr_congestion_off; } -static inline int blk_cpu_to_group(int cpu) -{ - int group = NR_CPUS; -#ifdef CONFIG_SCHED_MC - const struct cpumask *mask = cpu_coregroup_mask(cpu); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - group = cpumask_first(topology_thread_cpumask(cpu)); -#else - return cpu; -#endif - if (likely(group < NR_CPUS)) - return group; - return cpu; -} - /* * Contribute to IO statistics IFF: * diff --git a/fs/proc/base.c b/fs/proc/base.c index d4548dd49b02..965d4bde3a3b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1310,8 +1310,7 @@ sched_autogroup_write(struct file *file, const char __user *buf, if (!p) return -ESRCH; - err = nice; - err = proc_sched_autogroup_set_nice(p, &err); + err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9c66b1ada9d7..f994d51f70f2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -149,7 +149,7 @@ extern struct cred init_cred; }, \ .rt = { \ .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, \ + .time_slice = RR_TIMESLICE, \ .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ |