From 47fea2adfc9e16846bc57c2f64ff233b354fef39 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Mon, 29 Dec 2008 23:39:17 +0530 Subject: [PATCH 1/8] sched: sched.c declare variables before they get used Impact: cleanup, avoid sparse warnings In linux/sched.h moved out sysctl_sched_latency, sysctl_sched_min_granularity, sysctl_sched_wakeup_granularity, sysctl_sched_shares_ratelimit and sysctl_sched_shares_thresh from #ifdef CONFIG_SCHED_DEBUG as these variables are common for both. Fixes these sparse warnings: kernel/sched.c:825:14: warning: symbol 'sysctl_sched_shares_ratelimit' was not declared. Should it be static? kernel/sched.c:832:14: warning: symbol 'sysctl_sched_shares_thresh' was not declared. Should it be static? kernel/sched_fair.c:37:14: warning: symbol 'sysctl_sched_latency' was not declared. Should it be static? kernel/sched_fair.c:43:14: warning: symbol 'sysctl_sched_min_granularity' was not declared. Should it be static? kernel/sched_fair.c:72:14: warning: symbol 'sysctl_sched_wakeup_granularity' was not declared. Should it be static? Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 8395e715809..01d9fd268eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1651,16 +1651,16 @@ extern void wake_up_idle_cpu(int cpu); static inline void wake_up_idle_cpu(int cpu) { } #endif -#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; +extern unsigned int sysctl_sched_shares_ratelimit; +extern unsigned int sysctl_sched_shares_thresh; +#ifdef CONFIG_SCHED_DEBUG extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; int sched_nr_latency_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, From 1c5745aa380efb6417b5681104b007c8612fb496 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 22 Dec 2008 23:05:28 +0100 Subject: [PATCH 2/8] sched_clock: prevent scd->clock from moving backwards, take #2 Redo: 5b7dba4: sched_clock: prevent scd->clock from moving backwards which had to be reverted due to s2ram hangs: ca7e716: Revert "sched_clock: prevent scd->clock from moving backwards" ... this time with resume restoring GTOD later in the sequence taken into account as well. The "timekeeping_suspended" flag is not very nice but we cannot call into GTOD before it has been properly resumed and the scheduler will run very early in the resume sequence. Cc: Signed-off-by: Ingo Molnar --- include/linux/time.h | 1 + kernel/sched_clock.c | 5 ++++- kernel/time/timekeeping.c | 7 +++++-- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/linux/time.h b/include/linux/time.h index ce321ac5c8f..fbbd2a1c92b 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -105,6 +105,7 @@ extern unsigned long read_persistent_clock(void); extern int update_persistent_clock(struct timespec now); extern int no_sync_cmos_clock __read_mostly; void timekeeping_init(void); +extern int timekeeping_suspended; unsigned long get_seconds(void); struct timespec current_kernel_time(void); diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index e8ab096ddfe..a0b0852414c 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -124,7 +124,7 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now) clock = scd->tick_gtod + delta; min_clock = wrap_max(scd->tick_gtod, scd->clock); - max_clock = scd->tick_gtod + TICK_NSEC; + max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC); clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); @@ -227,6 +227,9 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); */ void sched_clock_idle_wakeup_event(u64 delta_ns) { + if (timekeeping_suspended) + return; + sched_clock_tick(); touch_softlockup_watchdog(); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index fa05e88aa76..900f1b6598d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -46,6 +46,9 @@ struct timespec xtime __attribute__ ((aligned (16))); struct timespec wall_to_monotonic __attribute__ ((aligned (16))); static unsigned long total_sleep_time; /* seconds */ +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + static struct timespec xtime_cache __attribute__ ((aligned (16))); void update_xtime_cache(u64 nsec) { @@ -92,6 +95,8 @@ void getnstimeofday(struct timespec *ts) unsigned long seq; s64 nsecs; + WARN_ON(timekeeping_suspended); + do { seq = read_seqbegin(&xtime_lock); @@ -299,8 +304,6 @@ void __init timekeeping_init(void) write_sequnlock_irqrestore(&xtime_lock, flags); } -/* flag for if timekeeping is suspended */ -static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; From 0a582440ff546e2c6610d1acec325e91b4efd313 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 2 Jan 2009 12:16:42 +0100 Subject: [PATCH 3/8] sched: fix sched_slice() Impact: fix bad-interactivity buglet Fix sched_slice() to emit a sane result whether a task is currently enqueued or not. Signed-off-by: Mike Galbraith Tested-by: Jayson King Signed-off-by: Ingo Molnar kernel/sched_fair.c | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) --- kernel/sched_fair.c | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 5ad4440f0fc..b808563f4f1 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -385,20 +385,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, } #endif -/* - * delta *= P[w / rw] - */ -static inline unsigned long -calc_delta_weight(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - se->load.weight, &cfs_rq_of(se)->load); - } - - return delta; -} - /* * delta /= w */ @@ -440,12 +426,20 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - unsigned long nr_running = cfs_rq->nr_running; + u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); - if (unlikely(!se->on_rq)) - nr_running++; + for_each_sched_entity(se) { + struct load_weight *load = &cfs_rq->load; - return calc_delta_weight(__sched_period(nr_running), se); + if (unlikely(!se->on_rq)) { + struct load_weight lw = cfs_rq->load; + + update_load_add(&lw, se->load.weight); + load = &lw; + } + slice = calc_delta_mine(slice, se->load.weight, load); + } + return slice; } /* From 8916edef5888c5d8fe283714416a9ca95b4c3431 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Sun, 4 Jan 2009 05:40:37 +0900 Subject: [PATCH 4/8] getrusage: RUSAGE_THREAD should return ru_utime and ru_stime Impact: task stats regression fix Original getrusage(RUSAGE_THREAD) implementation can return ru_utime and ru_stime. But commit "f06febc: timers: fix itimer/many thread hang" broke it. this patch restores it. Signed-off-by: KOSAKI Motohiro Acked-by: Roland McGrath Signed-off-by: Ingo Molnar --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sys.c b/kernel/sys.c index d356d79e84a..61dbfd4a54d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1627,6 +1627,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { + utime = task_utime(current); + stime = task_stime(current); accumulate_thread_rusage(p, r); goto out; } From 39aac64812da70f0af262f4700e67637338cbb3b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 5 Jan 2009 19:18:02 +0800 Subject: [PATCH 5/8] sched: mark sched_create_sysfs_power_savings_entries() as __init Impact: cleanup The only caller is cpu_dev_init() which is marked as __init. Signed-off-by: Li Zefan Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched.c b/kernel/sched.c index 545c6fccd1d..9a8e296959c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8060,7 +8060,7 @@ static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_store); #endif -int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) +int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) { int err = 0; From c70f22d203fc02c805b6ed4a3483b740dc36786b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 5 Jan 2009 19:07:50 +0800 Subject: [PATCH 6/8] sched: clean up arch_reinit_sched_domains() - Make arch_reinit_sched_domains() static. It was exported to be used in s390, but now rebuild_sched_domains() is used instead. - Make it return void. Signed-off-by: Li Zefan Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/sched.c | 9 +++------ 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 38a3f4b1539..91207df702e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -912,7 +912,6 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, struct sched_domain_attr *dattr_new); -extern int arch_reinit_sched_domains(void); /* Test a flag in parent sched domain */ static inline int test_sd_parent(struct sched_domain *sd, int flag) diff --git a/kernel/sched.c b/kernel/sched.c index 9a8e296959c..c5019a5dcaa 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7987,7 +7987,7 @@ match2: } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -int arch_reinit_sched_domains(void) +static void arch_reinit_sched_domains(void) { get_online_cpus(); @@ -7996,13 +7996,10 @@ int arch_reinit_sched_domains(void) rebuild_sched_domains(); put_online_cpus(); - - return 0; } static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) { - int ret; unsigned int level = 0; if (sscanf(buf, "%u", &level) != 1) @@ -8023,9 +8020,9 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) else sched_mc_power_savings = level; - ret = arch_reinit_sched_domains(); + arch_reinit_sched_domains(); - return ret ? ret : count; + return count; } #ifdef CONFIG_SCHED_MC From 0c910d289567163dbe40ccc174b36afd1c7723bd Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 6 Jan 2009 17:39:06 +0800 Subject: [PATCH 7/8] sched: fix double kfree in failure path It's not the responsibility of init_rootdomain() to free root_domain allocated by alloc_rootdomain(). Signed-off-by: Li Zefan Reviewed-by: Pekka Enberg Signed-off-by: Ingo Molnar --- kernel/sched.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index c5019a5dcaa..973f97362ce 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6970,7 +6970,7 @@ static int init_rootdomain(struct root_domain *rd, bool bootmem) } if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) - goto free_rd; + goto out; if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) @@ -6986,8 +6986,7 @@ free_online: free_cpumask_var(rd->online); free_span: free_cpumask_var(rd->span); -free_rd: - kfree(rd); +out: return -ENOMEM; } From db2f59c8c9b315f2b88b1dac159b988c6009034d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 6 Jan 2009 17:40:36 +0800 Subject: [PATCH 8/8] sched: fix section mismatch init_rootdomain() calls alloc_bootmem_cpumask_var() at system boot, so does cpupri_init(). Signed-off-by: Li Zefan Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- kernel/sched_cpupri.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 973f97362ce..2e3545f57e7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6957,7 +6957,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) spin_unlock_irqrestore(&rq->lock, flags); } -static int init_rootdomain(struct root_domain *rd, bool bootmem) +static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) { memset(rd, 0, sizeof(*rd)); diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index 018b7be1db2..1e00bfacf9b 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -151,7 +151,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * * Returns: -ENOMEM if memory fails. */ -int cpupri_init(struct cpupri *cp, bool bootmem) +int __init_refok cpupri_init(struct cpupri *cp, bool bootmem) { int i;