From 9c57259117b9c25472a3fa6d5a14d6bb3b647e87 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 3 Jun 2016 17:58:40 -0500 Subject: sched/debug: Fix /proc/sched_debug regression Commit: cb2517653fcc ("sched/debug: Make schedstats a runtime tunable that is disabled by default") ... introduced a bug when CONFIG_SCHEDSTATS is enabled and the runtime tunable is disabled (which is the default). The wait-time, sum-exec, and sum-sleep fields are missing from the /proc/sched_debug file in the runnable_tasks section. Fix it with a new schedstat_val() macro which returns the field value when schedstats is enabled and zero otherwise. The macro works with both SCHEDSTATS and !SCHEDSTATS. I put the macro in stats.h since it might end up being useful in other places. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Thomas Gleixner Fixes: cb2517653fcc ("sched/debug: Make schedstats a runtime tunable that is disabled by default") Link: http://lkml.kernel.org/r/bcda7c2790cf2ccbe586a28c02dd7b6fe7749a2b.1464994423.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 15 ++++----------- kernel/sched/stats.h | 3 +++ 2 files changed, 7 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index cf905f655ba1..0368c393a336 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) SPLIT_NS(p->se.vruntime), (long long)(p->nvcsw + p->nivcsw), p->prio); -#ifdef CONFIG_SCHEDSTATS - if (schedstat_enabled()) { - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.statistics.wait_sum), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.statistics.sum_sleep_runtime)); - } -#else + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - 0LL, 0L, + SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)), SPLIT_NS(p->se.sum_exec_runtime), - 0LL, 0L); -#endif + SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime))); + #ifdef CONFIG_NUMA_BALANCING SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); #endif diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 70b3b6a20fb0..78955cbea31c 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) # define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) # define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) # define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) +# define schedstat_val(rq, field) ((schedstat_enabled()) ? (rq)->field : 0) + #else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) @@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) # define schedstat_set(var, val) do { } while (0) +# define schedstat_val(rq, field) 0 #endif #ifdef CONFIG_SCHED_INFO -- cgit v1.2.3-59-g8ed1b From 4698f88c06b893f2acc0b443004a53bf490fde7c Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 7 Jun 2016 14:43:16 -0500 Subject: sched/debug: Fix 'schedstats=enable' cmdline option The 'schedstats=enable' option doesn't work, and also produces the following warning during boot: WARNING: CPU: 0 PID: 0 at /home/jpoimboe/git/linux/kernel/jump_label.c:61 static_key_slow_inc+0x8c/0xa0 static_key_slow_inc used before call to jump_label_init Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.7.0-rc1+ #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 0000000000000086 3ae3475a4bea95d4 ffffffff81e03da8 ffffffff8143fc83 ffffffff81e03df8 0000000000000000 ffffffff81e03de8 ffffffff810b1ffb 0000003d00000096 ffffffff823514d0 ffff88007ff197c8 0000000000000000 Call Trace: [] dump_stack+0x85/0xc2 [] __warn+0xcb/0xf0 [] warn_slowpath_fmt+0x5f/0x80 [] static_key_slow_inc+0x8c/0xa0 [] static_key_enable+0x16/0x40 [] setup_schedstats+0x29/0x94 [] unknown_bootoption+0x89/0x191 [] parse_args+0x297/0x4b0 [] start_kernel+0x1d8/0x4a9 [] ? set_init_arg+0x55/0x55 [] ? early_idt_handler_array+0x120/0x120 [] x86_64_start_reservations+0x2f/0x31 [] x86_64_start_kernel+0x14a/0x16d The problem is that it tries to update the 'sched_schedstats' static key before jump labels have been initialized. Changing jump_label_init() to be called earlier before parse_early_param() wouldn't fix it: it would still fail trying to poke_text() because mm isn't yet initialized. Instead, just create a temporary '__sched_schedstats' variable which can be copied to the static key later during sched_init() after jump labels have been initialized. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Matt Fleming Cc: Mel Gorman Cc: Peter Zijlstra Cc: Srikar Dronamraju Cc: Thomas Gleixner Fixes: cb2517653fcc ("sched/debug: Make schedstats a runtime tunable that is disabled by default") Link: http://lkml.kernel.org/r/453775fe3433bed65731a583e228ccea806d18cd.1465322027.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f2cae4620c7..385c947482e1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2253,9 +2253,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +#ifdef CONFIG_SCHEDSTATS + DEFINE_STATIC_KEY_FALSE(sched_schedstats); +static bool __initdata __sched_schedstats = false; -#ifdef CONFIG_SCHEDSTATS static void set_schedstats(bool enabled) { if (enabled) @@ -2278,11 +2280,16 @@ static int __init setup_schedstats(char *str) if (!str) goto out; + /* + * This code is called before jump labels have been set up, so we can't + * change the static branch directly just yet. Instead set a temporary + * variable so init_schedstats() can do it later. + */ if (!strcmp(str, "enable")) { - set_schedstats(true); + __sched_schedstats = true; ret = 1; } else if (!strcmp(str, "disable")) { - set_schedstats(false); + __sched_schedstats = false; ret = 1; } out: @@ -2293,6 +2300,11 @@ out: } __setup("schedstats=", setup_schedstats); +static void __init init_schedstats(void) +{ + set_schedstats(__sched_schedstats); +} + #ifdef CONFIG_PROC_SYSCTL int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -2313,8 +2325,10 @@ int sysctl_schedstats(struct ctl_table *table, int write, set_schedstats(state); return err; } -#endif -#endif +#endif /* CONFIG_PROC_SYSCTL */ +#else /* !CONFIG_SCHEDSTATS */ +static inline void init_schedstats(void) {} +#endif /* CONFIG_SCHEDSTATS */ /* * fork()/clone()-time setup: @@ -7487,6 +7501,8 @@ void __init sched_init(void) #endif init_sched_fair_class(); + init_schedstats(); + scheduler_running = 1; } -- cgit v1.2.3-59-g8ed1b