From 65d5dc47fe8530e17e318722fb4df676536c2bfc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:14:08 +0200 Subject: sched/debug: Remove unused variable Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb5a5de..2f93e4a2d9f6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { -- cgit v1.2.3 From 5f6ad26ea353fdf3dad2328052cbee49e0b9c5b4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:23:31 +0200 Subject: sched/tracing: Use common task-state helpers Remove yet another task-state char instance. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- kernel/trace/trace_output.c | 21 ++++++--------------- kernel/trace/trace_sched_wakeup.c | 8 ++++---- 3 files changed, 10 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index a2fe636b6825..bc7807933415 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -83,8 +83,6 @@ struct task_group; #define TASK_NEW 0x0800 #define TASK_STATE_MAX 0x1000 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" - /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629af2285..c738e764e2a5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b67646..0c331978b1a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) -- cgit v1.2.3 From 5d68cc95fb24b2f58060cc5340dd7402a11f054e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:32:41 +0200 Subject: sched/debug: Ignore TASK_IDLE for SysRq-W Markus reported that tasks in TASK_IDLE state are reported by SysRq-W, which results in undesirable clutter. Reported-by: Markus Trippelsdorf Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966567da..d17c5da523a0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } -- cgit v1.2.3 From 5ccba44ba118a5000cccc50076b0344632459779 Mon Sep 17 00:00:00 2001 From: Ethan Zhao Date: Mon, 4 Sep 2017 13:59:34 +0800 Subject: sched/sysctl: Check user input value of sysctl_sched_time_avg System will hang if user set sysctl_sched_time_avg to 0: [root@XXX ~]# sysctl kernel.sched_time_avg_ms=0 Stack traceback for pid 0 0xffff883f6406c600 0 0 1 3 R 0xffff883f6406cf50 *swapper/3 ffff883f7ccc3ae8 0000000000000018 ffffffff810c4dd0 0000000000000000 0000000000017800 ffff883f7ccc3d78 0000000000000003 ffff883f7ccc3bf8 ffffffff810c4fc9 ffff883f7ccc3c08 00000000810c5043 ffff883f7ccc3c08 Call Trace: [] ? update_group_capacity+0x110/0x200 [] ? update_sd_lb_stats+0x109/0x600 [] ? find_busiest_group+0x47/0x530 [] ? load_balance+0x194/0x900 [] ? update_rq_clock.part.83+0x1a/0xe0 [] ? rebalance_domains+0x152/0x290 [] ? run_rebalance_domains+0xdc/0x1d0 [] ? __do_softirq+0xfb/0x320 [] ? irq_exit+0x125/0x130 [] ? scheduler_ipi+0x97/0x160 [] ? smp_reschedule_interrupt+0x29/0x30 [] ? reschedule_interrupt+0x6e/0x80 [] ? cpuidle_enter_state+0xcc/0x230 [] ? cpuidle_enter_state+0x9c/0x230 [] ? cpuidle_enter+0x17/0x20 [] ? cpu_startup_entry+0x38c/0x420 [] ? start_secondary+0x173/0x1e0 Because divide-by-zero error happens in function: update_group_capacity() update_cpu_capacity() scale_rt_capacity() { ... total = sched_avg_period() + delta; used = div_u64(avg, total); ... } To fix this issue, check user input value of sysctl_sched_time_avg, keep it unchanged when hitting invalid input, and set the minimum limit of sysctl_sched_time_avg to 1 ms. Reported-by: James Puthukattukaran Signed-off-by: Ethan Zhao Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: ethan.kernel@gmail.com Cc: keescook@chromium.org Cc: mcgrof@kernel.org Cc: Link: http://lkml.kernel.org/r/1504504774-18253-1-git-send-email-ethan.zhao@oracle.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..423554ad3610 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { -- cgit v1.2.3