From 9b51f66dcb09ac5eb6bc68fc111d5c7a1e0131d6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 12 Dec 2008 13:49:45 +0100 Subject: perfcounters: implement "counter inheritance" Impact: implement new performance feature Counter inheritance can be used to run performance counters in a workload, transparently - and pipe back the counter results to the parent counter. Inheritance for performance counters works the following way: when creating a counter it can be marked with the .inherit=1 flag. Such counters are then 'inherited' by all child tasks (be they fork()-ed or clone()-ed). These counters get inherited through exec() boundaries as well (except through setuid boundaries). The counter values get added back to the parent counter(s) when the child task(s) exit - much like stime/utime statistics are gathered. So inherited counters are ideal to gather summary statistics about an application's behavior via shell commands, without having to modify that application. The timec.c command utilizes counter inheritance: http://redhat.com/~mingo/perfcounters/timec.c Sample output: $ ./timec -e 1 -e 3 -e 5 ls -lR /usr/include/ >/dev/null Performance counter stats for 'ls': 163516953 instructions 2295 cache-misses 2855182 branch-misses Signed-off-by: Ingo Molnar --- kernel/exit.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 2d8be7ebb0f..d336c90a5f1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1093,11 +1093,12 @@ NORET_TYPE void do_exit(long code) mpol_put(tsk->mempolicy); tsk->mempolicy = NULL; #endif -#ifdef CONFIG_FUTEX /* - * This must happen late, after the PID is not - * hashed anymore: + * These must happen late, after the PID is not + * hashed anymore, but still at a point that may sleep: */ + perf_counter_exit_task(tsk); +#ifdef CONFIG_FUTEX if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); if (unlikely(current->pi_state_cache)) -- cgit v1.2.3-70-g09d2 From aa9c4c0f967fdb482ea95e8473ec3d201e6e0781 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 17 Dec 2008 14:10:57 +0100 Subject: perfcounters: fix task clock counter Impact: fix per task clock counter precision Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 8 ++++++ kernel/exit.c | 17 +++++++---- kernel/perf_counter.c | 70 ++++++++++++++++++++++++++++++++++----------- kernel/sched.c | 49 +++++++++++++++++++++++++++++-- 4 files changed, 120 insertions(+), 24 deletions(-) (limited to 'kernel/exit.c') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 4a145caeee0..1b2e3242497 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -66,7 +66,15 @@ static inline unsigned int kstat_irqs(unsigned int irq) return sum; } + +/* + * Lock/unlock the current runqueue - to extract task statistics: + */ +extern void curr_rq_lock_irq_save(unsigned long *flags); +extern void curr_rq_unlock_irq_restore(unsigned long *flags); +extern unsigned long long __task_delta_exec(struct task_struct *tsk, int update); extern unsigned long long task_delta_exec(struct task_struct *); + extern void account_user_time(struct task_struct *, cputime_t); extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); diff --git a/kernel/exit.c b/kernel/exit.c index d336c90a5f1..244edfd9686 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -922,6 +922,12 @@ static void exit_notify(struct task_struct *tsk, int group_dead) forget_original_parent(tsk); exit_task_namespaces(tsk); + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + */ + perf_counter_exit_task(tsk); + write_lock_irq(&tasklist_lock); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); @@ -1093,11 +1099,6 @@ NORET_TYPE void do_exit(long code) mpol_put(tsk->mempolicy); tsk->mempolicy = NULL; #endif - /* - * These must happen late, after the PID is not - * hashed anymore, but still at a point that may sleep: - */ - perf_counter_exit_task(tsk); #ifdef CONFIG_FUTEX if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); @@ -1121,6 +1122,12 @@ NORET_TYPE void do_exit(long code) if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); + /* + * These must happen late, after the PID is not + * hashed anymore, but still at a point that may sleep: + */ + perf_counter_exit_task(tsk); + preempt_disable(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 961d651aa57..f1110ac1267 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -106,7 +107,8 @@ static void __perf_counter_remove_from_context(void *info) if (ctx->task && cpuctx->task_ctx != ctx) return; - spin_lock_irqsave(&ctx->lock, flags); + curr_rq_lock_irq_save(&flags); + spin_lock(&ctx->lock); if (counter->state == PERF_COUNTER_STATE_ACTIVE) { counter->hw_ops->disable(counter); @@ -135,7 +137,8 @@ static void __perf_counter_remove_from_context(void *info) perf_max_counters - perf_reserved_percpu); } - spin_unlock_irqrestore(&ctx->lock, flags); + spin_unlock(&ctx->lock); + curr_rq_unlock_irq_restore(&flags); } @@ -209,7 +212,8 @@ static void __perf_install_in_context(void *info) if (ctx->task && cpuctx->task_ctx != ctx) return; - spin_lock_irqsave(&ctx->lock, flags); + curr_rq_lock_irq_save(&flags); + spin_lock(&ctx->lock); /* * Protect the list operation against NMI by disabling the @@ -232,7 +236,8 @@ static void __perf_install_in_context(void *info) if (!ctx->task && cpuctx->max_pertask) cpuctx->max_pertask--; - spin_unlock_irqrestore(&ctx->lock, flags); + spin_unlock(&ctx->lock); + curr_rq_unlock_irq_restore(&flags); } /* @@ -438,15 +443,19 @@ int perf_counter_task_disable(void) struct task_struct *curr = current; struct perf_counter_context *ctx = &curr->perf_counter_ctx; struct perf_counter *counter; + unsigned long flags; u64 perf_flags; int cpu; if (likely(!ctx->nr_counters)) return 0; - local_irq_disable(); + curr_rq_lock_irq_save(&flags); cpu = smp_processor_id(); + /* force the update of the task clock: */ + __task_delta_exec(curr, 1); + perf_counter_task_sched_out(curr, cpu); spin_lock(&ctx->lock); @@ -463,7 +472,7 @@ int perf_counter_task_disable(void) spin_unlock(&ctx->lock); - local_irq_enable(); + curr_rq_unlock_irq_restore(&flags); return 0; } @@ -473,15 +482,19 @@ int perf_counter_task_enable(void) struct task_struct *curr = current; struct perf_counter_context *ctx = &curr->perf_counter_ctx; struct perf_counter *counter; + unsigned long flags; u64 perf_flags; int cpu; if (likely(!ctx->nr_counters)) return 0; - local_irq_disable(); + curr_rq_lock_irq_save(&flags); cpu = smp_processor_id(); + /* force the update of the task clock: */ + __task_delta_exec(curr, 1); + spin_lock(&ctx->lock); /* @@ -493,6 +506,7 @@ int perf_counter_task_enable(void) if (counter->state != PERF_COUNTER_STATE_OFF) continue; counter->state = PERF_COUNTER_STATE_INACTIVE; + counter->hw_event.disabled = 0; } hw_perf_restore(perf_flags); @@ -500,7 +514,7 @@ int perf_counter_task_enable(void) perf_counter_task_sched_in(curr, cpu); - local_irq_enable(); + curr_rq_unlock_irq_restore(&flags); return 0; } @@ -540,8 +554,11 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu) static void __read(void *info) { struct perf_counter *counter = info; + unsigned long flags; + curr_rq_lock_irq_save(&flags); counter->hw_ops->read(counter); + curr_rq_unlock_irq_restore(&flags); } static u64 perf_counter_read(struct perf_counter *counter) @@ -860,13 +877,27 @@ static const struct hw_perf_counter_ops perf_ops_cpu_clock = { .read = cpu_clock_perf_counter_read, }; -static void task_clock_perf_counter_update(struct perf_counter *counter) +/* + * Called from within the scheduler: + */ +static u64 task_clock_perf_counter_val(struct perf_counter *counter, int update) { - u64 prev, now; + struct task_struct *curr = counter->task; + u64 delta; + + WARN_ON_ONCE(counter->task != current); + + delta = __task_delta_exec(curr, update); + + return curr->se.sum_exec_runtime + delta; +} + +static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now) +{ + u64 prev; s64 delta; prev = atomic64_read(&counter->hw.prev_count); - now = current->se.sum_exec_runtime; atomic64_set(&counter->hw.prev_count, now); @@ -877,17 +908,23 @@ static void task_clock_perf_counter_update(struct perf_counter *counter) static void task_clock_perf_counter_read(struct perf_counter *counter) { - task_clock_perf_counter_update(counter); + u64 now = task_clock_perf_counter_val(counter, 1); + + task_clock_perf_counter_update(counter, now); } static void task_clock_perf_counter_enable(struct perf_counter *counter) { - atomic64_set(&counter->hw.prev_count, current->se.sum_exec_runtime); + u64 now = task_clock_perf_counter_val(counter, 0); + + atomic64_set(&counter->hw.prev_count, now); } static void task_clock_perf_counter_disable(struct perf_counter *counter) { - task_clock_perf_counter_update(counter); + u64 now = task_clock_perf_counter_val(counter, 0); + + task_clock_perf_counter_update(counter, now); } static const struct hw_perf_counter_ops perf_ops_task_clock = { @@ -1267,6 +1304,7 @@ __perf_counter_exit_task(struct task_struct *child, { struct perf_counter *parent_counter; u64 parent_val, child_val; + unsigned long flags; u64 perf_flags; /* @@ -1275,7 +1313,7 @@ __perf_counter_exit_task(struct task_struct *child, * Be careful about zapping the list - IRQ/NMI context * could still be processing it: */ - local_irq_disable(); + curr_rq_lock_irq_save(&flags); perf_flags = hw_perf_save_disable(); if (child_counter->state == PERF_COUNTER_STATE_ACTIVE) { @@ -1294,7 +1332,7 @@ __perf_counter_exit_task(struct task_struct *child, list_del_init(&child_counter->list_entry); hw_perf_restore(perf_flags); - local_irq_enable(); + curr_rq_unlock_irq_restore(&flags); parent_counter = child_counter->parent; /* diff --git a/kernel/sched.c b/kernel/sched.c index 382cfdb5e38..4d84ff4c877 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -638,7 +638,7 @@ static inline int cpu_of(struct rq *rq) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) -static inline void update_rq_clock(struct rq *rq) +inline void update_rq_clock(struct rq *rq) { rq->clock = sched_clock_cpu(cpu_of(rq)); } @@ -969,6 +969,26 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) } } +void curr_rq_lock_irq_save(unsigned long *flags) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_save(*flags); + rq = cpu_rq(smp_processor_id()); + spin_lock(&rq->lock); +} + +void curr_rq_unlock_irq_restore(unsigned long *flags) + __releases(rq->lock) +{ + struct rq *rq; + + rq = cpu_rq(smp_processor_id()); + spin_unlock(&rq->lock); + local_irq_restore(*flags); +} + void task_rq_unlock_wait(struct task_struct *p) { struct rq *rq = task_rq(p); @@ -2558,7 +2578,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { fire_sched_out_preempt_notifiers(prev, next); - perf_counter_task_sched_out(prev, cpu_of(rq)); prepare_lock_switch(rq, next); prepare_arch_switch(next); } @@ -4089,6 +4108,29 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); +/* + * Return any ns on the sched_clock that have not yet been banked in + * @p in case that task is currently running. + */ +unsigned long long __task_delta_exec(struct task_struct *p, int update) +{ + s64 delta_exec; + struct rq *rq; + + rq = task_rq(p); + WARN_ON_ONCE(!runqueue_is_locked()); + WARN_ON_ONCE(!task_current(rq, p)); + + if (update) + update_rq_clock(rq); + + delta_exec = rq->clock - p->se.exec_start; + + WARN_ON_ONCE(delta_exec < 0); + + return delta_exec; +} + /* * Return any ns on the sched_clock that have not yet been banked in * @p in case that task is currently running. @@ -4316,13 +4358,13 @@ void scheduler_tick(void) update_rq_clock(rq); update_cpu_load(rq); curr->sched_class->task_tick(rq, curr, 0); + perf_counter_task_tick(curr, cpu); spin_unlock(&rq->lock); #ifdef CONFIG_SMP rq->idle_at_tick = idle_cpu(cpu); trigger_load_balance(rq, cpu); #endif - perf_counter_task_tick(curr, cpu); } #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ @@ -4512,6 +4554,7 @@ need_resched_nonpreemptible: if (likely(prev != next)) { sched_info_switch(prev, next); + perf_counter_task_sched_out(prev, cpu); rq->nr_switches++; rq->curr = next; -- cgit v1.2.3-70-g09d2 From eef6cbf5844c620d9db9be99e4908cdf92492fb9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 19 Dec 2008 10:20:42 +0100 Subject: perfcounters: pull inherited counters Change counter inheritance from a 'push' to a 'pull' model: instead of child tasks pushing their final counts to the parent, reuse the wait4 infrastructure to pull counters as child tasks are exit-processed, much like how cutime/cstime is collected. Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 9 +++++++++ kernel/exit.c | 21 +++++++++------------ 2 files changed, 18 insertions(+), 12 deletions(-) (limited to 'kernel/exit.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 23fd8909b9e..54fa2fa2c8e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -113,6 +113,14 @@ extern struct group_info init_groups; # define CAP_INIT_BSET CAP_INIT_EFF_SET #endif +#ifdef CONFIG_PERF_COUNTERS +# define INIT_PERF_COUNTERS(tsk) \ + .perf_counter_ctx.counter_list = \ + LIST_HEAD_INIT(tsk.perf_counter_ctx.counter_list), +#else +# define INIT_PERF_COUNTERS(tsk) +#endif + /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -180,6 +188,7 @@ extern struct group_info init_groups; INIT_IDS \ INIT_TRACE_IRQFLAGS \ INIT_LOCKDEP \ + INIT_PERF_COUNTERS(tsk) \ } diff --git a/kernel/exit.c b/kernel/exit.c index 244edfd9686..101b7eeff44 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -153,6 +153,9 @@ static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); +#ifdef CONFIG_PERF_COUNTERS + WARN_ON_ONCE(!list_empty(&tsk->perf_counter_ctx.counter_list)); +#endif trace_sched_process_free(tsk); put_task_struct(tsk); } @@ -922,12 +925,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead) forget_original_parent(tsk); exit_task_namespaces(tsk); - /* - * Flush inherited counters to the parent - before the parent - * gets woken up by child-exit notifications. - */ - perf_counter_exit_task(tsk); - write_lock_irq(&tasklist_lock); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); @@ -1122,12 +1119,6 @@ NORET_TYPE void do_exit(long code) if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); - /* - * These must happen late, after the PID is not - * hashed anymore, but still at a point that may sleep: - */ - perf_counter_exit_task(tsk); - preempt_disable(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; @@ -1371,6 +1362,12 @@ static int wait_task_zombie(struct task_struct *p, int options, */ read_unlock(&tasklist_lock); + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + */ + perf_counter_exit_task(p); + retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; -- cgit v1.2.3-70-g09d2 From a8d154b009168337494fbf345671bab74d3e4b8b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 10 Apr 2009 09:36:00 -0400 Subject: tracing: create automated trace defines This patch lowers the number of places a developer must modify to add new tracepoints. The current method to add a new tracepoint into an existing system is to write the trace point macro in the trace header with one of the macros TRACE_EVENT, TRACE_FORMAT or DECLARE_TRACE, then they must add the same named item into the C file with the macro DEFINE_TRACE(name) and then add the trace point. This change cuts out the needing to add the DEFINE_TRACE(name). Every file that uses the tracepoint must still include the trace/.h file, but the one C file must also add a define before the including of that file. #define CREATE_TRACE_POINTS #include This will cause the trace/mytrace.h file to also produce the C code necessary to implement the trace point. Note, if more than one trace/.h is used to create the C code it is best to list them all together. #define CREATE_TRACE_POINTS #include #include #include Thanks to Mathieu Desnoyers and Christoph Hellwig for coming up with the cleaner solution of the define above the includes over my first design to have the C code include a "special" header. This patch converts sched, irq and lockdep and skb to use this new method. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Neil Horman Cc: Zhao Lei Cc: Eduard - Gabriel Munteanu Cc: Pekka Enberg Signed-off-by: Steven Rostedt --- include/trace/define_trace.h | 75 ++++++++++++++++++++++++++++++++++++++++++++ include/trace/irq.h | 5 ++- include/trace/kmem.h | 4 ++- include/trace/lockdep.h | 3 ++ include/trace/sched.h | 3 ++ include/trace/skb.h | 3 ++ kernel/exit.c | 4 --- kernel/fork.c | 2 -- kernel/irq/handle.c | 7 ++--- kernel/kthread.c | 3 -- kernel/lockdep.c | 12 ++----- kernel/sched.c | 10 ++---- kernel/signal.c | 2 -- kernel/softirq.c | 3 -- mm/util.c | 11 ++----- net/core/net-traces.c | 4 +-- 16 files changed, 105 insertions(+), 46 deletions(-) create mode 100644 include/trace/define_trace.h (limited to 'kernel/exit.c') diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h new file mode 100644 index 00000000000..de9dc7d8508 --- /dev/null +++ b/include/trace/define_trace.h @@ -0,0 +1,75 @@ +/* + * Trace files that want to automate creationg of all tracepoints defined + * in their file should include this file. The following are macros that the + * trace file may define: + * + * TRACE_SYSTEM defines the system the tracepoint is for + * + * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h + * This macro may be defined to tell define_trace.h what file to include. + * Note, leave off the ".h". + * + * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace + * then this macro can define the path to use. Note, the path is relative to + * define_trace.h, not the file including it. Full path names for out of tree + * modules must be used. + */ + +#ifdef CREATE_TRACE_POINTS + +/* Prevent recursion */ +#undef CREATE_TRACE_POINTS + +#include + +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ + DEFINE_TRACE(name) + +#undef TRACE_FORMAT +#define TRACE_FORMAT(name, proto, args, print) \ + DEFINE_TRACE(name) + +#undef DECLARE_TRACE +#define DECLARE_TRACE(name, proto, args) \ + DEFINE_TRACE(name) + +#undef TRACE_INCLUDE +#undef __TRACE_INCLUDE + +#ifndef TRACE_INCLUDE_FILE +# define TRACE_INCLUDE_FILE TRACE_SYSTEM +# define UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifndef TRACE_INCLUDE_PATH +# define __TRACE_INCLUDE(system) +# define UNDEF_TRACE_INCLUDE_FILE +#else +# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h) +#endif + +# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system) + +/* Let the trace headers be reread */ +#define TRACE_HEADER_MULTI_READ + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef TRACE_HEADER_MULTI_READ + +/* Only undef what we defined in this file */ +#ifdef UNDEF_TRACE_INCLUDE_FILE +# undef TRACE_INCLUDE_PATH +# undef UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifdef UNDEF_TRACE_INCLUDE_FILE +# undef TRACE_INCLUDE_PATH +# undef UNDEF_TRACE_INCLUDE_FILE +#endif + +/* We may be processing more files */ +#define CREATE_TRACE_POINTS + +#endif /* CREATE_TRACE_POINTS */ diff --git a/include/trace/irq.h b/include/trace/irq.h index 04ab4c65222..75e3468e449 100644 --- a/include/trace/irq.h +++ b/include/trace/irq.h @@ -51,4 +51,7 @@ TRACE_FORMAT(softirq_exit, TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) ); -#endif +#endif /* _TRACE_IRQ_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/kmem.h b/include/trace/kmem.h index d7d12189e5c..c22c42f980b 100644 --- a/include/trace/kmem.h +++ b/include/trace/kmem.h @@ -188,5 +188,7 @@ TRACE_EVENT(kmem_cache_free, TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) ); +#endif /* _TRACE_KMEM_H */ -#endif +/* This part must be outside protection */ +#include diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h index 8ee7900b38c..4d301e758de 100644 --- a/include/trace/lockdep.h +++ b/include/trace/lockdep.h @@ -55,3 +55,6 @@ TRACE_EVENT(lock_acquired, #endif #endif /* _TRACE_LOCKDEP_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/sched.h b/include/trace/sched.h index 5b1cf4a2846..ffa1cab586b 100644 --- a/include/trace/sched.h +++ b/include/trace/sched.h @@ -334,3 +334,6 @@ TRACE_EVENT(sched_signal_send, ); #endif /* _TRACE_SCHED_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/skb.h b/include/trace/skb.h index e6fd281f7f8..1e8fabb57c0 100644 --- a/include/trace/skb.h +++ b/include/trace/skb.h @@ -35,3 +35,6 @@ TRACE_EVENT(kfree_skb, ); #endif /* _TRACE_SKB_H */ + +/* This part must be outside protection */ +#include diff --git a/kernel/exit.c b/kernel/exit.c index abf9cf3b95c..2fe9d2c7eee 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -56,10 +56,6 @@ #include #include "cred-internals.h" -DEFINE_TRACE(sched_process_free); -DEFINE_TRACE(sched_process_exit); -DEFINE_TRACE(sched_process_wait); - static void exit_mm(struct task_struct * tsk); static void __unhash_process(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index b9e2edd0072..4bebf263923 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -83,8 +83,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ -DEFINE_TRACE(sched_process_fork); - int nr_processes(void) { int cpu; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d82142be8dd..983d8be8dff 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,9 +17,11 @@ #include #include #include -#include #include +#define CREATE_TRACE_POINTS +#include + #include "internals.h" /* @@ -348,9 +350,6 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) "but no thread function available.", irq, action->name); } -DEFINE_TRACE(irq_handler_entry); -DEFINE_TRACE(irq_handler_exit); - /** * handle_IRQ_event - irq action chain handler * @irq: the interrupt number diff --git a/kernel/kthread.c b/kernel/kthread.c index 4ebaf8519ab..e1c76924545 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,9 +21,6 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; -DEFINE_TRACE(sched_kthread_stop); -DEFINE_TRACE(sched_kthread_stop_ret); - struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/lockdep.c b/kernel/lockdep.c index c4582a6ea95..257f21a76c5 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -42,12 +42,14 @@ #include #include #include -#include #include #include "lockdep_internals.h" +#define CREATE_TRACE_POINTS +#include + #ifdef CONFIG_PROVE_LOCKING int prove_locking = 1; module_param(prove_locking, int, 0644); @@ -2929,8 +2931,6 @@ void lock_set_class(struct lockdep_map *lock, const char *name, } EXPORT_SYMBOL_GPL(lock_set_class); -DEFINE_TRACE(lock_acquire); - /* * We are not always called with irqs disabled - do that here, * and also avoid lockdep recursion: @@ -2957,8 +2957,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, } EXPORT_SYMBOL_GPL(lock_acquire); -DEFINE_TRACE(lock_release); - void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) { @@ -3061,8 +3059,6 @@ found_it: put_lock_stats(stats); } -DEFINE_TRACE(lock_acquired); - static void __lock_acquired(struct lockdep_map *lock, unsigned long ip) { @@ -3118,8 +3114,6 @@ found_it: lock->ip = ip; } -DEFINE_TRACE(lock_contended); - void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; diff --git a/kernel/sched.c b/kernel/sched.c index 5724508c3b6..e6d4518d47e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -72,13 +72,15 @@ #include #include #include -#include #include #include #include "sched_cpupri.h" +#define CREATE_TRACE_POINTS +#include + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -118,12 +120,6 @@ */ #define RUNTIME_INF ((u64)~0ULL) -DEFINE_TRACE(sched_wait_task); -DEFINE_TRACE(sched_wakeup); -DEFINE_TRACE(sched_wakeup_new); -DEFINE_TRACE(sched_switch); -DEFINE_TRACE(sched_migrate_task); - #ifdef CONFIG_SMP static void double_rq_lock(struct rq *rq1, struct rq *rq2); diff --git a/kernel/signal.c b/kernel/signal.c index d8034737db4..1d5703ff003 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -41,8 +41,6 @@ static struct kmem_cache *sigqueue_cachep; -DEFINE_TRACE(sched_signal_send); - static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; diff --git a/kernel/softirq.c b/kernel/softirq.c index 2fecefacdc5..a2d9b458ac2 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -186,9 +186,6 @@ EXPORT_SYMBOL(local_bh_enable_ip); */ #define MAX_SOFTIRQ_RESTART 10 -DEFINE_TRACE(softirq_entry); -DEFINE_TRACE(softirq_exit); - asmlinkage void __do_softirq(void) { struct softirq_action *h; diff --git a/mm/util.c b/mm/util.c index 2599e83eea1..0e74a22791c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -4,9 +4,11 @@ #include #include #include -#include #include +#define CREATE_TRACE_POINTS +#include + /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate @@ -239,13 +241,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start, EXPORT_SYMBOL_GPL(get_user_pages_fast); /* Tracepoints definitions. */ -DEFINE_TRACE(kmalloc); -DEFINE_TRACE(kmem_cache_alloc); -DEFINE_TRACE(kmalloc_node); -DEFINE_TRACE(kmem_cache_alloc_node); -DEFINE_TRACE(kfree); -DEFINE_TRACE(kmem_cache_free); - EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); diff --git a/net/core/net-traces.c b/net/core/net-traces.c index c8fb45665e4..80177205947 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -19,11 +19,11 @@ #include #include #include -#include #include #include +#define CREATE_TRACE_POINTS +#include -DEFINE_TRACE(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); -- cgit v1.2.3-70-g09d2 From ad8d75fff811a6a230f7f43b05a6483099349533 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Apr 2009 19:39:12 -0400 Subject: tracing/events: move trace point headers into include/trace/events Impact: clean up Create a sub directory in include/trace called events to keep the trace point headers in their own separate directory. Only headers that declare trace points should be defined in this directory. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Neil Horman Cc: Zhao Lei Cc: Eduard - Gabriel Munteanu Cc: Pekka Enberg Signed-off-by: Steven Rostedt --- include/linux/kmemtrace.h | 2 +- include/trace/define_trace.h | 2 +- include/trace/events/irq.h | 57 +++++++ include/trace/events/kmem.h | 194 ++++++++++++++++++++++ include/trace/events/lockdep.h | 60 +++++++ include/trace/events/sched.h | 339 ++++++++++++++++++++++++++++++++++++++ include/trace/events/skb.h | 40 +++++ include/trace/irq.h | 57 ------- include/trace/kmem.h | 194 ---------------------- include/trace/lockdep.h | 60 ------- include/trace/sched.h | 339 -------------------------------------- include/trace/skb.h | 40 ----- kernel/exit.c | 2 +- kernel/fork.c | 3 +- kernel/irq/handle.c | 2 +- kernel/kthread.c | 2 +- kernel/lockdep.c | 2 +- kernel/sched.c | 2 +- kernel/signal.c | 2 +- kernel/softirq.c | 2 +- kernel/trace/ftrace.c | 2 +- kernel/trace/trace_sched_switch.c | 2 +- kernel/trace/trace_sched_wakeup.c | 2 +- mm/util.c | 2 +- net/core/drop_monitor.c | 2 +- net/core/net-traces.c | 2 +- net/core/skbuff.c | 2 +- 27 files changed, 708 insertions(+), 707 deletions(-) create mode 100644 include/trace/events/irq.h create mode 100644 include/trace/events/kmem.h create mode 100644 include/trace/events/lockdep.h create mode 100644 include/trace/events/sched.h create mode 100644 include/trace/events/skb.h delete mode 100644 include/trace/irq.h delete mode 100644 include/trace/kmem.h delete mode 100644 include/trace/lockdep.h delete mode 100644 include/trace/sched.h delete mode 100644 include/trace/skb.h (limited to 'kernel/exit.c') diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h index 15c45a27a92..b616d3930c3 100644 --- a/include/linux/kmemtrace.h +++ b/include/linux/kmemtrace.h @@ -9,7 +9,7 @@ #ifdef __KERNEL__ -#include +#include #ifdef CONFIG_KMEMTRACE extern void kmemtrace_init(void); diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index 980eb66a6e3..18869417109 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -43,7 +43,7 @@ #endif #ifndef TRACE_INCLUDE_PATH -# define __TRACE_INCLUDE(system) +# define __TRACE_INCLUDE(system) # define UNDEF_TRACE_INCLUDE_FILE #else # define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h) diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h new file mode 100644 index 00000000000..75e3468e449 --- /dev/null +++ b/include/trace/events/irq.h @@ -0,0 +1,57 @@ +#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IRQ_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM irq + +/* + * Tracepoint for entry of interrupt handler: + */ +TRACE_FORMAT(irq_handler_entry, + TP_PROTO(int irq, struct irqaction *action), + TP_ARGS(irq, action), + TP_FMT("irq=%d handler=%s", irq, action->name) + ); + +/* + * Tracepoint for return of an interrupt handler: + */ +TRACE_EVENT(irq_handler_exit, + + TP_PROTO(int irq, struct irqaction *action, int ret), + + TP_ARGS(irq, action, ret), + + TP_STRUCT__entry( + __field( int, irq ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->ret = ret; + ), + + TP_printk("irq=%d return=%s", + __entry->irq, __entry->ret ? "handled" : "unhandled") +); + +TRACE_FORMAT(softirq_entry, + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + TP_ARGS(h, vec), + TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) + ); + +TRACE_FORMAT(softirq_exit, + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + TP_ARGS(h, vec), + TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) + ); + +#endif /* _TRACE_IRQ_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h new file mode 100644 index 00000000000..c22c42f980b --- /dev/null +++ b/include/trace/events/kmem.h @@ -0,0 +1,194 @@ +#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KMEM_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kmem + +TRACE_EVENT(kmalloc, + + TP_PROTO(unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags), + + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( size_t, bytes_req ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + __entry->bytes_req = bytes_req; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; + ), + + TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x", + __entry->call_site, + __entry->ptr, + __entry->bytes_req, + __entry->bytes_alloc, + __entry->gfp_flags) +); + +TRACE_EVENT(kmem_cache_alloc, + + TP_PROTO(unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags), + + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( size_t, bytes_req ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + __entry->bytes_req = bytes_req; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; + ), + + TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x", + __entry->call_site, + __entry->ptr, + __entry->bytes_req, + __entry->bytes_alloc, + __entry->gfp_flags) +); + +TRACE_EVENT(kmalloc_node, + + TP_PROTO(unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node), + + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( size_t, bytes_req ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) + __field( int, node ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + __entry->bytes_req = bytes_req; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; + __entry->node = node; + ), + + TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x node=%d", + __entry->call_site, + __entry->ptr, + __entry->bytes_req, + __entry->bytes_alloc, + __entry->gfp_flags, + __entry->node) +); + +TRACE_EVENT(kmem_cache_alloc_node, + + TP_PROTO(unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node), + + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( size_t, bytes_req ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) + __field( int, node ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + __entry->bytes_req = bytes_req; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; + __entry->node = node; + ), + + TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x node=%d", + __entry->call_site, + __entry->ptr, + __entry->bytes_req, + __entry->bytes_alloc, + __entry->gfp_flags, + __entry->node) +); + +TRACE_EVENT(kfree, + + TP_PROTO(unsigned long call_site, const void *ptr), + + TP_ARGS(call_site, ptr), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + ), + + TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) +); + +TRACE_EVENT(kmem_cache_free, + + TP_PROTO(unsigned long call_site, const void *ptr), + + TP_ARGS(call_site, ptr), + + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + ), + + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + ), + + TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) +); +#endif /* _TRACE_KMEM_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h new file mode 100644 index 00000000000..45e326b5c7f --- /dev/null +++ b/include/trace/events/lockdep.h @@ -0,0 +1,60 @@ +#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_LOCKDEP_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM lockdep + +#ifdef CONFIG_LOCKDEP + +TRACE_FORMAT(lock_acquire, + TP_PROTO(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, + struct lockdep_map *next_lock, unsigned long ip), + TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip), + TP_FMT("%s%s%s", trylock ? "try " : "", + read ? "read " : "", lock->name) + ); + +TRACE_FORMAT(lock_release, + TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip), + TP_ARGS(lock, nested, ip), + TP_FMT("%s", lock->name) + ); + +#ifdef CONFIG_LOCK_STAT + +TRACE_FORMAT(lock_contended, + TP_PROTO(struct lockdep_map *lock, unsigned long ip), + TP_ARGS(lock, ip), + TP_FMT("%s", lock->name) + ); + +TRACE_EVENT(lock_acquired, + TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime), + + TP_ARGS(lock, ip, waittime), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, wait_usec) + __field(unsigned long, wait_nsec_rem) + ), + TP_fast_assign( + __entry->name = lock->name; + __entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC); + __entry->wait_usec = (unsigned long) waittime; + ), + TP_printk("%s (%lu.%03lu us)", __entry->name, __entry->wait_usec, + __entry->wait_nsec_rem) +); + +#endif +#endif + +#endif /* _TRACE_LOCKDEP_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h new file mode 100644 index 00000000000..ffa1cab586b --- /dev/null +++ b/include/trace/events/sched.h @@ -0,0 +1,339 @@ +#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SCHED_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM sched + +/* + * Tracepoint for calling kthread_stop, performed to end a kthread: + */ +TRACE_EVENT(sched_kthread_stop, + + TP_PROTO(struct task_struct *t), + + TP_ARGS(t), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + memcpy(__entry->comm, t->comm, TASK_COMM_LEN); + __entry->pid = t->pid; + ), + + TP_printk("task %s:%d", __entry->comm, __entry->pid) +); + +/* + * Tracepoint for the return value of the kthread stopping: + */ +TRACE_EVENT(sched_kthread_stop_ret, + + TP_PROTO(int ret), + + TP_ARGS(ret), + + TP_STRUCT__entry( + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ret = ret; + ), + + TP_printk("ret %d", __entry->ret) +); + +/* + * Tracepoint for waiting on task to unschedule: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wait_task, + + TP_PROTO(struct rq *rq, struct task_struct *p), + + TP_ARGS(rq, p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for waking up a task: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wakeup, + + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + + TP_ARGS(rq, p, success), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, success ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->success = success; + ), + + TP_printk("task %s:%d [%d] success=%d", + __entry->comm, __entry->pid, __entry->prio, + __entry->success) +); + +/* + * Tracepoint for waking up a new task: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wakeup_new, + + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + + TP_ARGS(rq, p, success), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, success ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->success = success; + ), + + TP_printk("task %s:%d [%d] success=%d", + __entry->comm, __entry->pid, __entry->prio, + __entry->success) +); + +/* + * Tracepoint for task switches, performed by the scheduler: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_switch, + + TP_PROTO(struct rq *rq, struct task_struct *prev, + struct task_struct *next), + + TP_ARGS(rq, prev, next), + + TP_STRUCT__entry( + __array( char, prev_comm, TASK_COMM_LEN ) + __field( pid_t, prev_pid ) + __field( int, prev_prio ) + __array( char, next_comm, TASK_COMM_LEN ) + __field( pid_t, next_pid ) + __field( int, next_prio ) + ), + + TP_fast_assign( + memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); + __entry->prev_pid = prev->pid; + __entry->prev_prio = prev->prio; + memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); + __entry->next_pid = next->pid; + __entry->next_prio = next->prio; + ), + + TP_printk("task %s:%d [%d] ==> %s:%d [%d]", + __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, + __entry->next_comm, __entry->next_pid, __entry->next_prio) +); + +/* + * Tracepoint for a task being migrated: + */ +TRACE_EVENT(sched_migrate_task, + + TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu), + + TP_ARGS(p, orig_cpu, dest_cpu), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, orig_cpu ) + __field( int, dest_cpu ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->orig_cpu = orig_cpu; + __entry->dest_cpu = dest_cpu; + ), + + TP_printk("task %s:%d [%d] from: %d to: %d", + __entry->comm, __entry->pid, __entry->prio, + __entry->orig_cpu, __entry->dest_cpu) +); + +/* + * Tracepoint for freeing a task: + */ +TRACE_EVENT(sched_process_free, + + TP_PROTO(struct task_struct *p), + + TP_ARGS(p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for a task exiting: + */ +TRACE_EVENT(sched_process_exit, + + TP_PROTO(struct task_struct *p), + + TP_ARGS(p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for a waiting task: + */ +TRACE_EVENT(sched_process_wait, + + TP_PROTO(struct pid *pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + __entry->pid = pid_nr(pid); + __entry->prio = current->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for do_fork: + */ +TRACE_EVENT(sched_process_fork, + + TP_PROTO(struct task_struct *parent, struct task_struct *child), + + TP_ARGS(parent, child), + + TP_STRUCT__entry( + __array( char, parent_comm, TASK_COMM_LEN ) + __field( pid_t, parent_pid ) + __array( char, child_comm, TASK_COMM_LEN ) + __field( pid_t, child_pid ) + ), + + TP_fast_assign( + memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN); + __entry->parent_pid = parent->pid; + memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN); + __entry->child_pid = child->pid; + ), + + TP_printk("parent %s:%d child %s:%d", + __entry->parent_comm, __entry->parent_pid, + __entry->child_comm, __entry->child_pid) +); + +/* + * Tracepoint for sending a signal: + */ +TRACE_EVENT(sched_signal_send, + + TP_PROTO(int sig, struct task_struct *p), + + TP_ARGS(sig, p), + + TP_STRUCT__entry( + __field( int, sig ) + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->sig = sig; + ), + + TP_printk("sig: %d task %s:%d", + __entry->sig, __entry->comm, __entry->pid) +); + +#endif /* _TRACE_SCHED_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h new file mode 100644 index 00000000000..1e8fabb57c0 --- /dev/null +++ b/include/trace/events/skb.h @@ -0,0 +1,40 @@ +#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SKB_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM skb + +/* + * Tracepoint for free an sk_buff: + */ +TRACE_EVENT(kfree_skb, + + TP_PROTO(struct sk_buff *skb, void *location), + + TP_ARGS(skb, location), + + TP_STRUCT__entry( + __field( void *, skbaddr ) + __field( unsigned short, protocol ) + __field( void *, location ) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + if (skb) { + __entry->protocol = ntohs(skb->protocol); + } + __entry->location = location; + ), + + TP_printk("skbaddr=%p protocol=%u location=%p", + __entry->skbaddr, __entry->protocol, __entry->location) +); + +#endif /* _TRACE_SKB_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/irq.h b/include/trace/irq.h deleted file mode 100644 index 75e3468e449..00000000000 --- a/include/trace/irq.h +++ /dev/null @@ -1,57 +0,0 @@ -#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_IRQ_H - -#include -#include - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM irq - -/* - * Tracepoint for entry of interrupt handler: - */ -TRACE_FORMAT(irq_handler_entry, - TP_PROTO(int irq, struct irqaction *action), - TP_ARGS(irq, action), - TP_FMT("irq=%d handler=%s", irq, action->name) - ); - -/* - * Tracepoint for return of an interrupt handler: - */ -TRACE_EVENT(irq_handler_exit, - - TP_PROTO(int irq, struct irqaction *action, int ret), - - TP_ARGS(irq, action, ret), - - TP_STRUCT__entry( - __field( int, irq ) - __field( int, ret ) - ), - - TP_fast_assign( - __entry->irq = irq; - __entry->ret = ret; - ), - - TP_printk("irq=%d return=%s", - __entry->irq, __entry->ret ? "handled" : "unhandled") -); - -TRACE_FORMAT(softirq_entry, - TP_PROTO(struct softirq_action *h, struct softirq_action *vec), - TP_ARGS(h, vec), - TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) - ); - -TRACE_FORMAT(softirq_exit, - TP_PROTO(struct softirq_action *h, struct softirq_action *vec), - TP_ARGS(h, vec), - TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) - ); - -#endif /* _TRACE_IRQ_H */ - -/* This part must be outside protection */ -#include diff --git a/include/trace/kmem.h b/include/trace/kmem.h deleted file mode 100644 index c22c42f980b..00000000000 --- a/include/trace/kmem.h +++ /dev/null @@ -1,194 +0,0 @@ -#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_KMEM_H - -#include -#include - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM kmem - -TRACE_EVENT(kmalloc, - - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags), - - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - ), - - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - __entry->gfp_flags) -); - -TRACE_EVENT(kmem_cache_alloc, - - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags), - - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - ), - - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - __entry->gfp_flags) -); - -TRACE_EVENT(kmalloc_node, - - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node), - - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - __field( int, node ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - __entry->node = node; - ), - - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x node=%d", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - __entry->gfp_flags, - __entry->node) -); - -TRACE_EVENT(kmem_cache_alloc_node, - - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node), - - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - __field( int, node ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - __entry->node = node; - ), - - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%08x node=%d", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - __entry->gfp_flags, - __entry->node) -); - -TRACE_EVENT(kfree, - - TP_PROTO(unsigned long call_site, const void *ptr), - - TP_ARGS(call_site, ptr), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - ), - - TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) -); - -TRACE_EVENT(kmem_cache_free, - - TP_PROTO(unsigned long call_site, const void *ptr), - - TP_ARGS(call_site, ptr), - - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - ), - - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - ), - - TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) -); -#endif /* _TRACE_KMEM_H */ - -/* This part must be outside protection */ -#include diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h deleted file mode 100644 index 45e326b5c7f..00000000000 --- a/include/trace/lockdep.h +++ /dev/null @@ -1,60 +0,0 @@ -#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_LOCKDEP_H - -#include -#include - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM lockdep - -#ifdef CONFIG_LOCKDEP - -TRACE_FORMAT(lock_acquire, - TP_PROTO(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, - struct lockdep_map *next_lock, unsigned long ip), - TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip), - TP_FMT("%s%s%s", trylock ? "try " : "", - read ? "read " : "", lock->name) - ); - -TRACE_FORMAT(lock_release, - TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip), - TP_ARGS(lock, nested, ip), - TP_FMT("%s", lock->name) - ); - -#ifdef CONFIG_LOCK_STAT - -TRACE_FORMAT(lock_contended, - TP_PROTO(struct lockdep_map *lock, unsigned long ip), - TP_ARGS(lock, ip), - TP_FMT("%s", lock->name) - ); - -TRACE_EVENT(lock_acquired, - TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime), - - TP_ARGS(lock, ip, waittime), - - TP_STRUCT__entry( - __field(const char *, name) - __field(unsigned long, wait_usec) - __field(unsigned long, wait_nsec_rem) - ), - TP_fast_assign( - __entry->name = lock->name; - __entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC); - __entry->wait_usec = (unsigned long) waittime; - ), - TP_printk("%s (%lu.%03lu us)", __entry->name, __entry->wait_usec, - __entry->wait_nsec_rem) -); - -#endif -#endif - -#endif /* _TRACE_LOCKDEP_H */ - -/* This part must be outside protection */ -#include diff --git a/include/trace/sched.h b/include/trace/sched.h deleted file mode 100644 index ffa1cab586b..00000000000 --- a/include/trace/sched.h +++ /dev/null @@ -1,339 +0,0 @@ -#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_SCHED_H - -#include -#include - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM sched - -/* - * Tracepoint for calling kthread_stop, performed to end a kthread: - */ -TRACE_EVENT(sched_kthread_stop, - - TP_PROTO(struct task_struct *t), - - TP_ARGS(t), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - ), - - TP_fast_assign( - memcpy(__entry->comm, t->comm, TASK_COMM_LEN); - __entry->pid = t->pid; - ), - - TP_printk("task %s:%d", __entry->comm, __entry->pid) -); - -/* - * Tracepoint for the return value of the kthread stopping: - */ -TRACE_EVENT(sched_kthread_stop_ret, - - TP_PROTO(int ret), - - TP_ARGS(ret), - - TP_STRUCT__entry( - __field( int, ret ) - ), - - TP_fast_assign( - __entry->ret = ret; - ), - - TP_printk("ret %d", __entry->ret) -); - -/* - * Tracepoint for waiting on task to unschedule: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) - */ -TRACE_EVENT(sched_wait_task, - - TP_PROTO(struct rq *rq, struct task_struct *p), - - TP_ARGS(rq, p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("task %s:%d [%d]", - __entry->comm, __entry->pid, __entry->prio) -); - -/* - * Tracepoint for waking up a task: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) - */ -TRACE_EVENT(sched_wakeup, - - TP_PROTO(struct rq *rq, struct task_struct *p, int success), - - TP_ARGS(rq, p, success), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - __field( int, success ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - __entry->success = success; - ), - - TP_printk("task %s:%d [%d] success=%d", - __entry->comm, __entry->pid, __entry->prio, - __entry->success) -); - -/* - * Tracepoint for waking up a new task: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) - */ -TRACE_EVENT(sched_wakeup_new, - - TP_PROTO(struct rq *rq, struct task_struct *p, int success), - - TP_ARGS(rq, p, success), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - __field( int, success ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - __entry->success = success; - ), - - TP_printk("task %s:%d [%d] success=%d", - __entry->comm, __entry->pid, __entry->prio, - __entry->success) -); - -/* - * Tracepoint for task switches, performed by the scheduler: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) - */ -TRACE_EVENT(sched_switch, - - TP_PROTO(struct rq *rq, struct task_struct *prev, - struct task_struct *next), - - TP_ARGS(rq, prev, next), - - TP_STRUCT__entry( - __array( char, prev_comm, TASK_COMM_LEN ) - __field( pid_t, prev_pid ) - __field( int, prev_prio ) - __array( char, next_comm, TASK_COMM_LEN ) - __field( pid_t, next_pid ) - __field( int, next_prio ) - ), - - TP_fast_assign( - memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); - __entry->prev_pid = prev->pid; - __entry->prev_prio = prev->prio; - memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); - __entry->next_pid = next->pid; - __entry->next_prio = next->prio; - ), - - TP_printk("task %s:%d [%d] ==> %s:%d [%d]", - __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->next_comm, __entry->next_pid, __entry->next_prio) -); - -/* - * Tracepoint for a task being migrated: - */ -TRACE_EVENT(sched_migrate_task, - - TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu), - - TP_ARGS(p, orig_cpu, dest_cpu), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - __field( int, orig_cpu ) - __field( int, dest_cpu ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - __entry->orig_cpu = orig_cpu; - __entry->dest_cpu = dest_cpu; - ), - - TP_printk("task %s:%d [%d] from: %d to: %d", - __entry->comm, __entry->pid, __entry->prio, - __entry->orig_cpu, __entry->dest_cpu) -); - -/* - * Tracepoint for freeing a task: - */ -TRACE_EVENT(sched_process_free, - - TP_PROTO(struct task_struct *p), - - TP_ARGS(p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("task %s:%d [%d]", - __entry->comm, __entry->pid, __entry->prio) -); - -/* - * Tracepoint for a task exiting: - */ -TRACE_EVENT(sched_process_exit, - - TP_PROTO(struct task_struct *p), - - TP_ARGS(p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("task %s:%d [%d]", - __entry->comm, __entry->pid, __entry->prio) -); - -/* - * Tracepoint for a waiting task: - */ -TRACE_EVENT(sched_process_wait, - - TP_PROTO(struct pid *pid), - - TP_ARGS(pid), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - __entry->pid = pid_nr(pid); - __entry->prio = current->prio; - ), - - TP_printk("task %s:%d [%d]", - __entry->comm, __entry->pid, __entry->prio) -); - -/* - * Tracepoint for do_fork: - */ -TRACE_EVENT(sched_process_fork, - - TP_PROTO(struct task_struct *parent, struct task_struct *child), - - TP_ARGS(parent, child), - - TP_STRUCT__entry( - __array( char, parent_comm, TASK_COMM_LEN ) - __field( pid_t, parent_pid ) - __array( char, child_comm, TASK_COMM_LEN ) - __field( pid_t, child_pid ) - ), - - TP_fast_assign( - memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN); - __entry->parent_pid = parent->pid; - memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN); - __entry->child_pid = child->pid; - ), - - TP_printk("parent %s:%d child %s:%d", - __entry->parent_comm, __entry->parent_pid, - __entry->child_comm, __entry->child_pid) -); - -/* - * Tracepoint for sending a signal: - */ -TRACE_EVENT(sched_signal_send, - - TP_PROTO(int sig, struct task_struct *p), - - TP_ARGS(sig, p), - - TP_STRUCT__entry( - __field( int, sig ) - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->sig = sig; - ), - - TP_printk("sig: %d task %s:%d", - __entry->sig, __entry->comm, __entry->pid) -); - -#endif /* _TRACE_SCHED_H */ - -/* This part must be outside protection */ -#include diff --git a/include/trace/skb.h b/include/trace/skb.h deleted file mode 100644 index 1e8fabb57c0..00000000000 --- a/include/trace/skb.h +++ /dev/null @@ -1,40 +0,0 @@ -#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_SKB_H - -#include -#include - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM skb - -/* - * Tracepoint for free an sk_buff: - */ -TRACE_EVENT(kfree_skb, - - TP_PROTO(struct sk_buff *skb, void *location), - - TP_ARGS(skb, location), - - TP_STRUCT__entry( - __field( void *, skbaddr ) - __field( unsigned short, protocol ) - __field( void *, location ) - ), - - TP_fast_assign( - __entry->skbaddr = skb; - if (skb) { - __entry->protocol = ntohs(skb->protocol); - } - __entry->location = location; - ), - - TP_printk("skbaddr=%p protocol=%u location=%p", - __entry->skbaddr, __entry->protocol, __entry->location) -); - -#endif /* _TRACE_SKB_H */ - -/* This part must be outside protection */ -#include diff --git a/kernel/exit.c b/kernel/exit.c index 2fe9d2c7eee..cab535c427b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -48,7 +48,7 @@ #include #include #include -#include +#include #include #include diff --git a/kernel/fork.c b/kernel/fork.c index 4bebf263923..085f73ebcea 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -61,7 +61,6 @@ #include #include #include -#include #include #include @@ -71,6 +70,8 @@ #include #include +#include + /* * Protected counters by write_lock_irq(&tasklist_lock) */ diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 983d8be8dff..37c63633e78 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -20,7 +20,7 @@ #include #define CREATE_TRACE_POINTS -#include +#include #include "internals.h" diff --git a/kernel/kthread.c b/kernel/kthread.c index e1c76924545..41c88fe4050 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #define KTHREAD_NICE_LEVEL (-5) diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 257f21a76c5..47b201ecc6d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -48,7 +48,7 @@ #include "lockdep_internals.h" #define CREATE_TRACE_POINTS -#include +#include #ifdef CONFIG_PROVE_LOCKING int prove_locking = 1; diff --git a/kernel/sched.c b/kernel/sched.c index e6d4518d47e..9f7ffd00b6e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -79,7 +79,7 @@ #include "sched_cpupri.h" #define CREATE_TRACE_POINTS -#include +#include /* * Convert user-nice values [ -20 ... 0 ... 19 ] diff --git a/kernel/signal.c b/kernel/signal.c index 1d5703ff003..94ec0a4dde0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include #include diff --git a/kernel/softirq.c b/kernel/softirq.c index a2d9b458ac2..7ab9dfd8d08 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8e6a0b5c994..a2348898858 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -29,7 +29,7 @@ #include #include -#include +#include #include diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 9d8cccdfaa0..a98106dd979 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include "trace.h" diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5bc00e8f153..b8b13c5540f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include "trace.h" diff --git a/mm/util.c b/mm/util.c index 0e74a22791c..6794a336e9a 100644 --- a/mm/util.c +++ b/mm/util.c @@ -7,7 +7,7 @@ #include #define CREATE_TRACE_POINTS -#include +#include /** * kstrdup - allocate space for and copy an existing string diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 9fd0dc3cca9..b75b6cea49d 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -23,7 +23,7 @@ #include #include -#include +#include #include diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 80177205947..499a67eaf3a 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -24,6 +24,6 @@ #include #define CREATE_TRACE_POINTS -#include +#include EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce6356cd9f7..12806b84445 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -65,7 +65,7 @@ #include #include -#include +#include #include "kmap_skb.h" -- cgit v1.2.3-70-g09d2 From 78a3d9d5654a7fd99cf8b2ab06b9497b9c7aad64 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 29 Apr 2009 18:01:23 +0200 Subject: do_wait: do take security_task_wait() into account I was never able to understand what should we actually do when security_task_wait() fails, but the current code doesn't look right. If ->task_wait() returns the error, we update *notask_error correctly. But then we either reap the child (despite the fact this was forbidden) or clear *notask_error (and hide the securiy policy problems). This patch assumes that "stolen by ptrace" doesn't matter. If selinux denies the child we should ignore it but make sure we report -EACCESS instead of -ECHLD if there are no other eligible children. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: James Morris --- kernel/exit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 167e1e3ad7c..d2e8239ea18 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1582,6 +1582,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, */ if (*notask_error) *notask_error = ret; + return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { -- cgit v1.2.3-70-g09d2 From 856d56b9e5de650a64a6c41c17aaed702b55d578 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 May 2009 20:45:59 +0200 Subject: perf_counter: Fix counter inheritance Srivatsa Vaddagiri reported that a Java workload triggers this warning in kernel/exit.c: WARN_ON_ONCE(!list_empty(&tsk->perf_counter_ctx.counter_list)); Add the inherited counter propagation on self-detach, this could cause counter leaks and incomplete stats in threaded code like the below: #include #include void *thread(void *arg) { sleep(5); return NULL; } void main(void) { pthread_t thr; pthread_create(&thr, NULL, thread, NULL); } Reported-by: Srivatsa Vaddagiri Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Corey Ashford Cc: Arnaldo Carvalho de Melo Cc: Marcelo Tosatti Signed-off-by: Ingo Molnar --- kernel/exit.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 4741376c8de..16d74f13a3e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -128,6 +128,12 @@ static void __exit_signal(struct task_struct *tsk) sig = NULL; /* Marker for below. */ } + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + */ + perf_counter_exit_task(tsk); + __unhash_process(tsk); /* -- cgit v1.2.3-70-g09d2 From 0203026b58b4299ba7281c0b4b417207c1f05d0e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 17 May 2009 11:24:08 +0200 Subject: perf_counter: fix threaded task exit Flushing counters in __exit_signal() with irqs disabled is not a good idea as perf_counter_exit_task() acquires mutexes. So flush it before acquiring the tasklist lock. (Note, we still need a fix for when the PID has been unhashed.) [ Impact: fix crash with inherited counters ] Cc: Peter Zijlstra Cc: Srivatsa Vaddagiri Cc: Paul Mackerras Cc: Corey Ashford Cc: Arnaldo Carvalho de Melo Cc: Marcelo Tosatti Signed-off-by: Ingo Molnar --- kernel/exit.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 16d74f13a3e..73affd35e76 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -128,12 +128,6 @@ static void __exit_signal(struct task_struct *tsk) sig = NULL; /* Marker for below. */ } - /* - * Flush inherited counters to the parent - before the parent - * gets woken up by child-exit notifications. - */ - perf_counter_exit_task(tsk); - __unhash_process(tsk); /* @@ -183,6 +177,13 @@ repeat: atomic_dec(&__task_cred(p)->user->processes); proc_flush_task(p); + + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + */ + perf_counter_exit_task(p); + write_lock_irq(&tasklist_lock); tracehook_finish_release_task(p); __exit_signal(p); -- cgit v1.2.3-70-g09d2 From 33b2fb303fe7f6b08bbb32f708e67b96eaa94a7a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 17 May 2009 11:08:41 +0200 Subject: perf_counter: fix counter freeing logic Fix counter lifetime bugs which explain the crashes reported by Marcelo Tosatti and Arnaldo Carvalho de Melo. The new rule is: flushing + freeing is only done for a task's own counters, never for other tasks. [ Impact: fix crashes/lockups with inherited counters ] Reported-by: Arnaldo Carvalho de Melo Reported-by: Marcelo Tosatti Acked-by: Peter Zijlstra Cc: Paul Mackerras Cc: Corey Ashford Signed-off-by: Ingo Molnar --- kernel/exit.c | 19 +++++++------------ kernel/perf_counter.c | 2 ++ 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 73affd35e76..f9dfedd94af 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -178,12 +178,6 @@ repeat: proc_flush_task(p); - /* - * Flush inherited counters to the parent - before the parent - * gets woken up by child-exit notifications. - */ - perf_counter_exit_task(p); - write_lock_irq(&tasklist_lock); tracehook_finish_release_task(p); __exit_signal(p); @@ -985,6 +979,13 @@ NORET_TYPE void do_exit(long code) module_put(tsk->binfmt->module); proc_exit_connector(tsk); + + /* + * Flush inherited counters to the parent - before the parent + * gets woken up by child-exit notifications. + */ + perf_counter_exit_task(tsk); + exit_notify(tsk, group_dead); #ifdef CONFIG_NUMA mpol_put(tsk->mempolicy); @@ -1257,12 +1258,6 @@ static int wait_task_zombie(struct task_struct *p, int options, */ read_unlock(&tasklist_lock); - /* - * Flush inherited counters to the parent - before the parent - * gets woken up by child-exit notifications. - */ - perf_counter_exit_task(p); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 59a926d04ba..7af16d1c480 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -3299,6 +3299,8 @@ void perf_counter_exit_task(struct task_struct *child) struct perf_counter *child_counter, *tmp; struct perf_counter_context *child_ctx; + WARN_ON_ONCE(child != current); + child_ctx = &child->perf_counter_ctx; if (likely(!child_ctx->nr_counters)) -- cgit v1.2.3-70-g09d2 From a63eaf34ae60bdb067a354cc8def2e8f4a01f5f4 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 22 May 2009 14:17:31 +1000 Subject: perf_counter: Dynamically allocate tasks' perf_counter_context struct This replaces the struct perf_counter_context in the task_struct with a pointer to a dynamically allocated perf_counter_context struct. The main reason for doing is this is to allow us to transfer a perf_counter_context from one task to another when we do lazy PMU switching in a later patch. This has a few side-benefits: the task_struct becomes a little smaller, we save some memory because only tasks that have perf_counters attached get a perf_counter_context allocated for them, and we can remove the inclusion of in sched.h, meaning that we don't end up recompiling nearly everything whenever perf_counter.h changes. The perf_counter_context structures are reference-counted and freed when the last reference is dropped. A context can have references from its task and the counters on its task. Counters can outlive the task so it is possible that a context will be freed well after its task has exited. Contexts are allocated on fork if the parent had a context, or otherwise the first time that a per-task counter is created on a task. In the latter case, we set the context pointer in the task struct locklessly using an atomic compare-and-exchange operation in case we raced with some other task in creating a context for the subject task. This also removes the task pointer from the perf_counter struct. The task pointer was not used anywhere and would make it harder to move a context from one task to another. Anything that needed to know which task a counter was attached to was already using counter->ctx->task. The __perf_counter_init_context function moves up in perf_counter.c so that it can be called from find_get_context, and now initializes the refcount, but is otherwise unchanged. We were potentially calling list_del_counter twice: once from __perf_counter_exit_task when the task exits and once from __perf_counter_remove_from_context when the counter's fd gets closed. This adds a check in list_del_counter so it doesn't do anything if the counter has already been removed from the lists. Since perf_counter_task_sched_in doesn't do anything if the task doesn't have a context, and leaves cpuctx->task_ctx = NULL, this adds code to __perf_install_in_context to set cpuctx->task_ctx if necessary, i.e. in the case where the current task adds the first counter to itself and thus creates a context for itself. This also adds similar code to __perf_counter_enable to handle a similar situation which can arise when the counters have been disabled using prctl; that also leaves cpuctx->task_ctx = NULL. [ Impact: refactor counter context management to prepare for new feature ] Signed-off-by: Paul Mackerras Acked-by: Peter Zijlstra Cc: Corey Ashford Cc: Marcelo Tosatti Cc: Arnaldo Carvalho de Melo LKML-Reference: <18966.10075.781053.231153@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/apic.c | 1 + include/linux/init_task.h | 13 --- include/linux/perf_counter.h | 4 +- include/linux/sched.h | 6 +- kernel/exit.c | 3 +- kernel/fork.c | 1 + kernel/perf_counter.c | 218 +++++++++++++++++++++++++++---------------- 7 files changed, 145 insertions(+), 101 deletions(-) (limited to 'kernel/exit.c') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e9021a90802..b4f64402a82 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -14,6 +14,7 @@ * Mikael Pettersson : PM converted to driver model. */ +#include #include #include #include diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 503afaa0afa..d87247d2641 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -108,18 +108,6 @@ extern struct group_info init_groups; extern struct cred init_cred; -#ifdef CONFIG_PERF_COUNTERS -# define INIT_PERF_COUNTERS(tsk) \ - .perf_counter_ctx.counter_list = \ - LIST_HEAD_INIT(tsk.perf_counter_ctx.counter_list), \ - .perf_counter_ctx.event_list = \ - LIST_HEAD_INIT(tsk.perf_counter_ctx.event_list), \ - .perf_counter_ctx.lock = \ - __SPIN_LOCK_UNLOCKED(tsk.perf_counter_ctx.lock), -#else -# define INIT_PERF_COUNTERS(tsk) -#endif - /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -183,7 +171,6 @@ extern struct cred init_cred; }, \ .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ INIT_IDS \ - INIT_PERF_COUNTERS(tsk) \ INIT_TRACE_IRQFLAGS \ INIT_LOCKDEP \ INIT_FTRACE_GRAPH \ diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index f612941ef46..07130900546 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -449,7 +449,6 @@ struct perf_counter { struct hw_perf_counter hw; struct perf_counter_context *ctx; - struct task_struct *task; struct file *filp; struct perf_counter *parent; @@ -498,7 +497,6 @@ struct perf_counter { * Used as a container for task counters and CPU counters as well: */ struct perf_counter_context { -#ifdef CONFIG_PERF_COUNTERS /* * Protect the states of the counters in the list, * nr_active, and the list: @@ -516,6 +514,7 @@ struct perf_counter_context { int nr_counters; int nr_active; int is_active; + atomic_t refcount; struct task_struct *task; /* @@ -523,7 +522,6 @@ struct perf_counter_context { */ u64 time; u64 timestamp; -#endif }; /** diff --git a/include/linux/sched.h b/include/linux/sched.h index ff59d123151..9714d450f41 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -71,7 +71,6 @@ struct sched_param { #include #include #include -#include #include #include #include @@ -99,6 +98,7 @@ struct robust_list_head; struct bio; struct bts_tracer; struct fs_struct; +struct perf_counter_context; /* * List of flags we want to share for kernel threads, @@ -1387,7 +1387,9 @@ struct task_struct { struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; #endif - struct perf_counter_context perf_counter_ctx; +#ifdef CONFIG_PERF_COUNTERS + struct perf_counter_context *perf_counter_ctxp; +#endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; short il_next; diff --git a/kernel/exit.c b/kernel/exit.c index f9dfedd94af..99ad4063ee4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -159,7 +160,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp) struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); #ifdef CONFIG_PERF_COUNTERS - WARN_ON_ONCE(!list_empty(&tsk->perf_counter_ctx.counter_list)); + WARN_ON_ONCE(tsk->perf_counter_ctxp); #endif trace_sched_process_free(tsk); put_task_struct(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index d32fef4d38e..e72a09f5355 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 08584c16049..06ea3eae886 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -97,6 +97,17 @@ void perf_enable(void) hw_perf_enable(); } +static void get_ctx(struct perf_counter_context *ctx) +{ + atomic_inc(&ctx->refcount); +} + +static void put_ctx(struct perf_counter_context *ctx) +{ + if (atomic_dec_and_test(&ctx->refcount)) + kfree(ctx); +} + static void list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx) { @@ -118,11 +129,17 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx) ctx->nr_counters++; } +/* + * Remove a counter from the lists for its context. + * Must be called with counter->mutex and ctx->mutex held. + */ static void list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx) { struct perf_counter *sibling, *tmp; + if (list_empty(&counter->list_entry)) + return; ctx->nr_counters--; list_del_init(&counter->list_entry); @@ -216,8 +233,6 @@ static void __perf_counter_remove_from_context(void *info) counter_sched_out(counter, cpuctx, ctx); - counter->task = NULL; - list_del_counter(counter, ctx); if (!ctx->task) { @@ -279,7 +294,6 @@ retry: */ if (!list_empty(&counter->list_entry)) { list_del_counter(counter, ctx); - counter->task = NULL; } spin_unlock_irq(&ctx->lock); } @@ -568,11 +582,17 @@ static void __perf_install_in_context(void *info) * If this is a task context, we need to check whether it is * the current task context of this cpu. If not it has been * scheduled out before the smp call arrived. + * Or possibly this is the right context but it isn't + * on this cpu because it had no counters. */ - if (ctx->task && cpuctx->task_ctx != ctx) - return; + if (ctx->task && cpuctx->task_ctx != ctx) { + if (cpuctx->task_ctx || ctx->task != current) + return; + cpuctx->task_ctx = ctx; + } spin_lock_irqsave(&ctx->lock, flags); + ctx->is_active = 1; update_context_time(ctx); /* @@ -653,7 +673,6 @@ perf_install_in_context(struct perf_counter_context *ctx, return; } - counter->task = task; retry: task_oncpu_function_call(task, __perf_install_in_context, counter); @@ -693,10 +712,14 @@ static void __perf_counter_enable(void *info) * If this is a per-task counter, need to check whether this * counter's task is the current task on this cpu. */ - if (ctx->task && cpuctx->task_ctx != ctx) - return; + if (ctx->task && cpuctx->task_ctx != ctx) { + if (cpuctx->task_ctx || ctx->task != current) + return; + cpuctx->task_ctx = ctx; + } spin_lock_irqsave(&ctx->lock, flags); + ctx->is_active = 1; update_context_time(ctx); counter->prev_state = counter->state; @@ -852,10 +875,10 @@ void __perf_counter_sched_out(struct perf_counter_context *ctx, void perf_counter_task_sched_out(struct task_struct *task, int cpu) { struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu); - struct perf_counter_context *ctx = &task->perf_counter_ctx; + struct perf_counter_context *ctx = task->perf_counter_ctxp; struct pt_regs *regs; - if (likely(!cpuctx->task_ctx)) + if (likely(!ctx || !cpuctx->task_ctx)) return; update_context_time(ctx); @@ -871,6 +894,8 @@ static void __perf_counter_task_sched_out(struct perf_counter_context *ctx) { struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); + if (!cpuctx->task_ctx) + return; __perf_counter_sched_out(ctx, cpuctx); cpuctx->task_ctx = NULL; } @@ -969,8 +994,10 @@ __perf_counter_sched_in(struct perf_counter_context *ctx, void perf_counter_task_sched_in(struct task_struct *task, int cpu) { struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu); - struct perf_counter_context *ctx = &task->perf_counter_ctx; + struct perf_counter_context *ctx = task->perf_counter_ctxp; + if (likely(!ctx)) + return; __perf_counter_sched_in(ctx, cpuctx, cpu); cpuctx->task_ctx = ctx; } @@ -985,11 +1012,11 @@ static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu) int perf_counter_task_disable(void) { struct task_struct *curr = current; - struct perf_counter_context *ctx = &curr->perf_counter_ctx; + struct perf_counter_context *ctx = curr->perf_counter_ctxp; struct perf_counter *counter; unsigned long flags; - if (likely(!ctx->nr_counters)) + if (!ctx || !ctx->nr_counters) return 0; local_irq_save(flags); @@ -1020,12 +1047,12 @@ int perf_counter_task_disable(void) int perf_counter_task_enable(void) { struct task_struct *curr = current; - struct perf_counter_context *ctx = &curr->perf_counter_ctx; + struct perf_counter_context *ctx = curr->perf_counter_ctxp; struct perf_counter *counter; unsigned long flags; int cpu; - if (likely(!ctx->nr_counters)) + if (!ctx || !ctx->nr_counters) return 0; local_irq_save(flags); @@ -1128,19 +1155,23 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu) return; cpuctx = &per_cpu(perf_cpu_context, cpu); - ctx = &curr->perf_counter_ctx; + ctx = curr->perf_counter_ctxp; perf_adjust_freq(&cpuctx->ctx); - perf_adjust_freq(ctx); + if (ctx) + perf_adjust_freq(ctx); perf_counter_cpu_sched_out(cpuctx); - __perf_counter_task_sched_out(ctx); + if (ctx) + __perf_counter_task_sched_out(ctx); rotate_ctx(&cpuctx->ctx); - rotate_ctx(ctx); + if (ctx) + rotate_ctx(ctx); perf_counter_cpu_sched_in(cpuctx, cpu); - perf_counter_task_sched_in(curr, cpu); + if (ctx) + perf_counter_task_sched_in(curr, cpu); } /* @@ -1176,6 +1207,22 @@ static u64 perf_counter_read(struct perf_counter *counter) return atomic64_read(&counter->count); } +/* + * Initialize the perf_counter context in a task_struct: + */ +static void +__perf_counter_init_context(struct perf_counter_context *ctx, + struct task_struct *task) +{ + memset(ctx, 0, sizeof(*ctx)); + spin_lock_init(&ctx->lock); + mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->counter_list); + INIT_LIST_HEAD(&ctx->event_list); + atomic_set(&ctx->refcount, 1); + ctx->task = task; +} + static void put_context(struct perf_counter_context *ctx) { if (ctx->task) @@ -1186,6 +1233,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu) { struct perf_cpu_context *cpuctx; struct perf_counter_context *ctx; + struct perf_counter_context *tctx; struct task_struct *task; /* @@ -1225,15 +1273,36 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu) if (!task) return ERR_PTR(-ESRCH); - ctx = &task->perf_counter_ctx; - ctx->task = task; - /* Reuse ptrace permission checks for now. */ if (!ptrace_may_access(task, PTRACE_MODE_READ)) { - put_context(ctx); + put_task_struct(task); return ERR_PTR(-EACCES); } + ctx = task->perf_counter_ctxp; + if (!ctx) { + ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL); + if (!ctx) { + put_task_struct(task); + return ERR_PTR(-ENOMEM); + } + __perf_counter_init_context(ctx, task); + /* + * Make sure other cpus see correct values for *ctx + * once task->perf_counter_ctxp is visible to them. + */ + smp_wmb(); + tctx = cmpxchg(&task->perf_counter_ctxp, NULL, ctx); + if (tctx) { + /* + * We raced with some other task; use + * the context they set. + */ + kfree(ctx); + ctx = tctx; + } + } + return ctx; } @@ -1242,6 +1311,7 @@ static void free_counter_rcu(struct rcu_head *head) struct perf_counter *counter; counter = container_of(head, struct perf_counter, rcu_head); + put_ctx(counter->ctx); kfree(counter); } @@ -2247,7 +2317,7 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event) perf_counter_comm_ctx(&cpuctx->ctx, comm_event); put_cpu_var(perf_cpu_context); - perf_counter_comm_ctx(¤t->perf_counter_ctx, comm_event); + perf_counter_comm_ctx(current->perf_counter_ctxp, comm_event); } void perf_counter_comm(struct task_struct *task) @@ -2256,7 +2326,9 @@ void perf_counter_comm(struct task_struct *task) if (!atomic_read(&nr_comm_tracking)) return; - + if (!current->perf_counter_ctxp) + return; + comm_event = (struct perf_comm_event){ .task = task, .event = { @@ -2372,7 +2444,7 @@ got_name: perf_counter_mmap_ctx(&cpuctx->ctx, mmap_event); put_cpu_var(perf_cpu_context); - perf_counter_mmap_ctx(¤t->perf_counter_ctx, mmap_event); + perf_counter_mmap_ctx(current->perf_counter_ctxp, mmap_event); kfree(buf); } @@ -2384,6 +2456,8 @@ void perf_counter_mmap(unsigned long addr, unsigned long len, if (!atomic_read(&nr_mmap_tracking)) return; + if (!current->perf_counter_ctxp) + return; mmap_event = (struct perf_mmap_event){ .file = file, @@ -2985,6 +3059,7 @@ perf_counter_alloc(struct perf_counter_hw_event *hw_event, counter->group_leader = group_leader; counter->pmu = NULL; counter->ctx = ctx; + get_ctx(ctx); counter->state = PERF_COUNTER_STATE_INACTIVE; if (hw_event->disabled) @@ -3149,21 +3224,6 @@ err_put_context: goto out_fput; } -/* - * Initialize the perf_counter context in a task_struct: - */ -static void -__perf_counter_init_context(struct perf_counter_context *ctx, - struct task_struct *task) -{ - memset(ctx, 0, sizeof(*ctx)); - spin_lock_init(&ctx->lock); - mutex_init(&ctx->mutex); - INIT_LIST_HEAD(&ctx->counter_list); - INIT_LIST_HEAD(&ctx->event_list); - ctx->task = task; -} - /* * inherit a counter from parent task to child task: */ @@ -3195,7 +3255,6 @@ inherit_counter(struct perf_counter *parent_counter, /* * Link it up in the child's context: */ - child_counter->task = child; add_counter_to_ctx(child_counter, child_ctx); child_counter->parent = parent_counter; @@ -3294,40 +3353,15 @@ __perf_counter_exit_task(struct task_struct *child, struct perf_counter *parent_counter; /* - * If we do not self-reap then we have to wait for the - * child task to unschedule (it will happen for sure), - * so that its counter is at its final count. (This - * condition triggers rarely - child tasks usually get - * off their CPU before the parent has a chance to - * get this far into the reaping action) + * Protect against concurrent operations on child_counter + * due its fd getting closed, etc. */ - if (child != current) { - wait_task_inactive(child, 0); - update_counter_times(child_counter); - list_del_counter(child_counter, child_ctx); - } else { - struct perf_cpu_context *cpuctx; - unsigned long flags; - - /* - * Disable and unlink this counter. - * - * Be careful about zapping the list - IRQ/NMI context - * could still be processing it: - */ - local_irq_save(flags); - perf_disable(); - - cpuctx = &__get_cpu_var(perf_cpu_context); + mutex_lock(&child_counter->mutex); - group_sched_out(child_counter, cpuctx, child_ctx); - update_counter_times(child_counter); + update_counter_times(child_counter); + list_del_counter(child_counter, child_ctx); - list_del_counter(child_counter, child_ctx); - - perf_enable(); - local_irq_restore(flags); - } + mutex_unlock(&child_counter->mutex); parent_counter = child_counter->parent; /* @@ -3346,19 +3380,29 @@ __perf_counter_exit_task(struct task_struct *child, * * Note: we may be running in child context, but the PID is not hashed * anymore so new counters will not be added. + * (XXX not sure that is true when we get called from flush_old_exec. + * -- paulus) */ void perf_counter_exit_task(struct task_struct *child) { struct perf_counter *child_counter, *tmp; struct perf_counter_context *child_ctx; + unsigned long flags; WARN_ON_ONCE(child != current); - child_ctx = &child->perf_counter_ctx; + child_ctx = child->perf_counter_ctxp; - if (likely(!child_ctx->nr_counters)) + if (likely(!child_ctx)) return; + local_irq_save(flags); + __perf_counter_task_sched_out(child_ctx); + child->perf_counter_ctxp = NULL; + local_irq_restore(flags); + + mutex_lock(&child_ctx->mutex); + again: list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list, list_entry) @@ -3371,6 +3415,10 @@ again: */ if (!list_empty(&child_ctx->counter_list)) goto again; + + mutex_unlock(&child_ctx->mutex); + + put_ctx(child_ctx); } /* @@ -3382,19 +3430,25 @@ void perf_counter_init_task(struct task_struct *child) struct perf_counter *counter; struct task_struct *parent = current; - child_ctx = &child->perf_counter_ctx; - parent_ctx = &parent->perf_counter_ctx; - - __perf_counter_init_context(child_ctx, child); + child->perf_counter_ctxp = NULL; /* * This is executed from the parent task context, so inherit - * counters that have been marked for cloning: + * counters that have been marked for cloning. + * First allocate and initialize a context for the child. */ - if (likely(!parent_ctx->nr_counters)) + child_ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL); + if (!child_ctx) + return; + + parent_ctx = parent->perf_counter_ctxp; + if (likely(!parent_ctx || !parent_ctx->nr_counters)) return; + __perf_counter_init_context(child_ctx, child); + child->perf_counter_ctxp = child_ctx; + /* * Lock the parent list. No need to lock the child - not PID * hashed yet and not running, so nobody can access it. -- cgit v1.2.3-70-g09d2 From 87245135d5057edd5a8037131f81eeffd76d4fef Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:23 -0700 Subject: allow_signal: kill the bogus ->mm check, add a note about CLONE_SIGHAND allow_signal() checks ->mm == NULL. Not sure why. Perhaps to make sure current is the kernel thread. But this helper must not be used unless we are the kernel thread, kill this check. Also, document the fact that the CLONE_SIGHAND kthread must not use allow_signal(), unless the caller really wants to change the parent's ->sighand->action as well. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index b6c90b5ef50..533e5f85669 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -375,9 +375,8 @@ static void set_special_pids(struct pid *pid) } /* - * Let kernel threads use this to say that they - * allow a certain signal (since daemonize() will - * have disabled all of them by default). + * Let kernel threads use this to say that they allow a certain signal. + * Must not be used if kthread was cloned with CLONE_SIGHAND. */ int allow_signal(int sig) { @@ -385,14 +384,14 @@ int allow_signal(int sig) return -EINVAL; spin_lock_irq(¤t->sighand->siglock); + /* This is only needed for daemonize()'ed kthreads */ sigdelset(¤t->blocked, sig); - if (!current->mm) { - /* Kernel threads handle their own signals. - Let the signal code know it'll be handled, so - that they don't get converted to SIGKILL or - just silently dropped */ - current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; - } + /* + * Kernel threads handle their own signals. Let the signal code + * know it'll be handled, so that they don't get converted to + * SIGKILL or just silently dropped. + */ + current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); return 0; -- cgit v1.2.3-70-g09d2 From dea33cfd99022d82d923a0c6a3bd895fb6683fb2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:29 -0700 Subject: ptrace: mm_need_new_owner: use ->real_parent to search in the siblings "Search in the siblings" should use ->real_parent, not ->parent. If the task is traced then ->parent == tracer, while the task's parent is always ->real_parent. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 533e5f85669..213f906f5e1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -590,7 +590,7 @@ retry: /* * Search in the siblings */ - list_for_each_entry(c, &p->parent->children, sibling) { + list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } -- cgit v1.2.3-70-g09d2 From 5cb11446892833e50970fb2277a9f7563b0a8bd3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:30 -0700 Subject: ptrace: do not use task->ptrace directly in core kernel No functional changes. - Nobody except ptrace.c & co should use ptrace flags directly, we have task_ptrace() for that. - No need to specially check PT_PTRACED, we must not have other PT_ bits set without PT_PTRACED. And no need to know this flag exists. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 6 +++--- kernel/signal.c | 10 +++++----- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 213f906f5e1..938cceebb9a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -757,7 +757,7 @@ static void reparent_thread(struct task_struct *father, struct task_struct *p, p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ - if (!p->ptrace && + if (!task_ptrace(p) && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { do_notify_parent(p, p->exit_signal); if (task_detached(p)) { @@ -782,7 +782,7 @@ static void forget_original_parent(struct task_struct *father) list_for_each_entry_safe(p, n, &father->children, sibling) { p->real_parent = reaper; if (p->parent == father) { - BUG_ON(p->ptrace); + BUG_ON(task_ptrace(p)); p->parent = p->real_parent; } reparent_thread(father, p, &dead_children); @@ -1482,7 +1482,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, return 0; } - if (likely(!ptrace) && unlikely(p->ptrace)) { + if (likely(!ptrace) && unlikely(task_ptrace(p))) { /* * This child is hidden by ptrace. * We aren't allowed to see it now, but eventually we will. diff --git a/kernel/signal.c b/kernel/signal.c index d81f4952eeb..09ccc1c0e1f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1410,7 +1410,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) /* do_notify_parent_cldstop should have been called instead. */ BUG_ON(task_is_stopped_or_traced(tsk)); - BUG_ON(!tsk->ptrace && + BUG_ON(!task_ptrace(tsk) && (tsk->group_leader != tsk || !thread_group_empty(tsk))); info.si_signo = sig; @@ -1449,7 +1449,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) psig = tsk->parent->sighand; spin_lock_irqsave(&psig->siglock, flags); - if (!tsk->ptrace && sig == SIGCHLD && + if (!task_ptrace(tsk) && sig == SIGCHLD && (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { /* @@ -1486,7 +1486,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) struct task_struct *parent; struct sighand_struct *sighand; - if (tsk->ptrace & PT_PTRACED) + if (task_ptrace(tsk)) parent = tsk->parent; else { tsk = tsk->group_leader; @@ -1535,7 +1535,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) static inline int may_ptrace_stop(void) { - if (!likely(current->ptrace & PT_PTRACED)) + if (!likely(task_ptrace(current))) return 0; /* * Are we in the middle of do_coredump? @@ -1753,7 +1753,7 @@ static int do_signal_stop(int signr) static int ptrace_signal(int signr, siginfo_t *info, struct pt_regs *regs, void *cookie) { - if (!(current->ptrace & PT_PTRACED)) + if (!task_ptrace(current)) return signr; ptrace_signal_deliver(regs, cookie); -- cgit v1.2.3-70-g09d2 From d1e98f429aa10132b3010ba3b0be47552a2eb14b Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:34 -0700 Subject: ptrace: wait_task_zombie: s/->parent/->real_parent/ Change wait_task_zombie() to use ->real_parent instead of ->parent. We could even use current afaics, but ->real_parent is more clean. We know that the child is not ptrace_reparented() and thus they are equal. But we should avoid using task_struct->parent, we are going to remove it. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 938cceebb9a..826e1dc8168 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1204,7 +1204,7 @@ static int wait_task_zombie(struct task_struct *p, int options, * p->signal fields, because they are only touched by * __exit_signal, which runs with tasklist_lock * write-locked anyway, and so is excluded here. We do - * need to protect the access to p->parent->signal fields, + * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. * @@ -1213,8 +1213,8 @@ static int wait_task_zombie(struct task_struct *p, int options, * group including the group leader. */ thread_group_cputime(p, &cputime); - spin_lock_irq(&p->parent->sighand->siglock); - psig = p->parent->signal; + spin_lock_irq(&p->real_parent->sighand->siglock); + psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, @@ -1245,7 +1245,7 @@ static int wait_task_zombie(struct task_struct *p, int options, sig->oublock + sig->coublock; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); - spin_unlock_irq(&p->parent->sighand->siglock); + spin_unlock_irq(&p->real_parent->sighand->siglock); } /* -- cgit v1.2.3-70-g09d2 From 77d1ef79568b337f599b75795acc8f78a87ba9ba Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:36 -0700 Subject: wait_task_zombie: do not use thread_group_cputime() There is no reason for thread_group_cputime() in wait_task_zombie(), there must be no other threads. This call was previously needed to collect the per-cpu data which we do not have any longer. Signed-off-by: Oleg Nesterov Cc: Peter Zijlstra Acked-by: Roland McGrath Cc: Stanislaw Gruszka Cc: Vitaly Mayatskikh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 826e1dc8168..94a9992e6fd 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1191,7 +1191,6 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; - struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1207,23 +1206,20 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. - * - * We use thread_group_cputime() to get times for the thread - * group, which consolidates times for all threads in the - * group including the group leader. */ - thread_group_cputime(p, &cputime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, - cputime_add(cputime.utime, - sig->cutime)); + cputime_add(p->utime, + cputime_add(sig->utime, + sig->cutime))); psig->cstime = cputime_add(psig->cstime, - cputime_add(cputime.stime, - sig->cstime)); + cputime_add(p->stime, + cputime_add(sig->stime, + sig->cstime))); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, -- cgit v1.2.3-70-g09d2 From 47918025efdabd34e96b13b26eb2cf2fd6fd1f7c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:39 -0700 Subject: shift "ptrace implies WUNTRACED" from ptrace_do_wait() to wait_task_stopped() No functional changes, preparation for the next patch. ptrace_do_wait() adds WUNTRACED to options for wait_task_stopped() which should always accept the stopped tracee, even if do_wait() was called without WUNTRACED. Change wait_task_stopped() to check "ptrace || WUNTRACED" instead. This makes the code more explicit, and "int options" argument becomes const in do_wait() pathes. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 94a9992e6fd..fd781b56401 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1330,7 +1330,10 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; - if (!(options & WUNTRACED)) + /* + * Traditionally we see ptrace'd stopped tasks regardless of options. + */ + if (!ptrace && !(options & WUNTRACED)) return 0; exit_code = 0; @@ -1548,11 +1551,6 @@ static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, { struct task_struct *p; - /* - * Traditionally we see ptrace'd stopped tasks regardless of options. - */ - options |= WUNTRACED; - list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(tsk, 1, p, notask_error, type, pid, options, -- cgit v1.2.3-70-g09d2 From 9e8ae01d1c86dcaa6443c897662545d088036e4c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:39 -0700 Subject: introduce "struct wait_opts" to simplify do_wait() patches Introduce "struct wait_opts" which holds the parameters for misc helpers in do_wait() pathes. This adds 13 lines to kernel/exit.c, but saves 256 bytes from .o and imho makes the code much more readable. This patch temporary uglifies rusage/siginfo code a little bit, will be addressed by further cleanups. Signed-off-by: Oleg Nesterov Reviewed-by: Ingo Molnar Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 207 +++++++++++++++++++++++++++++++--------------------------- 1 file changed, 110 insertions(+), 97 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index fd781b56401..29622e468b7 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1080,6 +1080,18 @@ SYSCALL_DEFINE1(exit_group, int, error_code) return 0; } +struct wait_opts { + enum pid_type wo_type; + struct pid *wo_pid; + int wo_flags; + + struct siginfo __user *wo_info; + int __user *wo_stat; + struct rusage __user *wo_rusage; + + int notask_error; +}; + static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid = NULL; @@ -1090,13 +1102,12 @@ static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) return pid; } -static int eligible_child(enum pid_type type, struct pid *pid, int options, - struct task_struct *p) +static int eligible_child(struct wait_opts *wo, struct task_struct *p) { int err; - if (type < PIDTYPE_MAX) { - if (task_pid_type(p, type) != pid) + if (wo->wo_type < PIDTYPE_MAX) { + if (task_pid_type(p, wo->wo_type) != wo->wo_pid) return 0; } @@ -1105,8 +1116,8 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, * set; otherwise, wait for non-clone children *only*. (Note: * A "clone" child here is one that reports to its parent * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0)) - && !(options & __WALL)) + if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) + && !(wo->wo_flags & __WALL)) return 0; err = security_task_wait(p); @@ -1116,14 +1127,15 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, return 1; } -static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, - int why, int status, - struct siginfo __user *infop, - struct rusage __user *rusagep) +static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, + pid_t pid, uid_t uid, int why, int status) { - int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + struct siginfo __user *infop; + int retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); + infop = wo->wo_info; if (!retval) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval) @@ -1147,19 +1159,18 @@ static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_zombie(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); uid_t uid = __task_cred(p)->uid; + struct siginfo __user *infop; - if (!likely(options & WEXITED)) + if (!likely(wo->wo_flags & WEXITED)) return 0; - if (unlikely(options & WNOWAIT)) { + if (unlikely(wo->wo_flags & WNOWAIT)) { int exit_code = p->exit_code; int why, status; @@ -1172,8 +1183,7 @@ static int wait_task_zombie(struct task_struct *p, int options, why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; status = exit_code & 0x7f; } - return wait_noreap_copyout(p, pid, uid, why, - status, infop, ru); + return wait_noreap_copyout(wo, p, pid, uid, why, status); } /* @@ -1250,11 +1260,14 @@ static int wait_task_zombie(struct task_struct *p, int options, */ read_unlock(&tasklist_lock); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; - if (!retval && stat_addr) - retval = put_user(status, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(status, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1322,10 +1335,10 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace) * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_stopped(int ptrace, struct task_struct *p, - int options, struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_stopped(struct wait_opts *wo, + int ptrace, struct task_struct *p) { + struct siginfo __user *infop; int retval, exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; @@ -1333,7 +1346,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ - if (!ptrace && !(options & WUNTRACED)) + if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; exit_code = 0; @@ -1347,7 +1360,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, if (!exit_code) goto unlock_sig; - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; /* don't need the RCU readlock here as we're holding a spinlock */ @@ -1369,14 +1382,15 @@ unlock_sig: why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); - if (unlikely(options & WNOWAIT)) - return wait_noreap_copyout(p, pid, uid, - why, exit_code, - infop, ru); + if (unlikely(wo->wo_flags & WNOWAIT)) + return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); + + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (!retval && wo->wo_stat) + retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; - if (!retval && stat_addr) - retval = put_user((exit_code << 8) | 0x7f, stat_addr); + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1403,15 +1417,13 @@ unlock_sig: * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_continued(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { int retval; pid_t pid; uid_t uid; - if (!unlikely(options & WCONTINUED)) + if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) @@ -1423,7 +1435,7 @@ static int wait_task_continued(struct task_struct *p, int options, spin_unlock_irq(&p->sighand->siglock); return 0; } - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = __task_cred(p)->uid; spin_unlock_irq(&p->sighand->siglock); @@ -1432,17 +1444,17 @@ static int wait_task_continued(struct task_struct *p, int options, get_task_struct(p); read_unlock(&tasklist_lock); - if (!infop) { - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + if (!wo->wo_info) { + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); - if (!retval && stat_addr) - retval = put_user(0xffff, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(0xffff, wo->wo_stat); if (!retval) retval = pid; } else { - retval = wait_noreap_copyout(p, pid, uid, - CLD_CONTINUED, SIGCONT, - infop, ru); + retval = wait_noreap_copyout(wo, p, pid, uid, + CLD_CONTINUED, SIGCONT); BUG_ON(retval == 0); } @@ -1452,19 +1464,16 @@ static int wait_task_continued(struct task_struct *p, int options, /* * Consider @p for a wait by @parent. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; - * then *@notask_error is 0 if @p is an eligible child, + * then ->notask_error is 0 if @p is an eligible child, * or another error from security_task_wait(), or still -ECHILD. */ -static int wait_consider_task(struct task_struct *parent, int ptrace, - struct task_struct *p, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent, + int ptrace, struct task_struct *p) { - int ret = eligible_child(type, pid, options, p); + int ret = eligible_child(wo, p); if (!ret) return ret; @@ -1476,8 +1485,8 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, * to look for security policy problems, rather * than for mysterious wait bugs. */ - if (*notask_error) - *notask_error = ret; + if (wo->notask_error) + wo->notask_error = ret; return 0; } @@ -1486,7 +1495,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, * This child is hidden by ptrace. * We aren't allowed to see it now, but eventually we will. */ - *notask_error = 0; + wo->notask_error = 0; return 0; } @@ -1497,34 +1506,30 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, * We don't reap group leaders with subthreads. */ if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) - return wait_task_zombie(p, options, infop, stat_addr, ru); + return wait_task_zombie(wo, p); /* * It's stopped or running now, so it might * later continue, exit, or stop again. */ - *notask_error = 0; + wo->notask_error = 0; if (task_stopped_code(p, ptrace)) - return wait_task_stopped(ptrace, p, options, - infop, stat_addr, ru); + return wait_task_stopped(wo, ptrace, p); - return wait_task_continued(p, options, infop, stat_addr, ru); + return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then - * *@notask_error is 0 if there were any eligible children, + * ->notask_error is 0 if there were any eligible children, * or another error from security_task_wait(), or still -ECHILD. */ -static int do_wait_thread(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; @@ -1533,9 +1538,7 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error, * Do not consider detached threads. */ if (!task_detached(p)) { - int ret = wait_consider_task(tsk, 0, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 0, p); if (ret) return ret; } @@ -1544,17 +1547,12 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error, return 0; } -static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { - int ret = wait_consider_task(tsk, 1, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 1, p); if (ret) return ret; } @@ -1562,38 +1560,36 @@ static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, return 0; } -static long do_wait(enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static long do_wait(struct wait_opts *wo) { DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; int retval; - trace_sched_process_wait(pid); + trace_sched_process_wait(wo->wo_pid); add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: /* * If there is nothing that can match our critiera just get out. - * We will clear @retval to zero if we see any child that might later - * match our criteria, even if we are not able to reap it yet. + * We will clear ->notask_error to zero if we see any child that + * might later match our criteria, even if we are not able to reap + * it yet. */ - retval = -ECHILD; - if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type]))) + retval = wo->notask_error = -ECHILD; + if ((wo->wo_type < PIDTYPE_MAX) && + (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) goto end; current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); tsk = current; do { - int tsk_result = do_wait_thread(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); + int tsk_result = do_wait_thread(wo, tsk); + if (!tsk_result) - tsk_result = ptrace_do_wait(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); + tsk_result = ptrace_do_wait(wo, tsk); + if (tsk_result) { /* * tasklist_lock is unlocked and we have a final result. @@ -1602,25 +1598,27 @@ repeat: goto end; } - if (options & __WNOTHREAD) + if (wo->wo_flags & __WNOTHREAD) break; tsk = next_thread(tsk); BUG_ON(tsk->signal != current->signal); } while (tsk != current); read_unlock(&tasklist_lock); - if (!retval && !(options & WNOHANG)) { + retval = wo->notask_error; + if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } - end: current->state = TASK_RUNNING; remove_wait_queue(¤t->signal->wait_chldexit,&wait); - if (infop) { + if (wo->wo_info) { + struct siginfo __user *infop = wo->wo_info; + if (retval > 0) retval = 0; else { @@ -1649,6 +1647,7 @@ end: SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1678,7 +1677,14 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (type < PIDTYPE_MAX) pid = find_get_pid(upid); - ret = do_wait(type, pid, options, infop, NULL, ru); + + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options; + wo.wo_info = infop; + wo.wo_stat = NULL; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ @@ -1689,6 +1695,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1710,7 +1717,13 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, pid = find_get_pid(upid); } - ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru); + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options | WEXITED; + wo.wo_info = NULL; + wo.wo_stat = stat_addr; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ -- cgit v1.2.3-70-g09d2 From 64a16caf5e3417ee32f670debcb5857b02a9e08e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:40 -0700 Subject: do_wait: simplify retval/tsk_result/notask_error mess Now that we don't pass &retval down to other helpers we can simplify the code more. - kill tsk_result, just use retval - add the "notask" label right after the main loop, and s/got end/goto notask/ after the fastpath pid check. This way we don't need to initialize retval before this check and the code becomes a bit more clean, if this pid has no attached tasks we should just skip the list search. Signed-off-by: Oleg Nesterov Cc: Ingo Molnar Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 29622e468b7..9c6881a0a8b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1576,27 +1576,22 @@ repeat: * might later match our criteria, even if we are not able to reap * it yet. */ - retval = wo->notask_error = -ECHILD; + wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) - goto end; + goto notask; current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); tsk = current; do { - int tsk_result = do_wait_thread(wo, tsk); - - if (!tsk_result) - tsk_result = ptrace_do_wait(wo, tsk); + retval = do_wait_thread(wo, tsk); + if (retval) + goto end; - if (tsk_result) { - /* - * tasklist_lock is unlocked and we have a final result. - */ - retval = tsk_result; + retval = ptrace_do_wait(wo, tsk); + if (retval) goto end; - } if (wo->wo_flags & __WNOTHREAD) break; @@ -1605,6 +1600,7 @@ repeat: } while (tsk != current); read_unlock(&tasklist_lock); +notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; -- cgit v1.2.3-70-g09d2 From a3f6dfb7295facb0505b5beca5a7ce48b0612379 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:41 -0700 Subject: do_wait: kill the old BUG_ON, use while_each_thread() do_wait() does BUG_ON(tsk->signal != current->signal), this looks like a raher obsolete check. At least, I don't think do_wait() is the best place to verify that all threads have the same ->signal. Remove it. Also, change the code to use while_each_thread(). Signed-off-by: Oleg Nesterov Cc: Ingo Molnar Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 9c6881a0a8b..dd83c841910 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1595,9 +1595,7 @@ repeat: if (wo->wo_flags & __WNOTHREAD) break; - tsk = next_thread(tsk); - BUG_ON(tsk->signal != current->signal); - } while (tsk != current); + } while_each_thread(current, tsk); read_unlock(&tasklist_lock); notask: -- cgit v1.2.3-70-g09d2 From f95d39d10fe7d47336e65172f52bf64e0096f983 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 17 Jun 2009 16:27:42 -0700 Subject: do_wait: fix the theoretical race with stop/trace/cont do_wait: current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); ... search for the task to reap ... In theory, the ->state changing can leak into the critical section. Since the child can change its status under read_lock(tasklist) in parallel (finish_stop/ptrace_stop), we can miss the wakeup if __wake_up_parent() sees us in TASK_RUNNING state. Add the barrier. Also, use __set_current_state() to set TASK_RUNNING. Signed-off-by: Oleg Nesterov Cc: Ingo Molnar Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index dd83c841910..7ef355dd3dc 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1581,7 +1581,7 @@ repeat: (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) goto notask; - current->state = TASK_INTERRUPTIBLE; + set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); tsk = current; do { @@ -1608,7 +1608,7 @@ notask: } } end: - current->state = TASK_RUNNING; + __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit,&wait); if (wo->wo_info) { struct siginfo __user *infop = wo->wo_info; -- cgit v1.2.3-70-g09d2 From e1eb1ebcca871673c76caf63335c4237680040f1 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Wed, 17 Jun 2009 16:27:42 -0700 Subject: mm: exit.c reorder wait_opts to remove padding on 64 bit builds Reorder struct wait_opts to remove 8 bytes of alignment padding on 64 bit builds. Signed-off-by: Richard Kennedy Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 7ef355dd3dc..13ae64001fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1082,8 +1082,8 @@ SYSCALL_DEFINE1(exit_group, int, error_code) struct wait_opts { enum pid_type wo_type; - struct pid *wo_pid; int wo_flags; + struct pid *wo_pid; struct siginfo __user *wo_info; int __user *wo_stat; -- cgit v1.2.3-70-g09d2 From befca96779b0259ac8fad0183e748a62935c39cb Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 18 Jun 2009 16:49:11 -0700 Subject: ptrace: wait_task_zombie: do not account traced sub-threads The bug is ancient. If we trace the sub-thread of our natural child and this sub-thread exits, we update parent->signal->cxxx fields. But we should not do this until the whole thread-group exits, otherwise we account this thread (and all other live threads) twice. Add the task_detached() check. No need to check thread_group_empty(), wait_consider_task()->delay_group_leader() already did this. Signed-off-by: Oleg Nesterov Cc: Peter Zijlstra Acked-by: Roland McGrath Cc: Stanislaw Gruszka Cc: Vitaly Mayatskikh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 13ae64001fe..628d41f0dd5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1197,8 +1197,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) } traced = ptrace_reparented(p); - - if (likely(!traced)) { + /* + * It can be ptraced but not reparented, check + * !task_detached() to filter out sub-threads. + */ + if (likely(!traced) && likely(!task_detached(p))) { struct signal_struct *psig; struct signal_struct *sig; -- cgit v1.2.3-70-g09d2