perf/trace: Add ability to set a target task for events
A few events are interesting not only for a current task. For example, sched_stat_* events are interesting for a task which wakes up. For this reason, it will be good if such events will be delivered to a target task too. Now a target task can be set by using __perf_task(). The original idea and a draft patch belongs to Peter Zijlstra. I need these events for profiling sleep times. sched_switch is used for getting callchains and sched_stat_* is used for getting time periods. These events are combined in user space, then it can be analyzed by perf tools. Inspired-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Arun Sharma <asharma@fb.com> Signed-off-by: Andrew Vagin <avagin@openvz.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1342016098-213063-1-git-send-email-avagin@openvz.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
d07bdfd322
commit
e6dab5ffab
|
@ -306,9 +306,10 @@ extern void *perf_trace_buf_prepare(int size, unsigned short type,
|
|||
|
||||
static inline void
|
||||
perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
|
||||
u64 count, struct pt_regs *regs, void *head)
|
||||
u64 count, struct pt_regs *regs, void *head,
|
||||
struct task_struct *task)
|
||||
{
|
||||
perf_tp_event(addr, count, raw_data, size, regs, head, rctx);
|
||||
perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task);
|
||||
}
|
||||
#endif
|
||||
|
||||
|
|
|
@ -1272,7 +1272,8 @@ static inline bool perf_paranoid_kernel(void)
|
|||
extern void perf_event_init(void);
|
||||
extern void perf_tp_event(u64 addr, u64 count, void *record,
|
||||
int entry_size, struct pt_regs *regs,
|
||||
struct hlist_head *head, int rctx);
|
||||
struct hlist_head *head, int rctx,
|
||||
struct task_struct *task);
|
||||
extern void perf_bp_event(struct perf_event *event, void *data);
|
||||
|
||||
#ifndef perf_misc_flags
|
||||
|
|
|
@ -73,6 +73,9 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
|
|||
__entry->prio = p->prio;
|
||||
__entry->success = success;
|
||||
__entry->target_cpu = task_cpu(p);
|
||||
)
|
||||
TP_perf_assign(
|
||||
__perf_task(p);
|
||||
),
|
||||
|
||||
TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
|
||||
|
@ -325,6 +328,7 @@ DECLARE_EVENT_CLASS(sched_stat_template,
|
|||
)
|
||||
TP_perf_assign(
|
||||
__perf_count(delay);
|
||||
__perf_task(tsk);
|
||||
),
|
||||
|
||||
TP_printk("comm=%s pid=%d delay=%Lu [ns]",
|
||||
|
|
|
@ -712,6 +712,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
|
|||
#undef __perf_count
|
||||
#define __perf_count(c) __count = (c)
|
||||
|
||||
#undef __perf_task
|
||||
#define __perf_task(t) __task = (t)
|
||||
|
||||
#undef TP_perf_assign
|
||||
#define TP_perf_assign(args...) args
|
||||
|
||||
|
@ -725,6 +728,7 @@ perf_trace_##call(void *__data, proto) \
|
|||
struct ftrace_raw_##call *entry; \
|
||||
struct pt_regs __regs; \
|
||||
u64 __addr = 0, __count = 1; \
|
||||
struct task_struct *__task = NULL; \
|
||||
struct hlist_head *head; \
|
||||
int __entry_size; \
|
||||
int __data_size; \
|
||||
|
@ -752,7 +756,7 @@ perf_trace_##call(void *__data, proto) \
|
|||
\
|
||||
head = this_cpu_ptr(event_call->perf_events); \
|
||||
perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \
|
||||
__count, &__regs, head); \
|
||||
__count, &__regs, head, __task); \
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
|
@ -153,7 +153,8 @@ put_callchain_entry(int rctx)
|
|||
put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
|
||||
}
|
||||
|
||||
struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
|
||||
struct perf_callchain_entry *
|
||||
perf_callchain(struct perf_event *event, struct pt_regs *regs)
|
||||
{
|
||||
int rctx;
|
||||
struct perf_callchain_entry *entry;
|
||||
|
@ -178,6 +179,12 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
|
|||
}
|
||||
|
||||
if (regs) {
|
||||
/*
|
||||
* Disallow cross-task user callchains.
|
||||
*/
|
||||
if (event->ctx->task && event->ctx->task != current)
|
||||
goto exit_put;
|
||||
|
||||
perf_callchain_store(entry, PERF_CONTEXT_USER);
|
||||
perf_callchain_user(entry, regs);
|
||||
}
|
||||
|
|
|
@ -4039,7 +4039,7 @@ void perf_prepare_sample(struct perf_event_header *header,
|
|||
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
|
||||
int size = 1;
|
||||
|
||||
data->callchain = perf_callchain(regs);
|
||||
data->callchain = perf_callchain(event, regs);
|
||||
|
||||
if (data->callchain)
|
||||
size += data->callchain->nr;
|
||||
|
@ -5209,7 +5209,8 @@ static int perf_tp_event_match(struct perf_event *event,
|
|||
}
|
||||
|
||||
void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
|
||||
struct pt_regs *regs, struct hlist_head *head, int rctx)
|
||||
struct pt_regs *regs, struct hlist_head *head, int rctx,
|
||||
struct task_struct *task)
|
||||
{
|
||||
struct perf_sample_data data;
|
||||
struct perf_event *event;
|
||||
|
@ -5228,6 +5229,31 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
|
|||
perf_swevent_event(event, count, &data, regs);
|
||||
}
|
||||
|
||||
/*
|
||||
* If we got specified a target task, also iterate its context and
|
||||
* deliver this event there too.
|
||||
*/
|
||||
if (task && task != current) {
|
||||
struct perf_event_context *ctx;
|
||||
struct trace_entry *entry = record;
|
||||
|
||||
rcu_read_lock();
|
||||
ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]);
|
||||
if (!ctx)
|
||||
goto unlock;
|
||||
|
||||
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
|
||||
if (event->attr.type != PERF_TYPE_TRACEPOINT)
|
||||
continue;
|
||||
if (event->attr.config != entry->type)
|
||||
continue;
|
||||
if (perf_tp_event_match(event, &data, regs))
|
||||
perf_swevent_event(event, count, &data, regs);
|
||||
}
|
||||
unlock:
|
||||
rcu_read_unlock();
|
||||
}
|
||||
|
||||
perf_swevent_put_recursion_context(rctx);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(perf_tp_event);
|
||||
|
|
|
@ -101,7 +101,8 @@ __output_copy(struct perf_output_handle *handle,
|
|||
}
|
||||
|
||||
/* Callchain handling */
|
||||
extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
|
||||
extern struct perf_callchain_entry *
|
||||
perf_callchain(struct perf_event *event, struct pt_regs *regs);
|
||||
extern int get_callchain_buffers(void);
|
||||
extern void put_callchain_buffers(void);
|
||||
|
||||
|
|
|
@ -281,7 +281,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
|
|||
|
||||
head = this_cpu_ptr(event_function.perf_events);
|
||||
perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
|
||||
1, ®s, head);
|
||||
1, ®s, head, NULL);
|
||||
|
||||
#undef ENTRY_SIZE
|
||||
}
|
||||
|
|
|
@ -1002,7 +1002,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
|
|||
store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
|
||||
|
||||
head = this_cpu_ptr(call->perf_events);
|
||||
perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
|
||||
perf_trace_buf_submit(entry, size, rctx,
|
||||
entry->ip, 1, regs, head, NULL);
|
||||
}
|
||||
|
||||
/* Kretprobe profile handler */
|
||||
|
@ -1033,7 +1034,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
|
|||
store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
|
||||
|
||||
head = this_cpu_ptr(call->perf_events);
|
||||
perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
|
||||
perf_trace_buf_submit(entry, size, rctx,
|
||||
entry->ret_ip, 1, regs, head, NULL);
|
||||
}
|
||||
#endif /* CONFIG_PERF_EVENTS */
|
||||
|
||||
|
|
|
@ -532,7 +532,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
|
|||
(unsigned long *)&rec->args);
|
||||
|
||||
head = this_cpu_ptr(sys_data->enter_event->perf_events);
|
||||
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
|
||||
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
|
||||
}
|
||||
|
||||
int perf_sysenter_enable(struct ftrace_event_call *call)
|
||||
|
@ -608,7 +608,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
|
|||
rec->ret = syscall_get_return_value(current, regs);
|
||||
|
||||
head = this_cpu_ptr(sys_data->exit_event->perf_events);
|
||||
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
|
||||
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
|
||||
}
|
||||
|
||||
int perf_sysexit_enable(struct ftrace_event_call *call)
|
||||
|
|
|
@ -670,7 +670,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
|
|||
call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
|
||||
|
||||
head = this_cpu_ptr(call->perf_events);
|
||||
perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
|
||||
perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL);
|
||||
|
||||
out:
|
||||
preempt_enable();
|
||||
|
|
Loading…
Reference in New Issue