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>
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index af961d6..642928c 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -306,9 +306,10 @@
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
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 76c5c8b..7602ccb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1272,7 +1272,8 @@
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
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ea7a203..5a8671e 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -73,6 +73,9 @@
__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 @@
)
TP_perf_assign(
__perf_count(delay);
+ __perf_task(tsk);
),
TP_printk("comm=%s pid=%d delay=%Lu [ns]",
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6bc2fa..a763888 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -712,6 +712,9 @@
#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 @@
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 @@
\
head = this_cpu_ptr(event_call->perf_events); \
perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \
- __count, &__regs, head); \
+ __count, &__regs, head, __task); \
}
/*
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 6581a04..98d4597 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -153,7 +153,8 @@
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 @@
}
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);
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f1cf0ed..b7935fc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4039,7 +4039,7 @@
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 @@
}
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 @@
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);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index b0b107f..a096c19 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -101,7 +101,8 @@
}
/* 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);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index fee3752..8a6d2ee 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -281,7 +281,7 @@
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
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b31d3d5..1a21170 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1002,7 +1002,8 @@
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 @@
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 */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 96fc733..60e4d78 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -532,7 +532,7 @@
(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 @@
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)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 2b36ac6..03003cd 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -670,7 +670,7 @@
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();