summaryrefslogtreecommitdiffstats
path: root/include/linux
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2009-08-07 01:25:54 +0200
committerIngo Molnar <mingo@elte.hu>2009-08-09 12:53:48 +0200
commitf413cdb80ce00ec1a4d0ab949b5d96c81cae7f75 (patch)
tree08a9621cb1318f73a37faeed14c4e728408551ad /include/linux
parent3a6593050fbd8bbcaed3a44d01c31d907315c86c (diff)
downloadop-kernel-dev-f413cdb80ce00ec1a4d0ab949b5d96c81cae7f75.zip
op-kernel-dev-f413cdb80ce00ec1a4d0ab949b5d96c81cae7f75.tar.gz
perf_counter: Fix/complete ftrace event records sampling
This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/ftrace_event.h4
-rw-r--r--include/linux/perf_counter.h9
2 files changed, 11 insertions, 2 deletions
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index d7cd193..a81170d 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -89,7 +89,9 @@ enum print_line_t {
TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */
};
-
+void tracing_generic_entry_update(struct trace_entry *entry,
+ unsigned long flags,
+ int pc);
struct ring_buffer_event *
trace_current_buffer_lock_reserve(int type, unsigned long len,
unsigned long flags, int pc);
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index e604e6e..a67dd5c 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -121,8 +121,9 @@ enum perf_counter_sample_format {
PERF_SAMPLE_CPU = 1U << 7,
PERF_SAMPLE_PERIOD = 1U << 8,
PERF_SAMPLE_STREAM_ID = 1U << 9,
+ PERF_SAMPLE_TP_RECORD = 1U << 10,
- PERF_SAMPLE_MAX = 1U << 10, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */
};
/*
@@ -413,6 +414,11 @@ struct perf_callchain_entry {
__u64 ip[PERF_MAX_STACK_DEPTH];
};
+struct perf_tracepoint_record {
+ int size;
+ char *record;
+};
+
struct task_struct;
/**
@@ -681,6 +687,7 @@ struct perf_sample_data {
struct pt_regs *regs;
u64 addr;
u64 period;
+ void *private;
};
extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
OpenPOWER on IntegriCloud