perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
|
|
|
#ifndef __PERF_RECORD_H
|
|
|
|
#define __PERF_RECORD_H
|
2009-09-25 00:02:18 +08:00
|
|
|
|
2009-12-28 07:37:00 +08:00
|
|
|
#include <limits.h>
|
2011-12-02 21:06:37 +08:00
|
|
|
#include <stdio.h>
|
2009-12-28 07:37:00 +08:00
|
|
|
|
2009-08-12 16:19:53 +08:00
|
|
|
#include "../perf.h"
|
2009-12-28 07:37:00 +08:00
|
|
|
#include "map.h"
|
2012-10-28 05:18:29 +08:00
|
|
|
#include "build-id.h"
|
perf tools: Cache register accesses for unwind processing
Caching registers value into an array. Got about 4% speed up
of perf_reg_value function for report command processing
dwarf unwind stacks.
Output from report over 1.5 GB data with DWARF unwind stacks:
(TODO fix perf diff)
current code:
5.84% perf perf [.] perf_reg_value
change:
1.94% perf perf [.] perf_reg_value
And little bit of overall speed up:
(perf stat -r 5 -e '{cycles,instructions}:u' ...)
current code:
310,298,611,754 cycles ( +- 0.33% )
439,669,689,341 instructions ( +- 0.03% )
188.656753166 seconds time elapsed ( +- 0.82% )
change:
291,315,329,878 cycles ( +- 0.22% )
391,763,485,304 instructions ( +- 0.03% )
180.742249687 seconds time elapsed ( +- 0.64% )
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1401892622-30848-2-git-send-email-jolsa@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-04-18 01:39:10 +08:00
|
|
|
#include "perf_regs.h"
|
2009-08-12 16:19:53 +08:00
|
|
|
|
|
|
|
struct mmap_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u32 pid, tid;
|
|
|
|
u64 start;
|
|
|
|
u64 len;
|
|
|
|
u64 pgoff;
|
|
|
|
char filename[PATH_MAX];
|
|
|
|
};
|
|
|
|
|
2013-08-21 18:10:25 +08:00
|
|
|
struct mmap2_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u32 pid, tid;
|
|
|
|
u64 start;
|
|
|
|
u64 len;
|
|
|
|
u64 pgoff;
|
|
|
|
u32 maj;
|
|
|
|
u32 min;
|
|
|
|
u64 ino;
|
|
|
|
u64 ino_generation;
|
2014-05-20 03:13:49 +08:00
|
|
|
u32 prot;
|
|
|
|
u32 flags;
|
2013-08-21 18:10:25 +08:00
|
|
|
char filename[PATH_MAX];
|
|
|
|
};
|
|
|
|
|
2009-08-12 16:19:53 +08:00
|
|
|
struct comm_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u32 pid, tid;
|
|
|
|
char comm[16];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct fork_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u32 pid, ppid;
|
|
|
|
u32 tid, ptid;
|
2009-09-12 13:52:47 +08:00
|
|
|
u64 time;
|
2009-08-12 16:19:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct lost_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u64 id;
|
|
|
|
u64 lost;
|
|
|
|
};
|
|
|
|
|
2009-08-13 17:47:55 +08:00
|
|
|
/*
|
|
|
|
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
|
|
|
|
*/
|
2009-08-12 16:19:53 +08:00
|
|
|
struct read_event {
|
|
|
|
struct perf_event_header header;
|
2009-09-16 19:45:00 +08:00
|
|
|
u32 pid, tid;
|
2009-08-12 16:19:53 +08:00
|
|
|
u64 value;
|
|
|
|
u64 time_enabled;
|
|
|
|
u64 time_running;
|
|
|
|
u64 id;
|
|
|
|
};
|
|
|
|
|
2013-09-01 18:36:15 +08:00
|
|
|
struct throttle_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u64 time;
|
|
|
|
u64 id;
|
|
|
|
u64 stream_id;
|
|
|
|
};
|
2011-05-22 01:33:04 +08:00
|
|
|
|
|
|
|
#define PERF_SAMPLE_MASK \
|
|
|
|
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | \
|
|
|
|
PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \
|
|
|
|
PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \
|
2013-08-27 16:23:09 +08:00
|
|
|
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \
|
|
|
|
PERF_SAMPLE_IDENTIFIER)
|
2011-05-22 01:33:04 +08:00
|
|
|
|
2013-10-02 21:46:39 +08:00
|
|
|
/* perf sample has 16 bits size limit */
|
|
|
|
#define PERF_SAMPLE_MAX_SIZE (1 << 16)
|
|
|
|
|
2009-12-06 19:08:24 +08:00
|
|
|
struct sample_event {
|
2009-09-12 13:53:00 +08:00
|
|
|
struct perf_event_header header;
|
|
|
|
u64 array[];
|
|
|
|
};
|
|
|
|
|
2012-08-07 21:20:45 +08:00
|
|
|
struct regs_dump {
|
2013-08-27 16:23:10 +08:00
|
|
|
u64 abi;
|
2014-01-07 20:47:25 +08:00
|
|
|
u64 mask;
|
2012-08-07 21:20:45 +08:00
|
|
|
u64 *regs;
|
perf tools: Cache register accesses for unwind processing
Caching registers value into an array. Got about 4% speed up
of perf_reg_value function for report command processing
dwarf unwind stacks.
Output from report over 1.5 GB data with DWARF unwind stacks:
(TODO fix perf diff)
current code:
5.84% perf perf [.] perf_reg_value
change:
1.94% perf perf [.] perf_reg_value
And little bit of overall speed up:
(perf stat -r 5 -e '{cycles,instructions}:u' ...)
current code:
310,298,611,754 cycles ( +- 0.33% )
439,669,689,341 instructions ( +- 0.03% )
188.656753166 seconds time elapsed ( +- 0.82% )
change:
291,315,329,878 cycles ( +- 0.22% )
391,763,485,304 instructions ( +- 0.03% )
180.742249687 seconds time elapsed ( +- 0.64% )
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1401892622-30848-2-git-send-email-jolsa@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
2014-04-18 01:39:10 +08:00
|
|
|
|
|
|
|
/* Cached values/mask filled by first register access. */
|
|
|
|
u64 cache_regs[PERF_REGS_MAX];
|
|
|
|
u64 cache_mask;
|
2012-08-07 21:20:45 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct stack_dump {
|
|
|
|
u16 offset;
|
|
|
|
u64 size;
|
|
|
|
char *data;
|
|
|
|
};
|
|
|
|
|
2012-10-10 23:38:13 +08:00
|
|
|
struct sample_read_value {
|
|
|
|
u64 value;
|
|
|
|
u64 id;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct sample_read {
|
|
|
|
u64 time_enabled;
|
|
|
|
u64 time_running;
|
|
|
|
union {
|
|
|
|
struct {
|
|
|
|
u64 nr;
|
|
|
|
struct sample_read_value *values;
|
|
|
|
} group;
|
|
|
|
struct sample_read_value one;
|
|
|
|
};
|
|
|
|
};
|
|
|
|
|
2014-05-05 18:41:45 +08:00
|
|
|
struct ip_callchain {
|
|
|
|
u64 nr;
|
|
|
|
u64 ips[0];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct branch_flags {
|
|
|
|
u64 mispred:1;
|
|
|
|
u64 predicted:1;
|
|
|
|
u64 in_tx:1;
|
|
|
|
u64 abort:1;
|
|
|
|
u64 reserved:60;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct branch_entry {
|
|
|
|
u64 from;
|
|
|
|
u64 to;
|
|
|
|
struct branch_flags flags;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct branch_stack {
|
|
|
|
u64 nr;
|
|
|
|
struct branch_entry entries[0];
|
|
|
|
};
|
|
|
|
|
2014-10-30 22:09:42 +08:00
|
|
|
enum {
|
|
|
|
PERF_IP_FLAG_BRANCH = 1ULL << 0,
|
|
|
|
PERF_IP_FLAG_CALL = 1ULL << 1,
|
|
|
|
PERF_IP_FLAG_RETURN = 1ULL << 2,
|
|
|
|
PERF_IP_FLAG_CONDITIONAL = 1ULL << 3,
|
|
|
|
PERF_IP_FLAG_SYSCALLRET = 1ULL << 4,
|
|
|
|
PERF_IP_FLAG_ASYNC = 1ULL << 5,
|
|
|
|
PERF_IP_FLAG_INTERRUPT = 1ULL << 6,
|
|
|
|
PERF_IP_FLAG_TX_ABORT = 1ULL << 7,
|
|
|
|
PERF_IP_FLAG_TRACE_BEGIN = 1ULL << 8,
|
|
|
|
PERF_IP_FLAG_TRACE_END = 1ULL << 9,
|
|
|
|
PERF_IP_FLAG_IN_TX = 1ULL << 10,
|
|
|
|
};
|
|
|
|
|
|
|
|
#define PERF_BRANCH_MASK (\
|
|
|
|
PERF_IP_FLAG_BRANCH |\
|
|
|
|
PERF_IP_FLAG_CALL |\
|
|
|
|
PERF_IP_FLAG_RETURN |\
|
|
|
|
PERF_IP_FLAG_CONDITIONAL |\
|
|
|
|
PERF_IP_FLAG_SYSCALLRET |\
|
|
|
|
PERF_IP_FLAG_ASYNC |\
|
|
|
|
PERF_IP_FLAG_INTERRUPT |\
|
|
|
|
PERF_IP_FLAG_TX_ABORT |\
|
|
|
|
PERF_IP_FLAG_TRACE_BEGIN |\
|
|
|
|
PERF_IP_FLAG_TRACE_END)
|
|
|
|
|
2011-01-29 23:02:00 +08:00
|
|
|
struct perf_sample {
|
2009-12-06 19:08:24 +08:00
|
|
|
u64 ip;
|
|
|
|
u32 pid, tid;
|
|
|
|
u64 time;
|
|
|
|
u64 addr;
|
|
|
|
u64 id;
|
|
|
|
u64 stream_id;
|
|
|
|
u64 period;
|
2013-01-24 23:10:29 +08:00
|
|
|
u64 weight;
|
2013-09-20 22:40:43 +08:00
|
|
|
u64 transaction;
|
perf tools: Reorganize some structs to save space
Using 'pahole --packable' I found some structs that could be reorganized
to eliminate alignment holes, in some cases getting them to be cacheline
multiples.
[acme@doppio linux-2.6-tip]$ codiff perf.old ~/bin/perf
builtin-annotate.c:
struct perf_session | -8
struct perf_header | -8
2 structs changed
builtin-diff.c:
struct sample_data | -8
1 struct changed
diff__process_sample_event | -8
1 function changed, 8 bytes removed, diff: -8
builtin-sched.c:
struct sched_atom | -8
1 struct changed
builtin-timechart.c:
struct per_pid | -8
1 struct changed
cmd_timechart | -16
1 function changed, 16 bytes removed, diff: -16
builtin-probe.c:
struct perf_probe_point | -8
struct perf_probe_event | -8
2 structs changed
opt_add_probe_event | -3
1 function changed, 3 bytes removed, diff: -3
util/probe-finder.c:
struct probe_finder | -8
1 struct changed
find_kprobe_trace_events | -16
1 function changed, 16 bytes removed, diff: -16
/home/acme/bin/perf:
4 functions changed, 43 bytes removed, diff: -43
[acme@doppio linux-2.6-tip]$
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-05 23:53:45 +08:00
|
|
|
u32 cpu;
|
2009-12-06 19:08:24 +08:00
|
|
|
u32 raw_size;
|
2013-01-24 23:10:35 +08:00
|
|
|
u64 data_src;
|
2014-07-31 14:01:04 +08:00
|
|
|
u32 flags;
|
|
|
|
u16 insn_len;
|
2009-12-06 19:08:24 +08:00
|
|
|
void *raw_data;
|
perf tools: Reorganize some structs to save space
Using 'pahole --packable' I found some structs that could be reorganized
to eliminate alignment holes, in some cases getting them to be cacheline
multiples.
[acme@doppio linux-2.6-tip]$ codiff perf.old ~/bin/perf
builtin-annotate.c:
struct perf_session | -8
struct perf_header | -8
2 structs changed
builtin-diff.c:
struct sample_data | -8
1 struct changed
diff__process_sample_event | -8
1 function changed, 8 bytes removed, diff: -8
builtin-sched.c:
struct sched_atom | -8
1 struct changed
builtin-timechart.c:
struct per_pid | -8
1 struct changed
cmd_timechart | -16
1 function changed, 16 bytes removed, diff: -16
builtin-probe.c:
struct perf_probe_point | -8
struct perf_probe_event | -8
2 structs changed
opt_add_probe_event | -3
1 function changed, 3 bytes removed, diff: -3
util/probe-finder.c:
struct probe_finder | -8
1 struct changed
find_kprobe_trace_events | -16
1 function changed, 16 bytes removed, diff: -16
/home/acme/bin/perf:
4 functions changed, 43 bytes removed, diff: -43
[acme@doppio linux-2.6-tip]$
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-05 23:53:45 +08:00
|
|
|
struct ip_callchain *callchain;
|
2012-02-10 06:21:01 +08:00
|
|
|
struct branch_stack *branch_stack;
|
2012-08-07 21:20:45 +08:00
|
|
|
struct regs_dump user_regs;
|
2014-09-24 19:48:39 +08:00
|
|
|
struct regs_dump intr_regs;
|
2012-08-07 21:20:45 +08:00
|
|
|
struct stack_dump user_stack;
|
2012-10-10 23:38:13 +08:00
|
|
|
struct sample_read read;
|
2009-12-06 19:08:24 +08:00
|
|
|
};
|
|
|
|
|
2013-01-24 23:10:35 +08:00
|
|
|
#define PERF_MEM_DATA_SRC_NONE \
|
|
|
|
(PERF_MEM_S(OP, NA) |\
|
|
|
|
PERF_MEM_S(LVL, NA) |\
|
|
|
|
PERF_MEM_S(SNOOP, NA) |\
|
|
|
|
PERF_MEM_S(LOCK, NA) |\
|
|
|
|
PERF_MEM_S(TLB, NA))
|
|
|
|
|
perf symbols: Use the buildids if present
With this change 'perf record' will intercept PERF_RECORD_MMAP
calls, creating a linked list of DSOs, then when the session
finishes, it will traverse this list and read the buildids,
stashing them at the end of the file and will set up a new
feature bit in the header bitmask.
'perf report' will then notice this feature and populate the
'dsos' list and set the build ids.
When reading the symtabs it will refuse to load from a file that
doesn't have the same build id. This improves the
reliability of the profiler output, as symbols and profiling
data is more guaranteed to match.
Example:
[root@doppio ~]# perf report | head
/home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols
# Samples: 2621434559
#
# Overhead Command Shared Object Symbol
# ........ ............... ............................. ......
#
7.91% init [kernel] [k] read_hpet
7.64% init [kernel] [k] mwait_idle_with_hints
7.60% swapper [kernel] [k] read_hpet
7.60% swapper [kernel] [k] mwait_idle_with_hints
3.65% init [kernel] [k] 0xffffffffa02339d9
[root@doppio ~]#
In this case the 'perf' binary was an older one, vanished,
so its symbols probably wouldn't match or would cause subtly
different (and misleading) output.
Next patches will support the kernel as well, reading the build
id notes for it and the modules from /sys.
Another patch should also introduce a new plumbing command:
'perf list-buildids'
that will then be used in porcelain that is distro specific to
fetch -debuginfo packages where such buildids are present. This
will in turn allow for one to run 'perf record' in one machine
and 'perf report' in another.
Future work on having the buildid sent directly from the kernel
in the PERF_RECORD_MMAP event is needed to close races, as the
DSO can be changed during a 'perf record' session, but this
patch at least helps with non-corner cases and current/older
kernels.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: K. Prasad <prasad@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roland McGrath <roland@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
|
|
|
struct build_id_event {
|
|
|
|
struct perf_event_header header;
|
2010-04-19 13:32:50 +08:00
|
|
|
pid_t pid;
|
2012-09-11 06:15:01 +08:00
|
|
|
u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
|
perf symbols: Use the buildids if present
With this change 'perf record' will intercept PERF_RECORD_MMAP
calls, creating a linked list of DSOs, then when the session
finishes, it will traverse this list and read the buildids,
stashing them at the end of the file and will set up a new
feature bit in the header bitmask.
'perf report' will then notice this feature and populate the
'dsos' list and set the build ids.
When reading the symtabs it will refuse to load from a file that
doesn't have the same build id. This improves the
reliability of the profiler output, as symbols and profiling
data is more guaranteed to match.
Example:
[root@doppio ~]# perf report | head
/home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols
# Samples: 2621434559
#
# Overhead Command Shared Object Symbol
# ........ ............... ............................. ......
#
7.91% init [kernel] [k] read_hpet
7.64% init [kernel] [k] mwait_idle_with_hints
7.60% swapper [kernel] [k] read_hpet
7.60% swapper [kernel] [k] mwait_idle_with_hints
3.65% init [kernel] [k] 0xffffffffa02339d9
[root@doppio ~]#
In this case the 'perf' binary was an older one, vanished,
so its symbols probably wouldn't match or would cause subtly
different (and misleading) output.
Next patches will support the kernel as well, reading the build
id notes for it and the modules from /sys.
Another patch should also introduce a new plumbing command:
'perf list-buildids'
that will then be used in porcelain that is distro specific to
fetch -debuginfo packages where such buildids are present. This
will in turn allow for one to run 'perf record' in one machine
and 'perf report' in another.
Future work on having the buildid sent directly from the kernel
in the PERF_RECORD_MMAP event is needed to close races, as the
DSO can be changed during a 'perf record' session, but this
patch at least helps with non-corner cases and current/older
kernels.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: K. Prasad <prasad@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roland McGrath <roland@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
|
|
|
char filename[];
|
|
|
|
};
|
2009-09-12 13:53:00 +08:00
|
|
|
|
2010-05-03 04:05:29 +08:00
|
|
|
enum perf_user_event_type { /* above any possible kernel type */
|
2010-12-07 20:48:47 +08:00
|
|
|
PERF_RECORD_USER_TYPE_START = 64,
|
2010-04-02 12:59:19 +08:00
|
|
|
PERF_RECORD_HEADER_ATTR = 64,
|
2013-07-11 23:28:33 +08:00
|
|
|
PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */
|
2010-04-02 12:59:21 +08:00
|
|
|
PERF_RECORD_HEADER_TRACING_DATA = 66,
|
2010-04-02 12:59:22 +08:00
|
|
|
PERF_RECORD_HEADER_BUILD_ID = 67,
|
2010-05-03 04:05:29 +08:00
|
|
|
PERF_RECORD_FINISHED_ROUND = 68,
|
2014-10-27 21:49:22 +08:00
|
|
|
PERF_RECORD_ID_INDEX = 69,
|
2010-04-02 12:59:19 +08:00
|
|
|
PERF_RECORD_HEADER_MAX
|
|
|
|
};
|
|
|
|
|
2014-10-11 02:46:05 +08:00
|
|
|
/*
|
|
|
|
* The kernel collects the number of events it couldn't send in a stretch and
|
|
|
|
* when possible sends this number in a PERF_RECORD_LOST event. The number of
|
|
|
|
* such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
|
|
|
|
* total_lost tells exactly how many events the kernel in fact lost, i.e. it is
|
|
|
|
* the sum of all struct lost_event.lost fields reported.
|
|
|
|
*
|
|
|
|
* The total_period is needed because by default auto-freq is used, so
|
|
|
|
* multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
|
|
|
|
* the total number of low level events, it is necessary to to sum all struct
|
|
|
|
* sample_event.period and stash the result in total_period.
|
|
|
|
*/
|
|
|
|
struct events_stats {
|
|
|
|
u64 total_period;
|
|
|
|
u64 total_non_filtered_period;
|
|
|
|
u64 total_lost;
|
|
|
|
u64 total_invalid_chains;
|
|
|
|
u32 nr_events[PERF_RECORD_HEADER_MAX];
|
|
|
|
u32 nr_non_filtered_samples;
|
|
|
|
u32 nr_lost_warned;
|
|
|
|
u32 nr_unknown_events;
|
|
|
|
u32 nr_invalid_chains;
|
|
|
|
u32 nr_unknown_id;
|
|
|
|
u32 nr_unprocessable_samples;
|
2014-11-26 23:39:31 +08:00
|
|
|
u32 nr_unordered_events;
|
2014-10-11 02:46:05 +08:00
|
|
|
};
|
|
|
|
|
2010-04-02 12:59:19 +08:00
|
|
|
struct attr_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
struct perf_event_attr attr;
|
|
|
|
u64 id[];
|
2010-04-02 12:59:15 +08:00
|
|
|
};
|
|
|
|
|
2010-04-02 12:59:20 +08:00
|
|
|
#define MAX_EVENT_NAME 64
|
|
|
|
|
|
|
|
struct perf_trace_event_type {
|
|
|
|
u64 event_id;
|
|
|
|
char name[MAX_EVENT_NAME];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct event_type_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
struct perf_trace_event_type event_type;
|
|
|
|
};
|
|
|
|
|
2010-04-02 12:59:21 +08:00
|
|
|
struct tracing_data_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u32 size;
|
|
|
|
};
|
|
|
|
|
2014-10-27 21:49:22 +08:00
|
|
|
struct id_index_entry {
|
|
|
|
u64 id;
|
|
|
|
u64 idx;
|
|
|
|
u64 cpu;
|
|
|
|
u64 tid;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct id_index_event {
|
|
|
|
struct perf_event_header header;
|
|
|
|
u64 nr;
|
|
|
|
struct id_index_entry entries[0];
|
|
|
|
};
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
union perf_event {
|
2009-08-12 16:19:53 +08:00
|
|
|
struct perf_event_header header;
|
|
|
|
struct mmap_event mmap;
|
2013-08-21 18:10:25 +08:00
|
|
|
struct mmap2_event mmap2;
|
2009-08-12 16:19:53 +08:00
|
|
|
struct comm_event comm;
|
|
|
|
struct fork_event fork;
|
|
|
|
struct lost_event lost;
|
|
|
|
struct read_event read;
|
2013-09-01 18:36:15 +08:00
|
|
|
struct throttle_event throttle;
|
2009-09-12 13:53:00 +08:00
|
|
|
struct sample_event sample;
|
2010-04-02 12:59:19 +08:00
|
|
|
struct attr_event attr;
|
2010-04-02 12:59:20 +08:00
|
|
|
struct event_type_event event_type;
|
2010-04-02 12:59:21 +08:00
|
|
|
struct tracing_data_event tracing_data;
|
2010-04-02 12:59:22 +08:00
|
|
|
struct build_id_event build_id;
|
2014-10-27 21:49:22 +08:00
|
|
|
struct id_index_event id_index;
|
2011-01-30 00:01:45 +08:00
|
|
|
};
|
2009-08-12 17:07:25 +08:00
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
void perf_event__print_totals(void);
|
2009-11-28 02:29:22 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool;
|
2011-02-10 22:52:47 +08:00
|
|
|
struct thread_map;
|
perf session: Move kmaps to perf_session
There is still some more work to do to disentangle map creation
from DSO loading, but this happens only for the kernel, and for
the early adopters of perf diff, where this disentanglement
matters most, we'll be testing different kernels, so no problem
here.
Further clarification: right now we create the kernel maps for
the various modules and discontiguous kernel text maps when
loading the DSO, we should do it as a two step process, first
creating the maps, for multiple mappings with the same DSO
store, then doing the dso load just once, for the first hit on
one of the maps sharing this DSO backing store.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1260741029-4430-6-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-14 05:50:29 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
typedef int (*perf_event__handler_t)(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2011-01-30 00:01:45 +08:00
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2010-01-08 05:59:40 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_thread_map(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
struct thread_map *threads,
|
2011-02-11 21:45:54 +08:00
|
|
|
perf_event__handler_t process,
|
2013-11-11 20:44:09 +08:00
|
|
|
struct machine *machine, bool mmap_data);
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_threads(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_event__handler_t process,
|
2013-11-11 20:44:09 +08:00
|
|
|
struct machine *machine, bool mmap_data);
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_event__handler_t process,
|
2014-01-29 22:14:40 +08:00
|
|
|
struct machine *machine);
|
2011-01-30 00:01:45 +08:00
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__synthesize_modules(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
perf_event__handler_t process,
|
2011-01-30 00:01:45 +08:00
|
|
|
struct machine *machine);
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__process_comm(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__process_lost(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__process_mmap(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2013-08-21 18:10:25 +08:00
|
|
|
int perf_event__process_mmap2(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct machine *machine);
|
2012-10-07 02:44:59 +08:00
|
|
|
int perf_event__process_fork(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct machine *machine);
|
|
|
|
int perf_event__process_exit(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2011-11-28 18:30:20 +08:00
|
|
|
int perf_event__process(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine);
|
2009-11-28 02:29:22 +08:00
|
|
|
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
struct addr_location;
|
2013-11-06 02:32:36 +08:00
|
|
|
|
|
|
|
int perf_event__preprocess_sample(const union perf_event *event,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine,
|
2011-01-30 00:01:45 +08:00
|
|
|
struct addr_location *al,
|
2013-08-08 19:32:25 +08:00
|
|
|
struct perf_sample *sample);
|
perf tools: Consolidate symbol resolving across all tools
Now we have a very high level routine for simple tools to
process IP sample events:
int event__preprocess_sample(const event_t *self,
struct addr_location *al,
symbol_filter_t filter)
It receives the event itself and will insert new threads in the
global threads list and resolve the map and symbol, filling all
this info into the new addr_location struct, so that tools like
annotate and report can further process the event by creating
hist_entries in their specific way (with or without callgraphs,
etc).
It in turn uses the new next layer function:
void thread__find_addr_location(struct thread *self, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
This one will, given a thread (userspace or the kernel kthread
one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
too in the near future) at the given cpumode, taking vdsos into
account (userspace hit, but kernel symbol) and will fill all
these details in the addr_location given.
Tools that need a more compact API for plain function
resolution, like 'kmem', can use this other one:
struct symbol *thread__find_function(struct thread *self, u64 addr,
symbol_filter_t filter)
So, to resolve a kernel symbol, that is all the 'kmem' tool
needs, its just a matter of calling:
sym = thread__find_function(kthread, addr, NULL);
The 'filter' parameter is needed because we do lazy
parsing/loading of ELF symtabs or /proc/kallsyms.
With this we remove more code duplication all around, which is
always good, huh? :-)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
|
|
|
|
2014-07-22 21:17:39 +08:00
|
|
|
struct thread;
|
|
|
|
|
|
|
|
bool is_bts_event(struct perf_event_attr *attr);
|
|
|
|
bool sample_addr_correlates_sym(struct perf_event_attr *attr);
|
|
|
|
void perf_event__preprocess_sample_addr(union perf_event *event,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct thread *thread,
|
|
|
|
struct addr_location *al);
|
|
|
|
|
2011-01-30 00:01:45 +08:00
|
|
|
const char *perf_event__name(unsigned int id);
|
2010-05-14 21:36:42 +08:00
|
|
|
|
2013-08-27 16:23:12 +08:00
|
|
|
size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
|
2014-01-07 20:47:25 +08:00
|
|
|
u64 read_format);
|
2011-11-28 17:03:31 +08:00
|
|
|
int perf_event__synthesize_sample(union perf_event *event, u64 type,
|
2014-01-07 20:47:25 +08:00
|
|
|
u64 read_format,
|
2011-11-28 17:03:31 +08:00
|
|
|
const struct perf_sample *sample,
|
|
|
|
bool swapped);
|
2011-01-21 23:46:41 +08:00
|
|
|
|
2014-01-07 20:47:20 +08:00
|
|
|
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
|
|
|
|
union perf_event *event,
|
|
|
|
pid_t pid, pid_t tgid,
|
|
|
|
perf_event__handler_t process,
|
|
|
|
struct machine *machine,
|
|
|
|
bool mmap_data);
|
|
|
|
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
|
|
|
|
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
|
2013-08-21 18:10:25 +08:00
|
|
|
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
|
2011-12-02 21:06:37 +08:00
|
|
|
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
|
|
|
|
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
|
|
|
|
|
2014-01-29 22:14:37 +08:00
|
|
|
u64 kallsyms__get_function_start(const char *kallsyms_filename,
|
|
|
|
const char *symbol_name);
|
|
|
|
|
2009-09-25 00:02:18 +08:00
|
|
|
#endif /* __PERF_RECORD_H */
|