2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-18 18:23:53 +08:00
linux-next/tools/perf/util/evsel.h

397 lines
11 KiB
C
Raw Normal View History

#ifndef __PERF_EVSEL_H
#define __PERF_EVSEL_H 1
#include <linux/list.h>
#include <stdbool.h>
#include <stddef.h>
#include <linux/perf_event.h>
#include <linux/types.h>
#include "xyarray.h"
#include "symbol.h"
#include "cpumap.h"
#include "counts.h"
struct perf_evsel;
/*
* Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
* more than one entry in the evlist.
*/
struct perf_sample_id {
struct hlist_node node;
u64 id;
struct perf_evsel *evsel;
perf tools: Add id index Add an index of the event identifiers, in preparation for Intel PT. The event id (also called the sample id) is a unique number allocated by the kernel to the event created by perf_event_open(). Events can include the event id by having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER. Currently the main use of the event id is to match an event back to the evsel to which it belongs i.e. perf_evlist__id2evsel() The purpose of this patch is to make it possible to match an event back to the mmap from which it was read. The reason that is useful is because the mmap represents a time-ordered context (either for a cpu or for a thread). Intel PT decodes trace information on that basis. In full-trace mode, that information can be recorded when the Intel PT trace is read, but in sample-mode the Intel PT trace data is embedded in a sample and it is in that case that the "id index" is needed. So the mmaps are numbered (idx) and the cpu and tid recorded against the id by perf_evlist__set_sid_idx() which is called by perf_evlist__mmap_per_evsel(). That information is recorded on the perf.data file in the new "id index". idx, cpu and tid are added to struct perf_sample_id (which is the node of evlist's hash table to match ids to evsels). The information can be retrieved using perf_evlist__id2sid(). Note however this all depends on having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER, otherwise ids are not recorded. The "id index" is a synthesized event record which will be created when Intel PT sampling is used by calling perf_event__synthesize_id_index(). Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1414417770-18602-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-27 21:49:22 +08:00
int idx;
int cpu;
pid_t tid;
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
u64 period;
};
struct cgroup_sel;
/*
* The 'struct perf_evsel_config_term' is used to pass event
* specific configuration data to perf_evsel__config routine.
* It is allocated within event parsing and attached to
* perf_evsel::config_terms list head.
*/
enum {
PERF_EVSEL__CONFIG_TERM_PERIOD,
PERF_EVSEL__CONFIG_TERM_FREQ,
PERF_EVSEL__CONFIG_TERM_TIME,
PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
PERF_EVSEL__CONFIG_TERM_STACK_USER,
PERF_EVSEL__CONFIG_TERM_MAX,
};
struct perf_evsel_config_term {
struct list_head list;
int type;
union {
u64 period;
u64 freq;
bool time;
char *callgraph;
u64 stack_user;
} val;
};
/** struct perf_evsel - event selector
*
* @evlist - evlist this evsel is in, if it is in one.
* @node - To insert it into evlist->entries or in other list_heads, say in
* the event parsing routines.
* @name - Can be set to retain the original event name passed by the user,
* so that when showing results in tools such as 'perf stat', we
* show the name used, not some alias.
* @id_pos: the position of the event id (PERF_SAMPLE_ID or
* PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
* struct sample_event
* @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
* PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
* is used there is an id sample appended to non-sample events
* @priv: And what is in its containing unnamed union are tool specific
*/
struct perf_evsel {
struct list_head node;
struct perf_evlist *evlist;
struct perf_event_attr attr;
char *filter;
struct xyarray *fd;
struct xyarray *sample_id;
u64 *id;
struct perf_counts *counts;
struct perf_counts *prev_raw_counts;
int idx;
u32 ids;
char *name;
tools/perf/stat: Add event unit and scale support This patch adds perf stat support for handling event units and scales as exported by the kernel. The kernel can export PMU events actual unit and scaling factor via sysfs: $ ls -1 /sys/devices/power/events/energy-* /sys/devices/power/events/energy-cores /sys/devices/power/events/energy-cores.scale /sys/devices/power/events/energy-cores.unit /sys/devices/power/events/energy-pkg /sys/devices/power/events/energy-pkg.scale /sys/devices/power/events/energy-pkg.unit $ cat /sys/devices/power/events/energy-cores.scale 2.3283064365386962890625e-10 $ cat cat /sys/devices/power/events/energy-cores.unit Joules This patch modifies the pmu event alias code to check for the presence of the .unit and .scale files to load the corresponding values. They are then used by perf stat transparently: # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000 # time counts unit events 1.000214717 3.07 Joules power/energy-pkg/ [100.00%] 1.000214717 0.53 Joules power/energy-cores/ 1.000214717 12965028 cycles [100.00%] 2.000749289 3.01 Joules power/energy-pkg/ 2.000749289 0.52 Joules power/energy-cores/ 2.000749289 15817043 cycles When the event does not have an explicit unit exported by the kernel, nothing is printed. In csv output mode, there will be an empty field. Special thanks to Jiri for providing the supporting code in the parser to trigger reading of the scale and unit files. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Cc: maria.n.dimakopoulou@gmail.com Cc: acme@redhat.com Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-13 00:58:49 +08:00
double scale;
const char *unit;
struct event_format *tp_format;
union {
void *priv;
off_t id_offset;
u64 db_id;
};
struct cgroup_sel *cgrp;
void *handler;
struct cpu_map *cpus;
struct thread_map *threads;
unsigned int sample_size;
int id_pos;
int is_pos;
perf tools: Elliminate alignment holes perf_evsel: Before: /* size: 320, cachelines: 5, members: 35 */ /* sum members: 304, holes: 3, sum holes: 16 */ After: /* size: 304, cachelines: 5, members: 35 */ /* last cacheline: 48 bytes */ perf_evlist: Before: /* size: 2544, cachelines: 40, members: 17 */ /* sum members: 2533, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ After: /* size: 2536, cachelines: 40, members: 17 */ /* sum members: 2533, holes: 1, sum holes: 3 */ /* last cacheline: 40 bytes */ timechart: Before: /* size: 288, cachelines: 5, members: 21 */ /* sum members: 271, holes: 2, sum holes: 10 */ /* padding: 7 */ /* last cacheline: 32 bytes */ After: /* size: 272, cachelines: 5, members: 21 */ /* sum members: 271, holes: 1, sum holes: 1 */ /* last cacheline: 16 bytes */ thread: Before: /* size: 112, cachelines: 2, members: 15 */ /* sum members: 101, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ After: /* size: 104, cachelines: 2, members: 15 */ /* sum members: 101, holes: 1, sum holes: 3 */ /* last cacheline: 40 bytes */ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-a543w7zjl9yyrg9nkf1teukp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-16 04:29:56 +08:00
bool snapshot;
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
bool supported;
bool needs_swap;
bool no_aux_samples;
bool immediate;
bool system_wide;
bool tracking;
bool per_pkg;
2012-08-08 18:21:54 +08:00
/* parse modifier helper */
int exclude_GH;
int nr_members;
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> 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/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 23:39:03 +08:00
int sample_read;
perf tools: Elliminate alignment holes perf_evsel: Before: /* size: 320, cachelines: 5, members: 35 */ /* sum members: 304, holes: 3, sum holes: 16 */ After: /* size: 304, cachelines: 5, members: 35 */ /* last cacheline: 48 bytes */ perf_evlist: Before: /* size: 2544, cachelines: 40, members: 17 */ /* sum members: 2533, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ After: /* size: 2536, cachelines: 40, members: 17 */ /* sum members: 2533, holes: 1, sum holes: 3 */ /* last cacheline: 40 bytes */ timechart: Before: /* size: 288, cachelines: 5, members: 21 */ /* sum members: 271, holes: 2, sum holes: 10 */ /* padding: 7 */ /* last cacheline: 32 bytes */ After: /* size: 272, cachelines: 5, members: 21 */ /* sum members: 271, holes: 1, sum holes: 1 */ /* last cacheline: 16 bytes */ thread: Before: /* size: 112, cachelines: 2, members: 15 */ /* sum members: 101, holes: 2, sum holes: 11 */ /* last cacheline: 48 bytes */ After: /* size: 104, cachelines: 2, members: 15 */ /* sum members: 101, holes: 1, sum holes: 3 */ /* last cacheline: 40 bytes */ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-a543w7zjl9yyrg9nkf1teukp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-16 04:29:56 +08:00
unsigned long *per_pkg_mask;
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
struct perf_evsel *leader;
char *group_name;
perf record: Apply filter to all events in a glob matching There is an old problem in perf's filter applying which first posted at Sep. 2014 at https://lkml.org/lkml/2014/9/9/944 that, if passing multiple events in a glob matching expression in cmdline then add '--filter' after them, the filter will be applied on only the last one. For example: # dd if=/dev/zero of=/dev/null & [1] 464 # perf record -a -e 'syscalls:sys_*_read' --filter 'common_pid != 464' sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.239 MB perf.data (2094 samples) ] # perf report --stdio | tee ... # Samples: 2K of event 'syscalls:sys_enter_read' # Event count (approx.): 2092 ... # Samples: 2 of event 'syscalls:sys_exit_read' # Event count (approx.): 2 ... In this example, filter only applied on 'syscalls:sys_exit_read', and there's no way to set filter for ''syscalls:sys_enter_read'. This patch adds a 'cmdline_group_boundary' for 'struct evsel', and apply filter on all events between two boundary marks. After applying this patch: # perf record -a -e 'syscalls:sys_*_read' --filter 'common_pid != 464' sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.031 MB perf.data (3 samples) ] # perf report --stdio | tee ... # Samples: 1 of event 'syscalls:sys_enter_read' # Event count (approx.): 1 ... # Samples: 2 of event 'syscalls:sys_exit_read' # Event count (approx.): 2 ... Signed-off-by: Wang Nan <wangnan0@huawei.com> Reported-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1436513770-8896-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-10 15:36:09 +08:00
bool cmdline_group_boundary;
struct list_head config_terms;
};
union u64_swap {
u64 val64;
u32 val32[2];
};
struct cpu_map;
struct target;
struct thread_map;
struct record_opts;
static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
{
return evsel->cpus;
}
static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
{
return perf_evsel__cpus(evsel)->nr;
}
void perf_counts_values__scale(struct perf_counts_values *count,
bool scale, s8 *pscaled);
void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
int perf_evsel__object_config(size_t object_size,
int (*init)(struct perf_evsel *evsel),
void (*fini)(struct perf_evsel *evsel));
struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
{
return perf_evsel__new_idx(attr, 0);
}
struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
/*
* Returns pointer with encoded error via <linux/err.h> interface.
*/
static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name)
{
return perf_evsel__newtp_idx(sys, name, 0);
}
struct event_format *event_format__new(const char *sys, const char *name);
void perf_evsel__init(struct perf_evsel *evsel,
struct perf_event_attr *attr, int idx);
void perf_evsel__exit(struct perf_evsel *evsel);
void perf_evsel__delete(struct perf_evsel *evsel);
void perf_evsel__config(struct perf_evsel *evsel,
struct record_opts *opts);
int __perf_evsel__sample_size(u64 sample_type);
void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
#define PERF_EVSEL__MAX_ALIASES 8
extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
[PERF_EVSEL__MAX_ALIASES];
extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_EVSEL__MAX_ALIASES];
extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
[PERF_EVSEL__MAX_ALIASES];
extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX];
extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
char *bf, size_t size);
const char *perf_evsel__name(struct perf_evsel *evsel);
tools/perf/stat: Add event unit and scale support This patch adds perf stat support for handling event units and scales as exported by the kernel. The kernel can export PMU events actual unit and scaling factor via sysfs: $ ls -1 /sys/devices/power/events/energy-* /sys/devices/power/events/energy-cores /sys/devices/power/events/energy-cores.scale /sys/devices/power/events/energy-cores.unit /sys/devices/power/events/energy-pkg /sys/devices/power/events/energy-pkg.scale /sys/devices/power/events/energy-pkg.unit $ cat /sys/devices/power/events/energy-cores.scale 2.3283064365386962890625e-10 $ cat cat /sys/devices/power/events/energy-cores.unit Joules This patch modifies the pmu event alias code to check for the presence of the .unit and .scale files to load the corresponding values. They are then used by perf stat transparently: # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000 # time counts unit events 1.000214717 3.07 Joules power/energy-pkg/ [100.00%] 1.000214717 0.53 Joules power/energy-cores/ 1.000214717 12965028 cycles [100.00%] 2.000749289 3.01 Joules power/energy-pkg/ 2.000749289 0.52 Joules power/energy-cores/ 2.000749289 15817043 cycles When the event does not have an explicit unit exported by the kernel, nothing is printed. In csv output mode, there will be an empty field. Special thanks to Jiri for providing the supporting code in the parser to trigger reading of the scale and unit files. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Cc: maria.n.dimakopoulou@gmail.com Cc: acme@redhat.com Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-13 00:58:49 +08:00
const char *perf_evsel__group_name(struct perf_evsel *evsel);
int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
enum perf_event_sample_format bit);
void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
enum perf_event_sample_format bit);
#define perf_evsel__set_sample_bit(evsel, bit) \
__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
#define perf_evsel__reset_sample_bit(evsel, bit) \
__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
void perf_evsel__set_sample_id(struct perf_evsel *evsel,
bool use_sample_identifier);
int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter);
int perf_evsel__append_filter(struct perf_evsel *evsel,
const char *op, const char *filter);
perf evsel: Rename set_filter to apply_filter We need to be able to go on constructing a complex filter in multiple stages, since we can only set one filter per event. For instance, we need to be able, in 'perf trace' to filter by the 'common_pid' field all the time, if only for the tracer itself, to avoid a feedback loop, and, in addition, we may want to filter the raw_syscalls:sys_{enter,exit} events by its 'id' filter, when using 'perf trace -e open,close' or 'perf trace -e !open,close', i.e. when we are interested in just a subset of syscalls or when we are not interested in it. So we will have: perf_evsel__set_filter(evsel, char *filter) Replaces whatever is in evsel->filter. perf_evsel__append_filter(evsel, const char *op, char *filter) Appends, using op ("&&" or "||") with what is in evsel->filter. perf_evsel__apply_filter(evsel, filter): That actually applies a filter, be it the one being constructed in evsel->filter, or any other, for tools with more specific ways to build the filter, issuing the appropriate ioctl for all the evsel fds. The same changes will be made to the evlist__{set,apply} variants to keep everything consistent. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-2s5z9xtpnc2lwio3cv5x0jek@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 02:53:49 +08:00
int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
const char *filter);
int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
struct cpu_map *cpus);
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
struct thread_map *threads);
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 18:22:36 +08:00
struct thread_map *threads);
void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
struct perf_sample;
void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
const char *name);
u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
const char *name);
static inline char *perf_evsel__strval(struct perf_evsel *evsel,
struct perf_sample *sample,
const char *name)
{
return perf_evsel__rawptr(evsel, sample, name);
}
struct format_field;
struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
#define perf_evsel__match(evsel, t, c) \
(evsel->attr.type == PERF_TYPE_##t && \
evsel->attr.config == PERF_COUNT_##c)
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.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@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
static inline bool perf_evsel__match2(struct perf_evsel *e1,
struct perf_evsel *e2)
{
return (e1->attr.type == e2->attr.type) &&
(e1->attr.config == e2->attr.config);
}
#define perf_evsel__cmp(a, b) \
((a) && \
(b) && \
(a)->attr.type == (b)->attr.type && \
(a)->attr.config == (b)->attr.config)
int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
int cpu, int thread, bool scale);
/**
* perf_evsel__read_on_cpu - Read out the results on a CPU and thread
*
* @evsel - event selector to read value
* @cpu - CPU of interest
* @thread - thread of interest
*/
static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
int cpu, int thread)
{
return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
}
/**
* perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
*
* @evsel - event selector to read value
* @cpu - CPU of interest
* @thread - thread of interest
*/
static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
int cpu, int thread)
{
return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
}
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample);
static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
{
return list_entry(evsel->node.next, struct perf_evsel, node);
}
static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel)
{
return list_entry(evsel->node.prev, struct perf_evsel, node);
}
/**
* perf_evsel__is_group_leader - Return whether given evsel is a leader event
*
* @evsel - evsel selector to be tested
*
* Return %true if @evsel is a group leader or a stand-alone event
*/
static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
{
return evsel->leader == evsel;
}
/**
* perf_evsel__is_group_event - Return whether given evsel is a group event
*
* @evsel - evsel selector to be tested
*
* Return %true iff event group view is enabled and @evsel is a actual group
* leader which has other members in the group
*/
static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
{
if (!symbol_conf.event_group)
return false;
return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
}
/**
* perf_evsel__is_function_event - Return whether given evsel is a function
* trace event
*
* @evsel - evsel selector to be tested
*
* Return %true if event is function trace event
*/
static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
{
#define FUNCTION_EVENT "ftrace:function"
return evsel->name &&
!strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
#undef FUNCTION_EVENT
}
struct perf_attr_details {
bool freq;
bool verbose;
bool event_group;
bool force;
};
int perf_evsel__fprintf(struct perf_evsel *evsel,
struct perf_attr_details *details, FILE *fp);
bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
char *msg, size_t msgsize);
int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
int err, char *msg, size_t size);
static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
{
return evsel->idx - evsel->leader->idx;
}
#define for_each_group_member(_evsel, _leader) \
for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \
(_evsel) && (_evsel)->leader == (_leader); \
(_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
perf tools: Construct LBR call chain LBR call stack only has user-space callchains. It is output in the PERF_SAMPLE_BRANCH_STACK data format. For kernel callchains, it's still in the form of PERF_SAMPLE_CALLCHAIN. The perf tool has to handle both data sources to construct a complete callstack. For the "perf report -D" option, both lbr and fp information will be displayed. A new call chain recording option "lbr" is introduced into the perf tool for LBR call stack. The user can use --call-graph lbr to get the call stack information from hardware. Here are some examples. When profiling bc(1) on Fedora 19: echo 'scale=2000; 4*a(1)' > cmd; perf record --call-graph lbr bc -l < cmd If enabling LBR, perf report output looks like: 50.36% bc bc [.] bc_divide | --- bc_divide execute run_code yyparse main __libc_start_main _start 33.66% bc bc [.] _one_mult | --- _one_mult bc_divide execute run_code yyparse main __libc_start_main _start 7.62% bc bc [.] _bc_do_add | --- _bc_do_add | |--99.89%-- 0x2000186a8 --0.11%-- [...] 6.83% bc bc [.] _bc_do_sub | --- _bc_do_sub | |--99.94%-- bc_add | execute | run_code | yyparse | main | __libc_start_main | _start --0.06%-- [...] 0.46% bc libc-2.17.so [.] __memset_sse2 | --- __memset_sse2 | |--54.13%-- bc_new_num | | | |--51.00%-- bc_divide | | execute | | run_code | | yyparse | | main | | __libc_start_main | | _start | | | |--30.46%-- _bc_do_sub | | bc_add | | execute | | run_code | | yyparse | | main | | __libc_start_main | | _start | | | --18.55%-- _bc_do_add | bc_add | execute | run_code | yyparse | main | __libc_start_main | _start | --45.87%-- bc_divide execute run_code yyparse main __libc_start_main _start If using FP, perf report output looks like: echo 'scale=2000; 4*a(1)' > cmd; perf record --call-graph fp bc -l < cmd 50.49% bc bc [.] bc_divide | --- bc_divide 33.57% bc bc [.] _one_mult | --- _one_mult 7.61% bc bc [.] _bc_do_add | --- _bc_do_add 0x2000186a8 6.88% bc bc [.] _bc_do_sub | --- _bc_do_sub 0.42% bc libc-2.17.so [.] __memcpy_ssse3_back | --- __memcpy_ssse3_back If using LBR, perf report -D output looks like: 3458145275743 0x2fd750 [0xd8]: PERF_RECORD_SAMPLE(IP, 0x2): 9748/9748: 0x408ea8 period: 609644 addr: 0 ... LBR call chain: nr:8 ..... 0: fffffffffffffe00 ..... 1: 0000000000408e50 ..... 2: 000000000040a458 ..... 3: 000000000040562e ..... 4: 0000000000408590 ..... 5: 00000000004022c0 ..... 6: 00000000004015dd ..... 7: 0000003d1cc21b43 ... FP chain: nr:2 ..... 0: fffffffffffffe00 ..... 1: 0000000000408ea8 ... thread: bc:9748 ...... dso: /usr/bin/bc The LBR call stack has the following known limitations: - Zero length calls are not filtered out by the hardware - Exception handing such as setjmp/longjmp will have calls/returns not match - Pushing different return address onto the stack will have calls/returns not match - If callstack is deeper than the LBR, only the last entries are captured Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Simon Que <sque@chromium.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1420482185-29830-3-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-06 02:23:05 +08:00
static inline bool has_branch_callstack(struct perf_evsel *evsel)
{
return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 17:09:54 +08:00
typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
attr__fprintf_f attr__fprintf, void *priv);
#endif /* __PERF_EVSEL_H */