2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-28 07:04:00 +08:00
linux-next/tools/perf/util/evlist.h
Arnaldo Carvalho de Melo a8f23d8f8a perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:

  /*
   * perf event paranoia level:
   *  -1 - not paranoid at all
   *   0 - disallow raw tracepoint access for unpriv
   *   1 - disallow cpu events for unpriv
   *   2 - disallow kernel profiling for unpriv
   */
  int sysctl_perf_event_paranoid __read_mostly = 1;

So, with the default being 1, a non-root user can trace his stuff:

  [acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
  1
  [acme@zoo ~]$ yes > /dev/null &
  [1] 15338
  [acme@zoo ~]$ trace -p 15338 | head -5
       0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
       0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
  [acme@zoo ~]$
  [acme@zoo ~]$ trace --duration 1 sleep 1
    1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250                           ) = 0
  [acme@zoo ~]$
  [acme@zoo ~]$ trace -- usleep 1 | tail -5
       0.905 ( 0.002 ms): brk(                                                     ) = 0x1c82000
       0.910 ( 0.003 ms): brk(brk: 0x1ca3000                                       ) = 0x1ca3000
       0.913 ( 0.001 ms): brk(                                                     ) = 0x1ca3000
       0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280                           ) = 0
       0.995 ( 0.000 ms): exit_group(
  [acme@zoo ~]$

But can't do system wide tracing:

  [acme@zoo ~]$ trace
  Error:	Operation not permitted.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 1.
  [acme@zoo ~]$

  [acme@zoo ~]$ trace --cpu 0
  Error:	Operation not permitted.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 1.
  [acme@zoo ~]$

If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:

  [acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
  [acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
  2
  [acme@zoo ~]$
  [acme@zoo ~]$ trace usleep 1
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$
  [acme@zoo ~]$ trace
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$
  [acme@zoo ~]$ trace --cpu 1
  Error:	Permission denied.
  Hint:	Check /proc/sys/kernel/perf_event_paranoid setting.
  Hint:	For your workloads it needs to be <= 1
  Hint:	For system wide tracing it needs to be set to -1.
  Hint:	The current value is 2.
  [acme@zoo ~]$

If the user manages to get what he/she wants, convincing root not
to be paranoid at all...

  [root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
  [root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
  -1
  [root@zoo ~]#

  [acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
  root       729 Xorg
  [acme@zoo ~]$
  [acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg  | head -5
      23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
      23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096     ) = 8
      23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096     ) = -1 EAGAIN Resource temporarily unavailable
      23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
      23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
  [acme@zoo ~]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 17:38:29 -03:00

195 lines
5.8 KiB
C

#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
#include <linux/list.h>
#include <stdio.h>
#include "../perf.h"
#include "event.h"
#include "evsel.h"
#include "util.h"
#include <unistd.h>
struct pollfd;
struct thread_map;
struct cpu_map;
struct perf_record_opts;
#define PERF_EVLIST__HLIST_BITS 8
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
struct perf_mmap {
void *base;
int mask;
unsigned int prev;
char event_copy[PERF_SAMPLE_MAX_SIZE];
};
struct perf_evlist {
struct list_head entries;
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
int nr_entries;
int nr_groups;
int nr_fds;
int nr_mmaps;
size_t mmap_len;
int id_pos;
int is_pos;
u64 combined_sample_type;
struct {
int cork_fd;
pid_t pid;
} workload;
bool overwrite;
struct perf_mmap *mmap;
struct pollfd *pollfd;
struct thread_map *threads;
struct cpu_map *cpus;
struct perf_evsel *selected;
};
struct perf_evsel_str_handler {
const char *name;
void *handler;
};
struct perf_evlist *perf_evlist__new(void);
struct perf_evlist *perf_evlist__new_default(void);
void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
struct thread_map *threads);
void perf_evlist__exit(struct perf_evlist *evlist);
void perf_evlist__delete(struct perf_evlist *evlist);
void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
int perf_evlist__add_default(struct perf_evlist *evlist);
int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
struct perf_event_attr *attrs, size_t nr_attrs);
#define perf_evlist__add_default_attrs(evlist, array) \
__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
int perf_evlist__add_newtp(struct perf_evlist *evlist,
const char *sys, const char *name, void *handler);
int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
struct perf_evsel *
perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
struct perf_evsel *
perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
const char *name);
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
int perf_evlist__open(struct perf_evlist *evlist);
void perf_evlist__close(struct perf_evlist *evlist);
void perf_evlist__set_id_pos(struct perf_evlist *evlist);
bool perf_can_sample_identifier(void);
void perf_evlist__config(struct perf_evlist *evlist,
struct perf_record_opts *opts);
int perf_evlist__prepare_workload(struct perf_evlist *evlist,
struct perf_target *target,
const char *argv[], bool pipe_output,
bool want_signal);
int perf_evlist__start_workload(struct perf_evlist *evlist);
int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
void perf_evlist__disable(struct perf_evlist *evlist);
void perf_evlist__enable(struct perf_evlist *evlist);
int perf_evlist__disable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel);
int perf_evlist__enable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel);
void perf_evlist__set_selected(struct perf_evlist *evlist,
struct perf_evsel *evsel);
static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
struct cpu_map *cpus,
struct thread_map *threads)
{
evlist->cpus = cpus;
evlist->threads = threads;
}
int perf_evlist__create_maps(struct perf_evlist *evlist,
struct perf_target *target);
void perf_evlist__delete_maps(struct perf_evlist *evlist);
int perf_evlist__apply_filters(struct perf_evlist *evlist);
void __perf_evlist__set_leader(struct list_head *list);
void perf_evlist__set_leader(struct perf_evlist *evlist);
u64 perf_evlist__read_format(struct perf_evlist *evlist);
u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
struct perf_sample *sample);
bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
struct list_head *list,
int nr_entries);
static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
{
return list_entry(evlist->entries.next, struct perf_evsel, node);
}
static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
{
return list_entry(evlist->entries.prev, struct perf_evsel, node);
}
size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->base;
int head = pc->data_head;
rmb();
return head;
}
static inline void perf_mmap__write_tail(struct perf_mmap *md,
unsigned long tail)
{
struct perf_event_mmap_page *pc = md->base;
/*
* ensure all reads are done before we write the tail out.
*/
/* mb(); */
pc->data_tail = tail;
}
#endif /* __PERF_EVLIST_H */