mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 15:49:17 +07:00
384b60557b
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>
363 lines
10 KiB
C
363 lines
10 KiB
C
#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"
|
|
|
|
struct perf_counts_values {
|
|
union {
|
|
struct {
|
|
u64 val;
|
|
u64 ena;
|
|
u64 run;
|
|
};
|
|
u64 values[3];
|
|
};
|
|
};
|
|
|
|
struct perf_counts {
|
|
s8 scaled;
|
|
struct perf_counts_values aggr;
|
|
struct perf_counts_values cpu[];
|
|
};
|
|
|
|
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;
|
|
int idx;
|
|
int cpu;
|
|
pid_t tid;
|
|
|
|
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
|
|
u64 period;
|
|
};
|
|
|
|
struct cgroup_sel;
|
|
|
|
/** struct perf_evsel - event selector
|
|
*
|
|
* @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_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;
|
|
double scale;
|
|
const char *unit;
|
|
bool snapshot;
|
|
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;
|
|
unsigned int sample_size;
|
|
int id_pos;
|
|
int is_pos;
|
|
bool supported;
|
|
bool needs_swap;
|
|
bool no_aux_samples;
|
|
bool immediate;
|
|
bool system_wide;
|
|
bool tracking;
|
|
bool per_pkg;
|
|
unsigned long *per_pkg_mask;
|
|
/* parse modifier helper */
|
|
int exclude_GH;
|
|
int nr_members;
|
|
int sample_read;
|
|
struct perf_evsel *leader;
|
|
char *group_name;
|
|
};
|
|
|
|
union u64_swap {
|
|
u64 val64;
|
|
u32 val32[2];
|
|
};
|
|
|
|
struct cpu_map;
|
|
struct target;
|
|
struct thread_map;
|
|
struct perf_evlist;
|
|
struct record_opts;
|
|
|
|
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,
|
|
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);
|
|
|
|
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);
|
|
|
|
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);
|
|
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
|
|
void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
|
|
void perf_evsel__free_counts(struct perf_evsel *evsel);
|
|
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, 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,
|
|
struct cpu_map *cpus);
|
|
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
|
|
struct thread_map *threads);
|
|
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
|
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)
|
|
|
|
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)
|
|
|
|
typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
|
|
int cpu, int thread,
|
|
struct perf_counts_values *count);
|
|
|
|
int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
|
|
perf_evsel__read_cb_t cb);
|
|
|
|
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;
|
|
};
|
|
|
|
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))
|
|
|
|
static inline bool has_branch_callstack(struct perf_evsel *evsel)
|
|
{
|
|
return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
|
|
}
|
|
#endif /* __PERF_EVSEL_H */
|