mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-24 01:15:59 +07:00
d3f85437ad
A new branch sample type PERF_SAMPLE_BRANCH_HW_INDEX has been introduced in latest kernel. Enable HW_INDEX by default in LBR call stack mode. If kernel doesn't support the sample type, switching it off. Add HW_INDEX in attr_fprintf as well. User can check whether the branch sample type is set via debug information or header. Committer testing: First collect some samples with LBR callchains, system wide, for a few seconds: # perf record --call-graph lbr -a sleep 5 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.625 MB perf.data (224 samples) ] # Now lets use 'perf evlist -v' to look at the branch_sample_type: # perf evlist -v cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: USER|CALL_STACK|NO_FLAGS|NO_CYCLES|HW_INDEX # So the machine has the kernel feature, and it was correctly added to perf_event_attr.branch_sample_type, for the default 'cycles' event. If we do it in another machine, where the kernel lacks the HW_INDEX feature, we get: # perf record --call-graph lbr -a sleep 2s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.690 MB perf.data (499 samples) ] # perf evlist -v cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: USER|CALL_STACK|NO_FLAGS|NO_CYCLES # No HW_INDEX in attr.branch_sample_type. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Pavel Gerasimov <pavel.gerasimov@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com> Link: http://lore.kernel.org/lkml/20200228163011.19358-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
151 lines
4.7 KiB
C
151 lines
4.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <inttypes.h>
|
|
#include <stdio.h>
|
|
#include <stdbool.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/types.h>
|
|
#include <linux/perf_event.h>
|
|
#include "util/evsel_fprintf.h"
|
|
|
|
struct bit_names {
|
|
int bit;
|
|
const char *name;
|
|
};
|
|
|
|
static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
|
|
{
|
|
bool first_bit = true;
|
|
int i = 0;
|
|
|
|
do {
|
|
if (value & bits[i].bit) {
|
|
buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
|
|
first_bit = false;
|
|
}
|
|
} while (bits[++i].name != NULL);
|
|
}
|
|
|
|
static void __p_sample_type(char *buf, size_t size, u64 value)
|
|
{
|
|
#define bit_name(n) { PERF_SAMPLE_##n, #n }
|
|
struct bit_names bits[] = {
|
|
bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
|
|
bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
|
|
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
|
|
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
|
|
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
|
|
bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX),
|
|
{ .name = NULL, }
|
|
};
|
|
#undef bit_name
|
|
__p_bits(buf, size, value, bits);
|
|
}
|
|
|
|
static void __p_branch_sample_type(char *buf, size_t size, u64 value)
|
|
{
|
|
#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
|
|
struct bit_names bits[] = {
|
|
bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
|
|
bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
|
|
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
|
|
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
|
|
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
|
|
bit_name(HW_INDEX),
|
|
{ .name = NULL, }
|
|
};
|
|
#undef bit_name
|
|
__p_bits(buf, size, value, bits);
|
|
}
|
|
|
|
static void __p_read_format(char *buf, size_t size, u64 value)
|
|
{
|
|
#define bit_name(n) { PERF_FORMAT_##n, #n }
|
|
struct bit_names bits[] = {
|
|
bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
|
|
bit_name(ID), bit_name(GROUP),
|
|
{ .name = NULL, }
|
|
};
|
|
#undef bit_name
|
|
__p_bits(buf, size, value, bits);
|
|
}
|
|
|
|
#define BUF_SIZE 1024
|
|
|
|
#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
|
|
#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
|
|
#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
|
|
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
|
|
#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
|
|
#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val)
|
|
|
|
#define PRINT_ATTRn(_n, _f, _p) \
|
|
do { \
|
|
if (attr->_f) { \
|
|
_p(attr->_f); \
|
|
ret += attr__fprintf(fp, _n, buf, priv);\
|
|
} \
|
|
} while (0)
|
|
|
|
#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p)
|
|
|
|
int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
|
|
attr__fprintf_f attr__fprintf, void *priv)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
int ret = 0;
|
|
|
|
PRINT_ATTRf(type, p_unsigned);
|
|
PRINT_ATTRf(size, p_unsigned);
|
|
PRINT_ATTRf(config, p_hex);
|
|
PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
|
|
PRINT_ATTRf(sample_type, p_sample_type);
|
|
PRINT_ATTRf(read_format, p_read_format);
|
|
|
|
PRINT_ATTRf(disabled, p_unsigned);
|
|
PRINT_ATTRf(inherit, p_unsigned);
|
|
PRINT_ATTRf(pinned, p_unsigned);
|
|
PRINT_ATTRf(exclusive, p_unsigned);
|
|
PRINT_ATTRf(exclude_user, p_unsigned);
|
|
PRINT_ATTRf(exclude_kernel, p_unsigned);
|
|
PRINT_ATTRf(exclude_hv, p_unsigned);
|
|
PRINT_ATTRf(exclude_idle, p_unsigned);
|
|
PRINT_ATTRf(mmap, p_unsigned);
|
|
PRINT_ATTRf(comm, p_unsigned);
|
|
PRINT_ATTRf(freq, p_unsigned);
|
|
PRINT_ATTRf(inherit_stat, p_unsigned);
|
|
PRINT_ATTRf(enable_on_exec, p_unsigned);
|
|
PRINT_ATTRf(task, p_unsigned);
|
|
PRINT_ATTRf(watermark, p_unsigned);
|
|
PRINT_ATTRf(precise_ip, p_unsigned);
|
|
PRINT_ATTRf(mmap_data, p_unsigned);
|
|
PRINT_ATTRf(sample_id_all, p_unsigned);
|
|
PRINT_ATTRf(exclude_host, p_unsigned);
|
|
PRINT_ATTRf(exclude_guest, p_unsigned);
|
|
PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
|
|
PRINT_ATTRf(exclude_callchain_user, p_unsigned);
|
|
PRINT_ATTRf(mmap2, p_unsigned);
|
|
PRINT_ATTRf(comm_exec, p_unsigned);
|
|
PRINT_ATTRf(use_clockid, p_unsigned);
|
|
PRINT_ATTRf(context_switch, p_unsigned);
|
|
PRINT_ATTRf(write_backward, p_unsigned);
|
|
PRINT_ATTRf(namespaces, p_unsigned);
|
|
PRINT_ATTRf(ksymbol, p_unsigned);
|
|
PRINT_ATTRf(bpf_event, p_unsigned);
|
|
PRINT_ATTRf(aux_output, p_unsigned);
|
|
|
|
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
|
|
PRINT_ATTRf(bp_type, p_unsigned);
|
|
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
|
|
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
|
|
PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
|
|
PRINT_ATTRf(sample_regs_user, p_hex);
|
|
PRINT_ATTRf(sample_stack_user, p_unsigned);
|
|
PRINT_ATTRf(clockid, p_signed);
|
|
PRINT_ATTRf(sample_regs_intr, p_hex);
|
|
PRINT_ATTRf(aux_watermark, p_unsigned);
|
|
PRINT_ATTRf(sample_max_stack, p_unsigned);
|
|
PRINT_ATTRf(aux_sample_size, p_unsigned);
|
|
|
|
return ret;
|
|
}
|