OpenCloudOS-Kernel/tools/perf/util/perf_event_attr_fprintf.c

160 lines
5.1 KiB
C
Raw Normal View History

// 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),
bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), bit_name(CODE_PAGE_SIZE),
perf tools: Support PERF_SAMPLE_WEIGHT_STRUCT The new sample type, PERF_SAMPLE_WEIGHT_STRUCT, is an alternative of the PERF_SAMPLE_WEIGHT sample type. Users can apply either the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but they cannot apply both sample types simultaneously. The new sample type shares the same space as the PERF_SAMPLE_WEIGHT sample type. The lower 32 bits are exactly the same for both sample type. The higher 32 bits may be different for different architecture. Add arch specific arch_evsel__set_sample_weight() to set the new sample type for X86. Only store the lower 32 bits for the sample->weight if the new sample type is applied. In practice, no memory access could last than 4G cycles. No data will be lost. If the kernel doesn't support the new sample type. Fall back to the PERF_SAMPLE_WEIGHT sample type. There is no impact for other architectures. Committer notes: Fixup related to PERF_SAMPLE_CODE_PAGE_SIZE, present in acme/perf/core but not upstream yet. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/1612296553-21962-6-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-02-03 04:09:09 +08:00
bit_name(WEIGHT_STRUCT),
{ .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),
perf evsel: Support PERF_SAMPLE_BRANCH_HW_INDEX 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>
2020-02-29 00:30:01 +08:00
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_ATTRf(cgroup, p_unsigned);
perf record: Add --buildid-mmap option to enable PERF_RECORD_MMAP2's build id Add --buildid-mmap option to enable build id in PERF_RECORD_MMAP2 events. It will only work if there's kernel support for that and it disables build id cache (implies --no-buildid). It's also possible to enable it permanently via config option in ~/.perfconfig file: [record] build-id=mmap Also added build_id bit in the verbose output for perf_event_attr: # perf record --buildid-mmap -vv ... perf_event_attr: type 1 size 120 ... build_id 1 Adding also missing text_poke bit. Committer testing: $ perf record -h build Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -B, --no-buildid do not collect buildids in perf.data -N, --no-buildid-cache do not update the buildid cache --buildid-all Record build-id of all DSOs regardless of hits --buildid-mmap Record build-id in map events $ $ perf record --buildid-mmap sleep 1 Failed: no support to record build id in mmap events, update your kernel. $ After adding the needed kernel bits in a test kernel: $ perf record -vv --buildid-mmap sleep 1 |& grep -m1 build Enabling build id in mmap2 events. $ perf evlist -v cycles:u: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 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, ksymbol: 1, bpf_event: 1, build_id: 1 $ Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Budankov <abudankov@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20201214105457.543111-16-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-12-14 18:54:57 +08:00
PRINT_ATTRf(text_poke, p_unsigned);
PRINT_ATTRf(build_id, p_unsigned);
PRINT_ATTRf(inherit_thread, p_unsigned);
PRINT_ATTRf(remove_on_exec, p_unsigned);
PRINT_ATTRf(sigtrap, 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);
PRINT_ATTRf(sig_data, p_unsigned);
return ret;
}