1
linux/tools/perf/util/trace-event-parse.c

330 lines
7.0 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2009, Steven Rostedt <srostedt@redhat.com>
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include "debug.h"
perf tools: Add trace event information parser Add util/trace-event-parse.c which provides the handlers to parse the ftrace events info from the stream and handles the ftrace perf samples event printing. This file is a rename of the parse-events.c file from the trace-cmd tools, written by Steven Rostedt and Josh Triplett, originated from the git tree: git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git This is a perf tools integration. [ fweisbec@gmail.com: various changes for perf tools integration. ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Clark Williams <williams@redhat.com> Cc: Jon Masters <jonathan@jonmasters.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Christoph Hellwig <hch@infradead.org> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Zhaolei <zhaolei@cn.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Roland McGrath <roland@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1250518688-7207-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-17 07:18:07 -07:00
#include "trace-event.h"
#include <linux/ctype.h>
perf build: Use libtraceevent from the system Remove the LIBTRACEEVENT_DYNAMIC and LIBTRACEFS_DYNAMIC make command line variables. If libtraceevent isn't installed or NO_LIBTRACEEVENT=1 is passed to the build, don't compile in libtraceevent and libtracefs support. This also disables CONFIG_TRACE that controls "perf trace". CONFIG_LIBTRACEEVENT is used to control enablement in Build/Makefiles, HAVE_LIBTRACEEVENT is used in C code. Without HAVE_LIBTRACEEVENT tracepoints are disabled and as such the commands kmem, kwork, lock, sched and timechart are removed. The majority of commands continue to work including "perf test". Committer notes: Fixed up a tools/perf/util/Build reject and added: #include <traceevent/event-parse.h> to tools/perf/util/scripting-engines/trace-event-perl.c. Committer testing: $ rpm -qi libtraceevent-devel Name : libtraceevent-devel Version : 1.5.3 Release : 2.fc36 Architecture: x86_64 Install Date: Mon 25 Jul 2022 03:20:19 PM -03 Group : Unspecified Size : 27728 License : LGPLv2+ and GPLv2+ Signature : RSA/SHA256, Fri 15 Apr 2022 02:11:58 PM -03, Key ID 999f7cbf38ab71f4 Source RPM : libtraceevent-1.5.3-2.fc36.src.rpm Build Date : Fri 15 Apr 2022 10:57:01 AM -03 Build Host : buildvm-x86-05.iad2.fedoraproject.org Packager : Fedora Project Vendor : Fedora Project URL : https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/ Bug URL : https://bugz.fedoraproject.org/libtraceevent Summary : Development headers of libtraceevent Description : Development headers of libtraceevent-libs $ Default build: $ ldd ~/bin/perf | grep tracee libtraceevent.so.1 => /lib64/libtraceevent.so.1 (0x00007f1dcaf8f000) $ # perf trace -e sched:* --max-events 10 0.000 migration/0/17 sched:sched_migrate_task(comm: "", pid: 1603763 (perf), prio: 120, dest_cpu: 1) 0.005 migration/0/17 sched:sched_wake_idle_without_ipi(cpu: 1) 0.011 migration/0/17 sched:sched_switch(prev_comm: "", prev_pid: 17 (migration/0), prev_state: 1, next_comm: "", next_prio: 120) 1.173 :0/0 sched:sched_wakeup(comm: "", pid: 3138 (gnome-terminal-), prio: 120) 1.180 :0/0 sched:sched_switch(prev_comm: "", prev_prio: 120, next_comm: "", next_pid: 3138 (gnome-terminal-), next_prio: 120) 0.156 migration/1/21 sched:sched_migrate_task(comm: "", pid: 1603763 (perf), prio: 120, orig_cpu: 1, dest_cpu: 2) 0.160 migration/1/21 sched:sched_wake_idle_without_ipi(cpu: 2) 0.166 migration/1/21 sched:sched_switch(prev_comm: "", prev_pid: 21 (migration/1), prev_state: 1, next_comm: "", next_prio: 120) 1.183 :0/0 sched:sched_wakeup(comm: "", pid: 1602985 (kworker/u16:0-f), prio: 120, target_cpu: 1) 1.186 :0/0 sched:sched_switch(prev_comm: "", prev_prio: 120, next_comm: "", next_pid: 1602985 (kworker/u16:0-f), next_prio: 120) # Had to tweak tools/perf/util/setup.py to make sure the python binding shared object links with libtraceevent if -DHAVE_LIBTRACEEVENT is present in CFLAGS. Building with NO_LIBTRACEEVENT=1 uncovered some more build failures: - Make building of data-convert-bt.c to CONFIG_LIBTRACEEVENT=y - perf-$(CONFIG_LIBTRACEEVENT) += scripts/ - bpf_kwork.o needs also to be dependent on CONFIG_LIBTRACEEVENT=y - The python binding needed some fixups and util/trace-event.c can't be built and linked with the python binding shared object, so remove it in tools/perf/util/setup.py and exclude it from the list of dependencies in the python/perf.so Makefile.perf target. Building without libtraceevent-devel installed uncovered more build failures: - The python binding tools/perf/util/python.c was assuming that traceevent/parse-events.h was always available, which was the case when we defaulted to using the in-kernel tools/lib/traceevent/ files, now we need to enclose it under ifdef HAVE_LIBTRACEEVENT, just like the other parts of it that deal with tracepoints. - We have to ifdef the rules in the Build files with CONFIG_LIBTRACEEVENT=y to build builtin-trace.c and tools/perf/trace/beauty/ as we only ifdef setting CONFIG_TRACE=y when setting NO_LIBTRACEEVENT=1 in the make command line, not when we don't detect libtraceevent-devel installed in the system. Simplification here to avoid these two ways of disabling builtin-trace.c and not having CONFIG_TRACE=y when libtraceevent-devel isn't installed is the clean way. From Athira: <quote> tools/perf/arch/powerpc/util/Build -perf-y += kvm-stat.o +perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o </quote> Then, ditto for arm64 and s390, detected by container cross build tests. - s/390 uses test__checkevent_tracepoint() that is now only available if HAVE_LIBTRACEEVENT is defined, enclose the callsite with ifder HAVE_LIBTRACEEVENT. Also from Athira: <quote> With this change, I could successfully compile in these environment: - Without libtraceevent-devel installed - With libtraceevent-devel installed - With “make NO_LIBTRACEEVENT=1” </quote> Then, finally rename CONFIG_TRACEEVENT to CONFIG_LIBTRACEEVENT for consistency with other libraries detected in tools/perf/. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: bpf@vger.kernel.org Link: http://lore.kernel.org/lkml/20221205225940.3079667-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-12-05 15:59:39 -07:00
#include <linux/kernel.h>
#include <traceevent/event-parse.h>
static int get_common_field(struct scripting_context *context,
int *offset, int *size, const char *type)
{
struct tep_handle *pevent = context->pevent;
struct tep_event *event;
struct tep_format_field *field;
if (!*size) {
event = tep_get_first_event(pevent);
if (!event)
return 0;
field = tep_find_common_field(event, type);
if (!field)
return 0;
*offset = field->offset;
*size = field->size;
}
return tep_read_number(pevent, context->event_data + *offset, *size);
}
int common_lock_depth(struct scripting_context *context)
{
static int offset;
static int size;
int ret;
ret = get_common_field(context, &size, &offset,
"common_lock_depth");
if (ret < 0)
return -1;
return ret;
}
int common_flags(struct scripting_context *context)
{
static int offset;
static int size;
int ret;
ret = get_common_field(context, &size, &offset,
"common_flags");
if (ret < 0)
return -1;
return ret;
}
int common_pc(struct scripting_context *context)
{
static int offset;
static int size;
int ret;
ret = get_common_field(context, &size, &offset,
"common_preempt_count");
if (ret < 0)
return -1;
return ret;
}
unsigned long long
raw_field_value(struct tep_event *event, const char *name, void *data)
{
struct tep_format_field *field;
unsigned long long val;
field = tep_find_any_field(event, name);
if (!field)
return 0ULL;
tep_read_number_field(field, data, &val);
return val;
}
unsigned long long read_size(struct tep_event *event, void *ptr, int size)
{
return tep_read_number(event->tep, ptr, size);
}
void event_format__fprintf(struct tep_event *event,
int cpu, void *data, int size, FILE *fp)
{
struct tep_record record;
struct trace_seq s;
memset(&record, 0, sizeof(record));
record.cpu = cpu;
record.size = size;
record.data = data;
trace_seq_init(&s);
libtraceevent, perf tools: Changes in tep_print_event_* APIs Libtraceevent APIs for printing various trace events information are complicated, there are complex extra parameters. To control the way event information is printed, the user should call a set of functions in a specific sequence. These APIs are reimplemented to provide a more simple interface for printing event information. Removed APIs: tep_print_event_task() tep_print_event_time() tep_print_event_data() tep_event_info() tep_is_latency_format() tep_set_latency_format() tep_data_latency_format() tep_set_print_raw() A new API for printing event information is introduced: void tep_print_event(struct tep_handle *tep, struct trace_seq *s, struct tep_record *record, const char *fmt, ...); where "fmt" is a printf-like format string, followed by the event fields to be printed. Supported fields: TEP_PRINT_PID, "%d" - event PID TEP_PRINT_CPU, "%d" - event CPU TEP_PRINT_COMM, "%s" - event command string TEP_PRINT_NAME, "%s" - event name TEP_PRINT_LATENCY, "%s" - event latency TEP_PRINT_TIME, %d - event time stamp. A divisor and precision can be specified as part of this format string: "%precision.divisord". Example: "%3.1000d" - divide the time by 1000 and print the first 3 digits before the dot. Thus, the time stamp "123456000" will be printed as "123.456" TEP_PRINT_INFO, "%s" - event information. TEP_PRINT_INFO_RAW, "%s" - event information, in raw format. Example: tep_print_event(tep, s, record, "%16s-%-5d [%03d] %s %6.1000d %s %s", TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_CPU, TEP_PRINT_LATENCY, TEP_PRINT_TIME, TEP_PRINT_NAME, TEP_PRINT_INFO); Output: ls-11314 [005] d.h. 185207.366383 function __wake_up Signed-off-by: Tzvetomir Stoyanov <tstoyanov@vmware.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: linux-trace-devel@vger.kernel.org Cc: Patrick McLean <chutzpah@gentoo.org> Link: http://lore.kernel.org/linux-trace-devel/20190801074959.22023-2-tz.stoyanov@gmail.com Link: http://lore.kernel.org/lkml/20190805204355.041132030@goodmis.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-05 13:43:13 -07:00
tep_print_event(event->tep, &s, &record, "%s", TEP_PRINT_INFO);
trace_seq_do_fprintf(&s, fp);
trace_seq_destroy(&s);
}
void event_format__print(struct tep_event *event,
int cpu, void *data, int size)
{
return event_format__fprintf(event, cpu, data, size, stdout);
}
/*
* prev_state is of size long, which is 32 bits on 32 bit architectures.
* As it needs to have the same bits for both 32 bit and 64 bit architectures
* we can just assume that the flags we care about will all be within
* the 32 bits.
*/
#define MAX_STATE_BITS 32
static const char *convert_sym(struct tep_print_flag_sym *sym)
{
static char save_states[MAX_STATE_BITS + 1];
memset(save_states, 0, sizeof(save_states));
/* This is the flags for the prev_state_field, now make them into a string */
for (; sym; sym = sym->next) {
long bitmask = strtoul(sym->value, NULL, 0);
int i;
for (i = 0; !(bitmask & 1); i++)
bitmask >>= 1;
if (i >= MAX_STATE_BITS)
continue;
save_states[i] = sym->str[0];
}
return save_states;
}
static struct tep_print_arg_field *
find_arg_field(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
{
struct tep_print_arg_field *field;
if (!arg)
return NULL;
if (arg->type == TEP_PRINT_FIELD)
return &arg->field;
if (arg->type == TEP_PRINT_OP) {
field = find_arg_field(prev_state_field, arg->op.left);
if (field && field->field == prev_state_field)
return field;
field = find_arg_field(prev_state_field, arg->op.right);
if (field && field->field == prev_state_field)
return field;
}
return NULL;
}
static struct tep_print_flag_sym *
test_flags(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
{
struct tep_print_arg_field *field;
field = find_arg_field(prev_state_field, arg->flags.field);
if (!field)
return NULL;
return arg->flags.flags;
}
static struct tep_print_flag_sym *
search_op(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
{
struct tep_print_flag_sym *sym = NULL;
if (!arg)
return NULL;
if (arg->type == TEP_PRINT_OP) {
sym = search_op(prev_state_field, arg->op.left);
if (sym)
return sym;
sym = search_op(prev_state_field, arg->op.right);
if (sym)
return sym;
} else if (arg->type == TEP_PRINT_FLAGS) {
sym = test_flags(prev_state_field, arg);
}
return sym;
}
const char *parse_task_states(struct tep_format_field *state_field)
{
struct tep_print_flag_sym *sym;
struct tep_print_arg *arg;
struct tep_event *event;
event = state_field->event;
/*
* Look at the event format fields, and search for where
* the prev_state is parsed via the format flags.
*/
for (arg = event->print_fmt.args; arg; arg = arg->next) {
/*
* Currently, the __print_flags() for the prev_state
* is embedded in operations, so they too must be
* searched.
*/
sym = search_op(state_field, arg);
if (sym)
return convert_sym(sym);
}
return NULL;
}
void parse_ftrace_printk(struct tep_handle *pevent,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 15:15:03 -07:00
char *file, unsigned int size __maybe_unused)
{
unsigned long long addr;
char *printk;
char *line;
char *next = NULL;
char *addr_str;
char *fmt = NULL;
line = strtok_r(file, "\n", &next);
while (line) {
addr_str = strtok_r(line, ":", &fmt);
if (!addr_str) {
pr_warning("printk format with empty entry");
break;
}
addr = strtoull(addr_str, NULL, 16);
/* fmt still has a space, skip it */
printk = strdup(fmt+1);
line = strtok_r(NULL, "\n", &next);
tep_register_print_string(pevent, printk, addr);
free(printk);
}
}
void parse_saved_cmdline(struct tep_handle *pevent,
char *file, unsigned int size __maybe_unused)
{
char comm[17]; /* Max comm length in the kernel is 16. */
char *line;
char *next = NULL;
int pid;
line = strtok_r(file, "\n", &next);
while (line) {
if (sscanf(line, "%d %16s", &pid, comm) == 2)
tep_register_comm(pevent, comm, pid);
line = strtok_r(NULL, "\n", &next);
}
}
int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size)
{
return tep_parse_event(pevent, buf, size, "ftrace");
}
int parse_event_file(struct tep_handle *pevent,
char *buf, unsigned long size, char *sys)
{
return tep_parse_event(pevent, buf, size, sys);
}
struct flag {
const char *name;
unsigned long long value;
};
static const struct flag flags[] = {
{ "HI_SOFTIRQ", 0 },
{ "TIMER_SOFTIRQ", 1 },
{ "NET_TX_SOFTIRQ", 2 },
{ "NET_RX_SOFTIRQ", 3 },
{ "BLOCK_SOFTIRQ", 4 },
{ "IRQ_POLL_SOFTIRQ", 5 },
{ "TASKLET_SOFTIRQ", 6 },
{ "SCHED_SOFTIRQ", 7 },
{ "HRTIMER_SOFTIRQ", 8 },
{ "RCU_SOFTIRQ", 9 },
{ "HRTIMER_NORESTART", 0 },
{ "HRTIMER_RESTART", 1 },
};
unsigned long long eval_flag(const char *flag)
{
int i;
/*
* Some flags in the format files do not get converted.
* If the flag is not numeric, see if it is something that
* we already know about.
*/
if (isdigit(flag[0]))
return strtoull(flag, NULL, 0);
for (i = 0; i < (int)(ARRAY_SIZE(flags)); i++)
if (strcmp(flags[i].name, flag) == 0)
return flags[i].value;
return 0;
}