Default: fractal,0.5,callee,function.
+--max-stack::
+ Set the stack depth limit when parsing the callchain, anything
+ beyond the specified depth will be ignored. This is a trade-off
+ between information loss and faster processing especially for
+ workloads that can have a very long callchain stack.
+
+ Default: 127
+
-G::
--inverted::
alias for inverted caller based call graph.
Default: fractal,0.5,callee.
+--max-stack::
+ Set the stack depth limit when parsing the callchain, anything
+ beyond the specified depth will be ignored. This is a trade-off
+ between information loss and faster processing especially for
+ workloads that can have a very long callchain stack.
+
+ Default: 127
+
--ignore-callees=<regex>::
Ignore callees of the function(s) matching the given regex.
This has the effect of collecting the callers of each such
Show a summary of syscalls by thread with min, max, and average times (in
msec) and relative stddev.
+--tool_stats::
+ Show tool stats such as number of times fd->pathname was discovered thru
+ hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script[1]
LIB_OBJS += $(OUTPUT)util/stat.o
LIB_OBJS += $(OUTPUT)util/record.o
LIB_OBJS += $(OUTPUT)util/srcline.o
+LIB_OBJS += $(OUTPUT)util/data.o
LIB_OBJS += $(OUTPUT)ui/setup.o
LIB_OBJS += $(OUTPUT)ui/helpline.o
/* Check whether our max runtime timed out: */
if (g->p.nr_secs) {
timersub(&stop, &start0, &diff);
- if (diff.tv_sec >= g->p.nr_secs) {
+ if ((u32)diff.tv_sec >= g->p.nr_secs) {
g->stop_work = true;
break;
}
runtime_ns_max += diff.tv_usec * 1000;
if (details >= 0) {
- printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+ printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
process_nr, thread_nr, runtime_ns_max / bytes_done, val);
}
fflush(stdout);
#include "util/hist.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/data.h"
#include "arch/common.h"
#include <dlfcn.h>
struct perf_session *session;
struct perf_evsel *pos;
u64 total_nr_samples;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ .force = ann->force,
+ };
- session = perf_session__new(input_name, O_RDONLY,
- ann->force, false, &ann->tool);
+ session = perf_session__new(&file, false, &ann->tool);
if (session == NULL)
return -ENOMEM;
}
if (total_nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->filename);
+ ui__error("The %s file has no samples!\n", file.path);
goto out_delete;
}
static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
{
- struct perf_session *session = perf_session__new(filename, O_RDONLY,
- force, false, NULL);
+ struct perf_data_file file = {
+ .path = filename,
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
+ };
+ struct perf_session *session = perf_session__new(&file, false, NULL);
if (session == NULL)
return -1;
#include "util/parse-options.h"
#include "util/session.h"
#include "util/symbol.h"
+#include "util/data.h"
static int sysfs__fprintf_build_id(FILE *fp)
{
static int perf_session__list_build_ids(bool force, bool with_hits)
{
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
+ };
symbol__elf_init();
/*
if (filename__fprintf_build_id(input_name, stdout))
goto out;
- session = perf_session__new(input_name, O_RDONLY, force, false,
- &build_id__mark_dso_hit_ops);
+ session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
/*
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
*/
- if (with_hits || session->fd_pipe)
+ if (with_hits || perf_data_file__is_pipe(&file))
perf_session__process_events(session, &build_id__mark_dso_hit_ops);
perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
#include "util/sort.h"
#include "util/symbol.h"
#include "util/util.h"
+#include "util/data.h"
#include <stdlib.h>
#include <math.h>
struct data__file {
struct perf_session *session;
- const char *file;
+ struct perf_data_file file;
int idx;
struct hists *hists;
struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX];
data__for_each_file(i, d)
fprintf(stdout, "# [%d] %s %s\n",
- d->idx, d->file,
+ d->idx, d->file.path,
!d->idx ? "(Baseline)" : "");
fprintf(stdout, "#\n");
int ret = -EINVAL, i;
data__for_each_file(i, d) {
- d->session = perf_session__new(d->file, O_RDONLY, force,
- false, &tool);
+ d->session = perf_session__new(&d->file, false, &tool);
if (!d->session) {
- pr_err("Failed to open %s\n", d->file);
+ pr_err("Failed to open %s\n", d->file.path);
ret = -ENOMEM;
goto out_delete;
}
ret = perf_session__process_events(d->session, &tool);
if (ret) {
- pr_err("Failed to process %s\n", d->file);
+ pr_err("Failed to process %s\n", d->file.path);
goto out_delete;
}
return -ENOMEM;
data__for_each_file(i, d) {
- d->file = use_default ? defaults[i] : argv[i];
+ struct perf_data_file *file = &d->file;
+
+ file->path = use_default ? defaults[i] : argv[i];
+ file->mode = PERF_DATA_MODE_READ,
+ file->force = force,
+
d->idx = i;
}
#include "util/parse-events.h"
#include "util/parse-options.h"
#include "util/session.h"
+#include "util/data.h"
static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
{
struct perf_session *session;
struct perf_evsel *pos;
+ struct perf_data_file file = {
+ .path = file_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(file_name, O_RDONLY, 0, false, NULL);
+ session = perf_session__new(&file, 0, NULL);
if (session == NULL)
return -ENOMEM;
#include "util/tool.h"
#include "util/debug.h"
#include "util/build-id.h"
+#include "util/data.h"
#include "util/parse-options.h"
{
struct perf_session *session;
int ret = -EINVAL;
+ struct perf_data_file file = {
+ .path = inject->input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
signal(SIGINT, sig_handler);
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
- session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool);
+ session = perf_session__new(&file, true, &inject->tool);
if (session == NULL)
return -ENOMEM;
#include "util/parse-options.h"
#include "util/trace-event.h"
+#include "util/data.h"
#include "util/debug.h"
{ "kmem:kfree", perf_evsel__process_free_event, },
{ "kmem:kmem_cache_free", perf_evsel__process_free_event, },
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem);
+ session = perf_session__new(&file, false, &perf_kmem);
if (session == NULL)
return -ENOMEM;
#include "util/tool.h"
#include "util/stat.h"
#include "util/top.h"
+#include "util/data.h"
#include <sys/prctl.h>
#include <sys/timerfd.h>
.comm = perf_event__process_comm,
.ordered_samples = true,
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
kvm->tool = eops;
- kvm->session = perf_session__new(kvm->file_name, O_RDONLY, 0, false,
- &kvm->tool);
+ kvm->session = perf_session__new(&file, false, &kvm->tool);
if (!kvm->session) {
pr_err("Initializing perf session failed\n");
return -EINVAL;
"perf kvm stat live [<options>]",
NULL
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_WRITE,
+ };
/* event handling */
/*
* perf session
*/
- kvm->session = perf_session__new(NULL, O_WRONLY, false, false, &kvm->tool);
+ kvm->session = perf_session__new(&file, false, &kvm->tool);
if (kvm->session == NULL) {
err = -ENOMEM;
goto out;
#include "util/debug.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/data.h"
#include <sys/types.h>
#include <sys/prctl.h>
.comm = perf_event__process_comm,
.ordered_samples = true,
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &eops);
+ session = perf_session__new(&file, false, &eops);
if (!session) {
pr_err("Initializing perf session failed\n");
return -ENOMEM;
#include "util/trace-event.h"
#include "util/tool.h"
#include "util/session.h"
+#include "util/data.h"
#define MEM_OPERATION_LOAD "load"
#define MEM_OPERATION_STORE "store"
static int report_raw_events(struct perf_mem *mem)
{
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
int err = -EINVAL;
int ret;
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &mem->tool);
+ struct perf_session *session = perf_session__new(&file, false,
+ &mem->tool);
if (session == NULL)
return -ENOMEM;
#include "util/symbol.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
+#include "util/data.h"
#include <unistd.h>
#include <sched.h>
struct perf_tool tool;
struct perf_record_opts opts;
u64 bytes_written;
- const char *output_name;
+ struct perf_data_file file;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
- int output;
int realtime_prio;
bool no_buildid;
bool no_buildid_cache;
static int write_output(struct perf_record *rec, void *buf, size_t size)
{
+ struct perf_data_file *file = &rec->file;
+
while (size) {
- int ret = write(rec->output, buf, size);
+ int ret = write(file->fd, buf, size);
if (ret < 0) {
- pr_err("failed to write\n");
+ pr_err("failed to write perf data, error: %m\n");
return -1;
}
static int process_buildids(struct perf_record *rec)
{
- u64 size = lseek(rec->output, 0, SEEK_CUR);
+ struct perf_data_file *file = &rec->file;
+ struct perf_session *session = rec->session;
+ u64 size = lseek(file->fd, 0, SEEK_CUR);
if (size == 0)
return 0;
- rec->session->fd = rec->output;
- return __perf_session__process_events(rec->session, rec->post_processing_offset,
+ return __perf_session__process_events(session, rec->post_processing_offset,
size - rec->post_processing_offset,
size, &build_id__mark_dso_hit_ops);
}
static void perf_record__exit(int status, void *arg)
{
struct perf_record *rec = arg;
+ struct perf_data_file *file = &rec->file;
if (status != 0)
return;
- if (!rec->opts.pipe_output) {
+ if (!file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
if (!rec->no_buildid)
process_buildids(rec);
perf_session__write_header(rec->session, rec->evlist,
- rec->output, true);
+ file->fd, true);
perf_session__delete(rec->session);
perf_evlist__delete(rec->evlist);
symbol__exit();
static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
{
- struct stat st;
- int flags;
- int err, output, feat;
+ int err, feat;
unsigned long waking = 0;
const bool forks = argc > 0;
struct machine *machine;
struct perf_tool *tool = &rec->tool;
struct perf_record_opts *opts = &rec->opts;
struct perf_evlist *evsel_list = rec->evlist;
- const char *output_name = rec->output_name;
+ struct perf_data_file *file = &rec->file;
struct perf_session *session;
bool disabled = false;
signal(SIGUSR1, sig_handler);
signal(SIGTERM, sig_handler);
- if (!output_name) {
- if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
- opts->pipe_output = true;
- else
- rec->output_name = output_name = "perf.data";
- }
- if (output_name) {
- if (!strcmp(output_name, "-"))
- opts->pipe_output = true;
- else if (!stat(output_name, &st) && st.st_size) {
- char oldname[PATH_MAX];
- snprintf(oldname, sizeof(oldname), "%s.old",
- output_name);
- unlink(oldname);
- rename(output_name, oldname);
- }
- }
-
- flags = O_CREAT|O_RDWR|O_TRUNC;
-
- if (opts->pipe_output)
- output = STDOUT_FILENO;
- else
- output = open(output_name, flags, S_IRUSR | S_IWUSR);
- if (output < 0) {
- perror("failed to create output file");
- return -1;
- }
-
- rec->output = output;
-
- session = perf_session__new(output_name, O_WRONLY,
- true, false, NULL);
+ session = perf_session__new(file, false, NULL);
if (session == NULL) {
pr_err("Not enough memory for reading perf file header\n");
return -1;
if (forks) {
err = perf_evlist__prepare_workload(evsel_list, &opts->target,
- argv, opts->pipe_output,
+ argv, file->is_pipe,
true);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
*/
on_exit(perf_record__exit, rec);
- if (opts->pipe_output) {
- err = perf_header__write_pipe(output);
+ if (file->is_pipe) {
+ err = perf_header__write_pipe(file->fd);
if (err < 0)
goto out_delete_session;
} else {
err = perf_session__write_header(session, evsel_list,
- output, false);
+ file->fd, false);
if (err < 0)
goto out_delete_session;
}
goto out_delete_session;
}
- rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
+ rec->post_processing_offset = lseek(file->fd, 0, SEEK_CUR);
machine = &session->machines.host;
- if (opts->pipe_output) {
+ if (file->is_pipe) {
err = perf_event__synthesize_attrs(tool, session,
process_synthesized_event);
if (err < 0) {
* return this more properly and also
* propagate errors that now are calling die()
*/
- err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
+ err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
fprintf(stderr,
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
(double)rec->bytes_written / 1024.0 / 1024.0,
- output_name,
+ file->path,
rec->bytes_written / 24);
return 0;
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
- OPT_STRING('o', "output", &record.output_name, "file",
+ OPT_STRING('o', "output", &record.file.path, "file",
"output file name"),
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
"child tasks do not inherit counters"),
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
+#include "util/data.h"
#include "arch/common.h"
#include <dlfcn.h>
bool show_threads;
bool inverted_callchain;
bool mem_mode;
+ int max_stack;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
const char *cpu_list;
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
return err;
}
-static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+static int perf_evsel__add_hist_entry(struct perf_tool *tool,
+ struct perf_evsel *evsel,
struct addr_location *al,
struct perf_sample *sample,
struct machine *machine)
{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
struct symbol *parent = NULL;
int err = 0;
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
if (al.map != NULL)
al.map->dso->hit = 1;
- ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
+ ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
+ machine);
if (ret < 0)
pr_debug("problem incrementing symbol period, skipping event\n");
}
{
struct perf_session *self = rep->session;
u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
+ bool is_pipe = perf_data_file__is_pipe(self->file);
- if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+ if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
ui__error("Selected --sort parent, but no "
"callchain data. Did you call "
}
if (sort__mode == SORT_MODE__BRANCH) {
- if (!self->fd_pipe &&
+ if (!is_pipe &&
!(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
ui__error("Selected -b but no branch data. "
"Did you call perf record without -b?\n");
struct map *kernel_map;
struct kmap *kernel_kmap;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+ struct perf_data_file *file = session->file;
signal(SIGINT, sig_handler);
return 0;
if (nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->filename);
+ ui__error("The %s file has no samples!\n", file->path);
return 0;
}
.ordered_samples = true,
.ordering_requires_timestamps = true,
},
+ .max_stack = PERF_MAX_STACK_DEPTH,
.pretty_printing_style = "normal",
};
const struct option options[] = {
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+ OPT_INTEGER(0, "max-stack", &report.max_stack,
+ "Set the maximum stack depth when parsing the callchain, "
+ "anything beyond the specified depth will be ignored. "
+ "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
"Don't show entries under that percent", parse_percent_limit),
OPT_END()
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
perf_config(perf_report_config, &report);
perf_hpp__init();
}
+ file.path = input_name;
+ file.force = report.force;
+
repeat:
- session = perf_session__new(input_name, O_RDONLY,
- report.force, false, &report.tool);
+ session = perf_session__new(&file, false, &report.tool);
if (session == NULL)
return -ENOMEM;
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
};
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
- session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool);
+ session = perf_session__new(&file, false, &sched->tool);
if (session == NULL) {
pr_debug("No Memory for session\n");
return -1;
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/sort.h"
+#include "util/data.h"
#include <linux/bitmap.h>
static char const *script_name;
printf(" => ");
/* print branch_to information */
- if (PRINT_FIELD(ADDR))
+ if (PRINT_FIELD(ADDR) ||
+ ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+ !output[attr->type].user_set))
print_sample_addr(event, sample, machine, thread, attr);
printf("\n");
char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
DIR *scripts_dir, *lang_dir;
struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
char *temp;
int i = 0;
- session = perf_session__new(input_name, O_RDONLY, 0, false, NULL);
+ session = perf_session__new(&file, false, NULL);
if (!session)
return -1;
"perf script [<options>] <top-script> [script-args]",
NULL
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
setup_scripting();
argc = parse_options(argc, argv, options, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
+ file.path = input_name;
+
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
if (!rec_script_path)
if (!script_name)
setup_pager();
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &perf_script);
+ session = perf_session__new(&file, false, &perf_script);
if (session == NULL)
return -ENOMEM;
return -1;
}
- input = open(session->filename, O_RDONLY); /* input_name */
+ input = open(file.path, O_RDONLY); /* input_name */
if (input < 0) {
perror("failed to open file");
return -1;
#include "util/session.h"
#include "util/svghelper.h"
#include "util/tool.h"
+#include "util/data.h"
#define SUPPORT_OLD_POWER_EVENTS 1
#define PWR_EVENT_EXIT -1
{ "power:power_frequency", process_sample_power_frequency },
#endif
};
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &perf_timechart);
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
+
+ struct perf_session *session = perf_session__new(&file, false,
+ &perf_timechart);
int ret = -EINVAL;
if (session == NULL)
sample->callchain) {
err = machine__resolve_callchain(machine, evsel,
al.thread, sample,
- &parent, &al);
+ &parent, &al,
+ top->max_stack);
if (err)
return;
}
struct perf_record_opts *opts = &top->record_opts;
pthread_t thread;
int ret;
- /*
- * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
- * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
- */
- top->session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
+
+ top->session = perf_session__new(NULL, false, NULL);
if (top->session == NULL)
return -ENOMEM;
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000, /* 4 KHz */
- .target = {
+ .target = {
.uses_mmap = true,
},
},
+ .max_stack = PERF_MAX_STACK_DEPTH,
.sym_pcnt_filter = 5,
};
struct perf_record_opts *opts = &top.record_opts;
OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
"mode[,dump_size]", record_callchain_help,
&parse_callchain_opt, "fp"),
+ OPT_INTEGER(0, "max-stack", &top.max_stack,
+ "Set the maximum stack depth when parsing the callchain. "
+ "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
"ignore callees of these functions in call graphs",
report_parse_ignore_callees_opt),
struct trace {
struct perf_tool tool;
- int audit_machine;
+ struct {
+ int machine;
+ int open_id;
+ } audit;
struct {
int max;
struct syscall *table;
struct strlist *ev_qualifier;
bool not_ev_qualifier;
bool live;
+ const char *last_vfs_getname;
struct intlist *tid_list;
struct intlist *pid_list;
bool sched;
bool multiple_threads;
bool summary;
bool show_comm;
+ bool show_tool_stats;
double duration_filter;
double runtime_ms;
+ struct {
+ u64 vfs_getname, proc_getname;
+ } stats;
};
-static int thread__read_fd_path(struct thread *thread, int fd)
+static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
{
struct thread_trace *ttrace = thread->priv;
- char linkname[PATH_MAX], pathname[PATH_MAX];
- struct stat st;
- int ret;
-
- if (thread->pid_ == thread->tid) {
- scnprintf(linkname, sizeof(linkname),
- "/proc/%d/fd/%d", thread->pid_, fd);
- } else {
- scnprintf(linkname, sizeof(linkname),
- "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
- }
-
- if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
- return -1;
-
- ret = readlink(linkname, pathname, sizeof(pathname));
-
- if (ret < 0 || ret > st.st_size)
- return -1;
-
- pathname[ret] = '\0';
if (fd > ttrace->paths.max) {
char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
return ttrace->paths.table[fd] != NULL ? 0 : -1;
}
-static const char *thread__fd_path(struct thread *thread, int fd, bool live)
+static int thread__read_fd_path(struct thread *thread, int fd)
+{
+ char linkname[PATH_MAX], pathname[PATH_MAX];
+ struct stat st;
+ int ret;
+
+ if (thread->pid_ == thread->tid) {
+ scnprintf(linkname, sizeof(linkname),
+ "/proc/%d/fd/%d", thread->pid_, fd);
+ } else {
+ scnprintf(linkname, sizeof(linkname),
+ "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
+ }
+
+ if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
+ return -1;
+
+ ret = readlink(linkname, pathname, sizeof(pathname));
+
+ if (ret < 0 || ret > st.st_size)
+ return -1;
+
+ pathname[ret] = '\0';
+ return trace__set_fd_pathname(thread, fd, pathname);
+}
+
+static const char *thread__fd_path(struct thread *thread, int fd,
+ struct trace *trace)
{
struct thread_trace *ttrace = thread->priv;
if (fd < 0)
return NULL;
- if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL) &&
- (!live || thread__read_fd_path(thread, fd)))
- return NULL;
+ if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+ if (!trace->live)
+ return NULL;
+ ++trace->stats.proc_getname;
+ if (thread__read_fd_path(thread, fd)) {
+ return NULL;
+ }
return ttrace->paths.table[fd];
}
{
int fd = arg->val;
size_t printed = scnprintf(bf, size, "%d", fd);
- const char *path = thread__fd_path(arg->thread, fd, arg->trace->live);
+ const char *path = thread__fd_path(arg->thread, fd, arg->trace);
if (path)
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
}
static bool done = false;
+static bool interrupted = false;
-static void sig_handler(int sig __maybe_unused)
+static void sig_handler(int sig)
{
done = true;
+ interrupted = sig == SIGINT;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
{
char tp_name[128];
struct syscall *sc;
- const char *name = audit_syscall_to_name(id, trace->audit_machine);
+ const char *name = audit_syscall_to_name(id, trace->audit.machine);
if (name == NULL)
return -1;
ret = perf_evsel__intval(evsel, sample, "ret");
+ if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
+ trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
+ trace->last_vfs_getname = NULL;
+ ++trace->stats.vfs_getname;
+ }
+
ttrace = thread->priv;
ttrace->exit_time = sample->time;
return 0;
}
+static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
+ return 0;
+}
+
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample)
{
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
+static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname",
+ evlist->nr_entries);
+ if (evsel == NULL)
+ return;
+
+ if (perf_evsel__field(evsel, "pathname") == NULL) {
+ perf_evsel__delete(evsel);
+ return;
+ }
+
+ evsel->handler.func = trace__vfs_getname;
+ perf_evlist__add(evlist, evsel);
+}
+
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = perf_evlist__new();
perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit))
goto out_error_tp;
+ perf_evlist__add_vfs_getname(evlist);
+
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
trace__sched_stat_runtime))
}
err = perf_evlist__open(evlist);
- if (err < 0) {
- fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
- goto out_delete_maps;
- }
+ if (err < 0)
+ goto out_error_open;
err = perf_evlist__mmap(evlist, UINT_MAX, false);
if (err < 0) {
handler = evsel->handler.func;
handler(trace, evsel, &sample);
- if (done)
- goto out_unmap_evlist;
+ if (interrupted)
+ goto out_disable;
}
}
if (trace->nr_events == before) {
- if (done)
- goto out_unmap_evlist;
+ int timeout = done ? 100 : -1;
- poll(evlist->pollfd, evlist->nr_fds, -1);
+ if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+ goto again;
+ } else {
+ goto again;
}
- if (done)
- perf_evlist__disable(evlist);
+out_disable:
+ perf_evlist__disable(evlist);
- goto again;
+ if (!err) {
+ if (trace->summary)
+ trace__fprintf_thread_summary(trace, trace->output);
-out_unmap_evlist:
- if (!err && trace->summary)
- trace__fprintf_thread_summary(trace, trace->output);
+ if (trace->show_tool_stats) {
+ fprintf(trace->output, "Stats:\n "
+ " vfs_getname : %" PRIu64 "\n"
+ " proc_getname: %" PRIu64 "\n",
+ trace->stats.vfs_getname,
+ trace->stats.proc_getname);
+ }
+ }
perf_evlist__munmap(evlist);
out_close_evlist:
out:
trace->live = false;
return err;
+{
+ char errbuf[BUFSIZ];
+
out_error_tp:
- switch(errno) {
- case ENOENT:
- fputs("Error:\tUnable to find debugfs\n"
- "Hint:\tWas your kernel was compiled with debugfs support?\n"
- "Hint:\tIs the debugfs filesystem mounted?\n"
- "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'\n",
- trace->output);
- break;
- case EACCES:
- fprintf(trace->output,
- "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
- "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
- debugfs_mountpoint, debugfs_mountpoint);
- break;
- default: {
- char bf[256];
- fprintf(trace->output, "Can't trace: %s\n",
- strerror_r(errno, bf, sizeof(bf)));
- }
- break;
- }
+ perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
+ goto out_error;
+
+out_error_open:
+ perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+
+out_error:
+ fprintf(trace->output, "%s\n", errbuf);
goto out_delete_evlist;
}
+}
static int trace__replay(struct trace *trace)
{
const struct perf_evsel_str_handler handlers[] = {
{ "raw_syscalls:sys_enter", trace__sys_enter, },
{ "raw_syscalls:sys_exit", trace__sys_exit, },
+ { "probe:vfs_getname", trace__vfs_getname, },
+ };
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
};
-
struct perf_session *session;
int err = -1;
if (symbol__init() < 0)
return -1;
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &trace->tool);
+ session = perf_session__new(&file, false, &trace->tool);
if (session == NULL)
return -ENOMEM;
NULL
};
struct trace trace = {
- .audit_machine = audit_detect_machine(),
+ .audit = {
+ .machine = audit_detect_machine(),
+ .open_id = audit_name_to_syscall("open", trace.audit.machine),
+ },
.syscalls = {
. max = -1,
},
const struct option trace_options[] = {
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
+ OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
"list of events to trace"),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
#include <stdio.h>
+#include <stdlib.h>
static void exit_fn(int status, void *__data)
{
bool no_delay;
bool no_inherit;
bool no_samples;
- bool pipe_output;
bool raw_samples;
bool sample_address;
bool sample_weight;
__thread struct callchain_cursor callchain_cursor;
-#define chain_for_each_child(child, parent) \
- list_for_each_entry(child, &parent->children, siblings)
-
-#define chain_for_each_child_safe(child, next, parent) \
- list_for_each_entry_safe(child, next, &parent->children, siblings)
-
static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
__sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
u64 min_hit)
{
+ struct rb_node *n;
struct callchain_node *child;
- chain_for_each_child(child, node)
+ n = rb_first(&node->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+
__sort_chain_flat(rb_root, child, min_hit);
+ }
if (node->hit && node->hit >= min_hit)
rb_insert_callchain(rb_root, node, CHAIN_FLAT);
static void __sort_chain_graph_abs(struct callchain_node *node,
u64 min_hit)
{
+ struct rb_node *n;
struct callchain_node *child;
node->rb_root = RB_ROOT;
+ n = rb_first(&node->rb_root_in);
+
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
- chain_for_each_child(child, node) {
__sort_chain_graph_abs(child, min_hit);
if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
static void __sort_chain_graph_rel(struct callchain_node *node,
double min_percent)
{
+ struct rb_node *n;
struct callchain_node *child;
u64 min_hit;
node->rb_root = RB_ROOT;
min_hit = ceil(node->children_hit * min_percent);
- chain_for_each_child(child, node) {
+ n = rb_first(&node->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+
__sort_chain_graph_rel(child, min_percent);
if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
return NULL;
}
new->parent = parent;
- INIT_LIST_HEAD(&new->children);
INIT_LIST_HEAD(&new->val);
if (inherit_children) {
- struct callchain_node *next;
+ struct rb_node *n;
+ struct callchain_node *child;
+
+ new->rb_root_in = parent->rb_root_in;
+ parent->rb_root_in = RB_ROOT;
- list_splice(&parent->children, &new->children);
- INIT_LIST_HEAD(&parent->children);
+ n = rb_first(&new->rb_root_in);
+ while (n) {
+ child = rb_entry(n, struct callchain_node, rb_node_in);
+ child->parent = new;
+ n = rb_next(n);
+ }
- chain_for_each_child(next, new)
- next->parent = new;
+ /* make it the first child */
+ rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node);
+ rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
}
- list_add_tail(&new->siblings, &parent->children);
return new;
}
}
}
-static void
+static struct callchain_node *
add_child(struct callchain_node *parent,
struct callchain_cursor *cursor,
u64 period)
new->children_hit = 0;
new->hit = period;
+ return new;
+}
+
+static s64 match_chain(struct callchain_cursor_node *node,
+ struct callchain_list *cnode)
+{
+ struct symbol *sym = node->sym;
+
+ if (cnode->ms.sym && sym &&
+ callchain_param.key == CCKEY_FUNCTION)
+ return cnode->ms.sym->start - sym->start;
+ else
+ return cnode->ip - node->ip;
}
/*
/* create a new child for the new branch if any */
if (idx_total < cursor->nr) {
+ struct callchain_node *first;
+ struct callchain_list *cnode;
+ struct callchain_cursor_node *node;
+ struct rb_node *p, **pp;
+
parent->hit = 0;
- add_child(parent, cursor, period);
parent->children_hit += period;
+
+ node = callchain_cursor_current(cursor);
+ new = add_child(parent, cursor, period);
+
+ /*
+ * This is second child since we moved parent's children
+ * to new (first) child above.
+ */
+ p = parent->rb_root_in.rb_node;
+ first = rb_entry(p, struct callchain_node, rb_node_in);
+ cnode = list_first_entry(&first->val, struct callchain_list,
+ list);
+
+ if (match_chain(node, cnode) < 0)
+ pp = &p->rb_left;
+ else
+ pp = &p->rb_right;
+
+ rb_link_node(&new->rb_node_in, p, pp);
+ rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
} else {
parent->hit = period;
}
u64 period)
{
struct callchain_node *rnode;
+ struct callchain_cursor_node *node;
+ struct rb_node **p = &root->rb_root_in.rb_node;
+ struct rb_node *parent = NULL;
+
+ node = callchain_cursor_current(cursor);
+ if (!node)
+ return;
/* lookup in childrens */
- chain_for_each_child(rnode, root) {
- unsigned int ret = append_chain(rnode, cursor, period);
+ while (*p) {
+ s64 ret;
+ struct callchain_list *cnode;
- if (!ret)
+ parent = *p;
+ rnode = rb_entry(parent, struct callchain_node, rb_node_in);
+ cnode = list_first_entry(&rnode->val, struct callchain_list,
+ list);
+
+ /* just check first entry */
+ ret = match_chain(node, cnode);
+ if (ret == 0) {
+ append_chain(rnode, cursor, period);
goto inc_children_hit;
+ }
+
+ if (ret < 0)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
}
/* nothing in children, add to the current node */
- add_child(root, cursor, period);
+ rnode = add_child(root, cursor, period);
+ rb_link_node(&rnode->rb_node_in, parent, p);
+ rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
inc_children_hit:
root->children_hit += period;
*/
list_for_each_entry(cnode, &root->val, list) {
struct callchain_cursor_node *node;
- struct symbol *sym;
node = callchain_cursor_current(cursor);
if (!node)
break;
- sym = node->sym;
-
- if (cnode->ms.sym && sym &&
- callchain_param.key == CCKEY_FUNCTION) {
- if (cnode->ms.sym->start != sym->start)
- break;
- } else if (cnode->ip != node->ip)
+ if (match_chain(node, cnode) != 0)
break;
- if (!found)
- found = true;
+ found = true;
callchain_cursor_advance(cursor);
}
- /* matches not, relay on the parent */
+ /* matches not, relay no the parent */
if (!found) {
cursor->curr = curr_snap;
cursor->pos = start;
struct callchain_node *dst, struct callchain_node *src)
{
struct callchain_cursor_node **old_last = cursor->last;
- struct callchain_node *child, *next_child;
+ struct callchain_node *child;
struct callchain_list *list, *next_list;
+ struct rb_node *n;
int old_pos = cursor->nr;
int err = 0;
append_chain_children(dst, cursor, src->hit);
}
- chain_for_each_child_safe(child, next_child, src) {
+ n = rb_first(&src->rb_root_in);
+ while (n) {
+ child = container_of(n, struct callchain_node, rb_node_in);
+ n = rb_next(n);
+ rb_erase(&child->rb_node_in, &src->rb_root_in);
+
err = merge_chain_branch(cursor, dst, child);
if (err)
break;
- list_del(&child->siblings);
free(child);
}
struct callchain_node {
struct callchain_node *parent;
- struct list_head siblings;
- struct list_head children;
struct list_head val;
- struct rb_node rb_node; /* to sort nodes in an rbtree */
- struct rb_root rb_root; /* sorted tree of children */
+ struct rb_node rb_node_in; /* to insert nodes in an rbtree */
+ struct rb_node rb_node; /* to sort nodes in an output tree */
+ struct rb_root rb_root_in; /* input tree of children */
+ struct rb_root rb_root; /* sorted output tree of children */
unsigned int val_nr;
u64 hit;
u64 children_hit;
static inline void callchain_init(struct callchain_root *root)
{
- INIT_LIST_HEAD(&root->node.siblings);
- INIT_LIST_HEAD(&root->node.children);
INIT_LIST_HEAD(&root->node.val);
root->node.parent = NULL;
root->node.hit = 0;
root->node.children_hit = 0;
+ root->node.rb_root_in = RB_ROOT;
root->max_depth = 0;
}
--- /dev/null
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+
+#include "data.h"
+#include "util.h"
+
+static bool check_pipe(struct perf_data_file *file)
+{
+ struct stat st;
+ bool is_pipe = false;
+ int fd = perf_data_file__is_read(file) ?
+ STDIN_FILENO : STDOUT_FILENO;
+
+ if (!file->path) {
+ if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
+ is_pipe = true;
+ } else {
+ if (!strcmp(file->path, "-"))
+ is_pipe = true;
+ }
+
+ if (is_pipe)
+ file->fd = fd;
+
+ return file->is_pipe = is_pipe;
+}
+
+static int check_backup(struct perf_data_file *file)
+{
+ struct stat st;
+
+ if (!stat(file->path, &st) && st.st_size) {
+ /* TODO check errors properly */
+ char oldname[PATH_MAX];
+ snprintf(oldname, sizeof(oldname), "%s.old",
+ file->path);
+ unlink(oldname);
+ rename(file->path, oldname);
+ }
+
+ return 0;
+}
+
+static int open_file_read(struct perf_data_file *file)
+{
+ struct stat st;
+ int fd;
+
+ fd = open(file->path, O_RDONLY);
+ if (fd < 0) {
+ int err = errno;
+
+ pr_err("failed to open %s: %s", file->path, strerror(err));
+ if (err == ENOENT && !strcmp(file->path, "perf.data"))
+ pr_err(" (try 'perf record' first)");
+ pr_err("\n");
+ return -err;
+ }
+
+ if (fstat(fd, &st) < 0)
+ goto out_close;
+
+ if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+ pr_err("file %s not owned by current user or root\n",
+ file->path);
+ goto out_close;
+ }
+
+ if (!st.st_size) {
+ pr_info("zero-sized file (%s), nothing to do!\n",
+ file->path);
+ goto out_close;
+ }
+
+ file->size = st.st_size;
+ return fd;
+
+ out_close:
+ close(fd);
+ return -1;
+}
+
+static int open_file_write(struct perf_data_file *file)
+{
+ if (check_backup(file))
+ return -1;
+
+ return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+}
+
+static int open_file(struct perf_data_file *file)
+{
+ int fd;
+
+ fd = perf_data_file__is_read(file) ?
+ open_file_read(file) : open_file_write(file);
+
+ file->fd = fd;
+ return fd < 0 ? -1 : 0;
+}
+
+int perf_data_file__open(struct perf_data_file *file)
+{
+ if (check_pipe(file))
+ return 0;
+
+ if (!file->path)
+ file->path = "perf.data";
+
+ return open_file(file);
+}
+
+void perf_data_file__close(struct perf_data_file *file)
+{
+ close(file->fd);
+}
--- /dev/null
+#ifndef __PERF_DATA_H
+#define __PERF_DATA_H
+
+#include <stdbool.h>
+
+enum perf_data_mode {
+ PERF_DATA_MODE_WRITE,
+ PERF_DATA_MODE_READ,
+};
+
+struct perf_data_file {
+ const char *path;
+ int fd;
+ bool is_pipe;
+ bool force;
+ unsigned long size;
+ enum perf_data_mode mode;
+};
+
+static inline bool perf_data_file__is_read(struct perf_data_file *file)
+{
+ return file->mode == PERF_DATA_MODE_READ;
+}
+
+static inline bool perf_data_file__is_write(struct perf_data_file *file)
+{
+ return file->mode == PERF_DATA_MODE_WRITE;
+}
+
+static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+{
+ return file->is_pipe;
+}
+
+static inline int perf_data_file__fd(struct perf_data_file *file)
+{
+ return file->fd;
+}
+
+static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+{
+ return file->size;
+}
+
+int perf_data_file__open(struct perf_data_file *file);
+void perf_data_file__close(struct perf_data_file *file);
+
+#endif /* __PERF_DATA_H */
return 0;
}
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
+ int prot, int mask, int cpu, int thread,
+ int *output)
{
struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (*output == -1) {
+ *output = fd;
+ if (__perf_evlist__mmap(evlist, idx, prot, mask,
+ *output) < 0)
+ return -1;
+ } else {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
+ return -1;
+ }
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
+ int mask)
+{
int cpu, thread;
int nr_cpus = cpu_map__nr(evlist->cpus);
int nr_threads = thread_map__nr(evlist->threads);
int output = -1;
for (thread = 0; thread < nr_threads; thread++) {
- list_for_each_entry(evsel, &evlist->entries, node) {
- int fd = FD(evsel, cpu, thread);
-
- if (output == -1) {
- output = fd;
- if (__perf_evlist__mmap(evlist, cpu,
- prot, mask, output) < 0)
- goto out_unmap;
- } else {
- if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
- goto out_unmap;
- }
-
- if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
- perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
- goto out_unmap;
- }
+ if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
+ cpu, thread, &output))
+ goto out_unmap;
}
}
return -1;
}
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
+ int mask)
{
- struct perf_evsel *evsel;
int thread;
int nr_threads = thread_map__nr(evlist->threads);
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
- list_for_each_entry(evsel, &evlist->entries, node) {
- int fd = FD(evsel, 0, thread);
-
- if (output == -1) {
- output = fd;
- if (__perf_evlist__mmap(evlist, thread,
- prot, mask, output) < 0)
- goto out_unmap;
- } else {
- if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
- goto out_unmap;
- }
-
- if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
- perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
- goto out_unmap;
- }
+ if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
+ thread, &output))
+ goto out_unmap;
}
return 0;
return 0;
}
-/** perf_evlist__mmap - Create per cpu maps to receive events
- *
- * @evlist - list of events
- * @pages - map length in pages
- * @overwrite - overwrite older events?
- *
- * If overwrite is false the user needs to signal event consuption using:
- *
- * struct perf_mmap *m = &evlist->mmap[cpu];
- * unsigned int head = perf_mmap__read_head(m);
+/**
+ * perf_evlist__mmap - Create mmaps to receive events.
+ * @evlist: list of events
+ * @pages: map length in pages
+ * @overwrite: overwrite older events?
*
- * perf_mmap__write_tail(m, head)
+ * If @overwrite is %false the user needs to signal event consumption using
+ * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
+ * automatically.
*
- * Using perf_evlist__read_on_cpu does this automatically.
+ * Return: %0 on success, negative error code otherwise.
*/
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite)
evlist->overwrite = overwrite;
evlist->mmap_len = perf_evlist__mmap_size(pages);
- pr_debug("mmap size %luB\n", evlist->mmap_len);
+ pr_debug("mmap size %zuB\n", evlist->mmap_len);
mask = evlist->mmap_len - page_size - 1;
list_for_each_entry(evsel, &evlist->entries, node) {
return printed + fprintf(fp, "\n");;
}
+
+int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
+ int err, char *buf, size_t size)
+{
+ char sbuf[128];
+
+ switch (err) {
+ case ENOENT:
+ scnprintf(buf, size, "%s",
+ "Error:\tUnable to find debugfs\n"
+ "Hint:\tWas your kernel was compiled with debugfs support?\n"
+ "Hint:\tIs the debugfs filesystem mounted?\n"
+ "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+ break;
+ case EACCES:
+ scnprintf(buf, size,
+ "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
+ "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+ debugfs_mountpoint, debugfs_mountpoint);
+ break;
+ default:
+ scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+ break;
+ }
+
+ return 0;
+}
+
+int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+ int err, char *buf, size_t size)
+{
+ int printed, value;
+ char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+
+ switch (err) {
+ case EACCES:
+ case EPERM:
+ printed = scnprintf(buf, size,
+ "Error:\t%s.\n"
+ "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
+
+ if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
+ break;
+
+ printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
+
+ if (value >= 2) {
+ printed += scnprintf(buf + printed, size - printed,
+ "For your workloads it needs to be <= 1\nHint:\t");
+ }
+ printed += scnprintf(buf + printed, size - printed,
+ "For system wide tracing it needs to be set to -1");
+
+ printed += scnprintf(buf + printed, size - printed,
+ ".\nHint:\tThe current value is %d.", value);
+ break;
+ default:
+ scnprintf(buf, size, "%s", emsg);
+ break;
+ }
+
+ return 0;
+}
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;
ret += PRINT_ATTR2(exclude_host, exclude_guest);
ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
"excl.callchain_user", exclude_callchain_user);
+ ret += PRINT_ATTR_U32(mmap2);
ret += PRINT_ATTR_U32(wakeup_events);
ret += PRINT_ATTR_U32(wakeup_watermark);
sample->pid = u.val32[0];
sample->tid = u.val32[1];
+ array--;
}
return 0;
#include "vdso.h"
#include "strbuf.h"
#include "build-id.h"
+#include "data.h"
static bool no_buildid_cache = false;
{
struct header_print_data hd;
struct perf_header *header = &session->header;
- int fd = session->fd;
+ int fd = perf_data_file__fd(session->file);
hd.fp = fp;
hd.full = full;
struct perf_header *header = &session->header;
struct perf_pipe_file_header f_header;
- if (perf_file_header__read_pipe(&f_header, header, session->fd,
+ if (perf_file_header__read_pipe(&f_header, header,
+ perf_data_file__fd(session->file),
session->repipe) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
int perf_session__read_header(struct perf_session *session)
{
+ struct perf_data_file *file = session->file;
struct perf_header *header = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
- int fd = session->fd;
+ int fd = perf_data_file__fd(file);
session->evlist = perf_evlist__new();
if (session->evlist == NULL)
return -ENOMEM;
- if (session->fd_pipe)
+ if (perf_data_file__is_pipe(file))
return perf_header__read_pipe(session);
if (perf_file_header__read(&f_header, header, fd) < 0)
if (f_header.data.size == 0) {
pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
"Was the 'perf record' command properly terminated?\n",
- session->filename);
+ file->path);
}
nr_attrs = f_header.attrs.size / f_header.attr_size;
struct perf_session *session)
{
ssize_t size_read, padding, size = event->tracing_data.size;
- off_t offset = lseek(session->fd, 0, SEEK_CUR);
+ int fd = perf_data_file__fd(session->file);
+ off_t offset = lseek(fd, 0, SEEK_CUR);
char buf[BUFSIZ];
/* setup for reading amidst mmap */
- lseek(session->fd, offset + sizeof(struct tracing_data_event),
+ lseek(fd, offset + sizeof(struct tracing_data_event),
SEEK_SET);
- size_read = trace_report(session->fd, &session->pevent,
+ size_read = trace_report(fd, &session->pevent,
session->repipe);
padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
- if (readn(session->fd, buf, padding) < 0) {
+ if (readn(fd, buf, padding) < 0) {
pr_err("%s: reading input file", __func__);
return -1;
}
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
u8 cpumode = PERF_RECORD_MISC_USER;
- unsigned int i;
+ int chain_nr = min(max_stack, (int)chain->nr);
+ int i;
int err;
callchain_cursor_reset(&callchain_cursor);
return 0;
}
- for (i = 0; i < chain->nr; i++) {
+ for (i = 0; i < chain_nr; i++) {
u64 ip;
struct addr_location al;
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
int ret;
ret = machine__resolve_callchain_sample(machine, thread,
- sample->callchain, parent, root_al);
+ sample->callchain, parent,
+ root_al, max_stack);
if (ret)
return ret;
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al);
+ struct addr_location *root_al,
+ int max_stack);
/*
* Default guest kernel is defined by parameter --guestkallsyms
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
- if (debugfs_valid_mountpoint(tracing_events_path))
+ if (debugfs_valid_mountpoint(tracing_events_path)) {
+ printf(" [ Tracepoints not available: %s ]\n", strerror(errno));
return;
+ }
sys_dir = opendir(tracing_events_path);
if (!sys_dir)
event = find_cache_event(evsel);
if (!event)
- die("ug! no event found for type %" PRIu64, evsel->attr.config);
+ die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
pid = raw_field_value(event, "common_pid", data);
#include "perf_regs.h"
#include "vdso.h"
-static int perf_session__open(struct perf_session *self, bool force)
+static int perf_session__open(struct perf_session *self)
{
- struct stat input_stat;
-
- if (!strcmp(self->filename, "-")) {
- self->fd_pipe = true;
- self->fd = STDIN_FILENO;
-
- if (perf_session__read_header(self) < 0)
- pr_err("incompatible file format (rerun with -v to learn more)");
-
- return 0;
- }
-
- self->fd = open(self->filename, O_RDONLY);
- if (self->fd < 0) {
- int err = errno;
-
- pr_err("failed to open %s: %s", self->filename, strerror(err));
- if (err == ENOENT && !strcmp(self->filename, "perf.data"))
- pr_err(" (try 'perf record' first)");
- pr_err("\n");
- return -errno;
- }
-
- if (fstat(self->fd, &input_stat) < 0)
- goto out_close;
-
- if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) {
- pr_err("file %s not owned by current user or root\n",
- self->filename);
- goto out_close;
- }
-
- if (!input_stat.st_size) {
- pr_info("zero-sized file (%s), nothing to do!\n",
- self->filename);
- goto out_close;
- }
+ struct perf_data_file *file = self->file;
if (perf_session__read_header(self) < 0) {
pr_err("incompatible file format (rerun with -v to learn more)");
- goto out_close;
+ return -1;
}
+ if (perf_data_file__is_pipe(file))
+ return 0;
+
if (!perf_evlist__valid_sample_type(self->evlist)) {
pr_err("non matching sample_type");
- goto out_close;
+ return -1;
}
if (!perf_evlist__valid_sample_id_all(self->evlist)) {
pr_err("non matching sample_id_all");
- goto out_close;
+ return -1;
}
if (!perf_evlist__valid_read_format(self->evlist)) {
pr_err("non matching read_format");
- goto out_close;
+ return -1;
}
- self->size = input_stat.st_size;
return 0;
-
-out_close:
- close(self->fd);
- self->fd = -1;
- return -1;
}
void perf_session__set_id_hdr_size(struct perf_session *session)
machines__destroy_kernel_maps(&self->machines);
}
-struct perf_session *perf_session__new(const char *filename, int mode,
- bool force, bool repipe,
- struct perf_tool *tool)
+struct perf_session *perf_session__new(struct perf_data_file *file,
+ bool repipe, struct perf_tool *tool)
{
struct perf_session *self;
- struct stat st;
- size_t len;
-
- if (!filename || !strlen(filename)) {
- if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
- filename = "-";
- else
- filename = "perf.data";
- }
- len = strlen(filename);
- self = zalloc(sizeof(*self) + len);
-
- if (self == NULL)
+ self = zalloc(sizeof(*self));
+ if (!self)
goto out;
- memcpy(self->filename, filename, len);
self->repipe = repipe;
INIT_LIST_HEAD(&self->ordered_samples.samples);
INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
INIT_LIST_HEAD(&self->ordered_samples.to_free);
machines__init(&self->machines);
- if (mode == O_RDONLY) {
- if (perf_session__open(self, force) < 0)
+ if (file) {
+ if (perf_data_file__open(file))
goto out_delete;
- perf_session__set_id_hdr_size(self);
- } else if (mode == O_WRONLY) {
+
+ self->file = file;
+
+ if (perf_data_file__is_read(file)) {
+ if (perf_session__open(self) < 0)
+ goto out_close;
+
+ perf_session__set_id_hdr_size(self);
+ }
+ }
+
+ if (!file || perf_data_file__is_write(file)) {
/*
* In O_RDONLY mode this will be performed when reading the
* kernel MMAP event, in perf_event__process_mmap().
tool->ordered_samples = false;
}
-out:
return self;
-out_delete:
+
+ out_close:
+ perf_data_file__close(file);
+ out_delete:
perf_session__delete(self);
+ out:
return NULL;
}
perf_session__delete_threads(self);
perf_session_env__delete(&self->header.env);
machines__exit(&self->machines);
- close(self->fd);
+ if (self->file)
+ perf_data_file__close(self->file);
free(self);
vdso__exit();
}
attr->bp_type = bswap_32(attr->bp_type);
attr->bp_addr = bswap_64(attr->bp_addr);
attr->bp_len = bswap_64(attr->bp_len);
+ attr->branch_sample_type = bswap_64(attr->branch_sample_type);
+ attr->sample_regs_user = bswap_64(attr->sample_regs_user);
+ attr->sample_stack_user = bswap_32(attr->sample_stack_user);
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
struct perf_tool *tool, u64 file_offset)
{
+ int fd = perf_data_file__fd(session->file);
int err;
dump_event(session, event, file_offset, NULL);
return err;
case PERF_RECORD_HEADER_TRACING_DATA:
/* setup for reading amidst mmap */
- lseek(session->fd, file_offset, SEEK_SET);
+ lseek(fd, file_offset, SEEK_SET);
return tool->tracing_data(tool, event, session);
case PERF_RECORD_HEADER_BUILD_ID:
return tool->build_id(tool, event, session);
static int __perf_session__process_pipe_events(struct perf_session *self,
struct perf_tool *tool)
{
+ int fd = perf_data_file__fd(self->file);
union perf_event *event;
uint32_t size, cur_size = 0;
void *buf = NULL;
return -errno;
more:
event = buf;
- err = readn(self->fd, event, sizeof(struct perf_event_header));
+ err = readn(fd, event, sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0)
goto done;
p += sizeof(struct perf_event_header);
if (size - sizeof(struct perf_event_header)) {
- err = readn(self->fd, p, size - sizeof(struct perf_event_header));
+ err = readn(fd, p, size - sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0) {
pr_err("unexpected end of event stream\n");
if (!session_done())
goto more;
done:
- err = 0;
+ /* do the final flush for ordered samples */
+ self->ordered_samples.next_flush = ULLONG_MAX;
+ err = flush_sample_queue(self, tool);
out_err:
free(buf);
perf_session__warn_about_errors(self, tool);
u64 data_offset, u64 data_size,
u64 file_size, struct perf_tool *tool)
{
+ int fd = perf_data_file__fd(session->file);
u64 head, page_offset, file_offset, file_pos, progress_next;
int err, mmap_prot, mmap_flags, map_idx = 0;
size_t mmap_size;
mmap_flags = MAP_PRIVATE;
}
remap:
- buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd,
+ buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
file_offset);
if (buf == MAP_FAILED) {
pr_err("failed to mmap file\n");
"Processing events...");
}
- err = 0;
if (session_done())
- goto out_err;
+ goto out;
if (file_pos < file_size)
goto more;
+out:
/* do the final flush for ordered samples */
session->ordered_samples.next_flush = ULLONG_MAX;
err = flush_sample_queue(session, tool);
int perf_session__process_events(struct perf_session *self,
struct perf_tool *tool)
{
+ u64 size = perf_data_file__size(self->file);
int err;
if (perf_session__register_idle_thread(self) == NULL)
return -ENOMEM;
- if (!self->fd_pipe)
+ if (!perf_data_file__is_pipe(self->file))
err = __perf_session__process_events(self,
self->header.data_offset,
self->header.data_size,
- self->size, tool);
+ size, tool);
else
err = __perf_session__process_pipe_events(self, tool);
if (symbol_conf.use_callchain && sample->callchain) {
if (machine__resolve_callchain(machine, evsel, al.thread,
- sample, NULL, NULL) != 0) {
+ sample, NULL, NULL,
+ PERF_MAX_STACK_DEPTH) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
bool full)
{
+ int fd = perf_data_file__fd(session->file);
struct stat st;
int ret;
if (session == NULL || fp == NULL)
return;
- ret = fstat(session->fd, &st);
+ ret = fstat(fd, &st);
if (ret == -1)
return;
#include "machine.h"
#include "symbol.h"
#include "thread.h"
+#include "data.h"
#include <linux/rbtree.h>
#include <linux/perf_event.h>
struct perf_session {
struct perf_header header;
- unsigned long size;
struct machines machines;
struct perf_evlist *evlist;
struct pevent *pevent;
struct events_stats stats;
- int fd;
- bool fd_pipe;
bool repipe;
struct ordered_samples ordered_samples;
- char filename[1];
+ struct perf_data_file *file;
};
#define PRINT_IP_OPT_IP (1<<0)
struct perf_tool;
-struct perf_session *perf_session__new(const char *filename, int mode,
- bool force, bool repipe,
- struct perf_tool *tool);
+struct perf_session *perf_session__new(struct perf_data_file *file,
+ bool repipe, struct perf_tool *tool);
void perf_session__delete(struct perf_session *session);
void perf_event_header__bswap(struct perf_event_header *self);
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
+ int64_t ret;
+
if (!left->ms.sym && !right->ms.sym)
return right->level - left->level;
+ /*
+ * comparing symbol address alone is not enough since it's a
+ * relative address within a dso.
+ */
+ ret = sort__dso_cmp(left, right);
+ if (ret != 0)
+ return ret;
+
return _sort__sym_cmp(left->ms.sym, right->ms.sym);
}
u64 exact_samples;
u64 guest_us_samples, guest_kernel_samples;
int print_entries, count_filter, delay_secs;
+ int max_stack;
bool hide_kernel_symbols, hide_user_symbols, zero;
bool use_tui, use_stdio;
bool kptr_restrict_warned;
return (unsigned long) -1;
}
+
+int filename__read_int(const char *filename, int *value)
+{
+ char line[64];
+ int fd = open(filename, O_RDONLY), err = -1;
+
+ if (fd < 0)
+ return -1;
+
+ if (read(fd, line, sizeof(line)) > 0) {
+ *value = atoi(line);
+ err = 0;
+ }
+
+ close(fd);
+ return err;
+}
char *get_srcline(struct dso *dso, unsigned long addr);
void free_srcline(char *srcline);
+
+int filename__read_int(const char *filename, int *value);
#endif /* GIT_COMPAT_UTIL_H */