* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf, amd: Use kmalloc_node(,__GFP_ZERO) for northbridge structure allocation
perf_events: Fix time tracking in samples
perf trace: update usage
perf trace: update Documentation with new perf trace variants
perf trace: live-mode command-line cleanup
perf trace record: handle commands correctly
perf record: make the record options available outside perf record
perf trace scripting: remove system-wide param from shell scripts
perf trace scripting: fix some small memory leaks and missing error checks
perf: Fix usages of profile_cpu in builtin-top.c to use cpu_list
perf, ui: Eliminate stack-smashing protection compiler complaint
struct amd_nb *nb;
int i;
- nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+ nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
+ cpu_to_node(cpu));
if (!nb)
return NULL;
- memset(nb, 0, sizeof(*nb));
nb->nb_id = nb_id;
/*
u64 tstamp_running;
u64 tstamp_stopped;
+ /*
+ * timestamp shadows the actual context timing but it can
+ * be safely used in NMI interrupt context. It reflects the
+ * context time as it was when the event was last scheduled in.
+ *
+ * ctx_time already accounts for ctx->timestamp. Therefore to
+ * compute ctx_time for a sample, simply add perf_clock().
+ */
+ u64 shadow_ctx_time;
+
struct perf_event_attr attr;
struct hw_perf_event hw;
event->tstamp_running += ctx->time - event->tstamp_stopped;
+ event->shadow_ctx_time = ctx->time - ctx->timestamp;
+
if (!is_software_event(event))
cpuctx->active_oncpu++;
ctx->nr_active++;
}
static void perf_output_read_one(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
u64 read_format = event->attr.read_format;
u64 values[4];
values[n++] = perf_event_count(event);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
- values[n++] = event->total_time_enabled +
+ values[n++] = enabled +
atomic64_read(&event->child_total_time_enabled);
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
- values[n++] = event->total_time_running +
+ values[n++] = running +
atomic64_read(&event->child_total_time_running);
}
if (read_format & PERF_FORMAT_ID)
* XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
*/
static void perf_output_read_group(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
struct perf_event *leader = event->group_leader, *sub;
u64 read_format = event->attr.read_format;
values[n++] = 1 + leader->nr_siblings;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- values[n++] = leader->total_time_enabled;
+ values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- values[n++] = leader->total_time_running;
+ values[n++] = running;
if (leader != event)
leader->pmu->read(leader);
}
}
+#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
+ PERF_FORMAT_TOTAL_TIME_RUNNING)
+
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
+ u64 enabled = 0, running = 0, now, ctx_time;
+ u64 read_format = event->attr.read_format;
+
+ /*
+ * compute total_time_enabled, total_time_running
+ * based on snapshot values taken when the event
+ * was last scheduled in.
+ *
+ * we cannot simply called update_context_time()
+ * because of locking issue as we are called in
+ * NMI context
+ */
+ if (read_format & PERF_FORMAT_TOTAL_TIMES) {
+ now = perf_clock();
+ ctx_time = event->shadow_ctx_time + now;
+ enabled = ctx_time - event->tstamp_enabled;
+ running = ctx_time - event->tstamp_running;
+ }
+
if (event->attr.read_format & PERF_FORMAT_GROUP)
- perf_output_read_group(handle, event);
+ perf_output_read_group(handle, event, enabled, running);
else
- perf_output_read_one(handle, event);
+ perf_output_read_one(handle, event, enabled, running);
}
void perf_output_sample(struct perf_output_handle *handle,
SYNOPSIS
--------
[verse]
-'perf trace' {record <script> | report <script> [args] }
+'perf trace' [<options>]
+'perf trace' [<options>] record <script> [<record-options>] <command>
+'perf trace' [<options>] report <script> [script-args]
+'perf trace' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf trace' [<options>] <top-script> [script-args]
DESCRIPTION
-----------
available via 'perf trace -l'). The following variants allow you to
record and run those scripts:
- 'perf trace record <script>' to record the events required for 'perf
- trace report'. <script> is the name displayed in the output of
- 'perf trace --list' i.e. the actual script name minus any language
- extension.
+ 'perf trace record <script> <command>' to record the events required
+ for 'perf trace report'. <script> is the name displayed in the
+ output of 'perf trace --list' i.e. the actual script name minus any
+ language extension. If <command> is not specified, the events are
+ recorded using the -a (system-wide) 'perf record' option.
- 'perf trace report <script>' to run and display the results of
- <script>. <script> is the name displayed in the output of 'perf
+ 'perf trace report <script> [args]' to run and display the results
+ of <script>. <script> is the name displayed in the output of 'perf
trace --list' i.e. the actual script name minus any language
extension. The perf.data output from a previous run of 'perf trace
record <script>' is used and should be present for this command to
- succeed.
+ succeed. [args] refers to the (mainly optional) args expected by
+ the script.
+
+ 'perf trace <script> <required-script-args> <command>' to both
+ record the events required for <script> and to run the <script>
+ using 'live-mode' i.e. without writing anything to disk. <script>
+ is the name displayed in the output of 'perf trace --list' i.e. the
+ actual script name minus any language extension. If <command> is
+ not specified, the events are recorded using the -a (system-wide)
+ 'perf record' option. If <script> has any required args, they
+ should be specified before <command>. This mode doesn't allow for
+ optional script args to be specified; if optional script args are
+ desired, they can be specified using separate 'perf trace record'
+ and 'perf trace report' commands, with the stdout of the record step
+ piped to the stdin of the report script, using the '-o -' and '-i -'
+ options of the corresponding commands.
+
+ 'perf trace <top-script>' to both record the events required for
+ <top-script> and to run the <top-script> using 'live-mode'
+ i.e. without writing anything to disk. <top-script> is the name
+ displayed in the output of 'perf trace --list' i.e. the actual
+ script name minus any language extension; a <top-script> is defined
+ as any script name ending with the string 'top'.
+
+ [<record-options>] can be passed to the record steps of 'perf trace
+ record' and 'live-mode' variants; this isn't possible however for
+ <top-script> 'live-mode' or 'perf trace report' variants.
See the 'SEE ALSO' section for links to language-specific
information on how to write and run your own trace scripts.
OPTIONS
-------
+<command>...::
+ Any command you can specify in a shell.
+
-D::
--dump-raw-trace=::
Display verbose dump of the trace data.
Generate perf-trace.[ext] starter script for given language,
using current perf.data.
+-a::
+ Force system-wide collection. Scripts run without a <command>
+ normally use -a by default, while scripts run with a <command>
+ normally don't - this option allows the latter to be run in
+ system-wide mode.
+
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-trace-perl[1],
static bool force, append_file;
-static const struct option options[] = {
+const struct option record_options[] = {
OPT_CALLBACK('e', "event", NULL, "event",
"event selector. use 'perf list' to list available events",
parse_events),
{
int i, j, err = -ENOMEM;
- argc = parse_options(argc, argv, options, record_usage,
+ argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1 && target_tid == -1 &&
!system_wide && !cpu_list)
- usage_with_options(record_usage, options);
+ usage_with_options(record_usage, record_options);
if (force && append_file) {
fprintf(stderr, "Can't overwrite and append at the same time."
" You need to choose between -f and -A");
- usage_with_options(record_usage, options);
+ usage_with_options(record_usage, record_options);
} else if (append_file) {
write_mode = WRITE_APPEND;
} else {
if (thread_num <= 0) {
fprintf(stderr, "Can't find all threads of pid %d\n",
target_pid);
- usage_with_options(record_usage, options);
+ usage_with_options(record_usage, record_options);
}
} else {
all_tids=malloc(sizeof(pid_t));
static pid_t *all_tids = NULL;
static int thread_num = 0;
static bool inherit = false;
-static int profile_cpu = -1;
static int nr_cpus = 0;
static int realtime_prio = 0;
static bool group = false;
else
printf(" (all");
- if (profile_cpu != -1)
- printf(", cpu: %d)\n", profile_cpu);
+ if (cpu_list)
+ printf(", CPU%s: %s)\n", nr_cpus > 1 ? "s" : "", cpu_list);
else {
if (target_tid != -1)
printf(")\n");
else
- printf(", %d CPUs)\n", nr_cpus);
+ printf(", %d CPU%s)\n", nr_cpus, nr_cpus > 1 ? "s" : "");
}
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
static void start_counter(int i, int counter)
{
struct perf_event_attr *attr;
- int cpu;
+ int cpu = -1;
int thread_index;
- cpu = profile_cpu;
- if (target_tid == -1 && profile_cpu == -1)
+ if (target_tid == -1)
cpu = cpumap[i];
attr = attrs + counter;
#include "util/symbol.h"
#include "util/thread.h"
#include "util/trace-event.h"
+#include "util/parse-options.h"
#include "util/util.h"
static char const *script_name;
static bool debug_mode;
static u64 last_timestamp;
static u64 nr_unordered;
+extern const struct option record_options[];
static int default_start_script(const char *script __unused,
int argc __unused,
{
struct script_desc *s = zalloc(sizeof(*s));
- if (s != NULL)
+ if (s != NULL && name)
s->name = strdup(name);
return s;
static void script_desc__delete(struct script_desc *s)
{
free(s->name);
+ free(s->half_liner);
+ free(s->args);
free(s);
}
return path;
}
+static bool is_top_script(const char *script_path)
+{
+ return ends_with((char *)script_path, "top") == NULL ? false : true;
+}
+
+static int has_required_arg(char *script_path)
+{
+ struct script_desc *desc;
+ int n_args = 0;
+ char *p;
+
+ desc = script_desc__new(NULL);
+
+ if (read_script_info(desc, script_path))
+ goto out;
+
+ if (!desc->args)
+ goto out;
+
+ for (p = desc->args; *p; p++)
+ if (*p == '<')
+ n_args++;
+out:
+ script_desc__delete(desc);
+
+ return n_args;
+}
+
static const char * const trace_usage[] = {
- "perf trace [<options>] <command>",
+ "perf trace [<options>]",
+ "perf trace [<options>] record <script> [<record-options>] <command>",
+ "perf trace [<options>] report <script> [script-args]",
+ "perf trace [<options>] <script> [<record-options>] <command>",
+ "perf trace [<options>] <top-script> [script-args]",
NULL
};
OPT_END()
};
+static bool have_cmd(int argc, const char **argv)
+{
+ char **__argv = malloc(sizeof(const char *) * argc);
+
+ if (!__argv)
+ die("malloc");
+ memcpy(__argv, argv, sizeof(const char *) * argc);
+ argc = parse_options(argc, (const char **)__argv, record_options,
+ NULL, PARSE_OPT_STOP_AT_NON_OPTION);
+ free(__argv);
+
+ return argc != 0;
+}
+
int cmd_trace(int argc, const char **argv, const char *prefix __used)
{
+ char *rec_script_path = NULL;
+ char *rep_script_path = NULL;
struct perf_session *session;
- const char *suffix = NULL;
+ char *script_path = NULL;
const char **__argv;
- char *script_path;
- int i, err;
+ bool system_wide;
+ int i, j, err;
- if (argc >= 2 && strncmp(argv[1], "rec", strlen("rec")) == 0) {
- if (argc < 3) {
- fprintf(stderr,
- "Please specify a record script\n");
- return -1;
- }
- suffix = RECORD_SUFFIX;
+ setup_scripting();
+
+ argc = parse_options(argc, argv, options, trace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
+ rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+ if (!rec_script_path)
+ return cmd_record(argc, argv, NULL);
}
- if (argc >= 2 && strncmp(argv[1], "rep", strlen("rep")) == 0) {
- if (argc < 3) {
+ if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
+ rep_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+ if (!rep_script_path) {
fprintf(stderr,
- "Please specify a report script\n");
+ "Please specify a valid report script"
+ "(see 'perf trace -l' for listing)\n");
return -1;
}
- suffix = REPORT_SUFFIX;
}
/* make sure PERF_EXEC_PATH is set for scripts */
perf_set_argv_exec_path(perf_exec_path());
- if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
- char *record_script_path, *report_script_path;
+ if (argc && !script_name && !rec_script_path && !rep_script_path) {
int live_pipe[2];
+ int rep_args;
pid_t pid;
- record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
- if (!record_script_path) {
- fprintf(stderr, "record script not found\n");
- return -1;
+ rec_script_path = get_script_path(argv[0], RECORD_SUFFIX);
+ rep_script_path = get_script_path(argv[0], REPORT_SUFFIX);
+
+ if (!rec_script_path && !rep_script_path) {
+ fprintf(stderr, " Couldn't find script %s\n\n See perf"
+ " trace -l for available scripts.\n", argv[0]);
+ usage_with_options(trace_usage, options);
}
- report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
- if (!report_script_path) {
- fprintf(stderr, "report script not found\n");
- return -1;
+ if (is_top_script(argv[0])) {
+ rep_args = argc - 1;
+ } else {
+ int rec_args;
+
+ rep_args = has_required_arg(rep_script_path);
+ rec_args = (argc - 1) - rep_args;
+ if (rec_args < 0) {
+ fprintf(stderr, " %s script requires options."
+ "\n\n See perf trace -l for available "
+ "scripts and options.\n", argv[0]);
+ usage_with_options(trace_usage, options);
+ }
}
if (pipe(live_pipe) < 0) {
}
if (!pid) {
+ system_wide = true;
+ j = 0;
+
dup2(live_pipe[1], 1);
close(live_pipe[0]);
- __argv = malloc(6 * sizeof(const char *));
- __argv[0] = "/bin/sh";
- __argv[1] = record_script_path;
- __argv[2] = "-q";
- __argv[3] = "-o";
- __argv[4] = "-";
- __argv[5] = NULL;
+ if (!is_top_script(argv[0]))
+ system_wide = !have_cmd(argc - rep_args,
+ &argv[rep_args]);
+
+ __argv = malloc((argc + 6) * sizeof(const char *));
+ if (!__argv)
+ die("malloc");
+
+ __argv[j++] = "/bin/sh";
+ __argv[j++] = rec_script_path;
+ if (system_wide)
+ __argv[j++] = "-a";
+ __argv[j++] = "-q";
+ __argv[j++] = "-o";
+ __argv[j++] = "-";
+ for (i = rep_args + 1; i < argc; i++)
+ __argv[j++] = argv[i];
+ __argv[j++] = NULL;
execvp("/bin/sh", (char **)__argv);
+ free(__argv);
exit(-1);
}
dup2(live_pipe[0], 0);
close(live_pipe[1]);
- __argv = malloc((argc + 3) * sizeof(const char *));
- __argv[0] = "/bin/sh";
- __argv[1] = report_script_path;
- for (i = 2; i < argc; i++)
- __argv[i] = argv[i];
- __argv[i++] = "-i";
- __argv[i++] = "-";
- __argv[i++] = NULL;
+ __argv = malloc((argc + 4) * sizeof(const char *));
+ if (!__argv)
+ die("malloc");
+ j = 0;
+ __argv[j++] = "/bin/sh";
+ __argv[j++] = rep_script_path;
+ for (i = 1; i < rep_args + 1; i++)
+ __argv[j++] = argv[i];
+ __argv[j++] = "-i";
+ __argv[j++] = "-";
+ __argv[j++] = NULL;
execvp("/bin/sh", (char **)__argv);
+ free(__argv);
exit(-1);
}
- if (suffix) {
- script_path = get_script_path(argv[2], suffix);
- if (!script_path) {
- fprintf(stderr, "script not found\n");
- return -1;
- }
-
- __argv = malloc((argc + 1) * sizeof(const char *));
- __argv[0] = "/bin/sh";
- __argv[1] = script_path;
- for (i = 3; i < argc; i++)
- __argv[i - 1] = argv[i];
- __argv[argc - 1] = NULL;
+ if (rec_script_path)
+ script_path = rec_script_path;
+ if (rep_script_path)
+ script_path = rep_script_path;
+
+ if (script_path) {
+ system_wide = false;
+ j = 0;
+
+ if (rec_script_path)
+ system_wide = !have_cmd(argc - 1, &argv[1]);
+
+ __argv = malloc((argc + 2) * sizeof(const char *));
+ if (!__argv)
+ die("malloc");
+ __argv[j++] = "/bin/sh";
+ __argv[j++] = script_path;
+ if (system_wide)
+ __argv[j++] = "-a";
+ for (i = 2; i < argc; i++)
+ __argv[j++] = argv[i];
+ __argv[j++] = NULL;
execvp("/bin/sh", (char **)__argv);
+ free(__argv);
exit(-1);
}
- setup_scripting();
-
- argc = parse_options(argc, argv, options, trace_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
-
if (symbol__init() < 0)
return -1;
if (!script_name)
#!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
#!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
#!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
#!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
#!/bin/bash
-perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
+perf record -e sched:sched_switch -e sched:sched_wakeup $@
#!/bin/bash
-perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
+perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
#!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
#!/bin/bash
-perf record -a -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
+perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
#!/bin/bash
-perf record -a -e net:net_dev_xmit -e net:net_dev_queue \
+perf record -e net:net_dev_xmit -e net:net_dev_queue \
-e net:netif_receive_skb -e net:netif_rx \
-e skb:consume_skb -e skb:kfree_skb \
-e skb:skb_copy_datagram_iovec -e napi:napi_poll \
#!/bin/bash
-perf record -m 16384 -a -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
+perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
#!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
#!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
#!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
return rc;
}
+static const char yes[] = "Yes", no[] = "No";
+
bool ui__dialog_yesno(const char *msg)
{
/* newtWinChoice should really be accepting const char pointers... */
- char yes[] = "Yes", no[] = "No";
- return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+ return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
}
git://bbs.cooldavid.org / net-next-2.6.git / commitdiff