summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-script.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-01-11 14:39:17 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-11 14:39:17 -0800
commit5cb52b5e1654f3f1ed9c32e34456d98559c85aa0 (patch)
tree737c73d6aef99a17f57c2974f1e2a142a5f1a377 /tools/perf/builtin-script.c
parent24af98c4cf5f5e69266e270c7f3fb34b82ff6656 (diff)
parent3eb9ede23bdd96e9ba60e2b4d4d17a7c35d58448 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Kernel side changes: - Intel Knights Landing support. (Harish Chegondi) - Intel Broadwell-EP uncore PMU support. (Kan Liang) - Core code improvements. (Peter Zijlstra.) - Event filter, LBR and PEBS fixes. (Stephane Eranian) - Enable cycles:pp on Intel Atom. (Stephane Eranian) - Add cycles:ppp support for Skylake. (Andi Kleen) - Various x86 NMI overhead optimizations. (Andi Kleen) - Intel PT enhancements. (Takao Indoh) - AMD cache events fix. (Vince Weaver) Tons of tooling changes: - Show random perf tool tips in the 'perf report' bottom line (Namhyung Kim) - perf report now defaults to --group if the perf.data file has grouped events, try it with: # perf record -e '{cycles,instructions}' -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ] # perf report # Samples: 1K of event 'anon group { cycles, instructions }' # Event count (approx.): 1955219195 # # Overhead Command Shared Object Symbol 2.86% 0.22% swapper [kernel.kallsyms] [k] intel_idle 1.05% 0.33% firefox libxul.so [.] js::SetObjectElement 1.05% 0.00% kworker/0:3 [kernel.kallsyms] [k] gen6_ring_get_seqno 0.88% 0.17% chrome chrome [.] 0x0000000000ee27ab 0.65% 0.86% firefox libxul.so [.] js::ValueToId<(js::AllowGC)1> 0.64% 0.23% JS Helper libxul.so [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay 0.62% 1.27% firefox libxul.so [.] js::GetIterator 0.61% 1.74% firefox libxul.so [.] js::NativeSetProperty 0.61% 0.31% firefox libxul.so [.] js::SetPropertyByDefining - Introduce the 'perf stat record/report' workflow: Generate perf.data files from 'perf stat', to tap into the scripting capabilities perf has instead of defining a 'perf stat' specific scripting support to calculate event ratios, etc. Simple example: $ perf stat record -e cycles usleep 1 Performance counter stats for 'usleep 1': 1,134,996 cycles 0.000670644 seconds time elapsed $ perf stat report Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1': 1,134,996 cycles 0.000670644 seconds time elapsed $ It generates PERF_RECORD_ userspace records to store the details: $ perf report -D | grep PERF_RECORD 0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637 0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535 0x12a [0x40]: PERF_RECORD_STAT_CONFIG 0x16a [0x30]: PERF_RECORD_STAT -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text 0x1da [0x18]: PERF_RECORD_STAT_ROUND [acme@ssdandy linux]$ An effort was made to make perf.data files generated like this to not generate cryptic messages when processed by older tools. The 'perf script' bits need rebasing, will go up later. - Make command line options always available, even when they depend on some feature being enabled, warning the user about use of such options (Wang Nan) - Support hw breakpoint events (mem:0xAddress) in the default output mode in 'perf script' (Wang Nan) - Fixes and improvements for supporting annotating ARM binaries, support ARM call and jump instructions, more work needed to have arch specific stuff separated into tools/perf/arch/*/annotate/ (Russell King) - Add initial 'perf config' command, for now just with a --list command to the contents of the configuration file in use and a basic man page describing its format, commands for doing edits and detailed documentation are being reviewed and proof-read. (Taeung Song) - Allows BPF scriptlets specify arguments to be fetched using DWARF info, using a prologue generated at compile/build time (He Kuang, Wang Nan) - Allow attaching BPF scriptlets to module symbols (Wang Nan) - Allow attaching BPF scriptlets to userspace code using uprobe (Wang Nan) - BPF programs now can specify 'perf probe' tunables via its section name, separating key=val values using semicolons (Wang Nan) Testing some of these new BPF features: Use case: get callchains when receiving SSL packets, filter then in the kernel, at arbitrary place. # cat ssl.bpf.c #define SEC(NAME) __attribute__((section(NAME), used)) struct pt_regs; SEC("func=__inet_lookup_established hnum") int func(struct pt_regs *ctx, int err, unsigned short port) { return err == 0 && port == 443; } char _license[] SEC("license") = "GPL"; int _version SEC("version") = LINUX_VERSION_CODE; # # perf record -a -g -e ssl.bpf.c ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ] # perf script | head -30 swapper 0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb 8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux) 896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux) 8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux) 855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux) 8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux) 8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux) 856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux) 2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux) 2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux) 96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux) 969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux) 2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux) 95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux) 1163ffa start_kernel ([kernel.vmlinux].init.text) 11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text) 1163623 x86_64_start_kernel ([kernel.vmlinux].init.text) qemu-system-x86 9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb 8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux) 896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux) 8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux) 855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux) 8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux) 856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux) 8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux) 430a br_handle_frame_finish ([bridge]) 48bc br_handle_frame ([bridge]) 855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux) 8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux) # - Use 'perf probe' various options to list functions, see what variables can be collected at any given point, experiment first collecting without a filter, then filter, use it together with 'perf trace', 'perf top', with or without callchains, if it explodes, please tell us! - Introduce a new callchain mode: "folded", that will list per line representations of all callchains for a give histogram entry, facilitating 'perf report' output processing by other tools, such as Brendan Gregg's flamegraph tools (Namhyung Kim) E.g: # perf report | grep -v ^# | head 18.37% 0.00% swapper [kernel.kallsyms] [k] cpu_startup_entry | ---cpu_startup_entry | |--12.07%--start_secondary | --6.30%--rest_init start_kernel x86_64_start_reservations x86_64_start_kernel # Becomes, in "folded" mode: # perf report -g folded | grep -v ^# | head -5 18.37% 0.00% swapper [kernel.kallsyms] [k] cpu_startup_entry 12.07% cpu_startup_entry;start_secondary 6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel 16.90% 0.00% swapper [kernel.kallsyms] [k] call_cpuidle 11.23% call_cpuidle;cpu_startup_entry;start_secondary 5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel 16.90% 0.00% swapper [kernel.kallsyms] [k] cpuidle_enter 11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel 15.12% 0.00% swapper [kernel.kallsyms] [k] cpuidle_enter_state # The user can also select one of "count", "period" or "percent" as the first column. ... and lots of infrastructure enhancements, plus fixes and other changes, features I failed to list - see the shortlog and the git log for details" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits) perf evlist: Add --trace-fields option to show trace fields perf record: Store data mmaps for dwarf unwind perf libdw: Check for mmaps also in MAP__VARIABLE tree perf unwind: Check for mmaps also in MAP__VARIABLE tree perf unwind: Use find_map function in access_dso_mem perf evlist: Remove perf_evlist__(enable|disable)_event functions perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does) perf report: Show random usage tip on the help line perf hists: Export a couple of hist functions perf diff: Use perf_hpp__register_sort_field interface perf tools: Add overhead/overhead_children keys defaults via string perf tools: Remove list entry from struct sort_entry perf tools: Include all tools/lib directory for tags/cscope/TAGS targets perf script: Align event name properly perf tools: Add missing headers in perf's MANIFEST perf tools: Do not show trace command if it's not compiled in perf report: Change default to use event group view perf top: Decay periods in callchains tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/ tools lib: Sync tools/lib/find_bit.c with the kernel ...
Diffstat (limited to 'tools/perf/builtin-script.c')
-rw-r--r--tools/perf/builtin-script.c245
1 files changed, 199 insertions, 46 deletions
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 72b5deb4bd79..c691214d820f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3,9 +3,9 @@
#include "perf.h"
#include "util/cache.h"
#include "util/debug.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
#include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
#include "util/perf_regs.h"
#include "util/session.h"
#include "util/tool.h"
@@ -18,7 +18,11 @@
#include "util/sort.h"
#include "util/data.h"
#include "util/auxtrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/stat.h"
#include <linux/bitmap.h>
+#include "asm/bug.h"
static char const *script_name;
static char const *generate_script_lang;
@@ -32,6 +36,7 @@ static bool print_flags;
static bool nanosecs;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+static struct perf_stat_config stat_config;
unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
@@ -130,6 +135,18 @@ static struct {
.invalid_fields = PERF_OUTPUT_TRACE,
},
+
+ [PERF_TYPE_BREAKPOINT] = {
+ .user_set = false,
+
+ .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+ PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+ PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+ PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+ PERF_OUTPUT_PERIOD,
+
+ .invalid_fields = PERF_OUTPUT_TRACE,
+ },
};
static bool output_set_by_user(void)
@@ -204,6 +221,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
struct perf_event_attr *attr = &evsel->attr;
bool allow_user_set;
+ if (perf_header__has_feat(&session->header, HEADER_STAT))
+ return 0;
+
allow_user_set = perf_header__has_feat(&session->header,
HEADER_AUXTRACE);
@@ -588,8 +608,35 @@ static void print_sample_flags(u32 flags)
printf(" %-4s ", str);
}
-static void process_event(union perf_event *event, struct perf_sample *sample,
- struct perf_evsel *evsel, struct addr_location *al)
+struct perf_script {
+ struct perf_tool tool;
+ struct perf_session *session;
+ bool show_task_events;
+ bool show_mmap_events;
+ bool show_switch_events;
+ bool allocated;
+ struct cpu_map *cpus;
+ struct thread_map *threads;
+ int name_width;
+};
+
+static int perf_evlist__max_name_len(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+ int max = 0;
+
+ evlist__for_each(evlist, evsel) {
+ int len = strlen(perf_evsel__name(evsel));
+
+ max = MAX(len, max);
+ }
+
+ return max;
+}
+
+static void process_event(struct perf_script *script, union perf_event *event,
+ struct perf_sample *sample, struct perf_evsel *evsel,
+ struct addr_location *al)
{
struct thread *thread = al->thread;
struct perf_event_attr *attr = &evsel->attr;
@@ -604,7 +651,12 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
if (PRINT_FIELD(EVNAME)) {
const char *evname = perf_evsel__name(evsel);
- printf("%s: ", evname ? evname : "[unknown]");
+
+ if (!script->name_width)
+ script->name_width = perf_evlist__max_name_len(script->session->evlist);
+
+ printf("%*s: ", script->name_width,
+ evname ? evname : "[unknown]");
}
if (print_flags)
@@ -643,65 +695,81 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
printf("\n");
}
-static int default_start_script(const char *script __maybe_unused,
- int argc __maybe_unused,
- const char **argv __maybe_unused)
-{
- return 0;
-}
+static struct scripting_ops *scripting_ops;
-static int default_flush_script(void)
+static void __process_stat(struct perf_evsel *counter, u64 tstamp)
{
- return 0;
+ int nthreads = thread_map__nr(counter->threads);
+ int ncpus = perf_evsel__nr_cpus(counter);
+ int cpu, thread;
+ static int header_printed;
+
+ if (counter->system_wide)
+ nthreads = 1;
+
+ if (!header_printed) {
+ printf("%3s %8s %15s %15s %15s %15s %s\n",
+ "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
+ header_printed = 1;
+ }
+
+ for (thread = 0; thread < nthreads; thread++) {
+ for (cpu = 0; cpu < ncpus; cpu++) {
+ struct perf_counts_values *counts;
+
+ counts = perf_counts(counter->counts, cpu, thread);
+
+ printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
+ counter->cpus->map[cpu],
+ thread_map__pid(counter->threads, thread),
+ counts->val,
+ counts->ena,
+ counts->run,
+ tstamp,
+ perf_evsel__name(counter));
+ }
+ }
}
-static int default_stop_script(void)
+static void process_stat(struct perf_evsel *counter, u64 tstamp)
{
- return 0;
+ if (scripting_ops && scripting_ops->process_stat)
+ scripting_ops->process_stat(&stat_config, counter, tstamp);
+ else
+ __process_stat(counter, tstamp);
}
-static int default_generate_script(struct pevent *pevent __maybe_unused,
- const char *outfile __maybe_unused)
+static void process_stat_interval(u64 tstamp)
{
- return 0;
+ if (scripting_ops && scripting_ops->process_stat_interval)
+ scripting_ops->process_stat_interval(tstamp);
}
-static struct scripting_ops default_scripting_ops = {
- .start_script = default_start_script,
- .flush_script = default_flush_script,
- .stop_script = default_stop_script,
- .process_event = process_event,
- .generate_script = default_generate_script,
-};
-
-static struct scripting_ops *scripting_ops;
-
static void setup_scripting(void)
{
setup_perl_scripting();
setup_python_scripting();
-
- scripting_ops = &default_scripting_ops;
}
static int flush_scripting(void)
{
- return scripting_ops->flush_script();
+ return scripting_ops ? scripting_ops->flush_script() : 0;
}
static int cleanup_scripting(void)
{
pr_debug("\nperf script stopped\n");
- return scripting_ops->stop_script();
+ return scripting_ops ? scripting_ops->stop_script() : 0;
}
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
+ struct perf_script *scr = container_of(tool, struct perf_script, tool);
struct addr_location al;
if (debug_mode) {
@@ -727,20 +795,16 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
goto out_put;
- scripting_ops->process_event(event, sample, evsel, &al);
+ if (scripting_ops)
+ scripting_ops->process_event(event, sample, evsel, &al);
+ else
+ process_event(scr, event, sample, evsel, &al);
+
out_put:
addr_location__put(&al);
return 0;
}
-struct perf_script {
- struct perf_tool tool;
- struct perf_session *session;
- bool show_task_events;
- bool show_mmap_events;
- bool show_switch_events;
-};
-
static int process_attr(struct perf_tool *tool, union perf_event *event,
struct perf_evlist **pevlist)
{
@@ -1156,6 +1220,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
type = PERF_TYPE_TRACEPOINT;
else if (!strcmp(str, "raw"))
type = PERF_TYPE_RAW;
+ else if (!strcmp(str, "break"))
+ type = PERF_TYPE_BREAKPOINT;
else {
fprintf(stderr, "Invalid event type in field string.\n");
rc = -EINVAL;
@@ -1421,7 +1487,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
char first_half[BUFSIZ];
char *script_root;
- snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+ snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
scripts_dir = opendir(scripts_path);
if (!scripts_dir)
@@ -1542,7 +1608,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
if (!session)
return -1;
- snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+ snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
scripts_dir = opendir(scripts_path);
if (!scripts_dir) {
@@ -1600,7 +1666,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
char lang_path[MAXPATHLEN];
char *__script_root;
- snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+ snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
scripts_dir = opendir(scripts_path);
if (!scripts_dir)
@@ -1695,6 +1761,87 @@ static void script__setup_sample_type(struct perf_script *script)
}
}
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ struct stat_round_event *round = &event->stat_round;
+ struct perf_evsel *counter;
+
+ evlist__for_each(session->evlist, counter) {
+ perf_stat_process_counter(&stat_config, counter);
+ process_stat(counter, round->time);
+ }
+
+ process_stat_interval(round->time);
+ return 0;
+}
+
+static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ perf_event__read_stat_config(&stat_config, &event->stat_config);
+ return 0;
+}
+
+static int set_maps(struct perf_script *script)
+{
+ struct perf_evlist *evlist = script->session->evlist;
+
+ if (!script->cpus || !script->threads)
+ return 0;
+
+ if (WARN_ONCE(script->allocated, "stats double allocation\n"))
+ return -EINVAL;
+
+ perf_evlist__set_maps(evlist, script->cpus, script->threads);
+
+ if (perf_evlist__alloc_stats(evlist, true))
+ return -ENOMEM;
+
+ script->allocated = true;
+ return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+ if (script->threads) {
+ pr_warning("Extra thread map event, ignoring.\n");
+ return 0;
+ }
+
+ script->threads = thread_map__new_event(&event->thread_map);
+ if (!script->threads)
+ return -ENOMEM;
+
+ return set_maps(script);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+ if (script->cpus) {
+ pr_warning("Extra cpu map event, ignoring.\n");
+ return 0;
+ }
+
+ script->cpus = cpu_map__new_data(&event->cpu_map.data);
+ if (!script->cpus)
+ return -ENOMEM;
+
+ return set_maps(script);
+}
+
int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
{
bool show_full_info = false;
@@ -1723,6 +1870,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
.auxtrace_info = perf_event__process_auxtrace_info,
.auxtrace = perf_event__process_auxtrace,
.auxtrace_error = perf_event__process_auxtrace_error,
+ .stat = perf_event__process_stat_event,
+ .stat_round = process_stat_round_event,
+ .stat_config = process_stat_config_event,
+ .thread_map = process_thread_map_event,
+ .cpu_map = process_cpu_map_event,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -1836,7 +1988,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
scripting_max_stack = itrace_synth_opts.callchain_sz;
/* make sure PERF_EXEC_PATH is set for scripts */
- perf_set_argv_exec_path(perf_exec_path());
+ set_argv_exec_path(get_argv_exec_path());
if (argc && !script_name && !rec_script_path && !rep_script_path) {
int live_pipe[2];
@@ -2076,6 +2228,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
flush_scripting();
out_delete:
+ perf_evlist__free_stats(session->evlist);
perf_session__delete(session);
if (script_started)