Pick up v3.7-rc2 and fixes before applying more patches.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
--- /dev/null
+How to compile perf for Android
+=========================================
+
+I. Set the Android NDK environment
+------------------------------------------------
+
+(a). Use the Android NDK
+------------------------------------------------
+1. You need to download and install the Android Native Development Kit (NDK).
+Set the NDK variable to point to the path where you installed the NDK:
+ export NDK=/path/to/android-ndk
+
+2. Set cross-compiling environment variables for NDK toolchain and sysroot.
+For arm:
+ export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi-
+ export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm
+For x86:
+ export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android-
+ export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86
+
+This method is not working for Android NDK versions up to Revision 8b.
+perf uses some bionic enhancements that are not included in these NDK versions.
+You can use method (b) described below instead.
+
+(b). Use the Android source tree
+-----------------------------------------------
+1. Download the master branch of the Android source tree.
+Set the environment for the target you want using:
+ source build/envsetup.sh
+ lunch
+
+2. Build your own NDK sysroot to contain latest bionic changes and set the
+NDK sysroot environment variable.
+ cd ${ANDROID_BUILD_TOP}/ndk
+For arm:
+ ./build/tools/build-ndk-sysroot.sh --abi=arm
+ export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm
+For x86:
+ ./build/tools/build-ndk-sysroot.sh --abi=x86
+ export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86
+
+3. Set the NDK toolchain environment variable.
+For arm:
+ export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi-
+For x86:
+ export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android-
+
+II. Compile perf for Android
+------------------------------------------------
+You need to run make with the NDK toolchain and sysroot defined above:
+ make CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+
+III. Install perf
+-----------------------------------------------
+You need to connect to your Android device/emulator using adb.
+Install perf using:
+ adb push perf /data/perf
+
+If you also want to use perf-archive you need busybox tools for Android.
+For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh:
+ sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive
+ chmod +x /tmp/perf-archive
+ adb push /tmp/perf-archive /data/perf-archive
+
+IV. Environment settings for running perf
+------------------------------------------------
+Some perf features need environment variables to run properly.
+You need to set these before running perf on the target:
+ adb shell
+ # PERF_PAGER=cat
+
+IV. Run perf
+------------------------------------------------
+Run perf on your device/emulator to which you previously connected using adb:
+ # ./data/perf
--symfs=<directory>::
Look for files with symbols relative to this directory.
+-b::
+--baseline-only::
+ Show only items with match in baseline.
+
+-c::
+--compute::
+ Differential computation selection - delta,ratio,wdiff (default is delta).
+ If '+' is specified as a first character, the output is sorted based
+ on the computation results.
+ See COMPARISON METHODS section for more info.
+
+-p::
+--period::
+ Show period values for both compared hist entries.
+
+-F::
+--formula::
+ Show formula for given computation.
+
+COMPARISON METHODS
+------------------
+delta
+~~~~~
+If specified the 'Delta' column is displayed with value 'd' computed as:
+
+ d = A->period_percent - B->period_percent
+
+with:
+ - A/B being matching hist entry from first/second file specified
+ (or perf.data/perf.data.old) respectively.
+
+ - period_percent being the % of the hist entry period value within
+ single data file
+
+ratio
+~~~~~
+If specified the 'Ratio' column is displayed with value 'r' computed as:
+
+ r = A->period / B->period
+
+with:
+ - A/B being matching hist entry from first/second file specified
+ (or perf.data/perf.data.old) respectively.
+
+ - period being the hist entry period value
+
+wdiff
+~~~~~
+If specified the 'Weighted diff' column is displayed with value 'd' computed as:
+
+ d = B->period * WEIGHT-A - A->period * WEIGHT-B
+
+ - A/B being matching hist entry from first/second file specified
+ (or perf.data/perf.data.old) respectively.
+
+ - period being the hist entry period value
+
+ - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+ behind ':' separator like '-c wdiff:1,2'.
+
SEE ALSO
--------
linkperf:perf-record[1]
-include config/feature-tests.mak
-ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all),y)
CFLAGS := $(CFLAGS) -fstack-protector-all
endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wstack-protector),y)
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector),y)
CFLAGS := $(CFLAGS) -Wstack-protector
endif
-ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y)
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var),y)
CFLAGS := $(CFLAGS) -Wvolatile-register-var
endif
BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
BASIC_LDFLAGS =
+ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS)),y)
+ BIONIC := 1
+ EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
+ EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+ BASIC_CFLAGS += -I.
+endif
+
# Guard against environment variables
BUILTIN_OBJS =
LIB_H =
LIB_H += util/exec_cmd.h
LIB_H += util/types.h
LIB_H += util/levenshtein.h
+LIB_H += util/machine.h
LIB_H += util/map.h
LIB_H += util/parse-options.h
LIB_H += util/parse-events.h
LIB_OBJS += $(OUTPUT)util/callchain.o
LIB_OBJS += $(OUTPUT)util/values.o
LIB_OBJS += $(OUTPUT)util/debug.o
+LIB_OBJS += $(OUTPUT)util/machine.o
LIB_OBJS += $(OUTPUT)util/map.o
LIB_OBJS += $(OUTPUT)util/pstack.o
LIB_OBJS += $(OUTPUT)util/session.o
FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y)
FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS)
- ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y)
- msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
- else
+ ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y)
+ LIBC_SUPPORT := 1
+ endif
+ ifeq ($(BIONIC),1)
+ LIBC_SUPPORT := 1
+ endif
+ ifeq ($(LIBC_SUPPORT),1)
NO_LIBELF := 1
NO_DWARF := 1
NO_DEMANGLE := 1
+ else
+ msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
endif
else
FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
endif
endif
+ifndef NO_ON_EXIT
+ ifeq ($(call try-cc,$(SOURCE_ON_EXIT),),y)
+ BASIC_CFLAGS += -DHAVE_ON_EXIT
+ endif
+endif
+
ifndef NO_BACKTRACE
ifeq ($(call try-cc,$(SOURCE_BACKTRACE),),y)
BASIC_CFLAGS += -DBACKTRACE_SUPPORT
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
- .fork = perf_event__process_task,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
.ordered_samples = true,
.ordering_requires_timestamps = true,
},
static char diff__default_sort_order[] = "dso,symbol";
static bool force;
static bool show_displacement;
+static bool show_period;
+static bool show_formula;
+static bool show_baseline_only;
+static bool sort_compute;
+
+static s64 compute_wdiff_w1;
+static s64 compute_wdiff_w2;
+
+enum {
+ COMPUTE_DELTA,
+ COMPUTE_RATIO,
+ COMPUTE_WEIGHTED_DIFF,
+ COMPUTE_MAX,
+};
+
+const char *compute_names[COMPUTE_MAX] = {
+ [COMPUTE_DELTA] = "delta",
+ [COMPUTE_RATIO] = "ratio",
+ [COMPUTE_WEIGHTED_DIFF] = "wdiff",
+};
+
+static int compute;
+
+static int setup_compute_opt_wdiff(char *opt)
+{
+ char *w1_str = opt;
+ char *w2_str;
+
+ int ret = -EINVAL;
+
+ if (!opt)
+ goto out;
+
+ w2_str = strchr(opt, ',');
+ if (!w2_str)
+ goto out;
+
+ *w2_str++ = 0x0;
+ if (!*w2_str)
+ goto out;
+
+ compute_wdiff_w1 = strtol(w1_str, NULL, 10);
+ compute_wdiff_w2 = strtol(w2_str, NULL, 10);
+
+ if (!compute_wdiff_w1 || !compute_wdiff_w2)
+ goto out;
+
+ pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n",
+ compute_wdiff_w1, compute_wdiff_w2);
+
+ ret = 0;
+
+ out:
+ if (ret)
+ pr_err("Failed: wrong weight data, use 'wdiff:w1,w2'\n");
+
+ return ret;
+}
+
+static int setup_compute_opt(char *opt)
+{
+ if (compute == COMPUTE_WEIGHTED_DIFF)
+ return setup_compute_opt_wdiff(opt);
+
+ if (opt) {
+ pr_err("Failed: extra option specified '%s'", opt);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int setup_compute(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ int *cp = (int *) opt->value;
+ char *cstr = (char *) str;
+ char buf[50];
+ unsigned i;
+ char *option;
+
+ if (!str) {
+ *cp = COMPUTE_DELTA;
+ return 0;
+ }
+
+ if (*str == '+') {
+ sort_compute = true;
+ cstr = (char *) ++str;
+ if (!*str)
+ return 0;
+ }
+
+ option = strchr(str, ':');
+ if (option) {
+ unsigned len = option++ - str;
+
+ /*
+ * The str data are not writeable, so we need
+ * to use another buffer.
+ */
+
+ /* No option value is longer. */
+ if (len >= sizeof(buf))
+ return -EINVAL;
+
+ strncpy(buf, str, len);
+ buf[len] = 0x0;
+ cstr = buf;
+ }
+
+ for (i = 0; i < COMPUTE_MAX; i++)
+ if (!strcmp(cstr, compute_names[i])) {
+ *cp = i;
+ return setup_compute_opt(option);
+ }
+
+ pr_err("Failed: '%s' is not computation method "
+ "(use 'delta','ratio' or 'wdiff')\n", str);
+ return -EINVAL;
+}
+
+static double get_period_percent(struct hist_entry *he, u64 period)
+{
+ u64 total = he->hists->stats.total_period;
+ return (period * 100.0) / total;
+}
+
+double perf_diff__compute_delta(struct hist_entry *he)
+{
+ struct hist_entry *pair = he->pair;
+ double new_percent = get_period_percent(he, he->stat.period);
+ double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0;
+
+ he->diff.period_ratio_delta = new_percent - old_percent;
+ he->diff.computed = true;
+ return he->diff.period_ratio_delta;
+}
+
+double perf_diff__compute_ratio(struct hist_entry *he)
+{
+ struct hist_entry *pair = he->pair;
+ double new_period = he->stat.period;
+ double old_period = pair ? pair->stat.period : 0;
+
+ he->diff.computed = true;
+ he->diff.period_ratio = pair ? (new_period / old_period) : 0;
+ return he->diff.period_ratio;
+}
+
+s64 perf_diff__compute_wdiff(struct hist_entry *he)
+{
+ struct hist_entry *pair = he->pair;
+ u64 new_period = he->stat.period;
+ u64 old_period = pair ? pair->stat.period : 0;
+
+ he->diff.computed = true;
+
+ if (!pair)
+ he->diff.wdiff = 0;
+ else
+ he->diff.wdiff = new_period * compute_wdiff_w2 -
+ old_period * compute_wdiff_w1;
+
+ return he->diff.wdiff;
+}
+
+static int formula_delta(struct hist_entry *he, char *buf, size_t size)
+{
+ struct hist_entry *pair = he->pair;
+
+ if (!pair)
+ return -1;
+
+ return scnprintf(buf, size,
+ "(%" PRIu64 " * 100 / %" PRIu64 ") - "
+ "(%" PRIu64 " * 100 / %" PRIu64 ")",
+ he->stat.period, he->hists->stats.total_period,
+ pair->stat.period, pair->hists->stats.total_period);
+}
+
+static int formula_ratio(struct hist_entry *he, char *buf, size_t size)
+{
+ struct hist_entry *pair = he->pair;
+ double new_period = he->stat.period;
+ double old_period = pair ? pair->stat.period : 0;
+
+ if (!pair)
+ return -1;
+
+ return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
+}
+
+static int formula_wdiff(struct hist_entry *he, char *buf, size_t size)
+{
+ struct hist_entry *pair = he->pair;
+ u64 new_period = he->stat.period;
+ u64 old_period = pair ? pair->stat.period : 0;
+
+ if (!pair)
+ return -1;
+
+ return scnprintf(buf, size,
+ "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
+ new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
+}
+
+int perf_diff__formula(char *buf, size_t size, struct hist_entry *he)
+{
+ switch (compute) {
+ case COMPUTE_DELTA:
+ return formula_delta(he, buf, size);
+ case COMPUTE_RATIO:
+ return formula_ratio(he, buf, size);
+ case COMPUTE_WEIGHTED_DIFF:
+ return formula_wdiff(he, buf, size);
+ default:
+ BUG_ON(1);
+ }
+
+ return -1;
+}
static int hists__add_entry(struct hists *self,
struct addr_location *al, u64 period)
return -1;
}
- if (al.filtered || al.sym == NULL)
+ if (al.filtered)
return 0;
if (hists__add_entry(&evsel->hists, &al, sample->period)) {
.sample = diff__process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
.lost = perf_event__process_lost,
.ordered_samples = true,
.ordering_requires_timestamps = true,
}
}
+static void hists__baseline_only(struct hists *hists)
+{
+ struct rb_node *next = rb_first(&hists->entries);
+
+ while (next != NULL) {
+ struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+
+ next = rb_next(&he->rb_node);
+ if (!he->pair) {
+ rb_erase(&he->rb_node, &hists->entries);
+ hist_entry__free(he);
+ }
+ }
+}
+
+static void hists__precompute(struct hists *hists)
+{
+ struct rb_node *next = rb_first(&hists->entries);
+
+ while (next != NULL) {
+ struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+
+ next = rb_next(&he->rb_node);
+
+ switch (compute) {
+ case COMPUTE_DELTA:
+ perf_diff__compute_delta(he);
+ break;
+ case COMPUTE_RATIO:
+ perf_diff__compute_ratio(he);
+ break;
+ case COMPUTE_WEIGHTED_DIFF:
+ perf_diff__compute_wdiff(he);
+ break;
+ default:
+ BUG_ON(1);
+ }
+ }
+}
+
+static int64_t cmp_doubles(double l, double r)
+{
+ if (l > r)
+ return -1;
+ else if (l < r)
+ return 1;
+ else
+ return 0;
+}
+
+static int64_t
+hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
+ int c)
+{
+ switch (c) {
+ case COMPUTE_DELTA:
+ {
+ double l = left->diff.period_ratio_delta;
+ double r = right->diff.period_ratio_delta;
+
+ return cmp_doubles(l, r);
+ }
+ case COMPUTE_RATIO:
+ {
+ double l = left->diff.period_ratio;
+ double r = right->diff.period_ratio;
+
+ return cmp_doubles(l, r);
+ }
+ case COMPUTE_WEIGHTED_DIFF:
+ {
+ s64 l = left->diff.wdiff;
+ s64 r = right->diff.wdiff;
+
+ return r - l;
+ }
+ default:
+ BUG_ON(1);
+ }
+
+ return 0;
+}
+
+static void insert_hist_entry_by_compute(struct rb_root *root,
+ struct hist_entry *he,
+ int c)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent = NULL;
+ struct hist_entry *iter;
+
+ while (*p != NULL) {
+ parent = *p;
+ iter = rb_entry(parent, struct hist_entry, rb_node);
+ if (hist_entry__cmp_compute(he, iter, c) < 0)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&he->rb_node, parent, p);
+ rb_insert_color(&he->rb_node, root);
+}
+
+static void hists__compute_resort(struct hists *hists)
+{
+ struct rb_root tmp = RB_ROOT;
+ struct rb_node *next = rb_first(&hists->entries);
+
+ while (next != NULL) {
+ struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+
+ next = rb_next(&he->rb_node);
+
+ rb_erase(&he->rb_node, &hists->entries);
+ insert_hist_entry_by_compute(&tmp, he, compute);
+ }
+
+ hists->entries = tmp;
+}
+
+static void hists__process(struct hists *old, struct hists *new)
+{
+ hists__match(old, new);
+
+ if (show_baseline_only)
+ hists__baseline_only(new);
+
+ if (sort_compute) {
+ hists__precompute(new);
+ hists__compute_resort(new);
+ }
+
+ hists__fprintf(new, true, 0, 0, stdout);
+}
+
static int __cmd_diff(void)
{
int ret, i;
first = false;
- hists__match(&evsel_old->hists, &evsel->hists);
- hists__fprintf(&evsel->hists, true, 0, 0, stdout);
+ hists__process(&evsel_old->hists, &evsel->hists);
}
out_delete:
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('M', "displacement", &show_displacement,
"Show position displacement relative to baseline"),
+ OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
+ "Show only items with match in baseline"),
+ OPT_CALLBACK('c', "compute", &compute,
+ "delta,ratio,wdiff:w1,w2 (default delta)",
+ "Entries differential computation selection",
+ setup_compute),
+ OPT_BOOLEAN('p', "period", &show_period,
+ "Show period values."),
+ OPT_BOOLEAN('F', "formula", &show_formula,
+ "Show formula."),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
/* No overhead column. */
perf_hpp__column_enable(PERF_HPP__OVERHEAD, false);
- /* Display baseline/delta/displacement columns. */
+ /*
+ * Display baseline/delta/ratio/displacement/
+ * formula/periods columns.
+ */
perf_hpp__column_enable(PERF_HPP__BASELINE, true);
- perf_hpp__column_enable(PERF_HPP__DELTA, true);
+
+ switch (compute) {
+ case COMPUTE_DELTA:
+ perf_hpp__column_enable(PERF_HPP__DELTA, true);
+ break;
+ case COMPUTE_RATIO:
+ perf_hpp__column_enable(PERF_HPP__RATIO, true);
+ break;
+ case COMPUTE_WEIGHTED_DIFF:
+ perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF, true);
+ break;
+ default:
+ BUG_ON(1);
+ };
if (show_displacement)
perf_hpp__column_enable(PERF_HPP__DISPL, true);
+
+ if (show_formula)
+ perf_hpp__column_enable(PERF_HPP__FORMULA, true);
+
+ if (show_period) {
+ perf_hpp__column_enable(PERF_HPP__PERIOD, true);
+ perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE, true);
+ }
}
int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
return err;
}
-static int perf_event__repipe_task(struct perf_tool *tool,
+static int perf_event__repipe_fork(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
int err;
- err = perf_event__process_task(tool, event, sample, machine);
+ err = perf_event__process_fork(tool, event, sample, machine);
perf_event__repipe(tool, event, sample, machine);
return err;
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
inject->tool.mmap = perf_event__repipe_mmap;
- inject->tool.fork = perf_event__repipe_task;
+ inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
static void init_kvm_event_record(struct perf_kvm *kvm)
{
- int i;
+ unsigned int i;
- for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++)
+ for (i = 0; i < EVENTS_CACHE_SIZE; i++)
INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
}
BUG_ON(key->key == INVALID_KEY);
head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)];
- list_for_each_entry(event, head, hash_entry)
+ list_for_each_entry(event, head, hash_entry) {
if (event->key.key == key->key && event->key.info == key->info)
return event;
+ }
event = kvm_alloc_init_event(key);
if (!event)
static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
u64 time_diff)
{
- kvm_update_event_stats(&event->total, time_diff);
+ if (vcpu_id == -1) {
+ kvm_update_event_stats(&event->total, time_diff);
+ return true;
+ }
if (!kvm_event_expand(event, vcpu_id))
return false;
{
struct kvm_event *event;
u64 time_begin, time_diff;
+ int vcpu;
+
+ if (kvm->trace_vcpu == -1)
+ vcpu = -1;
+ else
+ vcpu = vcpu_record->vcpu_id;
event = vcpu_record->last_event;
time_begin = vcpu_record->start_time;
BUG_ON(timestamp < time_begin);
time_diff = timestamp - time_begin;
- return update_kvm_event(event, vcpu_record->vcpu_id, time_diff);
+ return update_kvm_event(event, vcpu, time_diff);
}
static
if (!vcpu_record)
return true;
+ /* only process events for vcpus user cares about */
+ if ((kvm->trace_vcpu != -1) &&
+ (kvm->trace_vcpu != vcpu_record->vcpu_id))
+ return true;
+
if (kvm->events_ops->is_begin_event(evsel, sample, &key))
return handle_begin_event(kvm, vcpu_record, &key, sample->time);
int vcpu = kvm->trace_vcpu;
struct kvm_event *event;
- for (i = 0; i < EVENTS_CACHE_SIZE; i++)
- list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry)
+ for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
+ list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) {
if (event_is_valid(event, vcpu)) {
update_total_count(kvm, event);
insert_to_result(&kvm->result, event,
kvm->compare, vcpu);
}
+ }
+ }
}
/* returns left most element of result, and erase it */
pr_info("\n");
}
- pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n",
- (unsigned long long)kvm->total_count, kvm->total_time / 1e3);
+ pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
+ kvm->total_count, kvm->total_time / 1e3);
}
static int process_sample_event(struct perf_tool *tool,
#include <sched.h>
#include <sys/mman.h>
+#ifndef HAVE_ON_EXIT
+#ifndef ATEXIT_MAX
+#define ATEXIT_MAX 32
+#endif
+static int __on_exit_count = 0;
+typedef void (*on_exit_func_t) (int, void *);
+static on_exit_func_t __on_exit_funcs[ATEXIT_MAX];
+static void *__on_exit_args[ATEXIT_MAX];
+static int __exitcode = 0;
+static void __handle_on_exit_funcs(void);
+static int on_exit(on_exit_func_t function, void *arg);
+#define exit(x) (exit)(__exitcode = (x))
+
+static int on_exit(on_exit_func_t function, void *arg)
+{
+ if (__on_exit_count == ATEXIT_MAX)
+ return -ENOMEM;
+ else if (__on_exit_count == 0)
+ atexit(__handle_on_exit_funcs);
+ __on_exit_funcs[__on_exit_count] = function;
+ __on_exit_args[__on_exit_count++] = arg;
+ return 0;
+}
+
+static void __handle_on_exit_funcs(void)
+{
+ int i;
+ for (i = 0; i < __on_exit_count; i++)
+ __on_exit_funcs[i] (__exitcode, __on_exit_args[i]);
+}
+#endif
+
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
.lost = perf_event__process_lost,
.read = process_read_event,
.attr = perf_event__process_attr,
.sample = perf_sched__process_tracepoint_sample,
.comm = perf_event__process_comm,
.lost = perf_event__process_lost,
- .fork = perf_event__process_task,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
.ordered_samples = true,
},
.cmp_pid = LIST_HEAD_INIT(sched.cmp_pid),
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
+ .exit = perf_event__process_exit,
+ .fork = perf_event__process_fork,
.attr = perf_event__process_attr,
.event_type = perf_event__process_event_type,
.tracing_data = perf_event__process_tracing_data,
struct map *kallsyms_map, *vmlinux_map;
struct machine kallsyms, vmlinux;
enum map_type type = MAP__FUNCTION;
- long page_size = sysconf(_SC_PAGE_SIZE);
struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
/*
static int __test__rdpmc(void)
{
- long page_size = sysconf(_SC_PAGE_SIZE);
volatile int tmp = 0;
u64 i, loops = 1000;
int n;
#include "util/color.h"
#include "util/evlist.h"
#include "util/evsel.h"
+#include "util/machine.h"
#include "util/session.h"
#include "util/symbol.h"
#include "util/thread.h"
&sample, machine);
} else if (event->header.type < PERF_RECORD_MAX) {
hists__inc_nr_events(&evsel->hists, event->header.type);
- perf_event__process(&top->tool, event, &sample, machine);
+ machine__process_event(machine, event);
} else
++session->hists.stats.nr_unknown_events;
}
struct perf_record_opts opts;
};
+static bool done = false;
+
+static void sig_handler(int sig __maybe_unused)
+{
+ done = true;
+}
+
static int trace__read_syscall_info(struct trace *trace, int id)
{
char tp_name[128];
return 0;
}
-static int trace__run(struct trace *trace)
+static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
struct perf_evsel *evsel;
int err = -1, i, nr_events = 0, before;
+ const bool forks = argc > 0;
if (evlist == NULL) {
printf("Not enough memory to run!\n");
perf_evlist__config_attrs(evlist, &trace->opts);
+ signal(SIGCHLD, sig_handler);
+ signal(SIGINT, sig_handler);
+
+ if (forks) {
+ err = perf_evlist__prepare_workload(evlist, &trace->opts, argv);
+ if (err < 0) {
+ printf("Couldn't run the workload!\n");
+ goto out_delete_evlist;
+ }
+ }
+
err = perf_evlist__open(evlist);
if (err < 0) {
printf("Couldn't create the events: %s\n", strerror(errno));
}
perf_evlist__enable(evlist);
+
+ if (forks)
+ perf_evlist__start_workload(evlist);
+
again:
before = nr_events;
}
}
- if (nr_events == before)
+ if (nr_events == before) {
+ if (done)
+ goto out_delete_evlist;
+
poll(evlist->pollfd, evlist->nr_fds, -1);
+ }
+
+ if (done)
+ perf_evlist__disable(evlist);
goto again;
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char * const trace_usage[] = {
- "perf trace [<options>]",
+ "perf trace [<options>] [<command>]",
+ "perf trace [<options>] -- <command> [<options>]",
NULL
};
struct trace trace = {
OPT_END()
};
int err;
+ char bf[BUFSIZ];
argc = parse_options(argc, argv, trace_options, trace_usage, 0);
- if (argc)
- usage_with_options(trace_usage, trace_options);
+
+ err = perf_target__validate(&trace.opts.target);
+ if (err) {
+ perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+ printf("%s", bf);
+ return err;
+ }
err = perf_target__parse_uid(&trace.opts.target);
if (err) {
- char bf[BUFSIZ];
perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
printf("%s", bf);
return err;
}
- return trace__run(&trace);
+ if (!argc && perf_target__none(&trace.opts.target))
+ trace.opts.target.system_wide = true;
+
+ return trace__run(&trace, argc, argv);
}
}
endef
+define SOURCE_BIONIC
+#include <android/api-level.h>
+
+int main(void)
+{
+ return __ANDROID_API__;
+}
+endef
+
define SOURCE_ELF_MMAP
#include <libelf.h>
int main(void)
return audit_open();
}
endef
-endif
\ No newline at end of file
+endif
+
+define SOURCE_ON_EXIT
+#include <stdio.h>
+
+int main(void)
+{
+ return on_exit(NULL, NULL);
+}
+endef
{
const char *cmd;
+ page_size = sysconf(_SC_PAGE_SIZE);
+
cmd = perf_extract_argv0_path(argv[0]);
if (!cmd)
cmd = "perf-help";
{
double percent = baseline_percent(he);
- return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
+ if (he->pair)
+ return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
+ else
+ return scnprintf(hpp->buf, hpp->size, " ");
}
static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he)
double percent = baseline_percent(he);
const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
- return scnprintf(hpp->buf, hpp->size, fmt, percent);
+ if (he->pair || symbol_conf.field_sep)
+ return scnprintf(hpp->buf, hpp->size, fmt, percent);
+ else
+ return scnprintf(hpp->buf, hpp->size, " ");
}
static int hpp__header_samples(struct perf_hpp *hpp)
return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period);
}
+static int hpp__header_period_baseline(struct perf_hpp *hpp)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
+
+ return scnprintf(hpp->buf, hpp->size, fmt, "Period Base");
+}
+
+static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused)
+{
+ return 12;
+}
+
+static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he)
+{
+ struct hist_entry *pair = he->pair;
+ u64 period = pair ? pair->stat.period : 0;
+ const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
+
+ return scnprintf(hpp->buf, hpp->size, fmt, period);
+}
static int hpp__header_delta(struct perf_hpp *hpp)
{
const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he)
{
- struct hist_entry *pair = he->pair;
- struct hists *pair_hists = pair ? pair->hists : NULL;
- struct hists *hists = he->hists;
- u64 old_total, new_total;
- double old_percent = 0, new_percent = 0;
- double diff;
const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s";
char buf[32] = " ";
+ double diff;
- old_total = pair_hists ? pair_hists->stats.total_period : 0;
- if (old_total > 0 && pair)
- old_percent = 100.0 * pair->stat.period / old_total;
-
- new_total = hists->stats.total_period;
- if (new_total > 0)
- new_percent = 100.0 * he->stat.period / new_total;
+ if (he->diff.computed)
+ diff = he->diff.period_ratio_delta;
+ else
+ diff = perf_diff__compute_delta(he);
- diff = new_percent - old_percent;
if (fabs(diff) >= 0.01)
scnprintf(buf, sizeof(buf), "%+4.2F%%", diff);
return scnprintf(hpp->buf, hpp->size, fmt, buf);
}
+static int hpp__header_ratio(struct perf_hpp *hpp)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
+
+ return scnprintf(hpp->buf, hpp->size, fmt, "Ratio");
+}
+
+static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused)
+{
+ return 14;
+}
+
+static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
+ char buf[32] = " ";
+ double ratio;
+
+ if (he->diff.computed)
+ ratio = he->diff.period_ratio;
+ else
+ ratio = perf_diff__compute_ratio(he);
+
+ if (ratio > 0.0)
+ scnprintf(buf, sizeof(buf), "%+14.6F", ratio);
+
+ return scnprintf(hpp->buf, hpp->size, fmt, buf);
+}
+
+static int hpp__header_wdiff(struct perf_hpp *hpp)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
+
+ return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff");
+}
+
+static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused)
+{
+ return 14;
+}
+
+static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
+ char buf[32] = " ";
+ s64 wdiff;
+
+ if (he->diff.computed)
+ wdiff = he->diff.wdiff;
+ else
+ wdiff = perf_diff__compute_wdiff(he);
+
+ if (wdiff != 0)
+ scnprintf(buf, sizeof(buf), "%14ld", wdiff);
+
+ return scnprintf(hpp->buf, hpp->size, fmt, buf);
+}
+
static int hpp__header_displ(struct perf_hpp *hpp)
{
return scnprintf(hpp->buf, hpp->size, "Displ.");
return scnprintf(hpp->buf, hpp->size, fmt, buf);
}
+static int hpp__header_formula(struct perf_hpp *hpp)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%70s";
+
+ return scnprintf(hpp->buf, hpp->size, fmt, "Formula");
+}
+
+static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused)
+{
+ return 70;
+}
+
+static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
+{
+ const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s";
+ char buf[96] = " ";
+
+ perf_diff__formula(buf, sizeof(buf), he);
+ return scnprintf(hpp->buf, hpp->size, fmt, buf);
+}
+
#define HPP__COLOR_PRINT_FNS(_name) \
.header = hpp__header_ ## _name, \
.width = hpp__width_ ## _name, \
{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) },
{ .cond = false, HPP__PRINT_FNS(samples) },
{ .cond = false, HPP__PRINT_FNS(period) },
+ { .cond = false, HPP__PRINT_FNS(period_baseline) },
{ .cond = false, HPP__PRINT_FNS(delta) },
- { .cond = false, HPP__PRINT_FNS(displ) }
+ { .cond = false, HPP__PRINT_FNS(ratio) },
+ { .cond = false, HPP__PRINT_FNS(wdiff) },
+ { .cond = false, HPP__PRINT_FNS(displ) },
+ { .cond = false, HPP__PRINT_FNS(formula) }
};
#undef HPP__COLOR_PRINT_FNS
const char *sep = symbol_conf.field_sep;
const char *col_width = symbol_conf.col_width_list_str;
int idx, nr_rows = 0;
- char bf[64];
+ char bf[96];
struct perf_hpp dummy_hpp = {
.buf = bf,
.size = sizeof(bf),
struct perf_tool build_id__mark_dso_hit_ops = {
.sample = build_id__mark_dso_hit,
.mmap = perf_event__process_mmap,
- .fork = perf_event__process_task,
+ .fork = perf_event__process_fork,
.exit = perf_event__exit_del_thread,
.attr = perf_event__process_attr,
.build_id = perf_event__process_build_id,
#include <linux/types.h>
#include "event.h"
#include "debug.h"
+#include "machine.h"
#include "sort.h"
#include "string.h"
#include "strlist.h"
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
- struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
-
- if (dump_trace)
- perf_event__fprintf_comm(event, stdout);
-
- if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
- dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
- return -1;
- }
-
- return 0;
+ return machine__process_comm_event(machine, event);
}
int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
- struct machine *machine __maybe_unused)
-{
- dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
- event->lost.id, event->lost.lost);
- return 0;
-}
-
-static void perf_event__set_kernel_mmap_len(union perf_event *event,
- struct map **maps)
+ struct machine *machine)
{
- maps[MAP__FUNCTION]->start = event->mmap.start;
- maps[MAP__FUNCTION]->end = event->mmap.start + event->mmap.len;
- /*
- * Be a bit paranoid here, some perf.data file came with
- * a zero sized synthesized MMAP event for the kernel.
- */
- if (maps[MAP__FUNCTION]->end == 0)
- maps[MAP__FUNCTION]->end = ~0ULL;
-}
-
-static int perf_event__process_kernel_mmap(struct perf_tool *tool
- __maybe_unused,
- union perf_event *event,
- struct machine *machine)
-{
- struct map *map;
- char kmmap_prefix[PATH_MAX];
- enum dso_kernel_type kernel_type;
- bool is_kernel_mmap;
-
- machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
- if (machine__is_host(machine))
- kernel_type = DSO_TYPE_KERNEL;
- else
- kernel_type = DSO_TYPE_GUEST_KERNEL;
-
- is_kernel_mmap = memcmp(event->mmap.filename,
- kmmap_prefix,
- strlen(kmmap_prefix) - 1) == 0;
- if (event->mmap.filename[0] == '/' ||
- (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
-
- char short_module_name[1024];
- char *name, *dot;
-
- if (event->mmap.filename[0] == '/') {
- name = strrchr(event->mmap.filename, '/');
- if (name == NULL)
- goto out_problem;
-
- ++name; /* skip / */
- dot = strrchr(name, '.');
- if (dot == NULL)
- goto out_problem;
- snprintf(short_module_name, sizeof(short_module_name),
- "[%.*s]", (int)(dot - name), name);
- strxfrchar(short_module_name, '-', '_');
- } else
- strcpy(short_module_name, event->mmap.filename);
-
- map = machine__new_module(machine, event->mmap.start,
- event->mmap.filename);
- if (map == NULL)
- goto out_problem;
-
- name = strdup(short_module_name);
- if (name == NULL)
- goto out_problem;
-
- map->dso->short_name = name;
- map->dso->sname_alloc = 1;
- map->end = map->start + event->mmap.len;
- } else if (is_kernel_mmap) {
- const char *symbol_name = (event->mmap.filename +
- strlen(kmmap_prefix));
- /*
- * Should be there already, from the build-id table in
- * the header.
- */
- struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
- kmmap_prefix);
- if (kernel == NULL)
- goto out_problem;
-
- kernel->kernel = kernel_type;
- if (__machine__create_kernel_maps(machine, kernel) < 0)
- goto out_problem;
-
- perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-
- /*
- * Avoid using a zero address (kptr_restrict) for the ref reloc
- * symbol. Effectively having zero here means that at record
- * time /proc/sys/kernel/kptr_restrict was non zero.
- */
- if (event->mmap.pgoff != 0) {
- maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
- symbol_name,
- event->mmap.pgoff);
- }
-
- if (machine__is_default_guest(machine)) {
- /*
- * preload dso of guest kernel and modules
- */
- dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
- NULL);
- }
- }
- return 0;
-out_problem:
- return -1;
+ return machine__process_lost_event(machine, event);
}
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
event->mmap.len, event->mmap.pgoff, event->mmap.filename);
}
-int perf_event__process_mmap(struct perf_tool *tool,
+int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
- struct thread *thread;
- struct map *map;
- u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- int ret = 0;
-
- if (dump_trace)
- perf_event__fprintf_mmap(event, stdout);
-
- if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
- cpumode == PERF_RECORD_MISC_KERNEL) {
- ret = perf_event__process_kernel_mmap(tool, event, machine);
- if (ret < 0)
- goto out_problem;
- return 0;
- }
-
- thread = machine__findnew_thread(machine, event->mmap.pid);
- if (thread == NULL)
- goto out_problem;
- map = map__new(&machine->user_dsos, event->mmap.start,
- event->mmap.len, event->mmap.pgoff,
- event->mmap.pid, event->mmap.filename,
- MAP__FUNCTION);
- if (map == NULL)
- goto out_problem;
-
- thread__insert_map(thread, map);
- return 0;
-
-out_problem:
- dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
- return 0;
+ return machine__process_mmap_event(machine, event);
}
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
event->fork.ppid, event->fork.ptid);
}
-int perf_event__process_task(struct perf_tool *tool __maybe_unused,
+int perf_event__process_fork(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
- struct machine *machine)
+ struct machine *machine)
{
- struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
- struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
-
- if (dump_trace)
- perf_event__fprintf_task(event, stdout);
-
- if (event->header.type == PERF_RECORD_EXIT) {
- machine__remove_thread(machine, thread);
- return 0;
- }
-
- if (thread == NULL || parent == NULL ||
- thread__fork(thread, parent) < 0) {
- dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
- return -1;
- }
+ return machine__process_fork_event(machine, event);
+}
- return 0;
+int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_exit_event(machine, event);
}
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
return ret;
}
-int perf_event__process(struct perf_tool *tool, union perf_event *event,
- struct perf_sample *sample, struct machine *machine)
+int perf_event__process(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
{
- switch (event->header.type) {
- case PERF_RECORD_COMM:
- perf_event__process_comm(tool, event, sample, machine);
- break;
- case PERF_RECORD_MMAP:
- perf_event__process_mmap(tool, event, sample, machine);
- break;
- case PERF_RECORD_FORK:
- case PERF_RECORD_EXIT:
- perf_event__process_task(tool, event, sample, machine);
- break;
- case PERF_RECORD_LOST:
- perf_event__process_lost(tool, event, sample, machine);
- default:
- break;
- }
-
- return 0;
+ return machine__process_event(machine, event);
}
void thread__find_addr_map(struct thread *self,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
-int perf_event__process_task(struct perf_tool *tool,
+int perf_event__process_fork(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_exit(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
{
- /* XXX Move this to perf.c, making it generally available */
- unsigned int page_size = sysconf(_SC_PAGE_SIZE);
struct perf_mmap *md = &evlist->mmap[idx];
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite)
{
- unsigned int page_size = sysconf(_SC_PAGE_SIZE);
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
PERF_HPP__OVERHEAD_GUEST_US,
PERF_HPP__SAMPLES,
PERF_HPP__PERIOD,
+ PERF_HPP__PERIOD_BASELINE,
PERF_HPP__DELTA,
+ PERF_HPP__RATIO,
+ PERF_HPP__WEIGHTED_DIFF,
PERF_HPP__DISPL,
+ PERF_HPP__FORMULA,
PERF_HPP__MAX_INDEX
};
unsigned int hists__sort_list_width(struct hists *self);
+double perf_diff__compute_delta(struct hist_entry *he);
+double perf_diff__compute_ratio(struct hist_entry *he);
+s64 perf_diff__compute_wdiff(struct hist_entry *he);
+int perf_diff__formula(char *buf, size_t size, struct hist_entry *he);
#endif /* __PERF_HIST_H */
--- /dev/null
+#include "debug.h"
+#include "event.h"
+#include "machine.h"
+#include "map.h"
+#include "thread.h"
+#include <stdbool.h>
+
+static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
+ bool create)
+{
+ struct rb_node **p = &machine->threads.rb_node;
+ struct rb_node *parent = NULL;
+ struct thread *th;
+
+ /*
+ * Font-end cache - PID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
+ */
+ if (machine->last_match && machine->last_match->pid == pid)
+ return machine->last_match;
+
+ while (*p != NULL) {
+ parent = *p;
+ th = rb_entry(parent, struct thread, rb_node);
+
+ if (th->pid == pid) {
+ machine->last_match = th;
+ return th;
+ }
+
+ if (pid < th->pid)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ if (!create)
+ return NULL;
+
+ th = thread__new(pid);
+ if (th != NULL) {
+ rb_link_node(&th->rb_node, parent, p);
+ rb_insert_color(&th->rb_node, &machine->threads);
+ machine->last_match = th;
+ }
+
+ return th;
+}
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid)
+{
+ return __machine__findnew_thread(machine, pid, true);
+}
+
+struct thread *machine__find_thread(struct machine *machine, pid_t pid)
+{
+ return __machine__findnew_thread(machine, pid, false);
+}
+
+int machine__process_comm_event(struct machine *machine, union perf_event *event)
+{
+ struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+
+ if (dump_trace)
+ perf_event__fprintf_comm(event, stdout);
+
+ if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
+ dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+int machine__process_lost_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+ event->lost.id, event->lost.lost);
+ return 0;
+}
+
+static void machine__set_kernel_mmap_len(struct machine *machine,
+ union perf_event *event)
+{
+ machine->vmlinux_maps[MAP__FUNCTION]->start = event->mmap.start;
+ machine->vmlinux_maps[MAP__FUNCTION]->end = (event->mmap.start +
+ event->mmap.len);
+ /*
+ * Be a bit paranoid here, some perf.data file came with
+ * a zero sized synthesized MMAP event for the kernel.
+ */
+ if (machine->vmlinux_maps[MAP__FUNCTION]->end == 0)
+ machine->vmlinux_maps[MAP__FUNCTION]->end = ~0ULL;
+}
+
+static int machine__process_kernel_mmap_event(struct machine *machine,
+ union perf_event *event)
+{
+ struct map *map;
+ char kmmap_prefix[PATH_MAX];
+ enum dso_kernel_type kernel_type;
+ bool is_kernel_mmap;
+
+ machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
+ if (machine__is_host(machine))
+ kernel_type = DSO_TYPE_KERNEL;
+ else
+ kernel_type = DSO_TYPE_GUEST_KERNEL;
+
+ is_kernel_mmap = memcmp(event->mmap.filename,
+ kmmap_prefix,
+ strlen(kmmap_prefix) - 1) == 0;
+ if (event->mmap.filename[0] == '/' ||
+ (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
+
+ char short_module_name[1024];
+ char *name, *dot;
+
+ if (event->mmap.filename[0] == '/') {
+ name = strrchr(event->mmap.filename, '/');
+ if (name == NULL)
+ goto out_problem;
+
+ ++name; /* skip / */
+ dot = strrchr(name, '.');
+ if (dot == NULL)
+ goto out_problem;
+ snprintf(short_module_name, sizeof(short_module_name),
+ "[%.*s]", (int)(dot - name), name);
+ strxfrchar(short_module_name, '-', '_');
+ } else
+ strcpy(short_module_name, event->mmap.filename);
+
+ map = machine__new_module(machine, event->mmap.start,
+ event->mmap.filename);
+ if (map == NULL)
+ goto out_problem;
+
+ name = strdup(short_module_name);
+ if (name == NULL)
+ goto out_problem;
+
+ map->dso->short_name = name;
+ map->dso->sname_alloc = 1;
+ map->end = map->start + event->mmap.len;
+ } else if (is_kernel_mmap) {
+ const char *symbol_name = (event->mmap.filename +
+ strlen(kmmap_prefix));
+ /*
+ * Should be there already, from the build-id table in
+ * the header.
+ */
+ struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
+ kmmap_prefix);
+ if (kernel == NULL)
+ goto out_problem;
+
+ kernel->kernel = kernel_type;
+ if (__machine__create_kernel_maps(machine, kernel) < 0)
+ goto out_problem;
+
+ machine__set_kernel_mmap_len(machine, event);
+
+ /*
+ * Avoid using a zero address (kptr_restrict) for the ref reloc
+ * symbol. Effectively having zero here means that at record
+ * time /proc/sys/kernel/kptr_restrict was non zero.
+ */
+ if (event->mmap.pgoff != 0) {
+ maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+ symbol_name,
+ event->mmap.pgoff);
+ }
+
+ if (machine__is_default_guest(machine)) {
+ /*
+ * preload dso of guest kernel and modules
+ */
+ dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
+ NULL);
+ }
+ }
+ return 0;
+out_problem:
+ return -1;
+}
+
+int machine__process_mmap_event(struct machine *machine, union perf_event *event)
+{
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ struct thread *thread;
+ struct map *map;
+ int ret = 0;
+
+ if (dump_trace)
+ perf_event__fprintf_mmap(event, stdout);
+
+ if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+ cpumode == PERF_RECORD_MISC_KERNEL) {
+ ret = machine__process_kernel_mmap_event(machine, event);
+ if (ret < 0)
+ goto out_problem;
+ return 0;
+ }
+
+ thread = machine__findnew_thread(machine, event->mmap.pid);
+ if (thread == NULL)
+ goto out_problem;
+ map = map__new(&machine->user_dsos, event->mmap.start,
+ event->mmap.len, event->mmap.pgoff,
+ event->mmap.pid, event->mmap.filename,
+ MAP__FUNCTION);
+ if (map == NULL)
+ goto out_problem;
+
+ thread__insert_map(thread, map);
+ return 0;
+
+out_problem:
+ dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
+ return 0;
+}
+
+int machine__process_fork_event(struct machine *machine, union perf_event *event)
+{
+ struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+ struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+
+ if (dump_trace)
+ perf_event__fprintf_task(event, stdout);
+
+ if (thread == NULL || parent == NULL ||
+ thread__fork(thread, parent) < 0) {
+ dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+int machine__process_exit_event(struct machine *machine, union perf_event *event)
+{
+ struct thread *thread = machine__find_thread(machine, event->fork.tid);
+
+ if (dump_trace)
+ perf_event__fprintf_task(event, stdout);
+
+ if (thread != NULL)
+ machine__remove_thread(machine, thread);
+
+ return 0;
+}
+
+int machine__process_event(struct machine *machine, union perf_event *event)
+{
+ int ret;
+
+ switch (event->header.type) {
+ case PERF_RECORD_COMM:
+ ret = machine__process_comm_event(machine, event); break;
+ case PERF_RECORD_MMAP:
+ ret = machine__process_mmap_event(machine, event); break;
+ case PERF_RECORD_FORK:
+ ret = machine__process_fork_event(machine, event); break;
+ case PERF_RECORD_EXIT:
+ ret = machine__process_exit_event(machine, event); break;
+ case PERF_RECORD_LOST:
+ ret = machine__process_lost_event(machine, event); break;
+ default:
+ ret = -1;
+ break;
+ }
+
+ return ret;
+}
--- /dev/null
+#ifndef __PERF_MACHINE_H
+#define __PERF_MACHINE_H
+
+#include <sys/types.h>
+
+struct thread;
+struct machine;
+union perf_event;
+
+struct thread *machine__find_thread(struct machine *machine, pid_t pid);
+
+int machine__process_comm_event(struct machine *machine, union perf_event *event);
+int machine__process_exit_event(struct machine *machine, union perf_event *event);
+int machine__process_fork_event(struct machine *machine, union perf_event *event);
+int machine__process_lost_event(struct machine *machine, union perf_event *event);
+int machine__process_mmap_event(struct machine *machine, union perf_event *event);
+int machine__process_event(struct machine *machine, union perf_event *event);
+
+#endif /* __PERF_MACHINE_H */
#include "../event.h"
#include "../thread.h"
#include "../trace-event.h"
-#include "../evsel.h"
PyMODINIT_FUNC initperf_trace_context(void);
{
u64 head, page_offset, file_offset, file_pos, progress_next;
int err, mmap_prot, mmap_flags, map_idx = 0;
- size_t page_size, mmap_size;
+ size_t mmap_size;
char *buf, *mmaps[8];
union perf_event *event;
uint32_t size;
perf_tool__fill_defaults(tool);
- page_size = sysconf(_SC_PAGESIZE);
-
page_offset = page_size * (data_offset / page_size);
file_offset = page_offset;
head = data_offset - page_offset;
u32 nr_events;
};
+struct hist_entry_diff {
+ bool computed;
+
+ /* PERF_HPP__DISPL */
+ int displacement;
+
+ /* PERF_HPP__DELTA */
+ double period_ratio_delta;
+
+ /* PERF_HPP__RATIO */
+ double period_ratio;
+
+ /* HISTC_WEIGHTED_DIFF */
+ s64 wdiff;
+};
+
/**
* struct hist_entry - histogram entry
*
u64 ip;
s32 cpu;
+ struct hist_entry_diff diff;
+
/* XXX These two should move to some tree widget lib */
u16 row_offset;
u16 nr_rows;
#include "util.h"
#include "debug.h"
-static struct thread *thread__new(pid_t pid)
+struct thread *thread__new(pid_t pid)
{
struct thread *self = zalloc(sizeof(*self));
map_groups__fprintf(&self->mg, verbose, fp);
}
-struct thread *machine__findnew_thread(struct machine *self, pid_t pid)
-{
- struct rb_node **p = &self->threads.rb_node;
- struct rb_node *parent = NULL;
- struct thread *th;
-
- /*
- * Font-end cache - PID lookups come in blocks,
- * so most of the time we dont have to look up
- * the full rbtree:
- */
- if (self->last_match && self->last_match->pid == pid)
- return self->last_match;
-
- while (*p != NULL) {
- parent = *p;
- th = rb_entry(parent, struct thread, rb_node);
-
- if (th->pid == pid) {
- self->last_match = th;
- return th;
- }
-
- if (pid < th->pid)
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
- }
-
- th = thread__new(pid);
- if (th != NULL) {
- rb_link_node(&th->rb_node, parent, p);
- rb_insert_color(&th->rb_node, &self->threads);
- self->last_match = th;
- }
-
- return th;
-}
-
void thread__insert_map(struct thread *self, struct map *map)
{
map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
#include <linux/rbtree.h>
#include <unistd.h>
+#include <sys/types.h>
#include "symbol.h"
struct thread {
struct machine;
+struct thread *thread__new(pid_t pid);
void thread__delete(struct thread *self);
int thread__set_comm(struct thread *self, const char *comm);
int host_bigendian;
static int long_size;
-static unsigned long page_size;
-
static ssize_t calc_data_size;
static bool repipe;
/*
* XXX We need to find a better place for these things...
*/
+unsigned int page_size;
+
bool perf_host = true;
bool perf_guest = false;
void dump_stack(void);
+extern unsigned int page_size;
+
#endif