Commit 028c63b5 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge tag 'perf-core-for-mingo' of... 

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

 into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Fix perf.data size reporting in 'perf record' in no-buildid mode (He Kuang)

Infrastructure changes:

  - Protect accesses the DSO rbtrees/lists with a rw lock and reference
    count struct dso instances (Arnaldo Carvalho de Melo)

  - Export dynamic symbols used by traceevent plugins (He Kuang)

  - Add libtrace-dynamic-list file to libtraceevent's .gitignore (He Kuang)

  - Refactor shadow stats code in 'perf stat', prep work for further
    patchkits (Jiri Olsa)

Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents a3d86542 d3a7c489

tools/lib/traceevent/.gitignore

+1 −0
Original line number Diff line number Diff line 
TRACEEVENT-CFLAGS

libtraceevent-dynamic-list

tools/lib/traceevent/Makefile

+13 −1
Original line number Diff line number Diff line
@@ -23,6 +23,7 @@ endef 
# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.

$(call allow-override,CC,$(CROSS_COMPILE)gcc)

$(call allow-override,AR,$(CROSS_COMPILE)ar)

$(call allow-override,NM,$(CROSS_COMPILE)nm)



EXT = -std=gnu99

INSTALL = install
@@ -157,8 +158,9 @@ PLUGINS_IN := $(PLUGINS:.so=-in.o) 


TE_IN    := $(OUTPUT)libtraceevent-in.o

LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))

DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list



CMD_TARGETS = $(LIB_FILE) $(PLUGINS)

CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)



TARGETS = $(CMD_TARGETS)
@@ -175,6 +177,9 @@ $(OUTPUT)libtraceevent.so: $(TE_IN) 
$(OUTPUT)libtraceevent.a: $(TE_IN)

	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^



$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)

	$(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)



plugins: $(PLUGINS)



__plugin_obj = $(notdir $@)
@@ -244,6 +249,13 @@ define do_install_plugins 
	done

endef



define do_generate_dynamic_list_file

	(echo '{';							\

	$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;	\

	echo '};';							\

	) > $2

endef



install_lib: all_cmd install_plugins

	$(call QUIET_INSTALL, $(LIB_FILE)) \

		$(call do_install,$(LIB_FILE),$(libdir_SQ))

tools/perf/Makefile.perf

+12 −2
Original line number Diff line number Diff line
@@ -173,6 +173,9 @@ endif 
LIBTRACEEVENT = $(TE_PATH)libtraceevent.a

export LIBTRACEEVENT



LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list

LDFLAGS += -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)



LIBAPI = $(LIB_PATH)libapi.a

export LIBAPI
@@ -278,7 +281,7 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj 
$(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE

	$(Q)$(MAKE) $(build)=perf



$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN)

$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)

	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(PERF_IN) $(LIBS) -o $@



$(GTK_IN): FORCE
@@ -373,7 +376,13 @@ $(LIB_FILE): $(LIBPERF_IN) 
LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)



$(LIBTRACEEVENT): FORCE

	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a plugins

	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a



libtraceevent_plugins: FORCE

	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins



$(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins

	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list



$(LIBTRACEEVENT)-clean:

	$(call QUIET_CLEAN, libtraceevent)
@@ -555,4 +564,5 @@ FORCE: 
.PHONY: all install clean config-clean strip install-gtk

.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell

.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE single_dep

.PHONY: libtraceevent_plugins

tools/perf/builtin-record.c

+2 −4
Original line number Diff line number Diff line
@@ -345,12 +345,9 @@ static int process_buildids(struct record *rec) 
	struct perf_data_file *file  = &rec->file;

	struct perf_session *session = rec->session;



	u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);

	if (size == 0)

	if (file->size == 0)

		return 0;



	file->size = size;



	/*

	 * During this process, it'll load kernel map and replace the

	 * dso->long_name to a real pathname it found.  In this case
@@ -719,6 +716,7 @@ out_child: 


	if (!err && !file->is_pipe) {

		rec->session->header.data_size += rec->bytes_written;

		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);



		if (!rec->no_buildid) {

			process_buildids(rec);

tools/perf/builtin-stat.c

+13 −493
Original line number Diff line number Diff line
@@ -73,8 +73,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix); 
static void print_aggr(char *prefix);



/* Default events used for perf stat -T */

static const char * const transaction_attrs[] = {

	"task-clock",

static const char *transaction_attrs = {

	"task-clock,"

	"{"

	"instructions,"

	"cycles,"
@@ -86,8 +86,8 @@ static const char * const transaction_attrs[] = { 
};



/* More limited version when the CPU does not have all events. */

static const char * const transaction_limited_attrs[] = {

	"task-clock",

static const char * transaction_limited_attrs = {

	"task-clock,"

	"{"

	"instructions,"

	"cycles,"
@@ -96,30 +96,12 @@ static const char * const transaction_limited_attrs[] = { 
	"}"

};



/* must match transaction_attrs and the beginning limited_attrs */

enum {

	T_TASK_CLOCK,

	T_INSTRUCTIONS,

	T_CYCLES,

	T_CYCLES_IN_TX,

	T_TRANSACTION_START,

	T_ELISION_START,

	T_CYCLES_IN_TX_CP,

};



static struct perf_evlist	*evsel_list;



static struct target target = {

	.uid	= UINT_MAX,

};



enum aggr_mode {

	AGGR_NONE,

	AGGR_GLOBAL,

	AGGR_SOCKET,

	AGGR_CORE,

};



static int			run_count			=  1;

static bool			no_inherit			= false;

static bool			scale				=  true;
@@ -147,10 +129,6 @@ static int (*aggr_get_id)(struct cpu_map *m, int cpu); 


static volatile int done = 0;



struct perf_stat {

	struct stats	  res_stats[3];

};



static inline void diff_timespec(struct timespec *r, struct timespec *a,

				 struct timespec *b)

{
@@ -180,6 +158,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) 


	for (i = 0; i < 3; i++)

		init_stats(&ps->res_stats[i]);



	perf_stat_evsel_id_init(evsel);

}



static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
@@ -247,51 +227,6 @@ out_free: 
	return -1;

}



enum {

	CTX_BIT_USER	= 1 << 0,

	CTX_BIT_KERNEL	= 1 << 1,

	CTX_BIT_HV	= 1 << 2,

	CTX_BIT_HOST	= 1 << 3,

	CTX_BIT_IDLE	= 1 << 4,

	CTX_BIT_MAX	= 1 << 5,

};



#define NUM_CTX CTX_BIT_MAX



static struct stats runtime_nsecs_stats[MAX_NR_CPUS];

static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats walltime_nsecs_stats;

static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];

static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];



static int evsel_context(struct perf_evsel *evsel)

{

	int ctx = 0;



	if (evsel->attr.exclude_kernel)

		ctx |= CTX_BIT_KERNEL;

	if (evsel->attr.exclude_user)

		ctx |= CTX_BIT_USER;

	if (evsel->attr.exclude_hv)

		ctx |= CTX_BIT_HV;

	if (evsel->attr.exclude_host)

		ctx |= CTX_BIT_HOST;

	if (evsel->attr.exclude_idle)

		ctx |= CTX_BIT_IDLE;



	return ctx;

}



static void perf_stat__reset_stats(struct perf_evlist *evlist)

{

	struct perf_evsel *evsel;
@@ -301,23 +236,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist) 
		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));

	}



	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));

	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));

	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));

	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));

	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));

	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));

	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));

	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));

	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));

	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));

	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));

	memset(runtime_cycles_in_tx_stats, 0,

			sizeof(runtime_cycles_in_tx_stats));

	memset(runtime_transaction_stats, 0,

		sizeof(runtime_transaction_stats));

	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));

	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));

	perf_stat__reset_shadow_stats();

}



static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -354,72 +273,6 @@ static inline int nsec_counter(struct perf_evsel *evsel) 
	return 0;

}



static struct perf_evsel *nth_evsel(int n)

{

	static struct perf_evsel **array;

	static int array_len;

	struct perf_evsel *ev;

	int j;



	/* Assumes this only called when evsel_list does not change anymore. */

	if (!array) {

		evlist__for_each(evsel_list, ev)

			array_len++;

		array = malloc(array_len * sizeof(void *));

		if (!array)

			exit(ENOMEM);

		j = 0;

		evlist__for_each(evsel_list, ev)

			array[j++] = ev;

	}

	if (n < array_len)

		return array[n];

	return NULL;

}



/*

 * Update various tracking values we maintain to print

 * more semantic information such as miss/hit ratios,

 * instruction rates, etc:

 */

static void update_shadow_stats(struct perf_evsel *counter, u64 *count,

				int cpu)

{

	int ctx = evsel_context(counter);



	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))

		update_stats(&runtime_nsecs_stats[cpu], count[0]);

	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))

		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);

	else if (transaction_run &&

		 perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))

		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);

	else if (transaction_run &&

		 perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))

		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);

	else if (transaction_run &&

		 perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))

		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))

		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))

		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))

		update_stats(&runtime_branches_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))

		update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))

		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))

		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))

		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))

		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);

	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))

		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);

}



static void zero_per_pkg(struct perf_evsel *counter)

{

	if (counter->per_pkg_mask)
@@ -480,7 +333,7 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, 
		perf_counts_values__scale(count, scale, NULL);

		evsel->counts->cpu[cpu] = *count;

		if (aggr_mode == AGGR_NONE)

			update_shadow_stats(evsel, count->values, cpu);

			perf_stat__update_shadow_stats(evsel, count->values, cpu);

		break;

	case AGGR_GLOBAL:

		aggr->val += count->val;
@@ -528,7 +381,7 @@ static int read_counter_aggr(struct perf_evsel *counter) 
	/*

	 * Save the full runtime - to allow normalization during printout:

	 */

	update_shadow_stats(counter, count, 0);

	perf_stat__update_shadow_stats(counter, count, 0);



	return 0;

}
@@ -906,200 +759,11 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) 
		fprintf(output, "                                   ");

}



/* used for get_ratio_color() */

enum grc_type {

	GRC_STALLED_CYCLES_FE,

	GRC_STALLED_CYCLES_BE,

	GRC_CACHE_MISSES,

	GRC_MAX_NR

};



static const char *get_ratio_color(enum grc_type type, double ratio)

{

	static const double grc_table[GRC_MAX_NR][3] = {

		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },

		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },

		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },

	};

	const char *color = PERF_COLOR_NORMAL;



	if (ratio > grc_table[type][0])

		color = PERF_COLOR_RED;

	else if (ratio > grc_table[type][1])

		color = PERF_COLOR_MAGENTA;

	else if (ratio > grc_table[type][2])

		color = PERF_COLOR_YELLOW;



	return color;

}



static void print_stalled_cycles_frontend(int cpu,

					  struct perf_evsel *evsel

					  __maybe_unused, double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " frontend cycles idle   ");

}



static void print_stalled_cycles_backend(int cpu,

					 struct perf_evsel *evsel

					 __maybe_unused, double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " backend  cycles idle   ");

}



static void print_branch_misses(int cpu,

				struct perf_evsel *evsel __maybe_unused,

				double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_branches_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all branches        ");

}



static void print_l1_dcache_misses(int cpu,

				   struct perf_evsel *evsel __maybe_unused,

				   double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all L1-dcache hits  ");

}



static void print_l1_icache_misses(int cpu,

				   struct perf_evsel *evsel __maybe_unused,

				   double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all L1-icache hits  ");

}



static void print_dtlb_cache_misses(int cpu,

				    struct perf_evsel *evsel __maybe_unused,

				    double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all dTLB cache hits ");

}



static void print_itlb_cache_misses(int cpu,

				    struct perf_evsel *evsel __maybe_unused,

				    double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all iTLB cache hits ");

}



static void print_ll_cache_misses(int cpu,

				  struct perf_evsel *evsel __maybe_unused,

				  double avg)

{

	double total, ratio = 0.0;

	const char *color;

	int ctx = evsel_context(evsel);



	total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);



	if (total)

		ratio = avg / total * 100.0;



	color = get_ratio_color(GRC_CACHE_MISSES, ratio);



	fprintf(output, " #  ");

	color_fprintf(output, color, "%6.2f%%", ratio);

	fprintf(output, " of all LL-cache hits   ");

}



static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)

{

	double total, ratio = 0.0, total2;

	double sc =  evsel->scale;

	const char *fmt;

	int cpu = cpu_map__id_to_cpu(id);

	int ctx = evsel_context(evsel);



	if (csv_output) {

		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -1130,138 +794,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) 
	if (csv_output || interval)

		return;



	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {

		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);

		if (total) {

			ratio = avg / total;

			fprintf(output, " #   %5.2f  insns per cycle        ", ratio);

		} else {

			fprintf(output, "                                   ");

		}

		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);

		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));



		if (total && avg) {

			ratio = total / avg;

			fprintf(output, "\n");

			if (aggr_mode == AGGR_NONE)

				fprintf(output, "        ");

			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);

		}



	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&

			runtime_branches_stats[ctx][cpu].n != 0) {

		print_branch_misses(cpu, evsel, avg);

	} else if (

		evsel->attr.type == PERF_TYPE_HW_CACHE &&

		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |

					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |

					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&

			runtime_l1_dcache_stats[ctx][cpu].n != 0) {

		print_l1_dcache_misses(cpu, evsel, avg);

	} else if (

		evsel->attr.type == PERF_TYPE_HW_CACHE &&

		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |

					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |

					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&

			runtime_l1_icache_stats[ctx][cpu].n != 0) {

		print_l1_icache_misses(cpu, evsel, avg);

	} else if (

		evsel->attr.type == PERF_TYPE_HW_CACHE &&

		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |

					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |

					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&

			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {

		print_dtlb_cache_misses(cpu, evsel, avg);

	} else if (

		evsel->attr.type == PERF_TYPE_HW_CACHE &&

		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |

					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |

					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&

			runtime_itlb_cache_stats[ctx][cpu].n != 0) {

		print_itlb_cache_misses(cpu, evsel, avg);

	} else if (

		evsel->attr.type == PERF_TYPE_HW_CACHE &&

		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |

					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |

					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&

			runtime_ll_cache_stats[ctx][cpu].n != 0) {

		print_ll_cache_misses(cpu, evsel, avg);

	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&

			runtime_cacherefs_stats[ctx][cpu].n != 0) {

		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);



		if (total)

			ratio = avg * 100 / total;



		fprintf(output, " # %8.3f %% of all cache refs    ", ratio);



	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {

		print_stalled_cycles_frontend(cpu, evsel, avg);

	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {

		print_stalled_cycles_backend(cpu, evsel, avg);

	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {

		total = avg_stats(&runtime_nsecs_stats[cpu]);



		if (total) {

			ratio = avg / total;

			fprintf(output, " # %8.3f GHz                    ", ratio);

		} else {

			fprintf(output, "                                   ");

		}

	} else if (transaction_run &&

		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {

		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);

		if (total)

			fprintf(output,

				" #   %5.2f%% transactional cycles   ",

				100.0 * (avg / total));

	} else if (transaction_run &&

		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {

		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);

		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);

		if (total2 < avg)

			total2 = avg;

		if (total)

			fprintf(output,

				" #   %5.2f%% aborted cycles         ",

				100.0 * ((total2-avg) / total));

	} else if (transaction_run &&

		   perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&

		   avg > 0 &&

		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {

		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);



		if (total)

			ratio = total / avg;



		fprintf(output, " # %8.0f cycles / transaction   ", ratio);

	} else if (transaction_run &&

		   perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&

		   avg > 0 &&

		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {

		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);



		if (total)

			ratio = total / avg;



		fprintf(output, " # %8.0f cycles / elision       ", ratio);

	} else if (runtime_nsecs_stats[cpu].n != 0) {

		char unit = 'M';



		total = avg_stats(&runtime_nsecs_stats[cpu]);



		if (total)

			ratio = 1000.0 * avg / total;

		if (ratio < 0.001) {

			ratio *= 1000;

			unit = 'K';

		}



		fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);

	} else {

		fprintf(output, "                                   ");

	}

	perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);

}



static void print_aggr(char *prefix)
@@ -1576,17 +1109,6 @@ static int perf_stat_init_aggr_mode(void) 
	return 0;

}



static int setup_events(const char * const *attrs, unsigned len)

{

	unsigned i;



	for (i = 0; i < len; i++) {

		if (parse_events(evsel_list, attrs[i], NULL))

			return -1;

	}

	return 0;

}



/*

 * Add default attributes, if there were no attributes specified or

 * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1708,12 +1230,10 @@ static int add_default_attributes(void) 
		int err;

		if (pmu_have_event("cpu", "cycles-ct") &&

		    pmu_have_event("cpu", "el-start"))

			err = setup_events(transaction_attrs,

					ARRAY_SIZE(transaction_attrs));

			err = parse_events(evsel_list, transaction_attrs, NULL);

		else

			err = setup_events(transaction_limited_attrs,

				 ARRAY_SIZE(transaction_limited_attrs));

		if (err < 0) {

			err = parse_events(evsel_list, transaction_limited_attrs, NULL);

		if (err) {

			fprintf(stderr, "Cannot set up transaction events\n");

			return -1;

		}

CRA Git | Maintained and supported by SUSTech CRA and CCSE