Merge tag 'perf-core-for-mingo-4.13-20170621' 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:

New features:

 - Add support to measure SMI cost in 'perf stat' (Kan Liang)

 - Add support for unwinding callchains in powerpc with libdw (Paolo Bonzini)

Fixes:

 - Fix message: cpu list option is -C not -c (Adrian Hunter)

 - Fix 'perf script' message: field list option is -F not -f (Adrian Hunter)

 - Intel PT fixes: (Adrian Hunter)

   o Fix missing stack clear
   o Ensure IP is zero when state is INTEL_PT_STATE_NO_IP
   o Fix last_ip usage
   o Ensure never to set 'last_ip' when packet 'count' is zero
   o Clear FUP flag on error
   o Fix transactions_sample_type

Infrastructure changes:

 - Intel PT cleanups/refactorings (Adrian Hunter)

   o Use FUP always when scanning for an IP
   o Add missing __fallthrough
   o Remove redundant initial_skip checks
   o Allow decoding with branch tracing disabled
   o Add default config for pass-through branch enable
   o Add documentation for new config terms
   o Add decoder support for ptwrite and power event packets
   o Add reserved byte to CBR packet payload
   o Add decoder support for CBR events

 - Move  find_process() to the only place that uses it, skimming some
   more fat from util.[ch] (Arnaldo Carvalho de Melo)

 - Do parameter validation earlier on fetch_kernel_version() (Arnaldo Carvalho de Melo)

 - Remove unused _ALL_SOURCE define (Arnaldo Carvalho de Melo)

 - Add sysfs__write_int function (Kan Liang)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/lib/api/fs/fs.c

@@ -387,6 +387,22 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 	return err;
 }
 
+int filename__write_int(const char *filename, int value)
+{
+	int fd = open(filename, O_WRONLY), err = -1;
+	char buf[64];
+
+	if (fd < 0)
+		return err;
+
+	sprintf(buf, "%d", value);
+	if (write(fd, buf, sizeof(buf)) == sizeof(buf))
+		err = 0;
+
+	close(fd);
+	return err;
+}
+
 int procfs__read_str(const char *entry, char **buf, size_t *sizep)
 {
 	char path[PATH_MAX];
@@ -480,3 +496,17 @@ int sysctl__read_int(const char *sysctl, int *value)
 
 	return filename__read_int(path, value);
 }
+
+int sysfs__write_int(const char *entry, int value)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	if (snprintf(path, sizeof(path), "%s/%s", sysfs, entry) >= PATH_MAX)
+		return -1;
+
+	return filename__write_int(path, value);
+}

tools/lib/api/fs/fs.h

@@ -31,11 +31,15 @@ int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
+int filename__write_int(const char *filename, int value);
+
 int procfs__read_str(const char *entry, char **buf, size_t *sizep);
 
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
 int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 int sysfs__read_bool(const char *entry, bool *value);
+
+int sysfs__write_int(const char *entry, int value);
 #endif /* __API_FS__ */

tools/perf/Documentation/intel-pt.txt

@@ -364,6 +364,42 @@ cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
 
 		CYC packets are not requested by default.
 
+pt		Specifies pass-through which enables the 'branch' config term.
+
+		The default config selects 'pt' if it is available, so a user will
+		never need to specify this term.
+
+branch		Enable branch tracing.  Branch tracing is enabled by default so to
+		disable branch tracing use 'branch=0'.
+
+		The default config selects 'branch' if it is available.
+
+ptw		Enable PTWRITE packets which are produced when a ptwrite instruction
+		is executed.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/ptwrite
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
+fup_on_ptw	Enable a FUP packet to follow the PTWRITE packet.  The FUP packet
+		provides the address of the ptwrite instruction.  In the absence of
+		fup_on_ptw, the decoder will use the address of the previous branch
+		if branch tracing is enabled, otherwise the address will be zero.
+		Note that fup_on_ptw will work even when branch tracing is disabled.
+
+pwr_evt		Enable power events.  The power events provide information about
+		changes to the CPU C-state.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/power_event_trace
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
 
 new snapshot option
 -------------------

tools/perf/Documentation/perf-stat.txt

@@ -239,6 +239,20 @@ taskset.
 --no-merge::
 Do not merge results from same PMUs.
 
+--smi-cost::
+Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
+
+During the measurement, the /sys/device/cpu/freeze_on_smi will be set to
+freeze core counters on SMI.
+The aperf counter will not be effected by the setting.
+The cost of SMI can be measured by (aperf - unhalted core cycles).
+
+In practice, the percentages of SMI cycles is very useful for performance
+oriented analysis. --metric_only will be applied by default.
+The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
+
+Users who wants to get the actual value can apply --no-metric-only.
+
 EXAMPLES
 --------
 

tools/perf/Makefile.config

@@ -61,7 +61,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 

tools/perf/arch/powerpc/util/Build

@@ -5,4 +5,6 @@ libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
+
 libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

tools/perf/arch/powerpc/util/unwind-libdw.c

@@ -0,0 +1,73 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils.  */
+static const int special_regs[3][2] = {
+	{ 65, PERF_REG_POWERPC_LINK },
+	{ 101, PERF_REG_POWERPC_XER },
+	{ 109, PERF_REG_POWERPC_CTR },
+};
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[32], dwarf_nip;
+	size_t i;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(R0);
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(R11);
+	dwarf_regs[12] = REG(R12);
+	dwarf_regs[13] = REG(R13);
+	dwarf_regs[14] = REG(R14);
+	dwarf_regs[15] = REG(R15);
+	dwarf_regs[16] = REG(R16);
+	dwarf_regs[17] = REG(R17);
+	dwarf_regs[18] = REG(R18);
+	dwarf_regs[19] = REG(R19);
+	dwarf_regs[20] = REG(R20);
+	dwarf_regs[21] = REG(R21);
+	dwarf_regs[22] = REG(R22);
+	dwarf_regs[23] = REG(R23);
+	dwarf_regs[24] = REG(R24);
+	dwarf_regs[25] = REG(R25);
+	dwarf_regs[26] = REG(R26);
+	dwarf_regs[27] = REG(R27);
+	dwarf_regs[28] = REG(R28);
+	dwarf_regs[29] = REG(R29);
+	dwarf_regs[30] = REG(R30);
+	dwarf_regs[31] = REG(R31);
+	if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs))
+		return false;
+
+	dwarf_nip = REG(NIP);
+	dwfl_thread_state_register_pc(thread, dwarf_nip);
+	for (i = 0; i < ARRAY_SIZE(special_regs); i++) {
+		Dwarf_Word val = 0;
+		perf_reg_value(&val, user_regs, special_regs[i][1]);
+		if (!dwfl_thread_state_registers(thread,
+						 special_regs[i][0], 1,
+						 &val))
+			return false;
+	}
+
+	return true;
+}

tools/perf/arch/x86/util/intel-pt.c

@@ -192,6 +192,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
 	int psb_cyc, psb_periods, psb_period;
 	int pos = 0;
 	u64 config;
+	char c;
 
 	pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc");
 
@@ -225,6 +226,10 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
 		}
 	}
 
+	if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 &&
+	    perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch");
+
 	pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf);
 
 	intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config);

tools/perf/builtin-script.c

@@ -385,7 +385,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		 */
 		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
 			pr_err("%s events do not exist. "
-			       "Remove corresponding -f option to proceed.\n",
+			       "Remove corresponding -F option to proceed.\n",
 			       event_type(j));
 			return -1;
 		}

tools/perf/builtin-stat.c

@@ -86,6 +86,7 @@
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
+#define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
 
@@ -122,6 +123,14 @@ static const char * topdown_attrs[] = {
 	NULL,
 };
 
+static const char *smi_cost_attrs = {
+	"{"
+	"msr/aperf/,"
+	"msr/smi/,"
+	"cycles"
+	"}"
+};
+
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
@@ -137,6 +146,8 @@ static bool			null_run			=  false;
 static int			detailed_run			=  0;
 static bool			transaction_run;
 static bool			topdown_run			= false;
+static bool			smi_cost			= false;
+static bool			smi_reset			= false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*csv_sep			= NULL;
@@ -1782,6 +1793,8 @@ static const struct option stat_options[] = {
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure topdown level 1 statistics"),
+	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
+			"measure SMI cost"),
 	OPT_END()
 };
 
@@ -2160,6 +2173,39 @@ static int add_default_attributes(void)
 		return 0;
 	}
 
+	if (smi_cost) {
+		int smi;
+
+		if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) {
+			fprintf(stderr, "freeze_on_smi is not supported.\n");
+			return -1;
+		}
+
+		if (!smi) {
+			if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) {
+				fprintf(stderr, "Failed to set freeze_on_smi.\n");
+				return -1;
+			}
+			smi_reset = true;
+		}
+
+		if (pmu_have_event("msr", "aperf") &&
+		    pmu_have_event("msr", "smi")) {
+			if (!force_metric_only)
+				metric_only = true;
+			err = parse_events(evsel_list, smi_cost_attrs, NULL);
+		} else {
+			fprintf(stderr, "To measure SMI cost, it needs "
+				"msr/aperf/, msr/smi/ and cpu/cycles/ support\n");
+			return -1;
+		}
+		if (err) {
+			fprintf(stderr, "Cannot set up SMI cost events\n");
+			return -1;
+		}
+		return 0;
+	}
+
 	if (topdown_run) {
 		char *str = NULL;
 		bool warn = false;
@@ -2742,6 +2788,9 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
+	if (smi_cost && smi_reset)
+		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
+
 	perf_evlist__delete(evsel_list);
 	return status;
 }

tools/perf/util/evsel.c

@@ -11,6 +11,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitops.h>
+#include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
@@ -19,6 +20,8 @@
 #include <linux/err.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
+#include <sys/types.h>
+#include <dirent.h>
 #include "asm/bug.h"
 #include "callchain.h"
 #include "cgroup.h"
@@ -2472,6 +2475,42 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 	return false;
 }
 
+static bool find_process(const char *name)
+{
+	size_t len = strlen(name);
+	DIR *dir;
+	struct dirent *d;
+	int ret = -1;
+
+	dir = opendir(procfs__mountpoint());
+	if (!dir)
+		return false;
+
+	/* Walk through the directory. */
+	while (ret && (d = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		char *data;
+		size_t size;
+
+		if ((d->d_type != DT_DIR) ||
+		     !strcmp(".", d->d_name) ||
+		     !strcmp("..", d->d_name))
+			continue;
+
+		scnprintf(path, sizeof(path), "%s/%s/comm",
+			  procfs__mountpoint(), d->d_name);
+
+		if (filename__read_str(path, &data, &size))
+			continue;
+
+		ret = strncmp(name, data, len);
+		free(data);
+	}
+
+	closedir(dir);
+	return ret ? false : true;
+}
+
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {