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:

Infrastructure changes:

 o More prep work to support Intel PT: (Adrian Hunter)
   - Polishing 'script' BTS output
   - 'inject' can specify --kallsym
   - VDSO is per machine, not a global var
   - Expose data addr lookup functions previously private to 'script'
   - Large mmap fixes in events processing

 o Fix build on gcc 4.4.7 (Arnaldo Carvalho de Melo)

 o Event ordering fixes (Jiri Olsa)

 o Include standard stringify macros in power pc code (Sukadev Bhattiprolu)

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

tools/perf/Documentation/perf-inject.txt

@@ -41,6 +41,9 @@ OPTIONS
 	tasks slept. sched_switch contains a callchain where a task slept and
 	sched_stat contains a timeslice how long a task slept.
 
+--kallsyms=<file>::
+	kallsyms pathname
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]

tools/perf/arch/powerpc/util/header.c

@@ -5,9 +5,7 @@
 #include <string.h>
 
 #include "../../util/header.h"
-
-#define __stringify_1(x)        #x
-#define __stringify(x)          __stringify_1(x)
+#include "../../util/util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \

tools/perf/arch/x86/util/tsc.c

@@ -37,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 
 	return 0;
 }
+
+u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}

tools/perf/builtin-inject.c

@@ -439,6 +439,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "where and how long tasks slept"),
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
+		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
+			   "kallsyms pathname"),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {

tools/perf/builtin-record.c

@@ -238,6 +238,7 @@ static struct perf_event_header finished_round_event = {
 
 static int record__mmap_read_all(struct record *rec)
 {
+	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
 
@@ -250,7 +251,11 @@ static int record__mmap_read_all(struct record *rec)
 		}
 	}
 
-	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+	/*
+	 * Mark the round finished in case we wrote
+	 * at least one event.
+	 */
+	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:

tools/perf/builtin-script.c

@@ -358,52 +358,20 @@ static void print_sample_start(struct perf_sample *sample,
 	}
 }
 
-static bool is_bts_event(struct perf_event_attr *attr)
-{
-	return ((attr->type == PERF_TYPE_HARDWARE) &&
-		(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-		(attr->sample_period == 1));
-}
-
-static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
-{
-	if ((attr->type == PERF_TYPE_SOFTWARE) &&
-	    ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
-		return true;
-
-	if (is_bts_event(attr))
-		return true;
-
-	return false;
-}
-
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
 			  struct machine *machine,
 			  struct thread *thread,
 			  struct perf_event_attr *attr)
 {
 	struct addr_location al;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	printf("%16" PRIx64, sample->addr);
 
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, &al);
-	if (!al.map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
-				      sample->addr, &al);
-
-	al.cpu = sample->cpu;
-	al.sym = NULL;
-
-	if (al.map)
-		al.sym = map__find_symbol(al.map, al.addr, NULL);
+	perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -427,25 +395,35 @@ static void print_sample_bts(union perf_event *event,
 			     struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool print_srcline_last = false;
 
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
-		if (!symbol_conf.use_callchain)
-			printf(" ");
-		else
+		unsigned int print_opts = output[attr->type].print_ip_opts;
+
+		if (symbol_conf.use_callchain && sample->callchain) {
 			printf("\n");
-		perf_evsel__print_ip(evsel, sample, al,
-				     output[attr->type].print_ip_opts,
+		} else {
+			printf(" ");
+			if (print_opts & PRINT_IP_OPT_SRCLINE) {
+				print_srcline_last = true;
+				print_opts &= ~PRINT_IP_OPT_SRCLINE;
+			}
+		}
+		perf_evsel__print_ip(evsel, sample, al, print_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
 
-	printf(" => ");
-
 	/* print branch_to information */
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	     !output[attr->type].user_set))
+	     !output[attr->type].user_set)) {
+		printf(" => ");
 		print_sample_addr(event, sample, al->machine, thread, attr);
+	}
+
+	if (print_srcline_last)
+		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
 	printf("\n");
 }

tools/perf/builtin-trace.c

@@ -1994,10 +1994,10 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
 	struct perf_event_attr attr = {
 		.type = PERF_TYPE_SOFTWARE,
 		.mmap_data = 1,
-		.sample_period = 1,
 	};
 
 	attr.config = config;
+	attr.sample_period = 1;
 
 	event_attr_init(&attr);
 

tools/perf/tests/perf-time-to-tsc.c

@@ -25,15 +25,6 @@
 	}					\
 }
 
-static u64 rdtsc(void)
-{
-	unsigned int low, high;
-
-	asm volatile("rdtsc" : "=a" (low), "=d" (high));
-
-	return low | ((u64)high) << 32;
-}
-
 /**
  * test__perf_time_to_tsc - test converting perf time to TSC.
  *

tools/perf/util/cloexec.c

@@ -1,3 +1,4 @@
+#include <sched.h>
 #include "util.h"
 #include "../perf.h"
 #include "cloexec.h"
@@ -14,9 +15,13 @@ static int perf_flag_probe(void)
 	};
 	int fd;
 	int err;
+	int cpu = sched_getcpu();
+
+	if (cpu < 0)
+		cpu = 0;
 
 	/* check cloexec flag */
-	fd = sys_perf_event_open(&attr, 0, -1, -1,
+	fd = sys_perf_event_open(&attr, -1, cpu, -1,
 				 PERF_FLAG_FD_CLOEXEC);
 	err = errno;
 
@@ -30,7 +35,7 @@ static int perf_flag_probe(void)
 		  err, strerror(err));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
 	err = errno;
 
 	if (WARN_ONCE(fd < 0,

tools/perf/util/dso.c

@@ -216,7 +216,7 @@ static int open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd = __open_dso(dso, machine);
 
-	if (fd > 0) {
+	if (fd >= 0) {
 		dso__list_add(dso);
 		/*
 		 * Check if we crossed the allowed number
@@ -331,26 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
 	if (dso->data.fd >= 0)
-		return dso->data.fd;
+		goto out;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
-		return dso->data.fd;
+		goto out;
 	}
 
 	do {
-		int fd;
-
 		dso->binary_type = binary_type_data[i++];
 
-		fd = open_dso(dso, machine);
-		if (fd >= 0)
-			return dso->data.fd = fd;
+		dso->data.fd = open_dso(dso, machine);
+		if (dso->data.fd >= 0)
+			goto out;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+out:
+	if (dso->data.fd >= 0)
+		dso->data.status = DSO_DATA_STATUS_OK;
+	else
+		dso->data.status = DSO_DATA_STATUS_ERROR;
 
-	return -EINVAL;
+	return dso->data.fd;
+}
+
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
+{
+	u32 flag = 1 << by;
+
+	if (dso->data.status_seen & flag)
+		return true;
+
+	dso->data.status_seen |= flag;
+
+	return false;
 }
 
 static void
@@ -526,6 +544,28 @@ static int data_file_size(struct dso *dso)
 	return 0;
 }
 
+/**
+ * dso__data_size - Return dso data size
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * Return: dso data size
+ */
+off_t dso__data_size(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return fd;
+
+	if (data_file_size(dso))
+		return -1;
+
+	/* For now just estimate dso data size is close to file size */
+	return dso->data.file_size;
+}
+
 static ssize_t data_read_offset(struct dso *dso, u64 offset,
 				u8 *data, ssize_t size)
 {
@@ -701,6 +741,7 @@ struct dso *dso__new(const char *name)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->data.cache = RB_ROOT;
 		dso->data.fd = -1;
+		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->is_64_bit = (sizeof(void *) == 8);
@@ -899,3 +940,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 
 	return ret;
 }
+
+enum dso_type dso__type(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return DSO__TYPE_UNKNOWN;
+
+	return dso__type_fd(fd);
+}