Merge tag 'perf-core-for-mingo-20160323' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes:

User visible fixes:

 - Fix documentation of :ppp modifier in 'perf list' (Andi Kleen)

 - Fix silly nodes bitfield bits/bytes length assertion in 'perf bench numa' (Jakub Jelen)

 - Remove redundant CPU output in libtraceevent (Steven Rostedt)

 - Remove 'core_id' check in topology 'perf test' (Sukadev Bhattiprolu)

Infrastructure changes/fixes:

 - Record text offset in dso to calculate objdump address, to use with
   modules in addition to vDSO symbol address calculations (Wang Nan)

 - Move utilities.mak from perf to tools/scripts/ (Arnaldo Carvalho de Melo)

 - Add cpumode to the perf_sample struct, this way we don't need to pass
   the union event to the machine and thread resolving routines, shortening
   function signatures and allowing the future introduction of a way
   to use tracepoint events instead of the unavailable HW cycles counter on
   powerpc guests in perf kvm by just hooking on perf_evsel__parse_sample,
   at the end (Arnaldo Carvalho de Melo)

 - Remove/unexport die() related infrastructure, that at some point will
   finally be removed (Arnaldo Carvalho de Melo)

 - Adopt linux/stringify.h from the kernel sources, not to touch this
   kernel header from tools/ (Arnaldo Carvalho de Melo)

 - Stop using strbuf for things we can instead trivially use libc's asprintf()
   (Arnaldo Carvalho de Melo)

 - Ditch tools/lib/util/abspath.c, its only exported function was used at just
   one place and can be replaced by libc's realpath() (Arnaldo Carvalho de Melo)

 - Use strerror_r() in the llvm infrastructure, tread safe, its what is used
   elsewhere in tools/perf/ (Arnaldo Carvalho de Melo)

Cleanups:

 - Removed misplaced or needless __maybe_unused/export (Arnaldo Carvalho de Melo)

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

tools/include/linux/stringify.h

@@ -0,0 +1,12 @@
+#ifndef __LINUX_STRINGIFY_H
+#define __LINUX_STRINGIFY_H
+
+/* Indirect stringification.  Doing two levels allows the parameter to be a
+ * macro itself.  For example, compile with -DFOO=bar, __stringify(FOO)
+ * converts to "bar".
+ */
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#endif	/* !__LINUX_STRINGIFY_H */

tools/lib/api/Makefile

@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../../perf/config/utilities.mak		# QUIET_CLEAN
+include ../../scripts/utilities.mak		# QUIET_CLEAN
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))

tools/lib/subcmd/Makefile

@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../../perf/config/utilities.mak		# QUIET_CLEAN
+include ../../scripts/utilities.mak		# QUIET_CLEAN
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))

tools/lib/traceevent/event-parse.c

@@ -5427,10 +5427,8 @@ void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
 	}
 
 	if (pevent->latency_format) {
-		trace_seq_printf(s, " %3d", record->cpu);
 		pevent_data_lat_fmt(pevent, s, record);
-	} else
-		trace_seq_printf(s, " [%03d]", record->cpu);
+	}
 
 	if (use_usec_format) {
 		if (pevent->flags & PEVENT_NSEC_OUTPUT) {

tools/perf/Documentation/Makefile

@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../config/utilities.mak
+include ../../scripts/utilities.mak
 
 MAN1_TXT= \
 	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \

tools/perf/Documentation/perf-list.txt

@@ -40,10 +40,12 @@ address should be. The 'p' modifier can be specified multiple times:
  0 - SAMPLE_IP can have arbitrary skid
  1 - SAMPLE_IP must have constant skid
  2 - SAMPLE_IP requested to have 0 skid
- 3 - SAMPLE_IP must have 0 skid
+ 3 - SAMPLE_IP must have 0 skid, or uses randomization to avoid
+     sample shadowing effects.
 
 For Intel systems precise event sampling is implemented with PEBS
-which supports up to precise-level 2.
+which supports up to precise-level 2, and precise level 3 for
+some special cases
 
 On AMD systems it is implemented using IBS (up to precise-level 2).
 The precise modifier works with event types 0x76 (cpu-cycles, CPU

tools/perf/Makefile.perf

@@ -3,7 +3,7 @@ include ../scripts/Makefile.include
 # The default target of this Makefile is...
 all:
 
-include config/utilities.mak
+include ../scripts/utilities.mak
 
 # Define V to have a more verbose compile.
 #

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

@@ -3,9 +3,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-
-#include "../../util/header.h"
-#include "../../util/util.h"
+#include <linux/stringify.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \

tools/perf/bench/bench.h

@@ -25,19 +25,17 @@
 # endif
 #endif
 
-extern int bench_numa(int argc, const char **argv, const char *prefix);
-extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-extern int bench_mem_memcpy(int argc, const char **argv,
-			    const char *prefix __maybe_unused);
-extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
-extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
-extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
-extern int bench_futex_wake_parallel(int argc, const char **argv,
-				     const char *prefix);
-extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv, const char *prefix);
+int bench_sched_messaging(int argc, const char **argv, const char *prefix);
+int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
+int bench_mem_memset(int argc, const char **argv, const char *prefix);
+int bench_futex_hash(int argc, const char **argv, const char *prefix);
+int bench_futex_wake(int argc, const char **argv, const char *prefix);
+int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
+int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 /* pi futexes */
-extern int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0

tools/perf/bench/mem-memcpy-arch.h

@@ -2,7 +2,7 @@
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc)		\
-	extern void *fn(void *, const void *, size_t);
+	void *fn(void *, const void *, size_t);
 
 #include "mem-memcpy-x86-64-asm-def.h"
 

tools/perf/bench/mem-memset-arch.h

@@ -2,7 +2,7 @@
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc)		\
-	extern void *fn(void *, int, size_t);
+	void *fn(void *, int, size_t);
 
 #include "mem-memset-x86-64-asm-def.h"
 

tools/perf/bench/numa.c

@@ -293,7 +293,7 @@ static void bind_to_memnode(int node)
 	if (node == -1)
 		return;
 
-	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask));
+	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
 	nodemask = 1L << node;
 
 	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);

tools/perf/builtin-annotate.c

@@ -94,7 +94,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct addr_location al;
 	int ret = 0;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;

tools/perf/builtin-diff.c

@@ -330,7 +330,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	struct hists *hists = evsel__hists(evsel);
 	int ret = -1;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;

tools/perf/builtin-help.c

@@ -106,12 +106,14 @@ static void exec_woman_emacs(const char *path, const char *page)
 
 	if (!check_emacsclient_version()) {
 		/* This works only with emacsclient version >= 22. */
-		struct strbuf man_page = STRBUF_INIT;
+		char *man_page;
 
 		if (!path)
 			path = "emacsclient";
-		strbuf_addf(&man_page, "(woman \"%s\")", page);
-		execlp(path, "emacsclient", "-e", man_page.buf, NULL);
+		if (asprintf(&man_page, "(woman \"%s\")", page) > 0) {
+			execlp(path, "emacsclient", "-e", man_page, NULL);
+			free(man_page);
+		}
 		warning("failed to exec '%s': %s", path,
 			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
@@ -122,7 +124,7 @@ static void exec_man_konqueror(const char *path, const char *page)
 	const char *display = getenv("DISPLAY");
 
 	if (display && *display) {
-		struct strbuf man_page = STRBUF_INIT;
+		char *man_page;
 		const char *filename = "kfmclient";
 		char sbuf[STRERR_BUFSIZE];
 
@@ -141,8 +143,10 @@ static void exec_man_konqueror(const char *path, const char *page)
 				filename = file;
 		} else
 			path = "kfmclient";
-		strbuf_addf(&man_page, "man:%s(1)", page);
-		execlp(path, filename, "newTab", man_page.buf, NULL);
+		if (asprintf(&man_page, "man:%s(1)", page) > 0) {
+			execlp(path, filename, "newTab", man_page, NULL);
+			free(man_page);
+		}
 		warning("failed to exec '%s': %s", path,
 			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
@@ -161,11 +165,13 @@ static void exec_man_man(const char *path, const char *page)
 
 static void exec_man_cmd(const char *cmd, const char *page)
 {
-	struct strbuf shell_cmd = STRBUF_INIT;
 	char sbuf[STRERR_BUFSIZE];
+	char *shell_cmd;
 
-	strbuf_addf(&shell_cmd, "%s %s", cmd, page);
-	execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
+	if (asprintf(&shell_cmd, "%s %s", cmd, page) > 0) {
+		execl("/bin/sh", "sh", "-c", shell_cmd, NULL);
+		free(shell_cmd);
+	}
 	warning("failed to exec '%s': %s", cmd,
 		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
@@ -299,43 +305,33 @@ static int is_perf_command(const char *s)
 		is_in_cmdlist(&other_cmds, s);
 }
 
-static const char *prepend(const char *prefix, const char *cmd)
-{
-	size_t pre_len = strlen(prefix);
-	size_t cmd_len = strlen(cmd);
-	char *p = malloc(pre_len + cmd_len + 1);
-	memcpy(p, prefix, pre_len);
-	strcpy(p + pre_len, cmd);
-	return p;
-}
-
 static const char *cmd_to_page(const char *perf_cmd)
 {
+	char *s;
+
 	if (!perf_cmd)
 		return "perf";
 	else if (!prefixcmp(perf_cmd, "perf"))
 		return perf_cmd;
-	else
-		return prepend("perf-", perf_cmd);
+
+	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
 }
 
 static void setup_man_path(void)
 {
-	struct strbuf new_path = STRBUF_INIT;
+	char *new_path;
 	const char *old_path = getenv("MANPATH");
 
 	/* We should always put ':' after our path. If there is no
 	 * old_path, the ':' at the end will let 'man' to try
 	 * system-wide paths after ours to find the manual page. If
 	 * there is old_path, we need ':' as delimiter. */
-	strbuf_addstr(&new_path, system_path(PERF_MAN_PATH));
-	strbuf_addch(&new_path, ':');
-	if (old_path)
-		strbuf_addstr(&new_path, old_path);
-
-	setenv("MANPATH", new_path.buf, 1);
-
-	strbuf_release(&new_path);
+	if (asprintf(&new_path, "%s:%s", system_path(PERF_MAN_PATH), old_path ?: "") > 0) {
+		setenv("MANPATH", new_path, 1);
+		free(new_path);
+	} else {
+		error("Unable to setup man path");
+	}
 }
 
 static void exec_viewer(const char *name, const char *page)
@@ -380,7 +376,7 @@ static int show_info_page(const char *perf_cmd)
 	return -1;
 }
 
-static int get_html_page_path(struct strbuf *page_path, const char *page)
+static int get_html_page_path(char **page_path, const char *page)
 {
 	struct stat st;
 	const char *html_path = system_path(PERF_HTML_PATH);
@@ -392,10 +388,7 @@ static int get_html_page_path(struct strbuf *page_path, const char *page)
 		return -1;
 	}
 
-	strbuf_init(page_path, 0);
-	strbuf_addf(page_path, "%s/%s.html", html_path, page);
-
-	return 0;
+	return asprintf(page_path, "%s/%s.html", html_path, page);
 }
 
 /*
@@ -413,12 +406,12 @@ static void open_html(const char *path)
 static int show_html_page(const char *perf_cmd)
 {
 	const char *page = cmd_to_page(perf_cmd);
-	struct strbuf page_path; /* it leaks but we exec bellow */
+	char *page_path; /* it leaks but we exec bellow */
 
-	if (get_html_page_path(&page_path, page) != 0)
+	if (get_html_page_path(&page_path, page) < 0)
 		return -1;
 
-	open_html(page_path.buf);
+	open_html(page_path);
 
 	return 0;
 }

tools/perf/builtin-inject.c

@@ -131,8 +131,7 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
 
 static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+				       struct perf_session *session)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
@@ -417,9 +416,6 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 {
 	struct addr_location al;
 	struct thread *thread;
-	u8 cpumode;
-
-	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL) {
@@ -428,7 +424,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {

tools/perf/builtin-mem.c

@@ -131,7 +131,7 @@ dump_raw_samples(struct perf_tool *tool,
 	struct addr_location al;
 	const char *fmt;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 				event->header.type);
 		return -1;

tools/perf/builtin-report.c

@@ -41,6 +41,7 @@
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
+#include <linux/stringify.h>
 
 struct report {
 	struct perf_tool	tool;
@@ -154,7 +155,7 @@ static int process_sample_event(struct perf_tool *tool,
 	};
 	int ret = 0;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
 		return -1;

tools/perf/builtin-script.c

@@ -405,9 +405,7 @@ out:
 	return 0;
 }
 
-static void print_sample_iregs(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
+static void print_sample_iregs(struct perf_sample *sample,
 			  struct perf_event_attr *attr)
 {
 	struct regs_dump *regs = &sample->intr_regs;
@@ -476,10 +474,7 @@ mispred_str(struct branch_entry *br)
 	return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
-			  struct perf_event_attr *attr __maybe_unused)
+static void print_sample_brstack(struct perf_sample *sample)
 {
 	struct branch_stack *br = sample->branch_stack;
 	u64 i;
@@ -498,14 +493,11 @@ static void print_sample_brstack(union perf_event *event __maybe_unused,
 	}
 }
 
-static void print_sample_brstacksym(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
-			  struct perf_event_attr *attr __maybe_unused)
+static void print_sample_brstacksym(struct perf_sample *sample,
+				    struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
 	struct addr_location alf, alt;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	u64 i, from, to;
 
 	if (!(br && br->nr))
@@ -518,11 +510,11 @@ static void print_sample_brstacksym(union perf_event *event __maybe_unused,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, from, &alf);
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
 		if (alf.map)
 			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
 
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, to, &alt);
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		if (alt.map)
 			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
 
@@ -538,8 +530,7 @@ static void print_sample_brstacksym(union perf_event *event __maybe_unused,
 }
 
 
-static void print_sample_addr(union perf_event *event,
-			  struct perf_sample *sample,
+static void print_sample_addr(struct perf_sample *sample,
 			  struct thread *thread,
 			  struct perf_event_attr *attr)
 {
@@ -550,7 +541,7 @@ static void print_sample_addr(union perf_event *event,
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	perf_event__preprocess_sample_addr(event, sample, thread, &al);
+	thread__resolve(thread, &al, sample);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -567,8 +558,7 @@ static void print_sample_addr(union perf_event *event,
 	}
 }
 
-static void print_sample_bts(union perf_event *event,
-			     struct perf_sample *sample,
+static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
 			     struct addr_location *al)
@@ -598,7 +588,7 @@ static void print_sample_bts(union perf_event *event,
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	     !output[attr->type].user_set)) {
 		printf(" => ");
-		print_sample_addr(event, sample, thread, attr);
+		print_sample_addr(sample, thread, attr);
 	}
 
 	if (print_srcline_last)
@@ -747,7 +737,7 @@ static size_t data_src__printf(u64 data_src)
 	return printf("%-*s", maxlen, out);
 }
 
-static void process_event(struct perf_script *script, union perf_event *event,
+static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al)
 {
@@ -776,7 +766,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, thread, al);
+		print_sample_bts(sample, evsel, thread, al);
 		return;
 	}
 
@@ -784,7 +774,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
 	if (PRINT_FIELD(ADDR))
-		print_sample_addr(event, sample, thread, attr);
+		print_sample_addr(sample, thread, attr);
 
 	if (PRINT_FIELD(DATA_SRC))
 		data_src__printf(sample->data_src);
@@ -804,12 +794,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	}
 
 	if (PRINT_FIELD(IREGS))
-		print_sample_iregs(event, sample, thread, attr);
+		print_sample_iregs(sample, attr);
 
 	if (PRINT_FIELD(BRSTACK))
-		print_sample_brstack(event, sample, thread, attr);
+		print_sample_brstack(sample);
 	else if (PRINT_FIELD(BRSTACKSYM))
-		print_sample_brstacksym(event, sample, thread, attr);
+		print_sample_brstacksym(sample, thread);
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
@@ -905,7 +895,7 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 	}
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
 		return -1;
@@ -920,7 +910,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, event, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al);
 
 out_put:
 	addr_location__put(&al);

tools/perf/builtin-timechart.c

@@ -489,7 +489,7 @@ static const char *cat_backtrace(union perf_event *event,
 	if (!chain)
 		goto exit;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 			event->header.type);
 		goto exit;