Merge branch 'perf/urgent' into perf/core

Merge reason: we'll be queueing up dependent changes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

18 files changed, 181 insertions, 117 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 158c30e..207dee5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -165,8 +165,12 @@ grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
-	$(QUIET_GEN)python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
-						--build-temp='$(OUTPUT)python/temp'
+	$(QUIET_GEN)( \
+		export CFLAGS="$(BASIC_CFLAGS)"; \
+		python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
+			--build-temp='$(OUTPUT)python/temp' \
+	)
+
 #
 # No Perl scripts right now:
 #
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index db6adec..4165382 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,7 +41,7 @@ static u64			user_interval			= ULLONG_MAX;
 static u64			default_interval		=      0;
 
 static unsigned int		page_size;
-static unsigned int		mmap_pages			=    128;
+static unsigned int		mmap_pages			= UINT_MAX;
 static unsigned int		user_freq 			= UINT_MAX;
 static int			freq				=   1000;
 static int			output;
@@ -163,6 +163,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
 				  PERF_FORMAT_ID;
@@ -251,6 +252,9 @@ static void open_counters(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
+	if (evlist->cpus->map[0] < 0)
+		no_inherit = true;
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
 		/*
@@ -271,8 +275,7 @@ static void open_counters(struct perf_evlist *evlist)
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
-				     !no_inherit) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
@@ -513,6 +516,10 @@ static int __cmd_record(int argc, const char **argv)
 	if (have_tracepoints(&evsel_list->entries))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
+	/* 512 kiB: default amount of unprivileged mlocked memory */
+	if (mmap_pages == UINT_MAX)
+		mmap_pages = (512 * 1024) / page_size;
+
 	if (forks) {
 		child_pid = fork();
 		if (child_pid < 0) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e2109f9..03f0e45 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -167,16 +167,17 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
+	attr->inherit = !no_inherit;
+
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
 
-	attr->inherit = !no_inherit;
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c..11e3c84 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -303,7 +303,7 @@ static int test__open_syscall_event(void)
 	}
 
 	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-		pr_debug("perf_evsel__open_read_on_cpu\n");
+		pr_debug("perf_evsel__read_on_cpu\n");
 		goto out_close_fd;
 	}
 
@@ -365,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -418,7 +418,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 			continue;
 
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-			pr_debug("perf_evsel__open_read_on_cpu\n");
+			pr_debug("perf_evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
@@ -529,7 +529,7 @@ static int test__basic_mmap(void)
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fc1273e..7e3d6e3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -845,9 +845,10 @@ static void start_counters(struct perf_evlist *evlist)
 		}
 
 		attr->mmap = 1;
+		attr->inherit = inherit;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group, inherit) < 0) {
+				     top.evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 9fea755..96bee5c 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 {
 	FILE *fp;
 	char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
-	char *token, *saved_ptr;
+	char *token, *saved_ptr = NULL;
 	int found = 0;
 
 	fp = fopen("/proc/mounts", "r");
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cef..45da8d1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
+#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -250,15 +251,19 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-			       int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			       int cpu, int prot, int mask, int fd)
 {
 	evlist->mmap[cpu].prev = 0;
 	evlist->mmap[cpu].mask = mask;
 	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED)
+	if (evlist->mmap[cpu].base == MAP_FAILED) {
+		if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit)
+			ui__warning("Inherit is not allowed on per-task "
+				    "events using mmap.\n");
 		return -1;
+	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -312,7 +317,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
 						  FD(first_evsel, cpu, 0)) != 0)
 						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+				} else if (__perf_evlist__mmap(evlist, evsel, cpu,
+							       prot, mask, fd) < 0)
 					goto out_unmap;
 
 				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596a..d6fd59b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -175,7 +175,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group, bool inherit)
+			      struct thread_map *threads, bool group)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -192,19 +192,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		int group_fd = -1;
-		/*
-		 * Don't allow mmap() of inherited per-task counters. This
-		 * would create a performance issue due to all children writing
-		 * to the same buffer.
-		 *
-		 * FIXME:
-		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-		 * but a 'flags' parameter, with 'group' folded there as well,
-		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-		 * set. Lets go for the minimal fix first tho.
-		 */
-		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +240,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit)
+		     struct thread_map *threads, bool group)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +250,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+	return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit)
+			     struct cpu_map *cpus, bool group)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit)
+				struct thread_map *threads, bool group)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab5..f79bb2c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit);
+			     struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit);
+				struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit);
+		     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5ddee66..f022316 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -234,7 +234,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	/* Searching trace events corresponding to probe event */
 	ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs);
-	close(fd);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("find %d probe_trace_events.\n", ntevs);
@@ -388,7 +387,6 @@ int show_line_range(struct line_range *lr, const char *module)
 	}
 
 	ret = find_line_range(fd, lr);
-	close(fd);
 	if (ret == 0) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
@@ -512,19 +510,18 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	fd = open_vmlinux(module);
-	if (fd < 0) {
-		pr_warning("Failed to open debug information file.\n");
-		return fd;
-	}
-
 	setup_pager();
 
-	for (i = 0; i < npevs && ret >= 0; i++)
+	for (i = 0; i < npevs && ret >= 0; i++) {
+		fd = open_vmlinux(module);
+		if (fd < 0) {
+			pr_warning("Failed to open debug information file.\n");
+			ret = fd;
+			break;
+		}
 		ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
 					     externs);
-
-	close(fd);
+	}
 	return ret;
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ff416b8..a7c7145 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -273,6 +273,25 @@ static const char *cu_get_comp_dir(Dwarf_Die *cu_die)
 	return dwarf_formstring(&attr);
 }
 
+/* Get a line number and file name for given address */
+static int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+			    const char **fname, int *lineno)
+{
+	Dwarf_Line *line;
+	Dwarf_Addr laddr;
+
+	line = dwarf_getsrc_die(cudie, (Dwarf_Addr)addr);
+	if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+	    addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+		*fname = dwarf_linesrc(line, NULL, NULL);
+		if (!*fname)
+			/* line number is useless without filename */
+			*lineno = 0;
+	}
+
+	return *lineno ?: -ENOENT;
+}
+
 /* Compare diename and tname */
 static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
@@ -497,7 +516,20 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 				      Dwarf_Die *die_mem)
 {
-	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+	Dwarf_Die tmp_die;
+
+	sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+	if (!sp_die)
+		return NULL;
+
+	/* Inlined function could be recursive. Trace it until fail */
+	while (sp_die) {
+		memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+		sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+					&tmp_die);
+	}
+
+	return die_mem;
 }
 
 /* Walker on lines (Note: line number will not be sorted) */
@@ -1395,6 +1427,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	    !die_compare_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
+	/* Check declared file */
+	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -1483,6 +1519,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 
@@ -1741,11 +1778,9 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 	Dwarf_Die cudie, spdie, indie;
 	Dwarf *dbg = NULL;
 	Dwfl *dwfl = NULL;
-	Dwarf_Line *line;
-	Dwarf_Addr laddr, eaddr, bias = 0;
-	const char *tmp;
-	int lineno, ret = 0;
-	bool found = false;
+	Dwarf_Addr _addr, baseaddr, bias = 0;
+	const char *fname = NULL, *func = NULL, *tmp;
+	int baseline = 0, lineno = 0, ret = 0;
 
 	/* Open the live linux kernel */
 	dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
@@ -1766,68 +1801,79 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 		goto end;
 	}
 
-	/* Find a corresponding line */
-	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
-	if (line) {
-		if (dwarf_lineaddr(line, &laddr) == 0 &&
-		    (Dwarf_Addr)addr == laddr &&
-		    dwarf_lineno(line, &lineno) == 0) {
-			tmp = dwarf_linesrc(line, NULL, NULL);
-			if (tmp) {
-				ppt->line = lineno;
-				ppt->file = strdup(tmp);
-				if (ppt->file == NULL) {
-					ret = -ENOMEM;
-					goto end;
-				}
-				found = true;
-			}
-		}
-	}
+	/* Find a corresponding line (filename and lineno) */
+	cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+	/* Don't care whether it failed or not */
 
-	/* Find a corresponding function */
+	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		/* Get function entry information */
 		tmp = dwarf_diename(&spdie);
-		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
-			goto end;
-
-		if (ppt->line) {
-			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-						&indie)) {
-				/* addr in an inline function */
+		if (!tmp ||
+		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+		    dwarf_decl_line(&spdie, &baseline) != 0)
+			goto post;
+		func = tmp;
+
+		if (addr == (unsigned long)baseaddr)
+			/* Function entry - Relative line number is 0 */
+			lineno = baseline;
+		else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+					     &indie)) {
+			if (dwarf_entrypc(&indie, &_addr) == 0 &&
+			    _addr == addr)
+				/*
+				 * addr is at an inline function entry.
+				 * In this case, lineno should be the call-site
+				 * line number.
+				 */
+				lineno = die_get_call_lineno(&indie);
+			else {
+				/*
+				 * addr is in an inline function body.
+				 * Since lineno points one of the lines
+				 * of the inline function, baseline should
+				 * be the entry line of the inline function.
+				 */
 				tmp = dwarf_diename(&indie);
-				if (!tmp)
-					goto end;
-				ret = dwarf_decl_line(&indie, &lineno);
-			} else {
-				if (eaddr == addr) {	/* Function entry */
-					lineno = ppt->line;
-					ret = 0;
-				} else
-					ret = dwarf_decl_line(&spdie, &lineno);
-			}
-			if (ret == 0) {
-				/* Make a relative line number */
-				ppt->line -= lineno;
-				goto found;
+				if (tmp &&
+				    dwarf_decl_line(&spdie, &baseline) == 0)
+					func = tmp;
 			}
 		}
-		/* We don't have a line number, let's use offset */
-		ppt->offset = addr - (unsigned long)eaddr;
-found:
-		ppt->function = strdup(tmp);
+	}
+
+post:
+	/* Make a relative line number or an offset */
+	if (lineno)
+		ppt->line = lineno - baseline;
+	else if (func)
+		ppt->offset = addr - (unsigned long)baseaddr;
+
+	/* Duplicate strings */
+	if (func) {
+		ppt->function = strdup(func);
 		if (ppt->function == NULL) {
 			ret = -ENOMEM;
 			goto end;
 		}
-		found = true;
 	}
-
+	if (fname) {
+		ppt->file = strdup(fname);
+		if (ppt->file == NULL) {
+			if (ppt->function) {
+				free(ppt->function);
+				ppt->function = NULL;
+			}
+			ret = -ENOMEM;
+			goto end;
+		}
+	}
 end:
 	if (dwfl)
 		dwfl_end(dwfl);
-	if (ret >= 0)
-		ret = found ? 1 : 0;
+	if (ret == 0 && (fname || func))
+		ret = 1;	/* Found a point */
 	return ret;
 }
 
@@ -1895,6 +1941,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
+	/* Check declared file */
+	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
@@ -1947,6 +1997,7 @@ int find_line_range(int fd, struct line_range *lr)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e..f5e3845 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	struct cpu_map *cpus = NULL;
 	struct thread_map *threads = NULL;
 	PyObject *pcpus = NULL, *pthreads = NULL;
-	int group = 0, overwrite = 0;
-	static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+	int group = 0, inherit = 0;
+	static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
-					 &pcpus, &pthreads, &group, &overwrite))
+					 &pcpus, &pthreads, &group, &inherit))
 		return NULL;
 
 	if (pthreads != NULL)
@@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	if (pcpus != NULL)
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-	if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+	evsel->attr.inherit = inherit;
+	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index e24ffad..bbc982f 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,13 +1,18 @@
 #!/usr/bin/python2
 
 from distutils.core import setup, Extension
+from os import getenv
+
+cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags += getenv('CFLAGS', '').split()
 
 perf = Extension('perf',
 		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
 			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
 			     'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
 		  include_dirs = ['util/include'],
-		  extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+		  extra_compile_args = cflags,
+                 )
 
 setup(name='perf',
       version='0.1',
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 8fc0bd3..b9a985d 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -85,7 +85,7 @@ out:
 
 /*
  * Helper function for splitting a string into an argv-like array.
- * originaly copied from lib/argv_split.c
+ * originally copied from lib/argv_split.c
  */
 static const char *skip_sep(const char *cp)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8f73907..f06c10f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2406,6 +2406,8 @@ int symbol__init(void)
 	if (symbol_conf.initialized)
 		return 0;
 
+	symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+
 	elf_version(EV_CURRENT);
 	if (symbol_conf.sort_by_name)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a87..15633d6 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -256,10 +256,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int refresh)
 {
 	struct objdump_line *pos, *n;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes;
 	struct annotate_browser browser = {
 		.b = {
-			.entries = &notes->src->source,
 			.refresh = ui_browser__list_head_refresh,
 			.seek	 = ui_browser__list_head_seek,
 			.write	 = annotate_browser__write,
@@ -281,6 +280,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
 	ui_helpline__push("Press <- or ESC to exit");
 
+	notes = symbol__annotation(sym);
+
 	list_for_each_entry(pos, &notes->src->source, node) {
 		struct objdump_line_rb_node *rbpos;
 		size_t line_len = strlen(pos->line);
@@ -291,6 +292,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		rbpos->idx = browser.b.nr_entries++;
 	}
 
+	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 	ret = annotate_browser__run(&browser, evidx, refresh);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdc..5d767c6 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel,
 			goto out_free_stack;
 		case 'a':
 			if (browser->selection == NULL ||
-			    browser->selection->map == NULL ||
+			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index d9678a3..2618ef2 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -46,7 +46,7 @@ int cpu = -1;
  *
  *  performance
  *	Performance is paramount.
- *	Unwilling to sacrafice any performance
+ *	Unwilling to sacrifice any performance
  *	for the sake of energy saving. (hardware default)
  *
  *  normal