24 files changed, 271 insertions, 120 deletions

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 31f934af9861..a91cd99f26ea 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -16,6 +16,7 @@
 
 static int build_id__mark_dso_hit(union perf_event *event,
 				  struct perf_sample *sample __used,
+				  struct perf_evsel *evsel __used,
 				  struct perf_session *session)
 {
 	struct addr_location al;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 9fea75535221..96bee5c46008 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/debug.c b/tools/perf/util/debug.c
index d4536a9e0d8c..155749d74350 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -57,6 +57,16 @@ void ui__warning(const char *format, ...)
 }
 #endif
 
+void ui__warning_paranoid(void)
+{
+	ui__warning("Permission error - are you root?\n"
+		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+		    " -1 - Not paranoid at all\n"
+		    "  0 - Disallow raw tracepoint access for unpriv\n"
+		    "  1 - Disallow cpu events for unpriv\n"
+		    "  2 - Disallow kernel profiling for unpriv\n");
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 93516cf4682c..fd53db47e3de 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -36,5 +36,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #endif
 
 void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+void ui__warning_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2b15c362ef56..1023f67633a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -710,7 +710,7 @@ try_again:
 		 * in the whole kernel symbol list.
 		 */
 		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
 			goto try_again;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cefa20de..45da8d186b49 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 662596afd7f1..d6fd59beb860 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 6710ab538342..f79bb2c09a6c 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/header.c b/tools/perf/util/header.c
index e5230c0ef95b..93862a8027ea 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -695,13 +695,50 @@ out:
 	return err;
 }
 
+static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
+						 int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct {
+		struct perf_event_header   header;
+		u8			   build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+		char			   filename[0];
+	} old_bev;
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+			return -1;
+
+		if (header->needs_swap)
+			perf_event_header__bswap(&old_bev.header);
+
+		len = old_bev.header.size - sizeof(old_bev);
+		if (read(input, filename, len) != len)
+			return -1;
+
+		bev.header = old_bev.header;
+		bev.pid	   = 0;
+		memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+
+	return 0;
+}
+
 static int perf_header__read_build_ids(struct perf_header *header,
 				       int input, u64 offset, u64 size)
 {
 	struct perf_session *session = container_of(header, struct perf_session, header);
 	struct build_id_event bev;
 	char filename[PATH_MAX];
-	u64 limit = offset + size;
+	u64 limit = offset + size, orig_offset = offset;
 	int err = -1;
 
 	while (offset < limit) {
@@ -716,6 +753,24 @@ static int perf_header__read_build_ids(struct perf_header *header,
 		len = bev.header.size - sizeof(bev);
 		if (read(input, filename, len) != len)
 			goto out;
+		/*
+		 * The a1645ce1 changeset:
+		 *
+		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
+		 *
+		 * Added a field to struct build_id_event that broke the file
+		 * format.
+		 *
+		 * Since the kernel build-id is the first entry, process the
+		 * table using the old format if the well known
+		 * '[kernel.kallsyms]' string for the kernel build-id has the
+		 * first 4 characters chopped off (where the pid_t sits).
+		 */
+		if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
+			if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
+				return -1;
+			return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
+		}
 
 		__event_process_build_id(&bev, filename, session);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index cb6858a2f9a3..3beb97c4d822 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -29,6 +29,7 @@ struct events_stats {
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_unknown_events;
 	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5ddee66020a7..f0223166e761 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 194f9e2a3285..b7c85ce466a1 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);
@@ -1451,6 +1487,7 @@ 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;
 	}
 
@@ -1686,11 +1723,9 @@ 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);
@@ -1711,68 +1746,79 @@ 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;
 }
 
@@ -1840,6 +1886,10 @@ 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);
@@ -1892,6 +1942,7 @@ 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 a9f2d7e1204d..f5e38451fdc5 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/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 621427212e86..74350ffb57fe 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -247,6 +247,7 @@ static inline struct event *find_cache_event(int type)
 
 static void perl_process_event(union perf_event *pevent __unused,
 			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
 			       struct perf_session *session __unused,
 			       struct thread *thread)
 {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 1b85d6055159..6ccf70e8d8f2 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -206,6 +206,7 @@ static inline struct event *find_cache_event(int type)
 
 static void python_process_event(union perf_event *pevent __unused,
 				 struct perf_sample *sample,
+				 struct perf_evsel *evsel __unused,
 				 struct perf_session *session __unused,
 				 struct thread *thread)
 {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c68cf40764f9..caa224522fea 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -280,6 +280,15 @@ static int process_event_synth_stub(union perf_event *event __used,
 	return 0;
 }
 
+static int process_event_sample_stub(union perf_event *event __used,
+				     struct perf_sample *sample __used,
+				     struct perf_evsel *evsel __used,
+				     struct perf_session *session __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_stub(union perf_event *event __used,
 			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
@@ -303,7 +312,7 @@ static int process_finished_round(union perf_event *event,
 static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 {
 	if (handler->sample == NULL)
-		handler->sample = process_event_stub;
+		handler->sample = process_event_sample_stub;
 	if (handler->mmap == NULL)
 		handler->mmap = process_event_stub;
 	if (handler->comm == NULL)
@@ -698,12 +707,19 @@ static int perf_session_deliver_event(struct perf_session *session,
 				      struct perf_event_ops *ops,
 				      u64 file_offset)
 {
+	struct perf_evsel *evsel;
+
 	dump_event(session, event, file_offset, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(session, event, sample);
-		return ops->sample(event, sample, session);
+		evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+		if (evsel == NULL) {
+			++session->hists.stats.nr_unknown_id;
+			return -1;
+		}
+		return ops->sample(event, sample, evsel, session);
 	case PERF_RECORD_MMAP:
 		return ops->mmap(event, sample, session);
 	case PERF_RECORD_COMM:
@@ -845,6 +861,11 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 			    session->hists.stats.nr_unknown_events);
 	}
 
+	if (session->hists.stats.nr_unknown_id != 0) {
+		ui__warning("%u samples with id not present in the header\n",
+			    session->hists.stats.nr_unknown_id);
+	}
+
  	if (session->hists.stats.nr_invalid_chains != 0) {
  		ui__warning("Found invalid callchains!\n\n"
  			    "%u out of %u events were discarded for this reason.\n\n"
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0b3c9afecaa9..1ac481fc1100 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -55,8 +55,11 @@ struct perf_session {
 	char			filename[0];
 };
 
+struct perf_evsel;
 struct perf_event_ops;
 
+typedef int (*event_sample)(union perf_event *event, struct perf_sample *sample,
+			    struct perf_evsel *evsel, struct perf_session *session);
 typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
 			struct perf_session *session);
 typedef int (*event_synth_op)(union perf_event *self,
@@ -65,8 +68,8 @@ typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
 			 struct perf_event_ops *ops);
 
 struct perf_event_ops {
-	event_op	sample,
-			mmap,
+	event_sample	sample;
+	event_op	mmap,
 			comm,
 			fork,
 			exit,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index e24ffadb20b2..bbc982f5dd8b 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 8fc0bd3a3a4a..b9a985dadd08 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 651dbfe7f4f3..f06c10f092ba 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1196,6 +1196,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				if (curr_dso == NULL)
 					goto out_elf_end;
 				curr_dso->kernel = self->kernel;
+				curr_dso->long_name = self->long_name;
+				curr_dso->long_name_len = self->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1486,7 +1488,9 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
-	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE, want_symtab = 1;
+	want_symtab = 1;
+restart:
+	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE;
 	     self->symtab_type != SYMTAB__NOT_FOUND;
 	     self->symtab_type++) {
 		switch (self->symtab_type) {
@@ -1536,17 +1540,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 			snprintf(name, size, "%s%s", symbol_conf.symfs,
 				 self->long_name);
 			break;
-
-		default:
-			/*
-			 * If we wanted a full symtab but no image had one,
-			 * relax our requirements and repeat the search.
-			 */
-			if (want_symtab) {
-				want_symtab = 0;
-				self->symtab_type = SYMTAB__BUILD_ID_CACHE;
-			} else
-				continue;
+		default:;
 		}
 
 		/* Name is now the name of the next image to try */
@@ -1573,6 +1567,15 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 		}
 	}
 
+	/*
+	 * If we wanted a full symtab but no image had one,
+	 * relax our requirements and repeat the search.
+	 */
+	if (ret <= 0 && want_symtab) {
+		want_symtab = 0;
+		goto restart;
+	}
+
 	free(name);
 	if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
 		return 0;
@@ -1841,6 +1844,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	if (fd < 0)
 		return -1;
 
+	dso__set_long_name(self, (char *)vmlinux);
 	dso__set_loaded(self, map->type);
 	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
@@ -2402,6 +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/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 66f4b78737ab..c9dcbec7d800 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -38,6 +38,7 @@ static int stop_script_unsupported(void)
 
 static void process_event_unsupported(union perf_event *event __unused,
 				      struct perf_sample *sample __unused,
+				      struct perf_evsel *evsel __unused,
 				      struct perf_session *session __unused,
 				      struct thread *thread __unused)
 {
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b04da5722437..f674dda3363b 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -280,6 +280,7 @@ struct scripting_ops {
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
 			       struct perf_session *session,
 			       struct thread *thread);
 	int (*generate_script) (const char *outfile);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a8730e4a..15633d608133 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 798efdca3ead..5d767c622dfc 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;