24 files changed, 498 insertions, 187 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 77f124fe57a..35655c3a7b7 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -319,6 +319,8 @@ LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -383,6 +385,8 @@ LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
 LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -983,7 +987,8 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	$(RM) $(OUTPUT)util/*-{bison,flex}*
+	$(RM) $(OUTPUT)util/*-bison*
+	$(RM) $(OUTPUT)util/*-flex*
 	$(python-clean)
 
 .PHONY: all install clean strip $(LIBTRACEEVENT)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f5a6452931e..4db6e1ba54e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -313,7 +313,7 @@ try_again:
 		}
  	}
 
-	perf_session__update_sample_type(session);
+	perf_session__set_id_hdr_size(session);
 }
 
 static int process_buildids(struct perf_record *rec)
@@ -844,8 +844,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	perf_header__set_cmdline(argc, argv);
-
 	evsel_list = perf_evlist__new(NULL, NULL);
 	if (evsel_list == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 69b1c118515..7c88a243b5d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -249,8 +249,9 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
+	u64 sample_type = perf_evlist__sample_type(self->evlist);
 
-	if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
 			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
@@ -274,7 +275,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 
 	if (sort__branch_mode == 1) {
 		if (!self->fd_pipe &&
-		    !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
 			ui__error("Selected -b but no branch data. "
 				  "Did you call perf record without -b?\n");
 			return -1;
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index d909eb74a0e..1d592f5cbea 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -478,7 +478,6 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -563,8 +562,7 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -661,12 +659,12 @@ static int test__PERF_RECORD(void)
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
 	char *bname;
-	u64 sample_type, prev_time = 0;
+	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
 	     found_vdso_mmap = false,
 	     found_ld_mmap = false;
-	int err = -1, errs = 0, i, wakeups = 0, sample_size;
+	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
 
@@ -757,13 +755,6 @@ static int test__PERF_RECORD(void)
 	}
 
 	/*
-	 * We'll need these two to parse the PERF_SAMPLE_* fields in each
-	 * event.
-	 */
-	sample_type = perf_evlist__sample_type(evlist);
-	sample_size = __perf_evsel__sample_size(sample_type);
-
-	/*
 	 * Now that all is properly set up, enable the events, they will
 	 * count just on workload.pid, which will start...
 	 */
@@ -788,9 +779,7 @@ static int test__PERF_RECORD(void)
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_event__parse_sample(event, sample_type,
-							       sample_size, true,
-							       &sample, false);
+				err = perf_evlist__parse_sample(evlist, event, &sample, false);
 				if (err < 0) {
 					if (verbose)
 						perf_event__fprintf(event, stderr);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 35e86c6df71..68cd61ef6ac 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -38,6 +38,7 @@
 #include "util/cpumap.h"
 #include "util/xyarray.h"
 #include "util/sort.h"
+#include "util/intlist.h"
 
 #include "util/debug.h"
 
@@ -706,8 +707,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	int err;
 
 	if (!machine && perf_guest) {
-		pr_err("Can't find guest [%d]'s kernel information\n",
-			event->ip.pid);
+		static struct intlist *seen;
+
+		if (!seen)
+			seen = intlist__new();
+
+		if (!intlist__has_entry(seen, event->ip.pid)) {
+			pr_err("Can't find guest [%d]'s kernel information\n",
+				event->ip.pid);
+			intlist__add(seen, event->ip.pid);
+		}
 		return;
 	}
 
@@ -811,7 +820,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_session__parse_sample(session, event, &sample);
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample, false);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			continue;
@@ -943,8 +952,10 @@ try_again:
 			 * based cpu-clock-tick sw counter, which
 			 * is always available even if no PMU support:
 			 */
-			if (attr->type == PERF_TYPE_HARDWARE &&
-			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if ((err == ENOENT || err == ENXIO) &&
+			    (attr->type == PERF_TYPE_HARDWARE) &&
+			    (attr->config == PERF_COUNT_HW_CPU_CYCLES)) {
+
 				if (verbose)
 					ui__warning("Cycles event not supported,\n"
 						    "trying to fall back to cpu-clock-ticks\n");
@@ -1032,7 +1043,7 @@ static int __cmd_top(struct perf_top *top)
 					       &top->session->host_machine);
 	perf_top__start_counters(top);
 	top->session->evlist = top->evlist;
-	perf_session__update_sample_type(top->session);
+	perf_session__set_id_hdr_size(top->session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1b197280c62..d84870b0642 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -197,9 +197,6 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample, bool swapped);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3edfd348381..9b38681add9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -881,3 +881,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped)
+{
+	struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return perf_evsel__parse_sample(e, event, sample, swapped);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 40d4d3cdced..528c1acd929 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -122,6 +122,9 @@ u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped);
+
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e8177136486..2eaae140def 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -20,7 +20,7 @@
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
-int __perf_evsel__sample_size(u64 sample_type)
+static int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -53,6 +53,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->attr	   = *attr;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
+	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -728,10 +729,10 @@ static bool sample_overlap(const union perf_event *event,
 	return false;
 }
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data, bool swapped)
 {
+	u64 type = evsel->attr.sample_type;
 	const u64 *array;
 
 	/*
@@ -746,14 +747,14 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
-		if (!sample_id_all)
+		if (!evsel->attr.sample_id_all)
 			return 0;
 		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;
 
-	if (sample_size + sizeof(event->header) > event->header.size)
+	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
 	if (type & PERF_SAMPLE_IP) {
@@ -895,7 +896,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[1] = sample->tid;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
@@ -930,7 +931,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[0] = sample->cpu;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val64 = bswap_64(u.val64);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 67cc5033d19..b559929983b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -65,6 +65,7 @@ struct perf_evsel {
 		void		*func;
 		void		*data;
 	} handler;
+	unsigned int		sample_size;
 	bool 			supported;
 };
 
@@ -177,13 +178,8 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-int __perf_evsel__sample_size(u64 sample_type);
-
-static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
-{
-	return __perf_evsel__sample_size(evsel->attr.sample_type);
-}
-
 void hists__init(struct hists *hists);
 
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *sample, bool swapped);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3a6d2044333..74ea3c2f813 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -174,6 +174,15 @@ perf_header__set_cmdline(int argc, const char **argv)
 {
 	int i;
 
+	/*
+	 * If header_argv has already been set, do not override it.
+	 * This allows a command to set the cmdline, parse args and
+	 * then call another builtin function that implements a
+	 * command -- e.g, cmd_kvm calling cmd_record.
+	 */
+	if (header_argv)
+		return 0;
+
 	header_argc = (u32)argc;
 
 	/* do not include NULL termination */
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
new file mode 100644
index 00000000000..fd530dced9c
--- /dev/null
+++ b/tools/perf/util/intlist.c
@@ -0,0 +1,101 @@
+/*
+ * Based on intlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+
+#include "intlist.h"
+
+static struct rb_node *intlist__node_new(struct rblist *rblist __used,
+					 const void *entry)
+{
+	int i = (int)((long)entry);
+	struct rb_node *rc = NULL;
+	struct int_node *node = malloc(sizeof(*node));
+
+	if (node != NULL) {
+		node->i = i;
+		rc = &node->rb_node;
+	}
+
+	return rc;
+}
+
+static void int_node__delete(struct int_node *ilist)
+{
+	free(ilist);
+}
+
+static void intlist__node_delete(struct rblist *rblist __used,
+				 struct rb_node *rb_node)
+{
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	int_node__delete(node);
+}
+
+static int intlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	int i = (int)((long)entry);
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	return node->i - i;
+}
+
+int intlist__add(struct intlist *ilist, int i)
+{
+	return rblist__add_node(&ilist->rblist, (void *)((long)i));
+}
+
+void intlist__remove(struct intlist *ilist __used, struct int_node *node)
+{
+	int_node__delete(node);
+}
+
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
+
+struct intlist *intlist__new(void)
+{
+	struct intlist *ilist = malloc(sizeof(*ilist));
+
+	if (ilist != NULL) {
+		rblist__init(&ilist->rblist);
+		ilist->rblist.node_cmp    = intlist__node_cmp;
+		ilist->rblist.node_new    = intlist__node_new;
+		ilist->rblist.node_delete = intlist__node_delete;
+	}
+
+	return ilist;
+}
+
+void intlist__delete(struct intlist *ilist)
+{
+	if (ilist != NULL)
+		rblist__delete(&ilist->rblist);
+}
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node;
+
+	rb_node = rblist__entry(&ilist->rblist, idx);
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
new file mode 100644
index 00000000000..6d63ab90db5
--- /dev/null
+++ b/tools/perf/util/intlist.h
@@ -0,0 +1,75 @@
+#ifndef __PERF_INTLIST_H
+#define __PERF_INTLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+#include "rblist.h"
+
+struct int_node {
+	struct rb_node rb_node;
+	int i;
+};
+
+struct intlist {
+	struct rblist rblist;
+};
+
+struct intlist *intlist__new(void);
+void intlist__delete(struct intlist *ilist);
+
+void intlist__remove(struct intlist *ilist, struct int_node *in);
+int intlist__add(struct intlist *ilist, int i);
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
+struct int_node *intlist__find(struct intlist *ilist, int i);
+
+static inline bool intlist__has_entry(struct intlist *ilist, int i)
+{
+	return intlist__find(ilist, i) != NULL;
+}
+
+static inline bool intlist__empty(const struct intlist *ilist)
+{
+	return rblist__empty(&ilist->rblist);
+}
+
+static inline unsigned int intlist__nr_entries(const struct intlist *ilist)
+{
+	return rblist__nr_entries(&ilist->rblist);
+}
+
+/* For intlist iteration */
+static inline struct int_node *intlist__first(struct intlist *ilist)
+{
+	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+static inline struct int_node *intlist__next(struct int_node *in)
+{
+	struct rb_node *rn;
+	if (!in)
+		return NULL;
+	rn = rb_next(&in->rb_node);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+
+/**
+ * intlist_for_each      - iterate over a intlist
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each(pos, ilist)	\
+	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
+
+/**
+ * intlist_for_each_safe - iterate over a intlist safe against removal of
+ *                         int_node
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @n:		another &struct int_node to use as temporary storage.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each_safe(pos, n, ilist)	\
+	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
+	     pos = n, n = intlist__next(n))
+#endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 1b997d2b89c..127d648cc54 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -13,6 +13,9 @@ do { \
 	} \
 } while (0)
 
+#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -21,8 +24,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	return 0;
 }
@@ -37,8 +39,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
-			(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU)
-			== evsel->attr.sample_type);
+			PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 		TEST_ASSERT_VAL("wrong sample_period",
 			1 == evsel->attr.sample_period);
 	}
@@ -428,8 +429,7 @@ static int test__checkevent_list(struct perf_evlist *evlist)
 	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 99d02aa57db..594f8fad5ec 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "parse-options.h"
 #include "cache.h"
+#include "header.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
@@ -413,6 +414,8 @@ int parse_options(int argc, const char **argv, const struct option *options,
 {
 	struct parse_opt_ctx_t ctx;
 
+	perf_header__set_cmdline(argc, argv);
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index e03b58a4842..0688bfb6d28 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -797,17 +797,13 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 	event = perf_evlist__mmap_read(evlist, cpu);
 	if (event != NULL) {
-		struct perf_evsel *first;
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		first = list_entry(evlist->entries.next, struct perf_evsel, node);
-		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
new file mode 100644
index 00000000000..0171fb61100
--- /dev/null
+++ b/tools/perf/util/rblist.c
@@ -0,0 +1,107 @@
+/*
+ * Based on strlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "rblist.h"
+
+int rblist__add_node(struct rblist *rblist, const void *new_entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL, *new_node;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, new_entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	new_node = rblist->node_new(rblist, new_entry);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	rb_link_node(new_node, parent, p);
+	rb_insert_color(new_node, &rblist->entries);
+	++rblist->nr_entries;
+
+	return 0;
+}
+
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
+{
+	rb_erase(rb_node, &rblist->entries);
+	rblist->node_delete(rblist, rb_node);
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return parent;
+	}
+
+	return NULL;
+}
+
+void rblist__init(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		rblist->entries	 = RB_ROOT;
+		rblist->nr_entries = 0;
+	}
+
+	return;
+}
+
+void rblist__delete(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+		while (next) {
+			pos = next;
+			next = rb_next(pos);
+			rb_erase(pos, &rblist->entries);
+			rblist->node_delete(rblist, pos);
+		}
+		free(rblist);
+	}
+}
+
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx)
+{
+	struct rb_node *node;
+
+	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+		if (!idx--)
+			return node;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
new file mode 100644
index 00000000000..6d0cae5ae83
--- /dev/null
+++ b/tools/perf/util/rblist.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_RBLIST_H
+#define __PERF_RBLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+/*
+ * create node structs of the form:
+ * struct my_node {
+ *     struct rb_node rb_node;
+ *     ... my data ...
+ * };
+ *
+ * create list structs of the form:
+ * struct mylist {
+ *     struct rblist rblist;
+ *     ... my data ...
+ * };
+ */
+
+struct rblist {
+	struct rb_root entries;
+	unsigned int   nr_entries;
+
+	int (*node_cmp)(struct rb_node *rbn, const void *entry);
+	struct rb_node *(*node_new)(struct rblist *rlist, const void *new_entry);
+	void (*node_delete)(struct rblist *rblist, struct rb_node *rb_node);
+};
+
+void rblist__init(struct rblist *rblist);
+void rblist__delete(struct rblist *rblist);
+int rblist__add_node(struct rblist *rblist, const void *new_entry);
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
+
+static inline bool rblist__empty(const struct rblist *rblist)
+{
+	return rblist->nr_entries == 0;
+}
+
+static inline unsigned int rblist__nr_entries(const struct rblist *rblist)
+{
+	return rblist->nr_entries;
+}
+
+#endif /* __PERF_RBLIST_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8e4f0755d2a..2437fb0b463 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -80,14 +80,12 @@ out_close:
 	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = __perf_evsel__sample_size(self->sample_type);
-	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
-	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
-	self->host_machine.id_hdr_size = self->id_hdr_size;
-	machines__set_id_hdr_size(&self->machines, self->id_hdr_size);
+	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+
+	session->host_machine.id_hdr_size = id_hdr_size;
+	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -147,7 +145,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
 			goto out_delete;
-		perf_session__update_sample_type(self);
+		perf_session__set_id_hdr_size(self);
 	} else if (mode == O_WRONLY) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
@@ -158,7 +156,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !self->sample_id_all) {
+	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_samples = false;
 	}
@@ -673,7 +671,8 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_session__parse_sample(s, iter->event, &sample);
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
+						s->header.needs_swap);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else
@@ -865,16 +864,18 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
+	u64 sample_type = perf_evlist__sample_type(session->evlist);
+
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !session->sample_id_all) {
+	    !perf_evlist__sample_id_all(session->evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
 
-	if ((session->sample_type & PERF_SAMPLE_CPU))
+	if ((sample_type & PERF_SAMPLE_CPU))
 		printf("%u ", sample->cpu);
 
-	if (session->sample_type & PERF_SAMPLE_TIME)
+	if (sample_type & PERF_SAMPLE_TIME)
 		printf("%" PRIu64 " ", sample->time);
 }
 
@@ -899,6 +900,8 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 static void dump_sample(struct perf_session *session, union perf_event *event,
 			struct perf_sample *sample)
 {
+	u64 sample_type;
+
 	if (!dump_trace)
 		return;
 
@@ -906,10 +909,12 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+	sample_type = perf_evlist__sample_type(session->evlist);
+
+	if (sample_type & PER