diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index ef6d22e879eb..eb30044a922a 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -222,10 +222,14 @@ install-pdf: pdf
 #install-html: html
 #	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
 
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE
 
 -include $(OUTPUT)PERF-VERSION-FILE
+endif
+endif
 
 #
 # Determine "include::" file references in asciidoc files.
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index c1057701a7dc..8e798baae0fd 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -24,6 +24,9 @@ OPTIONS
 -r::
 --remove=::
         Remove specified file from the cache.
+-M::
+--missing=:: 
+	List missing build ids in the cache for the specified file.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 194f37d635df..5b3123d5721f 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -22,10 +22,6 @@ specified perf.data files.
 
 OPTIONS
 -------
--M::
---displacement::
-        Show position displacement relative to baseline.
-
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 5b80d84d6b4a..a414bc95fd52 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -60,7 +60,7 @@ Default is to monitor all CPUS.
 
 -i::
 --inherit::
-	Child tasks inherit counters, only makes sens with -p option.
+	Child tasks do not inherit counters.
 
 -k <path>::
 --vmlinux=<path>::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 8ab05e543ef4..2cbaad83a6e2 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -153,6 +153,8 @@ INSTALL = install
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 -include config/feature-tests.mak
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
@@ -206,6 +208,8 @@ ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
 	EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
 	BASIC_CFLAGS += -I.
 endif
+endif # MAKECMDGOALS != tags
+endif # MAKECMDGOALS != clean
 
 # Guard against environment variables
 BUILTIN_OBJS =
@@ -230,11 +234,19 @@ endif
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 TE_LIB := -L$(TE_PATH) -ltraceevent
 
+export LIBTRACEEVENT
+
+# python extension build directories
+PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
+PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
+PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
+export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
+
+python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
+
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
 
-export LIBTRACEEVENT
-
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
@@ -378,8 +390,11 @@ LIB_H += util/rblist.h
 LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
 LIB_H += util/unwind.h
-LIB_H += ui/helpline.h
 LIB_H += util/vdso.h
+LIB_H += ui/helpline.h
+LIB_H += ui/progress.h
+LIB_H += ui/util.h
+LIB_H += ui/ui.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -453,6 +468,7 @@ LIB_OBJS += $(OUTPUT)util/stat.o
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
 LIB_OBJS += $(OUTPUT)ui/progress.o
+LIB_OBJS += $(OUTPUT)ui/util.o
 LIB_OBJS += $(OUTPUT)ui/hist.o
 LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
 
@@ -471,7 +487,6 @@ LIB_OBJS += $(OUTPUT)tests/rdpmc.o
 LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
 LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
 LIB_OBJS += $(OUTPUT)tests/pmu.o
-LIB_OBJS += $(OUTPUT)tests/util.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -510,6 +525,8 @@ PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT)
 #
 # Platform specific tweaks
 #
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
@@ -646,7 +663,6 @@ ifndef NO_NEWT
 		LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/map.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
-		LIB_OBJS += $(OUTPUT)ui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
 		LIB_OBJS += $(OUTPUT)ui/tui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
@@ -655,9 +671,6 @@ ifndef NO_NEWT
 		LIB_H += ui/browsers/map.h
 		LIB_H += ui/keysyms.h
 		LIB_H += ui/libslang.h
-		LIB_H += ui/progress.h
-		LIB_H += ui/util.h
-		LIB_H += ui/ui.h
 	endif
 endif
 
@@ -677,10 +690,6 @@ ifndef NO_GTK2
 		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
-		# Make sure that it'd be included only once.
-		ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),)
-			LIB_OBJS += $(OUTPUT)ui/util.o
-		endif
 	endif
 endif
 
@@ -707,7 +716,7 @@ disable-python = $(eval $(disable-python_code))
 define disable-python_code
   BASIC_CFLAGS += -DNO_LIBPYTHON
   $(if $(1),$(warning No $(1) was found))
-  $(warning Python support won't be built)
+  $(warning Python support will not be built)
 endef
 
 override PYTHON := \
@@ -715,19 +724,10 @@ override PYTHON := \
 
 ifndef PYTHON
   $(call disable-python,python interpreter)
-  python-clean :=
 else
 
   PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
-  # python extension build directories
-  PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
-  PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
-  PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
-  export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
-
-  python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
-
   ifdef NO_LIBPYTHON
     $(call disable-python)
   else
@@ -843,6 +843,9 @@ ifdef ASCIIDOC8
 	export ASCIIDOC8
 endif
 
+endif # MAKECMDGOALS != tags
+endif # MAKECMDGOALS != clean
+
 # Shell quote (do not use $(call) to accommodate ancient setups);
 
 ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
@@ -1099,7 +1102,7 @@ perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 
-install: all try-install-man
+install-bin: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
@@ -1120,6 +1123,8 @@ install: all try-install-man
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 	$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
+install: install-bin try-install-man
+
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index fae8b250b2ca..a336014e0286 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -14,6 +14,7 @@
 #include "util/parse-options.h"
 #include "util/strlist.h"
 #include "util/build-id.h"
+#include "util/session.h"
 #include "util/symbol.h"
 
 static int build_id_cache__add_file(const char *filename, const char *debugdir)
@@ -58,19 +59,59 @@ static int build_id_cache__remove_file(const char *filename,
 	return err;
 }
 
+static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
+{
+	char filename[PATH_MAX];
+	u8 build_id[BUILD_ID_SIZE];
+
+	if (dso__build_id_filename(dso, filename, sizeof(filename)) &&
+	    filename__read_build_id(filename, build_id,
+				    sizeof(build_id)) != sizeof(build_id)) {
+		if (errno == ENOENT)
+			return false;
+
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	} else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) {
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	}
+
+	return true;
+}
+
+static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+{
+	struct perf_session *session = perf_session__new(filename, O_RDONLY,
+							 force, false, NULL);
+	if (session == NULL)
+		return -1;
+
+	perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
+	perf_session__delete(session);
+
+	return 0;
+}
+
 int cmd_buildid_cache(int argc, const char **argv,
 		      const char *prefix __maybe_unused)
 {
 	struct strlist *list;
 	struct str_node *pos;
+	int ret = 0;
+	bool force = false;
 	char debugdir[PATH_MAX];
 	char const *add_name_list_str = NULL,
-		   *remove_name_list_str = NULL;
+		   *remove_name_list_str = NULL,
+		   *missing_filename = NULL;
 	const struct option buildid_cache_options[] = {
 	OPT_STRING('a', "add", &add_name_list_str,
 		   "file list", "file(s) to add"),
 	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
 		    "file(s) to remove"),
+	OPT_STRING('M', "missing", &missing_filename, "file",
+		   "to find missing build ids in the cache"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_END()
 	};
@@ -125,5 +166,8 @@ int cmd_buildid_cache(int argc, const char **argv,
 		}
 	}
 
-	return 0;
+	if (missing_filename)
+		ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index a82d99fec83e..e74366a13218 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -44,23 +44,26 @@ static int filename__fprintf_build_id(const char *name, FILE *fp)
 	return fprintf(fp, "%s\n", sbuild_id);
 }
 
+static bool dso__skip_buildid(struct dso *dso, int with_hits)
+{
+	return with_hits && !dso->hit;
+}
+
 static int perf_session__list_build_ids(bool force, bool with_hits)
 {
 	struct perf_session *session;
 
 	symbol__elf_init();
+	/*
+	 * See if this is an ELF file first:
+	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		goto out;
 
 	session = perf_session__new(input_name, O_RDONLY, force, false,
 				    &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
-
-	/*
-	 * See if this is an ELF file first:
-	 */
-	if (filename__fprintf_build_id(session->filename, stdout))
-		goto out;
-
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
@@ -68,9 +71,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	if (with_hits || session->fd_pipe)
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
 
-	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
-out:
+	perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
 	perf_session__delete(session);
+out:
 	return 0;
 }
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 93b852f8a5d5..b2e7d39f099b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -23,7 +23,6 @@ static char const *input_old = "perf.data.old",
 		  *input_new = "perf.data";
 static char	  diff__default_sort_order[] = "dso,symbol";
 static bool  force;
-static bool show_displacement;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
@@ -146,58 +145,47 @@ static int setup_compute(const struct option *opt, const char *str,
 	return -EINVAL;
 }
 
-static double get_period_percent(struct hist_entry *he, u64 period)
+double perf_diff__period_percent(struct hist_entry *he, u64 period)
 {
 	u64 total = he->hists->stats.total_period;
 	return (period * 100.0) / total;
 }
 
-double perf_diff__compute_delta(struct hist_entry *he)
+double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	double new_percent = get_period_percent(he, he->stat.period);
-	double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0;
+	double new_percent = perf_diff__period_percent(he, he->stat.period);
+	double old_percent = perf_diff__period_percent(pair, pair->stat.period);
 
 	he->diff.period_ratio_delta = new_percent - old_percent;
 	he->diff.computed = true;
 	return he->diff.period_ratio_delta;
 }
 
-double perf_diff__compute_ratio(struct hist_entry *he)
+double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	double new_period = he->stat.period;
-	double old_period = pair ? pair->stat.period : 0;
+	double old_period = pair->stat.period;
 
 	he->diff.computed = true;
-	he->diff.period_ratio = pair ? (new_period / old_period) : 0;
+	he->diff.period_ratio = new_period / old_period;
 	return he->diff.period_ratio;
 }
 
-s64 perf_diff__compute_wdiff(struct hist_entry *he)
+s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	u64 new_period = he->stat.period;
-	u64 old_period = pair ? pair->stat.period : 0;
+	u64 old_period = pair->stat.period;
 
 	he->diff.computed = true;
-
-	if (!pair)
-		he->diff.wdiff = 0;
-	else
-		he->diff.wdiff = new_period * compute_wdiff_w2 -
-				 old_period * compute_wdiff_w1;
+	he->diff.wdiff = new_period * compute_wdiff_w2 -
+			 old_period * compute_wdiff_w1;
 
 	return he->diff.wdiff;
 }
 
-static int formula_delta(struct hist_entry *he, char *buf, size_t size)
+static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
-
-	if (!pair)
-		return -1;
-
 	return scnprintf(buf, size,
 			 "(%" PRIu64 " * 100 / %" PRIu64 ") - "
 			 "(%" PRIu64 " * 100 / %" PRIu64 ")",
@@ -205,41 +193,36 @@ static int formula_delta(struct hist_entry *he, char *buf, size_t size)
 			  pair->stat.period, pair->hists->stats.total_period);
 }
 
-static int formula_ratio(struct hist_entry *he, char *buf, size_t size)
+static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	double new_period = he->stat.period;
-	double old_period = pair ? pair->stat.period : 0;
-
-	if (!pair)
-		return -1;
+	double old_period = pair->stat.period;
 
 	return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
 }
 
-static int formula_wdiff(struct hist_entry *he, char *buf, size_t size)
+static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	u64 new_period = he->stat.period;
-	u64 old_period = pair ? pair->stat.period : 0;
-
-	if (!pair)
-		return -1;
+	u64 old_period = pair->stat.period;
 
 	return scnprintf(buf, size,
 		  "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
 		  new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
 }
 
-int perf_diff__formula(char *buf, size_t size, struct hist_entry *he)
+int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
+		       char *buf, size_t size)
 {
 	switch (compute) {
 	case COMPUTE_DELTA:
-		return formula_delta(he, buf, size);
+		return formula_delta(he, pair, buf, size);
 	case COMPUTE_RATIO:
-		return formula_ratio(he, buf, size);
+		return formula_ratio(he, pair, buf, size);
 	case COMPUTE_WEIGHTED_DIFF:
-		return formula_wdiff(he, buf, size);
+		return formula_wdiff(he, pair, buf, size);
 	default:
 		BUG_ON(1);
 	}
@@ -312,9 +295,8 @@ static void insert_hist_entry_by_name(struct rb_root *root,
 	rb_insert_color(&he->rb_node, root);
 }
 
-static void hists__name_resort(struct hists *self, bool sort)
+static void hists__name_resort(struct hists *self)
 {
-	unsigned long position = 1;
 	struct rb_root tmp = RB_ROOT;
 	struct rb_node *next = rb_first(&self->entries);
 
@@ -322,16 +304,12 @@ static void hists__name_resort(struct hists *self, bool sort)
 		struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node);
 
 		next = rb_next(&n->rb_node);
-		n->position = position++;
 
-		if (sort) {
-			rb_erase(&n->rb_node, &self->entries);
-			insert_hist_entry_by_name(&tmp, n);
-		}
+		rb_erase(&n->rb_node, &self->entries);
+		insert_hist_entry_by_name(&tmp, n);
 	}
 
-	if (sort)
-		self->entries = tmp;
+	self->entries = tmp;
 }
 
 static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
@@ -355,12 +333,8 @@ static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name)
 
 		hists__output_resort(hists);
 
-		/*
-		 * The hists__name_resort only sets possition
-		 * if name is false.
-		 */
-		if (name || ((!name) && show_displacement))
-			hists__name_resort(hists, name);
+		if (name)
+			hists__name_resort(hists);
 	}
 }
 
@@ -385,18 +359,21 @@ static void hists__precompute(struct hists *hists)
 
 	while (next != NULL) {
 		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *pair = hist_entry__next_pair(he);
 
 		next = rb_next(&he->rb_node);
+		if (!pair)
+			continue;
 
 		switch (compute) {
 		case COMPUTE_DELTA:
-			perf_diff__compute_delta(he);
+			perf_diff__compute_delta(he, pair);
 			break;
 		case COMPUTE_RATIO:
-			perf_diff__compute_ratio(he);
+			perf_diff__compute_ratio(he, pair);
 			break;
 		case COMPUTE_WEIGHTED_DIFF:
-			perf_diff__compute_wdiff(he);
+			perf_diff__compute_wdiff(he, pair);
 			break;
 		default:
 			BUG_ON(1);
@@ -562,8 +539,6 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('M', "displacement", &show_displacement,
-		    "Show position displacement relative to baseline"),
 	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
 		    "Show only items with match in baseline"),
 	OPT_CALLBACK('c', "compute", &compute,
@@ -597,40 +572,32 @@ static const struct option options[] = {
 
 static void ui_init(void)
 {
-	perf_hpp__init();
-
-	/* No overhead column. */
-	perf_hpp__column_enable(PERF_HPP__OVERHEAD, false);
-
 	/*
-	 * Display baseline/delta/ratio/displacement/
+	 * Display baseline/delta/ratio
 	 * formula/periods columns.
 	 */
-	perf_hpp__column_enable(PERF_HPP__BASELINE, true);
+	perf_hpp__column_enable(PERF_HPP__BASELINE);
 
 	switch (compute) {
 	case COMPUTE_DELTA:
-		perf_hpp__column_enable(PERF_HPP__DELTA, true);
+		perf_hpp__column_enable(PERF_HPP__DELTA);
 		break;
 	case COMPUTE_RATIO:
-		perf_hpp__column_enable(PERF_HPP__RATIO, true);
+		perf_hpp__column_enable(PERF_HPP__RATIO);
 		break;
 	case COMPUTE_WEIGHTED_DIFF:
-		perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF, true);
+		perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF);
 		break;
 	default:
 		BUG_ON(1);
 	};
 
-	if (show_displacement)
-		perf_hpp__column_enable(PERF_HPP__DISPL, true);
-
 	if (show_formula)
-		perf_hpp__column_enable(PERF_HPP__FORMULA, true);
+		perf_hpp__column_enable(PERF_HPP__FORMULA);
 
 	if (show_period) {
-		perf_hpp__column_enable(PERF_HPP__PERIOD, true);
-		perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE, true);
+		perf_hpp__column_enable(PERF_HPP__PERIOD);
+		perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE);
 	}
 }
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index c20f1dcfb7e2..1312a5e03ec7 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,39 +15,6 @@
 #include "util/parse-options.h"
 #include "util/session.h"
 
-struct perf_attr_details {
-	bool freq;
-	bool verbose;
-};
-
-static int comma_printf(bool *first, const char *fmt, ...)
-{
-	va_list args;
-	int ret = 0;
-
-	if (!*first) {
-		ret += printf(",");
-	} else {
-		ret += printf(":");
-		*first = false;
-	}
-
-	va_start(args, fmt);
-	ret += vprintf(fmt, args);
-	va_end(args);
-	return ret;
-}
-
-static int __if_print(bool *first, const char *field, u64 value)
-{
-	if (value == 0)
-		return 0;
-
-	return comma_printf(first, " %s: %" PRIu64, field, value);
-}
-
-#define if_print(field) __if_print(&first, #field, pos->attr.field)
-
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
 	struct perf_session *session;
@@ -57,52 +24,8 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	if (session == NULL)
 		return -ENOMEM;
 
-	list_for_each_entry(pos, &session->evlist->entries, node) {
-		bool first = true;
-
-		printf("%s", perf_evsel__name(pos));
-
-		if (details->verbose || details->freq) {
-			comma_printf(&first, " sample_freq=%" PRIu64,
-				     (u64)pos->attr.sample_freq);
-		}
-
-		if (details->verbose) {
-			if_print(type);
-			if_print(config);
-			if_print(config1);
-			if_print(config2);
-			if_print(size);
-			if_print(sample_type);
-			if_print(read_format);
-			if_print(disabled);
-			if_print(inherit);
-			if_print(pinned);
-			if_print(exclusive);
-			if_print(exclude_user);
-			if_print(exclude_kernel);
-			if_print(exclude_hv);
-			if_print(exclude_idle);
-			if_print(mmap);
-			if_print(comm);
-			if_print(freq);
-			if_print(inherit_stat);
-			if_print(enable_on_exec);
-			if_print(task);
-			if_print(watermark);
-			if_print(precise_ip);
-			if_print(mmap_data);
-			if_print(sample_id_all);
-			if_print(exclude_host);
-			if_print(exclude_guest);
-			if_print(__reserved_1);
-			if_print(wakeup_events);
-			if_print(bp_type);
-			if_print(branch_sample_type);
-		}
-
-		putchar('\n');
-	}
+	list_for_each_entry(pos, &session->evlist->entries, node)
+		perf_evsel__fprintf(pos, details, stdout);
 
 	perf_session__delete(session);
 	return 0;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3151d3c70ce..028de726b832 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -230,14 +230,7 @@ static int perf_record__open(struct perf_record *rec)
 	struct perf_record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	/*
-	 * Set the evsel leader links before we configure attributes,
-	 * since some might depend on this info.
-	 */
-	if (opts->group)
-		perf_evlist__set_leader(evlist);
-
-	perf_evlist__config_attrs(evlist, opts);
+	perf_evlist__config(evlist, opts);
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
@@ -286,7 +279,7 @@ try_again:
 					 */
 					opts->sample_id_all_missing = true;
 					if (!opts->sample_time && !opts->raw_samples && !time_needed)
-						attr->sample_type &= ~PERF_SAMPLE_TIME;
+						perf_evsel__reset_sample_bit(pos, TIME);
 
 					goto retry_sample_id;
 				}
@@ -875,11 +868,10 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* LIBUNWIND_SUPPORT */
 
-static int
-parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
-		    int unset)
+int record_parse_callchain_opt(const struct option *opt,
+			       const char *arg, int unset)
 {
-	struct perf_record *rec = (struct perf_record *)opt->value;
+	struct perf_record_opts *opts = opt->value;
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
 	int ret = -1;
@@ -905,7 +897,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
 		/* Framepointer style */
 		if (!strncmp(name, "fp", sizeof("fp"))) {
 			if (!strtok_r(NULL, ",", &saveptr)) {
-				rec->opts.call_graph = CALLCHAIN_FP;
+				opts->call_graph = CALLCHAIN_FP;
 				ret = 0;
 			} else
 				pr_err("callchain: No more arguments "
@@ -918,20 +910,20 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
 			const unsigned long default_stack_dump_size = 8192;
 
 			ret = 0;
-			rec->opts.call_graph = CALLCHAIN_DWARF;
-			rec->opts.stack_dump_size = default_stack_dump_size;
+			opts->call_graph = CALLCHAIN_DWARF;
+			opts->stack_dump_size = default_stack_dump_size;
 
 			tok = strtok_r(NULL, ",", &saveptr);
 			if (tok) {
 				unsigned long size = 0;
 
 				ret = get_stack_size(tok, &size);
-				rec->opts.stack_dump_size = size;
+				opts->stack_dump_size = size;
 			}
 
 			if (!ret)
 				pr_debug("callchain: stack dump size %d\n",
-					 rec->opts.stack_dump_size);
+					 opts->stack_dump_size);
 #endif /* LIBUNWIND_SUPPORT */
 		} else {
 			pr_err("callchain: Unknown -g option "
@@ -944,7 +936,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
 	free(buf);
 
 	if (!ret)
-		pr_debug("callchain: type %d\n", rec->opts.call_graph);
+		pr_debug("callchain: type %d\n", opts->call_graph);
 
 	return ret;
 }
@@ -982,9 +974,9 @@ static struct perf_record record = {
 #define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
 
 #ifdef LIBUNWIND_SUPPORT
-static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
 #else
-static const char callchain_help[] = CALLCHAIN_HELP "[fp]";
+const char record_callchain_help[] = CALLCHAIN_HELP "[fp]";
 #endif
 
 /*
@@ -1028,9 +1020,9 @@ const struct option record_options[] = {
 		     "number of mmap data pages"),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
-			     callchain_help, &parse_callchain_opt,
-			     "fp"),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts,
+			     "mode[,dump_size]", record_callchain_help,
+			     &record_parse_callchain_opt, "fp"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fc251005dd3d..5134acf1c39a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -692,6 +692,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		setup_browser(true);
 	else {
 		use_browser = 0;
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 		perf_hpp__init();
 	}
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c247faca7127..c12655af2b88 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -153,7 +153,7 @@ retry:
 	}
 
 	if (!perf_target__has_task(&target) &&
-	    !perf_evsel__is_group_member(evsel)) {
+	    perf_evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c9ff3950cd4b..b7d2ea62dbc6 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -596,7 +596,7 @@ static void *display_thread_tui(void *arg)
 	 * via --uid.
 	 */
 	list_for_each_entry(pos, &top->evlist->entries, node)
-		pos->hists.uid_filter_str = top->target.uid_str;
+		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      &top->session->header.env);
@@ -727,7 +727,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (!machine) {
-		pr_err("%u unprocessable samples recorded.",
+		pr_err("%u unprocessable samples recorded.\n",
 		       top->session->hists.stats.nr_unprocessable_samples++);
 		return;
 	}
@@ -894,35 +894,13 @@ static void perf_top__start_counters(struct perf_top *top)
 {
 	struct perf_evsel *counter;
 	struct perf_evlist *evlist = top->evlist;
+	struct perf_record_opts *opts = &top->record_opts;
 
-	if (top->group)
-		perf_evlist__set_leader(evlist);
+	perf_evlist__config(evlist, opts);
 
 	list_for_each_entry(counter, &evlist->entries, node) {
 		struct perf_event_attr *attr = &counter->attr;
 
-		attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
-
-		if (top->freq) {
-			attr->sample_type |= PERF_SAMPLE_PERIOD;
-			attr->freq	  = 1;
-			attr->sample_freq = top->freq;
-		}
-
-		if (evlist->nr_entries > 1) {
-			attr->sample_type |= PERF_SAMPLE_ID;
-			attr->read_format |= PERF_FORMAT_ID;
-		}
-
-		if (perf_target__has_cpu(&top->target))
-			attr->sample_type |= PERF_SAMPLE_CPU;
-
-		if (symbol_conf.use_callchain)
-			attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
-
-		attr->mmap = 1;
-		attr->comm = 1;
-		attr->inherit = top->inherit;
 fallback_missing_features:
 		if (top->exclude_guest_missing)
 			attr->exclude_guest = attr->exclude_host = 0;
@@ -996,7 +974,7 @@ try_again:
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) {
+	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
 			    errno, strerror(errno));
 		goto out_err;
@@ -1016,7 +994,7 @@ static int perf_top__setup_sample_type(struct perf_top *top)
 			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
 			return -EINVAL;
 		}
-	} else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) {
+	} else if (callchain_param.mode != CHAIN_NONE) {
 		if (callchain_register_param(&callchain_param) < 0) {
 			ui__error("Can't register callchain params.\n");
 			return -EINVAL;
@@ -1028,6 +1006,7 @@ static int perf_top__setup_sample_type(struct perf_top *top)
 
 static int __cmd_top(struct perf_top *top)
 {
+	struct perf_record_opts *opts = &top->record_opts;
 	pthread_t thread;
 	int ret;
 	/*
@@ -1042,7 +1021,7 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
-	if (perf_target__has_task(&top->target))
+	if (perf_target__has_task(&opts->target))
 		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
 						  perf_event__process,
 						  &top->session->host_machine);
@@ -1053,6 +1032,17 @@ static int __cmd_top(struct perf_top *top)
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
 
+	/*
+	 * When perf is starting the traced process, all the events (apart from
+	 * group members) have enable_on_exec=1 set, so don't spoil it by
+	 * prematurely enabling them.
+	 *
+	 * XXX 'top' still doesn't start workloads like record, trace, but should,
+	 * so leave the check here.
+	 */
+        if (!perf_target__none(&opts->target))
+                perf_evlist__enable(top->evlist);
+
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 
@@ -1093,116 +1083,56 @@ out_delete:
 static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	struct perf_top *top = (struct perf_top *)opt->value;
-	char *tok, *tok2;
-	char *endptr;
-
 	/*
 	 * --no-call-graph
 	 */
-	if (unset) {
-		top->dont_use_callchains = true;
+	if (unset)
 		return 0;
-	}
 
 	symbol_conf.use_callchain = true;
 
-	if (!arg)
-		return 0;
-
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	else if (!strncmp(tok, "flat", strlen(arg)))
-		callchain_param.mode = CHAIN_FLAT;
-
-	else if (!strncmp(tok, "fractal", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_REL;
-
-	else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-
-		return 0;
-	} else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
-
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
-
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtod(tok2, &endptr);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
-	}
-
-	/* get the call chain order */
-	if (!strcmp(tok2, "caller"))
-		callchain_param.order = ORDER_CALLER;
-	else if (!strcmp(tok2, "callee"))
-		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
-setup:
-	if (callchain_register_param(&callchain_param) < 0) {
-		fprintf(stderr, "Can't register callchain params\n");
-		return -1;
-	}
-	return 0;
+	return record_parse_callchain_opt(opt, arg, unset);
 }
 
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	struct perf_evsel *pos;
 	int status;
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
 		.count_filter	     = 5,
 		.delay_secs	     = 2,
-		.freq		     = 4000, /* 4 KHz */
-		.mmap_pages	     = 128,
-		.sym_pcnt_filter     = 5,
-		.target		     = {
-			.uses_mmap   = true,
+		.record_opts = {
+			.mmap_pages	= UINT_MAX,
+			.user_freq	= UINT_MAX,
+			.user_interval	= ULLONG_MAX,
+			.freq		= 4000, /* 4 KHz */
+			.target		     = {
+				.uses_mmap   = true,
+			},
 		},
+		.sym_pcnt_filter     = 5,
 	};
-	char callchain_default_opt[] = "fractal,0.5,callee";
+	struct perf_record_opts *opts = &top.record_opts;
+	struct perf_target *target = &opts->target;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),
-	OPT_INTEGER('c', "count", &top.default_interval,
-		    "event period to sample"),
-	OPT_STRING('p', "pid", &top.target.pid, "pid",
+	OPT_U64('c', "count", &opts->user_interval, "event period to sample"),
+	OPT_STRING('p', "pid", &target->pid, "pid",
 		    "profile events on existing process id"),
-	OPT_STRING('t', "tid", &top.target.tid, "tid",
+	OPT_STRING('t', "tid", &target->tid, "tid",
 		    "profile events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &top.target.system_wide,
+	OPT_BOOLEAN('a', "all-cpus", &target->system_wide,
 			    "system-wide collection from all CPUs"),
-	OPT_STRING('C', "cpu", &top.target.cpu_list, "cpu",
+	OPT_STRING('C', "cpu", &target->cpu_list, "cpu",
 		    "list of cpus to monitor"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
 		    "hide kernel symbols"),
-	OPT_UINTEGER('m', "mmap-pages", &top.mmap_pages, "number of mmap data pages"),
+	OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages,
+		     "number of mmap data pages"),
 	OPT_INTEGER('r', "realtime", &top.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_INTEGER('d', "delay", &top.delay_secs,
@@ -1211,16 +1141,14 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "dump the symbol table used for profiling"),
 	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &top.group,
+	OPT_BOOLEAN('g', "group", &opts->group,
 			    "put the counters into a counter group"),
-	OPT_BOOLEAN('i', "inherit", &top.inherit,
-		    "child tasks inherit counters"),
+	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
+		    "child tasks do not inherit counters"),
 	OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('z', "zero", &top.zero,
-		    "zero history across updates"),
-	OPT_INTEGER('F', "freq", &top.freq,
-		    "profile at this frequency"),
+	OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"),
+	OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"),
 	OPT_INTEGER('E', "entries", &top.print_entries,
 		    "display this many functions"),
 	OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
@@ -1233,10 +1161,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_DEFAULT('G', "call-graph", &top, "output_type,min_percent, call_order",
-		     "Display callchains using output_type (graph, flat, fractal, or none), min percent threshold and callchain order. "
-		     "Default: fractal,0.5,callee", &parse_callchain_opt,
-		     callchain_default_opt),
+	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
+			     "mode[,dump_size]", record_callchain_help,
+			     &parse_callchain_opt, "fp"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
@@ -1251,7 +1178,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"),
+	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1281,27 +1208,27 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_browser(false);
 
-	status = perf_target__validate(&top.target);
+	status = perf_target__validate(target);
 	if (status) {
-		perf_target__strerror(&top.target, status, errbuf, BUFSIZ);
+		perf_target__strerror(target, status, errbuf, BUFSIZ);
 		ui__warning("%s", errbuf);
 	}
 
-	status = perf_target__parse_uid(&top.target);
+	status = perf_target__parse_uid(target);
 	if (status) {
 		int saved_errno = errno;
 
-		perf_target__strerror(&top.target, status, errbuf, BUFSIZ);
+		perf_target__strerror(target, status, errbuf, BUFSIZ);
 		ui__error("%s", errbuf);
 
 		status = -saved_errno;
 		goto out_delete_evlist;
 	}
 
-	if (perf_target__none(&top.target))
-		top.target.system_wide = true;
+	if (perf_target__none(target))
+		target->system_wide = true;
 
-	if (perf_evlist__create_maps(top.evlist, &top.target) < 0)
+	if (perf_evlist__create_maps(top.evlist, target) < 0)
 		usage_with_options(top_usage, options);
 
 	if (!top.evlist->nr_entries &&
@@ -1315,24 +1242,22 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (top.delay_secs < 1)
 		top.delay_secs = 1;
 
+	if (opts->user_interval != ULLONG_MAX)
+		opts->default_interval = opts->user_interval;
+	if (opts->user_freq != UINT_MAX)
+		opts->freq = opts->user_freq;
+
 	/*
 	 * User specified count overrides default frequency.
 	 */
-	if (top.default_interval)
-		top.freq = 0;
-	else if (top.freq) {
-		top.default_interval = top.freq;
+	if (opts->default_interval)
+		opts->freq = 0;
+	else if (opts->freq) {
+		opts->default_interval = opts->freq;
 	} else {
 		ui__error("frequency and count are zero, aborting\n");
-		exit(EXIT_FAILURE);
-	}
-
-	list_for_each_entry(pos, &top.evlist->entries, node) {
-		/*
-		 * Fill in the ones not specifically initialized via -c:
-		 */
-		if (!pos->attr.sample_period)
-			pos->attr.sample_period = top.default_interval;
+		status = -EINVAL;
+		goto out_delete_evlist;
 	}
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7932ffa29889..d222d7fc7e96 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -455,7 +455,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config_attrs(evlist, &trace->opts);
+	perf_evlist__config(evlist, &trace->opts);
 
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index f1485d8e6a0b..5bc3880f7be5 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -7,7 +7,7 @@ size=96
 config=0
 sample_period=4000
 sample_type=263
-read_format=7
+read_format=0
 disabled=1
 inherit=1
 pinned=0
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index a6599e9a19d3..57739cacdb2a 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -6,12 +6,14 @@ args    = --group -e cycles,instructions kill >/dev/null 2>&1
 fd=1
 group_fd=-1
 sample_type=327
+read_format=4
 
 [event-2:base-record]
 fd=2
 group_fd=1
 config=1
 sample_type=327
+read_format=4
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index 5a8359da38af..4d688a13fd2f 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -6,6 +6,7 @@ args    = -e '{cycles,instructions}' kill >/tmp/krava 2>&1
 fd=1
 group_fd=-1
 sample_type=327
+read_format=4
 
 [event-2:base-record]
 fd=2
@@ -13,6 +14,7 @@ group_fd=1
 type=0
 config=1
 sample_type=327
+read_format=4
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index e1746811e14b..cdd50755af51 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -22,36 +22,16 @@ int test__basic_mmap(void)
 	struct thread_map *threads;
 	struct cpu_map *cpus;
 	struct perf_evlist *evlist;
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_TRACEPOINT,
-		.read_format	= PERF_FORMAT_ID,
-		.sample_type	= PERF_SAMPLE_ID,
-		.watermark	= 0,
-	};
 	cpu_set_t cpu_set;
 	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
 					"getpgid", };
 	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
 				      (void*)getpgid };
 #define nsyscalls ARRAY_SIZE(syscall_names)
-	int ids[nsyscalls];
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 
-	for (i = 0; i < nsyscalls; ++i) {
-		char name[64];
-
-		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
-		ids[i] = trace_event__id(name);
-		if (ids[i] < 0) {
-			pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
-			return -1;
-		}
-		nr_events[i] = 0;
-		expected_nr_events[i] = random() % 257;
-	}
-
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -79,18 +59,19 @@ int test__basic_mmap(void)
 		goto out_free_cpus;
 	}
 
-	/* anonymous union fields, can't be initialized above */
-	attr.wakeup_events = 1;
-	attr.sample_period = 1;
-
 	for (i = 0; i < nsyscalls; ++i) {
-		attr.config = ids[i];
-		evsels[i] = perf_evsel__new(&attr, i);
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		evsels[i] = perf_evsel__newtp("syscalls", name, i);
 		if (evsels[i] == NULL) {
 			pr_debug("perf_evsel__new\n");
 			goto out_free_evlist;
 		}
 
+		evsels[i]->attr.wakeup_events = 1;
+		perf_evsel__set_sample_id(evsels[i]);
+
 		perf_evlist__add(evlist, evsels[i]);
 
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
@@ -99,6 +80,9 @@ int test__basic_mmap(void)
 				 strerror(errno));
 			goto out_close_fd;
 		}
+
+		nr_events[i] = 0;
+		expected_nr_events[i] = 1 + rand() % 127;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
@@ -128,6 +112,7 @@ int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
+		err = -1;
 		evsel = perf_evlist__id2evsel(evlist, sample.id);
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
@@ -137,16 +122,17 @@ int test__basic_mmap(void)
 		nr_events[evsel->idx]++;
 	}
 
+	err = 0;
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
 				 perf_evsel__name(evsel), nr_events[evsel->idx]);
+			err = -1;
 			goto out_munmap;
 		}
 	}
 
-	err = 0;
 out_munmap:
 	perf_evlist__munmap(evlist);
 out_close_fd:
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 31072aba0d54..9b920a0cce79 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -7,20 +7,12 @@
 int test__open_syscall_event_on_all_cpus(void)
 {
 	int err = -1, fd, cpu;
-	struct thread_map *threads;
 	struct cpu_map *cpus;
 	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
 	cpu_set_t cpu_set;
-	int id = trace_event__id("sys_enter_open");
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
@@ -32,15 +24,11 @@ int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-
 	CPU_ZERO(&cpu_set);
 
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
 	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\n");
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
 	}
 
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index 98be8b518b4f..befc0671f95d 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -6,29 +6,18 @@
 int test__open_syscall_event(void)
 {
 	int err = -1, fd;
-	struct thread_map *threads;
 	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
-	int id = trace_event__id("sys_enter_open");
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
 	}
 
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
 	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\n");
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 32ee478905eb..294ffddfbf42 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -521,7 +521,7 @@ static int test__group1(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	/* cycles:upp */
 	evsel = perf_evsel__next(evsel);
@@ -557,7 +557,7 @@ static int test__group2(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	/* cache-references + :u modifier */
 	evsel = perf_evsel__next(evsel);
@@ -583,7 +583,7 @@ static int test__group2(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
@@ -606,7 +606,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group1"));
 
@@ -636,7 +636,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group2"));
 
@@ -663,7 +663,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
@@ -687,7 +687,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	/* instructions:kp + p */
 	evsel = perf_evsel__next(evsel);
@@ -724,7 +724,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	/* instructions + G */
 	evsel = perf_evsel__next(evsel);
@@ -751,7 +751,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	/* instructions:G */
 	evsel = perf_evsel__next(evsel);
@@ -777,7 +777,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 70e0d4421df8..6ea66cf6791b 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -103,10 +103,10 @@ int test__PERF_RECORD(void)
 	 * Config the evsels, setting attr->comm on the first one, etc.
 	 */
 	evsel = perf_evlist__first(evlist);
-	evsel->attr.sample_type |= PERF_SAMPLE_CPU;
-	evsel->attr.sample_type |= PERF_SAMPLE_TID;
-	evsel->attr.sample_type |= PERF_SAMPLE_TIME;
-	perf_evlist__config_attrs(evlist, &opts);
+	perf_evsel__set_sample_bit(evsel, CPU);
+	perf_evsel__set_sample_bit(evsel, TID);
+	perf_evsel__set_sample_bit(evsel, TIME);
+	perf_evlist__config(evlist, &opts);
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index fc121edab016..0fd94657960e 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -16,7 +16,4 @@ int test__attr(void);
 int test__dso_data(void);
 int test__parse_events(void);
 
-/* Util */
-int trace_event__id(const char *evname);
-
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/util.c b/tools/perf/tests/util.c
deleted file mode 100644
index 748f2e8f6961..000000000000
--- a/tools/perf/tests/util.c
+++ /dev/null
@@ -1,30 +0,0 @@
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include "tests.h"
-#include "debugfs.h"
-
-int trace_event__id(const char *evname)
-{
-	char *filename;
-	int err = -1, fd;
-
-	if (asprintf(&filename,
-		     "%s/syscalls/%s/id",
-		     tracing_events_path, evname) < 0)
-		return -1;
-
-	fd = open(filename, O_RDONLY);
-	if (fd >= 0) {
-		char id[16];
-		if (read(fd, id, sizeof(id)) > 0)
-			err = atoi(id);
-		close(fd);
-	}
-
-	free(filename);
-	return err;
-}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index ccc4bd161420..57b82c26cd05 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -587,6 +587,8 @@ HPP__COLOR_FN(overhead_guest_us, period_guest_us)
 
 void hist_browser__init_hpp(void)
 {
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
 	perf_hpp__init();
 
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -607,12 +609,13 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 {
 	char s[256];
 	double percent;
-	int i, printed = 0;
+	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
 	bool first = true;
+	struct perf_hpp_fmt *fmt;
 
 	if (current_entry) {
 		browser->he_selection = entry;
@@ -629,12 +632,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.buf		= s,
 			.size		= sizeof(s),
 		};
+		int i = 0;
 
 		ui_browser__gotorc(&browser->b, row, 0);
 
-		for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-			if (!perf_hpp__format[i].cond)
-				continue;
+		perf_hpp__for_each_format(fmt) {
 
 			if (!first) {
 				slsmg_printf("  ");
@@ -642,14 +644,14 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 			first = false;
 
-			if (perf_hpp__format[i].color) {
+			if (fmt->color) {
 				hpp.ptr = &percent;
 				/* It will set percent for us. See HPP__COLOR_FN above. */
-				width -= perf_hpp__format[i].color(&hpp, entry);
+				width -= fmt->color(&hpp, entry);
 
 				ui_browser__set_percent_color(&browser->b, percent, current_entry);
 
-				if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) {
+				if (!i && symbol_conf.use_callchain) {
 					slsmg_printf("%c ", folded_sign);
 					width -= 2;
 				}
@@ -659,9 +661,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				if (!current_entry || !browser->b.navkeypressed)
 					ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
 			} else {
-				width -= perf_hpp__format[i].entry(&hpp, entry);
+				width -= fmt->entry(&hpp, entry);
 				slsmg_printf("%s", s);
 			}
+
+			i++;
 		}
 
 		/* The scroll bar isn't being used */
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 253b6219a39e..e59ba337f494 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -74,6 +74,8 @@ HPP__COLOR_FN(overhead_guest_us, period_guest_us)
 
 void perf_gtk__init_hpp(void)
 {
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
 	perf_hpp__init();
 
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -90,13 +92,14 @@ void perf_gtk__init_hpp(void)
 
 static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 {
+	struct perf_hpp_fmt *fmt;
 	GType col_types[MAX_COLUMNS];
 	GtkCellRenderer *renderer;
 	struct sort_entry *se;
 	GtkListStore *store;
 	struct rb_node *nd;
 	GtkWidget *view;
-	int i, col_idx;
+	int col_idx;
 	int nr_cols;
 	char s[512];
 
@@ -107,12 +110,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 
 	nr_cols = 0;
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
+	perf_hpp__for_each_format(fmt)
 		col_types[nr_cols++] = G_TYPE_STRING;
-	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
 		if (se->elide)
@@ -129,12 +128,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 
 	col_idx = 0;
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
-		perf_hpp__format[i].header(&hpp);
-
+	perf_hpp__for_each_format(fmt) {
+		fmt->header(&hpp);
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
 							    -1, s,
 							    renderer, "markup",
@@ -166,14 +161,11 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 
 		col_idx = 0;
 
-		for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-			if (!perf_hpp__format[i].cond)
-				continue;
-
-			if (perf_hpp__format[i].color)
-				perf_hpp__format[i].color(&hpp, h);
+		perf_hpp__for_each_format(fmt) {
+			if (fmt->color)
+				fmt->color(&hpp, h);
 			else
-				perf_hpp__format[i].entry(&hpp, h);
+				fmt->entry(&hpp, h);
 
 			gtk_list_store_set(store, &iter, col_idx++, s, -1);
 		}
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
index 5db4432ff12a..3388cbd12186 100644
--- a/tools/perf/ui/gtk/helpline.c
+++ b/tools/perf/ui/gtk/helpline.c
@@ -24,17 +24,7 @@ static void gtk_helpline_push(const char *msg)
 			   pgctx->statbar_ctx_id, msg);
 }
 
-static struct ui_helpline gtk_helpline_fns = {
-	.pop	= gtk_helpline_pop,
-	.push	= gtk_helpline_push,
-};
-
-void perf_gtk__init_helpline(void)
-{
-	helpline_fns = &gtk_helpline_fns;
-}
-
-int perf_gtk__show_helpline(const char *fmt, va_list ap)
+static int gtk_helpline_show(const char *fmt, va_list ap)
 {
 	int ret;
 	char *ptr;
@@ -54,3 +44,14 @@ int perf_gtk__show_helpline(const char *fmt, va_list ap)
 
 	return ret;
 }
+
+static struct ui_helpline gtk_helpline_fns = {
+	.pop	= gtk_helpline_pop,
+	.push	= gtk_helpline_push,
+	.show	= gtk_helpline_show,
+};
+
+void perf_gtk__init_helpline(void)
+{
+	helpline_fns = &gtk_helpline_fns;
+}
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index a49bcf3c190b..700fb3cfa1c7 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -16,9 +16,16 @@ static void nop_helpline__push(const char *msg __maybe_unused)
 {
 }
 
+static int nop_helpline__show(const char *fmt __maybe_unused,
+			       va_list ap __maybe_unused)
+{
+	return 0;
+}
+
 static struct ui_helpline default_helpline_fns = {
 	.pop	= nop_helpline__pop,
 	.push	= nop_helpline__push,
+	.show	= nop_helpline__show,
 };
 
 struct ui_helpline *helpline_fns = &default_helpline_fns;
@@ -59,3 +66,8 @@ void ui_helpline__puts(const char *msg)
 	ui_helpline__pop();
 	ui_helpline__push(msg);
 }
+
+int ui_helpline__vshow(const char *fmt, va_list ap)
+{
+	return helpline_fns->show(fmt, ap);
+}
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index baa28a4d16b9..46181f4fc07e 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -9,6 +9,7 @@
 struct ui_helpline {
 	void (*pop)(void);
 	void (*push)(const char *msg);
+	int  (*show)(const char *fmt, va_list ap);
 };
 
 extern struct ui_helpline *helpline_fns;
@@ -20,28 +21,9 @@ void ui_helpline__push(const char *msg);
 void ui_helpline__vpush(const char *fmt, va_list ap);
 void ui_helpline__fpush(const char *fmt, ...);
 void ui_helpline__puts(const char *msg);
+int  ui_helpline__vshow(const char *fmt, va_list ap);
 
 extern char ui_helpline__current[512];
-
-#ifdef NEWT_SUPPORT
 extern char ui_helpline__last_msg[];
-int ui_helpline__show_help(const char *format, va_list ap);
-#else
-static inline int ui_helpline__show_help(const char *format __maybe_unused,
-					 va_list ap __maybe_unused)
-{
-	return 0;
-}
-#endif /* NEWT_SUPPORT */
-
-#ifdef GTK2_SUPPORT
-int perf_gtk__show_helpline(const char *format, va_list ap);
-#else
-static inline int perf_gtk__show_helpline(const char *format __maybe_unused,
-					  va_list ap __maybe_unused)
-{
-	return 0;
-}
-#endif /* GTK2_SUPPORT */
 
 #endif /* _PERF_UI_HELPLINE_H_ */
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index aa84130024d5..1889c12ca81f 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -268,14 +268,18 @@ static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused)
 
 static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s";
 	char buf[32] = " ";
-	double diff;
+	double diff = 0.0;
 
-	if (he->diff.computed)
-		diff = he->diff.period_ratio_delta;
-	else
-		diff = perf_diff__compute_delta(he);
+	if (pair) {
+		if (he->diff.computed)
+			diff = he->diff.period_ratio_delta;
+		else
+			diff = perf_diff__compute_delta(he, pair);
+	} else
+		diff = perf_diff__period_percent(he, he->stat.period);
 
 	if (fabs(diff) >= 0.01)
 		scnprintf(buf, sizeof(buf), "%+4.2F%%", diff);
@@ -297,14 +301,17 @@ static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused)
 
 static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
 	char buf[32] = " ";
-	double ratio;
+	double ratio = 0.0;
 
-	if (he->diff.computed)
-		ratio = he->diff.period_ratio;
-	else
-		ratio = perf_diff__compute_ratio(he);
+	if (pair) {
+		if (he->diff.computed)
+			ratio = he->diff.period_ratio;
+		else
+			ratio = perf_diff__compute_ratio(he, pair);
+	}
 
 	if (ratio > 0.0)
 		scnprintf(buf, sizeof(buf), "%+14.6F", ratio);
@@ -326,14 +333,17 @@ static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused)
 
 static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
 	char buf[32] = " ";
-	s64 wdiff;
+	s64 wdiff = 0;
 
-	if (he->diff.computed)
-		wdiff = he->diff.wdiff;
-	else
-		wdiff = perf_diff__compute_wdiff(he);
+	if (pair) {
+		if (he->diff.computed)
+			wdiff = he->diff.wdiff;
+		else
+			wdiff = perf_diff__compute_wdiff(he, pair);
+	}
 
 	if (wdiff != 0)
 		scnprintf(buf, sizeof(buf), "%14ld", wdiff);
@@ -341,30 +351,6 @@ static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
 	return scnprintf(hpp->buf, hpp->size, fmt, buf);
 }
 
-static int hpp__header_displ(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "Displ.");
-}
-
-static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused)
-{
-	return 6;
-}
-
-static int hpp__entry_displ(struct perf_hpp *hpp,
-			    struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	long displacement = pair ? pair->position - he->position : 0;
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s";
-	char buf[32] = " ";
-
-	if (displacement)
-		scnprintf(buf, sizeof(buf), "%+4ld", displacement);
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
 static int hpp__header_formula(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%70s";
@@ -379,67 +365,80 @@ static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused)
 
 static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s";
 	char buf[96] = " ";
 
-	perf_diff__formula(buf, sizeof(buf), he);
+	if (pair)
+		perf_diff__formula(he, pair, buf, sizeof(buf));
+
 	return scnprintf(hpp->buf, hpp->size, fmt, buf);
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)		\
-	.header	= hpp__header_ ## _name,		\
-	.width	= hpp__width_ ## _name,		\
-	.color	= hpp__color_ ## _name,		\
-	.entry	= hpp__entry_ ## _name
+#define HPP__COLOR_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name		\
+	}
 
-#define HPP__PRINT_FNS(_name)			\
-	.header	= hpp__header_ ## _name,		\
-	.width	= hpp__width_ ## _name,		\
-	.entry	= hpp__entry_ ## _name
+#define HPP__PRINT_FNS(_name)				\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.entry	= hpp__entry_ ## _name		\
+	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	{ .cond = false, HPP__COLOR_PRINT_FNS(baseline) },
-	{ .cond = true,  HPP__COLOR_PRINT_FNS(overhead) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_sys) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) },
-	{ .cond = false, HPP__PRINT_FNS(samples) },
-	{ .cond = false, HPP__PRINT_FNS(period) },
-	{ .cond = false, HPP__PRINT_FNS(period_baseline) },
-	{ .cond = false, HPP__PRINT_FNS(delta) },
-	{ .cond = false, HPP__PRINT_FNS(ratio) },
-	{ .cond = false, HPP__PRINT_FNS(wdiff) },
-	{ .cond = false, HPP__PRINT_FNS(displ) },
-	{ .cond = false, HPP__PRINT_FNS(formula) }
+	HPP__COLOR_PRINT_FNS(baseline),
+	HPP__COLOR_PRINT_FNS(overhead),
+	HPP__COLOR_PRINT_FNS(overhead_sys),
+	HPP__COLOR_PRINT_FNS(overhead_us),
+	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS(overhead_guest_us),
+	HPP__PRINT_FNS(samples),
+	HPP__PRINT_FNS(period),
+	HPP__PRINT_FNS(period_baseline),
+	HPP__PRINT_FNS(delta),
+	HPP__PRINT_FNS(ratio),
+	HPP__PRINT_FNS(wdiff),
+	HPP__PRINT_FNS(formula)
 };
 
+LIST_HEAD(perf_hpp__list);
+
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__PRINT_FNS
 
 void perf_hpp__init(void)
 {
 	if (symbol_conf.show_cpu_utilization) {
-		perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true;
-		perf_hpp__format[PERF_HPP__OVERHEAD_US].cond = true;
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS);
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_US);
 
 		if (perf_guest) {
-			perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].cond = true;
-			perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].cond = true;
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_SYS);
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_US);
 		}
 	}
 
 	if (symbol_conf.show_nr_samples)
-		perf_hpp__format[PERF_HPP__SAMPLES].cond = true;
+		perf_hpp__column_enable(PERF_HPP__SAMPLES);
 
 	if (symbol_conf.show_total_period)
-		perf_hpp__format[PERF_HPP__PERIOD].cond = true;
+		perf_hpp__column_enable(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_enable(unsigned col, bool enable)
+void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	list_add_tail(&format->list, &perf_hpp__list);
+}
+
+void perf_hpp__column_enable(unsigned col)
 {
 	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__format[col].cond = enable;
+	perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
@@ -452,27 +451,29 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
 				bool color)
 {
 	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
 	char *start = hpp->buf;
-	int i, ret;
+	int ret;
 	bool first = true;
 
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
+	perf_hpp__for_each_format(fmt) {
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
 		if (!sep || !first) {
 			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
 			advance_hpp(hpp, ret);
+		} else
 			first = false;
-		}
 
-		if (color && perf_hpp__format[i].color)
-			ret = perf_hpp__format[i].color(hpp, he);
+		if (color && fmt->color)
+			ret = fmt->color(hpp, he);
 		else
-			ret = perf_hpp__format[i].entry(hpp, he);
+			ret = fmt->entry(hpp, he);
 
 		advance_hpp(hpp, ret);
 	}
@@ -504,16 +505,15 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size,
  */
 unsigned int hists__sort_list_width(struct hists *hists)
 {
+	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
-	int i, ret = 0;
+	int i = 0, ret = 0;
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
+	perf_hpp__for_each_format(fmt) {
 		if (i)
 			ret += 2;
 
-		ret += perf_hpp__format[i].width(NULL);
+		ret += fmt->width(NULL);
 	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list)
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ebb4cc107876..166f13df3134 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -30,6 +30,7 @@ void setup_browser(bool fallback_to_pager)
 		if (fallback_to_pager)
 			setup_pager();
 
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 		perf_hpp__init();
 		break;
 	}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index f0ee204f99bb..0eae3b2c32f2 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -335,13 +335,14 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, FILE *fp)
 {
+	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
 	const char *col_width = symbol_conf.col_width_list_str;
-	int idx, nr_rows = 0;
+	int nr_rows = 0;
 	char bf[96];
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
@@ -355,16 +356,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		goto print_entries;
 
 	fprintf(fp, "# ");
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		if (!perf_hpp__format[idx].cond)
-			continue;
 
+	perf_hpp__for_each_format(fmt) {
 		if (!first)
 			fprintf(fp, "%s", sep ?: "  ");
 		else
 			first = false;
 
-		perf_hpp__format[idx].header(&dummy_hpp);
+		fmt->header(&dummy_hpp);
 		fprintf(fp, "%s", bf);
 	}
 
@@ -400,18 +399,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	first = true;
 
 	fprintf(fp, "# ");
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		unsigned int i;
 
-		if (!perf_hpp__format[idx].cond)
-			continue;
+	perf_hpp__for_each_format(fmt) {
+		unsigned int i;
 
 		if (!first)
 			fprintf(fp, "%s", sep ?: "  ");
 		else
 			first = false;
 
-		width = perf_hpp__format[idx].width(&dummy_hpp);
+		width = fmt->width(&dummy_hpp);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 2884d2f41e33..1c8b9afd5d6e 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -8,6 +8,8 @@
 #include "../ui.h"
 #include "../libslang.h"
 
+char ui_helpline__last_msg[1024];
+
 static void tui_helpline__pop(void)
 {
 }
@@ -23,20 +25,7 @@ static void tui_helpline__push(const char *msg)
 	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
 }
 
-struct ui_helpline tui_helpline_fns = {
-	.pop	= tui_helpline__pop,
-	.push	= tui_helpline__push,
-};
-
-void ui_helpline__init(void)
-{
-	helpline_fns = &tui_helpline_fns;
-	ui_helpline__puts(" ");
-}
-
-char ui_helpline__last_msg[1024];
-
-int ui_helpline__show_help(const char *format, va_list ap)
+static int tui_helpline__show(const char *format, va_list ap)
 {
 	int ret;
 	static int backlog;
@@ -55,3 +44,15 @@ int ui_helpline__show_help(const char *format, va_list ap)
 
 	return ret;
 }
+
+struct ui_helpline tui_helpline_fns = {
+	.pop	= tui_helpline__pop,
+	.push	= tui_helpline__push,
+	.show	= tui_helpline__show,
+};
+
+void ui_helpline__init(void)
+{
+	helpline_fns = &tui_helpline_fns;
+	ui_helpline__puts(" ");
+}
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index 4f989774c8c6..3014a7cd5271 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -52,6 +52,16 @@ int ui__warning(const char *format, ...)
 	return ret;
 }
 
+int ui__error_paranoid(void)
+{
+	return ui__error("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");
+}
+
 
 /**
  * perf_error__register - Register error logging functions
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index eb340571e7d6..3ee9f67d5af0 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -143,4 +143,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 	cursor->curr = cursor->curr->next;
 	cursor->pos++;
 }
+
+struct option;
+
+int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+extern const char record_callchain_help[];
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 03f830b48148..399e74c34c1a 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -23,10 +23,8 @@ int eprintf(int level, const char *fmt, ...)
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		if (use_browser == 1)
-			ret = ui_helpline__show_help(fmt, args);
-		else if (use_browser == 2)
-			ret = perf_gtk__show_helpline(fmt, args);
+		if (use_browser >= 1)
+			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
 		va_end(args);
@@ -49,28 +47,6 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
-#if !defined(NEWT_SUPPORT) && !defined(GTK2_SUPPORT)
-int ui__warning(const char *format, ...)
-{
-	va_list args;
-
-	va_start(args, format);
-	vfprintf(stderr, format, args);
-	va_end(args);
-	return 0;
-}
-#endif
-
-int ui__error_paranoid(void)
-{
-	return ui__error("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 83e8d234af6b..6e2667fb8211 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -5,6 +5,8 @@
 #include <stdbool.h>
 #include "event.h"
 #include "../ui/helpline.h"
+#include "../ui/progress.h"
+#include "../ui/util.h"
 
 extern int verbose;
 extern bool quiet, dump_trace;
@@ -12,38 +14,7 @@ extern bool quiet, dump_trace;
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
-struct ui_progress;
-struct perf_error_ops;
-
-#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT)
-
-#include "../ui/progress.h"
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-#include "../ui/util.h"
-
-#else
-
-static inline void ui_progress__update(u64 curr __maybe_unused,
-				       u64 total __maybe_unused,
-				       const char *title __maybe_unused) {}
-static inline void ui_progress__finish(void) {}
-
-#define ui__error(format, arg...) ui__warning(format, ##arg)
-
-static inline int
-perf_error__register(struct perf_error_ops *eops __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-perf_error__unregister(struct perf_error_ops *eops __maybe_unused)
-{
-	return 0;
-}
-
-#endif /* NEWT_SUPPORT || GTK2_SUPPORT */
-
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 int ui__error_paranoid(void);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d6d9a465acdb..6f7d5a9d6b05 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -539,13 +539,13 @@ struct dso *__dsos__findnew(struct list_head *head, const char *name)
 }
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool with_hits)
+			       bool (skip)(struct dso *dso, int parm), int parm)
 {
 	struct dso *pos;
 	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
+		if (skip && skip(pos, parm))
 			continue;
 		ret += dso__fprintf_buildid(pos, fp);
 		ret += fprintf(fp, " %s\n", pos->long_name);
@@ -583,7 +583,7 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 	if (dso->short_name != dso->long_name)
 		ret += fprintf(fp, "%s, ", dso->long_name);
 	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       dso->loaded ? "" : "NOT ");
+		       dso__loaded(dso, type) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
 	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e03276940b99..450199ab51b5 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -138,7 +138,7 @@ struct dso *__dsos__findnew(struct list_head *head, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool with_hits);
+			       bool (skip)(struct dso *dso, int parm), int parm);
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 705293489e3c..dc8aee97a488 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -49,10 +49,16 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 	return evlist;
 }
 
-void perf_evlist__config_attrs(struct perf_evlist *evlist,
-			       struct perf_record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist,
+			struct perf_record_opts *opts)
 {
 	struct perf_evsel *evsel;
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
+	if (opts->group)
+		perf_evlist__set_leader(evlist);
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
@@ -61,7 +67,7 @@ void perf_evlist__config_attrs(struct perf_evlist *evlist,
 		perf_evsel__config(evsel, opts);
 
 		if (evlist->nr_entries > 1)
-			evsel->attr.sample_type |= PERF_SAMPLE_ID;
+			perf_evsel__set_sample_id(evsel);
 	}
 }
 
@@ -111,7 +117,6 @@ void __perf_evlist__set_leader(struct list_head *list)
 	struct perf_evsel *evsel, *leader;
 
 	leader = list_entry(list->next, struct perf_evsel, node);
-	leader->leader = NULL;
 
 	list_for_each_entry(evsel, list, node) {
 		if (evsel != leader)
@@ -222,7 +227,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
-			if (perf_evsel__is_group_member(pos))
+			if (!perf_evsel__is_group_leader(pos))
 				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
@@ -238,7 +243,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
-			if (perf_evsel__is_group_member(pos))
+			if (!perf_evsel__is_group_leader(pos))
 				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 56003f779e60..457e2350d21d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -76,8 +76,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
 
-void perf_evlist__config_attrs(struct perf_evlist *evlist,
-			       struct perf_record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist,
+			 struct perf_record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  struct perf_record_opts *opts,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1b16dd1edc8e..7a2a3dc3ff03 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -50,11 +50,36 @@ void hists__init(struct hists *hists)
 	pthread_mutex_init(&hists->lock, NULL);
 }
 
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit)
+{
+	if (!(evsel->attr.sample_type & bit)) {
+		evsel->attr.sample_type |= bit;
+		evsel->sample_size += sizeof(u64);
+	}
+}
+
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit)
+{
+	if (evsel->attr.sample_type & bit) {
+		evsel->attr.sample_type &= ~bit;
+		evsel->sample_size -= sizeof(u64);
+	}
+}
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel)
+{
+	perf_evsel__set_sample_bit(evsel, ID);
+	evsel->attr.read_format |= PERF_FORMAT_ID;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
 	evsel->attr	   = *attr;
+	evsel->leader	   = evsel;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
@@ -440,11 +465,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
-	attr->read_format   = PERF_FORMAT_TOTAL_TIME_ENABLED |
-			      PERF_FORMAT_TOTAL_TIME_RUNNING |
-			      PERF_FORMAT_ID;
 
-	attr->sample_type  |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	perf_evsel__set_sample_bit(evsel, IP);
+	perf_evsel__set_sample_bit(evsel, TID);
 
 	/*
 	 * We default some events to a 1 default interval. But keep
@@ -453,7 +476,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
-			attr->sample_type	|= PERF_SAMPLE_PERIOD;
+			perf_evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
@@ -468,16 +491,16 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		attr->inherit_stat = 1;
 
 	if (opts->sample_address) {
-		attr->sample_type	|= PERF_SAMPLE_ADDR;
+		perf_evsel__set_sample_bit(evsel, ADDR);
 		attr->mmap_data = track;
 	}
 
 	if (opts->call_graph) {
-		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;
+		perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
 		if (opts->call_graph == CALLCHAIN_DWARF) {
-			attr->sample_type |= PERF_SAMPLE_REGS_USER |
-					     PERF_SAMPLE_STACK_USER;
+			perf_evsel__set_sample_bit(evsel, REGS_USER);
+			perf_evsel__set_sample_bit(evsel, STACK_USER);
 			attr->sample_regs_user = PERF_REGS_MASK;
 			attr->sample_stack_user = opts->stack_dump_size;
 			attr->exclude_callchain_user = 1;
@@ -485,20 +508,20 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	}
 
 	if (perf_target__has_cpu(&opts->target))
-		attr->sample_type	|= PERF_SAMPLE_CPU;
+		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
-		attr->sample_type	|= PERF_SAMPLE_PERIOD;
+		perf_evsel__set_sample_bit(evsel, PERIOD);
 
 	if (!opts->sample_id_all_missing &&
 	    (opts->sample_time || !opts->no_inherit ||
 	     perf_target__has_cpu(&opts->target)))
-		attr->sample_type	|= PERF_SAMPLE_TIME;
+		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
-		attr->sample_type	|= PERF_SAMPLE_TIME;
-		attr->sample_type	|= PERF_SAMPLE_RAW;
-		attr->sample_type	|= PERF_SAMPLE_CPU;
+		perf_evsel__set_sample_bit(evsel, TIME);
+		perf_evsel__set_sample_bit(evsel, RAW);
+		perf_evsel__set_sample_bit(evsel, CPU);
 	}
 
 	if (opts->no_delay) {
@@ -506,7 +529,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		attr->wakeup_events = 1;
 	}
 	if (opts->branch_stack) {
-		attr->sample_type	|= PERF_SAMPLE_BRANCH_STACK;
+		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
@@ -519,14 +542,14 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	 * Disabling only independent events or group leaders,
 	 * keeping group members enabled.
 	 */
-	if (!perf_evsel__is_group_member(evsel))
+	if (perf_evsel__is_group_leader(evsel))
 		attr->disabled = 1;
 
 	/*
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (perf_target__none(&opts->target) && !perf_evsel__is_group_member(evsel))
+	if (perf_target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
 		attr->enable_on_exec = 1;
 }
 
@@ -707,7 +730,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
 	struct perf_evsel *leader = evsel->leader;
 	int fd;
 
-	if (!perf_evsel__is_group_member(evsel))
+	if (perf_evsel__is_group_leader(evsel))
 		return -1;
 
 	/*
@@ -1205,3 +1228,128 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 
 	return 0;
 }
+
+static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (!*first) {
+		ret += fprintf(fp, ",");
+	} else {
+		ret += fprintf(fp, ":");
+		*first = false;
+	}
+
+	va_start(args, fmt);
+	ret += vfprintf(fp, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value)
+{
+	if (value == 0)
+		return 0;
+
+	return comma_fprintf(fp, first, " %s: %" PRIu64, field, value);
+}
+
+#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field)
+
+struct bit_names {
+	int bit;
+	const char *name;
+};
+
+static int bits__fprintf(FILE *fp, const char *field, u64 value,
+			 struct bit_names *bits, bool *first)
+{
+	int i = 0, printed = comma_fprintf(fp, first, " %s: ", field);
+	bool first_bit = true;
+
+	do {
+		if (value & bits[i].bit) {
+			printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name);
+			first_bit = false;
+		}
+	} while (bits[++i].name != NULL);
+
+	return printed;
+}
+
+static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
+		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
+		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
+		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "sample_type", value, bits, first);
+}
+
+static int read_format__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_FORMAT_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
+		bit_name(ID), bit_name(GROUP),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "read_format", value, bits, first);
+}
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp)
+{
+	bool first = true;
+	int printed = fprintf(fp, "%s", perf_evsel__name(evsel));
+
+	if (details->verbose || details->freq) {
+		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
+					 (u64)evsel->attr.sample_freq);
+	}
+
+	if (details->verbose) {
+		if_print(type);
+		if_print(config);
+		if_print(config1);
+		if_print(config2);
+		if_print(size);
+		printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type);
+		if (evsel->attr.read_format)
+			printed += read_format__fprintf(fp, &first, evsel->attr.read_format);
+		if_print(disabled);
+		if_print(inherit);
+		if_print(pinned);
+		if_print(exclusive);
+		if_print(exclude_user);
+		if_print(exclude_kernel);
+		if_print(exclude_hv);
+		if_print(exclude_idle);
+		if_print(mmap);
+		if_print(comm);
+		if_print(freq);
+		if_print(inherit_stat);
+		if_print(enable_on_exec);
+		if_print(task);
+		if_print(watermark);
+		if_print(precise_ip);
+		if_print(mmap_data);
+		if_print(sample_id_all);
+		if_print(exclude_host);
+		if_print(exclude_guest);
+		if_print(__reserved_1);
+		if_print(wakeup_events);
+		if_print(bp_type);
+		if_print(branch_sample_type);
+	}
+
+	fputc('\n', fp);
+	return ++printed;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3d2b8017438c..9cb8a0215711 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -118,6 +118,19 @@ void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit);
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit);
+
+#define perf_evsel__set_sample_bit(evsel, bit) \
+	__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+#define perf_evsel__reset_sample_bit(evsel, bit) \
+	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			   const char *filter);
 
@@ -226,8 +239,16 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
 
-static inline bool perf_evsel__is_group_member(const struct perf_evsel *evsel)
+static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
 {
-	return evsel->leader != NULL;
+	return evsel->leader == evsel;
 }
+
+struct perf_attr_details {
+	bool freq;
+	bool verbose;
+};
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cb17e2a8c6ed..82df1b26f0d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -785,7 +785,7 @@ void hists__match(struct hists *leader, struct hists *other)
 		pair = hists__find_entry(other, pos);
 
 		if (pair)
-			hist__entry_add_pair(pos, pair);
+			hist_entry__add_pair(pair, pos);
 	}
 }
 
@@ -806,7 +806,7 @@ int hists__link(struct hists *leader, struct hists *other)
 			pair = hists__add_dummy_entry(leader, pos);
 			if (pair == NULL)
 				return -1;
-			hist__entry_add_pair(pair, pos);
+			hist_entry__add_pair(pos, pair);
 		}
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8b091a51e4a2..5b3b0075be64 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -126,13 +126,19 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
-	bool cond;
 	int (*header)(struct perf_hpp *hpp);
 	int (*width)(struct perf_hpp *hpp);
 	int (*color)(struct perf_hpp *hpp, struct hist_entry *he);
 	int (*entry)(struct perf_hpp *hpp, struct hist_entry *he);
+
+	struct list_head list;
 };
 
+extern struct list_head perf_hpp__list;
+
+#define perf_hpp__for_each_format(format) \
+	list_for_each_entry(format, &perf_hpp__list, list)
+
 extern struct perf_hpp_fmt perf_hpp__format[];
 
 enum {
@@ -148,14 +154,14 @@ enum {
 	PERF_HPP__DELTA,
 	PERF_HPP__RATIO,
 	PERF_HPP__WEIGHTED_DIFF,
-	PERF_HPP__DISPL,
 	PERF_HPP__FORMULA,
 
 	PERF_HPP__MAX_INDEX
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_enable(unsigned col, bool enable);
+void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_enable(unsigned col);
 int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
 				bool color);
 
@@ -219,8 +225,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
 
 unsigned int hists__sort_list_width(struct hists *self);
 
-double perf_diff__compute_delta(struct hist_entry *he);
-double perf_diff__compute_ratio(struct hist_entry *he);
-s64 perf_diff__compute_wdiff(struct hist_entry *he);
-int perf_diff__formula(char *buf, size_t size, struct hist_entry *he);
+double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair);
+double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair);
+s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair);
+int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
+		       char *buf, size_t size);
+double perf_diff__period_percent(struct hist_entry *he, u64 period);
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1f09d0581e6b..71fa90391fe4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1,10 +1,15 @@
+#include "callchain.h"
 #include "debug.h"
 #include "event.h"
+#include "evsel.h"
+#include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "sort.h"
 #include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
+#include "unwind.h"
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
@@ -48,6 +53,29 @@ static void dsos__delete(struct list_head *dsos)
 	}
 }
 
+void machine__delete_dead_threads(struct machine *machine)
+{
+	struct thread *n, *t;
+
+	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
+		list_del(&t->node);
+		thread__delete(t);
+	}
+}
+
+void machine__delete_threads(struct machine *machine)
+{
+	struct rb_node *nd = rb_first(&machine->threads);
+
+	while (nd) {
+		struct thread *t = rb_entry(nd, struct thread, rb_node);
+
+		rb_erase(&t->rb_node, &machine->threads);
+		nd = rb_next(nd);
+		thread__delete(t);
+	}
+}
+
 void machine__exit(struct machine *machine)
 {
 	map_groups__exit(&machine->kmaps);
@@ -264,6 +292,534 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+struct map *machine__new_module(struct machine *machine, u64 start,
+				const char *filename)
+{
+	struct map *map;
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+
+	if (dso == NULL)
+		return NULL;
+
+	map = map__new2(start, dso, MAP__FUNCTION);
+	if (map == NULL)
+		return NULL;
+
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+	map_groups__insert(&machine->kmaps, map);
+	return map;
+}
+
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
+{
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
+		ret += __dsos__fprintf(&pos->user_dsos, fp);
+	}
+
+	return ret;
+}
+
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
+	       __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+}
+
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm);
+	}
+	return ret;
+}
+
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
+
+	if (kdso->has_build_id) {
+		char filename[PATH_MAX];
+		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+			printed += fprintf(fp, "[0] %s\n", filename);
+	}
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n",
+				   i + kdso->has_build_id, vmlinux_path[i]);
+
+	return printed;
+}
+
+size_t machine__fprintf(struct machine *machine, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+
+		ret += thread__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+static struct dso *machine__get_kernel(struct machine *machine)
+{
+	const char *vmlinux_name = NULL;
+	struct dso *kernel;
+
+	if (machine__is_host(machine)) {
+		vmlinux_name = symbol_conf.vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = "[kernel.kallsyms]";
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[kernel]",
+					     DSO_TYPE_KERNEL);
+	} else {
+		char bf[PATH_MAX];
+
+		if (machine__is_default_guest(machine))
+			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = machine__mmap_name(machine, bf,
+							  sizeof(bf));
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[guest.kernel]",
+					     DSO_TYPE_GUEST_KERNEL);
+	}
+
+	if (kernel != NULL && (!kernel->has_build_id))
+		dso__read_running_kernel_build_id(kernel, machine);
+
+	return kernel;
+}
+
+struct process_args {
+	u64 start;
+};
+
+static int symbol__in_kernel(void *arg, const char *name,
+			     char type __maybe_unused, u64 start)
+{
+	struct process_args *args = arg;
+
+	if (strchr(name, '['))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+/* Figure out the start address of kernel map from /proc/kallsyms */
+static u64 machine__get_kernel_start_addr(struct machine *machine)
+{
+	const char *filename;
+	char path[PATH_MAX];
+	struct process_args args;
+
+	if (machine__is_host(machine)) {
+		filename = "/proc/kallsyms";
+	} else {
+		if (machine__is_default_guest(machine))
+			filename = (char *)symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+			filename = path;
+		}
+	}
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+		return 0;
+
+	return args.start;
+}
+
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+{
+	enum map_type type;
+	u64 start = machine__get_kernel_start_addr(machine);
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		if (machine->vmlinux_maps[type] == NULL)
+			return -1;
+
+		machine->vmlinux_maps[type]->map_ip =
+			machine->vmlinux_maps[type]->unmap_ip =
+				identity__map_ip;
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		kmap->kmaps = &machine->kmaps;
+		map_groups__insert(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+	}
+
+	return 0;
+}
+
+void machine__destroy_kernel_maps(struct machine *machine)
+{
+	enum map_type type;
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		if (machine->vmlinux_maps[type] == NULL)
+			continue;
+
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map_groups__remove(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+		if (kmap->ref_reloc_sym) {
+			/*
+			 * ref_reloc_sym is shared among all maps, so free just
+			 * on one of them.
+			 */
+			if (type == MAP__FUNCTION) {
+				free((char *)kmap->ref_reloc_sym->name);
+				kmap->ref_reloc_sym->name = NULL;
+				free(kmap->ref_reloc_sym);
+			}
+			kmap->ref_reloc_sym = NULL;
+		}
+
+		map__delete(machine->vmlinux_maps[type]);
+		machine->vmlinux_maps[type] = NULL;
+	}
+}
+
+int machines__create_guest_kernel_maps(struct rb_root *machines)
+{
+	int ret = 0;
+	struct dirent **namelist = NULL;
+	int i, items = 0;
+	char path[PATH_MAX];
+	pid_t pid;
+	char *endp;
+
+	if (symbol_conf.default_guest_vmlinux_name ||
+	    symbol_conf.default_guest_modules ||
+	    symbol_conf.default_guest_kallsyms) {
+		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
+	}
+
+	if (symbol_conf.guestmount) {
+		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
+		if (items <= 0)
+			return -ENOENT;
+		for (i = 0; i < items; i++) {
+			if (!isdigit(namelist[i]->d_name[0])) {
+				/* Filter out . and .. */
+				continue;
+			}
+			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
+			if ((*endp != '\0') ||
+			    (endp == namelist[i]->d_name) ||
+			    (errno == ERANGE)) {
+				pr_debug("invalid directory (%s). Skipping.\n",
+					 namelist[i]->d_name);
+				continue;
+			}
+			sprintf(path, "%s/%s/proc/kallsyms",
+				symbol_conf.guestmount,
+				namelist[i]->d_name);
+			ret = access(path, R_OK);
+			if (ret) {
+				pr_debug("Can't access file %s\n", path);
+				goto failure;
+			}
+			machines__create_kernel_maps(machines, pid);
+		}
+failure:
+		free(namelist);
+	}
+
+	return ret;
+}
+
+void machines__destroy_guest_kernel_maps(struct rb_root *machines)
+{
+	struct rb_node *next = rb_first(machines);
+
+	while (next) {
+		struct machine *pos = rb_entry(next, struct machine, rb_node);
+
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, machines);
+		machine__delete(pos);
+	}
+}
+
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
+{
+	struct machine *machine = machines__findnew(machines, pid);
+
+	if (machine == NULL)
+		return -1;
+
+	return machine__create_kernel_maps(machine);
+}
+
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		/*
+		 * Since /proc/kallsyms will have multiple sessions for the
+		 * kernel, with modules between them, fixup the end of all
+		 * sections.
+		 */
+		__map_groups__fixup_end(&machine->kmaps, type);
+	}
+
+	return ret;
+}
+
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
+			       symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		map__reloc_vmlinux(map);
+	}
+
+	return ret;
+}
+
+static void map_groups__fixup_end(struct map_groups *mg)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		__map_groups__fixup_end(mg, i);
+}
+
+static char *get_kernel_version(const char *root_dir)
+{
+	char version[PATH_MAX];
+	FILE *file;
+	char *name, *tmp;
+	const char *prefix = "Linux version ";
+
+	sprintf(version, "%s/proc/version", root_dir);
+	file = fopen(version, "r");
+	if (!file)
+		return NULL;
+
+	version[0] = '\0';
+	tmp = fgets(version, sizeof(version), file);
+	fclose(file);
+
+	name = strstr(version, prefix);
+	if (!name)
+		return NULL;
+	name += strlen(prefix);
+	tmp = strchr(name, ' ');
+	if (tmp)
+		*tmp = '\0';
+
+	return strdup(name);
+}
+
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
+				const char *dir_name)
+{
+	struct dirent *dent;
+	DIR *dir = opendir(dir_name);
+	int ret = 0;
+
+	if (!dir) {
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
+		return -1;
+	}
+
+	while ((dent = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		struct stat st;
+
+		/*sshfs might return bad dent->d_type, so we have to stat*/
+		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (S_ISDIR(st.st_mode)) {
+			if (!strcmp(dent->d_name, ".") ||
+			    !strcmp(dent->d_name, ".."))
+				continue;
+
+			ret = map_groups__set_modules_path_dir(mg, path);
+			if (ret < 0)
+				goto out;
+		} else {
+			char *dot = strrchr(dent->d_name, '.'),
+			     dso_name[PATH_MAX];
+			struct map *map;
+			char *long_name;
+
+			if (dot == NULL || strcmp(dot, ".ko"))
+				continue;
+			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
+				 (int)(dot - dent->d_name), dent->d_name);
+
+			strxfrchar(dso_name, '-', '_');
+			map = map_groups__find_by_name(mg, MAP__FUNCTION,
+						       dso_name);
+			if (map == NULL)
+				continue;
+
+			long_name = strdup(path);
+			if (long_name == NULL) {
+				ret = -1;
+				goto out;
+			}
+			dso__set_long_name(map->dso, long_name);
+			map->dso->lname_alloc = 1;
+			dso__kernel_module_get_build_id(map->dso, "");
+		}
+	}
+
+out:
+	closedir(dir);
+	return ret;
+}
+
+static int machine__set_modules_path(struct machine *machine)
+{
+	char *version;
+	char modules_path[PATH_MAX];
+
+	version = get_kernel_version(machine->root_dir);
+	if (!version)
+		return -1;
+
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+		 machine->root_dir, version);
+	free(version);
+
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
+}
+
+static int machine__create_modules(struct machine *machine)
+{
+	char *line = NULL;
+	size_t n;
+	FILE *file;
+	struct map *map;
+	const char *modules;
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine))
+		modules = symbol_conf.default_guest_modules;
+	else {
+		sprintf(path, "%s/proc/modules", machine->root_dir);
+		modules = path;
+	}
+
+	if (symbol__restricted_filename(path, "/proc/modules"))
+		return -1;
+
+	file = fopen(modules, "r");
+	if (file == NULL)
+		return -1;
+
+	while (!feof(file)) {
+		char name[PATH_MAX];
+		u64 start;
+		char *sep;
+		int line_len;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0)
+			break;
+
+		if (!line)
+			goto out_failure;
+
+		line[--line_len] = '\0'; /* \n */
+
+		sep = strrchr(line, 'x');
+		if (sep == NULL)
+			continue;
+
+		hex2u64(sep + 1, &start);
+
+		sep = strchr(line, ' ');
+		if (sep == NULL)
+			continue;
+
+		*sep = '\0';
+
+		snprintf(name, sizeof(name), "[%s]", line);
+		map = machine__new_module(machine, start, name);
+		if (map == NULL)
+			goto out_delete_line;
+		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
+	}
+
+	free(line);
+	fclose(file);
+
+	return machine__set_modules_path(machine);
+
+out_delete_line:
+	free(line);
+out_failure:
+	return -1;
+}
+
+int machine__create_kernel_maps(struct machine *machine)
+{
+	struct dso *kernel = machine__get_kernel(machine);
+
+	if (kernel == NULL ||
+	    __machine__create_kernel_maps(machine, kernel) < 0)
+		return -1;
+
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&machine->kmaps);
+	return 0;
+}
+
 static void machine__set_kernel_mmap_len(struct machine *machine,
 					 union perf_event *event)
 {
@@ -462,3 +1018,189 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 
 	return ret;
 }
+
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
+static bool symbol__match_parent_regex(struct symbol *sym)
+{
+	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+		return 1;
+
+	return 0;
+}
+
+static const u8 cpumodes[] = {
+	PERF_RECORD_MISC_USER,
+	PERF_RECORD_MISC_KERNEL,
+	PERF_RECORD_MISC_GUEST_USER,
+	PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+	size_t i;
+	u8 m;
+
+	memset(&al, 0, sizeof(al));
+
+	for (i = 0; i < NCPUMODES; i++) {
+		m = cpumodes[i];
+		/*
+		 * We cannot use the header.misc hint to determine whether a
+		 * branch stack address is user, kernel, guest, hypervisor.
+		 * Branches may straddle the kernel/user/hypervisor boundaries.
+		 * Thus, we have to try consecutively until we find a match
+		 * or else, the symbol is unknown
+		 */
+		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
+				ip, &al, NULL);
+		if (al.sym)
+			goto found;
+	}
+found:
+	ams->addr = ip;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *machine,
+					    struct thread *thr,
+					    struct branch_stack *bs)
+{
+	struct branch_info *bi;
+	unsigned int i;
+
+	bi = calloc(bs->nr, sizeof(struct branch_info));
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
+static int machine__resolve_callchain_sample(struct machine *machine,
+					     struct thread *thread,
+					     struct ip_callchain *chain,
+					     struct symbol **parent)
+
+{
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	unsigned int i;
+	int err;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+		pr_warning("corrupted callchain. skipping...\n");
+		return 0;
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
+		struct addr_location al;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				callchain_cursor_reset(&callchain_cursor);
+				return 0;
+			}
+			continue;
+		}
+
+		al.filtered = false;
+		thread__find_addr_location(thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &al, NULL);
+		if (al.sym != NULL) {
+			if (sort__has_parent && !*parent &&
+			    symbol__match_parent_regex(al.sym))
+				*parent = al.sym;
+			if (!symbol_conf.use_callchain)
+				break;
+		}
+
+		err = callchain_cursor_append(&callchain_cursor,
+					      ip, al.map, al.sym);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	struct callchain_cursor *cursor = arg;
+	return callchain_cursor_append(cursor, entry->ip,
+				       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent)
+
+{
+	int ret;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	ret = machine__resolve_callchain_sample(machine, thread,
+						sample->callchain, parent);
+	if (ret)
+		return ret;
+
+	/* Can we do dwarf post unwind? */
+	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+		return 0;
+
+	/* Bail out if nothing was captured. */
+	if ((!sample->user_regs.regs) ||
+	    (!sample->user_stack.size))
+		return 0;
+
+	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+				   thread, evsel->attr.sample_regs_user,
+				   sample);
+
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b7cde7467d55..e11236878ec1 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -61,9 +61,10 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
+void machine__delete_dead_threads(struct machine *machine);
+void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
 
-
 struct branch_info *machine__resolve_bstack(struct machine *machine,
 					    struct thread *thread,
 					    struct branch_stack *bs);
@@ -129,11 +130,11 @@ int machine__load_kallsyms(struct machine *machine, const char *filename,
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter);
 
-size_t machine__fprintf_dsos_buildid(struct machine *machine,
-				     FILE *fp, bool with_hits);
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
 size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
-				      FILE *fp, bool with_hits);
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
 
 void machine__destroy_kernel_maps(struct machine *machine);
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ce6f51162386..76d6e257b8a4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,7 +16,6 @@
 #include "cpumap.h"
 #include "event-parse.h"
 #include "perf_regs.h"
-#include "unwind.h"
 #include "vdso.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
@@ -128,15 +127,6 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 		goto out;
 
 	memcpy(self->filename, filename, len);
-	/*
-	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
-	 * slices. On 32bit we use 32MB.
-	 */
-#if BITS_PER_LONG == 64
-	self->mmap_window = ULLONG_MAX;
-#else
-	self->mmap_window = 32 * 1024 * 1024ULL;
-#endif
 	self->machines = RB_ROOT;
 	self->repipe = repipe;
 	INIT_LIST_HEAD(&self->ordered_samples.samples);
@@ -171,236 +161,44 @@ out_delete:
 	return NULL;
 }
 
-static void machine__delete_dead_threads(struct machine *machine)
-{
-	struct thread *n, *t;
-
-	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
-		list_del(&t->node);
-		thread__delete(t);
-	}
-}
-
 static void perf_session__delete_dead_threads(struct perf_session *session)
 {
 	machine__delete_dead_threads(&session->host_machine);
 }
 
-static void machine__delete_threads(struct machine *self)
-{
-	struct rb_node *nd = rb_first(&self->threads);
-
-	while (nd) {
-		struct thread *t = rb_entry(nd, struct thread, rb_node);
-
-		rb_erase(&t->rb_node, &self->threads);
-		nd = rb_next(nd);
-		thread__delete(t);
-	}
-}
-
 static void perf_session__delete_threads(struct perf_session *session)
 {
 	machine__delete_threads(&session->host_machine);
 }
 
+static void perf_session_env__delete(struct perf_session_env *env)
+{
+	free(env->hostname);
+	free(env->os_release);
+	free(env->version);
+	free(env->arch);
+	free(env->cpu_desc);
+	free(env->cpuid);
+
+	free(env->cmdline);
+	free(env->sibling_cores);
+	free(env->sibling_threads);
+	free(env->numa_nodes);
+	free(env->pmu_mappings);
+}
+
 void perf_session__delete(struct perf_session *self)
 {
 	perf_session__destroy_kernel_maps(self);
 	perf_session__delete_dead_threads(self);
 	perf_session__delete_threads(self);
+	perf_session_env__delete(&self->header.env);
 	machine__exit(&self->host_machine);
 	close(self->fd);
 	free(self);
 	vdso__exit();
 }
 
-void machine__remove_thread(struct machine *self, struct thread *th)
-{
-	self->last_match = NULL;
-	rb_erase(&th->rb_node, &self->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &self->dead_threads);
-}
-
-static bool symbol__match_parent_regex(struct symbol *sym)
-{
-	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
-		return 1;
-
-	return 0;
-}
-
-static const u8 cpumodes[] = {
-	PERF_RECORD_MISC_USER,
-	PERF_RECORD_MISC_KERNEL,
-	PERF_RECORD_MISC_GUEST_USER,
-	PERF_RECORD_MISC_GUEST_KERNEL
-};
-#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
-
-static void ip__resolve_ams(struct machine *self, struct thread *thread,
-			    struct addr_map_symbol *ams,
-			    u64 ip)
-{
-	struct addr_location al;
-	size_t i;
-	u8 m;
-
-	memset(&al, 0, sizeof(al));
-
-	for (i = 0; i < NCPUMODES; i++) {
-		m = cpumodes[i];
-		/*
-		 * We cannot use the header.misc hint to determine whether a
-		 * branch stack address is user, kernel, guest, hypervisor.
-		 * Branches may straddle the kernel/user/hypervisor boundaries.
-		 * Thus, we have to try consecutively until we find a match
-		 * or else, the symbol is unknown
-		 */
-		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
-				ip, &al, NULL);
-		if (al.sym)
-			goto found;
-	}
-found:
-	ams->addr = ip;
-	ams->al_addr = al.addr;
-	ams->sym = al.sym;
-	ams->map = al.map;
-}
-
-struct branch_info *machine__resolve_bstack(struct machine *self,
-					    struct thread *thr,
-					    struct branch_stack *bs)
-{
-	struct branch_info *bi;
-	unsigned int i;
-
-	bi = calloc(bs->nr, sizeof(struct branch_info));
-	if (!bi)
-		return NULL;
-
-	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
-		bi[i].flags = bs->entries[i].flags;
-	}
-	return bi;
-}
-
-static int machine__resolve_callchain_sample(struct machine *machine,
-					     struct thread *thread,
-					     struct ip_callchain *chain,
-					     struct symbol **parent)
-
-{
-	u8 cpumode = PERF_RECORD_MISC_USER;
-	unsigned int i;
-	int err;
-
-	callchain_cursor_reset(&callchain_cursor);
-
-	if (chain->nr > PERF_MAX_STACK_DEPTH) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = 0; i < chain->nr; i++) {
-		u64 ip;
-		struct addr_location al;
-
-		if (callchain_param.order == ORDER_CALLEE)
-			ip = chain->ips[i];
-		else
-			ip = chain->ips[chain->nr - i - 1];
-
-		if (ip >= PERF_CONTEXT_MAX) {
-			switch (ip) {
-			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;
-				break;
-			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;
-				break;
-			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;
-				break;
-			default:
-				pr_debug("invalid callchain context: "
-					 "%"PRId64"\n", (s64) ip);
-				/*
-				 * It seems the callchain is corrupted.
-				 * Discard all.
-				 */
-				callchain_cursor_reset(&callchain_cursor);
-				return 0;
-			}
-			continue;
-		}
-
-		al.filtered = false;
-		thread__find_addr_location(thread, machine, cpumode,
-					   MAP__FUNCTION, ip, &al, NULL);
-		if (al.sym != NULL) {
-			if (sort__has_parent && !*parent &&
-			    symbol__match_parent_regex(al.sym))
-				*parent = al.sym;
-			if (!symbol_conf.use_callchain)
-				break;
-		}
-
-		err = callchain_cursor_append(&callchain_cursor,
-					      ip, al.map, al.sym);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int unwind_entry(struct unwind_entry *entry, void *arg)
-{
-	struct callchain_cursor *cursor = arg;
-	return callchain_cursor_append(cursor, entry->ip,
-				       entry->map, entry->sym);
-}
-
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent)
-
-{
-	int ret;
-
-	callchain_cursor_reset(&callchain_cursor);
-
-	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent);
-	if (ret)
-		return ret;
-
-	/* Can we do dwarf post unwind? */
-	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
-	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
-		return 0;
-
-	/* Bail out if nothing was captured. */
-	if ((!sample->user_regs.regs) ||
-	    (!sample->user_stack.size))
-		return 0;
-
-	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
-				   thread, evsel->attr.sample_regs_user,
-				   sample);
-
-}
-
 static int process_event_synth_tracing_data_stub(union perf_event *event
 						 __maybe_unused,
 						 struct perf_session *session
@@ -1369,6 +1167,18 @@ fetch_mmaped_event(struct perf_session *session,
 	return event;
 }
 
+/*
+ * On 64bit we can mmap the data file in one go. No need for tiny mmap
+ * slices. On 32bit we use 32MB.
+ */
+#if BITS_PER_LONG == 64
+#define MMAP_SIZE ULLONG_MAX
+#define NUM_MMAPS 1
+#else
+#define MMAP_SIZE (32 * 1024 * 1024ULL)
+#define NUM_MMAPS 128
+#endif
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_tool *tool)
@@ -1376,7 +1186,7 @@ int __perf_session__process_events(struct perf_session *session,
 	u64 head, page_offset, file_offset, file_pos, progress_next;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
-	char *buf, *mmaps[8];
+	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
 	uint32_t size;
 
@@ -1391,7 +1201,7 @@ int __perf_session__process_events(struct perf_session *session,
 
 	progress_next = file_size / 16;
 
-	mmap_size = session->mmap_window;
+	mmap_size = MMAP_SIZE;
 	if (mmap_size > file_size)
 		mmap_size = file_size;
 
@@ -1532,10 +1342,10 @@ size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
 }
 
 size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
-					  bool with_hits)
+					  bool (skip)(struct dso *dso, int parm), int parm)
 {
-	size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
-	return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
+	size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, skip, parm);
+	return ret + machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm);
 }
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index cea133a6bdf1..8c2302504199 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -30,7 +30,6 @@ struct ordered_samples {
 struct perf_session {
 	struct perf_header	header;
 	unsigned long		size;
-	unsigned long		mmap_window;
 	struct machine		host_machine;
 	struct rb_root		machines;
 	struct perf_evlist	*evlist;
@@ -116,8 +115,8 @@ size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
 
 size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
 
-size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
-					  FILE *fp, bool with_hits);
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
+					  bool (fn)(struct dso *dso, int parm), int parm);
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b4e8c3ba559d..a1c0d56b6885 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -55,9 +55,6 @@ struct he_stat {
 struct hist_entry_diff {
 	bool	computed;
 
-	/* PERF_HPP__DISPL */
-	int	displacement;
-
 	/* PERF_HPP__DELTA */
 	double	period_ratio_delta;
 
@@ -118,7 +115,7 @@ static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
 	return NULL;
 }
 
-static inline void hist__entry_add_pair(struct hist_entry *he,
+static inline void hist_entry__add_pair(struct hist_entry *he,
 					struct hist_entry *pair)
 {
 	list_add_tail(&he->pairs.head, &pair->pairs.node);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index db0cc92cf2ea..f63557b59c06 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -718,6 +718,17 @@ int dso__load_sym(struct dso *dso, struct map *map,
 					sym.st_value);
 			used_opd = true;
 		}
+		/*
+		 * When loading symbols in a data mapping, ABS symbols (which
+		 * has a value of SHN_ABS in its st_shndx) failed at
+		 * elf_getscn().  And it marks the loading as a failure so
+		 * already loaded symbols cannot be fixed up.
+		 *
+		 * I'm not sure what should be done. Just ignore them for now.
+		 * - Namhyung Kim
+		 */
+		if (sym.st_shndx == SHN_ABS)
+			continue;
 
 		sec = elf_getscn(runtime_ss->elf, sym.st_shndx);
 		if (!sec)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 295f8d4feedf..2960284d6ae1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -28,8 +28,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 			symbol_filter_t filter);
-static int vmlinux_path__nr_entries;
-static char **vmlinux_path;
+int vmlinux_path__nr_entries;
+char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
 	.exclude_other	  = true,
@@ -202,13 +202,6 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	curr->end = ~0ULL;
 }
 
-static void map_groups__fixup_end(struct map_groups *mg)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(mg, i);
-}
-
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
@@ -652,8 +645,8 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	return count + moved;
 }
 
-static bool symbol__restricted_filename(const char *filename,
-					const char *restricted_filename)
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename)
 {
 	bool restricted = false;
 
@@ -887,200 +880,6 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 	return NULL;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *mg,
-				const char *dir_name)
-{
-	struct dirent *dent;
-	DIR *dir = opendir(dir_name);
-	int ret = 0;
-
-	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
-		return -1;
-	}
-
-	while ((dent = readdir(dir)) != NULL) {
-		char path[PATH_MAX];
-		struct stat st;
-
-		/*sshfs might return bad dent->d_type, so we have to stat*/
-		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
-		if (stat(path, &st))
-			continue;
-
-		if (S_ISDIR(st.st_mode)) {
-			if (!strcmp(dent->d_name, ".") ||
-			    !strcmp(dent->d_name, ".."))
-				continue;
-
-			ret = map_groups__set_modules_path_dir(mg, path);
-			if (ret < 0)
-				goto out;
-		} else {
-			char *dot = strrchr(dent->d_name, '.'),
-			     dso_name[PATH_MAX];
-			struct map *map;
-			char *long_name;
-
-			if (dot == NULL || strcmp(dot, ".ko"))
-				continue;
-			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
-				 (int)(dot - dent->d_name), dent->d_name);
-
-			strxfrchar(dso_name, '-', '_');
-			map = map_groups__find_by_name(mg, MAP__FUNCTION,
-						       dso_name);
-			if (map == NULL)
-				continue;
-
-			long_name = strdup(path);
-			if (long_name == NULL) {
-				ret = -1;
-				goto out;
-			}
-			dso__set_long_name(map->dso, long_name);
-			map->dso->lname_alloc = 1;
-			dso__kernel_module_get_build_id(map->dso, "");
-		}
-	}
-
-out:
-	closedir(dir);
-	return ret;
-}
-
-static char *get_kernel_version(const char *root_dir)
-{
-	char version[PATH_MAX];
-	FILE *file;
-	char *name, *tmp;
-	const char *prefix = "Linux version ";
-
-	sprintf(version, "%s/proc/version", root_dir);
-	file = fopen(version, "r");
-	if (!file)
-		return NULL;
-
-	version[0] = '\0';
-	tmp = fgets(version, sizeof(version), file);
-	fclose(file);
-
-	name = strstr(version, prefix);
-	if (!name)
-		return NULL;
-	name += strlen(prefix);
-	tmp = strchr(name, ' ');
-	if (tmp)
-		*tmp = '\0';
-
-	return strdup(name);
-}
-
-static int machine__set_modules_path(struct machine *machine)
-{
-	char *version;
-	char modules_path[PATH_MAX];
-
-	version = get_kernel_version(machine->root_dir);
-	if (!version)
-		return -1;
-
-	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-		 machine->root_dir, version);
-	free(version);
-
-	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
-}
-
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename)
-{
-	struct map *map;
-	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
-
-	if (dso == NULL)
-		return NULL;
-
-	map = map__new2(start, dso, MAP__FUNCTION);
-	if (map == NULL)
-		return NULL;
-
-	if (machine__is_host(machine))
-		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-	else
-		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-	map_groups__insert(&machine->kmaps, map);
-	return map;
-}
-
-static int machine__create_modules(struct machine *machine)
-{
-	char *line = NULL;
-	size_t n;
-	FILE *file;
-	struct map *map;
-	const char *modules;
-	char path[PATH_MAX];
-
-	if (machine__is_default_guest(machine))
-		modules = symbol_conf.default_guest_modules;
-	else {
-		sprintf(path, "%s/proc/modules", machine->root_dir);
-		modules = path;
-	}
-
-	if (symbol__restricted_filename(path, "/proc/modules"))
-		return -1;
-
-	file = fopen(modules, "r");
-	if (file == NULL)
-		return -1;
-
-	while (!feof(file)) {
-		char name[PATH_MAX];
-		u64 start;
-		char *sep;
-		int line_len;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0)
-			break;
-
-		if (!line)
-			goto out_failure;
-
-		line[--line_len] = '\0'; /* \n */
-
-		sep = strrchr(line, 'x');
-		if (sep == NULL)
-			continue;
-
-		hex2u64(sep + 1, &start);
-
-		sep = strchr(line, ' ');
-		if (sep == NULL)
-			continue;
-
-		*sep = '\0';
-
-		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(machine, start, name);
-		if (map == NULL)
-			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
-	}
-
-	free(line);
-	fclose(file);
-
-	return machine__set_modules_path(machine);
-
-out_delete_line:
-	free(line);
-out_failure:
-	return -1;
-}
-
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter)
 {
@@ -1300,195 +1099,6 @@ out_try_fixup:
 	return err;
 }
 
-size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
-		ret += __dsos__fprintf(&pos->user_dsos, fp);
-	}
-
-	return ret;
-}
-
-size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
-				     bool with_hits)
-{
-	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
-	       __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
-}
-
-size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
-				      FILE *fp, bool with_hits)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
-	}
-	return ret;
-}
-
-static struct dso *machine__get_kernel(struct machine *machine)
-{
-	const char *vmlinux_name = NULL;
-	struct dso *kernel;
-
-	if (machine__is_host(machine)) {
-		vmlinux_name = symbol_conf.vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = "[kernel.kallsyms]";
-
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[kernel]",
-					     DSO_TYPE_KERNEL);
-	} else {
-		char bf[PATH_MAX];
-
-		if (machine__is_default_guest(machine))
-			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = machine__mmap_name(machine, bf,
-							  sizeof(bf));
-
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[guest.kernel]",
-					     DSO_TYPE_GUEST_KERNEL);
-	}
-
-	if (kernel != NULL && (!kernel->has_build_id))
-		dso__read_running_kernel_build_id(kernel, machine);
-
-	return kernel;
-}
-
-struct process_args {
-	u64 start;
-};
-
-static int symbol__in_kernel(void *arg, const char *name,
-			     char type __maybe_unused, u64 start)
-{
-	struct process_args *args = arg;
-
-	if (strchr(name, '['))
-		return 0;
-
-	args->start = start;
-	return 1;
-}
-
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
-{
-	const char *filename;
-	char path[PATH_MAX];
-	struct process_args args;
-
-	if (machine__is_host(machine)) {
-		filename = "/proc/kallsyms";
-	} else {
-		if (machine__is_default_guest(machine))
-			filename = (char *)symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
-	}
-
-	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
-		return 0;
-
-	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
-		return 0;
-
-	return args.start;
-}
-
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
-{
-	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine);
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-
-		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
-		if (machine->vmlinux_maps[type] == NULL)
-			return -1;
-
-		machine->vmlinux_maps[type]->map_ip =
-			machine->vmlinux_maps[type]->unmap_ip =
-				identity__map_ip;
-		kmap = map__kmap(machine->vmlinux_maps[type]);
-		kmap->kmaps = &machine->kmaps;
-		map_groups__insert(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
-	}
-
-	return 0;
-}
-
-void machine__destroy_kernel_maps(struct machine *machine)
-{
-	enum map_type type;
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-
-		if (machine->vmlinux_maps[type] == NULL)
-			continue;
-
-		kmap = map__kmap(machine->vmlinux_maps[type]);
-		map_groups__remove(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
-		if (kmap->ref_reloc_sym) {
-			/*
-			 * ref_reloc_sym is shared among all maps, so free just
-			 * on one of them.
-			 */
-			if (type == MAP__FUNCTION) {
-				free((char *)kmap->ref_reloc_sym->name);
-				kmap->ref_reloc_sym->name = NULL;
-				free(kmap->ref_reloc_sym);
-			}
-			kmap->ref_reloc_sym = NULL;
-		}
-
-		map__delete(machine->vmlinux_maps[type]);
-		machine->vmlinux_maps[type] = NULL;
-	}
-}
-
-int machine__create_kernel_maps(struct machine *machine)
-{
-	struct dso *kernel = machine__get_kernel(machine);
-
-	if (kernel == NULL ||
-	    __machine__create_kernel_maps(machine, kernel) < 0)
-		return -1;
-
-	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
-		if (machine__is_host(machine))
-			pr_debug("Problems creating module maps, "
-				 "continuing anyway...\n");
-		else
-			pr_debug("Problems creating module maps for guest %d, "
-				 "continuing anyway...\n", machine->pid);
-	}
-
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
-	return 0;
-}
-
 static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0) {
@@ -1549,25 +1159,6 @@ out_fail:
 	return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
-{
-	int i;
-	size_t printed = 0;
-	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
-
-	if (kdso->has_build_id) {
-		char filename[PATH_MAX];
-		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
-			printed += fprintf(fp, "[0] %s\n", filename);
-	}
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i)
-		printed += fprintf(fp, "[%d] %s\n",
-				   i + kdso->has_build_id, vmlinux_path[i]);
-
-	return printed;
-}
-
 static int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
@@ -1671,108 +1262,3 @@ void symbol__exit(void)
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }
-
-int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
-{
-	struct machine *machine = machines__findnew(machines, pid);
-
-	if (machine == NULL)
-		return -1;
-
-	return machine__create_kernel_maps(machine);
-}
-
-int machines__create_guest_kernel_maps(struct rb_root *machines)
-{
-	int ret = 0;
-	struct dirent **namelist = NULL;
-	int i, items = 0;
-	char path[PATH_MAX];
-	pid_t pid;
-	char *endp;
-
-	if (symbol_conf.default_guest_vmlinux_name ||
-	    symbol_conf.default_guest_modules ||
-	    symbol_conf.default_guest_kallsyms) {
-		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
-	}
-
-	if (symbol_conf.guestmount) {
-		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
-		if (items <= 0)
-			return -ENOENT;
-		for (i = 0; i < items; i++) {
-			if (!isdigit(namelist[i]->d_name[0])) {
-				/* Filter out . and .. */
-				continue;
-			}
-			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
-			if ((*endp != '\0') ||
-			    (endp == namelist[i]->d_name) ||
-			    (errno == ERANGE)) {
-				pr_debug("invalid directory (%s). Skipping.\n",
-					 namelist[i]->d_name);
-				continue;
-			}
-			sprintf(path, "%s/%s/proc/kallsyms",
-				symbol_conf.guestmount,
-				namelist[i]->d_name);
-			ret = access(path, R_OK);
-			if (ret) {
-				pr_debug("Can't access file %s\n", path);
-				goto failure;
-			}
-			machines__create_kernel_maps(machines, pid);
-		}
-failure:
-		free(namelist);
-	}
-
-	return ret;
-}
-
-void machines__destroy_guest_kernel_maps(struct rb_root *machines)
-{
-	struct rb_node *next = rb_first(machines);
-
-	while (next) {
-		struct machine *pos = rb_entry(next, struct machine, rb_node);
-
-		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, machines);
-		machine__delete(pos);
-	}
-}
-
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
-{
-	struct map *map = machine->vmlinux_maps[type];
-	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		/*
-		 * Since /proc/kallsyms will have multiple sessions for the
-		 * kernel, with modules between them, fixup the end of all
-		 * sections.
-		 */
-		__map_groups__fixup_end(&machine->kmaps, type);
-	}
-
-	return ret;
-}
-
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter)
-{
-	struct map *map = machine->vmlinux_maps[type];
-	int ret = dso__load_vmlinux_path(map->dso, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		map__reloc_vmlinux(map);
-	}
-
-	return ret;
-}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index de68f98b236d..ec7b2405c377 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -120,6 +120,8 @@ struct symbol_conf {
 };
 
 extern struct symbol_conf symbol_conf;
+extern int vmlinux_path__nr_entries;
+extern char **vmlinux_path;
 
 static inline void *symbol__priv(struct symbol *sym)
 {
@@ -223,6 +225,8 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym,
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index df59623ac763..632e40e5ceca 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -54,10 +54,10 @@ int thread__comm_len(struct thread *self)
 	return self->comm_len;
 }
 
-static size_t thread__fprintf(struct thread *self, FILE *fp)
+size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, verbose, fp);
+	return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) +
+	       map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
 void thread__insert_map(struct thread *self, struct map *map)
@@ -84,17 +84,3 @@ int thread__fork(struct thread *self, struct thread *parent)
 			return -ENOMEM;
 	return 0;
 }
-
-size_t machine__fprintf(struct machine *machine, FILE *fp)
-{
-	size_t ret = 0;
-	struct rb_node *nd;
-
-	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
-
-		ret += thread__fprintf(pos, fp);
-	}
-
-	return ret;
-}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index f2fa17caa7d5..5ad266403098 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -30,6 +30,7 @@ int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 void thread__insert_map(struct thread *self, struct map *map);
 int thread__fork(struct thread *self, struct thread *parent);
+size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 static inline struct map *thread__find_map(struct thread *self,
 					   enum map_type type, u64 addr)
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 884dde9b9bc1..54d37a4753c5 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -26,6 +26,8 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	float samples_per_sec = top->samples / top->delay_secs;
 	float ksamples_per_sec = top->kernel_samples / top->delay_secs;
 	float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	struct perf_record_opts *opts = &top->record_opts;
+	struct perf_target *target = &opts->target;
 	size_t ret = 0;
 
 	if (!perf_guest) {
@@ -61,31 +63,31 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 		struct perf_evsel *first = perf_evlist__first(top->evlist);
 		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
 				(uint64_t)first->attr.sample_period,
-				top->freq ? "Hz" : "");
+				opts->freq ? "Hz" : "");
 	}
 
 	ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
 
 	ret += SNPRINTF(bf + ret, size - ret, "], ");
 
-	if (top->target.pid)
+	if (target->pid)
 		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
-				top->target.pid);
-	else if (top->target.tid)
+				target->pid);
+	else if (target->tid)
 		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
-				top->target.tid);
-	else if (top->target.uid_str != NULL)
+				target->tid);
+	else if (target->uid_str != NULL)
 		ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
-				top->target.uid_str);
+				target->uid_str);
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
-	if (top->target.cpu_list)
+	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
 				top->evlist->cpus->nr > 1 ? "s" : "",
-				top->target.cpu_list);
+				target->cpu_list);
 	else {
-		if (top->target.tid)
+		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 86ff1b15059b..927c229c2d9a 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -14,7 +14,7 @@ struct perf_session;
 struct perf_top {
 	struct perf_tool   tool;
 	struct perf_evlist *evlist;
-	struct perf_target target;
+	struct perf_record_opts record_opts;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.
@@ -24,15 +24,11 @@ struct perf_top {
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
 	int		   print_entries, count_filter, delay_secs;
-	int		   freq;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
 	bool		   sort_has_symbols;
-	bool		   dont_use_callchains;
 	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
-	bool		   inherit;
-	bool		   group;
 	bool		   sample_id_all_missing;
 	bool		   exclude_guest_missing;
 	bool		   dump_symtab;
@@ -40,8 +36,6 @@ struct perf_top {
 	struct perf_evsel  *sym_evsel;
 	struct perf_session *session;
 	struct winsize	   winsize;
-	unsigned int	   mmap_pages;
-	int		   default_interval;
 	int		   realtime_prio;
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;