diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 747ff50284b7..2b8097ee39d8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -115,7 +115,7 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min[,limit],order]::
+-g [type,min[,limit],order[,key]]::
 --call-graph::
         Display call chains using type, min percent threshold, optional print
 	limit and order.
@@ -129,7 +129,11 @@ OPTIONS
 	- callee: callee based call graph.
 	- caller: inverted caller based call graph.
 
-	Default: fractal,0.5,callee.
+	key can be:
+	- function: compare on functions
+	- address: compare on individual code addresses
+
+	Default: fractal,0.5,callee,function.
 
 -G::
 --inverted::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 2a6902677141..024680b23ddc 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -631,10 +631,10 @@ $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $<
 
 $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $<
 
 $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 25fd3f1966f1..8cdca43016b2 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -117,6 +117,8 @@ static void alloc_mem(void **dst, void **src, size_t length)
 	*src = zalloc(length);
 	if (!*src)
 		die("memory allocation failed - maybe length is too large?\n");
+	/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+	memset(*src, 0, length);
 }
 
 static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a34c587900c7..d785d89ed226 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -667,12 +667,23 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	}
 
 	/* get the call chain order */
-	if (!strcmp(tok2, "caller"))
+	if (!strncmp(tok2, "caller", strlen("caller")))
 		callchain_param.order = ORDER_CALLER;
-	else if (!strcmp(tok2, "callee"))
+	else if (!strncmp(tok2, "callee", strlen("callee")))
 		callchain_param.order = ORDER_CALLEE;
 	else
 		return -1;
+
+	/* Get the sort key */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+	if (!strncmp(tok2, "function", strlen("function")))
+		callchain_param.key = CCKEY_FUNCTION;
+	else if (!strncmp(tok2, "address", strlen("address")))
+		callchain_param.key = CCKEY_ADDRESS;
+	else
+		return -1;
 setup:
 	if (callchain_register_param(&callchain_param) < 0) {
 		fprintf(stderr, "Can't register callchain params\n");
@@ -784,8 +795,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
-		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit and callchain order. "
-		     "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
+		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
+		     "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
 	OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
 		    "alias for inverted call graph"),
 	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ecb697998d3b..1cad37014673 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -397,10 +397,10 @@ static void print_sample_bts(union perf_event *event,
 
 static void process_event(union perf_event *event, struct perf_sample *sample,
 			  struct perf_evsel *evsel, struct machine *machine,
-			  struct addr_location *al)
+			  struct thread *thread,
+			  struct addr_location *al __maybe_unused)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	struct thread *thread = al->thread;
 
 	if (output[attr->type].fields == 0)
 		return;
@@ -511,7 +511,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
 		return 0;
 
-	scripting_ops->process_event(event, sample, evsel, machine, &al);
+	scripting_ops->process_event(event, sample, evsel, machine, thread, &al);
 
 	evsel->hists.stats.total_period += sample->period;
 	return 0;
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index c441a2875128..2ca0abf1b2b6 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,6 +1,8 @@
 PERF := .
 MK   := Makefile
 
+has = $(shell which $1 2>/dev/null)
+
 # standard single make variable specified
 make_clean_all      := clean all
 make_python_perf_so := python/perf.so
@@ -25,6 +27,13 @@ make_help           := help
 make_doc            := doc
 make_perf_o         := perf.o
 make_util_map_o     := util/map.o
+make_install        := install
+make_install_bin    := install-bin
+make_install_doc    := install-doc
+make_install_man    := install-man
+make_install_html   := install-html
+make_install_info   := install-info
+make_install_pdf    := install-pdf
 
 # all the NO_* variable combined
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
@@ -50,14 +59,27 @@ run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
 run += make_no_libbionic
-run += make_tags
-run += make_cscope
 run += make_help
 run += make_doc
 run += make_perf_o
 run += make_util_map_o
+run += make_install
+run += make_install_bin
+# FIXME 'install-*' commented out till they're fixed
+# run += make_install_doc
+# run += make_install_man
+# run += make_install_html
+# run += make_install_info
+# run += make_install_pdf
 run += make_minimal
 
+ifneq ($(call has,ctags),)
+run += make_tags
+endif
+ifneq ($(call has,cscope),)
+run += make_cscope
+endif
+
 # $(run_O) contains same portion of $(run) tests with '_O' attached
 # to distinguish O=... tests
 run_O := $(addsuffix _O,$(run))
@@ -84,6 +106,31 @@ test_make_python_perf_so := test -f $(PERF)/python/perf.so
 test_make_perf_o     := test -f $(PERF)/perf.o
 test_make_util_map_o := test -f $(PERF)/util/map.o
 
+test_make_install       := test -x $$TMP_DEST/bin/perf
+test_make_install_O     := $(test_make_install)
+test_make_install_bin   := $(test_make_install)
+test_make_install_bin_O := $(test_make_install)
+
+# FIXME nothing gets installed
+test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
+test_make_install_man_O  := $(test_make_install_man)
+
+# FIXME nothing gets installed
+test_make_install_doc    := $(test_ok)
+test_make_install_doc_O  := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_html   := $(test_ok)
+test_make_install_html_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_info   := $(test_ok)
+test_make_install_info_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_pdf    := $(test_ok)
+test_make_install_pdf_O  := $(test_ok)
+
 # Kbuild tests only
 #test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
 #test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
@@ -95,7 +142,7 @@ test_make_util_map_o_O := true
 test_default = test -x $(PERF)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
 
-test_default_O = test -x $$TMP/perf
+test_default_O = test -x $$TMP_O/perf
 test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
 
 all:
@@ -111,23 +158,27 @@ clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
 
 $(run):
 	$(call clean)
-	@cmd="cd $(PERF) && make -f $(MK) $($@)"; \
+	@TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)"; \
 	$(call test,$@) && \
-	rm -f $@
+	rm -f $@ \
+	rm -rf $$TMP_DEST
 
 $(run_O):
 	$(call clean)
-	@TMP=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \
+	@TMP_O=$$(mktemp -d); \
+	TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)"; \
 	$(call test_O,$@) && \
 	rm -f $@ && \
-	rm -rf $$TMP
+	rm -rf $$TMP_O \
+	rm -rf $$TMP_DEST
 
 all: $(run) $(run_O)
 	@echo OK
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42b6a632fe7b..4fee33b229b0 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include <math.h>
 
+#include "hist.h"
 #include "util.h"
 #include "callchain.h"
 
@@ -327,7 +328,8 @@ append_chain(struct callchain_node *root,
 	/*
 	 * Lookup in the current node
 	 * If we have a symbol, then compare the start to match
-	 * anywhere inside a function.
+	 * anywhere inside a function, unless function
+	 * mode is disabled.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
 		struct callchain_cursor_node *node;
@@ -339,7 +341,8 @@ append_chain(struct callchain_node *root,
 
 		sym = node->sym;
 
-		if (cnode->ms.sym && sym) {
+		if (cnode->ms.sym && sym &&
+		    callchain_param.key == CCKEY_FUNCTION) {
 			if (cnode->ms.sym->start != sym->start)
 				break;
 		} else if (cnode->ip != node->ip)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 3ee9f67d5af0..812d5a0ff2bc 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -41,12 +41,18 @@ struct callchain_param;
 typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 				 u64, struct callchain_param *);
 
+enum chain_key {
+	CCKEY_FUNCTION,
+	CCKEY_ADDRESS
+};
+
 struct callchain_param {
 	enum chain_mode 	mode;
 	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
 	enum chain_order	order;
+	enum chain_key		key;
 };
 
 struct callchain_list {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a6354619fa5d..8bed0c1a1399 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1482,7 +1482,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
-	if ((err == ENOENT || err == ENXIO) &&
+	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
 	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 		/*
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a9dd1b9d8907..46a0d35a05e1 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -24,7 +24,8 @@ enum hist_filter {
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5,
-	.order  = ORDER_CALLEE
+	.order  = ORDER_CALLEE,
+	.key	= CCKEY_FUNCTION
 };
 
 u16 hists__col_len(struct hists *hists, enum hist_column col)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index eacec859f299..a85e4ae5f3ac 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -261,7 +261,8 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 				    struct perf_sample *sample,
 				    struct perf_evsel *evsel,
 				    struct machine *machine __maybe_unused,
-				    struct addr_location *al)
+				    struct thread *thread,
+					struct addr_location *al)
 {
 	struct format_field *field;
 	static char handler[256];
@@ -272,7 +273,6 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
 	unsigned long long nsecs = sample->time;
-	struct thread *thread = al->thread;
 	char *comm = thread->comm;
 
 	dSP;
@@ -351,7 +351,8 @@ static void perl_process_event_generic(union perf_event *event,
 				       struct perf_sample *sample,
 				       struct perf_evsel *evsel,
 				       struct machine *machine __maybe_unused,
-				       struct addr_location *al __maybe_unused)
+				       struct thread *thread __maybe_unused,
+					   struct addr_location *al __maybe_unused)
 {
 	dSP;
 
@@ -377,10 +378,11 @@ static void perl_process_event(union perf_event *event,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
-			       struct addr_location *al)
+			       struct thread *thread,
+				   struct addr_location *al)
 {
-	perl_process_tracepoint(event, sample, evsel, machine, al);
-	perl_process_event_generic(event, sample, evsel, machine, al);
+	perl_process_tracepoint(event, sample, evsel, machine, thread, al);
+	perl_process_event_generic(event, sample, evsel, machine, thread, al);
 }
 
 static void run_start_sub(void)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e87aa5d9696b..cc75a3cef388 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -225,6 +225,7 @@ static void python_process_tracepoint(union perf_event *perf_event
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct machine *machine __maybe_unused,
+				 struct thread *thread,
 				 struct addr_location *al)
 {
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
@@ -238,7 +239,6 @@ static void python_process_tracepoint(union perf_event *perf_event
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
 	unsigned long long nsecs = sample->time;
-	struct thread *thread = al->thread;
 	char *comm = thread->comm;
 
 	t = PyTuple_New(MAX_FIELDS);
@@ -345,12 +345,12 @@ static void python_process_general_event(union perf_event *perf_event
 					 struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct machine *machine __maybe_unused,
+					 struct thread *thread,
 					 struct addr_location *al)
 {
 	PyObject *handler, *retval, *t, *dict;
 	static char handler_name[64];
 	unsigned n = 0;
-	struct thread *thread = al->thread;
 
 	/*
 	 * Use the MAX_FIELDS to make the function expandable, though
@@ -404,17 +404,18 @@ static void python_process_event(union perf_event *perf_event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct machine *machine,
+				 struct thread *thread,
 				 struct addr_location *al)
 {
 	switch (evsel->attr.type) {
 	case PERF_TYPE_TRACEPOINT:
 		python_process_tracepoint(perf_event, sample, evsel,
-					  machine, al);
+					  machine, thread, al);
 		break;
 	/* Reserve for future process_hw/sw/raw APIs */
 	default:
 		python_process_general_event(perf_event, sample, evsel,
-					     machine, al);
+					     machine, thread, al);
 	}
 }
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index cb2b108635ee..5f118a089519 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -874,6 +874,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
+	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 };
 
 #undef DIM
@@ -893,8 +895,6 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 #define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
 
 static struct sort_dimension memory_sort_dimensions[] = {
-	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
-	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 	DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
 	DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
 	DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 586022dc3264..4e80dbd271e7 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -143,6 +143,8 @@ enum sort_type {
 	SORT_PARENT,
 	SORT_CPU,
 	SORT_SRCLINE,
+	SORT_LOCAL_WEIGHT,
+	SORT_GLOBAL_WEIGHT,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -154,9 +156,7 @@ enum sort_type {
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,
-	SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE,
-	SORT_GLOBAL_WEIGHT,
-	SORT_MEM_DADDR_SYMBOL,
+	SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE,
 	SORT_MEM_DADDR_DSO,
 	SORT_MEM_LOCKED,
 	SORT_MEM_TLB,
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 8715a1006d00..95199e4eea97 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -39,7 +39,8 @@ static void process_event_unsupported(union perf_event *event __maybe_unused,
 				      struct perf_sample *sample __maybe_unused,
 				      struct perf_evsel *evsel __maybe_unused,
 				      struct machine *machine __maybe_unused,
-				      struct addr_location *al __maybe_unused)
+				      struct thread *thread __maybe_unused,
+					  struct addr_location *al __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 669a64a660d7..fafe1a40444a 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -9,6 +9,7 @@ struct machine;
 struct perf_sample;
 union perf_event;
 struct perf_tool;
+struct thread;
 
 extern struct pevent *perf_pevent;
 
@@ -68,7 +69,8 @@ struct scripting_ops {
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
-			       struct addr_location *al);
+			       struct thread *thread,
+				   struct addr_location *al);
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };