Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (50 commits)
  perf report: Add "Fractal" mode output - support callchains with relative overhead rate
  perf_counter tools: callchains: Manage the cumul hits on the fly
  perf report: Change default callchain parameters
  perf report: Use a modifiable string for default callchain options
  perf report: Warn on callchain output request from non-callchain file
  x86: atomic64: Inline atomic64_read() again
  x86: atomic64: Clean up atomic64_sub_and_test() and atomic64_add_negative()
  x86: atomic64: Improve atomic64_xchg()
  x86: atomic64: Export APIs to modules
  x86: atomic64: Improve atomic64_read()
  x86: atomic64: Code atomic(64)_read and atomic(64)_set in C not CPP
  x86: atomic64: Fix unclean type use in atomic64_xchg()
  x86: atomic64: Make atomic_read() type-safe
  x86: atomic64: Reduce size of functions
  x86: atomic64: Improve atomic64_add_return()
  x86: atomic64: Improve cmpxchg8b()
  x86: atomic64: Improve atomic64_read()
  x86: atomic64: Move the 32-bit atomic64_t implementation to a .c file
  x86: atomic64: The atomic64_t data type should be 8 bytes aligned on 32-bit too
  perf report: Annotate variable initialization
  ...

43 files changed, 1752 insertions, 1580 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 9c6d0ae3708..7822b3d6bac 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -164,7 +164,7 @@ endif
 
 # CFLAGS and LDFLAGS are for the users to override from the command line.
 
-CFLAGS = $(M64) -ggdb3 -Wall -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -Werror -O6
+CFLAGS = $(M64) -ggdb3 -Wall -Wextra -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -Werror -O6
 LDFLAGS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS)
 ALL_LDFLAGS = $(LDFLAGS)
@@ -223,7 +223,7 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 # Those must not be GNU-specific; they are shared with perl/ which may
 # be built by a different compiler. (Note that this is an artifact now
 # but it still might be nice to keep that distinction.)
-BASIC_CFLAGS =
+BASIC_CFLAGS = -Iutil/include
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -289,10 +289,11 @@ export PERL_PATH
 LIB_FILE=libperf.a
 
 LIB_H += ../../include/linux/perf_counter.h
+LIB_H += ../../include/linux/rbtree.h
+LIB_H += ../../include/linux/list.h
+LIB_H += util/include/linux/list.h
 LIB_H += perf.h
 LIB_H += util/types.h
-LIB_H += util/list.h
-LIB_H += util/rbtree.h
 LIB_H += util/levenshtein.h
 LIB_H += util/parse-options.h
 LIB_H += util/parse-events.h
@@ -305,6 +306,7 @@ LIB_H += util/strlist.h
 LIB_H += util/run-command.h
 LIB_H += util/sigchain.h
 LIB_H += util/symbol.h
+LIB_H += util/module.h
 LIB_H += util/color.h
 
 LIB_OBJS += util/abspath.o
@@ -328,6 +330,7 @@ LIB_OBJS += util/usage.o
 LIB_OBJS += util/wrapper.o
 LIB_OBJS += util/sigchain.o
 LIB_OBJS += util/symbol.o
+LIB_OBJS += util/module.o
 LIB_OBJS += util/color.o
 LIB_OBJS += util/pager.o
 LIB_OBJS += util/header.o
@@ -381,12 +384,6 @@ ifndef CC_LD_DYNPATH
 	endif
 endif
 
-ifdef ZLIB_PATH
-	BASIC_CFLAGS += -I$(ZLIB_PATH)/include
-	EXTLIBS += -L$(ZLIB_PATH)/$(lib) $(CC_LD_DYNPATH)$(ZLIB_PATH)/$(lib)
-endif
-EXTLIBS += -lz
-
 ifdef NEEDS_SOCKET
 	EXTLIBS += -lsocket
 endif
@@ -697,6 +694,9 @@ builtin-init-db.o: builtin-init-db.c PERF-CFLAGS
 util/config.o: util/config.c PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 perf-%$X: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 722c0f54e54..5f9eefecc57 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -10,9 +10,9 @@
 #include "util/util.h"
 
 #include "util/color.h"
-#include "util/list.h"
+#include <linux/list.h>
 #include "util/cache.h"
-#include "util/rbtree.h"
+#include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/string.h"
 
@@ -25,10 +25,6 @@
 #define SHOW_USER	2
 #define SHOW_HV		4
 
-#define MIN_GREEN		0.5
-#define MIN_RED		5.0
-
-
 static char		const *input_name = "perf.data";
 static char		*vmlinux = "vmlinux";
 
@@ -43,6 +39,10 @@ static int		dump_trace = 0;
 
 static int		verbose;
 
+static int		modules;
+
+static int		full_paths;
+
 static int		print_line;
 
 static unsigned long	page_size;
@@ -160,7 +160,7 @@ static void dsos__fprintf(FILE *fp)
 
 static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip)
 {
-	return dso__find_symbol(kernel_dso, ip);
+	return dso__find_symbol(dso, ip);
 }
 
 static int load_kernel(void)
@@ -171,8 +171,8 @@ static int load_kernel(void)
 	if (!kernel_dso)
 		return -1;
 
-	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose);
-	if (err) {
+	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, modules);
+	if (err <= 0) {
 		dso__delete(kernel_dso);
 		kernel_dso = NULL;
 	} else
@@ -203,7 +203,7 @@ static u64 map__map_ip(struct map *map, u64 ip)
 	return ip - map->start + map->pgoff;
 }
 
-static u64 vdso__map_ip(struct map *map, u64 ip)
+static u64 vdso__map_ip(struct map *map __used, u64 ip)
 {
 	return ip;
 }
@@ -600,7 +600,7 @@ static LIST_HEAD(hist_entry__sort_list);
 
 static int sort_dimension__add(char *tok)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
 		struct sort_dimension *sd = &sort_dimensions[i];
@@ -1043,24 +1043,6 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 	return 0;
 }
 
-static char *get_color(double percent)
-{
-	char *color = PERF_COLOR_NORMAL;
-
-	/*
-	 * We color high-overhead entries in red, mid-overhead
-	 * entries in green - and keep the low overhead places
-	 * normal:
-	 */
-	if (percent >= MIN_RED)
-		color = PERF_COLOR_RED;
-	else {
-		if (percent > MIN_GREEN)
-			color = PERF_COLOR_GREEN;
-	}
-	return color;
-}
-
 static int
 parse_line(FILE *file, struct symbol *sym, u64 start, u64 len)
 {
@@ -1069,7 +1051,7 @@ parse_line(FILE *file, struct symbol *sym, u64 start, u64 len)
 	static const char *prev_color;
 	unsigned int offset;
 	size_t line_len;
-	u64 line_ip;
+	s64 line_ip;
 	int ret;
 	char *c;
 
@@ -1122,7 +1104,7 @@ parse_line(FILE *file, struct symbol *sym, u64 start, u64 len)
 		} else if (sym->hist_sum)
 			percent = 100.0 * hits / sym->hist_sum;
 
-		color = get_color(percent);
+		color = get_percent_color(percent);
 
 		/*
 		 * Also color the filename and line if needed, with
@@ -1258,7 +1240,7 @@ static void print_summary(char *filename)
 
 		sym_ext = rb_entry(node, struct sym_ext, node);
 		percent = sym_ext->percent;
-		color = get_color(percent);
+		color = get_percent_color(percent);
 		path = sym_ext->path;
 
 		color_fprintf(stdout, color, " %7.2f %s", percent, path);
@@ -1268,19 +1250,25 @@ static void print_summary(char *filename)
 
 static void annotate_sym(struct dso *dso, struct symbol *sym)
 {
-	char *filename = dso->name;
+	char *filename = dso->name, *d_filename;
 	u64 start, end, len;
 	char command[PATH_MAX*2];
 	FILE *file;
 
 	if (!filename)
 		return;
-	if (dso == kernel_dso)
+	if (sym->module)
+		filename = sym->module->path;
+	else if (dso == kernel_dso)
 		filename = vmlinux;
 
 	start = sym->obj_start;
 	if (!start)
 		start = sym->start;
+	if (full_paths)
+		d_filename = filename;
+	else
+		d_filename = basename(filename);
 
 	end = start + sym->end - sym->start + 1;
 	len = sym->end - sym->start;
@@ -1291,13 +1279,14 @@ static void annotate_sym(struct dso *dso, struct symbol *sym)
 	}
 
 	printf("\n\n------------------------------------------------\n");
-	printf(" Percent |	Source code & Disassembly of %s\n", filename);
+	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
 	printf("------------------------------------------------\n");
 
 	if (verbose >= 2)
 		printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name);
 
-	sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", (u64)start, (u64)end, filename);
+	sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s",
+			(u64)start, (u64)end, filename, filename);
 
 	if (verbose >= 3)
 		printf("doing: %s\n", command);
@@ -1428,7 +1417,7 @@ more:
 
 	head += size;
 
-	if (offset + head < stat.st_size)
+	if (offset + head < (unsigned long)stat.st_size)
 		goto more;
 
 	rc = EXIT_SUCCESS;
@@ -1472,8 +1461,12 @@ static const struct option options[] = {
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
+	OPT_BOOLEAN('m', "modules", &modules,
+		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
 	OPT_BOOLEAN('l', "print-line", &print_line,
 		    "print matching source lines (may be slow)"),
+	OPT_BOOLEAN('P', "full-paths", &full_paths,
+		    "Don't shorten the displayed pathnames"),
 	OPT_END()
 };
 
@@ -1492,7 +1485,7 @@ static void setup_sorting(void)
 	free(str);
 }
 
-int cmd_annotate(int argc, const char **argv, const char *prefix)
+int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 {
 	symbol__init();
 
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 0f32dc3f3c4..2599d86a733 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -3,6 +3,7 @@
  *
  * Builtin help command
  */
+#include "perf.h"
 #include "util/cache.h"
 #include "builtin.h"
 #include "util/exec_cmd.h"
@@ -277,7 +278,7 @@ static struct cmdnames main_cmds, other_cmds;
 
 void list_common_cmds_help(void)
 {
-	int i, longest = 0;
+	unsigned int i, longest = 0;
 
 	for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
 		if (longest < strlen(common_cmds[i].name))
@@ -415,9 +416,10 @@ static void show_html_page(const char *perf_cmd)
 	open_html(page_path.buf);
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix)
+int cmd_help(int argc, const char **argv, const char *prefix __used)
 {
 	const char *alias;
+
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
 	perf_config(perf_help_config, NULL);
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index fe60e37c96e..f990fa8a35c 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -13,7 +13,7 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 
-int cmd_list(int argc, const char **argv, const char *prefix)
+int cmd_list(int argc __used, const char **argv __used, const char *prefix __used)
 {
 	print_events();
 	return 0;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d18546f37d7..4ef78a5e6f3 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -294,7 +294,7 @@ static void pid_synthesize_mmap_samples(pid_t pid)
 	while (1) {
 		char bf[BUFSIZ], *pbf = bf;
 		struct mmap_event mmap_ev = {
-			.header.type = PERF_EVENT_MMAP,
+			.header = { .type = PERF_EVENT_MMAP },
 		};
 		int n;
 		size_t size;
@@ -650,7 +650,7 @@ static const struct option options[] = {
 	OPT_END()
 };
 
-int cmd_record(int argc, const char **argv, const char *prefix)
+int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
 	int counter;
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 135b7837e6b..4e5cc266311 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -10,9 +10,9 @@
 #include "util/util.h"
 
 #include "util/color.h"
-#include "util/list.h"
+#include <linux/list.h>
 #include "util/cache.h"
-#include "util/rbtree.h"
+#include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/string.h"
 #include "util/callchain.h"
@@ -46,6 +46,8 @@ static int		dump_trace = 0;
 static int		verbose;
 #define eprintf(x...)	do { if (verbose) fprintf(stderr, x); } while (0)
 
+static int		modules;
+
 static int		full_paths;
 
 static unsigned long	page_size;
@@ -56,8 +58,17 @@ static char		*parent_pattern = default_parent_pattern;
 static regex_t		parent_regex;
 
 static int		exclude_other = 1;
+
+static char		callchain_default_opt[] = "fractal,0.5";
+
 static int		callchain;
 
+static
+struct callchain_param	callchain_param = {
+	.mode	= CHAIN_GRAPH_ABS,
+	.min_percent = 0.5
+};
+
 static u64		sample_type;
 
 struct ip_event {
@@ -121,6 +132,7 @@ typedef union event_union {
 static LIST_HEAD(dsos);
 static struct dso *kernel_dso;
 static struct dso *vdso;
+static struct dso *hypervisor_dso;
 
 static void dsos__add(struct dso *dso)
 {
@@ -176,7 +188,7 @@ static void dsos__fprintf(FILE *fp)
 
 static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip)
 {
-	return dso__find_symbol(kernel_dso, ip);
+	return dso__find_symbol(dso, ip);
 }
 
 static int load_kernel(void)
@@ -187,8 +199,8 @@ static int load_kernel(void)
 	if (!kernel_dso)
 		return -1;
 
-	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose);
-	if (err) {
+	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, modules);
+	if (err <= 0) {
 		dso__delete(kernel_dso);
 		kernel_dso = NULL;
 	} else
@@ -202,6 +214,11 @@ static int load_kernel(void)
 
 	dsos__add(vdso);
 
+	hypervisor_dso = dso__new("[hypervisor]", 0);
+	if (!hypervisor_dso)
+		return -1;
+	dsos__add(hypervisor_dso);
+
 	return err;
 }
 
@@ -233,7 +250,7 @@ static u64 map__map_ip(struct map *map, u64 ip)
 	return ip - map->start + map->pgoff;
 }
 
-static u64 vdso__map_ip(struct map *map, u64 ip)
+static u64 vdso__map_ip(struct map *map __used, u64 ip)
 {
 	return ip;
 }
@@ -640,7 +657,11 @@ sort__sym_print(FILE *fp, struct hist_entry *self)
 
 	if (self->sym) {
 		ret += fprintf(fp, "[%c] %s",
-			self->dso == kernel_dso ? 'k' : '.', self->sym->name);
+			self->dso == kernel_dso ? 'k' :
+			self->dso == hypervisor_dso ? 'h' : '.', self->sym->name);
+
+		if (self->sym->module)
+			ret += fprintf(fp, "\t[%s]", self->sym->module->name);
 	} else {
 		ret += fprintf(fp, "%#016llx", (u64)self->ip);
 	}
@@ -705,7 +726,7 @@ static LIST_HEAD(hist_entry__sort_list);
 
 static int sort_dimension__add(char *tok)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
 		struct sort_dimension *sd = &sort_dimensions[i];
@@ -775,8 +796,109 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	return cmp;
 }
 
+static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask)
+{
+	int i;
+	size_t ret = 0;
+
+	ret += fprintf(fp, "%s", "                ");
+
+	for (i = 0; i < depth; i++)
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|          ");
+		else
+			ret += fprintf(fp, "           ");
+
+	ret += fprintf(fp, "\n");
+
+	return ret;
+}
+static size_t
+ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
+		       int depth_mask, int count, u64 total_samples,
+		       int hits)
+{
+	int i;
+	size_t ret = 0;
+
+	ret += fprintf(fp, "%s", "                ");
+	for (i = 0; i < depth; i++) {
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|");
+		else
+			ret += fprintf(fp, " ");
+		if (!count && i == depth - 1) {
+			double percent;
+
+			percent = hits * 100.0 / total_samples;
+			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+		} else
+			ret += fprintf(fp, "%s", "          ");
+	}
+	if (chain->sym)
+		ret += fprintf(fp, "%s\n", chain->sym->name);
+	else
+		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
+
+	return ret;
+}
+
+static size_t
+callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+			u64 total_samples, int depth, int depth_mask)
+{
+	struct rb_node *node, *next;
+	struct callchain_node *child;
+	struct callchain_list *chain;
+	int new_depth_mask = depth_mask;
+	u64 new_total;
+	size_t ret = 0;
+	int i;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = self->cumul_hit;
+	else
+		new_total = total_samples;
+
+	node = rb_first(&self->rb_root);
+	while (node) {
+		child = rb_entry(node, struct callchain_node, rb_node);
+
+		/*
+		 * The depth mask manages the output of pipes that show
+		 * the depth. We don't want to keep the pipes of the current
+		 * level for the last child of this depth
+		 */
+		next = rb_next(node);
+		if (!next)
+			new_depth_mask &= ~(1 << (depth - 1));
+
+		/*
+		 * But we keep the older depth mask for the line seperator
+		 * to keep the level link until we reach the last child
+		 */
+		ret += ipchain__fprintf_graph_line(fp, depth, depth_mask);
+		i = 0;
+		list_for_each_entry(chain, &child->val, list) {
+			if (chain->ip >= PERF_CONTEXT_MAX)
+				continue;
+			ret += ipchain__fprintf_graph(fp, chain, depth,
+						      new_depth_mask, i++,
+						      new_total,
+						      child->cumul_hit);
+		}
+		ret += callchain__fprintf_graph(fp, child, new_total,
+						depth + 1,
+						new_depth_mask | (1 << depth));
+		node = next;
+	}
+
+	return ret;
+}
+
 static size_t
-callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples)
+callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
+			u64 total_samples)
 {
 	struct callchain_list *chain;
 	size_t ret = 0;
@@ -784,11 +906,18 @@ callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples)
 	if (!self)
 		return 0;
 
-	ret += callchain__fprintf(fp, self->parent, total_samples);
+	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
 
 
-	list_for_each_entry(chain, &self->val, list)
-		ret += fprintf(fp, "                %p\n", (void *)chain->ip);
+	list_for_each_entry(chain, &self->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->sym)
+			ret += fprintf(fp, "                %s\n", chain->sym->name);
+		else
+			ret += fprintf(fp, "                %p\n",
+					(void *)(long)chain->ip);
+	}
 
 	return ret;
 }
@@ -807,8 +936,19 @@ hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
 		percent = chain->hit * 100.0 / total_samples;
-		ret += fprintf(fp, "           %6.2f%%\n", percent);
-		ret += callchain__fprintf(fp, chain, total_samples);
+		switch (callchain_param.mode) {
+		case CHAIN_FLAT:
+			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
+						     percent);
+			ret += callchain__fprintf_flat(fp, chain, total_samples);
+			break;
+		case CHAIN_GRAPH_ABS: /* Falldown */
+		case CHAIN_GRAPH_REL:
+			ret += callchain__fprintf_graph(fp, chain,
+							total_samples, 1, 1);
+		default:
+			break;
+		}
 		ret += fprintf(fp, "\n");
 		rb_node = rb_next(rb_node);
 	}
@@ -826,25 +966,10 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples)
 	if (exclude_other && !self->parent)
 		return 0;
 
-	if (total_samples) {
-		double percent = self->count * 100.0 / total_samples;
-		char *color = PERF_COLOR_NORMAL;
-
-		/*
-		 * We color high-overhead entries in red, mid-overhead
-		 * entries in green - and keep the low overhead places
-		 * normal:
-		 */
-		if (percent >= 5.0) {
-			color = PERF_COLOR_RED;
-		} else {
-			if (percent >= 0.5)
-				color = PERF_COLOR_GREEN;
-		}
-
-		ret = color_fprintf(fp, color, "   %6.2f%%",
+	if (total_samples)
+		ret = percent_color_fprintf(fp, "   %6.2f%%",
 				(self->count * 100.0) / total_samples);
-	} else
+	else
 		ret = fprintf(fp, "%12Ld ", self->count);
 
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
@@ -923,6 +1048,58 @@ static int call__match(struct symbol *sym)
 	return 0;
 }
 
+static struct symbol **
+resolve_callchain(struct thread *thread, struct map *map __used,
+		    struct ip_callchain *chain, struct hist_entry *entry)
+{
+	u64 context = PERF_CONTEXT_MAX;
+	struct symbol **syms = NULL;
+	unsigned int i;
+
+	if (callchain) {
+		syms = calloc(chain->nr, sizeof(*syms));
+		if (!syms) {
+			fprintf(stderr, "Can't allocate memory for symbols\n");
+			exit(-1);
+		}
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip = chain->ips[i];
+		struct dso *dso = NULL;
+		struct symbol *sym;
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			context = ip;
+			continue;
+		}
+
+		switch (context) {
+		case PERF_CONTEXT_HV:
+			dso = hypervisor_dso;
+			break;
+		case PERF_CONTEXT_KERNEL:
+			dso = kernel_dso;
+			break;
+		default:
+			break;
+		}
+
+		sym = resolve_symbol(thread, NULL, &dso, &ip);
+
+		if (sym) {
+			if (sort__has_parent && call__match(sym) &&
+			    !entry->parent)
+				entry->parent = sym;
+			if (!callchain)
+				break;
+			syms[i] = sym;
+		}
+	}
+
+	return syms;
+}
+
 /*
  * collect histogram counts
  */
@@ -935,6 +1112,7 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 	struct rb_node **p = &hist.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
+	struct symbol **syms = NULL;
 	struct hist_entry entry = {
 		.thread	= thread,
 		.map	= map,
@@ -948,36 +1126,8 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 	};
 	int cmp;
 
-	if (sort__has_parent && chain) {
-		u64 context = PERF_CONTEXT_MAX;
-		int i;
-
-		for (i = 0; i < chain->nr; i++) {
-			u64 ip = chain->ips[i];
-			struct dso *dso = NULL;
-			struct symbol *sym;
-
-			if (ip >= PERF_CONTEXT_MAX) {
-				context = ip;
-				continue;
-			}
-
-			switch (context) {
-			case PERF_CONTEXT_KERNEL:
-				dso = kernel_dso;
-				break;
-			default:
-				break;
-			}
-
-			sym = resolve_symbol(thread, NULL, &dso, &ip);
-
-			if (sym && call__match(sym)) {
-				entry.parent = sym;
-				break;
-			}
-		}
-	}
+	if ((sort__has_parent || callchain) && chain)
+		syms = resolve_callchain(thread, map, chain, &entry);
 
 	while (*p != NULL) {
 		parent = *p;
@@ -987,8 +1137,10 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 
 		if (!cmp) {
 			he->count += count;
-			if (callchain)
-				append_chain(&he->callchain, chain);
+			if (callchain) {
+				append_chain(&he->callchain, chain, syms);
+				free(syms);
+			}
 			return 0;
 		}
 
@@ -1004,7 +1156,8 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
 	*he = entry;
 	if (callchain) {
 		callchain_init(&he->callchain);
-		append_chain(&he->callchain, chain);
+		append_chain(&he->callchain, chain, syms);
+		free(syms);
 	}
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, &hist);
@@ -1076,14 +1229,15 @@ static void collapse__resort(void)<