diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 7a527f7e9da9933823eefc1b7d4c173c5085ede0..ddc22525228da27db7964a0bbfbf5bf4ced41f55 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -21,6 +21,8 @@ EVENT MODIFIERS
 Events can optionally have a modifer by appending a colon and one or
 more modifiers.  Modifiers allow the user to restrict when events are
 counted with 'u' for user-space, 'k' for kernel, 'h' for hypervisor.
+Additional modifiers are 'G' for guest counting (in KVM guests) and 'H'
+for host counting (not in KVM guests).
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier is currently only implemented for
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index c12659d8cb26fcefd8449581921aef2962cb651c..1078c5fadd5bfcb26e83755bb924eb377681d048 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,4 +1,5 @@
 tools/perf
+include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 032324a76b877bb69dcf4f3cdb7505719bb04b6d..9fc6e0fa3dce22f838324da57b3e2929892ed70a 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -22,9 +22,6 @@
 static const char		*file_name;
 static char			name_buffer[256];
 
-bool				perf_host = 1;
-bool				perf_guest;
-
 static const char * const kvm_usage[] = {
 	"perf kvm [<options>] {top|record|report|diff|buildid-list}",
 	NULL
@@ -107,7 +104,8 @@ static int __cmd_buildid_list(int argc, const char **argv)
 
 int cmd_kvm(int argc, const char **argv, const char *prefix __used)
 {
-	perf_host = perf_guest = 0;
+	perf_host  = 0;
+	perf_guest = 1;
 
 	argc = parse_options(argc, argv, kvm_options, kvm_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 4f81eeb998755a992f184104dd5390ffbc49d7b5..d89dec90103ef3e5a6280fb40426f573f4e99a49 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -235,7 +235,6 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	if (he == NULL)
 		return NULL;
 
-	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 	return he;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index fa1837088ca880ca5968709326e94f22fa436db4..3f16e08a5c8de740a3149879274dd69af720c97e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -111,8 +111,11 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
-	struct perf_evsel *evsel = perf_evsel__new(&attr, 0);
+	struct perf_evsel *evsel;
+
+	event_attr_init(&attr);
 
+	evsel = perf_evsel__new(&attr, 0);
 	if (evsel == NULL)
 		goto error;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index abef2703cd242eb8b8e5f1763cadd50286bdc8be..4df449549b0ce24aa14dfe6f8a2b75a83a5fa9ee 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -76,21 +76,21 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	}
 }
 
-static void hist_entry__add_cpumode_period(struct hist_entry *self,
+static void hist_entry__add_cpumode_period(struct hist_entry *he,
 					   unsigned int cpumode, u64 period)
 {
 	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
-		self->period_sys += period;
+		he->period_sys += period;
 		break;
 	case PERF_RECORD_MISC_USER:
-		self->period_us += period;
+		he->period_us += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		self->period_guest_sys += period;
+		he->period_guest_sys += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_USER:
-		self->period_guest_us += period;
+		he->period_guest_us += period;
 		break;
 	default:
 		break;
@@ -165,18 +165,18 @@ void hists__decay_entries_threaded(struct hists *hists,
 static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
 	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
+	struct hist_entry *he = malloc(sizeof(*he) + callchain_size);
 
-	if (self != NULL) {
-		*self = *template;
-		self->nr_events = 1;
-		if (self->ms.map)
-			self->ms.map->referenced = true;
+	if (he != NULL) {
+		*he = *template;
+		he->nr_events = 1;
+		if (he->ms.map)
+			he->ms.map->referenced = true;
 		if (symbol_conf.use_callchain)
-			callchain_init(self->callchain);
+			callchain_init(he->callchain);
 	}
 
-	return self;
+	return he;
 }
 
 static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
@@ -677,15 +677,16 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	return ret;
 }
 
-static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
-					    u64 total_samples, int left_margin)
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+					    u64 total_samples, int left_margin,
+					    FILE *fp)
 {
 	struct rb_node *rb_node;
 	struct callchain_node *chain;
 	size_t ret = 0;
 	u32 entries_printed = 0;
 
-	rb_node = rb_first(&self->sorted_chain);
+	rb_node = rb_first(&he->sorted_chain);
 	while (rb_node) {
 		double percent;
 
@@ -730,35 +731,35 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 	}
 }
 
-static int hist_entry__pcnt_snprintf(struct hist_entry *self, char *s,
+static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 				     size_t size, struct hists *pair_hists,
 				     bool show_displacement, long displacement,
-				     bool color, u64 session_total)
+				     bool color, u64 total_period)
 {
 	u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
 	u64 nr_events;
 	const char *sep = symbol_conf.field_sep;
 	int ret;
 
-	if (symbol_conf.exclude_other && !self->parent)
+	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
 	if (pair_hists) {
-		period = self->pair ? self->pair->period : 0;
-		nr_events = self->pair ? self->pair->nr_events : 0;
+		period = he->pair ? he->pair->period : 0;
+		nr_events = he->pair ? he->pair->nr_events : 0;
 		total = pair_hists->stats.total_period;
-		period_sys = self->pair ? self->pair->period_sys : 0;
-		period_us = self->pair ? self->pair->period_us : 0;
-		period_guest_sys = self->pair ? self->pair->period_guest_sys : 0;
-		period_guest_us = self->pair ? self->pair->period_guest_us : 0;
+		period_sys = he->pair ? he->pair->period_sys : 0;
+		period_us = he->pair ? he->pair->period_us : 0;
+		period_guest_sys = he->pair ? he->pair->period_guest_sys : 0;
+		period_guest_us = he->pair ? he->pair->period_guest_us : 0;
 	} else {
-		period = self->period;
-		nr_events = self->nr_events;
-		total = session_total;
-		period_sys = self->period_sys;
-		period_us = self->period_us;
-		period_guest_sys = self->period_guest_sys;
-		period_guest_us = self->period_guest_us;
+		period = he->period;
+		nr_events = he->nr_events;
+		total = total_period;
+		period_sys = he->period_sys;
+		period_us = he->period_us;
+		period_guest_sys = he->period_guest_sys;
+		period_guest_us = he->period_guest_us;
 	}
 
 	if (total) {
@@ -812,8 +813,8 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *self, char *s,
 
 		if (total > 0)
 			old_percent = (period * 100.0) / total;
-		if (session_total > 0)
-			new_percent = (self->period * 100.0) / session_total;
+		if (total_period > 0)
+			new_percent = (he->period * 100.0) / total_period;
 
 		diff = new_percent - old_percent;
 
@@ -862,9 +863,10 @@ int hist_entry__snprintf(struct hist_entry *he, char *s, size_t size,
 	return ret;
 }
 
-int hist_entry__fprintf(struct hist_entry *he, size_t size, struct hists *hists,
-			struct hists *pair_hists, bool show_displacement,
-			long displacement, FILE *fp, u64 session_total)
+static int hist_entry__fprintf(struct hist_entry *he, size_t size,
+			       struct hists *hists, struct hists *pair_hists,
+			       bool show_displacement, long displacement,
+			       u64 total_period, FILE *fp)
 {
 	char bf[512];
 	int ret;
@@ -874,14 +876,14 @@ int hist_entry__fprintf(struct hist_entry *he, size_t size, struct hists *hists,
 
 	ret = hist_entry__pcnt_snprintf(he, bf, size, pair_hists,
 					show_displacement, displacement,
-					true, session_total);
+					true, total_period);
 	hist_entry__snprintf(he, bf + ret, size - ret, hists);
 	return fprintf(fp, "%s\n", bf);
 }
 
-static size_t hist_entry__fprintf_callchain(struct hist_entry *self,
-					    struct hists *hists, FILE *fp,
-					    u64 session_total)
+static size_t hist_entry__fprintf_callchain(struct hist_entry *he,
+					    struct hists *hists,
+					    u64 total_period, FILE *fp)
 {
 	int left_margin = 0;
 
@@ -889,11 +891,10 @@ static size_t hist_entry__fprintf_callchain(struct hist_entry *self,
 		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
 							 typeof(*se), list);
 		left_margin = hists__col_len(hists, se->se_width_idx);
-		left_margin -= thread__comm_len(self->thread);
+		left_margin -= thread__comm_len(he->thread);
 	}
 
-	return hist_entry_callchain__fprintf(fp, self, session_total,
-					     left_margin);
+	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
 }
 
 size_t hists__fprintf(struct hists *hists, struct hists *pair,
@@ -903,6 +904,7 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair,
 	struct sort_entry *se;
 	struct rb_node *nd;
 	size_t ret = 0;
+	u64 total_period;
 	unsigned long position = 1;
 	long displacement = 0;
 	unsigned int width;
@@ -1025,6 +1027,8 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair,
 		goto out;
 
 print_entries:
+	total_period = hists->stats.total_period;
+
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
@@ -1040,11 +1044,10 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair,
 			++position;
 		}
 		ret += hist_entry__fprintf(h, max_cols, hists, pair, show_displacement,
-					   displacement, fp, hists->stats.total_period);
+					   displacement, total_period, fp);
 
 		if (symbol_conf.use_callchain)
-			ret += hist_entry__fprintf_callchain(h, hists, fp,
-							     hists->stats.total_period);
+			ret += hist_entry__fprintf_callchain(h, hists, total_period, fp);
 		if (max_rows && ++nr_rows >= max_rows)
 			goto out;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ff6f9d56ea4192531241474bf07e09a78dcf5695..f55f0a8d1f816d57cf2a7ee44677894dc5287e78 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -66,11 +66,8 @@ struct hists {
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
 				      struct symbol *parent, u64 period);
-extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
-int hist_entry__fprintf(struct hist_entry *he, size_t size, struct hists *hists,
-			struct hists *pair_hists, bool show_displacement,
-			long displacement, FILE *fp, u64 session_total);
+int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
 			 struct hists *hists);
 void hist_entry__free(struct hist_entry *);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 531c283fc0c503566cf00afdc675e074c88d41d0..b029296d20d9dfc3c8bd85fb563d7d404c9cb5a1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -735,8 +735,8 @@ static int
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
-	int exclude = 0;
-	int eu = 0, ek = 0, eh = 0, precise = 0;
+	int exclude = 0, exclude_GH = 0;
+	int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0;
 
 	if (!*str)
 		return 0;
@@ -760,6 +760,14 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			eh = 0;
+		} else if (*str == 'G') {
+			if (!exclude_GH)
+				exclude_GH = eG = eH = 1;
+			eG = 0;
+		} else if (*str == 'H') {
+			if (!exclude_GH)
+				exclude_GH = eG = eH = 1;
+			eH = 0;
 		} else if (*str == 'p') {
 			precise++;
 		} else
@@ -776,6 +784,8 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 	attr->exclude_kernel = ek;
 	attr->exclude_hv     = eh;
 	attr->precise_ip     = precise;
+	attr->exclude_host   = eH;
+	attr->exclude_guest  = eG;
 
 	return 0;
 }
@@ -838,6 +848,7 @@ int parse_events(struct perf_evlist *evlist , const char *str, int unset __used)
 	for (;;) {
 		ostr = str;
 		memset(&attr, 0, sizeof(attr));
+		event_attr_init(&attr);
 		ret = parse_event_symbols(evlist, &str, &attr);
 		if (ret == EVT_FAILED)
 			return -1;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 5b3ea49aa63ea1ff35b7d949b49a661187aa16e6..813141047fc22fcfd61ae377444f7ff2a97f06eb 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,6 +1,21 @@
+#include "../perf.h"
 #include "util.h"
 #include <sys/mman.h>
 
+/*
+ * XXX We need to find a better place for these things...
+ */
+bool perf_host  = true;
+bool perf_guest = true;
+
+void event_attr_init(struct perf_event_attr *attr)
+{
+	if (!perf_host)
+		attr->exclude_host  = 1;
+	if (!perf_guest)
+		attr->exclude_guest = 1;
+}
+
 int mkdir_p(char *path, mode_t mode)
 {
 	struct stat st;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 37be34dff7983c2834b051bc8cc3347ab213383b..b9c530cce79a793657778dcc5a1ce2c5dd2215da 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -242,6 +242,10 @@ int strtailcmp(const char *s1, const char *s2);
 unsigned long convert_unit(unsigned long value, char *unit);
 int readn(int fd, void *buf, size_t size);
 
+struct perf_event_attr;
+
+void event_attr_init(struct perf_event_attr *attr);
+
 #define _STR(x) #x
 #define STR(x) _STR(x)