perf: 'perf kvm' tool for monitoring guest performance from host

Here is the patch of userspace perf tool.

Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

30 files changed, 1407 insertions, 316 deletions

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
new file mode 100644
index 000000000000..93400a0f17f0
--- /dev/null
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -0,0 +1,67 @@
+perf-kvm(1)
+==============
+
+NAME
+----
+perf-kvm - Tool to trace/measure kvm guest os
+
+SYNOPSIS
+--------
+[verse]
+'perf kvm' [--host] [--guest] [--guestmount=<path>
+	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
+	{top|record|report|diff|buildid-list}
+'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list}
+
+DESCRIPTION
+-----------
+There are a couple of variants of perf kvm:
+
+  'perf kvm [options] top <command>' to generates and displays
+  a performance counter profile of guest os in realtime
+  of an arbitrary workload.
+
+  'perf kvm record <command>' to record the performance couinter profile
+  of an arbitrary workload and save it into a perf data file. If both
+  --host and --guest are input, the perf data file name is perf.data.kvm.
+  If there is  no --host but --guest, the file name is perf.data.guest.
+  If there is no --guest but --host, the file name is perf.data.host.
+
+  'perf kvm report' to display the performance counter profile information
+  recorded via perf kvm record.
+
+  'perf kvm diff' to displays the performance difference amongst two perf.data
+  files captured via perf record.
+
+  'perf kvm buildid-list' to  display the buildids found in a perf data file,
+  so that other tools can be used to fetch packages with matching symbol tables
+  for use by perf report.
+
+OPTIONS
+-------
+--host=::
+        Collect host side perforamnce profile.
+--guest=::
+        Collect guest side perforamnce profile.
+--guestmount=<path>::
+	Guest os root file system mount directory. Users mounts guest os
+        root directories under <path> by a specific filesystem access method,
+	typically, sshfs. For example, start 2 guest os. The one's pid is 8888
+	and the other's is 9999.
+        #mkdir ~/guestmount; cd ~/guestmount
+        #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/
+        #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/
+        #perf kvm --host --guest --guestmount=~/guestmount top
+--guestkallsyms=<path>::
+        Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest
+	kernel symbols. Users copy it out from guest os.
+--guestmodules=<path>::
+	Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest
+	kernel module information. Users copy it out from guest os.
+--guestvmlinux=<path>::
+	Guest os kernel vmlinux.
+
+SEE ALSO
+--------
+linkperf:perf-top[1] perf-record[1] perf-report[1] perf-diff[1] perf-buildid-list[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 57b3569716dd..3cb3449a9645 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -472,6 +472,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
 BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
 BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
 BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
 
 PERFLIBS = $(LIB_FILE)
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 06eaebe10d04..f924b4332be6 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -571,7 +571,7 @@ static int __cmd_annotate(void)
 		perf_session__fprintf(session, stdout);
 
 	if (verbose > 2)
-		dsos__fprintf(stdout);
+		dsos__fprintf(&session->kerninfo_root, stdout);
 
 	perf_session__collapse_resort(&session->hists);
 	perf_session__output_resort(&session->hists, session->event_total[0]);
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index af2ad8b92f76..623afe3fdcb8 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -46,7 +46,7 @@ static int __cmd_buildid_list(void)
 	if (with_hits)
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
 
-	dsos__fprintf_buildid(stdout, with_hits);
+	dsos__fprintf_buildid(&session->kerninfo_root, stdout, with_hits);
 
 	perf_session__delete(session);
 	return err;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 3a1d94d75dce..207e860591e2 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -33,7 +33,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 		return -ENOMEM;
 
 	if (hit)
-		he->count += count;
+		__perf_session__add_count(he, al, count);
 
 	return 0;
 }
@@ -225,6 +225,10 @@ int cmd_diff(int argc, const char **argv, const char *prefix __used)
 			input_new = argv[1];
 		} else
 			input_new = argv[0];
+	} else if (symbol_conf.default_guest_vmlinux_name ||
+		   symbol_conf.default_guest_kallsyms) {
+		input_old = "perf.data.host";
+		input_new = "perf.data.guest";
 	}
 
 	symbol_conf.exclude_other = false;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 513aa8a55db6..db474bbf3322 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -351,6 +351,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			   int n_lines, int is_caller)
 {
 	struct rb_node *next;
+	struct kernel_info *kerninfo;
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
@@ -359,10 +360,16 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 
 	next = rb_first(root);
 
+	kerninfo = kerninfo__findhost(&session->kerninfo_root);
+	if (!kerninfo) {
+		pr_err("__print_result: couldn't find kernel information\n");
+		return;
+	}
 	while (next && n_lines--) {
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
 		struct symbol *sym = NULL;
+		struct map_groups *kmaps = &kerninfo->kmaps;
 		struct map *map;
 		char buf[BUFSIZ];
 		u64 addr;
@@ -370,8 +377,8 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = map_groups__find_function(&session->kmaps,
-								addr, &map, NULL);
+				sym = map_groups__find_function(kmaps, addr,
+								&map, NULL);
 		} else
 			addr = data->ptr;
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
new file mode 100644
index 000000000000..a4c7cae45024
--- /dev/null
+++ b/tools/perf/builtin-kvm.c
@@ -0,0 +1,144 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/util.h"
+#include "util/cache.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/header.h"
+#include "util/session.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+
+#include "util/debug.h"
+
+#include <sys/prctl.h>
+
+#include <semaphore.h>
+#include <pthread.h>
+#include <math.h>
+
+static char			*file_name;
+static char			name_buffer[256];
+
+int				perf_host = 1;
+int				perf_guest;
+
+static const char * const kvm_usage[] = {
+	"perf kvm [<options>] {top|record|report|diff|buildid-list}",
+	NULL
+};
+
+static const struct option kvm_options[] = {
+	OPT_STRING('i', "input", &file_name, "file",
+		   "Input file name"),
+	OPT_STRING('o', "output", &file_name, "file",
+		   "Output file name"),
+	OPT_BOOLEAN(0, "guest", &perf_guest,
+		    "Collect guest os data"),
+	OPT_BOOLEAN(0, "host", &perf_host,
+		    "Collect guest os data"),
+	OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
+		   "guest mount directory under which every guest os"
+		   " instance has a subdir"),
+	OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
+		   "file", "file saving guest os vmlinux"),
+	OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
+		   "file", "file saving guest os /proc/kallsyms"),
+	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
+		   "file", "file saving guest os /proc/modules"),
+	OPT_END()
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("record");
+	rec_argv[i++] = strdup("-o");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_record(i, rec_argv, NULL);
+}
+
+static int __cmd_report(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("report");
+	rec_argv[i++] = strdup("-i");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_report(i, rec_argv, NULL);
+}
+
+static int __cmd_buildid_list(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+
+	rec_argc = argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	rec_argv[i++] = strdup("buildid-list");
+	rec_argv[i++] = strdup("-i");
+	rec_argv[i++] = strdup(file_name);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	BUG_ON(i != rec_argc);
+
+	return cmd_buildid_list(i, rec_argv, NULL);
+}
+
+int cmd_kvm(int argc, const char **argv, const char *prefix __used)
+{
+	perf_host = perf_guest = 0;
+
+	argc = parse_options(argc, argv, kvm_options, kvm_usage,
+			PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(kvm_usage, kvm_options);
+
+	if (!perf_host)
+		perf_guest = 1;
+
+	if (!file_name) {
+		if (perf_host && !perf_guest)
+			sprintf(name_buffer, "perf.data.host");
+		else if (!perf_host && perf_guest)
+			sprintf(name_buffer, "perf.data.guest");
+		else
+			sprintf(name_buffer, "perf.data.kvm");
+		file_name = name_buffer;
+	}
+
+	if (!strncmp(argv[0], "rec", 3))
+		return __cmd_record(argc, argv);
+	else if (!strncmp(argv[0], "rep", 3))
+		return __cmd_report(argc, argv);
+	else if (!strncmp(argv[0], "diff", 4))
+		return cmd_diff(argc, argv, NULL);
+	else if (!strncmp(argv[0], "top", 3))
+		return cmd_top(argc, argv, NULL);
+	else if (!strncmp(argv[0], "buildid-list", 12))
+		return __cmd_buildid_list(argc, argv);
+	else
+		usage_with_options(kvm_usage, kvm_options);
+
+	return 0;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a1b99eeac3c0..27f992aca8b5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -456,6 +456,52 @@ static void atexit_header(void)
 	}
 }
 
+static void event__synthesize_guest_os(struct kernel_info *kerninfo,
+		void *data __attribute__((unused)))
+{
+	int err;
+	char *guest_kallsyms;
+	char path[PATH_MAX];
+
+	if (is_host_kernel(kerninfo))
+		return;
+
+	/*
+	 *As for guest kernel when processing subcommand record&report,
+	 *we arrange module mmap prior to guest kernel mmap and trigger
+	 *a preload dso because default guest module symbols are loaded
+	 *from guest kallsyms instead of /lib/modules/XXX/XXX. This
+	 *method is used to avoid symbol missing when the first addr is
+	 *in module instead of in guest kernel.
+	 */
+	err = event__synthesize_modules(process_synthesized_event,
+			session,
+			kerninfo);
+	if (err < 0)
+		pr_err("Couldn't record guest kernel [%d]'s reference"
+			" relocation symbol.\n", kerninfo->pid);
+
+	if (is_default_guest(kerninfo))
+		guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms;
+	else {
+		sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir);
+		guest_kallsyms = path;
+	}
+
+	/*
+	 * We use _stext for guest kernel because guest kernel's /proc/kallsyms
+	 * have no _text sometimes.
+	 */
+	err = event__synthesize_kernel_mmap(process_synthesized_event,
+			session, kerninfo, "_text");
+	if (err < 0)
+		err = event__synthesize_kernel_mmap(process_synthesized_event,
+				session, kerninfo, "_stext");
+	if (err < 0)
+		pr_err("Couldn't record guest kernel [%d]'s reference"
+			" relocation symbol.\n", kerninfo->pid);
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	int i, counter;
@@ -467,6 +513,7 @@ static int __cmd_record(int argc, const char **argv)
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = argc > 0;
 	char buf;
+	struct kernel_info *kerninfo;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -635,21 +682,31 @@ static int __cmd_record(int argc, const char **argv)
 		advance_output(err);
 	}
 
+	kerninfo = kerninfo__findhost(&session->kerninfo_root);
+	if (!kerninfo) {
+		pr_err("Couldn't find native kernel information.\n");
+		return -1;
+	}
+
 	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    session, "_text");
+			session, kerninfo, "_text");
 	if (err < 0)
 		err = event__synthesize_kernel_mmap(process_synthesized_event,
-						    session, "_stext");
+				session, kerninfo, "_stext");
 	if (err < 0) {
 		pr_err("Couldn't record kernel reference relocation symbol.\n");
 		return err;
 	}
 
-	err = event__synthesize_modules(process_synthesized_event, session);
+	err = event__synthesize_modules(process_synthesized_event,
+				session, kerninfo);
 	if (err < 0) {
 		pr_err("Couldn't record kernel reference relocation symbol.\n");
 		return err;
 	}
+	if (perf_guest)
+		kerninfo__process_allkernels(&session->kerninfo_root,
+			event__synthesize_guest_os, session);
 
 	if (!system_wide && profile_cpu == -1)
 		event__synthesize_thread(target_tid, process_synthesized_event,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7da5fb365264..816edae7c5b2 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -108,7 +108,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 		return -ENOMEM;
 
 	if (hit)
-		he->count += data->period;
+		__perf_session__add_count(he, al,  data->period);
 
 	if (symbol_conf.use_callchain) {
 		if (!hit)
@@ -313,7 +313,7 @@ static int __cmd_report(void)
 		perf_session__fprintf(session, stdout);
 
 	if (verbose > 2)
-		dsos__fprintf(stdout);
+		dsos__fprintf(&session->kerninfo_root, stdout);
 
 	next = rb_first(&session->stats_by_id);
 	while (next) {
@@ -450,6 +450,8 @@ static const struct option options[] = {
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
 		    "Don't shorten the pathnames taking into account the cwd"),
+	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
+		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 40f24dd46ef4..dfd7ea7dabdd 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -420,8 +420,9 @@ static double sym_weight(const struct sym_entry *sym)
 }
 
 static long			samples;
-static long			userspace_samples;
+static long			kernel_samples, us_samples;
 static long			exact_samples;
+static long			guest_us_samples, guest_kernel_samples;
 static const char		CONSOLE_CLEAR[] = "";
 
 static void __list_insert_active_sym(struct sym_entry *syme)
@@ -461,7 +462,10 @@ static void print_sym_table(void)
 	int printed = 0, j;
 	int counter, snap = !display_weighted ? sym_counter : 0;
 	float samples_per_sec = samples/delay_secs;
-	float ksamples_per_sec = (samples-userspace_samples)/delay_secs;
+	float ksamples_per_sec = kernel_samples/delay_secs;
+	float us_samples_per_sec = (us_samples)/delay_secs;
+	float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
+	float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
 	float esamples_percent = (100.0*exact_samples)/samples;
 	float sum_ksamples = 0.0;
 	struct sym_entry *syme, *n;
@@ -470,7 +474,8 @@ static void print_sym_table(void)
 	int sym_width = 0, dso_width = 0, dso_short_width = 0;
 	const int win_width = winsize.ws_col - 1;
 
-	samples = userspace_samples = exact_samples = 0;
+	samples = us_samples = kernel_samples = exact_samples = 0;
+	guest_kernel_samples = guest_us_samples = 0;
 
 	/* Sort the active symbols */
 	pthread_mutex_lock(&active_symbols_lock);
@@ -501,10 +506,30 @@ static void print_sym_table(void)
 	puts(CONSOLE_CLEAR);
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-	printf( "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%  exact: %4.1f%% [",
-		samples_per_sec,
-		100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)),
-		esamples_percent);
+	if (!perf_guest) {
+		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
+			"  exact: %4.1f%% [",
+			samples_per_sec,
+			100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+					 samples_per_sec)),
+			esamples_percent);
+	} else {
+		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+			" guest kernel:%4.1f%% guest us:%4.1f%%"
+			" exact: %4.1f%% [",
+			samples_per_sec,
+			100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec -
+						guest_kernel_samples_per_sec) /
+					  samples_per_sec)),
+			100.0 - (100.0 * ((samples_per_sec -
+					   guest_us_samples_per_sec) /
+					  samples_per_sec)),
+			esamples_percent);
+	}
 
 	if (nr_counters == 1 || !display_weighted) {
 		printf("%Ld", (u64)attrs[0].sample_period);
@@ -597,7 +622,6 @@ static void print_sym_table(void)
 
 		syme = rb_entry(nd, struct sym_entry, rb_node);
 		sym = sym_entry__symbol(syme);
-
 		if (++printed > print_entries || (int)syme->snap_count < count_filter)
 			continue;
 
@@ -761,7 +785,7 @@ static int key_mapped(int c)
 	return 0;
 }
 
-static void handle_keypress(int c)
+static void handle_keypress(struct perf_session *session, int c)
 {
 	if (!key_mapped(c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -830,7 +854,7 @@ static void handle_keypress(int c)
 		case 'Q':
 			printf("exiting.\n");
 			if (dump_symtab)
-				dsos__fprintf(stderr);
+				dsos__fprintf(&session->kerninfo_root, stderr);
 			exit(0);
 		case 's':
 			prompt_symbol(&sym_filter_entry, "Enter details symbol");
@@ -866,6 +890,7 @@ static void *display_thread(void *arg __used)
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 	struct termios tc, save;
 	int delay_msecs, c;
+	struct perf_session *session = (struct perf_session *) arg;
 
 	tcgetattr(0, &save);
 	tc = save;
@@ -886,7 +911,7 @@ repeat:
 	c = getc(stdin);
 	tcsetattr(0, TCSAFLUSH, &save);
 
-	handle_keypress(c);
+	handle_keypress(session, c);
 	goto repeat;
 
 	return NULL;
@@ -957,24 +982,46 @@ static void event__process_sample(const event_t *self,
 	u64 ip = self->ip.ip;
 	struct sym_entry *syme;
 	struct addr_location al;
+	struct kernel_info *kerninfo;
 	u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	++samples;
 
 	switch (origin) {
 	case PERF_RECORD_MISC_USER:
-		++userspace_samples;
+		++us_samples;
 		if (hide_user_symbols)
 			return;
+		kerninfo = kerninfo__findhost(&session->kerninfo_root);
 		break;
 	case PERF_RECORD_MISC_KERNEL:
+		++kernel_samples;
 		if (hide_kernel_symbols)
 			return;
+		kerninfo = kerninfo__findhost(&session->kerninfo_root);
 		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		++guest_kernel_samples;
+		kerninfo = kerninfo__find(&session->kerninfo_root,
+					  self->ip.pid);
+		break;
+	case PERF_RECORD_MISC_GUEST_USER:
+		++guest_us_samples;
+		/*
+		 * TODO: we don't process guest user from host side
+		 * except simple counting.
+		 */
+		return;
 	default:
 		return;
 	}
 
+	if (!kerninfo && perf_guest) {
+		pr_err("Can't find guest [%d]'s kernel information\n",
+			self->ip.pid);
+		return;
+	}
+
 	if (self->header.misc & PERF_RECORD_MISC_EXACT)
 		exact_samples++;
 
@@ -994,7 +1041,7 @@ static void event__process_sample(const event_t *self,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == session->vmlinux_maps[MAP__FUNCTION] &&
+		if (al.map == kerninfo->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
 			pr_err("The %s file can't be used\n",
 			       symbol_conf.vmlinux_name);
@@ -1261,7 +1308,7 @@ static int __cmd_top(void)
 
 	perf_session__mmap_read(session);
 
-	if (pthread_create(&thread, NULL, display_thread, NULL)) {
+	if (pthread_create(&thread, NULL, display_thread, session)) {
 		printf("Could not create display thread.\n");
 		exit(-1);
 	}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 10fe49e7048a..ab28bca92e52 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -32,5 +32,6 @@ extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
 extern int cmd_lock(int argc, const char **argv, const char *prefix);
+extern int cmd_kvm(int argc, const char **argv, const char *prefix);
 
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index db6ee94d4a8e..2a1162d413a8 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -19,3 +19,4 @@ perf-trace			mainporcelain common
 perf-probe			mainporcelain common
 perf-kmem			mainporcelain common
 perf-lock			mainporcelain common
+perf-kvm			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index d4be55b6cd34..985cdb4bd005 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -307,6 +307,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "probe",	cmd_probe,	0 },
 		{ "kmem",	cmd_kmem,	0 },
 		{ "lock",	cmd_lock,	0 },
+		{ "kvm",	cmd_kvm,	0 },
 	};
 	unsigned int i;
 	static const char ext[] = STRIP_EXTENSION;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index ec212748d651..02821febb704 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -131,4 +131,6 @@ struct ip_callchain {
 	u64 ips[0];
 };
 
+extern int perf_host, perf_guest;
+
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 04904b35ba81..0f60a3906808 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -24,7 +24,7 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 	}
 
 	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      event->ip.pid, event->ip.ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 571fb25f7eb9..e3fa8d3d11b4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -112,7 +112,11 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 		event_t ev = {
 			.header = {
 				.type = PERF_RECORD_MMAP,
-				.misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */
+				/*
+				 * Just like the kernel, see __perf_event_mmap
+				 * in kernel/perf_event.c
+				 */
+				.misc = PERF_RECORD_MISC_USER,
 			 },
 		};
 		int n;
@@ -167,11 +171,23 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 }
 
 int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session)
+			      struct perf_session *session,
+			      struct kernel_info *kerninfo)
 {
 	struct rb_node *nd;
+	struct map_groups *kmaps = &kerninfo->kmaps;
+	u16 misc;
 
-	for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]);
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (is_host_kernel(kerninfo))
+		misc = PERF_RECORD_MISC_KERNEL;
+	else
+		misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
 		event_t ev;
 		size_t size;
@@ -182,12 +198,13 @@ int event__synthesize_modules(event__handler_t process,
 
 		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
 		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
+		ev.mmap.header.misc = misc;
 		ev.mmap.header.type = PERF_RECORD_MMAP;
 		ev.mmap.header.size = (sizeof(ev.mmap) -
 				        (sizeof(ev.mmap.filename) - size));
 		ev.mmap.start = pos->start;
 		ev.mmap.len   = pos->end - pos->start;
+		ev.mmap.pid   = kerninfo->pid;
 
 		memcpy(ev.mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
@@ -250,13 +267,18 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
 
 int event__synthesize_kernel_mmap(event__handler_t process,
 				  struct perf_session *session,
+				  struct kernel_info *kerninfo,
 				  const char *symbol_name)
 {
 	size_t size;
+	const char *filename, *mmap_name;
+	char path[PATH_MAX];
+	char name_buff[PATH_MAX];
+	struct map *map;
+
 	event_t ev = {
 		.header = {
 			.type = PERF_RECORD_MMAP,
-			.misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
 		},
 	};
 	/*
@@ -266,16 +288,37 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
 
-	if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0)
+	mmap_name = kern_mmap_name(kerninfo, name_buff);
+	if (is_host_kernel(kerninfo)) {
+		/*
+		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
+		 * see kernel/perf_event.c __perf_event_mmap
+		 */
+		ev.header.misc = PERF_RECORD_MISC_KERNEL;
+		filename = "/proc/kallsyms";
+	} else {
+		ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		if (is_default_guest(kerninfo))
+			filename = (char *) symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir);
+			filename = path;
+		}
+	}
+
+	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
 		return -ENOENT;
 
+	map = kerninfo->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
-			"[kernel.kallsyms.%s]", symbol_name) + 1;
+			"%s%s", mmap_name, symbol_name) + 1;
 	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size));
+	ev.mmap.header.size = (sizeof(ev.mmap) -
+			(sizeof(ev.mmap.filename) - size));
 	ev.mmap.pgoff = args.start;
-	ev.mmap.start = session->vmlinux_maps[MAP__FUNCTION]->start;
-	ev.mmap.len   = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ;
+	ev.mmap.start = map->start;
+	ev.mmap.len   = map->end - ev.mmap.start;
+	ev.mmap.pid   = kerninfo->pid;
 
 	return process(&ev, session);
 }
@@ -329,22 +372,50 @@ int event__process_lost(event_t *self, struct perf_session *session)