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>

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]

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)
 

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]);

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;

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;

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");
@@ -359,19 +360,25 @@ 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;
 
 		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;
 

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;
+}

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,