perf kvm: Events analysis tool

Add 'perf kvm stat' support to analyze kvm vmexit/mmio/ioport smartly

Usage:
- kvm stat
  run a command and gather performance counter statistics, it is the alias of
  perf stat

- trace kvm events:
  perf kvm stat record, or, if other tracepoints are interesting as well, we
  can append the events like this:
  perf kvm stat record -e timer:* -a

  If many guests are running, we can track the specified guest by using -p or
  --pid, -a is used to track events generated by all guests.

- show the result:
  perf kvm stat report

The output example is following:
13005
13059

total 2 guests are running on the host

Then, track the guest whose pid is 13059:
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.253 MB perf.data.guest (~11065 samples) ]

See the vmexit events:

Analyze events for all VCPUs:

             VM-EXIT    Samples  Samples%     Time%         Avg time

         APIC_ACCESS        460    70.55%     0.01%     22.44us ( +-   1.75% )
                 HLT         93    14.26%    99.98% 832077.26us ( +-  10.42% )
  EXTERNAL_INTERRUPT         64     9.82%     0.00%     35.35us ( +-  14.21% )
   PENDING_INTERRUPT         24     3.68%     0.00%      9.29us ( +-  31.39% )
           CR_ACCESS          7     1.07%     0.00%      8.12us ( +-   5.76% )
      IO_INSTRUCTION          3     0.46%     0.00%     18.00us ( +-  11.79% )
       EXCEPTION_NMI          1     0.15%     0.00%      5.83us ( +-   -nan% )

Total Samples:652, Total events handled time:77396109.80us.

See the mmio events:

Analyze events for all VCPUs:

         MMIO Access    Samples  Samples%     Time%         Avg time

        0xfee00380:W        387    84.31%    79.28%      8.29us ( +-   3.32% )
        0xfee00300:W         24     5.23%     9.96%     16.79us ( +-   1.97% )
        0xfee00300:R         24     5.23%     7.83%     13.20us ( +-   3.00% )
        0xfee00310:W         24     5.23%     2.93%      4.94us ( +-   3.84% )

Total Samples:459, Total events handled time:4044.59us.

See the ioport event:

Analyze events for all VCPUs:

      IO Port Access    Samples  Samples%     Time%         Avg time

         0xc050:POUT          3   100.00%   100.00%     13.75us ( +-  10.83% )

Total Samples:3, Total events handled time:41.26us.

And, --vcpu is used to track the specified vcpu and --key is used to sort the
result:

Analyze events for VCPU 0:

             VM-EXIT    Samples  Samples%     Time%         Avg time

                 HLT         27    13.85%    99.97% 405790.24us ( +-  12.70% )
  EXTERNAL_INTERRUPT         13     6.67%     0.00%     27.94us ( +-  22.26% )
         APIC_ACCESS        146    74.87%     0.03%     21.69us ( +-   2.91% )
      IO_INSTRUCTION          2     1.03%     0.00%     17.77us ( +-  20.56% )
           CR_ACCESS          2     1.03%     0.00%      8.55us ( +-   6.47% )
   PENDING_INTERRUPT          5     2.56%     0.00%      6.27us ( +-   3.94% )

Total Samples:195, Total events handled time:10959950.90us.
Signed-off-by: NDong Hao <haodong@linux.vnet.ibm.com>
Signed-off-by: NRunzhen Wang <runzhen@linux.vnet.ibm.com>
[ Dong Hao <haodong@linux.vnet.ibm.com>
  Runzhen Wang <runzhen@linux.vnet.ibm.com>:
     - rebase it on current acme's tree
     - fix the compiling-error on i386 ]
Signed-off-by: NXiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org
Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1347870675-31495-4-git-send-email-haodong@linux.vnet.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-kvm.txt

@@ -12,7 +12,7 @@ SYNOPSIS
 	[--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}
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
 
 DESCRIPTION
 -----------
@@ -38,6 +38,18 @@ There are a couple of variants of perf kvm:
   so that other tools can be used to fetch packages with matching symbol tables
   for use by perf report.
 
+  'perf kvm stat <command>' to run a command and gather performance counter
+  statistics.
+  Especially, perf 'kvm stat record/report' generates a statistical analysis
+  of KVM events. Currently, vmexit, mmio and ioport events are supported.
+  'perf kvm stat record <command>' records kvm events and the events between
+  start and end <command>.
+  And this command produces a file which contains tracing results of kvm
+  events.
+
+  'perf kvm stat report' reports statistical data which includes events
+  handled time, samples, and so on.
+
 OPTIONS
 -------
 -i::
@@ -68,7 +80,21 @@ OPTIONS
 --guestvmlinux=<path>::
 	Guest os kernel vmlinux.
 
+STAT REPORT OPTIONS
+-------------------
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+--events=<value>::
+       events to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
-linkperf:perf-diff[1], linkperf:perf-buildid-list[1]
+linkperf:perf-diff[1], linkperf:perf-buildid-list[1],
+linkperf:perf-stat[1]

tools/perf/MANIFEST

@@ -16,3 +16,6 @@ arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h
+arch/x86/include/asm/svm.h
+arch/x86/include/asm/vmx.h
+arch/x86/include/asm/kvm_host.h

tools/perf/util/header.c

@@ -1673,6 +1673,11 @@ static int process_build_id(struct perf_file_section *section,
 	return 0;
 }
 
+static char *read_cpuid(struct perf_header *ph, int fd)
+{
+	return do_read_string(fd, ph);
+}
+
 static struct perf_evsel *
 perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
@@ -1726,6 +1731,7 @@ process_event_desc(struct perf_file_section *section __maybe_unused,
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
+	char *(*read)(struct perf_header *h, int fd);
 	int (*process)(struct perf_file_section *section,
 		       struct perf_header *h, int feat, int fd, void *data);
 	const char *name;
@@ -1740,6 +1746,9 @@ struct feature_ops {
 #define FEAT_OPF(n, func) \
 	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
 		.full_only = true }
+#define FEAT_OPA_R(n, func) \
+	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
+		.read  = read_##func }
 
 /* feature_ops not implemented: */
 #define print_tracing_data	NULL
@@ -1754,7 +1763,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_ARCH,		arch),
 	FEAT_OPA(HEADER_NRCPUS,		nrcpus),
 	FEAT_OPA(HEADER_CPUDESC,	cpudesc),
-	FEAT_OPA(HEADER_CPUID,		cpuid),
+	FEAT_OPA_R(HEADER_CPUID,	cpuid),
 	FEAT_OPA(HEADER_TOTAL_MEM,	total_mem),
 	FEAT_OPP(HEADER_EVENT_DESC,	event_desc),
 	FEAT_OPA(HEADER_CMDLINE,	cmdline),
@@ -1809,6 +1818,54 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	return 0;
 }
 
+struct header_read_data {
+	int feat;
+	char *result;
+};
+
+static int perf_file_section__read_feature(struct perf_file_section *section,
+				struct perf_header *ph,
+				int feat, int fd, void *data)
+{
+	struct header_read_data *hd = data;
+
+	if (feat != hd->feat)
+		return 0;
+
+	if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
+		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+				"%d, continuing...\n", section->offset, feat);
+	return 0;
+	}
+
+	if (feat >= HEADER_LAST_FEATURE) {
+		pr_warning("unknown feature %d\n", feat);
+		return 0;
+	}
+
+	if (!feat_ops[feat].read) {
+		pr_warning("read is not supported for feature %d\n", feat);
+		return 0;
+	}
+
+	hd->result = feat_ops[feat].read(ph, fd);
+	return 0;
+}
+
+char *perf_header__read_feature(struct perf_session *session, int feat)
+{
+	struct perf_header *header = &session->header;
+	struct header_read_data hd;
+	int fd = session->fd;
+
+	hd.feat = feat;
+	hd.result = NULL;
+
+	perf_header__process_sections(header, fd, &hd,
+				perf_file_section__read_feature);
+	return hd.result;
+}
+
 static int do_write_feat(int fd, struct perf_header *h, int type,
 			 struct perf_file_section **p,
 			 struct perf_evlist *evlist)

tools/perf/util/header.h

@@ -94,6 +94,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 				  int feat, int fd, void *data));
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+char *perf_header__read_feature(struct perf_session *session, int feat);
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms, bool is_vdso);

tools/perf/util/thread.h

@@ -16,6 +16,8 @@ struct thread {
 	bool			comm_set;
 	char			*comm;
 	int			comm_len;
+
+	void			*priv;
 };
 
 struct machine;