Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf changes from Ingo Molnar:
 "Kernel side changes:

   - Consolidate the PMU interrupt-disabled code amongst architectures
     (Vince Weaver)

   - misc fixes

  Tooling changes (new features, user visible changes):

   - Add support for pagefault tracing in 'trace', please see multiple
     examples in the changeset messages (Stanislav Fomichev).

   - Add pagefault statistics in 'trace' (Stanislav Fomichev)

   - Add header for columns in 'top' and 'report' TUI browsers (Jiri
     Olsa)

   - Add pagefault statistics in 'trace' (Stanislav Fomichev)

   - Add IO mode into timechart command (Stanislav Fomichev)

   - Fallback to syscalls:* when raw_syscalls:* is not available in the
     perl and python perf scripts.  (Daniel Bristot de Oliveira)

   - Add --repeat global option to 'perf bench' to be used in benchmarks
     such as the existing 'futex' one, that was modified to use it
     instead of a local option.  (Davidlohr Bueso)

   - Fix fd -> pathname resolution in 'trace', be it using /proc or a
     vfs_getname probe point.  (Arnaldo Carvalho de Melo)

   - Add suggestion of how to set perf_event_paranoid sysctl, to help
     non-root users trying tools like 'trace' to get a working
     environment.  (Arnaldo Carvalho de Melo)

   - Updates from trace-cmd for traceevent plugin_kvm plus args cleanup
     (Steven Rostedt, Jan Kiszka)

   - Support S/390 in 'perf kvm stat' (Alexander Yarygin)

  Tooling infrastructure changes:

   - Allow reserving a row for header purposes in the hists browser
     (Arnaldo Carvalho de Melo)

   - Various fixes and prep work related to supporting Intel PT (Adrian
     Hunter)

   - Introduce multiple debug variables control (Jiri Olsa)

   - Add callchain and additional sample information for python scripts
     (Joseph Schuchart)

   - More prep work to support Intel PT: (Adrian Hunter)
     - Polishing 'script' BTS output
     - 'inject' can specify --kallsym
     - VDSO is per machine, not a global var
     - Expose data addr lookup functions previously private to 'script'
     - Large mmap fixes in events processing

   - Include standard stringify macros in power pc code (Sukadev
     Bhattiprolu)

  Tooling cleanups:

   - Convert open coded equivalents to asprintf() (Andy Shevchenko)

   - Remove needless reassignments in 'trace' (Arnaldo Carvalho de Melo)

   - Cache the is_exit syscall test in 'trace) (Arnaldo Carvalho de
     Melo)

   - No need to reimplement err() in 'perf bench sched-messaging', drop
     barf().  (Davidlohr Bueso).

   - Remove ev_name argument from perf_evsel__hists_browse, can be
     obtained from the other parameters.  (Jiri Olsa)

  Tooling fixes:

   - Fix memory leak in the 'sched-messaging' perf bench test.
     (Davidlohr Bueso)

   - The -o and -n 'perf bench mem' options are mutually exclusive, emit
     error when both are specified.  (Davidlohr Bueso)

   - Fix scrollbar refresh row index in the ui browser, problem exposed
     now that headers will be added and will be allowed to be switched
     on/off.  (Jiri Olsa)

   - Handle the num array type in python properly (Sebastian Andrzej
     Siewior)

   - Fix wrong condition for allocation failure (Jiri Olsa)

   - Adjust callchain based on DWARF debug info on powerpc (Sukadev
     Bhattiprolu)

   - Fix a risk for doing free on uninitialized pointer in traceevent
     lib (Rickard Strandqvist)

   - Update attr test with PERF_FLAG_FD_CLOEXEC flag (Jiri Olsa)

   - Enable close-on-exec flag on perf file descriptor (Yann Droneaud)

   - Fix build on gcc 4.4.7 (Arnaldo Carvalho de Melo)

   - Event ordering fixes (Jiri Olsa)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (123 commits)
  Revert "perf tools: Fix jump label always changing during tracing"
  perf tools: Fix perf usage string leftover
  perf: Check permission only for parent tracepoint event
  perf record: Store PERF_RECORD_FINISHED_ROUND only for nonempty rounds
  perf record: Always force PERF_RECORD_FINISHED_ROUND event
  perf inject: Add --kallsyms parameter
  perf tools: Expose 'addr' functions so they can be reused
  perf session: Fix accounting of ordered samples queue
  perf powerpc: Include util/util.h and remove stringify macros
  perf tools: Fix build on gcc 4.4.7
  perf tools: Add thread parameter to vdso__dso_findnew()
  perf tools: Add dso__type()
  perf tools: Separate the VDSO map name from the VDSO dso name
  perf tools: Add vdso__new()
  perf machine: Fix the lifetime of the VDSO temporary file
  perf tools: Group VDSO global variables into a structure
  perf session: Add ability to skip 4GiB or more
  perf session: Add ability to 'skip' a non-piped event stream
  perf tools: Pass machine to vdso__dso_findnew()
  perf tools: Add dso__data_size()
  ...

1 files changed, 156 insertions, 0 deletions

diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
new file mode 100644
index 000000000000..14e4e668fad7
--- /dev/null
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -0,0 +1,156 @@
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
+define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+/*
+ * For the mmio events, we treat:
+ * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+ * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+ */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "gpa");
+	key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	/* MMIO read begin event in kernel. */
+	if (kvm_exit_event(evsel))
+		return true;
+
+	/* MMIO write begin event in kernel. */
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+			   struct event_key *key)
+{
+	/* MMIO write end event in kernel. */
+	if (kvm_entry_event(evsel))
+		return true;
+
+	/* MMIO read end event in kernel.*/
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				  struct event_key *key,
+				  char *decode)
+{
+	scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+		  (unsigned long)key->key,
+		  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+	.is_begin_event = mmio_event_begin,
+	.is_end_event = mmio_event_end,
+	.decode_key = mmio_event_decode_key,
+	.name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "port");
+	key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+		ioport_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				    struct event_key *key,
+				    char *decode)
+{
+	scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+		  (unsigned long long)key->key,
+		  key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+	.is_begin_event = ioport_event_begin,
+	.is_end_event = ioport_event_end,
+	.decode_key = ioport_event_decode_key,
+	.name = "IO Port Access"
+};
+
+const char * const kvm_events_tp[] = {
+	"kvm:kvm_entry",
+	"kvm:kvm_exit",
+	"kvm:kvm_mmio",
+	"kvm:kvm_pio",
+	NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ .name = "mmio", .ops = &mmio_events },
+	{ .name = "ioport", .ops = &ioport_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	"HLT",
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+	if (strstr(cpuid, "Intel")) {
+		kvm->exit_reasons = vmx_exit_reasons;
+		kvm->exit_reasons_isa = "VMX";
+	} else if (strstr(cpuid, "AMD")) {
+		kvm->exit_reasons = svm_exit_reasons;
+		kvm->exit_reasons_isa = "SVM";
+	} else
+		return -ENOTSUP;
+
+	return 0;
+}