[RFC 3/4] perf kvm: Enable 'report' on powerpc

[Ravi Bangoria]

'perf kvm record' on powerpc will record kvm_hv:kvm_guest_exit event
instead of cycles. However, to have some kind of periodicity, we can't
use all the kvm exits, rather exits which are bound to happen in certain
intervals. HV_DECREMENTER Interrupt forces the threads to exit after an
interval of 10 ms.

This patch makes use of the 'kvm_guest_exit' tracepoint and checks the
exit reason for any kvm exit. If it is HV_DECREMENTER, then the
instruction pointer dumped along with this tracepoint is retrieved and
mapped with the guest kallsyms.

Signed-off-by: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>
---
 tools/perf/util/event.c   |  7 +++--
 tools/perf/util/evsel.c   | 77 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evsel.h   |  7 +++++
 tools/perf/util/session.c |  7 +++--
 4 files changed, 92 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc0a3f0..31bbc50 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1299,15 +1299,16 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct machine *machine,
 				  struct addr_location *al,
 				  struct perf_sample *sample,
-				  struct perf_evsel *evsel __maybe_unused)
+				  struct perf_evsel *evsel)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	u8 cpumode;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
-
 	if (thread == NULL)
 		return -1;
 
+	al->cpumode = cpumode = arch__get_cpumode(event, evsel, sample);
+
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0902fe4..a4d309e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1622,6 +1622,82 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset,
 #define OVERFLOW_CHECK_u64(offset) \
 	OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
 
+#define KVMPPC_EXIT "kvm_hv:kvm_guest_exit"
+#define HV_DECREMENTER 2432
+#define HV_BIT 3
+#define PR_BIT 49
+#define PPC_MAX 63
+
+bool is_kvmppc_exit_event(struct perf_evsel *evsel)
+{
+	static unsigned int kvmppc_exit;
+
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return false;
+
+	if (unlikely(kvmppc_exit == 0)) {
+		if (strcmp(KVMPPC_EXIT, evsel->name))
+			return false;
+		kvmppc_exit = evsel->attr.config;
+	} else if (kvmppc_exit != evsel->attr.config) {
+		return false;
+	}
+
+	return true;
+}
+
+bool is_hv_dec_trap(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	int trap = perf_evsel__intval(evsel, sample, "trap");
+	return trap == HV_DECREMENTER;
+}
+
+bool is_perf_data_reorded_on_ppc(struct perf_evlist *evlist)
+{
+	if (evlist && evlist->env && evlist->env->arch)
+		return !strcmp(evlist->env->arch, "ppc64") ||
+			!strcmp(evlist->env->arch, "ppc64le");
+	return false;
+}
+
+u8 arch__get_cpumode(const union perf_event *event,
+		     struct perf_evsel *evsel,
+		     struct perf_sample *sample)
+{
+	unsigned long hv, pr, msr;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	if (!(is_perf_data_reorded_on_ppc(evsel->evlist) &&
+	      perf_guest_only() &&
+	      is_kvmppc_exit_event(evsel)))
+		goto ret;
+
+	if (sample->raw_data && is_hv_dec_trap(evsel, sample)) {
+		msr = perf_evsel__intval(evsel, sample, "msr");
+		hv = msr & ((unsigned long)1 << (PPC_MAX - HV_BIT));
+		pr = msr & ((unsigned long)1 << (PPC_MAX - PR_BIT));
+
+		if (!hv && pr)
+			cpumode = PERF_RECORD_MISC_GUEST_USER;
+		else
+			cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+	}
+
+ret:
+	return cpumode;
+}
+
+u64 arch__get_ip(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	if (is_perf_data_reorded_on_ppc(evsel->evlist) &&
+	    perf_guest_only() &&
+	    is_kvmppc_exit_event(evsel) &&
+	    is_hv_dec_trap(evsel, sample))
+		return perf_evsel__intval(evsel, sample, "pc");
+
+	return sample->ip;
+}
+
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
@@ -1795,6 +1871,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		OVERFLOW_CHECK(array, data->raw_size, max_size);
 		data->raw_data = (void *)array;
 		array = (void *)array + data->raw_size;
+		data->ip = arch__get_ip(evsel, data);
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index efad78f..a5f5cb5 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -408,4 +408,11 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv);
 
+u64 arch__get_ip(struct perf_evsel *evsel, struct perf_sample *sample);
+u8 arch__get_cpumode(const union perf_event *event, struct perf_evsel *evsel,
+		     struct perf_sample *sample);
+bool is_kvmppc_exit_event(struct perf_evsel *evsel);
+bool is_hv_dec_trap(struct perf_evsel *evsel, struct perf_sample *sample);
+bool is_perf_data_reorded_on_ppc(struct perf_evlist *evlist);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d..52beee8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1131,9 +1131,10 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
 					       union perf_event *event,
-					       struct perf_sample *sample)
+					       struct perf_sample *sample,
+					       struct perf_evsel *evsel)
 {
-	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	const u8 cpumode = arch__get_cpumode(event, evsel, sample);
 	struct machine *machine;
 
 	if (perf_guest &&
@@ -1237,7 +1238,7 @@ static int machines__deliver_event(struct machines *machines,
 
 	evsel = perf_evlist__id2evsel(evlist, sample->id);
 
-	machine = machines__find_for_cpumode(machines, event, sample);
+	machine = machines__find_for_cpumode(machines, event, sample, evsel);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-- 
2.1.4