[PATCH v9 3/4] perf,kvm/powerpc: Port perf kvm stat to powerpc

From: Hemant Kumar
Date: Tue Oct 06 2015 - 22:27:21 EST


perf kvm can be used to analyze guest exit reasons. This support already
exists in x86. Hence, porting it to powerpc.

- To trace KVM events :
perf kvm stat record
If many guests are running, we can track for a specific guest by using
--pid as in : perf kvm stat record --pid <pid>

- To see the results :
perf kvm stat report

The result shows the number of exits (from the guest context to
host/hypervisor context) grouped by their respective exit reasons with
their frequency.

Since, different powerpc machines have different KVM tracepoints, this
patch discovers the available tracepoints dynamically and accordingly
looks for them. If any single tracepoint is not present, this support
won't be enabled for reporting. To record, this will fail if any of the
events we are looking to record isn't available.
Right now, its only supported on PowerPC Book3S_HV architectures.

To analyze the different exits, group them and present them (in a slight
descriptive way) to the user, we need a mapping between the "exit
code" (dumped in the kvm_guest_exit tracepoint data) and to its related
Interrupt vector description (exit reason). This patch adds this mapping
in book3s_hv_exits.h.

It records on two available KVM tracepoints for book3s_hv:
"kvm_hv:kvm_guest_exit" and "kvm_hv:kvm_guest_enter".

Here is a sample o/p:
# pgrep qemu
19378
60515

2 Guests are running on the host.

# perf kvm stat record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 4.153 MB perf.data.guest (39624
samples) ]

# perf kvm stat report -p 60515

Analyze events for pid(s) 60515, all VCPUs:

VM-EXIT Samples Samples% Time% Min Time Max Time Avg time

SYSCALL 9141 63.67% 7.49% 1.26us 5782.39us 9.87us ( +- 6.46% )
H_DATA_STORAGE 4114 28.66% 5.07% 1.72us 4597.68us 14.84us ( +- 20.06% )
HV_DECREMENTER 418 2.91% 4.26% 0.70us 30002.22us 122.58us ( +- 70.29% )
EXTERNAL 392 2.73% 0.06% 0.64us 104.10us 1.94us ( +- 18.83% )
RETURN_TO_HOST 287 2.00% 83.11% 1.53us 124240.15us 3486.52us ( +- 16.81% )
H_INST_STORAGE 5 0.03% 0.00% 1.88us 3.73us 2.39us ( +- 14.20% )

Total Samples:14357, Total events handled time:1203918.42us.

Signed-off-by: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>
---
Changelog:
v8 to v9:
- Moved the book3s specific setup into one function.
- Removed the macros (which were being used only once).
- Formatting changes.
v7 to v8:
- Fixed a perf kvm stat live bug.
v6 to v7:
- Removed dependency on uapi.
v4 to v5:
- Removed dependency on arch/powerpc/kvm/trace_book3s.h and added them in
the userspace side.
- No more arch side dependency.
v1 to v3:
- Split the patches for powerpc and perf

tools/perf/arch/powerpc/Makefile | 2 +
tools/perf/arch/powerpc/util/Build | 1 +
tools/perf/arch/powerpc/util/book3s_hv_exits.h | 33 ++++++++
tools/perf/arch/powerpc/util/kvm-stat.c | 100 +++++++++++++++++++++++++
tools/perf/builtin-kvm.c | 18 +++++
tools/perf/util/kvm-stat.h | 1 +
6 files changed, 155 insertions(+)
create mode 100644 tools/perf/arch/powerpc/util/book3s_hv_exits.h
create mode 100644 tools/perf/arch/powerpc/util/kvm-stat.c

diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7fbca17..9f9cea3 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,5 @@
ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
+
+HAVE_KVM_STAT_SUPPORT := 1
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 7b8b0d1..c8fe207 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,6 @@
libperf-y += header.o
libperf-y += sym-handling.o
+libperf-y += kvm-stat.o

libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
new file mode 100644
index 0000000..e68ba2d
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -0,0 +1,33 @@
+#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
+#define ARCH_PERF_BOOK3S_HV_EXITS_H
+
+/*
+ * PowerPC Interrupt vectors : exit code to name mapping
+ */
+
+#define kvm_trace_symbol_exit \
+ {0x0, "RETURN_TO_HOST"}, \
+ {0x100, "SYSTEM_RESET"}, \
+ {0x200, "MACHINE_CHECK"}, \
+ {0x300, "DATA_STORAGE"}, \
+ {0x380, "DATA_SEGMENT"}, \
+ {0x400, "INST_STORAGE"}, \
+ {0x480, "INST_SEGMENT"}, \
+ {0x500, "EXTERNAL"}, \
+ {0x501, "EXTERNAL_LEVEL"}, \
+ {0x502, "EXTERNAL_HV"}, \
+ {0x600, "ALIGNMENT"}, \
+ {0x700, "PROGRAM"}, \
+ {0x800, "FP_UNAVAIL"}, \
+ {0x900, "DECREMENTER"}, \
+ {0x980, "HV_DECREMENTER"}, \
+ {0xc00, "SYSCALL"}, \
+ {0xd00, "TRACE"}, \
+ {0xe00, "H_DATA_STORAGE"}, \
+ {0xe20, "H_INST_STORAGE"}, \
+ {0xe40, "H_EMUL_ASSIST"}, \
+ {0xf00, "PERFMON"}, \
+ {0xf20, "ALTIVEC"}, \
+ {0xf40, "VSX"}
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
new file mode 100644
index 0000000..9d64df5
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -0,0 +1,100 @@
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+
+#include "book3s_hv_exits.h"
+
+#define NR_TPS 2
+
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 40;
+const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
+const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
+
+define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit);
+
+/* Tracepoints specific to ppc_book3s_hv */
+const char *ppc_book3s_hv_kvm_tp[] = {
+ "kvm_hv:kvm_guest_enter",
+ "kvm_hv:kvm_guest_exit",
+};
+
+/* 1 extra placeholder for NULL */
+const char *kvm_events_tp[NR_TPS + 1];
+const char *kvm_exit_reason;
+
+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"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+ { .name = "vmexit", .ops = &exit_events },
+ { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+ NULL,
+};
+
+
+static int is_tracepoint_available(const char *str, struct perf_evlist *evlist)
+{
+ return parse_events(evlist, str, NULL);
+}
+
+static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm,
+ struct perf_evlist *evlist)
+{
+ const char **events_ptr;
+ int i, nr_tp = 0, err = -1;
+
+ /* Check for book3s_hv tracepoints */
+ for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) {
+ err = is_tracepoint_available(*events_ptr, evlist);
+ if (err)
+ return -1;
+ nr_tp++;
+ }
+
+ for (i = 0; i < nr_tp; i++)
+ kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i];
+
+ kvm_events_tp[i] = NULL;
+ kvm_exit_reason = "trap";
+ kvm->exit_reasons = hv_exit_reasons;
+ kvm->exit_reasons_isa = "HV";
+
+ return 0;
+}
+
+/* Wrapper to setup kvm tracepoints */
+static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm)
+{
+ struct perf_evlist *evlist = perf_evlist__new();
+
+ if (evlist == NULL)
+ return -ENOMEM;
+
+ /* Right now, only supported on book3s_hv */
+ return ppc__setup_book3s_hv(kvm, evlist);
+}
+
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm)
+{
+ return ppc__setup_kvm_tp(kvm);
+}
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+ int ret;
+
+ ret = ppc__setup_kvm_tp(kvm);
+ if (ret) {
+ kvm->exit_reasons = NULL;
+ kvm->exit_reasons_isa = NULL;
+ }
+
+ return ret;
+}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 5104c7e..b50d3b9 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1145,6 +1145,11 @@ exit:
_p; \
})

+int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused)
+{
+ return 0;
+}
+
static int
kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
{
@@ -1161,7 +1166,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
NULL
};
const char * const *events_tp;
+ int ret;
+
events_tp_size = 0;
+ ret = setup_kvm_events_tp(kvm);
+ if (ret < 0) {
+ pr_err("Unable to setup the kvm tracepoints\n");
+ return ret;
+ }

for (events_tp = kvm_events_tp; *events_tp; events_tp++)
events_tp_size++;
@@ -1391,6 +1403,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
/*
* generate the event list
*/
+ err = setup_kvm_events_tp(kvm);
+ if (err < 0) {
+ pr_err("Unable to setup the kvm tracepoints\n");
+ return err;
+ }
+
kvm->evlist = kvm_live_event_list();
if (kvm->evlist == NULL) {
err = -1;
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index c965dc8..d01e735 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,

bool kvm_exit_event(struct perf_evsel *evsel);
bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);

#define define_exit_reasons_table(name, symbols) \
static struct exit_reasons_table name[] = { \
--
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/