[PATCH v3 2/6] powerpc/perf: Export memory hierarchy info to user space

From: Madhavan Srinivasan
Date: Wed Mar 22 2017 - 23:27:11 EST


The LDST field and DATA_SRC in SIER identifies the memory hierarchy level
(eg: L1, L2 etc), from which a data-cache miss for a marked instruction
was satisfied. Use the 'perf_mem_data_src' object to export this
hierarchy level to user space.

Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Cc: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
Cc: Daniel Axtens <dja@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Signed-off-by: Sukadev Bhattiprolu <sukadev@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Madhavan Srinivasan <maddy@xxxxxxxxxxxxxxxxxx>
---
Changelog v2:
- Fixed isa207_find_source() to consider all the possible sier[ldst] values.


arch/powerpc/include/asm/perf_event_server.h | 2 +
arch/powerpc/perf/core-book3s.c | 4 ++
arch/powerpc/perf/isa207-common.c | 80 ++++++++++++++++++++++++++++
arch/powerpc/perf/isa207-common.h | 16 +++++-
4 files changed, 101 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index ae0a23091a9b..446cdcd9b7f5 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -38,6 +38,8 @@ struct power_pmu {
unsigned long *valp);
int (*get_alternatives)(u64 event_id, unsigned int flags,
u64 alt[]);
+ void (*get_mem_data_src)(union perf_mem_data_src *dsrc,
+ u32 flags, struct pt_regs *regs);
u64 (*bhrb_filter_map)(u64 branch_sample_type);
void (*config_bhrb)(u64 pmu_bhrb_filter);
void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 2ff13249f87a..e241ebebab6f 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2049,6 +2049,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
data.br_stack = &cpuhw->bhrb_stack;
}

+ if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
+ ppmu->get_mem_data_src)
+ ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
+
if (perf_event_overflow(event, &data, regs))
power_pmu_stop(event, 0);
}
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index cd951fd231c4..41cc053ee692 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -148,6 +148,86 @@ static bool is_thresh_cmp_valid(u64 event)
return true;
}

+static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
+{
+ u64 ret = PERF_MEM_NA;
+
+ switch(idx) {
+ case 0:
+ /* Nothing to do */
+ break;
+ case 1:
+ ret = PLH(LVL, L1);
+ break;
+ case 2:
+ ret = PLH(LVL, L2);
+ break;
+ case 3:
+ ret = PLH(LVL, L3);
+ break;
+ case 4:
+ if (sub_idx <= 1)
+ ret = PLH(LVL, LOC_RAM);
+ else if (sub_idx > 1 && sub_idx <= 2)
+ ret = PLH(LVL, REM_RAM1);
+ else
+ ret = PLH(LVL, REM_RAM2);
+ ret |= P(SNOOP, HIT);
+ break;
+ case 5:
+ ret = PLH(LVL, REM_CCE1);
+ if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4))
+ ret |= P(SNOOP, HIT);
+ else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5))
+ ret |= P(SNOOP, HITM);
+ break;
+ case 6:
+ ret = PLH(LVL, REM_CCE2);
+ if ((sub_idx == 0) || (sub_idx == 2))
+ ret |= P(SNOOP, HIT);
+ else if ((sub_idx == 1) || (sub_idx == 3))
+ ret |= P(SNOOP, HITM);
+ break;
+ case 7:
+ ret = PSM(LVL, L1);
+ break;
+ }
+
+ return ret;
+}
+
+static inline bool is_load_store_inst(u64 sier)
+{
+ u64 val;
+ val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
+
+ /* 1 = load, 2 = store */
+ return val == 1 || val == 2;
+}
+
+void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
+ struct pt_regs *regs)
+{
+ u64 idx;
+ u32 sub_idx;
+ u64 sier;
+
+ /* Skip if no SIER support */
+ if (!(flags & PPMU_HAS_SIER)) {
+ dsrc->val = 0;
+ return;
+ }
+
+ sier = mfspr(SPRN_SIER);
+ if (is_load_store_inst(sier)) {
+ idx = (sier & ISA207_SIER_LDST_MASK) >> ISA207_SIER_LDST_SHIFT;
+ sub_idx = (sier & ISA207_SIER_DATA_SRC_MASK) >> ISA207_SIER_DATA_SRC_SHIFT;
+
+ dsrc->val = isa207_find_source(idx, sub_idx);
+ }
+}
+
+
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
{
unsigned int unit, pmc, cache, ebb;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 899210f14ee4..592aa0917cf3 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -260,6 +260,19 @@
#define MAX_ALT 2
#define MAX_PMU_COUNTERS 6

+#define ISA207_SIER_TYPE_SHIFT 15
+#define ISA207_SIER_TYPE_MASK (0x7ull << ISA207_SIER_TYPE_SHIFT)
+
+#define ISA207_SIER_LDST_SHIFT 1
+#define ISA207_SIER_LDST_MASK (0x7ull << ISA207_SIER_LDST_SHIFT)
+
+#define ISA207_SIER_DATA_SRC_SHIFT 53
+#define ISA207_SIER_DATA_SRC_MASK (0x7ull << ISA207_SIER_DATA_SRC_SHIFT)
+
+#define P(a, b) PERF_MEM_S(a, b)
+#define PLH(a, b) (P(OP, LOAD) | P(LVL, HIT) | P(a, b))
+#define PSM(a, b) (P(OP, STORE) | P(LVL, MISS) | P(a, b))
+
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp);
int isa207_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], unsigned long mmcr[],
@@ -267,6 +280,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]);
int isa207_get_alternatives(u64 event, u64 alt[],
const unsigned int ev_alt[][MAX_ALT], int size);
-
+void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
+ struct pt_regs *regs);

#endif
--
2.7.4