Power8/Power9 Perforence Monitoring Unit (PMU) supports
different sampling modes (SM) such as Random Instruction
Sampling (RIS), Random Load/Store Facility Sampling (RLS)
and Random Branch Sampling (RBS). Sample mode RLS updates
Sampled Instruction Event Register [SIER] bits with memory
hierarchy information for a cache reload. Patchset exports
the hierarchy information to the user via the perf_mem_data_src
object from SIER.
Patchset is a rebase of the work posted previously with minor
updates to it.
https://lkml.org/lkml/2015/6/11/92
Changelog v2:
-Updated the commit messages
-Fixed isa207_find_source() to consider all the possible sier[ldst] values.
Changelog v1:
- Fixed author-ship for the first patch and added suka's "Signed-off-by:".
Madhavan Srinivasan (5):
powerpc/perf: Export memory hierarchy info to user space
powerpc/perf: Support to export MMCRA[TEC*] field to userspace
powerpc/perf: Support to export SIERs bit in Power8
powerpc/perf: Support to export SIERs bit in Power9
powerpc/perf: Add Power8 mem_access event to sysfs
Sukadev Bhattiprolu (1):
powerpc/perf: Define big-endian version of perf_mem_data_src
arch/powerpc/include/asm/perf_event_server.h | 3 +
arch/powerpc/perf/core-book3s.c | 8 +++
arch/powerpc/perf/isa207-common.c | 88 ++++++++++++++++++++++++++++
arch/powerpc/perf/isa207-common.h | 26 +++++++-
arch/powerpc/perf/power8-events-list.h | 6 ++
arch/powerpc/perf/power8-pmu.c | 4 ++
arch/powerpc/perf/power9-pmu.c | 2 +
include/uapi/linux/perf_event.h | 16 +++++
tools/include/uapi/linux/perf_event.h | 16 +++++
9 files changed, 168 insertions(+), 1 deletion(-)
--
2.7.4
From: Sukadev Bhattiprolu <[email protected]>
perf_mem_data_src is an union that is initialized via the ->val field
and accessed via the bitmap fields. For this to work on big endian
platforms (Which is broken now), we also need a big-endian represenation
of perf_mem_data_src. i.e, in a big endian system, if user request
PERF_SAMPLE_DATA_SRC (perf report -d), will get the default value from
perf_sample_data_init(), which is PERF_MEM_NA. Value for PERF_MEM_NA
is constructed using shifts:
/* TLB access */
#define PERF_MEM_TLB_NA 0x01 /* not available */
...
#define PERF_MEM_TLB_SHIFT 26
#define PERF_MEM_S(a, s) \
(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
PERF_MEM_S(LVL, NA) |\
PERF_MEM_S(SNOOP, NA) |\
PERF_MEM_S(LOCK, NA) |\
PERF_MEM_S(TLB, NA))
Which works out as:
((0x01 << 0) | (0x01 << 5) | (0x01 << 19) | (0x01 << 24) | (0x01 << 26))
Which means the PERF_MEM_NA value comes out of the kernel as 0x5080021
in CPU endian.
But then in the perf tool, the code uses the bitfields to inspect the
value, and currently the bitfields are defined using little endian
ordering.
So eg. in perf_mem__tlb_scnprintf() we see:
data_src->val = 0x5080021
op = 0x0
lvl = 0x0
snoop = 0x0
lock = 0x0
dtlb = 0x0
rsvd = 0x5080021
Patch does a minimal fix of adding big endian definition of the bitfields
to match the values that are already exported by the kernel on big endian.
And it makes no change on little endian.
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Sukadev Bhattiprolu <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
Changelog v2:
-Added Michael Ellerman's explanation to comiit message.
Changelog v1:
-Fixed author-ship and added suka's "Signed-off-by:".
include/uapi/linux/perf_event.h | 16 ++++++++++++++++
tools/include/uapi/linux/perf_event.h | 16 ++++++++++++++++
2 files changed, 32 insertions(+)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index c66a485a24ac..c4af1159a200 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -891,6 +891,7 @@ enum perf_callchain_context {
#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
+#if defined(__LITTLE_ENDIAN_BITFIELD)
union perf_mem_data_src {
__u64 val;
struct {
@@ -902,6 +903,21 @@ union perf_mem_data_src {
mem_rsvd:31;
};
};
+#elif defined(__BIG_ENDIAN_BITFIELD)
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_rsvd:31,
+ mem_dtlb:7, /* tlb access */
+ mem_lock:2, /* lock instr */
+ mem_snoop:5, /* snoop mode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_op:5; /* type of opcode */
+ };
+};
+#else
+#error "Unknown endianness"
+#endif
/* type of opcode (load/store/prefetch,code) */
#define PERF_MEM_OP_NA 0x01 /* not available */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index c66a485a24ac..c4af1159a200 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -891,6 +891,7 @@ enum perf_callchain_context {
#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
+#if defined(__LITTLE_ENDIAN_BITFIELD)
union perf_mem_data_src {
__u64 val;
struct {
@@ -902,6 +903,21 @@ union perf_mem_data_src {
mem_rsvd:31;
};
};
+#elif defined(__BIG_ENDIAN_BITFIELD)
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_rsvd:31,
+ mem_dtlb:7, /* tlb access */
+ mem_lock:2, /* lock instr */
+ mem_snoop:5, /* snoop mode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_op:5; /* type of opcode */
+ };
+};
+#else
+#error "Unknown endianness"
+#endif
/* type of opcode (load/store/prefetch,code) */
#define PERF_MEM_OP_NA 0x01 /* not available */
--
2.7.4
Threshold feature when used with MMCRA [Threshold Event Counter Event],
MMCRA[Threshold Start event] and MMCRA[Threshold End event] will update
MMCRA[Threashold Event Counter Exponent] and MMCRA[Threshold Event
Counter Multiplier] with the corresponding threshold event count values.
Patch to export MMCRA[TECX/TECM] to userspace in 'weight' field of
struct perf_sample_data.
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Sebastian Andrzej Siewior <[email protected]>
Cc: Anna-Maria Gleixner <[email protected]>
Cc: Daniel Axtens <[email protected]>
Cc: Sukadev Bhattiprolu <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
arch/powerpc/include/asm/perf_event_server.h | 1 +
arch/powerpc/perf/core-book3s.c | 4 ++++
arch/powerpc/perf/isa207-common.c | 8 ++++++++
arch/powerpc/perf/isa207-common.h | 10 ++++++++++
4 files changed, 23 insertions(+)
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 446cdcd9b7f5..723bf48e7494 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -40,6 +40,7 @@ struct power_pmu {
u64 alt[]);
void (*get_mem_data_src)(union perf_mem_data_src *dsrc,
u32 flags, struct pt_regs *regs);
+ void (*get_mem_weight)(u64 *weight);
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 e241ebebab6f..6c2d4168daec 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2053,6 +2053,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
ppmu->get_mem_data_src)
ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
+ if (event->attr.sample_type & PERF_SAMPLE_WEIGHT &&
+ ppmu->get_mem_weight)
+ ppmu->get_mem_weight(&data.weight);
+
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 41cc053ee692..292f6a242bb4 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -227,6 +227,14 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
}
}
+void isa207_get_mem_weight(u64 *weight)
+{
+ u64 mmcra = mfspr(SPRN_MMCRA);
+ u64 exp = MMCRA_THR_CTR_EXP(mmcra);
+ u64 mantissa = MMCRA_THR_CTR_MANT(mmcra);
+
+ *weight = mantissa << (2 * exp);
+}
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
{
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 592aa0917cf3..23e0516df4a4 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -248,6 +248,15 @@
#define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT)
#define MMCRA_SDAR_MODE_NO_UPDATES ~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
#define MMCRA_IFM_SHIFT 30
+#define MMCRA_THR_CTR_MANT_SHIFT 19
+#define MMCRA_THR_CTR_MANT_MASK 0x7Ful
+#define MMCRA_THR_CTR_MANT(v) (((v) >> MMCRA_THR_CTR_MANT_SHIFT) &\
+ MMCRA_THR_CTR_MANT_MASK)
+
+#define MMCRA_THR_CTR_EXP_SHIFT 27
+#define MMCRA_THR_CTR_EXP_MASK 0x7ul
+#define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\
+ MMCRA_THR_CTR_EXP_MASK)
/* MMCR1 Threshold Compare bit constant for power9 */
#define p9_MMCRA_THR_CMP_SHIFT 45
@@ -282,5 +291,6 @@ 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);
+void isa207_get_mem_weight(u64 *weight);
#endif
--
2.7.4
Patch to export SIER bits to userspace via
perf_mem_data_src and perf_sample_data struct.
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Daniel Axtens <[email protected]>
Cc: Andrew Donnellan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Sukadev Bhattiprolu <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
arch/powerpc/perf/power8-pmu.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index ce15b19a7962..932d7536f0eb 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -325,6 +325,8 @@ static struct power_pmu power8_pmu = {
.bhrb_filter_map = power8_bhrb_filter_map,
.get_constraint = isa207_get_constraint,
.get_alternatives = power8_get_alternatives,
+ .get_mem_data_src = isa207_get_mem_data_src,
+ .get_mem_weight = isa207_get_mem_weight,
.disable_pmc = isa207_disable_pmc,
.flags = PPMU_HAS_SIER | PPMU_ARCH_207S,
.n_generic = ARRAY_SIZE(power8_generic_events),
--
2.7.4
Patch add "mem_access" event to sysfs. This as-is not a raw event
supported by Power8 pmu. Instead, it is formed based on
raw event encoding specificed in isa207-common.h.
Primary PMU event used here is PM_MRK_INST_CMPL.
This event tracks only the completed marked instructions.
Random sampling mode (MMCRA[SM]) with Random Instruction
Sampling (RIS) is enabled to mark type of instructions.
With Random sampling in RLS mode with PM_MRK_INST_CMPL event,
the LDST /DATA_SRC fields in SIER identifies the memory
hierarchy level (eg: L1, L2 etc) statisfied a data-cache
miss for a marked instruction.
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Sukadev Bhattiprolu <[email protected]>
Cc: Daniel Axtens <[email protected]>
Cc: Andrew Donnellan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
arch/powerpc/perf/power8-events-list.h | 6 ++++++
arch/powerpc/perf/power8-pmu.c | 2 ++
2 files changed, 8 insertions(+)
diff --git a/arch/powerpc/perf/power8-events-list.h b/arch/powerpc/perf/power8-events-list.h
index 3a2e6e8ebb92..0f1d184627cc 100644
--- a/arch/powerpc/perf/power8-events-list.h
+++ b/arch/powerpc/perf/power8-events-list.h
@@ -89,3 +89,9 @@ EVENT(PM_MRK_FILT_MATCH, 0x2013c)
EVENT(PM_MRK_FILT_MATCH_ALT, 0x3012e)
/* Alternate event code for PM_LD_MISS_L1 */
EVENT(PM_LD_MISS_L1_ALT, 0x400f0)
+/*
+ * Memory Access Event -- mem_access
+ * Primary PMU event used here is PM_MRK_INST_CMPL, along with
+ * Random Load/Store Facility Sampling (RIS) in Random sampling mode (MMCRA[SM]).
+ */
+EVENT(MEM_ACCESS, 0x10401e0)
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 932d7536f0eb..5463516e369b 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -90,6 +90,7 @@ GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN);
GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL);
GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1);
GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(mem_access, MEM_ACCESS);
CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
@@ -120,6 +121,7 @@ static struct attribute *power8_events_attr[] = {
GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
GENERIC_EVENT_PTR(PM_LD_REF_L1),
GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(MEM_ACCESS),
CACHE_EVENT_PTR(PM_LD_MISS_L1),
CACHE_EVENT_PTR(PM_LD_REF_L1),
--
2.7.4
Patch to export SIER bits to userspace via
perf_mem_data_src and perf_sample_data struct.
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Sukadev Bhattiprolu <[email protected]>
Cc: Daniel Axtens <[email protected]>
Cc: Andrew Donnellan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
arch/powerpc/perf/power9-pmu.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 7f6582708e06..018f8e90ac35 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -427,6 +427,8 @@ static struct power_pmu power9_pmu = {
.bhrb_filter_map = power9_bhrb_filter_map,
.get_constraint = isa207_get_constraint,
.get_alternatives = power9_get_alternatives,
+ .get_mem_data_src = isa207_get_mem_data_src,
+ .get_mem_weight = isa207_get_mem_weight,
.disable_pmc = isa207_disable_pmc,
.flags = PPMU_HAS_SIER | PPMU_ARCH_207S,
.n_generic = ARRAY_SIZE(power9_generic_events),
--
2.7.4
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 <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Sebastian Andrzej Siewior <[email protected]>
Cc: Anna-Maria Gleixner <[email protected]>
Cc: Daniel Axtens <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Stephane Eranian <[email protected]>
Signed-off-by: Sukadev Bhattiprolu <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
---
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