[PATCH v3 2/6] powerpc/perf: Export memory hierarchy info to user space
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. Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Madhavan Srinivasan --- arch/powerpc/include/asm/perf_event_server.h | 2 + arch/powerpc/perf/core-book3s.c | 4 ++ arch/powerpc/perf/isa207-common.c| 74 arch/powerpc/perf/isa207-common.h| 16 +- 4 files changed, 95 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..a8b100ef8e6c 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -148,6 +148,80 @@ 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 = PH(LVL, L1); + break; + case 2: + ret = PH(LVL, L2); + break; + case 3: + ret = PH(LVL, L3); + break; + case 4: + if (sub_idx <= 1) + ret = PH(LVL, LOC_RAM); + else if (sub_idx > 1 && sub_idx <= 2) + ret = PH(LVL, REM_RAM1); + else + ret = PH(LVL, REM_RAM2); + ret |= P(SNOOP, HIT); + break; + case 5: + ret = PH(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 = PH(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 = PM(LVL, L1); + break; + } + + return ret; +} + +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; + u64 val; + + /* Skip if no SIER support */ + if (!(flags & PPMU_HAS_SIER)) { + dsrc->val = 0; + return; + } + + sier = mfspr(SPRN_SIER); + val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT; + if (val == 1 || val == 2) { + 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); + dsrc->val |= (val == 1) ? P(OP, LOAD) : P(OP, STORE); + } +} + + 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..f711f337e358 100644
[PATCH v3 2/6] powerpc/perf: Export memory hierarchy info to user space
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 Cc: Paul Mackerras Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Anna-Maria Gleixner Cc: Daniel Axtens Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Wang Nan Cc: Alexei Starovoitov Cc: Stephane Eranian Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Madhavan Srinivasan --- 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_L