diff options
Diffstat (limited to 'arch/powerpc/perf/power8-pmu.c')
| -rw-r--r-- | arch/powerpc/perf/power8-pmu.c | 400 |
1 files changed, 400 insertions, 0 deletions
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c new file mode 100644 index 000000000..5282e8415 --- /dev/null +++ b/arch/powerpc/perf/power8-pmu.c @@ -0,0 +1,400 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Performance counter support for POWER8 processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * Copyright 2013 Michael Ellerman, IBM Corporation. + */ + +#define pr_fmt(fmt) "power8-pmu: " fmt + +#include "isa207-common.h" + +/* + * Some power8 event codes. + */ +#define EVENT(_name, _code) _name = _code, + +enum { +#include "power8-events-list.h" +}; + +#undef EVENT + +/* MMCRA IFM bits - POWER8 */ +#define POWER8_MMCRA_IFM1 0x0000000040000000UL +#define POWER8_MMCRA_IFM2 0x0000000080000000UL +#define POWER8_MMCRA_IFM3 0x00000000C0000000UL +#define POWER8_MMCRA_BHRB_MASK 0x00000000C0000000UL + +/* + * Raw event encoding for PowerISA v2.07 (Power8): + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * | | [ ] [ thresh_cmp ] [ thresh_ctl ] + * | | | | + * | | *- IFM (Linux) thresh start/stop OR FAB match -* + * | *- BHRB (Linux) + * *- EBB (Linux) + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [cache] [ pmc ] [unit ] c m [ pmcxsel ] + * | | | | | + * | | | | *- mark + * | | *- L1/L2/L3 cache_sel | + * | | | + * | *- sampling mode for marked events *- combine + * | + * *- thresh_sel + * + * Below uses IBM bit numbering. + * + * MMCR1[x:y] = unit (PMCxUNIT) + * MMCR1[x] = combine (PMCxCOMB) + * + * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 + * # PM_MRK_FAB_RSP_MATCH + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 + * # PM_MRK_FAB_RSP_MATCH_CYC + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else + * MMCRA[48:55] = thresh_ctl (THRESH START/END) + * + * if thresh_sel: + * MMCRA[45:47] = thresh_sel + * + * if thresh_cmp: + * MMCRA[22:24] = thresh_cmp[0:2] + * MMCRA[25:31] = thresh_cmp[3:9] + * + * if unit == 6 or unit == 7 + * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) + * else if unit == 8 or unit == 9: + * if cache_sel[0] == 0: # L3 bank + * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) + * else if cache_sel[0] == 1: + * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) + * else if cache_sel[1]: # L1 event + * MMCR1[16] = cache_sel[2] + * MMCR1[17] = cache_sel[3] + * + * if mark: + * MMCRA[63] = 1 (SAMPLE_ENABLE) + * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) + * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) + * + * if EBB and BHRB: + * MMCRA[32:33] = IFM + * + */ + +/* PowerISA v2.07 format attribute structure*/ +extern struct attribute_group isa207_pmu_format_group; + +/* Table of alternatives, sorted by column 0 */ +static const unsigned int event_alternatives[][MAX_ALT] = { + { PM_MRK_ST_CMPL, PM_MRK_ST_CMPL_ALT }, + { PM_BR_MRK_2PATH, PM_BR_MRK_2PATH_ALT }, + { PM_L3_CO_MEPF, PM_L3_CO_MEPF_ALT }, + { PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L2MISS_ALT }, + { PM_CMPLU_STALL_ALT, PM_CMPLU_STALL }, + { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_MRK_FILT_MATCH, PM_MRK_FILT_MATCH_ALT }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, +}; + +static int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int num_alt = 0; + + num_alt = isa207_get_alternatives(event, alt, + ARRAY_SIZE(event_alternatives), flags, + event_alternatives); + + return num_alt; +} + +GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_GCT_NOSLOT_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL); +GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); +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); + +CACHE_EVENT_ATTR(L1-dcache-prefetches, PM_L1_PREF); +CACHE_EVENT_ATTR(L1-dcache-store-misses, PM_ST_MISS_L1); +CACHE_EVENT_ATTR(L1-icache-load-misses, PM_L1_ICACHE_MISS); +CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1); +CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_WRITE); + +CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS); +CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3); +CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PREF_ALL); +CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS); +CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST); + +CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL); +CACHE_EVENT_ATTR(branch-loads, PM_BRU_FIN); +CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); +CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS); + +static struct attribute *power8_events_attr[] = { + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC), + GENERIC_EVENT_PTR(PM_CMPLU_STALL), + GENERIC_EVENT_PTR(PM_INST_CMPL), + GENERIC_EVENT_PTR(PM_BRU_FIN), + 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), + CACHE_EVENT_PTR(PM_L1_PREF), + CACHE_EVENT_PTR(PM_ST_MISS_L1), + CACHE_EVENT_PTR(PM_L1_ICACHE_MISS), + CACHE_EVENT_PTR(PM_INST_FROM_L1), + CACHE_EVENT_PTR(PM_IC_PREF_WRITE), + CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS), + CACHE_EVENT_PTR(PM_DATA_FROM_L3), + CACHE_EVENT_PTR(PM_L3_PREF_ALL), + CACHE_EVENT_PTR(PM_L2_ST_MISS), + CACHE_EVENT_PTR(PM_L2_ST), + + CACHE_EVENT_PTR(PM_BR_MPRED_CMPL), + CACHE_EVENT_PTR(PM_BRU_FIN), + + CACHE_EVENT_PTR(PM_DTLB_MISS), + CACHE_EVENT_PTR(PM_ITLB_MISS), + NULL +}; + +static struct attribute_group power8_pmu_events_group = { + .name = "events", + .attrs = power8_events_attr, +}; + +static const struct attribute_group *power8_pmu_attr_groups[] = { + &isa207_pmu_format_group, + &power8_pmu_events_group, + NULL, +}; + +static int power8_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_GCT_NOSLOT_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, + [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, +}; + +static u64 power8_bhrb_filter_map(u64 branch_sample_type) +{ + u64 pmu_bhrb_filter = 0; + + /* BHRB and regular PMU events share the same privilege state + * filter configuration. BHRB is always recorded along with a + * regular PMU event. As the privilege state filter is handled + * in the basic PMC configuration of the accompanying regular + * PMU event, we ignore any separate BHRB specific request. + */ + + /* No branch filter requested */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + return pmu_bhrb_filter; + + /* Invalid branch filter options - HW does not support */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) { + pmu_bhrb_filter |= POWER8_MMCRA_IFM1; + return pmu_bhrb_filter; + } + + /* Every thing else is unsupported */ + return -1; +} + +static void power8_config_bhrb(u64 pmu_bhrb_filter) +{ + pmu_bhrb_filter &= POWER8_MMCRA_BHRB_MASK; + + /* Enable BHRB filter in PMU */ + mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); +} + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static u64 power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, + [ C(RESULT_MISS) ] = PM_LD_MISS_L1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ST_MISS_L1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_PREF, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_INST_FROM_L1, + [ C(RESULT_MISS) ] = PM_L1_ICACHE_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3, + [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L2_ST, + [ C(RESULT_MISS) ] = PM_L2_ST_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_DTLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ITLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_BRU_FIN, + [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +#undef C + +static struct power_pmu power8_pmu = { + .name = "POWER8", + .n_counter = MAX_PMU_COUNTERS, + .max_alternatives = MAX_ALT + 1, + .add_fields = ISA207_ADD_FIELDS, + .test_adder = ISA207_TEST_ADDER, + .compute_mmcr = isa207_compute_mmcr, + .config_bhrb = power8_config_bhrb, + .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), + .generic_events = power8_generic_events, + .cache_events = &power8_cache_events, + .attr_groups = power8_pmu_attr_groups, + .bhrb_nr = 32, +}; + +int init_power8_pmu(void) +{ + int rc; + + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8")) + return -ENODEV; + + rc = register_power_pmu(&power8_pmu); + if (rc) + return rc; + + /* Tell userspace that EBB is supported */ + cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB; + + if (cpu_has_feature(CPU_FTR_PMAO_BUG)) + pr_info("PMAO restore workaround active.\n"); + + return 0; +} |