diff options
Diffstat (limited to 'drivers/perf/arm_spe_pmu.c')
-rw-r--r-- | drivers/perf/arm_spe_pmu.c | 160 |
1 files changed, 102 insertions, 58 deletions
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 00e3a637f7b6..b9ba4c4fe5a2 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -12,6 +12,7 @@ #define DRVNAME PMUNAME "_pmu" #define pr_fmt(fmt) DRVNAME ": " fmt +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/capability.h> @@ -84,6 +85,7 @@ struct arm_spe_pmu { #define SPE_PMU_FEAT_ARCH_INST (1UL << 3) #define SPE_PMU_FEAT_LDS (1UL << 4) #define SPE_PMU_FEAT_ERND (1UL << 5) +#define SPE_PMU_FEAT_INV_FILT_EVT (1UL << 6) #define SPE_PMU_FEAT_DEV_PROBED (1UL << 63) u64 features; @@ -201,6 +203,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = { #define ATTR_CFG_FLD_min_latency_LO 0 #define ATTR_CFG_FLD_min_latency_HI 11 +#define ATTR_CFG_FLD_inv_event_filter_CFG config3 /* PMSNEVFR_EL1 */ +#define ATTR_CFG_FLD_inv_event_filter_LO 0 +#define ATTR_CFG_FLD_inv_event_filter_HI 63 + /* Why does everything I do descend into this? */ #define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi @@ -231,6 +237,7 @@ GEN_PMU_FORMAT_ATTR(branch_filter); GEN_PMU_FORMAT_ATTR(load_filter); GEN_PMU_FORMAT_ATTR(store_filter); GEN_PMU_FORMAT_ATTR(event_filter); +GEN_PMU_FORMAT_ATTR(inv_event_filter); GEN_PMU_FORMAT_ATTR(min_latency); static struct attribute *arm_spe_pmu_formats_attr[] = { @@ -242,12 +249,27 @@ static struct attribute *arm_spe_pmu_formats_attr[] = { &format_attr_load_filter.attr, &format_attr_store_filter.attr, &format_attr_event_filter.attr, + &format_attr_inv_event_filter.attr, &format_attr_min_latency.attr, NULL, }; +static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj, + struct attribute *attr, + int unused) + { + struct device *dev = kobj_to_dev(kobj); + struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev); + + if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) + return 0; + + return attr->mode; +} + static const struct attribute_group arm_spe_pmu_format_group = { .name = "format", + .is_visible = arm_spe_pmu_format_attr_is_visible, .attrs = arm_spe_pmu_formats_attr, }; @@ -282,18 +304,18 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event) struct perf_event_attr *attr = &event->attr; u64 reg = 0; - reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, pa_enable) << SYS_PMSCR_EL1_PA_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, pct_enable) << SYS_PMSCR_EL1_PCT_SHIFT; + reg |= FIELD_PREP(PMSCR_EL1_TS, ATTR_CFG_GET_FLD(attr, ts_enable)); + reg |= FIELD_PREP(PMSCR_EL1_PA, ATTR_CFG_GET_FLD(attr, pa_enable)); + reg |= FIELD_PREP(PMSCR_EL1_PCT, ATTR_CFG_GET_FLD(attr, pct_enable)); if (!attr->exclude_user) - reg |= BIT(SYS_PMSCR_EL1_E0SPE_SHIFT); + reg |= PMSCR_EL1_E0SPE; if (!attr->exclude_kernel) - reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT); + reg |= PMSCR_EL1_E1SPE; if (get_spe_event_has_cx(event)) - reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT); + reg |= PMSCR_EL1_CX; return reg; } @@ -302,8 +324,7 @@ static void arm_spe_event_sanitise_period(struct perf_event *event) { struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu); u64 period = event->hw.sample_period; - u64 max_period = SYS_PMSIRR_EL1_INTERVAL_MASK - << SYS_PMSIRR_EL1_INTERVAL_SHIFT; + u64 max_period = PMSIRR_EL1_INTERVAL_MASK; if (period < spe_pmu->min_period) period = spe_pmu->min_period; @@ -322,7 +343,7 @@ static u64 arm_spe_event_to_pmsirr(struct perf_event *event) arm_spe_event_sanitise_period(event); - reg |= ATTR_CFG_GET_FLD(attr, jitter) << SYS_PMSIRR_EL1_RND_SHIFT; + reg |= FIELD_PREP(PMSIRR_EL1_RND, ATTR_CFG_GET_FLD(attr, jitter)); reg |= event->hw.sample_period; return reg; @@ -333,18 +354,21 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event) struct perf_event_attr *attr = &event->attr; u64 reg = 0; - reg |= ATTR_CFG_GET_FLD(attr, load_filter) << SYS_PMSFCR_EL1_LD_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, store_filter) << SYS_PMSFCR_EL1_ST_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, branch_filter) << SYS_PMSFCR_EL1_B_SHIFT; + reg |= FIELD_PREP(PMSFCR_EL1_LD, ATTR_CFG_GET_FLD(attr, load_filter)); + reg |= FIELD_PREP(PMSFCR_EL1_ST, ATTR_CFG_GET_FLD(attr, store_filter)); + reg |= FIELD_PREP(PMSFCR_EL1_B, ATTR_CFG_GET_FLD(attr, branch_filter)); if (reg) - reg |= BIT(SYS_PMSFCR_EL1_FT_SHIFT); + reg |= PMSFCR_EL1_FT; if (ATTR_CFG_GET_FLD(attr, event_filter)) - reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT); + reg |= PMSFCR_EL1_FE; + + if (ATTR_CFG_GET_FLD(attr, inv_event_filter)) + reg |= PMSFCR_EL1_FnE; if (ATTR_CFG_GET_FLD(attr, min_latency)) - reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT); + reg |= PMSFCR_EL1_FL; return reg; } @@ -355,11 +379,16 @@ static u64 arm_spe_event_to_pmsevfr(struct perf_event *event) return ATTR_CFG_GET_FLD(attr, event_filter); } +static u64 arm_spe_event_to_pmsnevfr(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + return ATTR_CFG_GET_FLD(attr, inv_event_filter); +} + static u64 arm_spe_event_to_pmslatfr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; - return ATTR_CFG_GET_FLD(attr, min_latency) - << SYS_PMSLATFR_EL1_MINLAT_SHIFT; + return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency)); } static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len) @@ -511,7 +540,7 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, limit = buf->snapshot ? arm_spe_pmu_next_snapshot_off(handle) : arm_spe_pmu_next_off(handle); if (limit) - limit |= BIT(SYS_PMBLIMITR_EL1_E_SHIFT); + limit |= PMBLIMITR_EL1_E; limit += (u64)buf->base; base = (u64)buf->base + PERF_IDX2OFF(handle->head, buf); @@ -570,28 +599,28 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle) /* Service required? */ pmbsr = read_sysreg_s(SYS_PMBSR_EL1); - if (!(pmbsr & BIT(SYS_PMBSR_EL1_S_SHIFT))) + if (!FIELD_GET(PMBSR_EL1_S, pmbsr)) return SPE_PMU_BUF_FAULT_ACT_SPURIOUS; /* * If we've lost data, disable profiling and also set the PARTIAL * flag to indicate that the last record is corrupted. */ - if (pmbsr & BIT(SYS_PMBSR_EL1_DL_SHIFT)) + if (FIELD_GET(PMBSR_EL1_DL, pmbsr)) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED | PERF_AUX_FLAG_PARTIAL); /* Report collisions to userspace so that it can up the period */ - if (pmbsr & BIT(SYS_PMBSR_EL1_COLL_SHIFT)) + if (FIELD_GET(PMBSR_EL1_COLL, pmbsr)) perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION); /* We only expect buffer management events */ - switch (pmbsr & (SYS_PMBSR_EL1_EC_MASK << SYS_PMBSR_EL1_EC_SHIFT)) { - case SYS_PMBSR_EL1_EC_BUF: + switch (FIELD_GET(PMBSR_EL1_EC, pmbsr)) { + case PMBSR_EL1_EC_BUF: /* Handled below */ break; - case SYS_PMBSR_EL1_EC_FAULT_S1: - case SYS_PMBSR_EL1_EC_FAULT_S2: + case PMBSR_EL1_EC_FAULT_S1: + case PMBSR_EL1_EC_FAULT_S2: err_str = "Unexpected buffer fault"; goto out_err; default: @@ -600,9 +629,8 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle) } /* Buffer management event */ - switch (pmbsr & - (SYS_PMBSR_EL1_BUF_BSC_MASK << SYS_PMBSR_EL1_BUF_BSC_SHIFT)) { - case SYS_PMBSR_EL1_BUF_BSC_FULL: + switch (FIELD_GET(PMBSR_EL1_BUF_BSC_MASK, pmbsr)) { + case PMBSR_EL1_BUF_BSC_FULL: ret = SPE_PMU_BUF_FAULT_ACT_OK; goto out_stop; default: @@ -677,11 +705,13 @@ static u64 arm_spe_pmsevfr_res0(u16 pmsver) { switch (pmsver) { case ID_AA64DFR0_EL1_PMSVer_IMP: - return SYS_PMSEVFR_EL1_RES0_8_2; + return PMSEVFR_EL1_RES0_IMP; case ID_AA64DFR0_EL1_PMSVer_V1P1: + return PMSEVFR_EL1_RES0_V1P1; + case ID_AA64DFR0_EL1_PMSVer_V1P2: /* Return the highest version we support in default */ default: - return SYS_PMSEVFR_EL1_RES0_8_3; + return PMSEVFR_EL1_RES0_V1P2; } } @@ -703,6 +733,9 @@ static int arm_spe_pmu_event_init(struct perf_event *event) if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) return -EOPNOTSUPP; + if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) + return -EOPNOTSUPP; + if (attr->exclude_idle) return -EOPNOTSUPP; @@ -717,23 +750,26 @@ static int arm_spe_pmu_event_init(struct perf_event *event) return -EINVAL; reg = arm_spe_event_to_pmsfcr(event); - if ((reg & BIT(SYS_PMSFCR_EL1_FE_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FE, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT)) return -EOPNOTSUPP; - if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FnE, reg)) && + !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) + return -EOPNOTSUPP; + + if ((FIELD_GET(PMSFCR_EL1_FT, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP)) return -EOPNOTSUPP; - if ((reg & BIT(SYS_PMSFCR_EL1_FL_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FL, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT)) return -EOPNOTSUPP; set_spe_event_has_cx(event); reg = arm_spe_event_to_pmscr(event); if (!perfmon_capable() && - (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) | - BIT(SYS_PMSCR_EL1_PCT_SHIFT)))) + (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT))) return -EACCES; return 0; @@ -757,6 +793,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags) reg = arm_spe_event_to_pmsevfr(event); write_sysreg_s(reg, SYS_PMSEVFR_EL1); + if (spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT) { + reg = arm_spe_event_to_pmsnevfr(event); + write_sysreg_s(reg, SYS_PMSNEVFR_EL1); + } + reg = arm_spe_event_to_pmslatfr(event); write_sysreg_s(reg, SYS_PMSLATFR_EL1); @@ -971,14 +1012,14 @@ static void __arm_spe_pmu_dev_probe(void *info) /* Read PMBIDR first to determine whether or not we have access */ reg = read_sysreg_s(SYS_PMBIDR_EL1); - if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) { + if (FIELD_GET(PMBIDR_EL1_P, reg)) { dev_err(dev, "profiling buffer owned by higher exception level\n"); return; } /* Minimum alignment. If it's out-of-range, then fail the probe */ - fld = reg >> SYS_PMBIDR_EL1_ALIGN_SHIFT & SYS_PMBIDR_EL1_ALIGN_MASK; + fld = FIELD_GET(PMBIDR_EL1_ALIGN, reg); spe_pmu->align = 1 << fld; if (spe_pmu->align > SZ_2K) { dev_err(dev, "unsupported PMBIDR.Align [%d] on CPU %d\n", @@ -988,58 +1029,61 @@ static void __arm_spe_pmu_dev_probe(void *info) /* It's now safe to read PMSIDR and figure out what we've got */ reg = read_sysreg_s(SYS_PMSIDR_EL1); - if (reg & BIT(SYS_PMSIDR_EL1_FE_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FE, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_EVT; - if (reg & BIT(SYS_PMSIDR_EL1_FT_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FnE, reg)) + spe_pmu->features |= SPE_PMU_FEAT_INV_FILT_EVT; + + if (FIELD_GET(PMSIDR_EL1_FT, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_TYP; - if (reg & BIT(SYS_PMSIDR_EL1_FL_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FL, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_LAT; - if (reg & BIT(SYS_PMSIDR_EL1_ARCHINST_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_ARCHINST, reg)) spe_pmu->features |= SPE_PMU_FEAT_ARCH_INST; - if (reg & BIT(SYS_PMSIDR_EL1_LDS_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_LDS, reg)) spe_pmu->features |= SPE_PMU_FEAT_LDS; - if (reg & BIT(SYS_PMSIDR_EL1_ERND_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_ERND, reg)) spe_pmu->features |= SPE_PMU_FEAT_ERND; /* This field has a spaced out encoding, so just use a look-up */ - fld = reg >> SYS_PMSIDR_EL1_INTERVAL_SHIFT & SYS_PMSIDR_EL1_INTERVAL_MASK; + fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg); switch (fld) { - case 0: + case PMSIDR_EL1_INTERVAL_256: spe_pmu->min_period = 256; break; - case 2: + case PMSIDR_EL1_INTERVAL_512: spe_pmu->min_period = 512; break; - case 3: + case PMSIDR_EL1_INTERVAL_768: spe_pmu->min_period = 768; break; - case 4: + case PMSIDR_EL1_INTERVAL_1024: spe_pmu->min_period = 1024; break; - case 5: + case PMSIDR_EL1_INTERVAL_1536: spe_pmu->min_period = 1536; break; - case 6: + case PMSIDR_EL1_INTERVAL_2048: spe_pmu->min_period = 2048; break; - case 7: + case PMSIDR_EL1_INTERVAL_3072: spe_pmu->min_period = 3072; break; default: dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n", fld); fallthrough; - case 8: + case PMSIDR_EL1_INTERVAL_4096: spe_pmu->min_period = 4096; } /* Maximum record size. If it's out-of-range, then fail the probe */ - fld = reg >> SYS_PMSIDR_EL1_MAXSIZE_SHIFT & SYS_PMSIDR_EL1_MAXSIZE_MASK; + fld = FIELD_GET(PMSIDR_EL1_MAXSIZE, reg); spe_pmu->max_record_sz = 1 << fld; if (spe_pmu->max_record_sz > SZ_2K || spe_pmu->max_record_sz < 16) { dev_err(dev, "unsupported PMSIDR_EL1.MaxSize [%d] on CPU %d\n", @@ -1047,22 +1091,22 @@ static void __arm_spe_pmu_dev_probe(void *info) return; } - fld = reg >> SYS_PMSIDR_EL1_COUNTSIZE_SHIFT & SYS_PMSIDR_EL1_COUNTSIZE_MASK; + fld = FIELD_GET(PMSIDR_EL1_COUNTSIZE, reg); switch (fld) { default: dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n", fld); fallthrough; - case 2: + case PMSIDR_EL1_COUNTSIZE_12_BIT_SAT: spe_pmu->counter_sz = 12; break; - case 3: + case PMSIDR_EL1_COUNTSIZE_16_BIT_SAT: spe_pmu->counter_sz = 16; } dev_info(dev, - "probed for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n", - cpumask_pr_args(&spe_pmu->supported_cpus), + "probed SPEv1.%d for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n", + spe_pmu->pmsver - 1, cpumask_pr_args(&spe_pmu->supported_cpus), spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features); spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED; |