diff options
Diffstat (limited to 'drivers/perf')
| -rw-r--r-- | drivers/perf/arm-ni.c | 97 | ||||
| -rw-r--r-- | drivers/perf/arm_cspmu/arm_cspmu.c | 52 | ||||
| -rw-r--r-- | drivers/perf/arm_cspmu/arm_cspmu.h | 39 | ||||
| -rw-r--r-- | drivers/perf/arm_cspmu/nvidia_cspmu.c | 194 | ||||
| -rw-r--r-- | drivers/perf/arm_pmu.c | 55 | ||||
| -rw-r--r-- | drivers/perf/arm_pmu_acpi.c | 2 | ||||
| -rw-r--r-- | drivers/perf/arm_pmu_platform.c | 20 | ||||
| -rw-r--r-- | drivers/perf/arm_pmuv3.c | 26 | ||||
| -rw-r--r-- | drivers/perf/arm_spe_pmu.c | 50 | ||||
| -rw-r--r-- | drivers/perf/fsl_imx8_ddr_perf.c | 93 | ||||
| -rw-r--r-- | drivers/perf/riscv_pmu_sbi.c | 2 |
11 files changed, 491 insertions, 139 deletions
diff --git a/drivers/perf/arm-ni.c b/drivers/perf/arm-ni.c index 1615a0564031..66858c65215d 100644 --- a/drivers/perf/arm-ni.c +++ b/drivers/perf/arm-ni.c @@ -21,6 +21,11 @@ #define NI_CHILD_NODE_INFO 0x004 #define NI_CHILD_PTR(n) (0x008 + (n) * 4) +#define NI_NUM_SUB_FEATURES 0x100 +#define NI_SUB_FEATURE_TYPE(n) (0x108 + (n) * 8) +#define NI_SUB_FEATURE_PTR(n) (0x10c + (n) * 8) + +#define NI_SUB_FEATURE_TYPE_FCU 0x2 #define NI700_PMUSELA 0x00c @@ -33,9 +38,10 @@ #define NI_PIDR2_VERSION GENMASK(7, 4) /* PMU node */ -#define NI_PMEVCNTR(n) (0x008 + (n) * 8) -#define NI_PMCCNTR_L 0x0f8 -#define NI_PMCCNTR_U 0x0fc +#define NI700_PMEVCNTR(n) (0x008 + (n) * 8) +#define NI700_PMCCNTR_L 0x0f8 +#define NI_PMEVCNTR(n) (0x200 + (n) * 8) +#define NI_PMCCNTR_L 0x2f8 #define NI_PMEVTYPER(n) (0x400 + (n) * 4) #define NI_PMEVTYPER_NODE_TYPE GENMASK(12, 9) #define NI_PMEVTYPER_NODE_ID GENMASK(8, 0) @@ -66,6 +72,8 @@ enum ni_part { PART_NI_700 = 0x43b, PART_NI_710AE = 0x43d, + PART_NOC_S3 = 0x43f, + PART_SI_L1 = 0x455, }; enum ni_node_type { @@ -79,6 +87,10 @@ enum ni_node_type { NI_HSNI, NI_HMNI, NI_PMNI, + NI_TSNI, + NI_TMNI, + NI_CMNI = 0x0e, + NI_MCN = 0x63, }; struct arm_ni_node { @@ -179,6 +191,9 @@ static struct attribute *arm_ni_event_attrs[] = { NI_EVENT_ATTR(hsni, NI_HSNI), NI_EVENT_ATTR(hmni, NI_HMNI), NI_EVENT_ATTR(pmni, NI_PMNI), + NI_EVENT_ATTR(tsni, NI_TSNI), + NI_EVENT_ATTR(tmni, NI_TMNI), + NI_EVENT_ATTR(cmni, NI_CMNI), NULL }; @@ -308,9 +323,15 @@ static int arm_ni_validate_group(struct perf_event *event) return 0; } +static bool arm_ni_is_7xx(const struct arm_ni *ni) +{ + return ni->part == PART_NI_700 || ni->part == PART_NI_710AE; +} + static int arm_ni_event_init(struct perf_event *event) { struct arm_ni_cd *cd = pmu_to_cd(event->pmu); + struct arm_ni *ni; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -318,7 +339,10 @@ static int arm_ni_event_init(struct perf_event *event) if (is_sampling_event(event)) return -EINVAL; - event->cpu = cd_to_ni(cd)->cpu; + ni = cd_to_ni(cd); + event->cpu = ni->cpu; + event->hw.flags = arm_ni_is_7xx(ni); + if (NI_EVENT_TYPE(event) == NI_PMU) return arm_ni_validate_group(event); @@ -332,16 +356,16 @@ static int arm_ni_event_init(struct perf_event *event) return -EINVAL; } -static u64 arm_ni_read_ccnt(struct arm_ni_cd *cd) +static u64 arm_ni_read_ccnt(void __iomem *pmccntr) { u64 l, u_old, u_new; int retries = 3; /* 1st time unlucky, 2nd improbable, 3rd just broken */ - u_new = readl_relaxed(cd->pmu_base + NI_PMCCNTR_U); + u_new = readl_relaxed(pmccntr + 4); do { u_old = u_new; - l = readl_relaxed(cd->pmu_base + NI_PMCCNTR_L); - u_new = readl_relaxed(cd->pmu_base + NI_PMCCNTR_U); + l = readl_relaxed(pmccntr); + u_new = readl_relaxed(pmccntr + 4); } while (u_new != u_old && --retries); WARN_ON(!retries); @@ -350,7 +374,6 @@ static u64 arm_ni_read_ccnt(struct arm_ni_cd *cd) static void arm_ni_event_read(struct perf_event *event) { - struct arm_ni_cd *cd = pmu_to_cd(event->pmu); struct hw_perf_event *hw = &event->hw; u64 count, prev; bool ccnt = hw->idx == NI_CCNT_IDX; @@ -358,9 +381,9 @@ static void arm_ni_event_read(struct perf_event *event) do { prev = local64_read(&hw->prev_count); if (ccnt) - count = arm_ni_read_ccnt(cd); + count = arm_ni_read_ccnt((void __iomem *)event->hw.event_base); else - count = readl_relaxed(cd->pmu_base + NI_PMEVCNTR(hw->idx)); + count = readl_relaxed((void __iomem *)event->hw.event_base); } while (local64_cmpxchg(&hw->prev_count, prev, count) != prev); count -= prev; @@ -385,16 +408,16 @@ static void arm_ni_event_stop(struct perf_event *event, int flags) arm_ni_event_read(event); } -static void arm_ni_init_ccnt(struct arm_ni_cd *cd) +static void arm_ni_init_ccnt(struct hw_perf_event *hw) { - local64_set(&cd->ccnt->hw.prev_count, S64_MIN); - lo_hi_writeq_relaxed(S64_MIN, cd->pmu_base + NI_PMCCNTR_L); + local64_set(&hw->prev_count, S64_MIN); + lo_hi_writeq_relaxed(S64_MIN, (void __iomem *)hw->event_base); } -static void arm_ni_init_evcnt(struct arm_ni_cd *cd, int idx) +static void arm_ni_init_evcnt(struct hw_perf_event *hw) { - local64_set(&cd->evcnt[idx]->hw.prev_count, S32_MIN); - writel_relaxed(S32_MIN, cd->pmu_base + NI_PMEVCNTR(idx)); + local64_set(&hw->prev_count, S32_MIN); + writel_relaxed(S32_MIN, (void __iomem *)hw->event_base); } static int arm_ni_event_add(struct perf_event *event, int flags) @@ -409,8 +432,10 @@ static int arm_ni_event_add(struct perf_event *event, int flags) if (cd->ccnt) return -ENOSPC; hw->idx = NI_CCNT_IDX; + hw->event_base = (unsigned long)cd->pmu_base + + (hw->flags ? NI700_PMCCNTR_L : NI_PMCCNTR_L); cd->ccnt = event; - arm_ni_init_ccnt(cd); + arm_ni_init_ccnt(hw); } else { hw->idx = 0; while (cd->evcnt[hw->idx]) { @@ -420,7 +445,9 @@ static int arm_ni_event_add(struct perf_event *event, int flags) cd->evcnt[hw->idx] = event; unit = (void *)hw->config_base; unit->event[hw->idx] = NI_EVENT_EVENTID(event); - arm_ni_init_evcnt(cd, hw->idx); + hw->event_base = (unsigned long)cd->pmu_base + + (hw->flags ? NI700_PMEVCNTR(hw->idx) : NI_PMEVCNTR(hw->idx)); + arm_ni_init_evcnt(hw); lo_hi_writeq_relaxed(le64_to_cpu(unit->pmusel), unit->pmusela); reg = FIELD_PREP(NI_PMEVTYPER_NODE_TYPE, type) | @@ -457,7 +484,7 @@ static irqreturn_t arm_ni_handle_irq(int irq, void *dev_id) ret = IRQ_HANDLED; if (!(WARN_ON(!cd->ccnt))) { arm_ni_event_read(cd->ccnt); - arm_ni_init_ccnt(cd); + arm_ni_init_ccnt(&cd->ccnt->hw); } } for (int i = 0; i < NI_NUM_COUNTERS; i++) { @@ -466,7 +493,7 @@ static irqreturn_t arm_ni_handle_irq(int irq, void *dev_id) ret = IRQ_HANDLED; if (!(WARN_ON(!cd->evcnt[i]))) { arm_ni_event_read(cd->evcnt[i]); - arm_ni_init_evcnt(cd, i); + arm_ni_init_evcnt(&cd->evcnt[i]->hw); } } writel_relaxed(reg, cd->pmu_base + NI_PMOVSCLR); @@ -476,6 +503,25 @@ static irqreturn_t arm_ni_handle_irq(int irq, void *dev_id) } } +static void __iomem *arm_ni_get_pmusel(struct arm_ni *ni, void __iomem *unit_base) +{ + u32 type, ptr, num; + + if (arm_ni_is_7xx(ni)) + return unit_base + NI700_PMUSELA; + + num = readl_relaxed(unit_base + NI_NUM_SUB_FEATURES); + for (int i = 0; i < num; i++) { + type = readl_relaxed(unit_base + NI_SUB_FEATURE_TYPE(i)); + if (type != NI_SUB_FEATURE_TYPE_FCU) + continue; + ptr = readl_relaxed(unit_base + NI_SUB_FEATURE_PTR(i)); + return ni->base + ptr; + } + /* Should be impossible */ + return NULL; +} + static int arm_ni_init_cd(struct arm_ni *ni, struct arm_ni_node *node, u64 res_start) { struct arm_ni_cd *cd = ni->cds + node->id; @@ -512,13 +558,18 @@ static int arm_ni_init_cd(struct arm_ni *ni, struct arm_ni_node *node, u64 res_s case NI_HSNI: case NI_HMNI: case NI_PMNI: - unit->pmusela = unit_base + NI700_PMUSELA; + case NI_TSNI: + case NI_TMNI: + case NI_CMNI: + unit->pmusela = arm_ni_get_pmusel(ni, unit_base); writel_relaxed(1, unit->pmusela); if (readl_relaxed(unit->pmusela) != 1) dev_info(ni->dev, "No access to node 0x%04x%04x\n", unit->id, unit->type); else unit->ns = true; break; + case NI_MCN: + break; default: /* * e.g. FMU - thankfully bits 3:2 of FMU_ERR_FR0 are RES0 so @@ -649,6 +700,8 @@ static int arm_ni_probe(struct platform_device *pdev) switch (part) { case PART_NI_700: case PART_NI_710AE: + case PART_NOC_S3: + case PART_SI_L1: break; default: dev_WARN(&pdev->dev, "Unknown part number: 0x%03x, this may go badly\n", part); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index efa9b229e701..34430b68f602 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -322,14 +322,14 @@ static struct arm_cspmu_impl_match impl_match[] = { { .module_name = "nvidia_cspmu", .pmiidr_val = ARM_CSPMU_IMPL_ID_NVIDIA, - .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, + .pmiidr_mask = PMIIDR_IMPLEMENTER, .module = NULL, .impl_init_ops = NULL, }, { .module_name = "ampere_cspmu", .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE, - .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, + .pmiidr_mask = PMIIDR_IMPLEMENTER, .module = NULL, .impl_init_ops = NULL, }, @@ -351,6 +351,44 @@ static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr) return NULL; } +static u32 arm_cspmu_get_pmiidr(struct arm_cspmu *cspmu) +{ + u32 pmiidr, pmpidr; + + pmiidr = readl(cspmu->base0 + PMIIDR); + + if (pmiidr != 0) + return pmiidr; + + /* Construct PMIIDR value from PMPIDRs. */ + + pmpidr = readl(cspmu->base0 + PMPIDR0); + pmiidr |= FIELD_PREP(PMIIDR_PRODUCTID_PART_0, + FIELD_GET(PMPIDR0_PART_0, pmpidr)); + + pmpidr = readl(cspmu->base0 + PMPIDR1); + pmiidr |= FIELD_PREP(PMIIDR_PRODUCTID_PART_1, + FIELD_GET(PMPIDR1_PART_1, pmpidr)); + pmiidr |= FIELD_PREP(PMIIDR_IMPLEMENTER_DES_0, + FIELD_GET(PMPIDR1_DES_0, pmpidr)); + + pmpidr = readl(cspmu->base0 + PMPIDR2); + pmiidr |= FIELD_PREP(PMIIDR_VARIANT, + FIELD_GET(PMPIDR2_REVISION, pmpidr)); + pmiidr |= FIELD_PREP(PMIIDR_IMPLEMENTER_DES_1, + FIELD_GET(PMPIDR2_DES_1, pmpidr)); + + pmpidr = readl(cspmu->base0 + PMPIDR3); + pmiidr |= FIELD_PREP(PMIIDR_REVISION, + FIELD_GET(PMPIDR3_REVAND, pmpidr)); + + pmpidr = readl(cspmu->base0 + PMPIDR4); + pmiidr |= FIELD_PREP(PMIIDR_IMPLEMENTER_DES_2, + FIELD_GET(PMPIDR4_DES_2, pmpidr)); + + return pmiidr; +} + #define DEFAULT_IMPL_OP(name) .name = arm_cspmu_##name static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) @@ -361,7 +399,7 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) /* Start with a default PMU implementation */ cspmu->impl.module = THIS_MODULE; - cspmu->impl.pmiidr = readl(cspmu->base0 + PMIIDR); + cspmu->impl.pmiidr = arm_cspmu_get_pmiidr(cspmu); cspmu->impl.ops = (struct arm_cspmu_impl_ops) { DEFAULT_IMPL_OP(get_event_attrs), DEFAULT_IMPL_OP(get_format_attrs), @@ -815,6 +853,10 @@ static void arm_cspmu_stop(struct perf_event *event, int pmu_flags) return; arm_cspmu_disable_counter(cspmu, hwc->idx); + + if (cspmu->impl.ops.reset_ev_filter) + cspmu->impl.ops.reset_ev_filter(cspmu, event); + arm_cspmu_event_update(event); hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; @@ -1365,8 +1407,10 @@ void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match) /* Unbind the driver from all matching backend devices. */ while ((dev = driver_find_device(&arm_cspmu_driver.driver, NULL, - match, arm_cspmu_match_device))) + match, arm_cspmu_match_device))) { device_release_driver(dev); + put_device(dev); + } mutex_lock(&arm_cspmu_lock); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h index 19684b76bd96..cd65a58dbd88 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.h +++ b/drivers/perf/arm_cspmu/arm_cspmu.h @@ -86,6 +86,11 @@ #define PMCFGR 0xE00 #define PMCR 0xE04 #define PMIIDR 0xE08 +#define PMPIDR0 0xFE0 +#define PMPIDR1 0xFE4 +#define PMPIDR2 0xFE8 +#define PMPIDR3 0xFEC +#define PMPIDR4 0xFD0 /* PMCFGR register field */ #define PMCFGR_NCG GENMASK(31, 28) @@ -115,8 +120,34 @@ #define PMCR_E BIT(0) /* PMIIDR register field */ -#define ARM_CSPMU_PMIIDR_IMPLEMENTER GENMASK(11, 0) -#define ARM_CSPMU_PMIIDR_PRODUCTID GENMASK(31, 20) +#define PMIIDR_IMPLEMENTER GENMASK(11, 0) +#define PMIIDR_IMPLEMENTER_DES_0 GENMASK(3, 0) +#define PMIIDR_IMPLEMENTER_DES_1 GENMASK(6, 4) +#define PMIIDR_IMPLEMENTER_DES_2 GENMASK(11, 8) +#define PMIIDR_REVISION GENMASK(15, 12) +#define PMIIDR_VARIANT GENMASK(19, 16) +#define PMIIDR_PRODUCTID GENMASK(31, 20) +#define PMIIDR_PRODUCTID_PART_0 GENMASK(27, 20) +#define PMIIDR_PRODUCTID_PART_1 GENMASK(31, 28) + +/* PMPIDR0 register field */ +#define PMPIDR0_PART_0 GENMASK(7, 0) + +/* PMPIDR1 register field */ +#define PMPIDR1_DES_0 GENMASK(7, 4) +#define PMPIDR1_PART_1 GENMASK(3, 0) + +/* PMPIDR2 register field */ +#define PMPIDR2_REVISION GENMASK(7, 4) +#define PMPIDR2_DES_1 GENMASK(2, 0) + +/* PMPIDR3 register field */ +#define PMPIDR3_REVAND GENMASK(7, 4) +#define PMPIDR3_CMOD GENMASK(3, 0) + +/* PMPIDR4 register field */ +#define PMPIDR4_SIZE GENMASK(7, 4) +#define PMPIDR4_DES_2 GENMASK(3, 0) /* JEDEC-assigned JEP106 identification code */ #define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B @@ -152,11 +183,13 @@ struct arm_cspmu_impl_ops { bool (*is_cycle_counter_event)(const struct perf_event *event); /* Decode event type/id from configs */ u32 (*event_type)(const struct perf_event *event); - /* Set event filters */ + /* Set/reset event filters */ void (*set_cc_filter)(struct arm_cspmu *cspmu, const struct perf_event *event); void (*set_ev_filter)(struct arm_cspmu *cspmu, const struct perf_event *event); + void (*reset_ev_filter)(struct arm_cspmu *cspmu, + const struct perf_event *event); /* Implementation specific event validation */ int (*validate_event)(struct arm_cspmu *cspmu, struct perf_event *event); diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c index dc6d4e3e2a1b..e06a06d3407b 100644 --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c @@ -23,7 +23,7 @@ #define NV_GENERIC_FILTER_ID_MASK GENMASK_ULL(31, 0) -#define NV_PRODID_MASK GENMASK(31, 0) +#define NV_PRODID_MASK (PMIIDR_PRODUCTID | PMIIDR_VARIANT | PMIIDR_REVISION) #define NV_FORMAT_NAME_GENERIC 0 @@ -40,10 +40,21 @@ struct nv_cspmu_ctx { const char *name; - u32 filter_mask; - u32 filter_default_val; + struct attribute **event_attr; struct attribute **format_attr; + + u32 filter_mask; + u32 filter_default_val; + u32 filter2_mask; + u32 filter2_default_val; + + u32 (*get_filter)(const struct perf_event *event); + u32 (*get_filter2)(const struct perf_event *event); + + void *data; + + int (*init_data)(struct arm_cspmu *cspmu); }; static struct attribute *scf_pmu_event_attrs[] = { @@ -144,6 +155,7 @@ static struct attribute *cnvlink_pmu_format_attrs[] = { static struct attribute *generic_pmu_format_attrs[] = { ARM_CSPMU_FORMAT_EVENT_ATTR, ARM_CSPMU_FORMAT_FILTER_ATTR, + ARM_CSPMU_FORMAT_FILTER2_ATTR, NULL, }; @@ -184,13 +196,36 @@ static u32 nv_cspmu_event_filter(const struct perf_event *event) return filter_val; } +static u32 nv_cspmu_event_filter2(const struct perf_event *event) +{ + const struct nv_cspmu_ctx *ctx = + to_nv_cspmu_ctx(to_arm_cspmu(event->pmu)); + + const u32 filter_val = event->attr.config2 & ctx->filter2_mask; + + if (filter_val == 0) + return ctx->filter2_default_val; + + return filter_val; +} + static void nv_cspmu_set_ev_filter(struct arm_cspmu *cspmu, const struct perf_event *event) { - u32 filter = nv_cspmu_event_filter(event); - u32 offset = PMEVFILTR + (4 * event->hw.idx); + u32 filter, offset; + const struct nv_cspmu_ctx *ctx = + to_nv_cspmu_ctx(to_arm_cspmu(event->pmu)); + offset = 4 * event->hw.idx; + + if (ctx->get_filter) { + filter = ctx->get_filter(event); + writel(filter, cspmu->base0 + PMEVFILTR + offset); + } - writel(filter, cspmu->base0 + offset); + if (ctx->get_filter2) { + filter = ctx->get_filter2(event); + writel(filter, cspmu->base0 + PMEVFILT2R + offset); + } } static void nv_cspmu_set_cc_filter(struct arm_cspmu *cspmu, @@ -210,74 +245,120 @@ enum nv_cspmu_name_fmt { struct nv_cspmu_match { u32 prodid; u32 prodid_mask; - u64 filter_mask; - u32 filter_default_val; const char *name_pattern; enum nv_cspmu_name_fmt name_fmt; - struct attribute **event_attr; - struct attribute **format_attr; + struct nv_cspmu_ctx template_ctx; + struct arm_cspmu_impl_ops ops; }; static const struct nv_cspmu_match nv_cspmu_match[] = { { - .prodid = 0x103, + .prodid = 0x10300000, .prodid_mask = NV_PRODID_MASK, - .filter_mask = NV_PCIE_FILTER_ID_MASK, - .filter_default_val = NV_PCIE_FILTER_ID_MASK, .name_pattern = "nvidia_pcie_pmu_%u", .name_fmt = NAME_FMT_SOCKET, - .event_attr = mcf_pmu_event_attrs, - .format_attr = pcie_pmu_format_attrs + .template_ctx = { + .event_attr = mcf_pmu_event_attrs, + .format_attr = pcie_pmu_format_attrs, + .filter_mask = NV_PCIE_FILTER_ID_MASK, + .filter_default_val = NV_PCIE_FILTER_ID_MASK, + .filter2_mask = 0x0, + .filter2_default_val = 0x0, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = NULL, + .data = NULL, + .init_data = NULL + }, }, { - .prodid = 0x104, + .prodid = 0x10400000, .prodid_mask = NV_PRODID_MASK, - .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, - .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, .name_pattern = "nvidia_nvlink_c2c1_pmu_%u", .name_fmt = NAME_FMT_SOCKET, - .event_attr = mcf_pmu_event_attrs, - .format_attr = nvlink_c2c_pmu_format_attrs + .template_ctx = { + .event_attr = mcf_pmu_event_attrs, + .format_attr = nvlink_c2c_pmu_format_attrs, + .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, + .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, + .filter2_mask = 0x0, + .filter2_default_val = 0x0, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = NULL, + .data = NULL, + .init_data = NULL + }, }, { - .prodid = 0x105, + .prodid = 0x10500000, .prodid_mask = NV_PRODID_MASK, - .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, - .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, .name_pattern = "nvidia_nvlink_c2c0_pmu_%u", .name_fmt = NAME_FMT_SOCKET, - .event_attr = mcf_pmu_event_attrs, - .format_attr = nvlink_c2c_pmu_format_attrs + .template_ctx = { + .event_attr = mcf_pmu_event_attrs, + .format_attr = nvlink_c2c_pmu_format_attrs, + .filter_mask = NV_NVL_C2C_FILTER_ID_MASK, + .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK, + .filter2_mask = 0x0, + .filter2_default_val = 0x0, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = NULL, + .data = NULL, + .init_data = NULL + }, }, { - .prodid = 0x106, + .prodid = 0x10600000, .prodid_mask = NV_PRODID_MASK, - .filter_mask = NV_CNVL_FILTER_ID_MASK, - .filter_default_val = NV_CNVL_FILTER_ID_MASK, .name_pattern = "nvidia_cnvlink_pmu_%u", .name_fmt = NAME_FMT_SOCKET, - .event_attr = mcf_pmu_event_attrs, - .format_attr = cnvlink_pmu_format_attrs + .template_ctx = { + .event_attr = mcf_pmu_event_attrs, + .format_attr = cnvlink_pmu_format_attrs, + .filter_mask = NV_CNVL_FILTER_ID_MASK, + .filter_default_val = NV_CNVL_FILTER_ID_MASK, + .filter2_mask = 0x0, + .filter2_default_val = 0x0, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = NULL, + .data = NULL, + .init_data = NULL + }, }, { - .prodid = 0x2CF, + .prodid = 0x2CF00000, .prodid_mask = NV_PRODID_MASK, - .filter_mask = 0x0, - .filter_default_val = 0x0, .name_pattern = "nvidia_scf_pmu_%u", .name_fmt = NAME_FMT_SOCKET, - .event_attr = scf_pmu_event_attrs, - .format_attr = scf_pmu_format_attrs + .template_ctx = { + .event_attr = scf_pmu_event_attrs, + .format_attr = scf_pmu_format_attrs, + .filter_mask = 0x0, + .filter_default_val = 0x0, + .filter2_mask = 0x0, + .filter2_default_val = 0x0, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = NULL, + .data = NULL, + .init_data = NULL + }, }, { .prodid = 0, .prodid_mask = 0, - .filter_mask = NV_GENERIC_FILTER_ID_MASK, - .filter_default_val = NV_GENERIC_FILTER_ID_MASK, .name_pattern = "nvidia_uncore_pmu_%u", .name_fmt = NAME_FMT_GENERIC, - .event_attr = generic_pmu_event_attrs, - .format_attr = generic_pmu_format_attrs + .template_ctx = { + .event_attr = generic_pmu_event_attrs, + .format_attr = generic_pmu_format_attrs, + .filter_mask = NV_GENERIC_FILTER_ID_MASK, + .filter_default_val = NV_GENERIC_FILTER_ID_MASK, + .filter2_mask = NV_GENERIC_FILTER_ID_MASK, + .filter2_default_val = NV_GENERIC_FILTER_ID_MASK, + .get_filter = nv_cspmu_event_filter, + .get_filter2 = nv_cspmu_event_filter2, + .data = NULL, + .init_data = NULL + }, }, }; @@ -310,9 +391,16 @@ static char *nv_cspmu_format_name(const struct arm_cspmu *cspmu, return name; } +#define SET_OP(name, impl, match, default_op) \ + do { \ + if (match->ops.name) \ + impl->name = match->ops.name; \ + else if (default_op != NULL) \ + impl->name = default_op; \ + } while (false) + static int nv_cspmu_init_ops(struct arm_cspmu *cspmu) { - u32 prodid; struct nv_cspmu_ctx *ctx; struct device *dev = cspmu->dev; struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; @@ -322,30 +410,30 @@ static int nv_cspmu_init_ops(struct arm_cspmu *cspmu) if (!ctx) return -ENOMEM; - prodid = FIELD_GET(ARM_CSPMU_PMIIDR_PRODUCTID, cspmu->impl.pmiidr); - /* Find matching PMU. */ for (; match->prodid; match++) { const u32 prodid_mask = match->prodid_mask; - if ((match->prodid & prodid_mask) == (prodid & prodid_mask)) + if ((match->prodid & prodid_mask) == + (cspmu->impl.pmiidr & prodid_mask)) break; } - ctx->name = nv_cspmu_format_name(cspmu, match); - ctx->filter_mask = match->filter_mask; - ctx->filter_default_val = match->filter_default_val; - ctx->event_attr = match->event_attr; - ctx->format_attr = match->format_attr; + /* Initialize the context with the matched template. */ + memcpy(ctx, &match->template_ctx, sizeof(struct nv_cspmu_ctx)); + ctx->name = nv_cspmu_format_name(cspmu, match); cspmu->impl.ctx = ctx; /* NVIDIA specific callbacks. */ - impl_ops->set_cc_filter = nv_cspmu_set_cc_filter; - impl_ops->set_ev_filter = nv_cspmu_set_ev_filter; - impl_ops->get_event_attrs = nv_cspmu_get_event_attrs; - impl_ops->get_format_attrs = nv_cspmu_get_format_attrs; - impl_ops->get_name = nv_cspmu_get_name; + SET_OP(set_cc_filter, impl_ops, match, nv_cspmu_set_cc_filter); + SET_OP(set_ev_filter, impl_ops, match, nv_cspmu_set_ev_filter); + SET_OP(get_event_attrs, impl_ops, match, nv_cspmu_get_event_attrs); + SET_OP(get_format_attrs, impl_ops, match, nv_cspmu_get_format_attrs); + SET_OP(get_name, impl_ops, match, nv_cspmu_get_name); + + if (ctx->init_data) + return ctx->init_data(cspmu); return 0; } diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 5c310e803dd7..973a027d9063 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -26,7 +26,8 @@ #include <asm/irq_regs.h> -static int armpmu_count_irq_users(const int irq); +static int armpmu_count_irq_users(const struct cpumask *affinity, + const int irq); struct pmu_irq_ops { void (*enable_pmuirq)(unsigned int irq); @@ -64,7 +65,9 @@ static void armpmu_enable_percpu_pmuirq(unsigned int irq) static void armpmu_free_percpu_pmuirq(unsigned int irq, int cpu, void __percpu *devid) { - if (armpmu_count_irq_users(irq) == 1) + struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu); + + if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1) free_percpu_irq(irq, devid); } @@ -89,7 +92,9 @@ static void armpmu_disable_percpu_pmunmi(unsigned int irq) static void armpmu_free_percpu_pmunmi(unsigned int irq, int cpu, void __percpu *devid) { - if (armpmu_count_irq_users(irq) == 1) + struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu); + + if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1) free_percpu_nmi(irq, devid); } @@ -99,7 +104,6 @@ static const struct pmu_irq_ops percpu_pmunmi_ops = { .free_pmuirq = armpmu_free_percpu_pmunmi }; -DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu); static DEFINE_PER_CPU(int, cpu_irq); static DEFINE_PER_CPU(const struct pmu_irq_ops *, cpu_irq_ops); @@ -580,11 +584,11 @@ static const struct attribute_group armpmu_common_attr_group = { .attrs = armpmu_common_attrs, }; -static int armpmu_count_irq_users(const int irq) +static int armpmu_count_irq_users(const struct cpumask *affinity, const int irq) { int cpu, count = 0; - for_each_possible_cpu(cpu) { + for_each_cpu(cpu, affinity) { if (per_cpu(cpu_irq, cpu) == irq) count++; } @@ -592,12 +596,13 @@ static int armpmu_count_irq_users(const int irq) return count; } -static const struct pmu_irq_ops *armpmu_find_irq_ops(int irq) +static const struct pmu_irq_ops * +armpmu_find_irq_ops(const struct cpumask *affinity, int irq) { const struct pmu_irq_ops *ops = NULL; int cpu; - for_each_possible_cpu(cpu) { + for_each_cpu(cpu, affinity) { if (per_cpu(cpu_irq, cpu) != irq) continue; @@ -609,22 +614,25 @@ static const struct pmu_irq_ops *armpmu_find_irq_ops(int irq) return ops; } -void armpmu_free_irq(int irq, int cpu) +void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu) { if (per_cpu(cpu_irq, cpu) == 0) return; if (WARN_ON(irq != per_cpu(cpu_irq, cpu))) return; - per_cpu(cpu_irq_ops, cpu)->free_pmuirq(irq, cpu, &cpu_armpmu); + per_cpu(cpu_irq_ops, cpu)->free_pmuirq(irq, cpu, armpmu); per_cpu(cpu_irq, cpu) = 0; per_cpu(cpu_irq_ops, cpu) = NULL; } -int armpmu_request_irq(int irq, int cpu) +int armpmu_request_irq(struct arm_pmu * __percpu *pcpu_armpmu, int irq, int cpu) { int err = 0; + struct arm_pmu **armpmu = per_cpu_ptr(pcpu_armpmu, cpu); + const struct cpumask *affinity = *armpmu ? &(*armpmu)->supported_cpus : + cpu_possible_mask; /* ACPI */ const irq_handler_t handler = armpmu_dispatch_irq; const struct pmu_irq_ops *irq_ops; @@ -646,25 +654,24 @@ int armpmu_request_irq(int irq, int cpu) IRQF_NOBALANCING | IRQF_NO_AUTOEN | IRQF_NO_THREAD; - err = request_nmi(irq, handler, irq_flags, "arm-pmu", - per_cpu_ptr(&cpu_armpmu, cpu)); + err = request_nmi(irq, handler, irq_flags, "arm-pmu", armpmu); /* If cannot get an NMI, get a normal interrupt */ if (err) { err = request_irq(irq, handler, irq_flags, "arm-pmu", - per_cpu_ptr(&cpu_armpmu, cpu)); + armpmu); irq_ops = &pmuirq_ops; } else { has_nmi = true; irq_ops = &pmunmi_ops; } - } else if (armpmu_count_irq_users(irq) == 0) { - err = request_percpu_nmi(irq, handler, "arm-pmu", &cpu_armpmu); + } else if (armpmu_count_irq_users(affinity, irq) == 0) { + err = request_percpu_nmi(irq, handler, "arm-pmu", affinity, pcpu_armpmu); /* If cannot get an NMI, get a normal interrupt */ if (err) { - err = request_percpu_irq(irq, handler, "arm-pmu", - &cpu_armpmu); + err = request_percpu_irq_affinity(irq, handler, "arm-pmu", + affinity, pcpu_armpmu); irq_ops = &percpu_pmuirq_ops; } else { has_nmi = true; @@ -672,7 +679,7 @@ int armpmu_request_irq(int irq, int cpu) } } else { /* Per cpudevid irq was already requested by another CPU */ - irq_ops = armpmu_find_irq_ops(irq); + irq_ops = armpmu_find_irq_ops(affinity, irq); if (WARN_ON(!irq_ops)) err = -EINVAL; @@ -717,8 +724,6 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node) if (pmu->reset) pmu->reset(pmu); - per_cpu(cpu_armpmu, cpu) = pmu; - irq = armpmu_get_cpu_irq(pmu, cpu); if (irq) per_cpu(cpu_irq_ops, cpu)->enable_pmuirq(irq); @@ -738,8 +743,6 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node) if (irq) per_cpu(cpu_irq_ops, cpu)->disable_pmuirq(irq); - per_cpu(cpu_armpmu, cpu) = NULL; - return 0; } @@ -925,6 +928,12 @@ int armpmu_register(struct arm_pmu *pmu) if (ret) return ret; + /* + * By this stage we know our supported CPUs on either DT/ACPI platforms, + * detect the SMT implementation. + */ + pmu->has_smt = topology_core_has_smt(cpumask_first(&pmu->supported_cpus)); + if (!pmu->set_event_filter) pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c index 05dda19c5359..e80f76d95e68 100644 --- a/drivers/perf/arm_pmu_acpi.c +++ b/drivers/perf/arm_pmu_acpi.c @@ -218,7 +218,7 @@ static int arm_pmu_acpi_parse_irqs(void) * them with their PMUs. */ per_cpu(pmu_irqs, cpu) = irq; - err = armpmu_request_irq(irq, cpu); + err = armpmu_request_irq(&probed_pmus, irq, cpu); if (err) goto out_err; } diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c index 118170a5cede..1c9e50a13201 100644 --- a/drivers/perf/arm_pmu_platform.c +++ b/drivers/perf/arm_pmu_platform.c @@ -42,14 +42,13 @@ static int probe_current_pmu(struct arm_pmu *pmu, return ret; } -static int pmu_parse_percpu_irq(struct arm_pmu *pmu, int irq) +static int pmu_parse_percpu_irq(struct arm_pmu *pmu, int irq, + const struct cpumask *affinity) { - int cpu, ret; struct pmu_hw_events __percpu *hw_events = pmu->hw_events; + int cpu; - ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus); - if (ret) - return ret; + cpumask_copy(&pmu->supported_cpus, affinity); for_each_cpu(cpu, &pmu->supported_cpus) per_cpu(hw_events->irq, cpu) = irq; @@ -115,9 +114,12 @@ static int pmu_parse_irqs(struct arm_pmu *pmu) } if (num_irqs == 1) { - int irq = platform_get_irq(pdev, 0); + const struct cpumask *affinity; + int irq; + + irq = platform_get_irq_affinity(pdev, 0, &affinity); if ((irq > 0) && irq_is_percpu_devid(irq)) - return pmu_parse_percpu_irq(pmu, irq); + return pmu_parse_percpu_irq(pmu, irq, affinity); } if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(dev->of_node)) @@ -163,7 +165,7 @@ static int armpmu_request_irqs(struct arm_pmu *armpmu) if (!irq) continue; - err = armpmu_request_irq(irq, cpu); + err = armpmu_request_irq(&hw_events->percpu_pmu, irq, cpu); if (err) break; } @@ -179,7 +181,7 @@ static void armpmu_free_irqs(struct arm_pmu *armpmu) for_each_cpu(cpu, &armpmu->supported_cpus) { int irq = per_cpu(hw_events->irq, cpu); - armpmu_free_irq(irq, cpu); + armpmu_free_irq(&hw_events->percpu_pmu, irq, cpu); } } diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 69c5cc8f5606..8014ff766cff 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -981,6 +981,7 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc, static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc, struct perf_event *event) { + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT; @@ -1001,6 +1002,15 @@ static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc, if (has_branch_stack(event)) return false; + /* + * The PMCCNTR_EL0 increments from the processor clock rather than + * the PE clock (ARM DDI0487 L.b D13.1.3) which means it'll continue + * counting on a WFI PE if one of its SMT sibling is not idle on a + * multi-threaded implementation. So don't use it on SMT cores. + */ + if (cpu_pmu->has_smt) + return false; + return true; } @@ -1064,7 +1074,7 @@ static int armv8pmu_user_event_idx(struct perf_event *event) static void armv8pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in) { - struct arm_pmu *armpmu = *this_cpu_ptr(&cpu_armpmu); + struct arm_pmu *armpmu = to_arm_pmu(pmu_ctx->pmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); if (!hw_events->branch_users) @@ -1465,6 +1475,10 @@ static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ PMUV3_INIT_SIMPLE(armv8_pmuv3) +PMUV3_INIT_SIMPLE(armv8_c1_nano) +PMUV3_INIT_SIMPLE(armv8_c1_premium) +PMUV3_INIT_SIMPLE(armv8_c1_pro) +PMUV3_INIT_SIMPLE(armv8_c1_ultra) PMUV3_INIT_SIMPLE(armv8_cortex_a34) PMUV3_INIT_SIMPLE(armv8_cortex_a55) PMUV3_INIT_SIMPLE(armv8_cortex_a65) @@ -1472,11 +1486,14 @@ PMUV3_INIT_SIMPLE(armv8_cortex_a75) PMUV3_INIT_SIMPLE(armv8_cortex_a76) PMUV3_INIT_SIMPLE(armv8_cortex_a77) PMUV3_INIT_SIMPLE(armv8_cortex_a78) +PMUV3_INIT_SIMPLE(armv9_cortex_a320) PMUV3_INIT_SIMPLE(armv9_cortex_a510) PMUV3_INIT_SIMPLE(armv9_cortex_a520) +PMUV3_INIT_SIMPLE(armv9_cortex_a520ae) PMUV3_INIT_SIMPLE(armv9_cortex_a710) PMUV3_INIT_SIMPLE(armv9_cortex_a715) PMUV3_INIT_SIMPLE(armv9_cortex_a720) +PMUV3_INIT_SIMPLE(armv9_cortex_a720ae) PMUV3_INIT_SIMPLE(armv9_cortex_a725) PMUV3_INIT_SIMPLE(armv8_cortex_x1) PMUV3_INIT_SIMPLE(armv9_cortex_x2) @@ -1508,6 +1525,10 @@ PMUV3_INIT_MAP_EVENT(armv8_brcm_vulcan, armv8_vulcan_map_event) static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_pmu_init}, + {.compatible = "arm,c1-nano-pmu", .data = armv8_c1_nano_pmu_init}, + {.compatible = "arm,c1-premium-pmu", .data = armv8_c1_premium_pmu_init}, + {.compatible = "arm,c1-pro-pmu", .data = armv8_c1_pro_pmu_init}, + {.compatible = "arm,c1-ultra-pmu", .data = armv8_c1_ultra_pmu_init}, {.compatible = "arm,cortex-a34-pmu", .data = armv8_cortex_a34_pmu_init}, {.compatible = "arm,cortex-a35-pmu", .data = armv8_cortex_a35_pmu_init}, {.compatible = "arm,cortex-a53-pmu", .data = armv8_cortex_a53_pmu_init}, @@ -1520,11 +1541,14 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,cortex-a76-pmu", .data = armv8_cortex_a76_pmu_init}, {.compatible = "arm,cortex-a77-pmu", .data = armv8_cortex_a77_pmu_init}, {.compatible = "arm,cortex-a78-pmu", .data = armv8_cortex_a78_pmu_init}, + {.compatible = "arm,cortex-a320-pmu", .data = armv9_cortex_a320_pmu_init}, {.compatible = "arm,cortex-a510-pmu", .data = armv9_cortex_a510_pmu_init}, {.compatible = "arm,cortex-a520-pmu", .data = armv9_cortex_a520_pmu_init}, + {.compatible = "arm,cortex-a520ae-pmu", .data = armv9_cortex_a520ae_pmu_init}, {.compatible = "arm,cortex-a710-pmu", .data = armv9_cortex_a710_pmu_init}, {.compatible = "arm,cortex-a715-pmu", .data = armv9_cortex_a715_pmu_init}, {.compatible = "arm,cortex-a720-pmu", .data = armv9_cortex_a720_pmu_init}, + {.compatible = "arm,cortex-a720ae-pmu", .data = armv9_cortex_a720ae_pmu_init}, {.compatible = "arm,cortex-a725-pmu", .data = armv9_cortex_a725_pmu_init}, {.compatible = "arm,cortex-x1-pmu", .data = armv8_cortex_x1_pmu_init}, {.compatible = "arm,cortex-x2-pmu", .data = armv9_cortex_x2_pmu_init}, diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index fa50645fedda..4801115f2b54 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -87,6 +87,7 @@ struct arm_spe_pmu { #define SPE_PMU_FEAT_INV_FILT_EVT (1UL << 6) #define SPE_PMU_FEAT_DISCARD (1UL << 7) #define SPE_PMU_FEAT_EFT (1UL << 8) +#define SPE_PMU_FEAT_FDS (1UL << 9) #define SPE_PMU_FEAT_DEV_PROBED (1UL << 63) u64 features; @@ -252,6 +253,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = { #define ATTR_CFG_FLD_inv_event_filter_LO 0 #define ATTR_CFG_FLD_inv_event_filter_HI 63 +#define ATTR_CFG_FLD_inv_data_src_filter_CFG config4 /* inverse of PMSDSFR_EL1 */ +#define ATTR_CFG_FLD_inv_data_src_filter_LO 0 +#define ATTR_CFG_FLD_inv_data_src_filter_HI 63 + GEN_PMU_FORMAT_ATTR(ts_enable); GEN_PMU_FORMAT_ATTR(pa_enable); GEN_PMU_FORMAT_ATTR(pct_enable); @@ -268,6 +273,7 @@ GEN_PMU_FORMAT_ATTR(float_filter); GEN_PMU_FORMAT_ATTR(float_filter_mask); GEN_PMU_FORMAT_ATTR(event_filter); GEN_PMU_FORMAT_ATTR(inv_event_filter); +GEN_PMU_FORMAT_ATTR(inv_data_src_filter); GEN_PMU_FORMAT_ATTR(min_latency); GEN_PMU_FORMAT_ATTR(discard); @@ -288,6 +294,7 @@ static struct attribute *arm_spe_pmu_formats_attr[] = { &format_attr_float_filter_mask.attr, &format_attr_event_filter.attr, &format_attr_inv_event_filter.attr, + &format_attr_inv_data_src_filter.attr, &format_attr_min_latency.attr, &format_attr_discard.attr, NULL, @@ -306,6 +313,10 @@ static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj, if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) return 0; + if (attr == &format_attr_inv_data_src_filter.attr && + !(spe_pmu->features & SPE_PMU_FEAT_FDS)) + return 0; + if ((attr == &format_attr_branch_filter_mask.attr || attr == &format_attr_load_filter_mask.attr || attr == &format_attr_store_filter_mask.attr || @@ -430,6 +441,9 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event) if (ATTR_CFG_GET_FLD(attr, inv_event_filter)) reg |= PMSFCR_EL1_FnE; + if (ATTR_CFG_GET_FLD(attr, inv_data_src_filter)) + reg |= PMSFCR_EL1_FDS; + if (ATTR_CFG_GET_FLD(attr, min_latency)) reg |= PMSFCR_EL1_FL; @@ -454,6 +468,17 @@ static u64 arm_spe_event_to_pmslatfr(struct perf_event *event) return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency)); } +static u64 arm_spe_event_to_pmsdsfr(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + + /* + * Data src filter is inverted so that the default value of 0 is + * equivalent to no filtering. + */ + return ~ATTR_CFG_GET_FLD(attr, inv_data_src_filter); +} + static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len) { struct arm_spe_pmu_buf *buf = perf_get_aux(handle); @@ -791,6 +816,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event) if (arm_spe_event_to_pmsnevfr(event) & spe_pmu->pmsevfr_res0) return -EOPNOTSUPP; + if (arm_spe_event_to_pmsdsfr(event) != U64_MAX && + !(spe_pmu->features & SPE_PMU_FEAT_FDS)) + return -EOPNOTSUPP; + if (attr->exclude_idle) return -EOPNOTSUPP; @@ -866,6 +895,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags) write_sysreg_s(reg, SYS_PMSNEVFR_EL1); } + if (spe_pmu->features & SPE_PMU_FEAT_FDS) { + reg = arm_spe_event_to_pmsdsfr(event); + write_sysreg_s(reg, SYS_PMSDSFR_EL1); + } + reg = arm_spe_event_to_pmslatfr(event); write_sysreg_s(reg, SYS_PMSLATFR_EL1); @@ -1125,6 +1159,9 @@ static void __arm_spe_pmu_dev_probe(void *info) if (FIELD_GET(PMSIDR_EL1_EFT, reg)) spe_pmu->features |= SPE_PMU_FEAT_EFT; + if (FIELD_GET(PMSIDR_EL1_FDS, reg)) + spe_pmu->features |= SPE_PMU_FEAT_FDS; + /* This field has a spaced out encoding, so just use a look-up */ fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg); switch (fld) { @@ -1259,8 +1296,8 @@ static int arm_spe_pmu_dev_init(struct arm_spe_pmu *spe_pmu) return -ENXIO; /* Request our PPIs (note that the IRQ is still disabled) */ - ret = request_percpu_irq(spe_pmu->irq, arm_spe_pmu_irq_handler, DRVNAME, - spe_pmu->handle); + ret = request_percpu_irq_affinity(spe_pmu->irq, arm_spe_pmu_irq_handler, + DRVNAME, mask, spe_pmu->handle); if (ret) return ret; @@ -1287,8 +1324,10 @@ static void arm_spe_pmu_dev_teardown(struct arm_spe_pmu *spe_pmu) static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu) { struct platform_device *pdev = spe_pmu->pdev; - int irq = platform_get_irq(pdev, 0); + const struct cpumask *affinity; + int irq; + irq = platform_get_irq_affinity(pdev, 0, &affinity); if (irq < 0) return -ENXIO; @@ -1297,10 +1336,7 @@ static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu) return -EINVAL; } - if (irq_get_percpu_devid_partition(irq, &spe_pmu->supported_cpus)) { - dev_err(&pdev->dev, "failed to get PPI partition (%d)\n", irq); - return -EINVAL; - } + cpumask_copy(&spe_pmu->supported_cpus, affinity); spe_pmu->irq = irq; return 0; diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index b989ffa95d69..bcdf5575d71c 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -5,6 +5,7 @@ */ #include <linux/bitfield.h> +#include <linux/clk.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -52,18 +53,27 @@ #define to_ddr_pmu(p) container_of(p, struct ddr_pmu, pmu) #define DDR_PERF_DEV_NAME "imx8_ddr" +#define DB_PERF_DEV_NAME "imx8_db" #define DDR_CPUHP_CB_NAME DDR_PERF_DEV_NAME "_perf_pmu" static DEFINE_IDA(ddr_ida); +static DEFINE_IDA(db_ida); /* DDR Perf hardware feature */ #define DDR_CAP_AXI_ID_FILTER 0x1 /* support AXI ID filter */ #define DDR_CAP_AXI_ID_FILTER_ENHANCED 0x3 /* support enhanced AXI ID filter */ #define DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER 0x4 /* support AXI ID PORT CHANNEL filter */ +/* Perf type */ +enum fsl_ddr_type { + DDR_PERF_TYPE = 0, /* ddr Perf (default) */ + DB_PERF_TYPE, /* db Perf */ +}; + struct fsl_ddr_devtype_data { unsigned int quirks; /* quirks needed for different DDR Perf core */ const char *identifier; /* system PMU identifier for userspace */ + enum fsl_ddr_type type; /* types of Perf, ddr or db */ }; static const struct fsl_ddr_devtype_data imx8_devtype_data; @@ -97,6 +107,12 @@ static const struct fsl_ddr_devtype_data imx8dxl_devtype_data = { .identifier = "i.MX8DXL", }; +static const struct fsl_ddr_devtype_data imx8dxl_db_devtype_data = { + .quirks = DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER, + .identifier = "i.MX8DXL", + .type = DB_PERF_TYPE, +}; + static const struct of_device_id imx_ddr_pmu_dt_ids[] = { { .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data}, { .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data}, @@ -105,6 +121,7 @@ static const struct of_device_id imx_ddr_pmu_dt_ids[] = { { .compatible = "fsl,imx8mn-ddr-pmu", .data = &imx8mn_devtype_data}, { .compatible = "fsl,imx8mp-ddr-pmu", .data = &imx8mp_devtype_data}, { .compatible = "fsl,imx8dxl-ddr-pmu", .data = &imx8dxl_devtype_data}, + { .compatible = "fsl,imx8dxl-db-pmu", .data = &imx8dxl_db_devtype_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids); @@ -284,9 +301,37 @@ static struct attribute *ddr_perf_events_attrs[] = { NULL, }; +static const int ddr_perf_db_visible_event_list[] = { + EVENT_CYCLES_ID, + 0x41, + 0x42, +}; + +static umode_t ddr_perf_events_attrs_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct ddr_pmu *pmu = dev_get_drvdata(dev); + struct perf_pmu_events_attr *pmu_attr; + unsigned int i; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); + + if (pmu->devtype_data->type == DDR_PERF_TYPE) + return attr->mode; + + /* DB Type */ + for (i = 0; i < ARRAY_SIZE(ddr_perf_db_visible_event_list); i++) + if (pmu_attr->id == ddr_perf_db_visible_event_list[i]) + return attr->mode; + + return 0; +} + static const struct attribute_group ddr_perf_events_attr_group = { .name = "events", .attrs = ddr_perf_events_attrs, + .is_visible = ddr_perf_events_attrs_is_visible, }; PMU_FORMAT_ATTR(event, "config:0-7"); @@ -645,8 +690,8 @@ static void ddr_perf_pmu_disable(struct pmu *pmu) { } -static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base, - struct device *dev) +static void ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base, + struct device *dev) { *pmu = (struct ddr_pmu) { .pmu = (struct pmu) { @@ -667,9 +712,6 @@ static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base, .base = base, .dev = dev, }; - - pmu->id = ida_alloc(&ddr_ida, GFP_KERNEL); - return pmu->id; } static irqreturn_t ddr_perf_irq_handler(int irq, void *p) @@ -735,10 +777,13 @@ static int ddr_perf_offline_cpu(unsigned int cpu, struct hlist_node *node) static int ddr_perf_probe(struct platform_device *pdev) { + struct clk_bulk_data *clks; struct ddr_pmu *pmu; struct device_node *np; void __iomem *base; + struct ida *ida; char *name; + int nclks; int num; int ret; int irq; @@ -753,19 +798,33 @@ static int ddr_perf_probe(struct platform_device *pdev) if (!pmu) return -ENOMEM; - num = ddr_perf_init(pmu, base, &pdev->dev); + ddr_perf_init(pmu, base, &pdev->dev); platform_set_drvdata(pdev, pmu); - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d", - num); + nclks = devm_clk_bulk_get_all_enabled(&pdev->dev, &clks); + if (nclks < 0) + return dev_err_probe(&pdev->dev, nclks, "Failure get clks\n"); + + pmu->devtype_data = of_device_get_match_data(&pdev->dev); + + ida = pmu->devtype_data->type == DDR_PERF_TYPE ? &ddr_ida : &db_ida; + num = ida_alloc(ida, GFP_KERNEL); + if (num < 0) + return num; + + pmu->id = num; + + if (pmu->devtype_data->type == DDR_PERF_TYPE) + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d", num); + else + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DB_PERF_DEV_NAME "%d", num); + if (!name) { ret = -ENOMEM; - goto cpuhp_state_err; + goto idr_free; } - pmu->devtype_data = of_device_get_match_data(&pdev->dev); - pmu->cpu = raw_smp_processor_id(); ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DDR_CPUHP_CB_NAME, @@ -774,7 +833,7 @@ static int ddr_perf_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "cpuhp_setup_state_multi failed\n"); - goto cpuhp_state_err; + goto idr_free; } pmu->cpuhp_state = ret; @@ -821,8 +880,8 @@ ddr_perf_err: cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); cpuhp_instance_err: cpuhp_remove_multi_state(pmu->cpuhp_state); -cpuhp_state_err: - ida_free(&ddr_ida, pmu->id); +idr_free: + ida_free(ida, pmu->id); dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret); return ret; } @@ -836,7 +895,11 @@ static void ddr_perf_remove(struct platform_device *pdev) perf_pmu_unregister(&pmu->pmu); - ida_free(&ddr_ida, pmu->id); + if (pmu->devtype_data->type == DDR_PERF_TYPE) + ida_free(&ddr_ida, pmu->id); + else + ida_free(&db_ida, pmu->id); + } static struct platform_driver imx_ddr_pmu_driver = { diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index e255c1b069ec..7dd282da67ce 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1109,7 +1109,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) /* compute hardware counter index */ hidx = info->csr - CSR_CYCLE; - /* check if the corresponding bit is set in sscountovf or overflow mask in shmem */ + /* check if the corresponding bit is set in scountovf or overflow mask in shmem */ if (!(overflow & BIT(hidx))) continue; |