diff options
Diffstat (limited to 'arch/powerpc/perf')
| -rw-r--r-- | arch/powerpc/perf/8xx-pmu.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/perf/Makefile | 2 | ||||
| -rw-r--r-- | arch/powerpc/perf/callchain.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/perf/callchain_32.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/perf/callchain_64.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/perf/core-book3s.c | 55 | ||||
| -rw-r--r-- | arch/powerpc/perf/hv-24x7.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/perf/hv-gpci.c | 29 | ||||
| -rw-r--r-- | arch/powerpc/perf/internal.h | 1 | ||||
| -rw-r--r-- | arch/powerpc/perf/power10-pmu.c | 30 | ||||
| -rw-r--r-- | arch/powerpc/perf/vpa-pmu.c | 203 |
11 files changed, 291 insertions, 47 deletions
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c index 308a2e40d7be..1d2972229e3a 100644 --- a/arch/powerpc/perf/8xx-pmu.c +++ b/arch/powerpc/perf/8xx-pmu.c @@ -14,7 +14,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/inst.h> #define PERF_8xx_ID_CPU_CYCLES 1 diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 4f53d0b97539..ac2cf58d62db 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -16,6 +16,8 @@ obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o +obj-$(CONFIG_VPA_PMU) += vpa-pmu.o + obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 6b4434dd0ff3..26aa26482c9a 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -51,7 +51,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, perf_instruction_pointer(regs)); + perf_callchain_store(entry, perf_arch_instruction_pointer(regs)); if (!validate_sp(sp, current)) return; diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index ea8cfe3806dc..ddcc2d8aa64a 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -139,7 +139,7 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, long level = 0; unsigned int __user *fp, *uregs; - next_ip = perf_instruction_pointer(regs); + next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 488e8a21a11e..115d1c105e8a 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -74,7 +74,7 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, struct signal_frame_64 __user *sigframe; unsigned long __user *fp, *uregs; - next_ip = perf_instruction_pointer(regs); + next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index b7ff680cde96..2b79171ee185 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -16,7 +16,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/hw_irq.h> #include <asm/interrupt.h> @@ -256,7 +256,7 @@ static bool regs_sipr(struct pt_regs *regs) static inline u32 perf_flags_from_msr(struct pt_regs *regs) { - if (regs->msr & MSR_PR) + if (user_mode(regs)) return PERF_RECORD_MISC_USER; if ((regs->msr & MSR_HV) && freeze_events_kernel != MMCR0_FCHV) return PERF_RECORD_MISC_HYPERVISOR; @@ -266,51 +266,44 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs) static inline u32 perf_get_misc_flags(struct pt_regs *regs) { bool use_siar = regs_use_siar(regs); - unsigned long mmcra = regs->dsisr; - int marked = mmcra & MMCRA_SAMPLE_ENABLE; + unsigned long siar; + unsigned long addr; if (!use_siar) return perf_flags_from_msr(regs); /* - * Check the address in SIAR to identify the - * privilege levels since the SIER[MSR_HV, MSR_PR] - * bits are not set for marked events in power10 - * DD1. - */ - if (marked && (ppmu->flags & PPMU_P10_DD1)) { - unsigned long siar = mfspr(SPRN_SIAR); - if (siar) { - if (is_kernel_addr(siar)) - return PERF_RECORD_MISC_KERNEL; - return PERF_RECORD_MISC_USER; - } else { - if (is_kernel_addr(regs->nip)) - return PERF_RECORD_MISC_KERNEL; - return PERF_RECORD_MISC_USER; - } - } - - /* * If we don't have flags in MMCRA, rather than using * the MSR, we intuit the flags from the address in * SIAR which should give slightly more reliable * results */ if (ppmu->flags & PPMU_NO_SIPR) { - unsigned long siar = mfspr(SPRN_SIAR); + siar = mfspr(SPRN_SIAR); if (is_kernel_addr(siar)) return PERF_RECORD_MISC_KERNEL; return PERF_RECORD_MISC_USER; } /* PR has priority over HV, so order below is important */ - if (regs_sipr(regs)) - return PERF_RECORD_MISC_USER; - - if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV)) + if (regs_sipr(regs)) { + if (!(ppmu->flags & PPMU_P10)) + return PERF_RECORD_MISC_USER; + } else if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV)) return PERF_RECORD_MISC_HYPERVISOR; + /* + * Check the address in SIAR to identify the + * privilege levels since the SIER[MSR_HV, MSR_PR] + * bits are not set correctly in power10 sometimes + */ + if (ppmu->flags & PPMU_P10) { + siar = mfspr(SPRN_SIAR); + addr = siar ? siar : regs->nip; + if (!is_kernel_addr(addr)) + return PERF_RECORD_MISC_USER; + } + return PERF_RECORD_MISC_KERNEL; } @@ -2339,7 +2332,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * Called from generic code to get the misc flags (i.e. processor mode) * for an event_id. */ -unsigned long perf_misc_flags(struct pt_regs *regs) +unsigned long perf_arch_misc_flags(struct pt_regs *regs) { u32 flags = perf_get_misc_flags(regs); @@ -2353,7 +2346,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) * Called from generic code to get the instruction pointer * for an event_id. */ -unsigned long perf_instruction_pointer(struct pt_regs *regs) +unsigned long perf_arch_instruction_pointer(struct pt_regs *regs) { unsigned long siar = mfspr(SPRN_SIAR); @@ -2593,6 +2586,8 @@ static int __init init_ppc64_pmu(void) return 0; else if (!init_power10_pmu()) return 0; + else if (!init_power11_pmu()) + return 0; else if (!init_ppc970_pmu()) return 0; else diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 057ec2e3451d..d400fa391c27 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -425,16 +425,6 @@ static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp) return kasprintf(gfp, "%.*s", max_len, maybe_str); } -static ssize_t device_show_string(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct dev_ext_attribute *d; - - d = container_of(attr, struct dev_ext_attribute, attr); - - return sprintf(buf, "%s\n", (char *)d->var); -} - static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 27f18119fda1..241551d1282f 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -695,6 +695,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL', + * specifies that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * Since in this function we are only accessing data for a given starting index, + * we don't need to accommodate whole data and can get required count by + * accessing first entry data. + * Hence hcall fails only incase the ret value is other than H_SUCCESS or + * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B). + */ + if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B) + ret = 0; + if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); goto out; @@ -759,6 +773,7 @@ static int h_gpci_event_init(struct perf_event *event) { u64 count; u8 length; + unsigned long ret; /* Not our event */ if (event->attr.type != event->pmu->type) @@ -789,13 +804,23 @@ static int h_gpci_event_init(struct perf_event *event) } /* check if the request works... */ - if (single_gpci_request(event_get_request(event), + ret = single_gpci_request(event_get_request(event), event_get_starting_index(event), event_get_secondary_index(event), event_get_counter_info_version(event), event_get_offset(event), length, - &count)) { + &count); + + /* + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + if (ret) { pr_devel("gpci hcall failed\n"); return -EINVAL; } diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h index 4c18b5504326..a70ac471a5a5 100644 --- a/arch/powerpc/perf/internal.h +++ b/arch/powerpc/perf/internal.h @@ -10,4 +10,5 @@ int __init init_power7_pmu(void); int __init init_power8_pmu(void); int __init init_power9_pmu(void); int __init init_power10_pmu(void); +int __init init_power11_pmu(void); int __init init_generic_compat_pmu(void); diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index 9b5133e361a7..bb57b7cfe640 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -593,7 +593,8 @@ static struct power_pmu power10_pmu = { .get_mem_weight = isa207_get_mem_weight, .disable_pmc = isa207_disable_pmc, .flags = PPMU_HAS_SIER | PPMU_ARCH_207S | - PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1, + PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1 | + PPMU_P10, .n_generic = ARRAY_SIZE(power10_generic_events), .generic_events = power10_generic_events, .cache_events = &power10_cache_events, @@ -634,3 +635,30 @@ int __init init_power10_pmu(void) return 0; } + +static struct power_pmu power11_pmu; + +int __init init_power11_pmu(void) +{ + unsigned int pvr; + int rc; + + pvr = mfspr(SPRN_PVR); + if (PVR_VER(pvr) != PVR_POWER11) + return -ENODEV; + + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + + power11_pmu = power10_pmu; + power11_pmu.name = "Power11"; + + rc = register_power_pmu(&power11_pmu); + if (rc) + return rc; + + /* Tell userspace that EBB is supported */ + cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB; + + return 0; +} diff --git a/arch/powerpc/perf/vpa-pmu.c b/arch/powerpc/perf/vpa-pmu.c new file mode 100644 index 000000000000..6a5bfd2a13b5 --- /dev/null +++ b/arch/powerpc/perf/vpa-pmu.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Performance monitoring support for Virtual Processor Area(VPA) based counters + * + * Copyright (C) 2024 IBM Corporation + */ +#define pr_fmt(fmt) "vpa_pmu: " fmt + +#include <linux/module.h> +#include <linux/perf_event.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s_64.h> + +#define MODULE_VERS "1.0" +#define MODULE_NAME "pseries_vpa_pmu" + +#define EVENT(_name, _code) enum{_name = _code} + +#define VPA_PMU_EVENT_VAR(_id) event_attr_##_id +#define VPA_PMU_EVENT_PTR(_id) (&event_attr_##_id.attr.attr) + +static ssize_t vpa_pmu_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + + return sprintf(page, "event=0x%02llx\n", pmu_attr->id); +} + +#define VPA_PMU_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, VPA_PMU_EVENT_VAR(_id), _id, \ + vpa_pmu_events_sysfs_show) + +EVENT(L1_TO_L2_CS_LAT, 0x1); +EVENT(L2_TO_L1_CS_LAT, 0x2); +EVENT(L2_RUNTIME_AGG, 0x3); + +VPA_PMU_EVENT_ATTR(l1_to_l2_lat, L1_TO_L2_CS_LAT); +VPA_PMU_EVENT_ATTR(l2_to_l1_lat, L2_TO_L1_CS_LAT); +VPA_PMU_EVENT_ATTR(l2_runtime_agg, L2_RUNTIME_AGG); + +static struct attribute *vpa_pmu_events_attr[] = { + VPA_PMU_EVENT_PTR(L1_TO_L2_CS_LAT), + VPA_PMU_EVENT_PTR(L2_TO_L1_CS_LAT), + VPA_PMU_EVENT_PTR(L2_RUNTIME_AGG), + NULL +}; + +static const struct attribute_group vpa_pmu_events_group = { + .name = "events", + .attrs = vpa_pmu_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-31"); +static struct attribute *vpa_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group vpa_pmu_format_group = { + .name = "format", + .attrs = vpa_pmu_format_attr, +}; + +static const struct attribute_group *vpa_pmu_attr_groups[] = { + &vpa_pmu_events_group, + &vpa_pmu_format_group, + NULL +}; + +static int vpa_pmu_event_init(struct perf_event *event) +{ + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* it does not support event sampling mode */ + if (is_sampling_event(event)) + return -EOPNOTSUPP; + + /* no branch sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + /* Invalid event code */ + if ((event->attr.config <= 0) || (event->attr.config > 3)) + return -EINVAL; + + return 0; +} + +static unsigned long get_counter_data(struct perf_event *event) +{ + unsigned int config = event->attr.config; + u64 data; + + switch (config) { + case L1_TO_L2_CS_LAT: + if (event->attach_state & PERF_ATTACH_TASK) + data = kvmhv_get_l1_to_l2_cs_time_vcpu(); + else + data = kvmhv_get_l1_to_l2_cs_time(); + break; + case L2_TO_L1_CS_LAT: + if (event->attach_state & PERF_ATTACH_TASK) + data = kvmhv_get_l2_to_l1_cs_time_vcpu(); + else + data = kvmhv_get_l2_to_l1_cs_time(); + break; + case L2_RUNTIME_AGG: + if (event->attach_state & PERF_ATTACH_TASK) + data = kvmhv_get_l2_runtime_agg_vcpu(); + else + data = kvmhv_get_l2_runtime_agg(); + break; + default: + data = 0; + break; + } + + return data; +} + +static int vpa_pmu_add(struct perf_event *event, int flags) +{ + u64 data; + + kvmhv_set_l2_counters_status(smp_processor_id(), true); + + data = get_counter_data(event); + local64_set(&event->hw.prev_count, data); + + return 0; +} + +static void vpa_pmu_read(struct perf_event *event) +{ + u64 prev_data, new_data, final_data; + + prev_data = local64_read(&event->hw.prev_count); + new_data = get_counter_data(event); + final_data = new_data - prev_data; + + local64_add(final_data, &event->count); +} + +static void vpa_pmu_del(struct perf_event *event, int flags) +{ + vpa_pmu_read(event); + + /* + * Disable vpa counter accumulation + */ + kvmhv_set_l2_counters_status(smp_processor_id(), false); +} + +static struct pmu vpa_pmu = { + .task_ctx_nr = perf_sw_context, + .name = "vpa_pmu", + .event_init = vpa_pmu_event_init, + .add = vpa_pmu_add, + .del = vpa_pmu_del, + .read = vpa_pmu_read, + .attr_groups = vpa_pmu_attr_groups, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, +}; + +static int __init pseries_vpa_pmu_init(void) +{ + /* + * List of current Linux on Power platforms and + * this driver is supported only in PowerVM LPAR + * (L1) platform. + * + * Enabled Linux on Power Platforms + * ---------------------------------------- + * [X] PowerVM LPAR (L1) + * [ ] KVM Guest On PowerVM KoP(L2) + * [ ] Baremetal(PowerNV) + * [ ] KVM Guest On PowerNV + */ + if (!firmware_has_feature(FW_FEATURE_LPAR) || is_kvm_guest()) + return -ENODEV; + + perf_pmu_register(&vpa_pmu, vpa_pmu.name, -1); + pr_info("Virtual Processor Area PMU registered.\n"); + + return 0; +} + +static void __exit pseries_vpa_pmu_cleanup(void) +{ + perf_pmu_unregister(&vpa_pmu); + pr_info("Virtual Processor Area PMU unregistered.\n"); +} + +module_init(pseries_vpa_pmu_init); +module_exit(pseries_vpa_pmu_cleanup); +MODULE_DESCRIPTION("Perf Driver for pSeries VPA pmu counter"); +MODULE_AUTHOR("Kajol Jain <kjain@linux.ibm.com>"); +MODULE_AUTHOR("Madhavan Srinivasan <maddy@linux.ibm.com>"); +MODULE_LICENSE("GPL"); |