Ampere SoC PMU follows CoreSight PMU architecture. It uses implementation specific registers to filter events rather than PMEVFILTnR registers. Signed-off-by: Ilkka Koskinen <ilkka@xxxxxxxxxxxxxxxxxxxxxx> --- .../admin-guide/perf/ampere_cspmu.rst | 29 ++ drivers/perf/arm_cspmu/Kconfig | 10 + drivers/perf/arm_cspmu/Makefile | 2 + drivers/perf/arm_cspmu/ampere_cspmu.c | 271 ++++++++++++++++++ drivers/perf/arm_cspmu/arm_cspmu.c | 8 + drivers/perf/arm_cspmu/arm_cspmu.h | 1 + 6 files changed, 321 insertions(+) create mode 100644 Documentation/admin-guide/perf/ampere_cspmu.rst create mode 100644 drivers/perf/arm_cspmu/ampere_cspmu.c diff --git a/Documentation/admin-guide/perf/ampere_cspmu.rst b/Documentation/admin-guide/perf/ampere_cspmu.rst new file mode 100644 index 000000000000..94f93f5aee6c --- /dev/null +++ b/Documentation/admin-guide/perf/ampere_cspmu.rst @@ -0,0 +1,29 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================ +Ampere SoC Performance Monitoring Unit (PMU) +============================================ + +Ampere SoC PMU is a generic PMU IP that follows Arm CoreSight PMU architecture. +Therefore, the driver is implemented as a submodule of arm_cspmu driver. At the +first phase it's used for counting MCU events on AmpereOne. + + +MCU PMU events +-------------- + +The PMU driver supports setting filters for "rank", "bank", and "threshold". +Note, that the filters are per PMU instance rather than per event. + + +Example for perf tool use:: + + / # perf list ampere + + ampere_mcu_pmu_0/act_sent/ [Kernel PMU event] + <...> + ampere_mcu_pmu_1/rd_sent/ [Kernel PMU event] + <...> + + / # perf stat -a -e ampere_mcu_pmu_0/act_sent,bank=5,rank=3,threshold=2/,ampere_mcu_pmu_1/rd_sent/ \ + sleep 1 diff --git a/drivers/perf/arm_cspmu/Kconfig b/drivers/perf/arm_cspmu/Kconfig index d5f787d22234..6f4e28fc84a2 100644 --- a/drivers/perf/arm_cspmu/Kconfig +++ b/drivers/perf/arm_cspmu/Kconfig @@ -17,3 +17,13 @@ config NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU help Provides NVIDIA specific attributes for performance monitoring unit (PMU) devices based on ARM CoreSight PMU architecture. + +config AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU + tristate "Ampere Coresight Architecture PMU" + depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU + help + Provides Ampere specific attributes for performance monitoring unit + (PMU) devices based on ARM CoreSight PMU architecture. + + In the first phase, the driver enables support on MCU PMU used in + AmpereOne SoC family. diff --git a/drivers/perf/arm_cspmu/Makefile b/drivers/perf/arm_cspmu/Makefile index 0309d2ff264a..220a734efd54 100644 --- a/drivers/perf/arm_cspmu/Makefile +++ b/drivers/perf/arm_cspmu/Makefile @@ -3,6 +3,8 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu_module.o + arm_cspmu_module-y := arm_cspmu.o obj-$(CONFIG_NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += nvidia_cspmu.o +obj-$(CONFIG_AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += ampere_cspmu.o diff --git a/drivers/perf/arm_cspmu/ampere_cspmu.c b/drivers/perf/arm_cspmu/ampere_cspmu.c new file mode 100644 index 000000000000..992c61d79518 --- /dev/null +++ b/drivers/perf/arm_cspmu/ampere_cspmu.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ampere SoC PMU (Performance Monitor Unit) + * + * Copyright (c) 2023, Ampere Computing LLC + */ +#include <linux/module.h> +#include <linux/topology.h> + +#include "arm_cspmu.h" + +#define PMAUXR0 0xD80 +#define PMAUXR1 0xD84 +#define PMAUXR2 0xD88 +#define PMAUXR3 0xD8C + +#define to_ampere_cspmu_ctx(cspmu) ((struct ampere_cspmu_ctx *)(cspmu->impl.ctx)) + +struct ampere_cspmu_ctx { + const char *name; + struct attribute **event_attr; + struct attribute **format_attr; +}; + +static DEFINE_IDA(mcu_pmu_ida); + +#define SOC_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end) \ + static inline u32 get_##_name(const struct perf_event *event) \ + { \ + return FIELD_GET(GENMASK_ULL(_end, _start), \ + event->attr._config); \ + } \ + +SOC_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 8); +SOC_PMU_EVENT_ATTR_EXTRACTOR(threshold, config1, 0, 7); +SOC_PMU_EVENT_ATTR_EXTRACTOR(rank, config1, 8, 23); +SOC_PMU_EVENT_ATTR_EXTRACTOR(bank, config1, 24, 55); + +static struct attribute *ampereone_mcu_pmu_event_attrs[] = { + ARM_CSPMU_EVENT_ATTR(cycle_count, 0x00), + ARM_CSPMU_EVENT_ATTR(act_sent, 0x01), + ARM_CSPMU_EVENT_ATTR(pre_sent, 0x02), + ARM_CSPMU_EVENT_ATTR(rd_sent, 0x03), + ARM_CSPMU_EVENT_ATTR(rda_sent, 0x04), + ARM_CSPMU_EVENT_ATTR(wr_sent, 0x05), + ARM_CSPMU_EVENT_ATTR(wra_sent, 0x06), + ARM_CSPMU_EVENT_ATTR(pd_entry_vld, 0x07), + ARM_CSPMU_EVENT_ATTR(sref_entry_vld, 0x08), + ARM_CSPMU_EVENT_ATTR(prea_sent, 0x09), + ARM_CSPMU_EVENT_ATTR(pre_sb_sent, 0x0a), + ARM_CSPMU_EVENT_ATTR(ref_sent, 0x0b), + ARM_CSPMU_EVENT_ATTR(rfm_sent, 0x0c), + ARM_CSPMU_EVENT_ATTR(ref_sb_sent, 0x0d), + ARM_CSPMU_EVENT_ATTR(rfm_sb_sent, 0x0e), + ARM_CSPMU_EVENT_ATTR(rd_rda_sent, 0x0f), + ARM_CSPMU_EVENT_ATTR(wr_wra_sent, 0x10), + ARM_CSPMU_EVENT_ATTR(raw_hazard, 0x11), + ARM_CSPMU_EVENT_ATTR(war_hazard, 0x12), + ARM_CSPMU_EVENT_ATTR(waw_hazard, 0x13), + ARM_CSPMU_EVENT_ATTR(rar_hazard, 0x14), + ARM_CSPMU_EVENT_ATTR(raw_war_waw_hazard, 0x15), + ARM_CSPMU_EVENT_ATTR(hprd_lprd_wr_req_vld, 0x16), + ARM_CSPMU_EVENT_ATTR(lprd_req_vld, 0x17), + ARM_CSPMU_EVENT_ATTR(hprd_req_vld, 0x18), + ARM_CSPMU_EVENT_ATTR(hprd_lprd_req_vld, 0x19), + ARM_CSPMU_EVENT_ATTR(prefetch_tgt, 0x1a), + ARM_CSPMU_EVENT_ATTR(wr_req_vld, 0x1b), + ARM_CSPMU_EVENT_ATTR(partial_wr_req_vld, 0x1c), + ARM_CSPMU_EVENT_ATTR(rd_retry, 0x1d), + ARM_CSPMU_EVENT_ATTR(wr_retry, 0x1e), + ARM_CSPMU_EVENT_ATTR(retry_gnt, 0x1f), + ARM_CSPMU_EVENT_ATTR(rank_change, 0x20), + ARM_CSPMU_EVENT_ATTR(dir_change, 0x21), + ARM_CSPMU_EVENT_ATTR(rank_dir_change, 0x22), + ARM_CSPMU_EVENT_ATTR(rank_active, 0x23), + ARM_CSPMU_EVENT_ATTR(rank_idle, 0x24), + ARM_CSPMU_EVENT_ATTR(rank_pd, 0x25), + ARM_CSPMU_EVENT_ATTR(rank_sref, 0x26), + ARM_CSPMU_EVENT_ATTR(queue_fill_gt_thresh, 0x27), + ARM_CSPMU_EVENT_ATTR(queue_rds_gt_thresh, 0x28), + ARM_CSPMU_EVENT_ATTR(queue_wrs_gt_thresh, 0x29), + ARM_CSPMU_EVENT_ATTR(phy_updt_complt, 0x2a), + ARM_CSPMU_EVENT_ATTR(tz_fail, 0x2b), + ARM_CSPMU_EVENT_ATTR(dram_errc, 0x2c), + ARM_CSPMU_EVENT_ATTR(dram_errd, 0x2d), + ARM_CSPMU_EVENT_ATTR(read_data_return, 0x32), + ARM_CSPMU_EVENT_ATTR(chi_wr_data_delta, 0x33), + ARM_CSPMU_EVENT_ATTR(zq_start, 0x34), + ARM_CSPMU_EVENT_ATTR(zq_latch, 0x35), + ARM_CSPMU_EVENT_ATTR(wr_fifo_full, 0x36), + ARM_CSPMU_EVENT_ATTR(info_fifo_full, 0x37), + ARM_CSPMU_EVENT_ATTR(cmd_fifo_full, 0x38), + ARM_CSPMU_EVENT_ATTR(dfi_nop, 0x39), + ARM_CSPMU_EVENT_ATTR(dfi_cmd, 0x3a), + ARM_CSPMU_EVENT_ATTR(rd_run_len, 0x3b), + ARM_CSPMU_EVENT_ATTR(wr_run_len, 0x3c), + + ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT), + NULL, +}; + +static struct attribute *ampereone_mcu_format_attrs[] = { + ARM_CSPMU_FORMAT_EVENT_ATTR, + ARM_CSPMU_FORMAT_ATTR(threshold, "config1:0-7"), + ARM_CSPMU_FORMAT_ATTR(rank, "config1:8-23"), + ARM_CSPMU_FORMAT_ATTR(bank, "config1:24-55"), + NULL, +}; + +static struct attribute ** +ampere_cspmu_get_event_attrs(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->event_attr; +} + +static struct attribute ** +ampere_cspmu_get_format_attrs(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->format_attr; +} + +static const char * +ampere_cspmu_get_name(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->name; +} + +static u32 ampere_cspmu_event_filter(const struct perf_event *event) +{ + /* + * PMEVFILTR or PMCCFILTR aren't used in Ampere SoC PMU but are marked + * as RES0. Make sure, PMCCFILTR is written zero. + */ + return 0; +} + +static void ampere_cspmu_set_ev_filter(struct arm_cspmu *cspmu, + struct hw_perf_event *hwc, + u32 filter) +{ + struct perf_event *event; + unsigned int idx; + u32 threshold, rank, bank; + + /* + * At this point, all the events have the same filter settings. + * Therefore, take the first event and use its configuration. + */ + idx = find_first_bit(cspmu->hw_events.used_ctrs, + cspmu->cycle_counter_logical_idx); + + event = cspmu->hw_events.events[idx]; + + threshold = get_threshold(event); + rank = get_rank(event); + bank = get_bank(event); + + writel(threshold, cspmu->base0 + PMAUXR0); + writel(rank, cspmu->base0 + PMAUXR1); + writel(bank, cspmu->base0 + PMAUXR2); +} + +static int ampere_cspmu_validate_configs(struct perf_event *event, + struct perf_event *event2) +{ + if (get_threshold(event) != get_threshold(event2) || + get_rank(event) != get_rank(event2) || + get_bank(event) != get_bank(event2)) + return -EINVAL; + + return 0; +} + +static int ampere_cspmu_validate_event(struct arm_cspmu *cspmu, + struct perf_event *new) +{ + struct perf_event *curr, *leader = new->group_leader; + unsigned int idx; + int ret; + + ret = ampere_cspmu_validate_configs(new, leader); + if (ret) + return ret; + + /* We compare the global filter settings to the existing events */ + idx = find_first_bit(cspmu->hw_events.used_ctrs, + cspmu->cycle_counter_logical_idx); + + /* This is the first event, thus any configuration is fine */ + if (idx == cspmu->cycle_counter_logical_idx) + return 0; + + curr = cspmu->hw_events.events[idx]; + + return ampere_cspmu_validate_configs(curr, new); +} + +static char *ampere_cspmu_format_name(const struct arm_cspmu *cspmu, + const char *name_pattern) +{ + struct device *dev = cspmu->dev; + int id; + + id = ida_alloc(&mcu_pmu_ida, GFP_KERNEL); + if (id < 0) + return ERR_PTR(id); + + return devm_kasprintf(dev, GFP_KERNEL, name_pattern, id); +} + +static int ampere_cspmu_init_ops(struct arm_cspmu *cspmu) +{ + struct device *dev = cspmu->dev; + struct ampere_cspmu_ctx *ctx; + struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; + + ctx = devm_kzalloc(dev, sizeof(struct ampere_cspmu_ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->event_attr = ampereone_mcu_pmu_event_attrs; + ctx->format_attr = ampereone_mcu_format_attrs; + ctx->name = ampere_cspmu_format_name(cspmu, "ampere_mcu_pmu_%d"); + if (IS_ERR_OR_NULL(ctx->name)) + return ctx->name ? PTR_ERR(ctx->name) : -ENOMEM; + + cspmu->impl.ctx = ctx; + + impl_ops->event_filter = ampere_cspmu_event_filter; + impl_ops->set_ev_filter = ampere_cspmu_set_ev_filter; + impl_ops->validate_event = ampere_cspmu_validate_event; + impl_ops->get_name = ampere_cspmu_get_name; + impl_ops->get_event_attrs = ampere_cspmu_get_event_attrs; + impl_ops->get_format_attrs = ampere_cspmu_get_format_attrs; + + return 0; +} + +/* Match all Ampere Coresight PMU devices */ +static const struct arm_cspmu_impl_match ampere_cspmu_param = { + .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE, + .module = THIS_MODULE, + .impl_init_ops = ampere_cspmu_init_ops +}; + +static int __init ampere_cspmu_init(void) +{ + int ret; + + ret = arm_cspmu_impl_register(&ere_cspmu_param); + if (ret) + pr_err("ampere_cspmu backend registration error: %d\n", ret); + + return ret; +} + +static void __exit ampere_cspmu_exit(void) +{ + arm_cspmu_impl_unregister(&ere_cspmu_param); +} + +module_init(ampere_cspmu_init); +module_exit(ampere_cspmu_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index 1ba00d640352..0e3fe00d741d 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -383,6 +383,14 @@ static struct arm_cspmu_impl_match impl_match[] = { .module = NULL, .impl_init_ops = NULL, }, + { + .module_name = "ampere_cspmu", + .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE, + .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, + .module = NULL, + .impl_init_ops = NULL, + }, + {0} }; diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h index a30c8372214c..2fe723555a6b 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.h +++ b/drivers/perf/arm_cspmu/arm_cspmu.h @@ -71,6 +71,7 @@ /* JEDEC-assigned JEP106 identification code */ #define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B +#define ARM_CSPMU_IMPL_ID_AMPERE 0xA16 struct arm_cspmu; -- 2.40.1