From e3d4939267925ab66f39123744ffb4bc74a13149 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Thu, 28 Sep 2017 14:03:33 +0100 Subject: ACPI/IORT: Improve functions return type/storage class specifier indentation Some functions definition indentations are using a style that is frowned upon with return value type/storage class specifier in a separate line. Reindent the function definitions to fix them. Signed-off-by: Lorenzo Pieralisi Acked-by: Hanjun Guo Cc: Hanjun Guo Cc: Sudeep Holla --- include/linux/acpi_iort.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 8d3f0bf80379..2f7a29242b87 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -49,8 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size) { } -static inline -const struct iommu_ops *iort_iommu_configure(struct device *dev) +static inline const struct iommu_ops *iort_iommu_configure( + struct device *dev) { return NULL; } #endif -- cgit v1.2.3-71-gd317 From 2940bc4333707a05e69b3ffd737bda0dc0c3004f Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Thu, 19 Oct 2017 19:05:18 +0800 Subject: perf: hisi: Add support for HiSilicon SoC L3C PMU driver This patch adds support for L3C PMU driver in HiSilicon SoC chip, Each L3C has own control, counter and interrupt registers and is an separate PMU. For each L3C PMU, it has 8-programable counters and each counter is free-running. Interrupt is supported to handle counter (48-bits) overflow. Acked-by: Mark Rutland Reviewed-by: Jonathan Cameron Signed-off-by: Shaokun Zhang Signed-off-by: Anurup M Signed-off-by: Will Deacon --- drivers/perf/hisilicon/Makefile | 2 +- drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c | 463 +++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 3 files changed, 465 insertions(+), 1 deletion(-) create mode 100644 drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c (limited to 'include/linux') diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 2783bb31e72b..4a3d3e6002a6 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -1 +1 @@ -obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o +obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c new file mode 100644 index 000000000000..0bde5d919b2e --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -0,0 +1,463 @@ +/* + * HiSilicon SoC L3C uncore Hardware event counters support + * + * Copyright (C) 2017 Hisilicon Limited + * Author: Anurup M + * Shaokun Zhang + * + * This code is based on the uncore PMUs like arm-cci and arm-ccn. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hisi_uncore_pmu.h" + +/* L3C register definition */ +#define L3C_PERF_CTRL 0x0408 +#define L3C_INT_MASK 0x0800 +#define L3C_INT_STATUS 0x0808 +#define L3C_INT_CLEAR 0x080c +#define L3C_EVENT_CTRL 0x1c00 +#define L3C_EVENT_TYPE0 0x1d00 +/* + * Each counter is 48-bits and [48:63] are reserved + * which are Read-As-Zero and Writes-Ignored. + */ +#define L3C_CNTR0_LOWER 0x1e00 + +/* L3C has 8-counters */ +#define L3C_NR_COUNTERS 0x8 + +#define L3C_PERF_CTRL_EN 0x20000 +#define L3C_EVTYPE_NONE 0xff + +/* + * Select the counter register offset using the counter index + */ +static u32 hisi_l3c_pmu_get_counter_offset(int cntr_idx) +{ + return (L3C_CNTR0_LOWER + (cntr_idx * 8)); +} + +static u64 hisi_l3c_pmu_read_counter(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) { + dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx); + return 0; + } + + /* Read 64-bits and the upper 16 bits are RAZ */ + return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx)); +} + +static void hisi_l3c_pmu_write_counter(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc, u64 val) +{ + u32 idx = hwc->idx; + + if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) { + dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx); + return; + } + + /* Write 64-bits and the upper 16 bits are WI */ + writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx)); +} + +static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx, + u32 type) +{ + u32 reg, reg_idx, shift, val; + + /* + * Select the appropriate event select register(L3C_EVENT_TYPE0/1). + * There are 2 event select registers for the 8 hardware counters. + * Event code is 8-bits and for the former 4 hardware counters, + * L3C_EVENT_TYPE0 is chosen. For the latter 4 hardware counters, + * L3C_EVENT_TYPE1 is chosen. + */ + reg = L3C_EVENT_TYPE0 + (idx / 4) * 4; + reg_idx = idx % 4; + shift = 8 * reg_idx; + + /* Write event code to L3C_EVENT_TYPEx Register */ + val = readl(l3c_pmu->base + reg); + val &= ~(L3C_EVTYPE_NONE << shift); + val |= (type << shift); + writel(val, l3c_pmu->base + reg); +} + +static void hisi_l3c_pmu_start_counters(struct hisi_pmu *l3c_pmu) +{ + u32 val; + + /* + * Set perf_enable bit in L3C_PERF_CTRL register to start counting + * for all enabled counters. + */ + val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val |= L3C_PERF_CTRL_EN; + writel(val, l3c_pmu->base + L3C_PERF_CTRL); +} + +static void hisi_l3c_pmu_stop_counters(struct hisi_pmu *l3c_pmu) +{ + u32 val; + + /* + * Clear perf_enable bit in L3C_PERF_CTRL register to stop counting + * for all enabled counters. + */ + val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val &= ~(L3C_PERF_CTRL_EN); + writel(val, l3c_pmu->base + L3C_PERF_CTRL); +} + +static void hisi_l3c_pmu_enable_counter(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Enable counter index in L3C_EVENT_CTRL register */ + val = readl(l3c_pmu->base + L3C_EVENT_CTRL); + val |= (1 << hwc->idx); + writel(val, l3c_pmu->base + L3C_EVENT_CTRL); +} + +static void hisi_l3c_pmu_disable_counter(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Clear counter index in L3C_EVENT_CTRL register */ + val = readl(l3c_pmu->base + L3C_EVENT_CTRL); + val &= ~(1 << hwc->idx); + writel(val, l3c_pmu->base + L3C_EVENT_CTRL); +} + +static void hisi_l3c_pmu_enable_counter_int(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + val = readl(l3c_pmu->base + L3C_INT_MASK); + /* Write 0 to enable interrupt */ + val &= ~(1 << hwc->idx); + writel(val, l3c_pmu->base + L3C_INT_MASK); +} + +static void hisi_l3c_pmu_disable_counter_int(struct hisi_pmu *l3c_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + val = readl(l3c_pmu->base + L3C_INT_MASK); + /* Write 1 to mask interrupt */ + val |= (1 << hwc->idx); + writel(val, l3c_pmu->base + L3C_INT_MASK); +} + +static irqreturn_t hisi_l3c_pmu_isr(int irq, void *dev_id) +{ + struct hisi_pmu *l3c_pmu = dev_id; + struct perf_event *event; + unsigned long overflown; + int idx; + + /* Read L3C_INT_STATUS register */ + overflown = readl(l3c_pmu->base + L3C_INT_STATUS); + if (!overflown) + return IRQ_NONE; + + /* + * Find the counter index which overflowed if the bit was set + * and handle it. + */ + for_each_set_bit(idx, &overflown, L3C_NR_COUNTERS) { + /* Write 1 to clear the IRQ status flag */ + writel((1 << idx), l3c_pmu->base + L3C_INT_CLEAR); + + /* Get the corresponding event struct */ + event = l3c_pmu->pmu_events.hw_events[idx]; + if (!event) + continue; + + hisi_uncore_pmu_event_update(event); + hisi_uncore_pmu_set_event_period(event); + } + + return IRQ_HANDLED; +} + +static int hisi_l3c_pmu_init_irq(struct hisi_pmu *l3c_pmu, + struct platform_device *pdev) +{ + int irq, ret; + + /* Read and init IRQ */ + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "L3C PMU get irq fail; irq:%d\n", irq); + return irq; + } + + ret = devm_request_irq(&pdev->dev, irq, hisi_l3c_pmu_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, + dev_name(&pdev->dev), l3c_pmu); + if (ret < 0) { + dev_err(&pdev->dev, + "Fail to request IRQ:%d ret:%d\n", irq, ret); + return ret; + } + + l3c_pmu->irq = irq; + + return 0; +} + +static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = { + { "HISI0213", }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match); + +static int hisi_l3c_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *l3c_pmu) +{ + unsigned long long id; + struct resource *res; + acpi_status status; + + status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), + "_UID", NULL, &id); + if (ACPI_FAILURE(status)) + return -EINVAL; + + l3c_pmu->index_id = id; + + /* + * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while + * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1]. + */ + if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", + &l3c_pmu->sccl_id)) { + dev_err(&pdev->dev, "Can not read l3c sccl-id!\n"); + return -EINVAL; + } + + if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id", + &l3c_pmu->ccl_id)) { + dev_err(&pdev->dev, "Can not read l3c ccl-id!\n"); + return -EINVAL; + } + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + l3c_pmu->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(l3c_pmu->base)) { + dev_err(&pdev->dev, "ioremap failed for l3c_pmu resource\n"); + return PTR_ERR(l3c_pmu->base); + } + + return 0; +} + +static struct attribute *hisi_l3c_pmu_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), + NULL, +}; + +static const struct attribute_group hisi_l3c_pmu_format_group = { + .name = "format", + .attrs = hisi_l3c_pmu_format_attr, +}; + +static struct attribute *hisi_l3c_pmu_events_attr[] = { + HISI_PMU_EVENT_ATTR(rd_cpipe, 0x00), + HISI_PMU_EVENT_ATTR(wr_cpipe, 0x01), + HISI_PMU_EVENT_ATTR(rd_hit_cpipe, 0x02), + HISI_PMU_EVENT_ATTR(wr_hit_cpipe, 0x03), + HISI_PMU_EVENT_ATTR(victim_num, 0x04), + HISI_PMU_EVENT_ATTR(rd_spipe, 0x20), + HISI_PMU_EVENT_ATTR(wr_spipe, 0x21), + HISI_PMU_EVENT_ATTR(rd_hit_spipe, 0x22), + HISI_PMU_EVENT_ATTR(wr_hit_spipe, 0x23), + HISI_PMU_EVENT_ATTR(back_invalid, 0x29), + HISI_PMU_EVENT_ATTR(retry_cpu, 0x40), + HISI_PMU_EVENT_ATTR(retry_ring, 0x41), + HISI_PMU_EVENT_ATTR(prefetch_drop, 0x42), + NULL, +}; + +static const struct attribute_group hisi_l3c_pmu_events_group = { + .name = "events", + .attrs = hisi_l3c_pmu_events_attr, +}; + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static struct attribute *hisi_l3c_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group hisi_l3c_pmu_cpumask_attr_group = { + .attrs = hisi_l3c_pmu_cpumask_attrs, +}; + +static const struct attribute_group *hisi_l3c_pmu_attr_groups[] = { + &hisi_l3c_pmu_format_group, + &hisi_l3c_pmu_events_group, + &hisi_l3c_pmu_cpumask_attr_group, + NULL, +}; + +static const struct hisi_uncore_ops hisi_uncore_l3c_ops = { + .write_evtype = hisi_l3c_pmu_write_evtype, + .get_event_idx = hisi_uncore_pmu_get_event_idx, + .start_counters = hisi_l3c_pmu_start_counters, + .stop_counters = hisi_l3c_pmu_stop_counters, + .enable_counter = hisi_l3c_pmu_enable_counter, + .disable_counter = hisi_l3c_pmu_disable_counter, + .enable_counter_int = hisi_l3c_pmu_enable_counter_int, + .disable_counter_int = hisi_l3c_pmu_disable_counter_int, + .write_counter = hisi_l3c_pmu_write_counter, + .read_counter = hisi_l3c_pmu_read_counter, +}; + +static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev, + struct hisi_pmu *l3c_pmu) +{ + int ret; + + ret = hisi_l3c_pmu_init_data(pdev, l3c_pmu); + if (ret) + return ret; + + ret = hisi_l3c_pmu_init_irq(l3c_pmu, pdev); + if (ret) + return ret; + + l3c_pmu->num_counters = L3C_NR_COUNTERS; + l3c_pmu->counter_bits = 48; + l3c_pmu->ops = &hisi_uncore_l3c_ops; + l3c_pmu->dev = &pdev->dev; + l3c_pmu->on_cpu = -1; + l3c_pmu->check_event = 0x59; + + return 0; +} + +static int hisi_l3c_pmu_probe(struct platform_device *pdev) +{ + struct hisi_pmu *l3c_pmu; + char *name; + int ret; + + l3c_pmu = devm_kzalloc(&pdev->dev, sizeof(*l3c_pmu), GFP_KERNEL); + if (!l3c_pmu) + return -ENOMEM; + + platform_set_drvdata(pdev, l3c_pmu); + + ret = hisi_l3c_pmu_dev_probe(pdev, l3c_pmu); + if (ret) + return ret; + + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, + &l3c_pmu->node); + if (ret) { + dev_err(&pdev->dev, "Error %d registering hotplug\n", ret); + return ret; + } + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u", + l3c_pmu->sccl_id, l3c_pmu->index_id); + l3c_pmu->pmu = (struct pmu) { + .name = name, + .task_ctx_nr = perf_invalid_context, + .event_init = hisi_uncore_pmu_event_init, + .pmu_enable = hisi_uncore_pmu_enable, + .pmu_disable = hisi_uncore_pmu_disable, + .add = hisi_uncore_pmu_add, + .del = hisi_uncore_pmu_del, + .start = hisi_uncore_pmu_start, + .stop = hisi_uncore_pmu_stop, + .read = hisi_uncore_pmu_read, + .attr_groups = hisi_l3c_pmu_attr_groups, + }; + + ret = perf_pmu_register(&l3c_pmu->pmu, name, -1); + if (ret) { + dev_err(l3c_pmu->dev, "L3C PMU register failed!\n"); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, + &l3c_pmu->node); + } + + return ret; +} + +static int hisi_l3c_pmu_remove(struct platform_device *pdev) +{ + struct hisi_pmu *l3c_pmu = platform_get_drvdata(pdev); + + perf_pmu_unregister(&l3c_pmu->pmu); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, + &l3c_pmu->node); + + return 0; +} + +static struct platform_driver hisi_l3c_pmu_driver = { + .driver = { + .name = "hisi_l3c_pmu", + .acpi_match_table = ACPI_PTR(hisi_l3c_pmu_acpi_match), + }, + .probe = hisi_l3c_pmu_probe, + .remove = hisi_l3c_pmu_remove, +}; + +static int __init hisi_l3c_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, + "AP_PERF_ARM_HISI_L3_ONLINE", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret) { + pr_err("L3C PMU: Error setup hotplug, ret = %d\n", ret); + return ret; + } + + ret = platform_driver_register(&hisi_l3c_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE); + + return ret; +} +module_init(hisi_l3c_pmu_module_init); + +static void __exit hisi_l3c_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_l3c_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE); +} +module_exit(hisi_l3c_pmu_module_exit); + +MODULE_DESCRIPTION("HiSilicon SoC L3C uncore PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Anurup M "); +MODULE_AUTHOR("Shaokun Zhang "); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6d508767e144..9621efdbb3bd 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -153,6 +153,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, -- cgit v1.2.3-71-gd317 From 2bab3cf9104c5ab80a1b9c706d81d997548401e4 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Thu, 19 Oct 2017 19:05:19 +0800 Subject: perf: hisi: Add support for HiSilicon SoC HHA PMU driver L3 cache coherence is maintained by Hydra Home Agent (HHA) in HiSilicon SoC. This patch adds support for HHA PMU driver, Each HHA has own control, counter and interrupt registers and is an separate PMU. For each HHA PMU, it has 16-programable counters and each counter is free-running. Interrupt is supported to handle counter (48-bits) overflow. Acked-by: Mark Rutland Reviewed-by: Jonathan Cameron Signed-off-by: Shaokun Zhang Signed-off-by: Anurup M Signed-off-by: Will Deacon --- drivers/perf/hisilicon/Makefile | 2 +- drivers/perf/hisilicon/hisi_uncore_hha_pmu.c | 473 +++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 3 files changed, 475 insertions(+), 1 deletion(-) create mode 100644 drivers/perf/hisilicon/hisi_uncore_hha_pmu.c (limited to 'include/linux') diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 4a3d3e6002a6..a72afe84d034 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -1 +1 @@ -obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o +obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c new file mode 100644 index 000000000000..443906e0aff3 --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -0,0 +1,473 @@ +/* + * HiSilicon SoC HHA uncore Hardware event counters support + * + * Copyright (C) 2017 Hisilicon Limited + * Author: Shaokun Zhang + * Anurup M + * + * This code is based on the uncore PMUs like arm-cci and arm-ccn. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hisi_uncore_pmu.h" + +/* HHA register definition */ +#define HHA_INT_MASK 0x0804 +#define HHA_INT_STATUS 0x0808 +#define HHA_INT_CLEAR 0x080C +#define HHA_PERF_CTRL 0x1E00 +#define HHA_EVENT_CTRL 0x1E04 +#define HHA_EVENT_TYPE0 0x1E80 +/* + * Each counter is 48-bits and [48:63] are reserved + * which are Read-As-Zero and Writes-Ignored. + */ +#define HHA_CNT0_LOWER 0x1F00 + +/* HHA has 16-counters */ +#define HHA_NR_COUNTERS 0x10 + +#define HHA_PERF_CTRL_EN 0x1 +#define HHA_EVTYPE_NONE 0xff + +/* + * Select the counter register offset using the counter index + * each counter is 48-bits. + */ +static u32 hisi_hha_pmu_get_counter_offset(int cntr_idx) +{ + return (HHA_CNT0_LOWER + (cntr_idx * 8)); +} + +static u64 hisi_hha_pmu_read_counter(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) { + dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx); + return 0; + } + + /* Read 64 bits and like L3C, top 16 bits are RAZ */ + return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx)); +} + +static void hisi_hha_pmu_write_counter(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc, u64 val) +{ + u32 idx = hwc->idx; + + if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) { + dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx); + return; + } + + /* Write 64 bits and like L3C, top 16 bits are WI */ + writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx)); +} + +static void hisi_hha_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx, + u32 type) +{ + u32 reg, reg_idx, shift, val; + + /* + * Select the appropriate event select register(HHA_EVENT_TYPEx). + * There are 4 event select registers for the 16 hardware counters. + * Event code is 8-bits and for the first 4 hardware counters, + * HHA_EVENT_TYPE0 is chosen. For the next 4 hardware counters, + * HHA_EVENT_TYPE1 is chosen and so on. + */ + reg = HHA_EVENT_TYPE0 + 4 * (idx / 4); + reg_idx = idx % 4; + shift = 8 * reg_idx; + + /* Write event code to HHA_EVENT_TYPEx register */ + val = readl(hha_pmu->base + reg); + val &= ~(HHA_EVTYPE_NONE << shift); + val |= (type << shift); + writel(val, hha_pmu->base + reg); +} + +static void hisi_hha_pmu_start_counters(struct hisi_pmu *hha_pmu) +{ + u32 val; + + /* + * Set perf_enable bit in HHA_PERF_CTRL to start event + * counting for all enabled counters. + */ + val = readl(hha_pmu->base + HHA_PERF_CTRL); + val |= HHA_PERF_CTRL_EN; + writel(val, hha_pmu->base + HHA_PERF_CTRL); +} + +static void hisi_hha_pmu_stop_counters(struct hisi_pmu *hha_pmu) +{ + u32 val; + + /* + * Clear perf_enable bit in HHA_PERF_CTRL to stop event + * counting for all enabled counters. + */ + val = readl(hha_pmu->base + HHA_PERF_CTRL); + val &= ~(HHA_PERF_CTRL_EN); + writel(val, hha_pmu->base + HHA_PERF_CTRL); +} + +static void hisi_hha_pmu_enable_counter(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Enable counter index in HHA_EVENT_CTRL register */ + val = readl(hha_pmu->base + HHA_EVENT_CTRL); + val |= (1 << hwc->idx); + writel(val, hha_pmu->base + HHA_EVENT_CTRL); +} + +static void hisi_hha_pmu_disable_counter(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Clear counter index in HHA_EVENT_CTRL register */ + val = readl(hha_pmu->base + HHA_EVENT_CTRL); + val &= ~(1 << hwc->idx); + writel(val, hha_pmu->base + HHA_EVENT_CTRL); +} + +static void hisi_hha_pmu_enable_counter_int(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 0 to enable interrupt */ + val = readl(hha_pmu->base + HHA_INT_MASK); + val &= ~(1 << hwc->idx); + writel(val, hha_pmu->base + HHA_INT_MASK); +} + +static void hisi_hha_pmu_disable_counter_int(struct hisi_pmu *hha_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 1 to mask interrupt */ + val = readl(hha_pmu->base + HHA_INT_MASK); + val |= (1 << hwc->idx); + writel(val, hha_pmu->base + HHA_INT_MASK); +} + +static irqreturn_t hisi_hha_pmu_isr(int irq, void *dev_id) +{ + struct hisi_pmu *hha_pmu = dev_id; + struct perf_event *event; + unsigned long overflown; + int idx; + + /* Read HHA_INT_STATUS register */ + overflown = readl(hha_pmu->base + HHA_INT_STATUS); + if (!overflown) + return IRQ_NONE; + + /* + * Find the counter index which overflowed if the bit was set + * and handle it + */ + for_each_set_bit(idx, &overflown, HHA_NR_COUNTERS) { + /* Write 1 to clear the IRQ status flag */ + writel((1 << idx), hha_pmu->base + HHA_INT_CLEAR); + + /* Get the corresponding event struct */ + event = hha_pmu->pmu_events.hw_events[idx]; + if (!event) + continue; + + hisi_uncore_pmu_event_update(event); + hisi_uncore_pmu_set_event_period(event); + } + + return IRQ_HANDLED; +} + +static int hisi_hha_pmu_init_irq(struct hisi_pmu *hha_pmu, + struct platform_device *pdev) +{ + int irq, ret; + + /* Read and init IRQ */ + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "HHA PMU get irq fail; irq:%d\n", irq); + return irq; + } + + ret = devm_request_irq(&pdev->dev, irq, hisi_hha_pmu_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, + dev_name(&pdev->dev), hha_pmu); + if (ret < 0) { + dev_err(&pdev->dev, + "Fail to request IRQ:%d ret:%d\n", irq, ret); + return ret; + } + + hha_pmu->irq = irq; + + return 0; +} + +static const struct acpi_device_id hisi_hha_pmu_acpi_match[] = { + { "HISI0243", }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, hisi_hha_pmu_acpi_match); + +static int hisi_hha_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *hha_pmu) +{ + unsigned long long id; + struct resource *res; + acpi_status status; + + status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), + "_UID", NULL, &id); + if (ACPI_FAILURE(status)) + return -EINVAL; + + hha_pmu->index_id = id; + + /* + * Use SCCL_ID and UID to identify the HHA PMU, while + * SCCL_ID is in MPIDR[aff2]. + */ + if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", + &hha_pmu->sccl_id)) { + dev_err(&pdev->dev, "Can not read hha sccl-id!\n"); + return -EINVAL; + } + /* HHA PMUs only share the same SCCL */ + hha_pmu->ccl_id = -1; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + hha_pmu->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(hha_pmu->base)) { + dev_err(&pdev->dev, "ioremap failed for hha_pmu resource\n"); + return PTR_ERR(hha_pmu->base); + } + + return 0; +} + +static struct attribute *hisi_hha_pmu_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), + NULL, +}; + +static const struct attribute_group hisi_hha_pmu_format_group = { + .name = "format", + .attrs = hisi_hha_pmu_format_attr, +}; + +static struct attribute *hisi_hha_pmu_events_attr[] = { + HISI_PMU_EVENT_ATTR(rx_ops_num, 0x00), + HISI_PMU_EVENT_ATTR(rx_outer, 0x01), + HISI_PMU_EVENT_ATTR(rx_sccl, 0x02), + HISI_PMU_EVENT_ATTR(rx_ccix, 0x03), + HISI_PMU_EVENT_ATTR(rx_wbi, 0x04), + HISI_PMU_EVENT_ATTR(rx_wbip, 0x05), + HISI_PMU_EVENT_ATTR(rx_wtistash, 0x11), + HISI_PMU_EVENT_ATTR(rd_ddr_64b, 0x1c), + HISI_PMU_EVENT_ATTR(wr_dr_64b, 0x1d), + HISI_PMU_EVENT_ATTR(rd_ddr_128b, 0x1e), + HISI_PMU_EVENT_ATTR(wr_ddr_128b, 0x1f), + HISI_PMU_EVENT_ATTR(spill_num, 0x20), + HISI_PMU_EVENT_ATTR(spill_success, 0x21), + HISI_PMU_EVENT_ATTR(bi_num, 0x23), + HISI_PMU_EVENT_ATTR(mediated_num, 0x32), + HISI_PMU_EVENT_ATTR(tx_snp_num, 0x33), + HISI_PMU_EVENT_ATTR(tx_snp_outer, 0x34), + HISI_PMU_EVENT_ATTR(tx_snp_ccix, 0x35), + HISI_PMU_EVENT_ATTR(rx_snprspdata, 0x38), + HISI_PMU_EVENT_ATTR(rx_snprsp_outer, 0x3c), + HISI_PMU_EVENT_ATTR(sdir-lookup, 0x40), + HISI_PMU_EVENT_ATTR(edir-lookup, 0x41), + HISI_PMU_EVENT_ATTR(sdir-hit, 0x42), + HISI_PMU_EVENT_ATTR(edir-hit, 0x43), + HISI_PMU_EVENT_ATTR(sdir-home-migrate, 0x4c), + HISI_PMU_EVENT_ATTR(edir-home-migrate, 0x4d), + NULL, +}; + +static const struct attribute_group hisi_hha_pmu_events_group = { + .name = "events", + .attrs = hisi_hha_pmu_events_attr, +}; + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static struct attribute *hisi_hha_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group hisi_hha_pmu_cpumask_attr_group = { + .attrs = hisi_hha_pmu_cpumask_attrs, +}; + +static const struct attribute_group *hisi_hha_pmu_attr_groups[] = { + &hisi_hha_pmu_format_group, + &hisi_hha_pmu_events_group, + &hisi_hha_pmu_cpumask_attr_group, + NULL, +}; + +static const struct hisi_uncore_ops hisi_uncore_hha_ops = { + .write_evtype = hisi_hha_pmu_write_evtype, + .get_event_idx = hisi_uncore_pmu_get_event_idx, + .start_counters = hisi_hha_pmu_start_counters, + .stop_counters = hisi_hha_pmu_stop_counters, + .enable_counter = hisi_hha_pmu_enable_counter, + .disable_counter = hisi_hha_pmu_disable_counter, + .enable_counter_int = hisi_hha_pmu_enable_counter_int, + .disable_counter_int = hisi_hha_pmu_disable_counter_int, + .write_counter = hisi_hha_pmu_write_counter, + .read_counter = hisi_hha_pmu_read_counter, +}; + +static int hisi_hha_pmu_dev_probe(struct platform_device *pdev, + struct hisi_pmu *hha_pmu) +{ + int ret; + + ret = hisi_hha_pmu_init_data(pdev, hha_pmu); + if (ret) + return ret; + + ret = hisi_hha_pmu_init_irq(hha_pmu, pdev); + if (ret) + return ret; + + hha_pmu->num_counters = HHA_NR_COUNTERS; + hha_pmu->counter_bits = 48; + hha_pmu->ops = &hisi_uncore_hha_ops; + hha_pmu->dev = &pdev->dev; + hha_pmu->on_cpu = -1; + hha_pmu->check_event = 0x65; + + return 0; +} + +static int hisi_hha_pmu_probe(struct platform_device *pdev) +{ + struct hisi_pmu *hha_pmu; + char *name; + int ret; + + hha_pmu = devm_kzalloc(&pdev->dev, sizeof(*hha_pmu), GFP_KERNEL); + if (!hha_pmu) + return -ENOMEM; + + platform_set_drvdata(pdev, hha_pmu); + + ret = hisi_hha_pmu_dev_probe(pdev, hha_pmu); + if (ret) + return ret; + + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, + &hha_pmu->node); + if (ret) { + dev_err(&pdev->dev, "Error %d registering hotplug\n", ret); + return ret; + } + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u", + hha_pmu->sccl_id, hha_pmu->index_id); + hha_pmu->pmu = (struct pmu) { + .name = name, + .task_ctx_nr = perf_invalid_context, + .event_init = hisi_uncore_pmu_event_init, + .pmu_enable = hisi_uncore_pmu_enable, + .pmu_disable = hisi_uncore_pmu_disable, + .add = hisi_uncore_pmu_add, + .del = hisi_uncore_pmu_del, + .start = hisi_uncore_pmu_start, + .stop = hisi_uncore_pmu_stop, + .read = hisi_uncore_pmu_read, + .attr_groups = hisi_hha_pmu_attr_groups, + }; + + ret = perf_pmu_register(&hha_pmu->pmu, name, -1); + if (ret) { + dev_err(hha_pmu->dev, "HHA PMU register failed!\n"); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, + &hha_pmu->node); + } + + return ret; +} + +static int hisi_hha_pmu_remove(struct platform_device *pdev) +{ + struct hisi_pmu *hha_pmu = platform_get_drvdata(pdev); + + perf_pmu_unregister(&hha_pmu->pmu); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, + &hha_pmu->node); + + return 0; +} + +static struct platform_driver hisi_hha_pmu_driver = { + .driver = { + .name = "hisi_hha_pmu", + .acpi_match_table = ACPI_PTR(hisi_hha_pmu_acpi_match), + }, + .probe = hisi_hha_pmu_probe, + .remove = hisi_hha_pmu_remove, +}; + +static int __init hisi_hha_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, + "AP_PERF_ARM_HISI_HHA_ONLINE", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret) { + pr_err("HHA PMU: Error setup hotplug, ret = %d;\n", ret); + return ret; + } + + ret = platform_driver_register(&hisi_hha_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE); + + return ret; +} +module_init(hisi_hha_pmu_module_init); + +static void __exit hisi_hha_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_hha_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE); +} +module_exit(hisi_hha_pmu_module_exit); + +MODULE_DESCRIPTION("HiSilicon SoC HHA uncore PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Shaokun Zhang "); +MODULE_AUTHOR("Anurup M "); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 9621efdbb3bd..cd63c52e7d93 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -153,6 +153,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, -- cgit v1.2.3-71-gd317 From 904dcf03f086a2e3b9d1e02cb57c43ea2e588c8c Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Thu, 19 Oct 2017 19:05:20 +0800 Subject: perf: hisi: Add support for HiSilicon SoC DDRC PMU driver This patch adds support for DDRC PMU driver in HiSilicon SoC chip, Each DDRC has own control, counter and interrupt registers and is an separate PMU. For each DDRC PMU, it has 8-fixed-purpose counters which have been mapped to 8-events by hardware, it assumes that counter index is equal to event code (0 - 7) in DDRC PMU driver. Interrupt is supported to handle counter (32-bits) overflow. Acked-by: Mark Rutland Reviewed-by: Jonathan Cameron Signed-off-by: Shaokun Zhang Signed-off-by: Anurup M Signed-off-by: Will Deacon --- drivers/perf/hisilicon/Makefile | 2 +- drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c | 463 ++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 3 files changed, 465 insertions(+), 1 deletion(-) create mode 100644 drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c (limited to 'include/linux') diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index a72afe84d034..2621d51ae87a 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -1 +1 @@ -obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o +obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c new file mode 100644 index 000000000000..1b10ea05a914 --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -0,0 +1,463 @@ +/* + * HiSilicon SoC DDRC uncore Hardware event counters support + * + * Copyright (C) 2017 Hisilicon Limited + * Author: Shaokun Zhang + * Anurup M + * + * This code is based on the uncore PMUs like arm-cci and arm-ccn. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hisi_uncore_pmu.h" + +/* DDRC register definition */ +#define DDRC_PERF_CTRL 0x010 +#define DDRC_FLUX_WR 0x380 +#define DDRC_FLUX_RD 0x384 +#define DDRC_FLUX_WCMD 0x388 +#define DDRC_FLUX_RCMD 0x38c +#define DDRC_PRE_CMD 0x3c0 +#define DDRC_ACT_CMD 0x3c4 +#define DDRC_BNK_CHG 0x3c8 +#define DDRC_RNK_CHG 0x3cc +#define DDRC_EVENT_CTRL 0x6C0 +#define DDRC_INT_MASK 0x6c8 +#define DDRC_INT_STATUS 0x6cc +#define DDRC_INT_CLEAR 0x6d0 + +/* DDRC has 8-counters */ +#define DDRC_NR_COUNTERS 0x8 +#define DDRC_PERF_CTRL_EN 0x2 + +/* + * For DDRC PMU, there are eight-events and every event has been mapped + * to fixed-purpose counters which register offset is not consistent. + * Therefore there is no write event type and we assume that event + * code (0 to 7) is equal to counter index in PMU driver. + */ +#define GET_DDRC_EVENTID(hwc) (hwc->config_base & 0x7) + +static const u32 ddrc_reg_off[] = { + DDRC_FLUX_WR, DDRC_FLUX_RD, DDRC_FLUX_WCMD, DDRC_FLUX_RCMD, + DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_BNK_CHG, DDRC_RNK_CHG +}; + +/* + * Select the counter register offset using the counter index. + * In DDRC there are no programmable counter, the count + * is readed form the statistics counter register itself. + */ +static u32 hisi_ddrc_pmu_get_counter_offset(int cntr_idx) +{ + return ddrc_reg_off[cntr_idx]; +} + +static u64 hisi_ddrc_pmu_read_counter(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) +{ + /* Use event code as counter index */ + u32 idx = GET_DDRC_EVENTID(hwc); + + if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) { + dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx); + return 0; + } + + return readl(ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx)); +} + +static void hisi_ddrc_pmu_write_counter(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + u32 idx = GET_DDRC_EVENTID(hwc); + + if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) { + dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx); + return; + } + + writel((u32)val, + ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx)); +} + +/* + * For DDRC PMU, event has been mapped to fixed-purpose counter by hardware, + * so there is no need to write event type. + */ +static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx, + u32 type) +{ +} + +static void hisi_ddrc_pmu_start_counters(struct hisi_pmu *ddrc_pmu) +{ + u32 val; + + /* Set perf_enable in DDRC_PERF_CTRL to start event counting */ + val = readl(ddrc_pmu->base + DDRC_PERF_CTRL); + val |= DDRC_PERF_CTRL_EN; + writel(val, ddrc_pmu->base + DDRC_PERF_CTRL); +} + +static void hisi_ddrc_pmu_stop_counters(struct hisi_pmu *ddrc_pmu) +{ + u32 val; + + /* Clear perf_enable in DDRC_PERF_CTRL to stop event counting */ + val = readl(ddrc_pmu->base + DDRC_PERF_CTRL); + val &= ~DDRC_PERF_CTRL_EN; + writel(val, ddrc_pmu->base + DDRC_PERF_CTRL); +} + +static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Set counter index(event code) in DDRC_EVENT_CTRL register */ + val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL); + val |= (1 << GET_DDRC_EVENTID(hwc)); + writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL); +} + +static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Clear counter index(event code) in DDRC_EVENT_CTRL register */ + val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL); + val &= ~(1 << GET_DDRC_EVENTID(hwc)); + writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL); +} + +static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event) +{ + struct hisi_pmu *ddrc_pmu = to_hisi_pmu(event->pmu); + unsigned long *used_mask = ddrc_pmu->pmu_events.used_mask; + struct hw_perf_event *hwc = &event->hw; + /* For DDRC PMU, we use event code as counter index */ + int idx = GET_DDRC_EVENTID(hwc); + + if (test_bit(idx, used_mask)) + return -EAGAIN; + + set_bit(idx, used_mask); + + return idx; +} + +static void hisi_ddrc_pmu_enable_counter_int(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 0 to enable interrupt */ + val = readl(ddrc_pmu->base + DDRC_INT_MASK); + val &= ~(1 << GET_DDRC_EVENTID(hwc)); + writel(val, ddrc_pmu->base + DDRC_INT_MASK); +} + +static void hisi_ddrc_pmu_disable_counter_int(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) +{ + u32 val; + + /* Write 1 to mask interrupt */ + val = readl(ddrc_pmu->base + DDRC_INT_MASK); + val |= (1 << GET_DDRC_EVENTID(hwc)); + writel(val, ddrc_pmu->base + DDRC_INT_MASK); +} + +static irqreturn_t hisi_ddrc_pmu_isr(int irq, void *dev_id) +{ + struct hisi_pmu *ddrc_pmu = dev_id; + struct perf_event *event; + unsigned long overflown; + int idx; + + /* Read the DDRC_INT_STATUS register */ + overflown = readl(ddrc_pmu->base + DDRC_INT_STATUS); + if (!overflown) + return IRQ_NONE; + + /* + * Find the counter index which overflowed if the bit was set + * and handle it + */ + for_each_set_bit(idx, &overflown, DDRC_NR_COUNTERS) { + /* Write 1 to clear the IRQ status flag */ + writel((1 << idx), ddrc_pmu->base + DDRC_INT_CLEAR); + + /* Get the corresponding event struct */ + event = ddrc_pmu->pmu_events.hw_events[idx]; + if (!event) + continue; + + hisi_uncore_pmu_event_update(event); + hisi_uncore_pmu_set_event_period(event); + } + + return IRQ_HANDLED; +} + +static int hisi_ddrc_pmu_init_irq(struct hisi_pmu *ddrc_pmu, + struct platform_device *pdev) +{ + int irq, ret; + + /* Read and init IRQ */ + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "DDRC PMU get irq fail; irq:%d\n", irq); + return irq; + } + + ret = devm_request_irq(&pdev->dev, irq, hisi_ddrc_pmu_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, + dev_name(&pdev->dev), ddrc_pmu); + if (ret < 0) { + dev_err(&pdev->dev, + "Fail to request IRQ:%d ret:%d\n", irq, ret); + return ret; + } + + ddrc_pmu->irq = irq; + + return 0; +} + +static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = { + { "HISI0233", }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match); + +static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *ddrc_pmu) +{ + struct resource *res; + + /* + * Use the SCCL_ID and DDRC channel ID to identify the + * DDRC PMU, while SCCL_ID is in MPIDR[aff2]. + */ + if (device_property_read_u32(&pdev->dev, "hisilicon,ch-id", + &ddrc_pmu->index_id)) { + dev_err(&pdev->dev, "Can not read ddrc channel-id!\n"); + return -EINVAL; + } + + if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", + &ddrc_pmu->sccl_id)) { + dev_err(&pdev->dev, "Can not read ddrc sccl-id!\n"); + return -EINVAL; + } + /* DDRC PMUs only share the same SCCL */ + ddrc_pmu->ccl_id = -1; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ddrc_pmu->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ddrc_pmu->base)) { + dev_err(&pdev->dev, "ioremap failed for ddrc_pmu resource\n"); + return PTR_ERR(ddrc_pmu->base); + } + + return 0; +} + +static struct attribute *hisi_ddrc_pmu_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-4"), + NULL, +}; + +static const struct attribute_group hisi_ddrc_pmu_format_group = { + .name = "format", + .attrs = hisi_ddrc_pmu_format_attr, +}; + +static struct attribute *hisi_ddrc_pmu_events_attr[] = { + HISI_PMU_EVENT_ATTR(flux_wr, 0x00), + HISI_PMU_EVENT_ATTR(flux_rd, 0x01), + HISI_PMU_EVENT_ATTR(flux_wcmd, 0x02), + HISI_PMU_EVENT_ATTR(flux_rcmd, 0x03), + HISI_PMU_EVENT_ATTR(pre_cmd, 0x04), + HISI_PMU_EVENT_ATTR(act_cmd, 0x05), + HISI_PMU_EVENT_ATTR(rnk_chg, 0x06), + HISI_PMU_EVENT_ATTR(rw_chg, 0x07), + NULL, +}; + +static const struct attribute_group hisi_ddrc_pmu_events_group = { + .name = "events", + .attrs = hisi_ddrc_pmu_events_attr, +}; + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static struct attribute *hisi_ddrc_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group hisi_ddrc_pmu_cpumask_attr_group = { + .attrs = hisi_ddrc_pmu_cpumask_attrs, +}; + +static const struct attribute_group *hisi_ddrc_pmu_attr_groups[] = { + &hisi_ddrc_pmu_format_group, + &hisi_ddrc_pmu_events_group, + &hisi_ddrc_pmu_cpumask_attr_group, + NULL, +}; + +static const struct hisi_uncore_ops hisi_uncore_ddrc_ops = { + .write_evtype = hisi_ddrc_pmu_write_evtype, + .get_event_idx = hisi_ddrc_pmu_get_event_idx, + .start_counters = hisi_ddrc_pmu_start_counters, + .stop_counters = hisi_ddrc_pmu_stop_counters, + .enable_counter = hisi_ddrc_pmu_enable_counter, + .disable_counter = hisi_ddrc_pmu_disable_counter, + .enable_counter_int = hisi_ddrc_pmu_enable_counter_int, + .disable_counter_int = hisi_ddrc_pmu_disable_counter_int, + .write_counter = hisi_ddrc_pmu_write_counter, + .read_counter = hisi_ddrc_pmu_read_counter, +}; + +static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev, + struct hisi_pmu *ddrc_pmu) +{ + int ret; + + ret = hisi_ddrc_pmu_init_data(pdev, ddrc_pmu); + if (ret) + return ret; + + ret = hisi_ddrc_pmu_init_irq(ddrc_pmu, pdev); + if (ret) + return ret; + + ddrc_pmu->num_counters = DDRC_NR_COUNTERS; + ddrc_pmu->counter_bits = 32; + ddrc_pmu->ops = &hisi_uncore_ddrc_ops; + ddrc_pmu->dev = &pdev->dev; + ddrc_pmu->on_cpu = -1; + ddrc_pmu->check_event = 7; + + return 0; +} + +static int hisi_ddrc_pmu_probe(struct platform_device *pdev) +{ + struct hisi_pmu *ddrc_pmu; + char *name; + int ret; + + ddrc_pmu = devm_kzalloc(&pdev->dev, sizeof(*ddrc_pmu), GFP_KERNEL); + if (!ddrc_pmu) + return -ENOMEM; + + platform_set_drvdata(pdev, ddrc_pmu); + + ret = hisi_ddrc_pmu_dev_probe(pdev, ddrc_pmu); + if (ret) + return ret; + + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, + &ddrc_pmu->node); + if (ret) { + dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret); + return ret; + } + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_ddrc%u", + ddrc_pmu->sccl_id, ddrc_pmu->index_id); + ddrc_pmu->pmu = (struct pmu) { + .name = name, + .task_ctx_nr = perf_invalid_context, + .event_init = hisi_uncore_pmu_event_init, + .pmu_enable = hisi_uncore_pmu_enable, + .pmu_disable = hisi_uncore_pmu_disable, + .add = hisi_uncore_pmu_add, + .del = hisi_uncore_pmu_del, + .start = hisi_uncore_pmu_start, + .stop = hisi_uncore_pmu_stop, + .read = hisi_uncore_pmu_read, + .attr_groups = hisi_ddrc_pmu_attr_groups, + }; + + ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1); + if (ret) { + dev_err(ddrc_pmu->dev, "DDRC PMU register failed!\n"); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, + &ddrc_pmu->node); + } + + return ret; +} + +static int hisi_ddrc_pmu_remove(struct platform_device *pdev) +{ + struct hisi_pmu *ddrc_pmu = platform_get_drvdata(pdev); + + perf_pmu_unregister(&ddrc_pmu->pmu); + cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, + &ddrc_pmu->node); + + return 0; +} + +static struct platform_driver hisi_ddrc_pmu_driver = { + .driver = { + .name = "hisi_ddrc_pmu", + .acpi_match_table = ACPI_PTR(hisi_ddrc_pmu_acpi_match), + }, + .probe = hisi_ddrc_pmu_probe, + .remove = hisi_ddrc_pmu_remove, +}; + +static int __init hisi_ddrc_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, + "AP_PERF_ARM_HISI_DDRC_ONLINE", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret) { + pr_err("DDRC PMU: setup hotplug, ret = %d\n", ret); + return ret; + } + + ret = platform_driver_register(&hisi_ddrc_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE); + + return ret; +} +module_init(hisi_ddrc_pmu_module_init); + +static void __exit hisi_ddrc_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_ddrc_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE); + +} +module_exit(hisi_ddrc_pmu_module_exit); + +MODULE_DESCRIPTION("HiSilicon SoC DDRC uncore PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Shaokun Zhang "); +MODULE_AUTHOR("Anurup M "); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index cd63c52e7d93..587006de6f82 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -153,6 +153,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, -- cgit v1.2.3-71-gd317 From 08395c7f4d9f5808b5754a0dbed969f378bde0c3 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Fri, 13 Oct 2017 12:26:44 +0100 Subject: irqdesc: Add function to identify percpu_devid irqs irq_is_percpu indicates whether an irq should only target a single cpu. PERCPU_DEVID flag indicates that an irq can be configured differently on each cpu it can target. Provide a function to check whether an irq is PERCPU_DEVID. Reviewed-by: Thomas Gleixner Reviewed-by: Marc Zyngier Signed-off-by: Will Deacon Signed-off-by: Julien Thierry --- include/linux/irqdesc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 3e90a094798d..93960cf36e23 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -244,6 +244,14 @@ static inline int irq_is_percpu(unsigned int irq) return desc->status_use_accessors & IRQ_PER_CPU; } +static inline int irq_is_percpu_devid(unsigned int irq) +{ + struct irq_desc *desc; + + desc = irq_to_desc(irq); + return desc->status_use_accessors & IRQ_PER_CPU_DEVID; +} + static inline void irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class) { -- cgit v1.2.3-71-gd317 From 27e64b4be4b863d884f3ec1686a2f744ae93a1b9 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 31 Oct 2017 15:50:53 +0000 Subject: regset: Add support for dynamically sized regsets Currently the regset API doesn't allow for the possibility that regsets (or at least, the amount of meaningful data in a regset) may change in size. In particular, this results in useless padding being added to coredumps if a regset's current size is smaller than its theoretical maximum size. This patch adds a get_size() function to struct user_regset. Individual regset implementations can implement this function to return the current size of the regset data. A regset_size() function is added to provide callers with an abstract interface for determining the size of a regset without needing to know whether the regset is dynamically sized or not. The only affected user of this interface is the ELF coredump code: This patch ports ELF coredump to dump regsets with their actual size in the coredump. This has no effect except for new regsets that are dynamically sized and provide a get_size() implementation. Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Cc: Oleg Nesterov Cc: Alexander Viro Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Dmitry Safonov Cc: H. J. Lu Signed-off-by: Will Deacon --- fs/binfmt_elf.c | 10 ++++---- include/linux/regset.h | 67 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 65 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 73b01e474fdc..c697882b3aba 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1699,7 +1699,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, long signr, size_t *total) { unsigned int i; - unsigned int regset_size = view->regsets[0].n * view->regsets[0].size; + unsigned int regset0_size = regset_size(t->task, &view->regsets[0]); /* * NT_PRSTATUS is the one special case, because the regset data @@ -1708,11 +1708,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, * We assume that regset 0 is NT_PRSTATUS. */ fill_prstatus(&t->prstatus, t->task, signr); - (void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset_size, + (void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset0_size, &t->prstatus.pr_reg, NULL); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - PRSTATUS_SIZE(t->prstatus, regset_size), &t->prstatus); + PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1728,7 +1728,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, if (regset->core_note_type && regset->get && (!regset->active || regset->active(t->task, regset))) { int ret; - size_t size = regset->n * regset->size; + size_t size = regset_size(t->task, regset); void *data = kmalloc(size, GFP_KERNEL); if (unlikely(!data)) return 0; @@ -1743,7 +1743,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, size, data); else { SET_PR_FPVALID(&t->prstatus, - 1, regset_size); + 1, regset0_size); fill_note(&t->notes[i], "CORE", NT_PRFPREG, size, data); } diff --git a/include/linux/regset.h b/include/linux/regset.h index 8e0c9febf495..494cedaafdf2 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -106,6 +106,28 @@ typedef int user_regset_writeback_fn(struct task_struct *target, const struct user_regset *regset, int immediate); +/** + * user_regset_get_size_fn - type of @get_size function in &struct user_regset + * @target: thread being examined + * @regset: regset being examined + * + * This call is optional; usually the pointer is %NULL. + * + * When provided, this function must return the current size of regset + * data, as observed by the @get function in &struct user_regset. The + * value returned must be a multiple of @size. The returned size is + * required to be valid only until the next time (if any) @regset is + * modified for @target. + * + * This function is intended for dynamically sized regsets. A regset + * that is statically sized does not need to implement it. + * + * This function should not be called directly: instead, callers should + * call regset_size() to determine the current size of a regset. + */ +typedef unsigned int user_regset_get_size_fn(struct task_struct *target, + const struct user_regset *regset); + /** * struct user_regset - accessible thread CPU state * @n: Number of slots (registers). @@ -117,19 +139,33 @@ typedef int user_regset_writeback_fn(struct task_struct *target, * @set: Function to store values. * @active: Function to report if regset is active, or %NULL. * @writeback: Function to write data back to user memory, or %NULL. + * @get_size: Function to return the regset's size, or %NULL. * * This data structure describes a machine resource we call a register set. * This is part of the state of an individual thread, not necessarily * actual CPU registers per se. A register set consists of a number of * similar slots, given by @n. Each slot is @size bytes, and aligned to - * @align bytes (which is at least @size). + * @align bytes (which is at least @size). For dynamically-sized + * regsets, @n must contain the maximum possible number of slots for the + * regset, and @get_size must point to a function that returns the + * current regset size. * - * These functions must be called only on the current thread or on a - * thread that is in %TASK_STOPPED or %TASK_TRACED state, that we are - * guaranteed will not be woken up and return to user mode, and that we - * have called wait_task_inactive() on. (The target thread always might - * wake up for SIGKILL while these functions are working, in which case - * that thread's user_regset state might be scrambled.) + * Callers that need to know only the current size of the regset and do + * not care about its internal structure should call regset_size() + * instead of inspecting @n or calling @get_size. + * + * For backward compatibility, the @get and @set methods must pad to, or + * accept, @n * @size bytes, even if the current regset size is smaller. + * The precise semantics of these operations depend on the regset being + * accessed. + * + * The functions to which &struct user_regset members point must be + * called only on the current thread or on a thread that is in + * %TASK_STOPPED or %TASK_TRACED state, that we are guaranteed will not + * be woken up and return to user mode, and that we have called + * wait_task_inactive() on. (The target thread always might wake up for + * SIGKILL while these functions are working, in which case that + * thread's user_regset state might be scrambled.) * * The @pos argument must be aligned according to @align; the @count * argument must be a multiple of @size. These functions are not @@ -156,6 +192,7 @@ struct user_regset { user_regset_set_fn *set; user_regset_active_fn *active; user_regset_writeback_fn *writeback; + user_regset_get_size_fn *get_size; unsigned int n; unsigned int size; unsigned int align; @@ -371,5 +408,21 @@ static inline int copy_regset_from_user(struct task_struct *target, return regset->set(target, regset, offset, size, NULL, data); } +/** + * regset_size - determine the current size of a regset + * @target: thread to be examined + * @regset: regset to be examined + * + * Note that the returned size is valid only until the next time + * (if any) @regset is modified for @target. + */ +static inline unsigned int regset_size(struct task_struct *target, + const struct user_regset *regset) +{ + if (!regset->get_size) + return regset->n * regset->size; + else + return regset->get_size(target, regset); +} #endif /* */ -- cgit v1.2.3-71-gd317