From patchwork Fri Oct 28 20:50:13 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Neil Leeder X-Patchwork-Id: 9402659 X-Patchwork-Delegate: agross@codeaurora.org Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 934FA601C0 for ; Fri, 28 Oct 2016 20:50:37 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 8115A2A8A2 for ; Fri, 28 Oct 2016 20:50:37 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 74DB62A8BB; Fri, 28 Oct 2016 20:50:37 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.8 required=2.0 tests=BAYES_00,DKIM_SIGNED, RCVD_IN_DNSWL_HI,T_DKIM_INVALID autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id BFB692A8A2 for ; Fri, 28 Oct 2016 20:50:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754833AbcJ1Uue (ORCPT ); Fri, 28 Oct 2016 16:50:34 -0400 Received: from smtp.codeaurora.org ([198.145.29.96]:54292 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754806AbcJ1Uuc (ORCPT ); Fri, 28 Oct 2016 16:50:32 -0400 Received: by smtp.codeaurora.org (Postfix, from userid 1000) id 18B4060389; Fri, 28 Oct 2016 20:50:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=codeaurora.org; s=default; t=1477687832; bh=6DGtWAoczNcJ2e7JdOSncBEkLvfgSfe3PrAQ+OzlMBQ=; h=From:To:Cc:Subject:Date:From; b=QH3yRMgKiMZ3xG+d/Xng/AdLfxKC3mdTULe9Zt9n+jdYrvHDfhpOnkeaLl1kBhyNC iNJdIocq2fIXbFoSSgSmBVPXbUQgY5/KxVXzqdElhtWZN012RIoLz2pK1UnuBUM4uu 4LgKMrQWx+Po/4c4ohx6nckXacWiwt/gkp9mRDUM= Received: from codeaurora.org (global_nat1_iad_fw.qualcomm.com [129.46.232.65]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: nleeder@smtp.codeaurora.org) by smtp.codeaurora.org (Postfix) with ESMTPSA id AABD560389; Fri, 28 Oct 2016 20:50:27 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=codeaurora.org; s=default; t=1477687829; bh=6DGtWAoczNcJ2e7JdOSncBEkLvfgSfe3PrAQ+OzlMBQ=; h=From:To:Cc:Subject:Date:From; b=CJnduAI9C9dyu7vKRNGOc/qs5dvxO/2P40Udn868vUb3/oCR4CbGQLiAdpa6nLVI3 AvoXiRMyrrchLdQt17G7/WaiIUkRPQ3Ir0xACp8lJAp7QbOjAwIDoOwyTQVk/L7SpI WrJSmf1MthX85olFQtpOudN1JX4tthbwDDYAF6iE= DMARC-Filter: OpenDMARC Filter v1.3.1 smtp.codeaurora.org AABD560389 Authentication-Results: pdx-caf-mail.web.codeaurora.org; dmarc=none header.from=codeaurora.org Authentication-Results: pdx-caf-mail.web.codeaurora.org; spf=pass smtp.mailfrom=nleeder@codeaurora.org From: Neil Leeder To: Catalin Marinas , Will Deacon , Mark Rutland , Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo Cc: linux-arm-msm@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Mark Langsdorf , Mark Salter , Jon Masters , Timur Tabi , cov@codeaurora.org, nleeder@codeaurora.org Subject: [PATCH v7] soc: qcom: add l2 cache perf events driver Date: Fri, 28 Oct 2016 16:50:13 -0400 Message-Id: <1477687813-11412-1-git-send-email-nleeder@codeaurora.org> X-Mailer: git-send-email 1.9.1 Sender: linux-arm-msm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Adds perf events support for L2 cache PMU. The L2 cache PMU driver is named 'l2cache_0' and can be used with perf events to profile L2 events such as cache hits and misses on Qualcomm Technologies processors. Signed-off-by: Neil Leeder --- v7: Move to drivers/perf Rebased on 4.9-rc1 Successfully ran perf fuzzer against driver v6: restore accidentally dropped Kconfig dependencies v5: Fold the header and l2-accessors into .c file Use multi-instance framework for hotplug Change terminology from slice to cluster for clarity Remove unnecessary rmw sequence for enable registers Use prev_count in hwc rather than in slice Enforce all events in same group on same CPU Add comments, rename variables for clarity v4: Replace notifier with hotplug statemachine Allocate PMU struct dynamically v3: Remove exports from l2-accessors Change l2-accessors Kconfig to make it not user-selectable Reorder and remove unnecessary includes v2: Add the l2-accessors patch to this patchset, previously posted separately. Remove sampling and per-task functionality for this uncore PMU. Use cpumask to replace code which filtered events to one cpu per slice. Replace manual event filtering with filter_match callback. Use a separate used_mask for event groups. Add hotplug notifier for CPU and irq migration. Remove extraneous synchronisation instructions. Other miscellaneous cleanup. drivers/perf/Kconfig | 9 + drivers/perf/Makefile | 1 + drivers/perf/qcom_l2_pmu.c | 947 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 4 files changed, 958 insertions(+) create mode 100644 drivers/perf/qcom_l2_pmu.c diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 4d5c5f9..9365190 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -12,6 +12,15 @@ config ARM_PMU Say y if you want to use CPU performance monitors on ARM-based systems. +config QCOM_L2_PMU + bool "Qualcomm Technologies L2-cache PMU" + depends on ARCH_QCOM && ARM64 && PERF_EVENTS && ACPI + help + Provides support for the L2 cache performance monitor unit (PMU) + in Qualcomm Technologies processors. + Adds the L2 cache PMU into the perf events subsystem for + monitoring L2 cache events. + config XGENE_PMU depends on PERF_EVENTS && ARCH_XGENE bool "APM X-Gene SoC PMU" diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile index b116e98..ef24833 100644 --- a/drivers/perf/Makefile +++ b/drivers/perf/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_ARM_PMU) += arm_pmu.o +obj-$(CONFIG_QCOM_L2_PMU) += qcom_l2_pmu.o obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c new file mode 100644 index 0000000..c7b159f --- /dev/null +++ b/drivers/perf/qcom_l2_pmu.c @@ -0,0 +1,947 @@ +/* Copyright (c) 2015,2016 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include +#include +#include +#include + +#define MAX_L2_CTRS 9 + +#define L2PMCR_NUM_EV_SHIFT 11 +#define L2PMCR_NUM_EV_MASK 0x1F + +#define L2PMCR 0x400 +#define L2PMCNTENCLR 0x403 +#define L2PMCNTENSET 0x404 +#define L2PMINTENCLR 0x405 +#define L2PMINTENSET 0x406 +#define L2PMOVSCLR 0x407 +#define L2PMOVSSET 0x408 +#define L2PMCCNTCR 0x409 +#define L2PMCCNTR 0x40A +#define L2PMCCNTSR 0x40C +#define L2PMRESR 0x410 +#define IA_L2PMXEVCNTCR_BASE 0x420 +#define IA_L2PMXEVCNTR_BASE 0x421 +#define IA_L2PMXEVFILTER_BASE 0x423 +#define IA_L2PMXEVTYPER_BASE 0x424 + +#define IA_L2_REG_OFFSET 0x10 + +#define L2PMXEVFILTER_SUFILTER_ALL 0x000E0000 +#define L2PMXEVFILTER_ORGFILTER_IDINDEP 0x00000004 +#define L2PMXEVFILTER_ORGFILTER_ALL 0x00000003 + +#define L2PM_CC_ENABLE 0x80000000 + +#define L2EVTYPER_REG_SHIFT 3 + +#define L2PMRESR_GROUP_BITS 8 +#define L2PMRESR_GROUP_MASK GENMASK(7, 0) + +#define L2CYCLE_CTR_BIT 31 +#define L2CYCLE_CTR_RAW_CODE 0xFE + +#define L2PMCR_RESET_ALL 0x6 +#define L2PMCR_COUNTERS_ENABLE 0x1 +#define L2PMCR_COUNTERS_DISABLE 0x0 + +#define L2PMRESR_EN ((u64)1 << 63) + +#define L2_EVT_MASK 0x00000FFF +#define L2_EVT_CODE_MASK 0x00000FF0 +#define L2_EVT_GRP_MASK 0x0000000F +#define L2_EVT_CODE_SHIFT 4 +#define L2_EVT_GRP_SHIFT 0 + +#define L2_EVT_CODE(event) (((event) & L2_EVT_CODE_MASK) >> L2_EVT_CODE_SHIFT) +#define L2_EVT_GROUP(event) (((event) & L2_EVT_GRP_MASK) >> L2_EVT_GRP_SHIFT) + +#define L2_EVT_GROUP_MAX 7 + +#define L2_MAX_PERIOD U32_MAX +#define L2_CNT_PERIOD (U32_MAX - GENMASK(26, 0)) + +#define L2CPUSRSELR_EL1 S3_3_c15_c0_6 +#define L2CPUSRDR_EL1 S3_3_c15_c0_7 + +static DEFINE_RAW_SPINLOCK(l2_access_lock); + +/** + * set_l2_indirect_reg: write value to an L2 register + * @reg: Address of L2 register. + * @value: Value to be written to register. + * + * Use architecturally required barriers for ordering between system register + * accesses + */ +static void set_l2_indirect_reg(u64 reg, u64 val) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2_access_lock, flags); + write_sysreg(reg, L2CPUSRSELR_EL1); + isb(); + write_sysreg(val, L2CPUSRDR_EL1); + isb(); + raw_spin_unlock_irqrestore(&l2_access_lock, flags); +} + +/** + * get_l2_indirect_reg: read an L2 register value + * @reg: Address of L2 register. + * + * Use architecturally required barriers for ordering between system register + * accesses + */ +static u64 get_l2_indirect_reg(u64 reg) +{ + u64 val; + unsigned long flags; + + raw_spin_lock_irqsave(&l2_access_lock, flags); + write_sysreg(reg, L2CPUSRSELR_EL1); + isb(); + val = read_sysreg(L2CPUSRDR_EL1); + raw_spin_unlock_irqrestore(&l2_access_lock, flags); + + return val; +} + +/* + * Aggregate PMU. Implements the core pmu functions and manages + * the hardware PMUs. + */ +struct l2cache_pmu { + struct hlist_node node; + u32 num_pmus; + struct pmu pmu; + int num_counters; + cpumask_t cpumask; + struct platform_device *pdev; +}; + +/* + * The cache is made up of one or more clusters, each cluster has its own PMU. + * Each cluster is associated with one or more CPUs. + * This structure represents one of the hardware PMUs. + * + * Events can be envisioned as a 2-dimensional array. Each column represents + * a group of events. There are 8 groups. Only one entry from each + * group can be in use at a time. When an event is assigned a counter + * by *_event_add(), the counter index is assigned to group_to_counter[group]. + * This allows *filter_match() to detect and reject conflicting events in + * the same group. + * Events are specified as 0xCCG, where CC is 2 hex digits specifying + * the code (array row) and G specifies the group (column). + * + * In addition there is a cycle counter event specified by L2CYCLE_CTR_RAW_CODE + * which is outside the above scheme. + */ +struct hml2_pmu { + struct perf_event *events[MAX_L2_CTRS]; + struct l2cache_pmu *l2cache_pmu; + DECLARE_BITMAP(used_counters, MAX_L2_CTRS); + DECLARE_BITMAP(used_groups, L2_EVT_GROUP_MAX + 1); + int group_to_counter[L2_EVT_GROUP_MAX + 1]; + int irq; + /* The CPU that is used for collecting events on this cluster */ + int on_cpu; + /* All the CPUs associated with this cluster */ + cpumask_t cluster_cpus; + spinlock_t pmu_lock; +}; + +#define to_l2cache_pmu(p) (container_of(p, struct l2cache_pmu, pmu)) + +static DEFINE_PER_CPU(struct hml2_pmu *, pmu_cluster); +static u32 l2_cycle_ctr_idx; +static u32 l2_counter_present_mask; + +static inline u32 idx_to_reg_bit(u32 idx) +{ + if (idx == l2_cycle_ctr_idx) + return BIT(L2CYCLE_CTR_BIT); + + return BIT(idx); +} + +static inline struct hml2_pmu *get_hml2_pmu(int cpu) +{ + return per_cpu(pmu_cluster, cpu); +} + +static void hml2_pmu__reset_on_cluster(void *x) +{ + /* Reset all ctrs */ + set_l2_indirect_reg(L2PMCR, L2PMCR_RESET_ALL); + set_l2_indirect_reg(L2PMCNTENCLR, l2_counter_present_mask); + set_l2_indirect_reg(L2PMINTENCLR, l2_counter_present_mask); + set_l2_indirect_reg(L2PMOVSCLR, l2_counter_present_mask); +} + +static inline void hml2_pmu__reset(struct hml2_pmu *cluster) +{ + cpumask_t *mask = &cluster->cluster_cpus; + + if (smp_call_function_any(mask, hml2_pmu__reset_on_cluster, NULL, 1)) + dev_err(&cluster->l2cache_pmu->pdev->dev, + "Failed to reset on cluster with cpu %d\n", + cpumask_first(&cluster->cluster_cpus)); +} + +static inline void hml2_pmu__enable(void) +{ + set_l2_indirect_reg(L2PMCR, L2PMCR_COUNTERS_ENABLE); +} + +static inline void hml2_pmu__disable(void) +{ + set_l2_indirect_reg(L2PMCR, L2PMCR_COUNTERS_DISABLE); +} + +static inline void hml2_pmu__counter_set_value(u32 idx, u64 value) +{ + u32 counter_reg; + + if (idx == l2_cycle_ctr_idx) { + set_l2_indirect_reg(L2PMCCNTR, value); + } else { + counter_reg = (idx * IA_L2_REG_OFFSET) + IA_L2PMXEVCNTR_BASE; + set_l2_indirect_reg(counter_reg, value & GENMASK(31, 0)); + } +} + +static inline u64 hml2_pmu__counter_get_value(u32 idx) +{ + u64 value; + u32 counter_reg; + + if (idx == l2_cycle_ctr_idx) { + value = get_l2_indirect_reg(L2PMCCNTR); + } else { + counter_reg = (idx * IA_L2_REG_OFFSET) + IA_L2PMXEVCNTR_BASE; + value = get_l2_indirect_reg(counter_reg); + } + + return value; +} + +static inline void hml2_pmu__counter_enable(u32 idx) +{ + set_l2_indirect_reg(L2PMCNTENSET, idx_to_reg_bit(idx)); +} + +static inline void hml2_pmu__counter_disable(u32 idx) +{ + set_l2_indirect_reg(L2PMCNTENCLR, idx_to_reg_bit(idx)); +} + +static inline void hml2_pmu__counter_enable_interrupt(u32 idx) +{ + set_l2_indirect_reg(L2PMINTENSET, idx_to_reg_bit(idx)); +} + +static inline void hml2_pmu__counter_disable_interrupt(u32 idx) +{ + set_l2_indirect_reg(L2PMINTENCLR, idx_to_reg_bit(idx)); +} + +static inline void hml2_pmu__set_evccntcr(u32 val) +{ + set_l2_indirect_reg(L2PMCCNTCR, val); +} + +static inline void hml2_pmu__set_evcntcr(u32 ctr, u32 val) +{ + u32 evtcr_reg = (ctr * IA_L2_REG_OFFSET) + IA_L2PMXEVCNTCR_BASE; + + set_l2_indirect_reg(evtcr_reg, val); +} + +static inline void hml2_pmu__set_evtyper(u32 ctr, u32 val) +{ + u32 evtype_reg = (ctr * IA_L2_REG_OFFSET) + IA_L2PMXEVTYPER_BASE; + + set_l2_indirect_reg(evtype_reg, val); +} + +static void hml2_pmu__set_resr(struct hml2_pmu *cluster, + u32 event_group, u32 event_cc) +{ + u64 field; + u64 resr_val; + u32 shift; + unsigned long flags; + + shift = L2PMRESR_GROUP_BITS * event_group; + field = ((u64)(event_cc & L2PMRESR_GROUP_MASK) << shift) | L2PMRESR_EN; + + spin_lock_irqsave(&cluster->pmu_lock, flags); + + resr_val = get_l2_indirect_reg(L2PMRESR); + resr_val &= ~(L2PMRESR_GROUP_MASK << shift); + resr_val |= field; + set_l2_indirect_reg(L2PMRESR, resr_val); + + spin_unlock_irqrestore(&cluster->pmu_lock, flags); +} + +/* + * Hardware allows filtering of events based on the originating + * CPU. Turn this off by setting filter bits to allow events from + * all CPUS, subunits and ID independent events in this cluster. + */ +static inline void hml2_pmu__set_evfilter_sys_mode(u32 ctr) +{ + u32 reg = (ctr * IA_L2_REG_OFFSET) + IA_L2PMXEVFILTER_BASE; + u32 val = L2PMXEVFILTER_SUFILTER_ALL | + L2PMXEVFILTER_ORGFILTER_IDINDEP | + L2PMXEVFILTER_ORGFILTER_ALL; + + set_l2_indirect_reg(reg, val); +} + +static inline u32 hml2_pmu__getreset_ovsr(void) +{ + u32 result = get_l2_indirect_reg(L2PMOVSSET); + + set_l2_indirect_reg(L2PMOVSCLR, result); + return result; +} + +static inline bool hml2_pmu__has_overflowed(u32 ovsr) +{ + return !!(ovsr & l2_counter_present_mask); +} + +static inline bool hml2_pmu__counter_has_overflowed(u32 ovsr, u32 idx) +{ + return !!(ovsr & idx_to_reg_bit(idx)); +} + +static void l2_cache__event_update_from_cluster(struct perf_event *event, + struct hml2_pmu *cluster) +{ + struct hw_perf_event *hwc = &event->hw; + u64 delta64, prev, now; + u32 delta; + u32 idx = hwc->idx; + + do { + prev = local64_read(&hwc->prev_count); + now = hml2_pmu__counter_get_value(idx); + } while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev); + + if (idx == l2_cycle_ctr_idx) { + /* + * The cycle counter is 64-bit so needs separate handling + * of 64-bit delta. + */ + delta64 = now - prev; + local64_add(delta64, &event->count); + } else { + /* + * 32-bit counters need the unsigned 32-bit math to handle + * overflow and now < prev + */ + delta = now - prev; + local64_add(delta, &event->count); + } +} + +static void l2_cache__cluster_set_period(struct hml2_pmu *cluster, + struct hw_perf_event *hwc) +{ + u64 base = L2_MAX_PERIOD - (L2_CNT_PERIOD - 1); + u32 idx = hwc->idx; + u64 prev = local64_read(&hwc->prev_count); + u64 value; + + /* + * Limit the maximum period to prevent the counter value + * from overtaking the one we are about to program. + * Use a starting value which is high enough that after + * an overflow, interrupt latency will not cause the count + * to reach the base value. If the previous value + * is below the base, increase it to be above the base + * and update prev_count accordingly. Otherwise if + * the previous value is already above the base + * nothing needs to be done to prev_count. + */ + if (prev < base) { + value = base + prev; + local64_set(&hwc->prev_count, value); + } else { + value = prev; + } + + hml2_pmu__counter_set_value(idx, value); +} + +static int l2_cache__get_event_idx(struct hml2_pmu *cluster, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx; + + if (hwc->config_base == L2CYCLE_CTR_RAW_CODE) { + if (test_and_set_bit(l2_cycle_ctr_idx, cluster->used_counters)) + return -EAGAIN; + + return l2_cycle_ctr_idx; + } + + for (idx = 0; idx < cluster->l2cache_pmu->num_counters - 1; idx++) { + if (!test_and_set_bit(idx, cluster->used_counters)) { + set_bit(L2_EVT_GROUP(hwc->config_base), + cluster->used_groups); + return idx; + } + } + + /* The counters are all in use. */ + return -EAGAIN; +} + +static void l2_cache__clear_event_idx(struct hml2_pmu *cluster, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + clear_bit(idx, cluster->used_counters); + if (hwc->config_base != L2CYCLE_CTR_RAW_CODE) + clear_bit(L2_EVT_GROUP(hwc->config_base), cluster->used_groups); +} + +static irqreturn_t l2_cache__handle_irq(int irq_num, void *data) +{ + struct hml2_pmu *cluster = data; + int num_counters = cluster->l2cache_pmu->num_counters; + u32 ovsr; + int idx; + + ovsr = hml2_pmu__getreset_ovsr(); + if (!hml2_pmu__has_overflowed(ovsr)) + return IRQ_NONE; + + for_each_set_bit(idx, cluster->used_counters, num_counters) { + struct perf_event *event = cluster->events[idx]; + struct hw_perf_event *hwc; + + if (!hml2_pmu__counter_has_overflowed(ovsr, idx)) + continue; + + l2_cache__event_update_from_cluster(event, cluster); + hwc = &event->hw; + + l2_cache__cluster_set_period(cluster, hwc); + } + + return IRQ_HANDLED; +} + +/* + * Implementation of abstract pmu functionality required by + * the core perf events code. + */ + +static void l2_cache__pmu_enable(struct pmu *pmu) +{ + /* + * Although there is only one PMU (per socket) controlling multiple + * physical PMUs (per cluster), because we do not support per-task mode + * each event is associated with a CPU. Each event has pmu_enable + * called on its CPU, so here it is only necessary to enable the + * counters for the current CPU. + */ + + hml2_pmu__enable(); +} + +static void l2_cache__pmu_disable(struct pmu *pmu) +{ + hml2_pmu__disable(); +} + +static int l2_cache__event_init(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hml2_pmu *cluster; + struct perf_event *sibling; + struct l2cache_pmu *l2cache_pmu; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + l2cache_pmu = to_l2cache_pmu(event->pmu); + + if (hwc->sample_period) { + dev_warn(&l2cache_pmu->pdev->dev, "Sampling not supported\n"); + return -EOPNOTSUPP; + } + + if (event->cpu < 0) { + dev_warn(&l2cache_pmu->pdev->dev, "Per-task mode not supported\n"); + return -EOPNOTSUPP; + } + + /* We cannot filter accurately so we just don't allow it. */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_hv || event->attr.exclude_idle) { + dev_warn(&l2cache_pmu->pdev->dev, "Can't exclude execution levels\n"); + return -EOPNOTSUPP; + } + + if (((L2_EVT_GROUP(event->attr.config) > L2_EVT_GROUP_MAX) || + ((event->attr.config & ~L2_EVT_MASK) != 0)) && + (event->attr.config != L2CYCLE_CTR_RAW_CODE)) { + dev_warn(&l2cache_pmu->pdev->dev, "Invalid config %llx\n", + event->attr.config); + return -EINVAL; + } + + /* Don't allow groups with mixed PMUs, except for s/w events */ + if (event->group_leader->pmu != event->pmu && + !is_software_event(event->group_leader)) { + dev_warn(&l2cache_pmu->pdev->dev, + "Can't create mixed PMU group\n"); + return -EINVAL; + } + + list_for_each_entry(sibling, &event->group_leader->sibling_list, + group_entry) + if (sibling->pmu != event->pmu && + !is_software_event(sibling)) { + dev_warn(&l2cache_pmu->pdev->dev, + "Can't create mixed PMU group\n"); + return -EINVAL; + } + + /* Ensure all events in a group are on the same cpu */ + cluster = get_hml2_pmu(event->cpu); + if ((event->group_leader != event) && + (cluster->on_cpu != event->group_leader->cpu)) { + dev_warn(&l2cache_pmu->pdev->dev, + "Can't create group on CPUs %d and %d", + event->cpu, event->group_leader->cpu); + return -EINVAL; + } + + hwc->idx = -1; + hwc->config_base = event->attr.config; + + /* + * Ensure all events are on the same cpu so all events are in the + * same cpu context, to avoid races on pmu_enable etc. + */ + event->cpu = cluster->on_cpu; + + return 0; +} + +static void l2_cache__event_start(struct perf_event *event, int flags) +{ + struct hml2_pmu *cluster; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + u32 config; + u32 event_cc, event_group; + + hwc->state = 0; + + cluster = get_hml2_pmu(event->cpu); + l2_cache__cluster_set_period(cluster, hwc); + + if (hwc->config_base == L2CYCLE_CTR_RAW_CODE) { + hml2_pmu__set_evccntcr(0x0); + } else { + config = hwc->config_base; + event_cc = L2_EVT_CODE(config); + event_group = L2_EVT_GROUP(config); + + hml2_pmu__set_evcntcr(idx, 0x0); + hml2_pmu__set_evtyper(idx, event_group); + hml2_pmu__set_resr(cluster, event_group, event_cc); + hml2_pmu__set_evfilter_sys_mode(idx); + } + + hml2_pmu__counter_enable_interrupt(idx); + hml2_pmu__counter_enable(idx); +} + +static void l2_cache__event_stop(struct perf_event *event, int flags) +{ + struct hml2_pmu *cluster; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (!(hwc->state & PERF_HES_STOPPED)) { + cluster = get_hml2_pmu(event->cpu); + hml2_pmu__counter_disable_interrupt(idx); + hml2_pmu__counter_disable(idx); + + if (flags & PERF_EF_UPDATE) + l2_cache__event_update_from_cluster(event, cluster); + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + } +} + +static int l2_cache__event_add(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + int idx; + int err = 0; + struct hml2_pmu *cluster; + + cluster = get_hml2_pmu(event->cpu); + + idx = l2_cache__get_event_idx(cluster, event); + if (idx < 0) { + err = idx; + return err; + } + + hwc->idx = idx; + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + cluster->events[idx] = event; + cluster->group_to_counter[L2_EVT_GROUP(hwc->config_base)] = idx; + local64_set(&hwc->prev_count, 0ULL); + + if (flags & PERF_EF_START) + l2_cache__event_start(event, flags); + + /* Propagate changes to the userspace mapping. */ + perf_event_update_userpage(event); + + return err; +} + +static void l2_cache__event_del(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct hml2_pmu *cluster; + int idx = hwc->idx; + + cluster = get_hml2_pmu(event->cpu); + l2_cache__event_stop(event, flags | PERF_EF_UPDATE); + cluster->events[idx] = NULL; + l2_cache__clear_event_idx(cluster, event); + + perf_event_update_userpage(event); +} + +static void l2_cache__event_read(struct perf_event *event) +{ + l2_cache__event_update_from_cluster(event, get_hml2_pmu(event->cpu)); +} + +static int l2_cache_filter_match(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hml2_pmu *cluster = get_hml2_pmu(event->cpu); + unsigned int group = L2_EVT_GROUP(hwc->config_base); + + /* check for column exclusion: group already in use by another event */ + if (test_bit(group, cluster->used_groups) && + cluster->events[cluster->group_to_counter[group]] != event) + return 0; + + return 1; +} + +static ssize_t l2_cache_pmu_cpumask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct l2cache_pmu *l2cache_pmu = to_l2cache_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, &l2cache_pmu->cpumask); +} + +static DEVICE_ATTR(cpumask, S_IRUGO, l2_cache_pmu_cpumask_show, NULL); + +static struct attribute *l2_cache_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group l2_cache_pmu_cpumask_group = { + .attrs = l2_cache_pmu_cpumask_attrs, +}; + +/* CCG format for perf RAW codes. */ +PMU_FORMAT_ATTR(l2_code, "config:4-11"); +PMU_FORMAT_ATTR(l2_group, "config:0-3"); +static struct attribute *l2_cache_pmu_formats[] = { + &format_attr_l2_code.attr, + &format_attr_l2_group.attr, + NULL, +}; + +static struct attribute_group l2_cache_pmu_format_group = { + .name = "format", + .attrs = l2_cache_pmu_formats, +}; + +static const struct attribute_group *l2_cache_pmu_attr_grps[] = { + &l2_cache_pmu_format_group, + &l2_cache_pmu_cpumask_group, + NULL, +}; + +/* + * Generic device handlers + */ + +static const struct acpi_device_id l2_cache_pmu_acpi_match[] = { + { "QCOM8130", }, + { } +}; + +static int get_num_counters(void) +{ + int val; + + val = get_l2_indirect_reg(L2PMCR); + + /* + * Read number of counters from L2PMCR and add 1 + * for the cycle counter. + */ + return ((val >> L2PMCR_NUM_EV_SHIFT) & L2PMCR_NUM_EV_MASK) + 1; +} + +static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hml2_pmu *cluster; + cpumask_t cluster_online_cpus; + struct l2cache_pmu *l2cache_pmu; + + l2cache_pmu = hlist_entry_safe(node, struct l2cache_pmu, node); + cluster = get_hml2_pmu(cpu); + cpumask_and(&cluster_online_cpus, &cluster->cluster_cpus, + cpu_online_mask); + + if (cpumask_weight(&cluster_online_cpus) == 1) { + /* all CPUs on this cluster were down, use this one */ + cluster->on_cpu = cpu; + cpumask_set_cpu(cpu, &l2cache_pmu->cpumask); + WARN_ON(irq_set_affinity(cluster->irq, cpumask_of(cpu))); + } + + return 0; +} + +static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hml2_pmu *cluster; + struct l2cache_pmu *l2cache_pmu; + cpumask_t cluster_online_cpus; + unsigned int target; + + l2cache_pmu = hlist_entry_safe(node, struct l2cache_pmu, node); + + if (!cpumask_test_and_clear_cpu(cpu, &l2cache_pmu->cpumask)) + return 0; + cluster = get_hml2_pmu(cpu); + cpumask_and(&cluster_online_cpus, &cluster->cluster_cpus, + cpu_online_mask); + + /* Any other CPU for this cluster which is still online */ + target = cpumask_any_but(&cluster_online_cpus, cpu); + if (target >= nr_cpu_ids) + return 0; + + perf_pmu_migrate_context(&l2cache_pmu->pmu, cpu, target); + cluster->on_cpu = target; + cpumask_set_cpu(target, &l2cache_pmu->cpumask); + WARN_ON(irq_set_affinity(cluster->irq, cpumask_of(target))); + + return 0; +} + +static int l2_cache_pmu_probe_cluster(struct device *dev, void *data) +{ + struct platform_device *pdev = to_platform_device(dev->parent); + struct platform_device *sdev = to_platform_device(dev); + struct l2cache_pmu *l2cache_pmu = data; + struct hml2_pmu *cluster; + struct acpi_device *device; + unsigned long fw_cluster_id; + int cpu; + int err; + int irq; + + if (acpi_bus_get_device(ACPI_HANDLE(dev), &device)) + return -ENODEV; + + if (kstrtol(device->pnp.unique_id, 10, &fw_cluster_id) < 0) { + dev_err(&pdev->dev, "unable to read ACPI uid\n"); + return -ENODEV; + } + + irq = platform_get_irq(sdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, + "Failed to get valid irq for cluster %ld\n", + fw_cluster_id); + return irq; + } + + cluster = devm_kzalloc(&pdev->dev, sizeof(*cluster), GFP_KERNEL); + if (!cluster) + return -ENOMEM; + + cluster->l2cache_pmu = l2cache_pmu; + for_each_present_cpu(cpu) { + if (topology_physical_package_id(cpu) == fw_cluster_id) { + cpumask_set_cpu(cpu, &cluster->cluster_cpus); + per_cpu(pmu_cluster, cpu) = cluster; + } + } + cluster->irq = irq; + + if (cpumask_empty(&cluster->cluster_cpus)) { + dev_err(&pdev->dev, "No CPUs found for L2 cache instance %ld\n", + fw_cluster_id); + return -ENODEV; + } + + /* Pick one CPU to be the preferred one to use in the cluster */ + cluster->on_cpu = cpumask_first(&cluster->cluster_cpus); + + if (irq_set_affinity(irq, cpumask_of(cluster->on_cpu))) { + dev_err(&pdev->dev, + "Unable to set irq affinity (irq=%d, cpu=%d)\n", + irq, cluster->on_cpu); + return -ENODEV; + } + + err = devm_request_irq(&pdev->dev, irq, l2_cache__handle_irq, + IRQF_NOBALANCING, "l2-cache-pmu", cluster); + if (err) { + dev_err(&pdev->dev, + "Unable to request IRQ%d for L2 PMU counters\n", irq); + return err; + } + + dev_info(&pdev->dev, + "Registered L2 cache PMU instance %ld with %d CPUs\n", + fw_cluster_id, cpumask_weight(&cluster->cluster_cpus)); + + cluster->pmu_lock = __SPIN_LOCK_UNLOCKED(cluster->pmu_lock); + cpumask_set_cpu(cluster->on_cpu, &l2cache_pmu->cpumask); + + hml2_pmu__reset(cluster); + l2cache_pmu->num_pmus++; + + return 0; +} + +static int l2_cache_pmu_probe(struct platform_device *pdev) +{ + int err; + struct l2cache_pmu *l2cache_pmu; + + l2cache_pmu = + devm_kzalloc(&pdev->dev, sizeof(*l2cache_pmu), GFP_KERNEL); + if (!l2cache_pmu) + return -ENOMEM; + + platform_set_drvdata(pdev, l2cache_pmu); + l2cache_pmu->pmu = (struct pmu) { + /* suffix is instance id for future use with multiple sockets */ + .name = "l2cache_0", + .task_ctx_nr = perf_invalid_context, + .pmu_enable = l2_cache__pmu_enable, + .pmu_disable = l2_cache__pmu_disable, + .event_init = l2_cache__event_init, + .add = l2_cache__event_add, + .del = l2_cache__event_del, + .start = l2_cache__event_start, + .stop = l2_cache__event_stop, + .read = l2_cache__event_read, + .attr_groups = l2_cache_pmu_attr_grps, + .filter_match = l2_cache_filter_match, + }; + + l2cache_pmu->num_counters = get_num_counters(); + l2cache_pmu->pdev = pdev; + l2_cycle_ctr_idx = l2cache_pmu->num_counters - 1; + l2_counter_present_mask = GENMASK(l2cache_pmu->num_counters - 2, 0) | + L2PM_CC_ENABLE; + + cpumask_clear(&l2cache_pmu->cpumask); + + /* Read cluster info and initialize each cluster */ + err = device_for_each_child(&pdev->dev, l2cache_pmu, + l2_cache_pmu_probe_cluster); + if (err < 0) + return err; + + if (l2cache_pmu->num_pmus == 0) { + dev_err(&pdev->dev, "No hardware L2 cache PMUs found\n"); + return -ENODEV; + } + + err = perf_pmu_register(&l2cache_pmu->pmu, l2cache_pmu->pmu.name, -1); + if (err < 0) { + dev_err(&pdev->dev, "Error %d registering L2 cache PMU\n", err); + return err; + } + + dev_info(&pdev->dev, "Registered L2 cache PMU using %d HW PMUs\n", + l2cache_pmu->num_pmus); + + err = cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + &l2cache_pmu->node); + + return err; +} + +static int l2_cache_pmu_remove(struct platform_device *pdev) +{ + struct l2cache_pmu *l2cache_pmu = + to_l2cache_pmu(platform_get_drvdata(pdev)); + + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + &l2cache_pmu->node); + perf_pmu_unregister(&l2cache_pmu->pmu); + return 0; +} + +static struct platform_driver l2_cache_pmu_driver = { + .driver = { + .name = "qcom-l2cache-pmu", + .owner = THIS_MODULE, + .acpi_match_table = ACPI_PTR(l2_cache_pmu_acpi_match), + }, + .probe = l2_cache_pmu_probe, + .remove = l2_cache_pmu_remove, +}; + +static int __init register_l2_cache_pmu_driver(void) +{ + int err; + + err = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + "AP_PERF_ARM_QCOM_L2_ONLINE", + l2cache_pmu_online_cpu, + l2cache_pmu_offline_cpu); + if (err) + return err; + + return platform_driver_register(&l2_cache_pmu_driver); +} +device_initcall(register_l2_cache_pmu_driver); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 9b207a8..fbe33d2 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -117,6 +117,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, + CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_NOTIFY_ONLINE,