[PATCH v6] soc: qcom: add l2 cache perf events driver

Neil Leeder nleeder at codeaurora.org
Tue Oct 4 07:35:07 PDT 2016


On 9/21/2016 05:12 PM, Neil Leeder wrote:
> 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.
> 
> Signed-off-by: Neil Leeder <nleeder at codeaurora.org>
> ---
> 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/soc/qcom/Kconfig         |   9 +
>  drivers/soc/qcom/Makefile        |   1 +
>  drivers/soc/qcom/perf_event_l2.c | 948 +++++++++++++++++++++++++++++++++++++++
>  include/linux/cpuhotplug.h       |   1 +
>  4 files changed, 959 insertions(+)
>  create mode 100644 drivers/soc/qcom/perf_event_l2.c
> 
> diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
> index 461b387..3fa27a8 100644
> --- a/drivers/soc/qcom/Kconfig
> +++ b/drivers/soc/qcom/Kconfig
> @@ -10,6 +10,15 @@ config QCOM_GSBI
>            functions for connecting the underlying serial UART, SPI, and I2C
>            devices to the output pins.
>  
> +config QCOM_PERF_EVENTS_L2
> +	bool "Qualcomm Technologies L2-cache perf events"
> +	depends on ARCH_QCOM && ARM64 && HW_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 QCOM_PM
>  	bool "Qualcomm Power Management"
>  	depends on ARCH_QCOM && !ARM64
> diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
> index fdd664e..4c9df3b 100644
> --- a/drivers/soc/qcom/Makefile
> +++ b/drivers/soc/qcom/Makefile
> @@ -1,4 +1,5 @@
>  obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
> +obj-$(CONFIG_QCOM_PERF_EVENTS_L2)	+= perf_event_l2.o
>  obj-$(CONFIG_QCOM_PM)	+=	spm.o
>  obj-$(CONFIG_QCOM_SMD) +=	smd.o
>  obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
> diff --git a/drivers/soc/qcom/perf_event_l2.c b/drivers/soc/qcom/perf_event_l2.c
> new file mode 100644
> index 0000000..bbf47c9
> --- /dev/null
> +++ b/drivers/soc/qcom/perf_event_l2.c
> @@ -0,0 +1,948 @@
> +/* 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 <linux/acpi.h>
> +#include <linux/interrupt.h>
> +#include <linux/perf_event.h>
> +#include <linux/platform_device.h>
> +
> +#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 struct device_attribute l2_cache_pmu_cpumask_attr =
> +		__ATTR(cpumask, S_IRUGO, l2_cache_pmu_cpumask_show, NULL);
> +
> +static struct attribute *l2_cache_pmu_cpumask_attrs[] = {
> +	&l2_cache_pmu_cpumask_attr.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 45a4287..f342842 100644
> --- a/include/linux/cpuhotplug.h
> +++ b/include/linux/cpuhotplug.h
> @@ -113,6 +113,7 @@ 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,
> 

I believe this addresses all the issues raised previously - are there any other comments? Thanks. 

Neil

-- 
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.



More information about the linux-arm-kernel mailing list